diff options
1606 files changed, 30369 insertions, 14049 deletions
diff --git a/Documentation/ABI/testing/sysfs-driver-samsung-laptop b/Documentation/ABI/testing/sysfs-driver-samsung-laptop index 63c1ad0212fc..34d3a3359cf4 100644 --- a/Documentation/ABI/testing/sysfs-driver-samsung-laptop +++ b/Documentation/ABI/testing/sysfs-driver-samsung-laptop @@ -3,7 +3,7 @@ Date: January 1, 2010 KernelVersion: 2.6.33 Contact: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Description: Some Samsung laptops have different "performance levels" - that are can be modified by a function key, and by this + that can be modified by a function key, and by this sysfs file. These values don't always make a whole lot of sense, but some users like to modify them to keep their fans quiet at all costs. Reading from this file diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 39ac9d4fad7f..1d1d53f85ddd 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -931,9 +931,12 @@ earlycon= [KNL] Output early console device and options. - When used with no options, the early console is - determined by the stdout-path property in device - tree's chosen node. + [ARM64] The early console is determined by the + stdout-path property in device tree's chosen node, + or determined by the ACPI SPCR table. + + [X86] When used with no options the early console is + determined by the ACPI SPCR table. cdns,<addr>[,options] Start an early, polled-mode console on a Cadence diff --git a/Documentation/admin-guide/thunderbolt.rst b/Documentation/admin-guide/thunderbolt.rst index 9b55952039a6..9948ec36a204 100644 --- a/Documentation/admin-guide/thunderbolt.rst +++ b/Documentation/admin-guide/thunderbolt.rst @@ -3,13 +3,13 @@ ============= The interface presented here is not meant for end users. Instead there should be a userspace tool that handles all the low-level details, keeps -database of the authorized devices and prompts user for new connections. +a database of the authorized devices and prompts users for new connections. More details about the sysfs interface for Thunderbolt devices can be found in ``Documentation/ABI/testing/sysfs-bus-thunderbolt``. Those users who just want to connect any device without any sort of -manual work, can add following line to +manual work can add following line to ``/etc/udev/rules.d/99-local.rules``:: ACTION=="add", SUBSYSTEM=="thunderbolt", ATTR{authorized}=="0", ATTR{authorized}="1" @@ -20,7 +20,7 @@ vulnerable to DMA attacks. Security levels and how to use them ----------------------------------- -Starting from Intel Falcon Ridge Thunderbolt controller there are 4 +Starting with Intel Falcon Ridge Thunderbolt controller there are 4 security levels available. The reason for these is the fact that the connected devices can be DMA masters and thus read contents of the host memory without CPU and OS knowing about it. There are ways to prevent @@ -37,14 +37,14 @@ The security levels are as follows: user User is asked whether the device is allowed to be connected. Based on the device identification information available through - ``/sys/bus/thunderbolt/devices``. user then can do the decision. + ``/sys/bus/thunderbolt/devices``, the user then can make the decision. In BIOS settings this is typically called *Unique ID*. secure User is asked whether the device is allowed to be connected. In addition to UUID the device (if it supports secure connect) is sent a challenge that should match the expected one based on a random key - written to ``key`` sysfs attribute. In BIOS settings this is + written to the ``key`` sysfs attribute. In BIOS settings this is typically called *One time saved key*. dponly @@ -78,7 +78,7 @@ When a device is plugged in it will appear in sysfs as follows:: /sys/bus/thunderbolt/devices/0-1/unique_id - e0376f00-0300-0100-ffff-ffffffffffff The ``authorized`` attribute reads 0 which means no PCIe tunnels are -created yet. The user can authorize the device by simply:: +created yet. The user can authorize the device by simply entering:: # echo 1 > /sys/bus/thunderbolt/devices/0-1/authorized @@ -86,7 +86,7 @@ This will create the PCIe tunnels and the device is now connected. If the device supports secure connect, and the domain security level is set to ``secure``, it has an additional attribute ``key`` which can hold -a random 32 byte value used for authorization and challenging the device in +a random 32-byte value used for authorization and challenging the device in future connects:: /sys/bus/thunderbolt/devices/0-3/authorized - 0 @@ -99,12 +99,12 @@ future connects:: Notice the key is empty by default. -If the user does not want to use secure connect it can just ``echo 1`` +If the user does not want to use secure connect they can just ``echo 1`` to the ``authorized`` attribute and the PCIe tunnels will be created in -the same way than in ``user`` security level. +the same way as in the ``user`` security level. If the user wants to use secure connect, the first time the device is -plugged a key needs to be created and send to the device:: +plugged a key needs to be created and sent to the device:: # key=$(openssl rand -hex 32) # echo $key > /sys/bus/thunderbolt/devices/0-3/key @@ -121,27 +121,27 @@ device using the same key:: If the challenge the device returns back matches the one we expect based on the key, the device is connected and the PCIe tunnels are created. -However, if the challenge failed no tunnels are created and error is +However, if the challenge fails no tunnels are created and error is returned to the user. -If the user still wants to connect the device it can either approve -the device without a key or write new key and write 1 to the +If the user still wants to connect the device they can either approve +the device without a key or write a new key and write 1 to the ``authorized`` file to get the new key stored on the device NVM. Upgrading NVM on Thunderbolt device or host ------------------------------------------- -Since most of the functionality is handled in a firmware running on a +Since most of the functionality is handled in firmware running on a host controller or a device, it is important that the firmware can be upgraded to the latest where possible bugs in it have been fixed. Typically OEMs provide this firmware from their support site. -There is also a central site which has links where to download firmwares +There is also a central site which has links where to download firmware for some machines: `Thunderbolt Updates <https://thunderbolttechnology.net/updates>`_ -Before you upgrade firmware on a device or host, please make sure it is -the suitable. Failing to do that may render the device (or host) in a +Before you upgrade firmware on a device or host, please make sure it is a +suitable upgrade. Failing to do that may render the device (or host) in a state where it cannot be used properly anymore without special tools! Host NVM upgrade on Apple Macs is not supported. @@ -151,7 +151,7 @@ Thunderbolt device so that the host controller appears. It does not matter which device is connected (unless you are upgrading NVM on a device - then you need to connect that particular device). -Note OEM-specific method to power the controller up ("force power") may +Note an OEM-specific method to power the controller up ("force power") may be available for your system in which case there is no need to plug in a Thunderbolt device. @@ -171,7 +171,7 @@ it comes back the driver notices it and initiates a full power cycle. After a while the host controller appears again and this time it should be fully functional. -We can verify that the new NVM firmware is active by running following +We can verify that the new NVM firmware is active by running the following commands:: # cat /sys/bus/thunderbolt/devices/0-0/nvm_authenticate @@ -179,38 +179,38 @@ commands:: # cat /sys/bus/thunderbolt/devices/0-0/nvm_version 18.0 -If ``nvm_authenticate`` contains anything else than 0x0 it is the error +If ``nvm_authenticate`` contains anything other than 0x0 it is the error code from the last authentication cycle, which means the authentication of the NVM image failed. Note names of the NVMem devices ``nvm_activeN`` and ``nvm_non_activeN`` -depends on the order they are registered in the NVMem subsystem. N in +depend on the order they are registered in the NVMem subsystem. N in the name is the identifier added by the NVMem subsystem. Upgrading NVM when host controller is in safe mode -------------------------------------------------- If the existing NVM is not properly authenticated (or is missing) the -host controller goes into safe mode which means that only available -functionality is flashing new NVM image. When in this mode the reading +host controller goes into safe mode which means that the only available +functionality is flashing a new NVM image. When in this mode, reading ``nvm_version`` fails with ``ENODATA`` and the device identification information is missing. To recover from this mode, one needs to flash a valid NVM image to the -host host controller in the same way it is done in the previous chapter. +host controller in the same way it is done in the previous chapter. Networking over Thunderbolt cable --------------------------------- -Thunderbolt technology allows software communication across two hosts +Thunderbolt technology allows software communication between two hosts connected by a Thunderbolt cable. -It is possible to tunnel any kind of traffic over Thunderbolt link but +It is possible to tunnel any kind of traffic over a Thunderbolt link but currently we only support Apple ThunderboltIP protocol. -If the other host is running Windows or macOS only thing you need to -do is to connect Thunderbolt cable between the two hosts, the -``thunderbolt-net`` is loaded automatically. If the other host is also -Linux you should load ``thunderbolt-net`` manually on one host (it does -not matter which one):: +If the other host is running Windows or macOS, the only thing you need to +do is to connect a Thunderbolt cable between the two hosts; the +``thunderbolt-net`` driver is loaded automatically. If the other host is +also Linux you should load ``thunderbolt-net`` manually on one host (it +does not matter which one):: # modprobe thunderbolt-net @@ -220,12 +220,12 @@ is built-in to the kernel image, there is no need to do anything. The driver will create one virtual ethernet interface per Thunderbolt port which are named like ``thunderbolt0`` and so on. From this point you can either use standard userspace tools like ``ifconfig`` to -configure the interface or let your GUI to handle it automatically. +configure the interface or let your GUI handle it automatically. Forcing power ------------- Many OEMs include a method that can be used to force the power of a -thunderbolt controller to an "On" state even if nothing is connected. +Thunderbolt controller to an "On" state even if nothing is connected. If supported by your machine this will be exposed by the WMI bus with a sysfs attribute called "force_power". diff --git a/Documentation/bpf/bpf_devel_QA.txt b/Documentation/bpf/bpf_devel_QA.txt index cefef855dea4..84cbb302f2b5 100644 --- a/Documentation/bpf/bpf_devel_QA.txt +++ b/Documentation/bpf/bpf_devel_QA.txt @@ -516,4 +516,35 @@ A: LLVM has a -mcpu selector for the BPF back end in order to allow the By the way, the BPF kernel selftests run with -mcpu=probe for better test coverage. +Q: In some cases clang flag "-target bpf" is used but in other cases the + default clang target, which matches the underlying architecture, is used. + What is the difference and when I should use which? + +A: Although LLVM IR generation and optimization try to stay architecture + independent, "-target <arch>" still has some impact on generated code: + + - BPF program may recursively include header file(s) with file scope + inline assembly codes. The default target can handle this well, + while bpf target may fail if bpf backend assembler does not + understand these assembly codes, which is true in most cases. + + - When compiled without -g, additional elf sections, e.g., + .eh_frame and .rela.eh_frame, may be present in the object file + with default target, but not with bpf target. + + - The default target may turn a C switch statement into a switch table + lookup and jump operation. Since the switch table is placed + in the global readonly section, the bpf program will fail to load. + The bpf target does not support switch table optimization. + The clang option "-fno-jump-tables" can be used to disable + switch table generation. + + You should use default target when: + + - Your program includes a header file, e.g., ptrace.h, which eventually + pulls in some header files containing file scope host assembly codes. + - You can add "-fno-jump-tables" to work around the switch table issue. + + Otherwise, you can use bpf target. + Happy BPF hacking! diff --git a/Documentation/core-api/idr.rst b/Documentation/core-api/idr.rst new file mode 100644 index 000000000000..9078a5c3ac95 --- /dev/null +++ b/Documentation/core-api/idr.rst @@ -0,0 +1,79 @@ +.. SPDX-License-Identifier: CC-BY-SA-4.0 + +============= +ID Allocation +============= + +:Author: Matthew Wilcox + +Overview +======== + +A common problem to solve is allocating identifiers (IDs); generally +small numbers which identify a thing. Examples include file descriptors, +process IDs, packet identifiers in networking protocols, SCSI tags +and device instance numbers. The IDR and the IDA provide a reasonable +solution to the problem to avoid everybody inventing their own. The IDR +provides the ability to map an ID to a pointer, while the IDA provides +only ID allocation, and as a result is much more memory-efficient. + +IDR usage +========= + +Start by initialising an IDR, either with :c:func:`DEFINE_IDR` +for statically allocated IDRs or :c:func:`idr_init` for dynamically +allocated IDRs. + +You can call :c:func:`idr_alloc` to allocate an unused ID. Look up +the pointer you associated with the ID by calling :c:func:`idr_find` +and free the ID by calling :c:func:`idr_remove`. + +If you need to change the pointer associated with an ID, you can call +:c:func:`idr_replace`. One common reason to do this is to reserve an +ID by passing a ``NULL`` pointer to the allocation function; initialise the +object with the reserved ID and finally insert the initialised object +into the IDR. + +Some users need to allocate IDs larger than ``INT_MAX``. So far all of +these users have been content with a ``UINT_MAX`` limit, and they use +:c:func:`idr_alloc_u32`. If you need IDs that will not fit in a u32, +we will work with you to address your needs. + +If you need to allocate IDs sequentially, you can use +:c:func:`idr_alloc_cyclic`. The IDR becomes less efficient when dealing +with larger IDs, so using this function comes at a slight cost. + +To perform an action on all pointers used by the IDR, you can +either use the callback-based :c:func:`idr_for_each` or the +iterator-style :c:func:`idr_for_each_entry`. You may need to use +:c:func:`idr_for_each_entry_continue` to continue an iteration. You can +also use :c:func:`idr_get_next` if the iterator doesn't fit your needs. + +When you have finished using an IDR, you can call :c:func:`idr_destroy` +to release the memory used by the IDR. This will not free the objects +pointed to from the IDR; if you want to do that, use one of the iterators +to do it. + +You can use :c:func:`idr_is_empty` to find out whether there are any +IDs currently allocated. + +If you need to take a lock while allocating a new ID from the IDR, +you may need to pass a restrictive set of GFP flags, which can lead +to the IDR being unable to allocate memory. To work around this, +you can call :c:func:`idr_preload` before taking the lock, and then +:c:func:`idr_preload_end` after the allocation. + +.. kernel-doc:: include/linux/idr.h + :doc: idr sync + +IDA usage +========= + +.. kernel-doc:: lib/idr.c + :doc: IDA description + +Functions and structures +======================== + +.. kernel-doc:: include/linux/idr.h +.. kernel-doc:: lib/idr.c diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 1b1fd01990b5..c670a8031786 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -16,6 +16,7 @@ Core utilities atomic_ops refcount-vs-atomic cpu_hotplug + idr local_ops workqueue genericirq diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index e7fadf02c511..ff335f8aeb39 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -103,18 +103,6 @@ CRC Functions .. kernel-doc:: lib/crc-itu-t.c :export: -idr/ida Functions ------------------ - -.. kernel-doc:: include/linux/idr.h - :doc: idr sync - -.. kernel-doc:: lib/idr.c - :doc: IDA description - -.. kernel-doc:: lib/idr.c - :export: - Math Functions in Linux ======================= diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt index 434c49cc7330..61546ac578d6 100644 --- a/Documentation/cpu-freq/cpu-drivers.txt +++ b/Documentation/cpu-freq/cpu-drivers.txt @@ -291,3 +291,7 @@ For example: /* Do something with pos */ pos->frequency = ... } + +If you need to work with the position of pos within driver_freq_table, +do not subtract the pointers, as it is quite costly. Instead, use the +macros cpufreq_for_each_entry_idx() and cpufreq_for_each_valid_entry_idx(). diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt index 857df929a654..1fd5d69647ca 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt @@ -16,6 +16,9 @@ Required Properties: - "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU. - "renesas,ipmmu-r8a7794" for the R8A7794 (R-Car E2) IPMMU. - "renesas,ipmmu-r8a7795" for the R8A7795 (R-Car H3) IPMMU. + - "renesas,ipmmu-r8a7796" for the R8A7796 (R-Car M3-W) IPMMU. + - "renesas,ipmmu-r8a77970" for the R8A77970 (R-Car V3M) IPMMU. + - "renesas,ipmmu-r8a77995" for the R8A77995 (R-Car D3) IPMMU. - "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU. - reg: Base address and size of the IPMMU registers. diff --git a/Documentation/devicetree/bindings/thermal/armada-thermal.txt b/Documentation/devicetree/bindings/thermal/armada-thermal.txt index 24aacf8948c5..e0d013a2e66d 100644 --- a/Documentation/devicetree/bindings/thermal/armada-thermal.txt +++ b/Documentation/devicetree/bindings/thermal/armada-thermal.txt @@ -2,22 +2,35 @@ Required properties: -- compatible: Should be set to one of the following: - marvell,armada370-thermal - marvell,armada375-thermal - marvell,armada380-thermal - marvell,armadaxp-thermal +- compatible: Should be set to one of the following: + * marvell,armada370-thermal + * marvell,armada375-thermal + * marvell,armada380-thermal + * marvell,armadaxp-thermal + * marvell,armada-ap806-thermal + * marvell,armada-cp110-thermal -- reg: Device's register space. - Two entries are expected, see the examples below. - The first one is required for the sensor register; - the second one is required for the control register - to be used for sensor initialization (a.k.a. calibration). +- reg: Device's register space. + Two entries are expected, see the examples below. The first one points + to the status register (4B). The second one points to the control + registers (8B). + Note: The compatibles marvell,armada370-thermal, + marvell,armada380-thermal, and marvell,armadaxp-thermal must point to + "control MSB/control 1", with size of 4 (deprecated binding), or point + to "control LSB/control 0" with size of 8 (current binding). All other + compatibles must point to "control LSB/control 0" with size of 8. -Example: +Examples: + /* Legacy bindings */ thermal@d0018300 { compatible = "marvell,armada370-thermal"; - reg = <0xd0018300 0x4 + reg = <0xd0018300 0x4 0xd0018304 0x4>; }; + + ap_thermal: thermal@6f8084 { + compatible = "marvell,armada-ap806-thermal"; + reg = <0x6f808C 0x4>, + <0x6f8084 0x8>; + }; diff --git a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt index a8e52c8ccfcc..349e635f2d87 100644 --- a/Documentation/devicetree/bindings/thermal/rcar-thermal.txt +++ b/Documentation/devicetree/bindings/thermal/rcar-thermal.txt @@ -6,6 +6,7 @@ Required properties: "renesas,rcar-thermal" (without thermal-zone) as fallback. Examples with soctypes are: - "renesas,thermal-r8a73a4" (R-Mobile APE6) + - "renesas,thermal-r8a7743" (RZ/G1M) - "renesas,thermal-r8a7779" (R-Car H1) - "renesas,thermal-r8a7790" (R-Car H2) - "renesas,thermal-r8a7791" (R-Car M2-W) diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index b1fa64a1d4d0..ae850d6c0ad3 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -125,6 +125,7 @@ focaltech FocalTech Systems Co.,Ltd friendlyarm Guangzhou FriendlyARM Computer Tech Co., Ltd fsl Freescale Semiconductor fujitsu Fujitsu Ltd. +gcw Game Consoles Worldwide ge General Electric Company geekbuying GeekBuying gef GE Fanuc Intelligent Platforms Embedded Systems, Inc. diff --git a/Documentation/devicetree/bindings/watchdog/cortina,gemini-watchdog.txt b/Documentation/devicetree/bindings/watchdog/cortina,gemini-watchdog.txt deleted file mode 100644 index bc4b865d178b..000000000000 --- a/Documentation/devicetree/bindings/watchdog/cortina,gemini-watchdog.txt +++ /dev/null @@ -1,17 +0,0 @@ -Cortina Systems Gemini SoC Watchdog - -Required properties: -- compatible : must be "cortina,gemini-watchdog" -- reg : shall contain base register location and length -- interrupts : shall contain the interrupt for the watchdog - -Optional properties: -- timeout-sec : the default watchdog timeout in seconds. - -Example: - -watchdog@41000000 { - compatible = "cortina,gemini-watchdog"; - reg = <0x41000000 0x1000>; - interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; -}; diff --git a/Documentation/devicetree/bindings/watchdog/cortina,gemin-watchdog.txt b/Documentation/devicetree/bindings/watchdog/faraday,ftwdt010.txt index bc4b865d178b..9ecdb502e605 100644 --- a/Documentation/devicetree/bindings/watchdog/cortina,gemin-watchdog.txt +++ b/Documentation/devicetree/bindings/watchdog/faraday,ftwdt010.txt @@ -1,7 +1,12 @@ -Cortina Systems Gemini SoC Watchdog +Faraday Technology FTWDT010 watchdog + +This is an IP part from Faraday Technology found in the Gemini +SoCs and others. Required properties: -- compatible : must be "cortina,gemini-watchdog" +- compatible : must be one of + "faraday,ftwdt010" + "cortina,gemini-watchdog", "faraday,ftwdt010" - reg : shall contain base register location and length - interrupts : shall contain the interrupt for the watchdog @@ -11,7 +16,7 @@ Optional properties: Example: watchdog@41000000 { - compatible = "cortina,gemini-watchdog"; + compatible = "faraday,ftwdt010"; reg = <0x41000000 0x1000>; interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt b/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt index 3c7a1cd13b10..cb44918f01a8 100644 --- a/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt +++ b/Documentation/devicetree/bindings/watchdog/ingenic,jz4740-wdt.txt @@ -1,7 +1,7 @@ -Ingenic Watchdog Timer (WDT) Controller for JZ4740 +Ingenic Watchdog Timer (WDT) Controller for JZ4740 & JZ4780 Required properties: -compatible: "ingenic,jz4740-watchdog" +compatible: "ingenic,jz4740-watchdog" or "ingenic,jz4780-watchdog" reg: Register address and length for watchdog registers Example: diff --git a/Documentation/devicetree/bindings/watchdog/realtek,rtd119x.txt b/Documentation/devicetree/bindings/watchdog/realtek,rtd119x.txt new file mode 100644 index 000000000000..05653054bd5b --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/realtek,rtd119x.txt @@ -0,0 +1,17 @@ +Realtek RTD1295 Watchdog +======================== + +Required properties: + +- compatible : Should be "realtek,rtd1295-watchdog" +- reg : Specifies the physical base address and size of registers +- clocks : Specifies one clock input + + +Example: + + watchdog@98007680 { + compatible = "realtek,rtd1295-watchdog"; + reg = <0x98007680 0x100>; + clocks = <&osc27M>; + }; diff --git a/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt index bf6d1ca58af7..74b2f03c1515 100644 --- a/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt +++ b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt @@ -4,10 +4,11 @@ Required properties: - compatible : Should be "renesas,<soctype>-wdt", and "renesas,rcar-gen3-wdt" or "renesas,rza-wdt" as fallback. Examples with soctypes are: + - "renesas,r7s72100-wdt" (RZ/A1) - "renesas,r8a7795-wdt" (R-Car H3) - "renesas,r8a7796-wdt" (R-Car M3-W) + - "renesas,r8a77970-wdt" (R-Car V3M) - "renesas,r8a77995-wdt" (R-Car D3) - - "renesas,r7s72100-wdt" (RZ/A1) When compatible with the generic version, nodes must list the SoC-specific version corresponding to the platform first, followed by the generic diff --git a/Documentation/devicetree/bindings/watchdog/sprd-wdt.txt b/Documentation/devicetree/bindings/watchdog/sprd-wdt.txt new file mode 100644 index 000000000000..aeaf3e0caf47 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/sprd-wdt.txt @@ -0,0 +1,19 @@ +Spreadtrum SoCs Watchdog timer + +Required properties: +- compatible : Should be "sprd,sp9860-wdt". +- reg : Specifies base physical address and size of the registers. +- interrupts : Exactly one interrupt specifier. +- timeout-sec : Contain the default watchdog timeout in seconds. +- clock-names : Contain the input clock names. +- clocks : Phandles to input clocks. + +Example: + watchdog: watchdog@40310000 { + compatible = "sprd,sp9860-wdt"; + reg = <0 0x40310000 0 0x1000>; + interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>; + timeout-sec = <12>; + clock-names = "enable", "rtc_enable"; + clocks = <&clk_aon_apb_gates1 8>, <&clk_aon_apb_rtc_gates 9>; + }; diff --git a/Documentation/driver-api/s390-drivers.rst b/Documentation/driver-api/s390-drivers.rst index ecf8851d3565..30e6aa7e160b 100644 --- a/Documentation/driver-api/s390-drivers.rst +++ b/Documentation/driver-api/s390-drivers.rst @@ -22,9 +22,28 @@ While most I/O devices on a s390 system are typically driven through the channel I/O mechanism described here, there are various other methods (like the diag interface). These are out of the scope of this document. +The s390 common I/O layer also provides access to some devices that are +not strictly considered I/O devices. They are considered here as well, +although they are not the focus of this document. + Some additional information can also be found in the kernel source under Documentation/s390/driver-model.txt. +The css bus +=========== + +The css bus contains the subchannels available on the system. They fall +into several categories: + +* Standard I/O subchannels, for use by the system. They have a child + device on the ccw bus and are described below. +* I/O subchannels bound to the vfio-ccw driver. See + Documentation/s390/vfio-ccw.txt. +* Message subchannels. No Linux driver currently exists. +* CHSC subchannels (at most one). The chsc subchannel driver can be used + to send asynchronous chsc commands. +* eADM subchannels. Used for talking to storage class memory. + The ccw bus =========== @@ -102,10 +121,15 @@ ccw group devices Generic interfaces ================== -Some interfaces are available to other drivers that do not necessarily -have anything to do with the busses described above, but still are -indirectly using basic infrastructure in the common I/O layer. One -example is the support for adapter interrupts. +The following section contains interfaces in use not only by drivers +dealing with ccw devices, but drivers for various other s390 hardware +as well. + +Adapter interrupts +------------------ + +The common I/O layer provides helper functions for dealing with adapter +interrupts and interrupt vectors. .. kernel-doc:: drivers/s390/cio/airq.c :export: diff --git a/Documentation/filesystems/afs.txt b/Documentation/filesystems/afs.txt index ba99b5ac4fd8..c5254f6d234d 100644 --- a/Documentation/filesystems/afs.txt +++ b/Documentation/filesystems/afs.txt @@ -7,6 +7,7 @@ Contents: - Overview. - Usage. - Mountpoints. + - Dynamic root. - Proc filesystem. - The cell database. - Security. @@ -127,6 +128,22 @@ mounted on /afs in one go by doing: umount /afs +============ +DYNAMIC ROOT +============ + +A mount option is available to create a serverless mount that is only usable +for dynamic lookup. Creating such a mount can be done by, for example: + + mount -t afs none /afs -o dyn + +This creates a mount that just has an empty directory at the root. Attempting +to look up a name in this directory will cause a mountpoint to be created that +looks up a cell of the same name, for example: + + ls /afs/grand.central.org/ + + =============== PROC FILESYSTEM =============== diff --git a/Documentation/mips/AU1xxx_IDE.README b/Documentation/mips/AU1xxx_IDE.README index 52844a58cc8a..ff675a1b1422 100644 --- a/Documentation/mips/AU1xxx_IDE.README +++ b/Documentation/mips/AU1xxx_IDE.README @@ -56,8 +56,6 @@ Following extra configs variables are introduced: CONFIG_BLK_DEV_IDE_AU1XXX_PIO_DBDMA - enable the PIO+DBDMA mode CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA - enable the MWDMA mode - CONFIG_BLK_DEV_IDE_AU1XXX_BURSTABLE_ON - set Burstable FIFO in DBDMA - controller SUPPORTED IDE MODES @@ -82,11 +80,9 @@ CONFIG_IDE_GENERIC=y CONFIG_BLK_DEV_IDEPCI=y CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_IDEDMA_PCI=y -CONFIG_IDEDMA_PCI_AUTO=y CONFIG_BLK_DEV_IDE_AU1XXX=y CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y CONFIG_BLK_DEV_IDEDMA=y -CONFIG_IDEDMA_AUTO=y Also define 'IDE_AU1XXX_BURSTMODE' in 'drivers/ide/mips/au1xxx-ide.c' to enable the burst support on DBDMA controller. @@ -94,16 +90,13 @@ the burst support on DBDMA controller. If the used system need the USB support enable the following kernel configs for high IDE to USB throughput. -CONFIG_BLK_DEV_IDEDISK=y CONFIG_IDE_GENERIC=y CONFIG_BLK_DEV_IDEPCI=y CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_IDEDMA_PCI=y -CONFIG_IDEDMA_PCI_AUTO=y CONFIG_BLK_DEV_IDE_AU1XXX=y CONFIG_BLK_DEV_IDE_AU1XXX_MDMA2_DBDMA=y CONFIG_BLK_DEV_IDEDMA=y -CONFIG_IDEDMA_AUTO=y Also undefine 'IDE_AU1XXX_BURSTMODE' in 'drivers/ide/mips/au1xxx-ide.c' to disable the burst support on DBDMA controller. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 3f2c40d8e6aa..a553d4e4a0fb 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -508,7 +508,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max min: Minimal size of receive buffer used by TCP sockets. It is guaranteed to each TCP socket, even under moderate memory pressure. - Default: 1 page + Default: 4K default: initial size of receive buffer used by TCP sockets. This value overrides net.core.rmem_default used by other protocols. @@ -667,7 +667,7 @@ tcp_window_scaling - BOOLEAN tcp_wmem - vector of 3 INTEGERs: min, default, max min: Amount of memory reserved for send buffers for TCP sockets. Each TCP socket has rights to use it due to fact of its birth. - Default: 1 page + Default: 4K default: initial size of send buffer used by TCP sockets. This value overrides net.core.wmem_default used by other protocols. diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index a430f6eee756..1c9fe657ed01 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -24,6 +24,7 @@ Below are the essential guides that every developer should read. development-process submitting-patches coding-style + maintainer-pgp-guide email-clients kernel-enforcement-statement kernel-driver-statement diff --git a/Documentation/process/kernel-docs.rst b/Documentation/process/kernel-docs.rst index b8cac85a4001..3fb28de556e4 100644 --- a/Documentation/process/kernel-docs.rst +++ b/Documentation/process/kernel-docs.rst @@ -58,7 +58,7 @@ On-line docs * Title: **Linux Kernel Mailing List Glossary** :Author: various - :URL: http://kernelnewbies.org/glossary/ + :URL: https://kernelnewbies.org/KernelGlossary :Date: rolling version :Keywords: glossary, terms, linux-kernel. :Description: From the introduction: "This glossary is intended as diff --git a/Documentation/process/maintainer-pgp-guide.rst b/Documentation/process/maintainer-pgp-guide.rst new file mode 100644 index 000000000000..b453561a7148 --- /dev/null +++ b/Documentation/process/maintainer-pgp-guide.rst @@ -0,0 +1,929 @@ +.. _pgpguide: + +=========================== +Kernel Maintainer PGP guide +=========================== + +:Author: Konstantin Ryabitsev <konstantin@linuxfoundation.org> + +This document is aimed at Linux kernel developers, and especially at +subsystem maintainers. It contains a subset of information discussed in +the more general "`Protecting Code Integrity`_" guide published by the +Linux Foundation. Please read that document for more in-depth discussion +on some of the topics mentioned in this guide. + +.. _`Protecting Code Integrity`: https://github.com/lfit/itpol/blob/master/protecting-code-integrity.md + +The role of PGP in Linux Kernel development +=========================================== + +PGP helps ensure the integrity of the code that is produced by the Linux +kernel development community and, to a lesser degree, establish trusted +communication channels between developers via PGP-signed email exchange. + +The Linux kernel source code is available in two main formats: + +- Distributed source repositories (git) +- Periodic release snapshots (tarballs) + +Both git repositories and tarballs carry PGP signatures of the kernel +developers who create official kernel releases. These signatures offer a +cryptographic guarantee that downloadable versions made available via +kernel.org or any other mirrors are identical to what these developers +have on their workstations. To this end: + +- git repositories provide PGP signatures on all tags +- tarballs provide detached PGP signatures with all downloads + +.. _devs_not_infra: + +Trusting the developers, not infrastructure +------------------------------------------- + +Ever since the 2011 compromise of core kernel.org systems, the main +operating principle of the Kernel Archives project has been to assume +that any part of the infrastructure can be compromised at any time. For +this reason, the administrators have taken deliberate steps to emphasize +that trust must always be placed with developers and never with the code +hosting infrastructure, regardless of how good the security practices +for the latter may be. + +The above guiding principle is the reason why this guide is needed. We +want to make sure that by placing trust into developers we do not simply +shift the blame for potential future security incidents to someone else. +The goal is to provide a set of guidelines developers can use to create +a secure working environment and safeguard the PGP keys used to +establish the integrity of the Linux kernel itself. + +.. _pgp_tools: + +PGP tools +========= + +Use GnuPG v2 +------------ + +Your distro should already have GnuPG installed by default, you just +need to verify that you are using version 2.x and not the legacy 1.4 +release -- many distributions still package both, with the default +``gpg`` command invoking GnuPG v.1. To check, run:: + + $ gpg --version | head -n1 + +If you see ``gpg (GnuPG) 1.4.x``, then you are using GnuPG v.1. Try the +``gpg2`` command (if you don't have it, you may need to install the +gnupg2 package):: + + $ gpg2 --version | head -n1 + +If you see ``gpg (GnuPG) 2.x.x``, then you are good to go. This guide +will assume you have the version 2.2 of GnuPG (or later). If you are +using version 2.0 of GnuPG, then some of the commands in this guide will +not work, and you should consider installing the latest 2.2 version of +GnuPG. Versions of gnupg-2.1.11 and later should be compatible for the +purposes of this guide as well. + +If you have both ``gpg`` and ``gpg2`` commands, you should make sure you +are always using GnuPG v2, not the legacy version. You can enforce this +by setting the appropriate alias:: + + $ alias gpg=gpg2 + +You can put that in your ``.bashrc`` to make sure it's always the case. + +Configure gpg-agent options +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The GnuPG agent is a helper tool that will start automatically whenever +you use the ``gpg`` command and run in the background with the purpose +of caching the private key passphrase. There are two options you should +know in order to tweak when the passphrase should be expired from cache: + +- ``default-cache-ttl`` (seconds): If you use the same key again before + the time-to-live expires, the countdown will reset for another period. + The default is 600 (10 minutes). +- ``max-cache-ttl`` (seconds): Regardless of how recently you've used + the key since initial passphrase entry, if the maximum time-to-live + countdown expires, you'll have to enter the passphrase again. The + default is 30 minutes. + +If you find either of these defaults too short (or too long), you can +edit your ``~/.gnupg/gpg-agent.conf`` file to set your own values:: + + # set to 30 minutes for regular ttl, and 2 hours for max ttl + default-cache-ttl 1800 + max-cache-ttl 7200 + +.. note:: + + It is no longer necessary to start gpg-agent manually at the + beginning of your shell session. You may want to check your rc files + to remove anything you had in place for older versions of GnuPG, as + it may not be doing the right thing any more. + +Set up a refresh cronjob +~~~~~~~~~~~~~~~~~~~~~~~~ + +You will need to regularly refresh your keyring in order to get the +latest changes on other people's public keys, which is best done with a +daily cronjob:: + + @daily /usr/bin/gpg2 --refresh >/dev/null 2>&1 + +Check the full path to your ``gpg`` or ``gpg2`` command and use the +``gpg2`` command if regular ``gpg`` for you is the legacy GnuPG v.1. + +.. _master_key: + +Protect your master PGP key +=========================== + +This guide assumes that you already have a PGP key that you use for Linux +kernel development purposes. If you do not yet have one, please see the +"`Protecting Code Integrity`_" document mentioned earlier for guidance +on how to create a new one. + +You should also make a new key if your current one is weaker than 2048 bits +(RSA). + +Master key vs. Subkeys +---------------------- + +Subkeys are fully independent PGP keypairs that are tied to the "master" +key using certifying key signatures (certificates). It is important to +understand the following: + +1. There are no technical differences between the "master key" and "subkeys." +2. At creation time, we assign functional limitations to each key by + giving it specific capabilities. +3. A PGP key can have 4 capabilities: + + - **[S]** key can be used for signing + - **[E]** key can be used for encryption + - **[A]** key can be used for authentication + - **[C]** key can be used for certifying other keys + +4. A single key may have multiple capabilities. +5. A subkey is fully independent from the master key. A message + encrypted to a subkey cannot be decrypted with the master key. If you + lose your private subkey, it cannot be recreated from the master key + in any way. + +The key carrying the **[C]** (certify) capability is considered the +"master" key because it is the only key that can be used to indicate +relationship with other keys. Only the **[C]** key can be used to: + +- add or revoke other keys (subkeys) with S/E/A capabilities +- add, change or revoke identities (uids) associated with the key +- add or change the expiration date on itself or any subkey +- sign other people's keys for web of trust purposes + +By default, GnuPG creates the following when generating new keys: + +- A master key carrying both Certify and Sign capabilities (**[SC]**) +- A separate subkey with the Encryption capability (**[E]**) + +If you used the default parameters when generating your key, then that +is what you will have. You can verify by running ``gpg --list-secret-keys``, +for example:: + + sec rsa2048 2018-01-23 [SC] [expires: 2020-01-23] + 000000000000000000000000AAAABBBBCCCCDDDD + uid [ultimate] Alice Dev <adev@kernel.org> + ssb rsa2048 2018-01-23 [E] [expires: 2020-01-23] + +Any key carrying the **[C]** capability is your master key, regardless +of any other capabilities it may have assigned to it. + +The long line under the ``sec`` entry is your key fingerprint -- +whenever you see ``[fpr]`` in the examples below, that 40-character +string is what it refers to. + +Ensure your passphrase is strong +-------------------------------- + +GnuPG uses passphrases to encrypt your private keys before storing them on +disk. This way, even if your ``.gnupg`` directory is leaked or stolen in +its entirety, the attackers cannot use your private keys without first +obtaining the passphrase to decrypt them. + +It is absolutely essential that your private keys are protected by a +strong passphrase. To set it or change it, use:: + + $ gpg --change-passphrase [fpr] + +Create a separate Signing subkey +-------------------------------- + +Our goal is to protect your master key by moving it to offline media, so +if you only have a combined **[SC]** key, then you should create a separate +signing subkey:: + + $ gpg --quick-add-key [fpr] ed25519 sign + +Remember to tell the keyservers about this change, so others can pull down +your new subkey:: + + $ gpg --send-key [fpr] + +.. note:: ECC support in GnuPG + + GnuPG 2.1 and later has full support for Elliptic Curve + Cryptography, with ability to combine ECC subkeys with traditional + RSA master keys. The main upside of ECC cryptography is that it is + much faster computationally and creates much smaller signatures when + compared byte for byte with 2048+ bit RSA keys. Unless you plan on + using a smartcard device that does not support ECC operations, we + recommend that you create an ECC signing subkey for your kernel + work. + + If for some reason you prefer to stay with RSA subkeys, just replace + "ed25519" with "rsa2048" in the above command. + + +Back up your master key for disaster recovery +--------------------------------------------- + +The more signatures you have on your PGP key from other developers, the +more reasons you have to create a backup version that lives on something +other than digital media, for disaster recovery reasons. + +The best way to create a printable hardcopy of your private key is by +using the ``paperkey`` software written for this very purpose. See ``man +paperkey`` for more details on the output format and its benefits over +other solutions. Paperkey should already be packaged for most +distributions. + +Run the following command to create a hardcopy backup of your private +key:: + + $ gpg --export-secret-key [fpr] | paperkey -o /tmp/key-backup.txt + +Print out that file (or pipe the output straight to lpr), then take a +pen and write your passphrase on the margin of the paper. **This is +strongly recommended** because the key printout is still encrypted with +that passphrase, and if you ever change it you will not remember what it +used to be when you had created the backup -- *guaranteed*. + +Put the resulting printout and the hand-written passphrase into an envelope +and store in a secure and well-protected place, preferably away from your +home, such as your bank vault. + +.. note:: + + Your printer is probably no longer a simple dumb device connected to + your parallel port, but since the output is still encrypted with + your passphrase, printing out even to "cloud-integrated" modern + printers should remain a relatively safe operation. One option is to + change the passphrase on your master key immediately after you are + done with paperkey. + +Back up your whole GnuPG directory +---------------------------------- + +.. warning:: + + **!!!Do not skip this step!!!** + +It is important to have a readily available backup of your PGP keys +should you need to recover them. This is different from the +disaster-level preparedness we did with ``paperkey``. You will also rely +on these external copies whenever you need to use your Certify key -- +such as when making changes to your own key or signing other people's +keys after conferences and summits. + +Start by getting a small USB "thumb" drive (preferably two!) that you +will use for backup purposes. You will need to encrypt them using LUKS +-- refer to your distro's documentation on how to accomplish this. + +For the encryption passphrase, you can use the same one as on your +master key. + +Once the encryption process is over, re-insert the USB drive and make +sure it gets properly mounted. Copy your entire ``.gnupg`` directory +over to the encrypted storage:: + + $ cp -a ~/.gnupg /media/disk/foo/gnupg-backup + +You should now test to make sure everything still works:: + + $ gpg --homedir=/media/disk/foo/gnupg-backup --list-key [fpr] + +If you don't get any errors, then you should be good to go. Unmount the +USB drive, distinctly label it so you don't blow it away next time you +need to use a random USB drive, and put in a safe place -- but not too +far away, because you'll need to use it every now and again for things +like editing identities, adding or revoking subkeys, or signing other +people's keys. + +Remove the master key from your homedir +---------------------------------------- + +The files in our home directory are not as well protected as we like to +think. They can be leaked or stolen via many different means: + +- by accident when making quick homedir copies to set up a new workstation +- by systems administrator negligence or malice +- via poorly secured backups +- via malware in desktop apps (browsers, pdf viewers, etc) +- via coercion when crossing international borders + +Protecting your key with a good passphrase greatly helps reduce the risk +of any of the above, but passphrases can be discovered via keyloggers, +shoulder-surfing, or any number of other means. For this reason, the +recommended setup is to remove your master key from your home directory +and store it on offline storage. + +.. warning:: + + Please see the previous section and make sure you have backed up + your GnuPG directory in its entirety. What we are about to do will + render your key useless if you do not have a usable backup! + +First, identify the keygrip of your master key:: + + $ gpg --with-keygrip --list-key [fpr] + +The output will be something like this:: + + pub rsa2048 2018-01-24 [SC] [expires: 2020-01-24] + 000000000000000000000000AAAABBBBCCCCDDDD + Keygrip = 1111000000000000000000000000000000000000 + uid [ultimate] Alice Dev <adev@kernel.org> + sub rsa2048 2018-01-24 [E] [expires: 2020-01-24] + Keygrip = 2222000000000000000000000000000000000000 + sub ed25519 2018-01-24 [S] + Keygrip = 3333000000000000000000000000000000000000 + +Find the keygrip entry that is beneath the ``pub`` line (right under the +master key fingerprint). This will correspond directly to a file in your +``~/.gnupg`` directory:: + + $ cd ~/.gnupg/private-keys-v1.d + $ ls + 1111000000000000000000000000000000000000.key + 2222000000000000000000000000000000000000.key + 3333000000000000000000000000000000000000.key + +All you have to do is simply remove the .key file that corresponds to +the master keygrip:: + + $ cd ~/.gnupg/private-keys-v1.d + $ rm 1111000000000000000000000000000000000000.key + +Now, if you issue the ``--list-secret-keys`` command, it will show that +the master key is missing (the ``#`` indicates it is not available):: + + $ gpg --list-secret-keys + sec# rsa2048 2018-01-24 [SC] [expires: 2020-01-24] + 000000000000000000000000AAAABBBBCCCCDDDD + uid [ultimate] Alice Dev <adev@kernel.org> + ssb rsa2048 2018-01-24 [E] [expires: 2020-01-24] + ssb ed25519 2018-01-24 [S] + +You should also remove any ``secring.gpg`` files in the ``~/.gnupg`` +directory, which are left over from earlier versions of GnuPG. + +If you don't have the "private-keys-v1.d" directory +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +If you do not have a ``~/.gnupg/private-keys-v1.d`` directory, then your +secret keys are still stored in the legacy ``secring.gpg`` file used by +GnuPG v1. Making any changes to your key, such as changing the +passphrase or adding a subkey, should automatically convert the old +``secring.gpg`` format to use ``private-keys-v1.d`` instead. + +Once you get that done, make sure to delete the obsolete ``secring.gpg`` +file, which still contains your private keys. + +.. _smartcards: + +Move the subkeys to a dedicated crypto device +============================================= + +Even though the master key is now safe from being leaked or stolen, the +subkeys are still in your home directory. Anyone who manages to get +their hands on those will be able to decrypt your communication or fake +your signatures (if they know the passphrase). Furthermore, each time a +GnuPG operation is performed, the keys are loaded into system memory and +can be stolen from there by sufficiently advanced malware (think +Meltdown and Spectre). + +The best way to completely protect your keys is to move them to a +specialized hardware device that is capable of smartcard operations. + +The benefits of smartcards +-------------------------- + +A smartcard contains a cryptographic chip that is capable of storing +private keys and performing crypto operations directly on the card +itself. Because the key contents never leave the smartcard, the +operating system of the computer into which you plug in the hardware +device is not able to retrieve the private keys themselves. This is very +different from the encrypted USB storage device we used earlier for +backup purposes -- while that USB device is plugged in and mounted, the +operating system is able to access the private key contents. + +Using external encrypted USB media is not a substitute to having a +smartcard-capable device. + +Available smartcard devices +--------------------------- + +Unless all your laptops and workstations have smartcard readers, the +easiest is to get a specialized USB device that implements smartcard +functionality. There are several options available: + +- `Nitrokey Start`_: Open hardware and Free Software, based on FSI + Japan's `Gnuk`_. Offers support for ECC keys, but fewest security + features (such as resistance to tampering or some side-channel + attacks). +- `Nitrokey Pro`_: Similar to the Nitrokey Start, but more + tamper-resistant and offers more security features, but no ECC + support. +- `Yubikey 4`_: proprietary hardware and software, but cheaper than + Nitrokey Pro and comes available in the USB-C form that is more useful + with newer laptops. Offers additional security features such as FIDO + U2F, but no ECC. + +`LWN has a good review`_ of some of the above models, as well as several +others. If you want to use ECC keys, your best bet among commercially +available devices is the Nitrokey Start. + +.. _`Nitrokey Start`: https://shop.nitrokey.com/shop/product/nitrokey-start-6 +.. _`Nitrokey Pro`: https://shop.nitrokey.com/shop/product/nitrokey-pro-3 +.. _`Yubikey 4`: https://www.yubico.com/product/yubikey-4-series/ +.. _Gnuk: http://www.fsij.org/doc-gnuk/ +.. _`LWN has a good review`: https://lwn.net/Articles/736231/ + +Configure your smartcard device +------------------------------- + +Your smartcard device should Just Work (TM) the moment you plug it into +any modern Linux workstation. You can verify it by running:: + + $ gpg --card-status + +If you see full smartcard details, then you are good to go. +Unfortunately, troubleshooting all possible reasons why things may not +be working for you is way beyond the scope of this guide. If you are +having trouble getting the card to work with GnuPG, please seek help via +usual support channels. + +To configure your smartcard, you will need to use the GnuPG menu system, as +there are no convenient command-line switches:: + + $ gpg --card-edit + [...omitted...] + gpg/card> admin + Admin commands are allowed + gpg/card> passwd + +You should set the user PIN (1), Admin PIN (3), and the Reset Code (4). +Please make sure to record and store these in a safe place -- especially +the Admin PIN and the Reset Code (which allows you to completely wipe +the smartcard). You so rarely need to use the Admin PIN, that you will +inevitably forget what it is if you do not record it. + +Getting back to the main card menu, you can also set other values (such +as name, sex, login data, etc), but it's not necessary and will +additionally leak information about your smartcard should you lose it. + +.. note:: + + Despite having the name "PIN", neither the user PIN nor the admin + PIN on the card need to be numbers. + +Move the subkeys to your smartcard +---------------------------------- + +Exit the card menu (using "q") and save all changes. Next, let's move +your subkeys onto the smartcard. You will need both your PGP key +passphrase and the admin PIN of the card for most operations:: + + $ gpg --edit-key [fpr] + + Secret subkeys are available. + + pub rsa2048/AAAABBBBCCCCDDDD + created: 2018-01-23 expires: 2020-01-23 usage: SC + trust: ultimate validity: ultimate + ssb rsa2048/1111222233334444 + created: 2018-01-23 expires: never usage: E + ssb ed25519/5555666677778888 + created: 2017-12-07 expires: never usage: S + [ultimate] (1). Alice Dev <adev@kernel.org> + + gpg> + +Using ``--edit-key`` puts us into the menu mode again, and you will +notice that the key listing is a little different. From here on, all +commands are done from inside this menu mode, as indicated by ``gpg>``. + +First, let's select the key we'll be putting onto the card -- you do +this by typing ``key 1`` (it's the first one in the listing, the **[E]** +subkey):: + + gpg> key 1 + +In the output, you should now see ``ssb*`` on the **[E]** key. The ``*`` +indicates which key is currently "selected." It works as a *toggle*, +meaning that if you type ``key 1`` again, the ``*`` will disappear and +the key will not be selected any more. + +Now, let's move that key onto the smartcard:: + + gpg> keytocard + Please select where to store the key: + (2) Encryption key + Your selection? 2 + +Since it's our **[E]** key, it makes sense to put it into the Encryption +slot. When you submit your selection, you will be prompted first for +your PGP key passphrase, and then for the admin PIN. If the command +returns without an error, your key has been moved. + +**Important**: Now type ``key 1`` again to unselect the first key, and +``key 2`` to select the **[S]** key:: + + gpg> key 1 + gpg> key 2 + gpg> keytocard + Please select where to store the key: + (1) Signature key + (3) Authentication key + Your selection? 1 + +You can use the **[S]** key both for Signature and Authentication, but +we want to make sure it's in the Signature slot, so choose (1). Once +again, if your command returns without an error, then the operation was +successful:: + + gpg> q + Save changes? (y/N) y + +Saving the changes will delete the keys you moved to the card from your +home directory (but it's okay, because we have them in our backups +should we need to do this again for a replacement smartcard). + +Verifying that the keys were moved +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +If you perform ``--list-secret-keys`` now, you will see a subtle +difference in the output:: + + $ gpg --list-secret-keys + sec# rsa2048 2018-01-24 [SC] [expires: 2020-01-24] + 000000000000000000000000AAAABBBBCCCCDDDD + uid [ultimate] Alice Dev <adev@kernel.org> + ssb> rsa2048 2018-01-24 [E] [expires: 2020-01-24] + ssb> ed25519 2018-01-24 [S] + +The ``>`` in the ``ssb>`` output indicates that the subkey is only +available on the smartcard. If you go back into your secret keys +directory and look at the contents there, you will notice that the +``.key`` files there have been replaced with stubs:: + + $ cd ~/.gnupg/private-keys-v1.d + $ strings *.key | grep 'private-key' + +The output should contain ``shadowed-private-key`` to indicate that +these files are only stubs and the actual content is on the smartcard. + +Verifying that the smartcard is functioning +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +To verify that the smartcard is working as intended, you can create a +signature:: + + $ echo "Hello world" | gpg --clearsign > /tmp/test.asc + $ gpg --verify /tmp/test.asc + +This should ask for your smartcard PIN on your first command, and then +show "Good signature" after you run ``gpg --verify``. + +Congratulations, you have successfully made it extremely difficult to +steal your digital developer identity! + +Other common GnuPG operations +----------------------------- + +Here is a quick reference for some common operations you'll need to do +with your PGP key. + +Mounting your master key offline storage +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You will need your master key for any of the operations below, so you +will first need to mount your backup offline storage and tell GnuPG to +use it:: + + $ export GNUPGHOME=/media/disk/foo/gnupg-backup + $ gpg --list-secret-keys + +You want to make sure that you see ``sec`` and not ``sec#`` in the +output (the ``#`` means the key is not available and you're still using +your regular home directory location). + +Extending key expiration date +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The master key has the default expiration date of 2 years from the date +of creation. This is done both for security reasons and to make obsolete +keys eventually disappear from keyservers. + +To extend the expiration on your key by a year from current date, just +run:: + + $ gpg --quick-set-expire [fpr] 1y + +You can also use a specific date if that is easier to remember (e.g. +your birthday, January 1st, or Canada Day):: + + $ gpg --quick-set-expire [fpr] 2020-07-01 + +Remember to send the updated key back to keyservers:: + + $ gpg --send-key [fpr] + +Updating your work directory after any changes +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +After you make any changes to your key using the offline storage, you will +want to import these changes back into your regular working directory:: + + $ gpg --export | gpg --homedir ~/.gnupg --import + $ unset GNUPGHOME + + +Using PGP with Git +================== + +One of the core features of Git is its decentralized nature -- once a +repository is cloned to your system, you have full history of the +project, including all of its tags, commits and branches. However, with +hundreds of cloned repositories floating around, how does anyone verify +that their copy of linux.git has not been tampered with by a malicious +third party? + +Or what happens if a backdoor is discovered in the code and the "Author" +line in the commit says it was done by you, while you're pretty sure you +had `nothing to do with it`_? + +To address both of these issues, Git introduced PGP integration. Signed +tags prove the repository integrity by assuring that its contents are +exactly the same as on the workstation of the developer who created the +tag, while signed commits make it nearly impossible for someone to +impersonate you without having access to your PGP keys. + +.. _`nothing to do with it`: https://github.com/jayphelps/git-blame-someone-else + +Configure git to use your PGP key +--------------------------------- + +If you only have one secret key in your keyring, then you don't really +need to do anything extra, as it becomes your default key. However, if +you happen to have multiple secret keys, you can tell git which key +should be used (``[fpr]`` is the fingerprint of your key):: + + $ git config --global user.signingKey [fpr] + +**IMPORTANT**: If you have a distinct ``gpg2`` command, then you should +tell git to always use it instead of the legacy ``gpg`` from version 1:: + + $ git config --global gpg.program gpg2 + +How to work with signed tags +---------------------------- + +To create a signed tag, simply pass the ``-s`` switch to the tag +command:: + + $ git tag -s [tagname] + +Our recommendation is to always sign git tags, as this allows other +developers to ensure that the git repository they are pulling from has +not been maliciously altered. + +How to verify signed tags +~~~~~~~~~~~~~~~~~~~~~~~~~ + +To verify a signed tag, simply use the ``verify-tag`` command:: + + $ git verify-tag [tagname] + +If you are pulling a tag from another fork of the project repository, +git should automatically verify the signature at the tip you're pulling +and show you the results during the merge operation:: + + $ git pull [url] tags/sometag + +The merge message will contain something like this:: + + Merge tag 'sometag' of [url] + + [Tag message] + + # gpg: Signature made [...] + # gpg: Good signature from [...] + +If you are verifying someone else's git tag, then you will need to +import their PGP key. Please refer to the +":ref:`verify_identities`" section below. + +Configure git to always sign annotated tags +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Chances are, if you're creating an annotated tag, you'll want to sign +it. To force git to always sign annotated tags, you can set a global +configuration option:: + + $ git config --global tag.forceSignAnnotated true + +How to work with signed commits +------------------------------- + +It is easy to create signed commits, but it is much more difficult to +use them in Linux kernel development, since it relies on patches sent to +the mailing list, and this workflow does not preserve PGP commit +signatures. Furthermore, when rebasing your repository to match +upstream, even your own PGP commit signatures will end up discarded. For +this reason, most kernel developers don't bother signing their commits +and will ignore signed commits in any external repositories that they +rely upon in their work. + +However, if you have your working git tree publicly available at some +git hosting service (kernel.org, infradead.org, ozlabs.org, or others), +then the recommendation is that you sign all your git commits even if +upstream developers do not directly benefit from this practice. + +We recommend this for the following reasons: + +1. Should there ever be a need to perform code forensics or track code + provenance, even externally maintained trees carrying PGP commit + signatures will be valuable for such purposes. +2. If you ever need to re-clone your local repository (for example, + after a disk failure), this lets you easily verify the repository + integrity before resuming your work. +3. If someone needs to cherry-pick your commits, this allows them to + quickly verify their integrity before applying them. + +Creating signed commits +~~~~~~~~~~~~~~~~~~~~~~~ + +To create a signed commit, you just need to pass the ``-S`` flag to the +``git commit`` command (it's capital ``-S`` due to collision with +another flag):: + + $ git commit -S + +Configure git to always sign commits +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +You can tell git to always sign commits:: + + git config --global commit.gpgSign true + +.. note:: + + Make sure you configure ``gpg-agent`` before you turn this on. + +.. _verify_identities: + +How to verify kernel developer identities +========================================= + +Signing tags and commits is easy, but how does one go about verifying +that the key used to sign something belongs to the actual kernel +developer and not to a malicious imposter? + +Configure auto-key-retrieval using WKD and DANE +----------------------------------------------- + +If you are not already someone with an extensive collection of other +developers' public keys, then you can jumpstart your keyring by relying +on key auto-discovery and auto-retrieval. GnuPG can piggyback on other +delegated trust technologies, namely DNSSEC and TLS, to get you going if +the prospect of starting your own Web of Trust from scratch is too +daunting. + +Add the following to your ``~/.gnupg/gpg.conf``:: + + auto-key-locate wkd,dane,local + auto-key-retrieve + +DNS-Based Authentication of Named Entities ("DANE") is a method for +publishing public keys in DNS and securing them using DNSSEC signed +zones. Web Key Directory ("WKD") is the alternative method that uses +https lookups for the same purpose. When using either DANE or WKD for +looking up public keys, GnuPG will validate DNSSEC or TLS certificates, +respectively, before adding auto-retrieved public keys to your local +keyring. + +Kernel.org publishes the WKD for all developers who have kernel.org +accounts. Once you have the above changes in your ``gpg.conf``, you can +auto-retrieve the keys for Linus Torvalds and Greg Kroah-Hartman (if you +don't already have them):: + + $ gpg --locate-keys torvalds@kernel.org gregkh@kernel.org + +If you have a kernel.org account, then you should `add the kernel.org +UID to your key`_ to make WKD more useful to other kernel developers. + +.. _`add the kernel.org UID to your key`: https://korg.wiki.kernel.org/userdoc/mail#adding_a_kernelorg_uid_to_your_pgp_key + +Web of Trust (WOT) vs. Trust on First Use (TOFU) +------------------------------------------------ + +PGP incorporates a trust delegation mechanism known as the "Web of +Trust." At its core, this is an attempt to replace the need for +centralized Certification Authorities of the HTTPS/TLS world. Instead of +various software makers dictating who should be your trusted certifying +entity, PGP leaves this responsibility to each user. + +Unfortunately, very few people understand how the Web of Trust works. +While it remains an important aspect of the OpenPGP specification, +recent versions of GnuPG (2.2 and above) have implemented an alternative +mechanism called "Trust on First Use" (TOFU). You can think of TOFU as +"the SSH-like approach to trust." With SSH, the first time you connect +to a remote system, its key fingerprint is recorded and remembered. If +the key changes in the future, the SSH client will alert you and refuse +to connect, forcing you to make a decision on whether you choose to +trust the changed key or not. Similarly, the first time you import +someone's PGP key, it is assumed to be valid. If at any point in the +future GnuPG comes across another key with the same identity, both the +previously imported key and the new key will be marked as invalid and +you will need to manually figure out which one to keep. + +We recommend that you use the combined TOFU+PGP trust model (which is +the new default in GnuPG v2). To set it, add (or modify) the +``trust-model`` setting in ``~/.gnupg/gpg.conf``:: + + trust-model tofu+pgp + +How to use keyservers (more) safely +----------------------------------- + +If you get a "No public key" error when trying to validate someone's +tag, then you should attempt to lookup that key using a keyserver. It is +important to keep in mind that there is absolutely no guarantee that the +key you retrieve from PGP keyservers belongs to the actual person -- +that much is by design. You are supposed to use the Web of Trust to +establish key validity. + +How to properly maintain the Web of Trust is beyond the scope of this +document, simply because doing it properly requires both effort and +dedication that tends to be beyond the caring threshold of most human +beings. Here are some shortcuts that will help you reduce the risk of +importing a malicious key. + +First, let's say you've tried to run ``git verify-tag`` but it returned +an error saying the key is not found:: + + $ git verify-tag sunxi-fixes-for-4.15-2 + gpg: Signature made Sun 07 Jan 2018 10:51:55 PM EST + gpg: using RSA key DA73759BF8619E484E5A3B47389A54219C0F2430 + gpg: issuer "wens@...org" + gpg: Can't check signature: No public key + +Let's query the keyserver for more info about that key fingerprint (the +fingerprint probably belongs to a subkey, so we can't use it directly +without finding out the ID of the master key it is associated with):: + + $ gpg --search DA73759BF8619E484E5A3B47389A54219C0F2430 + gpg: data source: hkp://keys.gnupg.net + (1) Chen-Yu Tsai <wens@...org> + 4096 bit RSA key C94035C21B4F2AEB, created: 2017-03-14, expires: 2019-03-15 + Keys 1-1 of 1 for "DA73759BF8619E484E5A3B47389A54219C0F2430". Enter number(s), N)ext, or Q)uit > q + +Locate the ID of the master key in the output, in our example +``C94035C21B4F2AEB``. Now display the key of Linus Torvalds that you +have on your keyring:: + + $ gpg --list-key torvalds@kernel.org + pub rsa2048 2011-09-20 [SC] + ABAF11C65A2970B130ABE3C479BE3E4300411886 + uid [ unknown] Linus Torvalds <torvalds@kernel.org> + sub rsa2048 2011-09-20 [E] + +Next, open the `PGP pathfinder`_. In the "From" field, paste the key +fingerprint of Linus Torvalds from the output above. In the "To" field, +paste they key-id you found via ``gpg --search`` of the unknown key, and +check the results: + +- `Finding paths to Linus`_ + +If you get a few decent trust paths, then it's a pretty good indication +that it is a valid key. You can add it to your keyring from the +keyserver now:: + + $ gpg --recv-key C94035C21B4F2AEB + +This process is not perfect, and you are obviously trusting the +administrators of the PGP Pathfinder service to not be malicious (in +fact, this goes against :ref:`devs_not_infra`). However, if you +do not carefully maintain your own web of trust, then it is a marked +improvement over blindly trusting keyservers. + +.. _`PGP pathfinder`: https://pgp.cs.uu.nl/ +.. _`Finding paths to Linus`: https://pgp.cs.uu.nl/paths/79BE3E4300411886/to/C94035C21B4F2AEB.html diff --git a/Documentation/sysctl/user.txt b/Documentation/sysctl/user.txt index 1291c498f78f..a5882865836e 100644 --- a/Documentation/sysctl/user.txt +++ b/Documentation/sysctl/user.txt @@ -3,7 +3,7 @@ Documentation for /proc/sys/user/* kernel version 4.9.0 ============================================================== -This file contains the documetation for the sysctl files in +This file contains the documentation for the sysctl files in /proc/sys/user. The files in this directory can be used to override the default diff --git a/Documentation/virtual/kvm/00-INDEX b/Documentation/virtual/kvm/00-INDEX index 69fe1a8b7ad1..3da73aabff5a 100644 --- a/Documentation/virtual/kvm/00-INDEX +++ b/Documentation/virtual/kvm/00-INDEX @@ -26,3 +26,6 @@ s390-diag.txt - Diagnose hypercall description (for IBM S/390) timekeeping.txt - timekeeping virtualization for x86-based architectures. +amd-memory-encryption.txt + - notes on AMD Secure Encrypted Virtualization feature and SEV firmware + command description diff --git a/Documentation/virtual/kvm/amd-memory-encryption.rst b/Documentation/virtual/kvm/amd-memory-encryption.rst new file mode 100644 index 000000000000..71d6d257074f --- /dev/null +++ b/Documentation/virtual/kvm/amd-memory-encryption.rst @@ -0,0 +1,247 @@ +====================================== +Secure Encrypted Virtualization (SEV) +====================================== + +Overview +======== + +Secure Encrypted Virtualization (SEV) is a feature found on AMD processors. + +SEV is an extension to the AMD-V architecture which supports running +virtual machines (VMs) under the control of a hypervisor. When enabled, +the memory contents of a VM will be transparently encrypted with a key +unique to that VM. + +The hypervisor can determine the SEV support through the CPUID +instruction. The CPUID function 0x8000001f reports information related +to SEV:: + + 0x8000001f[eax]: + Bit[1] indicates support for SEV + ... + [ecx]: + Bits[31:0] Number of encrypted guests supported simultaneously + +If support for SEV is present, MSR 0xc001_0010 (MSR_K8_SYSCFG) and MSR 0xc001_0015 +(MSR_K7_HWCR) can be used to determine if it can be enabled:: + + 0xc001_0010: + Bit[23] 1 = memory encryption can be enabled + 0 = memory encryption can not be enabled + + 0xc001_0015: + Bit[0] 1 = memory encryption can be enabled + 0 = memory encryption can not be enabled + +When SEV support is available, it can be enabled in a specific VM by +setting the SEV bit before executing VMRUN.:: + + VMCB[0x90]: + Bit[1] 1 = SEV is enabled + 0 = SEV is disabled + +SEV hardware uses ASIDs to associate a memory encryption key with a VM. +Hence, the ASID for the SEV-enabled guests must be from 1 to a maximum value +defined in the CPUID 0x8000001f[ecx] field. + +SEV Key Management +================== + +The SEV guest key management is handled by a separate processor called the AMD +Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure +key management interface to perform common hypervisor activities such as +encrypting bootstrap code, snapshot, migrating and debugging the guest. For more +information, see the SEV Key Management spec [api-spec]_ + +KVM implements the following commands to support common lifecycle events of SEV +guests, such as launching, running, snapshotting, migrating and decommissioning. + +1. KVM_SEV_INIT +--------------- + +The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform +context. In a typical workflow, this command should be the first command issued. + +Returns: 0 on success, -negative on error + +2. KVM_SEV_LAUNCH_START +----------------------- + +The KVM_SEV_LAUNCH_START command is used for creating the memory encryption +context. To create the encryption context, user must provide a guest policy, +the owner's public Diffie-Hellman (PDH) key and session information. + +Parameters: struct kvm_sev_launch_start (in/out) + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_launch_start { + __u32 handle; /* if zero then firmware creates a new handle */ + __u32 policy; /* guest's policy */ + + __u64 dh_uaddr; /* userspace address pointing to the guest owner's PDH key */ + __u32 dh_len; + + __u64 session_addr; /* userspace address which points to the guest session information */ + __u32 session_len; + }; + +On success, the 'handle' field contains a new handle and on error, a negative value. + +For more details, see SEV spec Section 6.2. + +3. KVM_SEV_LAUNCH_UPDATE_DATA +----------------------------- + +The KVM_SEV_LAUNCH_UPDATE_DATA is used for encrypting a memory region. It also +calculates a measurement of the memory contents. The measurement is a signature +of the memory contents that can be sent to the guest owner as an attestation +that the memory was encrypted correctly by the firmware. + +Parameters (in): struct kvm_sev_launch_update_data + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_launch_update { + __u64 uaddr; /* userspace address to be encrypted (must be 16-byte aligned) */ + __u32 len; /* length of the data to be encrypted (must be 16-byte aligned) */ + }; + +For more details, see SEV spec Section 6.3. + +4. KVM_SEV_LAUNCH_MEASURE +------------------------- + +The KVM_SEV_LAUNCH_MEASURE command is used to retrieve the measurement of the +data encrypted by the KVM_SEV_LAUNCH_UPDATE_DATA command. The guest owner may +wait to provide the guest with confidential information until it can verify the +measurement. Since the guest owner knows the initial contents of the guest at +boot, the measurement can be verified by comparing it to what the guest owner +expects. + +Parameters (in): struct kvm_sev_launch_measure + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_launch_measure { + __u64 uaddr; /* where to copy the measurement */ + __u32 len; /* length of measurement blob */ + }; + +For more details on the measurement verification flow, see SEV spec Section 6.4. + +5. KVM_SEV_LAUNCH_FINISH +------------------------ + +After completion of the launch flow, the KVM_SEV_LAUNCH_FINISH command can be +issued to make the guest ready for the execution. + +Returns: 0 on success, -negative on error + +6. KVM_SEV_GUEST_STATUS +----------------------- + +The KVM_SEV_GUEST_STATUS command is used to retrieve status information about a +SEV-enabled guest. + +Parameters (out): struct kvm_sev_guest_status + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_guest_status { + __u32 handle; /* guest handle */ + __u32 policy; /* guest policy */ + __u8 state; /* guest state (see enum below) */ + }; + +SEV guest state: + +:: + + enum { + SEV_STATE_INVALID = 0; + SEV_STATE_LAUNCHING, /* guest is currently being launched */ + SEV_STATE_SECRET, /* guest is being launched and ready to accept the ciphertext data */ + SEV_STATE_RUNNING, /* guest is fully launched and running */ + SEV_STATE_RECEIVING, /* guest is being migrated in from another SEV machine */ + SEV_STATE_SENDING /* guest is getting migrated out to another SEV machine */ + }; + +7. KVM_SEV_DBG_DECRYPT +---------------------- + +The KVM_SEV_DEBUG_DECRYPT command can be used by the hypervisor to request the +firmware to decrypt the data at the given memory region. + +Parameters (in): struct kvm_sev_dbg + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_dbg { + __u64 src_uaddr; /* userspace address of data to decrypt */ + __u64 dst_uaddr; /* userspace address of destination */ + __u32 len; /* length of memory region to decrypt */ + }; + +The command returns an error if the guest policy does not allow debugging. + +8. KVM_SEV_DBG_ENCRYPT +---------------------- + +The KVM_SEV_DEBUG_ENCRYPT command can be used by the hypervisor to request the +firmware to encrypt the data at the given memory region. + +Parameters (in): struct kvm_sev_dbg + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_dbg { + __u64 src_uaddr; /* userspace address of data to encrypt */ + __u64 dst_uaddr; /* userspace address of destination */ + __u32 len; /* length of memory region to encrypt */ + }; + +The command returns an error if the guest policy does not allow debugging. + +9. KVM_SEV_LAUNCH_SECRET +------------------------ + +The KVM_SEV_LAUNCH_SECRET command can be used by the hypervisor to inject secret +data after the measurement has been validated by the guest owner. + +Parameters (in): struct kvm_sev_launch_secret + +Returns: 0 on success, -negative on error + +:: + + struct kvm_sev_launch_secret { + __u64 hdr_uaddr; /* userspace address containing the packet header */ + __u32 hdr_len; + + __u64 guest_uaddr; /* the guest memory region where the secret should be injected */ + __u32 guest_len; + + __u64 trans_uaddr; /* the hypervisor memory region which contains the secret */ + __u32 trans_len; + }; + +References +========== + +.. [white-paper] http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf +.. [api-spec] http://support.amd.com/TechDocs/55766_SEV-KM%20API_Specification.pdf +.. [amd-apm] http://support.amd.com/TechDocs/24593.pdf (section 15.34) +.. [kvm-forum] http://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index fc3ae951bc07..792fa8717d13 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1841,6 +1841,7 @@ registers, find a list below: PPC | KVM_REG_PPC_DBSR | 32 PPC | KVM_REG_PPC_TIDR | 64 PPC | KVM_REG_PPC_PSSCR | 64 + PPC | KVM_REG_PPC_DEC_EXPIRY | 64 PPC | KVM_REG_PPC_TM_GPR0 | 64 ... PPC | KVM_REG_PPC_TM_GPR31 | 64 @@ -3403,7 +3404,7 @@ invalid, if invalid pages are written to (e.g. after the end of memory) or if no page table is present for the addresses (e.g. when using hugepages). -4.108 KVM_PPC_GET_CPU_CHAR +4.109 KVM_PPC_GET_CPU_CHAR Capability: KVM_CAP_PPC_GET_CPU_CHAR Architectures: powerpc @@ -3449,6 +3450,57 @@ array bounds check and the array access. These fields use the same bit definitions as the new H_GET_CPU_CHARACTERISTICS hypercall. +4.110 KVM_MEMORY_ENCRYPT_OP + +Capability: basic +Architectures: x86 +Type: system +Parameters: an opaque platform specific structure (in/out) +Returns: 0 on success; -1 on error + +If the platform supports creating encrypted VMs then this ioctl can be used +for issuing platform-specific memory encryption commands to manage those +encrypted VMs. + +Currently, this ioctl is used for issuing Secure Encrypted Virtualization +(SEV) commands on AMD Processors. The SEV commands are defined in +Documentation/virtual/kvm/amd-memory-encryption.txt. + +4.111 KVM_MEMORY_ENCRYPT_REG_REGION + +Capability: basic +Architectures: x86 +Type: system +Parameters: struct kvm_enc_region (in) +Returns: 0 on success; -1 on error + +This ioctl can be used to register a guest memory region which may +contain encrypted data (e.g. guest RAM, SMRAM etc). + +It is used in the SEV-enabled guest. When encryption is enabled, a guest +memory region may contain encrypted data. The SEV memory encryption +engine uses a tweak such that two identical plaintext pages, each at +different locations will have differing ciphertexts. So swapping or +moving ciphertext of those pages will not result in plaintext being +swapped. So relocating (or migrating) physical backing pages for the SEV +guest will require some additional steps. + +Note: The current SEV key management spec does not provide commands to +swap or migrate (move) ciphertext pages. Hence, for now we pin the guest +memory region registered with the ioctl. + +4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION + +Capability: basic +Architectures: x86 +Type: system +Parameters: struct kvm_enc_region (in) +Returns: 0 on success; -1 on error + +This ioctl can be used to unregister the guest memory region registered +with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above. + + 5. The kvm_run structure ------------------------ diff --git a/Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt b/Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt deleted file mode 100644 index 38bca2835278..000000000000 --- a/Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt +++ /dev/null @@ -1,187 +0,0 @@ -KVM/ARM VGIC Forwarded Physical Interrupts -========================================== - -The KVM/ARM code implements software support for the ARM Generic -Interrupt Controller's (GIC's) hardware support for virtualization by -allowing software to inject virtual interrupts to a VM, which the guest -OS sees as regular interrupts. The code is famously known as the VGIC. - -Some of these virtual interrupts, however, correspond to physical -interrupts from real physical devices. One example could be the -architected timer, which itself supports virtualization, and therefore -lets a guest OS program the hardware device directly to raise an -interrupt at some point in time. When such an interrupt is raised, the -host OS initially handles the interrupt and must somehow signal this -event as a virtual interrupt to the guest. Another example could be a -passthrough device, where the physical interrupts are initially handled -by the host, but the device driver for the device lives in the guest OS -and KVM must therefore somehow inject a virtual interrupt on behalf of -the physical one to the guest OS. - -These virtual interrupts corresponding to a physical interrupt on the -host are called forwarded physical interrupts, but are also sometimes -referred to as 'virtualized physical interrupts' and 'mapped interrupts'. - -Forwarded physical interrupts are handled slightly differently compared -to virtual interrupts generated purely by a software emulated device. - - -The HW bit ----------- -Virtual interrupts are signalled to the guest by programming the List -Registers (LRs) on the GIC before running a VCPU. The LR is programmed -with the virtual IRQ number and the state of the interrupt (Pending, -Active, or Pending+Active). When the guest ACKs and EOIs a virtual -interrupt, the LR state moves from Pending to Active, and finally to -inactive. - -The LRs include an extra bit, called the HW bit. When this bit is set, -KVM must also program an additional field in the LR, the physical IRQ -number, to link the virtual with the physical IRQ. - -When the HW bit is set, KVM must EITHER set the Pending OR the Active -bit, never both at the same time. - -Setting the HW bit causes the hardware to deactivate the physical -interrupt on the physical distributor when the guest deactivates the -corresponding virtual interrupt. - - -Forwarded Physical Interrupts Life Cycle ----------------------------------------- - -The state of forwarded physical interrupts is managed in the following way: - - - The physical interrupt is acked by the host, and becomes active on - the physical distributor (*). - - KVM sets the LR.Pending bit, because this is the only way the GICV - interface is going to present it to the guest. - - LR.Pending will stay set as long as the guest has not acked the interrupt. - - LR.Pending transitions to LR.Active on the guest read of the IAR, as - expected. - - On guest EOI, the *physical distributor* active bit gets cleared, - but the LR.Active is left untouched (set). - - KVM clears the LR on VM exits when the physical distributor - active state has been cleared. - -(*): The host handling is slightly more complicated. For some forwarded -interrupts (shared), KVM directly sets the active state on the physical -distributor before entering the guest, because the interrupt is never actually -handled on the host (see details on the timer as an example below). For other -forwarded interrupts (non-shared) the host does not deactivate the interrupt -when the host ISR completes, but leaves the interrupt active until the guest -deactivates it. Leaving the interrupt active is allowed, because Linux -configures the physical GIC with EOIMode=1, which causes EOI operations to -perform a priority drop allowing the GIC to receive other interrupts of the -default priority. - - -Forwarded Edge and Level Triggered PPIs and SPIs ------------------------------------------------- -Forwarded physical interrupts injected should always be active on the -physical distributor when injected to a guest. - -Level-triggered interrupts will keep the interrupt line to the GIC -asserted, typically until the guest programs the device to deassert the -line. This means that the interrupt will remain pending on the physical -distributor until the guest has reprogrammed the device. Since we -always run the VM with interrupts enabled on the CPU, a pending -interrupt will exit the guest as soon as we switch into the guest, -preventing the guest from ever making progress as the process repeats -over and over. Therefore, the active state on the physical distributor -must be set when entering the guest, preventing the GIC from forwarding -the pending interrupt to the CPU. As soon as the guest deactivates the -interrupt, the physical line is sampled by the hardware again and the host -takes a new interrupt if and only if the physical line is still asserted. - -Edge-triggered interrupts do not exhibit the same problem with -preventing guest execution that level-triggered interrupts do. One -option is to not use HW bit at all, and inject edge-triggered interrupts -from a physical device as pure virtual interrupts. But that would -potentially slow down handling of the interrupt in the guest, because a -physical interrupt occurring in the middle of the guest ISR would -preempt the guest for the host to handle the interrupt. Additionally, -if you configure the system to handle interrupts on a separate physical -core from that running your VCPU, you still have to interrupt the VCPU -to queue the pending state onto the LR, even though the guest won't use -this information until the guest ISR completes. Therefore, the HW -bit should always be set for forwarded edge-triggered interrupts. With -the HW bit set, the virtual interrupt is injected and additional -physical interrupts occurring before the guest deactivates the interrupt -simply mark the state on the physical distributor as Pending+Active. As -soon as the guest deactivates the interrupt, the host takes another -interrupt if and only if there was a physical interrupt between injecting -the forwarded interrupt to the guest and the guest deactivating the -interrupt. - -Consequently, whenever we schedule a VCPU with one or more LRs with the -HW bit set, the interrupt must also be active on the physical -distributor. - - -Forwarded LPIs --------------- -LPIs, introduced in GICv3, are always edge-triggered and do not have an -active state. They become pending when a device signal them, and as -soon as they are acked by the CPU, they are inactive again. - -It therefore doesn't make sense, and is not supported, to set the HW bit -for physical LPIs that are forwarded to a VM as virtual interrupts, -typically virtual SPIs. - -For LPIs, there is no other choice than to preempt the VCPU thread if -necessary, and queue the pending state onto the LR. - - -Putting It Together: The Architected Timer ------------------------------------------- -The architected timer is a device that signals interrupts with level -triggered semantics. The timer hardware is directly accessed by VCPUs -which program the timer to fire at some point in time. Each VCPU on a -system programs the timer to fire at different times, and therefore the -hardware is multiplexed between multiple VCPUs. This is implemented by -context-switching the timer state along with each VCPU thread. - -However, this means that a scenario like the following is entirely -possible, and in fact, typical: - -1. KVM runs the VCPU -2. The guest programs the time to fire in T+100 -3. The guest is idle and calls WFI (wait-for-interrupts) -4. The hardware traps to the host -5. KVM stores the timer state to memory and disables the hardware timer -6. KVM schedules a soft timer to fire in T+(100 - time since step 2) -7. KVM puts the VCPU thread to sleep (on a waitqueue) -8. The soft timer fires, waking up the VCPU thread -9. KVM reprograms the timer hardware with the VCPU's values -10. KVM marks the timer interrupt as active on the physical distributor -11. KVM injects a forwarded physical interrupt to the guest -12. KVM runs the VCPU - -Notice that KVM injects a forwarded physical interrupt in step 11 without -the corresponding interrupt having actually fired on the host. That is -exactly why we mark the timer interrupt as active in step 10, because -the active state on the physical distributor is part of the state -belonging to the timer hardware, which is context-switched along with -the VCPU thread. - -If the guest does not idle because it is busy, the flow looks like this -instead: - -1. KVM runs the VCPU -2. The guest programs the time to fire in T+100 -4. At T+100 the timer fires and a physical IRQ causes the VM to exit - (note that this initially only traps to EL2 and does not run the host ISR - until KVM has returned to the host). -5. With interrupts still disabled on the CPU coming back from the guest, KVM - stores the virtual timer state to memory and disables the virtual hw timer. -6. KVM looks at the timer state (in memory) and injects a forwarded physical - interrupt because it concludes the timer has expired. -7. KVM marks the timer interrupt as active on the physical distributor -7. KVM enables the timer, enables interrupts, and runs the VCPU - -Notice that again the forwarded physical interrupt is injected to the -guest without having actually been handled on the host. In this case it -is because the physical interrupt is never actually seen by the host because the -timer is disabled upon guest return, and the virtual forwarded interrupt is -injected on the KVM guest entry path. diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt index 3c65feb83010..dcab6dc11e3b 100644 --- a/Documentation/virtual/kvm/cpuid.txt +++ b/Documentation/virtual/kvm/cpuid.txt @@ -54,6 +54,10 @@ KVM_FEATURE_PV_UNHALT || 7 || guest checks this feature bit || || before enabling paravirtualized || || spinlock support. ------------------------------------------------------------------------------ +KVM_FEATURE_PV_TLB_FLUSH || 9 || guest checks this feature bit + || || before enabling paravirtualized + || || tlb flush. +------------------------------------------------------------------------------ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side || || per-cpu warps are expected in || || kvmclock. diff --git a/Documentation/watchdog/watchdog-parameters.txt b/Documentation/watchdog/watchdog-parameters.txt index 6f9d7b418917..beea975980f6 100644 --- a/Documentation/watchdog/watchdog-parameters.txt +++ b/Documentation/watchdog/watchdog-parameters.txt @@ -40,11 +40,6 @@ margin: Watchdog margin in seconds (default=60) nowayout: Disable watchdog shutdown on close (default=kernel config parameter) ------------------------------------------------- -at32ap700x_wdt: -timeout: Timeout value. Limited to be 1 or 2 seconds. (default=2) -nowayout: Watchdog cannot be stopped once started - (default=kernel config parameter) -------------------------------------------------- at91rm9200_wdt: wdt_time: Watchdog time in seconds. (default=5) nowayout: Watchdog cannot be stopped once started @@ -162,11 +157,6 @@ testmode: Watchdog test mode (1 = no reboot), default=0 nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) ------------------------------------------------- -ixp2000_wdt: -heartbeat: Watchdog heartbeat in seconds (default 60s) -nowayout: Watchdog cannot be stopped once started - (default=kernel config parameter) -------------------------------------------------- ixp4xx_wdt: heartbeat: Watchdog heartbeat in seconds (default 60s) nowayout: Watchdog cannot be stopped once started @@ -381,19 +371,6 @@ timeout: Watchdog timeout in seconds. 1 <= timeout <= 255, default=60. nowayout: Watchdog cannot be stopped once started (default=kernel config parameter) ------------------------------------------------- -w83697hf_wdt: -wdt_io: w83697hf/hg WDT io port (default 0x2e, 0 = autodetect) -timeout: Watchdog timeout in seconds. 1<= timeout <=255 (default=60) -nowayout: Watchdog cannot be stopped once started - (default=kernel config parameter) -early_disable: Watchdog gets disabled at boot time (default=1) -------------------------------------------------- -w83697ug_wdt: -wdt_io: w83697ug/uf WDT io port (default 0x2e) -timeout: Watchdog timeout in seconds. 1<= timeout <=255 (default=60) -nowayout: Watchdog cannot be stopped once started - (default=kernel config parameter) -------------------------------------------------- w83877f_wdt: timeout: Watchdog timeout in seconds. (1<=timeout<=3600, default=30) nowayout: Watchdog cannot be stopped once started diff --git a/MAINTAINERS b/MAINTAINERS index 836f6c7bbf2d..3bdc260e36b7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -903,7 +903,6 @@ L: devel@driverdev.osuosl.org S: Supported F: drivers/staging/android/ion F: drivers/staging/android/uapi/ion.h -F: drivers/staging/android/uapi/ion_test.h AOA (Apple Onboard Audio) ALSA DRIVER M: Johannes Berg <johannes@sipsolutions.net> @@ -1308,7 +1307,6 @@ M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.armlinux.org.uk/~rmk/linux-arm.git clkdev -F: arch/arm/include/asm/clkdev.h F: drivers/clk/clkdev.c ARM/COMPULAB CM-X270/EM-X270 and CM-X300 MACHINE SUPPORT @@ -1360,7 +1358,7 @@ F: Documentation/devicetree/bindings/pinctrl/cortina,gemini-pinctrl.txt F: Documentation/devicetree/bindings/net/cortina,gemini-ethernet.txt F: Documentation/devicetree/bindings/rtc/faraday,ftrtc010.txt F: arch/arm/mach-gemini/ -F: drivers/net/ethernet/cortina/gemini/* +F: drivers/net/ethernet/cortina/ F: drivers/pinctrl/pinctrl-gemini.c F: drivers/rtc/rtc-ftrtc010.c @@ -1737,9 +1735,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-oxnas@lists.tuxfamily.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-oxnas/ -F: arch/arm/boot/dts/ox8*.dtsi -F: arch/arm/boot/dts/wd-mbwe.dts -F: arch/arm/boot/dts/cloudengines-pogoplug-series-3.dts +F: arch/arm/boot/dts/ox8*.dts* N: oxnas ARM/PALM TREO SUPPORT @@ -1747,8 +1743,7 @@ M: Tomas Cech <sleep_walker@suse.com> L: linux-arm-kernel@lists.infradead.org W: http://hackndev.com S: Maintained -F: arch/arm/mach-pxa/include/mach/palmtreo.h -F: arch/arm/mach-pxa/palmtreo.c +F: arch/arm/mach-pxa/palmtreo.* ARM/PALMTX,PALMT5,PALMLD,PALMTE2,PALMTC SUPPORT M: Marek Vasut <marek.vasut@gmail.com> @@ -1757,12 +1752,10 @@ W: http://hackndev.com S: Maintained F: arch/arm/mach-pxa/include/mach/palmtx.h F: arch/arm/mach-pxa/palmtx.c -F: arch/arm/mach-pxa/include/mach/palmt5.h -F: arch/arm/mach-pxa/palmt5.c +F: arch/arm/mach-pxa/palmt5.* F: arch/arm/mach-pxa/include/mach/palmld.h F: arch/arm/mach-pxa/palmld.c -F: arch/arm/mach-pxa/include/mach/palmte2.h -F: arch/arm/mach-pxa/palmte2.c +F: arch/arm/mach-pxa/palmte2.* F: arch/arm/mach-pxa/include/mach/palmtc.h F: arch/arm/mach-pxa/palmtc.c @@ -1771,8 +1764,7 @@ M: Sergey Lapin <slapin@ossfans.org> L: linux-arm-kernel@lists.infradead.org W: http://hackndev.com S: Maintained -F: arch/arm/mach-pxa/include/mach/palmz72.h -F: arch/arm/mach-pxa/palmz72.c +F: arch/arm/mach-pxa/palmz72.* ARM/PLEB SUPPORT M: Peter Chubb <pleb@gelato.unsw.edu.au> @@ -1801,7 +1793,6 @@ F: drivers/clk/qcom/ F: drivers/dma/qcom/ F: drivers/soc/qcom/ F: drivers/spi/spi-qup.c -F: drivers/tty/serial/msm_serial.h F: drivers/tty/serial/msm_serial.c F: drivers/*/pm8???-* F: drivers/mfd/ssbi.c @@ -3567,7 +3558,7 @@ F: drivers/media/platform/coda/ COMMON CLK FRAMEWORK M: Michael Turquette <mturquette@baylibre.com> -M: Stephen Boyd <sboyd@codeaurora.org> +M: Stephen Boyd <sboyd@kernel.org> L: linux-clk@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-clk/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git @@ -6001,6 +5992,12 @@ L: linux-input@vger.kernel.org S: Maintained F: drivers/input/touchscreen/goodix.c +GPD POCKET FAN DRIVER +M: Hans de Goede <hdegoede@redhat.com> +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: drivers/platform/x86/gpd-pocket-fan.c + GPIO ACPI SUPPORT M: Mika Westerberg <mika.westerberg@linux.intel.com> M: Andy Shevchenko <andriy.shevchenko@linux.intel.com> @@ -7751,7 +7748,9 @@ F: arch/powerpc/kernel/kvm* KERNEL VIRTUAL MACHINE for s390 (KVM/s390) M: Christian Borntraeger <borntraeger@de.ibm.com> -M: Cornelia Huck <cohuck@redhat.com> +M: Janosch Frank <frankja@linux.vnet.ibm.com> +R: David Hildenbrand <david@redhat.com> +R: Cornelia Huck <cohuck@redhat.com> L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git @@ -8939,12 +8938,13 @@ W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlxfw/ -MELLANOX MLX CPLD HOTPLUG DRIVER +MELLANOX HARDWARE PLATFORM SUPPORT +M: Andy Shevchenko <andy@infradead.org> +M: Darren Hart <dvhart@infradead.org> M: Vadim Pasternak <vadimp@mellanox.com> L: platform-driver-x86@vger.kernel.org S: Supported -F: drivers/platform/x86/mlxcpld-hotplug.c -F: include/linux/platform_data/mlxcpld-hotplug.h +F: drivers/platform/mellanox/ MELLANOX MLX4 core VPI driver M: Tariq Toukan <tariqt@mellanox.com> @@ -9018,6 +9018,7 @@ L: linux-kernel@vger.kernel.org S: Supported F: kernel/sched/membarrier.c F: include/uapi/linux/membarrier.h +F: arch/powerpc/include/asm/membarrier.h MEMORY MANAGEMENT L: linux-mm@kvack.org @@ -9189,6 +9190,7 @@ S: Supported F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ F: arch/mips/ +F: drivers/platform/mips/ MIPS BOSTON DEVELOPMENT BOARD M: Paul Burton <paul.burton@mips.com> @@ -9216,6 +9218,25 @@ F: arch/mips/include/asm/mach-loongson32/ F: drivers/*/*loongson1* F: drivers/*/*/*loongson1* +MIPS/LOONGSON2 ARCHITECTURE +M: Jiaxun Yang <jiaxun.yang@flygoat.com> +L: linux-mips@linux-mips.org +S: Maintained +F: arch/mips/loongson64/*{2e/2f}* +F: arch/mips/include/asm/mach-loongson64/ +F: drivers/*/*loongson2* +F: drivers/*/*/*loongson2* + +MIPS/LOONGSON3 ARCHITECTURE +M: Huacai Chen <chenhc@lemote.com> +L: linux-mips@linux-mips.org +S: Maintained +F: arch/mips/loongson64/ +F: arch/mips/include/asm/mach-loongson64/ +F: drivers/platform/mips/cpu_hwmon.c +F: drivers/*/*loongson3* +F: drivers/*/*/*loongson3* + MIPS RINT INSTRUCTION EMULATION M: Aleksandar Markovic <aleksandar.markovic@mips.com> L: linux-mips@linux-mips.org @@ -9261,7 +9282,6 @@ F: drivers/media/dvb-frontends/mn88473* MODULE SUPPORT M: Jessica Yu <jeyu@kernel.org> -M: Rusty Russell <rusty@rustcorp.com.au> T: git git://git.kernel.org/pub/scm/linux/kernel/git/jeyu/linux.git modules-next S: Maintained F: include/linux/module.h @@ -10276,7 +10296,7 @@ F: include/uapi/linux/openvswitch.h OPERATING PERFORMANCE POINTS (OPP) M: Viresh Kumar <vireshk@kernel.org> M: Nishanth Menon <nm@ti.com> -M: Stephen Boyd <sboyd@codeaurora.org> +M: Stephen Boyd <sboyd@kernel.org> L: linux-pm@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git @@ -10313,7 +10333,8 @@ F: fs/ocfs2/ ORANGEFS FILESYSTEM M: Mike Marshall <hubcap@omnibond.com> -L: pvfs2-developers@beowulf-underground.org (subscribers-only) +R: Martin Brandenburg <martin@omnibond.com> +L: devel@lists.orangefs.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux.git S: Supported F: fs/orangefs/ @@ -10411,7 +10432,6 @@ F: Documentation/parport*.txt PARAVIRT_OPS INTERFACE M: Juergen Gross <jgross@suse.com> M: Alok Kataria <akataria@vmware.com> -M: Rusty Russell <rusty@rustcorp.com.au> L: virtualization@lists.linux-foundation.org S: Supported F: Documentation/virtual/paravirt_ops.txt @@ -10782,11 +10802,9 @@ S: Maintained F: drivers/pci/dwc/*spear* PCMCIA SUBSYSTEM -P: Linux PCMCIA Team -L: linux-pcmcia@lists.infradead.org -W: http://lists.infradead.org/mailman/listinfo/linux-pcmcia +M: Dominik Brodowski <linux@dominikbrodowski.net> T: git git://git.kernel.org/pub/scm/linux/kernel/git/brodo/pcmcia.git -S: Maintained +S: Odd Fixes F: Documentation/pcmcia/ F: tools/pcmcia/ F: drivers/pcmcia/ @@ -11587,6 +11605,13 @@ S: Maintained F: Documentation/blockdev/ramdisk.txt F: drivers/block/brd.c +RANCHU VIRTUAL BOARD FOR MIPS +M: Miodrag Dinic <miodrag.dinic@mips.com> +L: linux-mips@linux-mips.org +S: Supported +F: arch/mips/generic/board-ranchu.c +F: arch/mips/configs/generic/board-ranchu.config + RANDOM NUMBER DRIVER M: "Theodore Ts'o" <tytso@mit.edu> S: Maintained @@ -12003,6 +12028,7 @@ F: drivers/pci/hotplug/s390_pci_hpc.c S390 VFIO-CCW DRIVER M: Cornelia Huck <cohuck@redhat.com> M: Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com> +M: Halil Pasic <pasic@linux.vnet.ibm.com> L: linux-s390@vger.kernel.org L: kvm@vger.kernel.org S: Supported @@ -13012,7 +13038,7 @@ F: Documentation/networking/spider_net.txt F: drivers/net/ethernet/toshiba/spider_net* SPMI SUBSYSTEM -R: Stephen Boyd <sboyd@codeaurora.org> +R: Stephen Boyd <sboyd@kernel.org> L: linux-arm-msm@vger.kernel.org F: Documentation/devicetree/bindings/spmi/ F: drivers/spmi/ @@ -13319,7 +13345,6 @@ F: include/linux/platform_data/dma-dw.h F: drivers/dma/dw/ SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER -M: Jie Deng <jiedeng@synopsys.com> M: Jose Abreu <Jose.Abreu@synopsys.com> L: netdev@vger.kernel.org S: Supported @@ -13898,7 +13923,7 @@ F: include/linux/usb/tilegx.h TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER M: John Stultz <john.stultz@linaro.org> M: Thomas Gleixner <tglx@linutronix.de> -R: Stephen Boyd <sboyd@codeaurora.org> +R: Stephen Boyd <sboyd@kernel.org> L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core S: Supported @@ -14966,8 +14991,8 @@ S: Maintained F: drivers/input/tablet/wacom_serial4.c WATCHDOG DEVICE DRIVERS -M: Wim Van Sebroeck <wim@iguana.be> -R: Guenter Roeck <linux@roeck-us.net> +M: Wim Van Sebroeck <wim@linux-watchdog.org> +M: Guenter Roeck <linux@roeck-us.net> L: linux-watchdog@vger.kernel.org W: http://www.linux-watchdog.org/ T: git git://www.linux-watchdog.org/linux-watchdog.git @@ -15134,7 +15159,7 @@ X86 PLATFORM DRIVERS M: Darren Hart <dvhart@infradead.org> M: Andy Shevchenko <andy@infradead.org> L: platform-driver-x86@vger.kernel.org -T: git git://git.infradead.org/users/dvhart/linux-platform-drivers-x86.git +T: git git://git.infradead.org/linux-platform-drivers-x86.git S: Maintained F: drivers/platform/x86/ F: drivers/platform/olpc/ @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 -PATCHLEVEL = 15 +PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Fearless Coyote # *DOCUMENTATION* @@ -434,7 +434,8 @@ export MAKE LEX YACC AWK GENKSYMS INSTALLKERNEL PERL PYTHON UTS_MACHINE export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS -export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE CFLAGS_KASAN CFLAGS_UBSAN +export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE +export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE CFLAGS_UBSAN export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL @@ -679,6 +680,10 @@ endif # This selects the stack protector compiler flag. Testing it is delayed # until after .config has been reprocessed, in the prepare-compiler-check # target. +ifdef CONFIG_CC_STACKPROTECTOR_AUTO + stackp-flag := $(call cc-option,-fstack-protector-strong,$(call cc-option,-fstack-protector)) + stackp-name := AUTO +else ifdef CONFIG_CC_STACKPROTECTOR_REGULAR stackp-flag := -fstack-protector stackp-name := REGULAR @@ -687,20 +692,43 @@ ifdef CONFIG_CC_STACKPROTECTOR_STRONG stackp-flag := -fstack-protector-strong stackp-name := STRONG else + # If either there is no stack protector for this architecture or + # CONFIG_CC_STACKPROTECTOR_NONE is selected, we're done, and $(stackp-name) + # is empty, skipping all remaining stack protector tests. + # # Force off for distro compilers that enable stack protector by default. - stackp-flag := $(call cc-option, -fno-stack-protector) + KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector) +endif endif endif # Find arch-specific stack protector compiler sanity-checking script. -ifdef CONFIG_CC_STACKPROTECTOR +ifdef stackp-name +ifneq ($(stackp-flag),) stackp-path := $(srctree)/scripts/gcc-$(SRCARCH)_$(BITS)-has-stack-protector.sh stackp-check := $(wildcard $(stackp-path)) + # If the wildcard test matches a test script, run it to check functionality. + ifdef stackp-check + ifneq ($(shell $(CONFIG_SHELL) $(stackp-check) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y) + stackp-broken := y + endif + endif + ifndef stackp-broken + # If the stack protector is functional, enable code that depends on it. + KBUILD_CPPFLAGS += -DCONFIG_CC_STACKPROTECTOR + # Either we've already detected the flag (for AUTO) or we'll fail the + # build in the prepare-compiler-check rule (for specific flag). + KBUILD_CFLAGS += $(stackp-flag) + else + # We have to make sure stack protector is unconditionally disabled if + # the compiler is broken (in case we're going to continue the build in + # AUTO mode). + KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector) + endif +endif endif -KBUILD_CFLAGS += $(stackp-flag) ifeq ($(cc-name),clang) KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable) KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) @@ -718,9 +746,9 @@ else # These warnings generated too much noise in a regular build. # Use make W=1 to enable them (see scripts/Makefile.extrawarn) KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) endif +KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls else @@ -1091,14 +1119,25 @@ PHONY += prepare-compiler-check prepare-compiler-check: FORCE # Make sure compiler supports requested stack protector flag. ifdef stackp-name + # Warn about CONFIG_CC_STACKPROTECTOR_AUTO having found no option. + ifeq ($(stackp-flag),) + @echo CONFIG_CC_STACKPROTECTOR_$(stackp-name): \ + Compiler does not support any known stack-protector >&2 + else + # Fail if specifically requested stack protector is missing. ifeq ($(call cc-option, $(stackp-flag)),) @echo Cannot use CONFIG_CC_STACKPROTECTOR_$(stackp-name): \ $(stackp-flag) not supported by compiler >&2 && exit 1 endif + endif endif -# Make sure compiler does not have buggy stack-protector support. -ifdef stackp-check - ifneq ($(shell $(CONFIG_SHELL) $(stackp-check) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y) +# Make sure compiler does not have buggy stack-protector support. If a +# specific stack-protector was requested, fail the build, otherwise warn. +ifdef stackp-broken + ifeq ($(stackp-name),AUTO) + @echo CONFIG_CC_STACKPROTECTOR_$(stackp-name): \ + $(stackp-flag) available but compiler is broken: disabling >&2 + else @echo Cannot use CONFIG_CC_STACKPROTECTOR_$(stackp-name): \ $(stackp-flag) available but compiler is broken >&2 && exit 1 endif diff --git a/arch/Kconfig b/arch/Kconfig index 467dfa35bf96..76c0b54443b1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -538,16 +538,10 @@ config HAVE_CC_STACKPROTECTOR - its compiler supports the -fstack-protector option - it has implemented a stack canary (e.g. __stack_chk_guard) -config CC_STACKPROTECTOR - def_bool n - help - Set when a stack-protector mode is enabled, so that the build - can enable kernel-side support for the GCC feature. - choice prompt "Stack Protector buffer overflow detection" depends on HAVE_CC_STACKPROTECTOR - default CC_STACKPROTECTOR_NONE + default CC_STACKPROTECTOR_AUTO help This option turns on the "stack-protector" GCC feature. This feature puts, at the beginning of functions, a canary value on @@ -564,7 +558,6 @@ config CC_STACKPROTECTOR_NONE config CC_STACKPROTECTOR_REGULAR bool "Regular" - select CC_STACKPROTECTOR help Functions will have the stack-protector canary logic added if they have an 8-byte or larger character array on the stack. @@ -578,7 +571,6 @@ config CC_STACKPROTECTOR_REGULAR config CC_STACKPROTECTOR_STRONG bool "Strong" - select CC_STACKPROTECTOR help Functions will have the stack-protector canary logic added in any of the following conditions: @@ -596,6 +588,12 @@ config CC_STACKPROTECTOR_STRONG about 20% of all kernel functions, which increases the kernel code size by about 2%. +config CC_STACKPROTECTOR_AUTO + bool "Automatic" + help + If the compiler supports it, the best available stack-protector + option will be chosen. + endchoice config THIN_ARCHIVES diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h index ce5ee762ed66..4cab9bb823fb 100644 --- a/arch/arm/include/asm/bitops.h +++ b/arch/arm/include/asm/bitops.h @@ -338,6 +338,7 @@ static inline int find_next_bit_le(const void *p, int size, int offset) #endif +#include <asm-generic/bitops/find.h> #include <asm-generic/bitops/le.h> /* diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 3d22eb87f919..9003bd19cb70 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -131,7 +131,7 @@ static inline bool mode_has_spsr(struct kvm_vcpu *vcpu) static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu) { unsigned long cpsr_mode = vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr & MODE_MASK; - return cpsr_mode > USR_MODE;; + return cpsr_mode > USR_MODE; } static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index acbf9ec7b396..248b930563e5 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -48,6 +48,8 @@ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) +DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); + u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode); int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); @@ -306,4 +308,11 @@ static inline void kvm_fpsimd_flush_cpu_state(void) {} static inline void kvm_arm_vhe_guest_enter(void) {} static inline void kvm_arm_vhe_guest_exit(void) {} + +static inline bool kvm_arm_harden_branch_predictor(void) +{ + /* No way to detect it yet, pretend it is not there. */ + return false; +} + #endif /* __ARM_KVM_HOST_H__ */ diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h index ab20ffa8b9e7..1ab8329e9ff7 100644 --- a/arch/arm/include/asm/kvm_hyp.h +++ b/arch/arm/include/asm/kvm_hyp.h @@ -21,7 +21,6 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/cp15.h> -#include <asm/kvm_mmu.h> #include <asm/vfp.h> #define __hyp_text __section(.hyp.text) notrace @@ -69,6 +68,8 @@ #define HIFAR __ACCESS_CP15(c6, 4, c0, 2) #define HPFAR __ACCESS_CP15(c6, 4, c0, 4) #define ICIALLUIS __ACCESS_CP15(c7, 0, c1, 0) +#define BPIALLIS __ACCESS_CP15(c7, 0, c1, 6) +#define ICIMVAU __ACCESS_CP15(c7, 0, c5, 1) #define ATS1CPR __ACCESS_CP15(c7, 0, c8, 0) #define TLBIALLIS __ACCESS_CP15(c8, 0, c3, 0) #define TLBIALL __ACCESS_CP15(c8, 0, c7, 0) diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index a2d176a308bd..de1b919404e4 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -37,6 +37,8 @@ #include <linux/highmem.h> #include <asm/cacheflush.h> +#include <asm/cputype.h> +#include <asm/kvm_hyp.h> #include <asm/pgalloc.h> #include <asm/stage2_pgtable.h> @@ -83,6 +85,18 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd) return pmd; } +static inline pte_t kvm_s2pte_mkexec(pte_t pte) +{ + pte_val(pte) &= ~L_PTE_XN; + return pte; +} + +static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) +{ + pmd_val(pmd) &= ~PMD_SECT_XN; + return pmd; +} + static inline void kvm_set_s2pte_readonly(pte_t *pte) { pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY; @@ -93,6 +107,11 @@ static inline bool kvm_s2pte_readonly(pte_t *pte) return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY; } +static inline bool kvm_s2pte_exec(pte_t *pte) +{ + return !(pte_val(*pte) & L_PTE_XN); +} + static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) { pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY; @@ -103,6 +122,11 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY; } +static inline bool kvm_s2pmd_exec(pmd_t *pmd) +{ + return !(pmd_val(*pmd) & PMD_SECT_XN); +} + static inline bool kvm_page_empty(void *ptr) { struct page *ptr_page = virt_to_page(ptr); @@ -126,10 +150,36 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_cp15(vcpu, c1_SCTLR) & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, - kvm_pfn_t pfn, - unsigned long size) +static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) +{ + /* + * Clean the dcache to the Point of Coherency. + * + * We need to do this through a kernel mapping (using the + * user-space mapping has proved to be the wrong + * solution). For that, we need to kmap one page at a time, + * and iterate over the range. + */ + + VM_BUG_ON(size & ~PAGE_MASK); + + while (size) { + void *va = kmap_atomic_pfn(pfn); + + kvm_flush_dcache_to_poc(va, PAGE_SIZE); + + size -= PAGE_SIZE; + pfn++; + + kunmap_atomic(va); + } +} + +static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn, + unsigned long size) { + u32 iclsz; + /* * If we are going to insert an instruction page and the icache is * either VIPT or PIPT, there is a potential problem where the host @@ -141,23 +191,40 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, * * VIVT caches are tagged using both the ASID and the VMID and doesn't * need any kind of flushing (DDI 0406C.b - Page B3-1392). - * - * We need to do this through a kernel mapping (using the - * user-space mapping has proved to be the wrong - * solution). For that, we need to kmap one page at a time, - * and iterate over the range. */ VM_BUG_ON(size & ~PAGE_MASK); + if (icache_is_vivt_asid_tagged()) + return; + + if (!icache_is_pipt()) { + /* any kind of VIPT cache */ + __flush_icache_all(); + return; + } + + /* + * CTR IminLine contains Log2 of the number of words in the + * cache line, so we can get the number of words as + * 2 << (IminLine - 1). To get the number of bytes, we + * multiply by 4 (the number of bytes in a 32-bit word), and + * get 4 << (IminLine). + */ + iclsz = 4 << (read_cpuid(CPUID_CACHETYPE) & 0xf); + while (size) { void *va = kmap_atomic_pfn(pfn); + void *end = va + PAGE_SIZE; + void *addr = va; - kvm_flush_dcache_to_poc(va, PAGE_SIZE); + do { + write_sysreg(addr, ICIMVAU); + addr += iclsz; + } while (addr < end); - if (icache_is_pipt()) - __cpuc_coherent_user_range((unsigned long)va, - (unsigned long)va + PAGE_SIZE); + dsb(ishst); + isb(); size -= PAGE_SIZE; pfn++; @@ -165,9 +232,11 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, kunmap_atomic(va); } - if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) { - /* any kind of VIPT cache */ - __flush_icache_all(); + /* Check if we need to invalidate the BTB */ + if ((read_cpuid_ext(CPUID_EXT_MMFR1) >> 28) != 4) { + write_sysreg(0, BPIALLIS); + dsb(ishst); + isb(); } } diff --git a/arch/arm/include/asm/kvm_psci.h b/arch/arm/include/asm/kvm_psci.h deleted file mode 100644 index 6bda945d31fa..000000000000 --- a/arch/arm/include/asm/kvm_psci.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Copyright (C) 2012 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef __ARM_KVM_PSCI_H__ -#define __ARM_KVM_PSCI_H__ - -#define KVM_ARM_PSCI_0_1 1 -#define KVM_ARM_PSCI_0_2 2 - -int kvm_psci_version(struct kvm_vcpu *vcpu); -int kvm_psci_call(struct kvm_vcpu *vcpu); - -#endif /* __ARM_KVM_PSCI_H__ */ diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 150ece66ddf3..a757401129f9 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -102,8 +102,8 @@ extern pgprot_t pgprot_s2_device; #define PAGE_HYP_EXEC _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY) #define PAGE_HYP_RO _MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN) #define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP) -#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY) -#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY) +#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY | L_PTE_XN) +#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY | L_PTE_XN) #define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE) #define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN) diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index cf8bf6bf87c4..910bd8dabb3c 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -21,7 +21,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> #include <asm/kvm_mmu.h> -#include <asm/kvm_psci.h> +#include <kvm/arm_psci.h> #include <trace/events/kvm.h> #include "trace.h" @@ -36,9 +36,9 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vcpu_hvc_get_imm(vcpu)); vcpu->stat.hvc_exit_stat++; - ret = kvm_psci_call(vcpu); + ret = kvm_hvc_call_handler(vcpu); if (ret < 0) { - kvm_inject_undefined(vcpu); + vcpu_set_reg(vcpu, 0, ~0UL); return 1; } @@ -47,7 +47,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_inject_undefined(vcpu); + /* + * "If an SMC instruction executed at Non-secure EL1 is + * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a + * Trap exception, not a Secure Monitor Call exception [...]" + * + * We need to advance the PC after the trap, as it would + * otherwise return to the same address... + */ + vcpu_set_reg(vcpu, 0, ~0UL); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 1; } diff --git a/arch/arm/kvm/hyp/switch.c b/arch/arm/kvm/hyp/switch.c index 330c9ce34ba5..ae45ae96aac2 100644 --- a/arch/arm/kvm/hyp/switch.c +++ b/arch/arm/kvm/hyp/switch.c @@ -18,6 +18,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> __asm__(".arch_extension virt"); diff --git a/arch/arm/kvm/hyp/tlb.c b/arch/arm/kvm/hyp/tlb.c index 6d810af2d9fd..c0edd450e104 100644 --- a/arch/arm/kvm/hyp/tlb.c +++ b/arch/arm/kvm/hyp/tlb.c @@ -19,6 +19,7 @@ */ #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> /** * Flush per-VMID TLBs diff --git a/arch/arm/mach-vt8500/Kconfig b/arch/arm/mach-vt8500/Kconfig index 1156a585dafc..8841199058ea 100644 --- a/arch/arm/mach-vt8500/Kconfig +++ b/arch/arm/mach-vt8500/Kconfig @@ -13,7 +13,6 @@ config ARCH_WM8505 depends on ARCH_MULTI_V5 select ARCH_VT8500 select CPU_ARM926T - help config ARCH_WM8750 bool "WonderMedia WM8750" diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 53612879fe56..7381eeb7ef8e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -16,6 +16,7 @@ config ARM64 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA select ARCH_HAS_KCOV + select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3873dd7b5a32..3c78835bba94 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -116,6 +116,24 @@ .endm /* + * Value prediction barrier + */ + .macro csdb + hint #20 + .endm + +/* + * Sanitise a 64-bit bounded index wrt speculation, returning zero if out + * of bounds. + */ + .macro mask_nospec64, idx, limit, tmp + sub \tmp, \idx, \limit + bic \tmp, \tmp, \idx + and \idx, \idx, \tmp, asr #63 + csdb + .endm + +/* * NOP sequence */ .macro nops, num @@ -418,6 +436,27 @@ alternative_endif .endm /* + * Macro to perform an instruction cache maintenance for the interval + * [start, end) + * + * start, end: virtual addresses describing the region + * label: A label to branch to on user fault. + * Corrupts: tmp1, tmp2 + */ + .macro invalidate_icache_by_line start, end, tmp1, tmp2, label + icache_line_size \tmp1, \tmp2 + sub \tmp2, \tmp1, #1 + bic \tmp2, \start, \tmp2 +9997: +USER(\label, ic ivau, \tmp2) // invalidate I line PoU + add \tmp2, \tmp2, \tmp1 + cmp \tmp2, \end + b.lo 9997b + dsb ish + isb + .endm + +/* * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present */ .macro reset_pmuserenr_el0, tmpreg @@ -514,7 +553,7 @@ alternative_endif * phys: physical address, preserved * ttbr: returns the TTBR value */ - .macro phys_to_ttbr, phys, ttbr + .macro phys_to_ttbr, ttbr, phys #ifdef CONFIG_ARM64_PA_BITS_52 orr \ttbr, \phys, \phys, lsr #46 and \ttbr, \ttbr, #TTBR_BADDR_MASK_52 @@ -523,6 +562,29 @@ alternative_endif #endif .endm + .macro phys_to_pte, pte, phys +#ifdef CONFIG_ARM64_PA_BITS_52 + /* + * We assume \phys is 64K aligned and this is guaranteed by only + * supporting this configuration with 64K pages. + */ + orr \pte, \phys, \phys, lsr #36 + and \pte, \pte, #PTE_ADDR_MASK +#else + mov \pte, \phys +#endif + .endm + + .macro pte_to_phys, phys, pte +#ifdef CONFIG_ARM64_PA_BITS_52 + ubfiz \phys, \pte, #(48 - 16 - 12), #16 + bfxil \phys, \pte, #16, #32 + lsl \phys, \phys, #16 +#else + and \phys, \pte, #PTE_ADDR_MASK +#endif + .endm + /** * Errata workaround prior to disable MMU. Insert an ISB immediately prior * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 77651c49ef44..f11518af96a9 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -32,6 +32,7 @@ #define dsb(opt) asm volatile("dsb " #opt : : : "memory") #define psb_csync() asm volatile("hint #17" : : : "memory") +#define csdb() asm volatile("hint #20" : : : "memory") #define mb() dsb(sy) #define rmb() dsb(ld) @@ -40,6 +41,27 @@ #define dma_rmb() dmb(oshld) #define dma_wmb() dmb(oshst) +/* + * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz + * and 0 otherwise. + */ +#define array_index_mask_nospec array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long idx, + unsigned long sz) +{ + unsigned long mask; + + asm volatile( + " cmp %1, %2\n" + " sbc %0, xzr, xzr\n" + : "=r" (mask) + : "r" (idx), "Ir" (sz) + : "cc"); + + csdb(); + return mask; +} + #define __smp_mb() dmb(ish) #define __smp_rmb() dmb(ishld) #define __smp_wmb() dmb(ishst) diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 955130762a3c..bef9f418f089 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -52,6 +52,12 @@ * - start - virtual start address * - end - virtual end address * + * invalidate_icache_range(start, end) + * + * Invalidate the I-cache in the region described by start, end. + * - start - virtual start address + * - end - virtual end address + * * __flush_cache_user_range(start, end) * * Ensure coherency between the I-cache and the D-cache in the @@ -66,6 +72,7 @@ * - size - region size */ extern void flush_icache_range(unsigned long start, unsigned long end); +extern int invalidate_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); extern void __inval_dcache_area(void *addr, size_t len); extern void __clean_dcache_area_poc(void *addr, size_t len); diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 5bb2fd4674e7..07fe2479d310 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -48,9 +48,10 @@ do { \ } while (0) static inline int -arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { int oldval = 0, ret, tmp; + u32 __user *uaddr = __uaccess_mask_ptr(_uaddr); pagefault_disable(); @@ -88,15 +89,17 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, u32 oldval, u32 newval) { int ret = 0; u32 val, tmp; + u32 __user *uaddr; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + if (!access_ok(VERIFY_WRITE, _uaddr, sizeof(u32))) return -EFAULT; + uaddr = __uaccess_mask_ptr(_uaddr); uaccess_enable(); asm volatile("// futex_atomic_cmpxchg_inatomic\n" " prfm pstl1strm, %2\n" diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index e266f80e45b7..8758bb008436 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -12,7 +12,8 @@ /* * KASAN_SHADOW_START: beginning of the kernel virtual addresses. - * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/8 of kernel virtual addresses. + * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses, + * where N = (1 << KASAN_SHADOW_SCALE_SHIFT). */ #define KASAN_SHADOW_START (VA_START) #define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) @@ -20,14 +21,16 @@ /* * This value is used to map an address to the corresponding shadow * address by the following formula: - * shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET; + * shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET * - * (1 << 61) shadow addresses - [KASAN_SHADOW_OFFSET,KASAN_SHADOW_END] - * cover all 64-bits of virtual addresses. So KASAN_SHADOW_OFFSET - * should satisfy the following equation: - * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - (1ULL << 61) + * (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) shadow addresses that lie in range + * [KASAN_SHADOW_OFFSET, KASAN_SHADOW_END) cover all 64-bits of virtual + * addresses. So KASAN_SHADOW_OFFSET should satisfy the following equation: + * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - + * (1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT)) */ -#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << (64 - 3))) +#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \ + (64 - KASAN_SHADOW_SCALE_SHIFT))) void kasan_init(void); void kasan_copy_shadow(pgd_t *pgdir); diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 82386e860dd2..a780f6714b44 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -123,16 +123,8 @@ /* * Initial memory map attributes. */ -#define _SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) -#define _SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) - -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define SWAPPER_PTE_FLAGS (_SWAPPER_PTE_FLAGS | PTE_NG) -#define SWAPPER_PMD_FLAGS (_SWAPPER_PMD_FLAGS | PMD_SECT_NG) -#else -#define SWAPPER_PTE_FLAGS _SWAPPER_PTE_FLAGS -#define SWAPPER_PMD_FLAGS _SWAPPER_PMD_FLAGS -#endif +#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) +#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) #if ARM64_SWAPPER_USES_SECTION_MAPS #define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 4485ae8e98de..596f8e414a4c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -48,6 +48,8 @@ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) +DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); + int __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext); @@ -415,4 +417,10 @@ static inline void kvm_arm_vhe_guest_exit(void) { local_daif_restore(DAIF_PROCCTX_NOIRQ); } + +static inline bool kvm_arm_harden_branch_predictor(void) +{ + return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR); +} + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 08d3bb66c8b7..f26f9cd70c72 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -20,7 +20,6 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> -#include <asm/kvm_mmu.h> #include <asm/sysreg.h> #define __hyp_text __section(.hyp.text) notrace diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 72e279dbae5f..9679067a1574 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -173,6 +173,18 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd) return pmd; } +static inline pte_t kvm_s2pte_mkexec(pte_t pte) +{ + pte_val(pte) &= ~PTE_S2_XN; + return pte; +} + +static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) +{ + pmd_val(pmd) &= ~PMD_S2_XN; + return pmd; +} + static inline void kvm_set_s2pte_readonly(pte_t *pte) { pteval_t old_pteval, pteval; @@ -191,6 +203,11 @@ static inline bool kvm_s2pte_readonly(pte_t *pte) return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY; } +static inline bool kvm_s2pte_exec(pte_t *pte) +{ + return !(pte_val(*pte) & PTE_S2_XN); +} + static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) { kvm_set_s2pte_readonly((pte_t *)pmd); @@ -201,6 +218,11 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) return kvm_s2pte_readonly((pte_t *)pmd); } +static inline bool kvm_s2pmd_exec(pmd_t *pmd) +{ + return !(pmd_val(*pmd) & PMD_S2_XN); +} + static inline bool kvm_page_empty(void *ptr) { struct page *ptr_page = virt_to_page(ptr); @@ -230,21 +252,25 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, - kvm_pfn_t pfn, - unsigned long size) +static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) { void *va = page_address(pfn_to_page(pfn)); kvm_flush_dcache_to_poc(va, size); +} +static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn, + unsigned long size) +{ if (icache_is_aliasing()) { /* any kind of VIPT cache */ __flush_icache_all(); } else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) { /* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */ - flush_icache_range((unsigned long)va, - (unsigned long)va + size); + void *va = page_address(pfn_to_page(pfn)); + + invalidate_icache_range((unsigned long)va, + (unsigned long)va + size); } } diff --git a/arch/arm64/include/asm/kvm_psci.h b/arch/arm64/include/asm/kvm_psci.h deleted file mode 100644 index bc39e557c56c..000000000000 --- a/arch/arm64/include/asm/kvm_psci.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef __ARM64_KVM_PSCI_H__ -#define __ARM64_KVM_PSCI_H__ - -#define KVM_ARM_PSCI_0_1 1 -#define KVM_ARM_PSCI_0_2 2 - -int kvm_psci_version(struct kvm_vcpu *vcpu); -int kvm_psci_call(struct kvm_vcpu *vcpu); - -#endif /* __ARM64_KVM_PSCI_H__ */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index d4bae7d6e0d8..50fa96a49792 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -85,7 +85,8 @@ * stack size when KASAN is in use. */ #ifdef CONFIG_KASAN -#define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - 3)) +#define KASAN_SHADOW_SCALE_SHIFT 3 +#define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_THREAD_SHIFT 1 #else #define KASAN_SHADOW_SIZE (0) diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index f42836da8723..cdfe3e657a9e 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -187,9 +187,11 @@ */ #define PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[2:1] */ #define PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ +#define PTE_S2_XN (_AT(pteval_t, 2) << 53) /* XN[1:0] */ #define PMD_S2_RDONLY (_AT(pmdval_t, 1) << 6) /* HAP[2:1] */ #define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ +#define PMD_S2_XN (_AT(pmdval_t, 2) << 53) /* XN[1:0] */ /* * Memory Attribute override for Stage-2 (MemAttr[3:0]) diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 22a926825e3f..108ecad7acc5 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -37,13 +37,11 @@ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define PROT_DEFAULT (_PROT_DEFAULT | PTE_NG) -#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_SECT_NG) -#else -#define PROT_DEFAULT _PROT_DEFAULT -#define PROT_SECT_DEFAULT _PROT_SECT_DEFAULT -#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ +#define PTE_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PTE_NG : 0) +#define PMD_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0) + +#define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) +#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) @@ -55,22 +53,22 @@ #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) #define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) -#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) -#define _HYP_PAGE_DEFAULT (_PAGE_DEFAULT & ~PTE_NG) +#define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) +#define _HYP_PAGE_DEFAULT _PAGE_DEFAULT -#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) -#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) -#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) +#define PAGE_KERNEL __pgprot(PROT_NORMAL) +#define PAGE_KERNEL_RO __pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY) +#define PAGE_KERNEL_EXEC __pgprot(PROT_NORMAL & ~PTE_PXN) +#define PAGE_KERNEL_EXEC_CONT __pgprot((PROT_NORMAL & ~PTE_PXN) | PTE_CONT) #define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN) #define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY) #define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN) #define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) -#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) -#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) +#define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY | PTE_S2_XN) +#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 6db43ebd648d..fce604e3e599 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -21,6 +21,9 @@ #define TASK_SIZE_64 (UL(1) << VA_BITS) +#define KERNEL_DS UL(-1) +#define USER_DS (TASK_SIZE_64 - 1) + #ifndef __ASSEMBLY__ /* diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index fdb827c7832f..ebdae15d665d 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -87,8 +87,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) " cbnz %w1, 1f\n" " add %w1, %w0, %3\n" " casa %w0, %w1, %2\n" - " and %w1, %w1, #0xffff\n" - " eor %w1, %w1, %w0, lsr #16\n" + " sub %w1, %w1, %3\n" + " eor %w1, %w1, %w0\n" "1:") : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) : "I" (1 << TICKET_SHIFT) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 59fda5292936..543e11f0f657 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -35,16 +35,20 @@ #include <asm/compiler.h> #include <asm/extable.h> -#define KERNEL_DS (-1UL) #define get_ds() (KERNEL_DS) - -#define USER_DS TASK_SIZE_64 #define get_fs() (current_thread_info()->addr_limit) static inline void set_fs(mm_segment_t fs) { current_thread_info()->addr_limit = fs; + /* + * Prevent a mispredicted conditional call to set_fs from forwarding + * the wrong address limit to access_ok under speculation. + */ + dsb(nsh); + isb(); + /* On user-mode return, check fs is correct */ set_thread_flag(TIF_FSCHECK); @@ -66,22 +70,32 @@ static inline void set_fs(mm_segment_t fs) * Returns 1 if the range is valid, 0 otherwise. * * This is equivalent to the following test: - * (u65)addr + (u65)size <= current->addr_limit - * - * This needs 65-bit arithmetic. + * (u65)addr + (u65)size <= (u65)current->addr_limit + 1 */ -#define __range_ok(addr, size) \ -({ \ - unsigned long __addr = (unsigned long)(addr); \ - unsigned long flag, roksum; \ - __chk_user_ptr(addr); \ - asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls" \ - : "=&r" (flag), "=&r" (roksum) \ - : "1" (__addr), "Ir" (size), \ - "r" (current_thread_info()->addr_limit) \ - : "cc"); \ - flag; \ -}) +static inline unsigned long __range_ok(unsigned long addr, unsigned long size) +{ + unsigned long limit = current_thread_info()->addr_limit; + + __chk_user_ptr(addr); + asm volatile( + // A + B <= C + 1 for all A,B,C, in four easy steps: + // 1: X = A + B; X' = X % 2^64 + " adds %0, %0, %2\n" + // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4 + " csel %1, xzr, %1, hi\n" + // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X' + // to compensate for the carry flag being set in step 4. For + // X > 2^64, X' merely has to remain nonzero, which it does. + " csinv %0, %0, xzr, cc\n" + // 4: For X < 2^64, this gives us X' - C - 1 <= 0, where the -1 + // comes from the carry in being clear. Otherwise, we are + // testing X' - C == 0, subject to the previous adjustments. + " sbcs xzr, %0, %1\n" + " cset %0, ls\n" + : "+r" (addr), "+r" (limit) : "Ir" (size) : "cc"); + + return addr; +} /* * When dealing with data aborts, watchpoints, or instruction traps we may end @@ -90,7 +104,7 @@ static inline void set_fs(mm_segment_t fs) */ #define untagged_addr(addr) sign_extend64(addr, 55) -#define access_ok(type, addr, size) __range_ok(addr, size) +#define access_ok(type, addr, size) __range_ok((unsigned long)(addr), size) #define user_addr_max get_fs #define _ASM_EXTABLE(from, to) \ @@ -221,6 +235,26 @@ static inline void uaccess_enable_not_uao(void) } /* + * Sanitise a uaccess pointer such that it becomes NULL if above the + * current addr_limit. + */ +#define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) +static inline void __user *__uaccess_mask_ptr(const void __user *ptr) +{ + void __user *safe_ptr; + + asm volatile( + " bics xzr, %1, %2\n" + " csel %0, %1, xzr, eq\n" + : "=&r" (safe_ptr) + : "r" (ptr), "r" (current_thread_info()->addr_limit) + : "cc"); + + csdb(); + return safe_ptr; +} + +/* * The "__xxx" versions of the user access functions do not verify the address * space - it must have been done previously with a separate "access_ok()" * call. @@ -272,28 +306,33 @@ do { \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) -#define __get_user(x, ptr) \ +#define __get_user_check(x, ptr, err) \ ({ \ - int __gu_err = 0; \ - __get_user_err((x), (ptr), __gu_err); \ - __gu_err; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_READ, __p, sizeof(*__p))) { \ + __p = uaccess_mask_ptr(__p); \ + __get_user_err((x), __p, (err)); \ + } else { \ + (x) = 0; (err) = -EFAULT; \ + } \ }) #define __get_user_error(x, ptr, err) \ ({ \ - __get_user_err((x), (ptr), (err)); \ + __get_user_check((x), (ptr), (err)); \ (void)0; \ }) -#define get_user(x, ptr) \ +#define __get_user(x, ptr) \ ({ \ - __typeof__(*(ptr)) __user *__p = (ptr); \ - might_fault(); \ - access_ok(VERIFY_READ, __p, sizeof(*__p)) ? \ - __get_user((x), __p) : \ - ((x) = 0, -EFAULT); \ + int __gu_err = 0; \ + __get_user_check((x), (ptr), __gu_err); \ + __gu_err; \ }) +#define get_user __get_user + #define __put_user_asm(instr, alt_instr, reg, x, addr, err, feature) \ asm volatile( \ "1:"ALTERNATIVE(instr " " reg "1, [%2]\n", \ @@ -336,43 +375,63 @@ do { \ uaccess_disable_not_uao(); \ } while (0) -#define __put_user(x, ptr) \ +#define __put_user_check(x, ptr, err) \ ({ \ - int __pu_err = 0; \ - __put_user_err((x), (ptr), __pu_err); \ - __pu_err; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) { \ + __p = uaccess_mask_ptr(__p); \ + __put_user_err((x), __p, (err)); \ + } else { \ + (err) = -EFAULT; \ + } \ }) #define __put_user_error(x, ptr, err) \ ({ \ - __put_user_err((x), (ptr), (err)); \ + __put_user_check((x), (ptr), (err)); \ (void)0; \ }) -#define put_user(x, ptr) \ +#define __put_user(x, ptr) \ ({ \ - __typeof__(*(ptr)) __user *__p = (ptr); \ - might_fault(); \ - access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ? \ - __put_user((x), __p) : \ - -EFAULT; \ + int __pu_err = 0; \ + __put_user_check((x), (ptr), __pu_err); \ + __pu_err; \ }) +#define put_user __put_user + extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); -#define raw_copy_from_user __arch_copy_from_user +#define raw_copy_from_user(to, from, n) \ +({ \ + __arch_copy_from_user((to), __uaccess_mask_ptr(from), (n)); \ +}) + extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); -#define raw_copy_to_user __arch_copy_to_user -extern unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n); -extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n); +#define raw_copy_to_user(to, from, n) \ +({ \ + __arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n)); \ +}) + +extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n); +#define raw_copy_in_user(to, from, n) \ +({ \ + __arch_copy_in_user(__uaccess_mask_ptr(to), \ + __uaccess_mask_ptr(from), (n)); \ +}) + #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER -static inline unsigned long __must_check clear_user(void __user *to, unsigned long n) +extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n); +static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { if (access_ok(VERIFY_WRITE, to, n)) - n = __clear_user(to, n); + n = __arch_clear_user(__uaccess_mask_ptr(to), n); return n; } +#define clear_user __clear_user extern long strncpy_from_user(char *dest, const char __user *src, long count); @@ -386,7 +445,7 @@ extern unsigned long __must_check __copy_user_flushcache(void *to, const void __ static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); - return __copy_user_flushcache(dst, src, size); + return __copy_user_flushcache(dst, __uaccess_mask_ptr(src), size); } #endif diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 252396a96c78..7b09487ff8fb 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -230,10 +230,10 @@ void __init acpi_boot_table_init(void) done: if (acpi_disabled) { - if (earlycon_init_is_deferred) + if (earlycon_acpi_spcr_enable) early_init_dt_scan_chosen_stdout(); } else { - parse_spcr(earlycon_init_is_deferred); + acpi_parse_spcr(earlycon_acpi_spcr_enable, true); if (IS_ENABLED(CONFIG_ACPI_BGRT)) acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); } diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 67368c7329c0..66be504edb6c 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -37,8 +37,8 @@ EXPORT_SYMBOL(clear_page); /* user mem (segment) */ EXPORT_SYMBOL(__arch_copy_from_user); EXPORT_SYMBOL(__arch_copy_to_user); -EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(raw_copy_in_user); +EXPORT_SYMBOL(__arch_clear_user); +EXPORT_SYMBOL(__arch_copy_in_user); /* physical memory */ EXPORT_SYMBOL(memstart_addr); diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S index 76225c2611ea..e5de33513b5d 100644 --- a/arch/arm64/kernel/bpi.S +++ b/arch/arm64/kernel/bpi.S @@ -17,6 +17,7 @@ */ #include <linux/linkage.h> +#include <linux/arm-smccc.h> .macro ventry target .rept 31 @@ -53,30 +54,6 @@ ENTRY(__bp_harden_hyp_vecs_start) vectors __kvm_hyp_vector .endr ENTRY(__bp_harden_hyp_vecs_end) -ENTRY(__psci_hyp_bp_inval_start) - sub sp, sp, #(8 * 18) - stp x16, x17, [sp, #(16 * 0)] - stp x14, x15, [sp, #(16 * 1)] - stp x12, x13, [sp, #(16 * 2)] - stp x10, x11, [sp, #(16 * 3)] - stp x8, x9, [sp, #(16 * 4)] - stp x6, x7, [sp, #(16 * 5)] - stp x4, x5, [sp, #(16 * 6)] - stp x2, x3, [sp, #(16 * 7)] - stp x0, x1, [sp, #(16 * 8)] - mov x0, #0x84000000 - smc #0 - ldp x16, x17, [sp, #(16 * 0)] - ldp x14, x15, [sp, #(16 * 1)] - ldp x12, x13, [sp, #(16 * 2)] - ldp x10, x11, [sp, #(16 * 3)] - ldp x8, x9, [sp, #(16 * 4)] - ldp x6, x7, [sp, #(16 * 5)] - ldp x4, x5, [sp, #(16 * 6)] - ldp x2, x3, [sp, #(16 * 7)] - ldp x0, x1, [sp, #(16 * 8)] - add sp, sp, #(8 * 18) -ENTRY(__psci_hyp_bp_inval_end) ENTRY(__qcom_hyp_sanitize_link_stack_start) stp x29, x30, [sp, #-16]! @@ -85,3 +62,22 @@ ENTRY(__qcom_hyp_sanitize_link_stack_start) .endr ldp x29, x30, [sp], #16 ENTRY(__qcom_hyp_sanitize_link_stack_end) + +.macro smccc_workaround_1 inst + sub sp, sp, #(8 * 4) + stp x2, x3, [sp, #(8 * 0)] + stp x0, x1, [sp, #(8 * 2)] + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 + \inst #0 + ldp x2, x3, [sp, #(8 * 0)] + ldp x0, x1, [sp, #(8 * 2)] + add sp, sp, #(8 * 4) +.endm + +ENTRY(__smccc_workaround_1_smc_start) + smccc_workaround_1 smc +ENTRY(__smccc_workaround_1_smc_end) + +ENTRY(__smccc_workaround_1_hvc_start) + smccc_workaround_1 hvc +ENTRY(__smccc_workaround_1_hvc_end) diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 2a752cb2a0f3..8021b46c9743 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -16,7 +16,7 @@ #include <asm/virt.h> .text -.pushsection .idmap.text, "ax" +.pushsection .idmap.text, "awx" /* * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ed6881882231..07823595b7f0 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -67,9 +67,12 @@ static int cpu_enable_trap_ctr_access(void *__unused) DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); #ifdef CONFIG_KVM -extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[]; extern char __qcom_hyp_sanitize_link_stack_start[]; extern char __qcom_hyp_sanitize_link_stack_end[]; +extern char __smccc_workaround_1_smc_start[]; +extern char __smccc_workaround_1_smc_end[]; +extern char __smccc_workaround_1_hvc_start[]; +extern char __smccc_workaround_1_hvc_end[]; static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, const char *hyp_vecs_end) @@ -112,10 +115,12 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn, spin_unlock(&bp_lock); } #else -#define __psci_hyp_bp_inval_start NULL -#define __psci_hyp_bp_inval_end NULL #define __qcom_hyp_sanitize_link_stack_start NULL #define __qcom_hyp_sanitize_link_stack_end NULL +#define __smccc_workaround_1_smc_start NULL +#define __smccc_workaround_1_smc_end NULL +#define __smccc_workaround_1_hvc_start NULL +#define __smccc_workaround_1_hvc_end NULL static void __install_bp_hardening_cb(bp_hardening_cb_t fn, const char *hyp_vecs_start, @@ -142,17 +147,59 @@ static void install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry, __install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end); } +#include <uapi/linux/psci.h> +#include <linux/arm-smccc.h> #include <linux/psci.h> -static int enable_psci_bp_hardening(void *data) +static void call_smc_arch_workaround_1(void) +{ + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); +} + +static void call_hvc_arch_workaround_1(void) +{ + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); +} + +static int enable_smccc_arch_workaround_1(void *data) { const struct arm64_cpu_capabilities *entry = data; + bp_hardening_cb_t cb; + void *smccc_start, *smccc_end; + struct arm_smccc_res res; + + if (!entry->matches(entry, SCOPE_LOCAL_CPU)) + return 0; + + if (psci_ops.smccc_version == SMCCC_VERSION_1_0) + return 0; + + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + if (res.a0) + return 0; + cb = call_hvc_arch_workaround_1; + smccc_start = __smccc_workaround_1_hvc_start; + smccc_end = __smccc_workaround_1_hvc_end; + break; + + case PSCI_CONDUIT_SMC: + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + if (res.a0) + return 0; + cb = call_smc_arch_workaround_1; + smccc_start = __smccc_workaround_1_smc_start; + smccc_end = __smccc_workaround_1_smc_end; + break; + + default: + return 0; + } - if (psci_ops.get_version) - install_bp_hardening_cb(entry, - (bp_hardening_cb_t)psci_ops.get_version, - __psci_hyp_bp_inval_start, - __psci_hyp_bp_inval_end); + install_bp_hardening_cb(entry, cb, smccc_start, smccc_end); return 0; } @@ -333,22 +380,22 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A75), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, @@ -362,12 +409,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, #endif { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0fb6a3151443..29b1f873e337 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -856,12 +856,23 @@ static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, int __unused) { + char const *str = "command line option"; u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); - /* Forced on command line? */ + /* + * For reasons that aren't entirely clear, enabling KPTI on Cavium + * ThunderX leads to apparent I-cache corruption of kernel text, which + * ends as well as you might imagine. Don't even try. + */ + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456)) { + str = "ARM64_WORKAROUND_CAVIUM_27456"; + __kpti_forced = -1; + } + + /* Forced? */ if (__kpti_forced) { - pr_info_once("kernel page table isolation forced %s by command line option\n", - __kpti_forced > 0 ? "ON" : "OFF"); + pr_info_once("kernel page table isolation forced %s by %s\n", + __kpti_forced > 0 ? "ON" : "OFF", str); return __kpti_forced > 0; } @@ -881,6 +892,30 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, ID_AA64PFR0_CSV3_SHIFT); } +static int kpti_install_ng_mappings(void *__unused) +{ + typedef void (kpti_remap_fn)(int, int, phys_addr_t); + extern kpti_remap_fn idmap_kpti_install_ng_mappings; + kpti_remap_fn *remap_fn; + + static bool kpti_applied = false; + int cpu = smp_processor_id(); + + if (kpti_applied) + return 0; + + remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); + + cpu_install_idmap(); + remap_fn(cpu, num_online_cpus(), __pa_symbol(swapper_pg_dir)); + cpu_uninstall_idmap(); + + if (!cpu) + kpti_applied = true; + + return 0; +} + static int __init parse_kpti(char *str) { bool enabled; @@ -1004,6 +1039,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_UNMAP_KERNEL_AT_EL0, .def_scope = SCOPE_SYSTEM, .matches = unmap_kernel_at_el0, + .enable = kpti_install_ng_mappings, }, #endif { diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index b34e717d7597..ec2ee720e33e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -167,10 +167,10 @@ alternative_else_nop_endif .else add x21, sp, #S_FRAME_SIZE get_thread_info tsk - /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ + /* Save the task's original addr_limit and set USER_DS */ ldr x20, [tsk, #TSK_TI_ADDR_LIMIT] str x20, [sp, #S_ORIG_ADDR_LIMIT] - mov x20, #TASK_SIZE_64 + mov x20, #USER_DS str x20, [tsk, #TSK_TI_ADDR_LIMIT] /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */ .endif /* \el == 0 */ @@ -324,6 +324,10 @@ alternative_else_nop_endif ldp x28, x29, [sp, #16 * 14] ldr lr, [sp, #S_LR] add sp, sp, #S_FRAME_SIZE // restore sp + /* + * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on eret context synchronization + * when returning from IPI handler, and when returning to user-space. + */ .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 @@ -378,6 +382,7 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 * x7 is reserved for the system call number in 32-bit mode. */ wsc_nr .req w25 // number of system calls +xsc_nr .req x25 // number of system calls (zero-extended) wscno .req w26 // syscall number xscno .req x26 // syscall number (zero-extended) stbl .req x27 // syscall table pointer @@ -766,7 +771,10 @@ el0_sp_pc: * Stack or PC alignment exception handling */ mrs x26, far_el1 - enable_daif + enable_da_f +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif ct_user_exit mov x0, x26 mov x1, x25 @@ -824,6 +832,11 @@ el0_irq_naked: #endif ct_user_exit +#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR + tbz x22, #55, 1f + bl do_el0_irq_bp_hardening +1: +#endif irq_handler #ifdef CONFIG_TRACE_IRQFLAGS @@ -935,6 +948,7 @@ el0_svc_naked: // compat entry point b.ne __sys_trace cmp wscno, wsc_nr // check upper syscall limit b.hs ni_sys + mask_nospec64 xscno, xsc_nr, x19 // enforce bounds for syscall number ldr x16, [stbl, xscno, lsl #3] // address in the syscall table blr x16 // call sys_* routine b ret_fast_syscall @@ -1013,16 +1027,9 @@ alternative_else_nop_endif orr \tmp, \tmp, #USER_ASID_FLAG msr ttbr1_el1, \tmp /* - * We avoid running the post_ttbr_update_workaround here because the - * user and kernel ASIDs don't have conflicting mappings, so any - * "blessing" as described in: - * - * http://lkml.kernel.org/r/56BB848A.6060603@caviumnetworks.com - * - * will not hurt correctness. Whilst this may partially defeat the - * point of using split ASIDs in the first place, it avoids - * the hit of invalidating the entire I-cache on every return to - * userspace. + * We avoid running the post_ttbr_update_workaround here because + * it's only needed by Cavium ThunderX, which requires KPTI to be + * disabled. */ .endm diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ba3ab04788dc..2b6b8b24e5ab 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -148,26 +148,6 @@ preserve_boot_args: ENDPROC(preserve_boot_args) /* - * Macro to arrange a physical address in a page table entry, taking care of - * 52-bit addresses. - * - * Preserves: phys - * Returns: pte - */ - .macro phys_to_pte, phys, pte -#ifdef CONFIG_ARM64_PA_BITS_52 - /* - * We assume \phys is 64K aligned and this is guaranteed by only - * supporting this configuration with 64K pages. - */ - orr \pte, \phys, \phys, lsr #36 - and \pte, \pte, #PTE_ADDR_MASK -#else - mov \pte, \phys -#endif - .endm - -/* * Macro to create a table entry to the next page. * * tbl: page table address @@ -181,7 +161,7 @@ ENDPROC(preserve_boot_args) */ .macro create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2 add \tmp1, \tbl, #PAGE_SIZE - phys_to_pte \tmp1, \tmp2 + phys_to_pte \tmp2, \tmp1 orr \tmp2, \tmp2, #PMD_TYPE_TABLE // address of next table and entry type lsr \tmp1, \virt, #\shift sub \ptrs, \ptrs, #1 @@ -207,7 +187,7 @@ ENDPROC(preserve_boot_args) * Returns: rtbl */ .macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1 -.Lpe\@: phys_to_pte \rtbl, \tmp1 +.Lpe\@: phys_to_pte \tmp1, \rtbl orr \tmp1, \tmp1, \flags // tmp1 = table entry str \tmp1, [\tbl, \index, lsl #3] add \rtbl, \rtbl, \inc // rtbl = pa next level @@ -475,7 +455,7 @@ ENDPROC(__primary_switched) * end early head section, begin head code that is also used for * hotplug and needs to have the same protections as the text region */ - .section ".idmap.text","ax" + .section ".idmap.text","awx" ENTRY(kimage_vaddr) .quad _text - TEXT_OFFSET @@ -776,8 +756,8 @@ ENTRY(__enable_mmu) update_early_cpu_boot_status 0, x1, x2 adrp x1, idmap_pg_dir adrp x2, swapper_pg_dir - phys_to_ttbr x1, x3 - phys_to_ttbr x2, x4 + phys_to_ttbr x3, x1 + phys_to_ttbr x4, x2 msr ttbr0_el1, x3 // load TTBR0 msr ttbr1_el1, x4 // load TTBR1 isb diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 84f5d52fddda..dd14ab8c9f72 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -34,12 +34,12 @@ * each stage of the walk. */ .macro break_before_make_ttbr_switch zero_page, page_table, tmp - phys_to_ttbr \zero_page, \tmp + phys_to_ttbr \tmp, \zero_page msr ttbr1_el1, \tmp isb tlbi vmalle1 dsb nsh - phys_to_ttbr \page_table, \tmp + phys_to_ttbr \tmp, \page_table msr ttbr1_el1, \tmp isb .endm diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 3affca3dd96a..75b220ba73a3 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -925,9 +925,8 @@ static void __armv8pmu_probe_pmu(void *info) pmceid[0] = read_sysreg(pmceid0_el0); pmceid[1] = read_sysreg(pmceid1_el0); - bitmap_from_u32array(cpu_pmu->pmceid_bitmap, - ARMV8_PMUV3_MAX_COMMON_EVENTS, pmceid, - ARRAY_SIZE(pmceid)); + bitmap_from_arr32(cpu_pmu->pmceid_bitmap, + pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); } static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu) diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 10dd16d7902d..bebec8ef9372 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -96,7 +96,7 @@ ENTRY(__cpu_suspend_enter) ret ENDPROC(__cpu_suspend_enter) - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly bl __cpu_setup diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5c7f657dd207..d7e3299a7734 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -361,10 +361,16 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { + int ret = 0; + + vcpu_load(vcpu); + trace_kvm_set_guest_debug(vcpu, dbg->control); - if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) - return -EINVAL; + if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) { + ret = -EINVAL; + goto out; + } if (dbg->control & KVM_GUESTDBG_ENABLE) { vcpu->guest_debug = dbg->control; @@ -378,7 +384,10 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, /* If not enabled clear all flags */ vcpu->guest_debug = 0; } - return 0; + +out: + vcpu_put(vcpu); + return ret; } int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 520b0dad3c62..e5e741bfffe1 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -22,13 +22,14 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <kvm/arm_psci.h> + #include <asm/esr.h> #include <asm/exception.h> #include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> -#include <asm/kvm_psci.h> #include <asm/debug-monitors.h> #include <asm/traps.h> @@ -51,7 +52,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vcpu_hvc_get_imm(vcpu)); vcpu->stat.hvc_exit_stat++; - ret = kvm_psci_call(vcpu); + ret = kvm_hvc_call_handler(vcpu); if (ret < 0) { vcpu_set_reg(vcpu, 0, ~0UL); return 1; @@ -62,7 +63,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { + /* + * "If an SMC instruction executed at Non-secure EL1 is + * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a + * Trap exception, not a Secure Monitor Call exception [...]" + * + * We need to advance the PC after the trap, as it would + * otherwise return to the same address... + */ vcpu_set_reg(vcpu, 0, ~0UL); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 1; } diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index e086c6eff8c6..5aa9ccf6db99 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -63,7 +63,7 @@ __do_hyp_init: cmp x0, #HVC_STUB_HCALL_NR b.lo __kvm_handle_stub_hvc - phys_to_ttbr x0, x4 + phys_to_ttbr x4, x0 msr ttbr0_el2, x4 mrs x4, tcr_el1 diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index f4363d40e2cd..dabb5cc7b087 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -21,6 +21,7 @@ #include <asm/debug-monitors.h> #include <asm/kvm_asm.h> #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> #define read_debug(r,n) read_sysreg(r##n##_el1) #define write_debug(v,r,n) write_sysreg(v, r##n##_el1) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index e4f37b9dd47c..f36464bd57c5 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -15,6 +15,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/arm-smccc.h> #include <linux/linkage.h> #include <asm/alternative.h> @@ -64,10 +65,11 @@ alternative_endif lsr x0, x1, #ESR_ELx_EC_SHIFT cmp x0, #ESR_ELx_EC_HVC64 + ccmp x0, #ESR_ELx_EC_HVC32, #4, ne b.ne el1_trap - mrs x1, vttbr_el2 // If vttbr is valid, the 64bit guest - cbnz x1, el1_trap // called HVC + mrs x1, vttbr_el2 // If vttbr is valid, the guest + cbnz x1, el1_hvc_guest // called HVC /* Here, we're pretty sure the host called HVC. */ ldp x0, x1, [sp], #16 @@ -100,6 +102,20 @@ alternative_endif eret +el1_hvc_guest: + /* + * Fastest possible path for ARM_SMCCC_ARCH_WORKAROUND_1. + * The workaround has already been applied on the host, + * so let's quickly get back to the guest. We don't bother + * restoring x1, as it can be clobbered anyway. + */ + ldr x1, [sp] // Guest's x0 + eor w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1 + cbnz w1, el1_trap + mov x0, x1 + add sp, sp, #16 + eret + el1_trap: /* * x0: ESR_EC diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 036e1f3d77a6..116252a8d3a5 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -19,9 +19,12 @@ #include <linux/jump_label.h> #include <uapi/linux/psci.h> +#include <kvm/arm_psci.h> + #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> #include <asm/fpsimd.h> #include <asm/debug-monitors.h> @@ -348,18 +351,6 @@ again: if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu)) goto again; - if (exit_code == ARM_EXCEPTION_TRAP && - (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 || - kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) && - vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) { - u64 val = PSCI_RET_NOT_SUPPORTED; - if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) - val = 2; - - vcpu_set_reg(vcpu, 0, val); - goto again; - } - if (static_branch_unlikely(&vgic_v2_cpuif_trap) && exit_code == ARM_EXCEPTION_TRAP) { bool valid; diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 73464a96c365..131c7772703c 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -16,6 +16,7 @@ */ #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> #include <asm/tlbflush.h> static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm) diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 3d69a8d41fa5..21ba0b29621b 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -21,7 +21,7 @@ .text -/* Prototype: int __clear_user(void *addr, size_t sz) +/* Prototype: int __arch_clear_user(void *addr, size_t sz) * Purpose : clear some user memory * Params : addr - user memory address to clear * : sz - number of bytes to clear @@ -29,7 +29,7 @@ * * Alignment fixed up by hardware. */ -ENTRY(__clear_user) +ENTRY(__arch_clear_user) uaccess_enable_not_uao x2, x3, x4 mov x2, x1 // save the size for fixup return subs x1, x1, #8 @@ -52,7 +52,7 @@ uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 uaccess_disable_not_uao x2, x3 ret -ENDPROC(__clear_user) +ENDPROC(__arch_clear_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index fbb090f431a5..54b75deb1d16 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -64,14 +64,15 @@ .endm end .req x5 -ENTRY(raw_copy_in_user) + +ENTRY(__arch_copy_in_user) uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" uaccess_disable_not_uao x3, x4 mov x0, #0 ret -ENDPROC(raw_copy_in_user) +ENDPROC(__arch_copy_in_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 91464e7f77cc..758bde7e2fa6 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -60,16 +60,7 @@ user_alt 9f, "dc cvau, x4", "dc civac, x4", ARM64_WORKAROUND_CLEAN_CACHE b.lo 1b dsb ish - icache_line_size x2, x3 - sub x3, x2, #1 - bic x4, x0, x3 -1: -USER(9f, ic ivau, x4 ) // invalidate I line PoU - add x4, x4, x2 - cmp x4, x1 - b.lo 1b - dsb ish - isb + invalidate_icache_by_line x0, x1, x2, x3, 9f mov x0, #0 1: uaccess_ttbr0_disable x1, x2 @@ -81,6 +72,27 @@ ENDPROC(flush_icache_range) ENDPROC(__flush_cache_user_range) /* + * invalidate_icache_range(start,end) + * + * Ensure that the I cache is invalid within specified region. + * + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(invalidate_icache_range) + uaccess_ttbr0_enable x2, x3, x4 + + invalidate_icache_by_line x0, x1, x2, x3, 2f + mov x0, xzr +1: + uaccess_ttbr0_disable x1, x2 + ret +2: + mov x0, #-EFAULT + b 1b +ENDPROC(invalidate_icache_range) + +/* * __flush_dcache_area(kaddr, size) * * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index ce441d29e7f6..f76bb2c3c943 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -240,7 +240,7 @@ static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs, if (fsc_type == ESR_ELx_FSC_PERM) return true; - if (addr < USER_DS && system_uses_ttbr0_pan()) + if (addr < TASK_SIZE && system_uses_ttbr0_pan()) return fsc_type == ESR_ELx_FSC_FAULT && (regs->pstate & PSR_PAN_BIT); @@ -414,7 +414,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, mm_flags |= FAULT_FLAG_WRITE; } - if (addr < USER_DS && is_permission_fault(esr, regs, addr)) { + if (addr < TASK_SIZE && is_permission_fault(esr, regs, addr)) { /* regs->orig_addr_limit may be 0 if we entered from EL0 */ if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); @@ -707,6 +707,12 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, arm64_notify_die("", regs, &info, esr); } +asmlinkage void __exception do_el0_irq_bp_hardening(void) +{ + /* PC has already been checked in entry.S */ + arm64_apply_bp_hardening(); +} + asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, struct pt_regs *regs) @@ -731,6 +737,12 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr, struct siginfo info; struct task_struct *tsk = current; + if (user_mode(regs)) { + if (instruction_pointer(regs) > TASK_SIZE) + arm64_apply_bp_hardening(); + local_irq_enable(); + } + if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS)) pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n", tsk->comm, task_pid_nr(tsk), @@ -790,6 +802,9 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, if (interrupts_enabled(regs)) trace_hardirqs_off(); + if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE) + arm64_apply_bp_hardening(); + if (!inf->fn(addr, esr, regs)) { rv = 1; } else { diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index acba49fb5aac..6e02e6fb4c7b 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -135,7 +135,8 @@ static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, /* The early shadow maps everything to a single page of zeroes */ asmlinkage void __init kasan_early_init(void) { - BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << 61)); + BUILD_BUG_ON(KASAN_SHADOW_OFFSET != + KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 4e369dfb83b1..4694cda823c9 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -118,6 +118,10 @@ static bool pgattr_change_is_safe(u64 old, u64 new) if ((old | new) & PTE_CONT) return false; + /* Transitioning from Global to Non-Global is safe */ + if (((old ^ new) == PTE_NG) && (new & PTE_NG)) + return true; + return ((old ^ new) & ~mask) == 0; } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 9f177aac6390..71baed7e592a 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -90,7 +90,7 @@ ENDPROC(cpu_do_suspend) * * x0: Address of context pointer */ - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" ENTRY(cpu_do_resume) ldp x2, x3, [x0] ldp x4, x5, [x0, #16] @@ -153,7 +153,7 @@ ENDPROC(cpu_do_resume) ENTRY(cpu_do_switch_mm) mrs x2, ttbr1_el1 mmid x1, x1 // get mm->context.id - phys_to_ttbr x0, x3 + phys_to_ttbr x3, x0 #ifdef CONFIG_ARM64_SW_TTBR0_PAN bfi x3, x1, #48, #16 // set the ASID field in TTBR0 #endif @@ -165,7 +165,18 @@ ENTRY(cpu_do_switch_mm) b post_ttbr_update_workaround // Back to C code... ENDPROC(cpu_do_switch_mm) - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" + +.macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 + adrp \tmp1, empty_zero_page + phys_to_ttbr \tmp2, \tmp1 + msr ttbr1_el1, \tmp2 + isb + tlbi vmalle1 + dsb nsh + isb +.endm + /* * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd) * @@ -175,24 +186,201 @@ ENDPROC(cpu_do_switch_mm) ENTRY(idmap_cpu_replace_ttbr1) save_and_disable_daif flags=x2 - adrp x1, empty_zero_page - phys_to_ttbr x1, x3 + __idmap_cpu_set_reserved_ttbr1 x1, x3 + + phys_to_ttbr x3, x0 msr ttbr1_el1, x3 isb - tlbi vmalle1 - dsb nsh + restore_daif x2 + + ret +ENDPROC(idmap_cpu_replace_ttbr1) + .popsection + +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + .pushsection ".idmap.text", "awx" + + .macro __idmap_kpti_get_pgtable_ent, type + dc cvac, cur_\()\type\()p // Ensure any existing dirty + dmb sy // lines are written back before + ldr \type, [cur_\()\type\()p] // loading the entry + tbz \type, #0, next_\()\type // Skip invalid entries + .endm + + .macro __idmap_kpti_put_pgtable_ent_ng, type + orr \type, \type, #PTE_NG // Same bit for blocks and pages + str \type, [cur_\()\type\()p] // Update the entry and ensure it + dc civac, cur_\()\type\()p // is visible to all CPUs. + .endm + +/* + * void __kpti_install_ng_mappings(int cpu, int num_cpus, phys_addr_t swapper) + * + * Called exactly once from stop_machine context by each CPU found during boot. + */ +__idmap_kpti_flag: + .long 1 +ENTRY(idmap_kpti_install_ng_mappings) + cpu .req w0 + num_cpus .req w1 + swapper_pa .req x2 + swapper_ttb .req x3 + flag_ptr .req x4 + cur_pgdp .req x5 + end_pgdp .req x6 + pgd .req x7 + cur_pudp .req x8 + end_pudp .req x9 + pud .req x10 + cur_pmdp .req x11 + end_pmdp .req x12 + pmd .req x13 + cur_ptep .req x14 + end_ptep .req x15 + pte .req x16 + + mrs swapper_ttb, ttbr1_el1 + adr flag_ptr, __idmap_kpti_flag + + cbnz cpu, __idmap_kpti_secondary + + /* We're the boot CPU. Wait for the others to catch up */ + sevl +1: wfe + ldaxr w18, [flag_ptr] + eor w18, w18, num_cpus + cbnz w18, 1b + + /* We need to walk swapper, so turn off the MMU. */ + pre_disable_mmu_workaround + mrs x18, sctlr_el1 + bic x18, x18, #SCTLR_ELx_M + msr sctlr_el1, x18 isb - phys_to_ttbr x0, x3 - msr ttbr1_el1, x3 + /* Everybody is enjoying the idmap, so we can rewrite swapper. */ + /* PGD */ + mov cur_pgdp, swapper_pa + add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) +do_pgd: __idmap_kpti_get_pgtable_ent pgd + tbnz pgd, #1, walk_puds + __idmap_kpti_put_pgtable_ent_ng pgd +next_pgd: + add cur_pgdp, cur_pgdp, #8 + cmp cur_pgdp, end_pgdp + b.ne do_pgd + + /* Publish the updated tables and nuke all the TLBs */ + dsb sy + tlbi vmalle1is + dsb ish isb - restore_daif x2 + /* We're done: fire up the MMU again */ + mrs x18, sctlr_el1 + orr x18, x18, #SCTLR_ELx_M + msr sctlr_el1, x18 + isb + /* Set the flag to zero to indicate that we're all done */ + str wzr, [flag_ptr] ret -ENDPROC(idmap_cpu_replace_ttbr1) + + /* PUD */ +walk_puds: + .if CONFIG_PGTABLE_LEVELS > 3 + pte_to_phys cur_pudp, pgd + add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) +do_pud: __idmap_kpti_get_pgtable_ent pud + tbnz pud, #1, walk_pmds + __idmap_kpti_put_pgtable_ent_ng pud +next_pud: + add cur_pudp, cur_pudp, 8 + cmp cur_pudp, end_pudp + b.ne do_pud + b next_pgd + .else /* CONFIG_PGTABLE_LEVELS <= 3 */ + mov pud, pgd + b walk_pmds +next_pud: + b next_pgd + .endif + + /* PMD */ +walk_pmds: + .if CONFIG_PGTABLE_LEVELS > 2 + pte_to_phys cur_pmdp, pud + add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) +do_pmd: __idmap_kpti_get_pgtable_ent pmd + tbnz pmd, #1, walk_ptes + __idmap_kpti_put_pgtable_ent_ng pmd +next_pmd: + add cur_pmdp, cur_pmdp, #8 + cmp cur_pmdp, end_pmdp + b.ne do_pmd + b next_pud + .else /* CONFIG_PGTABLE_LEVELS <= 2 */ + mov pmd, pud + b walk_ptes +next_pmd: + b next_pud + .endif + + /* PTE */ +walk_ptes: + pte_to_phys cur_ptep, pmd + add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) +do_pte: __idmap_kpti_get_pgtable_ent pte + __idmap_kpti_put_pgtable_ent_ng pte +next_pte: + add cur_ptep, cur_ptep, #8 + cmp cur_ptep, end_ptep + b.ne do_pte + b next_pmd + + /* Secondary CPUs end up here */ +__idmap_kpti_secondary: + /* Uninstall swapper before surgery begins */ + __idmap_cpu_set_reserved_ttbr1 x18, x17 + + /* Increment the flag to let the boot CPU we're ready */ +1: ldxr w18, [flag_ptr] + add w18, w18, #1 + stxr w17, w18, [flag_ptr] + cbnz w17, 1b + + /* Wait for the boot CPU to finish messing around with swapper */ + sevl +1: wfe + ldxr w18, [flag_ptr] + cbnz w18, 1b + + /* All done, act like nothing happened */ + msr ttbr1_el1, swapper_ttb + isb + ret + + .unreq cpu + .unreq num_cpus + .unreq swapper_pa + .unreq swapper_ttb + .unreq flag_ptr + .unreq cur_pgdp + .unreq end_pgdp + .unreq pgd + .unreq cur_pudp + .unreq end_pudp + .unreq pud + .unreq cur_pmdp + .unreq end_pmdp + .unreq pmd + .unreq cur_ptep + .unreq end_ptep + .unreq pte +ENDPROC(idmap_kpti_install_ng_mappings) .popsection +#endif /* * __cpu_setup @@ -200,7 +388,7 @@ ENDPROC(idmap_cpu_replace_ttbr1) * Initialise the processor for turning the MMU on. Return in x0 the * value of the SCTLR_EL1 register. */ - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" ENTRY(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh diff --git a/arch/blackfin/include/uapi/asm/poll.h b/arch/blackfin/include/uapi/asm/poll.h index 3b162f2d2970..cd2f1a78aba5 100644 --- a/arch/blackfin/include/uapi/asm/poll.h +++ b/arch/blackfin/include/uapi/asm/poll.h @@ -9,25 +9,8 @@ #ifndef _UAPI__BFIN_POLL_H #define _UAPI__BFIN_POLL_H -#ifndef __KERNEL__ #define POLLWRNORM POLLOUT -#define POLLWRBAND (__force __poll_t)256 -#else -#define __ARCH_HAS_MANGLED_POLL -static inline __u16 mangle_poll(__poll_t val) -{ - __u16 v = (__force __u16)val; - /* bit 9 -> bit 8, bit 8 -> bit 2 */ - return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6); -} - -static inline __poll_t demangle_poll(__u16 v) -{ - /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */ - return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) | - ((v & 4) << 6)); -} -#endif +#define POLLWRBAND 256 #include <asm-generic/poll.h> diff --git a/arch/cris/arch-v10/drivers/gpio.c b/arch/cris/arch-v10/drivers/gpio.c index a2986c60aaac..cd0e05d89d42 100644 --- a/arch/cris/arch-v10/drivers/gpio.c +++ b/arch/cris/arch-v10/drivers/gpio.c @@ -173,7 +173,7 @@ static __poll_t gpio_poll(struct file *file, poll_table *wait) if ((data & priv->highalarm) || (~data & priv->lowalarm)) { - mask = POLLIN|POLLRDNORM; + mask = EPOLLIN|EPOLLRDNORM; } out: diff --git a/arch/cris/arch-v10/drivers/sync_serial.c b/arch/cris/arch-v10/drivers/sync_serial.c index 177843c64071..ed1a568a7217 100644 --- a/arch/cris/arch-v10/drivers/sync_serial.c +++ b/arch/cris/arch-v10/drivers/sync_serial.c @@ -666,16 +666,16 @@ static __poll_t sync_serial_poll(struct file *file, poll_table *wait) poll_wait(file, &port->in_wait_q, wait); /* Some room to write */ if (port->out_count < OUT_BUFFER_SIZE) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; /* At least an inbufchunk of data */ if (sync_data_avail(port) >= port->inbufchunk) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; DEBUGPOLL(if (mask != prev_mask) printk(KERN_DEBUG "sync_serial_poll: mask 0x%08X %s %s\n", mask, - mask & POLLOUT ? "POLLOUT" : "", - mask & POLLIN ? "POLLIN" : ""); + mask & EPOLLOUT ? "POLLOUT" : "", + mask & EPOLLIN ? "POLLIN" : ""); prev_mask = mask; ); return mask; diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c index e20e0b9a3a5c..1b0ce8a8af16 100644 --- a/arch/cris/arch-v32/drivers/sync_serial.c +++ b/arch/cris/arch-v32/drivers/sync_serial.c @@ -574,24 +574,24 @@ static __poll_t sync_serial_poll(struct file *file, poll_table *wait) /* No active transfer, descriptors are available */ if (port->output && !port->tr_running) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; /* Descriptor and buffer space available. */ if (port->output && port->active_tr_descr != port->catch_tr_descr && port->out_buf_count < OUT_BUFFER_SIZE) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; /* At least an inbufchunk of data */ if (port->input && sync_data_avail(port) >= port->inbufchunk) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; DEBUGPOLL( if (mask != prev_mask) pr_info("sync_serial_poll: mask 0x%08X %s %s\n", mask, - mask & POLLOUT ? "POLLOUT" : "", - mask & POLLIN ? "POLLIN" : ""); + mask & EPOLLOUT ? "POLLOUT" : "", + mask & EPOLLIN ? "POLLIN" : ""); prev_mask = mask; ); return mask; diff --git a/arch/cris/kernel/Makefile b/arch/cris/kernel/Makefile index e69de29bb2d1..f6bfee6c8c1b 100644 --- a/arch/cris/kernel/Makefile +++ b/arch/cris/kernel/Makefile @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the CRIS port. +# + +CPPFLAGS_vmlinux.lds := -DDRAM_VIRTUAL_BASE=0x$(CONFIG_ETRAX_DRAM_VIRTUAL_BASE) +extra-y := vmlinux.lds + +obj-y := process.o traps.o irq.o ptrace.o setup.o time.o sys_cris.o +obj-y += stacktrace.o + +obj-$(CONFIG_MODULES) += crisksyms.o +obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_SYSTEM_PROFILER) += profile.o + +clean: + diff --git a/arch/cris/kernel/setup.c b/arch/cris/kernel/setup.c index 524d47501a23..1b61a7207afb 100644 --- a/arch/cris/kernel/setup.c +++ b/arch/cris/kernel/setup.c @@ -24,6 +24,7 @@ #include <linux/of_fdt.h> #include <asm/setup.h> #include <arch/system.h> +#include <asm/sections.h> /* * Setup options @@ -31,7 +32,6 @@ struct screen_info screen_info; extern int root_mountflags; -extern char _etext, _edata, _end; char __initdata cris_command_line[COMMAND_LINE_SIZE] = { 0, }; diff --git a/arch/frv/include/uapi/asm/poll.h b/arch/frv/include/uapi/asm/poll.h index a44c8f0ebee7..f55b45f475ec 100644 --- a/arch/frv/include/uapi/asm/poll.h +++ b/arch/frv/include/uapi/asm/poll.h @@ -2,25 +2,8 @@ #ifndef _ASM_POLL_H #define _ASM_POLL_H -#ifndef __KERNEL__ #define POLLWRNORM POLLOUT -#define POLLWRBAND (__force __poll_t)256 -#else -#define __ARCH_HAS_MANGLED_POLL -static inline __u16 mangle_poll(__poll_t val) -{ - __u16 v = (__force __u16)val; - /* bit 9 -> bit 8, bit 8 -> bit 2 */ - return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6); -} - -static inline __poll_t demangle_poll(__u16 v) -{ - /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */ - return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) | - ((v & 4) << 6)); -} -#endif +#define POLLWRBAND 256 #include <asm-generic/poll.h> #undef POLLREMOVE diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index c44f002e8f6b..8fb280e33114 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -1670,7 +1670,7 @@ pfm_poll(struct file *filp, poll_table * wait) PROTECT_CTX(ctx, flags); if (PFM_CTXQ_EMPTY(ctx) == 0) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; UNPROTECT_CTX(ctx, flags); @@ -2610,17 +2610,10 @@ pfm_get_task(pfm_context_t *ctx, pid_t pid, struct task_struct **task) if (pid < 2) return -EPERM; if (pid != task_pid_vnr(current)) { - - read_lock(&tasklist_lock); - - p = find_task_by_vpid(pid); - /* make sure task cannot go away while we operate on it */ - if (p) get_task_struct(p); - - read_unlock(&tasklist_lock); - - if (p == NULL) return -ESRCH; + p = find_get_task_by_vpid(pid); + if (!p) + return -ESRCH; } ret = pfm_task_incompatible(ctx, p); diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index dda58cfe8c22..93b47b1f6fb4 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -311,7 +311,6 @@ static inline int bfchg_mem_test_and_change_bit(int nr, * functions. */ #if defined(CONFIG_CPU_HAS_NO_BITFIELDS) -#include <asm-generic/bitops/find.h> #include <asm-generic/bitops/ffz.h> #else @@ -441,6 +440,8 @@ static inline unsigned long ffz(unsigned long word) #endif +#include <asm-generic/bitops/find.h> + #ifdef __KERNEL__ #if defined(CONFIG_CPU_HAS_NO_BITFIELDS) diff --git a/arch/m68k/include/uapi/asm/poll.h b/arch/m68k/include/uapi/asm/poll.h index d8be239e8141..c3e3fcc15e1d 100644 --- a/arch/m68k/include/uapi/asm/poll.h +++ b/arch/m68k/include/uapi/asm/poll.h @@ -2,25 +2,8 @@ #ifndef __m68k_POLL_H #define __m68k_POLL_H -#ifndef __KERNEL__ #define POLLWRNORM POLLOUT -#define POLLWRBAND (__force __poll_t)256 -#else -#define __ARCH_HAS_MANGLED_POLL -static inline __u16 mangle_poll(__poll_t val) -{ - __u16 v = (__force __u16)val; - /* bit 9 -> bit 8, bit 8 -> bit 2 */ - return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6); -} - -static inline __poll_t demangle_poll(__u16 v) -{ - /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */ - return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) | - ((v & 4) << 6)); -} -#endif +#define POLLWRBAND 256 #include <asm-generic/poll.h> diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index ab98569994f0..8128c3b68d6b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -7,8 +7,6 @@ config MIPS select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST - select ARCH_MIGHT_HAVE_PC_PARPORT - select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if 64BIT @@ -119,12 +117,12 @@ config MIPS_GENERIC select SYS_SUPPORTS_MULTITHREADING select SYS_SUPPORTS_RELOCATABLE select SYS_SUPPORTS_SMARTMIPS - select USB_EHCI_BIG_ENDIAN_DESC if BIG_ENDIAN - select USB_EHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN - select USB_OHCI_BIG_ENDIAN_DESC if BIG_ENDIAN - select USB_OHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN - select USB_UHCI_BIG_ENDIAN_DESC if BIG_ENDIAN - select USB_UHCI_BIG_ENDIAN_MMIO if BIG_ENDIAN + select USB_EHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN + select USB_EHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN + select USB_OHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN + select USB_OHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN + select USB_UHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN + select USB_UHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN select USE_OF help Select this to build a kernel which aims to support multiple boards, @@ -253,6 +251,7 @@ config BCM47XX select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_MIPS16 + select SYS_SUPPORTS_ZBOOT select SYS_HAS_EARLY_PRINTK select USE_GENERIC_EARLY_PRINTK_8250 select GPIOLIB @@ -341,6 +340,8 @@ config MACH_DECSTATION config MACH_JAZZ bool "Jazz family of machines" + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select FW_ARC select FW_ARC32 select ARCH_MAY_HAVE_PC_FDC @@ -476,6 +477,8 @@ config MACH_PISTACHIO config MIPS_MALTA bool "MIPS Malta board" select ARCH_MAY_HAVE_PC_FDC + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select BOOT_ELF32 select BOOT_RAW select BUILTIN_DTB @@ -613,6 +616,7 @@ config SGI_IP22 bool "SGI IP22 (Indy/Indigo2)" select FW_ARC select FW_ARC32 + select ARCH_MIGHT_HAVE_PC_SERIO select BOOT_ELF32 select CEVT_R4K select CSRC_R4K @@ -675,6 +679,7 @@ config SGI_IP28 bool "SGI IP28 (Indigo2 R10k)" select FW_ARC select FW_ARC64 + select ARCH_MIGHT_HAVE_PC_SERIO select BOOT_ELF64 select CEVT_R4K select CSRC_R4K @@ -824,6 +829,8 @@ config SNI_RM select FW_ARC32 if CPU_LITTLE_ENDIAN select FW_SNIPROM if CPU_BIG_ENDIAN select ARCH_MAY_HAVE_PC_FDC + select ARCH_MIGHT_HAVE_PC_PARPORT + select ARCH_MIGHT_HAVE_PC_SERIO select BOOT_ELF32 select CEVT_R4K select CSRC_R4K @@ -2326,7 +2333,6 @@ config MIPS_VPE_LOADER_TOM config MIPS_VPE_APSP_API bool "Enable support for AP/SP API (RTLX)" depends on MIPS_VPE_LOADER - help config MIPS_VPE_APSP_API_CMP bool diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 9f6a26d72f9f..d1ca839c3981 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -216,6 +216,12 @@ cflags-$(toolchain-msa) += -DTOOLCHAIN_SUPPORTS_MSA endif toolchain-virt := $(call cc-option-yn,$(mips-cflags) -mvirt) cflags-$(toolchain-virt) += -DTOOLCHAIN_SUPPORTS_VIRT +# For -mmicromips, use -Wa,-fatal-warnings to catch unsupported -mxpa which +# only warns +xpa-cflags-y := $(mips-cflags) +xpa-cflags-$(micromips-ase) += -mmicromips -Wa$(comma)-fatal-warnings +toolchain-xpa := $(call cc-option-yn,$(xpa-cflags-y) -mxpa) +cflags-$(toolchain-xpa) += -DTOOLCHAIN_SUPPORTS_XPA # # Firmware support @@ -228,7 +234,7 @@ libs-y += arch/mips/fw/lib/ # # Kernel compression # -ifdef SYS_SUPPORTS_ZBOOT +ifdef CONFIG_SYS_SUPPORTS_ZBOOT COMPRESSION_FNAME = vmlinuz else COMPRESSION_FNAME = vmlinux diff --git a/arch/mips/bcm47xx/Platform b/arch/mips/bcm47xx/Platform index 874b7ca4cd11..70783b75fd9d 100644 --- a/arch/mips/bcm47xx/Platform +++ b/arch/mips/bcm47xx/Platform @@ -5,3 +5,4 @@ platform-$(CONFIG_BCM47XX) += bcm47xx/ cflags-$(CONFIG_BCM47XX) += \ -I$(srctree)/arch/mips/include/asm/mach-bcm47xx load-$(CONFIG_BCM47XX) := 0xffffffff80001000 +zload-$(CONFIG_BCM47XX) += 0xffffffff80400000 diff --git a/arch/mips/bcm63xx/boards/Kconfig b/arch/mips/bcm63xx/boards/Kconfig index 6ff0a7481081..f60d96610ace 100644 --- a/arch/mips/bcm63xx/boards/Kconfig +++ b/arch/mips/bcm63xx/boards/Kconfig @@ -7,6 +7,5 @@ choice config BOARD_BCM963XX bool "Generic Broadcom 963xx boards" select SSB - help endchoice diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index c675eece389a..adce180f3ee4 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -133,4 +133,8 @@ vmlinuz.srec: vmlinuz uzImage.bin: vmlinuz.bin FORCE $(call if_changed,uimage,none) -clean-files := $(objtree)/vmlinuz $(objtree)/vmlinuz.{32,ecoff,bin,srec} +clean-files += $(objtree)/vmlinuz +clean-files += $(objtree)/vmlinuz.32 +clean-files += $(objtree)/vmlinuz.ecoff +clean-files += $(objtree)/vmlinuz.bin +clean-files += $(objtree)/vmlinuz.srec diff --git a/arch/mips/boot/dts/ingenic/Makefile b/arch/mips/boot/dts/ingenic/Makefile index 6a31759839b4..5b1361a89e02 100644 --- a/arch/mips/boot/dts/ingenic/Makefile +++ b/arch/mips/boot/dts/ingenic/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_JZ4740_QI_LB60) += qi_lb60.dtb +dtb-$(CONFIG_JZ4770_GCW0) += gcw0.dtb dtb-$(CONFIG_JZ4780_CI20) += ci20.dtb obj-y += $(patsubst %.dtb, %.dtb.o, $(dtb-y)) diff --git a/arch/mips/boot/dts/ingenic/gcw0.dts b/arch/mips/boot/dts/ingenic/gcw0.dts new file mode 100644 index 000000000000..35f0291e8d38 --- /dev/null +++ b/arch/mips/boot/dts/ingenic/gcw0.dts @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/dts-v1/; + +#include "jz4770.dtsi" + +/ { + compatible = "gcw,zero", "ingenic,jz4770"; + model = "GCW Zero"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + }; + + chosen { + stdout-path = "serial2:57600n8"; + }; + + board { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + otg_phy: otg-phy { + compatible = "usb-nop-xceiv"; + clocks = <&cgu JZ4770_CLK_OTG_PHY>; + clock-names = "main_clk"; + }; + }; +}; + +&ext { + clock-frequency = <12000000>; +}; + +&uart2 { + status = "okay"; +}; + +&cgu { + /* Put high-speed peripherals under PLL1, such that we can change the + * PLL0 frequency on demand without having to suspend peripherals. + * We use a rate of 432 MHz, which is the least common multiple of + * 27 MHz (required by TV encoder) and 48 MHz (required by USB host). + */ + assigned-clocks = + <&cgu JZ4770_CLK_PLL1>, + <&cgu JZ4770_CLK_UHC>; + assigned-clock-parents = + <0>, + <&cgu JZ4770_CLK_PLL1>; + assigned-clock-rates = + <432000000>; +}; + +&uhc { + /* The WiFi module is connected to the UHC. */ + status = "okay"; +}; diff --git a/arch/mips/boot/dts/ingenic/jz4770.dtsi b/arch/mips/boot/dts/ingenic/jz4770.dtsi new file mode 100644 index 000000000000..7c2804f3f5f1 --- /dev/null +++ b/arch/mips/boot/dts/ingenic/jz4770.dtsi @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <dt-bindings/clock/jz4770-cgu.h> + +/ { + #address-cells = <1>; + #size-cells = <1>; + compatible = "ingenic,jz4770"; + + cpuintc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + compatible = "mti,cpu-interrupt-controller"; + }; + + intc: interrupt-controller@10001000 { + compatible = "ingenic,jz4770-intc"; + reg = <0x10001000 0x40>; + + interrupt-controller; + #interrupt-cells = <1>; + + interrupt-parent = <&cpuintc>; + interrupts = <2>; + }; + + ext: ext { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + + osc32k: osc32k { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32768>; + }; + + cgu: jz4770-cgu@10000000 { + compatible = "ingenic,jz4770-cgu"; + reg = <0x10000000 0x100>; + + clocks = <&ext>, <&osc32k>; + clock-names = "ext", "osc32k"; + + #clock-cells = <1>; + }; + + pinctrl: pin-controller@10010000 { + compatible = "ingenic,jz4770-pinctrl"; + reg = <0x10010000 0x600>; + + #address-cells = <1>; + #size-cells = <0>; + + gpa: gpio@0 { + compatible = "ingenic,jz4770-gpio"; + reg = <0>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 0 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <17>; + }; + + gpb: gpio@1 { + compatible = "ingenic,jz4770-gpio"; + reg = <1>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 32 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <16>; + }; + + gpc: gpio@2 { + compatible = "ingenic,jz4770-gpio"; + reg = <2>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 64 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <15>; + }; + + gpd: gpio@3 { + compatible = "ingenic,jz4770-gpio"; + reg = <3>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 96 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <14>; + }; + + gpe: gpio@4 { + compatible = "ingenic,jz4770-gpio"; + reg = <4>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 128 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <13>; + }; + + gpf: gpio@5 { + compatible = "ingenic,jz4770-gpio"; + reg = <5>; + + gpio-controller; + gpio-ranges = <&pinctrl 0 160 32>; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + + interrupt-parent = <&intc>; + interrupts = <12>; + }; + }; + + uart0: serial@10030000 { + compatible = "ingenic,jz4770-uart"; + reg = <0x10030000 0x100>; + + clocks = <&ext>, <&cgu JZ4770_CLK_UART0>; + clock-names = "baud", "module"; + + interrupt-parent = <&intc>; + interrupts = <5>; + + status = "disabled"; + }; + + uart1: serial@10031000 { + compatible = "ingenic,jz4770-uart"; + reg = <0x10031000 0x100>; + + clocks = <&ext>, <&cgu JZ4770_CLK_UART1>; + clock-names = "baud", "module"; + + interrupt-parent = <&intc>; + interrupts = <4>; + + status = "disabled"; + }; + + uart2: serial@10032000 { + compatible = "ingenic,jz4770-uart"; + reg = <0x10032000 0x100>; + + clocks = <&ext>, <&cgu JZ4770_CLK_UART2>; + clock-names = "baud", "module"; + + interrupt-parent = <&intc>; + interrupts = <3>; + + status = "disabled"; + }; + + uart3: serial@10033000 { + compatible = "ingenic,jz4770-uart"; + reg = <0x10033000 0x100>; + + clocks = <&ext>, <&cgu JZ4770_CLK_UART3>; + clock-names = "baud", "module"; + + interrupt-parent = <&intc>; + interrupts = <2>; + + status = "disabled"; + }; + + uhc: uhc@13430000 { + compatible = "generic-ohci"; + reg = <0x13430000 0x1000>; + + clocks = <&cgu JZ4770_CLK_UHC>, <&cgu JZ4770_CLK_UHC_PHY>; + assigned-clocks = <&cgu JZ4770_CLK_UHC>; + assigned-clock-rates = <48000000>; + + interrupt-parent = <&intc>; + interrupts = <20>; + + status = "disabled"; + }; +}; diff --git a/arch/mips/configs/bigsur_defconfig b/arch/mips/configs/bigsur_defconfig index a55009edbb29..5e73fe755be6 100644 --- a/arch/mips/configs/bigsur_defconfig +++ b/arch/mips/configs/bigsur_defconfig @@ -153,7 +153,6 @@ CONFIG_SLIP_COMPRESSED=y CONFIG_SLIP_SMART=y CONFIG_SLIP_MODE_SLIP6=y # CONFIG_INPUT is not set -# CONFIG_SERIO_I8042 is not set CONFIG_SERIO_RAW=m # CONFIG_VT is not set CONFIG_SERIAL_NONSTANDARD=y diff --git a/arch/mips/configs/gcw0_defconfig b/arch/mips/configs/gcw0_defconfig new file mode 100644 index 000000000000..99ac1fa3b35f --- /dev/null +++ b/arch/mips/configs/gcw0_defconfig @@ -0,0 +1,27 @@ +CONFIG_MACH_INGENIC=y +CONFIG_JZ4770_GCW0=y +CONFIG_HIGHMEM=y +# CONFIG_BOUNCE is not set +CONFIG_PREEMPT_VOLUNTARY=y +# CONFIG_SECCOMP is not set +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_EMBEDDED=y +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_SUSPEND is not set +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_NETDEVICES=y +CONFIG_SERIAL_8250=y +# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_INGENIC=y +CONFIG_USB=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_NOP_USB_XCEIV=y +CONFIG_TMPFS=y diff --git a/arch/mips/configs/generic/board-ranchu.config b/arch/mips/configs/generic/board-ranchu.config new file mode 100644 index 000000000000..fee9ad4c5598 --- /dev/null +++ b/arch/mips/configs/generic/board-ranchu.config @@ -0,0 +1,30 @@ +CONFIG_VIRT_BOARD_RANCHU=y + +CONFIG_BATTERY_GOLDFISH=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_GOLDFISH=y +CONFIG_STAGING=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH_PIC=y +CONFIG_GOLDFISH_PIPE=y +CONFIG_GOLDFISH_TTY=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y + +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y + +CONFIG_MAGIC_SYSRQ=y +CONFIG_POWER_SUPPLY=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y + +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_NETDEVICES=y +CONFIG_VIRTIO_NET=y diff --git a/arch/mips/configs/ip27_defconfig b/arch/mips/configs/ip27_defconfig index a0d593248668..91a9c13e2c82 100644 --- a/arch/mips/configs/ip27_defconfig +++ b/arch/mips/configs/ip27_defconfig @@ -252,7 +252,6 @@ CONFIG_RT2800PCI=m CONFIG_WL12XX=m CONFIG_WL1251=m # CONFIG_INPUT is not set -# CONFIG_SERIO_I8042 is not set CONFIG_SERIO_LIBPS2=m CONFIG_SERIO_RAW=m CONFIG_SERIO_ALTERA_PS2=m diff --git a/arch/mips/configs/ip32_defconfig b/arch/mips/configs/ip32_defconfig index 1e26e58b9dc3..ebff297328ae 100644 --- a/arch/mips/configs/ip32_defconfig +++ b/arch/mips/configs/ip32_defconfig @@ -75,7 +75,6 @@ CONFIG_DE2104X=m CONFIG_TULIP=m CONFIG_TULIP_MMIO=y CONFIG_INPUT_EVDEV=m -# CONFIG_SERIO_I8042 is not set CONFIG_SERIO_MACEPS2=y CONFIG_SERIO_RAW=y # CONFIG_CONSOLE_TRANSLATIONS is not set diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig index 396408404487..df8a9a15ca83 100644 --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@ -312,9 +312,8 @@ CONFIG_HOSTAP_PCI=m CONFIG_IPW2100=m CONFIG_IPW2100_MONITOR=y CONFIG_LIBERTAS=m -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set +CONFIG_INPUT_MOUSEDEV=y +CONFIG_MOUSE_PS2_ELANTECH=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig index 5691673a3327..14df9ef15d40 100644 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@ -324,9 +324,7 @@ CONFIG_HOSTAP_PCI=m CONFIG_IPW2100=m CONFIG_IPW2100_MONITOR=y CONFIG_LIBERTAS=m -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set +CONFIG_INPUT_MOUSEDEV=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig index e9cadb37d684..25092e344574 100644 --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@ -326,9 +326,7 @@ CONFIG_HOSTAP_PCI=m CONFIG_IPW2100=m CONFIG_IPW2100_MONITOR=y CONFIG_LIBERTAS=m -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set +CONFIG_INPUT_MOUSEDEV=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig index 77145ecaa23b..210bf609f785 100644 --- a/arch/mips/configs/malta_qemu_32r6_defconfig +++ b/arch/mips/configs/malta_qemu_32r6_defconfig @@ -126,6 +126,7 @@ CONFIG_PCNET32=y # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_WLAN is not set +CONFIG_INPUT_MOUSEDEV=y # CONFIG_VT is not set CONFIG_LEGACY_PTY_COUNT=4 CONFIG_SERIAL_8250=y diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig index cc2687cfdc13..e5934aa98397 100644 --- a/arch/mips/configs/maltaaprp_defconfig +++ b/arch/mips/configs/maltaaprp_defconfig @@ -126,6 +126,7 @@ CONFIG_PCNET32=y # CONFIG_NET_VENDOR_TOSHIBA is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_WLAN is not set +CONFIG_INPUT_MOUSEDEV=y # CONFIG_VT is not set CONFIG_LEGACY_PTY_COUNT=16 CONFIG_SERIAL_8250=y diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig index d8c8f5fb8918..cb2ca11c1789 100644 --- a/arch/mips/configs/maltasmvp_defconfig +++ b/arch/mips/configs/maltasmvp_defconfig @@ -127,6 +127,7 @@ CONFIG_PCNET32=y # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_WLAN is not set +CONFIG_INPUT_MOUSEDEV=y # CONFIG_VT is not set CONFIG_LEGACY_PTY_COUNT=4 CONFIG_SERIAL_8250=y diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig index 04827bc9f87f..be29fcec69fc 100644 --- a/arch/mips/configs/maltasmvp_eva_defconfig +++ b/arch/mips/configs/maltasmvp_eva_defconfig @@ -130,6 +130,7 @@ CONFIG_PCNET32=y # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_WLAN is not set +CONFIG_INPUT_MOUSEDEV=y # CONFIG_VT is not set CONFIG_LEGACY_PTY_COUNT=4 CONFIG_SERIAL_8250=y diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig index 7ea7c0ba2666..40462d4c90a0 100644 --- a/arch/mips/configs/maltaup_defconfig +++ b/arch/mips/configs/maltaup_defconfig @@ -125,6 +125,7 @@ CONFIG_PCNET32=y # CONFIG_NET_VENDOR_TOSHIBA is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_WLAN is not set +CONFIG_INPUT_MOUSEDEV=y # CONFIG_VT is not set CONFIG_LEGACY_PTY_COUNT=16 CONFIG_SERIAL_8250=y diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig index 2942610e4082..4e50176cb3df 100644 --- a/arch/mips/configs/maltaup_xpa_defconfig +++ b/arch/mips/configs/maltaup_xpa_defconfig @@ -321,9 +321,8 @@ CONFIG_HOSTAP_PCI=m CONFIG_IPW2100=m CONFIG_IPW2100_MONITOR=y CONFIG_LIBERTAS=m -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set +CONFIG_INPUT_MOUSEDEV=y +CONFIG_MOUSE_PS2_ELANTECH=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_POWER_RESET=y diff --git a/arch/mips/configs/nlm_xlp_defconfig b/arch/mips/configs/nlm_xlp_defconfig index 7357248b3d7a..e8e1dd8e0e99 100644 --- a/arch/mips/configs/nlm_xlp_defconfig +++ b/arch/mips/configs/nlm_xlp_defconfig @@ -399,7 +399,6 @@ CONFIG_INPUT_EVDEV=y CONFIG_INPUT_EVBUG=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set CONFIG_SERIO_SERPORT=m CONFIG_SERIO_LIBPS2=y CONFIG_SERIO_RAW=m diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig index 1e18fd7de209..c4477a4d40c1 100644 --- a/arch/mips/configs/nlm_xlr_defconfig +++ b/arch/mips/configs/nlm_xlr_defconfig @@ -332,7 +332,6 @@ CONFIG_INPUT_EVDEV=y CONFIG_INPUT_EVBUG=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set CONFIG_SERIO_SERPORT=m CONFIG_SERIO_LIBPS2=y CONFIG_SERIO_RAW=m diff --git a/arch/mips/configs/pnx8335_stb225_defconfig b/arch/mips/configs/pnx8335_stb225_defconfig index 81b5eb89446c..e73cdb08fc6e 100644 --- a/arch/mips/configs/pnx8335_stb225_defconfig +++ b/arch/mips/configs/pnx8335_stb225_defconfig @@ -49,7 +49,6 @@ CONFIG_INPUT_EVDEV=m CONFIG_INPUT_EVBUG=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO_I8042 is not set # CONFIG_VT_CONSOLE is not set CONFIG_SERIAL_PNX8XXX=y CONFIG_SERIAL_PNX8XXX_CONSOLE=y diff --git a/arch/mips/configs/sb1250_swarm_defconfig b/arch/mips/configs/sb1250_swarm_defconfig index c724bdd6a7e6..1edd8430ad61 100644 --- a/arch/mips/configs/sb1250_swarm_defconfig +++ b/arch/mips/configs/sb1250_swarm_defconfig @@ -65,7 +65,6 @@ CONFIG_NET_ETHERNET=y CONFIG_MII=y CONFIG_SB1250_MAC=y # CONFIG_INPUT is not set -# CONFIG_SERIO_I8042 is not set CONFIG_SERIO_RAW=m # CONFIG_VT is not set # CONFIG_HW_RANDOM is not set diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig index 52e0286a1612..2ff3b17bfab1 100644 --- a/arch/mips/generic/Kconfig +++ b/arch/mips/generic/Kconfig @@ -49,4 +49,14 @@ config FIT_IMAGE_FDT_XILFPGA Enable this to include the FDT for the MIPSfpga platform from Imagination Technologies in the FIT kernel image. +config VIRT_BOARD_RANCHU + bool "Support Ranchu platform for Android emulator" + help + This enables support for the platform used by Android emulator. + + Ranchu platform consists of a set of virtual devices. This platform + enables emulation of variety of virtual configurations while using + Android emulator. Android emulator is based on Qemu, and contains + the support for the same set of virtual devices. + endif diff --git a/arch/mips/generic/Makefile b/arch/mips/generic/Makefile index 874967363dbb..5c31e0c4697d 100644 --- a/arch/mips/generic/Makefile +++ b/arch/mips/generic/Makefile @@ -15,3 +15,4 @@ obj-y += proc.o obj-$(CONFIG_YAMON_DT_SHIM) += yamon-dt.o obj-$(CONFIG_LEGACY_BOARD_SEAD3) += board-sead3.o obj-$(CONFIG_KEXEC) += kexec.o +obj-$(CONFIG_VIRT_BOARD_RANCHU) += board-ranchu.o diff --git a/arch/mips/generic/board-ranchu.c b/arch/mips/generic/board-ranchu.c new file mode 100644 index 000000000000..59a8c18fa2cc --- /dev/null +++ b/arch/mips/generic/board-ranchu.c @@ -0,0 +1,93 @@ +/* + * Support code for virtual Ranchu board for MIPS. + * + * Author: Miodrag Dinic <miodrag.dinic@mips.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/of_address.h> +#include <linux/types.h> + +#include <asm/machine.h> +#include <asm/mipsregs.h> +#include <asm/time.h> + +#define GOLDFISH_TIMER_LOW 0x00 +#define GOLDFISH_TIMER_HIGH 0x04 + +static __init u64 read_rtc_time(void __iomem *base) +{ + u32 time_low; + u32 time_high; + + /* + * Reading the low address latches the high value + * as well so there is no fear that we may read + * inaccurate high value. + */ + time_low = readl(base + GOLDFISH_TIMER_LOW); + time_high = readl(base + GOLDFISH_TIMER_HIGH); + + return ((u64)time_high << 32) | time_low; +} + +static __init unsigned int ranchu_measure_hpt_freq(void) +{ + u64 rtc_start, rtc_current, rtc_delta; + unsigned int start, count; + struct device_node *np; + void __iomem *rtc_base; + + np = of_find_compatible_node(NULL, NULL, "google,goldfish-rtc"); + if (!np) + panic("%s(): Failed to find 'google,goldfish-rtc' dt node!", + __func__); + + rtc_base = of_iomap(np, 0); + if (!rtc_base) + panic("%s(): Failed to ioremap Goldfish RTC base!", __func__); + + /* + * Poll the nanosecond resolution RTC for one + * second to calibrate the CPU frequency. + */ + rtc_start = read_rtc_time(rtc_base); + start = read_c0_count(); + + do { + rtc_current = read_rtc_time(rtc_base); + rtc_delta = rtc_current - rtc_start; + } while (rtc_delta < NSEC_PER_SEC); + + count = read_c0_count() - start; + + /* + * Make sure the frequency will be a round number. + * Without this correction, the returned value may vary + * between subsequent emulation executions. + * + * TODO: Set this value using device tree. + */ + count += 5000; + count -= count % 10000; + + iounmap(rtc_base); + + return count; +} + +static const struct of_device_id ranchu_of_match[] __initconst = { + { + .compatible = "mti,ranchu", + }, + {} +}; + +MIPS_MACHINE(ranchu) = { + .matches = ranchu_of_match, + .measure_hpt_freq = ranchu_measure_hpt_freq, +}; diff --git a/arch/mips/generic/irq.c b/arch/mips/generic/irq.c index 394f8161e462..cb7fdaeef426 100644 --- a/arch/mips/generic/irq.c +++ b/arch/mips/generic/irq.c @@ -22,10 +22,10 @@ int get_c0_fdc_int(void) { int mips_cpu_fdc_irq; - if (cpu_has_veic) - panic("Unimplemented!"); - else if (mips_gic_present()) + if (mips_gic_present()) mips_cpu_fdc_irq = gic_get_c0_fdc_int(); + else if (cpu_has_veic) + panic("Unimplemented!"); else if (cp0_fdc_irq >= 0) mips_cpu_fdc_irq = MIPS_CPU_IRQ_BASE + cp0_fdc_irq; else @@ -38,10 +38,10 @@ int get_c0_perfcount_int(void) { int mips_cpu_perf_irq; - if (cpu_has_veic) - panic("Unimplemented!"); - else if (mips_gic_present()) + if (mips_gic_present()) mips_cpu_perf_irq = gic_get_c0_perfcount_int(); + else if (cpu_has_veic) + panic("Unimplemented!"); else if (cp0_perfcount_irq >= 0) mips_cpu_perf_irq = MIPS_CPU_IRQ_BASE + cp0_perfcount_irq; else @@ -54,10 +54,10 @@ unsigned int get_c0_compare_int(void) { int mips_cpu_timer_irq; - if (cpu_has_veic) - panic("Unimplemented!"); - else if (mips_gic_present()) + if (mips_gic_present()) mips_cpu_timer_irq = gic_get_c0_compare_int(); + else if (cpu_has_veic) + panic("Unimplemented!"); else mips_cpu_timer_irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq; diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h index e26a093bb17a..a301a8f4bc66 100644 --- a/arch/mips/include/asm/bootinfo.h +++ b/arch/mips/include/asm/bootinfo.h @@ -79,6 +79,8 @@ enum loongson_machine_type { */ #define MACH_INGENIC_JZ4730 0 /* JZ4730 SOC */ #define MACH_INGENIC_JZ4740 1 /* JZ4740 SOC */ +#define MACH_INGENIC_JZ4770 2 /* JZ4770 SOC */ +#define MACH_INGENIC_JZ4780 3 /* JZ4780 SOC */ extern char *system_type; const char *get_system_type(void); diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h index 77cad232a1c6..e8161e4dfde7 100644 --- a/arch/mips/include/asm/checksum.h +++ b/arch/mips/include/asm/checksum.h @@ -110,7 +110,7 @@ __wsum csum_partial_copy_nocheck(const void *src, void *dst, */ static inline __sum16 csum_fold(__wsum csum) { - u32 sum = (__force u32)csum;; + u32 sum = (__force u32)csum; sum += (sum << 16); csum = (sum < csum); diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index 4f69f08717f6..8c286bedff3e 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -4,7 +4,7 @@ #define SYSTEM_RAM_LOW 1 #define SYSTEM_RAM_HIGH 2 -#define MEM_RESERVED 3 +#define SYSTEM_RAM_RESERVED 3 #define PCI_IO 4 #define PCI_MEM 5 #define LOONGSON_CFG_REG 6 diff --git a/arch/mips/include/asm/machine.h b/arch/mips/include/asm/machine.h index e0d9b373d415..f83879dadd1e 100644 --- a/arch/mips/include/asm/machine.h +++ b/arch/mips/include/asm/machine.h @@ -52,7 +52,7 @@ mips_machine_is_compatible(const struct mips_machine *mach, const void *fdt) if (!mach->matches) return NULL; - for (match = mach->matches; match->compatible; match++) { + for (match = mach->matches; match->compatible[0]; match++) { if (fdt_node_check_compatible(fdt, 0, match->compatible) == 0) return match; } diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 6b1f1ad0542c..858752dac337 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -1181,6 +1181,89 @@ static inline int mm_insn_16bit(u16 insn) #endif /* + * parse_r var, r - Helper assembler macro for parsing register names. + * + * This converts the register name in $n form provided in \r to the + * corresponding register number, which is assigned to the variable \var. It is + * needed to allow explicit encoding of instructions in inline assembly where + * registers are chosen by the compiler in $n form, allowing us to avoid using + * fixed register numbers. + * + * It also allows newer instructions (not implemented by the assembler) to be + * transparently implemented using assembler macros, instead of needing separate + * cases depending on toolchain support. + * + * Simple usage example: + * __asm__ __volatile__("parse_r __rt, %0\n\t" + * ".insn\n\t" + * "# di %0\n\t" + * ".word (0x41606000 | (__rt << 16))" + * : "=r" (status); + */ + +/* Match an individual register number and assign to \var */ +#define _IFC_REG(n) \ + ".ifc \\r, $" #n "\n\t" \ + "\\var = " #n "\n\t" \ + ".endif\n\t" + +__asm__(".macro parse_r var r\n\t" + "\\var = -1\n\t" + _IFC_REG(0) _IFC_REG(1) _IFC_REG(2) _IFC_REG(3) + _IFC_REG(4) _IFC_REG(5) _IFC_REG(6) _IFC_REG(7) + _IFC_REG(8) _IFC_REG(9) _IFC_REG(10) _IFC_REG(11) + _IFC_REG(12) _IFC_REG(13) _IFC_REG(14) _IFC_REG(15) + _IFC_REG(16) _IFC_REG(17) _IFC_REG(18) _IFC_REG(19) + _IFC_REG(20) _IFC_REG(21) _IFC_REG(22) _IFC_REG(23) + _IFC_REG(24) _IFC_REG(25) _IFC_REG(26) _IFC_REG(27) + _IFC_REG(28) _IFC_REG(29) _IFC_REG(30) _IFC_REG(31) + ".iflt \\var\n\t" + ".error \"Unable to parse register name \\r\"\n\t" + ".endif\n\t" + ".endm"); + +#undef _IFC_REG + +/* + * C macros for generating assembler macros for common instruction formats. + * + * The names of the operands can be chosen by the caller, and the encoding of + * register operand \<Rn> is assigned to __<Rn> where it can be accessed from + * the ENC encodings. + */ + +/* Instructions with no operands */ +#define _ASM_MACRO_0(OP, ENC) \ + __asm__(".macro " #OP "\n\t" \ + ENC \ + ".endm") + +/* Instructions with 2 register operands */ +#define _ASM_MACRO_2R(OP, R1, R2, ENC) \ + __asm__(".macro " #OP " " #R1 ", " #R2 "\n\t" \ + "parse_r __" #R1 ", \\" #R1 "\n\t" \ + "parse_r __" #R2 ", \\" #R2 "\n\t" \ + ENC \ + ".endm") + +/* Instructions with 3 register operands */ +#define _ASM_MACRO_3R(OP, R1, R2, R3, ENC) \ + __asm__(".macro " #OP " " #R1 ", " #R2 ", " #R3 "\n\t" \ + "parse_r __" #R1 ", \\" #R1 "\n\t" \ + "parse_r __" #R2 ", \\" #R2 "\n\t" \ + "parse_r __" #R3 ", \\" #R3 "\n\t" \ + ENC \ + ".endm") + +/* Instructions with 2 register operands and 1 optional select operand */ +#define _ASM_MACRO_2R_1S(OP, R1, R2, SEL3, ENC) \ + __asm__(".macro " #OP " " #R1 ", " #R2 ", " #SEL3 " = 0\n\t" \ + "parse_r __" #R1 ", \\" #R1 "\n\t" \ + "parse_r __" #R2 ", \\" #R2 "\n\t" \ + ENC \ + ".endm") + +/* * TLB Invalidate Flush */ static inline void tlbinvf(void) @@ -1245,14 +1328,14 @@ do { \ * Macros to access the system control coprocessor */ -#define __read_32bit_c0_register(source, sel) \ +#define ___read_32bit_c0_register(source, sel, vol) \ ({ unsigned int __res; \ if (sel == 0) \ - __asm__ __volatile__( \ + __asm__ vol( \ "mfc0\t%0, " #source "\n\t" \ : "=r" (__res)); \ else \ - __asm__ __volatile__( \ + __asm__ vol( \ ".set\tmips32\n\t" \ "mfc0\t%0, " #source ", " #sel "\n\t" \ ".set\tmips0\n\t" \ @@ -1260,18 +1343,18 @@ do { \ __res; \ }) -#define __read_64bit_c0_register(source, sel) \ +#define ___read_64bit_c0_register(source, sel, vol) \ ({ unsigned long long __res; \ if (sizeof(unsigned long) == 4) \ - __res = __read_64bit_c0_split(source, sel); \ + __res = __read_64bit_c0_split(source, sel, vol); \ else if (sel == 0) \ - __asm__ __volatile__( \ + __asm__ vol( \ ".set\tmips3\n\t" \ "dmfc0\t%0, " #source "\n\t" \ ".set\tmips0" \ : "=r" (__res)); \ else \ - __asm__ __volatile__( \ + __asm__ vol( \ ".set\tmips64\n\t" \ "dmfc0\t%0, " #source ", " #sel "\n\t" \ ".set\tmips0" \ @@ -1279,6 +1362,18 @@ do { \ __res; \ }) +#define __read_32bit_c0_register(source, sel) \ + ___read_32bit_c0_register(source, sel, __volatile__) + +#define __read_const_32bit_c0_register(source, sel) \ + ___read_32bit_c0_register(source, sel,) + +#define __read_64bit_c0_register(source, sel) \ + ___read_64bit_c0_register(source, sel, __volatile__) + +#define __read_const_64bit_c0_register(source, sel) \ + ___read_64bit_c0_register(source, sel,) + #define __write_32bit_c0_register(register, sel, value) \ do { \ if (sel == 0) \ @@ -1316,6 +1411,11 @@ do { \ (unsigned long) __read_32bit_c0_register(reg, sel) : \ (unsigned long) __read_64bit_c0_register(reg, sel)) +#define __read_const_ulong_c0_register(reg, sel) \ + ((sizeof(unsigned long) == 4) ? \ + (unsigned long) __read_const_32bit_c0_register(reg, sel) : \ + (unsigned long) __read_const_64bit_c0_register(reg, sel)) + #define __write_ulong_c0_register(reg, sel, val) \ do { \ if (sizeof(unsigned long) == 4) \ @@ -1346,14 +1446,14 @@ do { \ * These versions are only needed for systems with more than 38 bits of * physical address space running the 32-bit kernel. That's none atm :-) */ -#define __read_64bit_c0_split(source, sel) \ +#define __read_64bit_c0_split(source, sel, vol) \ ({ \ unsigned long long __val; \ unsigned long __flags; \ \ local_irq_save(__flags); \ if (sel == 0) \ - __asm__ __volatile__( \ + __asm__ vol( \ ".set\tmips64\n\t" \ "dmfc0\t%L0, " #source "\n\t" \ "dsra\t%M0, %L0, 32\n\t" \ @@ -1361,7 +1461,7 @@ do { \ ".set\tmips0" \ : "=r" (__val)); \ else \ - __asm__ __volatile__( \ + __asm__ vol( \ ".set\tmips64\n\t" \ "dmfc0\t%L0, " #source ", " #sel "\n\t" \ "dsra\t%M0, %L0, 32\n\t" \ @@ -1404,37 +1504,43 @@ do { \ local_irq_restore(__flags); \ } while (0) -#define __readx_32bit_c0_register(source) \ +#ifndef TOOLCHAIN_SUPPORTS_XPA +_ASM_MACRO_2R_1S(mfhc0, rt, rs, sel, + _ASM_INSN_IF_MIPS(0x40400000 | __rt << 16 | __rs << 11 | \\sel) + _ASM_INSN32_IF_MM(0x000000f4 | __rt << 21 | __rs << 16 | \\sel << 11)); +_ASM_MACRO_2R_1S(mthc0, rt, rd, sel, + _ASM_INSN_IF_MIPS(0x40c00000 | __rt << 16 | __rd << 11 | \\sel) + _ASM_INSN32_IF_MM(0x000002f4 | __rt << 21 | __rd << 16 | \\sel << 11)); +#define _ASM_SET_XPA "" +#else /* !TOOLCHAIN_SUPPORTS_XPA */ +#define _ASM_SET_XPA ".set\txpa\n\t" +#endif + +#define __readx_32bit_c0_register(source, sel) \ ({ \ unsigned int __res; \ \ __asm__ __volatile__( \ " .set push \n" \ - " .set noat \n" \ " .set mips32r2 \n" \ - " # mfhc0 $1, %1 \n" \ - _ASM_INSN_IF_MIPS(0x40410000 | ((%1 & 0x1f) << 11)) \ - _ASM_INSN32_IF_MM(0x002000f4 | ((%1 & 0x1f) << 16)) \ - " move %0, $1 \n" \ + _ASM_SET_XPA \ + " mfhc0 %0, " #source ", %1 \n" \ " .set pop \n" \ : "=r" (__res) \ - : "i" (source)); \ + : "i" (sel)); \ __res; \ }) -#define __writex_32bit_c0_register(register, value) \ +#define __writex_32bit_c0_register(register, sel, value) \ do { \ __asm__ __volatile__( \ " .set push \n" \ - " .set noat \n" \ " .set mips32r2 \n" \ - " move $1, %0 \n" \ - " # mthc0 $1, %1 \n" \ - _ASM_INSN_IF_MIPS(0x40c10000 | ((%1 & 0x1f) << 11)) \ - _ASM_INSN32_IF_MM(0x002002f4 | ((%1 & 0x1f) << 16)) \ + _ASM_SET_XPA \ + " mthc0 %z0, " #register ", %1 \n" \ " .set pop \n" \ : \ - : "r" (value), "i" (register)); \ + : "Jr" (value), "i" (sel)); \ } while (0) #define read_c0_index() __read_32bit_c0_register($0, 0) @@ -1446,14 +1552,14 @@ do { \ #define read_c0_entrylo0() __read_ulong_c0_register($2, 0) #define write_c0_entrylo0(val) __write_ulong_c0_register($2, 0, val) -#define readx_c0_entrylo0() __readx_32bit_c0_register(2) -#define writex_c0_entrylo0(val) __writex_32bit_c0_register(2, val) +#define readx_c0_entrylo0() __readx_32bit_c0_register($2, 0) +#define writex_c0_entrylo0(val) __writex_32bit_c0_register($2, 0, val) #define read_c0_entrylo1() __read_ulong_c0_register($3, 0) #define write_c0_entrylo1(val) __write_ulong_c0_register($3, 0, val) -#define readx_c0_entrylo1() __readx_32bit_c0_register(3) -#define writex_c0_entrylo1(val) __writex_32bit_c0_register(3, val) +#define readx_c0_entrylo1() __readx_32bit_c0_register($3, 0) +#define writex_c0_entrylo1(val) __writex_32bit_c0_register($3, 0, val) #define read_c0_conf() __read_32bit_c0_register($3, 0) #define write_c0_conf(val) __write_32bit_c0_register($3, 0, val) @@ -1541,7 +1647,7 @@ do { \ #define read_c0_epc() __read_ulong_c0_register($14, 0) #define write_c0_epc(val) __write_ulong_c0_register($14, 0, val) -#define read_c0_prid() __read_32bit_c0_register($15, 0) +#define read_c0_prid() __read_const_32bit_c0_register($15, 0) #define read_c0_cmgcrbase() __read_ulong_c0_register($15, 3) @@ -1830,18 +1936,44 @@ do { \ * Macros to access the guest system control coprocessor */ -#ifdef TOOLCHAIN_SUPPORTS_VIRT +#ifndef TOOLCHAIN_SUPPORTS_VIRT +_ASM_MACRO_2R_1S(mfgc0, rt, rs, sel, + _ASM_INSN_IF_MIPS(0x40600000 | __rt << 16 | __rs << 11 | \\sel) + _ASM_INSN32_IF_MM(0x000004fc | __rt << 21 | __rs << 16 | \\sel << 11)); +_ASM_MACRO_2R_1S(dmfgc0, rt, rs, sel, + _ASM_INSN_IF_MIPS(0x40600100 | __rt << 16 | __rs << 11 | \\sel) + _ASM_INSN32_IF_MM(0x580004fc | __rt << 21 | __rs << 16 | \\sel << 11)); +_ASM_MACRO_2R_1S(mtgc0, rt, rd, sel, + _ASM_INSN_IF_MIPS(0x40600200 | __rt << 16 | __rd << 11 | \\sel) + _ASM_INSN32_IF_MM(0x000006fc | __rt << 21 | __rd << 16 | \\sel << 11)); +_ASM_MACRO_2R_1S(dmtgc0, rt, rd, sel, + _ASM_INSN_IF_MIPS(0x40600300 | __rt << 16 | __rd << 11 | \\sel) + _ASM_INSN32_IF_MM(0x580006fc | __rt << 21 | __rd << 16 | \\sel << 11)); +_ASM_MACRO_0(tlbgp, _ASM_INSN_IF_MIPS(0x42000010) + _ASM_INSN32_IF_MM(0x0000017c)); +_ASM_MACRO_0(tlbgr, _ASM_INSN_IF_MIPS(0x42000009) + _ASM_INSN32_IF_MM(0x0000117c)); +_ASM_MACRO_0(tlbgwi, _ASM_INSN_IF_MIPS(0x4200000a) + _ASM_INSN32_IF_MM(0x0000217c)); +_ASM_MACRO_0(tlbgwr, _ASM_INSN_IF_MIPS(0x4200000e) + _ASM_INSN32_IF_MM(0x0000317c)); +_ASM_MACRO_0(tlbginvf, _ASM_INSN_IF_MIPS(0x4200000c) + _ASM_INSN32_IF_MM(0x0000517c)); +#define _ASM_SET_VIRT "" +#else /* !TOOLCHAIN_SUPPORTS_VIRT */ +#define _ASM_SET_VIRT ".set\tvirt\n\t" +#endif #define __read_32bit_gc0_register(source, sel) \ ({ int __res; \ __asm__ __volatile__( \ ".set\tpush\n\t" \ ".set\tmips32r2\n\t" \ - ".set\tvirt\n\t" \ - "mfgc0\t%0, $%1, %2\n\t" \ + _ASM_SET_VIRT \ + "mfgc0\t%0, " #source ", %1\n\t" \ ".set\tpop" \ : "=r" (__res) \ - : "i" (source), "i" (sel)); \ + : "i" (sel)); \ __res; \ }) @@ -1850,11 +1982,11 @@ do { \ __asm__ __volatile__( \ ".set\tpush\n\t" \ ".set\tmips64r2\n\t" \ - ".set\tvirt\n\t" \ - "dmfgc0\t%0, $%1, %2\n\t" \ + _ASM_SET_VIRT \ + "dmfgc0\t%0, " #source ", %1\n\t" \ ".set\tpop" \ : "=r" (__res) \ - : "i" (source), "i" (sel)); \ + : "i" (sel)); \ __res; \ }) @@ -1863,11 +1995,11 @@ do { \ __asm__ __volatile__( \ ".set\tpush\n\t" \ ".set\tmips32r2\n\t" \ - ".set\tvirt\n\t" \ - "mtgc0\t%z0, $%1, %2\n\t" \ + _ASM_SET_VIRT \ + "mtgc0\t%z0, " #register ", %1\n\t" \ ".set\tpop" \ : : "Jr" ((unsigned int)(value)), \ - "i" (register), "i" (sel)); \ + "i" (sel)); \ } while (0) #define __write_64bit_gc0_register(register, sel, value) \ @@ -1875,75 +2007,13 @@ do { \ __asm__ __volatile__( \ ".set\tpush\n\t" \ ".set\tmips64r2\n\t" \ - ".set\tvirt\n\t" \ - "dmtgc0\t%z0, $%1, %2\n\t" \ + _ASM_SET_VIRT \ + "dmtgc0\t%z0, " #register ", %1\n\t" \ ".set\tpop" \ : : "Jr" (value), \ - "i" (register), "i" (sel)); \ + "i" (sel)); \ } while (0) -#else /* TOOLCHAIN_SUPPORTS_VIRT */ - -#define __read_32bit_gc0_register(source, sel) \ -({ int __res; \ - __asm__ __volatile__( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ - "# mfgc0\t$1, $%1, %2\n\t" \ - _ASM_INSN_IF_MIPS(0x40610000 | %1 << 11 | %2) \ - _ASM_INSN32_IF_MM(0x002004fc | %1 << 16 | %2 << 11) \ - "move\t%0, $1\n\t" \ - ".set\tpop" \ - : "=r" (__res) \ - : "i" (source), "i" (sel)); \ - __res; \ -}) - -#define __read_64bit_gc0_register(source, sel) \ -({ unsigned long long __res; \ - __asm__ __volatile__( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ - "# dmfgc0\t$1, $%1, %2\n\t" \ - _ASM_INSN_IF_MIPS(0x40610100 | %1 << 11 | %2) \ - _ASM_INSN32_IF_MM(0x582004fc | %1 << 16 | %2 << 11) \ - "move\t%0, $1\n\t" \ - ".set\tpop" \ - : "=r" (__res) \ - : "i" (source), "i" (sel)); \ - __res; \ -}) - -#define __write_32bit_gc0_register(register, sel, value) \ -do { \ - __asm__ __volatile__( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ - "move\t$1, %z0\n\t" \ - "# mtgc0\t$1, $%1, %2\n\t" \ - _ASM_INSN_IF_MIPS(0x40610200 | %1 << 11 | %2) \ - _ASM_INSN32_IF_MM(0x002006fc | %1 << 16 | %2 << 11) \ - ".set\tpop" \ - : : "Jr" ((unsigned int)(value)), \ - "i" (register), "i" (sel)); \ -} while (0) - -#define __write_64bit_gc0_register(register, sel, value) \ -do { \ - __asm__ __volatile__( \ - ".set\tpush\n\t" \ - ".set\tnoat\n\t" \ - "move\t$1, %z0\n\t" \ - "# dmtgc0\t$1, $%1, %2\n\t" \ - _ASM_INSN_IF_MIPS(0x40610300 | %1 << 11 | %2) \ - _ASM_INSN32_IF_MM(0x582006fc | %1 << 16 | %2 << 11) \ - ".set\tpop" \ - : : "Jr" (value), \ - "i" (register), "i" (sel)); \ -} while (0) - -#endif /* !TOOLCHAIN_SUPPORTS_VIRT */ - #define __read_ulong_gc0_register(reg, sel) \ ((sizeof(unsigned long) == 4) ? \ (unsigned long) __read_32bit_gc0_register(reg, sel) : \ @@ -1957,207 +2027,207 @@ do { \ __write_64bit_gc0_register(reg, sel, val); \ } while (0) -#define read_gc0_index() __read_32bit_gc0_register(0, 0) -#define write_gc0_index(val) __write_32bit_gc0_register(0, 0, val) +#define read_gc0_index() __read_32bit_gc0_register($0, 0) +#define write_gc0_index(val) __write_32bit_gc0_register($0, 0, val) -#define read_gc0_entrylo0() __read_ulong_gc0_register(2, 0) -#define write_gc0_entrylo0(val) __write_ulong_gc0_register(2, 0, val) +#define read_gc0_entrylo0() __read_ulong_gc0_register($2, 0) +#define write_gc0_entrylo0(val) __write_ulong_gc0_register($2, 0, val) -#define read_gc0_entrylo1() __read_ulong_gc0_register(3, 0) -#define write_gc0_entrylo1(val) __write_ulong_gc0_register(3, 0, val) +#define read_gc0_entrylo1() __read_ulong_gc0_register($3, 0) +#define write_gc0_entrylo1(val) __write_ulong_gc0_register($3, 0, val) -#define read_gc0_context() __read_ulong_gc0_register(4, 0) -#define write_gc0_context(val) __write_ulong_gc0_register(4, 0, val) +#define read_gc0_context() __read_ulong_gc0_register($4, 0) +#define write_gc0_context(val) __write_ulong_gc0_register($4, 0, val) -#define read_gc0_contextconfig() __read_32bit_gc0_register(4, 1) -#define write_gc0_contextconfig(val) __write_32bit_gc0_register(4, 1, val) +#define read_gc0_contextconfig() __read_32bit_gc0_register($4, 1) +#define write_gc0_contextconfig(val) __write_32bit_gc0_register($4, 1, val) -#define read_gc0_userlocal() __read_ulong_gc0_register(4, 2) -#define write_gc0_userlocal(val) __write_ulong_gc0_register(4, 2, val) +#define read_gc0_userlocal() __read_ulong_gc0_register($4, 2) +#define write_gc0_userlocal(val) __write_ulong_gc0_register($4, 2, val) -#define read_gc0_xcontextconfig() __read_ulong_gc0_register(4, 3) -#define write_gc0_xcontextconfig(val) __write_ulong_gc0_register(4, 3, val) +#define read_gc0_xcontextconfig() __read_ulong_gc0_register($4, 3) +#define write_gc0_xcontextconfig(val) __write_ulong_gc0_register($4, 3, val) -#define read_gc0_pagemask() __read_32bit_gc0_register(5, 0) -#define write_gc0_pagemask(val) __write_32bit_gc0_register(5, 0, val) +#define read_gc0_pagemask() __read_32bit_gc0_register($5, 0) +#define write_gc0_pagemask(val) __write_32bit_gc0_register($5, 0, val) -#define read_gc0_pagegrain() __read_32bit_gc0_register(5, 1) -#define write_gc0_pagegrain(val) __write_32bit_gc0_register(5, 1, val) +#define read_gc0_pagegrain() __read_32bit_gc0_register($5, 1) +#define write_gc0_pagegrain(val) __write_32bit_gc0_register($5, 1, val) -#define read_gc0_segctl0() __read_ulong_gc0_register(5, 2) -#define write_gc0_segctl0(val) __write_ulong_gc0_register(5, 2, val) +#define read_gc0_segctl0() __read_ulong_gc0_register($5, 2) +#define write_gc0_segctl0(val) __write_ulong_gc0_register($5, 2, val) -#define read_gc0_segctl1() __read_ulong_gc0_register(5, 3) -#define write_gc0_segctl1(val) __write_ulong_gc0_register(5, 3, val) +#define read_gc0_segctl1() __read_ulong_gc0_register($5, 3) +#define write_gc0_segctl1(val) __write_ulong_gc0_register($5, 3, val) -#define read_gc0_segctl2() __read_ulong_gc0_register(5, 4) -#define write_gc0_segctl2(val) __write_ulong_gc0_register(5, 4, val) +#define read_gc0_segctl2() __read_ulong_gc0_register($5, 4) +#define write_gc0_segctl2(val) __write_ulong_gc0_register($5, 4, val) -#define read_gc0_pwbase() __read_ulong_gc0_register(5, 5) -#define write_gc0_pwbase(val) __write_ulong_gc0_register(5, 5, val) +#define read_gc0_pwbase() __read_ulong_gc0_register($5, 5) +#define write_gc0_pwbase(val) __write_ulong_gc0_register($5, 5, val) -#define read_gc0_pwfield() __read_ulong_gc0_register(5, 6) -#define write_gc0_pwfield(val) __write_ulong_gc0_register(5, 6, val) +#define read_gc0_pwfield() __read_ulong_gc0_register($5, 6) +#define write_gc0_pwfield(val) __write_ulong_gc0_register($5, 6, val) -#define read_gc0_pwsize() __read_ulong_gc0_register(5, 7) -#define write_gc0_pwsize(val) __write_ulong_gc0_register(5, 7, val) +#define read_gc0_pwsize() __read_ulong_gc0_register($5, 7) +#define write_gc0_pwsize(val) __write_ulong_gc0_register($5, 7, val) -#define read_gc0_wired() __read_32bit_gc0_register(6, 0) -#define write_gc0_wired(val) __write_32bit_gc0_register(6, 0, val) +#define read_gc0_wired() __read_32bit_gc0_register($6, 0) +#define write_gc0_wired(val) __write_32bit_gc0_register($6, 0, val) -#define read_gc0_pwctl() __read_32bit_gc0_register(6, 6) -#define write_gc0_pwctl(val) __write_32bit_gc0_register(6, 6, val) - -#define read_gc0_hwrena() __read_32bit_gc0_register(7, 0) -#define write_gc0_hwrena(val) __write_32bit_gc0_register(7, 0, val) - -#define read_gc0_badvaddr() __read_ulong_gc0_register(8, 0) -#define write_gc0_badvaddr(val) __write_ulong_gc0_register(8, 0, val) - -#define read_gc0_badinstr() __read_32bit_gc0_register(8, 1) -#define write_gc0_badinstr(val) __write_32bit_gc0_register(8, 1, val) - -#define read_gc0_badinstrp() __read_32bit_gc0_register(8, 2) -#define write_gc0_badinstrp(val) __write_32bit_gc0_register(8, 2, val) - -#define read_gc0_count() __read_32bit_gc0_register(9, 0) - -#define read_gc0_entryhi() __read_ulong_gc0_register(10, 0) -#define write_gc0_entryhi(val) __write_ulong_gc0_register(10, 0, val) - -#define read_gc0_compare() __read_32bit_gc0_register(11, 0) -#define write_gc0_compare(val) __write_32bit_gc0_register(11, 0, val) - -#define read_gc0_status() __read_32bit_gc0_register(12, 0) -#define write_gc0_status(val) __write_32bit_gc0_register(12, 0, val) - -#define read_gc0_intctl() __read_32bit_gc0_register(12, 1) -#define write_gc0_intctl(val) __write_32bit_gc0_register(12, 1, val) - -#define read_gc0_cause() __read_32bit_gc0_register(13, 0) -#define write_gc0_cause(val) __write_32bit_gc0_register(13, 0, val) - -#define read_gc0_epc() __read_ulong_gc0_register(14, 0) -#define write_gc0_epc(val) __write_ulong_gc0_register(14, 0, val) - -#define read_gc0_prid() __read_32bit_gc0_register(15, 0) - -#define read_gc0_ebase() __read_32bit_gc0_register(15, 1) -#define write_gc0_ebase(val) __write_32bit_gc0_register(15, 1, val) - -#define read_gc0_ebase_64() __read_64bit_gc0_register(15, 1) -#define write_gc0_ebase_64(val) __write_64bit_gc0_register(15, 1, val) - -#define read_gc0_config() __read_32bit_gc0_register(16, 0) -#define read_gc0_config1() __read_32bit_gc0_register(16, 1) -#define read_gc0_config2() __read_32bit_gc0_register(16, 2) -#define read_gc0_config3() __read_32bit_gc0_register(16, 3) -#define read_gc0_config4() __read_32bit_gc0_register(16, 4) -#define read_gc0_config5() __read_32bit_gc0_register(16, 5) -#define read_gc0_config6() __read_32bit_gc0_register(16, 6) -#define read_gc0_config7() __read_32bit_gc0_register(16, 7) -#define write_gc0_config(val) __write_32bit_gc0_register(16, 0, val) -#define write_gc0_config1(val) __write_32bit_gc0_register(16, 1, val) -#define write_gc0_config2(val) __write_32bit_gc0_register(16, 2, val) -#define write_gc0_config3(val) __write_32bit_gc0_register(16, 3, val) -#define write_gc0_config4(val) __write_32bit_gc0_register(16, 4, val) -#define write_gc0_config5(val) __write_32bit_gc0_register(16, 5, val) -#define write_gc0_config6(val) __write_32bit_gc0_register(16, 6, val) -#define write_gc0_config7(val) __write_32bit_gc0_register(16, 7, val) - -#define read_gc0_lladdr() __read_ulong_gc0_register(17, 0) -#define write_gc0_lladdr(val) __write_ulong_gc0_register(17, 0, val) - -#define read_gc0_watchlo0() __read_ulong_gc0_register(18, 0) -#define read_gc0_watchlo1() __read_ulong_gc0_register(18, 1) -#define read_gc0_watchlo2() __read_ulong_gc0_register(18, 2) -#define read_gc0_watchlo3() __read_ulong_gc0_register(18, 3) -#define read_gc0_watchlo4() __read_ulong_gc0_register(18, 4) -#define read_gc0_watchlo5() __read_ulong_gc0_register(18, 5) -#define read_gc0_watchlo6() __read_ulong_gc0_register(18, 6) -#define read_gc0_watchlo7() __read_ulong_gc0_register(18, 7) -#define write_gc0_watchlo0(val) __write_ulong_gc0_register(18, 0, val) -#define write_gc0_watchlo1(val) __write_ulong_gc0_register(18, 1, val) -#define write_gc0_watchlo2(val) __write_ulong_gc0_register(18, 2, val) -#define write_gc0_watchlo3(val) __write_ulong_gc0_register(18, 3, val) -#define write_gc0_watchlo4(val) __write_ulong_gc0_register(18, 4, val) -#define write_gc0_watchlo5(val) __write_ulong_gc0_register(18, 5, val) -#define write_gc0_watchlo6(val) __write_ulong_gc0_register(18, 6, val) -#define write_gc0_watchlo7(val) __write_ulong_gc0_register(18, 7, val) - -#define read_gc0_watchhi0() __read_32bit_gc0_register(19, 0) -#define read_gc0_watchhi1() __read_32bit_gc0_register(19, 1) -#define read_gc0_watchhi2() __read_32bit_gc0_register(19, 2) -#define read_gc0_watchhi3() __read_32bit_gc0_register(19, 3) -#define read_gc0_watchhi4() __read_32bit_gc0_register(19, 4) -#define read_gc0_watchhi5() __read_32bit_gc0_register(19, 5) -#define read_gc0_watchhi6() __read_32bit_gc0_register(19, 6) -#define read_gc0_watchhi7() __read_32bit_gc0_register(19, 7) -#define write_gc0_watchhi0(val) __write_32bit_gc0_register(19, 0, val) -#define write_gc0_watchhi1(val) __write_32bit_gc0_register(19, 1, val) -#define write_gc0_watchhi2(val) __write_32bit_gc0_register(19, 2, val) -#define write_gc0_watchhi3(val) __write_32bit_gc0_register(19, 3, val) -#define write_gc0_watchhi4(val) __write_32bit_gc0_register(19, 4, val) -#define write_gc0_watchhi5(val) __write_32bit_gc0_register(19, 5, val) -#define write_gc0_watchhi6(val) __write_32bit_gc0_register(19, 6, val) -#define write_gc0_watchhi7(val) __write_32bit_gc0_register(19, 7, val) - -#define read_gc0_xcontext() __read_ulong_gc0_register(20, 0) -#define write_gc0_xcontext(val) __write_ulong_gc0_register(20, 0, val) - -#define read_gc0_perfctrl0() __read_32bit_gc0_register(25, 0) -#define write_gc0_perfctrl0(val) __write_32bit_gc0_register(25, 0, val) -#define read_gc0_perfcntr0() __read_32bit_gc0_register(25, 1) -#define write_gc0_perfcntr0(val) __write_32bit_gc0_register(25, 1, val) -#define read_gc0_perfcntr0_64() __read_64bit_gc0_register(25, 1) -#define write_gc0_perfcntr0_64(val) __write_64bit_gc0_register(25, 1, val) -#define read_gc0_perfctrl1() __read_32bit_gc0_register(25, 2) -#define write_gc0_perfctrl1(val) __write_32bit_gc0_register(25, 2, val) -#define read_gc0_perfcntr1() __read_32bit_gc0_register(25, 3) -#define write_gc0_perfcntr1(val) __write_32bit_gc0_register(25, 3, val) -#define read_gc0_perfcntr1_64() __read_64bit_gc0_register(25, 3) -#define write_gc0_perfcntr1_64(val) __write_64bit_gc0_register(25, 3, val) -#define read_gc0_perfctrl2() __read_32bit_gc0_register(25, 4) -#define write_gc0_perfctrl2(val) __write_32bit_gc0_register(25, 4, val) -#define read_gc0_perfcntr2() __read_32bit_gc0_register(25, 5) -#define write_gc0_perfcntr2(val) __write_32bit_gc0_register(25, 5, val) -#define read_gc0_perfcntr2_64() __read_64bit_gc0_register(25, 5) -#define write_gc0_perfcntr2_64(val) __write_64bit_gc0_register(25, 5, val) -#define read_gc0_perfctrl3() __read_32bit_gc0_register(25, 6) -#define write_gc0_perfctrl3(val) __write_32bit_gc0_register(25, 6, val) -#define read_gc0_perfcntr3() __read_32bit_gc0_register(25, 7) -#define write_gc0_perfcntr3(val) __write_32bit_gc0_register(25, 7, val) -#define read_gc0_perfcntr3_64() __read_64bit_gc0_register(25, 7) -#define write_gc0_perfcntr3_64(val) __write_64bit_gc0_register(25, 7, val) - -#define read_gc0_errorepc() __read_ulong_gc0_register(30, 0) -#define write_gc0_errorepc(val) __write_ulong_gc0_register(30, 0, val) - -#define read_gc0_kscratch1() __read_ulong_gc0_register(31, 2) -#define read_gc0_kscratch2() __read_ulong_gc0_register(31, 3) -#define read_gc0_kscratch3() __read_ulong_gc0_register(31, 4) -#define read_gc0_kscratch4() __read_ulong_gc0_register(31, 5) -#define read_gc0_kscratch5() __read_ulong_gc0_register(31, 6) -#define read_gc0_kscratch6() __read_ulong_gc0_register(31, 7) -#define write_gc0_kscratch1(val) __write_ulong_gc0_register(31, 2, val) -#define write_gc0_kscratch2(val) __write_ulong_gc0_register(31, 3, val) -#define write_gc0_kscratch3(val) __write_ulong_gc0_register(31, 4, val) -#define write_gc0_kscratch4(val) __write_ulong_gc0_register(31, 5, val) -#define write_gc0_kscratch5(val) __write_ulong_gc0_register(31, 6, val) -#define write_gc0_kscratch6(val) __write_ulong_gc0_register(31, 7, val) +#define read_gc0_pwctl() __read_32bit_gc0_register($6, 6) +#define write_gc0_pwctl(val) __write_32bit_gc0_register($6, 6, val) + +#define read_gc0_hwrena() __read_32bit_gc0_register($7, 0) +#define write_gc0_hwrena(val) __write_32bit_gc0_register($7, 0, val) + +#define read_gc0_badvaddr() __read_ulong_gc0_register($8, 0) +#define write_gc0_badvaddr(val) __write_ulong_gc0_register($8, 0, val) + +#define read_gc0_badinstr() __read_32bit_gc0_register($8, 1) +#define write_gc0_badinstr(val) __write_32bit_gc0_register($8, 1, val) + +#define read_gc0_badinstrp() __read_32bit_gc0_register($8, 2) +#define write_gc0_badinstrp(val) __write_32bit_gc0_register($8, 2, val) + +#define read_gc0_count() __read_32bit_gc0_register($9, 0) + +#define read_gc0_entryhi() __read_ulong_gc0_register($10, 0) +#define write_gc0_entryhi(val) __write_ulong_gc0_register($10, 0, val) + +#define read_gc0_compare() __read_32bit_gc0_register($11, 0) +#define write_gc0_compare(val) __write_32bit_gc0_register($11, 0, val) + +#define read_gc0_status() __read_32bit_gc0_register($12, 0) +#define write_gc0_status(val) __write_32bit_gc0_register($12, 0, val) + +#define read_gc0_intctl() __read_32bit_gc0_register($12, 1) +#define write_gc0_intctl(val) __write_32bit_gc0_register($12, 1, val) + +#define read_gc0_cause() __read_32bit_gc0_register($13, 0) +#define write_gc0_cause(val) __write_32bit_gc0_register($13, 0, val) + +#define read_gc0_epc() __read_ulong_gc0_register($14, 0) +#define write_gc0_epc(val) __write_ulong_gc0_register($14, 0, val) + +#define read_gc0_prid() __read_32bit_gc0_register($15, 0) + +#define read_gc0_ebase() __read_32bit_gc0_register($15, 1) +#define write_gc0_ebase(val) __write_32bit_gc0_register($15, 1, val) + +#define read_gc0_ebase_64() __read_64bit_gc0_register($15, 1) +#define write_gc0_ebase_64(val) __write_64bit_gc0_register($15, 1, val) + +#define read_gc0_config() __read_32bit_gc0_register($16, 0) +#define read_gc0_config1() __read_32bit_gc0_register($16, 1) +#define read_gc0_config2() __read_32bit_gc0_register($16, 2) +#define read_gc0_config3() __read_32bit_gc0_register($16, 3) +#define read_gc0_config4() __read_32bit_gc0_register($16, 4) +#define read_gc0_config5() __read_32bit_gc0_register($16, 5) +#define read_gc0_config6() __read_32bit_gc0_register($16, 6) +#define read_gc0_config7() __read_32bit_gc0_register($16, 7) +#define write_gc0_config(val) __write_32bit_gc0_register($16, 0, val) +#define write_gc0_config1(val) __write_32bit_gc0_register($16, 1, val) +#define write_gc0_config2(val) __write_32bit_gc0_register($16, 2, val) +#define write_gc0_config3(val) __write_32bit_gc0_register($16, 3, val) +#define write_gc0_config4(val) __write_32bit_gc0_register($16, 4, val) +#define write_gc0_config5(val) __write_32bit_gc0_register($16, 5, val) +#define write_gc0_config6(val) __write_32bit_gc0_register($16, 6, val) +#define write_gc0_config7(val) __write_32bit_gc0_register($16, 7, val) + +#define read_gc0_lladdr() __read_ulong_gc0_register($17, 0) +#define write_gc0_lladdr(val) __write_ulong_gc0_register($17, 0, val) + +#define read_gc0_watchlo0() __read_ulong_gc0_register($18, 0) +#define read_gc0_watchlo1() __read_ulong_gc0_register($18, 1) +#define read_gc0_watchlo2() __read_ulong_gc0_register($18, 2) +#define read_gc0_watchlo3() __read_ulong_gc0_register($18, 3) +#define read_gc0_watchlo4() __read_ulong_gc0_register($18, 4) +#define read_gc0_watchlo5() __read_ulong_gc0_register($18, 5) +#define read_gc0_watchlo6() __read_ulong_gc0_register($18, 6) +#define read_gc0_watchlo7() __read_ulong_gc0_register($18, 7) +#define write_gc0_watchlo0(val) __write_ulong_gc0_register($18, 0, val) +#define write_gc0_watchlo1(val) __write_ulong_gc0_register($18, 1, val) +#define write_gc0_watchlo2(val) __write_ulong_gc0_register($18, 2, val) +#define write_gc0_watchlo3(val) __write_ulong_gc0_register($18, 3, val) +#define write_gc0_watchlo4(val) __write_ulong_gc0_register($18, 4, val) +#define write_gc0_watchlo5(val) __write_ulong_gc0_register($18, 5, val) +#define write_gc0_watchlo6(val) __write_ulong_gc0_register($18, 6, val) +#define write_gc0_watchlo7(val) __write_ulong_gc0_register($18, 7, val) + +#define read_gc0_watchhi0() __read_32bit_gc0_register($19, 0) +#define read_gc0_watchhi1() __read_32bit_gc0_register($19, 1) +#define read_gc0_watchhi2() __read_32bit_gc0_register($19, 2) +#define read_gc0_watchhi3() __read_32bit_gc0_register($19, 3) +#define read_gc0_watchhi4() __read_32bit_gc0_register($19, 4) +#define read_gc0_watchhi5() __read_32bit_gc0_register($19, 5) +#define read_gc0_watchhi6() __read_32bit_gc0_register($19, 6) +#define read_gc0_watchhi7() __read_32bit_gc0_register($19, 7) +#define write_gc0_watchhi0(val) __write_32bit_gc0_register($19, 0, val) +#define write_gc0_watchhi1(val) __write_32bit_gc0_register($19, 1, val) +#define write_gc0_watchhi2(val) __write_32bit_gc0_register($19, 2, val) +#define write_gc0_watchhi3(val) __write_32bit_gc0_register($19, 3, val) +#define write_gc0_watchhi4(val) __write_32bit_gc0_register($19, 4, val) +#define write_gc0_watchhi5(val) __write_32bit_gc0_register($19, 5, val) +#define write_gc0_watchhi6(val) __write_32bit_gc0_register($19, 6, val) +#define write_gc0_watchhi7(val) __write_32bit_gc0_register($19, 7, val) + +#define read_gc0_xcontext() __read_ulong_gc0_register($20, 0) +#define write_gc0_xcontext(val) __write_ulong_gc0_register($20, 0, val) + +#define read_gc0_perfctrl0() __read_32bit_gc0_register($25, 0) +#define write_gc0_perfctrl0(val) __write_32bit_gc0_register($25, 0, val) +#define read_gc0_perfcntr0() __read_32bit_gc0_register($25, 1) +#define write_gc0_perfcntr0(val) __write_32bit_gc0_register($25, 1, val) +#define read_gc0_perfcntr0_64() __read_64bit_gc0_register($25, 1) +#define write_gc0_perfcntr0_64(val) __write_64bit_gc0_register($25, 1, val) +#define read_gc0_perfctrl1() __read_32bit_gc0_register($25, 2) +#define write_gc0_perfctrl1(val) __write_32bit_gc0_register($25, 2, val) +#define read_gc0_perfcntr1() __read_32bit_gc0_register($25, 3) +#define write_gc0_perfcntr1(val) __write_32bit_gc0_register($25, 3, val) +#define read_gc0_perfcntr1_64() __read_64bit_gc0_register($25, 3) +#define write_gc0_perfcntr1_64(val) __write_64bit_gc0_register($25, 3, val) +#define read_gc0_perfctrl2() __read_32bit_gc0_register($25, 4) +#define write_gc0_perfctrl2(val) __write_32bit_gc0_register($25, 4, val) +#define read_gc0_perfcntr2() __read_32bit_gc0_register($25, 5) +#define write_gc0_perfcntr2(val) __write_32bit_gc0_register($25, 5, val) +#define read_gc0_perfcntr2_64() __read_64bit_gc0_register($25, 5) +#define write_gc0_perfcntr2_64(val) __write_64bit_gc0_register($25, 5, val) +#define read_gc0_perfctrl3() __read_32bit_gc0_register($25, 6) +#define write_gc0_perfctrl3(val) __write_32bit_gc0_register($25, 6, val) +#define read_gc0_perfcntr3() __read_32bit_gc0_register($25, 7) +#define write_gc0_perfcntr3(val) __write_32bit_gc0_register($25, 7, val) +#define read_gc0_perfcntr3_64() __read_64bit_gc0_register($25, 7) +#define write_gc0_perfcntr3_64(val) __write_64bit_gc0_register($25, 7, val) + +#define read_gc0_errorepc() __read_ulong_gc0_register($30, 0) +#define write_gc0_errorepc(val) __write_ulong_gc0_register($30, 0, val) + +#define read_gc0_kscratch1() __read_ulong_gc0_register($31, 2) +#define read_gc0_kscratch2() __read_ulong_gc0_register($31, 3) +#define read_gc0_kscratch3() __read_ulong_gc0_register($31, 4) +#define read_gc0_kscratch4() __read_ulong_gc0_register($31, 5) +#define read_gc0_kscratch5() __read_ulong_gc0_register($31, 6) +#define read_gc0_kscratch6() __read_ulong_gc0_register($31, 7) +#define write_gc0_kscratch1(val) __write_ulong_gc0_register($31, 2, val) +#define write_gc0_kscratch2(val) __write_ulong_gc0_register($31, 3, val) +#define write_gc0_kscratch3(val) __write_ulong_gc0_register($31, 4, val) +#define write_gc0_kscratch4(val) __write_ulong_gc0_register($31, 5, val) +#define write_gc0_kscratch5(val) __write_ulong_gc0_register($31, 6, val) +#define write_gc0_kscratch6(val) __write_ulong_gc0_register($31, 7, val) /* Cavium OCTEON (cnMIPS) */ -#define read_gc0_cvmcount() __read_ulong_gc0_register(9, 6) -#define write_gc0_cvmcount(val) __write_ulong_gc0_register(9, 6, val) +#define read_gc0_cvmcount() __read_ulong_gc0_register($9, 6) +#define write_gc0_cvmcount(val) __write_ulong_gc0_register($9, 6, val) -#define read_gc0_cvmctl() __read_64bit_gc0_register(9, 7) -#define write_gc0_cvmctl(val) __write_64bit_gc0_register(9, 7, val) +#define read_gc0_cvmctl() __read_64bit_gc0_register($9, 7) +#define write_gc0_cvmctl(val) __write_64bit_gc0_register($9, 7, val) -#define read_gc0_cvmmemctl() __read_64bit_gc0_register(11, 7) -#define write_gc0_cvmmemctl(val) __write_64bit_gc0_register(11, 7, val) +#define read_gc0_cvmmemctl() __read_64bit_gc0_register($11, 7) +#define write_gc0_cvmmemctl(val) __write_64bit_gc0_register($11, 7, val) -#define read_gc0_cvmmemctl2() __read_64bit_gc0_register(16, 6) -#define write_gc0_cvmmemctl2(val) __write_64bit_gc0_register(16, 6, val) +#define read_gc0_cvmmemctl2() __read_64bit_gc0_register($16, 6) +#define write_gc0_cvmmemctl2(val) __write_64bit_gc0_register($16, 6, val) /* * Macros to access the floating point coprocessor control registers @@ -2581,8 +2651,6 @@ static inline void tlb_write_random(void) ".set reorder"); } -#ifdef TOOLCHAIN_SUPPORTS_VIRT - /* * Guest TLB operations. * @@ -2593,7 +2661,7 @@ static inline void guest_tlb_probe(void) __asm__ __volatile__( ".set push\n\t" ".set noreorder\n\t" - ".set virt\n\t" + _ASM_SET_VIRT "tlbgp\n\t" ".set pop"); } @@ -2603,7 +2671,7 @@ static inline void guest_tlb_read(void) __asm__ __volatile__( ".set push\n\t" ".set noreorder\n\t" - ".set virt\n\t" + _ASM_SET_VIRT "tlbgr\n\t" ".set pop"); } @@ -2613,7 +2681,7 @@ static inline void guest_tlb_write_indexed(void) __asm__ __volatile__( ".set push\n\t" ".set noreorder\n\t" - ".set virt\n\t" + _ASM_SET_VIRT "tlbgwi\n\t" ".set pop"); } @@ -2623,7 +2691,7 @@ static inline void guest_tlb_write_random(void) __asm__ __volatile__( ".set push\n\t" ".set noreorder\n\t" - ".set virt\n\t" + _ASM_SET_VIRT "tlbgwr\n\t" ".set pop"); } @@ -2636,63 +2704,11 @@ static inline void guest_tlbinvf(void) __asm__ __volatile__( ".set push\n\t" ".set noreorder\n\t" - ".set virt\n\t" + _ASM_SET_VIRT "tlbginvf\n\t" ".set pop"); } -#else /* TOOLCHAIN_SUPPORTS_VIRT */ - -/* - * Guest TLB operations. - * - * It is responsibility of the caller to take care of any TLB hazards. - */ -static inline void guest_tlb_probe(void) -{ - __asm__ __volatile__( - "# tlbgp\n\t" - _ASM_INSN_IF_MIPS(0x42000010) - _ASM_INSN32_IF_MM(0x0000017c)); -} - -static inline void guest_tlb_read(void) -{ - __asm__ __volatile__( - "# tlbgr\n\t" - _ASM_INSN_IF_MIPS(0x42000009) - _ASM_INSN32_IF_MM(0x0000117c)); -} - -static inline void guest_tlb_write_indexed(void) -{ - __asm__ __volatile__( - "# tlbgwi\n\t" - _ASM_INSN_IF_MIPS(0x4200000a) - _ASM_INSN32_IF_MM(0x0000217c)); -} - -static inline void guest_tlb_write_random(void) -{ - __asm__ __volatile__( - "# tlbgwr\n\t" - _ASM_INSN_IF_MIPS(0x4200000e) - _ASM_INSN32_IF_MM(0x0000317c)); -} - -/* - * Guest TLB Invalidate Flush - */ -static inline void guest_tlbinvf(void) -{ - __asm__ __volatile__( - "# tlbginvf\n\t" - _ASM_INSN_IF_MIPS(0x4200000c) - _ASM_INSN32_IF_MM(0x0000517c)); -} - -#endif /* !TOOLCHAIN_SUPPORTS_VIRT */ - /* * Manipulate bits in a register. */ diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h index b1845102f8f9..b4f9577ed96a 100644 --- a/arch/mips/include/asm/msa.h +++ b/arch/mips/include/asm/msa.h @@ -160,7 +160,23 @@ static inline void init_msa_upper(void) _init_msa_upper(); } -#ifdef TOOLCHAIN_SUPPORTS_MSA +#ifndef TOOLCHAIN_SUPPORTS_MSA +/* + * Define assembler macros using .word for the c[ft]cmsa instructions in order + * to allow compilation with toolchains that do not support MSA. Once all + * toolchains in use support MSA these can be removed. + */ +_ASM_MACRO_2R(cfcmsa, rd, cs, + _ASM_INSN_IF_MIPS(0x787e0019 | __cs << 11 | __rd << 6) + _ASM_INSN32_IF_MM(0x587e0016 | __cs << 11 | __rd << 6)); +_ASM_MACRO_2R(ctcmsa, cd, rs, + _ASM_INSN_IF_MIPS(0x783e0019 | __rs << 11 | __cd << 6) + _ASM_INSN32_IF_MM(0x583e0016 | __rs << 11 | __cd << 6)); +#define _ASM_SET_MSA "" +#else /* TOOLCHAIN_SUPPORTS_MSA */ +#define _ASM_SET_MSA ".set\tfp=64\n\t" \ + ".set\tmsa\n\t" +#endif #define __BUILD_MSA_CTL_REG(name, cs) \ static inline unsigned int read_msa_##name(void) \ @@ -168,8 +184,7 @@ static inline unsigned int read_msa_##name(void) \ unsigned int reg; \ __asm__ __volatile__( \ " .set push\n" \ - " .set fp=64\n" \ - " .set msa\n" \ + _ASM_SET_MSA \ " cfcmsa %0, $" #cs "\n" \ " .set pop\n" \ : "=r"(reg)); \ @@ -180,52 +195,12 @@ static inline void write_msa_##name(unsigned int val) \ { \ __asm__ __volatile__( \ " .set push\n" \ - " .set fp=64\n" \ - " .set msa\n" \ + _ASM_SET_MSA \ " ctcmsa $" #cs ", %0\n" \ " .set pop\n" \ : : "r"(val)); \ } -#else /* !TOOLCHAIN_SUPPORTS_MSA */ - -/* - * Define functions using .word for the c[ft]cmsa instructions in order to - * allow compilation with toolchains that do not support MSA. Once all - * toolchains in use support MSA these can be removed. - */ - -#define __BUILD_MSA_CTL_REG(name, cs) \ -static inline unsigned int read_msa_##name(void) \ -{ \ - unsigned int reg; \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noat\n" \ - " # cfcmsa $1, $%1\n" \ - _ASM_INSN_IF_MIPS(0x787e0059 | %1 << 11) \ - _ASM_INSN32_IF_MM(0x587e0056 | %1 << 11) \ - " move %0, $1\n" \ - " .set pop\n" \ - : "=r"(reg) : "i"(cs)); \ - return reg; \ -} \ - \ -static inline void write_msa_##name(unsigned int val) \ -{ \ - __asm__ __volatile__( \ - " .set push\n" \ - " .set noat\n" \ - " move $1, %0\n" \ - " # ctcmsa $%1, $1\n" \ - _ASM_INSN_IF_MIPS(0x783e0819 | %1 << 6) \ - _ASM_INSN32_IF_MM(0x583e0816 | %1 << 6) \ - " .set pop\n" \ - : : "r"(val), "i"(cs)); \ -} - -#endif /* !TOOLCHAIN_SUPPORTS_MSA */ - __BUILD_MSA_CTL_REG(ir, 0) __BUILD_MSA_CTL_REG(csr, 1) __BUILD_MSA_CTL_REG(access, 2) diff --git a/arch/mips/include/uapi/asm/poll.h b/arch/mips/include/uapi/asm/poll.h index 3173f8917128..ad289d7b7434 100644 --- a/arch/mips/include/uapi/asm/poll.h +++ b/arch/mips/include/uapi/asm/poll.h @@ -2,25 +2,8 @@ #ifndef __ASM_POLL_H #define __ASM_POLL_H -#ifndef __KERNEL__ #define POLLWRNORM POLLOUT -#define POLLWRBAND (__force __poll_t)0x0100 -#else -#define __ARCH_HAS_MANGLED_POLL -static inline __u16 mangle_poll(__poll_t val) -{ - __u16 v = (__force __u16)val; - /* bit 9 -> bit 8, bit 8 -> bit 2 */ - return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6); -} - -static inline __poll_t demangle_poll(__u16 v) -{ - /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */ - return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) | - ((v & 4) << 6)); -} -#endif +#define POLLWRBAND 0x0100 #include <asm-generic/poll.h> diff --git a/arch/mips/jz4740/Kconfig b/arch/mips/jz4740/Kconfig index 643af2012e14..4dd0c446ecec 100644 --- a/arch/mips/jz4740/Kconfig +++ b/arch/mips/jz4740/Kconfig @@ -8,6 +8,10 @@ config JZ4740_QI_LB60 bool "Qi Hardware Ben NanoNote" select MACH_JZ4740 +config JZ4770_GCW0 + bool "Game Consoles Worldwide GCW Zero" + select MACH_JZ4770 + config JZ4780_CI20 bool "MIPS Creator CI20" select MACH_JZ4780 @@ -18,6 +22,12 @@ config MACH_JZ4740 bool select SYS_HAS_CPU_MIPS32_R1 +config MACH_JZ4770 + bool + select MIPS_CPU_SCACHE + select SYS_HAS_CPU_MIPS32_R2 + select SYS_SUPPORTS_HIGHMEM + config MACH_JZ4780 bool select MIPS_CPU_SCACHE diff --git a/arch/mips/jz4740/prom.c b/arch/mips/jz4740/prom.c index 47e857194ce6..eb9f2f97bedb 100644 --- a/arch/mips/jz4740/prom.c +++ b/arch/mips/jz4740/prom.c @@ -20,33 +20,12 @@ #include <linux/serial_reg.h> #include <asm/bootinfo.h> +#include <asm/fw/fw.h> #include <asm/mach-jz4740/base.h> -static __init void jz4740_init_cmdline(int argc, char *argv[]) -{ - unsigned int count = COMMAND_LINE_SIZE - 1; - int i; - char *dst = &(arcs_cmdline[0]); - char *src; - - for (i = 1; i < argc && count; ++i) { - src = argv[i]; - while (*src && count) { - *dst++ = *src++; - --count; - } - *dst++ = ' '; - } - if (i > 1) - --dst; - - *dst = 0; -} - void __init prom_init(void) { - jz4740_init_cmdline((int)fw_arg0, (char **)fw_arg1); - mips_machtype = MACH_INGENIC_JZ4740; + fw_init_cmdline(); } void __init prom_free_prom_memory(void) diff --git a/arch/mips/jz4740/setup.c b/arch/mips/jz4740/setup.c index 6d0152321819..afb40f8bce96 100644 --- a/arch/mips/jz4740/setup.c +++ b/arch/mips/jz4740/setup.c @@ -53,6 +53,16 @@ static void __init jz4740_detect_mem(void) add_memory_region(0, size, BOOT_MEM_RAM); } +static unsigned long __init get_board_mach_type(const void *fdt) +{ + if (!fdt_node_check_compatible(fdt, 0, "ingenic,jz4780")) + return MACH_INGENIC_JZ4780; + if (!fdt_node_check_compatible(fdt, 0, "ingenic,jz4770")) + return MACH_INGENIC_JZ4770; + + return MACH_INGENIC_JZ4740; +} + void __init plat_mem_setup(void) { int offset; @@ -63,6 +73,8 @@ void __init plat_mem_setup(void) offset = fdt_path_offset(__dtb_start, "/memory"); if (offset < 0) jz4740_detect_mem(); + + mips_machtype = get_board_mach_type(__dtb_start); } void __init device_tree_init(void) @@ -75,10 +87,14 @@ void __init device_tree_init(void) const char *get_system_type(void) { - if (IS_ENABLED(CONFIG_MACH_JZ4780)) + switch (mips_machtype) { + case MACH_INGENIC_JZ4780: return "JZ4780"; - - return "JZ4740"; + case MACH_INGENIC_JZ4770: + return "JZ4770"; + default: + return "JZ4740"; + } } void __init arch_init_irq(void) diff --git a/arch/mips/jz4740/time.c b/arch/mips/jz4740/time.c index bb1ad5119da4..2ca9160f642a 100644 --- a/arch/mips/jz4740/time.c +++ b/arch/mips/jz4740/time.c @@ -113,7 +113,7 @@ static struct clock_event_device jz4740_clockevent = { #ifdef CONFIG_MACH_JZ4740 .irq = JZ4740_IRQ_TCU0, #endif -#ifdef CONFIG_MACH_JZ4780 +#if defined(CONFIG_MACH_JZ4770) || defined(CONFIG_MACH_JZ4780) .irq = JZ4780_IRQ_TCU2, #endif }; diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index b79ed9af9886..e48f6c0a9e4a 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -399,7 +399,7 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs) * * @regs: Pointer to pt_regs * @insn: branch instruction to decode - * @returns: -EFAULT on error and forces SIGILL, and on success + * Return: -EFAULT on error and forces SIGILL, and on success * returns 0 or BRANCH_LIKELY_TAKEN as appropriate after * evaluating the branch. * diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index e68e6e04063a..1025f937ab0e 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -388,15 +388,16 @@ LEAF(mips_cps_boot_vpes) #elif defined(CONFIG_MIPS_MT) - .set push - .set MIPS_ISA_LEVEL_RAW - .set mt - /* If the core doesn't support MT then return */ has_mt t0, 5f /* Enter VPE configuration state */ + .set push + .set MIPS_ISA_LEVEL_RAW + .set mt dvpe + .set pop + PTR_LA t1, 1f jr.hb t1 nop @@ -422,6 +423,10 @@ LEAF(mips_cps_boot_vpes) mtc0 t0, CP0_VPECONTROL ehb + .set push + .set MIPS_ISA_LEVEL_RAW + .set mt + /* Skip the VPE if its TC is not halted */ mftc0 t0, CP0_TCHALT beqz t0, 2f @@ -495,6 +500,8 @@ LEAF(mips_cps_boot_vpes) ehb evpe + .set pop + /* Check whether this VPE is meant to be running */ li t0, 1 sll t0, t0, a1 @@ -509,7 +516,7 @@ LEAF(mips_cps_boot_vpes) 1: jr.hb t0 nop -2: .set pop +2: #endif /* CONFIG_MIPS_MT_SMP */ diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 99285be0e088..7f3dfdbc3657 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -361,7 +361,7 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, * If fails when getting the stack address of the non-leaf function's * ra, stop function graph tracer and return */ - if (parent_ra_addr == 0) + if (parent_ra_addr == NULL) goto out; #endif /* *parent_ra_addr = return_hooker; */ diff --git a/arch/mips/kernel/rtlx.c b/arch/mips/kernel/rtlx.c index bbb0f4770c0d..18c509c59f33 100644 --- a/arch/mips/kernel/rtlx.c +++ b/arch/mips/kernel/rtlx.c @@ -349,11 +349,11 @@ static __poll_t file_poll(struct file *file, poll_table *wait) /* data available to read? */ if (rtlx_read_poll(minor, 0)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* space to write */ if (rtlx_write_poll(minor)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 702c678de116..85bc601e9a0d 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -826,25 +826,6 @@ static void __init arch_mem_init(char **cmdline_p) struct memblock_region *reg; extern void plat_mem_setup(void); - /* call board setup routine */ - plat_mem_setup(); - - /* - * Make sure all kernel memory is in the maps. The "UP" and - * "DOWN" are opposite for initdata since if it crosses over - * into another memory section you don't want that to be - * freed when the initdata is freed. - */ - arch_mem_addpart(PFN_DOWN(__pa_symbol(&_text)) << PAGE_SHIFT, - PFN_UP(__pa_symbol(&_edata)) << PAGE_SHIFT, - BOOT_MEM_RAM); - arch_mem_addpart(PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT, - PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT, - BOOT_MEM_INIT_RAM); - - pr_info("Determined physical RAM map:\n"); - print_memory_map(); - #if defined(CONFIG_CMDLINE_BOOL) && defined(CONFIG_CMDLINE_OVERRIDE) strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); #else @@ -872,6 +853,26 @@ static void __init arch_mem_init(char **cmdline_p) } #endif #endif + + /* call board setup routine */ + plat_mem_setup(); + + /* + * Make sure all kernel memory is in the maps. The "UP" and + * "DOWN" are opposite for initdata since if it crosses over + * into another memory section you don't want that to be + * freed when the initdata is freed. + */ + arch_mem_addpart(PFN_DOWN(__pa_symbol(&_text)) << PAGE_SHIFT, + PFN_UP(__pa_symbol(&_edata)) << PAGE_SHIFT, + BOOT_MEM_RAM); + arch_mem_addpart(PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT, + PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT, + BOOT_MEM_INIT_RAM); + + pr_info("Determined physical RAM map:\n"); + print_memory_map(); + strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index ecc1a853f48d..03f1026ad148 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -439,8 +439,6 @@ void play_dead(void) pr_debug("CPU%d going offline\n", cpu); if (cpu_has_mipsmt || cpu_has_vp) { - core = cpu_core(&cpu_data[cpu]); - /* Look for another online VPE within the core */ for_each_online_cpu(cpu_death_sibling) { if (!cpus_are_siblings(cpu, cpu_death_sibling)) diff --git a/arch/mips/kernel/watch.c b/arch/mips/kernel/watch.c index 19fcab7348b1..0e61a5b7647f 100644 --- a/arch/mips/kernel/watch.c +++ b/arch/mips/kernel/watch.c @@ -18,27 +18,24 @@ void mips_install_watch_registers(struct task_struct *t) { struct mips3264_watch_reg_state *watches = &t->thread.watch.mips3264; + unsigned int watchhi = MIPS_WATCHHI_G | /* Trap all ASIDs */ + MIPS_WATCHHI_IRW; /* Clear result bits */ + switch (current_cpu_data.watch_reg_use_cnt) { default: BUG(); case 4: write_c0_watchlo3(watches->watchlo[3]); - /* Write 1 to the I, R, and W bits to clear them, and - 1 to G so all ASIDs are trapped. */ - write_c0_watchhi3(MIPS_WATCHHI_G | MIPS_WATCHHI_IRW | - watches->watchhi[3]); + write_c0_watchhi3(watchhi | watches->watchhi[3]); case 3: write_c0_watchlo2(watches->watchlo[2]); - write_c0_watchhi2(MIPS_WATCHHI_G | MIPS_WATCHHI_IRW | - watches->watchhi[2]); + write_c0_watchhi2(watchhi | watches->watchhi[2]); case 2: write_c0_watchlo1(watches->watchlo[1]); - write_c0_watchhi1(MIPS_WATCHHI_G | MIPS_WATCHHI_IRW | - watches->watchhi[1]); + write_c0_watchhi1(watchhi | watches->watchhi[1]); case 1: write_c0_watchlo0(watches->watchlo[0]); - write_c0_watchhi0(MIPS_WATCHHI_G | MIPS_WATCHHI_IRW | - watches->watchhi[0]); + write_c0_watchhi0(watchhi | watches->watchhi[0]); } } @@ -51,21 +48,19 @@ void mips_read_watch_registers(void) { struct mips3264_watch_reg_state *watches = ¤t->thread.watch.mips3264; + unsigned int watchhi_mask = MIPS_WATCHHI_MASK | MIPS_WATCHHI_IRW; + switch (current_cpu_data.watch_reg_use_cnt) { default: BUG(); case 4: - watches->watchhi[3] = (read_c0_watchhi3() & - (MIPS_WATCHHI_MASK | MIPS_WATCHHI_IRW)); + watches->watchhi[3] = (read_c0_watchhi3() & watchhi_mask); case 3: - watches->watchhi[2] = (read_c0_watchhi2() & - (MIPS_WATCHHI_MASK | MIPS_WATCHHI_IRW)); + watches->watchhi[2] = (read_c0_watchhi2() & watchhi_mask); case 2: - watches->watchhi[1] = (read_c0_watchhi1() & - (MIPS_WATCHHI_MASK | MIPS_WATCHHI_IRW)); + watches->watchhi[1] = (read_c0_watchhi1() & watchhi_mask); case 1: - watches->watchhi[0] = (read_c0_watchhi0() & - (MIPS_WATCHHI_MASK | MIPS_WATCHHI_IRW)); + watches->watchhi[0] = (read_c0_watchhi0() & watchhi_mask); } if (current_cpu_data.watch_reg_use_cnt == 1 && (watches->watchhi[0] & MIPS_WATCHHI_IRW) == 0) { diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index b17447ce8873..76b93a9c8c9b 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -22,6 +22,7 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select KVM_GENERIC_DIRTYLOG_READ_PROTECT + select HAVE_KVM_VCPU_ASYNC_IOCTL select KVM_MMIO select MMU_NOTIFIER select SRCU diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 75fdeaa8c62f..2549fdd27ee1 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -446,6 +446,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) { int r = -EINTR; + vcpu_load(vcpu); + kvm_sigset_activate(vcpu); if (vcpu->mmio_needed) { @@ -480,6 +482,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) out: kvm_sigset_deactivate(vcpu); + vcpu_put(vcpu); return r; } @@ -900,6 +903,26 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return r; } +long kvm_arch_vcpu_async_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + + if (ioctl == KVM_INTERRUPT) { + struct kvm_mips_interrupt irq; + + if (copy_from_user(&irq, argp, sizeof(irq))) + return -EFAULT; + kvm_debug("[%d] %s: irq: %d\n", vcpu->vcpu_id, __func__, + irq.irq); + + return kvm_vcpu_ioctl_interrupt(vcpu, &irq); + } + + return -ENOIOCTLCMD; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -907,56 +930,54 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, void __user *argp = (void __user *)arg; long r; + vcpu_load(vcpu); + switch (ioctl) { case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; + r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) - return -EFAULT; + break; if (ioctl == KVM_SET_ONE_REG) - return kvm_mips_set_reg(vcpu, ®); + r = kvm_mips_set_reg(vcpu, ®); else - return kvm_mips_get_reg(vcpu, ®); + r = kvm_mips_get_reg(vcpu, ®); + break; } case KVM_GET_REG_LIST: { struct kvm_reg_list __user *user_list = argp; struct kvm_reg_list reg_list; unsigned n; + r = -EFAULT; if (copy_from_user(®_list, user_list, sizeof(reg_list))) - return -EFAULT; + break; n = reg_list.n; reg_list.n = kvm_mips_num_regs(vcpu); if (copy_to_user(user_list, ®_list, sizeof(reg_list))) - return -EFAULT; + break; + r = -E2BIG; if (n < reg_list.n) - return -E2BIG; - return kvm_mips_copy_reg_indices(vcpu, user_list->reg); - } - case KVM_INTERRUPT: - { - struct kvm_mips_interrupt irq; - - if (copy_from_user(&irq, argp, sizeof(irq))) - return -EFAULT; - kvm_debug("[%d] %s: irq: %d\n", vcpu->vcpu_id, __func__, - irq.irq); - - r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; - } + r = kvm_mips_copy_reg_indices(vcpu, user_list->reg); + break; + } case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; + r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) - return -EFAULT; + break; r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); break; } default: r = -ENOIOCTLCMD; } + + vcpu_put(vcpu); return r; } @@ -1145,6 +1166,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + for (i = 1; i < ARRAY_SIZE(vcpu->arch.gprs); i++) vcpu->arch.gprs[i] = regs->gpr[i]; vcpu->arch.gprs[0] = 0; /* zero is special, and cannot be set. */ @@ -1152,6 +1175,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) vcpu->arch.lo = regs->lo; vcpu->arch.pc = regs->pc; + vcpu_put(vcpu); return 0; } @@ -1159,6 +1183,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.gprs); i++) regs->gpr[i] = vcpu->arch.gprs[i]; @@ -1166,6 +1192,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) regs->lo = vcpu->arch.lo; regs->pc = vcpu->arch.pc; + vcpu_put(vcpu); return 0; } diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig index 6f109bb54cdb..bc2fdbfa8223 100644 --- a/arch/mips/loongson64/Kconfig +++ b/arch/mips/loongson64/Kconfig @@ -17,7 +17,6 @@ config LEMOTE_FULOONG2E select I8259 select ISA select IRQ_MIPS_CPU - select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_HIGHMEM @@ -49,7 +48,6 @@ config LEMOTE_MACH2F select ISA select SYS_HAS_CPU_LOONGSON2F select SYS_HAS_EARLY_PRINTK - select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_HIGHMEM select SYS_SUPPORTS_LITTLE_ENDIAN diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c index b01d52473da8..c549e525fc11 100644 --- a/arch/mips/loongson64/common/mem.c +++ b/arch/mips/loongson64/common/mem.c @@ -79,7 +79,7 @@ void __init prom_init_memory(void) (u64)loongson_memmap->map[i].mem_size << 20, BOOT_MEM_RAM); break; - case MEM_RESERVED: + case SYSTEM_RAM_RESERVED: add_memory_region(loongson_memmap->map[i].mem_start, (u64)loongson_memmap->map[i].mem_size << 20, BOOT_MEM_RESERVED); diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index f17ef520799a..9717106de4a5 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -166,7 +166,7 @@ static void __init szmem(unsigned int node) memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), node); break; - case MEM_RESERVED: + case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", (u32)node_id, mem_type, mem_start, mem_size); add_memory_region((node_id << 44) + mem_start, diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index da6c1c0c30c1..62deb025970b 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -451,7 +451,7 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; } - /* Fall through */ + /* fall through */ case jr_op: /* For R6, JR already emulated in jalr_op */ if (NO_R6EMU && insn.r_format.func == jr_op) @@ -471,10 +471,11 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, regs->regs[31] = regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ + /* fall through */ case bltzl_op: if (NO_R6EMU) break; + /* fall through */ case bltz_op: if ((long)regs->regs[insn.i_format.rs] < 0) *contpc = regs->cp0_epc + @@ -494,10 +495,11 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, regs->regs[31] = regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ + /* fall through */ case bgezl_op: if (NO_R6EMU) break; + /* fall through */ case bgez_op: if ((long)regs->regs[insn.i_format.rs] >= 0) *contpc = regs->cp0_epc + @@ -512,11 +514,12 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, break; case jalx_op: set_isa16_mode(bit); + /* fall through */ case jal_op: regs->regs[31] = regs->cp0_epc + dec_insn.pc_inc + dec_insn.next_pc_inc; - /* Fall through */ + /* fall through */ case j_op: *contpc = regs->cp0_epc + dec_insn.pc_inc; *contpc >>= 28; @@ -528,6 +531,7 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case beql_op: if (NO_R6EMU) break; + /* fall through */ case beq_op: if (regs->regs[insn.i_format.rs] == regs->regs[insn.i_format.rt]) @@ -542,6 +546,7 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case bnel_op: if (NO_R6EMU) break; + /* fall through */ case bne_op: if (regs->regs[insn.i_format.rs] != regs->regs[insn.i_format.rt]) @@ -556,6 +561,7 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case blezl_op: if (!insn.i_format.rt && NO_R6EMU) break; + /* fall through */ case blez_op: /* @@ -593,6 +599,7 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case bgtzl_op: if (!insn.i_format.rt && NO_R6EMU) break; + /* fall through */ case bgtz_op: /* * Compact branches for R6 for the @@ -729,7 +736,8 @@ int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, return 1; } - /* R2/R6 compatible cop1 instruction. Fall through */ + /* R2/R6 compatible cop1 instruction */ + /* fall through */ case cop2_op: case cop1x_op: if (insn.i_format.rs == bc_op) { @@ -1190,7 +1198,8 @@ emul: if (!cpu_has_mips_r6 || delay_slot(xcp)) return SIGILL; - cond = likely = 0; + likely = 0; + cond = 0; fpr = ¤t->thread.fpu.fpr[MIPSInst_RT(ir)]; bit0 = get_fpr32(fpr, 0) & 0x1; switch (MIPSInst_RS(ir)) { @@ -1220,14 +1229,14 @@ emul: case bcfl_op: if (cpu_has_mips_2_3_4_5_r) likely = 1; - /* Fall through */ + /* fall through */ case bcf_op: cond = !cond; break; case bctl_op: if (cpu_has_mips_2_3_4_5_r) likely = 1; - /* Fall through */ + /* fall through */ case bct_op: break; } @@ -1353,7 +1362,8 @@ branch_common: return SIGILL; /* a real fpu computation instruction */ - if ((sig = fpu_emu(xcp, ctx, ir))) + sig = fpu_emu(xcp, ctx, ir); + if (sig) return sig; } break; diff --git a/arch/mips/math-emu/dp_add.c b/arch/mips/math-emu/dp_add.c index 8954ef031f84..678de20e4cb1 100644 --- a/arch/mips/math-emu/dp_add.c +++ b/arch/mips/math-emu/dp_add.c @@ -104,8 +104,7 @@ union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; - - /* FALL THROUGH */ + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_div.c b/arch/mips/math-emu/dp_div.c index f4746f7c5f63..3063ae3ab3b9 100644 --- a/arch/mips/math-emu/dp_div.c +++ b/arch/mips/math-emu/dp_div.c @@ -103,6 +103,7 @@ union ieee754dp ieee754dp_div(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c index 5bec64f2884e..d1f984b40344 100644 --- a/arch/mips/math-emu/dp_fmax.c +++ b/arch/mips/math-emu/dp_fmax.c @@ -96,6 +96,7 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; @@ -224,6 +225,7 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c index a287b23818d8..f98b96135c8d 100644 --- a/arch/mips/math-emu/dp_fmin.c +++ b/arch/mips/math-emu/dp_fmin.c @@ -96,6 +96,7 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; @@ -224,6 +225,7 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c index 7ad79ed411f5..7ea2f8222026 100644 --- a/arch/mips/math-emu/dp_maddf.c +++ b/arch/mips/math-emu/dp_maddf.c @@ -16,7 +16,7 @@ /* 128 bits shift right logical with rounding. */ -void srl128(u64 *hptr, u64 *lptr, int count) +static void srl128(u64 *hptr, u64 *lptr, int count) { u64 low; @@ -157,6 +157,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): if (zc == IEEE754_CLASS_INF) @@ -173,7 +174,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); - /* fall through to real computations */ + /* continue to real computations */ } /* Finally get to do some computation */ @@ -201,9 +202,6 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, * Multiply 64 bits xm and ym to give 128 bits result in hrm:lrm. */ - /* 32 * 32 => 64 */ -#define DPXMULT(x, y) ((u64)(x) * (u64)y) - lxm = xm; hxm = xm >> 32; lym = ym; diff --git a/arch/mips/math-emu/dp_mul.c b/arch/mips/math-emu/dp_mul.c index 60c8bfe40947..c34a6cdf1b25 100644 --- a/arch/mips/math-emu/dp_mul.c +++ b/arch/mips/math-emu/dp_mul.c @@ -101,6 +101,7 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): DPDNORMY; @@ -128,9 +129,6 @@ union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y) * Multiply 64 bits xm, ym to give high 64 bits rm with stickness. */ - /* 32 * 32 => 64 */ -#define DPXMULT(x, y) ((u64)(x) * (u64)y) - lxm = xm; hxm = xm >> 32; lym = ym; diff --git a/arch/mips/math-emu/dp_sqrt.c b/arch/mips/math-emu/dp_sqrt.c index cea907b83146..1d26c92e5295 100644 --- a/arch/mips/math-emu/dp_sqrt.c +++ b/arch/mips/math-emu/dp_sqrt.c @@ -91,7 +91,8 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x) scalx -= 256; } - y = x = builddp(0, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); + x = builddp(0, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT); + y = x; /* magic initial approximation to almost 8 sig. bits */ yh = y.bits >> 32; @@ -108,7 +109,8 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x) /* triple to almost 56 sig. bits: y ~= sqrt(x) to within 1 ulp */ /* t=y*y; z=t; pt[n0]+=0x00100000; t+=z; z=(x-z)*y; */ - z = t = ieee754dp_mul(y, y); + t = ieee754dp_mul(y, y); + z = t; t.bexp += 0x001; t = ieee754dp_add(t, z); z = ieee754dp_mul(ieee754dp_sub(x, z), y); @@ -140,7 +142,7 @@ union ieee754dp ieee754dp_sqrt(union ieee754dp x) switch (oldcsr.rm) { case FPU_CSR_RU: y.bits += 1; - /* drop through */ + /* fall through */ case FPU_CSR_RN: t.bits += 1; break; diff --git a/arch/mips/math-emu/dp_sub.c b/arch/mips/math-emu/dp_sub.c index fc17a781b9ae..3cc48b86519b 100644 --- a/arch/mips/math-emu/dp_sub.c +++ b/arch/mips/math-emu/dp_sub.c @@ -106,7 +106,7 @@ union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; - /* FALL THROUGH */ + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): /* normalize ym,ye */ diff --git a/arch/mips/math-emu/ieee754dp.h b/arch/mips/math-emu/ieee754dp.h index 9ba023004eb6..a56707b75282 100644 --- a/arch/mips/math-emu/ieee754dp.h +++ b/arch/mips/math-emu/ieee754dp.h @@ -55,6 +55,9 @@ static inline int ieee754dp_finite(union ieee754dp x) #define XDPSRS1(v) \ (((v) >> 1) | ((v) & 1)) +/* 32bit * 32bit => 64bit unsigned integer multiplication */ +#define DPXMULT(x, y) ((u64)(x) * (u64)y) + /* convert denormal to normalized with extended exponent */ #define DPDNORMx(m,e) \ while ((m >> DP_FBITS) == 0) { m <<= 1; e--; } diff --git a/arch/mips/math-emu/sp_add.c b/arch/mips/math-emu/sp_add.c index c55c0c00bca8..51dced9fbdaf 100644 --- a/arch/mips/math-emu/sp_add.c +++ b/arch/mips/math-emu/sp_add.c @@ -104,8 +104,7 @@ union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; - - /* FALL THROUGH */ + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_div.c b/arch/mips/math-emu/sp_div.c index 23587b31ca87..5d2904960eb8 100644 --- a/arch/mips/math-emu/sp_div.c +++ b/arch/mips/math-emu/sp_div.c @@ -103,6 +103,7 @@ union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_fdp.c b/arch/mips/math-emu/sp_fdp.c index 5060e8fdcb0b..36a50f9082d1 100644 --- a/arch/mips/math-emu/sp_fdp.c +++ b/arch/mips/math-emu/sp_fdp.c @@ -46,7 +46,8 @@ union ieee754sp ieee754sp_fdp(union ieee754dp x) case IEEE754_CLASS_SNAN: x = ieee754dp_nanxcpt(x); EXPLODEXDP; - /* Fall through. */ + /* fall through */ + case IEEE754_CLASS_QNAN: y = ieee754sp_nan_fdp(xs, xm); if (!ieee754_csr.nan2008) { diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c index 74a5a00d2f22..22019ed691df 100644 --- a/arch/mips/math-emu/sp_fmax.c +++ b/arch/mips/math-emu/sp_fmax.c @@ -96,6 +96,7 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; @@ -224,6 +225,7 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c index c51385f46b09..feaec3985cca 100644 --- a/arch/mips/math-emu/sp_fmin.c +++ b/arch/mips/math-emu/sp_fmin.c @@ -96,6 +96,7 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; @@ -224,6 +225,7 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c index f823338dbb65..07ba675401e2 100644 --- a/arch/mips/math-emu/sp_maddf.c +++ b/arch/mips/math-emu/sp_maddf.c @@ -126,6 +126,7 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): if (zc == IEEE754_CLASS_INF) @@ -142,7 +143,7 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); - /* fall through to real computations */ + /* continue to real computations */ } /* Finally get to do some computation */ diff --git a/arch/mips/math-emu/sp_mul.c b/arch/mips/math-emu/sp_mul.c index 4015101fbc37..fde71e293ec4 100644 --- a/arch/mips/math-emu/sp_mul.c +++ b/arch/mips/math-emu/sp_mul.c @@ -101,6 +101,7 @@ union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_sqrt.c b/arch/mips/math-emu/sp_sqrt.c index 67059c33a250..9cc83f012342 100644 --- a/arch/mips/math-emu/sp_sqrt.c +++ b/arch/mips/math-emu/sp_sqrt.c @@ -82,7 +82,8 @@ union ieee754sp ieee754sp_sqrt(union ieee754sp x) /* generate sqrt(x) bit by bit */ ix += ix; - q = s = 0; /* q = sqrt(x) */ + s = 0; + q = 0; /* q = sqrt(x) */ r = 0x01000000; /* r = moving bit from right to left */ while (r != 0) { diff --git a/arch/mips/math-emu/sp_sub.c b/arch/mips/math-emu/sp_sub.c index dc998ed47295..9f2ff72c3d6b 100644 --- a/arch/mips/math-emu/sp_sub.c +++ b/arch/mips/math-emu/sp_sub.c @@ -106,6 +106,7 @@ union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; + /* fall through */ case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): SPDNORMY; diff --git a/arch/mips/math-emu/sp_tlong.c b/arch/mips/math-emu/sp_tlong.c index a2450c7e452a..bca5ac995801 100644 --- a/arch/mips/math-emu/sp_tlong.c +++ b/arch/mips/math-emu/sp_tlong.c @@ -20,7 +20,6 @@ */ #include "ieee754sp.h" -#include "ieee754dp.h" s64 ieee754sp_tlong(union ieee754sp x) { diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index 237532e89919..dcafa43613b6 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -370,11 +370,6 @@ static void mips_dma_sync_sg_for_device(struct device *dev, } } -static int mips_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - return 0; -} - static int mips_dma_supported(struct device *dev, u64 mask) { return plat_dma_supported(dev, mask); @@ -401,7 +396,6 @@ static const struct dma_map_ops mips_default_dma_map_ops = { .sync_single_for_device = mips_dma_sync_single_for_device, .sync_sg_for_cpu = mips_dma_sync_sg_for_cpu, .sync_sg_for_device = mips_dma_sync_sg_for_device, - .mapping_error = mips_dma_mapping_error, .dma_supported = mips_dma_supported, .cache_sync = mips_dma_cache_sync, }; diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 548acb7f8557..394673991bab 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -16,6 +16,7 @@ #include <asm/mmu_context.h> #include <asm/r4kcache.h> #include <asm/mips-cps.h> +#include <asm/bootinfo.h> /* * MIPS32/MIPS64 L2 cache handling @@ -220,6 +221,14 @@ static inline int __init mips_sc_probe(void) else return 0; + /* + * According to config2 it would be 5-ways, but that is contradicted + * by all documentation. + */ + if (current_cpu_type() == CPU_JZRISC && + mips_machtype == MACH_INGENIC_JZ4770) + c->scache.ways = 4; + c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize); diff --git a/arch/mips/txx9/rbtx4939/setup.c b/arch/mips/txx9/rbtx4939/setup.c index 8b937300fb7f..fd26fadc8617 100644 --- a/arch/mips/txx9/rbtx4939/setup.c +++ b/arch/mips/txx9/rbtx4939/setup.c @@ -186,7 +186,7 @@ static void __init rbtx4939_update_ioc_pen(void) #define RBTX4939_MAX_7SEGLEDS 8 -#if IS_ENABLED(CONFIG_LEDS_CLASS) +#if IS_BUILTIN(CONFIG_LEDS_CLASS) static u8 led_val[RBTX4939_MAX_7SEGLEDS]; struct rbtx4939_led_data { struct led_classdev cdev; @@ -261,7 +261,7 @@ static inline void rbtx4939_led_setup(void) static void __rbtx4939_7segled_putc(unsigned int pos, unsigned char val) { -#if IS_ENABLED(CONFIG_LEDS_CLASS) +#if IS_BUILTIN(CONFIG_LEDS_CLASS) unsigned long flags; local_irq_save(flags); /* bit7: reserved for LED class */ diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 60fae03dac79..3d4ec88f1db1 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -152,7 +152,6 @@ menu "Advanced setup" config ADVANCED_OPTIONS bool "Prompt for advanced kernel configuration options" - help comment "Default settings for advanced configuration options are used" depends on !ADVANCED_OPTIONS diff --git a/arch/nios2/boot/dts/3c120_devboard.dts b/arch/nios2/boot/dts/3c120_devboard.dts index 36ccdf05837d..56f4b5df6d65 100644 --- a/arch/nios2/boot/dts/3c120_devboard.dts +++ b/arch/nios2/boot/dts/3c120_devboard.dts @@ -29,7 +29,7 @@ #address-cells = <1>; #size-cells = <0>; - cpu: cpu@0x0 { + cpu: cpu@0 { device_type = "cpu"; compatible = "altr,nios2-1.0"; reg = <0x00000000>; @@ -69,7 +69,7 @@ compatible = "altr,avalon", "simple-bus"; bus-frequency = <125000000>; - pb_cpu_to_io: bridge@0x8000000 { + pb_cpu_to_io: bridge@8000000 { compatible = "simple-bus"; reg = <0x08000000 0x00800000>; #address-cells = <1>; @@ -83,7 +83,7 @@ <0x00008000 0x08008000 0x00000020>, <0x00400000 0x08400000 0x00000020>; - timer_1ms: timer@0x400000 { + timer_1ms: timer@400000 { compatible = "altr,timer-1.0"; reg = <0x00400000 0x00000020>; interrupt-parent = <&cpu>; @@ -91,7 +91,7 @@ clock-frequency = <125000000>; }; - timer_0: timer@0x8000 { + timer_0: timer@8000 { compatible = "altr,timer-1.0"; reg = < 0x00008000 0x00000020 >; interrupt-parent = < &cpu >; @@ -99,14 +99,14 @@ clock-frequency = < 125000000 >; }; - jtag_uart: serial@0x4d50 { + jtag_uart: serial@4d50 { compatible = "altr,juart-1.0"; reg = <0x00004d50 0x00000008>; interrupt-parent = <&cpu>; interrupts = <1>; }; - tse_mac: ethernet@0x4000 { + tse_mac: ethernet@4000 { compatible = "altr,tse-1.0"; reg = <0x00004000 0x00000400>, <0x00004400 0x00000040>, @@ -133,7 +133,7 @@ }; }; - uart: serial@0x4c80 { + uart: serial@4c80 { compatible = "altr,uart-1.0"; reg = <0x00004c80 0x00000020>; interrupt-parent = <&cpu>; @@ -143,7 +143,7 @@ }; }; - cfi_flash_64m: flash@0x0 { + cfi_flash_64m: flash@0 { compatible = "cfi-flash"; reg = <0x00000000 0x04000000>; bank-width = <2>; diff --git a/arch/nios2/configs/10m50_defconfig b/arch/nios2/configs/10m50_defconfig index 8b2a30b3b34f..c601c8ff1ae6 100644 --- a/arch/nios2/configs/10m50_defconfig +++ b/arch/nios2/configs/10m50_defconfig @@ -33,7 +33,6 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" diff --git a/arch/nios2/configs/3c120_defconfig b/arch/nios2/configs/3c120_defconfig index 9451940678a0..fce33588d55c 100644 --- a/arch/nios2/configs/3c120_defconfig +++ b/arch/nios2/configs/3c120_defconfig @@ -35,7 +35,6 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 9d3329811cc1..73ce5dd07642 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -141,6 +141,7 @@ config PPC select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API if PPC64 + select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION) diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 9a667007bff8..376ae803b69c 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -249,10 +249,8 @@ extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd); extern void kvmppc_pr_init_default_hcalls(struct kvm *kvm); extern int kvmppc_hcall_impl_pr(unsigned long cmd); extern int kvmppc_hcall_impl_hv_realmode(unsigned long cmd); -extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, - struct kvm_vcpu *vcpu); -extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, - struct kvmppc_book3s_shadow_vcpu *svcpu); +extern void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu); +extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu); extern int kvm_irq_bypass; static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 735cfa35298a..998f7b7aaa9e 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -122,13 +122,13 @@ static inline int kvmppc_hpte_page_shifts(unsigned long h, unsigned long l) lphi = (l >> 16) & 0xf; switch ((l >> 12) & 0xf) { case 0: - return !lphi ? 24 : -1; /* 16MB */ + return !lphi ? 24 : 0; /* 16MB */ break; case 1: return 16; /* 64kB */ break; case 3: - return !lphi ? 34 : -1; /* 16GB */ + return !lphi ? 34 : 0; /* 16GB */ break; case 7: return (16 << 8) + 12; /* 64kB in 4kB */ @@ -140,7 +140,7 @@ static inline int kvmppc_hpte_page_shifts(unsigned long h, unsigned long l) return (24 << 8) + 12; /* 16MB in 4kB */ break; } - return -1; + return 0; } static inline int kvmppc_hpte_base_page_shift(unsigned long h, unsigned long l) @@ -159,7 +159,11 @@ static inline int kvmppc_hpte_actual_page_shift(unsigned long h, unsigned long l static inline unsigned long kvmppc_actual_pgsz(unsigned long v, unsigned long r) { - return 1ul << kvmppc_hpte_actual_page_shift(v, r); + int shift = kvmppc_hpte_actual_page_shift(v, r); + + if (shift) + return 1ul << shift; + return 0; } static inline int kvmppc_pgsize_lp_encoding(int base_shift, int actual_shift) @@ -232,7 +236,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, va_low ^= v >> (SID_SHIFT_1T - 16); va_low &= 0x7ff; - if (b_pgshift == 12) { + if (b_pgshift <= 12) { if (a_pgshift > 12) { sllp = (a_pgshift == 16) ? 5 : 4; rb |= sllp << 5; /* AP field */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 3aa5b577cd60..1f53b562726f 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -690,6 +690,7 @@ struct kvm_vcpu_arch { u8 mmio_vsx_offset; u8 mmio_vsx_copy_type; u8 mmio_vsx_tx_sx_enabled; + u8 mmio_vmx_copy_nums; u8 osi_needed; u8 osi_enabled; u8 papr_enabled; @@ -709,6 +710,7 @@ struct kvm_vcpu_arch { u8 ceded; u8 prodded; u8 doorbell_request; + u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; struct swait_queue_head *wqp; @@ -738,8 +740,11 @@ struct kvm_vcpu_arch { struct kvmppc_icp *icp; /* XICS presentation controller */ struct kvmppc_xive_vcpu *xive_vcpu; /* XIVE virtual CPU data */ __be32 xive_cam_word; /* Cooked W2 in proper endian with valid bit */ - u32 xive_pushed; /* Is the VP pushed on the physical CPU ? */ + u8 xive_pushed; /* Is the VP pushed on the physical CPU ? */ + u8 xive_esc_on; /* Is the escalation irq enabled ? */ union xive_tma_w01 xive_saved_state; /* W0..1 of XIVE thread state */ + u64 xive_esc_raddr; /* Escalation interrupt ESB real addr */ + u64 xive_esc_vaddr; /* Escalation interrupt ESB virt addr */ #endif #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -800,6 +805,7 @@ struct kvm_vcpu_arch { #define KVM_MMIO_REG_QPR 0x0040 #define KVM_MMIO_REG_FQPR 0x0060 #define KVM_MMIO_REG_VSX 0x0080 +#define KVM_MMIO_REG_VMX 0x00c0 #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 9db18287b5f4..7765a800ddae 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -81,6 +81,10 @@ extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu, extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int rt, unsigned int bytes, int is_default_endian, int mmio_sign_extend); +extern int kvmppc_handle_load128_by2x64(struct kvm_run *run, + struct kvm_vcpu *vcpu, unsigned int rt, int is_default_endian); +extern int kvmppc_handle_store128_by2x64(struct kvm_run *run, + struct kvm_vcpu *vcpu, unsigned int rs, int is_default_endian); extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, u64 val, unsigned int bytes, int is_default_endian); diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h new file mode 100644 index 000000000000..6e20bb5c74ea --- /dev/null +++ b/arch/powerpc/include/asm/membarrier.h @@ -0,0 +1,27 @@ +#ifndef _ASM_POWERPC_MEMBARRIER_H +#define _ASM_POWERPC_MEMBARRIER_H + +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ + /* + * Only need the full barrier when switching between processes. + * Barrier when switching from kernel to userspace is not + * required here, given that it is implied by mmdrop(). Barrier + * when switching from userspace to kernel is not needed after + * store to rq->curr. + */ + if (likely(!(atomic_read(&next->membarrier_state) & + (MEMBARRIER_STATE_PRIVATE_EXPEDITED | + MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev)) + return; + + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + */ + smp_mb(); +} + +#endif /* _ASM_POWERPC_MEMBARRIER_H */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 24c73f5575ee..94bd1bf2c873 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -1076,6 +1076,7 @@ enum { /* Flags for OPAL_XIVE_GET/SET_VP_INFO */ enum { OPAL_XIVE_VP_ENABLED = 0x00000001, + OPAL_XIVE_VP_SINGLE_ESCALATION = 0x00000002, }; /* "Any chip" replacement for chip ID for allocation functions */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index ab5c1588b487..f1083bcf449c 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -156,6 +156,12 @@ #define OP_31_XOP_LFDX 599 #define OP_31_XOP_LFDUX 631 +/* VMX Vector Load Instructions */ +#define OP_31_XOP_LVX 103 + +/* VMX Vector Store Instructions */ +#define OP_31_XOP_STVX 231 + #define OP_LWZ 32 #define OP_STFS 52 #define OP_STFSU 53 diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index 7624e22f5045..8d1a2792484f 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -111,9 +111,10 @@ extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio); extern void xive_native_sync_source(u32 hw_irq); extern bool is_xive_irq(struct irq_chip *chip); -extern int xive_native_enable_vp(u32 vp_id); +extern int xive_native_enable_vp(u32 vp_id, bool single_escalation); extern int xive_native_disable_vp(u32 vp_id); extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id); +extern bool xive_native_has_single_escalation(void); #else diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 637b7263cb86..833ed9a16adf 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) #define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) +#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 88b84ac76b53..ea5eb91b836e 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -520,6 +520,7 @@ int main(void) OFFSET(VCPU_PENDING_EXC, kvm_vcpu, arch.pending_exceptions); OFFSET(VCPU_CEDED, kvm_vcpu, arch.ceded); OFFSET(VCPU_PRODDED, kvm_vcpu, arch.prodded); + OFFSET(VCPU_IRQ_PENDING, kvm_vcpu, arch.irq_pending); OFFSET(VCPU_DBELL_REQ, kvm_vcpu, arch.doorbell_request); OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr); OFFSET(VCPU_PMC, kvm_vcpu, arch.pmc); @@ -739,6 +740,9 @@ int main(void) DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu, arch.xive_cam_word)); DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed)); + DEFINE(VCPU_XIVE_ESC_ON, offsetof(struct kvm_vcpu, arch.xive_esc_on)); + DEFINE(VCPU_XIVE_ESC_RADDR, offsetof(struct kvm_vcpu, arch.xive_esc_raddr)); + DEFINE(VCPU_XIVE_ESC_VADDR, offsetof(struct kvm_vcpu, arch.xive_esc_vaddr)); #endif #ifdef CONFIG_KVM_EXIT_TIMING diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index ae2ede4de6be..446c79611d56 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -362,7 +362,7 @@ struct pci_controller* pci_find_hose_for_OF_device(struct device_node* node) */ static int pci_read_irq_line(struct pci_dev *pci_dev) { - unsigned int virq = 0; + int virq; pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev)); @@ -370,7 +370,8 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) memset(&oirq, 0xff, sizeof(oirq)); #endif /* Try to get a mapping from the device-tree */ - if (!of_irq_parse_and_map_pci(pci_dev, 0, 0)) { + virq = of_irq_parse_and_map_pci(pci_dev, 0, 0); + if (virq <= 0) { u8 line, pin; /* If that fails, lets fallback to what is in the config diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index fc600a8b1e77..f915db93cd42 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -392,7 +392,7 @@ static __poll_t rtas_log_poll(struct file *file, poll_table * wait) { poll_wait(file, &rtas_log_wait, wait); if (rtas_log_size) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index b12b8eb39c29..68a0e9d5b440 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -22,6 +22,7 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_EVENTFD + select HAVE_KVM_VCPU_ASYNC_IOCTL select SRCU select KVM_VFIO select IRQ_BYPASS_MANAGER @@ -68,7 +69,7 @@ config KVM_BOOK3S_64 select KVM_BOOK3S_64_HANDLER select KVM select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE - select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV) + select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_PSERIES || PPC_POWERNV) ---help--- Support running unmodified book3s_64 and book3s_32 guest kernels in virtual machines on book3s_64 host processors. diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 72d977e30952..234531d1bee1 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -484,19 +484,33 @@ void kvmppc_subarch_vcpu_uninit(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs); + int ret; + + vcpu_load(vcpu); + ret = vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs); + vcpu_put(vcpu); + + return ret; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs); + int ret; + + vcpu_load(vcpu); + ret = vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs); + vcpu_put(vcpu); + + return ret; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + regs->pc = kvmppc_get_pc(vcpu); regs->cr = kvmppc_get_cr(vcpu); regs->ctr = kvmppc_get_ctr(vcpu); @@ -518,6 +532,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) regs->gpr[i] = kvmppc_get_gpr(vcpu, i); + vcpu_put(vcpu); return 0; } @@ -525,6 +540,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + kvmppc_set_pc(vcpu, regs->pc); kvmppc_set_cr(vcpu, regs->cr); kvmppc_set_ctr(vcpu, regs->ctr); @@ -545,6 +562,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) kvmppc_set_gpr(vcpu, i, regs->gpr[i]); + vcpu_put(vcpu); return 0; } @@ -737,7 +755,9 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { + vcpu_load(vcpu); vcpu->guest_debug = dbg->control; + vcpu_put(vcpu); return 0; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index b73dbc9e797d..ef243fed2f2b 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -1269,6 +1269,11 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, /* Nothing to do */ goto out; + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + rpte = be64_to_cpu(hptep[1]); + vpte = hpte_new_to_old_v(vpte, rpte); + } + /* Unmap */ rev = &old->rev[idx]; guest_rpte = rev->guest_rpte; @@ -1298,7 +1303,6 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, /* Reload PTE after unmap */ vpte = be64_to_cpu(hptep[0]); - BUG_ON(vpte & HPTE_V_VALID); BUG_ON(!(vpte & HPTE_V_ABSENT)); @@ -1307,6 +1311,12 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, goto out; rpte = be64_to_cpu(hptep[1]); + + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + vpte = hpte_new_to_old_v(vpte, rpte); + rpte = hpte_new_to_old_r(rpte); + } + pshift = kvmppc_hpte_base_page_shift(vpte, rpte); avpn = HPTE_V_AVPN_VAL(vpte) & ~(((1ul << pshift) - 1) >> 23); pteg = idx / HPTES_PER_GROUP; @@ -1337,17 +1347,17 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, } new_pteg = hash & new_hash_mask; - if (vpte & HPTE_V_SECONDARY) { - BUG_ON(~pteg != (hash & old_hash_mask)); - new_pteg = ~new_pteg; - } else { - BUG_ON(pteg != (hash & old_hash_mask)); - } + if (vpte & HPTE_V_SECONDARY) + new_pteg = ~hash & new_hash_mask; new_idx = new_pteg * HPTES_PER_GROUP + (idx % HPTES_PER_GROUP); new_hptep = (__be64 *)(new->virt + (new_idx << 4)); replace_vpte = be64_to_cpu(new_hptep[0]); + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + unsigned long replace_rpte = be64_to_cpu(new_hptep[1]); + replace_vpte = hpte_new_to_old_v(replace_vpte, replace_rpte); + } if (replace_vpte & (HPTE_V_VALID | HPTE_V_ABSENT)) { BUG_ON(new->order >= old->order); @@ -1363,6 +1373,11 @@ static unsigned long resize_hpt_rehash_hpte(struct kvm_resize_hpt *resize, /* Discard the previous HPTE */ } + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + rpte = hpte_old_to_new_r(vpte, rpte); + vpte = hpte_old_to_new_v(vpte); + } + new_hptep[1] = cpu_to_be64(rpte); new->rev[new_idx].guest_rpte = guest_rpte; /* No need for a barrier, since new HPT isn't active */ @@ -1380,12 +1395,6 @@ static int resize_hpt_rehash(struct kvm_resize_hpt *resize) unsigned long i; int rc; - /* - * resize_hpt_rehash_hpte() doesn't handle the new-format HPTEs - * that POWER9 uses, and could well hit a BUG_ON on POWER9. - */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) - return -EIO; for (i = 0; i < kvmppc_hpt_npte(&kvm->arch.hpt); i++) { rc = resize_hpt_rehash_hpte(resize, i); if (rc != 0) @@ -1416,6 +1425,9 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize) synchronize_srcu_expedited(&kvm->srcu); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + kvmppc_setup_partition_table(kvm); + resize_hpt_debug(resize, "resize_hpt_pivot() done\n"); } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 58618f644c56..0c854816e653 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -573,7 +573,7 @@ long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm, j = i + 1; if (npages) { set_dirty_bits(map, i, npages); - i = j + npages; + j = i + npages; } } return 0; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index e4f70c33fbc7..89707354c2ef 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -116,6 +116,9 @@ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect, 0644); MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core"); #endif +/* If set, the threads on each CPU core have to be in the same MMU mode */ +static bool no_mixing_hpt_and_radix; + static void kvmppc_end_cede(struct kvm_vcpu *vcpu); static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu); @@ -1003,8 +1006,6 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tvcpu; - if (!cpu_has_feature(CPU_FTR_ARCH_300)) - return EMULATE_FAIL; if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst) != EMULATE_DONE) return RESUME_GUEST; if (get_op(inst) != 31) @@ -1054,6 +1055,7 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) return RESUME_GUEST; } +/* Called with vcpu->arch.vcore->lock held */ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, struct task_struct *tsk) { @@ -1174,7 +1176,10 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, swab32(vcpu->arch.emul_inst) : vcpu->arch.emul_inst; if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) { + /* Need vcore unlocked to call kvmppc_get_last_inst */ + spin_unlock(&vcpu->arch.vcore->lock); r = kvmppc_emulate_debug_inst(run, vcpu); + spin_lock(&vcpu->arch.vcore->lock); } else { kvmppc_core_queue_program(vcpu, SRR1_PROGILL); r = RESUME_GUEST; @@ -1189,8 +1194,13 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu, */ case BOOK3S_INTERRUPT_H_FAC_UNAVAIL: r = EMULATE_FAIL; - if ((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) + if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) && + cpu_has_feature(CPU_FTR_ARCH_300)) { + /* Need vcore unlocked to call kvmppc_get_last_inst */ + spin_unlock(&vcpu->arch.vcore->lock); r = kvmppc_emulate_doorbell_instr(vcpu); + spin_lock(&vcpu->arch.vcore->lock); + } if (r == EMULATE_FAIL) { kvmppc_core_queue_program(vcpu, SRR1_PROGILL); r = RESUME_GUEST; @@ -1495,6 +1505,10 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_ARCH_COMPAT: *val = get_reg_val(id, vcpu->arch.vcore->arch_compat); break; + case KVM_REG_PPC_DEC_EXPIRY: + *val = get_reg_val(id, vcpu->arch.dec_expires + + vcpu->arch.vcore->tb_offset); + break; default: r = -EINVAL; break; @@ -1722,6 +1736,10 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_ARCH_COMPAT: r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val)); break; + case KVM_REG_PPC_DEC_EXPIRY: + vcpu->arch.dec_expires = set_reg_val(id, *val) - + vcpu->arch.vcore->tb_offset; + break; default: r = -EINVAL; break; @@ -2376,8 +2394,8 @@ static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc) static bool subcore_config_ok(int n_subcores, int n_threads) { /* - * POWER9 "SMT4" cores are permanently in what is effectively a 4-way split-core - * mode, with one thread per subcore. + * POWER9 "SMT4" cores are permanently in what is effectively a 4-way + * split-core mode, with one thread per subcore. */ if (cpu_has_feature(CPU_FTR_ARCH_300)) return n_subcores <= 4 && n_threads == 1; @@ -2413,8 +2431,8 @@ static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip) if (!cpu_has_feature(CPU_FTR_ARCH_207S)) return false; - /* POWER9 currently requires all threads to be in the same MMU mode */ - if (cpu_has_feature(CPU_FTR_ARCH_300) && + /* Some POWER9 chips require all threads to be in the same MMU mode */ + if (no_mixing_hpt_and_radix && kvm_is_radix(vc->kvm) != kvm_is_radix(cip->vc[0]->kvm)) return false; @@ -2677,9 +2695,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) * threads are offline. Also check if the number of threads in this * guest are greater than the current system threads per guest. * On POWER9, we need to be not in independent-threads mode if - * this is a HPT guest on a radix host. + * this is a HPT guest on a radix host machine where the + * CPU threads may not be in different MMU modes. */ - hpt_on_radix = radix_enabled() && !kvm_is_radix(vc->kvm); + hpt_on_radix = no_mixing_hpt_and_radix && radix_enabled() && + !kvm_is_radix(vc->kvm); if (((controlled_threads > 1) && ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) || (hpt_on_radix && vc->kvm->arch.threads_indep)) { @@ -2829,7 +2849,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) */ if (!thr0_done) kvmppc_start_thread(NULL, pvc); - thr += pvc->num_threads; } /* @@ -2932,13 +2951,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) /* make sure updates to secondary vcpu structs are visible now */ smp_mb(); + preempt_enable(); + for (sub = 0; sub < core_info.n_subcores; ++sub) { pvc = core_info.vc[sub]; post_guest_process(pvc, pvc == vc); } spin_lock(&vc->lock); - preempt_enable(); out: vc->vcore_state = VCORE_INACTIVE; @@ -2985,7 +3005,7 @@ static inline bool xive_interrupt_pending(struct kvm_vcpu *vcpu) { if (!xive_enabled()) return false; - return vcpu->arch.xive_saved_state.pipr < + return vcpu->arch.irq_pending || vcpu->arch.xive_saved_state.pipr < vcpu->arch.xive_saved_state.cppr; } #else @@ -3174,17 +3194,8 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) * this thread straight away and have it join in. */ if (!signal_pending(current)) { - if (vc->vcore_state == VCORE_PIGGYBACK) { - if (spin_trylock(&vc->lock)) { - if (vc->vcore_state == VCORE_RUNNING && - !VCORE_IS_EXITING(vc)) { - kvmppc_create_dtl_entry(vcpu, vc); - kvmppc_start_thread(vcpu, vc); - trace_kvm_guest_enter(vcpu); - } - spin_unlock(&vc->lock); - } - } else if (vc->vcore_state == VCORE_RUNNING && + if ((vc->vcore_state == VCORE_PIGGYBACK || + vc->vcore_state == VCORE_RUNNING) && !VCORE_IS_EXITING(vc)) { kvmppc_create_dtl_entry(vcpu, vc); kvmppc_start_thread(vcpu, vc); @@ -4446,6 +4457,19 @@ static int kvmppc_book3s_init_hv(void) if (kvmppc_radix_possible()) r = kvmppc_radix_init(); + + /* + * POWER9 chips before version 2.02 can't have some threads in + * HPT mode and some in radix mode on the same core. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + unsigned int pvr = mfspr(SPRN_PVR); + if ((pvr >> 16) == PVR_POWER9 && + (((pvr & 0xe000) == 0 && (pvr & 0xfff) < 0x202) || + ((pvr & 0xe000) == 0x2000 && (pvr & 0xfff) < 0x101))) + no_mixing_hpt_and_radix = true; + } + return r; } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 7886b313d135..f31f357b8c5a 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -413,10 +413,11 @@ FTR_SECTION_ELSE /* On P9 we use the split_info for coordinating LPCR changes */ lwz r4, KVM_SPLIT_DO_SET(r6) cmpwi r4, 0 - beq 63f + beq 1f mr r3, r6 bl kvmhv_p9_set_lpcr nop +1: ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) 63: /* Order load of vcpu after load of vcore */ @@ -617,13 +618,6 @@ kvmppc_hv_entry: lbz r0, KVM_RADIX(r9) cmpwi cr7, r0, 0 - /* Clear out SLB if hash */ - bne cr7, 2f - li r6,0 - slbmte r6,r6 - slbia - ptesync -2: /* * POWER7/POWER8 host -> guest partition switch code. * We don't have to lock against concurrent tlbies, @@ -738,19 +732,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 10: cmpdi r4, 0 beq kvmppc_primary_no_guest kvmppc_got_guest: - - /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */ - lwz r5,VCPU_SLB_MAX(r4) - cmpwi r5,0 - beq 9f - mtctr r5 - addi r6,r4,VCPU_SLB -1: ld r8,VCPU_SLB_E(r6) - ld r9,VCPU_SLB_V(r6) - slbmte r9,r8 - addi r6,r6,VCPU_SLB_SIZE - bdnz 1b -9: /* Increment yield count if they have a VPA */ ld r3, VCPU_VPA(r4) cmpdi r3, 0 @@ -957,7 +938,6 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) mftb r7 subf r3,r7,r8 mtspr SPRN_DEC,r3 - std r3,VCPU_DEC(r4) ld r5, VCPU_SPRG0(r4) ld r6, VCPU_SPRG1(r4) @@ -1018,6 +998,29 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) cmpdi r3, 512 /* 1 microsecond */ blt hdec_soon + /* For hash guest, clear out and reload the SLB */ + ld r6, VCPU_KVM(r4) + lbz r0, KVM_RADIX(r6) + cmpwi r0, 0 + bne 9f + li r6, 0 + slbmte r6, r6 + slbia + ptesync + + /* Load up guest SLB entries (N.B. slb_max will be 0 for radix) */ + lwz r5,VCPU_SLB_MAX(r4) + cmpwi r5,0 + beq 9f + mtctr r5 + addi r6,r4,VCPU_SLB +1: ld r8,VCPU_SLB_E(r6) + ld r9,VCPU_SLB_V(r6) + slbmte r9,r8 + addi r6,r6,VCPU_SLB_SIZE + bdnz 1b +9: + #ifdef CONFIG_KVM_XICS /* We are entering the guest on that thread, push VCPU to XIVE */ ld r10, HSTATE_XIVE_TIMA_PHYS(r13) @@ -1031,8 +1034,53 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300) li r9, TM_QW1_OS + TM_WORD2 stwcix r11,r9,r10 li r9, 1 - stw r9, VCPU_XIVE_PUSHED(r4) + stb r9, VCPU_XIVE_PUSHED(r4) eieio + + /* + * We clear the irq_pending flag. There is a small chance of a + * race vs. the escalation interrupt happening on another + * processor setting it again, but the only consequence is to + * cause a spurrious wakeup on the next H_CEDE which is not an + * issue. + */ + li r0,0 + stb r0, VCPU_IRQ_PENDING(r4) + + /* + * In single escalation mode, if the escalation interrupt is + * on, we mask it. + */ + lbz r0, VCPU_XIVE_ESC_ON(r4) + cmpwi r0,0 + beq 1f + ld r10, VCPU_XIVE_ESC_RADDR(r4) + li r9, XIVE_ESB_SET_PQ_01 + ldcix r0, r10, r9 + sync + + /* We have a possible subtle race here: The escalation interrupt might + * have fired and be on its way to the host queue while we mask it, + * and if we unmask it early enough (re-cede right away), there is + * a theorical possibility that it fires again, thus landing in the + * target queue more than once which is a big no-no. + * + * Fortunately, solving this is rather easy. If the above load setting + * PQ to 01 returns a previous value where P is set, then we know the + * escalation interrupt is somewhere on its way to the host. In that + * case we simply don't clear the xive_esc_on flag below. It will be + * eventually cleared by the handler for the escalation interrupt. + * + * Then, when doing a cede, we check that flag again before re-enabling + * the escalation interrupt, and if set, we abort the cede. + */ + andi. r0, r0, XIVE_ESB_VAL_P + bne- 1f + + /* Now P is 0, we can clear the flag */ + li r0, 0 + stb r0, VCPU_XIVE_ESC_ON(r4) +1: no_xive: #endif /* CONFIG_KVM_XICS */ @@ -1193,7 +1241,7 @@ hdec_soon: addi r3, r4, VCPU_TB_RMEXIT bl kvmhv_accumulate_time #endif - b guest_exit_cont + b guest_bypass /****************************************************************************** * * @@ -1423,15 +1471,35 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) blt deliver_guest_interrupt guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ + /* Save more register state */ + mfdar r6 + mfdsisr r7 + std r6, VCPU_DAR(r9) + stw r7, VCPU_DSISR(r9) + /* don't overwrite fault_dar/fault_dsisr if HDSI */ + cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE + beq mc_cont + std r6, VCPU_FAULT_DAR(r9) + stw r7, VCPU_FAULT_DSISR(r9) + + /* See if it is a machine check */ + cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK + beq machine_check_realmode +mc_cont: +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + addi r3, r9, VCPU_TB_RMEXIT + mr r4, r9 + bl kvmhv_accumulate_time +#endif #ifdef CONFIG_KVM_XICS /* We are exiting, pull the VP from the XIVE */ - lwz r0, VCPU_XIVE_PUSHED(r9) + lbz r0, VCPU_XIVE_PUSHED(r9) cmpwi cr0, r0, 0 beq 1f li r7, TM_SPC_PULL_OS_CTX li r6, TM_QW1_OS mfmsr r0 - andi. r0, r0, MSR_IR /* in real mode? */ + andi. r0, r0, MSR_DR /* in real mode? */ beq 2f ld r10, HSTATE_XIVE_TIMA_VIRT(r13) cmpldi cr0, r10, 0 @@ -1454,33 +1522,42 @@ guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */ /* Fixup some of the state for the next load */ li r10, 0 li r0, 0xff - stw r10, VCPU_XIVE_PUSHED(r9) + stb r10, VCPU_XIVE_PUSHED(r9) stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9) stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9) eieio 1: #endif /* CONFIG_KVM_XICS */ - /* Save more register state */ - mfdar r6 - mfdsisr r7 - std r6, VCPU_DAR(r9) - stw r7, VCPU_DSISR(r9) - /* don't overwrite fault_dar/fault_dsisr if HDSI */ - cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE - beq mc_cont - std r6, VCPU_FAULT_DAR(r9) - stw r7, VCPU_FAULT_DSISR(r9) - /* See if it is a machine check */ - cmpwi r12, BOOK3S_INTERRUPT_MACHINE_CHECK - beq machine_check_realmode -mc_cont: -#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING - addi r3, r9, VCPU_TB_RMEXIT - mr r4, r9 - bl kvmhv_accumulate_time -#endif + /* For hash guest, read the guest SLB and save it away */ + ld r5, VCPU_KVM(r9) + lbz r0, KVM_RADIX(r5) + li r5, 0 + cmpwi r0, 0 + bne 3f /* for radix, save 0 entries */ + lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */ + mtctr r0 + li r6,0 + addi r7,r9,VCPU_SLB +1: slbmfee r8,r6 + andis. r0,r8,SLB_ESID_V@h + beq 2f + add r8,r8,r6 /* put index in */ + slbmfev r3,r6 + std r8,VCPU_SLB_E(r7) + std r3,VCPU_SLB_V(r7) + addi r7,r7,VCPU_SLB_SIZE + addi r5,r5,1 +2: addi r6,r6,1 + bdnz 1b + /* Finally clear out the SLB */ + li r0,0 + slbmte r0,r0 + slbia + ptesync +3: stw r5,VCPU_SLB_MAX(r9) +guest_bypass: mr r3, r12 /* Increment exit count, poke other threads to exit */ bl kvmhv_commence_exit @@ -1501,31 +1578,6 @@ mc_cont: ori r6,r6,1 mtspr SPRN_CTRLT,r6 4: - /* Check if we are running hash or radix and store it in cr2 */ - ld r5, VCPU_KVM(r9) - lbz r0, KVM_RADIX(r5) - cmpwi cr2,r0,0 - - /* Read the guest SLB and save it away */ - li r5, 0 - bne cr2, 3f /* for radix, save 0 entries */ - lwz r0,VCPU_SLB_NR(r9) /* number of entries in SLB */ - mtctr r0 - li r6,0 - addi r7,r9,VCPU_SLB -1: slbmfee r8,r6 - andis. r0,r8,SLB_ESID_V@h - beq 2f - add r8,r8,r6 /* put index in */ - slbmfev r3,r6 - std r8,VCPU_SLB_E(r7) - std r3,VCPU_SLB_V(r7) - addi r7,r7,VCPU_SLB_SIZE - addi r5,r5,1 -2: addi r6,r6,1 - bdnz 1b -3: stw r5,VCPU_SLB_MAX(r9) - /* * Save the guest PURR/SPURR */ @@ -1803,7 +1855,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) ld r5, VCPU_KVM(r9) lbz r0, KVM_RADIX(r5) cmpwi cr2, r0, 0 - beq cr2, 3f + beq cr2, 4f /* Radix: Handle the case where the guest used an illegal PID */ LOAD_REG_ADDR(r4, mmu_base_pid) @@ -1839,15 +1891,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) BEGIN_FTR_SECTION PPC_INVALIDATE_ERAT END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) - b 4f +4: #endif /* CONFIG_PPC_RADIX_MMU */ - /* Hash: clear out SLB */ -3: li r5,0 - slbmte r5,r5 - slbia - ptesync -4: /* * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do @@ -2745,7 +2791,32 @@ kvm_cede_prodded: /* we've ceded but we want to give control to the host */ kvm_cede_exit: ld r9, HSTATE_KVM_VCPU(r13) - b guest_exit_cont +#ifdef CONFIG_KVM_XICS + /* Abort if we still have a pending escalation */ + lbz r5, VCPU_XIVE_ESC_ON(r9) + cmpwi r5, 0 + beq 1f + li r0, 0 + stb r0, VCPU_CEDED(r9) +1: /* Enable XIVE escalation */ + li r5, XIVE_ESB_SET_PQ_00 + mfmsr r0 + andi. r0, r0, MSR_DR /* in real mode? */ + beq 1f + ld r10, VCPU_XIVE_ESC_VADDR(r9) + cmpdi r10, 0 + beq 3f + ldx r0, r10, r5 + b 2f +1: ld r10, VCPU_XIVE_ESC_RADDR(r9) + cmpdi r10, 0 + beq 3f + ldcix r0, r10, r5 +2: sync + li r0, 1 + stb r0, VCPU_XIVE_ESC_ON(r9) +#endif /* CONFIG_KVM_XICS */ +3: b guest_exit_cont /* Try to handle a machine check in real mode */ machine_check_realmode: diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index 901e6fe00c39..c18e845019ec 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -96,7 +96,7 @@ kvm_start_entry: kvm_start_lightweight: /* Copy registers into shadow vcpu so we can access them in real mode */ - GET_SHADOW_VCPU(r3) + mr r3, r4 bl FUNC(kvmppc_copy_to_svcpu) nop REST_GPR(4, r1) @@ -165,9 +165,7 @@ after_sprg3_load: stw r12, VCPU_TRAP(r3) /* Transfer reg values from shadow vcpu back to vcpu struct */ - /* On 64-bit, interrupts are still off at this point */ - GET_SHADOW_VCPU(r4) bl FUNC(kvmppc_copy_from_svcpu) nop diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 7deaeeb14b93..3ae752314b34 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -121,7 +121,7 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) #ifdef CONFIG_PPC_BOOK3S_64 struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); if (svcpu->in_use) { - kvmppc_copy_from_svcpu(vcpu, svcpu); + kvmppc_copy_from_svcpu(vcpu); } memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; @@ -143,9 +143,10 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) } /* Copy data needed by real-mode code from vcpu to shadow vcpu */ -void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, - struct kvm_vcpu *vcpu) +void kvmppc_copy_to_svcpu(struct kvm_vcpu *vcpu) { + struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); + svcpu->gpr[0] = vcpu->arch.gpr[0]; svcpu->gpr[1] = vcpu->arch.gpr[1]; svcpu->gpr[2] = vcpu->arch.gpr[2]; @@ -177,17 +178,14 @@ void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu, if (cpu_has_feature(CPU_FTR_ARCH_207S)) vcpu->arch.entry_ic = mfspr(SPRN_IC); svcpu->in_use = true; + + svcpu_put(svcpu); } /* Copy data touched by real-mode code from shadow vcpu back to vcpu */ -void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, - struct kvmppc_book3s_shadow_vcpu *svcpu) +void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu) { - /* - * vcpu_put would just call us again because in_use hasn't - * been updated yet. - */ - preempt_disable(); + struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); /* * Maybe we were already preempted and synced the svcpu from @@ -233,7 +231,7 @@ void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu, svcpu->in_use = false; out: - preempt_enable(); + svcpu_put(svcpu); } static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 6882bc94eba8..f0f5cd4d2fe7 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -84,12 +84,22 @@ static irqreturn_t xive_esc_irq(int irq, void *data) { struct kvm_vcpu *vcpu = data; - /* We use the existing H_PROD mechanism to wake up the target */ - vcpu->arch.prodded = 1; + vcpu->arch.irq_pending = 1; smp_mb(); if (vcpu->arch.ceded) kvmppc_fast_vcpu_kick(vcpu); + /* Since we have the no-EOI flag, the interrupt is effectively + * disabled now. Clearing xive_esc_on means we won't bother + * doing so on the next entry. + * + * This also allows the entry code to know that if a PQ combination + * of 10 is observed while xive_esc_on is true, it means the queue + * contains an unprocessed escalation interrupt. We don't make use of + * that knowledge today but might (see comment in book3s_hv_rmhandler.S) + */ + vcpu->arch.xive_esc_on = false; + return IRQ_HANDLED; } @@ -112,19 +122,21 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio) return -EIO; } - /* - * Future improvement: start with them disabled - * and handle DD2 and later scheme of merged escalation - * interrupts - */ - name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d", - vcpu->kvm->arch.lpid, xc->server_num, prio); + if (xc->xive->single_escalation) + name = kasprintf(GFP_KERNEL, "kvm-%d-%d", + vcpu->kvm->arch.lpid, xc->server_num); + else + name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d", + vcpu->kvm->arch.lpid, xc->server_num, prio); if (!name) { pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n", prio, xc->server_num); rc = -ENOMEM; goto error; } + + pr_devel("Escalation %s irq %d (prio %d)\n", name, xc->esc_virq[prio], prio); + rc = request_irq(xc->esc_virq[prio], xive_esc_irq, IRQF_NO_THREAD, name, vcpu); if (rc) { @@ -133,6 +145,25 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio) goto error; } xc->esc_virq_names[prio] = name; + + /* In single escalation mode, we grab the ESB MMIO of the + * interrupt and mask it. Also populate the VCPU v/raddr + * of the ESB page for use by asm entry/exit code. Finally + * set the XIVE_IRQ_NO_EOI flag which will prevent the + * core code from performing an EOI on the escalation + * interrupt, thus leaving it effectively masked after + * it fires once. + */ + if (xc->xive->single_escalation) { + struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]); + struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); + + xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01); + vcpu->arch.xive_esc_raddr = xd->eoi_page; + vcpu->arch.xive_esc_vaddr = (__force u64)xd->eoi_mmio; + xd->flags |= XIVE_IRQ_NO_EOI; + } + return 0; error: irq_dispose_mapping(xc->esc_virq[prio]); @@ -191,12 +222,12 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio) pr_devel("Provisioning prio... %d\n", prio); - /* Provision each VCPU and enable escalations */ + /* Provision each VCPU and enable escalations if needed */ kvm_for_each_vcpu(i, vcpu, kvm) { if (!vcpu->arch.xive_vcpu) continue; rc = xive_provision_queue(vcpu, prio); - if (rc == 0) + if (rc == 0 && !xive->single_escalation) xive_attach_escalation(vcpu, prio); if (rc) return rc; @@ -1082,6 +1113,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, /* Allocate IPI */ xc->vp_ipi = xive_native_alloc_irq(); if (!xc->vp_ipi) { + pr_err("Failed to allocate xive irq for VCPU IPI\n"); r = -EIO; goto bail; } @@ -1092,18 +1124,33 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, goto bail; /* + * Enable the VP first as the single escalation mode will + * affect escalation interrupts numbering + */ + r = xive_native_enable_vp(xc->vp_id, xive->single_escalation); + if (r) { + pr_err("Failed to enable VP in OPAL, err %d\n", r); + goto bail; + } + + /* * Initialize queues. Initially we set them all for no queueing * and we enable escalation for queue 0 only which we'll use for * our mfrr change notifications. If the VCPU is hot-plugged, we - * do handle provisioning however. + * do handle provisioning however based on the existing "map" + * of enabled queues. */ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { struct xive_q *q = &xc->queues[i]; + /* Single escalation, no queue 7 */ + if (i == 7 && xive->single_escalation) + break; + /* Is queue already enabled ? Provision it */ if (xive->qmap & (1 << i)) { r = xive_provision_queue(vcpu, i); - if (r == 0) + if (r == 0 && !xive->single_escalation) xive_attach_escalation(vcpu, i); if (r) goto bail; @@ -1123,11 +1170,6 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, if (r) goto bail; - /* Enable the VP */ - r = xive_native_enable_vp(xc->vp_id); - if (r) - goto bail; - /* Route the IPI */ r = xive_native_configure_irq(xc->vp_ipi, xc->vp_id, 0, XICS_IPI); if (!r) @@ -1474,6 +1516,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr) pr_devel(" val=0x016%llx (server=0x%x, guest_prio=%d)\n", val, server, guest_prio); + /* * If the source doesn't already have an IPI, allocate * one and get the corresponding data @@ -1762,6 +1805,8 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type) if (xive->vp_base == XIVE_INVALID_VP) ret = -ENOMEM; + xive->single_escalation = xive_native_has_single_escalation(); + if (ret) { kfree(xive); return ret; @@ -1795,6 +1840,7 @@ static int xive_debug_show(struct seq_file *m, void *private) kvm_for_each_vcpu(i, vcpu, kvm) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; + unsigned int i; if (!xc) continue; @@ -1804,6 +1850,33 @@ static int xive_debug_show(struct seq_file *m, void *private) xc->server_num, xc->cppr, xc->hw_cppr, xc->mfrr, xc->pending, xc->stat_rm_h_xirr, xc->stat_vm_h_xirr); + for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) { + struct xive_q *q = &xc->queues[i]; + u32 i0, i1, idx; + + if (!q->qpage && !xc->esc_virq[i]) + continue; + + seq_printf(m, " [q%d]: ", i); + + if (q->qpage) { + idx = q->idx; + i0 = be32_to_cpup(q->qpage + idx); + idx = (idx + 1) & q->msk; + i1 = be32_to_cpup(q->qpage + idx); + seq_printf(m, "T=%d %08x %08x... \n", q->toggle, i0, i1); + } + if (xc->esc_virq[i]) { + struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]); + struct xive_irq_data *xd = irq_data_get_irq_handler_data(d); + u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET); + seq_printf(m, "E:%c%c I(%d:%llx:%llx)", + (pq & XIVE_ESB_VAL_P) ? 'P' : 'p', + (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q', + xc->esc_virq[i], pq, xd->eoi_page); + seq_printf(m, "\n"); + } + } t_rm_h_xirr += xc->stat_rm_h_xirr; t_rm_h_ipoll += xc->stat_rm_h_ipoll; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 6ba63f8e8a61..a08ae6fd4c51 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -120,6 +120,8 @@ struct kvmppc_xive { u32 q_order; u32 q_page_order; + /* Flags */ + u8 single_escalation; }; #define KVMPPC_XIVE_Q_COUNT 8 @@ -201,25 +203,20 @@ static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmpp * is as follow. * * Guest request for 0...6 are honored. Guest request for anything - * higher results in a priority of 7 being applied. - * - * However, when XIRR is returned via H_XIRR, 7 is translated to 0xb - * in order to match AIX expectations + * higher results in a priority of 6 being applied. * * Similar mapping is done for CPPR values */ static inline u8 xive_prio_from_guest(u8 prio) { - if (prio == 0xff || prio < 8) + if (prio == 0xff || prio < 6) return prio; - return 7; + return 6; } static inline u8 xive_prio_to_guest(u8 prio) { - if (prio == 0xff || prio < 7) - return prio; - return 0xb; + return prio; } static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle) diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 83b485810aea..6038e2e7aee0 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1431,6 +1431,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + regs->pc = vcpu->arch.pc; regs->cr = kvmppc_get_cr(vcpu); regs->ctr = vcpu->arch.ctr; @@ -1452,6 +1454,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) regs->gpr[i] = kvmppc_get_gpr(vcpu, i); + vcpu_put(vcpu); return 0; } @@ -1459,6 +1462,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { int i; + vcpu_load(vcpu); + vcpu->arch.pc = regs->pc; kvmppc_set_cr(vcpu, regs->cr); vcpu->arch.ctr = regs->ctr; @@ -1480,6 +1485,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) for (i = 0; i < ARRAY_SIZE(regs->gpr); i++) kvmppc_set_gpr(vcpu, i, regs->gpr[i]); + vcpu_put(vcpu); return 0; } @@ -1607,30 +1613,42 @@ int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + int ret; + + vcpu_load(vcpu); + sregs->pvr = vcpu->arch.pvr; get_sregs_base(vcpu, sregs); get_sregs_arch206(vcpu, sregs); - return vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs); + ret = vcpu->kvm->arch.kvm_ops->get_sregs(vcpu, sregs); + + vcpu_put(vcpu); + return ret; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - int ret; + int ret = -EINVAL; + vcpu_load(vcpu); if (vcpu->arch.pvr != sregs->pvr) - return -EINVAL; + goto out; ret = set_sregs_base(vcpu, sregs); if (ret < 0) - return ret; + goto out; ret = set_sregs_arch206(vcpu, sregs); if (ret < 0) - return ret; + goto out; - return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs); + ret = vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs); + +out: + vcpu_put(vcpu); + return ret; } int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id, @@ -1773,7 +1791,9 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, { int r; + vcpu_load(vcpu); r = kvmppc_core_vcpu_translate(vcpu, tr); + vcpu_put(vcpu); return r; } @@ -1996,12 +2016,15 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, { struct debug_reg *dbg_reg; int n, b = 0, w = 0; + int ret = 0; + + vcpu_load(vcpu); if (!(dbg->control & KVM_GUESTDBG_ENABLE)) { vcpu->arch.dbg_reg.dbcr0 = 0; vcpu->guest_debug = 0; kvm_guest_protect_msr(vcpu, MSR_DE, false); - return 0; + goto out; } kvm_guest_protect_msr(vcpu, MSR_DE, true); @@ -2033,8 +2056,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, #endif if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - return 0; + goto out; + ret = -EINVAL; for (n = 0; n < (KVMPPC_BOOKE_IAC_NUM + KVMPPC_BOOKE_DAC_NUM); n++) { uint64_t addr = dbg->arch.bp[n].addr; uint32_t type = dbg->arch.bp[n].type; @@ -2045,21 +2069,24 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, if (type & ~(KVMPPC_DEBUG_WATCH_READ | KVMPPC_DEBUG_WATCH_WRITE | KVMPPC_DEBUG_BREAKPOINT)) - return -EINVAL; + goto out; if (type & KVMPPC_DEBUG_BREAKPOINT) { /* Setting H/W breakpoint */ if (kvmppc_booke_add_breakpoint(dbg_reg, addr, b++)) - return -EINVAL; + goto out; } else { /* Setting H/W watchpoint */ if (kvmppc_booke_add_watchpoint(dbg_reg, addr, type, w++)) - return -EINVAL; + goto out; } } - return 0; + ret = 0; +out: + vcpu_put(vcpu); + return ret; } void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu) diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index af833531af31..a382e15135e6 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -58,6 +58,18 @@ static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu) } #endif /* CONFIG_VSX */ +#ifdef CONFIG_ALTIVEC +static bool kvmppc_check_altivec_disabled(struct kvm_vcpu *vcpu) +{ + if (!(kvmppc_get_msr(vcpu) & MSR_VEC)) { + kvmppc_core_queue_vec_unavail(vcpu); + return true; + } + + return false; +} +#endif /* CONFIG_ALTIVEC */ + /* * XXX to do: * lfiwax, lfiwzx @@ -98,6 +110,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) vcpu->arch.mmio_vsx_copy_type = KVMPPC_VSX_COPY_NONE; vcpu->arch.mmio_sp64_extend = 0; vcpu->arch.mmio_sign_extend = 0; + vcpu->arch.mmio_vmx_copy_nums = 0; switch (get_op(inst)) { case 31: @@ -459,6 +472,29 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) rs, 4, 1); break; #endif /* CONFIG_VSX */ + +#ifdef CONFIG_ALTIVEC + case OP_31_XOP_LVX: + if (kvmppc_check_altivec_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.vaddr_accessed &= ~0xFULL; + vcpu->arch.paddr_accessed &= ~0xFULL; + vcpu->arch.mmio_vmx_copy_nums = 2; + emulated = kvmppc_handle_load128_by2x64(run, vcpu, + KVM_MMIO_REG_VMX|rt, 1); + break; + + case OP_31_XOP_STVX: + if (kvmppc_check_altivec_disabled(vcpu)) + return EMULATE_DONE; + vcpu->arch.vaddr_accessed &= ~0xFULL; + vcpu->arch.paddr_accessed &= ~0xFULL; + vcpu->arch.mmio_vmx_copy_nums = 2; + emulated = kvmppc_handle_store128_by2x64(run, vcpu, + rs, 1); + break; +#endif /* CONFIG_ALTIVEC */ + default: emulated = EMULATE_FAIL; break; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 0a7c88786ec0..403e642c78f5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -638,8 +638,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_SPAPR_RESIZE_HPT: - /* Disable this on POWER9 until code handles new HPTE format */ - r = !!hv_enabled && !cpu_has_feature(CPU_FTR_ARCH_300); + r = !!hv_enabled; break; #endif #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -763,7 +762,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup; - vcpu->arch.dec_expires = ~(u64)0; + vcpu->arch.dec_expires = get_tb(); #ifdef CONFIG_KVM_EXIT_TIMING mutex_init(&vcpu->arch.exit_timing_lock); @@ -930,6 +929,34 @@ static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu, } #endif /* CONFIG_VSX */ +#ifdef CONFIG_ALTIVEC +static inline void kvmppc_set_vmx_dword(struct kvm_vcpu *vcpu, + u64 gpr) +{ + int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK; + u32 hi, lo; + u32 di; + +#ifdef __BIG_ENDIAN + hi = gpr >> 32; + lo = gpr & 0xffffffff; +#else + lo = gpr >> 32; + hi = gpr & 0xffffffff; +#endif + + di = 2 - vcpu->arch.mmio_vmx_copy_nums; /* doubleword index */ + if (di > 1) + return; + + if (vcpu->arch.mmio_host_swabbed) + di = 1 - di; + + VCPU_VSX_VR(vcpu, index).u[di * 2] = hi; + VCPU_VSX_VR(vcpu, index).u[di * 2 + 1] = lo; +} +#endif /* CONFIG_ALTIVEC */ + #ifdef CONFIG_PPC_FPU static inline u64 sp_to_dp(u32 fprs) { @@ -1033,6 +1060,11 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu, kvmppc_set_vsr_dword_dump(vcpu, gpr); break; #endif +#ifdef CONFIG_ALTIVEC + case KVM_MMIO_REG_VMX: + kvmppc_set_vmx_dword(vcpu, gpr); + break; +#endif default: BUG(); } @@ -1106,11 +1138,9 @@ int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu, { enum emulation_result emulated = EMULATE_DONE; - /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */ - if ( (vcpu->arch.mmio_vsx_copy_nums > 4) || - (vcpu->arch.mmio_vsx_copy_nums < 0) ) { + /* Currently, mmio_vsx_copy_nums only allowed to be 4 or less */ + if (vcpu->arch.mmio_vsx_copy_nums > 4) return EMULATE_FAIL; - } while (vcpu->arch.mmio_vsx_copy_nums) { emulated = __kvmppc_handle_load(run, vcpu, rt, bytes, @@ -1252,11 +1282,9 @@ int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu, vcpu->arch.io_gpr = rs; - /* Currently, mmio_vsx_copy_nums only allowed to be less than 4 */ - if ( (vcpu->arch.mmio_vsx_copy_nums > 4) || - (vcpu->arch.mmio_vsx_copy_nums < 0) ) { + /* Currently, mmio_vsx_copy_nums only allowed to be 4 or less */ + if (vcpu->arch.mmio_vsx_copy_nums > 4) return EMULATE_FAIL; - } while (vcpu->arch.mmio_vsx_copy_nums) { if (kvmppc_get_vsr_data(vcpu, rs, &val) == -1) @@ -1312,6 +1340,111 @@ static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu, } #endif /* CONFIG_VSX */ +#ifdef CONFIG_ALTIVEC +/* handle quadword load access in two halves */ +int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rt, int is_default_endian) +{ + enum emulation_result emulated; + + while (vcpu->arch.mmio_vmx_copy_nums) { + emulated = __kvmppc_handle_load(run, vcpu, rt, 8, + is_default_endian, 0); + + if (emulated != EMULATE_DONE) + break; + + vcpu->arch.paddr_accessed += run->mmio.len; + vcpu->arch.mmio_vmx_copy_nums--; + } + + return emulated; +} + +static inline int kvmppc_get_vmx_data(struct kvm_vcpu *vcpu, int rs, u64 *val) +{ + vector128 vrs = VCPU_VSX_VR(vcpu, rs); + u32 di; + u64 w0, w1; + + di = 2 - vcpu->arch.mmio_vmx_copy_nums; /* doubleword index */ + if (di > 1) + return -1; + + if (vcpu->arch.mmio_host_swabbed) + di = 1 - di; + + w0 = vrs.u[di * 2]; + w1 = vrs.u[di * 2 + 1]; + +#ifdef __BIG_ENDIAN + *val = (w0 << 32) | w1; +#else + *val = (w1 << 32) | w0; +#endif + return 0; +} + +/* handle quadword store in two halves */ +int kvmppc_handle_store128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu, + unsigned int rs, int is_default_endian) +{ + u64 val = 0; + enum emulation_result emulated = EMULATE_DONE; + + vcpu->arch.io_gpr = rs; + + while (vcpu->arch.mmio_vmx_copy_nums) { + if (kvmppc_get_vmx_data(vcpu, rs, &val) == -1) + return EMULATE_FAIL; + + emulated = kvmppc_handle_store(run, vcpu, val, 8, + is_default_endian); + if (emulated != EMULATE_DONE) + break; + + vcpu->arch.paddr_accessed += run->mmio.len; + vcpu->arch.mmio_vmx_copy_nums--; + } + + return emulated; +} + +static int kvmppc_emulate_mmio_vmx_loadstore(struct kvm_vcpu *vcpu, + struct kvm_run *run) +{ + enum emulation_result emulated = EMULATE_FAIL; + int r; + + vcpu->arch.paddr_accessed += run->mmio.len; + + if (!vcpu->mmio_is_write) { + emulated = kvmppc_handle_load128_by2x64(run, vcpu, + vcpu->arch.io_gpr, 1); + } else { + emulated = kvmppc_handle_store128_by2x64(run, vcpu, + vcpu->arch.io_gpr, 1); + } + + switch (emulated) { + case EMULATE_DO_MMIO: + run->exit_reason = KVM_EXIT_MMIO; + r = RESUME_HOST; + break; + case EMULATE_FAIL: + pr_info("KVM: MMIO emulation failed (VMX repeat)\n"); + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + r = RESUME_HOST; + break; + default: + r = RESUME_GUEST; + break; + } + return r; +} +#endif /* CONFIG_ALTIVEC */ + int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) { int r = 0; @@ -1413,6 +1546,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) { int r; + vcpu_load(vcpu); + if (vcpu->mmio_needed) { vcpu->mmio_needed = 0; if (!vcpu->mmio_is_write) @@ -1427,7 +1562,19 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) r = kvmppc_emulate_mmio_vsx_loadstore(vcpu, run); if (r == RESUME_HOST) { vcpu->mmio_needed = 1; - return r; + goto out; + } + } +#endif +#ifdef CONFIG_ALTIVEC + if (vcpu->arch.mmio_vmx_copy_nums > 0) + vcpu->arch.mmio_vmx_copy_nums--; + + if (vcpu->arch.mmio_vmx_copy_nums > 0) { + r = kvmppc_emulate_mmio_vmx_loadstore(vcpu, run); + if (r == RESUME_HOST) { + vcpu->mmio_needed = 1; + goto out; } } #endif @@ -1461,6 +1608,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_sigset_deactivate(vcpu); +out: + vcpu_put(vcpu); return r; } @@ -1608,23 +1757,31 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return -EINVAL; } -long kvm_arch_vcpu_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +long kvm_arch_vcpu_async_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; - long r; - switch (ioctl) { - case KVM_INTERRUPT: { + if (ioctl == KVM_INTERRUPT) { struct kvm_interrupt irq; - r = -EFAULT; if (copy_from_user(&irq, argp, sizeof(irq))) - goto out; - r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); - goto out; + return -EFAULT; + return kvm_vcpu_ioctl_interrupt(vcpu, &irq); } + return -ENOIOCTLCMD; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + long r; + + vcpu_load(vcpu); + switch (ioctl) { case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; @@ -1664,6 +1821,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } out: + vcpu_put(vcpu); return r; } diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c index e44d2b2ea97e..1c03c978eb18 100644 --- a/arch/powerpc/kvm/timing.c +++ b/arch/powerpc/kvm/timing.c @@ -143,8 +143,7 @@ static int kvmppc_exit_timing_show(struct seq_file *m, void *private) int i; u64 min, max, sum, sum_quad; - seq_printf(m, "%s", "type count min max sum sum_squared\n"); - + seq_puts(m, "type count min max sum sum_squared\n"); for (i = 0; i < __NUMBER_OF_KVM_EXIT_TYPES; i++) { diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c index d60a62bf4fc7..0ab297c4cfad 100644 --- a/arch/powerpc/mm/mmu_context.c +++ b/arch/powerpc/mm/mmu_context.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/cpu.h> +#include <linux/sched/mm.h> #include <asm/mmu_context.h> @@ -58,6 +59,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * * On the read side the barrier is in pte_xchg(), which orders * the store to the PTE vs the load of mm_cpumask. + * + * This full barrier is needed by membarrier when switching + * between processes after store to rq->curr, before user-space + * memory accesses. */ smp_mb(); @@ -80,6 +85,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (new_on_cpu) radix_kvm_prefetch_workaround(next); + else + membarrier_arch_switch_mm(prev, next, tsk); /* * The actual HW switching method differs between the various diff --git a/arch/powerpc/platforms/cell/spufs/backing_ops.c b/arch/powerpc/platforms/cell/spufs/backing_ops.c index 1a9a756b0b2f..857580a78bbd 100644 --- a/arch/powerpc/platforms/cell/spufs/backing_ops.c +++ b/arch/powerpc/platforms/cell/spufs/backing_ops.c @@ -101,9 +101,9 @@ static __poll_t spu_backing_mbox_stat_poll(struct spu_context *ctx, but first mark any pending interrupts as done so we don't get woken up unnecessarily */ - if (events & (POLLIN | POLLRDNORM)) { + if (events & (EPOLLIN | EPOLLRDNORM)) { if (stat & 0xff0000) - ret |= POLLIN | POLLRDNORM; + ret |= EPOLLIN | EPOLLRDNORM; else { ctx->csa.priv1.int_stat_class2_RW &= ~CLASS2_MAILBOX_INTR; @@ -111,9 +111,9 @@ static __poll_t spu_backing_mbox_stat_poll(struct spu_context *ctx, CLASS2_ENABLE_MAILBOX_INTR; } } - if (events & (POLLOUT | POLLWRNORM)) { + if (events & (EPOLLOUT | EPOLLWRNORM)) { if (stat & 0x00ff00) - ret = POLLOUT | POLLWRNORM; + ret = EPOLLOUT | EPOLLWRNORM; else { ctx->csa.priv1.int_stat_class2_RW &= ~CLASS2_MAILBOX_THRESHOLD_INTR; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index c1be486da899..469bdd0b748f 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -774,7 +774,7 @@ static __poll_t spufs_ibox_poll(struct file *file, poll_table *wait) * that poll should not sleep. Will be fixed later. */ mutex_lock(&ctx->state_mutex); - mask = ctx->ops->mbox_stat_poll(ctx, POLLIN | POLLRDNORM); + mask = ctx->ops->mbox_stat_poll(ctx, EPOLLIN | EPOLLRDNORM); spu_release(ctx); return mask; @@ -910,7 +910,7 @@ static __poll_t spufs_wbox_poll(struct file *file, poll_table *wait) * that poll should not sleep. Will be fixed later. */ mutex_lock(&ctx->state_mutex); - mask = ctx->ops->mbox_stat_poll(ctx, POLLOUT | POLLWRNORM); + mask = ctx->ops->mbox_stat_poll(ctx, EPOLLOUT | EPOLLWRNORM); spu_release(ctx); return mask; @@ -1710,9 +1710,9 @@ static __poll_t spufs_mfc_poll(struct file *file,poll_table *wait) mask = 0; if (free_elements & 0xffff) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; if (tagstatus & ctx->tagwait) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; pr_debug("%s: free %d tagstatus %d tagwait %d\n", __func__, free_elements, tagstatus, ctx->tagwait); @@ -2469,7 +2469,7 @@ static __poll_t spufs_switch_log_poll(struct file *file, poll_table *wait) return rc; if (spufs_switch_log_used(ctx) > 0) - mask |= POLLIN; + mask |= EPOLLIN; spu_release(ctx); diff --git a/arch/powerpc/platforms/cell/spufs/hw_ops.c b/arch/powerpc/platforms/cell/spufs/hw_ops.c index fff58198b5b6..ae9d24d31eed 100644 --- a/arch/powerpc/platforms/cell/spufs/hw_ops.c +++ b/arch/powerpc/platforms/cell/spufs/hw_ops.c @@ -70,17 +70,17 @@ static __poll_t spu_hw_mbox_stat_poll(struct spu_context *ctx, __poll_t events) but first mark any pending interrupts as done so we don't get woken up unnecessarily */ - if (events & (POLLIN | POLLRDNORM)) { + if (events & (EPOLLIN | EPOLLRDNORM)) { if (stat & 0xff0000) - ret |= POLLIN | POLLRDNORM; + ret |= EPOLLIN | EPOLLRDNORM; else { spu_int_stat_clear(spu, 2, CLASS2_MAILBOX_INTR); spu_int_mask_or(spu, 2, CLASS2_ENABLE_MAILBOX_INTR); } } - if (events & (POLLOUT | POLLWRNORM)) { + if (events & (EPOLLOUT | EPOLLWRNORM)) { if (stat & 0x00ff00) - ret = POLLOUT | POLLWRNORM; + ret = EPOLLOUT | EPOLLWRNORM; else { spu_int_stat_clear(spu, 2, CLASS2_MAILBOX_THRESHOLD_INTR); diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index c18de0a9b1bd..4070bb4e9da4 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -153,7 +153,7 @@ static __poll_t opal_prd_poll(struct file *file, poll_wait(file, &opal_prd_msg_wait, wait); if (!opal_msg_queue_empty()) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index ebc244b08d67..d22aeb0b69e1 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -42,6 +42,7 @@ static u32 xive_provision_chip_count; static u32 xive_queue_shift; static u32 xive_pool_vps = XIVE_INVALID_VP; static struct kmem_cache *xive_provision_cache; +static bool xive_has_single_esc; int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data) { @@ -571,6 +572,10 @@ bool __init xive_native_init(void) break; } + /* Do we support single escalation */ + if (of_get_property(np, "single-escalation-support", NULL) != NULL) + xive_has_single_esc = true; + /* Configure Thread Management areas for KVM */ for_each_possible_cpu(cpu) kvmppc_set_xive_tima(cpu, r.start, tima); @@ -667,12 +672,15 @@ void xive_native_free_vp_block(u32 vp_base) } EXPORT_SYMBOL_GPL(xive_native_free_vp_block); -int xive_native_enable_vp(u32 vp_id) +int xive_native_enable_vp(u32 vp_id, bool single_escalation) { s64 rc; + u64 flags = OPAL_XIVE_VP_ENABLED; + if (single_escalation) + flags |= OPAL_XIVE_VP_SINGLE_ESCALATION; for (;;) { - rc = opal_xive_set_vp_info(vp_id, OPAL_XIVE_VP_ENABLED, 0); + rc = opal_xive_set_vp_info(vp_id, flags, 0); if (rc != OPAL_BUSY) break; msleep(1); @@ -710,3 +718,9 @@ int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id) return 0; } EXPORT_SYMBOL_GPL(xive_native_get_vp_info); + +bool xive_native_has_single_escalation(void) +{ + return xive_has_single_esc; +} +EXPORT_SYMBOL_GPL(xive_native_has_single_escalation); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 865e14f50c14..b6722c246d9c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -22,6 +22,7 @@ config RISCV select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_API_DEBUG select HAVE_DMA_CONTIGUOUS select HAVE_GENERIC_DMA_COHERENT @@ -43,6 +44,10 @@ config MMU config ARCH_PHYS_ADDR_T_64BIT def_bool y +config ZONE_DMA32 + bool + default y + config ARCH_DMA_ADDR_T_64BIT def_bool y @@ -55,6 +60,9 @@ config PAGE_OFFSET config STACKTRACE_SUPPORT def_bool y +config TRACE_IRQFLAGS_SUPPORT + def_bool y + config RWSEM_GENERIC_SPINLOCK def_bool y @@ -107,6 +115,8 @@ config ARCH_RV64I bool "RV64I" select CPU_SUPPORTS_64BIT_KERNEL select 64BIT + select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER endchoice diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 681ac0d09314..4286a5f83876 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -12,7 +12,6 @@ generic-y += errno.h generic-y += exec.h generic-y += fb.h generic-y += fcntl.h -generic-y += ftrace.h generic-y += futex.h generic-y += hardirq.h generic-y += hash.h diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 3c7a2c97e377..421fa3585798 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -40,15 +40,15 @@ #define SR_SD _AC(0x8000000000000000, UL) /* FS/XS dirty */ #endif -/* SPTBR flags */ +/* SATP flags */ #if __riscv_xlen == 32 -#define SPTBR_PPN _AC(0x003FFFFF, UL) -#define SPTBR_MODE_32 _AC(0x80000000, UL) -#define SPTBR_MODE SPTBR_MODE_32 +#define SATP_PPN _AC(0x003FFFFF, UL) +#define SATP_MODE_32 _AC(0x80000000, UL) +#define SATP_MODE SATP_MODE_32 #else -#define SPTBR_PPN _AC(0x00000FFFFFFFFFFF, UL) -#define SPTBR_MODE_39 _AC(0x8000000000000000, UL) -#define SPTBR_MODE SPTBR_MODE_39 +#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL) +#define SATP_MODE_39 _AC(0x8000000000000000, UL) +#define SATP_MODE SATP_MODE_39 #endif /* Interrupt Enable and Interrupt Pending flags */ diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h new file mode 100644 index 000000000000..66d4175eb13e --- /dev/null +++ b/arch/riscv/include/asm/ftrace.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +/* + * The graph frame test is not possible if CONFIG_FRAME_POINTER is not enabled. + * Check arch/riscv/kernel/mcount.S for detail. + */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_FRAME_POINTER) +#define HAVE_FUNCTION_GRAPH_FP_TEST +#endif diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h index 97424834dce2..336d60ec5698 100644 --- a/arch/riscv/include/asm/mmu_context.h +++ b/arch/riscv/include/asm/mmu_context.h @@ -39,16 +39,6 @@ static inline void destroy_context(struct mm_struct *mm) { } -static inline pgd_t *current_pgdir(void) -{ - return pfn_to_virt(csr_read(sptbr) & SPTBR_PPN); -} - -static inline void set_pgdir(pgd_t *pgd) -{ - csr_write(sptbr, virt_to_pfn(pgd) | SPTBR_MODE); -} - /* * When necessary, performs a deferred icache flush for the given MM context, * on the local CPU. RISC-V has no direct mechanism for instruction cache @@ -93,7 +83,12 @@ static inline void switch_mm(struct mm_struct *prev, cpumask_clear_cpu(cpu, mm_cpumask(prev)); cpumask_set_cpu(cpu, mm_cpumask(next)); - set_pgdir(next->pgd); + /* + * Use the old spbtr name instead of using the current satp + * name to support binutils 2.29 which doesn't know about the + * privileged ISA 1.10 yet. + */ + csr_write(sptbr, virt_to_pfn(next->pgd) | SATP_MODE); local_flush_tlb_all(); flush_icache_deferred(next); diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 7b9c24ebdf52..7b209aec355d 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -36,7 +36,14 @@ static inline void local_flush_tlb_page(unsigned long addr) #define flush_tlb_all() local_flush_tlb_all() #define flush_tlb_page(vma, addr) local_flush_tlb_page(addr) -#define flush_tlb_range(vma, start, end) local_flush_tlb_all() + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + local_flush_tlb_all(); +} + +#define flush_tlb_mm(mm) flush_tlb_all() #else /* CONFIG_SMP */ @@ -45,16 +52,13 @@ static inline void local_flush_tlb_page(unsigned long addr) #define flush_tlb_all() sbi_remote_sfence_vma(0, 0, -1) #define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0) #define flush_tlb_range(vma, start, end) \ - sbi_remote_sfence_vma(0, start, (end) - (start)) + sbi_remote_sfence_vma(mm_cpumask((vma)->vm_mm)->bits, \ + start, (end) - (start)) +#define flush_tlb_mm(mm) \ + sbi_remote_sfence_vma(mm_cpumask(mm)->bits, 0, -1) #endif /* CONFIG_SMP */ -/* Flush the TLB entries of the specified mm context */ -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - flush_tlb_all(); -} - /* Flush a range of kernel pages */ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h index 2f704a5c4196..080fb28061de 100644 --- a/arch/riscv/include/asm/unistd.h +++ b/arch/riscv/include/asm/unistd.h @@ -11,7 +11,6 @@ * GNU General Public License for more details. */ -#define __ARCH_HAVE_MMU #define __ARCH_WANT_SYS_CLONE #include <uapi/asm/unistd.h> #include <uapi/asm/syscalls.h> diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index ab8baf7bd142..196f62ffc428 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -2,6 +2,11 @@ # Makefile for the RISC-V Linux kernel # +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_ftrace.o = -pg +CFLAGS_REMOVE_setup.o = -pg +endif + extra-y += head.o extra-y += vmlinux.lds @@ -29,5 +34,7 @@ CFLAGS_setup.o := -mcmodel=medany obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_FUNCTION_TRACER) += mcount.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o clean: diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 7404ec222406..87fc045be51f 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -78,10 +78,13 @@ _save_context: REG_S x31, PT_T6(sp) /* - * Disable FPU to detect illegal usage of - * floating point in kernel space + * Disable user-mode memory access as it should only be set in the + * actual user copy routines. + * + * Disable the FPU to detect illegal usage of floating point in kernel + * space. */ - li t0, SR_FS + li t0, SR_SUM | SR_FS REG_L s0, TASK_TI_USER_SP(tp) csrrc s1, sstatus, t0 diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c new file mode 100644 index 000000000000..d0de68d144cb --- /dev/null +++ b/arch/riscv/kernel/ftrace.c @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2013 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * Copyright (C) 2017 Andes Technology Corporation + */ + +#include <linux/ftrace.h> + +/* + * Most of this file is copied from arm64. + */ +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; + struct ftrace_graph_ent trace; + int err; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * We don't suffer access faults, so no extra fault-recovery assembly + * is needed here. + */ + old = *parent; + + trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; + + if (!ftrace_graph_entry(&trace)) + return; + + err = ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer, NULL); + if (err == -EBUSY) + return; + *parent = return_hooker; +} diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 78f670d70133..226eeb190f90 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -74,15 +74,15 @@ relocate: sub a1, a1, a0 add ra, ra, a1 - /* Point stvec to virtual address of intruction after sptbr write */ + /* Point stvec to virtual address of intruction after satp write */ la a0, 1f add a0, a0, a1 csrw stvec, a0 - /* Compute sptbr for kernel page tables, but don't load it yet */ + /* Compute satp for kernel page tables, but don't load it yet */ la a2, swapper_pg_dir srl a2, a2, PAGE_SHIFT - li a1, SPTBR_MODE + li a1, SATP_MODE or a2, a2, a1 /* diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S new file mode 100644 index 000000000000..c46a778627be --- /dev/null +++ b/arch/riscv/kernel/mcount.S @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/asm.h> +#include <asm/csr.h> +#include <asm/unistd.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> +#include <asm-generic/export.h> +#include <asm/ftrace.h> + + .text + + .macro SAVE_ABI_STATE + addi sp, sp, -16 + sd s0, 0(sp) + sd ra, 8(sp) + addi s0, sp, 16 + .endm + + /* + * The call to ftrace_return_to_handler would overwrite the return + * register if a0 was not saved. + */ + .macro SAVE_RET_ABI_STATE + addi sp, sp, -32 + sd s0, 16(sp) + sd ra, 24(sp) + sd a0, 8(sp) + addi s0, sp, 32 + .endm + + .macro STORE_ABI_STATE + ld ra, 8(sp) + ld s0, 0(sp) + addi sp, sp, 16 + .endm + + .macro STORE_RET_ABI_STATE + ld ra, 24(sp) + ld s0, 16(sp) + ld a0, 8(sp) + addi sp, sp, 32 + .endm + +ENTRY(ftrace_stub) + ret +ENDPROC(ftrace_stub) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(return_to_handler) +/* + * On implementing the frame point test, the ideal way is to compare the + * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return. + * However, the psABI of variable-length-argument functions does not allow this. + * + * So alternatively we check the *old* frame pointer position, that is, the + * value stored in -16(s0) on entry, and the s0 on return. + */ +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + mv t6, s0 +#endif + SAVE_RET_ABI_STATE +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + mv a0, t6 +#endif + la t0, ftrace_return_to_handler + jalr t0 + mv a1, a0 + STORE_RET_ABI_STATE + jalr a1 +ENDPROC(return_to_handler) +EXPORT_SYMBOL(return_to_handler) +#endif + +ENTRY(_mcount) + la t4, ftrace_stub +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + la t0, ftrace_graph_return + ld t1, 0(t0) + bne t1, t4, do_ftrace_graph_caller + + la t3, ftrace_graph_entry + ld t2, 0(t3) + la t6, ftrace_graph_entry_stub + bne t2, t6, do_ftrace_graph_caller +#endif + la t3, ftrace_trace_function + ld t5, 0(t3) + bne t5, t4, do_trace + ret + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* + * A pseudo representation for the function graph tracer: + * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller) + */ +do_ftrace_graph_caller: + addi a0, s0, -8 + mv a1, ra +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + ld a2, -16(s0) +#endif + SAVE_ABI_STATE + la t0, prepare_ftrace_return + jalr t0 + STORE_ABI_STATE + ret +#endif + +/* + * A pseudo representation for the function tracer: + * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller) + */ +do_trace: + ld a1, -8(s0) + mv a0, ra + + SAVE_ABI_STATE + jalr t5 + STORE_ABI_STATE + ret +ENDPROC(_mcount) +EXPORT_SYMBOL(_mcount) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index cb7b0c63014e..09f7064e898c 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -49,10 +49,6 @@ struct screen_info screen_info = { }; #endif -#ifdef CONFIG_CMDLINE_BOOL -static char __initdata builtin_cmdline[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; -#endif /* CONFIG_CMDLINE_BOOL */ - unsigned long va_pa_offset; EXPORT_SYMBOL(va_pa_offset); unsigned long pfn_base; @@ -153,25 +149,6 @@ void __init sbi_save(unsigned int hartid, void *dtb) early_init_dt_scan(__va(dtb)); } -/* - * Allow the user to manually add a memory region (in case DTS is broken); - * "mem_end=nn[KkMmGg]" - */ -static int __init mem_end_override(char *p) -{ - resource_size_t base, end; - - if (!p) - return -EINVAL; - base = (uintptr_t) __pa(PAGE_OFFSET); - end = memparse(p, &p) & PMD_MASK; - if (end == 0) - return -EINVAL; - memblock_add(base, end - base); - return 0; -} -early_param("mem_end", mem_end_override); - static void __init setup_bootmem(void) { struct memblock_region *reg; @@ -204,22 +181,19 @@ static void __init setup_bootmem(void) early_init_fdt_scan_reserved_mem(); memblock_allow_resize(); memblock_dump_all(); + + for_each_memblock(memory, reg) { + unsigned long start_pfn = memblock_region_memory_base_pfn(reg); + unsigned long end_pfn = memblock_region_memory_end_pfn(reg); + + memblock_set_node(PFN_PHYS(start_pfn), + PFN_PHYS(end_pfn - start_pfn), + &memblock.memory, 0); + } } void __init setup_arch(char **cmdline_p) { -#ifdef CONFIG_CMDLINE_BOOL -#ifdef CONFIG_CMDLINE_OVERRIDE - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if (builtin_cmdline[0] != '\0') { - /* Append bootloader command line to built-in */ - strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); - strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } -#endif /* CONFIG_CMDLINE_OVERRIDE */ -#endif /* CONFIG_CMDLINE_BOOL */ *cmdline_p = boot_command_line; parse_early_param(); diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index e8a178df8144..582cb153eb24 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -74,7 +74,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, down_write(&mm->mmap_sem); vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); - if (unlikely(IS_ERR_VALUE(vdso_base))) { + if (IS_ERR_VALUE(vdso_base)) { ret = vdso_base; goto end; } diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index ceebfc29305b..148c98ca9b45 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -238,6 +238,10 @@ vmalloc_fault: * Do _not_ use "tsk->active_mm->pgd" here. * We might be inside an interrupt in the middle * of a task switch. + * + * Note: Use the old spbtr name instead of using the current + * satp name to support binutils 2.29 which doesn't know about + * the privileged ISA 1.10 yet. */ index = pgd_index(addr); pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)) + index; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 9f4bee5e51fd..c77df8142be2 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -17,6 +17,7 @@ #include <linux/initrd.h> #include <linux/memblock.h> #include <linux/swap.h> +#include <linux/sizes.h> #include <asm/tlbflush.h> #include <asm/sections.h> @@ -25,11 +26,12 @@ static void __init zone_sizes_init(void) { - unsigned long zones_size[MAX_NR_ZONES]; + unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; - memset(zones_size, 0, sizeof(zones_size)); - zones_size[ZONE_NORMAL] = max_mapnr; - free_area_init_node(0, zones_size, pfn_base, NULL); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn)); + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; + + free_area_init_nodes(max_zone_pfns); } void setup_zero_page(void) @@ -39,8 +41,6 @@ void setup_zero_page(void) void __init paging_init(void) { - init_mm.pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)); - setup_zero_page(); local_flush_tlb_all(); zone_sizes_init(); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 0105ce28e246..eaee7087886f 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -112,7 +112,6 @@ config S390 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT - select ARCH_WANTS_PROT_NUMA_PROT_NONE select ARCH_WANTS_UBSAN_NO_NULL select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_EXTABLE_SORT @@ -540,6 +539,51 @@ config ARCH_RANDOM If unsure, say Y. +config KERNEL_NOBP + def_bool n + prompt "Enable modified branch prediction for the kernel by default" + help + If this option is selected the kernel will switch to a modified + branch prediction mode if the firmware interface is available. + The modified branch prediction mode improves the behaviour in + regard to speculative execution. + + With the option enabled the kernel parameter "nobp=0" or "nospec" + can be used to run the kernel in the normal branch prediction mode. + + With the option disabled the modified branch prediction mode is + enabled with the "nobp=1" kernel parameter. + + If unsure, say N. + +config EXPOLINE + def_bool n + prompt "Avoid speculative indirect branches in the kernel" + help + Compile the kernel with the expoline compiler options to guard + against kernel-to-user data leaks by avoiding speculative indirect + branches. + Requires a compiler with -mindirect-branch=thunk support for full + protection. The kernel may run slower. + + If unsure, say N. + +choice + prompt "Expoline default" + depends on EXPOLINE + default EXPOLINE_FULL + +config EXPOLINE_OFF + bool "spectre_v2=off" + +config EXPOLINE_MEDIUM + bool "spectre_v2=auto" + +config EXPOLINE_FULL + bool "spectre_v2=on" + +endchoice + endmenu menu "Memory setup" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index fd691c4ff89e..2ced3239cb84 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -78,6 +78,16 @@ ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y) cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack endif +ifdef CONFIG_EXPOLINE + ifeq ($(call cc-option-yn,$(CC_FLAGS_MARCH) -mindirect-branch=thunk),y) + CC_FLAGS_EXPOLINE := -mindirect-branch=thunk + CC_FLAGS_EXPOLINE += -mfunction-return=thunk + CC_FLAGS_EXPOLINE += -mindirect-branch-table + export CC_FLAGS_EXPOLINE + cflags-y += $(CC_FLAGS_EXPOLINE) + endif +endif + ifdef CONFIG_FUNCTION_TRACER # make use of hotpatch feature if the compiler supports it cc_hotpatch := -mhotpatch=0,3 diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index 10432607a573..f9eddbca79d2 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -49,6 +49,30 @@ do { \ #define __smp_mb__before_atomic() barrier() #define __smp_mb__after_atomic() barrier() +/** + * array_index_mask_nospec - generate a mask for array_idx() that is + * ~0UL when the bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + */ +#define array_index_mask_nospec array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + if (__builtin_constant_p(size) && size > 0) { + asm(" clgr %2,%1\n" + " slbgr %0,%0\n" + :"=d" (mask) : "d" (size-1), "d" (index) :"cc"); + return mask; + } + asm(" clgr %1,%2\n" + " slbgr %0,%0\n" + :"=d" (mask) : "d" (size), "d" (index) :"cc"); + return ~mask; +} + #include <asm-generic/barrier.h> #endif /* __ASM_BARRIER_H */ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 31e400c1a1f3..86e5b2fdee3c 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -261,6 +261,11 @@ static inline void clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); } +static inline int test_and_clear_bit_inv(unsigned long nr, volatile unsigned long *ptr) +{ + return test_and_clear_bit(nr ^ (BITS_PER_LONG - 1), ptr); +} + static inline void __set_bit_inv(unsigned long nr, volatile unsigned long *ptr) { return __set_bit(nr ^ (BITS_PER_LONG - 1), ptr); diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h index a478eb61aaf7..fb56fa3283a2 100644 --- a/arch/s390/include/asm/css_chars.h +++ b/arch/s390/include/asm/css_chars.h @@ -20,7 +20,9 @@ struct css_general_char { u32 aif_tdd : 1; /* bit 56 */ u32 : 1; u32 qebsm : 1; /* bit 58 */ - u32 : 8; + u32 : 2; + u32 aiv : 1; /* bit 61 */ + u32 : 5; u32 aif_osa : 1; /* bit 67 */ u32 : 12; u32 eadm_rf : 1; /* bit 80 */ diff --git a/arch/s390/include/asm/eadm.h b/arch/s390/include/asm/eadm.h index eb5323161f11..bb63b2afdf6f 100644 --- a/arch/s390/include/asm/eadm.h +++ b/arch/s390/include/asm/eadm.h @@ -4,7 +4,7 @@ #include <linux/types.h> #include <linux/device.h> -#include <linux/blkdev.h> +#include <linux/blk_types.h> struct arqb { u64 data; diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index fbe0c4be3cd8..99c8ce30b3cd 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -15,6 +15,24 @@ #define MAX_FACILITY_BIT (sizeof(((struct lowcore *)0)->stfle_fac_list) * 8) +static inline void __set_facility(unsigned long nr, void *facilities) +{ + unsigned char *ptr = (unsigned char *) facilities; + + if (nr >= MAX_FACILITY_BIT) + return; + ptr[nr >> 3] |= 0x80 >> (nr & 7); +} + +static inline void __clear_facility(unsigned long nr, void *facilities) +{ + unsigned char *ptr = (unsigned char *) facilities; + + if (nr >= MAX_FACILITY_BIT) + return; + ptr[nr >> 3] &= ~(0x80 >> (nr & 7)); +} + static inline int __test_facility(unsigned long nr, void *facilities) { unsigned char *ptr; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index c1b0a9ac1dc8..afb0f08b8021 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -2,7 +2,7 @@ /* * definition for kernel virtual machines on s390 * - * Copyright IBM Corp. 2008, 2009 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> */ @@ -183,6 +183,7 @@ struct kvm_s390_sie_block { #define ECA_IB 0x40000000 #define ECA_SIGPI 0x10000000 #define ECA_MVPGI 0x01000000 +#define ECA_AIV 0x00200000 #define ECA_VX 0x00020000 #define ECA_PROTEXCI 0x00002000 #define ECA_SII 0x00000001 @@ -228,7 +229,9 @@ struct kvm_s390_sie_block { __u8 epdx; /* 0x0069 */ __u8 reserved6a[2]; /* 0x006a */ __u32 todpr; /* 0x006c */ - __u8 reserved70[16]; /* 0x0070 */ +#define GISA_FORMAT1 0x00000001 + __u32 gd; /* 0x0070 */ + __u8 reserved74[12]; /* 0x0074 */ __u64 mso; /* 0x0080 */ __u64 msl; /* 0x0088 */ psw_t gpsw; /* 0x0090 */ @@ -317,18 +320,30 @@ struct kvm_vcpu_stat { u64 deliver_program_int; u64 deliver_io_int; u64 exit_wait_state; + u64 instruction_epsw; + u64 instruction_gs; + u64 instruction_io_other; + u64 instruction_lpsw; + u64 instruction_lpswe; u64 instruction_pfmf; + u64 instruction_ptff; + u64 instruction_sck; + u64 instruction_sckpf; u64 instruction_stidp; u64 instruction_spx; u64 instruction_stpx; u64 instruction_stap; - u64 instruction_storage_key; + u64 instruction_iske; + u64 instruction_ri; + u64 instruction_rrbe; + u64 instruction_sske; u64 instruction_ipte_interlock; - u64 instruction_stsch; - u64 instruction_chsc; u64 instruction_stsi; u64 instruction_stfl; + u64 instruction_tb; + u64 instruction_tpi; u64 instruction_tprot; + u64 instruction_tsch; u64 instruction_sie; u64 instruction_essa; u64 instruction_sthyi; @@ -354,6 +369,7 @@ struct kvm_vcpu_stat { u64 diagnose_258; u64 diagnose_308; u64 diagnose_500; + u64 diagnose_other; }; #define PGM_OPERATION 0x01 @@ -410,35 +426,35 @@ struct kvm_vcpu_stat { #define PGM_PER 0x80 #define PGM_CRYPTO_OPERATION 0x119 -/* irq types in order of priority */ +/* irq types in ascend order of priorities */ enum irq_types { - IRQ_PEND_MCHK_EX = 0, - IRQ_PEND_SVC, - IRQ_PEND_PROG, - IRQ_PEND_MCHK_REP, - IRQ_PEND_EXT_IRQ_KEY, - IRQ_PEND_EXT_MALFUNC, - IRQ_PEND_EXT_EMERGENCY, - IRQ_PEND_EXT_EXTERNAL, - IRQ_PEND_EXT_CLOCK_COMP, - IRQ_PEND_EXT_CPU_TIMER, - IRQ_PEND_EXT_TIMING, - IRQ_PEND_EXT_SERVICE, - IRQ_PEND_EXT_HOST, - IRQ_PEND_PFAULT_INIT, - IRQ_PEND_PFAULT_DONE, - IRQ_PEND_VIRTIO, - IRQ_PEND_IO_ISC_0, - IRQ_PEND_IO_ISC_1, - IRQ_PEND_IO_ISC_2, - IRQ_PEND_IO_ISC_3, - IRQ_PEND_IO_ISC_4, - IRQ_PEND_IO_ISC_5, - IRQ_PEND_IO_ISC_6, - IRQ_PEND_IO_ISC_7, - IRQ_PEND_SIGP_STOP, + IRQ_PEND_SET_PREFIX = 0, IRQ_PEND_RESTART, - IRQ_PEND_SET_PREFIX, + IRQ_PEND_SIGP_STOP, + IRQ_PEND_IO_ISC_7, + IRQ_PEND_IO_ISC_6, + IRQ_PEND_IO_ISC_5, + IRQ_PEND_IO_ISC_4, + IRQ_PEND_IO_ISC_3, + IRQ_PEND_IO_ISC_2, + IRQ_PEND_IO_ISC_1, + IRQ_PEND_IO_ISC_0, + IRQ_PEND_VIRTIO, + IRQ_PEND_PFAULT_DONE, + IRQ_PEND_PFAULT_INIT, + IRQ_PEND_EXT_HOST, + IRQ_PEND_EXT_SERVICE, + IRQ_PEND_EXT_TIMING, + IRQ_PEND_EXT_CPU_TIMER, + IRQ_PEND_EXT_CLOCK_COMP, + IRQ_PEND_EXT_EXTERNAL, + IRQ_PEND_EXT_EMERGENCY, + IRQ_PEND_EXT_MALFUNC, + IRQ_PEND_EXT_IRQ_KEY, + IRQ_PEND_MCHK_REP, + IRQ_PEND_PROG, + IRQ_PEND_SVC, + IRQ_PEND_MCHK_EX, IRQ_PEND_COUNT }; @@ -516,9 +532,6 @@ struct kvm_s390_irq_payload { struct kvm_s390_local_interrupt { spinlock_t lock; - struct kvm_s390_float_interrupt *float_int; - struct swait_queue_head *wq; - atomic_t *cpuflags; DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); struct kvm_s390_irq_payload irq; unsigned long pending_irqs; @@ -707,14 +720,50 @@ struct kvm_s390_crypto_cb { struct kvm_s390_apcb1 apcb1; /* 0x0080 */ }; +struct kvm_s390_gisa { + union { + struct { /* common to all formats */ + u32 next_alert; + u8 ipm; + u8 reserved01[2]; + u8 iam; + }; + struct { /* format 0 */ + u32 next_alert; + u8 ipm; + u8 reserved01; + u8 : 6; + u8 g : 1; + u8 c : 1; + u8 iam; + u8 reserved02[4]; + u32 airq_count; + } g0; + struct { /* format 1 */ + u32 next_alert; + u8 ipm; + u8 simm; + u8 nimm; + u8 iam; + u8 aism[8]; + u8 : 6; + u8 g : 1; + u8 c : 1; + u8 reserved03[11]; + u32 airq_count; + } g1; + }; +}; + /* - * sie_page2 has to be allocated as DMA because fac_list and crycb need - * 31bit addresses in the sie control block. + * sie_page2 has to be allocated as DMA because fac_list, crycb and + * gisa need 31bit addresses in the sie control block. */ struct sie_page2 { __u64 fac_list[S390_ARCH_FAC_LIST_SIZE_U64]; /* 0x0000 */ struct kvm_s390_crypto_cb crycb; /* 0x0800 */ - u8 reserved900[0x1000 - 0x900]; /* 0x0900 */ + struct kvm_s390_gisa gisa; /* 0x0900 */ + u8 reserved920[0x1000 - 0x920]; /* 0x0920 */ }; struct kvm_s390_vsie { @@ -761,6 +810,7 @@ struct kvm_arch{ struct kvm_s390_migration_state *migration_state; /* subset of available cpu features enabled by user space */ DECLARE_BITMAP(cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS); + struct kvm_s390_gisa *gisa; }; #define KVM_HVA_ERR_BAD (-1UL) diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index ec6592e8ba36..5bc888841eaf 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -136,7 +136,11 @@ struct lowcore { __u64 vdso_per_cpu_data; /* 0x03b8 */ __u64 machine_flags; /* 0x03c0 */ __u64 gmap; /* 0x03c8 */ - __u8 pad_0x03d0[0x0e00-0x03d0]; /* 0x03d0 */ + __u8 pad_0x03d0[0x0400-0x03d0]; /* 0x03d0 */ + + /* br %r1 trampoline */ + __u16 br_r1_trampoline; /* 0x0400 */ + __u8 pad_0x0402[0x0e00-0x0402]; /* 0x0402 */ /* * 0xe00 contains the address of the IPL Parameter Information @@ -151,7 +155,8 @@ struct lowcore { __u8 pad_0x0e20[0x0f00-0x0e20]; /* 0x0e20 */ /* Extended facility list */ - __u64 stfle_fac_list[32]; /* 0x0f00 */ + __u64 stfle_fac_list[16]; /* 0x0f00 */ + __u64 alt_stfle_fac_list[16]; /* 0x0f80 */ __u8 pad_0x1000[0x11b0-0x1000]; /* 0x1000 */ /* Pointer to the machine check extended save area */ diff --git a/arch/s390/include/asm/nospec-branch.h b/arch/s390/include/asm/nospec-branch.h new file mode 100644 index 000000000000..7df48e5cf36f --- /dev/null +++ b/arch/s390/include/asm/nospec-branch.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_EXPOLINE_H +#define _ASM_S390_EXPOLINE_H + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +extern int nospec_call_disable; +extern int nospec_return_disable; + +void nospec_init_branches(void); +void nospec_call_revert(s32 *start, s32 *end); +void nospec_return_revert(s32 *start, s32 *end); + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_S390_EXPOLINE_H */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index bfbfad482289..7f2953c15c37 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -91,6 +91,7 @@ void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; extern int sysctl_ieee_emulation_warnings; extern void execve_tail(void); +extern void __bpon(void); /* * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit. @@ -377,6 +378,9 @@ extern void memcpy_absolute(void *, void *, size_t); memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ } while (0) +extern int s390_isolate_bp(void); +extern int s390_isolate_bp_guest(void); + #endif /* __ASSEMBLY__ */ #endif /* __ASM_S390_PROCESSOR_H */ diff --git a/arch/s390/include/asm/runtime_instr.h b/arch/s390/include/asm/runtime_instr.h index 6b1540337ed6..0e1605538cd4 100644 --- a/arch/s390/include/asm/runtime_instr.h +++ b/arch/s390/include/asm/runtime_instr.h @@ -2,75 +2,10 @@ #ifndef _RUNTIME_INSTR_H #define _RUNTIME_INSTR_H -#define S390_RUNTIME_INSTR_START 0x1 -#define S390_RUNTIME_INSTR_STOP 0x2 - -struct runtime_instr_cb { - __u64 rca; - __u64 roa; - __u64 rla; - - __u32 v : 1; - __u32 s : 1; - __u32 k : 1; - __u32 h : 1; - __u32 a : 1; - __u32 reserved1 : 3; - __u32 ps : 1; - __u32 qs : 1; - __u32 pc : 1; - __u32 qc : 1; - __u32 reserved2 : 1; - __u32 g : 1; - __u32 u : 1; - __u32 l : 1; - __u32 key : 4; - __u32 reserved3 : 8; - __u32 t : 1; - __u32 rgs : 3; - - __u32 m : 4; - __u32 n : 1; - __u32 mae : 1; - __u32 reserved4 : 2; - __u32 c : 1; - __u32 r : 1; - __u32 b : 1; - __u32 j : 1; - __u32 e : 1; - __u32 x : 1; - __u32 reserved5 : 2; - __u32 bpxn : 1; - __u32 bpxt : 1; - __u32 bpti : 1; - __u32 bpni : 1; - __u32 reserved6 : 2; - - __u32 d : 1; - __u32 f : 1; - __u32 ic : 4; - __u32 dc : 4; - - __u64 reserved7; - __u64 sf; - __u64 rsic; - __u64 reserved8; -} __packed __aligned(8); +#include <uapi/asm/runtime_instr.h> extern struct runtime_instr_cb runtime_instr_empty_cb; -static inline void load_runtime_instr_cb(struct runtime_instr_cb *cb) -{ - asm volatile(".insn rsy,0xeb0000000060,0,0,%0" /* LRIC */ - : : "Q" (*cb)); -} - -static inline void store_runtime_instr_cb(struct runtime_instr_cb *cb) -{ - asm volatile(".insn rsy,0xeb0000000061,0,0,%0" /* STRIC */ - : "=Q" (*cb) : : "cc"); -} - static inline void save_ri_cb(struct runtime_instr_cb *cb_prev) { if (cb_prev) diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index d3c1a8a2e3ad..3cae9168f63c 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -77,6 +77,7 @@ struct sclp_info { unsigned char has_ibs : 1; unsigned char has_skey : 1; unsigned char has_kss : 1; + unsigned char has_gisaf : 1; unsigned int ibc; unsigned int mtid; unsigned int mtid_cp; diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h index 25057c118d56..fe7b3f8f0791 100644 --- a/arch/s390/include/asm/sysinfo.h +++ b/arch/s390/include/asm/sysinfo.h @@ -21,7 +21,8 @@ struct sysinfo_1_1_1 { unsigned char :8; unsigned char ccr; unsigned char cai; - char reserved_0[28]; + char reserved_0[20]; + unsigned long lic; char manufacturer[16]; char type[4]; char reserved_1[12]; diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 25d6ec3aaddd..83ba57533ce6 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -58,6 +58,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */ #define TIF_PATCH_PENDING 5 /* pending live patching update */ #define TIF_PGSTE 6 /* New mm's will use 4K page tables */ +#define TIF_ISOLATE_BP 8 /* Run process with isolated BP */ +#define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */ #define TIF_31BIT 16 /* 32bit process */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ @@ -78,6 +80,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #define _TIF_UPROBE _BITUL(TIF_UPROBE) #define _TIF_GUARDED_STORAGE _BITUL(TIF_GUARDED_STORAGE) #define _TIF_PATCH_PENDING _BITUL(TIF_PATCH_PENDING) +#define _TIF_ISOLATE_BP _BITUL(TIF_ISOLATE_BP) +#define _TIF_ISOLATE_BP_GUEST _BITUL(TIF_ISOLATE_BP_GUEST) #define _TIF_31BIT _BITUL(TIF_31BIT) #define _TIF_SINGLE_STEP _BITUL(TIF_SINGLE_STEP) diff --git a/arch/s390/include/uapi/asm/runtime_instr.h b/arch/s390/include/uapi/asm/runtime_instr.h new file mode 100644 index 000000000000..45c9ec984e6b --- /dev/null +++ b/arch/s390/include/uapi/asm/runtime_instr.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _S390_UAPI_RUNTIME_INSTR_H +#define _S390_UAPI_RUNTIME_INSTR_H + +#include <linux/types.h> + +#define S390_RUNTIME_INSTR_START 0x1 +#define S390_RUNTIME_INSTR_STOP 0x2 + +struct runtime_instr_cb { + __u64 rca; + __u64 roa; + __u64 rla; + + __u32 v : 1; + __u32 s : 1; + __u32 k : 1; + __u32 h : 1; + __u32 a : 1; + __u32 reserved1 : 3; + __u32 ps : 1; + __u32 qs : 1; + __u32 pc : 1; + __u32 qc : 1; + __u32 reserved2 : 1; + __u32 g : 1; + __u32 u : 1; + __u32 l : 1; + __u32 key : 4; + __u32 reserved3 : 8; + __u32 t : 1; + __u32 rgs : 3; + + __u32 m : 4; + __u32 n : 1; + __u32 mae : 1; + __u32 reserved4 : 2; + __u32 c : 1; + __u32 r : 1; + __u32 b : 1; + __u32 j : 1; + __u32 e : 1; + __u32 x : 1; + __u32 reserved5 : 2; + __u32 bpxn : 1; + __u32 bpxt : 1; + __u32 bpti : 1; + __u32 bpni : 1; + __u32 reserved6 : 2; + + __u32 d : 1; + __u32 f : 1; + __u32 ic : 4; + __u32 dc : 4; + + __u64 reserved7; + __u64 sf; + __u64 rsic; + __u64 reserved8; +} __packed __aligned(8); + +static inline void load_runtime_instr_cb(struct runtime_instr_cb *cb) +{ + asm volatile(".insn rsy,0xeb0000000060,0,0,%0" /* LRIC */ + : : "Q" (*cb)); +} + +static inline void store_runtime_instr_cb(struct runtime_instr_cb *cb) +{ + asm volatile(".insn rsy,0xeb0000000061,0,0,%0" /* STRIC */ + : "=Q" (*cb) : : "cc"); +} + +#endif /* _S390_UAPI_RUNTIME_INSTR_H */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 909bce65cb2b..7f27e3da9709 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -29,6 +29,7 @@ UBSAN_SANITIZE_early.o := n # ifneq ($(CC_FLAGS_MARCH),-march=z900) CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH) +CFLAGS_REMOVE_als.o += $(CC_FLAGS_EXPOLINE) CFLAGS_als.o += -march=z900 AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH) AFLAGS_head.o += -march=z900 @@ -63,6 +64,9 @@ obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o extra-y += head.o head64.o vmlinux.lds +obj-$(CONFIG_EXPOLINE) += nospec-branch.o +CFLAGS_REMOVE_expoline.o += $(CC_FLAGS_EXPOLINE) + obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCHED_TOPOLOGY) += topology.o diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c index 574e77622c04..22476135f738 100644 --- a/arch/s390/kernel/alternative.c +++ b/arch/s390/kernel/alternative.c @@ -15,6 +15,29 @@ static int __init disable_alternative_instructions(char *str) early_param("noaltinstr", disable_alternative_instructions); +static int __init nobp_setup_early(char *str) +{ + bool enabled; + int rc; + + rc = kstrtobool(str, &enabled); + if (rc) + return rc; + if (enabled && test_facility(82)) + __set_facility(82, S390_lowcore.alt_stfle_fac_list); + else + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); + return 0; +} +early_param("nobp", nobp_setup_early); + +static int __init nospec_setup_early(char *str) +{ + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); + return 0; +} +early_param("nospec", nospec_setup_early); + struct brcl_insn { u16 opc; s32 disp; @@ -75,7 +98,8 @@ static void __init_or_module __apply_alternatives(struct alt_instr *start, instr = (u8 *)&a->instr_offset + a->instr_offset; replacement = (u8 *)&a->repl_offset + a->repl_offset; - if (!test_facility(a->facility)) + if (!__test_facility(a->facility, + S390_lowcore.alt_stfle_fac_list)) continue; if (unlikely(a->instrlen % 2 || a->replacementlen % 2)) { diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 497a92047591..ac707a9f729e 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -193,6 +193,11 @@ static noinline __init void setup_facility_list(void) { stfle(S390_lowcore.stfle_fac_list, ARRAY_SIZE(S390_lowcore.stfle_fac_list)); + memcpy(S390_lowcore.alt_stfle_fac_list, + S390_lowcore.stfle_fac_list, + sizeof(S390_lowcore.alt_stfle_fac_list)); + if (!IS_ENABLED(CONFIG_KERNEL_NOBP)) + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); } static __init void detect_diag9c(void) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 6cd444d25545..13a133a6015c 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -107,6 +107,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 3f 1: UPDATE_VTIME %r14,%r15,\timer + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP 2: lg %r15,__LC_ASYNC_STACK # load async stack 3: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm @@ -159,6 +160,130 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) tm off+\addr, \mask .endm + .macro BPOFF + .pushsection .altinstr_replacement, "ax" +660: .long 0xb2e8c000 + .popsection +661: .long 0x47000000 + .pushsection .altinstructions, "a" + .long 661b - . + .long 660b - . + .word 82 + .byte 4 + .byte 4 + .popsection + .endm + + .macro BPON + .pushsection .altinstr_replacement, "ax" +662: .long 0xb2e8d000 + .popsection +663: .long 0x47000000 + .pushsection .altinstructions, "a" + .long 663b - . + .long 662b - . + .word 82 + .byte 4 + .byte 4 + .popsection + .endm + + .macro BPENTER tif_ptr,tif_mask + .pushsection .altinstr_replacement, "ax" +662: .word 0xc004, 0x0000, 0x0000 # 6 byte nop + .word 0xc004, 0x0000, 0x0000 # 6 byte nop + .popsection +664: TSTMSK \tif_ptr,\tif_mask + jz . + 8 + .long 0xb2e8d000 + .pushsection .altinstructions, "a" + .long 664b - . + .long 662b - . + .word 82 + .byte 12 + .byte 12 + .popsection + .endm + + .macro BPEXIT tif_ptr,tif_mask + TSTMSK \tif_ptr,\tif_mask + .pushsection .altinstr_replacement, "ax" +662: jnz . + 8 + .long 0xb2e8d000 + .popsection +664: jz . + 8 + .long 0xb2e8c000 + .pushsection .altinstructions, "a" + .long 664b - . + .long 662b - . + .word 82 + .byte 8 + .byte 8 + .popsection + .endm + +#ifdef CONFIG_EXPOLINE + + .macro GEN_BR_THUNK name,reg,tmp + .section .text.\name,"axG",@progbits,\name,comdat + .globl \name + .hidden \name + .type \name,@function +\name: + .cfi_startproc +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + exrl 0,0f +#else + larl \tmp,0f + ex 0,0(\tmp) +#endif + j . +0: br \reg + .cfi_endproc + .endm + + GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1 + GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1 + GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11 + + .macro BASR_R14_R9 +0: brasl %r14,__s390x_indirect_jump_r1use_r9 + .pushsection .s390_indirect_branches,"a",@progbits + .long 0b-. + .popsection + .endm + + .macro BR_R1USE_R14 +0: jg __s390x_indirect_jump_r1use_r14 + .pushsection .s390_indirect_branches,"a",@progbits + .long 0b-. + .popsection + .endm + + .macro BR_R11USE_R14 +0: jg __s390x_indirect_jump_r11use_r14 + .pushsection .s390_indirect_branches,"a",@progbits + .long 0b-. + .popsection + .endm + +#else /* CONFIG_EXPOLINE */ + + .macro BASR_R14_R9 + basr %r14,%r9 + .endm + + .macro BR_R1USE_R14 + br %r14 + .endm + + .macro BR_R11USE_R14 + br %r14 + .endm + +#endif /* CONFIG_EXPOLINE */ + + .section .kprobes.text, "ax" .Ldummy: /* @@ -171,6 +296,11 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) */ nop 0 +ENTRY(__bpon) + .globl __bpon + BPON + BR_R1USE_R14 + /* * Scheduler resume function, called by switch_to * gpr2 = (task_struct *) prev @@ -193,9 +323,9 @@ ENTRY(__switch_to) mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_LPP - bzr %r14 + jz 0f .insn s,0xb2800000,__LC_LPP # set program parameter - br %r14 +0: BR_R1USE_R14 .L__critical_start: @@ -207,9 +337,11 @@ ENTRY(__switch_to) */ ENTRY(sie64a) stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers + lg %r12,__LC_CURRENT stg %r2,__SF_EMPTY(%r15) # save control block pointer stg %r3,__SF_EMPTY+8(%r15) # save guest register save area xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # reason code = 0 + mvc __SF_EMPTY+24(8,%r15),__TI_flags(%r12) # copy thread flags TSTMSK __LC_CPU_FLAGS,_CIF_FPU # load guest fp/vx registers ? jno .Lsie_load_guest_gprs brasl %r14,load_fpu_regs # load guest fp/vx regs @@ -226,8 +358,12 @@ ENTRY(sie64a) jnz .Lsie_skip TSTMSK __LC_CPU_FLAGS,_CIF_FPU jo .Lsie_skip # exit if fp/vx regs changed + BPEXIT __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) .Lsie_entry: sie 0(%r14) +.Lsie_exit: + BPOFF + BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) .Lsie_skip: ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce @@ -248,9 +384,15 @@ ENTRY(sie64a) sie_exit: lg %r14,__SF_EMPTY+8(%r15) # load guest register save area stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + xgr %r0,%r0 # clear guest registers to + xgr %r1,%r1 # prevent speculative use + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers lg %r2,__SF_EMPTY+16(%r15) # return exit reason code - br %r14 + BR_R1USE_R14 .Lsie_fault: lghi %r14,-EFAULT stg %r14,__SF_EMPTY+16(%r15) # set exit reason code @@ -273,6 +415,7 @@ ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER .Lsysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC + BPOFF lg %r12,__LC_CURRENT lghi %r13,__TASK_thread lghi %r14,_PIF_SYSCALL @@ -281,7 +424,10 @@ ENTRY(system_call) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs .Lsysc_vtime: UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled register to prevent speculative use + xgr %r0,%r0 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC @@ -305,7 +451,7 @@ ENTRY(system_call) lgf %r9,0(%r8,%r10) # get system call add. TSTMSK __TI_flags(%r12),_TIF_TRACE jnz .Lsysc_tracesys - basr %r14,%r9 # call sys_xxxx + BASR_R14_R9 # call sys_xxxx stg %r2,__PT_R2(%r11) # store return value .Lsysc_return: @@ -317,6 +463,7 @@ ENTRY(system_call) jnz .Lsysc_work # check for work TSTMSK __LC_CPU_FLAGS,_CIF_WORK jnz .Lsysc_work + BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP .Lsysc_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) @@ -489,7 +636,7 @@ ENTRY(system_call) lmg %r3,%r7,__PT_R3(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lg %r2,__PT_ORIG_GPR2(%r11) - basr %r14,%r9 # call sys_xxx + BASR_R14_R9 # call sys_xxx stg %r2,__PT_R2(%r11) # store return value .Lsysc_tracenogo: TSTMSK __TI_flags(%r12),_TIF_TRACE @@ -513,7 +660,7 @@ ENTRY(ret_from_fork) lmg %r9,%r10,__PT_R9(%r11) # load gprs ENTRY(kernel_thread_starter) la %r2,0(%r10) - basr %r14,%r9 + BASR_R14_R9 j .Lsysc_tracenogo /* @@ -522,6 +669,7 @@ ENTRY(kernel_thread_starter) ENTRY(pgm_check_handler) stpt __LC_SYNC_ENTER_TIMER + BPOFF stmg %r8,%r15,__LC_SAVE_AREA_SYNC lg %r10,__LC_LAST_BREAK lg %r12,__LC_CURRENT @@ -550,6 +698,7 @@ ENTRY(pgm_check_handler) aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 4f 2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP lg %r15,__LC_KERNEL_STACK lgr %r14,%r12 aghi %r14,__TASK_thread # pointer to thread_struct @@ -561,6 +710,15 @@ ENTRY(pgm_check_handler) 4: lgr %r13,%r11 la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC @@ -582,9 +740,9 @@ ENTRY(pgm_check_handler) nill %r10,0x007f sll %r10,2 je .Lpgm_return - lgf %r1,0(%r10,%r1) # load address of handler routine + lgf %r9,0(%r10,%r1) # load address of handler routine lgr %r2,%r11 # pass pointer to pt_regs - basr %r14,%r1 # branch to interrupt-handler + BASR_R14_R9 # branch to interrupt-handler .Lpgm_return: LOCKDEP_SYS_EXIT tm __PT_PSW+1(%r11),0x01 # returning to user ? @@ -620,12 +778,23 @@ ENTRY(pgm_check_handler) ENTRY(io_int_handler) STCK __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER + BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC lg %r12,__LC_CURRENT larl %r13,cleanup_critical lmg %r8,%r9,__LC_IO_OLD_PSW SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 + xgr %r10,%r10 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID @@ -660,9 +829,13 @@ ENTRY(io_int_handler) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jno .Lio_exit_kernel + BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP .Lio_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER +.Lio_exit_kernel: lmg %r11,%r15,__PT_R11(%r11) lpswe __LC_RETURN_PSW .Lio_done: @@ -833,12 +1006,23 @@ ENTRY(io_int_handler) ENTRY(ext_int_handler) STCK __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER + BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC lg %r12,__LC_CURRENT larl %r13,cleanup_critical lmg %r8,%r9,__LC_EXT_OLD_PSW SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 + xgr %r10,%r10 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) lghi %r1,__LC_EXT_PARAMS2 @@ -871,11 +1055,12 @@ ENTRY(psw_idle) .Lpsw_idle_stcctm: #endif oi __LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT + BPON STCK __CLOCK_IDLE_ENTER(%r2) stpt __TIMER_IDLE_ENTER(%r2) .Lpsw_idle_lpsw: lpswe __SF_EMPTY(%r15) - br %r14 + BR_R1USE_R14 .Lpsw_idle_end: /* @@ -889,7 +1074,7 @@ ENTRY(save_fpu_regs) lg %r2,__LC_CURRENT aghi %r2,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bor %r14 + jo .Lsave_fpu_regs_exit stfpc __THREAD_FPU_fpc(%r2) lg %r3,__THREAD_FPU_regs(%r2) TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX @@ -916,7 +1101,8 @@ ENTRY(save_fpu_regs) std 15,120(%r3) .Lsave_fpu_regs_done: oi __LC_CPU_FLAGS+7,_CIF_FPU - br %r14 +.Lsave_fpu_regs_exit: + BR_R1USE_R14 .Lsave_fpu_regs_end: EXPORT_SYMBOL(save_fpu_regs) @@ -934,7 +1120,7 @@ load_fpu_regs: lg %r4,__LC_CURRENT aghi %r4,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bnor %r14 + jno .Lload_fpu_regs_exit lfpc __THREAD_FPU_fpc(%r4) TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area @@ -961,7 +1147,8 @@ load_fpu_regs: ld 15,120(%r4) .Lload_fpu_regs_done: ni __LC_CPU_FLAGS+7,255-_CIF_FPU - br %r14 +.Lload_fpu_regs_exit: + BR_R1USE_R14 .Lload_fpu_regs_end: .L__critical_end: @@ -971,6 +1158,7 @@ load_fpu_regs: */ ENTRY(mcck_int_handler) STCK __LC_MCCK_CLOCK + BPOFF la %r1,4095 # validate r1 spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer sckc __LC_CLOCK_COMPARATOR # validate comparator @@ -1046,6 +1234,16 @@ ENTRY(mcck_int_handler) .Lmcck_skip: lghi %r14,__LC_GPREGS_SAVE_AREA+64 stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 + xgr %r10,%r10 mvc __PT_R8(64,%r11),0(%r14) stmg %r8,%r9,__PT_PSW(%r11) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) @@ -1071,6 +1269,7 @@ ENTRY(mcck_int_handler) mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ? jno 0f + BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER 0: lmg %r11,%r15,__PT_R11(%r11) @@ -1166,7 +1365,7 @@ cleanup_critical: jl 0f clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end jl .Lcleanup_load_fpu_regs -0: br %r14 +0: BR_R11USE_R14 .align 8 .Lcleanup_table: @@ -1197,11 +1396,12 @@ cleanup_critical: clg %r9,BASED(.Lsie_crit_mcck_length) jh 1f oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST -1: lg %r9,__SF_EMPTY(%r15) # get control block pointer +1: BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) + lg %r9,__SF_EMPTY(%r15) # get control block pointer ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce larl %r9,sie_exit # skip forward to sie_exit - br %r14 + BR_R11USE_R14 #endif .Lcleanup_system_call: @@ -1254,7 +1454,7 @@ cleanup_critical: stg %r15,56(%r11) # r15 stack pointer # set new psw address and exit larl %r9,.Lsysc_do_svc - br %r14 + BR_R11USE_R14 .Lcleanup_system_call_insn: .quad system_call .quad .Lsysc_stmg @@ -1266,7 +1466,7 @@ cleanup_critical: .Lcleanup_sysc_tif: larl %r9,.Lsysc_tif - br %r14 + BR_R11USE_R14 .Lcleanup_sysc_restore: # check if stpt has been executed @@ -1283,14 +1483,14 @@ cleanup_critical: mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) 1: lmg %r8,%r9,__LC_RETURN_PSW - br %r14 + BR_R11USE_R14 .Lcleanup_sysc_restore_insn: .quad .Lsysc_exit_timer .quad .Lsysc_done - 4 .Lcleanup_io_tif: larl %r9,.Lio_tif - br %r14 + BR_R11USE_R14 .Lcleanup_io_restore: # check if stpt has been executed @@ -1304,7 +1504,7 @@ cleanup_critical: mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) 1: lmg %r8,%r9,__LC_RETURN_PSW - br %r14 + BR_R11USE_R14 .Lcleanup_io_restore_insn: .quad .Lio_exit_timer .quad .Lio_done - 4 @@ -1357,17 +1557,17 @@ cleanup_critical: # prepare return psw nihh %r8,0xfcfd # clear irq & wait state bits lg %r9,48(%r11) # return from psw_idle - br %r14 + BR_R11USE_R14 .Lcleanup_idle_insn: .quad .Lpsw_idle_lpsw .Lcleanup_save_fpu_regs: larl %r9,save_fpu_regs - br %r14 + BR_R11USE_R14 .Lcleanup_load_fpu_regs: larl %r9,load_fpu_regs - br %r14 + BR_R11USE_R14 /* * Integer constants @@ -1387,7 +1587,6 @@ cleanup_critical: .Lsie_crit_mcck_length: .quad .Lsie_skip - .Lsie_entry #endif - .section .rodata, "a" #define SYSCALL(esame,emu) .long esame .globl sys_call_table diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index da5cc3b469aa..34477c1aee6d 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -543,6 +543,7 @@ static struct kset *ipl_kset; static void __ipl_run(void *unused) { + __bpon(); diag308(DIAG308_LOAD_CLEAR, NULL); if (MACHINE_IS_VM) __cpcmd("IPL", NULL, 0, NULL); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 943d13e90c98..60f60afa645c 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -281,7 +281,7 @@ static void kprobe_reenter_check(struct kprobe_ctlblk *kcb, struct kprobe *p) * is a BUG. The code path resides in the .kprobes.text * section and is executed with interrupts disabled. */ - printk(KERN_EMERG "Invalid kprobe detected at %p.\n", p->addr); + pr_err("Invalid kprobe detected.\n"); dump_kprobe(p); BUG(); } diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index b7abfad4fd7d..1fc6d1ff92d3 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -19,6 +19,8 @@ #include <linux/moduleloader.h> #include <linux/bug.h> #include <asm/alternative.h> +#include <asm/nospec-branch.h> +#include <asm/facility.h> #if 0 #define DEBUGP printk @@ -156,7 +158,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, me->arch.got_offset = me->core_layout.size; me->core_layout.size += me->arch.got_size; me->arch.plt_offset = me->core_layout.size; - me->core_layout.size += me->arch.plt_size; + if (me->arch.plt_size) { + if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_call_disable) + me->arch.plt_size += PLT_ENTRY_SIZE; + me->core_layout.size += me->arch.plt_size; + } return 0; } @@ -310,9 +316,21 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, unsigned int *ip; ip = me->core_layout.base + me->arch.plt_offset + info->plt_offset; - ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ - ip[1] = 0x100a0004; - ip[2] = 0x07f10000; + ip[0] = 0x0d10e310; /* basr 1,0 */ + ip[1] = 0x100a0004; /* lg 1,10(1) */ + if (IS_ENABLED(CONFIG_EXPOLINE) && + !nospec_call_disable) { + unsigned int *ij; + ij = me->core_layout.base + + me->arch.plt_offset + + me->arch.plt_size - PLT_ENTRY_SIZE; + ip[2] = 0xa7f40000 + /* j __jump_r1 */ + (unsigned int)(u16) + (((unsigned long) ij - 8 - + (unsigned long) ip) / 2); + } else { + ip[2] = 0x07f10000; /* br %r1 */ + } ip[3] = (unsigned int) (val >> 32); ip[4] = (unsigned int) val; info->plt_initialized = 1; @@ -418,16 +436,42 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s; - char *secstrings; + char *secstrings, *secname; + void *aseg; + + if (IS_ENABLED(CONFIG_EXPOLINE) && + !nospec_call_disable && me->arch.plt_size) { + unsigned int *ij; + + ij = me->core_layout.base + me->arch.plt_offset + + me->arch.plt_size - PLT_ENTRY_SIZE; + if (test_facility(35)) { + ij[0] = 0xc6000000; /* exrl %r0,.+10 */ + ij[1] = 0x0005a7f4; /* j . */ + ij[2] = 0x000007f1; /* br %r1 */ + } else { + ij[0] = 0x44000000 | (unsigned int) + offsetof(struct lowcore, br_r1_trampoline); + ij[1] = 0xa7f40000; /* j . */ + } + } secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { - if (!strcmp(".altinstructions", secstrings + s->sh_name)) { - /* patch .altinstructions */ - void *aseg = (void *)s->sh_addr; + aseg = (void *) s->sh_addr; + secname = secstrings + s->sh_name; + if (!strcmp(".altinstructions", secname)) + /* patch .altinstructions */ apply_alternatives(aseg, aseg + s->sh_size); - } + + if (IS_ENABLED(CONFIG_EXPOLINE) && + (!strcmp(".nospec_call_table", secname))) + nospec_call_revert(aseg, aseg + s->sh_size); + + if (IS_ENABLED(CONFIG_EXPOLINE) && + (!strcmp(".nospec_return_table", secname))) + nospec_return_revert(aseg, aseg + s->sh_size); } jump_label_apply_nops(me); diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c new file mode 100644 index 000000000000..69d7fcf48158 --- /dev/null +++ b/arch/s390/kernel/nospec-branch.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/module.h> +#include <asm/nospec-branch.h> + +int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF); +int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL); + +static int __init nospectre_v2_setup_early(char *str) +{ + nospec_call_disable = 1; + nospec_return_disable = 1; + return 0; +} +early_param("nospectre_v2", nospectre_v2_setup_early); + +static int __init spectre_v2_setup_early(char *str) +{ + if (str && !strncmp(str, "on", 2)) { + nospec_call_disable = 0; + nospec_return_disable = 0; + } + if (str && !strncmp(str, "off", 3)) { + nospec_call_disable = 1; + nospec_return_disable = 1; + } + if (str && !strncmp(str, "auto", 4)) { + nospec_call_disable = 0; + nospec_return_disable = 1; + } + return 0; +} +early_param("spectre_v2", spectre_v2_setup_early); + +static void __init_or_module __nospec_revert(s32 *start, s32 *end) +{ + enum { BRCL_EXPOLINE, BRASL_EXPOLINE } type; + u8 *instr, *thunk, *br; + u8 insnbuf[6]; + s32 *epo; + + /* Second part of the instruction replace is always a nop */ + memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4); + for (epo = start; epo < end; epo++) { + instr = (u8 *) epo + *epo; + if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04) + type = BRCL_EXPOLINE; /* brcl instruction */ + else if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x05) + type = BRASL_EXPOLINE; /* brasl instruction */ + else + continue; + thunk = instr + (*(int *)(instr + 2)) * 2; + if (thunk[0] == 0xc6 && thunk[1] == 0x00) + /* exrl %r0,<target-br> */ + br = thunk + (*(int *)(thunk + 2)) * 2; + else if (thunk[0] == 0xc0 && (thunk[1] & 0x0f) == 0x00 && + thunk[6] == 0x44 && thunk[7] == 0x00 && + (thunk[8] & 0x0f) == 0x00 && thunk[9] == 0x00 && + (thunk[1] & 0xf0) == (thunk[8] & 0xf0)) + /* larl %rx,<target br> + ex %r0,0(%rx) */ + br = thunk + (*(int *)(thunk + 2)) * 2; + else + continue; + if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0) + continue; + switch (type) { + case BRCL_EXPOLINE: + /* brcl to thunk, replace with br + nop */ + insnbuf[0] = br[0]; + insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f); + break; + case BRASL_EXPOLINE: + /* brasl to thunk, replace with basr + nop */ + insnbuf[0] = 0x0d; + insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f); + break; + } + + s390_kernel_write(instr, insnbuf, 6); + } +} + +void __init_or_module nospec_call_revert(s32 *start, s32 *end) +{ + if (nospec_call_disable) + __nospec_revert(start, end); +} + +void __init_or_module nospec_return_revert(s32 *start, s32 *end) +{ + if (nospec_return_disable) + __nospec_revert(start, end); +} + +extern s32 __nospec_call_start[], __nospec_call_end[]; +extern s32 __nospec_return_start[], __nospec_return_end[]; +void __init nospec_init_branches(void) +{ + nospec_call_revert(__nospec_call_start, __nospec_call_end); + nospec_return_revert(__nospec_return_start, __nospec_return_end); +} diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c index 94f90cefbffc..c5bc3f209652 100644 --- a/arch/s390/kernel/perf_cpum_cf_events.c +++ b/arch/s390/kernel/perf_cpum_cf_events.c @@ -226,7 +226,7 @@ CPUMF_EVENT_ATTR(cf_z14, L1I_OFFDRAWER_L4_SOURCED_WRITES, 0x00af); CPUMF_EVENT_ATTR(cf_z14, BCD_DFP_EXECUTION_SLOTS, 0x00e0); CPUMF_EVENT_ATTR(cf_z14, VX_BCD_EXECUTION_SLOTS, 0x00e1); CPUMF_EVENT_ATTR(cf_z14, DECIMAL_INSTRUCTIONS, 0x00e2); -CPUMF_EVENT_ATTR(cf_z14, LAST_HOST_TRANSLATIONS, 0x00e9); +CPUMF_EVENT_ATTR(cf_z14, LAST_HOST_TRANSLATIONS, 0x00e8); CPUMF_EVENT_ATTR(cf_z14, TX_NC_TABORT, 0x00f3); CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_NO_SPECIAL, 0x00f4); CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_SPECIAL, 0x00f5); diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 5362fd868d0d..6fe2e1875058 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -197,3 +197,21 @@ const struct seq_operations cpuinfo_op = { .stop = c_stop, .show = show_cpuinfo, }; + +int s390_isolate_bp(void) +{ + if (!test_facility(82)) + return -EOPNOTSUPP; + set_thread_flag(TIF_ISOLATE_BP); + return 0; +} +EXPORT_SYMBOL(s390_isolate_bp); + +int s390_isolate_bp_guest(void) +{ + if (!test_facility(82)) + return -EOPNOTSUPP; + set_thread_flag(TIF_ISOLATE_BP_GUEST); + return 0; +} +EXPORT_SYMBOL(s390_isolate_bp_guest); diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 09f5bf0d5c0c..125c7f6e8715 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -18,6 +18,8 @@ #include <asm/cpu_mf.h> #include <asm/irq.h> +#include "entry.h" + /* empty control block to disable RI by loading it */ struct runtime_instr_cb runtime_instr_empty_cb; @@ -59,7 +61,13 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb) cb->v = 1; } -SYSCALL_DEFINE1(s390_runtime_instr, int, command) +/* + * The signum argument is unused. In older kernels it was used to + * specify a real-time signal. For backwards compatibility user space + * should pass a valid real-time signal number (the signum argument + * was checked in older kernels). + */ +SYSCALL_DEFINE2(s390_runtime_instr, int, command, int, signum) { struct runtime_instr_cb *cb; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 793da97f9a6e..a6a91f01a17a 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -68,6 +68,7 @@ #include <asm/sysinfo.h> #include <asm/numa.h> #include <asm/alternative.h> +#include <asm/nospec-branch.h> #include "entry.h" /* @@ -340,7 +341,9 @@ static void __init setup_lowcore(void) lc->preempt_count = S390_lowcore.preempt_count; lc->stfl_fac_list = S390_lowcore.stfl_fac_list; memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, - MAX_FACILITY_BIT/8); + sizeof(lc->stfle_fac_list)); + memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list, + sizeof(lc->alt_stfle_fac_list)); nmi_alloc_boot_cpu(lc); vdso_alloc_boot_cpu(lc); lc->sync_enter_timer = S390_lowcore.sync_enter_timer; @@ -377,6 +380,7 @@ static void __init setup_lowcore(void) lc->spinlock_index = 0; arch_spin_lock_setup(0); #endif + lc->br_r1_trampoline = 0x07f1; /* br %r1 */ set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; @@ -952,6 +956,8 @@ void __init setup_arch(char **cmdline_p) set_preferred_console(); apply_alternative_instructions(); + if (IS_ENABLED(CONFIG_EXPOLINE)) + nospec_init_branches(); /* Setup zfcpdump support */ setup_zfcpdump(); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index a919b2f0141d..a4a9fe1934e9 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -214,6 +214,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) lc->cpu_nr = cpu; lc->spinlock_lockval = arch_spin_lockval(cpu); lc->spinlock_index = 0; + lc->br_r1_trampoline = 0x07f1; /* br %r1 */ if (nmi_alloc_per_cpu(lc)) goto out; if (vdso_alloc_per_cpu(lc)) @@ -266,7 +267,9 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) __ctl_store(lc->cregs_save_area, 0, 15); save_access_regs((unsigned int *) lc->access_regs_save_area); memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, - MAX_FACILITY_BIT/8); + sizeof(lc->stfle_fac_list)); + memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list, + sizeof(lc->alt_stfle_fac_list)); arch_spin_lock_setup(cpu); } @@ -317,6 +320,7 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), mem_assign_absolute(lc->restart_fn, (unsigned long) func); mem_assign_absolute(lc->restart_data, (unsigned long) data); mem_assign_absolute(lc->restart_source, source_cpu); + __bpon(); asm volatile( "0: sigp 0,%0,%2 # sigp restart to target cpu\n" " brc 2,0b # busy, try again\n" @@ -901,6 +905,7 @@ void __cpu_die(unsigned int cpu) void __noreturn cpu_die(void) { idle_task_exit(); + __bpon(); pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); for (;;) ; } diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index a441cba8d165..fc7e04c2195b 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -89,6 +89,8 @@ static void stsi_1_1_1(struct seq_file *m, struct sysinfo_1_1_1 *info) EBCASC(info->model_temp_cap, sizeof(info->model_temp_cap)); seq_printf(m, "Manufacturer: %-16.16s\n", info->manufacturer); seq_printf(m, "Type: %-4.4s\n", info->type); + if (info->lic) + seq_printf(m, "LIC Identifier: %016lx\n", info->lic); /* * Sigh: the model field has been renamed with System z9 * to model_capacity and a new model field has been added diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 608cf2987d19..08d12cfaf091 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -123,6 +123,20 @@ SECTIONS *(.altinstr_replacement) } + /* + * Table with the patch locations to undo expolines + */ + .nospec_call_table : { + __nospec_call_start = . ; + *(.s390_indirect*) + __nospec_call_end = . ; + } + .nospec_return_table : { + __nospec_return_start = . ; + *(.s390_return*) + __nospec_return_end = . ; + } + /* early.c uses stsi, which requires page aligned data. */ . = ALIGN(PAGE_SIZE); INIT_DATA_SECTION(0x100) diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 9a4594e0a1ff..a3dbd459cce9 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -23,6 +23,7 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_CPU_RELAX_INTERCEPT + select HAVE_KVM_VCPU_ASYNC_IOCTL select HAVE_KVM_EVENTFD select KVM_ASYNC_PF select KVM_ASYNC_PF_SYNC diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 89aa114a2cba..45634b3d2e0a 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -257,6 +257,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu) case 0x500: return __diag_virtio_hypercall(vcpu); default: + vcpu->stat.diagnose_other++; return -EOPNOTSUPP; } } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 024ad8bcc516..aabf46f5f883 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -36,7 +36,7 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) { int c, scn; - if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND)) + if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND)) return 0; BUG_ON(!kvm_s390_use_sca_entries()); @@ -101,18 +101,17 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) /* another external call is pending */ return -EBUSY; } - atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_ECALL_PEND); return 0; } static void sca_clear_ext_call(struct kvm_vcpu *vcpu) { - struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; int rc, expect; if (!kvm_s390_use_sca_entries()) return; - atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND); read_lock(&vcpu->kvm->arch.sca_lock); if (vcpu->kvm->arch.use_esca) { struct esca_block *sca = vcpu->kvm->arch.sca; @@ -190,8 +189,8 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu) static inline int is_ioirq(unsigned long irq_type) { - return ((irq_type >= IRQ_PEND_IO_ISC_0) && - (irq_type <= IRQ_PEND_IO_ISC_7)); + return ((irq_type >= IRQ_PEND_IO_ISC_7) && + (irq_type <= IRQ_PEND_IO_ISC_0)); } static uint64_t isc_to_isc_bits(int isc) @@ -199,25 +198,59 @@ static uint64_t isc_to_isc_bits(int isc) return (0x80 >> isc) << 24; } +static inline u32 isc_to_int_word(u8 isc) +{ + return ((u32)isc << 27) | 0x80000000; +} + static inline u8 int_word_to_isc(u32 int_word) { return (int_word & 0x38000000) >> 27; } +/* + * To use atomic bitmap functions, we have to provide a bitmap address + * that is u64 aligned. However, the ipm might be u32 aligned. + * Therefore, we logically start the bitmap at the very beginning of the + * struct and fixup the bit number. + */ +#define IPM_BIT_OFFSET (offsetof(struct kvm_s390_gisa, ipm) * BITS_PER_BYTE) + +static inline void kvm_s390_gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) +{ + set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); +} + +static inline u8 kvm_s390_gisa_get_ipm(struct kvm_s390_gisa *gisa) +{ + return READ_ONCE(gisa->ipm); +} + +static inline void kvm_s390_gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) +{ + clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); +} + +static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) +{ + return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); +} + static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.float_int.pending_irqs | - vcpu->arch.local_int.pending_irqs; + vcpu->arch.local_int.pending_irqs | + kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7; } static inline int isc_to_irq_type(unsigned long isc) { - return IRQ_PEND_IO_ISC_0 + isc; + return IRQ_PEND_IO_ISC_0 - isc; } static inline int irq_type_to_isc(unsigned long irq_type) { - return irq_type - IRQ_PEND_IO_ISC_0; + return IRQ_PEND_IO_ISC_0 - irq_type; } static unsigned long disable_iscs(struct kvm_vcpu *vcpu, @@ -278,20 +311,20 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) static void __set_cpu_idle(struct kvm_vcpu *vcpu) { - atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); - set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT); + set_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask); } static void __unset_cpu_idle(struct kvm_vcpu *vcpu) { - atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); - clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT); + clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask); } static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) { - atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT, - &vcpu->arch.sie_block->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IO_INT | CPUSTAT_EXT_INT | + CPUSTAT_STOP_INT); vcpu->arch.sie_block->lctl = 0x0000; vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT); @@ -302,17 +335,12 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) } } -static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) -{ - atomic_or(flag, &vcpu->arch.sie_block->cpuflags); -} - static void set_intercept_indicators_io(struct kvm_vcpu *vcpu) { if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK)) return; else if (psw_ioint_disabled(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_IO_INT); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT); else vcpu->arch.sie_block->lctl |= LCTL_CR6; } @@ -322,7 +350,7 @@ static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK)) return; if (psw_extint_disabled(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_EXT_INT); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT); else vcpu->arch.sie_block->lctl |= LCTL_CR0; } @@ -340,7 +368,7 @@ static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu) static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu) { if (kvm_s390_is_stop_irq_pending(vcpu)) - __set_cpuflag(vcpu, CPUSTAT_STOP_INT); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT); } /* Set interception request for non-deliverable interrupts */ @@ -897,18 +925,38 @@ static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu) return rc ? -EFAULT : 0; } +static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io) +{ + int rc; + + rc = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID); + rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR); + rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM); + rc |= put_guest_lc(vcpu, io->io_int_word, (u32 *)__LC_IO_INT_WORD); + rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, + &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + static int __must_check __deliver_io(struct kvm_vcpu *vcpu, unsigned long irq_type) { struct list_head *isc_list; struct kvm_s390_float_interrupt *fi; struct kvm_s390_interrupt_info *inti = NULL; + struct kvm_s390_io_info io; + u32 isc; int rc = 0; fi = &vcpu->kvm->arch.float_int; spin_lock(&fi->lock); - isc_list = &fi->lists[irq_type_to_isc(irq_type)]; + isc = irq_type_to_isc(irq_type); + isc_list = &fi->lists[isc]; inti = list_first_entry_or_null(isc_list, struct kvm_s390_interrupt_info, list); @@ -936,24 +984,31 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu, spin_unlock(&fi->lock); if (inti) { - rc = put_guest_lc(vcpu, inti->io.subchannel_id, - (u16 *)__LC_SUBCHANNEL_ID); - rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, - (u16 *)__LC_SUBCHANNEL_NR); - rc |= put_guest_lc(vcpu, inti->io.io_int_parm, - (u32 *)__LC_IO_INT_PARM); - rc |= put_guest_lc(vcpu, inti->io.io_int_word, - (u32 *)__LC_IO_INT_WORD); - rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); + rc = __do_deliver_io(vcpu, &(inti->io)); kfree(inti); + goto out; } - return rc ? -EFAULT : 0; + if (vcpu->kvm->arch.gisa && + kvm_s390_gisa_tac_ipm_gisc(vcpu->kvm->arch.gisa, isc)) { + /* + * in case an adapter interrupt was not delivered + * in SIE context KVM will handle the delivery + */ + VCPU_EVENT(vcpu, 4, "%s isc %u", "deliver: I/O (AI/gisa)", isc); + memset(&io, 0, sizeof(io)); + io.io_int_word = isc_to_int_word(isc); + vcpu->stat.deliver_io_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_IO(1, 0, 0, 0), + ((__u32)io.subchannel_id << 16) | + io.subchannel_nr, + ((__u64)io.io_int_parm << 32) | + io.io_int_word); + rc = __do_deliver_io(vcpu, &io); + } +out: + return rc; } typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); @@ -1155,8 +1210,8 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); while ((irqs = deliverable_irqs(vcpu)) && !rc) { - /* bits are in the order of interrupt priority */ - irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT); + /* bits are in the reverse order of interrupt priority */ + irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT); if (is_ioirq(irq_type)) { rc = __deliver_io(vcpu, irq_type); } else { @@ -1228,7 +1283,7 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) li->irq.ext = irq->u.ext; set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs); - atomic_or(CPUSTAT_EXT_INT, li->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT); return 0; } @@ -1253,7 +1308,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) return -EBUSY; *extcall = irq->u.extcall; - atomic_or(CPUSTAT_EXT_INT, li->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT); return 0; } @@ -1297,7 +1352,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs)) return -EBUSY; stop->flags = irq->u.stop.flags; - __set_cpuflag(vcpu, CPUSTAT_STOP_INT); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT); return 0; } @@ -1329,7 +1384,7 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, set_bit(irq->u.emerg.code, li->sigp_emerg_pending); set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); - atomic_or(CPUSTAT_EXT_INT, li->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT); return 0; } @@ -1373,7 +1428,7 @@ static int __inject_ckc(struct kvm_vcpu *vcpu) 0, 0); set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); - atomic_or(CPUSTAT_EXT_INT, li->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT); return 0; } @@ -1386,7 +1441,7 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu) 0, 0); set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); - atomic_or(CPUSTAT_EXT_INT, li->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT); return 0; } @@ -1416,20 +1471,86 @@ static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm, return NULL; } +static struct kvm_s390_interrupt_info *get_top_io_int(struct kvm *kvm, + u64 isc_mask, u32 schid) +{ + struct kvm_s390_interrupt_info *inti = NULL; + int isc; + + for (isc = 0; isc <= MAX_ISC && !inti; isc++) { + if (isc_mask & isc_to_isc_bits(isc)) + inti = get_io_int(kvm, isc, schid); + } + return inti; +} + +static int get_top_gisa_isc(struct kvm *kvm, u64 isc_mask, u32 schid) +{ + unsigned long active_mask; + int isc; + + if (schid) + goto out; + if (!kvm->arch.gisa) + goto out; + + active_mask = (isc_mask & kvm_s390_gisa_get_ipm(kvm->arch.gisa) << 24) << 32; + while (active_mask) { + isc = __fls(active_mask) ^ (BITS_PER_LONG - 1); + if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, isc)) + return isc; + clear_bit_inv(isc, &active_mask); + } +out: + return -EINVAL; +} + /* * Dequeue and return an I/O interrupt matching any of the interruption * subclasses as designated by the isc mask in cr6 and the schid (if != 0). + * Take into account the interrupts pending in the interrupt list and in GISA. + * + * Note that for a guest that does not enable I/O interrupts + * but relies on TPI, a flood of classic interrupts may starve + * out adapter interrupts on the same isc. Linux does not do + * that, and it is possible to work around the issue by configuring + * different iscs for classic and adapter interrupts in the guest, + * but we may want to revisit this in the future. */ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, u64 isc_mask, u32 schid) { - struct kvm_s390_interrupt_info *inti = NULL; + struct kvm_s390_interrupt_info *inti, *tmp_inti; int isc; - for (isc = 0; isc <= MAX_ISC && !inti; isc++) { - if (isc_mask & isc_to_isc_bits(isc)) - inti = get_io_int(kvm, isc, schid); + inti = get_top_io_int(kvm, isc_mask, schid); + + isc = get_top_gisa_isc(kvm, isc_mask, schid); + if (isc < 0) + /* no AI in GISA */ + goto out; + + if (!inti) + /* AI in GISA but no classical IO int */ + goto gisa_out; + + /* both types of interrupts present */ + if (int_word_to_isc(inti->io.io_int_word) <= isc) { + /* classical IO int with higher priority */ + kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc); + goto out; } +gisa_out: + tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL); + if (tmp_inti) { + tmp_inti->type = KVM_S390_INT_IO(1, 0, 0, 0); + tmp_inti->io.io_int_word = isc_to_int_word(isc); + if (inti) + kvm_s390_reinject_io_int(kvm, inti); + inti = tmp_inti; + } else + kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc); +out: return inti; } @@ -1517,6 +1638,15 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) struct list_head *list; int isc; + isc = int_word_to_isc(inti->io.io_int_word); + + if (kvm->arch.gisa && inti->type & KVM_S390_INT_IO_AI_MASK) { + VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc); + kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc); + kfree(inti); + return 0; + } + fi = &kvm->arch.float_int; spin_lock(&fi->lock); if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) { @@ -1532,7 +1662,6 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) inti->io.subchannel_id >> 8, inti->io.subchannel_id >> 1 & 0x3, inti->io.subchannel_nr); - isc = int_word_to_isc(inti->io.io_int_word); list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc]; list_add_tail(&inti->list, list); set_bit(isc_to_irq_type(isc), &fi->pending_irqs); @@ -1546,7 +1675,6 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) static void __floating_irq_kick(struct kvm *kvm, u64 type) { struct kvm_s390_float_interrupt *fi = &kvm->arch.float_int; - struct kvm_s390_local_interrupt *li; struct kvm_vcpu *dst_vcpu; int sigcpu, online_vcpus, nr_tries = 0; @@ -1568,20 +1696,17 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type) dst_vcpu = kvm_get_vcpu(kvm, sigcpu); /* make the VCPU drop out of the SIE, or wake it up if sleeping */ - li = &dst_vcpu->arch.local_int; - spin_lock(&li->lock); switch (type) { case KVM_S390_MCHK: - atomic_or(CPUSTAT_STOP_INT, li->cpuflags); + kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT); break; case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - atomic_or(CPUSTAT_IO_INT, li->cpuflags); + kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT); break; default: - atomic_or(CPUSTAT_EXT_INT, li->cpuflags); + kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT); break; } - spin_unlock(&li->lock); kvm_s390_vcpu_wakeup(dst_vcpu); } @@ -1820,6 +1945,7 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm) for (i = 0; i < FIRQ_MAX_COUNT; i++) fi->counters[i] = 0; spin_unlock(&fi->lock); + kvm_s390_gisa_clear(kvm); }; static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) @@ -1847,6 +1973,22 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) max_irqs = len / sizeof(struct kvm_s390_irq); + if (kvm->arch.gisa && + kvm_s390_gisa_get_ipm(kvm->arch.gisa)) { + for (i = 0; i <= MAX_ISC; i++) { + if (n == max_irqs) { + /* signal userspace to try again */ + ret = -ENOMEM; + goto out_nolock; + } + if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, i)) { + irq = (struct kvm_s390_irq *) &buf[n]; + irq->type = KVM_S390_INT_IO(1, 0, 0, 0); + irq->u.io.io_int_word = isc_to_int_word(i); + n++; + } + } + } fi = &kvm->arch.float_int; spin_lock(&fi->lock); for (i = 0; i < FIRQ_LIST_COUNT; i++) { @@ -1885,6 +2027,7 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len) out: spin_unlock(&fi->lock); +out_nolock: if (!ret && n > 0) { if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n)) ret = -EFAULT; @@ -2245,7 +2388,7 @@ static int kvm_s390_inject_airq(struct kvm *kvm, struct kvm_s390_interrupt s390int = { .type = KVM_S390_INT_IO(1, 0, 0, 0), .parm = 0, - .parm64 = (adapter->isc << 27) | 0x80000000, + .parm64 = isc_to_int_word(adapter->isc), }; int ret = 0; @@ -2687,3 +2830,28 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) return n; } + +void kvm_s390_gisa_clear(struct kvm *kvm) +{ + if (kvm->arch.gisa) { + memset(kvm->arch.gisa, 0, sizeof(struct kvm_s390_gisa)); + kvm->arch.gisa->next_alert = (u32)(u64)kvm->arch.gisa; + VM_EVENT(kvm, 3, "gisa 0x%pK cleared", kvm->arch.gisa); + } +} + +void kvm_s390_gisa_init(struct kvm *kvm) +{ + if (css_general_characteristics.aiv) { + kvm->arch.gisa = &kvm->arch.sie_page2->gisa; + VM_EVENT(kvm, 3, "gisa 0x%pK initialized", kvm->arch.gisa); + kvm_s390_gisa_clear(kvm); + } +} + +void kvm_s390_gisa_destroy(struct kvm *kvm) +{ + if (!kvm->arch.gisa) + return; + kvm->arch.gisa = NULL; +} diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 1371dff2b90d..ba4c7092335a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2,7 +2,7 @@ /* * hosting IBM Z kernel virtual machines (s390x) * - * Copyright IBM Corp. 2008, 2017 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -87,19 +87,31 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) }, { "deliver_program_interruption", VCPU_STAT(deliver_program_int) }, { "exit_wait_state", VCPU_STAT(exit_wait_state) }, + { "instruction_epsw", VCPU_STAT(instruction_epsw) }, + { "instruction_gs", VCPU_STAT(instruction_gs) }, + { "instruction_io_other", VCPU_STAT(instruction_io_other) }, + { "instruction_lpsw", VCPU_STAT(instruction_lpsw) }, + { "instruction_lpswe", VCPU_STAT(instruction_lpswe) }, { "instruction_pfmf", VCPU_STAT(instruction_pfmf) }, + { "instruction_ptff", VCPU_STAT(instruction_ptff) }, { "instruction_stidp", VCPU_STAT(instruction_stidp) }, + { "instruction_sck", VCPU_STAT(instruction_sck) }, + { "instruction_sckpf", VCPU_STAT(instruction_sckpf) }, { "instruction_spx", VCPU_STAT(instruction_spx) }, { "instruction_stpx", VCPU_STAT(instruction_stpx) }, { "instruction_stap", VCPU_STAT(instruction_stap) }, - { "instruction_storage_key", VCPU_STAT(instruction_storage_key) }, + { "instruction_iske", VCPU_STAT(instruction_iske) }, + { "instruction_ri", VCPU_STAT(instruction_ri) }, + { "instruction_rrbe", VCPU_STAT(instruction_rrbe) }, + { "instruction_sske", VCPU_STAT(instruction_sske) }, { "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) }, - { "instruction_stsch", VCPU_STAT(instruction_stsch) }, - { "instruction_chsc", VCPU_STAT(instruction_chsc) }, { "instruction_essa", VCPU_STAT(instruction_essa) }, { "instruction_stsi", VCPU_STAT(instruction_stsi) }, { "instruction_stfl", VCPU_STAT(instruction_stfl) }, + { "instruction_tb", VCPU_STAT(instruction_tb) }, + { "instruction_tpi", VCPU_STAT(instruction_tpi) }, { "instruction_tprot", VCPU_STAT(instruction_tprot) }, + { "instruction_tsch", VCPU_STAT(instruction_tsch) }, { "instruction_sthyi", VCPU_STAT(instruction_sthyi) }, { "instruction_sie", VCPU_STAT(instruction_sie) }, { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) }, @@ -118,12 +130,13 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) }, { "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) }, { "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) }, - { "diagnose_10", VCPU_STAT(diagnose_10) }, - { "diagnose_44", VCPU_STAT(diagnose_44) }, - { "diagnose_9c", VCPU_STAT(diagnose_9c) }, - { "diagnose_258", VCPU_STAT(diagnose_258) }, - { "diagnose_308", VCPU_STAT(diagnose_308) }, - { "diagnose_500", VCPU_STAT(diagnose_500) }, + { "instruction_diag_10", VCPU_STAT(diagnose_10) }, + { "instruction_diag_44", VCPU_STAT(diagnose_44) }, + { "instruction_diag_9c", VCPU_STAT(diagnose_9c) }, + { "instruction_diag_258", VCPU_STAT(diagnose_258) }, + { "instruction_diag_308", VCPU_STAT(diagnose_308) }, + { "instruction_diag_500", VCPU_STAT(diagnose_500) }, + { "instruction_diag_other", VCPU_STAT(diagnose_other) }, { NULL } }; @@ -576,7 +589,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) case KVM_CAP_S390_GS: r = -EINVAL; mutex_lock(&kvm->lock); - if (atomic_read(&kvm->online_vcpus)) { + if (kvm->created_vcpus) { r = -EBUSY; } else if (test_facility(133)) { set_kvm_facility(kvm->arch.model.fac_mask, 133); @@ -1088,7 +1101,6 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm, struct kvm_device_attr *attr) { struct kvm_s390_vm_cpu_feat data; - int ret = -EBUSY; if (copy_from_user(&data, (void __user *)attr->addr, sizeof(data))) return -EFAULT; @@ -1098,13 +1110,18 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm, return -EINVAL; mutex_lock(&kvm->lock); - if (!atomic_read(&kvm->online_vcpus)) { - bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat, - KVM_S390_VM_CPU_FEAT_NR_BITS); - ret = 0; + if (kvm->created_vcpus) { + mutex_unlock(&kvm->lock); + return -EBUSY; } + bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat, + KVM_S390_VM_CPU_FEAT_NR_BITS); mutex_unlock(&kvm->lock); - return ret; + VM_EVENT(kvm, 3, "SET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx", + data.feat[0], + data.feat[1], + data.feat[2]); + return 0; } static int kvm_s390_set_processor_subfunc(struct kvm *kvm, @@ -1206,6 +1223,10 @@ static int kvm_s390_get_processor_feat(struct kvm *kvm, KVM_S390_VM_CPU_FEAT_NR_BITS); if (copy_to_user((void __user *)attr->addr, &data, sizeof(data))) return -EFAULT; + VM_EVENT(kvm, 3, "GET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx", + data.feat[0], + data.feat[1], + data.feat[2]); return 0; } @@ -1219,6 +1240,10 @@ static int kvm_s390_get_machine_feat(struct kvm *kvm, KVM_S390_VM_CPU_FEAT_NR_BITS); if (copy_to_user((void __user *)attr->addr, &data, sizeof(data))) return -EFAULT; + VM_EVENT(kvm, 3, "GET: host feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx", + data.feat[0], + data.feat[1], + data.feat[2]); return 0; } @@ -1911,6 +1936,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (!kvm->arch.dbf) goto out_err; + BUILD_BUG_ON(sizeof(struct sie_page2) != 4096); kvm->arch.sie_page2 = (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA); if (!kvm->arch.sie_page2) @@ -1981,6 +2007,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) spin_lock_init(&kvm->arch.start_stop_lock); kvm_s390_vsie_init(kvm); + kvm_s390_gisa_init(kvm); KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); return 0; @@ -2043,6 +2070,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_free_vcpus(kvm); sca_dispose(kvm); debug_unregister(kvm->arch.dbf); + kvm_s390_gisa_destroy(kvm); free_page((unsigned long)kvm->arch.sie_page2); if (!kvm_is_ucontrol(kvm)) gmap_remove(kvm->arch.gmap); @@ -2314,7 +2342,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { gmap_enable(vcpu->arch.enabled_gmap); - atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_RUNNING); if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu)) __start_cpu_timer_accounting(vcpu); vcpu->cpu = cpu; @@ -2325,7 +2353,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->cpu = -1; if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu)) __stop_cpu_timer_accounting(vcpu); - atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_RUNNING); vcpu->arch.enabled_gmap = gmap_get_enabled(); gmap_disable(vcpu->arch.enabled_gmap); @@ -2422,9 +2450,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) CPUSTAT_STOPPED); if (test_kvm_facility(vcpu->kvm, 78)) - atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED2); else if (test_kvm_facility(vcpu->kvm, 8)) - atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED); kvm_s390_vcpu_setup_model(vcpu); @@ -2456,12 +2484,17 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) if (test_kvm_facility(vcpu->kvm, 139)) vcpu->arch.sie_block->ecd |= ECD_MEF; + if (vcpu->arch.sie_block->gd) { + vcpu->arch.sie_block->eca |= ECA_AIV; + VCPU_EVENT(vcpu, 3, "AIV gisa format-%u enabled for cpu %03u", + vcpu->arch.sie_block->gd & 0x3, vcpu->vcpu_id); + } vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx) | SDNXC; vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb; if (sclp.has_kss) - atomic_or(CPUSTAT_KSS, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_KSS); else vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; @@ -2508,9 +2541,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->icpua = id; spin_lock_init(&vcpu->arch.local_int.lock); - vcpu->arch.local_int.float_int = &kvm->arch.float_int; - vcpu->arch.local_int.wq = &vcpu->wq; - vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; + vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa; + if (vcpu->arch.sie_block->gd && sclp.has_gisaf) + vcpu->arch.sie_block->gd |= GISA_FORMAT1; seqcount_init(&vcpu->arch.cputm_seqcount); rc = kvm_vcpu_init(vcpu, kvm, id); @@ -2567,7 +2600,7 @@ static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu) * return immediately. */ void exit_sie(struct kvm_vcpu *vcpu) { - atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT); while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE) cpu_relax(); } @@ -2720,47 +2753,70 @@ static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + vcpu_load(vcpu); memcpy(&vcpu->run->s.regs.gprs, ®s->gprs, sizeof(regs->gprs)); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + vcpu_load(vcpu); memcpy(®s->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs)); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + vcpu_load(vcpu); + memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs)); memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs)); + + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + vcpu_load(vcpu); + memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs)); memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs)); + + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - if (test_fp_ctl(fpu->fpc)) - return -EINVAL; + int ret = 0; + + vcpu_load(vcpu); + + if (test_fp_ctl(fpu->fpc)) { + ret = -EINVAL; + goto out; + } vcpu->run->s.regs.fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, (freg_t *) fpu->fprs); else memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs)); - return 0; + +out: + vcpu_put(vcpu); + return ret; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { + vcpu_load(vcpu); + /* make sure we have the latest values */ save_fpu_regs(); if (MACHINE_HAS_VX) @@ -2769,6 +2825,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) else memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs)); fpu->fpc = vcpu->run->s.regs.fpc; + + vcpu_put(vcpu); return 0; } @@ -2800,41 +2858,56 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, { int rc = 0; + vcpu_load(vcpu); + vcpu->guest_debug = 0; kvm_s390_clear_bp_data(vcpu); - if (dbg->control & ~VALID_GUESTDBG_FLAGS) - return -EINVAL; - if (!sclp.has_gpere) - return -EINVAL; + if (dbg->control & ~VALID_GUESTDBG_FLAGS) { + rc = -EINVAL; + goto out; + } + if (!sclp.has_gpere) { + rc = -EINVAL; + goto out; + } if (dbg->control & KVM_GUESTDBG_ENABLE) { vcpu->guest_debug = dbg->control; /* enforce guest PER */ - atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_P); if (dbg->control & KVM_GUESTDBG_USE_HW_BP) rc = kvm_s390_import_bp_data(vcpu, dbg); } else { - atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P); vcpu->arch.guestdbg.last_bp = 0; } if (rc) { vcpu->guest_debug = 0; kvm_s390_clear_bp_data(vcpu); - atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P); } +out: + vcpu_put(vcpu); return rc; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int ret; + + vcpu_load(vcpu); + /* CHECK_STOP and LOAD are not supported yet */ - return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED : - KVM_MP_STATE_OPERATING; + ret = is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED : + KVM_MP_STATE_OPERATING; + + vcpu_put(vcpu); + return ret; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, @@ -2842,6 +2915,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, { int rc = 0; + vcpu_load(vcpu); + /* user space knows about this interface - let it control the state */ vcpu->kvm->arch.user_cpu_state_ctrl = 1; @@ -2859,12 +2934,13 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, rc = -ENXIO; } + vcpu_put(vcpu); return rc; } static bool ibs_enabled(struct kvm_vcpu *vcpu) { - return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS; + return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS); } static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) @@ -2900,8 +2976,7 @@ retry: if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) { if (!ibs_enabled(vcpu)) { trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1); - atomic_or(CPUSTAT_IBS, - &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_IBS); } goto retry; } @@ -2909,8 +2984,7 @@ retry: if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) { if (ibs_enabled(vcpu)) { trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0); - atomic_andnot(CPUSTAT_IBS, - &vcpu->arch.sie_block->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IBS); } goto retry; } @@ -3390,9 +3464,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (kvm_run->immediate_exit) return -EINTR; + vcpu_load(vcpu); + if (guestdbg_exit_pending(vcpu)) { kvm_s390_prepare_debug_exit(vcpu); - return 0; + rc = 0; + goto out; } kvm_sigset_activate(vcpu); @@ -3402,7 +3479,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } else if (is_vcpu_stopped(vcpu)) { pr_err_ratelimited("can't run stopped vcpu %d\n", vcpu->vcpu_id); - return -EINVAL; + rc = -EINVAL; + goto out; } sync_regs(vcpu, kvm_run); @@ -3432,6 +3510,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_sigset_deactivate(vcpu); vcpu->stat.exit_userspace++; +out: + vcpu_put(vcpu); return rc; } @@ -3560,7 +3640,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu) __disable_ibs_on_all_vcpus(vcpu->kvm); } - atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED); /* * Another VCPU might have used IBS while we were offline. * Let's play safe and flush the VCPU at startup. @@ -3586,7 +3666,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu) /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */ kvm_s390_clear_stop_irq(vcpu); - atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED); __disable_ibs_on_vcpu(vcpu); for (i = 0; i < online_vcpus; i++) { @@ -3693,36 +3773,45 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu, return r; } -long kvm_arch_vcpu_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +long kvm_arch_vcpu_async_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; - int idx; - long r; switch (ioctl) { case KVM_S390_IRQ: { struct kvm_s390_irq s390irq; - r = -EFAULT; if (copy_from_user(&s390irq, argp, sizeof(s390irq))) - break; - r = kvm_s390_inject_vcpu(vcpu, &s390irq); - break; + return -EFAULT; + return kvm_s390_inject_vcpu(vcpu, &s390irq); } case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; struct kvm_s390_irq s390irq; - r = -EFAULT; if (copy_from_user(&s390int, argp, sizeof(s390int))) - break; + return -EFAULT; if (s390int_to_s390irq(&s390int, &s390irq)) return -EINVAL; - r = kvm_s390_inject_vcpu(vcpu, &s390irq); - break; + return kvm_s390_inject_vcpu(vcpu, &s390irq); + } } + return -ENOIOCTLCMD; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + int idx; + long r; + + vcpu_load(vcpu); + + switch (ioctl) { case KVM_S390_STORE_STATUS: idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_s390_vcpu_store_status(vcpu, arg); @@ -3847,6 +3936,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, default: r = -ENOTTY; } + + vcpu_put(vcpu); return r; } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 5e46ba429bcb..bd31b37b0e6f 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -47,14 +47,29 @@ do { \ d_args); \ } while (0) +static inline void kvm_s390_set_cpuflags(struct kvm_vcpu *vcpu, u32 flags) +{ + atomic_or(flags, &vcpu->arch.sie_block->cpuflags); +} + +static inline void kvm_s390_clear_cpuflags(struct kvm_vcpu *vcpu, u32 flags) +{ + atomic_andnot(flags, &vcpu->arch.sie_block->cpuflags); +} + +static inline bool kvm_s390_test_cpuflags(struct kvm_vcpu *vcpu, u32 flags) +{ + return (atomic_read(&vcpu->arch.sie_block->cpuflags) & flags) == flags; +} + static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) { - return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED; + return kvm_s390_test_cpuflags(vcpu, CPUSTAT_STOPPED); } static inline int is_vcpu_idle(struct kvm_vcpu *vcpu) { - return test_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask); + return test_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask); } static inline int kvm_is_ucontrol(struct kvm *kvm) @@ -367,6 +382,9 @@ int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *buf, int len); int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len); +void kvm_s390_gisa_init(struct kvm *kvm); +void kvm_s390_gisa_clear(struct kvm *kvm); +void kvm_s390_gisa_destroy(struct kvm *kvm); /* implemented in guestdbg.c */ void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 0714bfa56da0..c4c4e157c036 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -2,7 +2,7 @@ /* * handling privileged instructions * - * Copyright IBM Corp. 2008, 2013 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -34,6 +34,8 @@ static int handle_ri(struct kvm_vcpu *vcpu) { + vcpu->stat.instruction_ri++; + if (test_kvm_facility(vcpu->kvm, 64)) { VCPU_EVENT(vcpu, 3, "%s", "ENABLE: RI (lazy)"); vcpu->arch.sie_block->ecb3 |= ECB3_RI; @@ -53,6 +55,8 @@ int kvm_s390_handle_aa(struct kvm_vcpu *vcpu) static int handle_gs(struct kvm_vcpu *vcpu) { + vcpu->stat.instruction_gs++; + if (test_kvm_facility(vcpu->kvm, 133)) { VCPU_EVENT(vcpu, 3, "%s", "ENABLE: GS (lazy)"); preempt_disable(); @@ -85,6 +89,8 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) u8 ar; u64 op2, val; + vcpu->stat.instruction_sck++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -203,14 +209,14 @@ int kvm_s390_skey_check_enable(struct kvm_vcpu *vcpu) trace_kvm_s390_skey_related_inst(vcpu); if (!(sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)) && - !(atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS)) + !kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS)) return rc; rc = s390_enable_skey(); VCPU_EVENT(vcpu, 3, "enabling storage keys for guest: %d", rc); if (!rc) { - if (atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS) - atomic_andnot(CPUSTAT_KSS, &sie_block->cpuflags); + if (kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS)) + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_KSS); else sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE); @@ -222,7 +228,6 @@ static int try_handle_skey(struct kvm_vcpu *vcpu) { int rc; - vcpu->stat.instruction_storage_key++; rc = kvm_s390_skey_check_enable(vcpu); if (rc) return rc; @@ -242,6 +247,8 @@ static int handle_iske(struct kvm_vcpu *vcpu) int reg1, reg2; int rc; + vcpu->stat.instruction_iske++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -274,6 +281,8 @@ static int handle_rrbe(struct kvm_vcpu *vcpu) int reg1, reg2; int rc; + vcpu->stat.instruction_rrbe++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -312,6 +321,8 @@ static int handle_sske(struct kvm_vcpu *vcpu) int reg1, reg2; int rc; + vcpu->stat.instruction_sske++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -392,6 +403,8 @@ static int handle_test_block(struct kvm_vcpu *vcpu) gpa_t addr; int reg2; + vcpu->stat.instruction_tb++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -424,6 +437,8 @@ static int handle_tpi(struct kvm_vcpu *vcpu) u64 addr; u8 ar; + vcpu->stat.instruction_tpi++; + addr = kvm_s390_get_base_disp_s(vcpu, &ar); if (addr & 3) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); @@ -484,6 +499,8 @@ static int handle_tsch(struct kvm_vcpu *vcpu) struct kvm_s390_interrupt_info *inti = NULL; const u64 isc_mask = 0xffUL << 24; /* all iscs set */ + vcpu->stat.instruction_tsch++; + /* a valid schid has at least one bit set */ if (vcpu->run->s.regs.gprs[1]) inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask, @@ -527,6 +544,7 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->ipa == 0xb235) return handle_tsch(vcpu); /* Handle in userspace. */ + vcpu->stat.instruction_io_other++; return -EOPNOTSUPP; } else { /* @@ -592,6 +610,8 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu) int rc; u8 ar; + vcpu->stat.instruction_lpsw++; + if (gpsw->mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -619,6 +639,8 @@ static int handle_lpswe(struct kvm_vcpu *vcpu) int rc; u8 ar; + vcpu->stat.instruction_lpswe++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -828,6 +850,8 @@ static int handle_epsw(struct kvm_vcpu *vcpu) { int reg1, reg2; + vcpu->stat.instruction_epsw++; + kvm_s390_get_regs_rre(vcpu, ®1, ®2); /* This basically extracts the mask half of the psw. */ @@ -1332,6 +1356,8 @@ static int handle_sckpf(struct kvm_vcpu *vcpu) { u32 value; + vcpu->stat.instruction_sckpf++; + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); @@ -1347,6 +1373,8 @@ static int handle_sckpf(struct kvm_vcpu *vcpu) static int handle_ptff(struct kvm_vcpu *vcpu) { + vcpu->stat.instruction_ptff++; + /* we don't emulate any control instructions yet */ kvm_s390_set_psw_cc(vcpu, 3); return 0; diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index c1f5cde2c878..683036c1c92a 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -20,22 +20,18 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, u64 *reg) { - struct kvm_s390_local_interrupt *li; - int cpuflags; + const bool stopped = kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED); int rc; int ext_call_pending; - li = &dst_vcpu->arch.local_int; - - cpuflags = atomic_read(li->cpuflags); ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu); - if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending) + if (!stopped && !ext_call_pending) rc = SIGP_CC_ORDER_CODE_ACCEPTED; else { *reg &= 0xffffffff00000000UL; if (ext_call_pending) *reg |= SIGP_STATUS_EXT_CALL_PENDING; - if (cpuflags & CPUSTAT_STOPPED) + if (stopped) *reg |= SIGP_STATUS_STOPPED; rc = SIGP_CC_STATUS_STORED; } @@ -208,11 +204,9 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, u32 addr, u64 *reg) { - int flags; int rc; - flags = atomic_read(dst_vcpu->arch.local_int.cpuflags); - if (!(flags & CPUSTAT_STOPPED)) { + if (!kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED)) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INCORRECT_STATE; return SIGP_CC_STATUS_STORED; @@ -231,7 +225,6 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, static int __sigp_sense_running(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, u64 *reg) { - struct kvm_s390_local_interrupt *li; int rc; if (!test_kvm_facility(vcpu->kvm, 9)) { @@ -240,8 +233,7 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, return SIGP_CC_STATUS_STORED; } - li = &dst_vcpu->arch.local_int; - if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) { + if (kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_RUNNING)) { /* running */ rc = SIGP_CC_ORDER_CODE_ACCEPTED; } else { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 751348348477..ec772700ff96 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -28,13 +28,23 @@ struct vsie_page { * the same offset as that in struct sie_page! */ struct mcck_volatile_info mcck_info; /* 0x0200 */ - /* the pinned originial scb */ + /* + * The pinned original scb. Be aware that other VCPUs can modify + * it while we read from it. Values that are used for conditions or + * are reused conditionally, should be accessed via READ_ONCE. + */ struct kvm_s390_sie_block *scb_o; /* 0x0218 */ /* the shadow gmap in use by the vsie_page */ struct gmap *gmap; /* 0x0220 */ /* address of the last reported fault to guest2 */ unsigned long fault_addr; /* 0x0228 */ - __u8 reserved[0x0700 - 0x0230]; /* 0x0230 */ + /* calculated guest addresses of satellite control blocks */ + gpa_t sca_gpa; /* 0x0230 */ + gpa_t itdba_gpa; /* 0x0238 */ + gpa_t gvrd_gpa; /* 0x0240 */ + gpa_t riccbd_gpa; /* 0x0248 */ + gpa_t sdnx_gpa; /* 0x0250 */ + __u8 reserved[0x0700 - 0x0258]; /* 0x0258 */ struct kvm_s390_crypto_cb crycb; /* 0x0700 */ __u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */ }; @@ -140,12 +150,13 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; - u32 crycb_addr = scb_o->crycbd & 0x7ffffff8U; + const uint32_t crycbd_o = READ_ONCE(scb_o->crycbd); + const u32 crycb_addr = crycbd_o & 0x7ffffff8U; unsigned long *b1, *b2; u8 ecb3_flags; scb_s->crycbd = 0; - if (!(scb_o->crycbd & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1)) + if (!(crycbd_o & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1)) return 0; /* format-1 is supported with message-security-assist extension 3 */ if (!test_kvm_facility(vcpu->kvm, 76)) @@ -183,12 +194,15 @@ static void prepare_ibc(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + /* READ_ONCE does not work on bitfields - use a temporary variable */ + const uint32_t __new_ibc = scb_o->ibc; + const uint32_t new_ibc = READ_ONCE(__new_ibc) & 0x0fffU; __u64 min_ibc = (sclp.ibc >> 16) & 0x0fffU; scb_s->ibc = 0; /* ibc installed in g2 and requested for g3 */ - if (vcpu->kvm->arch.model.ibc && (scb_o->ibc & 0x0fffU)) { - scb_s->ibc = scb_o->ibc & 0x0fffU; + if (vcpu->kvm->arch.model.ibc && new_ibc) { + scb_s->ibc = new_ibc; /* takte care of the minimum ibc level of the machine */ if (scb_s->ibc < min_ibc) scb_s->ibc = min_ibc; @@ -259,6 +273,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; + /* READ_ONCE does not work on bitfields - use a temporary variable */ + const uint32_t __new_prefix = scb_o->prefix; + const uint32_t new_prefix = READ_ONCE(__new_prefix); + const bool wants_tx = READ_ONCE(scb_o->ecb) & ECB_TE; bool had_tx = scb_s->ecb & ECB_TE; unsigned long new_mso = 0; int rc; @@ -306,14 +324,14 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->icpua = scb_o->icpua; if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_SM)) - new_mso = scb_o->mso & 0xfffffffffff00000UL; + new_mso = READ_ONCE(scb_o->mso) & 0xfffffffffff00000UL; /* if the hva of the prefix changes, we have to remap the prefix */ - if (scb_s->mso != new_mso || scb_s->prefix != scb_o->prefix) + if (scb_s->mso != new_mso || scb_s->prefix != new_prefix) prefix_unmapped(vsie_page); /* SIE will do mso/msl validity and exception checks for us */ scb_s->msl = scb_o->msl & 0xfffffffffff00000UL; scb_s->mso = new_mso; - scb_s->prefix = scb_o->prefix; + scb_s->prefix = new_prefix; /* We have to definetly flush the tlb if this scb never ran */ if (scb_s->ihcpu != 0xffffU) @@ -325,11 +343,11 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP)) scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT; /* transactional execution */ - if (test_kvm_facility(vcpu->kvm, 73)) { + if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) { /* remap the prefix is tx is toggled on */ - if ((scb_o->ecb & ECB_TE) && !had_tx) + if (!had_tx) prefix_unmapped(vsie_page); - scb_s->ecb |= scb_o->ecb & ECB_TE; + scb_s->ecb |= ECB_TE; } /* branch prediction */ if (test_kvm_facility(vcpu->kvm, 82)) @@ -473,46 +491,42 @@ static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa) /* unpin all blocks previously pinned by pin_blocks(), marking them dirty */ static void unpin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { - struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; hpa_t hpa; - gpa_t gpa; hpa = (u64) scb_s->scaoh << 32 | scb_s->scaol; if (hpa) { - gpa = scb_o->scaol & ~0xfUL; - if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO)) - gpa |= (u64) scb_o->scaoh << 32; - unpin_guest_page(vcpu->kvm, gpa, hpa); + unpin_guest_page(vcpu->kvm, vsie_page->sca_gpa, hpa); + vsie_page->sca_gpa = 0; scb_s->scaol = 0; scb_s->scaoh = 0; } hpa = scb_s->itdba; if (hpa) { - gpa = scb_o->itdba & ~0xffUL; - unpin_guest_page(vcpu->kvm, gpa, hpa); + unpin_guest_page(vcpu->kvm, vsie_page->itdba_gpa, hpa); + vsie_page->itdba_gpa = 0; scb_s->itdba = 0; } hpa = scb_s->gvrd; if (hpa) { - gpa = scb_o->gvrd & ~0x1ffUL; - unpin_guest_page(vcpu->kvm, gpa, hpa); + unpin_guest_page(vcpu->kvm, vsie_page->gvrd_gpa, hpa); + vsie_page->gvrd_gpa = 0; scb_s->gvrd = 0; } hpa = scb_s->riccbd; if (hpa) { - gpa = scb_o->riccbd & ~0x3fUL; - unpin_guest_page(vcpu->kvm, gpa, hpa); + unpin_guest_page(vcpu->kvm, vsie_page->riccbd_gpa, hpa); + vsie_page->riccbd_gpa = 0; scb_s->riccbd = 0; } hpa = scb_s->sdnxo; if (hpa) { - gpa = scb_o->sdnxo; - unpin_guest_page(vcpu->kvm, gpa, hpa); + unpin_guest_page(vcpu->kvm, vsie_page->sdnx_gpa, hpa); + vsie_page->sdnx_gpa = 0; scb_s->sdnxo = 0; } } @@ -539,9 +553,9 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) gpa_t gpa; int rc = 0; - gpa = scb_o->scaol & ~0xfUL; + gpa = READ_ONCE(scb_o->scaol) & ~0xfUL; if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO)) - gpa |= (u64) scb_o->scaoh << 32; + gpa |= (u64) READ_ONCE(scb_o->scaoh) << 32; if (gpa) { if (!(gpa & ~0x1fffUL)) rc = set_validity_icpt(scb_s, 0x0038U); @@ -557,11 +571,12 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) } if (rc) goto unpin; + vsie_page->sca_gpa = gpa; scb_s->scaoh = (u32)((u64)hpa >> 32); scb_s->scaol = (u32)(u64)hpa; } - gpa = scb_o->itdba & ~0xffUL; + gpa = READ_ONCE(scb_o->itdba) & ~0xffUL; if (gpa && (scb_s->ecb & ECB_TE)) { if (!(gpa & ~0x1fffU)) { rc = set_validity_icpt(scb_s, 0x0080U); @@ -573,10 +588,11 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) rc = set_validity_icpt(scb_s, 0x0080U); goto unpin; } + vsie_page->itdba_gpa = gpa; scb_s->itdba = hpa; } - gpa = scb_o->gvrd & ~0x1ffUL; + gpa = READ_ONCE(scb_o->gvrd) & ~0x1ffUL; if (gpa && (scb_s->eca & ECA_VX) && !(scb_s->ecd & ECD_HOSTREGMGMT)) { if (!(gpa & ~0x1fffUL)) { rc = set_validity_icpt(scb_s, 0x1310U); @@ -591,10 +607,11 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) rc = set_validity_icpt(scb_s, 0x1310U); goto unpin; } + vsie_page->gvrd_gpa = gpa; scb_s->gvrd = hpa; } - gpa = scb_o->riccbd & ~0x3fUL; + gpa = READ_ONCE(scb_o->riccbd) & ~0x3fUL; if (gpa && (scb_s->ecb3 & ECB3_RI)) { if (!(gpa & ~0x1fffUL)) { rc = set_validity_icpt(scb_s, 0x0043U); @@ -607,13 +624,14 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) goto unpin; } /* Validity 0x0044 will be checked by SIE */ + vsie_page->riccbd_gpa = gpa; scb_s->riccbd = hpa; } if ((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) { unsigned long sdnxc; - gpa = scb_o->sdnxo & ~0xfUL; - sdnxc = scb_o->sdnxo & 0xfUL; + gpa = READ_ONCE(scb_o->sdnxo) & ~0xfUL; + sdnxc = READ_ONCE(scb_o->sdnxo) & 0xfUL; if (!gpa || !(gpa & ~0x1fffUL)) { rc = set_validity_icpt(scb_s, 0x10b0U); goto unpin; @@ -634,6 +652,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) rc = set_validity_icpt(scb_s, 0x10b0U); goto unpin; } + vsie_page->sdnx_gpa = gpa; scb_s->sdnxo = hpa | sdnxc; } return 0; @@ -778,7 +797,7 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page) static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; - __u32 fac = vsie_page->scb_o->fac & 0x7ffffff8U; + __u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U; if (fac && test_kvm_facility(vcpu->kvm, 7)) { retry_vsie_icpt(vsie_page); @@ -904,7 +923,7 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu, * External calls have to lead to a kick of the vcpu and * therefore the vsie -> Simulate Wait state. */ - atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); + kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT); /* * We have to adjust the g3 epoch by the g2 epoch. The epoch will * automatically be adjusted on tod clock changes via kvm_sync_clock. @@ -926,7 +945,7 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu, */ static void unregister_shadow_scb(struct kvm_vcpu *vcpu) { - atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); + kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT); WRITE_ONCE(vcpu->arch.vsie_block, NULL); } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 05d459b638f5..2c55a2b9d6c6 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -815,27 +815,17 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, * @ptl: pointer to the spinlock pointer * * Returns a pointer to the locked pte for a guest address, or NULL - * - * Note: Can also be called for shadow gmaps. */ static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr, spinlock_t **ptl) { unsigned long *table; - if (gmap_is_shadow(gmap)) - spin_lock(&gmap->guest_table_lock); + BUG_ON(gmap_is_shadow(gmap)); /* Walk the gmap page table, lock and get pte pointer */ table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */ - if (!table || *table & _SEGMENT_ENTRY_INVALID) { - if (gmap_is_shadow(gmap)) - spin_unlock(&gmap->guest_table_lock); + if (!table || *table & _SEGMENT_ENTRY_INVALID) return NULL; - } - if (gmap_is_shadow(gmap)) { - *ptl = &gmap->guest_table_lock; - return pte_offset_map((pmd_t *) table, gaddr); - } return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl); } @@ -889,8 +879,6 @@ static void gmap_pte_op_end(spinlock_t *ptl) * -EFAULT if gaddr is invalid (or mapping for shadows is missing). * * Called with sg->mm->mmap_sem in read. - * - * Note: Can also be called for shadow gmaps. */ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr, unsigned long len, int prot, unsigned long bits) @@ -900,6 +888,7 @@ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr, pte_t *ptep; int rc; + BUG_ON(gmap_is_shadow(gmap)); while (len) { rc = -EAGAIN; ptep = gmap_pte_op_walk(gmap, gaddr, &ptl); @@ -960,7 +949,8 @@ EXPORT_SYMBOL_GPL(gmap_mprotect_notify); * @val: pointer to the unsigned long value to return * * Returns 0 if the value was read, -ENOMEM if out of memory and -EFAULT - * if reading using the virtual address failed. + * if reading using the virtual address failed. -EINVAL if called on a gmap + * shadow. * * Called with gmap->mm->mmap_sem in read. */ @@ -971,6 +961,9 @@ int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val) pte_t *ptep, pte; int rc; + if (gmap_is_shadow(gmap)) + return -EINVAL; + while (1) { rc = -EAGAIN; ptep = gmap_pte_op_walk(gmap, gaddr, &ptl); @@ -1028,18 +1021,17 @@ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, } /** - * gmap_protect_rmap - modify access rights to memory and create an rmap + * gmap_protect_rmap - restrict access rights to memory (RO) and create an rmap * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow gmap * @paddr: address in the parent guest address space * @len: length of the memory area to protect - * @prot: indicates access rights: none, read-only or read-write * * Returns 0 if successfully protected and the rmap was created, -ENOMEM * if out of memory and -EFAULT if paddr is invalid. */ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr, - unsigned long paddr, unsigned long len, int prot) + unsigned long paddr, unsigned long len) { struct gmap *parent; struct gmap_rmap *rmap; @@ -1067,7 +1059,7 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr, ptep = gmap_pte_op_walk(parent, paddr, &ptl); if (ptep) { spin_lock(&sg->guest_table_lock); - rc = ptep_force_prot(parent->mm, paddr, ptep, prot, + rc = ptep_force_prot(parent->mm, paddr, ptep, PROT_READ, PGSTE_VSIE_BIT); if (!rc) gmap_insert_rmap(sg, vmaddr, rmap); @@ -1077,7 +1069,7 @@ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr, radix_tree_preload_end(); if (rc) { kfree(rmap); - rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot); + rc = gmap_pte_op_fixup(parent, paddr, vmaddr, PROT_READ); if (rc) return rc; continue; @@ -1616,7 +1608,7 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, origin = r2t & _REGION_ENTRY_ORIGIN; offset = ((r2t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE; len = ((r2t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset; - rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ); + rc = gmap_protect_rmap(sg, raddr, origin + offset, len); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 4); @@ -1699,7 +1691,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, origin = r3t & _REGION_ENTRY_ORIGIN; offset = ((r3t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE; len = ((r3t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset; - rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ); + rc = gmap_protect_rmap(sg, raddr, origin + offset, len); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 3); @@ -1783,7 +1775,7 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, origin = sgt & _REGION_ENTRY_ORIGIN; offset = ((sgt & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE; len = ((sgt & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset; - rc = gmap_protect_rmap(sg, raddr, origin + offset, len, PROT_READ); + rc = gmap_protect_rmap(sg, raddr, origin + offset, len); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 2); @@ -1902,7 +1894,7 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, /* Make pgt read-only in parent gmap page table (not the pgste) */ raddr = (saddr & _SEGMENT_MASK) | _SHADOW_RMAP_SEGMENT; origin = pgt & _SEGMENT_ENTRY_ORIGIN & PAGE_MASK; - rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE, PROT_READ); + rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 1); @@ -2005,7 +1997,7 @@ EXPORT_SYMBOL_GPL(gmap_shadow_page); * Called with sg->parent->shadow_lock. */ static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr, - unsigned long gaddr, pte_t *pte) + unsigned long gaddr) { struct gmap_rmap *rmap, *rnext, *head; unsigned long start, end, bits, raddr; @@ -2090,7 +2082,7 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, spin_lock(&gmap->shadow_lock); list_for_each_entry_safe(sg, next, &gmap->children, list) - gmap_shadow_notify(sg, vmaddr, gaddr, pte); + gmap_shadow_notify(sg, vmaddr, gaddr); spin_unlock(&gmap->shadow_lock); } if (bits & PGSTE_IN_BIT) diff --git a/arch/score/kernel/setup.c b/arch/score/kernel/setup.c index f3a0649ab521..627416bbd0b1 100644 --- a/arch/score/kernel/setup.c +++ b/arch/score/kernel/setup.c @@ -124,9 +124,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; - seq_printf(m, "processor\t\t: %ld\n", n); - seq_printf(m, "\n"); - + seq_printf(m, "processor\t\t: %ld\n\n", n); return 0; } diff --git a/arch/sparc/include/uapi/asm/poll.h b/arch/sparc/include/uapi/asm/poll.h index 2a81e79aa3ea..72356c999125 100644 --- a/arch/sparc/include/uapi/asm/poll.h +++ b/arch/sparc/include/uapi/asm/poll.h @@ -2,31 +2,11 @@ #ifndef __SPARC_POLL_H #define __SPARC_POLL_H -#ifndef __KERNEL__ #define POLLWRNORM POLLOUT -#define POLLWRBAND (__force __poll_t)256 -#define POLLMSG (__force __poll_t)512 -#define POLLREMOVE (__force __poll_t)1024 -#define POLLRDHUP (__force __poll_t)2048 -#else -#define __ARCH_HAS_MANGLED_POLL -static inline __u16 mangle_poll(__poll_t val) -{ - __u16 v = (__force __u16)val; - /* bit 9 -> bit 8, bit 8 -> bit 2, bit 13 -> bit 11 */ - return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6) | - ((v & 0x2000) >> 2); - - -} - -static inline __poll_t demangle_poll(__u16 v) -{ - /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */ - return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) | - ((v & 4) << 6) | ((v & 0x800) << 2)); -} -#endif +#define POLLWRBAND 256 +#define POLLMSG 512 +#define POLLREMOVE 1024 +#define POLLRDHUP 2048 #include <asm-generic/poll.h> diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index c4d162a94be9..d5f9a2d1da1b 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -130,6 +130,7 @@ void mconsole_proc(struct mc_request *req) struct file *file; int first_chunk = 1; char *ptr = req->request.data; + loff_t pos = 0; ptr += strlen("proc"); ptr = skip_spaces(ptr); @@ -148,7 +149,7 @@ void mconsole_proc(struct mc_request *req) } do { - len = kernel_read(file, buf, PAGE_SIZE - 1, &file->f_pos); + len = kernel_read(file, buf, PAGE_SIZE - 1, &pos); if (len < 0) { mconsole_reply(req, "Read of file failed", 1, 0); goto out_free; diff --git a/arch/unicore32/include/asm/bitops.h b/arch/unicore32/include/asm/bitops.h index 401f597bc38c..c0cbdbe17168 100644 --- a/arch/unicore32/include/asm/bitops.h +++ b/arch/unicore32/include/asm/bitops.h @@ -44,4 +44,6 @@ static inline int fls(int x) #define find_first_bit find_first_bit #define find_first_zero_bit find_first_zero_bit +#include <asm-generic/bitops/find.h> + #endif /* __UNICORE_BITOPS_H__ */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b0771ceabb4b..63bf349b2b24 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,6 +55,7 @@ config X86 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PHYS_TO_DMA + select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 @@ -62,6 +63,7 @@ config X86 select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX + select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_ZONE_DEVICE if X86_64 select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -322,7 +324,7 @@ config X86_64_SMP config X86_32_LAZY_GS def_bool y - depends on X86_32 && !CC_STACKPROTECTOR + depends on X86_32 && CC_STACKPROTECTOR_NONE config ARCH_SUPPORTS_UPROBES def_bool y diff --git a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c index 36870b26067a..d08805032f01 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb_mgr_init_avx2.c @@ -57,10 +57,12 @@ void sha512_mb_mgr_init_avx2(struct sha512_mb_mgr *state) { unsigned int j; - state->lens[0] = 0; - state->lens[1] = 1; - state->lens[2] = 2; - state->lens[3] = 3; + /* initially all lanes are unused */ + state->lens[0] = 0xFFFFFFFF00000000; + state->lens[1] = 0xFFFFFFFF00000001; + state->lens[2] = 0xFFFFFFFF00000002; + state->lens[3] = 0xFFFFFFFF00000003; + state->unused_lanes = 0xFF03020100; for (j = 0; j < 4; j++) state->ldata[j].job_in_lane = NULL; diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 2a35b1e0fb90..16c2c022540d 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -566,6 +566,11 @@ restore_all: .Lrestore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code .Lirq_return: + /* + * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization + * when returning from IPI handler and when returning from + * scheduler to user-space. + */ INTERRUPT_RETURN .section .fixup, "ax" @@ -895,6 +900,9 @@ BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, hyperv_vector_handler) +BUILD_INTERRUPT3(hyperv_reenlightenment_vector, HYPERV_REENLIGHTENMENT_VECTOR, + hyperv_reenlightenment_intr) + #endif /* CONFIG_HYPERV */ ENTRY(page_fault) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index c752abe89d80..30c8c5344c4a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -691,6 +691,10 @@ GLOBAL(restore_regs_and_return_to_kernel) POP_EXTRA_REGS POP_C_REGS addq $8, %rsp /* skip regs->orig_ax */ + /* + * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization + * when returning from IPI handler. + */ INTERRUPT_RETURN ENTRY(native_iret) @@ -1132,6 +1136,9 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ #if IS_ENABLED(CONFIG_HYPERV) apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ hyperv_callback_vector hyperv_vector_handler + +apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \ + hyperv_reenlightenment_vector hyperv_reenlightenment_intr #endif /* CONFIG_HYPERV */ idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 8e4ea143ed96..78f91ec1056e 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -93,7 +93,8 @@ struct amd_nb { PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \ - PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER) + PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \ + PERF_SAMPLE_PERIOD) #define PEBS_REGS \ (PERF_REG_X86_AX | \ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a0a206556919..2edc49e7409b 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -18,6 +18,8 @@ */ #include <linux/types.h> +#include <asm/apic.h> +#include <asm/desc.h> #include <asm/hypervisor.h> #include <asm/hyperv.h> #include <asm/mshyperv.h> @@ -37,6 +39,7 @@ struct ms_hyperv_tsc_page *hv_get_tsc_page(void) { return tsc_pg; } +EXPORT_SYMBOL_GPL(hv_get_tsc_page); static u64 read_hv_clock_tsc(struct clocksource *arg) { @@ -101,6 +104,115 @@ static int hv_cpu_init(unsigned int cpu) return 0; } +static void (*hv_reenlightenment_cb)(void); + +static void hv_reenlightenment_notify(struct work_struct *dummy) +{ + struct hv_tsc_emulation_status emu_status; + + rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status); + + /* Don't issue the callback if TSC accesses are not emulated */ + if (hv_reenlightenment_cb && emu_status.inprogress) + hv_reenlightenment_cb(); +} +static DECLARE_DELAYED_WORK(hv_reenlightenment_work, hv_reenlightenment_notify); + +void hyperv_stop_tsc_emulation(void) +{ + u64 freq; + struct hv_tsc_emulation_status emu_status; + + rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status); + emu_status.inprogress = 0; + wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status); + + rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq); + tsc_khz = div64_u64(freq, 1000); +} +EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation); + +static inline bool hv_reenlightenment_available(void) +{ + /* + * Check for required features and priviliges to make TSC frequency + * change notifications work. + */ + return ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE && + ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT; +} + +__visible void __irq_entry hyperv_reenlightenment_intr(struct pt_regs *regs) +{ + entering_ack_irq(); + + inc_irq_stat(irq_hv_reenlightenment_count); + + schedule_delayed_work(&hv_reenlightenment_work, HZ/10); + + exiting_irq(); +} + +void set_hv_tscchange_cb(void (*cb)(void)) +{ + struct hv_reenlightenment_control re_ctrl = { + .vector = HYPERV_REENLIGHTENMENT_VECTOR, + .enabled = 1, + .target_vp = hv_vp_index[smp_processor_id()] + }; + struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1}; + + if (!hv_reenlightenment_available()) { + pr_warn("Hyper-V: reenlightenment support is unavailable\n"); + return; + } + + hv_reenlightenment_cb = cb; + + /* Make sure callback is registered before we write to MSRs */ + wmb(); + + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); + wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl)); +} +EXPORT_SYMBOL_GPL(set_hv_tscchange_cb); + +void clear_hv_tscchange_cb(void) +{ + struct hv_reenlightenment_control re_ctrl; + + if (!hv_reenlightenment_available()) + return; + + rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl); + re_ctrl.enabled = 0; + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl); + + hv_reenlightenment_cb = NULL; +} +EXPORT_SYMBOL_GPL(clear_hv_tscchange_cb); + +static int hv_cpu_die(unsigned int cpu) +{ + struct hv_reenlightenment_control re_ctrl; + unsigned int new_cpu; + + if (hv_reenlightenment_cb == NULL) + return 0; + + rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); + if (re_ctrl.target_vp == hv_vp_index[cpu]) { + /* Reassign to some other online CPU */ + new_cpu = cpumask_any_but(cpu_online_mask, cpu); + + re_ctrl.target_vp = hv_vp_index[new_cpu]; + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); + } + + return 0; +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -110,12 +222,19 @@ static int hv_cpu_init(unsigned int cpu) */ void hyperv_init(void) { - u64 guest_id; + u64 guest_id, required_msrs; union hv_x64_msr_hypercall_contents hypercall_msr; if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; + /* Absolutely required MSRs */ + required_msrs = HV_X64_MSR_HYPERCALL_AVAILABLE | + HV_X64_MSR_VP_INDEX_AVAILABLE; + + if ((ms_hyperv.features & required_msrs) != required_msrs) + return; + /* Allocate percpu VP index */ hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index), GFP_KERNEL); @@ -123,7 +242,7 @@ void hyperv_init(void) return; if (cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online", - hv_cpu_init, NULL) < 0) + hv_cpu_init, hv_cpu_die) < 0) goto free_vp_index; /* diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1d9199e1c2ad..0dfe4d3f74e2 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -210,6 +210,7 @@ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ +#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 51cc979dd364..7c341a74ec8c 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -38,6 +38,9 @@ typedef struct { #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) unsigned int irq_hv_callback_count; #endif +#if IS_ENABLED(CONFIG_HYPERV) + unsigned int irq_hv_reenlightenment_count; +#endif } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 35a6bc4da8ad..cf090e584202 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -10,6 +10,10 @@ * * Things ending in "2" are usually because we have no better * name for them. There's no processor called "SILVERMONT2". + * + * While adding a new CPUID for a new microarchitecture, add a new + * group to keep logically sorted out in chronological order. Within + * that group keep the CPUID for the variants sorted by model number. */ #define INTEL_FAM6_CORE_YONAH 0x0E @@ -49,6 +53,8 @@ #define INTEL_FAM6_KABYLAKE_MOBILE 0x8E #define INTEL_FAM6_KABYLAKE_DESKTOP 0x9E +#define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_PINEVIEW 0x1C diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h index 528ed4be4393..9e7adcdbe031 100644 --- a/arch/x86/include/asm/intel_pmc_ipc.h +++ b/arch/x86/include/asm/intel_pmc_ipc.h @@ -38,6 +38,7 @@ int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out, u32 outlen); int intel_pmc_s0ix_counter_read(u64 *data); int intel_pmc_gcr_read(u32 offset, u32 *data); +int intel_pmc_gcr_read64(u32 offset, u64 *data); int intel_pmc_gcr_write(u32 offset, u32 data); int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val); @@ -70,6 +71,11 @@ static inline int intel_pmc_gcr_read(u32 offset, u32 *data) return -EINVAL; } +static inline int intel_pmc_gcr_read64(u32 offset, u64 *data) +{ + return -EINVAL; +} + static inline int intel_pmc_gcr_write(u32 offset, u32 data) { return -EINVAL; diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 67421f649cfa..e71c1120426b 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -103,7 +103,12 @@ #endif #define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef -#define LOCAL_TIMER_VECTOR 0xee + +#if IS_ENABLED(CONFIG_HYPERV) +#define HYPERV_REENLIGHTENMENT_VECTOR 0xee +#endif + +#define LOCAL_TIMER_VECTOR 0xed #define NR_VECTORS 256 diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h index b577dd0916aa..13e70da38bed 100644 --- a/arch/x86/include/asm/kasan.h +++ b/arch/x86/include/asm/kasan.h @@ -4,6 +4,7 @@ #include <linux/const.h> #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) +#define KASAN_SHADOW_SCALE_SHIFT 3 /* * Compiler uses shadow offset assuming that addresses start @@ -12,12 +13,15 @@ * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT */ #define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ - ((-1UL << __VIRTUAL_MASK_SHIFT) >> 3)) + ((-1UL << __VIRTUAL_MASK_SHIFT) >> \ + KASAN_SHADOW_SCALE_SHIFT)) /* - * 47 bits for kernel address -> (47 - 3) bits for shadow - * 56 bits for kernel address -> (56 - 3) bits for shadow + * 47 bits for kernel address -> (47 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow + * 56 bits for kernel address -> (56 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow */ -#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3))) +#define KASAN_SHADOW_END (KASAN_SHADOW_START + \ + (1ULL << (__VIRTUAL_MASK_SHIFT - \ + KASAN_SHADOW_SCALE_SHIFT))) #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 516798431328..dd6f57a54a26 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -86,7 +86,7 @@ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ - | X86_CR4_SMAP | X86_CR4_PKE)) + | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) @@ -504,6 +504,7 @@ struct kvm_vcpu_arch { int mp_state; u64 ia32_misc_enable_msr; u64 smbase; + u64 smi_count; bool tpr_access_reporting; u64 ia32_xss; @@ -760,6 +761,15 @@ enum kvm_irqchip_mode { KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; +struct kvm_sev_info { + bool active; /* SEV enabled guest */ + unsigned int asid; /* ASID used for this guest */ + unsigned int handle; /* SEV firmware handle */ + int fd; /* SEV device fd */ + unsigned long pages_locked; /* Number of pages locked */ + struct list_head regions_list; /* List of registered regions */ +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -847,6 +857,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + struct kvm_sev_info sev_info; }; struct kvm_vm_stat { @@ -883,7 +895,6 @@ struct kvm_vcpu_stat { u64 request_irq_exits; u64 irq_exits; u64 host_state_reload; - u64 efer_reload; u64 fpu_reload; u64 insn_emulation; u64 insn_emulation_fail; @@ -965,7 +976,7 @@ struct kvm_x86_ops { unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); - void (*tlb_flush)(struct kvm_vcpu *vcpu); + void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); void (*run)(struct kvm_vcpu *vcpu); int (*handle_exit)(struct kvm_vcpu *vcpu); @@ -1017,6 +1028,7 @@ struct kvm_x86_ops { void (*handle_external_intr)(struct kvm_vcpu *vcpu); bool (*mpx_supported)(void); bool (*xsaves_supported)(void); + bool (*umip_emulated)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); @@ -1079,6 +1091,10 @@ struct kvm_x86_ops { int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); int (*enable_smi_window)(struct kvm_vcpu *vcpu); + + int (*mem_enc_op)(struct kvm *kvm, void __user *argp); + int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); + int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); }; struct kvm_arch_async_pf { diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index b52af150cbd8..25283f7eb299 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -160,6 +160,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) #define hv_set_synint_state(int_num, val) wrmsrl(int_num, val) void hyperv_callback_vector(void); +void hyperv_reenlightenment_vector(void); #ifdef CONFIG_TRACING #define trace_hyperv_callback_vector hyperv_callback_vector #endif @@ -316,18 +317,27 @@ void hyper_alloc_mmu(void); void hyperv_report_panic(struct pt_regs *regs, long err); bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); + +void hyperv_reenlightenment_intr(struct pt_regs *regs); +void set_hv_tscchange_cb(void (*cb)(void)); +void clear_hv_tscchange_cb(void); +void hyperv_stop_tsc_emulation(void); #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline bool hv_is_hyperv_initialized(void) { return false; } static inline void hyperv_cleanup(void) {} static inline void hyperv_setup_mmu_ops(void) {} +static inline void set_hv_tscchange_cb(void (*cb)(void)) {} +static inline void clear_hv_tscchange_cb(void) {} +static inline void hyperv_stop_tsc_emulation(void) {}; #endif /* CONFIG_HYPERV */ #ifdef CONFIG_HYPERV_TSCPAGE struct ms_hyperv_tsc_page *hv_get_tsc_page(void); -static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) +static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc) { - u64 scale, offset, cur_tsc; + u64 scale, offset; u32 sequence; /* @@ -358,7 +368,7 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) scale = READ_ONCE(tsc_pg->tsc_scale); offset = READ_ONCE(tsc_pg->tsc_offset); - cur_tsc = rdtsc_ordered(); + *cur_tsc = rdtsc_ordered(); /* * Make sure we read sequence after we read all other values @@ -368,7 +378,14 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) } while (READ_ONCE(tsc_pg->tsc_sequence) != sequence); - return mul_u64_u64_shr(cur_tsc, scale, 64) + offset; + return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset; +} + +static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) +{ + u64 cur_tsc; + + return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc); } #else @@ -376,5 +393,12 @@ static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void) { return NULL; } + +static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, + u64 *cur_tsc) +{ + BUG(); + return U64_MAX; +} #endif #endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e520a1e6fc11..c9084dedfcfa 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -397,6 +397,8 @@ #define MSR_K7_PERFCTR3 0xc0010007 #define MSR_K7_CLK_CTL 0xc001001b #define MSR_K7_HWCR 0xc0010015 +#define MSR_K7_HWCR_SMMLOCK_BIT 0 +#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 8a3ee355b422..92015c65fa2a 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -22,4 +22,6 @@ int io_reserve_memtype(resource_size_t start, resource_size_t end, void io_free_memtype(resource_size_t start, resource_size_t end); +bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn); + #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/pmc_core.h b/arch/x86/include/asm/pmc_core.h deleted file mode 100644 index d4855f11136d..000000000000 --- a/arch/x86/include/asm/pmc_core.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Intel Core SoC Power Management Controller Header File - * - * Copyright (c) 2016, Intel Corporation. - * All Rights Reserved. - * - * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com> - * Vishwanath Somayaji <vishwanath.somayaji@intel.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - */ - -#ifndef _ASM_PMC_CORE_H -#define _ASM_PMC_CORE_H - -/* API to read SLP_S0_RESIDENCY counter */ -int intel_pmc_slp_s0_counter_read(u32 *data); - -#endif /* _ASM_PMC_CORE_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 78dd9df88157..0487ac054870 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -146,6 +146,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL #define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL +#define SVM_NESTED_CTL_NP_ENABLE BIT(0) +#define SVM_NESTED_CTL_SEV_ENABLE BIT(1) + struct __attribute__ ((__packed__)) vmcb_seg { u16 selector; u16 attrib; diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h new file mode 100644 index 000000000000..c67caafd3381 --- /dev/null +++ b/arch/x86/include/asm/sync_core.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SYNC_CORE_H +#define _ASM_X86_SYNC_CORE_H + +#include <linux/preempt.h> +#include <asm/processor.h> +#include <asm/cpufeature.h> + +/* + * Ensure that a core serializing instruction is issued before returning + * to user-mode. x86 implements return to user-space through sysexit, + * sysrel, and sysretq, which are not core serializing. + */ +static inline void sync_core_before_usermode(void) +{ + /* With PTI, we unconditionally serialize before running user code. */ + if (static_cpu_has(X86_FEATURE_PTI)) + return; + /* + * Return from interrupt and NMI is done through iret, which is core + * serializing. + */ + if (in_irq() || in_nmi()) + return; + sync_core(); +} + +#endif /* _ASM_X86_SYNC_CORE_H */ diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 1a5bfead93b4..197c2e6c7376 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -40,6 +40,9 @@ */ #define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11) +/* AccessReenlightenmentControls privilege */ +#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13) + /* * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available @@ -234,6 +237,30 @@ #define HV_X64_MSR_CRASH_PARAMS \ (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) +/* TSC emulation after migration */ +#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 + +struct hv_reenlightenment_control { + u64 vector:8; + u64 reserved1:8; + u64 enabled:1; + u64 reserved2:15; + u64 target_vp:32; +}; + +#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 +#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 + +struct hv_tsc_emulation_control { + u64 enabled:1; + u64 reserved:63; +}; + +struct hv_tsc_emulation_status { + u64 inprogress:1; + u64 reserved:63; +}; + #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 09cc06483bed..7a2ade4aa235 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -25,6 +25,7 @@ #define KVM_FEATURE_STEAL_TIME 5 #define KVM_FEATURE_PV_EOI 6 #define KVM_FEATURE_PV_UNHALT 7 +#define KVM_FEATURE_PV_TLB_FLUSH 9 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. @@ -51,6 +52,9 @@ struct kvm_steal_time { __u32 pad[11]; }; +#define KVM_VCPU_PREEMPTED (1 << 0) +#define KVM_VCPU_FLUSH_TLB (1 << 1) + #define KVM_CLOCK_PAIRING_WALLCLOCK 0 struct kvm_clock_pairing { __s64 sec; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index ec3a286163c3..2aa92094b59d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -36,6 +36,7 @@ #include <linux/ioport.h> #include <linux/pci.h> #include <linux/efi-bgrt.h> +#include <linux/serial_core.h> #include <asm/e820/api.h> #include <asm/irqdomain.h> @@ -1625,6 +1626,8 @@ int __init acpi_boot_init(void) if (!acpi_noirq) x86_init.pci.init = pci_acpi_init; + /* Do not enable ACPI SPCR console by default */ + acpi_parse_spcr(earlycon_acpi_spcr_enable, false); return 0; } diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ab1865342002..dfcbe6924eaf 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1515,7 +1515,7 @@ static __poll_t do_poll(struct file *fp, poll_table *wait) return 0; poll_wait(fp, &apm_waitqueue, wait); if (!queue_empty(as)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } @@ -2389,6 +2389,7 @@ static int __init apm_init(void) if (HZ != 100) idle_period = (idle_period * HZ) / 100; if (idle_threshold < 100) { + cpuidle_poll_state_init(&apm_idle_driver); if (!cpuidle_register_driver(&apm_idle_driver)) if (cpuidle_register_device(&apm_cpuidle_device)) cpuidle_unregister_driver(&apm_idle_driver); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ea831c858195..5bddbdcbc4a3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -556,6 +556,51 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } } +static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) +{ + u64 msr; + + /* + * BIOS support is required for SME and SEV. + * For SME: If BIOS has enabled SME then adjust x86_phys_bits by + * the SME physical address space reduction value. + * If BIOS has not enabled SME then don't advertise the + * SME feature (set in scattered.c). + * For SEV: If BIOS has not enabled SEV then don't advertise the + * SEV feature (set in scattered.c). + * + * In all cases, since support for SME and SEV requires long mode, + * don't advertise the feature under CONFIG_X86_32. + */ + if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) { + /* Check if memory encryption is enabled */ + rdmsrl(MSR_K8_SYSCFG, msr); + if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + goto clear_all; + + /* + * Always adjust physical address bits. Even though this + * will be a value above 32-bits this is still done for + * CONFIG_X86_32 so that accurate values are reported. + */ + c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f; + + if (IS_ENABLED(CONFIG_X86_32)) + goto clear_all; + + rdmsrl(MSR_K7_HWCR, msr); + if (!(msr & MSR_K7_HWCR_SMMLOCK)) + goto clear_sev; + + return; + +clear_all: + clear_cpu_cap(c, X86_FEATURE_SME); +clear_sev: + clear_cpu_cap(c, X86_FEATURE_SEV); + } +} + static void early_init_amd(struct cpuinfo_x86 *c) { u32 dummy; @@ -627,26 +672,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_E400); - /* - * BIOS support is required for SME. If BIOS has enabled SME then - * adjust x86_phys_bits by the SME physical address space reduction - * value. If BIOS has not enabled SME then don't advertise the - * feature (set in scattered.c). Also, since the SME support requires - * long mode, don't advertise the feature under CONFIG_X86_32. - */ - if (cpu_has(c, X86_FEATURE_SME)) { - u64 msr; - - /* Check if SME is enabled */ - rdmsrl(MSR_K8_SYSCFG, msr); - if (msr & MSR_K8_SYSCFG_MEM_ENCRYPT) { - c->x86_phys_bits -= (cpuid_ebx(0x8000001f) >> 6) & 0x3f; - if (IS_ENABLED(CONFIG_X86_32)) - clear_cpu_cap(c, X86_FEATURE_SME); - } else { - clear_cpu_cap(c, X86_FEATURE_SME); - } - } + early_detect_mem_encrypt(c); } static void init_amd_k8(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 213e8c2ca702..97685a0c3175 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -247,9 +247,9 @@ static __poll_t mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); if (READ_ONCE(mcelog.next)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 85eb5fc180c8..9340f41ce8d3 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -251,6 +251,12 @@ static void __init ms_hyperv_init_platform(void) hyperv_setup_mmu_ops(); /* Setup the IDT for hypervisor callback */ alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + + /* Setup the IDT for reenlightenment notifications */ + if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT) + alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR, + hyperv_reenlightenment_vector); + #endif } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 4075d2be5357..772c219b6889 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -30,6 +30,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, + { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 68e1867cca80..45fb4d2565f8 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -142,6 +142,15 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Hypervisor callback interrupts\n"); } #endif +#if IS_ENABLED(CONFIG_HYPERV) + if (test_bit(HYPERV_REENLIGHTENMENT_VECTOR, system_vectors)) { + seq_printf(p, "%*s: ", prec, "HRE"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->irq_hv_reenlightenment_count); + seq_puts(p, " Hyper-V reenlightenment interrupts\n"); + } +#endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b40ffbf156c1..4e37d1a851a6 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -498,6 +498,34 @@ static void __init kvm_apf_trap_init(void) update_intr_gate(X86_TRAP_PF, async_page_fault); } +static DEFINE_PER_CPU(cpumask_var_t, __pv_tlb_mask); + +static void kvm_flush_tlb_others(const struct cpumask *cpumask, + const struct flush_tlb_info *info) +{ + u8 state; + int cpu; + struct kvm_steal_time *src; + struct cpumask *flushmask = this_cpu_cpumask_var_ptr(__pv_tlb_mask); + + cpumask_copy(flushmask, cpumask); + /* + * We have to call flush only on online vCPUs. And + * queue flush_on_enter for pre-empted vCPUs + */ + for_each_cpu(cpu, flushmask) { + src = &per_cpu(steal_time, cpu); + state = READ_ONCE(src->preempted); + if ((state & KVM_VCPU_PREEMPTED)) { + if (try_cmpxchg(&src->preempted, &state, + state | KVM_VCPU_FLUSH_TLB)) + __cpumask_clear_cpu(cpu, flushmask); + } + } + + native_flush_tlb_others(flushmask, info); +} + static void __init kvm_guest_init(void) { int i; @@ -517,6 +545,9 @@ static void __init kvm_guest_init(void) pv_time_ops.steal_clock = kvm_steal_clock; } + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) + pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); @@ -598,6 +629,22 @@ static __init int activate_jump_labels(void) } arch_initcall(activate_jump_labels); +static __init int kvm_setup_pv_tlb_flush(void) +{ + int cpu; + + if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) { + for_each_possible_cpu(cpu) { + zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + } + pr_info("KVM setup pv remote TLB flush\n"); + } + + return 0; +} +arch_initcall(kvm_setup_pv_tlb_flush); + #ifdef CONFIG_PARAVIRT_SPINLOCKS /* Kick a cpu by its apicid. Used to wake up a halted vcpu */ @@ -643,7 +690,7 @@ __visible bool __kvm_vcpu_is_preempted(long cpu) { struct kvm_steal_time *src = &per_cpu(steal_time, cpu); - return !!src->preempted; + return !!(src->preempted & KVM_VCPU_PREEMPTED); } PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 3df51c287844..92fd433c50b9 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -81,6 +81,14 @@ config KVM_AMD To compile this as a module, choose M here: the module will be called kvm-amd. +config KVM_AMD_SEV + def_bool y + bool "AMD Secure Encrypted Virtualization (SEV) support" + depends on KVM_AMD && X86_64 + depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP + ---help--- + Provides support for launching Encrypted VMs on AMD processors. + config KVM_MMU_AUDIT bool "Audit KVM MMU" depends on KVM && TRACEPOINTS diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 13f5d4217e4f..a0c5a69bc7c4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -291,13 +291,18 @@ static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, { switch (func) { case 0: - entry->eax = 1; /* only one leaf currently */ + entry->eax = 7; ++*nent; break; case 1: entry->ecx = F(MOVBE); ++*nent; break; + case 7: + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + if (index == 0) + entry->ecx = F(RDPID); + ++*nent; default: break; } @@ -325,6 +330,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0; unsigned f_mpx = kvm_mpx_supported() ? F(MPX) : 0; unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0; + unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; /* cpuid 1.edx */ const u32 kvm_cpuid_1_edx_x86_features = @@ -363,7 +369,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | + F(TOPOEXT); /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = @@ -389,8 +396,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | - 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ); + F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | + F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG); /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = @@ -476,6 +484,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ebx |= F(TSC_ADJUST); entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; cpuid_mask(&entry->ecx, CPUID_7_ECX); + entry->ecx |= f_umip; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); @@ -597,7 +606,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_ASYNC_PF) | (1 << KVM_FEATURE_PV_EOI) | (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | - (1 << KVM_FEATURE_PV_UNHALT); + (1 << KVM_FEATURE_PV_UNHALT) | + (1 << KVM_FEATURE_PV_TLB_FLUSH); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); @@ -607,7 +617,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->edx = 0; break; case 0x80000000: - entry->eax = min(entry->eax, 0x8000001a); + entry->eax = min(entry->eax, 0x8000001f); break; case 0x80000001: entry->edx &= kvm_cpuid_8000_0001_edx_x86_features; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 290ecf711aec..d91eaeb01034 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3533,6 +3533,16 @@ static int em_cwd(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_rdpid(struct x86_emulate_ctxt *ctxt) +{ + u64 tsc_aux = 0; + + if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) + return emulate_gp(ctxt, 0); + ctxt->dst.val = tsc_aux; + return X86EMUL_CONTINUE; +} + static int em_rdtsc(struct x86_emulate_ctxt *ctxt) { u64 tsc = 0; @@ -3652,17 +3662,27 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) +static int em_store_sreg(struct x86_emulate_ctxt *ctxt, int segment) { - if (ctxt->modrm_reg > VCPU_SREG_GS) - return emulate_ud(ctxt); + if (segment > VCPU_SREG_GS && + (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) && + ctxt->ops->cpl(ctxt) > 0) + return emulate_gp(ctxt, 0); - ctxt->dst.val = get_segment_selector(ctxt, ctxt->modrm_reg); + ctxt->dst.val = get_segment_selector(ctxt, segment); if (ctxt->dst.bytes == 4 && ctxt->dst.type == OP_MEM) ctxt->dst.bytes = 2; return X86EMUL_CONTINUE; } +static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) +{ + if (ctxt->modrm_reg > VCPU_SREG_GS) + return emulate_ud(ctxt); + + return em_store_sreg(ctxt, ctxt->modrm_reg); +} + static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; @@ -3678,6 +3698,11 @@ static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg); } +static int em_sldt(struct x86_emulate_ctxt *ctxt) +{ + return em_store_sreg(ctxt, VCPU_SREG_LDTR); +} + static int em_lldt(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; @@ -3687,6 +3712,11 @@ static int em_lldt(struct x86_emulate_ctxt *ctxt) return load_segment_descriptor(ctxt, sel, VCPU_SREG_LDTR); } +static int em_str(struct x86_emulate_ctxt *ctxt) +{ + return em_store_sreg(ctxt, VCPU_SREG_TR); +} + static int em_ltr(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; @@ -3739,6 +3769,10 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, { struct desc_ptr desc_ptr; + if ((ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) && + ctxt->ops->cpl(ctxt) > 0) + return emulate_gp(ctxt, 0); + if (ctxt->mode == X86EMUL_MODE_PROT64) ctxt->op_bytes = 8; get(ctxt, &desc_ptr); @@ -3798,6 +3832,10 @@ static int em_lidt(struct x86_emulate_ctxt *ctxt) static int em_smsw(struct x86_emulate_ctxt *ctxt) { + if ((ctxt->ops->get_cr(ctxt, 4) & X86_CR4_UMIP) && + ctxt->ops->cpl(ctxt) > 0) + return emulate_gp(ctxt, 0); + if (ctxt->dst.type == OP_MEM) ctxt->dst.bytes = 2; ctxt->dst.val = ctxt->ops->get_cr(ctxt, 0); @@ -4383,8 +4421,8 @@ static const struct opcode group5[] = { }; static const struct opcode group6[] = { - DI(Prot | DstMem, sldt), - DI(Prot | DstMem, str), + II(Prot | DstMem, em_sldt, sldt), + II(Prot | DstMem, em_str, str), II(Prot | Priv | SrcMem16, em_lldt, lldt), II(Prot | Priv | SrcMem16, em_ltr, ltr), N, N, N, N, @@ -4415,10 +4453,20 @@ static const struct opcode group8[] = { F(DstMem | SrcImmByte | Lock | PageTable, em_btc), }; +/* + * The "memory" destination is actually always a register, since we come + * from the register case of group9. + */ +static const struct gprefix pfx_0f_c7_7 = { + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), +}; + + static const struct group_dual group9 = { { N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { - N, N, N, N, N, N, N, N, + N, N, N, N, N, N, N, + GP(0, &pfx_0f_c7_7), } }; static const struct opcode group11[] = { diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 5c24811e8b0b..f171051eecf3 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -79,7 +79,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (kvm_cpu_has_extint(v)) return 1; - if (kvm_vcpu_apicv_active(v)) + if (!is_guest_mode(v) && kvm_vcpu_apicv_active(v)) return 0; return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e2c1fb8d35ce..924ac8ce9d50 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -364,32 +364,41 @@ static u8 count_vectors(void *bitmap) return count; } -int __kvm_apic_update_irr(u32 *pir, void *regs) +bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr) { u32 i, vec; - u32 pir_val, irr_val; - int max_irr = -1; + u32 pir_val, irr_val, prev_irr_val; + int max_updated_irr; + + max_updated_irr = -1; + *max_irr = -1; for (i = vec = 0; i <= 7; i++, vec += 32) { pir_val = READ_ONCE(pir[i]); irr_val = *((u32 *)(regs + APIC_IRR + i * 0x10)); if (pir_val) { + prev_irr_val = irr_val; irr_val |= xchg(&pir[i], 0); *((u32 *)(regs + APIC_IRR + i * 0x10)) = irr_val; + if (prev_irr_val != irr_val) { + max_updated_irr = + __fls(irr_val ^ prev_irr_val) + vec; + } } if (irr_val) - max_irr = __fls(irr_val) + vec; + *max_irr = __fls(irr_val) + vec; } - return max_irr; + return ((max_updated_irr != -1) && + (max_updated_irr == *max_irr)); } EXPORT_SYMBOL_GPL(__kvm_apic_update_irr); -int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) +bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr) { struct kvm_lapic *apic = vcpu->arch.apic; - return __kvm_apic_update_irr(pir, apic->regs); + return __kvm_apic_update_irr(pir, apic->regs, max_irr); } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); @@ -581,7 +590,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; - if (kvm_x86_ops->sync_pir_to_irr && apic->vcpu->arch.apicv_active) + if (apic->vcpu->arch.apicv_active) highest_irr = kvm_x86_ops->sync_pir_to_irr(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 4b9935a38347..56c36014f7b7 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -75,8 +75,8 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); -int __kvm_apic_update_irr(u32 *pir, void *regs); -int kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); +bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); +bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2b8eb4da4d08..8eca1d04aeb8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -42,6 +42,7 @@ #include <linux/kern_levels.h> #include <asm/page.h> +#include <asm/pat.h> #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/vmx.h> @@ -381,7 +382,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); -void kvm_mmu_clear_all_pte_masks(void) +static void kvm_mmu_clear_all_pte_masks(void) { shadow_user_mask = 0; shadow_accessed_mask = 0; @@ -2708,7 +2709,18 @@ static bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) - return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) && + /* + * Some reserved pages, such as those from NVDIMM + * DAX devices, are not for MMIO, and can be mapped + * with cached memory type for better performance. + * However, the above check misconceives those pages + * as MMIO, and results in KVM mapping them with UC + * memory type, which would hurt the performance. + * Therefore, we check the host memory type in addition + * and only treat UC/UC-/WC pages as MMIO. + */ + (!pat_enabled() || pat_pfn_immune_to_uc_mtrr(pfn)); return true; } @@ -4951,6 +4963,16 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, if (mmio_info_in_cache(vcpu, cr2, direct)) emulation_type = 0; emulate: + /* + * On AMD platforms, under certain conditions insn_len may be zero on #NPF. + * This can happen if a guest gets a page-fault on data access but the HW + * table walker is not able to read the instruction page (e.g instruction + * page is not present in memory). In those cases we simply restart the + * guest. + */ + if (unlikely(insn && !insn_len)) + return 1; + er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); switch (er) { diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index d22ddbdf5e6e..1272861e77b9 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -19,7 +19,7 @@ #include <linux/ratelimit.h> -char const *audit_point_name[] = { +static char const *audit_point_name[] = { "pre page fault", "post page fault", "pre pte write", diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4e3c79530526..b3e488a74828 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -37,6 +37,10 @@ #include <linux/amd-iommu.h> #include <linux/hashtable.h> #include <linux/frame.h> +#include <linux/psp-sev.h> +#include <linux/file.h> +#include <linux/pagemap.h> +#include <linux/swap.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -214,6 +218,9 @@ struct vcpu_svm { */ struct list_head ir_list; spinlock_t ir_list_lock; + + /* which host CPU was used for running this vcpu */ + unsigned int last_cpu; }; /* @@ -289,8 +296,12 @@ module_param(vls, int, 0444); static int vgif = true; module_param(vgif, int, 0444); +/* enable/disable SEV support */ +static int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); +module_param(sev, int, 0444); + static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -static void svm_flush_tlb(struct kvm_vcpu *vcpu); +static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa); static void svm_complete_interrupts(struct vcpu_svm *svm); static int nested_svm_exit_handled(struct vcpu_svm *svm); @@ -324,6 +335,38 @@ enum { #define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL +static unsigned int max_sev_asid; +static unsigned int min_sev_asid; +static unsigned long *sev_asid_bitmap; +#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) + +struct enc_region { + struct list_head list; + unsigned long npages; + struct page **pages; + unsigned long uaddr; + unsigned long size; +}; + +static inline bool svm_sev_enabled(void) +{ + return max_sev_asid; +} + +static inline bool sev_guest(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + return sev->active; +} + +static inline int sev_get_asid(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + return sev->asid; +} + static inline void mark_all_dirty(struct vmcb *vmcb) { vmcb->control.clean = 0; @@ -530,10 +573,14 @@ struct svm_cpu_data { u64 asid_generation; u32 max_asid; u32 next_asid; + u32 min_asid; struct kvm_ldttss_desc *tss_desc; struct page *save_area; struct vmcb *current_vmcb; + + /* index = sev_asid, value = vmcb pointer */ + struct vmcb **sev_vmcbs; }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); @@ -788,6 +835,7 @@ static int svm_hardware_enable(void) sd->asid_generation = 1; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; sd->next_asid = sd->max_asid + 1; + sd->min_asid = max_sev_asid + 1; gdt = get_current_gdt_rw(); sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); @@ -846,6 +894,7 @@ static void svm_cpu_uninit(int cpu) return; per_cpu(svm_data, raw_smp_processor_id()) = NULL; + kfree(sd->sev_vmcbs); __free_page(sd->save_area); kfree(sd); } @@ -859,11 +908,18 @@ static int svm_cpu_init(int cpu) if (!sd) return -ENOMEM; sd->cpu = cpu; - sd->save_area = alloc_page(GFP_KERNEL); r = -ENOMEM; + sd->save_area = alloc_page(GFP_KERNEL); if (!sd->save_area) goto err_1; + if (svm_sev_enabled()) { + r = -ENOMEM; + sd->sev_vmcbs = kmalloc((max_sev_asid + 1) * sizeof(void *), GFP_KERNEL); + if (!sd->sev_vmcbs) + goto err_1; + } + per_cpu(svm_data, cpu) = sd; return 0; @@ -1070,6 +1126,48 @@ static int avic_ga_log_notifier(u32 ga_tag) return 0; } +static __init int sev_hardware_setup(void) +{ + struct sev_user_data_status *status; + int rc; + + /* Maximum number of encrypted guests supported simultaneously */ + max_sev_asid = cpuid_ecx(0x8000001F); + + if (!max_sev_asid) + return 1; + + /* Minimum ASID value that should be used for SEV guest */ + min_sev_asid = cpuid_edx(0x8000001F); + + /* Initialize SEV ASID bitmap */ + sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid), + sizeof(unsigned long), GFP_KERNEL); + if (!sev_asid_bitmap) + return 1; + + status = kmalloc(sizeof(*status), GFP_KERNEL); + if (!status) + return 1; + + /* + * Check SEV platform status. + * + * PLATFORM_STATUS can be called in any state, if we failed to query + * the PLATFORM status then either PSP firmware does not support SEV + * feature or SEV firmware is dead. + */ + rc = sev_platform_status(status, NULL); + if (rc) + goto err; + + pr_info("SEV supported\n"); + +err: + kfree(status); + return rc; +} + static __init int svm_hardware_setup(void) { int cpu; @@ -1105,6 +1203,17 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); } + if (sev) { + if (boot_cpu_has(X86_FEATURE_SEV) && + IS_ENABLED(CONFIG_KVM_AMD_SEV)) { + r = sev_hardware_setup(); + if (r) + sev = false; + } else { + sev = false; + } + } + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -1166,6 +1275,9 @@ static __exit void svm_hardware_unsetup(void) { int cpu; + if (svm_sev_enabled()) + kfree(sev_asid_bitmap); + for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -1318,7 +1430,7 @@ static void init_vmcb(struct vcpu_svm *svm) if (npt_enabled) { /* Setup VMCB for Nested Paging */ - control->nested_ctl = 1; + control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE; clr_intercept(svm, INTERCEPT_INVLPG); clr_exception_intercept(svm, PF_VECTOR); clr_cr_intercept(svm, INTERCEPT_CR3_READ); @@ -1356,6 +1468,11 @@ static void init_vmcb(struct vcpu_svm *svm) svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK; } + if (sev_guest(svm->vcpu.kvm)) { + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; + clr_exception_intercept(svm, UD_VECTOR); + } + mark_all_dirty(svm->vmcb); enable_gif(svm); @@ -1438,6 +1555,179 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +static void __sev_asid_free(int asid) +{ + struct svm_cpu_data *sd; + int cpu, pos; + + pos = asid - 1; + clear_bit(pos, sev_asid_bitmap); + + for_each_possible_cpu(cpu) { + sd = per_cpu(svm_data, cpu); + sd->sev_vmcbs[pos] = NULL; + } +} + +static void sev_asid_free(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + __sev_asid_free(sev->asid); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ + struct sev_data_decommission *decommission; + struct sev_data_deactivate *data; + + if (!handle) + return; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return; + + /* deactivate handle */ + data->handle = handle; + sev_guest_deactivate(data, NULL); + + wbinvd_on_all_cpus(); + sev_guest_df_flush(NULL); + kfree(data); + + decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); + if (!decommission) + return; + + /* decommission handle */ + decommission->handle = handle; + sev_guest_decommission(decommission, NULL); + + kfree(decommission); +} + +static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, + unsigned long ulen, unsigned long *n, + int write) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + unsigned long npages, npinned, size; + unsigned long locked, lock_limit; + struct page **pages; + int first, last; + + /* Calculate number of pages. */ + first = (uaddr & PAGE_MASK) >> PAGE_SHIFT; + last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT; + npages = (last - first + 1); + + locked = sev->pages_locked + npages; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { + pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit); + return NULL; + } + + /* Avoid using vmalloc for smaller buffers. */ + size = npages * sizeof(struct page *); + if (size > PAGE_SIZE) + pages = vmalloc(size); + else + pages = kmalloc(size, GFP_KERNEL); + + if (!pages) + return NULL; + + /* Pin the user virtual address. */ + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); + if (npinned != npages) { + pr_err("SEV: Failure locking %lu pages.\n", npages); + goto err; + } + + *n = npages; + sev->pages_locked = locked; + + return pages; + +err: + if (npinned > 0) + release_pages(pages, npinned); + + kvfree(pages); + return NULL; +} + +static void sev_unpin_memory(struct kvm *kvm, struct page **pages, + unsigned long npages) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + release_pages(pages, npages); + kvfree(pages); + sev->pages_locked -= npages; +} + +static void sev_clflush_pages(struct page *pages[], unsigned long npages) +{ + uint8_t *page_virtual; + unsigned long i; + + if (npages == 0 || pages == NULL) + return; + + for (i = 0; i < npages; i++) { + page_virtual = kmap_atomic(pages[i]); + clflush_cache_range(page_virtual, PAGE_SIZE); + kunmap_atomic(page_virtual); + } +} + +static void __unregister_enc_region_locked(struct kvm *kvm, + struct enc_region *region) +{ + /* + * The guest may change the memory encryption attribute from C=0 -> C=1 + * or vice versa for this memory range. Lets make sure caches are + * flushed to ensure that guest data gets written into memory with + * correct C-bit. + */ + sev_clflush_pages(region->pages, region->npages); + + sev_unpin_memory(kvm, region->pages, region->npages); + list_del(®ion->list); + kfree(region); +} + +static void sev_vm_destroy(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct list_head *head = &sev->regions_list; + struct list_head *pos, *q; + + if (!sev_guest(kvm)) + return; + + mutex_lock(&kvm->lock); + + /* + * if userspace was terminated before unregistering the memory regions + * then lets unpin all the registered memory. + */ + if (!list_empty(head)) { + list_for_each_safe(pos, q, head) { + __unregister_enc_region_locked(kvm, + list_entry(pos, struct enc_region, list)); + } + } + + mutex_unlock(&kvm->lock); + + sev_unbind_asid(kvm, sev->handle); + sev_asid_free(kvm); +} + static void avic_vm_destroy(struct kvm *kvm) { unsigned long flags; @@ -1456,6 +1746,12 @@ static void avic_vm_destroy(struct kvm *kvm) spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); } +static void svm_vm_destroy(struct kvm *kvm) +{ + avic_vm_destroy(kvm); + sev_vm_destroy(kvm); +} + static int avic_vm_init(struct kvm *kvm) { unsigned long flags; @@ -2066,7 +2362,7 @@ static int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); vcpu->arch.cr4 = cr4; if (!npt_enabled) @@ -2125,7 +2421,7 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) { if (sd->next_asid > sd->max_asid) { ++sd->asid_generation; - sd->next_asid = 1; + sd->next_asid = sd->min_asid; svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; } @@ -2173,22 +2469,24 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) static int pf_interception(struct vcpu_svm *svm) { - u64 fault_address = svm->vmcb->control.exit_info_2; + u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); u64 error_code = svm->vmcb->control.exit_info_1; return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address, - svm->vmcb->control.insn_bytes, + static_cpu_has(X86_FEATURE_DECODEASSISTS) ? + svm->vmcb->control.insn_bytes : NULL, svm->vmcb->control.insn_len); } static int npf_interception(struct vcpu_svm *svm) { - u64 fault_address = svm->vmcb->control.exit_info_2; + u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); u64 error_code = svm->vmcb->control.exit_info_1; trace_kvm_page_fault(fault_address, error_code); return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code, - svm->vmcb->control.insn_bytes, + static_cpu_has(X86_FEATURE_DECODEASSISTS) ? + svm->vmcb->control.insn_bytes : NULL, svm->vmcb->control.insn_len); } @@ -2415,7 +2713,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, svm->vmcb->control.nested_cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_NPT); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, @@ -2957,7 +3255,8 @@ static bool nested_vmcb_checks(struct vmcb *vmcb) if (vmcb->control.asid == 0) return false; - if (vmcb->control.nested_ctl && !npt_enabled) + if ((vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && + !npt_enabled) return false; return true; @@ -2971,7 +3270,7 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, else svm->vcpu.arch.hflags &= ~HF_HIF_MASK; - if (nested_vmcb->control.nested_ctl) { + if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) { kvm_mmu_unload(&svm->vcpu); svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3; nested_svm_init_mmu_context(&svm->vcpu); @@ -3019,7 +3318,7 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; svm->nested.intercept = nested_vmcb->control.intercept; - svm_flush_tlb(&svm->vcpu); + svm_flush_tlb(&svm->vcpu, true); svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; @@ -4442,12 +4741,39 @@ static void reload_tss(struct kvm_vcpu *vcpu) load_TR_desc(); } +static void pre_sev_run(struct vcpu_svm *svm, int cpu) +{ + struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + int asid = sev_get_asid(svm->vcpu.kvm); + + /* Assign the asid allocated with this SEV guest */ + svm->vmcb->control.asid = asid; + + /* + * Flush guest TLB: + * + * 1) when different VMCB for the same ASID is to be run on the same host CPU. + * 2) or this VMCB was executed on different host CPU in previous VMRUNs. + */ + if (sd->sev_vmcbs[asid] == svm->vmcb && + svm->last_cpu == cpu) + return; + + svm->last_cpu = cpu; + sd->sev_vmcbs[asid] = svm->vmcb; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; + mark_dirty(svm->vmcb, VMCB_ASID); +} + static void pre_svm_run(struct vcpu_svm *svm) { int cpu = raw_smp_processor_id(); struct svm_cpu_data *sd = per_cpu(svm_data, cpu); + if (sev_guest(svm->vcpu.kvm)) + return pre_sev_run(svm, cpu); + /* FIXME: handle wraparound of asid_generation */ if (svm->asid_generation != sd->asid_generation) new_asid(svm, sd); @@ -4865,7 +5191,7 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void svm_flush_tlb(struct kvm_vcpu *vcpu) +static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5208,7 +5534,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = __sme_set(root); mark_dirty(svm->vmcb, VMCB_CR); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) @@ -5222,7 +5548,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) svm->vmcb->save.cr3 = kvm_read_cr3(vcpu); mark_dirty(svm->vmcb, VMCB_CR); - svm_flush_tlb(vcpu); + svm_flush_tlb(vcpu, true); } static int is_disabled(void) @@ -5308,6 +5634,12 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) entry->edx |= SVM_FEATURE_NPT; break; + case 0x8000001F: + /* Support memory encryption cpuid if host supports it */ + if (boot_cpu_has(X86_FEATURE_SEV)) + cpuid(0x8000001f, &entry->eax, &entry->ebx, + &entry->ecx, &entry->edx); + } } @@ -5336,6 +5668,11 @@ static bool svm_xsaves_supported(void) return false; } +static bool svm_umip_emulated(void) +{ + return false; +} + static bool svm_has_wbinvd_exit(void) { return true; @@ -5637,6 +5974,828 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static int sev_asid_new(void) +{ + int pos; + + /* + * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid. + */ + pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1); + if (pos >= max_sev_asid) + return -EBUSY; + + set_bit(pos, sev_asid_bitmap); + return pos + 1; +} + +static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + int asid, ret; + + ret = -EBUSY; + asid = sev_asid_new(); + if (asid < 0) + return ret; + + ret = sev_platform_init(&argp->error); + if (ret) + goto e_free; + + sev->active = true; + sev->asid = asid; + INIT_LIST_HEAD(&sev->regions_list); + + return 0; + +e_free: + __sev_asid_free(asid); + return ret; +} + +static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) +{ + struct sev_data_activate *data; + int asid = sev_get_asid(kvm); + int ret; + + wbinvd_on_all_cpus(); + + ret = sev_guest_df_flush(error); + if (ret) + return ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* activate ASID on the given handle */ + data->handle = handle; + data->asid = asid; + ret = sev_guest_activate(data, error); + kfree(data); + + return ret; +} + +static int __sev_issue_cmd(int fd, int id, void *data, int *error) +{ + struct fd f; + int ret; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = sev_issue_cmd_external_user(f.file, id, data, error); + + fdput(f); + return ret; +} + +static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + + return __sev_issue_cmd(sev->fd, id, data, error); +} + +static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_start *start; + struct kvm_sev_launch_start params; + void *dh_blob, *session_blob; + int *error = &argp->error; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + start = kzalloc(sizeof(*start), GFP_KERNEL); + if (!start) + return -ENOMEM; + + dh_blob = NULL; + if (params.dh_uaddr) { + dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len); + if (IS_ERR(dh_blob)) { + ret = PTR_ERR(dh_blob); + goto e_free; + } + + start->dh_cert_address = __sme_set(__pa(dh_blob)); + start->dh_cert_len = params.dh_len; + } + + session_blob = NULL; + if (params.session_uaddr) { + session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len); + if (IS_ERR(session_blob)) { + ret = PTR_ERR(session_blob); + goto e_free_dh; + } + + start->session_address = __sme_set(__pa(session_blob)); + start->session_len = params.session_len; + } + + start->handle = params.handle; + start->policy = params.policy; + + /* create memory encryption context */ + ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, start, error); + if (ret) + goto e_free_session; + + /* Bind ASID to this guest */ + ret = sev_bind_asid(kvm, start->handle, error); + if (ret) + goto e_free_session; + + /* return handle to userspace */ + params.handle = start->handle; + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { + sev_unbind_asid(kvm, start->handle); + ret = -EFAULT; + goto e_free_session; + } + + sev->handle = start->handle; + sev->fd = argp->sev_fd; + +e_free_session: + kfree(session_blob); +e_free_dh: + kfree(dh_blob); +e_free: + kfree(start); + return ret; +} + +static int get_num_contig_pages(int idx, struct page **inpages, + unsigned long npages) +{ + unsigned long paddr, next_paddr; + int i = idx + 1, pages = 1; + + /* find the number of contiguous pages starting from idx */ + paddr = __sme_page_pa(inpages[idx]); + while (i < npages) { + next_paddr = __sme_page_pa(inpages[i++]); + if ((paddr + PAGE_SIZE) == next_paddr) { + pages++; + paddr = next_paddr; + continue; + } + break; + } + + return pages; +} + +static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + unsigned long vaddr, vaddr_end, next_vaddr, npages, size; + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct kvm_sev_launch_update_data params; + struct sev_data_launch_update_data *data; + struct page **inpages; + int i, ret, pages; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + vaddr = params.uaddr; + size = params.len; + vaddr_end = vaddr + size; + + /* Lock the user memory. */ + inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1); + if (!inpages) { + ret = -ENOMEM; + goto e_free; + } + + /* + * The LAUNCH_UPDATE command will perform in-place encryption of the + * memory content (i.e it will write the same memory region with C=1). + * It's possible that the cache may contain the data with C=0, i.e., + * unencrypted so invalidate it first. + */ + sev_clflush_pages(inpages, npages); + + for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) { + int offset, len; + + /* + * If the user buffer is not page-aligned, calculate the offset + * within the page. + */ + offset = vaddr & (PAGE_SIZE - 1); + + /* Calculate the number of pages that can be encrypted in one go. */ + pages = get_num_contig_pages(i, inpages, npages); + + len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size); + + data->handle = sev->handle; + data->len = len; + data->address = __sme_page_pa(inpages[i]) + offset; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, data, &argp->error); + if (ret) + goto e_unpin; + + size -= len; + next_vaddr = vaddr + len; + } + +e_unpin: + /* content of memory is updated, mark pages dirty */ + for (i = 0; i < npages; i++) { + set_page_dirty_lock(inpages[i]); + mark_page_accessed(inpages[i]); + } + /* unlock the user pages */ + sev_unpin_memory(kvm, inpages, npages); +e_free: + kfree(data); + return ret; +} + +static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_measure *data; + struct kvm_sev_launch_measure params; + void *blob = NULL; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* User wants to query the blob length */ + if (!params.len) + goto cmd; + + if (params.uaddr) { + if (params.len > SEV_FW_BLOB_MAX_SIZE) { + ret = -EINVAL; + goto e_free; + } + + if (!access_ok(VERIFY_WRITE, params.uaddr, params.len)) { + ret = -EFAULT; + goto e_free; + } + + ret = -ENOMEM; + blob = kmalloc(params.len, GFP_KERNEL); + if (!blob) + goto e_free; + + data->address = __psp_pa(blob); + data->len = params.len; + } + +cmd: + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, data, &argp->error); + + /* + * If we query the session length, FW responded with expected data. + */ + if (!params.len) + goto done; + + if (ret) + goto e_free_blob; + + if (blob) { + if (copy_to_user((void __user *)(uintptr_t)params.uaddr, blob, params.len)) + ret = -EFAULT; + } + +done: + params.len = data->len; + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free_blob: + kfree(blob); +e_free: + kfree(data); + return ret; +} + +static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_finish *data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, data, &argp->error); + + kfree(data); + return ret; +} + +static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct kvm_sev_guest_status params; + struct sev_data_guest_status *data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error); + if (ret) + goto e_free; + + params.policy = data->policy; + params.state = data->state; + params.handle = data->handle; + + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free: + kfree(data); + return ret; +} + +static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, + unsigned long dst, int size, + int *error, bool enc) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_dbg *data; + int ret; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->handle = sev->handle; + data->dst_addr = dst; + data->src_addr = src; + data->len = size; + + ret = sev_issue_cmd(kvm, + enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT, + data, error); + kfree(data); + return ret; +} + +static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, + unsigned long dst_paddr, int sz, int *err) +{ + int offset; + + /* + * Its safe to read more than we are asked, caller should ensure that + * destination has enough space. + */ + src_paddr = round_down(src_paddr, 16); + offset = src_paddr & 15; + sz = round_up(sz + offset, 16); + + return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); +} + +static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, + unsigned long __user dst_uaddr, + unsigned long dst_paddr, + int size, int *err) +{ + struct page *tpage = NULL; + int ret, offset; + + /* if inputs are not 16-byte then use intermediate buffer */ + if (!IS_ALIGNED(dst_paddr, 16) || + !IS_ALIGNED(paddr, 16) || + !IS_ALIGNED(size, 16)) { + tpage = (void *)alloc_page(GFP_KERNEL); + if (!tpage) + return -ENOMEM; + + dst_paddr = __sme_page_pa(tpage); + } + + ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err); + if (ret) + goto e_free; + + if (tpage) { + offset = paddr & 15; + if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, + page_address(tpage) + offset, size)) + ret = -EFAULT; + } + +e_free: + if (tpage) + __free_page(tpage); + + return ret; +} + +static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, + unsigned long __user vaddr, + unsigned long dst_paddr, + unsigned long __user dst_vaddr, + int size, int *error) +{ + struct page *src_tpage = NULL; + struct page *dst_tpage = NULL; + int ret, len = size; + + /* If source buffer is not aligned then use an intermediate buffer */ + if (!IS_ALIGNED(vaddr, 16)) { + src_tpage = alloc_page(GFP_KERNEL); + if (!src_tpage) + return -ENOMEM; + + if (copy_from_user(page_address(src_tpage), + (void __user *)(uintptr_t)vaddr, size)) { + __free_page(src_tpage); + return -EFAULT; + } + + paddr = __sme_page_pa(src_tpage); + } + + /* + * If destination buffer or length is not aligned then do read-modify-write: + * - decrypt destination in an intermediate buffer + * - copy the source buffer in an intermediate buffer + * - use the intermediate buffer as source buffer + */ + if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + int dst_offset; + + dst_tpage = alloc_page(GFP_KERNEL); + if (!dst_tpage) { + ret = -ENOMEM; + goto e_free; + } + + ret = __sev_dbg_decrypt(kvm, dst_paddr, + __sme_page_pa(dst_tpage), size, error); + if (ret) + goto e_free; + + /* + * If source is kernel buffer then use memcpy() otherwise + * copy_from_user(). + */ + dst_offset = dst_paddr & 15; + + if (src_tpage) + memcpy(page_address(dst_tpage) + dst_offset, + page_address(src_tpage), size); + else { + if (copy_from_user(page_address(dst_tpage) + dst_offset, + (void __user *)(uintptr_t)vaddr, size)) { + ret = -EFAULT; + goto e_free; + } + } + + paddr = __sme_page_pa(dst_tpage); + dst_paddr = round_down(dst_paddr, 16); + len = round_up(size, 16); + } + + ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true); + +e_free: + if (src_tpage) + __free_page(src_tpage); + if (dst_tpage) + __free_page(dst_tpage); + return ret; +} + +static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) +{ + unsigned long vaddr, vaddr_end, next_vaddr; + unsigned long dst_vaddr, dst_vaddr_end; + struct page **src_p, **dst_p; + struct kvm_sev_dbg debug; + unsigned long n; + int ret, size; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) + return -EFAULT; + + vaddr = debug.src_uaddr; + size = debug.len; + vaddr_end = vaddr + size; + dst_vaddr = debug.dst_uaddr; + dst_vaddr_end = dst_vaddr + size; + + for (; vaddr < vaddr_end; vaddr = next_vaddr) { + int len, s_off, d_off; + + /* lock userspace source and destination page */ + src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0); + if (!src_p) + return -EFAULT; + + dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1); + if (!dst_p) { + sev_unpin_memory(kvm, src_p, n); + return -EFAULT; + } + + /* + * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the + * memory content (i.e it will write the same memory region with C=1). + * It's possible that the cache may contain the data with C=0, i.e., + * unencrypted so invalidate it first. + */ + sev_clflush_pages(src_p, 1); + sev_clflush_pages(dst_p, 1); + + /* + * Since user buffer may not be page aligned, calculate the + * offset within the page. + */ + s_off = vaddr & ~PAGE_MASK; + d_off = dst_vaddr & ~PAGE_MASK; + len = min_t(size_t, (PAGE_SIZE - s_off), size); + + if (dec) + ret = __sev_dbg_decrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + dst_vaddr, + __sme_page_pa(dst_p[0]) + d_off, + len, &argp->error); + else + ret = __sev_dbg_encrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + vaddr, + __sme_page_pa(dst_p[0]) + d_off, + dst_vaddr, + len, &argp->error); + + sev_unpin_memory(kvm, src_p, 1); + sev_unpin_memory(kvm, dst_p, 1); + + if (ret) + goto err; + + next_vaddr = vaddr + len; + dst_vaddr = dst_vaddr + len; + size -= len; + } +err: + return ret; +} + +static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct sev_data_launch_secret *data; + struct kvm_sev_launch_secret params; + struct page **pages; + void *blob, *hdr; + unsigned long n; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1); + if (!pages) + return -ENOMEM; + + /* + * The secret must be copied into contiguous memory region, lets verify + * that userspace memory pages are contiguous before we issue command. + */ + if (get_num_contig_pages(0, pages, n) != n) { + ret = -EINVAL; + goto e_unpin_memory; + } + + ret = -ENOMEM; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto e_unpin_memory; + + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); + if (IS_ERR(blob)) { + ret = PTR_ERR(blob); + goto e_free; + } + + data->trans_address = __psp_pa(blob); + data->trans_len = params.trans_len; + + hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); + if (IS_ERR(hdr)) { + ret = PTR_ERR(hdr); + goto e_free_blob; + } + data->trans_address = __psp_pa(blob); + data->trans_len = params.trans_len; + + data->handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, data, &argp->error); + + kfree(hdr); + +e_free_blob: + kfree(blob); +e_free: + kfree(data); +e_unpin_memory: + sev_unpin_memory(kvm, pages, n); + return ret; +} + +static int svm_mem_enc_op(struct kvm *kvm, void __user *argp) +{ + struct kvm_sev_cmd sev_cmd; + int r; + + if (!svm_sev_enabled()) + return -ENOTTY; + + if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) + return -EFAULT; + + mutex_lock(&kvm->lock); + + switch (sev_cmd.id) { + case KVM_SEV_INIT: + r = sev_guest_init(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_START: + r = sev_launch_start(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_UPDATE_DATA: + r = sev_launch_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_MEASURE: + r = sev_launch_measure(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_FINISH: + r = sev_launch_finish(kvm, &sev_cmd); + break; + case KVM_SEV_GUEST_STATUS: + r = sev_guest_status(kvm, &sev_cmd); + break; + case KVM_SEV_DBG_DECRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, true); + break; + case KVM_SEV_DBG_ENCRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, false); + break; + case KVM_SEV_LAUNCH_SECRET: + r = sev_launch_secret(kvm, &sev_cmd); + break; + default: + r = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) + r = -EFAULT; + +out: + mutex_unlock(&kvm->lock); + return r; +} + +static int svm_register_enc_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct enc_region *region; + int ret = 0; + + if (!sev_guest(kvm)) + return -ENOTTY; + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return -ENOMEM; + + region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); + if (!region->pages) { + ret = -ENOMEM; + goto e_free; + } + + /* + * The guest may change the memory encryption attribute from C=0 -> C=1 + * or vice versa for this memory range. Lets make sure caches are + * flushed to ensure that guest data gets written into memory with + * correct C-bit. + */ + sev_clflush_pages(region->pages, region->npages); + + region->uaddr = range->addr; + region->size = range->size; + + mutex_lock(&kvm->lock); + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + + return ret; + +e_free: + kfree(region); + return ret; +} + +static struct enc_region * +find_enc_region(struct kvm *kvm, struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &kvm->arch.sev_info; + struct list_head *head = &sev->regions_list; + struct enc_region *i; + + list_for_each_entry(i, head, list) { + if (i->uaddr == range->addr && + i->size == range->size) + return i; + } + + return NULL; +} + + +static int svm_unregister_enc_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct enc_region *region; + int ret; + + mutex_lock(&kvm->lock); + + if (!sev_guest(kvm)) { + ret = -ENOTTY; + goto failed; + } + + region = find_enc_region(kvm, range); + if (!region) { + ret = -EINVAL; + goto failed; + } + + __unregister_enc_region_locked(kvm, region); + + mutex_unlock(&kvm->lock); + return 0; + +failed: + mutex_unlock(&kvm->lock); + return ret; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -5653,7 +6812,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .vcpu_reset = svm_vcpu_reset, .vm_init = avic_vm_init, - .vm_destroy = avic_vm_destroy, + .vm_destroy = svm_vm_destroy, .prepare_guest_switch = svm_prepare_guest_switch, .vcpu_load = svm_vcpu_load, @@ -5713,6 +6872,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_irr_update = svm_hwapic_irr_update, .hwapic_isr_update = svm_hwapic_isr_update, + .sync_pir_to_irr = kvm_lapic_find_highest_irr, .apicv_post_state_restore = avic_post_state_restore, .set_tss_addr = svm_set_tss_addr, @@ -5729,6 +6889,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .invpcid_supported = svm_invpcid_supported, .mpx_supported = svm_mpx_supported, .xsaves_supported = svm_xsaves_supported, + .umip_emulated = svm_umip_emulated, .set_supported_cpuid = svm_set_supported_cpuid, @@ -5752,6 +6913,10 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .pre_enter_smm = svm_pre_enter_smm, .pre_leave_smm = svm_pre_leave_smm, .enable_smi_window = enable_smi_window, + + .mem_enc_op = svm_mem_enc_op, + .mem_enc_reg_region = svm_register_enc_region, + .mem_enc_unreg_region = svm_unregister_enc_region, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index bee4c49f6dd0..f427723dc7db 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -419,6 +419,12 @@ struct __packed vmcs12 { #define VMCS12_SIZE 0x1000 /* + * VMCS12_MAX_FIELD_INDEX is the highest index value used in any + * supported VMCS12 field encoding. + */ +#define VMCS12_MAX_FIELD_INDEX 0x17 + +/* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. */ @@ -441,6 +447,7 @@ struct nested_vmx { * data hold by vmcs12 */ bool sync_shadow_vmcs; + bool dirty_vmcs12; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ @@ -664,6 +671,8 @@ struct vcpu_vmx { u32 host_pkru; + unsigned long host_debugctlmsr; + /* * Only bits masked by msr_ia32_feature_control_valid_bits can be set in * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included @@ -692,67 +701,24 @@ static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) return &(to_vmx(vcpu)->pi_desc); } +#define ROL16(val, n) ((u16)(((u16)(val) << (n)) | ((u16)(val) >> (16 - (n))))) #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x) -#define FIELD(number, name) [number] = VMCS12_OFFSET(name) -#define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ - [number##_HIGH] = VMCS12_OFFSET(name)+4 +#define FIELD(number, name) [ROL16(number, 6)] = VMCS12_OFFSET(name) +#define FIELD64(number, name) \ + FIELD(number, name), \ + [ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32) -static unsigned long shadow_read_only_fields[] = { - /* - * We do NOT shadow fields that are modified when L0 - * traps and emulates any vmx instruction (e.g. VMPTRLD, - * VMXON...) executed by L1. - * For example, VM_INSTRUCTION_ERROR is read - * by L1 if a vmx instruction fails (part of the error path). - * Note the code assumes this logic. If for some reason - * we start shadowing these fields then we need to - * force a shadow sync when L0 emulates vmx instructions - * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified - * by nested_vmx_failValid) - */ - VM_EXIT_REASON, - VM_EXIT_INTR_INFO, - VM_EXIT_INSTRUCTION_LEN, - IDT_VECTORING_INFO_FIELD, - IDT_VECTORING_ERROR_CODE, - VM_EXIT_INTR_ERROR_CODE, - EXIT_QUALIFICATION, - GUEST_LINEAR_ADDRESS, - GUEST_PHYSICAL_ADDRESS +static u16 shadow_read_only_fields[] = { +#define SHADOW_FIELD_RO(x) x, +#include "vmx_shadow_fields.h" }; static int max_shadow_read_only_fields = ARRAY_SIZE(shadow_read_only_fields); -static unsigned long shadow_read_write_fields[] = { - TPR_THRESHOLD, - GUEST_RIP, - GUEST_RSP, - GUEST_CR0, - GUEST_CR3, - GUEST_CR4, - GUEST_INTERRUPTIBILITY_INFO, - GUEST_RFLAGS, - GUEST_CS_SELECTOR, - GUEST_CS_AR_BYTES, - GUEST_CS_LIMIT, - GUEST_CS_BASE, - GUEST_ES_BASE, - GUEST_BNDCFGS, - CR0_GUEST_HOST_MASK, - CR0_READ_SHADOW, - CR4_READ_SHADOW, - TSC_OFFSET, - EXCEPTION_BITMAP, - CPU_BASED_VM_EXEC_CONTROL, - VM_ENTRY_EXCEPTION_ERROR_CODE, - VM_ENTRY_INTR_INFO_FIELD, - VM_ENTRY_INSTRUCTION_LEN, - VM_ENTRY_EXCEPTION_ERROR_CODE, - HOST_FS_BASE, - HOST_GS_BASE, - HOST_FS_SELECTOR, - HOST_GS_SELECTOR +static u16 shadow_read_write_fields[] = { +#define SHADOW_FIELD_RW(x) x, +#include "vmx_shadow_fields.h" }; static int max_shadow_read_write_fields = ARRAY_SIZE(shadow_read_write_fields); @@ -905,13 +871,17 @@ static inline short vmcs_field_to_offset(unsigned long field) { const size_t size = ARRAY_SIZE(vmcs_field_to_offset_table); unsigned short offset; + unsigned index; + + if (field >> 15) + return -ENOENT; - BUILD_BUG_ON(size > SHRT_MAX); - if (field >= size) + index = ROL16(field, 6); + if (index >= size) return -ENOENT; - field = array_index_nospec(field, size); - offset = vmcs_field_to_offset_table[field]; + index = array_index_nospec(index, size); + offset = vmcs_field_to_offset_table[index]; if (offset == 0) return -ENOENT; return offset; @@ -957,8 +927,6 @@ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); enum { - VMX_IO_BITMAP_A, - VMX_IO_BITMAP_B, VMX_VMREAD_BITMAP, VMX_VMWRITE_BITMAP, VMX_BITMAP_NR @@ -966,8 +934,6 @@ enum { static unsigned long *vmx_bitmap[VMX_BITMAP_NR]; -#define vmx_io_bitmap_a (vmx_bitmap[VMX_IO_BITMAP_A]) -#define vmx_io_bitmap_b (vmx_bitmap[VMX_IO_BITMAP_B]) #define vmx_vmread_bitmap (vmx_bitmap[VMX_VMREAD_BITMAP]) #define vmx_vmwrite_bitmap (vmx_bitmap[VMX_VMWRITE_BITMAP]) @@ -2373,6 +2339,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vmx_vcpu_pi_load(vcpu, cpu); vmx->host_pkru = read_pkru(); + vmx->host_debugctlmsr = get_debugctlmsr(); } static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) @@ -2930,7 +2897,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) rdmsrl(MSR_IA32_VMX_CR4_FIXED1, vmx->nested.nested_vmx_cr4_fixed1); /* highest index: VMX_PREEMPTION_TIMER_VALUE */ - vmx->nested.nested_vmx_vmcs_enum = 0x2e; + vmx->nested.nested_vmx_vmcs_enum = VMCS12_MAX_FIELD_INDEX << 1; } /* @@ -3266,6 +3233,7 @@ static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, */ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { + struct vcpu_vmx *vmx = to_vmx(vcpu); struct shared_msr_entry *msr; switch (msr_info->index) { @@ -3277,8 +3245,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: - vmx_load_host_state(to_vmx(vcpu)); - msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + vmx_load_host_state(vmx); + msr_info->data = vmx->msr_guest_kernel_gs_base; break; #endif case MSR_EFER: @@ -3318,13 +3286,13 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_MCG_EXT_CTL: if (!msr_info->host_initiated && - !(to_vmx(vcpu)->msr_ia32_feature_control & + !(vmx->msr_ia32_feature_control & FEATURE_CONTROL_LMCE)) return 1; msr_info->data = vcpu->arch.mcg_ext_ctl; break; case MSR_IA32_FEATURE_CONTROL: - msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control; + msr_info->data = vmx->msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) @@ -3341,7 +3309,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; /* Otherwise falls through */ default: - msr = find_msr_entry(to_vmx(vcpu), msr_info->index); + msr = find_msr_entry(vmx, msr_info->index); if (msr) { msr_info->data = msr->data; break; @@ -3727,7 +3695,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) #endif CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING | - CPU_BASED_USE_IO_BITMAPS | + CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_MOV_DR_EXITING | CPU_BASED_USE_TSC_OFFSETING | CPU_BASED_INVLPG_EXITING | @@ -3757,6 +3725,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_ENABLE_EPT | SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_PAUSE_LOOP_EXITING | + SECONDARY_EXEC_DESC | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_APIC_REGISTER_VIRT | @@ -3982,17 +3951,17 @@ static void free_kvm_area(void) } } -enum vmcs_field_type { - VMCS_FIELD_TYPE_U16 = 0, - VMCS_FIELD_TYPE_U64 = 1, - VMCS_FIELD_TYPE_U32 = 2, - VMCS_FIELD_TYPE_NATURAL_WIDTH = 3 +enum vmcs_field_width { + VMCS_FIELD_WIDTH_U16 = 0, + VMCS_FIELD_WIDTH_U64 = 1, + VMCS_FIELD_WIDTH_U32 = 2, + VMCS_FIELD_WIDTH_NATURAL_WIDTH = 3 }; -static inline int vmcs_field_type(unsigned long field) +static inline int vmcs_field_width(unsigned long field) { if (0x1 & field) /* the *_HIGH fields are all 32 bit */ - return VMCS_FIELD_TYPE_U32; + return VMCS_FIELD_WIDTH_U32; return (field >> 13) & 0x3 ; } @@ -4005,43 +3974,66 @@ static void init_vmcs_shadow_fields(void) { int i, j; - /* No checks for read only fields yet */ + for (i = j = 0; i < max_shadow_read_only_fields; i++) { + u16 field = shadow_read_only_fields[i]; + if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && + (i + 1 == max_shadow_read_only_fields || + shadow_read_only_fields[i + 1] != field + 1)) + pr_err("Missing field from shadow_read_only_field %x\n", + field + 1); + + clear_bit(field, vmx_vmread_bitmap); +#ifdef CONFIG_X86_64 + if (field & 1) + continue; +#endif + if (j < i) + shadow_read_only_fields[j] = field; + j++; + } + max_shadow_read_only_fields = j; for (i = j = 0; i < max_shadow_read_write_fields; i++) { - switch (shadow_read_write_fields[i]) { - case GUEST_BNDCFGS: - if (!kvm_mpx_supported()) + u16 field = shadow_read_write_fields[i]; + if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 && + (i + 1 == max_shadow_read_write_fields || + shadow_read_write_fields[i + 1] != field + 1)) + pr_err("Missing field from shadow_read_write_field %x\n", + field + 1); + + /* + * PML and the preemption timer can be emulated, but the + * processor cannot vmwrite to fields that don't exist + * on bare metal. + */ + switch (field) { + case GUEST_PML_INDEX: + if (!cpu_has_vmx_pml()) + continue; + break; + case VMX_PREEMPTION_TIMER_VALUE: + if (!cpu_has_vmx_preemption_timer()) + continue; + break; + case GUEST_INTR_STATUS: + if (!cpu_has_vmx_apicv()) continue; break; default: break; } + clear_bit(field, vmx_vmwrite_bitmap); + clear_bit(field, vmx_vmread_bitmap); +#ifdef CONFIG_X86_64 + if (field & 1) + continue; +#endif if (j < i) - shadow_read_write_fields[j] = - shadow_read_write_fields[i]; + shadow_read_write_fields[j] = field; j++; } max_shadow_read_write_fields = j; - - /* shadowed fields guest access without vmexit */ - for (i = 0; i < max_shadow_read_write_fields; i++) { - unsigned long field = shadow_read_write_fields[i]; - - clear_bit(field, vmx_vmwrite_bitmap); - clear_bit(field, vmx_vmread_bitmap); - if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) { - clear_bit(field + 1, vmx_vmwrite_bitmap); - clear_bit(field + 1, vmx_vmread_bitmap); - } - } - for (i = 0; i < max_shadow_read_only_fields; i++) { - unsigned long field = shadow_read_only_fields[i]; - - clear_bit(field, vmx_vmread_bitmap); - if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) - clear_bit(field + 1, vmx_vmread_bitmap); - } } static __init int alloc_kvm_area(void) @@ -4254,9 +4246,10 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) +static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid, + bool invalidate_gpa) { - if (enable_ept) { + if (enable_ept && (invalidate_gpa || !enable_vpid)) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa)); @@ -4265,15 +4258,15 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) } } -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) { - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa); } static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu) { if (enable_ept) - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) @@ -4471,7 +4464,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) ept_load_pdptrs(vcpu); } - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); vmcs_writel(GUEST_CR3, guest_cr3); } @@ -4488,6 +4481,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) (to_vmx(vcpu)->rmode.vm86_active ? KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); + if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_DESC); + hw_cr4 &= ~X86_CR4_UMIP; + } else + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_DESC); + if (cr4 & X86_CR4_VMXE) { /* * To use VMXON (and later other VMX instructions), a guest @@ -5119,11 +5120,6 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, { int f = sizeof(unsigned long); - if (!cpu_has_vmx_msr_bitmap()) { - WARN_ON(1); - return; - } - /* * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals * have the write-low and read-high bitmap offsets the wrong way round. @@ -5263,7 +5259,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); if (max_irr != 256) { vapic_page = kmap(vmx->nested.virtual_apic_page); - __kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page); + __kvm_apic_update_irr(vmx->nested.pi_desc->pir, + vapic_page, &max_irr); kunmap(vmx->nested.virtual_apic_page); status = vmcs_read16(GUEST_INTR_STATUS); @@ -5323,14 +5320,15 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { - /* the PIR and ON have been set by L1. */ - kvm_vcpu_trigger_posted_interrupt(vcpu, true); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. */ vmx->nested.pi_pending = true; kvm_make_request(KVM_REQ_EVENT, vcpu); + /* the PIR and ON have been set by L1. */ + if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true)) + kvm_vcpu_kick(vcpu); return 0; } return -1; @@ -5509,6 +5507,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) struct kvm_vcpu *vcpu = &vmx->vcpu; u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; + if (!cpu_need_virtualize_apic_accesses(vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) @@ -5527,6 +5526,11 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + + /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, + * in vmx_set_cr4. */ + exec_control &= ~SECONDARY_EXEC_DESC; + /* SECONDARY_EXEC_SHADOW_VMCS is enabled when L1 executes VMPTRLD (handle_vmptrld). We can NOT enable shadow_vmcs here because we don't have yet @@ -5646,10 +5650,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) #endif int i; - /* I/O */ - vmcs_write64(IO_BITMAP_A, __pa(vmx_io_bitmap_a)); - vmcs_write64(IO_BITMAP_B, __pa(vmx_io_bitmap_b)); - if (enable_shadow_vmcs) { vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap)); vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap)); @@ -6304,6 +6304,12 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) return kvm_set_cr4(vcpu, val); } +static int handle_desc(struct kvm_vcpu *vcpu) +{ + WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); + return emulate_instruction(vcpu, 0) == EMULATE_DONE; +} + static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; @@ -6760,7 +6766,21 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu) && !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { trace_kvm_fast_mmio(gpa); - return kvm_skip_emulated_instruction(vcpu); + /* + * Doing kvm_skip_emulated_instruction() depends on undefined + * behavior: Intel's manual doesn't mandate + * VM_EXIT_INSTRUCTION_LEN to be set in VMCS when EPT MISCONFIG + * occurs and while on real hardware it was observed to be set, + * other hypervisors (namely Hyper-V) don't set it, we end up + * advancing IP with some random value. Disable fast mmio when + * running nested and keep it for real hardware in hope that + * VM_EXIT_INSTRUCTION_LEN will always be set correctly. + */ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + return kvm_skip_emulated_instruction(vcpu); + else + return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP, + NULL, 0) == EMULATE_DONE; } ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -6957,10 +6977,6 @@ static __init int hardware_setup(void) memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE); memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE); - memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE); - - memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE); - if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; goto out; @@ -6973,11 +6989,6 @@ static __init int hardware_setup(void) !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; - if (!cpu_has_vmx_shadow_vmcs()) - enable_shadow_vmcs = 0; - if (enable_shadow_vmcs) - init_vmcs_shadow_fields(); - if (!cpu_has_vmx_ept() || !cpu_has_vmx_ept_4levels() || !cpu_has_vmx_ept_mt_wb() || @@ -7063,6 +7074,11 @@ static __init int hardware_setup(void) kvm_x86_ops->cancel_hv_timer = NULL; } + if (!cpu_has_vmx_shadow_vmcs()) + enable_shadow_vmcs = 0; + if (enable_shadow_vmcs) + init_vmcs_shadow_fields(); + kvm_set_posted_intr_wakeup_handler(wakeup_handler); kvm_mce_cap_supported |= MCG_LMCE_P; @@ -7593,17 +7609,17 @@ static inline int vmcs12_read_any(struct kvm_vcpu *vcpu, p = ((char *)(get_vmcs12(vcpu))) + offset; - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_NATURAL_WIDTH: + switch (vmcs_field_width(field)) { + case VMCS_FIELD_WIDTH_NATURAL_WIDTH: *ret = *((natural_width *)p); return 0; - case VMCS_FIELD_TYPE_U16: + case VMCS_FIELD_WIDTH_U16: *ret = *((u16 *)p); return 0; - case VMCS_FIELD_TYPE_U32: + case VMCS_FIELD_WIDTH_U32: *ret = *((u32 *)p); return 0; - case VMCS_FIELD_TYPE_U64: + case VMCS_FIELD_WIDTH_U64: *ret = *((u64 *)p); return 0; default: @@ -7620,17 +7636,17 @@ static inline int vmcs12_write_any(struct kvm_vcpu *vcpu, if (offset < 0) return offset; - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: + switch (vmcs_field_width(field)) { + case VMCS_FIELD_WIDTH_U16: *(u16 *)p = field_value; return 0; - case VMCS_FIELD_TYPE_U32: + case VMCS_FIELD_WIDTH_U32: *(u32 *)p = field_value; return 0; - case VMCS_FIELD_TYPE_U64: + case VMCS_FIELD_WIDTH_U64: *(u64 *)p = field_value; return 0; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: + case VMCS_FIELD_WIDTH_NATURAL_WIDTH: *(natural_width *)p = field_value; return 0; default: @@ -7646,7 +7662,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) unsigned long field; u64 field_value; struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; - const unsigned long *fields = shadow_read_write_fields; + const u16 *fields = shadow_read_write_fields; const int num_fields = max_shadow_read_write_fields; preempt_disable(); @@ -7655,23 +7671,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) for (i = 0; i < num_fields; i++) { field = fields[i]; - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: - field_value = vmcs_read16(field); - break; - case VMCS_FIELD_TYPE_U32: - field_value = vmcs_read32(field); - break; - case VMCS_FIELD_TYPE_U64: - field_value = vmcs_read64(field); - break; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: - field_value = vmcs_readl(field); - break; - default: - WARN_ON(1); - continue; - } + field_value = __vmcs_readl(field); vmcs12_write_any(&vmx->vcpu, field, field_value); } @@ -7683,7 +7683,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) { - const unsigned long *fields[] = { + const u16 *fields[] = { shadow_read_write_fields, shadow_read_only_fields }; @@ -7702,24 +7702,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) for (i = 0; i < max_fields[q]; i++) { field = fields[q][i]; vmcs12_read_any(&vmx->vcpu, field, &field_value); - - switch (vmcs_field_type(field)) { - case VMCS_FIELD_TYPE_U16: - vmcs_write16(field, (u16)field_value); - break; - case VMCS_FIELD_TYPE_U32: - vmcs_write32(field, (u32)field_value); - break; - case VMCS_FIELD_TYPE_U64: - vmcs_write64(field, (u64)field_value); - break; - case VMCS_FIELD_TYPE_NATURAL_WIDTH: - vmcs_writel(field, (long)field_value); - break; - default: - WARN_ON(1); - break; - } + __vmcs_writel(field, field_value); } } @@ -7788,8 +7771,10 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) { unsigned long field; gva_t gva; + struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + /* The value to write might be 32 or 64 bits, depending on L1's long * mode, and eventually we need to write that into a field of several * possible lengths. The code below first zero-extends the value to 64 @@ -7832,6 +7817,20 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } + switch (field) { +#define SHADOW_FIELD_RW(x) case x: +#include "vmx_shadow_fields.h" + /* + * The fields that can be updated by L1 without a vmexit are + * always updated in the vmcs02, the others go down the slow + * path of prepare_vmcs02. + */ + break; + default: + vmx->nested.dirty_vmcs12 = true; + break; + } + nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); } @@ -7846,6 +7845,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr) __pa(vmx->vmcs01.shadow_vmcs)); vmx->nested.sync_shadow_vmcs = true; } + vmx->nested.dirty_vmcs12 = true; } /* Emulate the VMPTRLD instruction */ @@ -8066,7 +8066,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } - __vmx_flush_tlb(vcpu, vmx->nested.vpid02); + __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); @@ -8260,6 +8260,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_XSETBV] = handle_xsetbv, [EXIT_REASON_TASK_SWITCH] = handle_task_switch, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, + [EXIT_REASON_GDTR_IDTR] = handle_desc, + [EXIT_REASON_LDTR_TR] = handle_desc, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, @@ -9069,36 +9071,23 @@ static void vmx_set_rvi(int vector) static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) { - if (!is_guest_mode(vcpu)) { - vmx_set_rvi(max_irr); - return; - } - - if (max_irr == -1) - return; - - /* - * In guest mode. If a vmexit is needed, vmx_check_nested_events - * handles it. - */ - if (nested_exit_on_intr(vcpu)) - return; - /* - * Else, fall back to pre-APICv interrupt injection since L2 - * is run without virtual interrupt delivery. + * When running L2, updating RVI is only relevant when + * vmcs12 virtual-interrupt-delivery enabled. + * However, it can be enabled only when L1 also + * intercepts external-interrupts and in that case + * we should not update vmcs02 RVI but instead intercept + * interrupt. Therefore, do nothing when running L2. */ - if (!kvm_event_needs_reinjection(vcpu) && - vmx_interrupt_allowed(vcpu)) { - kvm_queue_interrupt(vcpu, max_irr, false); - vmx_inject_irq(vcpu); - } + if (!is_guest_mode(vcpu)) + vmx_set_rvi(max_irr); } static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); int max_irr; + bool max_irr_updated; WARN_ON(!vcpu->arch.apicv_active); if (pi_test_on(&vmx->pi_desc)) { @@ -9108,7 +9097,23 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); - max_irr = kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); + max_irr_updated = + kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr); + + /* + * If we are running L2 and L1 has a new pending interrupt + * which can be injected, we should re-evaluate + * what should be done with this new L1 interrupt. + * If L1 intercepts external-interrupts, we should + * exit from L2 to L1. Otherwise, interrupt should be + * delivered directly to L2. + */ + if (is_guest_mode(vcpu) && max_irr_updated) { + if (nested_exit_on_intr(vcpu)) + kvm_vcpu_exiting_guest_mode(vcpu); + else + kvm_make_request(KVM_REQ_EVENT, vcpu); + } } else { max_irr = kvm_lapic_find_highest_irr(vcpu); } @@ -9223,6 +9228,12 @@ static bool vmx_xsaves_supported(void) SECONDARY_EXEC_XSAVES; } +static bool vmx_umip_emulated(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_DESC; +} + static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -9378,7 +9389,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr, cr3, cr4; + unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -9431,7 +9442,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vcpu->arch.pkru); atomic_switch_perf_msrs(vmx); - debugctlmsr = get_debugctlmsr(); vmx_arm_hv_timer(vcpu); @@ -9587,8 +9597,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmexit_fill_RSB(); /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ - if (debugctlmsr) - update_debugctlmsr(debugctlmsr); + if (vmx->host_debugctlmsr) + update_debugctlmsr(vmx->host_debugctlmsr); #ifndef CONFIG_X86_64 /* @@ -9668,10 +9678,8 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int r; - r = vcpu_load(vcpu); - BUG_ON(r); + vcpu_load(vcpu); vmx_switch_vmcs(vcpu, &vmx->vmcs01); free_nested(vmx); vcpu_put(vcpu); @@ -9871,7 +9879,8 @@ static void vmcs_set_secondary_exec_control(u32 new_ctl) u32 mask = SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_DESC; u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); @@ -10037,8 +10046,8 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu, } } -static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12); +static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12); static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) @@ -10127,11 +10136,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, (unsigned long)(vmcs12->posted_intr_desc_addr & (PAGE_SIZE - 1))); } - if (cpu_has_vmx_msr_bitmap() && - nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS) && - nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) - ; - else + if (!nested_vmx_prepare_msr_bitmap(vcpu, vmcs12)) vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_USE_MSR_BITMAPS); } @@ -10199,8 +10204,8 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. */ -static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, - struct vmcs12 *vmcs12) +static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) { int msr; struct page *page; @@ -10222,6 +10227,11 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, bool pred_cmd = msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD); bool spec_ctrl = msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL); + /* Nothing to do if the MSR bitmap is not in use. */ + if (!cpu_has_vmx_msr_bitmap() || + !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) + return false; + if (!nested_cpu_has_virt_x2apic_mode(vmcs12) && !pred_cmd && !spec_ctrl) return false; @@ -10229,32 +10239,41 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap); if (is_error_page(page)) return false; - msr_bitmap_l1 = (unsigned long *)kmap(page); - memset(msr_bitmap_l0, 0xff, PAGE_SIZE); + msr_bitmap_l1 = (unsigned long *)kmap(page); + if (nested_cpu_has_apic_reg_virt(vmcs12)) { + /* + * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it + * just lets the processor take the value from the virtual-APIC page; + * take those 256 bits directly from the L1 bitmap. + */ + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap_l0[word] = msr_bitmap_l1[word]; + msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; + } + } else { + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + msr_bitmap_l0[word] = ~0; + msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; + } + } - if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { - if (nested_cpu_has_apic_reg_virt(vmcs12)) - for (msr = 0x800; msr <= 0x8ff; msr++) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - msr, MSR_TYPE_R); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_TASKPRI), + MSR_TYPE_W); + if (nested_cpu_has_vid(vmcs12)) { nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - APIC_BASE_MSR + (APIC_TASKPRI >> 4), - MSR_TYPE_R | MSR_TYPE_W); - - if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - APIC_BASE_MSR + (APIC_EOI >> 4), - MSR_TYPE_W); - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - APIC_BASE_MSR + (APIC_SELF_IPI >> 4), - MSR_TYPE_W); - } + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_EOI), + MSR_TYPE_W); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_SELF_IPI), + MSR_TYPE_W); } if (spec_ctrl) @@ -10534,25 +10553,12 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne return 0; } -/* - * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested - * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it - * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2 - * guest in a way that will both be appropriate to L1's requests, and our - * needs. In addition to modifying the active vmcs (which is vmcs02), this - * function also has additional necessary side-effects, like setting various - * vcpu->arch fields. - * Returns 0 on success, 1 on failure. Invalid state exit qualification code - * is assigned to entry_failure_code on failure. - */ -static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - bool from_vmentry, u32 *entry_failure_code) +static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exec_control, vmcs12_exec_ctrl; vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); - vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector); vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector); vmcs_write16(GUEST_FS_SELECTOR, vmcs12->guest_fs_selector); @@ -10560,7 +10566,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write16(GUEST_LDTR_SELECTOR, vmcs12->guest_ldtr_selector); vmcs_write16(GUEST_TR_SELECTOR, vmcs12->guest_tr_selector); vmcs_write32(GUEST_ES_LIMIT, vmcs12->guest_es_limit); - vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit); vmcs_write32(GUEST_SS_LIMIT, vmcs12->guest_ss_limit); vmcs_write32(GUEST_DS_LIMIT, vmcs12->guest_ds_limit); vmcs_write32(GUEST_FS_LIMIT, vmcs12->guest_fs_limit); @@ -10570,15 +10575,12 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write32(GUEST_GDTR_LIMIT, vmcs12->guest_gdtr_limit); vmcs_write32(GUEST_IDTR_LIMIT, vmcs12->guest_idtr_limit); vmcs_write32(GUEST_ES_AR_BYTES, vmcs12->guest_es_ar_bytes); - vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes); vmcs_write32(GUEST_SS_AR_BYTES, vmcs12->guest_ss_ar_bytes); vmcs_write32(GUEST_DS_AR_BYTES, vmcs12->guest_ds_ar_bytes); vmcs_write32(GUEST_FS_AR_BYTES, vmcs12->guest_fs_ar_bytes); vmcs_write32(GUEST_GS_AR_BYTES, vmcs12->guest_gs_ar_bytes); vmcs_write32(GUEST_LDTR_AR_BYTES, vmcs12->guest_ldtr_ar_bytes); vmcs_write32(GUEST_TR_AR_BYTES, vmcs12->guest_tr_ar_bytes); - vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base); - vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base); vmcs_writel(GUEST_SS_BASE, vmcs12->guest_ss_base); vmcs_writel(GUEST_DS_BASE, vmcs12->guest_ds_base); vmcs_writel(GUEST_FS_BASE, vmcs12->guest_fs_base); @@ -10588,6 +10590,125 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); + vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vmcs12->guest_pending_dbg_exceptions); + vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp); + vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip); + + if (nested_cpu_has_xsaves(vmcs12)) + vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap); + vmcs_write64(VMCS_LINK_POINTER, -1ull); + + if (cpu_has_vmx_posted_intr()) + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR); + + /* + * Whether page-faults are trapped is determined by a combination of + * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. + * If enable_ept, L0 doesn't care about page faults and we should + * set all of these to L1's desires. However, if !enable_ept, L0 does + * care about (at least some) page faults, and because it is not easy + * (if at all possible?) to merge L0 and L1's desires, we simply ask + * to exit on each and every L2 page fault. This is done by setting + * MASK=MATCH=0 and (see below) EB.PF=1. + * Note that below we don't need special code to set EB.PF beyond the + * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, + * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when + * !enable_ept, EB.PF is 1, so the "or" will always be 1. + */ + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, + enable_ept ? vmcs12->page_fault_error_code_mask : 0); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, + enable_ept ? vmcs12->page_fault_error_code_match : 0); + + /* All VMFUNCs are currently emulated through L0 vmexits. */ + if (cpu_has_vmx_vmfunc()) + vmcs_write64(VM_FUNCTION_CONTROL, 0); + + if (cpu_has_vmx_apicv()) { + vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0); + vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1); + vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2); + vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3); + } + + /* + * Set host-state according to L0's settings (vmcs12 is irrelevant here) + * Some constant fields are set here by vmx_set_constant_host_state(). + * Other fields are different per CPU, and will be set later when + * vmx_vcpu_load() is called, and when vmx_save_host_state() is called. + */ + vmx_set_constant_host_state(vmx); + + /* + * Set the MSR load/store lists to match L0's settings. + */ + vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); + vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); + vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); + vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); + vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); + + set_cr4_guest_host_mask(vmx); + + if (vmx_mpx_supported()) + vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); + + if (enable_vpid) { + if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); + else + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + } + + /* + * L1 may access the L2's PDPTR, so save them to construct vmcs12 + */ + if (enable_ept) { + vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); + vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); + vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); + vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); + } + + if (cpu_has_vmx_msr_bitmap()) + vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); +} + +/* + * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested + * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it + * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2 + * guest in a way that will both be appropriate to L1's requests, and our + * needs. In addition to modifying the active vmcs (which is vmcs02), this + * function also has additional necessary side-effects, like setting various + * vcpu->arch fields. + * Returns 0 on success, 1 on failure. Invalid state exit qualification code + * is assigned to entry_failure_code on failure. + */ +static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, + bool from_vmentry, u32 *entry_failure_code) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 exec_control, vmcs12_exec_ctrl; + + /* + * First, the fields that are shadowed. This must be kept in sync + * with vmx_shadow_fields.h. + */ + + vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); + vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit); + vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes); + vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base); + vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base); + + /* + * Not in vmcs02: GUEST_PML_INDEX, HOST_FS_SELECTOR, HOST_GS_SELECTOR, + * HOST_FS_BASE, HOST_GS_BASE. + */ + if (from_vmentry && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); @@ -10610,16 +10731,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } else { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); } - vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); vmx_set_rflags(vcpu, vmcs12->guest_rflags); - vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, - vmcs12->guest_pending_dbg_exceptions); - vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp); - vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip); - - if (nested_cpu_has_xsaves(vmcs12)) - vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap); - vmcs_write64(VMCS_LINK_POINTER, -1ull); exec_control = vmcs12->pin_based_vm_exec_control; @@ -10633,7 +10745,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_NESTED_VECTOR); } else { exec_control &= ~PIN_BASED_POSTED_INTR; } @@ -10644,25 +10755,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_preemption_timer(vmcs12)) vmx_start_preemption_timer(vcpu); - /* - * Whether page-faults are trapped is determined by a combination of - * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. - * If enable_ept, L0 doesn't care about page faults and we should - * set all of these to L1's desires. However, if !enable_ept, L0 does - * care about (at least some) page faults, and because it is not easy - * (if at all possible?) to merge L0 and L1's desires, we simply ask - * to exit on each and every L2 page fault. This is done by setting - * MASK=MATCH=0 and (see below) EB.PF=1. - * Note that below we don't need special code to set EB.PF beyond the - * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept, - * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when - * !enable_ept, EB.PF is 1, so the "or" will always be 1. - */ - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, - enable_ept ? vmcs12->page_fault_error_code_mask : 0); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, - enable_ept ? vmcs12->page_fault_error_code_match : 0); - if (cpu_has_secondary_exec_ctrls()) { exec_control = vmx->secondary_exec_control; @@ -10681,22 +10773,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control |= vmcs12_exec_ctrl; } - /* All VMFUNCs are currently emulated through L0 vmexits. */ - if (exec_control & SECONDARY_EXEC_ENABLE_VMFUNC) - vmcs_write64(VM_FUNCTION_CONTROL, 0); - - if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) { - vmcs_write64(EOI_EXIT_BITMAP0, - vmcs12->eoi_exit_bitmap0); - vmcs_write64(EOI_EXIT_BITMAP1, - vmcs12->eoi_exit_bitmap1); - vmcs_write64(EOI_EXIT_BITMAP2, - vmcs12->eoi_exit_bitmap2); - vmcs_write64(EOI_EXIT_BITMAP3, - vmcs12->eoi_exit_bitmap3); + if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) vmcs_write16(GUEST_INTR_STATUS, vmcs12->guest_intr_status); - } /* * Write an illegal value to APIC_ACCESS_ADDR. Later, @@ -10709,24 +10788,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } - - /* - * Set host-state according to L0's settings (vmcs12 is irrelevant here) - * Some constant fields are set here by vmx_set_constant_host_state(). - * Other fields are different per CPU, and will be set later when - * vmx_vcpu_load() is called, and when vmx_save_host_state() is called. - */ - vmx_set_constant_host_state(vmx); - - /* - * Set the MSR load/store lists to match L0's settings. - */ - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host)); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr); - vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); - /* * HOST_RSP is normally set correctly in vmx_vcpu_run() just before * entry, but only if the current (host) sp changed from the value @@ -10758,8 +10819,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } /* - * Merging of IO bitmap not currently supported. - * Rather, exit every time. + * A vmexit (to either L1 hypervisor or L0 userspace) is always needed + * for I/O port accesses. */ exec_control &= ~CPU_BASED_USE_IO_BITMAPS; exec_control |= CPU_BASED_UNCOND_IO_EXITING; @@ -10796,12 +10857,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); } - set_cr4_guest_host_mask(vmx); - - if (from_vmentry && - vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) - vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs); - if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset + vmcs12->tsc_offset); @@ -10810,9 +10865,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); - if (cpu_has_vmx_msr_bitmap()) - vmcs_write64(MSR_BITMAP, __pa(vmx->nested.vmcs02.msr_bitmap)); - if (enable_vpid) { /* * There is no direct mapping between vpid02 and vpid12, the @@ -10823,16 +10875,13 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * even if spawn a lot of nested vCPUs. */ if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) { - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true); } } else { - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } - } if (enable_pml) { @@ -10881,6 +10930,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, /* Note: modifies VM_ENTRY/EXIT_CONTROLS and GUEST/HOST_IA32_EFER */ vmx_set_efer(vcpu, vcpu->arch.efer); + if (vmx->nested.dirty_vmcs12) { + prepare_vmcs02_full(vcpu, vmcs12, from_vmentry); + vmx->nested.dirty_vmcs12 = false; + } + /* Shadow page tables on either EPT or shadow page tables. */ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), entry_failure_code)) @@ -10889,16 +10943,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; - /* - * L1 may access the L2's PDPTR, so save them to construct vmcs12 - */ - if (enable_ept) { - vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); - vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); - vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); - vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); - } - kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp); kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip); return 0; @@ -11254,7 +11298,6 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); - vcpu->arch.exception.pending = false; return 0; } @@ -11535,11 +11578,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * L1's vpid. TODO: move to a more elaborate solution, giving * each L2 its own vpid and exposing the vpid feature to L1. */ - vmx_flush_tlb(vcpu); + vmx_flush_tlb(vcpu, true); } - /* Restore posted intr vector. */ - if (nested_cpu_has_posted_intr(vmcs12)) - vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp); @@ -11800,6 +11840,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt; + + /* + * RDPID causes #UD if disabled through secondary execution controls. + * Because it is marked as EmulateOnUD, we need to intercept it here. + */ + if (info->intercept == x86_intercept_rdtscp && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) { + ctxt->exception.vector = UD_VECTOR; + ctxt->exception.error_code_valid = false; + return X86EMUL_PROPAGATE_FAULT; + } + + /* TODO: check more intercepts... */ return X86EMUL_CONTINUE; } @@ -12313,6 +12368,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .handle_external_intr = vmx_handle_external_intr, .mpx_supported = vmx_mpx_supported, .xsaves_supported = vmx_xsaves_supported, + .umip_emulated = vmx_umip_emulated, .check_nested_events = vmx_check_nested_events, diff --git a/arch/x86/kvm/vmx_shadow_fields.h b/arch/x86/kvm/vmx_shadow_fields.h new file mode 100644 index 000000000000..cd0c75f6d037 --- /dev/null +++ b/arch/x86/kvm/vmx_shadow_fields.h @@ -0,0 +1,77 @@ +#ifndef SHADOW_FIELD_RO +#define SHADOW_FIELD_RO(x) +#endif +#ifndef SHADOW_FIELD_RW +#define SHADOW_FIELD_RW(x) +#endif + +/* + * We do NOT shadow fields that are modified when L0 + * traps and emulates any vmx instruction (e.g. VMPTRLD, + * VMXON...) executed by L1. + * For example, VM_INSTRUCTION_ERROR is read + * by L1 if a vmx instruction fails (part of the error path). + * Note the code assumes this logic. If for some reason + * we start shadowing these fields then we need to + * force a shadow sync when L0 emulates vmx instructions + * (e.g. force a sync if VM_INSTRUCTION_ERROR is modified + * by nested_vmx_failValid) + * + * When adding or removing fields here, note that shadowed + * fields must always be synced by prepare_vmcs02, not just + * prepare_vmcs02_full. + */ + +/* + * Keeping the fields ordered by size is an attempt at improving + * branch prediction in vmcs_read_any and vmcs_write_any. + */ + +/* 16-bits */ +SHADOW_FIELD_RW(GUEST_CS_SELECTOR) +SHADOW_FIELD_RW(GUEST_INTR_STATUS) +SHADOW_FIELD_RW(GUEST_PML_INDEX) +SHADOW_FIELD_RW(HOST_FS_SELECTOR) +SHADOW_FIELD_RW(HOST_GS_SELECTOR) + +/* 32-bits */ +SHADOW_FIELD_RO(VM_EXIT_REASON) +SHADOW_FIELD_RO(VM_EXIT_INTR_INFO) +SHADOW_FIELD_RO(VM_EXIT_INSTRUCTION_LEN) +SHADOW_FIELD_RO(IDT_VECTORING_INFO_FIELD) +SHADOW_FIELD_RO(IDT_VECTORING_ERROR_CODE) +SHADOW_FIELD_RO(VM_EXIT_INTR_ERROR_CODE) +SHADOW_FIELD_RW(CPU_BASED_VM_EXEC_CONTROL) +SHADOW_FIELD_RW(EXCEPTION_BITMAP) +SHADOW_FIELD_RW(VM_ENTRY_EXCEPTION_ERROR_CODE) +SHADOW_FIELD_RW(VM_ENTRY_INTR_INFO_FIELD) +SHADOW_FIELD_RW(VM_ENTRY_INSTRUCTION_LEN) +SHADOW_FIELD_RW(TPR_THRESHOLD) +SHADOW_FIELD_RW(GUEST_CS_LIMIT) +SHADOW_FIELD_RW(GUEST_CS_AR_BYTES) +SHADOW_FIELD_RW(GUEST_INTERRUPTIBILITY_INFO) +SHADOW_FIELD_RW(VMX_PREEMPTION_TIMER_VALUE) + +/* Natural width */ +SHADOW_FIELD_RO(EXIT_QUALIFICATION) +SHADOW_FIELD_RO(GUEST_LINEAR_ADDRESS) +SHADOW_FIELD_RW(GUEST_RIP) +SHADOW_FIELD_RW(GUEST_RSP) +SHADOW_FIELD_RW(GUEST_CR0) +SHADOW_FIELD_RW(GUEST_CR3) +SHADOW_FIELD_RW(GUEST_CR4) +SHADOW_FIELD_RW(GUEST_RFLAGS) +SHADOW_FIELD_RW(GUEST_CS_BASE) +SHADOW_FIELD_RW(GUEST_ES_BASE) +SHADOW_FIELD_RW(CR0_GUEST_HOST_MASK) +SHADOW_FIELD_RW(CR0_READ_SHADOW) +SHADOW_FIELD_RW(CR4_READ_SHADOW) +SHADOW_FIELD_RW(HOST_FS_BASE) +SHADOW_FIELD_RW(HOST_GS_BASE) + +/* 64-bit */ +SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS) +SHADOW_FIELD_RO(GUEST_PHYSICAL_ADDRESS_HIGH) + +#undef SHADOW_FIELD_RO +#undef SHADOW_FIELD_RW diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f9c5171dad2b..c8a0b545ac20 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -67,6 +67,8 @@ #include <asm/pvclock.h> #include <asm/div64.h> #include <asm/irq_remapping.h> +#include <asm/mshyperv.h> +#include <asm/hypervisor.h> #define CREATE_TRACE_POINTS #include "trace.h" @@ -177,7 +179,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "request_irq", VCPU_STAT(request_irq_exits) }, { "irq_exits", VCPU_STAT(irq_exits) }, { "host_state_reload", VCPU_STAT(host_state_reload) }, - { "efer_reload", VCPU_STAT(efer_reload) }, { "fpu_reload", VCPU_STAT(fpu_reload) }, { "insn_emulation", VCPU_STAT(insn_emulation) }, { "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) }, @@ -702,7 +703,8 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { /* kvm_set_xcr() also depends on this */ - xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); + if (vcpu->arch.xcr0 != host_xcr0) + xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); vcpu->guest_xcr0_loaded = 1; } } @@ -794,6 +796,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + return 1; + if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; @@ -1037,6 +1042,7 @@ static u32 emulated_msrs[] = { MSR_IA32_MCG_CTL, MSR_IA32_MCG_EXT_CTL, MSR_IA32_SMBASE, + MSR_SMI_COUNT, MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, }; @@ -1378,6 +1384,11 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +static inline int gtod_is_based_on_tsc(int mode) +{ + return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK; +} + static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 @@ -1397,7 +1408,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) * perform request to enable masterclock. */ if (ka->use_master_clock || - (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched)) + (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -1460,6 +1471,19 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) vcpu->arch.tsc_offset = offset; } +static inline bool kvm_check_tsc_unstable(void) +{ +#ifdef CONFIG_X86_64 + /* + * TSC is marked unstable when we're running on Hyper-V, + * 'TSC page' clocksource is good. + */ + if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK) + return false; +#endif + return check_tsc_unstable(); +} + void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; @@ -1505,7 +1529,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) */ if (synchronizing && vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) { - if (!check_tsc_unstable()) { + if (!kvm_check_tsc_unstable()) { offset = kvm->arch.cur_tsc_offset; pr_debug("kvm: matched tsc offset for %llu\n", data); } else { @@ -1605,18 +1629,43 @@ static u64 read_tsc(void) return last; } -static inline u64 vgettsc(u64 *cycle_now) +static inline u64 vgettsc(u64 *tsc_timestamp, int *mode) { long v; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + u64 tsc_pg_val; + + switch (gtod->clock.vclock_mode) { + case VCLOCK_HVCLOCK: + tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(), + tsc_timestamp); + if (tsc_pg_val != U64_MAX) { + /* TSC page valid */ + *mode = VCLOCK_HVCLOCK; + v = (tsc_pg_val - gtod->clock.cycle_last) & + gtod->clock.mask; + } else { + /* TSC page invalid */ + *mode = VCLOCK_NONE; + } + break; + case VCLOCK_TSC: + *mode = VCLOCK_TSC; + *tsc_timestamp = read_tsc(); + v = (*tsc_timestamp - gtod->clock.cycle_last) & + gtod->clock.mask; + break; + default: + *mode = VCLOCK_NONE; + } - *cycle_now = read_tsc(); + if (*mode == VCLOCK_NONE) + *tsc_timestamp = v = 0; - v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask; return v * gtod->clock.mult; } -static int do_monotonic_boot(s64 *t, u64 *cycle_now) +static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1625,9 +1674,8 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now) do { seq = read_seqcount_begin(>od->seq); - mode = gtod->clock.vclock_mode; ns = gtod->nsec_base; - ns += vgettsc(cycle_now); + ns += vgettsc(tsc_timestamp, &mode); ns >>= gtod->clock.shift; ns += gtod->boot_ns; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -1636,7 +1684,7 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now) return mode; } -static int do_realtime(struct timespec *ts, u64 *cycle_now) +static int do_realtime(struct timespec *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1645,10 +1693,9 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now) do { seq = read_seqcount_begin(>od->seq); - mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->nsec_base; - ns += vgettsc(cycle_now); + ns += vgettsc(tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -1658,25 +1705,26 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now) return mode; } -/* returns true if host is using tsc clocksource */ -static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now) +/* returns true if host is using TSC based clocksource */ +static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ - if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC; + return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns, + tsc_timestamp)); } -/* returns true if host is using tsc clocksource */ +/* returns true if host is using TSC based clocksource */ static bool kvm_get_walltime_and_clockread(struct timespec *ts, - u64 *cycle_now) + u64 *tsc_timestamp) { /* checked again under seqlock below */ - if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC) + if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return do_realtime(ts, cycle_now) == VCLOCK_TSC; + return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp)); } #endif @@ -2119,6 +2167,12 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) vcpu->arch.pv_time_enabled = false; } +static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) +{ + ++vcpu->stat.tlb_flush; + kvm_x86_ops->tlb_flush(vcpu, invalidate_gpa); +} + static void record_steal_time(struct kvm_vcpu *vcpu) { if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) @@ -2128,7 +2182,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu) &vcpu->arch.st.steal, sizeof(struct kvm_steal_time)))) return; - vcpu->arch.st.steal.preempted = 0; + /* + * Doing a TLB flush here, on the guest's behalf, can avoid + * expensive IPIs. + */ + if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB) + kvm_vcpu_flush_tlb(vcpu, false); if (vcpu->arch.st.steal.version & 1) vcpu->arch.st.steal.version += 1; /* first time write, random junk */ @@ -2229,6 +2288,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.smbase = data; break; + case MSR_SMI_COUNT: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.smi_count = data; + break; case MSR_KVM_WALL_CLOCK_NEW: case MSR_KVM_WALL_CLOCK: vcpu->kvm->arch.wall_clock = data; @@ -2503,6 +2567,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; msr_info->data = vcpu->arch.smbase; break; + case MSR_SMI_COUNT: + msr_info->data = vcpu->arch.smi_count; + break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ msr_info->data = 1000ULL; @@ -2870,13 +2937,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); } - if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { + if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) { s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); - if (check_tsc_unstable()) { + if (kvm_check_tsc_unstable()) { u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_vcpu_write_tsc_offset(vcpu, offset); @@ -2905,7 +2972,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - vcpu->arch.st.steal.preempted = 1; + vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED; kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime, &vcpu->arch.st.steal.preempted, @@ -2939,12 +3006,18 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) pagefault_enable(); kvm_x86_ops->vcpu_put(vcpu); vcpu->arch.last_host_tsc = rdtsc(); + /* + * If userspace has set any breakpoints or watchpoints, dr6 is restored + * on every vmexit, but if not, we might have a stale dr6 from the + * guest. do_debug expects dr6 to be cleared after it runs, do the same. + */ + set_debugreg(0, 6); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) + if (vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); return kvm_apic_get_state(vcpu, s); @@ -3473,6 +3546,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, void *buffer; } u; + vcpu_load(vcpu); + u.buffer = NULL; switch (ioctl) { case KVM_GET_LAPIC: { @@ -3498,8 +3573,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!lapic_in_kernel(vcpu)) goto out; u.lapic = memdup_user(argp, sizeof(*u.lapic)); - if (IS_ERR(u.lapic)) - return PTR_ERR(u.lapic); + if (IS_ERR(u.lapic)) { + r = PTR_ERR(u.lapic); + goto out_nofree; + } r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); break; @@ -3673,8 +3750,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_SET_XSAVE: { u.xsave = memdup_user(argp, sizeof(*u.xsave)); - if (IS_ERR(u.xsave)) - return PTR_ERR(u.xsave); + if (IS_ERR(u.xsave)) { + r = PTR_ERR(u.xsave); + goto out_nofree; + } r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; @@ -3696,8 +3775,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } case KVM_SET_XCRS: { u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); - if (IS_ERR(u.xcrs)) - return PTR_ERR(u.xcrs); + if (IS_ERR(u.xcrs)) { + r = PTR_ERR(u.xcrs); + goto out_nofree; + } r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; @@ -3741,6 +3822,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } out: kfree(u.buffer); +out_nofree: + vcpu_put(vcpu); return r; } @@ -4297,6 +4380,36 @@ set_identity_unlock: r = kvm_vm_ioctl_enable_cap(kvm, &cap); break; } + case KVM_MEMORY_ENCRYPT_OP: { + r = -ENOTTY; + if (kvm_x86_ops->mem_enc_op) + r = kvm_x86_ops->mem_enc_op(kvm, argp); + break; + } + case KVM_MEMORY_ENCRYPT_REG_REGION: { + struct kvm_enc_region region; + + r = -EFAULT; + if (copy_from_user(®ion, argp, sizeof(region))) + goto out; + + r = -ENOTTY; + if (kvm_x86_ops->mem_enc_reg_region) + r = kvm_x86_ops->mem_enc_reg_region(kvm, ®ion); + break; + } + case KVM_MEMORY_ENCRYPT_UNREG_REGION: { + struct kvm_enc_region region; + + r = -EFAULT; + if (copy_from_user(®ion, argp, sizeof(region))) + goto out; + + r = -ENOTTY; + if (kvm_x86_ops->mem_enc_unreg_region) + r = kvm_x86_ops->mem_enc_unreg_region(kvm, ®ion); + break; + } default: r = -ENOTTY; } @@ -5705,7 +5818,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, * handle watchpoints yet, those would be handled in * the emulate_ops. */ - if (kvm_vcpu_check_breakpoint(vcpu, &r)) + if (!(emulation_type & EMULTYPE_SKIP) && + kvm_vcpu_check_breakpoint(vcpu, &r)) return r; ctxt->interruptibility = 0; @@ -5891,6 +6005,43 @@ static void tsc_khz_changed(void *data) __this_cpu_write(cpu_tsc_khz, khz); } +#ifdef CONFIG_X86_64 +static void kvm_hyperv_tsc_notifier(void) +{ + struct kvm *kvm; + struct kvm_vcpu *vcpu; + int cpu; + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) + kvm_make_mclock_inprogress_request(kvm); + + hyperv_stop_tsc_emulation(); + + /* TSC frequency always matches when on Hyper-V */ + for_each_present_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + kvm_max_guest_tsc_khz = tsc_khz; + + list_for_each_entry(kvm, &vm_list, vm_list) { + struct kvm_arch *ka = &kvm->arch; + + spin_lock(&ka->pvclock_gtod_sync_lock); + + pvclock_update_vm_gtod_copy(kvm); + + kvm_for_each_vcpu(cpu, vcpu, kvm) + kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); + + kvm_for_each_vcpu(cpu, vcpu, kvm) + kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); + + spin_unlock(&ka->pvclock_gtod_sync_lock); + } + spin_unlock(&kvm_lock); +} +#endif + static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -6112,9 +6263,9 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, update_pvclock_gtod(tk); /* disable master clock if host does not trust, or does not - * use, TSC clocksource + * use, TSC based clocksource. */ - if (gtod->clock.vclock_mode != VCLOCK_TSC && + if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) queue_work(system_long_wq, &pvclock_gtod_work); @@ -6176,6 +6327,9 @@ int kvm_arch_init(void *opaque) kvm_lapic_init(); #ifdef CONFIG_X86_64 pvclock_gtod_register_notifier(&pvclock_gtod_notifier); + + if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) + set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif return 0; @@ -6188,6 +6342,10 @@ out: void kvm_arch_exit(void) { +#ifdef CONFIG_X86_64 + if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) + clear_hv_tscchange_cb(); +#endif kvm_lapic_exit(); perf_unregister_guest_info_callbacks(&kvm_guest_cbs); @@ -6450,6 +6608,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) kvm_x86_ops->queue_exception(vcpu); } else if (vcpu->arch.smi_pending && !is_smm(vcpu) && kvm_x86_ops->smi_allowed(vcpu)) { vcpu->arch.smi_pending = false; + ++vcpu->arch.smi_count; enter_smm(vcpu); } else if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { --vcpu->arch.nmi_pending; @@ -6751,7 +6910,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) + if (vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -6760,12 +6919,6 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } -static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu); -} - void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end) { @@ -6834,7 +6987,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu)) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) - kvm_vcpu_flush_tlb(vcpu); + kvm_vcpu_flush_tlb(vcpu, true); if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; @@ -6983,10 +7136,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * This handles the case where a posted interrupt was * notified with kvm_vcpu_kick. */ - if (kvm_lapic_enabled(vcpu)) { - if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active) - kvm_x86_ops->sync_pir_to_irr(vcpu); - } + if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || need_resched() || signal_pending(current)) { @@ -7007,7 +7158,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); + if (lapic_timer_advance_ns) + wait_lapic_expire(vcpu); guest_enter_irqoff(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -7268,8 +7420,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; + vcpu_load(vcpu); kvm_sigset_activate(vcpu); - kvm_load_guest_fpu(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { @@ -7316,11 +7468,14 @@ out: post_kvm_run_save(vcpu); kvm_sigset_deactivate(vcpu); + vcpu_put(vcpu); return r; } int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + vcpu_load(vcpu); + if (vcpu->arch.emulate_regs_need_sync_to_vcpu) { /* * We are here if userspace calls get_regs() in the middle of @@ -7354,11 +7509,14 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) regs->rip = kvm_rip_read(vcpu); regs->rflags = kvm_get_rflags(vcpu); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) { + vcpu_load(vcpu); + vcpu->arch.emulate_regs_need_sync_from_vcpu = true; vcpu->arch.emulate_regs_need_sync_to_vcpu = false; @@ -7388,6 +7546,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_make_request(KVM_REQ_EVENT, vcpu); + vcpu_put(vcpu); return 0; } @@ -7406,6 +7565,8 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, { struct desc_ptr dt; + vcpu_load(vcpu); + kvm_get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); kvm_get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); kvm_get_segment(vcpu, &sregs->es, VCPU_SREG_ES); @@ -7437,12 +7598,15 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, set_bit(vcpu->arch.interrupt.nr, (unsigned long *)sregs->interrupt_bitmap); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + vcpu_load(vcpu); + kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && vcpu->arch.pv.pv_unhalted) @@ -7450,21 +7614,26 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, else mp_state->mp_state = vcpu->arch.mp_state; + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int ret = -EINVAL; + + vcpu_load(vcpu); + if (!lapic_in_kernel(vcpu) && mp_state->mp_state != KVM_MP_STATE_RUNNABLE) - return -EINVAL; + goto out; /* INITs are latched while in SMM */ if ((is_smm(vcpu) || vcpu->arch.smi_pending) && (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED || mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED)) - return -EINVAL; + goto out; if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) { vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; @@ -7472,7 +7641,11 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, } else vcpu->arch.mp_state = mp_state->mp_state; kvm_make_request(KVM_REQ_EVENT, vcpu); - return 0; + + ret = 0; +out: + vcpu_put(vcpu); + return ret; } int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, @@ -7526,18 +7699,21 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int mmu_reset_needed = 0; int pending_vec, max_bits, idx; struct desc_ptr dt; + int ret = -EINVAL; + + vcpu_load(vcpu); if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; + goto out; if (kvm_valid_sregs(vcpu, sregs)) - return -EINVAL; + goto out; apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) - return -EINVAL; + goto out; dt.size = sregs->idt.limit; dt.address = sregs->idt.base; @@ -7603,7 +7779,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_make_request(KVM_REQ_EVENT, vcpu); - return 0; + ret = 0; +out: + vcpu_put(vcpu); + return ret; } int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, @@ -7612,6 +7791,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, unsigned long rflags; int i, r; + vcpu_load(vcpu); + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { r = -EBUSY; if (vcpu->arch.exception.pending) @@ -7657,7 +7838,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, r = 0; out: - + vcpu_put(vcpu); return r; } @@ -7671,6 +7852,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, gpa_t gpa; int idx; + vcpu_load(vcpu); + idx = srcu_read_lock(&vcpu->kvm->srcu); gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -7679,14 +7862,17 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, tr->writeable = 1; tr->usermode = 0; + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxregs_state *fxsave = - &vcpu->arch.guest_fpu.state.fxsave; + struct fxregs_state *fxsave; + + vcpu_load(vcpu); + fxsave = &vcpu->arch.guest_fpu.state.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; fpu->fsw = fxsave->swd; @@ -7696,13 +7882,17 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fpu->last_dp = fxsave->rdp; memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct fxregs_state *fxsave = - &vcpu->arch.guest_fpu.state.fxsave; + struct fxregs_state *fxsave; + + vcpu_load(vcpu); + + fxsave = &vcpu->arch.guest_fpu.state.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -7713,6 +7903,7 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) fxsave->rdp = fpu->last_dp; memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); + vcpu_put(vcpu); return 0; } @@ -7769,7 +7960,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, { struct kvm_vcpu *vcpu; - if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) + if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) printk_once(KERN_WARNING "kvm: SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); @@ -7781,16 +7972,12 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { - int r; - kvm_vcpu_mtrr_init(vcpu); - r = vcpu_load(vcpu); - if (r) - return r; + vcpu_load(vcpu); kvm_vcpu_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); - return r; + return 0; } void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) @@ -7800,13 +7987,15 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) kvm_hv_vcpu_postcreate(vcpu); - if (vcpu_load(vcpu)) + if (mutex_lock_killable(&vcpu->mutex)) return; + vcpu_load(vcpu); msr.data = 0x0; msr.index = MSR_IA32_TSC; msr.host_initiated = true; kvm_write_tsc(vcpu, &msr); vcpu_put(vcpu); + mutex_unlock(&vcpu->mutex); if (!kvmclock_periodic_sync) return; @@ -7817,11 +8006,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - int r; vcpu->arch.apf.msr_val = 0; - r = vcpu_load(vcpu); - BUG_ON(r); + vcpu_load(vcpu); kvm_mmu_unload(vcpu); vcpu_put(vcpu); @@ -7833,6 +8020,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; + vcpu->arch.smi_count = 0; atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; @@ -7926,7 +8114,7 @@ int kvm_arch_hardware_enable(void) return ret; local_tsc = rdtsc(); - stable = !check_tsc_unstable(); + stable = !kvm_check_tsc_unstable(); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (!stable && vcpu->cpu == smp_processor_id()) @@ -8192,9 +8380,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { - int r; - r = vcpu_load(vcpu); - BUG_ON(r); + vcpu_load(vcpu); kvm_mmu_unload(vcpu); vcpu_put(vcpu); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index d0b95b7a90b4..b91215d1fd80 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -12,6 +12,7 @@ static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) { + vcpu->arch.exception.pending = false; vcpu->arch.exception.injected = false; } @@ -265,36 +266,8 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) static inline bool kvm_mwait_in_guest(void) { - unsigned int eax, ebx, ecx, edx; - - if (!cpu_has(&boot_cpu_data, X86_FEATURE_MWAIT)) - return false; - - switch (boot_cpu_data.x86_vendor) { - case X86_VENDOR_AMD: - /* All AMD CPUs have a working MWAIT implementation */ - return true; - case X86_VENDOR_INTEL: - /* Handle Intel below */ - break; - default: - return false; - } - - /* - * Intel CPUs without CPUID5_ECX_INTERRUPT_BREAK are problematic as - * they would allow guest to stop the CPU completely by disabling - * interrupts then invoking MWAIT. - */ - if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) - return false; - - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); - - if (!(ecx & CPUID5_ECX_INTERRUPT_BREAK)) - return false; - - return true; + return boot_cpu_has(X86_FEATURE_MWAIT) && + !boot_cpu_has_bug(X86_BUG_MONITOR); } #endif diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index fe7d57a8fb60..1555bd7d3449 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -678,6 +678,25 @@ static enum page_cache_mode lookup_memtype(u64 paddr) } /** + * pat_pfn_immune_to_uc_mtrr - Check whether the PAT memory type + * of @pfn cannot be overridden by UC MTRR memory type. + * + * Only to be called when PAT is enabled. + * + * Returns true, if the PAT memory type of @pfn is UC, UC-, or WC. + * Returns false in other cases. + */ +bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn) +{ + enum page_cache_mode cm = lookup_memtype(PFN_PHYS(pfn)); + + return cm == _PAGE_CACHE_MODE_UC || + cm == _PAGE_CACHE_MODE_UC_MINUS || + cm == _PAGE_CACHE_MODE_WC; +} +EXPORT_SYMBOL_GPL(pat_pfn_immune_to_uc_mtrr); + +/** * io_reserve_memtype - Request a memory type mapping for a region of memory * @start: start (physical address) of the region * @end: end (physical address) of the region diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 012d02624848..8dcc0607f805 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -229,6 +229,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, #endif this_cpu_write(cpu_tlbstate.is_lazy, false); + /* + * The membarrier system call requires a full memory barrier and + * core serialization before returning to user-space, after + * storing to rq->curr. Writing to CR3 provides that full + * memory barrier and core serializing instruction. + */ if (real_prev == next) { VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 13b4f19b9131..159a897151d6 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -694,6 +694,9 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, int i, ret = 0; pte_t *pte; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + if (kmap_ops) { ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, kmap_ops, count); @@ -736,6 +739,9 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, { int i, ret = 0; + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; + for (i = 0; i < count; i++) { unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i])); unsigned long pfn = page_to_pfn(pages[i]); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 497cc55a0c16..96f26e026783 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -9,7 +9,9 @@ #include <asm/boot.h> #include <asm/asm.h> +#include <asm/msr.h> #include <asm/page_types.h> +#include <asm/percpu.h> #include <asm/unwind_hints.h> #include <xen/interface/elfnote.h> @@ -35,6 +37,20 @@ ENTRY(startup_xen) mov %_ASM_SI, xen_start_info mov $init_thread_union+THREAD_SIZE, %_ASM_SP +#ifdef CONFIG_X86_64 + /* Set up %gs. + * + * The base of %gs always points to the bottom of the irqstack + * union. If the stack protector canary is enabled, it is + * located at %gs:40. Note that, on SMP, the boot cpu uses + * init data section till per cpu areas are set up. + */ + movl $MSR_GS_BASE,%ecx + movq $INIT_PER_CPU_VAR(irq_stack_union),%rax + cdq + wrmsr +#endif + jmp xen_start_kernel END(startup_xen) __FINIT diff --git a/arch/xtensa/include/asm/kasan.h b/arch/xtensa/include/asm/kasan.h index 54be80876e57..216b6f32c375 100644 --- a/arch/xtensa/include/asm/kasan.h +++ b/arch/xtensa/include/asm/kasan.h @@ -10,6 +10,8 @@ #include <linux/sizes.h> #include <asm/kmem_layout.h> +#define KASAN_SHADOW_SCALE_SHIFT 3 + /* Start of area covered by KASAN */ #define KASAN_START_VADDR __XTENSA_UL_CONST(0x90000000) /* Start of the shadow map */ diff --git a/arch/xtensa/include/uapi/asm/poll.h b/arch/xtensa/include/uapi/asm/poll.h index e3246d41182c..4d249040b33d 100644 --- a/arch/xtensa/include/uapi/asm/poll.h +++ b/arch/xtensa/include/uapi/asm/poll.h @@ -12,26 +12,9 @@ #ifndef _XTENSA_POLL_H #define _XTENSA_POLL_H -#ifndef __KERNEL__ #define POLLWRNORM POLLOUT -#define POLLWRBAND (__force __poll_t)0x0100 -#define POLLREMOVE (__force __poll_t)0x0800 -#else -#define __ARCH_HAS_MANGLED_POLL -static inline __u16 mangle_poll(__poll_t val) -{ - __u16 v = (__force __u16)val; - /* bit 9 -> bit 8, bit 8 -> bit 2 */ - return (v & ~0x300) | ((v & 0x200) >> 1) | ((v & 0x100) >> 6); -} - -static inline __poll_t demangle_poll(__u16 v) -{ - /* bit 8 -> bit 9, bit 2 -> bits 2 and 8 */ - return (__force __poll_t)((v & ~0x100) | ((v & 0x100) << 1) | - ((v & 4) << 6)); -} -#endif +#define POLLWRBAND 0x0100 +#define POLLREMOVE 0x0800 #include <asm-generic/poll.h> diff --git a/block/blk-mq.c b/block/blk-mq.c index df93102e2149..357492712b0e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3164,6 +3164,7 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) cpu_relax(); } + __set_current_state(TASK_RUNNING); return false; } diff --git a/block/bsg.c b/block/bsg.c index 2e2c1e222209..06dc96e1f670 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -849,9 +849,9 @@ static __poll_t bsg_poll(struct file *file, poll_table *wait) spin_lock_irq(&bd->lock); if (!list_empty(&bd->done_list)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (bd->queued_cmds < bd->max_queue) - mask |= POLLOUT; + mask |= EPOLLOUT; spin_unlock_irq(&bd->lock); return mask; diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 0f8d8d5523c3..c49766b03165 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -735,9 +735,9 @@ void af_alg_wmem_wakeup(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLIN | - POLLRDNORM | - POLLRDBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | + EPOLLRDNORM | + EPOLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } @@ -800,9 +800,9 @@ void af_alg_data_wakeup(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | - POLLRDNORM | - POLLRDBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | + EPOLLRDNORM | + EPOLLRDBAND); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } @@ -1076,10 +1076,10 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock, mask = 0; if (!ctx->more || ctx->used) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (af_alg_writable(sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; } diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c index a965b9d80559..ded148783303 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -20,6 +20,20 @@ #include <crypto/sha3.h> #include <asm/unaligned.h> +/* + * On some 32-bit architectures (mn10300 and h8300), GCC ends up using + * over 1 KB of stack if we inline the round calculation into the loop + * in keccakf(). On the other hand, on 64-bit architectures with plenty + * of [64-bit wide] general purpose registers, not inlining it severely + * hurts performance. So let's use 64-bitness as a heuristic to decide + * whether to inline or not. + */ +#ifdef CONFIG_64BIT +#define SHA3_INLINE inline +#else +#define SHA3_INLINE noinline +#endif + #define KECCAK_ROUNDS 24 static const u64 keccakf_rndc[24] = { @@ -35,111 +49,115 @@ static const u64 keccakf_rndc[24] = { /* update the state with given number of rounds */ -static void __attribute__((__optimize__("O3"))) keccakf(u64 st[25]) +static SHA3_INLINE void keccakf_round(u64 st[25]) { u64 t[5], tt, bc[5]; - int round; - for (round = 0; round < KECCAK_ROUNDS; round++) { + /* Theta */ + bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20]; + bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21]; + bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22]; + bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23]; + bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24]; + + t[0] = bc[4] ^ rol64(bc[1], 1); + t[1] = bc[0] ^ rol64(bc[2], 1); + t[2] = bc[1] ^ rol64(bc[3], 1); + t[3] = bc[2] ^ rol64(bc[4], 1); + t[4] = bc[3] ^ rol64(bc[0], 1); + + st[0] ^= t[0]; + + /* Rho Pi */ + tt = st[1]; + st[ 1] = rol64(st[ 6] ^ t[1], 44); + st[ 6] = rol64(st[ 9] ^ t[4], 20); + st[ 9] = rol64(st[22] ^ t[2], 61); + st[22] = rol64(st[14] ^ t[4], 39); + st[14] = rol64(st[20] ^ t[0], 18); + st[20] = rol64(st[ 2] ^ t[2], 62); + st[ 2] = rol64(st[12] ^ t[2], 43); + st[12] = rol64(st[13] ^ t[3], 25); + st[13] = rol64(st[19] ^ t[4], 8); + st[19] = rol64(st[23] ^ t[3], 56); + st[23] = rol64(st[15] ^ t[0], 41); + st[15] = rol64(st[ 4] ^ t[4], 27); + st[ 4] = rol64(st[24] ^ t[4], 14); + st[24] = rol64(st[21] ^ t[1], 2); + st[21] = rol64(st[ 8] ^ t[3], 55); + st[ 8] = rol64(st[16] ^ t[1], 45); + st[16] = rol64(st[ 5] ^ t[0], 36); + st[ 5] = rol64(st[ 3] ^ t[3], 28); + st[ 3] = rol64(st[18] ^ t[3], 21); + st[18] = rol64(st[17] ^ t[2], 15); + st[17] = rol64(st[11] ^ t[1], 10); + st[11] = rol64(st[ 7] ^ t[2], 6); + st[ 7] = rol64(st[10] ^ t[0], 3); + st[10] = rol64( tt ^ t[1], 1); + + /* Chi */ + bc[ 0] = ~st[ 1] & st[ 2]; + bc[ 1] = ~st[ 2] & st[ 3]; + bc[ 2] = ~st[ 3] & st[ 4]; + bc[ 3] = ~st[ 4] & st[ 0]; + bc[ 4] = ~st[ 0] & st[ 1]; + st[ 0] ^= bc[ 0]; + st[ 1] ^= bc[ 1]; + st[ 2] ^= bc[ 2]; + st[ 3] ^= bc[ 3]; + st[ 4] ^= bc[ 4]; + + bc[ 0] = ~st[ 6] & st[ 7]; + bc[ 1] = ~st[ 7] & st[ 8]; + bc[ 2] = ~st[ 8] & st[ 9]; + bc[ 3] = ~st[ 9] & st[ 5]; + bc[ 4] = ~st[ 5] & st[ 6]; + st[ 5] ^= bc[ 0]; + st[ 6] ^= bc[ 1]; + st[ 7] ^= bc[ 2]; + st[ 8] ^= bc[ 3]; + st[ 9] ^= bc[ 4]; + + bc[ 0] = ~st[11] & st[12]; + bc[ 1] = ~st[12] & st[13]; + bc[ 2] = ~st[13] & st[14]; + bc[ 3] = ~st[14] & st[10]; + bc[ 4] = ~st[10] & st[11]; + st[10] ^= bc[ 0]; + st[11] ^= bc[ 1]; + st[12] ^= bc[ 2]; + st[13] ^= bc[ 3]; + st[14] ^= bc[ 4]; + + bc[ 0] = ~st[16] & st[17]; + bc[ 1] = ~st[17] & st[18]; + bc[ 2] = ~st[18] & st[19]; + bc[ 3] = ~st[19] & st[15]; + bc[ 4] = ~st[15] & st[16]; + st[15] ^= bc[ 0]; + st[16] ^= bc[ 1]; + st[17] ^= bc[ 2]; + st[18] ^= bc[ 3]; + st[19] ^= bc[ 4]; + + bc[ 0] = ~st[21] & st[22]; + bc[ 1] = ~st[22] & st[23]; + bc[ 2] = ~st[23] & st[24]; + bc[ 3] = ~st[24] & st[20]; + bc[ 4] = ~st[20] & st[21]; + st[20] ^= bc[ 0]; + st[21] ^= bc[ 1]; + st[22] ^= bc[ 2]; + st[23] ^= bc[ 3]; + st[24] ^= bc[ 4]; +} - /* Theta */ - bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20]; - bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21]; - bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22]; - bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23]; - bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24]; - - t[0] = bc[4] ^ rol64(bc[1], 1); - t[1] = bc[0] ^ rol64(bc[2], 1); - t[2] = bc[1] ^ rol64(bc[3], 1); - t[3] = bc[2] ^ rol64(bc[4], 1); - t[4] = bc[3] ^ rol64(bc[0], 1); - - st[0] ^= t[0]; - - /* Rho Pi */ - tt = st[1]; - st[ 1] = rol64(st[ 6] ^ t[1], 44); - st[ 6] = rol64(st[ 9] ^ t[4], 20); - st[ 9] = rol64(st[22] ^ t[2], 61); - st[22] = rol64(st[14] ^ t[4], 39); - st[14] = rol64(st[20] ^ t[0], 18); - st[20] = rol64(st[ 2] ^ t[2], 62); - st[ 2] = rol64(st[12] ^ t[2], 43); - st[12] = rol64(st[13] ^ t[3], 25); - st[13] = rol64(st[19] ^ t[4], 8); - st[19] = rol64(st[23] ^ t[3], 56); - st[23] = rol64(st[15] ^ t[0], 41); - st[15] = rol64(st[ 4] ^ t[4], 27); - st[ 4] = rol64(st[24] ^ t[4], 14); - st[24] = rol64(st[21] ^ t[1], 2); - st[21] = rol64(st[ 8] ^ t[3], 55); - st[ 8] = rol64(st[16] ^ t[1], 45); - st[16] = rol64(st[ 5] ^ t[0], 36); - st[ 5] = rol64(st[ 3] ^ t[3], 28); - st[ 3] = rol64(st[18] ^ t[3], 21); - st[18] = rol64(st[17] ^ t[2], 15); - st[17] = rol64(st[11] ^ t[1], 10); - st[11] = rol64(st[ 7] ^ t[2], 6); - st[ 7] = rol64(st[10] ^ t[0], 3); - st[10] = rol64( tt ^ t[1], 1); - - /* Chi */ - bc[ 0] = ~st[ 1] & st[ 2]; - bc[ 1] = ~st[ 2] & st[ 3]; - bc[ 2] = ~st[ 3] & st[ 4]; - bc[ 3] = ~st[ 4] & st[ 0]; - bc[ 4] = ~st[ 0] & st[ 1]; - st[ 0] ^= bc[ 0]; - st[ 1] ^= bc[ 1]; - st[ 2] ^= bc[ 2]; - st[ 3] ^= bc[ 3]; - st[ 4] ^= bc[ 4]; - - bc[ 0] = ~st[ 6] & st[ 7]; - bc[ 1] = ~st[ 7] & st[ 8]; - bc[ 2] = ~st[ 8] & st[ 9]; - bc[ 3] = ~st[ 9] & st[ 5]; - bc[ 4] = ~st[ 5] & st[ 6]; - st[ 5] ^= bc[ 0]; - st[ 6] ^= bc[ 1]; - st[ 7] ^= bc[ 2]; - st[ 8] ^= bc[ 3]; - st[ 9] ^= bc[ 4]; - - bc[ 0] = ~st[11] & st[12]; - bc[ 1] = ~st[12] & st[13]; - bc[ 2] = ~st[13] & st[14]; - bc[ 3] = ~st[14] & st[10]; - bc[ 4] = ~st[10] & st[11]; - st[10] ^= bc[ 0]; - st[11] ^= bc[ 1]; - st[12] ^= bc[ 2]; - st[13] ^= bc[ 3]; - st[14] ^= bc[ 4]; - - bc[ 0] = ~st[16] & st[17]; - bc[ 1] = ~st[17] & st[18]; - bc[ 2] = ~st[18] & st[19]; - bc[ 3] = ~st[19] & st[15]; - bc[ 4] = ~st[15] & st[16]; - st[15] ^= bc[ 0]; - st[16] ^= bc[ 1]; - st[17] ^= bc[ 2]; - st[18] ^= bc[ 3]; - st[19] ^= bc[ 4]; - - bc[ 0] = ~st[21] & st[22]; - bc[ 1] = ~st[22] & st[23]; - bc[ 2] = ~st[23] & st[24]; - bc[ 3] = ~st[24] & st[20]; - bc[ 4] = ~st[20] & st[21]; - st[20] ^= bc[ 0]; - st[21] ^= bc[ 1]; - st[22] ^= bc[ 2]; - st[23] ^= bc[ 3]; - st[24] ^= bc[ 4]; +static void __optimize("O3") keccakf(u64 st[25]) +{ + int round; + for (round = 0; round < KECCAK_ROUNDS; round++) { + keccakf_round(st); /* Iota */ st[0] ^= keccakf_rndc[round]; } diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index d650c5b6ec90..f505e9a01b2d 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -79,7 +79,12 @@ config ACPI_DEBUGGER_USER endif config ACPI_SPCR_TABLE - bool + bool "ACPI Serial Port Console Redirection Support" + default y if X86 + help + Enable support for Serial Port Console Redirection (SPCR) Table. + This table provides information about the configuration of the + earlycon console. config ACPI_LPIT bool diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c index 2ff5c8c04e3b..f21c99ec46ee 100644 --- a/drivers/acpi/acpi_dbg.c +++ b/drivers/acpi/acpi_dbg.c @@ -724,9 +724,9 @@ static __poll_t acpi_aml_poll(struct file *file, poll_table *wait) poll_wait(file, &acpi_aml_io.wait, wait); if (acpi_aml_user_readable()) - masks |= POLLIN | POLLRDNORM; + masks |= EPOLLIN | EPOLLRDNORM; if (acpi_aml_user_writable()) - masks |= POLLOUT | POLLWRNORM; + masks |= EPOLLOUT | EPOLLWRNORM; return masks; } diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c index e94e478dd18b..cf4fc0161164 100644 --- a/drivers/acpi/acpi_lpit.c +++ b/drivers/acpi/acpi_lpit.c @@ -100,6 +100,7 @@ int lpit_read_residency_count_address(u64 *address) return 0; } +EXPORT_SYMBOL_GPL(lpit_read_residency_count_address); static void lpit_update_residency(struct lpit_residency_info *info, struct acpi_lpit_native *lpit_native) diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index f53ccc680238..76fb96966f7b 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -53,7 +53,7 @@ MODULE_AUTHOR("Bruno Ducrot"); MODULE_DESCRIPTION("ACPI Video Driver"); MODULE_LICENSE("GPL"); -static bool brightness_switch_enabled = 1; +static bool brightness_switch_enabled = true; module_param(brightness_switch_enabled, bool, 0644); /* diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h index 2243c8164b34..e65478593f9a 100644 --- a/drivers/acpi/acpica/acapps.h +++ b/drivers/acpi/acpica/acapps.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -51,7 +51,7 @@ /* Common info for tool signons */ #define ACPICA_NAME "Intel ACPI Component Architecture" -#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2017 Intel Corporation" +#define ACPICA_COPYRIGHT "Copyright (c) 2000 - 2018 Intel Corporation" #if ACPI_MACHINE_WIDTH == 64 #define ACPI_WIDTH " (64-bit version)" diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h index 49bf47ca5477..c349ffdf5557 100644 --- a/drivers/acpi/acpica/accommon.h +++ b/drivers/acpi/acpica/accommon.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acconvert.h b/drivers/acpi/acpica/acconvert.h index c84223b60b35..ce6e8db83e27 100644 --- a/drivers/acpi/acpica/acconvert.h +++ b/drivers/acpi/acpica/acconvert.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h index 54b8d9df9423..8b2cca5a717b 100644 --- a/drivers/acpi/acpica/acdebug.h +++ b/drivers/acpi/acpica/acdebug.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h index f8f3a6e74128..fab590bc5fd3 100644 --- a/drivers/acpi/acpica/acdispat.h +++ b/drivers/acpi/acpica/acdispat.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index a2adfd42f85c..1b0269f6ac2d 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 45ef3f5dc9ad..27f322b2fed1 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h index cd722d8edacb..3569aa3bf5ee 100644 --- a/drivers/acpi/acpica/achware.h +++ b/drivers/acpi/acpica/achware.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h index 29555c8789a3..744374ab9285 100644 --- a/drivers/acpi/acpica/acinterp.h +++ b/drivers/acpi/acpica/acinterp.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index a56675f0661e..3ba3ff0f1c04 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h index 128a3d71b598..6463340c4522 100644 --- a/drivers/acpi/acpica/acmacros.h +++ b/drivers/acpi/acpica/acmacros.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h index 2fb1bb78d85c..6c8f364fe2fc 100644 --- a/drivers/acpi/acpica/acnamesp.h +++ b/drivers/acpi/acpica/acnamesp.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index 5226146190bf..a1f4d3f385c8 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h index cbd59a302679..36c2c5825986 100644 --- a/drivers/acpi/acpica/acopcode.h +++ b/drivers/acpi/acpica/acopcode.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h index c23c47328060..e25634951d03 100644 --- a/drivers/acpi/acpica/acparser.h +++ b/drivers/acpi/acpica/acparser.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index cdfcad8eb74c..7c27bcee6ac7 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h index 438f3098a093..20f36949928a 100644 --- a/drivers/acpi/acpica/acresrc.h +++ b/drivers/acpi/acpica/acresrc.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h index 62134bdbeda6..0338ac32f9c6 100644 --- a/drivers/acpi/acpica/acstruct.h +++ b/drivers/acpi/acpica/acstruct.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h index 84a3ceb6e384..15b23414245a 100644 --- a/drivers/acpi/acpica/actables.h +++ b/drivers/acpi/acpica/actables.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h index b6b29d717824..00d21d2f766e 100644 --- a/drivers/acpi/acpica/acutils.h +++ b/drivers/acpi/acpica/acutils.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h index f54dc5a34bdc..b0e9492a6297 100644 --- a/drivers/acpi/acpica/amlcode.h +++ b/drivers/acpi/acpica/amlcode.h @@ -7,7 +7,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h index 1236e9a414e4..b680c229ddd5 100644 --- a/drivers/acpi/acpica/amlresrc.h +++ b/drivers/acpi/acpica/amlresrc.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbcmds.c b/drivers/acpi/acpica/dbcmds.c index 5984b90eb590..4112c85f2aab 100644 --- a/drivers/acpi/acpica/dbcmds.c +++ b/drivers/acpi/acpica/dbcmds.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c index 32d546f0db2f..27236a6c51ff 100644 --- a/drivers/acpi/acpica/dbconvert.c +++ b/drivers/acpi/acpica/dbconvert.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbdisply.c b/drivers/acpi/acpica/dbdisply.c index 5a606eac0c22..7df920cda77d 100644 --- a/drivers/acpi/acpica/dbdisply.c +++ b/drivers/acpi/acpica/dbdisply.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbexec.c b/drivers/acpi/acpica/dbexec.c index ed088fceb18d..8ad9e6d9e54b 100644 --- a/drivers/acpi/acpica/dbexec.c +++ b/drivers/acpi/acpica/dbexec.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbfileio.c b/drivers/acpi/acpica/dbfileio.c index cf9607945704..084bb332f8e2 100644 --- a/drivers/acpi/acpica/dbfileio.c +++ b/drivers/acpi/acpica/dbfileio.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbhistry.c b/drivers/acpi/acpica/dbhistry.c index 7d08974c64c2..55c0f2742339 100644 --- a/drivers/acpi/acpica/dbhistry.c +++ b/drivers/acpi/acpica/dbhistry.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbinput.c b/drivers/acpi/acpica/dbinput.c index 954ca3b981a7..f7c661e06f37 100644 --- a/drivers/acpi/acpica/dbinput.c +++ b/drivers/acpi/acpica/dbinput.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbmethod.c b/drivers/acpi/acpica/dbmethod.c index df62c9245efc..2cda0bff6f2c 100644 --- a/drivers/acpi/acpica/dbmethod.c +++ b/drivers/acpi/acpica/dbmethod.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c index 8c207c772517..8796fc1e0360 100644 --- a/drivers/acpi/acpica/dbnames.c +++ b/drivers/acpi/acpica/dbnames.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbobject.c b/drivers/acpi/acpica/dbobject.c index e7b415c20aa8..d2063cbab39a 100644 --- a/drivers/acpi/acpica/dbobject.c +++ b/drivers/acpi/acpica/dbobject.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbstats.c b/drivers/acpi/acpica/dbstats.c index 99fb0160b8fb..d6aaef54e369 100644 --- a/drivers/acpi/acpica/dbstats.c +++ b/drivers/acpi/acpica/dbstats.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbtest.c b/drivers/acpi/acpica/dbtest.c index c6bee6143266..56e446b89d18 100644 --- a/drivers/acpi/acpica/dbtest.c +++ b/drivers/acpi/acpica/dbtest.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbutils.c b/drivers/acpi/acpica/dbutils.c index bfa972b64171..cd40854ee9be 100644 --- a/drivers/acpi/acpica/dbutils.c +++ b/drivers/acpi/acpica/dbutils.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dbxface.c b/drivers/acpi/acpica/dbxface.c index b6985323e7eb..77bbfa97cf91 100644 --- a/drivers/acpi/acpica/dbxface.c +++ b/drivers/acpi/acpica/dbxface.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c index 2873455c986d..04a9f60e7ad1 100644 --- a/drivers/acpi/acpica/dsargs.c +++ b/drivers/acpi/acpica/dsargs.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c index 4b6ebc2a2851..606697e741a5 100644 --- a/drivers/acpi/acpica/dscontrol.c +++ b/drivers/acpi/acpica/dscontrol.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c index d1f457eda980..14ec52eba408 100644 --- a/drivers/acpi/acpica/dsdebug.c +++ b/drivers/acpi/acpica/dsdebug.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c index 0cab34a593d5..95ea639a9424 100644 --- a/drivers/acpi/acpica/dsfield.c +++ b/drivers/acpi/acpica/dsfield.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c index b1842dd4edf7..946ff2e130d9 100644 --- a/drivers/acpi/acpica/dsinit.c +++ b/drivers/acpi/acpica/dsinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index d7fc36917c67..b9c460c2d763 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsmthdat.c b/drivers/acpi/acpica/dsmthdat.c index 27a7de95f7b0..157f1645d91a 100644 --- a/drivers/acpi/acpica/dsmthdat.c +++ b/drivers/acpi/acpica/dsmthdat.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c index b21fe084ffc8..4fa3400a95ba 100644 --- a/drivers/acpi/acpica/dsobject.c +++ b/drivers/acpi/acpica/dsobject.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index 0336df7ac47d..0181cd317751 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dspkginit.c b/drivers/acpi/acpica/dspkginit.c index 5a602b75084e..902bee78036c 100644 --- a/drivers/acpi/acpica/dspkginit.c +++ b/drivers/acpi/acpica/dspkginit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c index 4c5faf629a83..a4ce0b4a55a6 100644 --- a/drivers/acpi/acpica/dsutils.c +++ b/drivers/acpi/acpica/dsutils.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c index 22f45d090733..2c07d220a50f 100644 --- a/drivers/acpi/acpica/dswexec.c +++ b/drivers/acpi/acpica/dswexec.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c index 5771e4e4a99a..fa4ef9229e17 100644 --- a/drivers/acpi/acpica/dswload.c +++ b/drivers/acpi/acpica/dswload.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c index b3d0aaec8203..3b1313ba60d0 100644 --- a/drivers/acpi/acpica/dswload2.c +++ b/drivers/acpi/acpica/dswload2.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c index 3e081983d2ee..8b5c3613c060 100644 --- a/drivers/acpi/acpica/dswscope.c +++ b/drivers/acpi/acpica/dswscope.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c index da111a1f5bfb..ee002d17526e 100644 --- a/drivers/acpi/acpica/dswstate.c +++ b/drivers/acpi/acpica/dswstate.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c index d3b6b314fa50..4b2b0b44a16b 100644 --- a/drivers/acpi/acpica/evevent.c +++ b/drivers/acpi/acpica/evevent.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c index 0ce33b0f430c..012b80de1501 100644 --- a/drivers/acpi/acpica/evglock.c +++ b/drivers/acpi/acpica/evglock.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c index 263d8fc4a9e2..410a3907c051 100644 --- a/drivers/acpi/acpica/evgpe.c +++ b/drivers/acpi/acpica/evgpe.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c index 3a3cb8624f41..7ce756cc28ab 100644 --- a/drivers/acpi/acpica/evgpeblk.c +++ b/drivers/acpi/acpica/evgpeblk.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c index 8649c6242478..8ad4816c9950 100644 --- a/drivers/acpi/acpica/evgpeinit.c +++ b/drivers/acpi/acpica/evgpeinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c index c8adb400330a..729a8960a3af 100644 --- a/drivers/acpi/acpica/evgpeutil.c +++ b/drivers/acpi/acpica/evgpeutil.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c index 2db61ef1b4a3..20fb51c06b8d 100644 --- a/drivers/acpi/acpica/evhandler.c +++ b/drivers/acpi/acpica/evhandler.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c index 4f6bb3f016ab..40d0b1f541a0 100644 --- a/drivers/acpi/acpica/evmisc.c +++ b/drivers/acpi/acpica/evmisc.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index bb58419f0d61..de196c8e3f30 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c index 93ec528bcd9a..4187f563fede 100644 --- a/drivers/acpi/acpica/evrgnini.c +++ b/drivers/acpi/acpica/evrgnini.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c index 8ce73b962006..d5594f79f877 100644 --- a/drivers/acpi/acpica/evsci.c +++ b/drivers/acpi/acpica/evsci.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c index dd1b9dd64cef..9b3c01bf1438 100644 --- a/drivers/acpi/acpica/evxface.c +++ b/drivers/acpi/acpica/evxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c index c773ac4892cb..96c2520f9570 100644 --- a/drivers/acpi/acpica/evxfevnt.c +++ b/drivers/acpi/acpica/evxfevnt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c index 67c7c4ce276c..cbb1598df9dc 100644 --- a/drivers/acpi/acpica/evxfgpe.c +++ b/drivers/acpi/acpica/evxfgpe.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index beba9d56a0d8..705fcd86151a 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c index 59b8de2f07d3..ea20e10dd1f2 100644 --- a/drivers/acpi/acpica/exconcat.c +++ b/drivers/acpi/acpica/exconcat.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 61813bd43f9e..827f47b72663 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c index 23ebadb06a95..9abcc41a573b 100644 --- a/drivers/acpi/acpica/exconvrt.c +++ b/drivers/acpi/acpica/exconvrt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c index b8adb11f1b07..3dece45dd997 100644 --- a/drivers/acpi/acpica/excreate.c +++ b/drivers/acpi/acpica/excreate.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c index a8191d2ca5e3..d931a66a16e3 100644 --- a/drivers/acpi/acpica/exdebug.c +++ b/drivers/acpi/acpica/exdebug.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c index b2ff61bdb9a8..4989ce9591ae 100644 --- a/drivers/acpi/acpica/exdump.c +++ b/drivers/acpi/acpica/exdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index 5fda981f6498..e3b0650e5bb6 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c index a656608dca84..3d0f274be88b 100644 --- a/drivers/acpi/acpica/exfldio.c +++ b/drivers/acpi/acpica/exfldio.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c index dbad3ebd7df5..1518fcb22ae1 100644 --- a/drivers/acpi/acpica/exmisc.c +++ b/drivers/acpi/acpica/exmisc.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c index ecd95b3f35f1..24c9741dee48 100644 --- a/drivers/acpi/acpica/exmutex.c +++ b/drivers/acpi/acpica/exmutex.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c index caa5ed1f65ec..c7b249cda5c0 100644 --- a/drivers/acpi/acpica/exnames.c +++ b/drivers/acpi/acpica/exnames.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c index f787651348c1..dae01c93e480 100644 --- a/drivers/acpi/acpica/exoparg1.c +++ b/drivers/acpi/acpica/exoparg1.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c index 57980b7d3594..3cafa1d6f31a 100644 --- a/drivers/acpi/acpica/exoparg2.c +++ b/drivers/acpi/acpica/exoparg2.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c index ce857addc8db..f16c655121ff 100644 --- a/drivers/acpi/acpica/exoparg3.c +++ b/drivers/acpi/acpica/exoparg3.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c index 688032b58a21..8b39fffce6dc 100644 --- a/drivers/acpi/acpica/exoparg6.c +++ b/drivers/acpi/acpica/exoparg6.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 8de060664204..1d1040f2e3f8 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c index 7bcc9d809b7e..387c438aa485 100644 --- a/drivers/acpi/acpica/exregion.c +++ b/drivers/acpi/acpica/exregion.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c index 91c1de046442..77fa8d9aa5bf 100644 --- a/drivers/acpi/acpica/exresnte.c +++ b/drivers/acpi/acpica/exresnte.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c index 5e1854ea85f6..b104bc3ca809 100644 --- a/drivers/acpi/acpica/exresolv.c +++ b/drivers/acpi/acpica/exresolv.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c index 1c7c9962b0de..2643d34f194d 100644 --- a/drivers/acpi/acpica/exresop.c +++ b/drivers/acpi/acpica/exresop.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c index bdd43cde8f36..8f106bdcad5f 100644 --- a/drivers/acpi/acpica/exstore.c +++ b/drivers/acpi/acpica/exstore.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c index 56f59cf5da29..3d458d1996b0 100644 --- a/drivers/acpi/acpica/exstoren.c +++ b/drivers/acpi/acpica/exstoren.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c index 4ba7fcbf23b0..905443a3c28f 100644 --- a/drivers/acpi/acpica/exstorob.c +++ b/drivers/acpi/acpica/exstorob.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c index ad3b610057f3..420d9b145d2e 100644 --- a/drivers/acpi/acpica/exsystem.c +++ b/drivers/acpi/acpica/exsystem.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/extrace.c b/drivers/acpi/acpica/extrace.c index ae9df8672d9e..9a67d507a132 100644 --- a/drivers/acpi/acpica/extrace.c +++ b/drivers/acpi/acpica/extrace.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c index 34d608358eaf..fb80d3f55d63 100644 --- a/drivers/acpi/acpica/exutils.c +++ b/drivers/acpi/acpica/exutils.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c index fad249e774b4..68e958d4c25f 100644 --- a/drivers/acpi/acpica/hwacpi.c +++ b/drivers/acpi/acpica/hwacpi.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c index 12626d021a9b..64855b62a5ae 100644 --- a/drivers/acpi/acpica/hwesleep.c +++ b/drivers/acpi/acpica/hwesleep.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c index 09b6822aa5cc..c1c54af148d0 100644 --- a/drivers/acpi/acpica/hwgpe.c +++ b/drivers/acpi/acpica/hwgpe.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwpci.c b/drivers/acpi/acpica/hwpci.c index 283819930be6..faa2fa45eb1c 100644 --- a/drivers/acpi/acpica/hwpci.c +++ b/drivers/acpi/acpica/hwpci.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c index aa6e00081915..f3e7b7851a3a 100644 --- a/drivers/acpi/acpica/hwregs.c +++ b/drivers/acpi/acpica/hwregs.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c index 1fe7387a00e6..c85c373ecbc4 100644 --- a/drivers/acpi/acpica/hwsleep.c +++ b/drivers/acpi/acpica/hwsleep.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c index 5b4282902a83..511e3b8ffc6d 100644 --- a/drivers/acpi/acpica/hwtimer.c +++ b/drivers/acpi/acpica/hwtimer.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c index d1679035d5f3..65d82e6add0b 100644 --- a/drivers/acpi/acpica/hwvalid.c +++ b/drivers/acpi/acpica/hwvalid.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c index b3c6e439933c..d320b129b7d7 100644 --- a/drivers/acpi/acpica/hwxface.c +++ b/drivers/acpi/acpica/hwxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c index e5c095ca6083..589c774bbf9a 100644 --- a/drivers/acpi/acpica/hwxfsleep.c +++ b/drivers/acpi/acpica/hwxfsleep.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c index 33e652a12fca..07f672b5a1d1 100644 --- a/drivers/acpi/acpica/nsaccess.c +++ b/drivers/acpi/acpica/nsaccess.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsalloc.c b/drivers/acpi/acpica/nsalloc.c index 8ba5b32c9f71..ce57ccf4c1bf 100644 --- a/drivers/acpi/acpica/nsalloc.c +++ b/drivers/acpi/acpica/nsalloc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c index 67b7370dcae5..ce296ac14cf0 100644 --- a/drivers/acpi/acpica/nsarguments.c +++ b/drivers/acpi/acpica/nsarguments.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c index d55dcc82f434..2f9d5d190fa9 100644 --- a/drivers/acpi/acpica/nsconvert.c +++ b/drivers/acpi/acpica/nsconvert.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c index 4123b5077a7d..e2ac16818dc3 100644 --- a/drivers/acpi/acpica/nsdump.c +++ b/drivers/acpi/acpica/nsdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c index 5026594763ea..09ac00dee450 100644 --- a/drivers/acpi/acpica/nsdumpdv.c +++ b/drivers/acpi/acpica/nsdumpdv.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c index d22167cbd0ca..c2d883b8c45e 100644 --- a/drivers/acpi/acpica/nseval.c +++ b/drivers/acpi/acpica/nseval.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index 9c6297949712..c17af4a3ab67 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c index d2915e186ae1..fdfe9309bd33 100644 --- a/drivers/acpi/acpica/nsload.c +++ b/drivers/acpi/acpica/nsload.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c index 22c92d1a24d8..c686eda7ca66 100644 --- a/drivers/acpi/acpica/nsnames.c +++ b/drivers/acpi/acpica/nsnames.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c index 707b2aa501e1..757e44555ec3 100644 --- a/drivers/acpi/acpica/nsobject.c +++ b/drivers/acpi/acpica/nsobject.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c index 2fc33a5203f4..c5b22ea5b369 100644 --- a/drivers/acpi/acpica/nsparse.c +++ b/drivers/acpi/acpica/nsparse.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c index 9d14b509529e..4f1f6d6d9ddf 100644 --- a/drivers/acpi/acpica/nspredef.c +++ b/drivers/acpi/acpica/nspredef.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c index a8ea8fb1d299..7805d5ce8127 100644 --- a/drivers/acpi/acpica/nsprepkg.c +++ b/drivers/acpi/acpica/nsprepkg.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c index 418ef2ac82ab..7b6b6d281f1c 100644 --- a/drivers/acpi/acpica/nsrepair.c +++ b/drivers/acpi/acpica/nsrepair.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index 06037e044694..29c3973c7815 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c index e91dbee9235f..a469447f5c02 100644 --- a/drivers/acpi/acpica/nssearch.c +++ b/drivers/acpi/acpica/nssearch.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c index b43fe5fce64b..0487fdb59b0e 100644 --- a/drivers/acpi/acpica/nsutils.c +++ b/drivers/acpi/acpica/nsutils.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c index 6b6e6f498cff..dd7ae1bc8af8 100644 --- a/drivers/acpi/acpica/nswalk.c +++ b/drivers/acpi/acpica/nswalk.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c index 9b51f65823b2..1075bd9541f5 100644 --- a/drivers/acpi/acpica/nsxfeval.c +++ b/drivers/acpi/acpica/nsxfeval.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c index 106966235805..e9603fc9586c 100644 --- a/drivers/acpi/acpica/nsxfname.c +++ b/drivers/acpi/acpica/nsxfname.c @@ -6,7 +6,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c index 47f689ec3fcb..ac1fbf767cac 100644 --- a/drivers/acpi/acpica/nsxfobj.c +++ b/drivers/acpi/acpica/nsxfobj.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index 171e2faa7c50..dbc51bc5fdd6 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index bb04dec168ad..7dca287d7690 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c index c0b179883ff2..b18f1e048985 100644 --- a/drivers/acpi/acpica/psobject.c +++ b/drivers/acpi/acpica/psobject.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c index a402ad772a1e..d31f3eb23225 100644 --- a/drivers/acpi/acpica/psopcode.c +++ b/drivers/acpi/acpica/psopcode.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c index eff22950232b..1dc1fc79297e 100644 --- a/drivers/acpi/acpica/psopinfo.c +++ b/drivers/acpi/acpica/psopinfo.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c index ac88319dc111..2474ff961294 100644 --- a/drivers/acpi/acpica/psparse.c +++ b/drivers/acpi/acpica/psparse.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c index 22d7f1d6849b..f49cdcc65700 100644 --- a/drivers/acpi/acpica/psscope.c +++ b/drivers/acpi/acpica/psscope.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c index c06d6e2fc7a5..f9fa88c79b32 100644 --- a/drivers/acpi/acpica/pstree.c +++ b/drivers/acpi/acpica/pstree.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c index cd59dfe6a47d..fe151f42de3a 100644 --- a/drivers/acpi/acpica/psutils.c +++ b/drivers/acpi/acpica/psutils.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c index 22a37c82af19..bc5c779e54e8 100644 --- a/drivers/acpi/acpica/pswalk.c +++ b/drivers/acpi/acpica/pswalk.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c index c88a681586bf..d2270ade5cf8 100644 --- a/drivers/acpi/acpica/psxface.c +++ b/drivers/acpi/acpica/psxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c index a131a28bb09d..213bad89675b 100644 --- a/drivers/acpi/acpica/rsaddr.c +++ b/drivers/acpi/acpica/rsaddr.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c index 659fb718504a..576f7aae162b 100644 --- a/drivers/acpi/acpica/rscalc.c +++ b/drivers/acpi/acpica/rscalc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rscreate.c b/drivers/acpi/acpica/rscreate.c index f72ff0b54a63..fe07001ea865 100644 --- a/drivers/acpi/acpica/rscreate.c +++ b/drivers/acpi/acpica/rscreate.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsdump.c b/drivers/acpi/acpica/rsdump.c index 55fd1880efbe..bc4c4755aeb9 100644 --- a/drivers/acpi/acpica/rsdump.c +++ b/drivers/acpi/acpica/rsdump.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsdumpinfo.c b/drivers/acpi/acpica/rsdumpinfo.c index da150e17795b..c4a2a08e31ac 100644 --- a/drivers/acpi/acpica/rsdumpinfo.c +++ b/drivers/acpi/acpica/rsdumpinfo.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsinfo.c b/drivers/acpi/acpica/rsinfo.c index b0e50518d766..e819bb0f45af 100644 --- a/drivers/acpi/acpica/rsinfo.c +++ b/drivers/acpi/acpica/rsinfo.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsio.c b/drivers/acpi/acpica/rsio.c index b7a47fbc519b..eafd993592f6 100644 --- a/drivers/acpi/acpica/rsio.c +++ b/drivers/acpi/acpica/rsio.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsirq.c b/drivers/acpi/acpica/rsirq.c index 092a733c42b8..aabd73298eb8 100644 --- a/drivers/acpi/acpica/rsirq.c +++ b/drivers/acpi/acpica/rsirq.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rslist.c b/drivers/acpi/acpica/rslist.c index 36a6657dd34d..11214780ea8f 100644 --- a/drivers/acpi/acpica/rslist.c +++ b/drivers/acpi/acpica/rslist.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsmemory.c b/drivers/acpi/acpica/rsmemory.c index 273eecb3001b..05e375abc6b5 100644 --- a/drivers/acpi/acpica/rsmemory.c +++ b/drivers/acpi/acpica/rsmemory.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsmisc.c b/drivers/acpi/acpica/rsmisc.c index cc4b5486c4bc..7b4627181cc6 100644 --- a/drivers/acpi/acpica/rsmisc.c +++ b/drivers/acpi/acpica/rsmisc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsserial.c b/drivers/acpi/acpica/rsserial.c index 14d12d6eb716..87dac2812072 100644 --- a/drivers/acpi/acpica/rsserial.c +++ b/drivers/acpi/acpica/rsserial.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsutils.c b/drivers/acpi/acpica/rsutils.c index b2aeca01204a..49ff7f851d58 100644 --- a/drivers/acpi/acpica/rsutils.c +++ b/drivers/acpi/acpica/rsutils.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c index be65e65e216e..3b481f0b81c5 100644 --- a/drivers/acpi/acpica/rsxface.c +++ b/drivers/acpi/acpica/rsxface.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c index b19a2f0ea331..ec69267f1447 100644 --- a/drivers/acpi/acpica/tbdata.c +++ b/drivers/acpi/acpica/tbdata.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c index 5f051d82188d..d1763c5e4e91 100644 --- a/drivers/acpi/acpica/tbfadt.c +++ b/drivers/acpi/acpica/tbfadt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c index fea89c8d305c..999a64a48e1a 100644 --- a/drivers/acpi/acpica/tbfind.c +++ b/drivers/acpi/acpica/tbfind.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 0dfc0ac3c141..00be16da1ee2 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c index edfd7b10be19..8cdcdd2c4697 100644 --- a/drivers/acpi/acpica/tbprint.c +++ b/drivers/acpi/acpica/tbprint.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c index 0c6768d20395..30d40ff8992b 100644 --- a/drivers/acpi/acpica/tbutils.c +++ b/drivers/acpi/acpica/tbutils.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c index 5ecb8d2e6834..dca91b6f8cc2 100644 --- a/drivers/acpi/acpica/tbxface.c +++ b/drivers/acpi/acpica/tbxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c index d81f442228b8..e09b4b26300e 100644 --- a/drivers/acpi/acpica/tbxfload.c +++ b/drivers/acpi/acpica/tbxfload.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c index f9f9a7da2cad..abf3c62e1e80 100644 --- a/drivers/acpi/acpica/tbxfroot.c +++ b/drivers/acpi/acpica/tbxfroot.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c index 26a0633115be..d8540f380ae5 100644 --- a/drivers/acpi/acpica/utaddress.c +++ b/drivers/acpi/acpica/utaddress.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c index 5594a359dbf1..12fbaddbfb0d 100644 --- a/drivers/acpi/acpica/utalloc.c +++ b/drivers/acpi/acpica/utalloc.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c index 909bdb198651..95565e46a695 100644 --- a/drivers/acpi/acpica/utascii.c +++ b/drivers/acpi/acpica/utascii.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c index f17eaa009dde..2c5a14c2f46b 100644 --- a/drivers/acpi/acpica/utbuffer.c +++ b/drivers/acpi/acpica/utbuffer.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c index 531493306dee..08e6944404b3 100644 --- a/drivers/acpi/acpica/utcache.c +++ b/drivers/acpi/acpica/utcache.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c index e9382255d6c6..01434af99035 100644 --- a/drivers/acpi/acpica/utcopy.c +++ b/drivers/acpi/acpica/utcopy.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c index cff7154b7fee..2201be1bf4c2 100644 --- a/drivers/acpi/acpica/utdebug.c +++ b/drivers/acpi/acpica/utdebug.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c index 55debbad487d..1a3f316a18a8 100644 --- a/drivers/acpi/acpica/utdecode.c +++ b/drivers/acpi/acpica/utdecode.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c index c6eb9fae70f9..7d8d0208f0a3 100644 --- a/drivers/acpi/acpica/utdelete.c +++ b/drivers/acpi/acpica/utdelete.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c index 42388dcb5ccc..ce5e891291bf 100644 --- a/drivers/acpi/acpica/uterror.c +++ b/drivers/acpi/acpica/uterror.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c index 3fce7519c690..b8be0b82a130 100644 --- a/drivers/acpi/acpica/uteval.c +++ b/drivers/acpi/acpica/uteval.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utexcep.c b/drivers/acpi/acpica/utexcep.c index eb6dcab33d2f..e3dbad8b73e5 100644 --- a/drivers/acpi/acpica/utexcep.c +++ b/drivers/acpi/acpica/utexcep.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c index 230a50c82f22..933595b0e594 100644 --- a/drivers/acpi/acpica/utglobal.c +++ b/drivers/acpi/acpica/utglobal.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c index fb406daf47fa..f5886d557a94 100644 --- a/drivers/acpi/acpica/uthex.c +++ b/drivers/acpi/acpica/uthex.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c index a6eb580ee21d..db3c3c1d33da 100644 --- a/drivers/acpi/acpica/utids.c +++ b/drivers/acpi/acpica/utids.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c index 45eeb0dcf283..a2005b030347 100644 --- a/drivers/acpi/acpica/utinit.c +++ b/drivers/acpi/acpica/utinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c index db2d9910866e..0636074a4c23 100644 --- a/drivers/acpi/acpica/utlock.c +++ b/drivers/acpi/acpica/utlock.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utmath.c b/drivers/acpi/acpica/utmath.c index 2055a858e5f5..eddf71990433 100644 --- a/drivers/acpi/acpica/utmath.c +++ b/drivers/acpi/acpica/utmath.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c index 45c78c2adbf0..a331313ad5fa 100644 --- a/drivers/acpi/acpica/utmisc.c +++ b/drivers/acpi/acpica/utmisc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c index 524ba931d5e8..6767bd1626f7 100644 --- a/drivers/acpi/acpica/utmutex.c +++ b/drivers/acpi/acpica/utmutex.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utnonansi.c b/drivers/acpi/acpica/utnonansi.c index 33a0970646df..94219610e259 100644 --- a/drivers/acpi/acpica/utnonansi.c +++ b/drivers/acpi/acpica/utnonansi.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c index cb3db9fed50d..375901c0a596 100644 --- a/drivers/acpi/acpica/utobject.c +++ b/drivers/acpi/acpica/utobject.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c index f6b8dd24b006..00ea104f6a0a 100644 --- a/drivers/acpi/acpica/utosi.c +++ b/drivers/acpi/acpica/utosi.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utownerid.c b/drivers/acpi/acpica/utownerid.c index 1b3ee74a87eb..9923dfa708be 100644 --- a/drivers/acpi/acpica/utownerid.c +++ b/drivers/acpi/acpica/utownerid.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c index 350709f23e4c..ae6fef02b692 100644 --- a/drivers/acpi/acpica/utpredef.c +++ b/drivers/acpi/acpica/utpredef.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c index c008589b41bd..ac07700f5b79 100644 --- a/drivers/acpi/acpica/utprint.c +++ b/drivers/acpi/acpica/utprint.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utresdecode.c b/drivers/acpi/acpica/utresdecode.c index e15a2538558b..93fa3450ca88 100644 --- a/drivers/acpi/acpica/utresdecode.c +++ b/drivers/acpi/acpica/utresdecode.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c index f9801d13547f..4d289d9c734c 100644 --- a/drivers/acpi/acpica/utresrc.c +++ b/drivers/acpi/acpica/utresrc.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utstate.c b/drivers/acpi/acpica/utstate.c index eafabcd2fada..7750c48739d8 100644 --- a/drivers/acpi/acpica/utstate.c +++ b/drivers/acpi/acpica/utstate.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c index 9eacbcb9e4f4..a9507d1976ff 100644 --- a/drivers/acpi/acpica/utstring.c +++ b/drivers/acpi/acpica/utstring.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utstrsuppt.c b/drivers/acpi/acpica/utstrsuppt.c index 97f48d71f9e6..6fc76f0b60e9 100644 --- a/drivers/acpi/acpica/utstrsuppt.c +++ b/drivers/acpi/acpica/utstrsuppt.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utstrtoul64.c b/drivers/acpi/acpica/utstrtoul64.c index e2067dcb9389..9f7cef1de34a 100644 --- a/drivers/acpi/acpica/utstrtoul64.c +++ b/drivers/acpi/acpica/utstrtoul64.c @@ -6,7 +6,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c index 633b4e2c669f..8cc70ca4e0fb 100644 --- a/drivers/acpi/acpica/uttrack.c +++ b/drivers/acpi/acpica/uttrack.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c index 5028e06718b1..95946fdb55d5 100644 --- a/drivers/acpi/acpica/utuuid.c +++ b/drivers/acpi/acpica/utuuid.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c index 6b9ba4029f8e..25ef2ce64603 100644 --- a/drivers/acpi/acpica/utxface.c +++ b/drivers/acpi/acpica/utxface.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c index 9da4f8ef2e77..a78861ded894 100644 --- a/drivers/acpi/acpica/utxferror.c +++ b/drivers/acpi/acpica/utxferror.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c index 6d5180601cf2..e727db52a55e 100644 --- a/drivers/acpi/acpica/utxfinit.c +++ b/drivers/acpi/acpica/utxfinit.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/acpica/utxfmutex.c b/drivers/acpi/acpica/utxfmutex.c index 0b85f113f726..764782fcf1bd 100644 --- a/drivers/acpi/acpica/utxfmutex.c +++ b/drivers/acpi/acpica/utxfmutex.c @@ -5,7 +5,7 @@ ******************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 19bc440820e6..7128488a3a72 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -1209,6 +1209,22 @@ static const struct dmi_system_id bat_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "UX305LA"), }, }, + { + .callback = battery_full_discharging_quirk, + .ident = "ASUS UX360UA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "UX360UA"), + }, + }, + { + .callback = battery_full_discharging_quirk, + .ident = "ASUS UX410UAK", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "UX410UAK"), + }, + }, {}, }; diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index f87ed3be779a..676c9788e1c8 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -66,10 +66,37 @@ static int set_copy_dsdt(const struct dmi_system_id *id) return 0; } #endif +static int set_gbl_term_list(const struct dmi_system_id *id) +{ + acpi_gbl_parse_table_as_term_list = 1; + return 0; +} -static const struct dmi_system_id dsdt_dmi_table[] __initconst = { +static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = { + /* + * Touchpad on Dell XPS 9570/Precision M5530 doesn't work under I2C + * mode. + * https://bugzilla.kernel.org/show_bug.cgi?id=198515 + */ + { + .callback = set_gbl_term_list, + .ident = "Dell Precision M5530", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision M5530"), + }, + }, + { + .callback = set_gbl_term_list, + .ident = "Dell XPS 15 9570", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"), + }, + }, /* * Invoke DSDT corruption work-around on all Toshiba Satellite. + * DSDT will be copied to memory. * https://bugzilla.kernel.org/show_bug.cgi?id=14679 */ { @@ -83,7 +110,7 @@ static const struct dmi_system_id dsdt_dmi_table[] __initconst = { {} }; #else -static const struct dmi_system_id dsdt_dmi_table[] __initconst = { +static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = { {} }; #endif @@ -108,6 +135,7 @@ acpi_status acpi_bus_get_status_handle(acpi_handle handle, } return status; } +EXPORT_SYMBOL_GPL(acpi_bus_get_status_handle); int acpi_bus_get_status(struct acpi_device *device) { @@ -119,6 +147,12 @@ int acpi_bus_get_status(struct acpi_device *device) return 0; } + /* Battery devices must have their deps met before calling _STA */ + if (acpi_device_is_battery(device) && device->dep_unmet) { + acpi_set_device_status(device, 0); + return 0; + } + status = acpi_bus_get_status_handle(device->handle, &sta); if (ACPI_FAILURE(status)) return -ENODEV; @@ -1019,11 +1053,8 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; - /* - * If the machine falls into the DMI check table, - * DSDT will be copied to memory - */ - dmi_check_system(dsdt_dmi_table); + /* Check machine-specific quirks */ + dmi_check_system(acpi_quirks_dmi_table); status = acpi_reallocate_root_table(); if (ACPI_FAILURE(status)) { diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 06ea4749ebd9..0afbb2658cbc 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -119,7 +119,7 @@ static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr); * to PCC commands. Keeping it high enough to cover emulators where * the processors run painfully slow. */ -#define NUM_RETRIES 500 +#define NUM_RETRIES 500ULL struct cppc_attr { struct attribute attr; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 5f0071c7e2e1..abb559cd28d7 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -292,6 +292,9 @@ static int acpi_processor_get_power_info_default(struct acpi_processor *pr) pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1; pr->power.states[ACPI_STATE_C1].valid = 1; pr->power.states[ACPI_STATE_C1].entry_method = ACPI_CSTATE_HALT; + + snprintf(pr->power.states[ACPI_STATE_C1].desc, + ACPI_CX_DESC_LEN, "ACPI HLT"); } /* the C0 state only exists as a filler in our array */ pr->power.states[ACPI_STATE_C0].valid = 1; diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 18b72eec3507..c7cf48ad5cb9 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -159,7 +159,7 @@ void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) { int ret; - if (ignore_ppc) { + if (ignore_ppc || !pr->performance) { /* * Only when it is notification event, the _OST object * will be evaluated. Otherwise it is skipped. diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c index 2fa8304171e0..7a3431018e0a 100644 --- a/drivers/acpi/sbshc.c +++ b/drivers/acpi/sbshc.c @@ -275,8 +275,8 @@ static int acpi_smbus_hc_add(struct acpi_device *device) device->driver_data = hc; acpi_ec_add_query_handler(hc->ec, hc->query_bit, NULL, smbus_alarm, hc); - printk(KERN_INFO PREFIX "SBS HC: EC = 0x%p, offset = 0x%0x, query_bit = 0x%0x\n", - hc->ec, hc->offset, hc->query_bit); + dev_info(&device->dev, "SBS HC: offset = 0x%0x, query_bit = 0x%0x\n", + hc->offset, hc->query_bit); return 0; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index b0fe5272c76a..8e63d937babb 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1565,6 +1565,8 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, device_initialize(&device->dev); dev_set_uevent_suppress(&device->dev, true); acpi_init_coherency(device); + /* Assume there are unmet deps until acpi_device_dep_initialize() runs */ + device->dep_unmet = 1; } void acpi_device_add_finalize(struct acpi_device *device) @@ -1588,6 +1590,14 @@ static int acpi_add_single_object(struct acpi_device **child, } acpi_init_device_object(device, handle, type, sta); + /* + * For ACPI_BUS_TYPE_DEVICE getting the status is delayed till here so + * that we can call acpi_bus_get_status() and use its quirk handling. + * Note this must be done before the get power-/wakeup_dev-flags calls. + */ + if (type == ACPI_BUS_TYPE_DEVICE) + acpi_bus_get_status(device); + acpi_bus_get_power_flags(device); acpi_bus_get_wakeup_device_flags(device); @@ -1660,9 +1670,11 @@ static int acpi_bus_type_and_status(acpi_handle handle, int *type, return -ENODEV; *type = ACPI_BUS_TYPE_DEVICE; - status = acpi_bus_get_status_handle(handle, sta); - if (ACPI_FAILURE(status)) - *sta = 0; + /* + * acpi_add_single_object updates this once we've an acpi_device + * so that acpi_bus_get_status' quirk handling can be used. + */ + *sta = 0; break; case ACPI_TYPE_PROCESSOR: *type = ACPI_BUS_TYPE_PROCESSOR; @@ -1760,6 +1772,8 @@ static void acpi_device_dep_initialize(struct acpi_device *adev) acpi_status status; int i; + adev->dep_unmet = 0; + if (!acpi_has_method(adev->handle, "_DEP")) return; diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c index 324b35bfe781..89e97d21a89c 100644 --- a/drivers/acpi/spcr.c +++ b/drivers/acpi/spcr.c @@ -21,7 +21,7 @@ * occasionally getting stuck as 1. To avoid the potential for a hang, check * TXFE == 0 instead of BUSY == 1. This may not be suitable for all UART * implementations, so only do so if an affected platform is detected in - * parse_spcr(). + * acpi_parse_spcr(). */ bool qdf2400_e44_present; EXPORT_SYMBOL(qdf2400_e44_present); @@ -74,19 +74,21 @@ static bool xgene_8250_erratum_present(struct acpi_table_spcr *tb) } /** - * parse_spcr() - parse ACPI SPCR table and add preferred console + * acpi_parse_spcr() - parse ACPI SPCR table and add preferred console * - * @earlycon: set up earlycon for the console specified by the table + * @enable_earlycon: set up earlycon for the console specified by the table + * @enable_console: setup the console specified by the table. * * For the architectures with support for ACPI, CONFIG_ACPI_SPCR_TABLE may be * defined to parse ACPI SPCR table. As a result of the parsing preferred - * console is registered and if @earlycon is true, earlycon is set up. + * console is registered and if @enable_earlycon is true, earlycon is set up. + * If @enable_console is true the system console is also configured. * * When CONFIG_ACPI_SPCR_TABLE is defined, this function should be called * from arch initialization code as soon as the DT/ACPI decision is made. * */ -int __init parse_spcr(bool earlycon) +int __init acpi_parse_spcr(bool enable_earlycon, bool enable_console) { static char opts[64]; struct acpi_table_spcr *table; @@ -105,11 +107,8 @@ int __init parse_spcr(bool earlycon) if (ACPI_FAILURE(status)) return -ENOENT; - if (table->header.revision < 2) { - err = -ENOENT; - pr_err("wrong table version\n"); - goto done; - } + if (table->header.revision < 2) + pr_info("SPCR table version %d\n", table->header.revision); if (table->serial_port.space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { switch (ACPI_ACCESS_BIT_WIDTH(( @@ -185,7 +184,7 @@ int __init parse_spcr(bool earlycon) */ if (qdf2400_erratum_44_present(&table->header)) { qdf2400_e44_present = true; - if (earlycon) + if (enable_earlycon) uart = "qdf2400_e44"; } @@ -205,11 +204,13 @@ int __init parse_spcr(bool earlycon) pr_info("console: %s\n", opts); - if (earlycon) + if (enable_earlycon) setup_earlycon(opts); - err = add_preferred_console(uart, 0, opts + strlen(uart) + 1); - + if (enable_console) + err = add_preferred_console(uart, 0, opts + strlen(uart) + 1); + else + err = 0; done: acpi_put_table((struct acpi_table_header *)table); return err; diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 80ce2a7d224b..7bcb66ccccf3 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -456,7 +456,8 @@ static const char * const table_sigs[] = { ACPI_SIG_SLIC, ACPI_SIG_SPCR, ACPI_SIG_SPMI, ACPI_SIG_TCPA, ACPI_SIG_UEFI, ACPI_SIG_WAET, ACPI_SIG_WDAT, ACPI_SIG_WDDT, ACPI_SIG_WDRT, ACPI_SIG_DSDT, ACPI_SIG_FADT, ACPI_SIG_PSDT, - ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, NULL }; + ACPI_SIG_RSDT, ACPI_SIG_XSDT, ACPI_SIG_SSDT, ACPI_SIG_IORT, + NULL }; #define ACPI_HEADER_SIZE sizeof(struct acpi_table_header) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index d21040c5d343..15e3d3c2260d 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -4371,7 +4371,7 @@ static int binder_thread_release(struct binder_proc *proc, */ if ((thread->looper & BINDER_LOOPER_STATE_POLL) && waitqueue_active(&thread->wait)) { - wake_up_poll(&thread->wait, POLLHUP | POLLFREE); + wake_up_poll(&thread->wait, EPOLLHUP | POLLFREE); } binder_inner_proc_unlock(thread->proc); @@ -4401,7 +4401,7 @@ static __poll_t binder_poll(struct file *filp, poll_wait(filp, &thread->wait, wait); if (binder_has_work(thread, wait_for_proc_work)) - return POLLIN; + return EPOLLIN; return 0; } diff --git a/drivers/atm/he.c b/drivers/atm/he.c index e58538c29377..29f102dcfec4 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -738,13 +738,13 @@ static int he_init_cs_block_rcm(struct he_dev *he_dev) #else /* this is pretty, but avoids _divdu3 and is mostly correct */ mult = he_dev->atm_dev->link_rate / ATM_OC3_PCR; - if (rate_cps > (272 * mult)) + if (rate_cps > (272ULL * mult)) buf = 4; - else if (rate_cps > (204 * mult)) + else if (rate_cps > (204ULL * mult)) buf = 3; - else if (rate_cps > (136 * mult)) + else if (rate_cps > (136ULL * mult)) buf = 2; - else if (rate_cps > (68 * mult)) + else if (rate_cps > (68ULL * mult)) buf = 1; else buf = 0; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 528b24149bc7..1ea0e2502e8e 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2290,6 +2290,38 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, return 0; } +static int genpd_iterate_idle_states(struct device_node *dn, + struct genpd_power_state *states) +{ + int ret; + struct of_phandle_iterator it; + struct device_node *np; + int i = 0; + + ret = of_count_phandle_with_args(dn, "domain-idle-states", NULL); + if (ret <= 0) + return ret; + + /* Loop over the phandles until all the requested entry is found */ + of_for_each_phandle(&it, ret, dn, "domain-idle-states", NULL, 0) { + np = it.node; + if (!of_match_node(idle_state_match, np)) + continue; + if (states) { + ret = genpd_parse_state(&states[i], np); + if (ret) { + pr_err("Parsing idle state node %pOF failed with err %d\n", + np, ret); + of_node_put(np); + return ret; + } + } + i++; + } + + return i; +} + /** * of_genpd_parse_idle_states: Return array of idle states for the genpd. * @@ -2299,49 +2331,31 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, * * Returns the device states parsed from the OF node. The memory for the states * is allocated by this function and is the responsibility of the caller to - * free the memory after use. + * free the memory after use. If no domain idle states is found it returns + * -EINVAL and in case of errors, a negative error code. */ int of_genpd_parse_idle_states(struct device_node *dn, struct genpd_power_state **states, int *n) { struct genpd_power_state *st; - struct device_node *np; - int i = 0; - int err, ret; - int count; - struct of_phandle_iterator it; - const struct of_device_id *match_id; + int ret; - count = of_count_phandle_with_args(dn, "domain-idle-states", NULL); - if (count <= 0) - return -EINVAL; + ret = genpd_iterate_idle_states(dn, NULL); + if (ret <= 0) + return ret < 0 ? ret : -EINVAL; - st = kcalloc(count, sizeof(*st), GFP_KERNEL); + st = kcalloc(ret, sizeof(*st), GFP_KERNEL); if (!st) return -ENOMEM; - /* Loop over the phandles until all the requested entry is found */ - of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) { - np = it.node; - match_id = of_match_node(idle_state_match, np); - if (!match_id) - continue; - ret = genpd_parse_state(&st[i++], np); - if (ret) { - pr_err - ("Parsing idle state node %pOF failed with err %d\n", - np, ret); - of_node_put(np); - kfree(st); - return ret; - } + ret = genpd_iterate_idle_states(dn, st); + if (ret <= 0) { + kfree(st); + return ret < 0 ? ret : -EINVAL; } - *n = i; - if (!i) - kfree(st); - else - *states = st; + *states = st; + *n = ret; return 0; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index cc93522a6d41..8e40da093766 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -124,11 +124,13 @@ static int atomic_dec_return_safe(atomic_t *v) #define RBD_FEATURE_STRIPINGV2 (1ULL<<1) #define RBD_FEATURE_EXCLUSIVE_LOCK (1ULL<<2) #define RBD_FEATURE_DATA_POOL (1ULL<<7) +#define RBD_FEATURE_OPERATIONS (1ULL<<8) #define RBD_FEATURES_ALL (RBD_FEATURE_LAYERING | \ RBD_FEATURE_STRIPINGV2 | \ RBD_FEATURE_EXCLUSIVE_LOCK | \ - RBD_FEATURE_DATA_POOL) + RBD_FEATURE_DATA_POOL | \ + RBD_FEATURE_OPERATIONS) /* Features supported by this (client software) implementation. */ @@ -281,7 +283,6 @@ struct rbd_obj_request { int result; rbd_obj_callback_t callback; - struct completion completion; struct kref kref; }; @@ -1734,10 +1735,7 @@ static void rbd_obj_request_complete(struct rbd_obj_request *obj_request) { dout("%s: obj %p cb %p\n", __func__, obj_request, obj_request->callback); - if (obj_request->callback) - obj_request->callback(obj_request); - else - complete_all(&obj_request->completion); + obj_request->callback(obj_request); } static void rbd_obj_request_error(struct rbd_obj_request *obj_request, int err) @@ -2013,7 +2011,6 @@ rbd_obj_request_create(enum obj_request_type type) obj_request->which = BAD_WHICH; obj_request->type = type; INIT_LIST_HEAD(&obj_request->links); - init_completion(&obj_request->completion); kref_init(&obj_request->kref); dout("%s %p\n", __func__, obj_request); @@ -2129,15 +2126,13 @@ static struct rbd_img_request *rbd_img_request_create( { struct rbd_img_request *img_request; - img_request = kmem_cache_alloc(rbd_img_request_cache, GFP_NOIO); + img_request = kmem_cache_zalloc(rbd_img_request_cache, GFP_NOIO); if (!img_request) return NULL; - img_request->rq = NULL; img_request->rbd_dev = rbd_dev; img_request->offset = offset; img_request->length = length; - img_request->flags = 0; if (op_type == OBJ_OP_DISCARD) { img_request_discard_set(img_request); img_request->snapc = snapc; @@ -2149,11 +2144,8 @@ static struct rbd_img_request *rbd_img_request_create( } if (rbd_dev_parent_get(rbd_dev)) img_request_layered_set(img_request); + spin_lock_init(&img_request->completion_lock); - img_request->next_completion = 0; - img_request->callback = NULL; - img_request->result = 0; - img_request->obj_request_count = 0; INIT_LIST_HEAD(&img_request->obj_requests); kref_init(&img_request->kref); @@ -2692,8 +2684,6 @@ static int rbd_img_obj_parent_read_full(struct rbd_obj_request *obj_request) parent_request->copyup_pages = NULL; parent_request->copyup_page_count = 0; - parent_request->obj_request = NULL; - rbd_obj_request_put(obj_request); out_err: if (pages) ceph_release_page_vector(pages, page_count); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 79908e6ddbf2..4a07593c2efd 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -373,14 +373,12 @@ static ssize_t virtblk_serial_show(struct device *dev, static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL); -static void virtblk_config_changed_work(struct work_struct *work) +/* The queue's logical block size must be set before calling this */ +static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize) { - struct virtio_blk *vblk = - container_of(work, struct virtio_blk, config_work); struct virtio_device *vdev = vblk->vdev; struct request_queue *q = vblk->disk->queue; char cap_str_2[10], cap_str_10[10]; - char *envp[] = { "RESIZE=1", NULL }; unsigned long long nblocks; u64 capacity; @@ -402,13 +400,24 @@ static void virtblk_config_changed_work(struct work_struct *work) STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); dev_notice(&vdev->dev, - "new size: %llu %d-byte logical blocks (%s/%s)\n", + "[%s] %s%llu %d-byte logical blocks (%s/%s)\n", + vblk->disk->disk_name, + resize ? "new size: " : "", nblocks, queue_logical_block_size(q), cap_str_10, cap_str_2); set_capacity(vblk->disk, capacity); +} + +static void virtblk_config_changed_work(struct work_struct *work) +{ + struct virtio_blk *vblk = + container_of(work, struct virtio_blk, config_work); + char *envp[] = { "RESIZE=1", NULL }; + + virtblk_update_capacity(vblk, true); revalidate_disk(vblk->disk); kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp); } @@ -621,7 +630,6 @@ static int virtblk_probe(struct virtio_device *vdev) struct request_queue *q; int err, index; - u64 cap; u32 v, blk_size, sg_elems, opt_io_size; u16 min_io_size; u8 physical_block_exp, alignment_offset; @@ -719,17 +727,6 @@ static int virtblk_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO)) set_disk_ro(vblk->disk, 1); - /* Host must always specify the capacity. */ - virtio_cread(vdev, struct virtio_blk_config, capacity, &cap); - - /* If capacity is too big, truncate with warning. */ - if ((sector_t)cap != cap) { - dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n", - (unsigned long long)cap); - cap = (sector_t)-1; - } - set_capacity(vblk->disk, cap); - /* We can handle whatever the host told us to handle. */ blk_queue_max_segments(q, vblk->sg_elems-2); @@ -780,6 +777,7 @@ static int virtblk_probe(struct virtio_device *vdev) if (!err && opt_io_size) blk_queue_io_opt(q, blk_size * opt_io_size); + virtblk_update_capacity(vblk, false); virtio_device_ready(vdev); device_add_disk(&vdev->dev, vblk->disk); diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 0521748a1972..22f9145a426f 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -306,9 +306,9 @@ static __poll_t vhci_poll(struct file *file, poll_table *wait) poll_wait(file, &data->read_wait, wait); if (!skb_queue_empty(&data->readq)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; - return POLLOUT | POLLWRNORM; + return EPOLLOUT | EPOLLWRNORM; } static void vhci_open_timeout(struct work_struct *work) diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c index a2a1c1478cd0..a5e2f9e557ea 100644 --- a/drivers/char/apm-emulation.c +++ b/drivers/char/apm-emulation.c @@ -241,7 +241,7 @@ static __poll_t apm_poll(struct file *fp, poll_table * wait) struct apm_user *as = fp->private_data; poll_wait(fp, &apm_waitqueue, wait); - return queue_empty(&as->queue) ? 0 : POLLIN | POLLRDNORM; + return queue_empty(&as->queue) ? 0 : EPOLLIN | EPOLLRDNORM; } /* diff --git a/drivers/char/dsp56k.c b/drivers/char/dsp56k.c index 2f92cc46698b..06749e295ada 100644 --- a/drivers/char/dsp56k.c +++ b/drivers/char/dsp56k.c @@ -414,7 +414,7 @@ static __poll_t dsp56k_poll(struct file *file, poll_table *wait) { case DSP56K_DEV_56001: /* poll_wait(file, ???, wait); */ - return POLLIN | POLLRDNORM | POLLOUT; + return EPOLLIN | EPOLLRDNORM | EPOLLOUT; default: printk("DSP56k driver: Unknown minor device: %d\n", dev); diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c index 2697c22e3be2..f882460b5a44 100644 --- a/drivers/char/dtlk.c +++ b/drivers/char/dtlk.c @@ -62,7 +62,7 @@ #include <linux/uaccess.h> /* for get_user, etc. */ #include <linux/wait.h> /* for wait_queue */ #include <linux/init.h> /* for __init, module_{init,exit} */ -#include <linux/poll.h> /* for POLLIN, etc. */ +#include <linux/poll.h> /* for EPOLLIN, etc. */ #include <linux/dtlk.h> /* local header file for DoubleTalk values */ #ifdef TRACING @@ -244,11 +244,11 @@ static __poll_t dtlk_poll(struct file *file, poll_table * wait) if (dtlk_has_indexing && dtlk_readable()) { del_timer(&dtlk_timer); - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; } if (dtlk_writeable()) { del_timer(&dtlk_timer); - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } /* there are no exception conditions */ diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index dbed4953f86c..be426eb2a353 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -359,7 +359,7 @@ static __poll_t hpet_poll(struct file *file, poll_table * wait) spin_unlock_irq(&hpet_lock); if (v != 0) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/char/ipmi/bt-bmc.c b/drivers/char/ipmi/bt-bmc.c index 7992c870b0a2..c95b93b7598b 100644 --- a/drivers/char/ipmi/bt-bmc.c +++ b/drivers/char/ipmi/bt-bmc.c @@ -349,10 +349,10 @@ static __poll_t bt_bmc_poll(struct file *file, poll_table *wait) ctrl = bt_inb(bt_bmc, BT_CTRL); if (ctrl & BT_CTRL_H2B_ATN) - mask |= POLLIN; + mask |= EPOLLIN; if (!(ctrl & (BT_CTRL_H_BUSY | BT_CTRL_B2H_ATN))) - mask |= POLLOUT; + mask |= EPOLLOUT; return mask; } diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index a011a7739f5e..5f1bc9174735 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -89,7 +89,7 @@ static __poll_t ipmi_poll(struct file *file, poll_table *wait) spin_lock_irqsave(&priv->recv_msg_lock, flags); if (!list_empty(&(priv->recv_msgs))) - mask |= (POLLIN | POLLRDNORM); + mask |= (EPOLLIN | EPOLLRDNORM); spin_unlock_irqrestore(&priv->recv_msg_lock, flags); diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 34bc1f3ca414..a58acdcf7414 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -895,7 +895,7 @@ static __poll_t ipmi_poll(struct file *file, poll_table *wait) spin_lock(&ipmi_read_lock); if (data_to_read) - mask |= (POLLIN | POLLRDNORM); + mask |= (EPOLLIN | EPOLLRDNORM); spin_unlock(&ipmi_read_lock); return mask; diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c index 819fe37a3683..f80965407d3c 100644 --- a/drivers/char/pcmcia/cm4040_cs.c +++ b/drivers/char/pcmcia/cm4040_cs.c @@ -423,9 +423,9 @@ static __poll_t cm4040_poll(struct file *filp, poll_table *wait) poll_wait(filp, &dev->poll_wait, wait); if (test_and_clear_bit(BS_READABLE, &dev->buffer_status)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (test_and_clear_bit(BS_WRITABLE, &dev->buffer_status)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; DEBUGP(2, dev, "<- cm4040_poll(%u)\n", mask); diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index 7a56d1a13ec3..1ae77b41050a 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -776,7 +776,7 @@ static __poll_t pp_poll(struct file *file, poll_table *wait) poll_wait(file, &pp->irq_wait, wait); if (atomic_read(&pp->irqc)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 80f2c326db47..e5b3d3ba4660 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1793,9 +1793,9 @@ random_poll(struct file *file, poll_table * wait) poll_wait(file, &random_write_wait, wait); mask = 0; if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c index c6a317120a55..0c858d027bf3 100644 --- a/drivers/char/rtc.c +++ b/drivers/char/rtc.c @@ -804,7 +804,7 @@ static __poll_t rtc_poll(struct file *file, poll_table *wait) spin_unlock_irq(&rtc_lock); if (l != 0) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } #endif diff --git a/drivers/char/snsc.c b/drivers/char/snsc.c index 7f49fa0f41d7..5918ea7499bb 100644 --- a/drivers/char/snsc.c +++ b/drivers/char/snsc.c @@ -340,10 +340,10 @@ scdrv_poll(struct file *file, struct poll_table_struct *wait) if (status > 0) { if (status & SAL_IROUTER_INTR_RECV) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } if (status & SAL_IROUTER_INTR_XMIT) { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } } diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c index fc041c462aa4..186689833231 100644 --- a/drivers/char/sonypi.c +++ b/drivers/char/sonypi.c @@ -944,7 +944,7 @@ static __poll_t sonypi_misc_poll(struct file *file, poll_table *wait) { poll_wait(file, &sonypi_device.fifo_proc_list, wait); if (kfifo_len(&sonypi_device.fifo)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 674218b50b13..e4f79f920450 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -180,15 +180,15 @@ static __poll_t vtpm_proxy_fops_poll(struct file *filp, poll_table *wait) poll_wait(filp, &proxy_dev->wq, wait); - ret = POLLOUT; + ret = EPOLLOUT; mutex_lock(&proxy_dev->buf_lock); if (proxy_dev->req_len) - ret |= POLLIN | POLLRDNORM; + ret |= EPOLLIN | EPOLLRDNORM; if (!(proxy_dev->state & STATE_OPENED_FLAG)) - ret |= POLLHUP; + ret |= EPOLLHUP; mutex_unlock(&proxy_dev->buf_lock); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 813a2e46824d..468f06134012 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -992,15 +992,15 @@ static __poll_t port_fops_poll(struct file *filp, poll_table *wait) if (!port->guest_connected) { /* Port got unplugged */ - return POLLHUP; + return EPOLLHUP; } ret = 0; if (!will_read_block(port)) - ret |= POLLIN | POLLRDNORM; + ret |= EPOLLIN | EPOLLRDNORM; if (!will_write_block(port)) - ret |= POLLOUT; + ret |= EPOLLOUT; if (!port->host_connected) - ret |= POLLHUP; + ret |= EPOLLHUP; return ret; } diff --git a/drivers/char/xillybus/xillybus_core.c b/drivers/char/xillybus/xillybus_core.c index 88e1cf475d3f..a11af94e2e65 100644 --- a/drivers/char/xillybus/xillybus_core.c +++ b/drivers/char/xillybus/xillybus_core.c @@ -1758,15 +1758,15 @@ static __poll_t xillybus_poll(struct file *filp, poll_table *wait) spin_lock_irqsave(&channel->wr_spinlock, flags); if (!channel->wr_empty || channel->wr_ready) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (channel->wr_hangup) /* - * Not POLLHUP, because its behavior is in the - * mist, and POLLIN does what we want: Wake up + * Not EPOLLHUP, because its behavior is in the + * mist, and EPOLLIN does what we want: Wake up * the read file descriptor so it sees EOF. */ - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; spin_unlock_irqrestore(&channel->wr_spinlock, flags); } @@ -1781,12 +1781,12 @@ static __poll_t xillybus_poll(struct file *filp, poll_table *wait) spin_lock_irqsave(&channel->rd_spinlock, flags); if (!channel->rd_full) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; spin_unlock_irqrestore(&channel->rd_spinlock, flags); } if (channel->endpoint->fatal_error) - mask |= POLLERR; + mask |= EPOLLERR; return mask; } diff --git a/drivers/clk/ingenic/Makefile b/drivers/clk/ingenic/Makefile index cd47b0664c2b..1456e4cdb562 100644 --- a/drivers/clk/ingenic/Makefile +++ b/drivers/clk/ingenic/Makefile @@ -1,3 +1,4 @@ obj-y += cgu.o obj-$(CONFIG_MACH_JZ4740) += jz4740-cgu.o +obj-$(CONFIG_MACH_JZ4770) += jz4770-cgu.o obj-$(CONFIG_MACH_JZ4780) += jz4780-cgu.o diff --git a/drivers/clk/ingenic/cgu.c b/drivers/clk/ingenic/cgu.c index ab393637f7b0..56a712c9075f 100644 --- a/drivers/clk/ingenic/cgu.c +++ b/drivers/clk/ingenic/cgu.c @@ -100,15 +100,13 @@ ingenic_pll_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) n += pll_info->n_offset; od_enc = ctl >> pll_info->od_shift; od_enc &= GENMASK(pll_info->od_bits - 1, 0); - bypass = !!(ctl & BIT(pll_info->bypass_bit)); + bypass = !pll_info->no_bypass_bit && + !!(ctl & BIT(pll_info->bypass_bit)); enable = !!(ctl & BIT(pll_info->enable_bit)); if (bypass) return parent_rate; - if (!enable) - return 0; - for (od = 0; od < pll_info->od_max; od++) { if (pll_info->od_encoding[od] == od_enc) break; @@ -152,17 +150,25 @@ ingenic_pll_calc(const struct ingenic_cgu_clk_info *clk_info, return div_u64((u64)parent_rate * m, n * od); } -static long -ingenic_pll_round_rate(struct clk_hw *hw, unsigned long req_rate, - unsigned long *prate) +static inline const struct ingenic_cgu_clk_info *to_clk_info( + struct ingenic_clk *ingenic_clk) { - struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); struct ingenic_cgu *cgu = ingenic_clk->cgu; const struct ingenic_cgu_clk_info *clk_info; clk_info = &cgu->clock_info[ingenic_clk->idx]; BUG_ON(clk_info->type != CGU_CLK_PLL); + return clk_info; +} + +static long +ingenic_pll_round_rate(struct clk_hw *hw, unsigned long req_rate, + unsigned long *prate) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + return ingenic_pll_calc(clk_info, req_rate, *prate, NULL, NULL, NULL); } @@ -170,19 +176,14 @@ static int ingenic_pll_set_rate(struct clk_hw *hw, unsigned long req_rate, unsigned long parent_rate) { - const unsigned timeout = 100; struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); struct ingenic_cgu *cgu = ingenic_clk->cgu; - const struct ingenic_cgu_clk_info *clk_info; - const struct ingenic_cgu_pll_info *pll_info; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; unsigned long rate, flags; - unsigned m, n, od, i; + unsigned int m, n, od; u32 ctl; - clk_info = &cgu->clock_info[ingenic_clk->idx]; - BUG_ON(clk_info->type != CGU_CLK_PLL); - pll_info = &clk_info->pll; - rate = ingenic_pll_calc(clk_info, req_rate, parent_rate, &m, &n, &od); if (rate != req_rate) @@ -201,6 +202,26 @@ ingenic_pll_set_rate(struct clk_hw *hw, unsigned long req_rate, ctl &= ~(GENMASK(pll_info->od_bits - 1, 0) << pll_info->od_shift); ctl |= pll_info->od_encoding[od - 1] << pll_info->od_shift; + writel(ctl, cgu->base + pll_info->reg); + spin_unlock_irqrestore(&cgu->lock, flags); + + return 0; +} + +static int ingenic_pll_enable(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + const unsigned int timeout = 100; + unsigned long flags; + unsigned int i; + u32 ctl; + + spin_lock_irqsave(&cgu->lock, flags); + ctl = readl(cgu->base + pll_info->reg); + ctl &= ~BIT(pll_info->bypass_bit); ctl |= BIT(pll_info->enable_bit); @@ -222,10 +243,48 @@ ingenic_pll_set_rate(struct clk_hw *hw, unsigned long req_rate, return 0; } +static void ingenic_pll_disable(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + unsigned long flags; + u32 ctl; + + spin_lock_irqsave(&cgu->lock, flags); + ctl = readl(cgu->base + pll_info->reg); + + ctl &= ~BIT(pll_info->enable_bit); + + writel(ctl, cgu->base + pll_info->reg); + spin_unlock_irqrestore(&cgu->lock, flags); +} + +static int ingenic_pll_is_enabled(struct clk_hw *hw) +{ + struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw); + struct ingenic_cgu *cgu = ingenic_clk->cgu; + const struct ingenic_cgu_clk_info *clk_info = to_clk_info(ingenic_clk); + const struct ingenic_cgu_pll_info *pll_info = &clk_info->pll; + unsigned long flags; + u32 ctl; + + spin_lock_irqsave(&cgu->lock, flags); + ctl = readl(cgu->base + pll_info->reg); + spin_unlock_irqrestore(&cgu->lock, flags); + + return !!(ctl & BIT(pll_info->enable_bit)); +} + static const struct clk_ops ingenic_pll_ops = { .recalc_rate = ingenic_pll_recalc_rate, .round_rate = ingenic_pll_round_rate, .set_rate = ingenic_pll_set_rate, + + .enable = ingenic_pll_enable, + .disable = ingenic_pll_disable, + .is_enabled = ingenic_pll_is_enabled, }; /* @@ -328,6 +387,8 @@ ingenic_clk_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) div *= clk_info->div.div; rate /= div; + } else if (clk_info->type & CGU_CLK_FIXDIV) { + rate /= clk_info->fixdiv.div; } return rate; @@ -598,6 +659,7 @@ static int ingenic_register_clock(struct ingenic_cgu *cgu, unsigned idx) } } else if (caps & CGU_CLK_PLL) { clk_init.ops = &ingenic_pll_ops; + clk_init.flags |= CLK_SET_RATE_GATE; caps &= ~CGU_CLK_PLL; diff --git a/drivers/clk/ingenic/cgu.h b/drivers/clk/ingenic/cgu.h index e78b586536ea..9da34910bd80 100644 --- a/drivers/clk/ingenic/cgu.h +++ b/drivers/clk/ingenic/cgu.h @@ -48,6 +48,7 @@ * @bypass_bit: the index of the bypass bit in the PLL control register * @enable_bit: the index of the enable bit in the PLL control register * @stable_bit: the index of the stable bit in the PLL control register + * @no_bypass_bit: if set, the PLL has no bypass functionality */ struct ingenic_cgu_pll_info { unsigned reg; @@ -58,6 +59,7 @@ struct ingenic_cgu_pll_info { u8 bypass_bit; u8 enable_bit; u8 stable_bit; + bool no_bypass_bit; }; /** @@ -120,7 +122,7 @@ struct ingenic_cgu_gate_info { * @clk_ops: custom clock operation callbacks */ struct ingenic_cgu_custom_info { - struct clk_ops *clk_ops; + const struct clk_ops *clk_ops; }; /** diff --git a/drivers/clk/ingenic/jz4770-cgu.c b/drivers/clk/ingenic/jz4770-cgu.c new file mode 100644 index 000000000000..c78d369b9403 --- /dev/null +++ b/drivers/clk/ingenic/jz4770-cgu.c @@ -0,0 +1,483 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * JZ4770 SoC CGU driver + * Copyright 2018, Paul Cercueil <paul@crapouillou.net> + */ + +#include <linux/bitops.h> +#include <linux/clk-provider.h> +#include <linux/delay.h> +#include <linux/of.h> +#include <linux/syscore_ops.h> +#include <dt-bindings/clock/jz4770-cgu.h> +#include "cgu.h" + +/* + * CPM registers offset address definition + */ +#define CGU_REG_CPCCR 0x00 +#define CGU_REG_LCR 0x04 +#define CGU_REG_CPPCR0 0x10 +#define CGU_REG_CLKGR0 0x20 +#define CGU_REG_OPCR 0x24 +#define CGU_REG_CLKGR1 0x28 +#define CGU_REG_CPPCR1 0x30 +#define CGU_REG_USBPCR1 0x48 +#define CGU_REG_USBCDR 0x50 +#define CGU_REG_I2SCDR 0x60 +#define CGU_REG_LPCDR 0x64 +#define CGU_REG_MSC0CDR 0x68 +#define CGU_REG_UHCCDR 0x6c +#define CGU_REG_SSICDR 0x74 +#define CGU_REG_CIMCDR 0x7c +#define CGU_REG_GPSCDR 0x80 +#define CGU_REG_PCMCDR 0x84 +#define CGU_REG_GPUCDR 0x88 +#define CGU_REG_MSC1CDR 0xA4 +#define CGU_REG_MSC2CDR 0xA8 +#define CGU_REG_BCHCDR 0xAC + +/* bits within the LCR register */ +#define LCR_LPM BIT(0) /* Low Power Mode */ + +/* bits within the OPCR register */ +#define OPCR_SPENDH BIT(5) /* UHC PHY suspend */ +#define OPCR_SPENDN BIT(7) /* OTG PHY suspend */ + +/* bits within the USBPCR1 register */ +#define USBPCR1_UHC_POWER BIT(5) /* UHC PHY power down */ + +static struct ingenic_cgu *cgu; + +static int jz4770_uhc_phy_enable(struct clk_hw *hw) +{ + void __iomem *reg_opcr = cgu->base + CGU_REG_OPCR; + void __iomem *reg_usbpcr1 = cgu->base + CGU_REG_USBPCR1; + + writel(readl(reg_opcr) & ~OPCR_SPENDH, reg_opcr); + writel(readl(reg_usbpcr1) | USBPCR1_UHC_POWER, reg_usbpcr1); + return 0; +} + +static void jz4770_uhc_phy_disable(struct clk_hw *hw) +{ + void __iomem *reg_opcr = cgu->base + CGU_REG_OPCR; + void __iomem *reg_usbpcr1 = cgu->base + CGU_REG_USBPCR1; + + writel(readl(reg_usbpcr1) & ~USBPCR1_UHC_POWER, reg_usbpcr1); + writel(readl(reg_opcr) | OPCR_SPENDH, reg_opcr); +} + +static int jz4770_uhc_phy_is_enabled(struct clk_hw *hw) +{ + void __iomem *reg_opcr = cgu->base + CGU_REG_OPCR; + void __iomem *reg_usbpcr1 = cgu->base + CGU_REG_USBPCR1; + + return !(readl(reg_opcr) & OPCR_SPENDH) && + (readl(reg_usbpcr1) & USBPCR1_UHC_POWER); +} + +static const struct clk_ops jz4770_uhc_phy_ops = { + .enable = jz4770_uhc_phy_enable, + .disable = jz4770_uhc_phy_disable, + .is_enabled = jz4770_uhc_phy_is_enabled, +}; + +static int jz4770_otg_phy_enable(struct clk_hw *hw) +{ + void __iomem *reg_opcr = cgu->base + CGU_REG_OPCR; + + writel(readl(reg_opcr) | OPCR_SPENDN, reg_opcr); + + /* Wait for the clock to be stable */ + udelay(50); + return 0; +} + +static void jz4770_otg_phy_disable(struct clk_hw *hw) +{ + void __iomem *reg_opcr = cgu->base + CGU_REG_OPCR; + + writel(readl(reg_opcr) & ~OPCR_SPENDN, reg_opcr); +} + +static int jz4770_otg_phy_is_enabled(struct clk_hw *hw) +{ + void __iomem *reg_opcr = cgu->base + CGU_REG_OPCR; + + return !!(readl(reg_opcr) & OPCR_SPENDN); +} + +static const struct clk_ops jz4770_otg_phy_ops = { + .enable = jz4770_otg_phy_enable, + .disable = jz4770_otg_phy_disable, + .is_enabled = jz4770_otg_phy_is_enabled, +}; + +static const s8 pll_od_encoding[8] = { + 0x0, 0x1, -1, 0x2, -1, -1, -1, 0x3, +}; + +static const struct ingenic_cgu_clk_info jz4770_cgu_clocks[] = { + + /* External clocks */ + + [JZ4770_CLK_EXT] = { "ext", CGU_CLK_EXT }, + [JZ4770_CLK_OSC32K] = { "osc32k", CGU_CLK_EXT }, + + /* PLLs */ + + [JZ4770_CLK_PLL0] = { + "pll0", CGU_CLK_PLL, + .parents = { JZ4770_CLK_EXT }, + .pll = { + .reg = CGU_REG_CPPCR0, + .m_shift = 24, + .m_bits = 7, + .m_offset = 1, + .n_shift = 18, + .n_bits = 5, + .n_offset = 1, + .od_shift = 16, + .od_bits = 2, + .od_max = 8, + .od_encoding = pll_od_encoding, + .bypass_bit = 9, + .enable_bit = 8, + .stable_bit = 10, + }, + }, + + [JZ4770_CLK_PLL1] = { + /* TODO: PLL1 can depend on PLL0 */ + "pll1", CGU_CLK_PLL, + .parents = { JZ4770_CLK_EXT }, + .pll = { + .reg = CGU_REG_CPPCR1, + .m_shift = 24, + .m_bits = 7, + .m_offset = 1, + .n_shift = 18, + .n_bits = 5, + .n_offset = 1, + .od_shift = 16, + .od_bits = 2, + .od_max = 8, + .od_encoding = pll_od_encoding, + .enable_bit = 7, + .stable_bit = 6, + .no_bypass_bit = true, + }, + }, + + /* Main clocks */ + + [JZ4770_CLK_CCLK] = { + "cclk", CGU_CLK_DIV, + .parents = { JZ4770_CLK_PLL0, }, + .div = { CGU_REG_CPCCR, 0, 1, 4, 22, -1, -1 }, + }, + [JZ4770_CLK_H0CLK] = { + "h0clk", CGU_CLK_DIV, + .parents = { JZ4770_CLK_PLL0, }, + .div = { CGU_REG_CPCCR, 4, 1, 4, 22, -1, -1 }, + }, + [JZ4770_CLK_H1CLK] = { + "h1clk", CGU_CLK_DIV | CGU_CLK_GATE, + .parents = { JZ4770_CLK_PLL0, }, + .div = { CGU_REG_CPCCR, 24, 1, 4, 22, -1, -1 }, + .gate = { CGU_REG_LCR, 30 }, + }, + [JZ4770_CLK_H2CLK] = { + "h2clk", CGU_CLK_DIV, + .parents = { JZ4770_CLK_PLL0, }, + .div = { CGU_REG_CPCCR, 16, 1, 4, 22, -1, -1 }, + }, + [JZ4770_CLK_C1CLK] = { + "c1clk", CGU_CLK_DIV, + .parents = { JZ4770_CLK_PLL0, }, + .div = { CGU_REG_CPCCR, 12, 1, 4, 22, -1, -1 }, + }, + [JZ4770_CLK_PCLK] = { + "pclk", CGU_CLK_DIV, + .parents = { JZ4770_CLK_PLL0, }, + .div = { CGU_REG_CPCCR, 8, 1, 4, 22, -1, -1 }, + }, + + /* Those divided clocks can connect to PLL0 or PLL1 */ + + [JZ4770_CLK_MMC0_MUX] = { + "mmc0_mux", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_MSC0CDR, 30, 1 }, + .div = { CGU_REG_MSC0CDR, 0, 1, 7, -1, -1, 31 }, + .gate = { CGU_REG_MSC0CDR, 31 }, + }, + [JZ4770_CLK_MMC1_MUX] = { + "mmc1_mux", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_MSC1CDR, 30, 1 }, + .div = { CGU_REG_MSC1CDR, 0, 1, 7, -1, -1, 31 }, + .gate = { CGU_REG_MSC1CDR, 31 }, + }, + [JZ4770_CLK_MMC2_MUX] = { + "mmc2_mux", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_MSC2CDR, 30, 1 }, + .div = { CGU_REG_MSC2CDR, 0, 1, 7, -1, -1, 31 }, + .gate = { CGU_REG_MSC2CDR, 31 }, + }, + [JZ4770_CLK_CIM] = { + "cim", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_CIMCDR, 31, 1 }, + .div = { CGU_REG_CIMCDR, 0, 1, 8, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR0, 26 }, + }, + [JZ4770_CLK_UHC] = { + "uhc", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_UHCCDR, 29, 1 }, + .div = { CGU_REG_UHCCDR, 0, 1, 4, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR0, 24 }, + }, + [JZ4770_CLK_GPU] = { + "gpu", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, -1 }, + .mux = { CGU_REG_GPUCDR, 31, 1 }, + .div = { CGU_REG_GPUCDR, 0, 1, 3, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR1, 9 }, + }, + [JZ4770_CLK_BCH] = { + "bch", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_BCHCDR, 31, 1 }, + .div = { CGU_REG_BCHCDR, 0, 1, 3, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR0, 1 }, + }, + [JZ4770_CLK_LPCLK_MUX] = { + "lpclk", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_LPCDR, 29, 1 }, + .div = { CGU_REG_LPCDR, 0, 1, 11, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR0, 28 }, + }, + [JZ4770_CLK_GPS] = { + "gps", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_PLL0, JZ4770_CLK_PLL1, }, + .mux = { CGU_REG_GPSCDR, 31, 1 }, + .div = { CGU_REG_GPSCDR, 0, 1, 4, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR0, 22 }, + }, + + /* Those divided clocks can connect to EXT, PLL0 or PLL1 */ + + [JZ4770_CLK_SSI_MUX] = { + "ssi_mux", CGU_CLK_DIV | CGU_CLK_MUX, + .parents = { JZ4770_CLK_EXT, -1, + JZ4770_CLK_PLL0, JZ4770_CLK_PLL1 }, + .mux = { CGU_REG_SSICDR, 30, 2 }, + .div = { CGU_REG_SSICDR, 0, 1, 6, -1, -1, -1 }, + }, + [JZ4770_CLK_PCM_MUX] = { + "pcm_mux", CGU_CLK_DIV | CGU_CLK_MUX, + .parents = { JZ4770_CLK_EXT, -1, + JZ4770_CLK_PLL0, JZ4770_CLK_PLL1 }, + .mux = { CGU_REG_PCMCDR, 30, 2 }, + .div = { CGU_REG_PCMCDR, 0, 1, 9, -1, -1, -1 }, + }, + [JZ4770_CLK_I2S] = { + "i2s", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_EXT, -1, + JZ4770_CLK_PLL0, JZ4770_CLK_PLL1 }, + .mux = { CGU_REG_I2SCDR, 30, 2 }, + .div = { CGU_REG_I2SCDR, 0, 1, 9, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR1, 13 }, + }, + [JZ4770_CLK_OTG] = { + "usb", CGU_CLK_DIV | CGU_CLK_GATE | CGU_CLK_MUX, + .parents = { JZ4770_CLK_EXT, -1, + JZ4770_CLK_PLL0, JZ4770_CLK_PLL1 }, + .mux = { CGU_REG_USBCDR, 30, 2 }, + .div = { CGU_REG_USBCDR, 0, 1, 8, -1, -1, -1 }, + .gate = { CGU_REG_CLKGR0, 2 }, + }, + + /* Gate-only clocks */ + + [JZ4770_CLK_SSI0] = { + "ssi0", CGU_CLK_GATE, + .parents = { JZ4770_CLK_SSI_MUX, }, + .gate = { CGU_REG_CLKGR0, 4 }, + }, + [JZ4770_CLK_SSI1] = { + "ssi1", CGU_CLK_GATE, + .parents = { JZ4770_CLK_SSI_MUX, }, + .gate = { CGU_REG_CLKGR0, 19 }, + }, + [JZ4770_CLK_SSI2] = { + "ssi2", CGU_CLK_GATE, + .parents = { JZ4770_CLK_SSI_MUX, }, + .gate = { CGU_REG_CLKGR0, 20 }, + }, + [JZ4770_CLK_PCM0] = { + "pcm0", CGU_CLK_GATE, + .parents = { JZ4770_CLK_PCM_MUX, }, + .gate = { CGU_REG_CLKGR1, 8 }, + }, + [JZ4770_CLK_PCM1] = { + "pcm1", CGU_CLK_GATE, + .parents = { JZ4770_CLK_PCM_MUX, }, + .gate = { CGU_REG_CLKGR1, 10 }, + }, + [JZ4770_CLK_DMA] = { + "dma", CGU_CLK_GATE, + .parents = { JZ4770_CLK_H2CLK, }, + .gate = { CGU_REG_CLKGR0, 21 }, + }, + [JZ4770_CLK_I2C0] = { + "i2c0", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 5 }, + }, + [JZ4770_CLK_I2C1] = { + "i2c1", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 6 }, + }, + [JZ4770_CLK_I2C2] = { + "i2c2", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR1, 15 }, + }, + [JZ4770_CLK_UART0] = { + "uart0", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 15 }, + }, + [JZ4770_CLK_UART1] = { + "uart1", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 16 }, + }, + [JZ4770_CLK_UART2] = { + "uart2", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 17 }, + }, + [JZ4770_CLK_UART3] = { + "uart3", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 18 }, + }, + [JZ4770_CLK_IPU] = { + "ipu", CGU_CLK_GATE, + .parents = { JZ4770_CLK_H0CLK, }, + .gate = { CGU_REG_CLKGR0, 29 }, + }, + [JZ4770_CLK_ADC] = { + "adc", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 14 }, + }, + [JZ4770_CLK_AIC] = { + "aic", CGU_CLK_GATE, + .parents = { JZ4770_CLK_EXT, }, + .gate = { CGU_REG_CLKGR0, 8 }, + }, + [JZ4770_CLK_AUX] = { + "aux", CGU_CLK_GATE, + .parents = { JZ4770_CLK_C1CLK, }, + .gate = { CGU_REG_CLKGR1, 14 }, + }, + [JZ4770_CLK_VPU] = { + "vpu", CGU_CLK_GATE, + .parents = { JZ4770_CLK_H1CLK, }, + .gate = { CGU_REG_CLKGR1, 7 }, + }, + [JZ4770_CLK_MMC0] = { + "mmc0", CGU_CLK_GATE, + .parents = { JZ4770_CLK_MMC0_MUX, }, + .gate = { CGU_REG_CLKGR0, 3 }, + }, + [JZ4770_CLK_MMC1] = { + "mmc1", CGU_CLK_GATE, + .parents = { JZ4770_CLK_MMC1_MUX, }, + .gate = { CGU_REG_CLKGR0, 11 }, + }, + [JZ4770_CLK_MMC2] = { + "mmc2", CGU_CLK_GATE, + .parents = { JZ4770_CLK_MMC2_MUX, }, + .gate = { CGU_REG_CLKGR0, 12 }, + }, + + /* Custom clocks */ + + [JZ4770_CLK_UHC_PHY] = { + "uhc_phy", CGU_CLK_CUSTOM, + .parents = { JZ4770_CLK_UHC, -1, -1, -1 }, + .custom = { &jz4770_uhc_phy_ops }, + }, + [JZ4770_CLK_OTG_PHY] = { + "usb_phy", CGU_CLK_CUSTOM, + .parents = { JZ4770_CLK_OTG, -1, -1, -1 }, + .custom = { &jz4770_otg_phy_ops }, + }, + + [JZ4770_CLK_EXT512] = { + "ext/512", CGU_CLK_FIXDIV, + .parents = { JZ4770_CLK_EXT }, + .fixdiv = { 512 }, + }, + + [JZ4770_CLK_RTC] = { + "rtc", CGU_CLK_MUX, + .parents = { JZ4770_CLK_EXT512, JZ4770_CLK_OSC32K, }, + .mux = { CGU_REG_OPCR, 2, 1}, + }, +}; + +#if IS_ENABLED(CONFIG_PM_SLEEP) +static int jz4770_cgu_pm_suspend(void) +{ + u32 val; + + val = readl(cgu->base + CGU_REG_LCR); + writel(val | LCR_LPM, cgu->base + CGU_REG_LCR); + return 0; +} + +static void jz4770_cgu_pm_resume(void) +{ + u32 val; + + val = readl(cgu->base + CGU_REG_LCR); + writel(val & ~LCR_LPM, cgu->base + CGU_REG_LCR); +} + +static struct syscore_ops jz4770_cgu_pm_ops = { + .suspend = jz4770_cgu_pm_suspend, + .resume = jz4770_cgu_pm_resume, +}; +#endif /* CONFIG_PM_SLEEP */ + +static void __init jz4770_cgu_init(struct device_node *np) +{ + int retval; + + cgu = ingenic_cgu_new(jz4770_cgu_clocks, + ARRAY_SIZE(jz4770_cgu_clocks), np); + if (!cgu) + pr_err("%s: failed to initialise CGU\n", __func__); + + retval = ingenic_cgu_register_clocks(cgu); + if (retval) + pr_err("%s: failed to register CGU Clocks\n", __func__); + +#if IS_ENABLED(CONFIG_PM_SLEEP) + register_syscore_ops(&jz4770_cgu_pm_ops); +#endif +} + +/* We only probe via devicetree, no need for a platform driver */ +CLK_OF_DECLARE(jz4770_cgu, "ingenic,jz4770-cgu", jz4770_cgu_init); diff --git a/drivers/clk/ingenic/jz4780-cgu.c b/drivers/clk/ingenic/jz4780-cgu.c index ac3585ed8228..6427be117ff1 100644 --- a/drivers/clk/ingenic/jz4780-cgu.c +++ b/drivers/clk/ingenic/jz4780-cgu.c @@ -203,7 +203,7 @@ static int jz4780_otg_phy_set_rate(struct clk_hw *hw, unsigned long req_rate, return 0; } -static struct clk_ops jz4780_otg_phy_ops = { +static const struct clk_ops jz4780_otg_phy_ops = { .get_parent = jz4780_otg_phy_get_parent, .set_parent = jz4780_otg_phy_set_parent, diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index d8addbce40bc..608af20a3494 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -239,16 +239,6 @@ if PPC32 || PPC64 source "drivers/cpufreq/Kconfig.powerpc" endif -if AVR32 -config AVR32_AT32AP_CPUFREQ - bool "CPU frequency driver for AT32AP" - depends on PLATFORM_AT32AP - default n - help - This enables the CPU frequency driver for AT32AP processors. - If in doubt, say N. -endif - if IA64 config IA64_ACPI_CPUFREQ tristate "ACPI Processor P-States driver" diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index e07715ce8844..c60c1e141d9d 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -100,7 +100,6 @@ obj-$(CONFIG_POWERNV_CPUFREQ) += powernv-cpufreq.o ################################################################################## # Other platform drivers -obj-$(CONFIG_AVR32_AT32AP_CPUFREQ) += at32ap-cpufreq.o obj-$(CONFIG_BFIN_CPU_FREQ) += blackfin-cpufreq.o obj-$(CONFIG_BMIPS_CPUFREQ) += bmips-cpufreq.o obj-$(CONFIG_CRIS_MACH_ARTPEC3) += cris-artpec3-cpufreq.o diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c index 042023bbbf62..be926d9a66e5 100644 --- a/drivers/cpufreq/amd_freq_sensitivity.c +++ b/drivers/cpufreq/amd_freq_sensitivity.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> +#include <linux/pci.h> #include <linux/percpu-defs.h> #include <linux/init.h> #include <linux/mod_devicetable.h> @@ -109,12 +110,18 @@ out: static int __init amd_freq_sensitivity_init(void) { u64 val; + struct pci_dev *pcidev; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return -ENODEV; - if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK)) - return -ENODEV; + pcidev = pci_get_device(PCI_VENDOR_ID_AMD, + PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, NULL); + + if (!pcidev) { + if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK)) + return -ENODEV; + } if (rdmsrl_safe(MSR_AMD64_FREQ_SENSITIVITY_ACTUAL, &val)) return -ENODEV; diff --git a/drivers/cpufreq/at32ap-cpufreq.c b/drivers/cpufreq/at32ap-cpufreq.c deleted file mode 100644 index 7b612c8bb09e..000000000000 --- a/drivers/cpufreq/at32ap-cpufreq.c +++ /dev/null @@ -1,127 +0,0 @@ -/* - * Copyright (C) 2004-2007 Atmel Corporation - * - * Based on MIPS implementation arch/mips/kernel/time.c - * Copyright 2001 MontaVista Software Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -/*#define DEBUG*/ - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/cpufreq.h> -#include <linux/io.h> -#include <linux/clk.h> -#include <linux/err.h> -#include <linux/export.h> -#include <linux/slab.h> - -static struct cpufreq_frequency_table *freq_table; - -static unsigned int ref_freq; -static unsigned long loops_per_jiffy_ref; - -static int at32_set_target(struct cpufreq_policy *policy, unsigned int index) -{ - unsigned int old_freq, new_freq; - - old_freq = policy->cur; - new_freq = freq_table[index].frequency; - - if (!ref_freq) { - ref_freq = old_freq; - loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy; - } - - if (old_freq < new_freq) - boot_cpu_data.loops_per_jiffy = cpufreq_scale( - loops_per_jiffy_ref, ref_freq, new_freq); - clk_set_rate(policy->clk, new_freq * 1000); - if (new_freq < old_freq) - boot_cpu_data.loops_per_jiffy = cpufreq_scale( - loops_per_jiffy_ref, ref_freq, new_freq); - - return 0; -} - -static int at32_cpufreq_driver_init(struct cpufreq_policy *policy) -{ - unsigned int frequency, rate, min_freq; - struct clk *cpuclk; - int retval, steps, i; - - if (policy->cpu != 0) - return -EINVAL; - - cpuclk = clk_get(NULL, "cpu"); - if (IS_ERR(cpuclk)) { - pr_debug("cpufreq: could not get CPU clk\n"); - retval = PTR_ERR(cpuclk); - goto out_err; - } - - min_freq = (clk_round_rate(cpuclk, 1) + 500) / 1000; - frequency = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000; - policy->cpuinfo.transition_latency = 0; - - /* - * AVR32 CPU frequency rate scales in power of two between maximum and - * minimum, also add space for the table end marker. - * - * Further validate that the frequency is usable, and append it to the - * frequency table. - */ - steps = fls(frequency / min_freq) + 1; - freq_table = kzalloc(steps * sizeof(struct cpufreq_frequency_table), - GFP_KERNEL); - if (!freq_table) { - retval = -ENOMEM; - goto out_err_put_clk; - } - - for (i = 0; i < (steps - 1); i++) { - rate = clk_round_rate(cpuclk, frequency * 1000) / 1000; - - if (rate != frequency) - freq_table[i].frequency = CPUFREQ_ENTRY_INVALID; - else - freq_table[i].frequency = frequency; - - frequency /= 2; - } - - policy->clk = cpuclk; - freq_table[steps - 1].frequency = CPUFREQ_TABLE_END; - - retval = cpufreq_table_validate_and_show(policy, freq_table); - if (!retval) { - printk("cpufreq: AT32AP CPU frequency driver\n"); - return 0; - } - - kfree(freq_table); -out_err_put_clk: - clk_put(cpuclk); -out_err: - return retval; -} - -static struct cpufreq_driver at32_driver = { - .name = "at32ap", - .init = at32_cpufreq_driver_init, - .verify = cpufreq_generic_frequency_table_verify, - .target_index = at32_set_target, - .get = cpufreq_generic_get, - .flags = CPUFREQ_STICKY, -}; - -static int __init at32_cpufreq_init(void) -{ - return cpufreq_register_driver(&at32_driver); -} -late_initcall(at32_cpufreq_init); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 421f318c0e66..de33ebf008ad 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1686,6 +1686,9 @@ void cpufreq_resume(void) if (!cpufreq_driver) return; + if (unlikely(!cpufreq_suspended)) + return; + cpufreq_suspended = false; if (!has_target() && !cpufreq_driver->resume) diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c index b6b369c22272..932caa386ece 100644 --- a/drivers/cpufreq/exynos5440-cpufreq.c +++ b/drivers/cpufreq/exynos5440-cpufreq.c @@ -115,10 +115,10 @@ static struct cpufreq_freqs freqs; static int init_div_table(void) { struct cpufreq_frequency_table *pos, *freq_tbl = dvfs_info->freq_table; - unsigned int tmp, clk_div, ema_div, freq, volt_id; + unsigned int tmp, clk_div, ema_div, freq, volt_id, idx; struct dev_pm_opp *opp; - cpufreq_for_each_entry(pos, freq_tbl) { + cpufreq_for_each_entry_idx(pos, freq_tbl, idx) { opp = dev_pm_opp_find_freq_exact(dvfs_info->dev, pos->frequency * 1000, true); if (IS_ERR(opp)) { @@ -154,8 +154,7 @@ static int init_div_table(void) tmp = (clk_div | ema_div | (volt_id << P0_7_VDD_SHIFT) | ((freq / FREQ_UNIT) << P0_7_FREQ_SHIFT)); - __raw_writel(tmp, dvfs_info->base + XMU_PMU_P0_7 + 4 * - (pos - freq_tbl)); + __raw_writel(tmp, dvfs_info->base + XMU_PMU_P0_7 + 4 * idx); dev_pm_opp_put(opp); } diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 3bbbf9e6960c..6d007f824ca7 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -143,10 +143,9 @@ int cpufreq_table_index_unsorted(struct cpufreq_policy *policy, break; } - cpufreq_for_each_valid_entry(pos, table) { + cpufreq_for_each_valid_entry_idx(pos, table, i) { freq = pos->frequency; - i = pos - table; if ((freq < policy->min) || (freq > policy->max)) continue; if (freq == target_freq) { @@ -211,15 +210,16 @@ int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy, unsigned int freq) { struct cpufreq_frequency_table *pos, *table = policy->freq_table; + int idx; if (unlikely(!table)) { pr_debug("%s: Unable to find frequency table\n", __func__); return -ENOENT; } - cpufreq_for_each_valid_entry(pos, table) + cpufreq_for_each_valid_entry_idx(pos, table, idx) if (pos->frequency == freq) - return pos - table; + return idx; return -EINVAL; } diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 741f22e5cee3..ff67859948b3 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -504,6 +504,7 @@ static struct platform_driver imx6q_cpufreq_platdrv = { }; module_platform_driver(imx6q_cpufreq_platdrv); +MODULE_ALIAS("platform:imx6q-cpufreq"); MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>"); MODULE_DESCRIPTION("Freescale i.MX6Q cpufreq driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 7edf7a0e5a96..6d084c61ee25 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -779,6 +779,8 @@ static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) return 0; } +static void intel_pstate_hwp_enable(struct cpudata *cpudata); + static int intel_pstate_resume(struct cpufreq_policy *policy) { if (!hwp_active) @@ -786,6 +788,9 @@ static int intel_pstate_resume(struct cpufreq_policy *policy) mutex_lock(&intel_pstate_limits_lock); + if (policy->cpu == 0) + intel_pstate_hwp_enable(all_cpu_data[policy->cpu]); + all_cpu_data[policy->cpu]->epp_policy = 0; intel_pstate_hwp_set(policy->cpu); diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c index 5faa37c5b091..942632a27b50 100644 --- a/drivers/cpufreq/longhaul.c +++ b/drivers/cpufreq/longhaul.c @@ -600,7 +600,7 @@ static void longhaul_setup_voltagescaling(void) /* Calculate kHz for one voltage step */ kHz_step = (highest_speed - min_vid_speed) / numvscales; - cpufreq_for_each_entry(freq_pos, longhaul_table) { + cpufreq_for_each_entry_idx(freq_pos, longhaul_table, j) { speed = freq_pos->frequency; if (speed > min_vid_speed) pos = (speed - min_vid_speed) / kHz_step + minvid.pos; @@ -609,7 +609,7 @@ static void longhaul_setup_voltagescaling(void) freq_pos->driver_data |= mV_vrm_table[pos] << 8; vid = vrm_mV_table[mV_vrm_table[pos]]; pr_info("f: %d kHz, index: %d, vid: %d mV\n", - speed, (int)(freq_pos - longhaul_table), vid.mV); + speed, j, vid.mV); } can_scale_voltage = 1; diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c index b257fc7d5204..75dfbd2a58ea 100644 --- a/drivers/cpufreq/pasemi-cpufreq.c +++ b/drivers/cpufreq/pasemi-cpufreq.c @@ -139,7 +139,7 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) struct cpufreq_frequency_table *pos; const u32 *max_freqp; u32 max_freq; - int cur_astate; + int cur_astate, idx; struct resource res; struct device_node *cpu, *dn; int err = -ENODEV; @@ -198,9 +198,9 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy) pr_debug("initializing frequency table\n"); /* initialize frequency table */ - cpufreq_for_each_entry(pos, pas_freqs) { + cpufreq_for_each_entry_idx(pos, pas_freqs, idx) { pos->frequency = get_astate_freq(pos->driver_data) * 100000; - pr_debug("%d: %d\n", (int)(pos - pas_freqs), pos->frequency); + pr_debug("%d: %d\n", idx, pos->frequency); } cur_astate = get_cur_astate(policy->cpu); diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index 247fcbfa4cb5..c32a833e1b00 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -145,6 +145,7 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy) if (IS_ERR(priv->clk)) { dev_err(cpu_dev, "%s: Failed to get clk for cpu: %d\n", __func__, cpu_dev->id); + ret = PTR_ERR(priv->clk); goto out_free_cpufreq_table; } @@ -197,11 +198,8 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy) static void scpi_cpufreq_ready(struct cpufreq_policy *policy) { struct scpi_data *priv = policy->driver_data; - struct thermal_cooling_device *cdev; - cdev = of_cpufreq_cooling_register(policy); - if (!IS_ERR(cdev)) - priv->cdev = cdev; + priv->cdev = of_cpufreq_cooling_register(policy); } static struct cpufreq_driver scpi_cpufreq_driver = { diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 75d280cb2dc0..e843cf410373 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -228,12 +228,16 @@ static int instantiate_rng(struct device *ctrldev, int state_handle_mask, * without any error (HW optimizations for later * CAAM eras), then try again. */ + if (ret) + break; + rdsta_val = rd_reg32(&ctrl->r4tst[0].rdsta) & RDSTA_IFMASK; if ((status && status != JRSTA_SSRC_JUMP_HALT_CC) || - !(rdsta_val & (1 << sh_idx))) + !(rdsta_val & (1 << sh_idx))) { ret = -EAGAIN; - if (ret) break; + } + dev_info(ctrldev, "Instantiated RNG4 SH%d\n", sh_idx); /* Clear the contents before recreating the descriptor */ memset(desc, 0x00, CAAM_CMD_SZ * 7); diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig index 6d626606b9c5..b9dfae47aefd 100644 --- a/drivers/crypto/ccp/Kconfig +++ b/drivers/crypto/ccp/Kconfig @@ -1,5 +1,6 @@ config CRYPTO_DEV_CCP_DD tristate "Secure Processor device driver" + depends on CPU_SUP_AMD || ARM64 default m help Provides AMD Secure Processor device driver. @@ -32,3 +33,14 @@ config CRYPTO_DEV_CCP_CRYPTO Support for using the cryptographic API with the AMD Cryptographic Coprocessor. This module supports offload of SHA and AES algorithms. If you choose 'M' here, this module will be called ccp_crypto. + +config CRYPTO_DEV_SP_PSP + bool "Platform Security Processor (PSP) device" + default y + depends on CRYPTO_DEV_CCP_DD && X86_64 + help + Provide support for the AMD Platform Security Processor (PSP). + The PSP is a dedicated processor that provides support for key + management commands in Secure Encrypted Virtualization (SEV) mode, + along with software-based Trusted Execution Environment (TEE) to + enable third-party trusted applications. diff --git a/drivers/crypto/ccp/Makefile b/drivers/crypto/ccp/Makefile index c4ce726b931e..51d1c0cf66c7 100644 --- a/drivers/crypto/ccp/Makefile +++ b/drivers/crypto/ccp/Makefile @@ -8,6 +8,7 @@ ccp-$(CONFIG_CRYPTO_DEV_SP_CCP) += ccp-dev.o \ ccp-dmaengine.o \ ccp-debugfs.o ccp-$(CONFIG_PCI) += sp-pci.o +ccp-$(CONFIG_CRYPTO_DEV_SP_PSP) += psp-dev.o obj-$(CONFIG_CRYPTO_DEV_CCP_CRYPTO) += ccp-crypto.o ccp-crypto-objs := ccp-crypto-main.o \ diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c new file mode 100644 index 000000000000..fcfa5b1eae61 --- /dev/null +++ b/drivers/crypto/ccp/psp-dev.c @@ -0,0 +1,805 @@ +/* + * AMD Platform Security Processor (PSP) interface + * + * Copyright (C) 2016-2017 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/sched.h> +#include <linux/interrupt.h> +#include <linux/spinlock.h> +#include <linux/spinlock_types.h> +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/delay.h> +#include <linux/hw_random.h> +#include <linux/ccp.h> + +#include "sp-dev.h" +#include "psp-dev.h" + +#define DEVICE_NAME "sev" + +static DEFINE_MUTEX(sev_cmd_mutex); +static struct sev_misc_dev *misc_dev; +static struct psp_device *psp_master; + +static struct psp_device *psp_alloc_struct(struct sp_device *sp) +{ + struct device *dev = sp->dev; + struct psp_device *psp; + + psp = devm_kzalloc(dev, sizeof(*psp), GFP_KERNEL); + if (!psp) + return NULL; + + psp->dev = dev; + psp->sp = sp; + + snprintf(psp->name, sizeof(psp->name), "psp-%u", sp->ord); + + return psp; +} + +static irqreturn_t psp_irq_handler(int irq, void *data) +{ + struct psp_device *psp = data; + unsigned int status; + int reg; + + /* Read the interrupt status: */ + status = ioread32(psp->io_regs + PSP_P2CMSG_INTSTS); + + /* Check if it is command completion: */ + if (!(status & BIT(PSP_CMD_COMPLETE_REG))) + goto done; + + /* Check if it is SEV command completion: */ + reg = ioread32(psp->io_regs + PSP_CMDRESP); + if (reg & PSP_CMDRESP_RESP) { + psp->sev_int_rcvd = 1; + wake_up(&psp->sev_int_queue); + } + +done: + /* Clear the interrupt status by writing the same value we read. */ + iowrite32(status, psp->io_regs + PSP_P2CMSG_INTSTS); + + return IRQ_HANDLED; +} + +static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg) +{ + psp->sev_int_rcvd = 0; + + wait_event(psp->sev_int_queue, psp->sev_int_rcvd); + *reg = ioread32(psp->io_regs + PSP_CMDRESP); +} + +static int sev_cmd_buffer_len(int cmd) +{ + switch (cmd) { + case SEV_CMD_INIT: return sizeof(struct sev_data_init); + case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status); + case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr); + case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import); + case SEV_CMD_PDH_CERT_EXPORT: return sizeof(struct sev_data_pdh_cert_export); + case SEV_CMD_LAUNCH_START: return sizeof(struct sev_data_launch_start); + case SEV_CMD_LAUNCH_UPDATE_DATA: return sizeof(struct sev_data_launch_update_data); + case SEV_CMD_LAUNCH_UPDATE_VMSA: return sizeof(struct sev_data_launch_update_vmsa); + case SEV_CMD_LAUNCH_FINISH: return sizeof(struct sev_data_launch_finish); + case SEV_CMD_LAUNCH_MEASURE: return sizeof(struct sev_data_launch_measure); + case SEV_CMD_ACTIVATE: return sizeof(struct sev_data_activate); + case SEV_CMD_DEACTIVATE: return sizeof(struct sev_data_deactivate); + case SEV_CMD_DECOMMISSION: return sizeof(struct sev_data_decommission); + case SEV_CMD_GUEST_STATUS: return sizeof(struct sev_data_guest_status); + case SEV_CMD_DBG_DECRYPT: return sizeof(struct sev_data_dbg); + case SEV_CMD_DBG_ENCRYPT: return sizeof(struct sev_data_dbg); + case SEV_CMD_SEND_START: return sizeof(struct sev_data_send_start); + case SEV_CMD_SEND_UPDATE_DATA: return sizeof(struct sev_data_send_update_data); + case SEV_CMD_SEND_UPDATE_VMSA: return sizeof(struct sev_data_send_update_vmsa); + case SEV_CMD_SEND_FINISH: return sizeof(struct sev_data_send_finish); + case SEV_CMD_RECEIVE_START: return sizeof(struct sev_data_receive_start); + case SEV_CMD_RECEIVE_FINISH: return sizeof(struct sev_data_receive_finish); + case SEV_CMD_RECEIVE_UPDATE_DATA: return sizeof(struct sev_data_receive_update_data); + case SEV_CMD_RECEIVE_UPDATE_VMSA: return sizeof(struct sev_data_receive_update_vmsa); + case SEV_CMD_LAUNCH_UPDATE_SECRET: return sizeof(struct sev_data_launch_secret); + default: return 0; + } + + return 0; +} + +static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) +{ + struct psp_device *psp = psp_master; + unsigned int phys_lsb, phys_msb; + unsigned int reg, ret = 0; + + if (!psp) + return -ENODEV; + + /* Get the physical address of the command buffer */ + phys_lsb = data ? lower_32_bits(__psp_pa(data)) : 0; + phys_msb = data ? upper_32_bits(__psp_pa(data)) : 0; + + dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x\n", + cmd, phys_msb, phys_lsb); + + print_hex_dump_debug("(in): ", DUMP_PREFIX_OFFSET, 16, 2, data, + sev_cmd_buffer_len(cmd), false); + + iowrite32(phys_lsb, psp->io_regs + PSP_CMDBUFF_ADDR_LO); + iowrite32(phys_msb, psp->io_regs + PSP_CMDBUFF_ADDR_HI); + + reg = cmd; + reg <<= PSP_CMDRESP_CMD_SHIFT; + reg |= PSP_CMDRESP_IOC; + iowrite32(reg, psp->io_regs + PSP_CMDRESP); + + /* wait for command completion */ + sev_wait_cmd_ioc(psp, ®); + + if (psp_ret) + *psp_ret = reg & PSP_CMDRESP_ERR_MASK; + + if (reg & PSP_CMDRESP_ERR_MASK) { + dev_dbg(psp->dev, "sev command %#x failed (%#010x)\n", + cmd, reg & PSP_CMDRESP_ERR_MASK); + ret = -EIO; + } + + print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, + sev_cmd_buffer_len(cmd), false); + + return ret; +} + +static int sev_do_cmd(int cmd, void *data, int *psp_ret) +{ + int rc; + + mutex_lock(&sev_cmd_mutex); + rc = __sev_do_cmd_locked(cmd, data, psp_ret); + mutex_unlock(&sev_cmd_mutex); + + return rc; +} + +static int __sev_platform_init_locked(int *error) +{ + struct psp_device *psp = psp_master; + int rc = 0; + + if (!psp) + return -ENODEV; + + if (psp->sev_state == SEV_STATE_INIT) + return 0; + + rc = __sev_do_cmd_locked(SEV_CMD_INIT, &psp->init_cmd_buf, error); + if (rc) + return rc; + + psp->sev_state = SEV_STATE_INIT; + dev_dbg(psp->dev, "SEV firmware initialized\n"); + + return rc; +} + +int sev_platform_init(int *error) +{ + int rc; + + mutex_lock(&sev_cmd_mutex); + rc = __sev_platform_init_locked(error); + mutex_unlock(&sev_cmd_mutex); + + return rc; +} +EXPORT_SYMBOL_GPL(sev_platform_init); + +static int __sev_platform_shutdown_locked(int *error) +{ + int ret; + + ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, 0, error); + if (ret) + return ret; + + psp_master->sev_state = SEV_STATE_UNINIT; + dev_dbg(psp_master->dev, "SEV firmware shutdown\n"); + + return ret; +} + +static int sev_platform_shutdown(int *error) +{ + int rc; + + mutex_lock(&sev_cmd_mutex); + rc = __sev_platform_shutdown_locked(NULL); + mutex_unlock(&sev_cmd_mutex); + + return rc; +} + +static int sev_get_platform_state(int *state, int *error) +{ + int rc; + + rc = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, + &psp_master->status_cmd_buf, error); + if (rc) + return rc; + + *state = psp_master->status_cmd_buf.state; + return rc; +} + +static int sev_ioctl_do_reset(struct sev_issue_cmd *argp) +{ + int state, rc; + + /* + * The SEV spec requires that FACTORY_RESET must be issued in + * UNINIT state. Before we go further lets check if any guest is + * active. + * + * If FW is in WORKING state then deny the request otherwise issue + * SHUTDOWN command do INIT -> UNINIT before issuing the FACTORY_RESET. + * + */ + rc = sev_get_platform_state(&state, &argp->error); + if (rc) + return rc; + + if (state == SEV_STATE_WORKING) + return -EBUSY; + + if (state == SEV_STATE_INIT) { + rc = __sev_platform_shutdown_locked(&argp->error); + if (rc) + return rc; + } + + return __sev_do_cmd_locked(SEV_CMD_FACTORY_RESET, 0, &argp->error); +} + +static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp) +{ + struct sev_user_data_status *data = &psp_master->status_cmd_buf; + int ret; + + ret = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, data, &argp->error); + if (ret) + return ret; + + if (copy_to_user((void __user *)argp->data, data, sizeof(*data))) + ret = -EFAULT; + + return ret; +} + +static int sev_ioctl_do_pek_pdh_gen(int cmd, struct sev_issue_cmd *argp) +{ + int rc; + + if (psp_master->sev_state == SEV_STATE_UNINIT) { + rc = __sev_platform_init_locked(&argp->error); + if (rc) + return rc; + } + + return __sev_do_cmd_locked(cmd, 0, &argp->error); +} + +static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp) +{ + struct sev_user_data_pek_csr input; + struct sev_data_pek_csr *data; + void *blob = NULL; + int ret; + + if (copy_from_user(&input, (void __user *)argp->data, sizeof(input))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* userspace wants to query CSR length */ + if (!input.address || !input.length) + goto cmd; + + /* allocate a physically contiguous buffer to store the CSR blob */ + if (!access_ok(VERIFY_WRITE, input.address, input.length) || + input.length > SEV_FW_BLOB_MAX_SIZE) { + ret = -EFAULT; + goto e_free; + } + + blob = kmalloc(input.length, GFP_KERNEL); + if (!blob) { + ret = -ENOMEM; + goto e_free; + } + + data->address = __psp_pa(blob); + data->len = input.length; + +cmd: + if (psp_master->sev_state == SEV_STATE_UNINIT) { + ret = __sev_platform_init_locked(&argp->error); + if (ret) + goto e_free_blob; + } + + ret = __sev_do_cmd_locked(SEV_CMD_PEK_CSR, data, &argp->error); + + /* If we query the CSR length, FW responded with expected data. */ + input.length = data->len; + + if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) { + ret = -EFAULT; + goto e_free_blob; + } + + if (blob) { + if (copy_to_user((void __user *)input.address, blob, input.length)) + ret = -EFAULT; + } + +e_free_blob: + kfree(blob); +e_free: + kfree(data); + return ret; +} + +void *psp_copy_user_blob(u64 __user uaddr, u32 len) +{ + void *data; + + if (!uaddr || !len) + return ERR_PTR(-EINVAL); + + /* verify that blob length does not exceed our limit */ + if (len > SEV_FW_BLOB_MAX_SIZE) + return ERR_PTR(-EINVAL); + + data = kmalloc(len, GFP_KERNEL); + if (!data) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(data, (void __user *)(uintptr_t)uaddr, len)) + goto e_free; + + return data; + +e_free: + kfree(data); + return ERR_PTR(-EFAULT); +} +EXPORT_SYMBOL_GPL(psp_copy_user_blob); + +static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp) +{ + struct sev_user_data_pek_cert_import input; + struct sev_data_pek_cert_import *data; + void *pek_blob, *oca_blob; + int ret; + + if (copy_from_user(&input, (void __user *)argp->data, sizeof(input))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* copy PEK certificate blobs from userspace */ + pek_blob = psp_copy_user_blob(input.pek_cert_address, input.pek_cert_len); + if (IS_ERR(pek_blob)) { + ret = PTR_ERR(pek_blob); + goto e_free; + } + + data->pek_cert_address = __psp_pa(pek_blob); + data->pek_cert_len = input.pek_cert_len; + + /* copy PEK certificate blobs from userspace */ + oca_blob = psp_copy_user_blob(input.oca_cert_address, input.oca_cert_len); + if (IS_ERR(oca_blob)) { + ret = PTR_ERR(oca_blob); + goto e_free_pek; + } + + data->oca_cert_address = __psp_pa(oca_blob); + data->oca_cert_len = input.oca_cert_len; + + /* If platform is not in INIT state then transition it to INIT */ + if (psp_master->sev_state != SEV_STATE_INIT) { + ret = __sev_platform_init_locked(&argp->error); + if (ret) + goto e_free_oca; + } + + ret = __sev_do_cmd_locked(SEV_CMD_PEK_CERT_IMPORT, data, &argp->error); + +e_free_oca: + kfree(oca_blob); +e_free_pek: + kfree(pek_blob); +e_free: + kfree(data); + return ret; +} + +static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp) +{ + struct sev_user_data_pdh_cert_export input; + void *pdh_blob = NULL, *cert_blob = NULL; + struct sev_data_pdh_cert_export *data; + int ret; + + if (copy_from_user(&input, (void __user *)argp->data, sizeof(input))) + return -EFAULT; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* Userspace wants to query the certificate length. */ + if (!input.pdh_cert_address || + !input.pdh_cert_len || + !input.cert_chain_address) + goto cmd; + + /* Allocate a physically contiguous buffer to store the PDH blob. */ + if ((input.pdh_cert_len > SEV_FW_BLOB_MAX_SIZE) || + !access_ok(VERIFY_WRITE, input.pdh_cert_address, input.pdh_cert_len)) { + ret = -EFAULT; + goto e_free; + } + + /* Allocate a physically contiguous buffer to store the cert chain blob. */ + if ((input.cert_chain_len > SEV_FW_BLOB_MAX_SIZE) || + !access_ok(VERIFY_WRITE, input.cert_chain_address, input.cert_chain_len)) { + ret = -EFAULT; + goto e_free; + } + + pdh_blob = kmalloc(input.pdh_cert_len, GFP_KERNEL); + if (!pdh_blob) { + ret = -ENOMEM; + goto e_free; + } + + data->pdh_cert_address = __psp_pa(pdh_blob); + data->pdh_cert_len = input.pdh_cert_len; + + cert_blob = kmalloc(input.cert_chain_len, GFP_KERNEL); + if (!cert_blob) { + ret = -ENOMEM; + goto e_free_pdh; + } + + data->cert_chain_address = __psp_pa(cert_blob); + data->cert_chain_len = input.cert_chain_len; + +cmd: + /* If platform is not in INIT state then transition it to INIT. */ + if (psp_master->sev_state != SEV_STATE_INIT) { + ret = __sev_platform_init_locked(&argp->error); + if (ret) + goto e_free_cert; + } + + ret = __sev_do_cmd_locked(SEV_CMD_PDH_CERT_EXPORT, data, &argp->error); + + /* If we query the length, FW responded with expected data. */ + input.cert_chain_len = data->cert_chain_len; + input.pdh_cert_len = data->pdh_cert_len; + + if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) { + ret = -EFAULT; + goto e_free_cert; + } + + if (pdh_blob) { + if (copy_to_user((void __user *)input.pdh_cert_address, + pdh_blob, input.pdh_cert_len)) { + ret = -EFAULT; + goto e_free_cert; + } + } + + if (cert_blob) { + if (copy_to_user((void __user *)input.cert_chain_address, + cert_blob, input.cert_chain_len)) + ret = -EFAULT; + } + +e_free_cert: + kfree(cert_blob); +e_free_pdh: + kfree(pdh_blob); +e_free: + kfree(data); + return ret; +} + +static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct sev_issue_cmd input; + int ret = -EFAULT; + + if (!psp_master) + return -ENODEV; + + if (ioctl != SEV_ISSUE_CMD) + return -EINVAL; + + if (copy_from_user(&input, argp, sizeof(struct sev_issue_cmd))) + return -EFAULT; + + if (input.cmd > SEV_MAX) + return -EINVAL; + + mutex_lock(&sev_cmd_mutex); + + switch (input.cmd) { + + case SEV_FACTORY_RESET: + ret = sev_ioctl_do_reset(&input); + break; + case SEV_PLATFORM_STATUS: + ret = sev_ioctl_do_platform_status(&input); + break; + case SEV_PEK_GEN: + ret = sev_ioctl_do_pek_pdh_gen(SEV_CMD_PEK_GEN, &input); + break; + case SEV_PDH_GEN: + ret = sev_ioctl_do_pek_pdh_gen(SEV_CMD_PDH_GEN, &input); + break; + case SEV_PEK_CSR: + ret = sev_ioctl_do_pek_csr(&input); + break; + case SEV_PEK_CERT_IMPORT: + ret = sev_ioctl_do_pek_import(&input); + break; + case SEV_PDH_CERT_EXPORT: + ret = sev_ioctl_do_pdh_export(&input); + break; + default: + ret = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &input, sizeof(struct sev_issue_cmd))) + ret = -EFAULT; +out: + mutex_unlock(&sev_cmd_mutex); + + return ret; +} + +static const struct file_operations sev_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = sev_ioctl, +}; + +int sev_platform_status(struct sev_user_data_status *data, int *error) +{ + return sev_do_cmd(SEV_CMD_PLATFORM_STATUS, data, error); +} +EXPORT_SYMBOL_GPL(sev_platform_status); + +int sev_guest_deactivate(struct sev_data_deactivate *data, int *error) +{ + return sev_do_cmd(SEV_CMD_DEACTIVATE, data, error); +} +EXPORT_SYMBOL_GPL(sev_guest_deactivate); + +int sev_guest_activate(struct sev_data_activate *data, int *error) +{ + return sev_do_cmd(SEV_CMD_ACTIVATE, data, error); +} +EXPORT_SYMBOL_GPL(sev_guest_activate); + +int sev_guest_decommission(struct sev_data_decommission *data, int *error) +{ + return sev_do_cmd(SEV_CMD_DECOMMISSION, data, error); +} +EXPORT_SYMBOL_GPL(sev_guest_decommission); + +int sev_guest_df_flush(int *error) +{ + return sev_do_cmd(SEV_CMD_DF_FLUSH, 0, error); +} +EXPORT_SYMBOL_GPL(sev_guest_df_flush); + +static void sev_exit(struct kref *ref) +{ + struct sev_misc_dev *misc_dev = container_of(ref, struct sev_misc_dev, refcount); + + misc_deregister(&misc_dev->misc); +} + +static int sev_misc_init(struct psp_device *psp) +{ + struct device *dev = psp->dev; + int ret; + + /* + * SEV feature support can be detected on multiple devices but the SEV + * FW commands must be issued on the master. During probe, we do not + * know the master hence we create /dev/sev on the first device probe. + * sev_do_cmd() finds the right master device to which to issue the + * command to the firmware. + */ + if (!misc_dev) { + struct miscdevice *misc; + + misc_dev = devm_kzalloc(dev, sizeof(*misc_dev), GFP_KERNEL); + if (!misc_dev) + return -ENOMEM; + + misc = &misc_dev->misc; + misc->minor = MISC_DYNAMIC_MINOR; + misc->name = DEVICE_NAME; + misc->fops = &sev_fops; + + ret = misc_register(misc); + if (ret) + return ret; + + kref_init(&misc_dev->refcount); + } else { + kref_get(&misc_dev->refcount); + } + + init_waitqueue_head(&psp->sev_int_queue); + psp->sev_misc = misc_dev; + dev_dbg(dev, "registered SEV device\n"); + + return 0; +} + +static int sev_init(struct psp_device *psp) +{ + /* Check if device supports SEV feature */ + if (!(ioread32(psp->io_regs + PSP_FEATURE_REG) & 1)) { + dev_dbg(psp->dev, "device does not support SEV\n"); + return 1; + } + + return sev_misc_init(psp); +} + +int psp_dev_init(struct sp_device *sp) +{ + struct device *dev = sp->dev; + struct psp_device *psp; + int ret; + + ret = -ENOMEM; + psp = psp_alloc_struct(sp); + if (!psp) + goto e_err; + + sp->psp_data = psp; + + psp->vdata = (struct psp_vdata *)sp->dev_vdata->psp_vdata; + if (!psp->vdata) { + ret = -ENODEV; + dev_err(dev, "missing driver data\n"); + goto e_err; + } + + psp->io_regs = sp->io_map + psp->vdata->offset; + + /* Disable and clear interrupts until ready */ + iowrite32(0, psp->io_regs + PSP_P2CMSG_INTEN); + iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTSTS); + + /* Request an irq */ + ret = sp_request_psp_irq(psp->sp, psp_irq_handler, psp->name, psp); + if (ret) { + dev_err(dev, "psp: unable to allocate an IRQ\n"); + goto e_err; + } + + ret = sev_init(psp); + if (ret) + goto e_irq; + + if (sp->set_psp_master_device) + sp->set_psp_master_device(sp); + + /* Enable interrupt */ + iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTEN); + + return 0; + +e_irq: + sp_free_psp_irq(psp->sp, psp); +e_err: + sp->psp_data = NULL; + + dev_notice(dev, "psp initialization failed\n"); + + return ret; +} + +void psp_dev_destroy(struct sp_device *sp) +{ + struct psp_device *psp = sp->psp_data; + + if (psp->sev_misc) + kref_put(&misc_dev->refcount, sev_exit); + + sp_free_psp_irq(sp, psp); +} + +int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd, + void *data, int *error) +{ + if (!filep || filep->f_op != &sev_fops) + return -EBADF; + + return sev_do_cmd(cmd, data, error); +} +EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user); + +void psp_pci_init(void) +{ + struct sev_user_data_status *status; + struct sp_device *sp; + int error, rc; + + sp = sp_get_psp_master_device(); + if (!sp) + return; + + psp_master = sp->psp_data; + + /* Initialize the platform */ + rc = sev_platform_init(&error); + if (rc) { + dev_err(sp->dev, "SEV: failed to INIT error %#x\n", error); + goto err; + } + + /* Display SEV firmware version */ + status = &psp_master->status_cmd_buf; + rc = sev_platform_status(status, &error); + if (rc) { + dev_err(sp->dev, "SEV: failed to get status error %#x\n", error); + goto err; + } + + dev_info(sp->dev, "SEV API:%d.%d build:%d\n", status->api_major, + status->api_minor, status->build); + return; + +err: + psp_master = NULL; +} + +void psp_pci_exit(void) +{ + if (!psp_master) + return; + + sev_platform_shutdown(NULL); +} diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h new file mode 100644 index 000000000000..c81f0b11287a --- /dev/null +++ b/drivers/crypto/ccp/psp-dev.h @@ -0,0 +1,83 @@ +/* + * AMD Platform Security Processor (PSP) interface driver + * + * Copyright (C) 2017 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __PSP_DEV_H__ +#define __PSP_DEV_H__ + +#include <linux/device.h> +#include <linux/pci.h> +#include <linux/spinlock.h> +#include <linux/mutex.h> +#include <linux/list.h> +#include <linux/wait.h> +#include <linux/dmapool.h> +#include <linux/hw_random.h> +#include <linux/bitops.h> +#include <linux/interrupt.h> +#include <linux/irqreturn.h> +#include <linux/dmaengine.h> +#include <linux/psp-sev.h> +#include <linux/miscdevice.h> + +#include "sp-dev.h" + +#define PSP_C2PMSG(_num) ((_num) << 2) +#define PSP_CMDRESP PSP_C2PMSG(32) +#define PSP_CMDBUFF_ADDR_LO PSP_C2PMSG(56) +#define PSP_CMDBUFF_ADDR_HI PSP_C2PMSG(57) +#define PSP_FEATURE_REG PSP_C2PMSG(63) + +#define PSP_P2CMSG(_num) ((_num) << 2) +#define PSP_CMD_COMPLETE_REG 1 +#define PSP_CMD_COMPLETE PSP_P2CMSG(PSP_CMD_COMPLETE_REG) + +#define PSP_P2CMSG_INTEN 0x0110 +#define PSP_P2CMSG_INTSTS 0x0114 + +#define PSP_C2PMSG_ATTR_0 0x0118 +#define PSP_C2PMSG_ATTR_1 0x011c +#define PSP_C2PMSG_ATTR_2 0x0120 +#define PSP_C2PMSG_ATTR_3 0x0124 +#define PSP_P2CMSG_ATTR_0 0x0128 + +#define PSP_CMDRESP_CMD_SHIFT 16 +#define PSP_CMDRESP_IOC BIT(0) +#define PSP_CMDRESP_RESP BIT(31) +#define PSP_CMDRESP_ERR_MASK 0xffff + +#define MAX_PSP_NAME_LEN 16 + +struct sev_misc_dev { + struct kref refcount; + struct miscdevice misc; +}; + +struct psp_device { + struct list_head entry; + + struct psp_vdata *vdata; + char name[MAX_PSP_NAME_LEN]; + + struct device *dev; + struct sp_device *sp; + + void __iomem *io_regs; + + int sev_state; + unsigned int sev_int_rcvd; + wait_queue_head_t sev_int_queue; + struct sev_misc_dev *sev_misc; + struct sev_user_data_status status_cmd_buf; + struct sev_data_init init_cmd_buf; +}; + +#endif /* __PSP_DEV_H */ diff --git a/drivers/crypto/ccp/sp-dev.c b/drivers/crypto/ccp/sp-dev.c index bef387c8abfd..eb0da6572720 100644 --- a/drivers/crypto/ccp/sp-dev.c +++ b/drivers/crypto/ccp/sp-dev.c @@ -198,6 +198,8 @@ int sp_init(struct sp_device *sp) if (sp->dev_vdata->ccp_vdata) ccp_dev_init(sp); + if (sp->dev_vdata->psp_vdata) + psp_dev_init(sp); return 0; } @@ -206,6 +208,9 @@ void sp_destroy(struct sp_device *sp) if (sp->dev_vdata->ccp_vdata) ccp_dev_destroy(sp); + if (sp->dev_vdata->psp_vdata) + psp_dev_destroy(sp); + sp_del_device(sp); } @@ -237,6 +242,27 @@ int sp_resume(struct sp_device *sp) } #endif +struct sp_device *sp_get_psp_master_device(void) +{ + struct sp_device *i, *ret = NULL; + unsigned long flags; + + write_lock_irqsave(&sp_unit_lock, flags); + if (list_empty(&sp_units)) + goto unlock; + + list_for_each_entry(i, &sp_units, entry) { + if (i->psp_data) + break; + } + + if (i->get_psp_master_device) + ret = i->get_psp_master_device(); +unlock: + write_unlock_irqrestore(&sp_unit_lock, flags); + return ret; +} + static int __init sp_mod_init(void) { #ifdef CONFIG_X86 @@ -246,6 +272,10 @@ static int __init sp_mod_init(void) if (ret) return ret; +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + psp_pci_init(); +#endif + return 0; #endif @@ -265,6 +295,11 @@ static int __init sp_mod_init(void) static void __exit sp_mod_exit(void) { #ifdef CONFIG_X86 + +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + psp_pci_exit(); +#endif + sp_pci_exit(); #endif diff --git a/drivers/crypto/ccp/sp-dev.h b/drivers/crypto/ccp/sp-dev.h index 5ab486ade1ad..acb197b66ced 100644 --- a/drivers/crypto/ccp/sp-dev.h +++ b/drivers/crypto/ccp/sp-dev.h @@ -42,12 +42,17 @@ struct ccp_vdata { const unsigned int offset; const unsigned int rsamax; }; + +struct psp_vdata { + const unsigned int offset; +}; + /* Structure to hold SP device data */ struct sp_dev_vdata { const unsigned int bar; const struct ccp_vdata *ccp_vdata; - void *psp_vdata; + const struct psp_vdata *psp_vdata; }; struct sp_device { @@ -68,6 +73,10 @@ struct sp_device { /* DMA caching attribute support */ unsigned int axcache; + /* get and set master device */ + struct sp_device*(*get_psp_master_device)(void); + void (*set_psp_master_device)(struct sp_device *); + bool irq_registered; bool use_tasklet; @@ -103,6 +112,7 @@ void sp_free_ccp_irq(struct sp_device *sp, void *data); int sp_request_psp_irq(struct sp_device *sp, irq_handler_t handler, const char *name, void *data); void sp_free_psp_irq(struct sp_device *sp, void *data); +struct sp_device *sp_get_psp_master_device(void); #ifdef CONFIG_CRYPTO_DEV_SP_CCP @@ -130,4 +140,20 @@ static inline int ccp_dev_resume(struct sp_device *sp) } #endif /* CONFIG_CRYPTO_DEV_SP_CCP */ +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + +int psp_dev_init(struct sp_device *sp); +void psp_pci_init(void); +void psp_dev_destroy(struct sp_device *sp); +void psp_pci_exit(void); + +#else /* !CONFIG_CRYPTO_DEV_SP_PSP */ + +static inline int psp_dev_init(struct sp_device *sp) { return 0; } +static inline void psp_pci_init(void) { } +static inline void psp_dev_destroy(struct sp_device *sp) { } +static inline void psp_pci_exit(void) { } + +#endif /* CONFIG_CRYPTO_DEV_SP_PSP */ + #endif diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c index 9859aa683a28..f5f43c50698a 100644 --- a/drivers/crypto/ccp/sp-pci.c +++ b/drivers/crypto/ccp/sp-pci.c @@ -25,6 +25,7 @@ #include <linux/ccp.h> #include "ccp-dev.h" +#include "psp-dev.h" #define MSIX_VECTORS 2 @@ -32,6 +33,7 @@ struct sp_pci { int msix_count; struct msix_entry msix_entry[MSIX_VECTORS]; }; +static struct sp_device *sp_dev_master; static int sp_get_msix_irqs(struct sp_device *sp) { @@ -108,6 +110,45 @@ static void sp_free_irqs(struct sp_device *sp) sp->psp_irq = 0; } +static bool sp_pci_is_master(struct sp_device *sp) +{ + struct device *dev_cur, *dev_new; + struct pci_dev *pdev_cur, *pdev_new; + + dev_new = sp->dev; + dev_cur = sp_dev_master->dev; + + pdev_new = to_pci_dev(dev_new); + pdev_cur = to_pci_dev(dev_cur); + + if (pdev_new->bus->number < pdev_cur->bus->number) + return true; + + if (PCI_SLOT(pdev_new->devfn) < PCI_SLOT(pdev_cur->devfn)) + return true; + + if (PCI_FUNC(pdev_new->devfn) < PCI_FUNC(pdev_cur->devfn)) + return true; + + return false; +} + +static void psp_set_master(struct sp_device *sp) +{ + if (!sp_dev_master) { + sp_dev_master = sp; + return; + } + + if (sp_pci_is_master(sp)) + sp_dev_master = sp; +} + +static struct sp_device *psp_get_master(void) +{ + return sp_dev_master; +} + static int sp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct sp_device *sp; @@ -166,6 +207,8 @@ static int sp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto e_err; pci_set_master(pdev); + sp->set_psp_master_device = psp_set_master; + sp->get_psp_master_device = psp_get_master; ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); if (ret) { @@ -225,6 +268,12 @@ static int sp_pci_resume(struct pci_dev *pdev) } #endif +#ifdef CONFIG_CRYPTO_DEV_SP_PSP +static const struct psp_vdata psp_entry = { + .offset = 0x10500, +}; +#endif + static const struct sp_dev_vdata dev_vdata[] = { { .bar = 2, @@ -237,6 +286,9 @@ static const struct sp_dev_vdata dev_vdata[] = { #ifdef CONFIG_CRYPTO_DEV_SP_CCP .ccp_vdata = &ccpv5a, #endif +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + .psp_vdata = &psp_entry +#endif }, { .bar = 2, diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c index 0d01d1624252..63d636424161 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-prng.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-prng.c @@ -28,7 +28,7 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng); ss = algt->ss; - spin_lock(&ss->slock); + spin_lock_bh(&ss->slock); writel(mode, ss->base + SS_CTL); @@ -51,6 +51,6 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, } writel(0, ss->base + SS_CTL); - spin_unlock(&ss->slock); - return dlen; + spin_unlock_bh(&ss->slock); + return 0; } diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 9c80e0cb1664..6882fa2f8bad 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -1138,6 +1138,10 @@ static int talitos_sg_map(struct device *dev, struct scatterlist *src, struct talitos_private *priv = dev_get_drvdata(dev); bool is_sec1 = has_ftr_sec1(priv); + if (!src) { + to_talitos_ptr(ptr, 0, 0, is_sec1); + return 1; + } if (sg_count == 1) { to_talitos_ptr(ptr, sg_dma_address(src) + offset, len, is_sec1); return sg_count; diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 539450713838..d78d5fc173dc 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -135,10 +135,10 @@ static loff_t dma_buf_llseek(struct file *file, loff_t offset, int whence) * Userspace can query the state of these implicitly tracked fences using poll() * and related system calls: * - * - Checking for POLLIN, i.e. read access, can be use to query the state of the + * - Checking for EPOLLIN, i.e. read access, can be use to query the state of the * most recent write or exclusive fence. * - * - Checking for POLLOUT, i.e. write access, can be used to query the state of + * - Checking for EPOLLOUT, i.e. write access, can be used to query the state of * all attached fences, shared and exclusive ones. * * Note that this only signals the completion of the respective fences, i.e. the @@ -168,13 +168,13 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) - return POLLERR; + return EPOLLERR; resv = dmabuf->resv; poll_wait(file, &dmabuf->poll, poll); - events = poll_requested_events(poll) & (POLLIN | POLLOUT); + events = poll_requested_events(poll) & (EPOLLIN | EPOLLOUT); if (!events) return 0; @@ -193,12 +193,12 @@ retry: goto retry; } - if (fence_excl && (!(events & POLLOUT) || shared_count == 0)) { + if (fence_excl && (!(events & EPOLLOUT) || shared_count == 0)) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; - __poll_t pevents = POLLIN; + __poll_t pevents = EPOLLIN; if (shared_count == 0) - pevents |= POLLOUT; + pevents |= EPOLLOUT; spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) { @@ -228,19 +228,19 @@ retry: } } - if ((events & POLLOUT) && shared_count > 0) { + if ((events & EPOLLOUT) && shared_count > 0) { struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; int i; /* Only queue a new callback if no event has fired yet */ spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) - events &= ~POLLOUT; + events &= ~EPOLLOUT; else - dcb->active = POLLOUT; + dcb->active = EPOLLOUT; spin_unlock_irq(&dmabuf->poll.lock); - if (!(events & POLLOUT)) + if (!(events & EPOLLOUT)) goto out; for (i = 0; i < shared_count; ++i) { @@ -253,14 +253,14 @@ retry: * * call dma_buf_poll_cb and force a recheck! */ - events &= ~POLLOUT; + events &= ~EPOLLOUT; dma_buf_poll_cb(NULL, &dcb->cb); break; } if (!dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb)) { dma_fence_put(fence); - events &= ~POLLOUT; + events &= ~EPOLLOUT; break; } dma_fence_put(fence); diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 8e8c4a12a0bc..35dd06479867 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -325,7 +325,7 @@ static __poll_t sync_file_poll(struct file *file, poll_table *wait) wake_up_all(&sync_file->wq); } - return dma_fence_is_signaled(sync_file->fence) ? POLLIN : 0; + return dma_fence_is_signaled(sync_file->fence) ? EPOLLIN : 0; } static long sync_file_ioctl_merge(struct sync_file *sync_file, diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 523391bb3fbe..f0587273940e 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1792,9 +1792,9 @@ static __poll_t fw_device_op_poll(struct file *file, poll_table * pt) poll_wait(file, &client->wait, pt); if (fw_device_is_shutdown(client->device)) - mask |= POLLHUP | POLLERR; + mask |= EPOLLHUP | EPOLLERR; if (!list_empty(&client->event_list)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index fee2e9e7ea20..a128dd1126ae 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -337,10 +337,10 @@ nosy_poll(struct file *file, poll_table *pt) poll_wait(file, &client->buffer.wait, pt); if (atomic_read(&client->buffer.size) > 0) - ret = POLLIN | POLLRDNORM; + ret = EPOLLIN | EPOLLRDNORM; if (list_empty(&client->lynx->link)) - ret |= POLLHUP; + ret |= EPOLLHUP; return ret; } diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c index 8b25d31e8401..c80ec1d03274 100644 --- a/drivers/firmware/psci.c +++ b/drivers/firmware/psci.c @@ -59,7 +59,10 @@ bool psci_tos_resident_on(int cpu) return cpu == resident_cpu; } -struct psci_operations psci_ops; +struct psci_operations psci_ops = { + .conduit = PSCI_CONDUIT_NONE, + .smccc_version = SMCCC_VERSION_1_0, +}; typedef unsigned long (psci_fn)(unsigned long, unsigned long, unsigned long, unsigned long); @@ -210,6 +213,22 @@ static unsigned long psci_migrate_info_up_cpu(void) 0, 0, 0); } +static void set_conduit(enum psci_conduit conduit) +{ + switch (conduit) { + case PSCI_CONDUIT_HVC: + invoke_psci_fn = __invoke_psci_fn_hvc; + break; + case PSCI_CONDUIT_SMC: + invoke_psci_fn = __invoke_psci_fn_smc; + break; + default: + WARN(1, "Unexpected PSCI conduit %d\n", conduit); + } + + psci_ops.conduit = conduit; +} + static int get_set_conduit_method(struct device_node *np) { const char *method; @@ -222,9 +241,9 @@ static int get_set_conduit_method(struct device_node *np) } if (!strcmp("hvc", method)) { - invoke_psci_fn = __invoke_psci_fn_hvc; + set_conduit(PSCI_CONDUIT_HVC); } else if (!strcmp("smc", method)) { - invoke_psci_fn = __invoke_psci_fn_smc; + set_conduit(PSCI_CONDUIT_SMC); } else { pr_warn("invalid \"method\" property: %s\n", method); return -EINVAL; @@ -493,6 +512,31 @@ static void __init psci_init_migrate(void) pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid); } +static void __init psci_init_smccc(void) +{ + u32 ver = ARM_SMCCC_VERSION_1_0; + int feature; + + feature = psci_features(ARM_SMCCC_VERSION_FUNC_ID); + + if (feature != PSCI_RET_NOT_SUPPORTED) { + u32 ret; + ret = invoke_psci_fn(ARM_SMCCC_VERSION_FUNC_ID, 0, 0, 0); + if (ret == ARM_SMCCC_VERSION_1_1) { + psci_ops.smccc_version = SMCCC_VERSION_1_1; + ver = ret; + } + } + + /* + * Conveniently, the SMCCC and PSCI versions are encoded the + * same way. No, this isn't accidental. + */ + pr_info("SMC Calling Convention v%d.%d\n", + PSCI_VERSION_MAJOR(ver), PSCI_VERSION_MINOR(ver)); + +} + static void __init psci_0_2_set_functions(void) { pr_info("Using standard PSCI v0.2 function IDs\n"); @@ -541,6 +585,7 @@ static int __init psci_probe(void) psci_init_migrate(); if (PSCI_VERSION_MAJOR(ver) >= 1) { + psci_init_smccc(); psci_init_cpu_suspend(); psci_init_system_suspend(); } @@ -654,9 +699,9 @@ int __init psci_acpi_init(void) pr_info("probing for conduit method from ACPI.\n"); if (acpi_psci_use_hvc()) - invoke_psci_fn = __invoke_psci_fn_hvc; + set_conduit(PSCI_CONDUIT_HVC); else - invoke_psci_fn = __invoke_psci_fn_smc; + set_conduit(PSCI_CONDUIT_SMC); return psci_probe(); } diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index deb483064f53..a41b572eeeb1 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -694,10 +694,8 @@ static int fw_cfg_cmdline_set(const char *arg, const struct kernel_param *kp) */ fw_cfg_cmdline_dev = platform_device_register_simple("fw_cfg", PLATFORM_DEVID_NONE, res, processed); - if (IS_ERR(fw_cfg_cmdline_dev)) - return PTR_ERR(fw_cfg_cmdline_dev); - return 0; + return PTR_ERR_OR_ZERO(fw_cfg_cmdline_dev); } static int fw_cfg_cmdline_get(char *buf, const struct kernel_param *kp) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 36ca5064486e..d66de67ef307 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -630,7 +630,7 @@ static __poll_t lineevent_poll(struct file *filep, poll_wait(filep, &le->wait, wait); if (!kfifo_is_empty(&le->events)) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; return events; } @@ -775,7 +775,7 @@ static irqreturn_t lineevent_irq_thread(int irq, void *p) ret = kfifo_put(&le->events, ge); if (ret != 0) - wake_up_poll(&le->wait, POLLIN); + wake_up_poll(&le->wait, EPOLLIN); return IRQ_HANDLED; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index bb40d2529a30..239bf2a4b3c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -179,8 +179,12 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, amdgpu_gfx_bit_to_queue(adev, queue_bit, &mec, &pipe, &queue); - /* Using pipes 2/3 from MEC 2 seems cause problems */ - if (mec == 1 && pipe > 1) + /* + * 1. Using pipes 2/3 from MEC 2 seems cause problems. + * 2. It must use queue id 0, because CGPG_IDLE/SAVE/LOAD/RUN + * only can be issued on queue 0. + */ + if ((mec == 1 && pipe > 1) || queue != 0) continue; ring->me = mec + 1; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6fc16eecf2dc..5afbc5e714d0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2262,12 +2262,12 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, { const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE, AMDGPU_VM_PTE_COUNT(adev) * 8); + uint64_t init_pde_value = 0, flags; unsigned ring_instance; struct amdgpu_ring *ring; struct drm_sched_rq *rq; + unsigned long size; int r, i; - u64 flags; - uint64_t init_pde_value = 0; vm->va = RB_ROOT_CACHED; for (i = 0; i < AMDGPU_MAX_VMHUBS; i++) @@ -2318,29 +2318,21 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS | AMDGPU_GEM_CREATE_SHADOW); - r = amdgpu_bo_create(adev, - amdgpu_vm_bo_size(adev, adev->vm_manager.root_level), - align, true, - AMDGPU_GEM_DOMAIN_VRAM, - flags, - NULL, NULL, init_pde_value, &vm->root.base.bo); + size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level); + r = amdgpu_bo_create(adev, size, align, true, AMDGPU_GEM_DOMAIN_VRAM, + flags, NULL, NULL, init_pde_value, + &vm->root.base.bo); if (r) goto error_free_sched_entity; + r = amdgpu_bo_reserve(vm->root.base.bo, true); + if (r) + goto error_free_root; + vm->root.base.vm = vm; list_add_tail(&vm->root.base.bo_list, &vm->root.base.bo->va); - INIT_LIST_HEAD(&vm->root.base.vm_status); - - if (vm->use_cpu_for_update) { - r = amdgpu_bo_reserve(vm->root.base.bo, false); - if (r) - goto error_free_root; - - r = amdgpu_bo_kmap(vm->root.base.bo, NULL); - amdgpu_bo_unreserve(vm->root.base.bo); - if (r) - goto error_free_root; - } + list_add_tail(&vm->root.base.vm_status, &vm->evicted); + amdgpu_bo_unreserve(vm->root.base.bo); if (pasid) { unsigned long flags; diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c index b69ceafb7888..ee14d78be2a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c +++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c @@ -278,9 +278,9 @@ static bool vega10_ih_prescreen_iv(struct amdgpu_device *adev) /* Track retry faults in per-VM fault FIFO. */ spin_lock(&adev->vm_manager.pasid_lock); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); - spin_unlock(&adev->vm_manager.pasid_lock); - if (WARN_ON_ONCE(!vm)) { + if (!vm) { /* VM not found, process it normally */ + spin_unlock(&adev->vm_manager.pasid_lock); amdgpu_ih_clear_fault(adev, key); return true; } @@ -288,9 +288,11 @@ static bool vega10_ih_prescreen_iv(struct amdgpu_device *adev) r = kfifo_put(&vm->faults, key); if (!r) { /* FIFO is full. Ignore it until there is space */ + spin_unlock(&adev->vm_manager.pasid_lock); amdgpu_ih_clear_fault(adev, key); goto ignore_iv; } + spin_unlock(&adev->vm_manager.pasid_lock); /* It's the first fault for this address, process it normally */ return true; diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index da2b99c2d95f..1e3e05a11f7a 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -1049,7 +1049,6 @@ static int vi_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_CP_LS | AMD_CG_SUPPORT_GFX_CGTS | AMD_CG_SUPPORT_GFX_CGTS_LS | - AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_BIF_LS | AMD_CG_SUPPORT_HDP_MGCG | diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 9a17bd3639d1..e394799979a6 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -567,7 +567,7 @@ __poll_t drm_poll(struct file *filp, struct poll_table_struct *wait) poll_wait(filp, &file_priv->event_wait, wait); if (!list_empty(&file_priv->event_list)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 97bfc00d2a82..c62346fdc05d 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -119,16 +119,6 @@ static int map_aperture(struct intel_vgpu *vgpu, bool map) if (map == vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].tracked) return 0; - if (map) { - vgpu->gm.aperture_va = memremap(aperture_pa, aperture_sz, - MEMREMAP_WC); - if (!vgpu->gm.aperture_va) - return -ENOMEM; - } else { - memunmap(vgpu->gm.aperture_va); - vgpu->gm.aperture_va = NULL; - } - val = vgpu_cfg_space(vgpu)[PCI_BASE_ADDRESS_2]; if (val & PCI_BASE_ADDRESS_MEM_TYPE_64) val = *(u64 *)(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_2); @@ -141,11 +131,8 @@ static int map_aperture(struct intel_vgpu *vgpu, bool map) aperture_pa >> PAGE_SHIFT, aperture_sz >> PAGE_SHIFT, map); - if (ret) { - memunmap(vgpu->gm.aperture_va); - vgpu->gm.aperture_va = NULL; + if (ret) return ret; - } vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].tracked = map; return 0; diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 2ab584f97dfb..2fb7b34ef561 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -472,7 +472,6 @@ int intel_vgpu_get_dmabuf(struct intel_vgpu *vgpu, unsigned int dmabuf_id) ret = PTR_ERR(dmabuf); goto out_free_gem; } - obj->base.dma_buf = dmabuf; i915_gem_object_put(obj); diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c index 769c1c24ae75..70494e394d2c 100644 --- a/drivers/gpu/drm/i915/gvt/execlist.c +++ b/drivers/gpu/drm/i915/gvt/execlist.c @@ -521,24 +521,23 @@ static void init_vgpu_execlist(struct intel_vgpu *vgpu, int ring_id) ctx_status_ptr_reg = execlist_ring_mmio(vgpu->gvt, ring_id, _EL_OFFSET_STATUS_PTR); - ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg); ctx_status_ptr.read_ptr = 0; ctx_status_ptr.write_ptr = 0x7; vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw; } -static void clean_execlist(struct intel_vgpu *vgpu) +static void clean_execlist(struct intel_vgpu *vgpu, unsigned long engine_mask) { - enum intel_engine_id i; + unsigned int tmp; + struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; struct intel_engine_cs *engine; + struct intel_vgpu_submission *s = &vgpu->submission; - for_each_engine(engine, vgpu->gvt->dev_priv, i) { - struct intel_vgpu_submission *s = &vgpu->submission; - - kfree(s->ring_scan_buffer[i]); - s->ring_scan_buffer[i] = NULL; - s->ring_scan_buffer_size[i] = 0; + for_each_engine_masked(engine, dev_priv, engine_mask, tmp) { + kfree(s->ring_scan_buffer[engine->id]); + s->ring_scan_buffer[engine->id] = NULL; + s->ring_scan_buffer_size[engine->id] = 0; } } @@ -553,9 +552,10 @@ static void reset_execlist(struct intel_vgpu *vgpu, init_vgpu_execlist(vgpu, engine->id); } -static int init_execlist(struct intel_vgpu *vgpu) +static int init_execlist(struct intel_vgpu *vgpu, + unsigned long engine_mask) { - reset_execlist(vgpu, ALL_ENGINES); + reset_execlist(vgpu, engine_mask); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index a529d2bd393c..8d5317d0122d 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -997,9 +997,11 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se, static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt) { struct intel_vgpu *vgpu = spt->vgpu; + struct intel_gvt *gvt = vgpu->gvt; + struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops; struct intel_vgpu_ppgtt_spt *s; struct intel_gvt_gtt_entry se, ge; - unsigned long i; + unsigned long gfn, i; int ret; trace_spt_change(spt->vgpu->id, "born", spt, @@ -1007,9 +1009,10 @@ static int ppgtt_populate_shadow_page(struct intel_vgpu_ppgtt_spt *spt) if (gtt_type_is_pte_pt(spt->shadow_page.type)) { for_each_present_guest_entry(spt, &ge, i) { - ret = gtt_entry_p2m(vgpu, &ge, &se); - if (ret) - goto fail; + gfn = ops->get_pfn(&ge); + if (!intel_gvt_hypervisor_is_valid_gfn(vgpu, gfn) || + gtt_entry_p2m(vgpu, &ge, &se)) + ops->set_pfn(&se, gvt->gtt.scratch_mfn); ppgtt_set_shadow_entry(spt, &se, i); } return 0; @@ -1906,7 +1909,7 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, struct intel_vgpu_mm *ggtt_mm = vgpu->gtt.ggtt_mm; struct intel_gvt_gtt_pte_ops *ops = gvt->gtt.pte_ops; unsigned long g_gtt_index = off >> info->gtt_entry_size_shift; - unsigned long gma; + unsigned long gma, gfn; struct intel_gvt_gtt_entry e, m; int ret; @@ -1925,6 +1928,16 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, bytes); if (ops->test_present(&e)) { + gfn = ops->get_pfn(&e); + + /* one PTE update may be issued in multiple writes and the + * first write may not construct a valid gfn + */ + if (!intel_gvt_hypervisor_is_valid_gfn(vgpu, gfn)) { + ops->set_pfn(&m, gvt->gtt.scratch_mfn); + goto out; + } + ret = gtt_entry_p2m(vgpu, &e, &m); if (ret) { gvt_vgpu_err("fail to translate guest gtt entry\n"); @@ -1939,6 +1952,7 @@ static int emulate_gtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, ops->set_pfn(&m, gvt->gtt.scratch_mfn); } +out: ggtt_set_shadow_entry(ggtt_mm, &m, g_gtt_index); gtt_invalidate(gvt->dev_priv); ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 7dc7a80213a8..c6197d990818 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -82,7 +82,6 @@ struct intel_gvt_device_info { struct intel_vgpu_gm { u64 aperture_sz; u64 hidden_sz; - void *aperture_va; struct drm_mm_node low_gm_node; struct drm_mm_node high_gm_node; }; @@ -127,7 +126,6 @@ struct intel_vgpu_irq { struct intel_vgpu_opregion { bool mapped; void *va; - void *va_gopregion; u32 gfn[INTEL_GVT_OPREGION_PAGES]; }; @@ -152,8 +150,8 @@ enum { struct intel_vgpu_submission_ops { const char *name; - int (*init)(struct intel_vgpu *vgpu); - void (*clean)(struct intel_vgpu *vgpu); + int (*init)(struct intel_vgpu *vgpu, unsigned long engine_mask); + void (*clean)(struct intel_vgpu *vgpu, unsigned long engine_mask); void (*reset)(struct intel_vgpu *vgpu, unsigned long engine_mask); }; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 92d6468daeee..9be639aa3b55 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1494,7 +1494,6 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { - struct intel_vgpu_submission *s = &vgpu->submission; u32 data = *(u32 *)p_data; int ring_id = intel_gvt_render_mmio_to_ring_id(vgpu->gvt, offset); bool enable_execlist; @@ -1523,11 +1522,9 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, if (!enable_execlist) return 0; - if (s->active) - return 0; - ret = intel_vgpu_select_submission_ops(vgpu, - INTEL_VGPU_EXECLIST_SUBMISSION); + ENGINE_MASK(ring_id), + INTEL_VGPU_EXECLIST_SUBMISSION); if (ret) return ret; @@ -2843,6 +2840,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_A)), D_SKL_PLUS); MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_B)), D_SKL_PLUS); MMIO_D(_MMIO(_PLANE_KEYVAL_1(PIPE_C)), D_SKL_PLUS); + MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_A)), D_SKL_PLUS); + MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_B)), D_SKL_PLUS); + MMIO_D(_MMIO(_PLANE_KEYMAX_1(PIPE_C)), D_SKL_PLUS); MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_A)), D_SKL_PLUS); MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_B)), D_SKL_PLUS); MMIO_D(_MMIO(_PLANE_KEYMSK_1(PIPE_C)), D_SKL_PLUS); diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h index a1bd82feb827..f8e77e166246 100644 --- a/drivers/gpu/drm/i915/gvt/hypercall.h +++ b/drivers/gpu/drm/i915/gvt/hypercall.h @@ -58,6 +58,7 @@ struct intel_gvt_mpt { int (*set_opregion)(void *vgpu); int (*get_vfio_device)(void *vgpu); void (*put_vfio_device)(void *vgpu); + bool (*is_valid_gfn)(unsigned long handle, unsigned long gfn); }; extern struct intel_gvt_mpt xengt_mpt; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 554d1db1f3c8..909499b73d03 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -651,6 +651,39 @@ static int intel_vgpu_bar_rw(struct intel_vgpu *vgpu, int bar, uint64_t off, return ret; } +static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, uint64_t off) +{ + return off >= vgpu_aperture_offset(vgpu) && + off < vgpu_aperture_offset(vgpu) + vgpu_aperture_sz(vgpu); +} + +static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, uint64_t off, + void *buf, unsigned long count, bool is_write) +{ + void *aperture_va; + + if (!intel_vgpu_in_aperture(vgpu, off) || + !intel_vgpu_in_aperture(vgpu, off + count)) { + gvt_vgpu_err("Invalid aperture offset %llu\n", off); + return -EINVAL; + } + + aperture_va = io_mapping_map_wc(&vgpu->gvt->dev_priv->ggtt.iomap, + ALIGN_DOWN(off, PAGE_SIZE), + count + offset_in_page(off)); + if (!aperture_va) + return -EIO; + + if (is_write) + memcpy(aperture_va + offset_in_page(off), buf, count); + else + memcpy(buf, aperture_va + offset_in_page(off), count); + + io_mapping_unmap(aperture_va); + + return 0; +} + static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf, size_t count, loff_t *ppos, bool is_write) { @@ -679,8 +712,7 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf, buf, count, is_write); break; case VFIO_PCI_BAR2_REGION_INDEX: - ret = intel_vgpu_bar_rw(vgpu, PCI_BASE_ADDRESS_2, pos, - buf, count, is_write); + ret = intel_vgpu_aperture_rw(vgpu, pos, buf, count, is_write); break; case VFIO_PCI_BAR1_REGION_INDEX: case VFIO_PCI_BAR3_REGION_INDEX: @@ -1575,6 +1607,21 @@ static unsigned long kvmgt_virt_to_pfn(void *addr) return PFN_DOWN(__pa(addr)); } +static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn) +{ + struct kvmgt_guest_info *info; + struct kvm *kvm; + + if (!handle_valid(handle)) + return false; + + info = (struct kvmgt_guest_info *)handle; + kvm = info->kvm; + + return kvm_is_visible_gfn(kvm, gfn); + +} + struct intel_gvt_mpt kvmgt_mpt = { .host_init = kvmgt_host_init, .host_exit = kvmgt_host_exit, @@ -1590,6 +1637,7 @@ struct intel_gvt_mpt kvmgt_mpt = { .set_opregion = kvmgt_set_opregion, .get_vfio_device = kvmgt_get_vfio_device, .put_vfio_device = kvmgt_put_vfio_device, + .is_valid_gfn = kvmgt_is_valid_gfn, }; EXPORT_SYMBOL_GPL(kvmgt_mpt); diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 562b5ad857a4..5c869e3fdf3b 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -56,38 +56,6 @@ int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa) (reg >= gvt->device_info.gtt_start_offset \ && reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt)) -static bool vgpu_gpa_is_aperture(struct intel_vgpu *vgpu, uint64_t gpa) -{ - u64 aperture_gpa = intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_2); - u64 aperture_sz = vgpu_aperture_sz(vgpu); - - return gpa >= aperture_gpa && gpa < aperture_gpa + aperture_sz; -} - -static int vgpu_aperture_rw(struct intel_vgpu *vgpu, uint64_t gpa, - void *pdata, unsigned int size, bool is_read) -{ - u64 aperture_gpa = intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_2); - u64 offset = gpa - aperture_gpa; - - if (!vgpu_gpa_is_aperture(vgpu, gpa + size - 1)) { - gvt_vgpu_err("Aperture rw out of range, offset %llx, size %d\n", - offset, size); - return -EINVAL; - } - - if (!vgpu->gm.aperture_va) { - gvt_vgpu_err("BAR is not enabled\n"); - return -ENXIO; - } - - if (is_read) - memcpy(pdata, vgpu->gm.aperture_va + offset, size); - else - memcpy(vgpu->gm.aperture_va + offset, pdata, size); - return 0; -} - static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa, void *p_data, unsigned int bytes, bool read) { @@ -144,11 +112,6 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa, } mutex_lock(&gvt->lock); - if (vgpu_gpa_is_aperture(vgpu, pa)) { - ret = vgpu_aperture_rw(vgpu, pa, p_data, bytes, true); - goto out; - } - offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa); if (WARN_ON(bytes > 8)) @@ -222,11 +185,6 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa, mutex_lock(&gvt->lock); - if (vgpu_gpa_is_aperture(vgpu, pa)) { - ret = vgpu_aperture_rw(vgpu, pa, p_data, bytes, false); - goto out; - } - offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa); if (WARN_ON(bytes > 8)) diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 74834395dd89..73ad6e90e49d 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -80,7 +80,7 @@ static struct engine_mmio gen8_engine_mmio_list[] __cacheline_aligned = { {BCS, RING_INSTPM(BLT_RING_BASE), 0xffff, false}, /* 0x220c0 */ {BCS, RING_HWSTAM(BLT_RING_BASE), 0x0, false}, /* 0x22098 */ {BCS, RING_EXCC(BLT_RING_BASE), 0x0, false}, /* 0x22028 */ - { /* Terminated */ } + {RCS, INVALID_MMIO_REG, 0, false } /* Terminated */ }; static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { @@ -146,7 +146,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */ {RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */ {RCS, FF_SLICE_CS_CHICKEN2, 0xffff, false}, /* 0x20e4 */ - { /* Terminated */ } + {RCS, INVALID_MMIO_REG, 0, false } /* Terminated */ }; static struct { @@ -167,7 +167,7 @@ static void load_render_mocs(struct drm_i915_private *dev_priv) }; int ring_id, i; - for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) { + for (ring_id = 0; ring_id < ARRAY_SIZE(regs); ring_id++) { offset.reg = regs[ring_id]; for (i = 0; i < 64; i++) { gen9_render_mocs.control_table[ring_id][i] = @@ -310,8 +310,8 @@ static void switch_mmio(struct intel_vgpu *pre, if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) switch_mocs(pre, next, ring_id); - mmio = dev_priv->gvt->engine_mmio_list; - while (i915_mmio_reg_offset((mmio++)->reg)) { + for (mmio = dev_priv->gvt->engine_mmio_list; + i915_mmio_reg_valid(mmio->reg); mmio++) { if (mmio->ring_id != ring_id) continue; // save diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h index ca8005a6d5fa..81aff4eacbfe 100644 --- a/drivers/gpu/drm/i915/gvt/mpt.h +++ b/drivers/gpu/drm/i915/gvt/mpt.h @@ -339,4 +339,21 @@ static inline void intel_gvt_hypervisor_put_vfio_device(struct intel_vgpu *vgpu) intel_gvt_host.mpt->put_vfio_device(vgpu); } +/** + * intel_gvt_hypervisor_is_valid_gfn - check if a visible gfn + * @vgpu: a vGPU + * @gfn: guest PFN + * + * Returns: + * true on valid gfn, false on not. + */ +static inline bool intel_gvt_hypervisor_is_valid_gfn( + struct intel_vgpu *vgpu, unsigned long gfn) +{ + if (!intel_gvt_host.mpt->is_valid_gfn) + return true; + + return intel_gvt_host.mpt->is_valid_gfn(vgpu->handle, gfn); +} + #endif /* _GVT_MPT_H_ */ diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 8420d1fc3ddb..fa75a2eead90 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -299,21 +299,13 @@ int intel_vgpu_opregion_base_write_handler(struct intel_vgpu *vgpu, u32 gpa) { int i, ret = 0; - unsigned long pfn; gvt_dbg_core("emulate opregion from kernel\n"); switch (intel_gvt_host.hypervisor_type) { case INTEL_GVT_HYPERVISOR_KVM: - pfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, gpa >> PAGE_SHIFT); - vgpu_opregion(vgpu)->va_gopregion = memremap(pfn << PAGE_SHIFT, - INTEL_GVT_OPREGION_SIZE, - MEMREMAP_WB); - if (!vgpu_opregion(vgpu)->va_gopregion) { - gvt_vgpu_err("failed to map guest opregion\n"); - ret = -EFAULT; - } - vgpu_opregion(vgpu)->mapped = true; + for (i = 0; i < INTEL_GVT_OPREGION_PAGES; i++) + vgpu_opregion(vgpu)->gfn[i] = (gpa >> PAGE_SHIFT) + i; break; case INTEL_GVT_HYPERVISOR_XEN: /** @@ -352,10 +344,7 @@ void intel_vgpu_clean_opregion(struct intel_vgpu *vgpu) if (vgpu_opregion(vgpu)->mapped) map_vgpu_opregion(vgpu, false); } else if (intel_gvt_host.hypervisor_type == INTEL_GVT_HYPERVISOR_KVM) { - if (vgpu_opregion(vgpu)->mapped) { - memunmap(vgpu_opregion(vgpu)->va_gopregion); - vgpu_opregion(vgpu)->va_gopregion = NULL; - } + /* Guest opregion is released by VFIO */ } free_pages((unsigned long)vgpu_opregion(vgpu)->va, get_order(INTEL_GVT_OPREGION_SIZE)); @@ -480,19 +469,40 @@ static bool querying_capabilities(u32 scic) */ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci) { - u32 *scic, *parm; + u32 scic, parm; u32 func, subfunc; + u64 scic_pa = 0, parm_pa = 0; + int ret; switch (intel_gvt_host.hypervisor_type) { case INTEL_GVT_HYPERVISOR_XEN: - scic = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_SCIC; - parm = vgpu_opregion(vgpu)->va + INTEL_GVT_OPREGION_PARM; + scic = *((u32 *)vgpu_opregion(vgpu)->va + + INTEL_GVT_OPREGION_SCIC); + parm = *((u32 *)vgpu_opregion(vgpu)->va + + INTEL_GVT_OPREGION_PARM); break; case INTEL_GVT_HYPERVISOR_KVM: - scic = vgpu_opregion(vgpu)->va_gopregion + - INTEL_GVT_OPREGION_SCIC; - parm = vgpu_opregion(vgpu)->va_gopregion + - INTEL_GVT_OPREGION_PARM; + scic_pa = (vgpu_opregion(vgpu)->gfn[0] << PAGE_SHIFT) + + INTEL_GVT_OPREGION_SCIC; + parm_pa = (vgpu_opregion(vgpu)->gfn[0] << PAGE_SHIFT) + + INTEL_GVT_OPREGION_PARM; + + ret = intel_gvt_hypervisor_read_gpa(vgpu, scic_pa, + &scic, sizeof(scic)); + if (ret) { + gvt_vgpu_err("guest opregion read error %d, gpa 0x%llx, len %lu\n", + ret, scic_pa, sizeof(scic)); + return ret; + } + + ret = intel_gvt_hypervisor_read_gpa(vgpu, parm_pa, + &parm, sizeof(parm)); + if (ret) { + gvt_vgpu_err("guest opregion read error %d, gpa 0x%llx, len %lu\n", + ret, scic_pa, sizeof(scic)); + return ret; + } + break; default: gvt_vgpu_err("not supported hypervisor\n"); @@ -510,9 +520,9 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci) return 0; } - func = GVT_OPREGION_FUNC(*scic); - subfunc = GVT_OPREGION_SUBFUNC(*scic); - if (!querying_capabilities(*scic)) { + func = GVT_OPREGION_FUNC(scic); + subfunc = GVT_OPREGION_SUBFUNC(scic); + if (!querying_capabilities(scic)) { gvt_vgpu_err("requesting runtime service: func \"%s\"," " subfunc \"%s\"\n", opregion_func_name(func), @@ -521,11 +531,43 @@ int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci) * emulate exit status of function call, '0' means * "failure, generic, unsupported or unknown cause" */ - *scic &= ~OPREGION_SCIC_EXIT_MASK; - return 0; + scic &= ~OPREGION_SCIC_EXIT_MASK; + goto out; + } + + scic = 0; + parm = 0; + +out: + switch (intel_gvt_host.hypervisor_type) { + case INTEL_GVT_HYPERVISOR_XEN: + *((u32 *)vgpu_opregion(vgpu)->va + + INTEL_GVT_OPREGION_SCIC) = scic; + *((u32 *)vgpu_opregion(vgpu)->va + + INTEL_GVT_OPREGION_PARM) = parm; + break; + case INTEL_GVT_HYPERVISOR_KVM: + ret = intel_gvt_hypervisor_write_gpa(vgpu, scic_pa, + &scic, sizeof(scic)); + if (ret) { + gvt_vgpu_err("guest opregion write error %d, gpa 0x%llx, len %lu\n", + ret, scic_pa, sizeof(scic)); + return ret; + } + + ret = intel_gvt_hypervisor_write_gpa(vgpu, parm_pa, + &parm, sizeof(parm)); + if (ret) { + gvt_vgpu_err("guest opregion write error %d, gpa 0x%llx, len %lu\n", + ret, scic_pa, sizeof(scic)); + return ret; + } + + break; + default: + gvt_vgpu_err("not supported hypervisor\n"); + return -EINVAL; } - *scic = 0; - *parm = 0; return 0; } diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index eea1a2f92099..cc1ce361cd76 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -50,6 +50,7 @@ static bool vgpu_has_pending_workload(struct intel_vgpu *vgpu) struct vgpu_sched_data { struct list_head lru_list; struct intel_vgpu *vgpu; + bool active; ktime_t sched_in_time; ktime_t sched_out_time; @@ -308,8 +309,15 @@ static int tbs_sched_init_vgpu(struct intel_vgpu *vgpu) static void tbs_sched_clean_vgpu(struct intel_vgpu *vgpu) { + struct intel_gvt *gvt = vgpu->gvt; + struct gvt_sched_data *sched_data = gvt->scheduler.sched_data; + kfree(vgpu->sched_data); vgpu->sched_data = NULL; + + /* this vgpu id has been removed */ + if (idr_is_empty(&gvt->vgpu_idr)) + hrtimer_cancel(&sched_data->timer); } static void tbs_sched_start_schedule(struct intel_vgpu *vgpu) @@ -325,6 +333,7 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu) if (!hrtimer_active(&sched_data->timer)) hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(), sched_data->period), HRTIMER_MODE_ABS); + vgpu_data->active = true; } static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu) @@ -332,6 +341,7 @@ static void tbs_sched_stop_schedule(struct intel_vgpu *vgpu) struct vgpu_sched_data *vgpu_data = vgpu->sched_data; list_del_init(&vgpu_data->lru_list); + vgpu_data->active = false; } static struct intel_gvt_sched_policy_ops tbs_schedule_ops = { @@ -367,9 +377,12 @@ void intel_vgpu_clean_sched_policy(struct intel_vgpu *vgpu) void intel_vgpu_start_schedule(struct intel_vgpu *vgpu) { - gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id); + struct vgpu_sched_data *vgpu_data = vgpu->sched_data; - vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu); + if (!vgpu_data->active) { + gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id); + vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu); + } } void intel_gvt_kick_schedule(struct intel_gvt *gvt) @@ -382,6 +395,10 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) struct intel_gvt_workload_scheduler *scheduler = &vgpu->gvt->scheduler; int ring_id; + struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + + if (!vgpu_data->active) + return; gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id); diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 0056638b0c16..b55b3580ca1d 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -991,7 +991,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu) { struct intel_vgpu_submission *s = &vgpu->submission; - intel_vgpu_select_submission_ops(vgpu, 0); + intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); i915_gem_context_put(s->shadow_ctx); kmem_cache_destroy(s->workloads); } @@ -1079,6 +1079,7 @@ out_shadow_ctx: * */ int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu, + unsigned long engine_mask, unsigned int interface) { struct intel_vgpu_submission *s = &vgpu->submission; @@ -1091,21 +1092,21 @@ int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu, if (WARN_ON(interface >= ARRAY_SIZE(ops))) return -EINVAL; - if (s->active) { - s->ops->clean(vgpu); - s->active = false; - gvt_dbg_core("vgpu%d: de-select ops [ %s ] \n", - vgpu->id, s->ops->name); - } + if (WARN_ON(interface == 0 && engine_mask != ALL_ENGINES)) + return -EINVAL; + + if (s->active) + s->ops->clean(vgpu, engine_mask); if (interface == 0) { s->ops = NULL; s->virtual_submission_interface = 0; - gvt_dbg_core("vgpu%d: no submission ops\n", vgpu->id); + s->active = false; + gvt_dbg_core("vgpu%d: remove submission ops\n", vgpu->id); return 0; } - ret = ops[interface]->init(vgpu); + ret = ops[interface]->init(vgpu, engine_mask); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h index 3de77dfa7c59..ff175a98b19e 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.h +++ b/drivers/gpu/drm/i915/gvt/scheduler.h @@ -141,6 +141,7 @@ void intel_vgpu_reset_submission(struct intel_vgpu *vgpu, void intel_vgpu_clean_submission(struct intel_vgpu *vgpu); int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu, + unsigned long engine_mask, unsigned int interface); extern const struct intel_vgpu_submission_ops diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 4688619f6a1c..b87b19d8443c 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -258,6 +258,8 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) intel_gvt_debugfs_remove_vgpu(vgpu); idr_remove(&gvt->vgpu_idr, vgpu->id); + if (idr_is_empty(&gvt->vgpu_idr)) + intel_gvt_clean_irq(gvt); intel_vgpu_clean_sched_policy(vgpu); intel_vgpu_clean_submission(vgpu); intel_vgpu_clean_display(vgpu); @@ -518,8 +520,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_submission(vgpu, resetting_eng); /* full GPU reset or device model level reset */ if (engine_mask == ALL_ENGINES || dmlr) { - intel_vgpu_select_submission_ops(vgpu, 0); - + intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); /*fence will not be reset during virtual reset */ if (dmlr) { intel_vgpu_reset_gtt(vgpu); diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index ccb5ba043b63..95478db9998b 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1032,7 +1032,7 @@ find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) const struct drm_i915_reg_table *table = engine->reg_tables; int count = engine->reg_table_count; - do { + for (; count > 0; ++table, --count) { if (!table->master || is_master) { const struct drm_i915_reg_descriptor *reg; @@ -1040,7 +1040,7 @@ find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) if (reg != NULL) return reg; } - } while (table++, --count); + } return NULL; } @@ -1212,6 +1212,12 @@ static bool check_cmd(const struct intel_engine_cs *engine, continue; } + if (desc->bits[i].offset >= length) { + DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n", + *cmd, engine->name); + return false; + } + dword = cmd[desc->bits[i].offset] & desc->bits[i].mask; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 6c8da9d20c33..173d0095e3b2 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1842,6 +1842,8 @@ static int i915_drm_resume_early(struct drm_device *dev) if (IS_GEN9_LP(dev_priv) || !(dev_priv->suspended_to_idle && dev_priv->csr.dmc_payload)) intel_power_domains_init_hw(dev_priv, true); + else + intel_display_set_init_power(dev_priv, true); i915_gem_sanitize(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index caebd5825279..a42deebedb0f 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3717,7 +3717,11 @@ extern void intel_display_print_error_state(struct drm_i915_error_state_buf *e, struct intel_display_error_state *error); int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val); -int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u32 mbox, u32 val); +int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv, u32 mbox, + u32 val, int timeout_us); +#define sandybridge_pcode_write(dev_priv, mbox, val) \ + sandybridge_pcode_write_timeout(dev_priv, mbox, val, 500) + int skl_pcode_request(struct drm_i915_private *dev_priv, u32 mbox, u32 request, u32 reply_mask, u32 reply, int timeout_base_ms); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 8bc3283484be..dd89abd2263d 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3323,16 +3323,15 @@ i915_gem_retire_work_handler(struct work_struct *work) mutex_unlock(&dev->struct_mutex); } - /* Keep the retire handler running until we are finally idle. + /* + * Keep the retire handler running until we are finally idle. * We do not need to do this test under locking as in the worst-case * we queue the retire worker once too often. */ - if (READ_ONCE(dev_priv->gt.awake)) { - i915_queue_hangcheck(dev_priv); + if (READ_ONCE(dev_priv->gt.awake)) queue_delayed_work(dev_priv->wq, &dev_priv->gt.retire_work, round_jiffies_up_relative(HZ)); - } } static inline bool @@ -5283,6 +5282,8 @@ err_unlock: intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); mutex_unlock(&dev_priv->drm.struct_mutex); + intel_uc_fini_wq(dev_priv); + if (ret != -EIO) i915_gem_cleanup_userptr(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index c5f393870532..7e403eaa9e0f 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -377,6 +377,7 @@ static gen6_pte_t iris_pte_encode(dma_addr_t addr, static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp) { struct pagevec *pvec = &vm->free_pages; + struct pagevec stash; if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1))) i915_gem_shrink_all(vm->i915); @@ -395,7 +396,15 @@ static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp) if (likely(pvec->nr)) return pvec->pages[--pvec->nr]; - /* Otherwise batch allocate pages to amoritize cost of set_pages_wc. */ + /* + * Otherwise batch allocate pages to amoritize cost of set_pages_wc. + * + * We have to be careful as page allocation may trigger the shrinker + * (via direct reclaim) which will fill up the WC stash underneath us. + * So we add our WB pages into a temporary pvec on the stack and merge + * them into the WC stash after all the allocations are complete. + */ + pagevec_init(&stash); do { struct page *page; @@ -403,15 +412,24 @@ static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp) if (unlikely(!page)) break; - pvec->pages[pvec->nr++] = page; - } while (pagevec_space(pvec)); + stash.pages[stash.nr++] = page; + } while (stash.nr < pagevec_space(pvec)); - if (unlikely(!pvec->nr)) - return NULL; + if (stash.nr) { + int nr = min_t(int, stash.nr, pagevec_space(pvec)); + struct page **pages = stash.pages + stash.nr - nr; - set_pages_array_wc(pvec->pages, pvec->nr); + if (nr && !set_pages_array_wc(pages, nr)) { + memcpy(pvec->pages + pvec->nr, + pages, sizeof(pages[0]) * nr); + pvec->nr += nr; + stash.nr -= nr; + } - return pvec->pages[--pvec->nr]; + pagevec_release(&stash); + } + + return likely(pvec->nr) ? pvec->pages[--pvec->nr] : NULL; } static void vm_free_pages_release(struct i915_address_space *vm, @@ -1341,15 +1359,18 @@ static int gen8_ppgtt_alloc_pd(struct i915_address_space *vm, int count = gen8_pte_count(start, length); if (pt == vm->scratch_pt) { + pd->used_pdes++; + pt = alloc_pt(vm); - if (IS_ERR(pt)) + if (IS_ERR(pt)) { + pd->used_pdes--; goto unwind; + } if (count < GEN8_PTES || intel_vgpu_active(vm->i915)) gen8_initialize_pt(vm, pt); gen8_ppgtt_set_pde(vm, pd, pt, pde); - pd->used_pdes++; GEM_BUG_ON(pd->used_pdes > I915_PDES); } @@ -1373,13 +1394,16 @@ static int gen8_ppgtt_alloc_pdp(struct i915_address_space *vm, gen8_for_each_pdpe(pd, pdp, start, length, pdpe) { if (pd == vm->scratch_pd) { + pdp->used_pdpes++; + pd = alloc_pd(vm); - if (IS_ERR(pd)) + if (IS_ERR(pd)) { + pdp->used_pdpes--; goto unwind; + } gen8_initialize_pd(vm, pd); gen8_ppgtt_set_pdpe(vm, pdp, pd, pdpe); - pdp->used_pdpes++; GEM_BUG_ON(pdp->used_pdpes > i915_pdpes_per_pdp(vm)); mark_tlbs_dirty(i915_vm_to_ppgtt(vm)); @@ -2287,12 +2311,23 @@ static void gen8_check_and_clear_faults(struct drm_i915_private *dev_priv) u32 fault = I915_READ(GEN8_RING_FAULT_REG); if (fault & RING_FAULT_VALID) { + u32 fault_data0, fault_data1; + u64 fault_addr; + + fault_data0 = I915_READ(GEN8_FAULT_TLB_DATA0); + fault_data1 = I915_READ(GEN8_FAULT_TLB_DATA1); + fault_addr = ((u64)(fault_data1 & FAULT_VA_HIGH_BITS) << 44) | + ((u64)fault_data0 << 12); + DRM_DEBUG_DRIVER("Unexpected fault\n" - "\tAddr: 0x%08lx\n" + "\tAddr: 0x%08x_%08x\n" + "\tAddress space: %s\n" "\tEngine ID: %d\n" "\tSource ID: %d\n" "\tType: %d\n", - fault & PAGE_MASK, + upper_32_bits(fault_addr), + lower_32_bits(fault_addr), + fault_data1 & FAULT_GTT_SEL ? "GGTT" : "PPGTT", GEN8_RING_FAULT_ENGINE_ID(fault), RING_FAULT_SRCID(fault), RING_FAULT_FAULT_TYPE(fault)); diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index d575109f7a7f..e09d18df8b7f 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -276,6 +276,8 @@ static void mark_busy(struct drm_i915_private *i915) intel_engines_unpark(i915); + i915_queue_hangcheck(i915); + queue_delayed_work(i915->wq, &i915->gt.retire_work, round_jiffies_up_relative(HZ)); diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 9029ed04879c..0e158f9287c4 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -363,13 +363,13 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_PURGEABLE); - if (freed < sc->nr_to_scan) + if (sc->nr_scanned < sc->nr_to_scan) freed += i915_gem_shrink(i915, sc->nr_to_scan - sc->nr_scanned, &sc->nr_scanned, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); - if (freed < sc->nr_to_scan && current_is_kswapd()) { + if (sc->nr_scanned < sc->nr_to_scan && current_is_kswapd()) { intel_runtime_pm_get(i915); freed += i915_gem_shrink(i915, sc->nr_to_scan - sc->nr_scanned, diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 36d48422b475..1c30c688f23a 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -74,19 +74,19 @@ GEN_DEFAULT_PAGE_SIZES, \ CURSOR_OFFSETS -static const struct intel_device_info intel_i830_info __initconst = { +static const struct intel_device_info intel_i830_info = { GEN2_FEATURES, .platform = INTEL_I830, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2, /* legal, last one wins */ }; -static const struct intel_device_info intel_i845g_info __initconst = { +static const struct intel_device_info intel_i845g_info = { GEN2_FEATURES, .platform = INTEL_I845G, }; -static const struct intel_device_info intel_i85x_info __initconst = { +static const struct intel_device_info intel_i85x_info = { GEN2_FEATURES, .platform = INTEL_I85X, .is_mobile = 1, .num_pipes = 2, /* legal, last one wins */ @@ -94,7 +94,7 @@ static const struct intel_device_info intel_i85x_info __initconst = { .has_fbc = 1, }; -static const struct intel_device_info intel_i865g_info __initconst = { +static const struct intel_device_info intel_i865g_info = { GEN2_FEATURES, .platform = INTEL_I865G, }; @@ -108,7 +108,7 @@ static const struct intel_device_info intel_i865g_info __initconst = { GEN_DEFAULT_PAGE_SIZES, \ CURSOR_OFFSETS -static const struct intel_device_info intel_i915g_info __initconst = { +static const struct intel_device_info intel_i915g_info = { GEN3_FEATURES, .platform = INTEL_I915G, .cursor_needs_physical = 1, .has_overlay = 1, .overlay_needs_physical = 1, @@ -116,7 +116,7 @@ static const struct intel_device_info intel_i915g_info __initconst = { .unfenced_needs_alignment = 1, }; -static const struct intel_device_info intel_i915gm_info __initconst = { +static const struct intel_device_info intel_i915gm_info = { GEN3_FEATURES, .platform = INTEL_I915GM, .is_mobile = 1, @@ -128,7 +128,7 @@ static const struct intel_device_info intel_i915gm_info __initconst = { .unfenced_needs_alignment = 1, }; -static const struct intel_device_info intel_i945g_info __initconst = { +static const struct intel_device_info intel_i945g_info = { GEN3_FEATURES, .platform = INTEL_I945G, .has_hotplug = 1, .cursor_needs_physical = 1, @@ -137,7 +137,7 @@ static const struct intel_device_info intel_i945g_info __initconst = { .unfenced_needs_alignment = 1, }; -static const struct intel_device_info intel_i945gm_info __initconst = { +static const struct intel_device_info intel_i945gm_info = { GEN3_FEATURES, .platform = INTEL_I945GM, .is_mobile = 1, .has_hotplug = 1, .cursor_needs_physical = 1, @@ -148,14 +148,14 @@ static const struct intel_device_info intel_i945gm_info __initconst = { .unfenced_needs_alignment = 1, }; -static const struct intel_device_info intel_g33_info __initconst = { +static const struct intel_device_info intel_g33_info = { GEN3_FEATURES, .platform = INTEL_G33, .has_hotplug = 1, .has_overlay = 1, }; -static const struct intel_device_info intel_pineview_info __initconst = { +static const struct intel_device_info intel_pineview_info = { GEN3_FEATURES, .platform = INTEL_PINEVIEW, .is_mobile = 1, .has_hotplug = 1, @@ -172,7 +172,7 @@ static const struct intel_device_info intel_pineview_info __initconst = { GEN_DEFAULT_PAGE_SIZES, \ CURSOR_OFFSETS -static const struct intel_device_info intel_i965g_info __initconst = { +static const struct intel_device_info intel_i965g_info = { GEN4_FEATURES, .platform = INTEL_I965G, .has_overlay = 1, @@ -180,7 +180,7 @@ static const struct intel_device_info intel_i965g_info __initconst = { .has_snoop = false, }; -static const struct intel_device_info intel_i965gm_info __initconst = { +static const struct intel_device_info intel_i965gm_info = { GEN4_FEATURES, .platform = INTEL_I965GM, .is_mobile = 1, .has_fbc = 1, @@ -190,13 +190,13 @@ static const struct intel_device_info intel_i965gm_info __initconst = { .has_snoop = false, }; -static const struct intel_device_info intel_g45_info __initconst = { +static const struct intel_device_info intel_g45_info = { GEN4_FEATURES, .platform = INTEL_G45, .ring_mask = RENDER_RING | BSD_RING, }; -static const struct intel_device_info intel_gm45_info __initconst = { +static const struct intel_device_info intel_gm45_info = { GEN4_FEATURES, .platform = INTEL_GM45, .is_mobile = 1, .has_fbc = 1, @@ -215,12 +215,12 @@ static const struct intel_device_info intel_gm45_info __initconst = { GEN_DEFAULT_PAGE_SIZES, \ CURSOR_OFFSETS -static const struct intel_device_info intel_ironlake_d_info __initconst = { +static const struct intel_device_info intel_ironlake_d_info = { GEN5_FEATURES, .platform = INTEL_IRONLAKE, }; -static const struct intel_device_info intel_ironlake_m_info __initconst = { +static const struct intel_device_info intel_ironlake_m_info = { GEN5_FEATURES, .platform = INTEL_IRONLAKE, .is_mobile = 1, .has_fbc = 1, @@ -243,12 +243,12 @@ static const struct intel_device_info intel_ironlake_m_info __initconst = { GEN6_FEATURES, \ .platform = INTEL_SANDYBRIDGE -static const struct intel_device_info intel_sandybridge_d_gt1_info __initconst = { +static const struct intel_device_info intel_sandybridge_d_gt1_info = { SNB_D_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_sandybridge_d_gt2_info __initconst = { +static const struct intel_device_info intel_sandybridge_d_gt2_info = { SNB_D_PLATFORM, .gt = 2, }; @@ -259,12 +259,12 @@ static const struct intel_device_info intel_sandybridge_d_gt2_info __initconst = .is_mobile = 1 -static const struct intel_device_info intel_sandybridge_m_gt1_info __initconst = { +static const struct intel_device_info intel_sandybridge_m_gt1_info = { SNB_M_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_sandybridge_m_gt2_info __initconst = { +static const struct intel_device_info intel_sandybridge_m_gt2_info = { SNB_M_PLATFORM, .gt = 2, }; @@ -288,12 +288,12 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info __initconst = .platform = INTEL_IVYBRIDGE, \ .has_l3_dpf = 1 -static const struct intel_device_info intel_ivybridge_d_gt1_info __initconst = { +static const struct intel_device_info intel_ivybridge_d_gt1_info = { IVB_D_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_ivybridge_d_gt2_info __initconst = { +static const struct intel_device_info intel_ivybridge_d_gt2_info = { IVB_D_PLATFORM, .gt = 2, }; @@ -304,17 +304,17 @@ static const struct intel_device_info intel_ivybridge_d_gt2_info __initconst = { .is_mobile = 1, \ .has_l3_dpf = 1 -static const struct intel_device_info intel_ivybridge_m_gt1_info __initconst = { +static const struct intel_device_info intel_ivybridge_m_gt1_info = { IVB_M_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_ivybridge_m_gt2_info __initconst = { +static const struct intel_device_info intel_ivybridge_m_gt2_info = { IVB_M_PLATFORM, .gt = 2, }; -static const struct intel_device_info intel_ivybridge_q_info __initconst = { +static const struct intel_device_info intel_ivybridge_q_info = { GEN7_FEATURES, .platform = INTEL_IVYBRIDGE, .gt = 2, @@ -322,7 +322,7 @@ static const struct intel_device_info intel_ivybridge_q_info __initconst = { .has_l3_dpf = 1, }; -static const struct intel_device_info intel_valleyview_info __initconst = { +static const struct intel_device_info intel_valleyview_info = { .platform = INTEL_VALLEYVIEW, .gen = 7, .is_lp = 1, @@ -358,17 +358,17 @@ static const struct intel_device_info intel_valleyview_info __initconst = { .platform = INTEL_HASWELL, \ .has_l3_dpf = 1 -static const struct intel_device_info intel_haswell_gt1_info __initconst = { +static const struct intel_device_info intel_haswell_gt1_info = { HSW_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_haswell_gt2_info __initconst = { +static const struct intel_device_info intel_haswell_gt2_info = { HSW_PLATFORM, .gt = 2, }; -static const struct intel_device_info intel_haswell_gt3_info __initconst = { +static const struct intel_device_info intel_haswell_gt3_info = { HSW_PLATFORM, .gt = 3, }; @@ -388,17 +388,17 @@ static const struct intel_device_info intel_haswell_gt3_info __initconst = { .gen = 8, \ .platform = INTEL_BROADWELL -static const struct intel_device_info intel_broadwell_gt1_info __initconst = { +static const struct intel_device_info intel_broadwell_gt1_info = { BDW_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_broadwell_gt2_info __initconst = { +static const struct intel_device_info intel_broadwell_gt2_info = { BDW_PLATFORM, .gt = 2, }; -static const struct intel_device_info intel_broadwell_rsvd_info __initconst = { +static const struct intel_device_info intel_broadwell_rsvd_info = { BDW_PLATFORM, .gt = 3, /* According to the device ID those devices are GT3, they were @@ -406,13 +406,13 @@ static const struct intel_device_info intel_broadwell_rsvd_info __initconst = { */ }; -static const struct intel_device_info intel_broadwell_gt3_info __initconst = { +static const struct intel_device_info intel_broadwell_gt3_info = { BDW_PLATFORM, .gt = 3, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, }; -static const struct intel_device_info intel_cherryview_info __initconst = { +static const struct intel_device_info intel_cherryview_info = { .gen = 8, .num_pipes = 3, .has_hotplug = 1, .is_lp = 1, @@ -455,12 +455,12 @@ static const struct intel_device_info intel_cherryview_info __initconst = { .gen = 9, \ .platform = INTEL_SKYLAKE -static const struct intel_device_info intel_skylake_gt1_info __initconst = { +static const struct intel_device_info intel_skylake_gt1_info = { SKL_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_skylake_gt2_info __initconst = { +static const struct intel_device_info intel_skylake_gt2_info = { SKL_PLATFORM, .gt = 2, }; @@ -470,12 +470,12 @@ static const struct intel_device_info intel_skylake_gt2_info __initconst = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING -static const struct intel_device_info intel_skylake_gt3_info __initconst = { +static const struct intel_device_info intel_skylake_gt3_info = { SKL_GT3_PLUS_PLATFORM, .gt = 3, }; -static const struct intel_device_info intel_skylake_gt4_info __initconst = { +static const struct intel_device_info intel_skylake_gt4_info = { SKL_GT3_PLUS_PLATFORM, .gt = 4, }; @@ -511,13 +511,13 @@ static const struct intel_device_info intel_skylake_gt4_info __initconst = { IVB_CURSOR_OFFSETS, \ BDW_COLORS -static const struct intel_device_info intel_broxton_info __initconst = { +static const struct intel_device_info intel_broxton_info = { GEN9_LP_FEATURES, .platform = INTEL_BROXTON, .ddb_size = 512, }; -static const struct intel_device_info intel_geminilake_info __initconst = { +static const struct intel_device_info intel_geminilake_info = { GEN9_LP_FEATURES, .platform = INTEL_GEMINILAKE, .ddb_size = 1024, @@ -529,17 +529,17 @@ static const struct intel_device_info intel_geminilake_info __initconst = { .gen = 9, \ .platform = INTEL_KABYLAKE -static const struct intel_device_info intel_kabylake_gt1_info __initconst = { +static const struct intel_device_info intel_kabylake_gt1_info = { KBL_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_kabylake_gt2_info __initconst = { +static const struct intel_device_info intel_kabylake_gt2_info = { KBL_PLATFORM, .gt = 2, }; -static const struct intel_device_info intel_kabylake_gt3_info __initconst = { +static const struct intel_device_info intel_kabylake_gt3_info = { KBL_PLATFORM, .gt = 3, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, @@ -550,17 +550,17 @@ static const struct intel_device_info intel_kabylake_gt3_info __initconst = { .gen = 9, \ .platform = INTEL_COFFEELAKE -static const struct intel_device_info intel_coffeelake_gt1_info __initconst = { +static const struct intel_device_info intel_coffeelake_gt1_info = { CFL_PLATFORM, .gt = 1, }; -static const struct intel_device_info intel_coffeelake_gt2_info __initconst = { +static const struct intel_device_info intel_coffeelake_gt2_info = { CFL_PLATFORM, .gt = 2, }; -static const struct intel_device_info intel_coffeelake_gt3_info __initconst = { +static const struct intel_device_info intel_coffeelake_gt3_info = { CFL_PLATFORM, .gt = 3, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING, @@ -571,7 +571,7 @@ static const struct intel_device_info intel_coffeelake_gt3_info __initconst = { .ddb_size = 1024, \ GLK_COLORS -static const struct intel_device_info intel_cannonlake_gt2_info __initconst = { +static const struct intel_device_info intel_cannonlake_gt2_info = { GEN10_FEATURES, .is_alpha_support = 1, .platform = INTEL_CANNONLAKE, diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index e42d9a4de322..0be50e43507d 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -244,7 +244,7 @@ * The two separate pointers let us decouple read()s from tail pointer aging. * * The tail pointers are checked and updated at a limited rate within a hrtimer - * callback (the same callback that is used for delivering POLLIN events) + * callback (the same callback that is used for delivering EPOLLIN events) * * Initially the tails are marked invalid with %INVALID_TAIL_PTR which * indicates that an updated tail pointer is needed. @@ -2292,13 +2292,13 @@ static ssize_t i915_perf_read(struct file *file, mutex_unlock(&dev_priv->perf.lock); } - /* We allow the poll checking to sometimes report false positive POLLIN + /* We allow the poll checking to sometimes report false positive EPOLLIN * events where we might actually report EAGAIN on read() if there's * not really any data available. In this situation though we don't - * want to enter a busy loop between poll() reporting a POLLIN event + * want to enter a busy loop between poll() reporting a EPOLLIN event * and read() returning -EAGAIN. Clearing the oa.pollin state here * effectively ensures we back off until the next hrtimer callback - * before reporting another POLLIN event. + * before reporting another EPOLLIN event. */ if (ret >= 0 || ret == -EAGAIN) { /* Maybe make ->pollin per-stream state if we support multiple @@ -2358,7 +2358,7 @@ static __poll_t i915_perf_poll_locked(struct drm_i915_private *dev_priv, * samples to read. */ if (dev_priv->perf.oa.pollin) - events |= POLLIN; + events |= EPOLLIN; return events; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 505c605eff98..a2108e35c599 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2489,6 +2489,8 @@ enum i915_power_well_id { #define GEN8_FAULT_TLB_DATA0 _MMIO(0x4b10) #define GEN8_FAULT_TLB_DATA1 _MMIO(0x4b14) +#define FAULT_VA_HIGH_BITS (0xf << 0) +#define FAULT_GTT_SEL (1 << 4) #define FPGA_DBG _MMIO(0x42300) #define FPGA_DBG_RM_NOCLAIM (1<<31) diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index f1502a0188eb..522d54fecb53 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -779,7 +779,7 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, { struct intel_encoder *encoder; - if (WARN_ON(pipe >= INTEL_INFO(dev_priv)->num_pipes)) + if (WARN_ON(pipe >= ARRAY_SIZE(dev_priv->av_enc_map))) return NULL; /* MST */ diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 51108ffc28d1..f7f771749e48 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1107,6 +1107,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv, } static const u8 cnp_ddc_pin_map[] = { + [0] = 0, /* N/A */ [DDC_BUS_DDI_B] = GMBUS_PIN_1_BXT, [DDC_BUS_DDI_C] = GMBUS_PIN_2_BXT, [DDC_BUS_DDI_D] = GMBUS_PIN_4_CNP, /* sic */ @@ -1115,9 +1116,14 @@ static const u8 cnp_ddc_pin_map[] = { static u8 map_ddc_pin(struct drm_i915_private *dev_priv, u8 vbt_pin) { - if (HAS_PCH_CNP(dev_priv) && - vbt_pin > 0 && vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map)) - return cnp_ddc_pin_map[vbt_pin]; + if (HAS_PCH_CNP(dev_priv)) { + if (vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map)) { + return cnp_ddc_pin_map[vbt_pin]; + } else { + DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n", vbt_pin); + return 0; + } + } return vbt_pin; } @@ -1323,11 +1329,13 @@ parse_general_definitions(struct drm_i915_private *dev_priv, expected_size = LEGACY_CHILD_DEVICE_CONFIG_SIZE; } else if (bdb->version == 195) { expected_size = 37; - } else if (bdb->version <= 197) { + } else if (bdb->version <= 215) { expected_size = 38; + } else if (bdb->version <= 216) { + expected_size = 39; } else { - expected_size = 38; - BUILD_BUG_ON(sizeof(*child) < 38); + expected_size = sizeof(*child); + BUILD_BUG_ON(sizeof(*child) < 39); DRM_DEBUG_DRIVER("Expected child device config size for VBT version %u not known; assuming %u\n", bdb->version, expected_size); } diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index 58c624f982d9..bd40fea16b4f 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -149,17 +149,6 @@ static void intel_breadcrumbs_fake_irq(struct timer_list *t) return; mod_timer(&b->fake_irq, jiffies + 1); - - /* Ensure that even if the GPU hangs, we get woken up. - * - * However, note that if no one is waiting, we never notice - * a gpu hang. Eventually, we will have to wait for a resource - * held by the GPU and so trigger a hangcheck. In the most - * pathological case, this will be upon memory starvation! To - * prevent this, we also queue the hangcheck from the retire - * worker. - */ - i915_queue_hangcheck(engine->i915); } static void irq_enable(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index d77e2bec1e29..5dc118f26b51 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -1370,10 +1370,15 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, break; } - /* Inform power controller of upcoming frequency change */ + /* + * Inform power controller of upcoming frequency change. BSpec + * requires us to wait up to 150usec, but that leads to timeouts; + * the 2ms used here is based on experiment. + */ mutex_lock(&dev_priv->pcu_lock); - ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, - 0x80000000); + ret = sandybridge_pcode_write_timeout(dev_priv, + HSW_PCODE_DE_WRITE_FREQ_REQ, + 0x80000000, 2000); mutex_unlock(&dev_priv->pcu_lock); if (ret) { @@ -1404,8 +1409,15 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, I915_WRITE(CDCLK_CTL, val); mutex_lock(&dev_priv->pcu_lock); - ret = sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, - cdclk_state->voltage_level); + /* + * The timeout isn't specified, the 2ms used here is based on + * experiment. + * FIXME: Waiting for the request completion could be delayed until + * the next PCODE request based on BSpec. + */ + ret = sandybridge_pcode_write_timeout(dev_priv, + HSW_PCODE_DE_WRITE_FREQ_REQ, + cdclk_state->voltage_level, 2000); mutex_unlock(&dev_priv->pcu_lock); if (ret) { diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 0cd355978ab4..f288bcc7be22 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -5661,8 +5661,8 @@ static u64 get_crtc_power_domains(struct drm_crtc *crtc, if (!crtc_state->base.active) return 0; - mask = BIT(POWER_DOMAIN_PIPE(pipe)); - mask |= BIT(POWER_DOMAIN_TRANSCODER(transcoder)); + mask = BIT_ULL(POWER_DOMAIN_PIPE(pipe)); + mask |= BIT_ULL(POWER_DOMAIN_TRANSCODER(transcoder)); if (crtc_state->pch_pfit.enabled || crtc_state->pch_pfit.force_thru) mask |= BIT_ULL(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe)); @@ -5674,7 +5674,7 @@ static u64 get_crtc_power_domains(struct drm_crtc *crtc, } if (HAS_DDI(dev_priv) && crtc_state->has_audio) - mask |= BIT(POWER_DOMAIN_AUDIO); + mask |= BIT_ULL(POWER_DOMAIN_AUDIO); if (crtc_state->shared_dpll) mask |= BIT_ULL(POWER_DOMAIN_PLLS); diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c index 05907fa8a553..cf8fef8b6f58 100644 --- a/drivers/gpu/drm/i915/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/intel_dp_link_training.c @@ -328,14 +328,22 @@ intel_dp_start_link_train(struct intel_dp *intel_dp) return; failure_handling: - DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d", - intel_connector->base.base.id, - intel_connector->base.name, - intel_dp->link_rate, intel_dp->lane_count); - if (!intel_dp_get_link_train_fallback_values(intel_dp, - intel_dp->link_rate, - intel_dp->lane_count)) - /* Schedule a Hotplug Uevent to userspace to start modeset */ - schedule_work(&intel_connector->modeset_retry_work); + /* Dont fallback and prune modes if its eDP */ + if (!intel_dp_is_edp(intel_dp)) { + DRM_DEBUG_KMS("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d", + intel_connector->base.base.id, + intel_connector->base.name, + intel_dp->link_rate, intel_dp->lane_count); + if (!intel_dp_get_link_train_fallback_values(intel_dp, + intel_dp->link_rate, + intel_dp->lane_count)) + /* Schedule a Hotplug Uevent to userspace to start modeset */ + schedule_work(&intel_connector->modeset_retry_work); + } else { + DRM_ERROR("[CONNECTOR:%d:%s] Link Training failed at link rate = %d, lane count = %d", + intel_connector->base.base.id, + intel_connector->base.name, + intel_dp->link_rate, intel_dp->lane_count); + } return; } diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 6bb51a502b8b..d790bdc227ff 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1951,8 +1951,22 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine) spin_lock_irqsave(&engine->stats.lock, flags); if (engine->stats.enabled == ~0) goto busy; - if (engine->stats.enabled++ == 0) + if (engine->stats.enabled++ == 0) { + struct intel_engine_execlists *execlists = &engine->execlists; + const struct execlist_port *port = execlists->port; + unsigned int num_ports = execlists_num_ports(execlists); + engine->stats.enabled_at = ktime_get(); + + /* XXX submission method oblivious? */ + while (num_ports-- && port_isset(port)) { + engine->stats.active++; + port++; + } + + if (engine->stats.active) + engine->stats.start = engine->stats.enabled_at; + } spin_unlock_irqrestore(&engine->stats.lock, flags); return 0; diff --git a/drivers/gpu/drm/i915/intel_guc_fw.c b/drivers/gpu/drm/i915/intel_guc_fw.c index cbc51c960425..3b0932942857 100644 --- a/drivers/gpu/drm/i915/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/intel_guc_fw.c @@ -39,9 +39,6 @@ #define KBL_FW_MAJOR 9 #define KBL_FW_MINOR 39 -#define GLK_FW_MAJOR 10 -#define GLK_FW_MINOR 56 - #define GUC_FW_PATH(platform, major, minor) \ "i915/" __stringify(platform) "_guc_ver" __stringify(major) "_" __stringify(minor) ".bin" @@ -54,8 +51,6 @@ MODULE_FIRMWARE(I915_BXT_GUC_UCODE); #define I915_KBL_GUC_UCODE GUC_FW_PATH(kbl, KBL_FW_MAJOR, KBL_FW_MINOR) MODULE_FIRMWARE(I915_KBL_GUC_UCODE); -#define I915_GLK_GUC_UCODE GUC_FW_PATH(glk, GLK_FW_MAJOR, GLK_FW_MINOR) - static void guc_fw_select(struct intel_uc_fw *guc_fw) { struct intel_guc *guc = container_of(guc_fw, struct intel_guc, fw); @@ -82,10 +77,6 @@ static void guc_fw_select(struct intel_uc_fw *guc_fw) guc_fw->path = I915_KBL_GUC_UCODE; guc_fw->major_ver_wanted = KBL_FW_MAJOR; guc_fw->minor_ver_wanted = KBL_FW_MINOR; - } else if (IS_GEMINILAKE(dev_priv)) { - guc_fw->path = I915_GLK_GUC_UCODE; - guc_fw->major_ver_wanted = GLK_FW_MAJOR; - guc_fw->minor_ver_wanted = GLK_FW_MINOR; } else { DRM_WARN("%s: No firmware known for this platform!\n", intel_uc_fw_type_repr(guc_fw->type)); diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c index 31f01d64c021..348a4f7ffb67 100644 --- a/drivers/gpu/drm/i915/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/intel_hangcheck.c @@ -411,7 +411,6 @@ static void i915_hangcheck_elapsed(struct work_struct *work) struct intel_engine_cs *engine; enum intel_engine_id id; unsigned int hung = 0, stuck = 0; - int busy_count = 0; if (!i915_modparams.enable_hangcheck) return; @@ -429,7 +428,6 @@ static void i915_hangcheck_elapsed(struct work_struct *work) intel_uncore_arm_unclaimed_mmio_detection(dev_priv); for_each_engine(engine, dev_priv, id) { - const bool busy = intel_engine_has_waiter(engine); struct intel_engine_hangcheck hc; semaphore_clear_deadlocks(dev_priv); @@ -443,16 +441,13 @@ static void i915_hangcheck_elapsed(struct work_struct *work) if (hc.action != ENGINE_DEAD) stuck |= intel_engine_flag(engine); } - - busy_count += busy; } if (hung) hangcheck_declare_hang(dev_priv, hung, stuck); /* Reset timer in case GPU hangs without another request being added */ - if (busy_count) - i915_queue_hangcheck(dev_priv); + i915_queue_hangcheck(dev_priv); } void intel_engine_init_hangcheck(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index bced7b954d93..179d0ad3889d 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1595,12 +1595,20 @@ intel_hdmi_set_edid(struct drm_connector *connector) struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); struct edid *edid; bool connected = false; + struct i2c_adapter *i2c; intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); - edid = drm_get_edid(connector, - intel_gmbus_get_adapter(dev_priv, - intel_hdmi->ddc_bus)); + i2c = intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus); + + edid = drm_get_edid(connector, i2c); + + if (!edid && !intel_gmbus_is_forced_bit(i2c)) { + DRM_DEBUG_KMS("HDMI GMBUS EDID read failed, retry using GPIO bit-banging\n"); + intel_gmbus_force_bit(i2c, true); + edid = drm_get_edid(connector, i2c); + intel_gmbus_force_bit(i2c, false); + } intel_hdmi_dp_dual_mode_detect(connector, edid != NULL); diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c index 974be3defa70..8ed05182f944 100644 --- a/drivers/gpu/drm/i915/intel_huc.c +++ b/drivers/gpu/drm/i915/intel_huc.c @@ -54,10 +54,6 @@ #define KBL_HUC_FW_MINOR 00 #define KBL_BLD_NUM 1810 -#define GLK_HUC_FW_MAJOR 02 -#define GLK_HUC_FW_MINOR 00 -#define GLK_BLD_NUM 1748 - #define HUC_FW_PATH(platform, major, minor, bld_num) \ "i915/" __stringify(platform) "_huc_ver" __stringify(major) "_" \ __stringify(minor) "_" __stringify(bld_num) ".bin" @@ -74,9 +70,6 @@ MODULE_FIRMWARE(I915_BXT_HUC_UCODE); KBL_HUC_FW_MINOR, KBL_BLD_NUM) MODULE_FIRMWARE(I915_KBL_HUC_UCODE); -#define I915_GLK_HUC_UCODE HUC_FW_PATH(glk, GLK_HUC_FW_MAJOR, \ - GLK_HUC_FW_MINOR, GLK_BLD_NUM) - static void huc_fw_select(struct intel_uc_fw *huc_fw) { struct intel_huc *huc = container_of(huc_fw, struct intel_huc, fw); @@ -103,10 +96,6 @@ static void huc_fw_select(struct intel_uc_fw *huc_fw) huc_fw->path = I915_KBL_HUC_UCODE; huc_fw->major_ver_wanted = KBL_HUC_FW_MAJOR; huc_fw->minor_ver_wanted = KBL_HUC_FW_MINOR; - } else if (IS_GEMINILAKE(dev_priv)) { - huc_fw->path = I915_GLK_HUC_UCODE; - huc_fw->major_ver_wanted = GLK_HUC_FW_MAJOR; - huc_fw->minor_ver_wanted = GLK_HUC_FW_MINOR; } else { DRM_WARN("%s: No firmware known for this platform!\n", intel_uc_fw_type_repr(huc_fw->type)); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 1db79a860b96..1a6e699e19e0 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -9149,8 +9149,8 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val return 0; } -int sandybridge_pcode_write(struct drm_i915_private *dev_priv, - u32 mbox, u32 val) +int sandybridge_pcode_write_timeout(struct drm_i915_private *dev_priv, + u32 mbox, u32 val, int timeout_us) { int status; @@ -9173,7 +9173,7 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, if (__intel_wait_for_register_fw(dev_priv, GEN6_PCODE_MAILBOX, GEN6_PCODE_READY, 0, - 500, 0, NULL)) { + timeout_us, 0, NULL)) { DRM_ERROR("timeout waiting for pcode write of 0x%08x to mbox %x to finish for %ps\n", val, mbox, __builtin_return_address(0)); return -ETIMEDOUT; diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c index 907deac6e3fa..d82ca0f438f5 100644 --- a/drivers/gpu/drm/i915/intel_uc.c +++ b/drivers/gpu/drm/i915/intel_uc.c @@ -209,8 +209,6 @@ void intel_uc_fini_wq(struct drm_i915_private *dev_priv) if (!USES_GUC(dev_priv)) return; - GEM_BUG_ON(!HAS_GUC(dev_priv)); - intel_guc_fini_wq(&dev_priv->guc); } diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h index e3d7745a9151..98dff6058d3c 100644 --- a/drivers/gpu/drm/i915/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/intel_vbt_defs.h @@ -412,6 +412,8 @@ struct child_device_config { u16 dp_gpio_pin_num; /* 195 */ u8 dp_iboost_level:4; /* 196 */ u8 hdmi_iboost_level:4; /* 196 */ + u8 dp_max_link_rate:2; /* 216 CNL+ */ + u8 dp_max_link_rate_reserved:6; /* 216 */ } __packed; struct bdb_general_definitions { diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h index adb78f7d083a..92be0e5269c6 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h @@ -75,6 +75,7 @@ int mcp89_fb_new(struct nvkm_device *, int, struct nvkm_fb **); int gf100_fb_new(struct nvkm_device *, int, struct nvkm_fb **); int gf108_fb_new(struct nvkm_device *, int, struct nvkm_fb **); int gk104_fb_new(struct nvkm_device *, int, struct nvkm_fb **); +int gk110_fb_new(struct nvkm_device *, int, struct nvkm_fb **); int gk20a_fb_new(struct nvkm_device *, int, struct nvkm_fb **); int gm107_fb_new(struct nvkm_device *, int, struct nvkm_fb **); int gm200_fb_new(struct nvkm_device *, int, struct nvkm_fb **); diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h index 59f3ba551681..b57fe4ae93ba 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/secboot.h @@ -60,6 +60,7 @@ int nvkm_secboot_reset(struct nvkm_secboot *, unsigned long); int gm200_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **); int gm20b_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **); int gp102_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **); +int gp108_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **); int gp10b_secboot_new(struct nvkm_device *, int, struct nvkm_secboot **); #endif diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h index b1ac47eb786e..9398d9f09339 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/therm.h @@ -46,6 +46,16 @@ enum nvkm_therm_attr_type { NVKM_THERM_ATTR_THRS_SHUTDOWN_HYST = 17, }; +struct nvkm_therm_clkgate_init { + u32 addr; + u8 count; + u32 data; +}; + +struct nvkm_therm_clkgate_pack { + const struct nvkm_therm_clkgate_init *init; +}; + struct nvkm_therm { const struct nvkm_therm_func *func; struct nvkm_subdev subdev; @@ -85,17 +95,24 @@ struct nvkm_therm { int (*attr_get)(struct nvkm_therm *, enum nvkm_therm_attr_type); int (*attr_set)(struct nvkm_therm *, enum nvkm_therm_attr_type, int); + + bool clkgating_enabled; }; int nvkm_therm_temp_get(struct nvkm_therm *); int nvkm_therm_fan_sense(struct nvkm_therm *); int nvkm_therm_cstate(struct nvkm_therm *, int, int); +void nvkm_therm_clkgate_init(struct nvkm_therm *, + const struct nvkm_therm_clkgate_pack *); +void nvkm_therm_clkgate_enable(struct nvkm_therm *); +void nvkm_therm_clkgate_fini(struct nvkm_therm *, bool); int nv40_therm_new(struct nvkm_device *, int, struct nvkm_therm **); int nv50_therm_new(struct nvkm_device *, int, struct nvkm_therm **); int g84_therm_new(struct nvkm_device *, int, struct nvkm_therm **); int gt215_therm_new(struct nvkm_device *, int, struct nvkm_therm **); int gf119_therm_new(struct nvkm_device *, int, struct nvkm_therm **); +int gk104_therm_new(struct nvkm_device *, int, struct nvkm_therm **); int gm107_therm_new(struct nvkm_device *, int, struct nvkm_therm **); int gm200_therm_new(struct nvkm_device *, int, struct nvkm_therm **); int gp100_therm_new(struct nvkm_device *, int, struct nvkm_therm **); diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h index 7b5cc5c73d20..be8e00b49cde 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.h +++ b/drivers/gpu/drm/nouveau/nouveau_bo.h @@ -105,4 +105,32 @@ nvbo_kmap_obj_iovirtual(struct nouveau_bo *nvbo) return ioptr; } +static inline void +nouveau_bo_unmap_unpin_unref(struct nouveau_bo **pnvbo) +{ + if (*pnvbo) { + nouveau_bo_unmap(*pnvbo); + nouveau_bo_unpin(*pnvbo); + nouveau_bo_ref(NULL, pnvbo); + } +} + +static inline int +nouveau_bo_new_pin_map(struct nouveau_cli *cli, u64 size, int align, u32 flags, + struct nouveau_bo **pnvbo) +{ + int ret = nouveau_bo_new(cli, size, align, flags, + 0, 0, NULL, NULL, pnvbo); + if (ret == 0) { + ret = nouveau_bo_pin(*pnvbo, flags, true); + if (ret == 0) { + ret = nouveau_bo_map(*pnvbo); + if (ret == 0) + return ret; + nouveau_bo_unpin(*pnvbo); + } + nouveau_bo_ref(NULL, pnvbo); + } + return ret; +} #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_crtc.h b/drivers/gpu/drm/nouveau/nouveau_crtc.h index b7a18fbee6dc..366acb928f57 100644 --- a/drivers/gpu/drm/nouveau/nouveau_crtc.h +++ b/drivers/gpu/drm/nouveau/nouveau_crtc.h @@ -60,7 +60,6 @@ struct nouveau_crtc { } cursor; struct { - struct nouveau_bo *nvbo; int depth; } lut; diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index ee5d1dc2eaf5..85c1f10bc2b6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -56,6 +56,10 @@ MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration"); int nouveau_nofbaccel = 0; module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400); +MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)"); +static int nouveau_fbcon_bpp; +module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400); + static void nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect) { @@ -488,7 +492,7 @@ nouveau_fbcon_init(struct drm_device *dev) { struct nouveau_drm *drm = nouveau_drm(dev); struct nouveau_fbdev *fbcon; - int preferred_bpp; + int preferred_bpp = nouveau_fbcon_bpp; int ret; if (!dev->mode_config.num_crtc || @@ -512,13 +516,15 @@ nouveau_fbcon_init(struct drm_device *dev) if (ret) goto fini; - if (drm->client.device.info.ram_size <= 32 * 1024 * 1024) - preferred_bpp = 8; - else - if (drm->client.device.info.ram_size <= 64 * 1024 * 1024) - preferred_bpp = 16; - else - preferred_bpp = 32; + if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) { + if (drm->client.device.info.ram_size <= 32 * 1024 * 1024) + preferred_bpp = 8; + else + if (drm->client.device.info.ram_size <= 64 * 1024 * 1024) + preferred_bpp = 16; + else + preferred_bpp = 32; + } /* disable all the possible outputs/crtcs before entering KMS mode */ if (!drm_drv_uses_atomic_modeset(dev)) diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index b22c37bde13f..dd8d4352ed99 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -137,8 +137,10 @@ struct nv50_head_atom { } mode; struct { + bool visible; u32 handle; u64 offset:40; + u8 mode:4; } lut; struct { @@ -192,6 +194,7 @@ struct nv50_head_atom { union { struct { + bool ilut:1; bool core:1; bool curs:1; }; @@ -200,6 +203,7 @@ struct nv50_head_atom { union { struct { + bool ilut:1; bool core:1; bool curs:1; bool view:1; @@ -660,6 +664,10 @@ nv50_ovly_create(struct nvif_device *device, struct nvif_object *disp, struct nv50_head { struct nouveau_crtc base; + struct { + struct nouveau_bo *nvbo[2]; + int next; + } lut; struct nv50_ovly ovly; struct nv50_oimm oimm; }; @@ -1795,6 +1803,54 @@ nv50_head_lut_clr(struct nv50_head *head) } static void +nv50_head_lut_load(struct drm_property_blob *blob, int mode, + struct nouveau_bo *nvbo) +{ + struct drm_color_lut *in = (struct drm_color_lut *)blob->data; + void __iomem *lut = (u8 *)nvbo_kmap_obj_iovirtual(nvbo); + const int size = blob->length / sizeof(*in); + int bits, shift, i; + u16 zero, r, g, b; + + /* This can't happen.. But it shuts the compiler up. */ + if (WARN_ON(size != 256)) + return; + + switch (mode) { + case 0: /* LORES. */ + case 1: /* HIRES. */ + bits = 11; + shift = 3; + zero = 0x0000; + break; + case 7: /* INTERPOLATE_257_UNITY_RANGE. */ + bits = 14; + shift = 0; + zero = 0x6000; + break; + default: + WARN_ON(1); + return; + } + + for (i = 0; i < size; i++) { + r = (drm_color_lut_extract(in[i]. red, bits) + zero) << shift; + g = (drm_color_lut_extract(in[i].green, bits) + zero) << shift; + b = (drm_color_lut_extract(in[i]. blue, bits) + zero) << shift; + writew(r, lut + (i * 0x08) + 0); + writew(g, lut + (i * 0x08) + 2); + writew(b, lut + (i * 0x08) + 4); + } + + /* INTERPOLATE modes require a "next" entry to interpolate with, + * so we replicate the last entry to deal with this for now. + */ + writew(r, lut + (i * 0x08) + 0); + writew(g, lut + (i * 0x08) + 2); + writew(b, lut + (i * 0x08) + 4); +} + +static void nv50_head_lut_set(struct nv50_head *head, struct nv50_head_atom *asyh) { struct nv50_dmac *core = &nv50_disp(head->base.base.dev)->mast.base; @@ -1802,18 +1858,18 @@ nv50_head_lut_set(struct nv50_head *head, struct nv50_head_atom *asyh) if ((push = evo_wait(core, 7))) { if (core->base.user.oclass < G82_DISP_CORE_CHANNEL_DMA) { evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2); - evo_data(push, 0xc0000000); + evo_data(push, 0x80000000 | asyh->lut.mode << 30); evo_data(push, asyh->lut.offset >> 8); } else if (core->base.user.oclass < GF110_DISP_CORE_CHANNEL_DMA) { evo_mthd(push, 0x0840 + (head->base.index * 0x400), 2); - evo_data(push, 0xc0000000); + evo_data(push, 0x80000000 | asyh->lut.mode << 30); evo_data(push, asyh->lut.offset >> 8); evo_mthd(push, 0x085c + (head->base.index * 0x400), 1); evo_data(push, asyh->lut.handle); } else { evo_mthd(push, 0x0440 + (head->base.index * 0x300), 4); - evo_data(push, 0x83000000); + evo_data(push, 0x80000000 | asyh->lut.mode << 24); evo_data(push, asyh->lut.offset >> 8); evo_data(push, 0x00000000); evo_data(push, 0x00000000); @@ -1896,7 +1952,7 @@ nv50_head_view(struct nv50_head *head, struct nv50_head_atom *asyh) static void nv50_head_flush_clr(struct nv50_head *head, struct nv50_head_atom *asyh, bool y) { - if (asyh->clr.core && (!asyh->set.core || y)) + if (asyh->clr.ilut && (!asyh->set.ilut || y)) nv50_head_lut_clr(head); if (asyh->clr.core && (!asyh->set.core || y)) nv50_head_core_clr(head); @@ -1909,7 +1965,15 @@ nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh) { if (asyh->set.view ) nv50_head_view (head, asyh); if (asyh->set.mode ) nv50_head_mode (head, asyh); - if (asyh->set.core ) nv50_head_lut_set (head, asyh); + if (asyh->set.ilut ) { + struct nouveau_bo *nvbo = head->lut.nvbo[head->lut.next]; + struct drm_property_blob *blob = asyh->state.gamma_lut; + if (blob) + nv50_head_lut_load(blob, asyh->lut.mode, nvbo); + asyh->lut.offset = nvbo->bo.offset; + head->lut.next ^= 1; + nv50_head_lut_set(head, asyh); + } if (asyh->set.core ) nv50_head_core_set(head, asyh); if (asyh->set.curs ) nv50_head_curs_set(head, asyh); if (asyh->set.base ) nv50_head_base (head, asyh); @@ -2044,6 +2108,37 @@ nv50_head_atomic_check_view(struct nv50_head_atom *armh, } static void +nv50_head_atomic_check_lut(struct nv50_head *head, + struct nv50_head_atom *armh, + struct nv50_head_atom *asyh) +{ + struct nv50_disp *disp = nv50_disp(head->base.base.dev); + + /* An I8 surface without an input LUT makes no sense, and + * EVO will throw an error if you try. + * + * Legacy clients actually cause this due to the order in + * which they call ioctls, so we will enable the LUT with + * whatever contents the buffer already contains to avoid + * triggering the error check. + */ + if (!asyh->state.gamma_lut && asyh->base.cpp != 1) { + asyh->lut.handle = 0; + asyh->clr.ilut = armh->lut.visible; + return; + } + + if (disp->disp->oclass < GF110_DISP) { + asyh->lut.mode = (asyh->base.cpp == 1) ? 0 : 1; + asyh->set.ilut = true; + } else { + asyh->lut.mode = 7; + asyh->set.ilut = asyh->state.color_mgmt_changed; + } + asyh->lut.handle = disp->mast.base.vram.handle; +} + +static void nv50_head_atomic_check_mode(struct nv50_head *head, struct nv50_head_atom *asyh) { struct drm_display_mode *mode = &asyh->state.adjusted_mode; @@ -2128,6 +2223,11 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state) if (asyh->state.mode_changed) nv50_head_atomic_check_mode(head, asyh); + if (asyh->state.color_mgmt_changed || + asyh->base.cpp != armh->base.cpp) + nv50_head_atomic_check_lut(head, armh, asyh); + asyh->lut.visible = asyh->lut.handle != 0; + if (asyc) { if (asyc->set.scaler) nv50_head_atomic_check_view(armh, asyh, asyc); @@ -2143,7 +2243,8 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state) asyh->core.w = asyh->base.w; asyh->core.h = asyh->base.h; } else - if ((asyh->core.visible = asyh->curs.visible)) { + if ((asyh->core.visible = asyh->curs.visible) || + (asyh->core.visible = asyh->lut.visible)) { /*XXX: We need to either find some way of having the * primary base layer appear black, while still * being able to display the other layers, or we @@ -2161,11 +2262,10 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state) asyh->core.layout = 1; asyh->core.block = 0; asyh->core.pitch = ALIGN(asyh->core.w, 64) * 4; - asyh->lut.handle = disp->mast.base.vram.handle; - asyh->lut.offset = head->base.lut.nvbo->bo.offset; asyh->set.base = armh->base.cpp != asyh->base.cpp; asyh->set.ovly = armh->ovly.cpp != asyh->ovly.cpp; } else { + asyh->lut.visible = false; asyh->core.visible = false; asyh->curs.visible = false; asyh->base.cpp = 0; @@ -2189,8 +2289,10 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state) asyh->clr.curs = true; } } else { + asyh->clr.ilut = armh->lut.visible; asyh->clr.core = armh->core.visible; asyh->clr.curs = armh->curs.visible; + asyh->set.ilut = asyh->lut.visible; asyh->set.core = asyh->core.visible; asyh->set.curs = asyh->curs.visible; } @@ -2200,47 +2302,11 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state) return 0; } -static void -nv50_head_lut_load(struct drm_crtc *crtc) -{ - struct nv50_disp *disp = nv50_disp(crtc->dev); - struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); - void __iomem *lut = nvbo_kmap_obj_iovirtual(nv_crtc->lut.nvbo); - u16 *r, *g, *b; - int i; - - r = crtc->gamma_store; - g = r + crtc->gamma_size; - b = g + crtc->gamma_size; - - for (i = 0; i < 256; i++) { - if (disp->disp->oclass < GF110_DISP) { - writew((*r++ >> 2) + 0x0000, lut + (i * 0x08) + 0); - writew((*g++ >> 2) + 0x0000, lut + (i * 0x08) + 2); - writew((*b++ >> 2) + 0x0000, lut + (i * 0x08) + 4); - } else { - /* 0x6000 interferes with the 14-bit color??? */ - writew((*r++ >> 2) + 0x6000, lut + (i * 0x20) + 0); - writew((*g++ >> 2) + 0x6000, lut + (i * 0x20) + 2); - writew((*b++ >> 2) + 0x6000, lut + (i * 0x20) + 4); - } - } -} - static const struct drm_crtc_helper_funcs nv50_head_help = { .atomic_check = nv50_head_atomic_check, }; -static int -nv50_head_gamma_set(struct drm_crtc *crtc, u16 *r, u16 *g, u16 *b, - uint32_t size, - struct drm_modeset_acquire_ctx *ctx) -{ - nv50_head_lut_load(crtc); - return 0; -} - static void nv50_head_atomic_destroy_state(struct drm_crtc *crtc, struct drm_crtc_state *state) @@ -2296,17 +2362,15 @@ nv50_head_reset(struct drm_crtc *crtc) static void nv50_head_destroy(struct drm_crtc *crtc) { - struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); struct nv50_disp *disp = nv50_disp(crtc->dev); struct nv50_head *head = nv50_head(crtc); + int i; nv50_dmac_destroy(&head->ovly.base, disp->disp); nv50_pioc_destroy(&head->oimm.base); - nouveau_bo_unmap(nv_crtc->lut.nvbo); - if (nv_crtc->lut.nvbo) - nouveau_bo_unpin(nv_crtc->lut.nvbo); - nouveau_bo_ref(NULL, &nv_crtc->lut.nvbo); + for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++) + nouveau_bo_unmap_unpin_unref(&head->lut.nvbo[i]); drm_crtc_cleanup(crtc); kfree(crtc); @@ -2315,7 +2379,7 @@ nv50_head_destroy(struct drm_crtc *crtc) static const struct drm_crtc_funcs nv50_head_func = { .reset = nv50_head_reset, - .gamma_set = nv50_head_gamma_set, + .gamma_set = drm_atomic_helper_legacy_gamma_set, .destroy = nv50_head_destroy, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -2333,7 +2397,7 @@ nv50_head_create(struct drm_device *dev, int index) struct nv50_base *base; struct nv50_curs *curs; struct drm_crtc *crtc; - int ret; + int ret, i; head = kzalloc(sizeof(*head), GFP_KERNEL); if (!head) @@ -2355,22 +2419,14 @@ nv50_head_create(struct drm_device *dev, int index) drm_crtc_helper_add(crtc, &nv50_head_help); drm_mode_crtc_set_gamma_size(crtc, 256); - ret = nouveau_bo_new(&drm->client, 8192, 0x100, TTM_PL_FLAG_VRAM, - 0, 0x0000, NULL, NULL, &head->base.lut.nvbo); - if (!ret) { - ret = nouveau_bo_pin(head->base.lut.nvbo, TTM_PL_FLAG_VRAM, true); - if (!ret) { - ret = nouveau_bo_map(head->base.lut.nvbo); - if (ret) - nouveau_bo_unpin(head->base.lut.nvbo); - } + for (i = 0; i < ARRAY_SIZE(head->lut.nvbo); i++) { + ret = nouveau_bo_new_pin_map(&drm->client, 1025 * 8, 0x100, + TTM_PL_FLAG_VRAM, + &head->lut.nvbo[i]); if (ret) - nouveau_bo_ref(NULL, &head->base.lut.nvbo); + goto out; } - if (ret) - goto out; - /* allocate overlay resources */ ret = nv50_oimm_create(device, disp->disp, index, &head->oimm); if (ret) @@ -4350,7 +4406,6 @@ nv50_display_init(struct drm_device *dev) { struct drm_encoder *encoder; struct drm_plane *plane; - struct drm_crtc *crtc; u32 *push; push = evo_wait(nv50_mast(dev), 32); @@ -4369,10 +4424,6 @@ nv50_display_init(struct drm_device *dev) } } - drm_for_each_crtc(crtc, dev) { - nv50_head_lut_load(crtc); - } - drm_for_each_plane(plane, dev) { struct nv50_wndw *wndw = nv50_wndw(plane); if (plane->funcs != &nv50_wndw) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 08e77cd55e6e..05cd674326a6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -28,6 +28,7 @@ #include <core/option.h> #include <subdev/bios.h> +#include <subdev/therm.h> static DEFINE_MUTEX(nv_devices_mutex); static LIST_HEAD(nv_devices); @@ -1682,7 +1683,7 @@ nve4_chipset = { .mxm = nv50_mxm_new, .pci = gk104_pci_new, .pmu = gk104_pmu_new, - .therm = gf119_therm_new, + .therm = gk104_therm_new, .timer = nv41_timer_new, .top = gk104_top_new, .volt = gk104_volt_new, @@ -1721,7 +1722,7 @@ nve6_chipset = { .mxm = nv50_mxm_new, .pci = gk104_pci_new, .pmu = gk104_pmu_new, - .therm = gf119_therm_new, + .therm = gk104_therm_new, .timer = nv41_timer_new, .top = gk104_top_new, .volt = gk104_volt_new, @@ -1760,7 +1761,7 @@ nve7_chipset = { .mxm = nv50_mxm_new, .pci = gk104_pci_new, .pmu = gk104_pmu_new, - .therm = gf119_therm_new, + .therm = gk104_therm_new, .timer = nv41_timer_new, .top = gk104_top_new, .volt = gk104_volt_new, @@ -1811,7 +1812,7 @@ nvf0_chipset = { .bus = gf100_bus_new, .clk = gk104_clk_new, .devinit = gf100_devinit_new, - .fb = gk104_fb_new, + .fb = gk110_fb_new, .fuse = gf100_fuse_new, .gpio = gk104_gpio_new, .i2c = gk104_i2c_new, @@ -1824,7 +1825,7 @@ nvf0_chipset = { .mxm = nv50_mxm_new, .pci = gk104_pci_new, .pmu = gk110_pmu_new, - .therm = gf119_therm_new, + .therm = gk104_therm_new, .timer = nv41_timer_new, .top = gk104_top_new, .volt = gk104_volt_new, @@ -1849,7 +1850,7 @@ nvf1_chipset = { .bus = gf100_bus_new, .clk = gk104_clk_new, .devinit = gf100_devinit_new, - .fb = gk104_fb_new, + .fb = gk110_fb_new, .fuse = gf100_fuse_new, .gpio = gk104_gpio_new, .i2c = gk104_i2c_new, @@ -1862,7 +1863,7 @@ nvf1_chipset = { .mxm = nv50_mxm_new, .pci = gk104_pci_new, .pmu = gk110_pmu_new, - .therm = gf119_therm_new, + .therm = gk104_therm_new, .timer = nv41_timer_new, .top = gk104_top_new, .volt = gk104_volt_new, @@ -1887,7 +1888,7 @@ nv106_chipset = { .bus = gf100_bus_new, .clk = gk104_clk_new, .devinit = gf100_devinit_new, - .fb = gk104_fb_new, + .fb = gk110_fb_new, .fuse = gf100_fuse_new, .gpio = gk104_gpio_new, .i2c = gk104_i2c_new, @@ -1900,7 +1901,7 @@ nv106_chipset = { .mxm = nv50_mxm_new, .pci = gk104_pci_new, .pmu = gk208_pmu_new, - .therm = gf119_therm_new, + .therm = gk104_therm_new, .timer = nv41_timer_new, .top = gk104_top_new, .volt = gk104_volt_new, @@ -1925,7 +1926,7 @@ nv108_chipset = { .bus = gf100_bus_new, .clk = gk104_clk_new, .devinit = gf100_devinit_new, - .fb = gk104_fb_new, + .fb = gk110_fb_new, .fuse = gf100_fuse_new, .gpio = gk104_gpio_new, .i2c = gk104_i2c_new, @@ -1938,7 +1939,7 @@ nv108_chipset = { .mxm = nv50_mxm_new, .pci = gk104_pci_new, .pmu = gk208_pmu_new, - .therm = gf119_therm_new, + .therm = gk104_therm_new, .timer = nv41_timer_new, .top = gk104_top_new, .volt = gk104_volt_new, @@ -2345,6 +2346,7 @@ nv138_chipset = { .mc = gp100_mc_new, .mmu = gp100_mmu_new, .therm = gp100_therm_new, + .secboot = gp108_secboot_new, .pci = gp100_pci_new, .pmu = gp102_pmu_new, .timer = gk20a_timer_new, @@ -2356,6 +2358,10 @@ nv138_chipset = { .disp = gp102_disp_new, .dma = gf119_dma_new, .fifo = gp100_fifo_new, + .gr = gp107_gr_new, + .nvdec = gp102_nvdec_new, + .sec2 = gp102_sec2_new, + .sw = gf100_sw_new, }; static const struct nvkm_device_chip @@ -2508,6 +2514,7 @@ nvkm_device_fini(struct nvkm_device *device, bool suspend) } } + nvkm_therm_clkgate_fini(device->therm, suspend); if (device->func->fini) device->func->fini(device, suspend); @@ -2597,6 +2604,7 @@ nvkm_device_init(struct nvkm_device *device) } nvkm_acpi_init(device); + nvkm_therm_clkgate_enable(device->therm); time = ktime_to_us(ktime_get()) - time; nvdev_trace(device, "init completed in %lldus\n", time); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h index d7c2adb9b543..c8ec3fd97155 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h @@ -137,6 +137,7 @@ struct gf100_gr_func { int (*rops)(struct gf100_gr *); int ppc_nr; const struct gf100_grctx_func *grctx; + const struct nvkm_therm_clkgate_pack *clkgate_pack; struct nvkm_sclass sclass[]; }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c index 5e82f94c2245..1b52fcb2c49a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c @@ -22,6 +22,7 @@ * Authors: Ben Skeggs <bskeggs@redhat.com> */ #include "gf100.h" +#include "gk104.h" #include "ctxgf100.h" #include <nvif/class.h> @@ -173,6 +174,208 @@ gk104_gr_pack_mmio[] = { {} }; +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_main_0[] = { + { 0x4041f0, 1, 0x00004046 }, + { 0x409890, 1, 0x00000045 }, + { 0x4098b0, 1, 0x0000007f }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_rstr2d_0[] = { + { 0x4078c0, 1, 0x00000042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_unk_0[] = { + { 0x406000, 1, 0x00004044 }, + { 0x405860, 1, 0x00004042 }, + { 0x40590c, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gcc_0[] = { + { 0x408040, 1, 0x00004044 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_sked_0[] = { + { 0x407000, 1, 0x00004044 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_unk_1[] = { + { 0x405bf0, 1, 0x00004044 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_ctxctl_0[] = { + { 0x41a890, 1, 0x00000042 }, + { 0x41a8b0, 1, 0x0000007f }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_unk_0[] = { + { 0x418500, 1, 0x00004042 }, + { 0x418608, 1, 0x00004042 }, + { 0x418688, 1, 0x00004042 }, + { 0x418718, 1, 0x00000042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_esetup_0[] = { + { 0x418828, 1, 0x00000044 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_tpbus_0[] = { + { 0x418bbc, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_zcull_0[] = { + { 0x418970, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_tpconf_0[] = { + { 0x418c70, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_unk_1[] = { + { 0x418cf0, 1, 0x00004042 }, + { 0x418d70, 1, 0x00004042 }, + { 0x418f0c, 1, 0x00004042 }, + { 0x418e0c, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_gcc_0[] = { + { 0x419020, 1, 0x00004042 }, + { 0x419038, 1, 0x00000042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_ffb_0[] = { + { 0x418898, 1, 0x00000042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_tex_0[] = { + { 0x419a40, 9, 0x00004042 }, + { 0x419acc, 1, 0x00004047 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_poly_0[] = { + { 0x419868, 1, 0x00000042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_l1c_0[] = { + { 0x419ccc, 3, 0x00000042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_unk_2[] = { + { 0x419c70, 1, 0x00004045 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_mp_0[] = { + { 0x419fd0, 1, 0x00004043 }, + { 0x419fd8, 1, 0x00004049 }, + { 0x419fe0, 2, 0x00004042 }, + { 0x419ff0, 1, 0x00004046 }, + { 0x419ff8, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_gpc_ppc_0[] = { + { 0x41be28, 1, 0x00000042 }, + { 0x41bfe8, 1, 0x00004042 }, + { 0x41bed0, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_rop_zrop_0[] = { + { 0x408810, 2, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_rop_0[] = { + { 0x408a80, 6, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_rop_crop_0[] = { + { 0x4089a8, 1, 0x00004042 }, + { 0x4089b0, 1, 0x00000042 }, + { 0x4089b8, 1, 0x00004042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_clkgate_blcg_init_pxbar_0[] = { + { 0x13c820, 1, 0x0001007f }, + { 0x13cbe0, 1, 0x00000042 }, + {} +}; + +static const struct nvkm_therm_clkgate_pack +gk104_clkgate_pack[] = { + { gk104_clkgate_blcg_init_main_0 }, + { gk104_clkgate_blcg_init_rstr2d_0 }, + { gk104_clkgate_blcg_init_unk_0 }, + { gk104_clkgate_blcg_init_gcc_0 }, + { gk104_clkgate_blcg_init_sked_0 }, + { gk104_clkgate_blcg_init_unk_1 }, + { gk104_clkgate_blcg_init_gpc_ctxctl_0 }, + { gk104_clkgate_blcg_init_gpc_unk_0 }, + { gk104_clkgate_blcg_init_gpc_esetup_0 }, + { gk104_clkgate_blcg_init_gpc_tpbus_0 }, + { gk104_clkgate_blcg_init_gpc_zcull_0 }, + { gk104_clkgate_blcg_init_gpc_tpconf_0 }, + { gk104_clkgate_blcg_init_gpc_unk_1 }, + { gk104_clkgate_blcg_init_gpc_gcc_0 }, + { gk104_clkgate_blcg_init_gpc_ffb_0 }, + { gk104_clkgate_blcg_init_gpc_tex_0 }, + { gk104_clkgate_blcg_init_gpc_poly_0 }, + { gk104_clkgate_blcg_init_gpc_l1c_0 }, + { gk104_clkgate_blcg_init_gpc_unk_2 }, + { gk104_clkgate_blcg_init_gpc_mp_0 }, + { gk104_clkgate_blcg_init_gpc_ppc_0 }, + { gk104_clkgate_blcg_init_rop_zrop_0 }, + { gk104_clkgate_blcg_init_rop_0 }, + { gk104_clkgate_blcg_init_rop_crop_0 }, + { gk104_clkgate_blcg_init_pxbar_0 }, + {} +}; + /******************************************************************************* * PGRAPH engine/subdev functions ******************************************************************************/ @@ -214,6 +417,9 @@ gk104_gr_init(struct gf100_gr *gr) gr->func->init_gpc_mmu(gr); gf100_gr_mmio(gr, gr->func->mmio); + if (gr->func->clkgate_pack) + nvkm_therm_clkgate_init(gr->base.engine.subdev.device->therm, + gr->func->clkgate_pack); nvkm_wr32(device, GPC_UNIT(0, 0x3018), 0x00000001); @@ -338,6 +544,7 @@ gk104_gr = { .rops = gf100_gr_rops, .ppc_nr = 1, .grctx = &gk104_grctx, + .clkgate_pack = gk104_clkgate_pack, .sclass = { { -1, -1, FERMI_TWOD_A }, { -1, -1, KEPLER_INLINE_TO_MEMORY_A }, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.h new file mode 100644 index 000000000000..a24c177365d1 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.h @@ -0,0 +1,55 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Lyude Paul <lyude@redhat.com> + */ +#ifndef __GK104_GR_H__ +#define __GK104_GR_H__ + +#include <subdev/therm.h> + +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_main_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rstr2d_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_unk_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gcc_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_sked_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_unk_1[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ctxctl_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_esetup_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tpbus_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_zcull_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tpconf_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_1[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_gcc_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ffb_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_tex_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_poly_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_l1c_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_unk_2[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_mp_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_gpc_ppc_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_zrop_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_rop_crop_0[]; +extern const struct nvkm_therm_clkgate_init gk104_clkgate_blcg_init_pxbar_0[]; + +#endif diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c index a38e19b61c1d..4da916a9fc73 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c @@ -22,6 +22,7 @@ * Authors: Ben Skeggs <bskeggs@redhat.com> */ #include "gf100.h" +#include "gk104.h" #include "ctxgf100.h" #include <subdev/timer.h> @@ -156,6 +157,159 @@ gk110_gr_pack_mmio[] = { {} }; +static const struct nvkm_therm_clkgate_init +gk110_clkgate_blcg_init_sked_0[] = { + { 0x407000, 1, 0x00004041 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_blcg_init_gpc_gcc_0[] = { + { 0x419020, 1, 0x00000042 }, + { 0x419038, 1, 0x00000042 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_blcg_init_gpc_l1c_0[] = { + { 0x419cd4, 2, 0x00004042 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_blcg_init_gpc_mp_0[] = { + { 0x419fd0, 1, 0x00004043 }, + { 0x419fd8, 1, 0x00004049 }, + { 0x419fe0, 2, 0x00004042 }, + { 0x419ff0, 1, 0x00000046 }, + { 0x419ff8, 1, 0x00004042 }, + { 0x419f90, 1, 0x00004042 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_main_0[] = { + { 0x4041f4, 1, 0x00000000 }, + { 0x409894, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_unk_0[] = { + { 0x406004, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_sked_0[] = { + { 0x407004, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_ctxctl_0[] = { + { 0x41a894, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_unk_0[] = { + { 0x418504, 1, 0x00000000 }, + { 0x41860c, 1, 0x00000000 }, + { 0x41868c, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_esetup_0[] = { + { 0x41882c, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_zcull_0[] = { + { 0x418974, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_l1c_0[] = { + { 0x419cd8, 2, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_unk_1[] = { + { 0x419c74, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_mp_0[] = { + { 0x419fd4, 1, 0x00004a4a }, + { 0x419fdc, 1, 0x00000014 }, + { 0x419fe4, 1, 0x00000000 }, + { 0x419ff4, 1, 0x00001724 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_gpc_ppc_0[] = { + { 0x41be2c, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_init +gk110_clkgate_slcg_init_pcounter_0[] = { + { 0x1be018, 1, 0x000001ff }, + { 0x1bc018, 1, 0x000001ff }, + { 0x1b8018, 1, 0x000001ff }, + { 0x1b4124, 1, 0x00000000 }, + {} +}; + +static const struct nvkm_therm_clkgate_pack +gk110_clkgate_pack[] = { + { gk104_clkgate_blcg_init_main_0 }, + { gk104_clkgate_blcg_init_rstr2d_0 }, + { gk104_clkgate_blcg_init_unk_0 }, + { gk104_clkgate_blcg_init_gcc_0 }, + { gk110_clkgate_blcg_init_sked_0 }, + { gk104_clkgate_blcg_init_unk_1 }, + { gk104_clkgate_blcg_init_gpc_ctxctl_0 }, + { gk104_clkgate_blcg_init_gpc_unk_0 }, + { gk104_clkgate_blcg_init_gpc_esetup_0 }, + { gk104_clkgate_blcg_init_gpc_tpbus_0 }, + { gk104_clkgate_blcg_init_gpc_zcull_0 }, + { gk104_clkgate_blcg_init_gpc_tpconf_0 }, + { gk104_clkgate_blcg_init_gpc_unk_1 }, + { gk110_clkgate_blcg_init_gpc_gcc_0 }, + { gk104_clkgate_blcg_init_gpc_ffb_0 }, + { gk104_clkgate_blcg_init_gpc_tex_0 }, + { gk104_clkgate_blcg_init_gpc_poly_0 }, + { gk110_clkgate_blcg_init_gpc_l1c_0 }, + { gk104_clkgate_blcg_init_gpc_unk_2 }, + { gk110_clkgate_blcg_init_gpc_mp_0 }, + { gk104_clkgate_blcg_init_gpc_ppc_0 }, + { gk104_clkgate_blcg_init_rop_zrop_0 }, + { gk104_clkgate_blcg_init_rop_0 }, + { gk104_clkgate_blcg_init_rop_crop_0 }, + { gk104_clkgate_blcg_init_pxbar_0 }, + { gk110_clkgate_slcg_init_main_0 }, + { gk110_clkgate_slcg_init_unk_0 }, + { gk110_clkgate_slcg_init_sked_0 }, + { gk110_clkgate_slcg_init_gpc_ctxctl_0 }, + { gk110_clkgate_slcg_init_gpc_unk_0 }, + { gk110_clkgate_slcg_init_gpc_esetup_0 }, + { gk110_clkgate_slcg_init_gpc_zcull_0 }, + { gk110_clkgate_slcg_init_gpc_l1c_0 }, + { gk110_clkgate_slcg_init_gpc_unk_1 }, + { gk110_clkgate_slcg_init_gpc_mp_0 }, + { gk110_clkgate_slcg_init_gpc_ppc_0 }, + { gk110_clkgate_slcg_init_pcounter_0 }, + {} +}; + /******************************************************************************* * PGRAPH engine/subdev functions ******************************************************************************/ @@ -192,6 +346,7 @@ gk110_gr = { .rops = gf100_gr_rops, .ppc_nr = 2, .grctx = &gk110_grctx, + .clkgate_pack = gk110_clkgate_pack, .sclass = { { -1, -1, FERMI_TWOD_A }, { -1, -1, KEPLER_INLINE_TO_MEMORY_B }, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c index dde89a4a0f5b..53859b6254d6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c @@ -462,7 +462,7 @@ nvkm_perfmon_mthd_query_domain(struct nvkm_perfmon *perfmon, args->v0.id = di; args->v0.signal_nr = nvkm_perfdom_count_perfsig(dom); - strncpy(args->v0.name, dom->name, sizeof(args->v0.name)); + strncpy(args->v0.name, dom->name, sizeof(args->v0.name) - 1); /* Currently only global counters (PCOUNTER) are implemented * but this will be different for local counters (MP). */ @@ -514,7 +514,7 @@ nvkm_perfmon_mthd_query_signal(struct nvkm_perfmon *perfmon, "/%s/%02x", dom->name, si); } else { strncpy(args->v0.name, sig->name, - sizeof(args->v0.name)); + sizeof(args->v0.name) - 1); } args->v0.signal = si; @@ -572,7 +572,7 @@ nvkm_perfmon_mthd_query_source(struct nvkm_perfmon *perfmon, args->v0.source = sig->source[si]; args->v0.mask = src->mask; - strncpy(args->v0.name, src->name, sizeof(args->v0.name)); + strncpy(args->v0.name, src->name, sizeof(args->v0.name) - 1); } if (++si < source_nr) { diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c index 77273b53672c..58a59b7db2e5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c @@ -505,6 +505,7 @@ nvkm_msgqueue_new(u32 version, struct nvkm_falcon *falcon, ret = msgqueue_0137bca5_new(falcon, sb, queue); break; case 0x0148cdec: + case 0x015ccf3e: ret = msgqueue_0148cdec_new(falcon, sb, queue); break; default: diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c index 96e0941c8edd..f0a26881d9b9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c @@ -110,6 +110,7 @@ read_pll(struct gt215_clk *clk, int idx, u32 pll) struct nvkm_device *device = clk->base.subdev.device; u32 ctrl = nvkm_rd32(device, pll + 0); u32 sclk = 0, P = 1, N = 1, M = 1; + u32 MP; if (!(ctrl & 0x00000008)) { if (ctrl & 0x00000001) { @@ -130,10 +131,12 @@ read_pll(struct gt215_clk *clk, int idx, u32 pll) sclk = read_clk(clk, 0x10 + idx, false); } - if (M * P) - return sclk * N / (M * P); + MP = M * P; - return 0; + if (!MP) + return 0; + + return sclk * N / MP; } static int diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild index 2571530e82f1..b4f22cce5d43 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild @@ -22,6 +22,7 @@ nvkm-y += nvkm/subdev/fb/mcp89.o nvkm-y += nvkm/subdev/fb/gf100.o nvkm-y += nvkm/subdev/fb/gf108.o nvkm-y += nvkm/subdev/fb/gk104.o +nvkm-y += nvkm/subdev/fb/gk110.o nvkm-y += nvkm/subdev/fb/gk20a.o nvkm-y += nvkm/subdev/fb/gm107.o nvkm-y += nvkm/subdev/fb/gm200.o diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c index 47d28c279707..cdc4e0a2cc6b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf100.c @@ -26,6 +26,7 @@ #include <core/memory.h> #include <core/option.h> +#include <subdev/therm.h> void gf100_fb_intr(struct nvkm_fb *base) @@ -92,6 +93,11 @@ gf100_fb_init(struct nvkm_fb *base) if (fb->r100c10_page) nvkm_wr32(device, 0x100c10, fb->r100c10 >> 8); + + if (base->func->clkgate_pack) { + nvkm_therm_clkgate_init(device->therm, + base->func->clkgate_pack); + } } void * diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c index 0a6e8eaad42c..48fd98e08baa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c @@ -20,10 +20,56 @@ * OTHER DEALINGS IN THE SOFTWARE. * * Authors: Ben Skeggs + * Lyude Paul */ +#include "gk104.h" #include "gf100.h" #include "ram.h" +/* + ******************************************************************************* + * PGRAPH registers for clockgating + ******************************************************************************* + */ +const struct nvkm_therm_clkgate_init +gk104_fb_clkgate_blcg_init_unk_0[] = { + { 0x100d10, 1, 0x0000c244 }, + { 0x100d30, 1, 0x0000c242 }, + { 0x100d3c, 1, 0x00000242 }, + { 0x100d48, 1, 0x00000242 }, + { 0x100d1c, 1, 0x00000042 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_fb_clkgate_blcg_init_vm_0[] = { + { 0x100c98, 1, 0x00000242 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_fb_clkgate_blcg_init_main_0[] = { + { 0x10f000, 1, 0x00000042 }, + { 0x17e030, 1, 0x00000044 }, + { 0x17e040, 1, 0x00000044 }, + {} +}; + +const struct nvkm_therm_clkgate_init +gk104_fb_clkgate_blcg_init_bcast_0[] = { + { 0x17ea60, 4, 0x00000044 }, + {} +}; + +static const struct nvkm_therm_clkgate_pack +gk104_fb_clkgate_pack[] = { + { gk104_fb_clkgate_blcg_init_unk_0 }, + { gk104_fb_clkgate_blcg_init_vm_0 }, + { gk104_fb_clkgate_blcg_init_main_0 }, + { gk104_fb_clkgate_blcg_init_bcast_0 }, + {} +}; + static const struct nvkm_fb_func gk104_fb = { .dtor = gf100_fb_dtor, @@ -33,6 +79,7 @@ gk104_fb = { .intr = gf100_fb_intr, .ram_new = gk104_ram_new, .default_bigpage = 17, + .clkgate_pack = gk104_fb_clkgate_pack, }; int diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.h new file mode 100644 index 000000000000..b3c78e4ff706 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.h @@ -0,0 +1,35 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Lyude Paul + */ + +#ifndef __GK104_FB_H__ +#define __GK104_FB_H__ + +#include <subdev/therm.h> + +extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_unk_0[]; +extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_vm_0[]; +extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_main_0[]; +extern const struct nvkm_therm_clkgate_init gk104_fb_clkgate_blcg_init_bcast_0[]; + +#endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c new file mode 100644 index 000000000000..0695e5dd360e --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c @@ -0,0 +1,71 @@ +/* + * Copyright 2017 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Lyude Paul + */ +#include "gf100.h" +#include "gk104.h" +#include "ram.h" +#include <subdev/therm.h> +#include <subdev/fb.h> + +/* + ******************************************************************************* + * PGRAPH registers for clockgating + ******************************************************************************* + */ + +static const struct nvkm_therm_clkgate_init +gk110_fb_clkgate_blcg_init_unk_0[] = { + { 0x100d10, 1, 0x0000c242 }, + { 0x100d30, 1, 0x0000c242 }, + { 0x100d3c, 1, 0x00000242 }, + { 0x100d48, 1, 0x0000c242 }, + { 0x100d1c, 1, 0x00000042 }, + {} +}; + +static const struct nvkm_therm_clkgate_pack +gk110_fb_clkgate_pack[] = { + { gk110_fb_clkgate_blcg_init_unk_0 }, + { gk104_fb_clkgate_blcg_init_vm_0 }, + { gk104_fb_clkgate_blcg_init_main_0 }, + { gk104_fb_clkgate_blcg_init_bcast_0 }, + {} +}; + +static const struct nvkm_fb_func +gk110_fb = { + .dtor = gf100_fb_dtor, + .oneinit = gf100_fb_oneinit, + .init = gf100_fb_init, + .init_page = gf100_fb_init_page, + .intr = gf100_fb_intr, + .ram_new = gk104_ram_new, + .default_bigpage = 17, + .clkgate_pack = gk110_fb_clkgate_pack, +}; + +int +gk110_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb) +{ + return gf100_fb_new_(&gk110_fb, device, index, pfb); +} diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h index 9351188d5d76..414a423e0e55 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h @@ -3,6 +3,7 @@ #define __NVKM_FB_PRIV_H__ #define nvkm_fb(p) container_of((p), struct nvkm_fb, subdev) #include <subdev/fb.h> +#include <subdev/therm.h> struct nvkm_bios; struct nvkm_fb_func { @@ -27,6 +28,7 @@ struct nvkm_fb_func { int (*ram_new)(struct nvkm_fb *, struct nvkm_ram **); u8 default_bigpage; + const struct nvkm_therm_clkgate_pack *clkgate_pack; }; void nvkm_fb_ctor(const struct nvkm_fb_func *, struct nvkm_device *device, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c index fa81d0c1ba41..37b201b95f15 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c @@ -106,7 +106,8 @@ nvkm_uvmm_mthd_map(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } else return ret; - if (IS_ERR((memory = nvkm_umem_search(client, handle)))) { + memory = nvkm_umem_search(client, handle); + if (IS_ERR(memory)) { VMM_DEBUG(vmm, "memory %016llx %ld\n", handle, PTR_ERR(memory)); return PTR_ERR(memory); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index e35d3e17cd7c..93946dcee319 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -642,7 +642,7 @@ nvkm_vmm_ptes_sparse(struct nvkm_vmm *vmm, u64 addr, u64 size, bool ref) else block = (size >> page[i].shift) << page[i].shift; } else { - block = (size >> page[i].shift) << page[i].shift;; + block = (size >> page[i].shift) << page[i].shift; } /* Perform operation. */ diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h index 53d01fb00a8b..1dbe593e5960 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h @@ -47,8 +47,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x584d454d, - 0x00000756, - 0x00000748, + 0x00000754, + 0x00000746, 0x00000000, 0x00000000, 0x00000000, @@ -69,8 +69,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x46524550, - 0x0000075a, 0x00000758, + 0x00000756, 0x00000000, 0x00000000, 0x00000000, @@ -91,8 +91,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x5f433249, - 0x00000b8a, - 0x00000a2d, + 0x00000b88, + 0x00000a2b, 0x00000000, 0x00000000, 0x00000000, @@ -113,8 +113,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x54534554, - 0x00000bb3, - 0x00000b8c, + 0x00000bb1, + 0x00000b8a, 0x00000000, 0x00000000, 0x00000000, @@ -135,8 +135,8 @@ static uint32_t gf100_pmu_data[] = { 0x00000000, 0x00000000, 0x454c4449, - 0x00000bbf, 0x00000bbd, + 0x00000bbb, 0x00000000, 0x00000000, 0x00000000, @@ -237,19 +237,19 @@ static uint32_t gf100_pmu_data[] = { 0x000005d3, 0x00000003, 0x00000002, - 0x0000069d, + 0x0000069b, 0x00040004, 0x00000000, - 0x000006b9, + 0x000006b7, 0x00010005, 0x00000000, - 0x000006d6, + 0x000006d4, 0x00010006, 0x00000000, 0x0000065b, 0x00000007, 0x00000000, - 0x000006e1, + 0x000006df, /* 0x03c4: memx_func_tail */ /* 0x03c4: memx_ts_start */ 0x00000000, @@ -1373,432 +1373,432 @@ static uint32_t gf100_pmu_code[] = { /* 0x065b: memx_func_wait_vblank */ 0x9800f840, 0x66b00016, - 0x130bf400, + 0x120bf400, 0xf40166b0, 0x0ef4060b, /* 0x066d: memx_func_wait_vblank_head1 */ - 0x2077f12e, - 0x070ef400, -/* 0x0674: memx_func_wait_vblank_head0 */ - 0x000877f1, -/* 0x0678: memx_func_wait_vblank_0 */ - 0x07c467f1, - 0xcf0664b6, - 0x67fd0066, - 0xf31bf404, -/* 0x0688: memx_func_wait_vblank_1 */ - 0x07c467f1, - 0xcf0664b6, - 0x67fd0066, - 0xf30bf404, -/* 0x0698: memx_func_wait_vblank_fini */ - 0xf80410b6, -/* 0x069d: memx_func_wr32 */ - 0x00169800, - 0xb6011598, - 0x60f90810, - 0xd0fc50f9, - 0x21f4e0fc, - 0x0242b640, - 0xf8e91bf4, -/* 0x06b9: memx_func_wait */ - 0x2c87f000, - 0xcf0684b6, - 0x1e980088, - 0x011d9800, - 0x98021c98, - 0x10b6031b, - 0xa321f410, -/* 0x06d6: memx_func_delay */ - 0x1e9800f8, - 0x0410b600, - 0xf87e21f4, -/* 0x06e1: memx_func_train */ -/* 0x06e3: memx_exec */ - 0xf900f800, - 0xb9d0f9e0, - 0xb2b902c1, -/* 0x06ed: memx_exec_next */ - 0x00139802, - 0xe70410b6, - 0xe701f034, - 0xb601e033, - 0x30f00132, - 0xde35980c, - 0x12b855f9, - 0xe41ef406, - 0x98f10b98, - 0xcbbbf20c, - 0xc4b7f102, - 0x06b4b607, - 0xfc00bbcf, - 0xf5e0fcd0, - 0xf8033621, -/* 0x0729: memx_info */ - 0x01c67000, -/* 0x072f: memx_info_data */ - 0xf10e0bf4, - 0xf103ccc7, - 0xf40800b7, -/* 0x073a: memx_info_train */ - 0xc7f10b0e, - 0xb7f10bcc, -/* 0x0742: memx_info_send */ - 0x21f50100, - 0x00f80336, -/* 0x0748: memx_recv */ - 0xf401d6b0, - 0xd6b0980b, - 0xd80bf400, -/* 0x0756: memx_init */ - 0x00f800f8, -/* 0x0758: perf_recv */ -/* 0x075a: perf_init */ + 0x2077f02c, +/* 0x0673: memx_func_wait_vblank_head0 */ + 0xf0060ef4, +/* 0x0676: memx_func_wait_vblank_0 */ + 0x67f10877, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x0686: memx_func_wait_vblank_1 */ + 0x67f1f31b, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x0696: memx_func_wait_vblank_fini */ + 0x10b6f30b, +/* 0x069b: memx_func_wr32 */ + 0x9800f804, + 0x15980016, + 0x0810b601, + 0x50f960f9, + 0xe0fcd0fc, + 0xb64021f4, + 0x1bf40242, +/* 0x06b7: memx_func_wait */ + 0xf000f8e9, + 0x84b62c87, + 0x0088cf06, + 0x98001e98, + 0x1c98011d, + 0x031b9802, + 0xf41010b6, + 0x00f8a321, +/* 0x06d4: memx_func_delay */ + 0xb6001e98, + 0x21f40410, +/* 0x06df: memx_func_train */ + 0xf800f87e, +/* 0x06e1: memx_exec */ + 0xf9e0f900, + 0x02c1b9d0, +/* 0x06eb: memx_exec_next */ + 0x9802b2b9, + 0x10b60013, + 0xf034e704, + 0xe033e701, + 0x0132b601, + 0x980c30f0, + 0x55f9de35, + 0xf40612b8, + 0x0b98e41e, + 0xf20c98f1, + 0xf102cbbb, + 0xb607c4b7, + 0xbbcf06b4, + 0xfcd0fc00, + 0x3621f5e0, +/* 0x0727: memx_info */ + 0x7000f803, + 0x0bf401c6, +/* 0x072d: memx_info_data */ + 0xccc7f10e, + 0x00b7f103, + 0x0b0ef408, +/* 0x0738: memx_info_train */ + 0x0bccc7f1, + 0x0100b7f1, +/* 0x0740: memx_info_send */ + 0x033621f5, +/* 0x0746: memx_recv */ + 0xd6b000f8, + 0x980bf401, + 0xf400d6b0, + 0x00f8d80b, +/* 0x0754: memx_init */ +/* 0x0756: perf_recv */ 0x00f800f8, -/* 0x075c: i2c_drive_scl */ - 0xf40036b0, - 0x07f1110b, - 0x04b607e0, - 0x0001d006, - 0x00f804bd, -/* 0x0770: i2c_drive_scl_lo */ - 0x07e407f1, - 0xd00604b6, - 0x04bd0001, -/* 0x077e: i2c_drive_sda */ +/* 0x0758: perf_init */ +/* 0x075a: i2c_drive_scl */ 0x36b000f8, 0x110bf400, 0x07e007f1, 0xd00604b6, - 0x04bd0002, -/* 0x0792: i2c_drive_sda_lo */ + 0x04bd0001, +/* 0x076e: i2c_drive_scl_lo */ 0x07f100f8, 0x04b607e4, + 0x0001d006, + 0x00f804bd, +/* 0x077c: i2c_drive_sda */ + 0xf40036b0, + 0x07f1110b, + 0x04b607e0, 0x0002d006, 0x00f804bd, -/* 0x07a0: i2c_sense_scl */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0431fd00, - 0xf4060bf4, -/* 0x07b6: i2c_sense_scl_done */ - 0x00f80131, -/* 0x07b8: i2c_sense_sda */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0432fd00, - 0xf4060bf4, -/* 0x07ce: i2c_sense_sda_done */ - 0x00f80131, -/* 0x07d0: i2c_raise_scl */ - 0x47f140f9, - 0x37f00898, - 0x5c21f501, -/* 0x07dd: i2c_raise_scl_wait */ - 0xe8e7f107, - 0x7e21f403, - 0x07a021f5, - 0xb60901f4, - 0x1bf40142, -/* 0x07f1: i2c_raise_scl_done */ - 0xf840fcef, -/* 0x07f5: i2c_start */ - 0xa021f500, - 0x0d11f407, - 0x07b821f5, - 0xf40611f4, -/* 0x0806: i2c_start_rep */ - 0x37f0300e, - 0x5c21f500, - 0x0137f007, - 0x077e21f5, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0xd021f550, - 0x0464b607, -/* 0x0833: i2c_start_send */ - 0xf01f11f4, +/* 0x0790: i2c_drive_sda_lo */ + 0x07e407f1, + 0xd00604b6, + 0x04bd0002, +/* 0x079e: i2c_sense_scl */ + 0x32f400f8, + 0xc437f101, + 0x0634b607, + 0xfd0033cf, + 0x0bf40431, + 0x0131f406, +/* 0x07b4: i2c_sense_scl_done */ +/* 0x07b6: i2c_sense_sda */ + 0x32f400f8, + 0xc437f101, + 0x0634b607, + 0xfd0033cf, + 0x0bf40432, + 0x0131f406, +/* 0x07cc: i2c_sense_sda_done */ +/* 0x07ce: i2c_raise_scl */ + 0x40f900f8, + 0x089847f1, + 0xf50137f0, +/* 0x07db: i2c_raise_scl_wait */ + 0xf1075a21, + 0xf403e8e7, + 0x21f57e21, + 0x01f4079e, + 0x0142b609, +/* 0x07ef: i2c_raise_scl_done */ + 0xfcef1bf4, +/* 0x07f3: i2c_start */ + 0xf500f840, + 0xf4079e21, + 0x21f50d11, + 0x11f407b6, + 0x300ef406, +/* 0x0804: i2c_start_rep */ + 0xf50037f0, + 0xf0075a21, + 0x21f50137, + 0x76bb077c, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb607ce21, + 0x11f40464, +/* 0x0831: i2c_start_send */ + 0x0037f01f, + 0x077c21f5, + 0x1388e7f1, + 0xf07e21f4, 0x21f50037, - 0xe7f1077e, + 0xe7f1075a, 0x21f41388, - 0x0037f07e, - 0x075c21f5, - 0x1388e7f1, -/* 0x084f: i2c_start_out */ - 0xf87e21f4, -/* 0x0851: i2c_stop */ - 0x0037f000, - 0x075c21f5, - 0xf50037f0, - 0xf1077e21, - 0xf403e8e7, - 0x37f07e21, - 0x5c21f501, - 0x88e7f107, - 0x7e21f413, +/* 0x084d: i2c_start_out */ +/* 0x084f: i2c_stop */ + 0xf000f87e, + 0x21f50037, + 0x37f0075a, + 0x7c21f500, + 0xe8e7f107, + 0x7e21f403, 0xf50137f0, - 0xf1077e21, + 0xf1075a21, 0xf41388e7, - 0x00f87e21, -/* 0x0884: i2c_bitw */ - 0x077e21f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x07d021f5, - 0xf40464b6, - 0xe7f11811, - 0x21f41388, - 0x0037f07e, - 0x075c21f5, - 0x1388e7f1, -/* 0x08c3: i2c_bitw_out */ - 0xf87e21f4, -/* 0x08c5: i2c_bitr */ - 0x0137f000, - 0x077e21f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x07d021f5, - 0xf40464b6, - 0x21f51b11, - 0x37f007b8, - 0x5c21f500, + 0x37f07e21, + 0x7c21f501, 0x88e7f107, 0x7e21f413, - 0xf4013cf0, -/* 0x090a: i2c_bitr_done */ - 0x00f80131, -/* 0x090c: i2c_get_byte */ - 0xf00057f0, -/* 0x0912: i2c_get_byte_next */ - 0x54b60847, - 0x0076bb01, +/* 0x0882: i2c_bitw */ + 0x21f500f8, + 0xe7f1077c, + 0x21f403e8, + 0x0076bb7e, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b608c5, - 0x2b11f404, - 0xb60553fd, - 0x1bf40142, - 0x0137f0d8, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0x8421f550, - 0x0464b608, -/* 0x095c: i2c_get_byte_done */ -/* 0x095e: i2c_put_byte */ - 0x47f000f8, -/* 0x0961: i2c_put_byte_next */ - 0x0142b608, - 0xbb3854ff, + 0x64b607ce, + 0x1811f404, + 0x1388e7f1, + 0xf07e21f4, + 0x21f50037, + 0xe7f1075a, + 0x21f41388, +/* 0x08c1: i2c_bitw_out */ +/* 0x08c3: i2c_bitr */ + 0xf000f87e, + 0x21f50137, + 0xe7f1077c, + 0x21f403e8, + 0x0076bb7e, + 0xf90465b6, + 0x04659450, + 0xbd0256bb, + 0x0475fd50, + 0x21f550fc, + 0x64b607ce, + 0x1b11f404, + 0x07b621f5, + 0xf50037f0, + 0xf1075a21, + 0xf41388e7, + 0x3cf07e21, + 0x0131f401, +/* 0x0908: i2c_bitr_done */ +/* 0x090a: i2c_get_byte */ + 0x57f000f8, + 0x0847f000, +/* 0x0910: i2c_get_byte_next */ + 0xbb0154b6, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x088421f5, + 0x08c321f5, 0xf40464b6, - 0x46b03411, - 0xd81bf400, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0xc521f550, - 0x0464b608, - 0xbb0f11f4, - 0x36b00076, - 0x061bf401, -/* 0x09b7: i2c_put_byte_done */ - 0xf80132f4, -/* 0x09b9: i2c_addr */ - 0x0076bb00, + 0x53fd2b11, + 0x0142b605, + 0xf0d81bf4, + 0x76bb0137, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb6088221, +/* 0x095a: i2c_get_byte_done */ + 0x00f80464, +/* 0x095c: i2c_put_byte */ +/* 0x095f: i2c_put_byte_next */ + 0xb60847f0, + 0x54ff0142, + 0x0076bb38, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b607f5, - 0x2911f404, - 0x012ec3e7, - 0xfd0134b6, - 0x76bb0553, + 0x64b60882, + 0x3411f404, + 0xf40046b0, + 0x76bbd81b, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0xf550fc04, - 0xb6095e21, -/* 0x09fe: i2c_addr_done */ - 0x00f80464, -/* 0x0a00: i2c_acquire_addr */ - 0xb6f8cec7, - 0xe0b702e4, - 0xee980d1c, -/* 0x0a0f: i2c_acquire */ - 0xf500f800, - 0xf40a0021, - 0xd9f00421, - 0x4021f403, -/* 0x0a1e: i2c_release */ - 0x21f500f8, - 0x21f40a00, - 0x03daf004, - 0xf84021f4, -/* 0x0a2d: i2c_recv */ - 0x0132f400, - 0xb6f8c1c7, - 0x16b00214, - 0x3a1ff528, - 0xf413a001, - 0x0032980c, - 0x0ccc13a0, - 0xf4003198, - 0xd0f90231, - 0xd0f9e0f9, - 0x000067f1, - 0x100063f1, - 0xbb016792, + 0xb608c321, + 0x11f40464, + 0x0076bb0f, + 0xf40136b0, + 0x32f4061b, +/* 0x09b5: i2c_put_byte_done */ +/* 0x09b7: i2c_addr */ + 0xbb00f801, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0a0f21f5, - 0xfc0464b6, - 0x00d6b0d0, - 0x00b31bf5, - 0xbb0057f0, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x09b921f5, - 0xf50464b6, - 0xc700d011, - 0x76bbe0c5, - 0x0465b600, - 0x659450f9, - 0x0256bb04, - 0x75fd50bd, - 0xf550fc04, - 0xb6095e21, - 0x11f50464, - 0x57f000ad, + 0x07f321f5, + 0xf40464b6, + 0xc3e72911, + 0x34b6012e, + 0x0553fd01, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x5c21f550, + 0x0464b609, +/* 0x09fc: i2c_addr_done */ +/* 0x09fe: i2c_acquire_addr */ + 0xcec700f8, + 0x02e4b6f8, + 0x0d1ce0b7, + 0xf800ee98, +/* 0x0a0d: i2c_acquire */ + 0xfe21f500, + 0x0421f409, + 0xf403d9f0, + 0x00f84021, +/* 0x0a1c: i2c_release */ + 0x09fe21f5, + 0xf00421f4, + 0x21f403da, +/* 0x0a2b: i2c_recv */ + 0xf400f840, + 0xc1c70132, + 0x0214b6f8, + 0xf52816b0, + 0xa0013a1f, + 0x980cf413, + 0x13a00032, + 0x31980ccc, + 0x0231f400, + 0xe0f9d0f9, + 0x67f1d0f9, + 0x63f10000, + 0x67921000, 0x0076bb01, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b609b9, - 0x8a11f504, + 0x64b60a0d, + 0xb0d0fc04, + 0x1bf500d6, + 0x57f000b3, 0x0076bb00, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b6090c, - 0x6a11f404, - 0xbbe05bcb, + 0x64b609b7, + 0xd011f504, + 0xe0c5c700, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x5c21f550, + 0x0464b609, + 0x00ad11f5, + 0xbb0157f0, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x085121f5, - 0xb90464b6, - 0x74bd025b, -/* 0x0b33: i2c_recv_not_rd08 */ - 0xb0430ef4, - 0x1bf401d6, - 0x0057f03d, - 0x09b921f5, - 0xc73311f4, - 0x21f5e0c5, - 0x11f4095e, - 0x0057f029, - 0x09b921f5, - 0xc71f11f4, - 0x21f5e0b5, - 0x11f4095e, - 0x5121f515, - 0xc774bd08, - 0x1bf408c5, - 0x0232f409, -/* 0x0b73: i2c_recv_not_wr08 */ -/* 0x0b73: i2c_recv_done */ - 0xc7030ef4, - 0x21f5f8ce, - 0xe0fc0a1e, - 0x12f4d0fc, - 0x027cb90a, - 0x033621f5, -/* 0x0b88: i2c_recv_exit */ -/* 0x0b8a: i2c_init */ - 0x00f800f8, -/* 0x0b8c: test_recv */ - 0x05d817f1, + 0x09b721f5, + 0xf50464b6, + 0xbb008a11, + 0x65b60076, + 0x9450f904, + 0x56bb0465, + 0xfd50bd02, + 0x50fc0475, + 0x090a21f5, + 0xf40464b6, + 0x5bcb6a11, + 0x0076bbe0, + 0xf90465b6, + 0x04659450, + 0xbd0256bb, + 0x0475fd50, + 0x21f550fc, + 0x64b6084f, + 0x025bb904, + 0x0ef474bd, +/* 0x0b31: i2c_recv_not_rd08 */ + 0x01d6b043, + 0xf03d1bf4, + 0x21f50057, + 0x11f409b7, + 0xe0c5c733, + 0x095c21f5, + 0xf02911f4, + 0x21f50057, + 0x11f409b7, + 0xe0b5c71f, + 0x095c21f5, + 0xf51511f4, + 0xbd084f21, + 0x08c5c774, + 0xf4091bf4, + 0x0ef40232, +/* 0x0b71: i2c_recv_not_wr08 */ +/* 0x0b71: i2c_recv_done */ + 0xf8cec703, + 0x0a1c21f5, + 0xd0fce0fc, + 0xb90a12f4, + 0x21f5027c, +/* 0x0b86: i2c_recv_exit */ + 0x00f80336, +/* 0x0b88: i2c_init */ +/* 0x0b8a: test_recv */ + 0x17f100f8, + 0x14b605d8, + 0x0011cf06, + 0xf10110b6, + 0xb605d807, + 0x01d00604, + 0xf104bd00, + 0xf1d900e7, + 0xf5134fe3, + 0xf8025621, +/* 0x0bb1: test_init */ + 0x00e7f100, + 0x5621f508, +/* 0x0bbb: idle_recv */ + 0xf800f802, +/* 0x0bbd: idle */ + 0x0031f400, + 0x05d417f1, 0xcf0614b6, 0x10b60011, - 0xd807f101, + 0xd407f101, 0x0604b605, 0xbd0001d0, - 0x00e7f104, - 0x4fe3f1d9, - 0x5621f513, -/* 0x0bb3: test_init */ - 0xf100f802, - 0xf50800e7, - 0xf8025621, -/* 0x0bbd: idle_recv */ -/* 0x0bbf: idle */ - 0xf400f800, - 0x17f10031, - 0x14b605d4, - 0x0011cf06, - 0xf10110b6, - 0xb605d407, - 0x01d00604, -/* 0x0bdb: idle_loop */ - 0xf004bd00, - 0x32f45817, -/* 0x0be1: idle_proc */ -/* 0x0be1: idle_proc_exec */ - 0xb910f902, - 0x21f5021e, - 0x10fc033f, - 0xf40911f4, - 0x0ef40231, -/* 0x0bf5: idle_proc_next */ - 0x5810b6ef, - 0xf4061fb8, - 0x02f4e61b, - 0x0028f4dd, - 0x00bb0ef4, +/* 0x0bd9: idle_loop */ + 0x5817f004, +/* 0x0bdf: idle_proc */ +/* 0x0bdf: idle_proc_exec */ + 0xf90232f4, + 0x021eb910, + 0x033f21f5, + 0x11f410fc, + 0x0231f409, +/* 0x0bf3: idle_proc_next */ + 0xb6ef0ef4, + 0x1fb85810, + 0xe61bf406, + 0xf4dd02f4, + 0x0ef40028, + 0x000000bb, 0x00000000, 0x00000000, 0x00000000, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h index c4edbc79e41a..e0222cb832fb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h @@ -47,8 +47,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x584d454d, - 0x000005f3, - 0x000005e5, + 0x000005ee, + 0x000005e0, 0x00000000, 0x00000000, 0x00000000, @@ -69,8 +69,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x46524550, - 0x000005f7, - 0x000005f5, + 0x000005f2, + 0x000005f0, 0x00000000, 0x00000000, 0x00000000, @@ -91,8 +91,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x5f433249, - 0x000009f8, - 0x000008a2, + 0x000009f3, + 0x0000089d, 0x00000000, 0x00000000, 0x00000000, @@ -113,8 +113,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x54534554, - 0x00000a16, - 0x000009fa, + 0x00000a11, + 0x000009f5, 0x00000000, 0x00000000, 0x00000000, @@ -135,8 +135,8 @@ static uint32_t gk208_pmu_data[] = { 0x00000000, 0x00000000, 0x454c4449, - 0x00000a21, - 0x00000a1f, + 0x00000a1c, + 0x00000a1a, 0x00000000, 0x00000000, 0x00000000, @@ -234,22 +234,22 @@ static uint32_t gk208_pmu_data[] = { /* 0x037c: memx_func_next */ 0x00000002, 0x00000000, - 0x000004cf, + 0x000004cc, 0x00000003, 0x00000002, - 0x00000546, + 0x00000541, 0x00040004, 0x00000000, - 0x00000563, + 0x0000055e, 0x00010005, 0x00000000, - 0x0000057d, + 0x00000578, 0x00010006, 0x00000000, - 0x00000541, + 0x0000053c, 0x00000007, 0x00000000, - 0x00000589, + 0x00000584, /* 0x03c4: memx_func_tail */ /* 0x03c4: memx_ts_start */ 0x00000000, @@ -1239,454 +1239,454 @@ static uint32_t gk208_pmu_code[] = { 0x0001f604, 0x00f804bd, /* 0x045c: memx_func_enter */ - 0x162067f1, - 0xf55d77f1, - 0x047e6eb2, - 0xd8b20000, - 0xf90487fd, - 0xfc80f960, - 0x7ee0fcd0, - 0x0700002d, - 0x7e6eb2fe, + 0x47162046, + 0x6eb2f55d, + 0x0000047e, + 0x87fdd8b2, + 0xf960f904, + 0xfcd0fc80, + 0x002d7ee0, + 0xb2fe0700, + 0x00047e6e, + 0xfdd8b200, + 0x60f90487, + 0xd0fc80f9, + 0x2d7ee0fc, + 0xf0460000, + 0x7e6eb226, 0xb2000004, 0x0487fdd8, 0x80f960f9, 0xe0fcd0fc, 0x00002d7e, - 0x26f067f1, - 0x047e6eb2, - 0xd8b20000, - 0xf90487fd, - 0xfc80f960, - 0x7ee0fcd0, - 0x0600002d, - 0x07e04004, - 0xbd0006f6, -/* 0x04b9: memx_func_enter_wait */ - 0x07c04604, - 0xf00066cf, - 0x0bf40464, - 0xcf2c06f7, - 0x06b50066, -/* 0x04cf: memx_func_leave */ - 0x0600f8f1, - 0x0066cf2c, - 0x06f206b5, - 0x07e44004, - 0xbd0006f6, -/* 0x04e1: memx_func_leave_wait */ - 0x07c04604, - 0xf00066cf, - 0x1bf40464, - 0xf067f1f7, + 0xe0400406, + 0x0006f607, +/* 0x04b6: memx_func_enter_wait */ + 0xc04604bd, + 0x0066cf07, + 0xf40464f0, + 0x2c06f70b, + 0xb50066cf, + 0x00f8f106, +/* 0x04cc: memx_func_leave */ + 0x66cf2c06, + 0xf206b500, + 0xe4400406, + 0x0006f607, +/* 0x04de: memx_func_leave_wait */ + 0xc04604bd, + 0x0066cf07, + 0xf40464f0, + 0xf046f71b, 0xb2010726, 0x00047e6e, 0xfdd8b200, 0x60f90587, 0xd0fc80f9, 0x2d7ee0fc, - 0x67f10000, - 0x6eb21620, - 0x0000047e, - 0x87fdd8b2, - 0xf960f905, - 0xfcd0fc80, - 0x002d7ee0, - 0x0aa24700, - 0x047e6eb2, - 0xd8b20000, - 0xf90587fd, - 0xfc80f960, - 0x7ee0fcd0, - 0xf800002d, -/* 0x0541: memx_func_wait_vblank */ + 0x20460000, + 0x7e6eb216, + 0xb2000004, + 0x0587fdd8, + 0x80f960f9, + 0xe0fcd0fc, + 0x00002d7e, + 0xb20aa247, + 0x00047e6e, + 0xfdd8b200, + 0x60f90587, + 0xd0fc80f9, + 0x2d7ee0fc, + 0x00f80000, +/* 0x053c: memx_func_wait_vblank */ + 0xf80410b6, +/* 0x0541: memx_func_wr32 */ + 0x00169800, + 0xb6011598, + 0x60f90810, + 0xd0fc50f9, + 0x2d7ee0fc, + 0x42b60000, + 0xe81bf402, +/* 0x055e: memx_func_wait */ + 0x2c0800f8, + 0x980088cf, + 0x1d98001e, + 0x021c9801, + 0xb6031b98, + 0x747e1010, + 0x00f80000, +/* 0x0578: memx_func_delay */ + 0xb6001e98, + 0x587e0410, + 0x00f80000, +/* 0x0584: memx_func_train */ +/* 0x0586: memx_exec */ + 0xe0f900f8, + 0xc1b2d0f9, +/* 0x058e: memx_exec_next */ + 0x1398b2b2, 0x0410b600, -/* 0x0546: memx_func_wr32 */ - 0x169800f8, - 0x01159800, - 0xf90810b6, - 0xfc50f960, + 0x01f034e7, + 0x01e033e7, + 0xf00132b6, + 0x35980c30, + 0xa655f9de, + 0xe51ef412, + 0x98f10b98, + 0xcbbbf20c, + 0x07c44b02, + 0xfc00bbcf, 0x7ee0fcd0, - 0xb600002d, - 0x1bf40242, -/* 0x0563: memx_func_wait */ - 0x0800f8e8, - 0x0088cf2c, - 0x98001e98, - 0x1c98011d, - 0x031b9802, - 0x7e1010b6, - 0xf8000074, -/* 0x057d: memx_func_delay */ - 0x001e9800, - 0x7e0410b6, - 0xf8000058, -/* 0x0589: memx_func_train */ -/* 0x058b: memx_exec */ - 0xf900f800, - 0xb2d0f9e0, -/* 0x0593: memx_exec_next */ - 0x98b2b2c1, - 0x10b60013, - 0xf034e704, - 0xe033e701, - 0x0132b601, - 0x980c30f0, - 0x55f9de35, - 0x1ef412a6, - 0xf10b98e5, - 0xbbf20c98, - 0xc44b02cb, - 0x00bbcf07, - 0xe0fcd0fc, - 0x00029f7e, -/* 0x05ca: memx_info */ - 0xc67000f8, - 0x0c0bf401, -/* 0x05d0: memx_info_data */ - 0x4b03cc4c, - 0x0ef40800, -/* 0x05d9: memx_info_train */ - 0x0bcc4c09, -/* 0x05df: memx_info_send */ - 0x7e01004b, 0xf800029f, -/* 0x05e5: memx_recv */ - 0x01d6b000, - 0xb0a30bf4, - 0x0bf400d6, -/* 0x05f3: memx_init */ - 0xf800f8dc, -/* 0x05f5: perf_recv */ -/* 0x05f7: perf_init */ - 0xf800f800, -/* 0x05f9: i2c_drive_scl */ - 0x0036b000, - 0x400d0bf4, - 0x01f607e0, - 0xf804bd00, -/* 0x0609: i2c_drive_scl_lo */ - 0x07e44000, - 0xbd0001f6, -/* 0x0613: i2c_drive_sda */ - 0xb000f804, - 0x0bf40036, - 0x07e0400d, - 0xbd0002f6, -/* 0x0623: i2c_drive_sda_lo */ - 0x4000f804, - 0x02f607e4, - 0xf804bd00, -/* 0x062d: i2c_sense_scl */ - 0x0132f400, - 0xcf07c443, - 0x31fd0033, - 0x060bf404, -/* 0x063f: i2c_sense_scl_done */ - 0xf80131f4, -/* 0x0641: i2c_sense_sda */ - 0x0132f400, - 0xcf07c443, - 0x32fd0033, - 0x060bf404, -/* 0x0653: i2c_sense_sda_done */ - 0xf80131f4, -/* 0x0655: i2c_raise_scl */ - 0x4440f900, - 0x01030898, - 0x0005f97e, -/* 0x0660: i2c_raise_scl_wait */ - 0x7e03e84e, - 0x7e000058, - 0xf400062d, - 0x42b60901, - 0xef1bf401, -/* 0x0674: i2c_raise_scl_done */ - 0x00f840fc, -/* 0x0678: i2c_start */ - 0x00062d7e, - 0x7e0d11f4, - 0xf4000641, - 0x0ef40611, -/* 0x0689: i2c_start_rep */ - 0x7e00032e, - 0x030005f9, - 0x06137e01, +/* 0x05c5: memx_info */ + 0x01c67000, +/* 0x05cb: memx_info_data */ + 0x4c0c0bf4, + 0x004b03cc, + 0x090ef408, +/* 0x05d4: memx_info_train */ + 0x4b0bcc4c, +/* 0x05da: memx_info_send */ + 0x9f7e0100, + 0x00f80002, +/* 0x05e0: memx_recv */ + 0xf401d6b0, + 0xd6b0a30b, + 0xdc0bf400, +/* 0x05ee: memx_init */ + 0x00f800f8, +/* 0x05f0: perf_recv */ +/* 0x05f2: perf_init */ + 0x00f800f8, +/* 0x05f4: i2c_drive_scl */ + 0xf40036b0, + 0xe0400d0b, + 0x0001f607, + 0x00f804bd, +/* 0x0604: i2c_drive_scl_lo */ + 0xf607e440, + 0x04bd0001, +/* 0x060e: i2c_drive_sda */ + 0x36b000f8, + 0x0d0bf400, + 0xf607e040, + 0x04bd0002, +/* 0x061e: i2c_drive_sda_lo */ + 0xe44000f8, + 0x0002f607, + 0x00f804bd, +/* 0x0628: i2c_sense_scl */ + 0x430132f4, + 0x33cf07c4, + 0x0431fd00, + 0xf4060bf4, +/* 0x063a: i2c_sense_scl_done */ + 0x00f80131, +/* 0x063c: i2c_sense_sda */ + 0x430132f4, + 0x33cf07c4, + 0x0432fd00, + 0xf4060bf4, +/* 0x064e: i2c_sense_sda_done */ + 0x00f80131, +/* 0x0650: i2c_raise_scl */ + 0x984440f9, + 0x7e010308, +/* 0x065b: i2c_raise_scl_wait */ + 0x4e0005f4, + 0x587e03e8, + 0x287e0000, + 0x01f40006, + 0x0142b609, +/* 0x066f: i2c_raise_scl_done */ + 0xfcef1bf4, +/* 0x0673: i2c_start */ + 0x7e00f840, + 0xf4000628, + 0x3c7e0d11, + 0x11f40006, + 0x2e0ef406, +/* 0x0684: i2c_start_rep */ + 0xf47e0003, + 0x01030005, + 0x00060e7e, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x06507e50, + 0x0464b600, +/* 0x06af: i2c_start_send */ + 0x031d11f4, + 0x060e7e00, + 0x13884e00, + 0x0000587e, + 0xf47e0003, + 0x884e0005, + 0x00587e13, +/* 0x06c9: i2c_start_out */ +/* 0x06cb: i2c_stop */ + 0x0300f800, + 0x05f47e00, + 0x7e000300, + 0x4e00060e, + 0x587e03e8, + 0x01030000, + 0x0005f47e, + 0x7e13884e, + 0x03000058, + 0x060e7e01, + 0x13884e00, + 0x0000587e, +/* 0x06fa: i2c_bitw */ + 0x0e7e00f8, + 0xe84e0006, + 0x00587e03, 0x0076bb00, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, - 0x557e50fc, + 0x507e50fc, 0x64b60006, - 0x1d11f404, -/* 0x06b4: i2c_start_send */ - 0x137e0003, - 0x884e0006, - 0x00587e13, - 0x7e000300, - 0x4e0005f9, - 0x587e1388, -/* 0x06ce: i2c_start_out */ - 0x00f80000, -/* 0x06d0: i2c_stop */ - 0xf97e0003, - 0x00030005, - 0x0006137e, - 0x7e03e84e, + 0x1711f404, + 0x7e13884e, 0x03000058, - 0x05f97e01, + 0x05f47e00, 0x13884e00, 0x0000587e, - 0x137e0103, - 0x884e0006, - 0x00587e13, -/* 0x06ff: i2c_bitw */ - 0x7e00f800, - 0x4e000613, - 0x587e03e8, - 0x76bb0000, +/* 0x0738: i2c_bitw_out */ +/* 0x073a: i2c_bitr */ + 0x010300f8, + 0x00060e7e, + 0x7e03e84e, + 0xbb000058, + 0x65b60076, + 0x9450f904, + 0x56bb0465, + 0xfd50bd02, + 0x50fc0475, + 0x0006507e, + 0xf40464b6, + 0x3c7e1a11, + 0x00030006, + 0x0005f47e, + 0x7e13884e, + 0xf0000058, + 0x31f4013c, +/* 0x077d: i2c_bitr_done */ +/* 0x077f: i2c_get_byte */ + 0x0500f801, +/* 0x0783: i2c_get_byte_next */ + 0xb6080400, + 0x76bb0154, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0x7e50fc04, - 0xb6000655, + 0xb600073a, 0x11f40464, - 0x13884e17, - 0x0000587e, - 0xf97e0003, - 0x884e0005, - 0x00587e13, -/* 0x073d: i2c_bitw_out */ -/* 0x073f: i2c_bitr */ - 0x0300f800, - 0x06137e01, - 0x03e84e00, - 0x0000587e, + 0x0553fd2a, + 0xf40142b6, + 0x0103d81b, 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0x06557e50, + 0x06fa7e50, 0x0464b600, - 0x7e1a11f4, - 0x03000641, - 0x05f97e00, - 0x13884e00, - 0x0000587e, - 0xf4013cf0, -/* 0x0782: i2c_bitr_done */ - 0x00f80131, -/* 0x0784: i2c_get_byte */ - 0x08040005, -/* 0x0788: i2c_get_byte_next */ - 0xbb0154b6, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x00073f7e, - 0xf40464b6, - 0x53fd2a11, - 0x0142b605, - 0x03d81bf4, - 0x0076bb01, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0xff7e50fc, - 0x64b60006, -/* 0x07d1: i2c_get_byte_done */ -/* 0x07d3: i2c_put_byte */ - 0x0400f804, -/* 0x07d5: i2c_put_byte_next */ - 0x0142b608, - 0xbb3854ff, +/* 0x07cc: i2c_get_byte_done */ +/* 0x07ce: i2c_put_byte */ + 0x080400f8, +/* 0x07d0: i2c_put_byte_next */ + 0xff0142b6, + 0x76bb3854, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0x7e50fc04, + 0xb60006fa, + 0x11f40464, + 0x0046b034, + 0xbbd81bf4, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0006ff7e, + 0x00073a7e, 0xf40464b6, - 0x46b03411, - 0xd81bf400, + 0x76bb0f11, + 0x0136b000, + 0xf4061bf4, +/* 0x0826: i2c_put_byte_done */ + 0x00f80132, +/* 0x0828: i2c_addr */ 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0x073f7e50, + 0x06737e50, 0x0464b600, - 0xbb0f11f4, - 0x36b00076, - 0x061bf401, -/* 0x082b: i2c_put_byte_done */ - 0xf80132f4, -/* 0x082d: i2c_addr */ - 0x0076bb00, + 0xe72911f4, + 0xb6012ec3, + 0x53fd0134, + 0x0076bb05, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, - 0x787e50fc, - 0x64b60006, - 0x2911f404, - 0x012ec3e7, - 0xfd0134b6, - 0x76bb0553, - 0x0465b600, - 0x659450f9, - 0x0256bb04, - 0x75fd50bd, - 0x7e50fc04, - 0xb60007d3, -/* 0x0872: i2c_addr_done */ - 0x00f80464, -/* 0x0874: i2c_acquire_addr */ - 0xb6f8cec7, - 0xe0b705e4, - 0x00f8d014, -/* 0x0880: i2c_acquire */ - 0x0008747e, + 0xce7e50fc, + 0x64b60007, +/* 0x086d: i2c_addr_done */ +/* 0x086f: i2c_acquire_addr */ + 0xc700f804, + 0xe4b6f8ce, + 0x14e0b705, +/* 0x087b: i2c_acquire */ + 0x7e00f8d0, + 0x7e00086f, + 0xf0000004, + 0x2d7e03d9, + 0x00f80000, +/* 0x088c: i2c_release */ + 0x00086f7e, 0x0000047e, - 0x7e03d9f0, + 0x7e03daf0, 0xf800002d, -/* 0x0891: i2c_release */ - 0x08747e00, - 0x00047e00, - 0x03daf000, - 0x00002d7e, -/* 0x08a2: i2c_recv */ - 0x32f400f8, - 0xf8c1c701, - 0xb00214b6, - 0x1ff52816, - 0x13b80134, - 0x98000cf4, - 0x13b80032, - 0x98000ccc, - 0x31f40031, - 0xf9d0f902, - 0xd6d0f9e0, - 0x10000000, - 0xbb016792, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x0008807e, - 0xfc0464b6, - 0x00d6b0d0, - 0x00b01bf5, - 0x76bb0005, +/* 0x089d: i2c_recv */ + 0x0132f400, + 0xb6f8c1c7, + 0x16b00214, + 0x341ff528, + 0xf413b801, + 0x3298000c, + 0xcc13b800, + 0x3198000c, + 0x0231f400, + 0xe0f9d0f9, + 0x00d6d0f9, + 0x92100000, + 0x76bb0167, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0x7e50fc04, - 0xb600082d, - 0x11f50464, - 0xc5c700cc, - 0x0076bbe0, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0xd37e50fc, - 0x64b60007, - 0xa911f504, - 0xbb010500, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x00082d7e, - 0xf50464b6, - 0xbb008711, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x0007847e, - 0xf40464b6, - 0x5bcb6711, - 0x0076bbe0, + 0xb600087b, + 0xd0fc0464, + 0xf500d6b0, + 0x0500b01b, + 0x0076bb00, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, - 0xd07e50fc, - 0x64b60006, - 0xbd5bb204, - 0x410ef474, -/* 0x09a4: i2c_recv_not_rd08 */ - 0xf401d6b0, - 0x00053b1b, - 0x00082d7e, - 0xc73211f4, - 0xd37ee0c5, - 0x11f40007, - 0x7e000528, - 0xf400082d, - 0xb5c71f11, - 0x07d37ee0, - 0x1511f400, - 0x0006d07e, - 0xc5c774bd, - 0x091bf408, - 0xf40232f4, -/* 0x09e2: i2c_recv_not_wr08 */ -/* 0x09e2: i2c_recv_done */ - 0xcec7030e, - 0x08917ef8, - 0xfce0fc00, - 0x0912f4d0, - 0x9f7e7cb2, -/* 0x09f6: i2c_recv_exit */ - 0x00f80002, -/* 0x09f8: i2c_init */ -/* 0x09fa: test_recv */ - 0x584100f8, - 0x0011cf04, - 0x400110b6, - 0x01f60458, - 0xde04bd00, - 0x134fd900, - 0x0001de7e, -/* 0x0a16: test_init */ - 0x004e00f8, - 0x01de7e08, -/* 0x0a1f: idle_recv */ + 0x287e50fc, + 0x64b60008, + 0xcc11f504, + 0xe0c5c700, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x07ce7e50, + 0x0464b600, + 0x00a911f5, + 0x76bb0105, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0x7e50fc04, + 0xb6000828, + 0x11f50464, + 0x76bb0087, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0x7e50fc04, + 0xb600077f, + 0x11f40464, + 0xe05bcb67, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x06cb7e50, + 0x0464b600, + 0x74bd5bb2, +/* 0x099f: i2c_recv_not_rd08 */ + 0xb0410ef4, + 0x1bf401d6, + 0x7e00053b, + 0xf4000828, + 0xc5c73211, + 0x07ce7ee0, + 0x2811f400, + 0x287e0005, + 0x11f40008, + 0xe0b5c71f, + 0x0007ce7e, + 0x7e1511f4, + 0xbd0006cb, + 0x08c5c774, + 0xf4091bf4, + 0x0ef40232, +/* 0x09dd: i2c_recv_not_wr08 */ +/* 0x09dd: i2c_recv_done */ + 0xf8cec703, + 0x00088c7e, + 0xd0fce0fc, + 0xb20912f4, + 0x029f7e7c, +/* 0x09f1: i2c_recv_exit */ +/* 0x09f3: i2c_init */ 0xf800f800, -/* 0x0a21: idle */ - 0x0031f400, - 0xcf045441, - 0x10b60011, - 0x04544001, - 0xbd0001f6, -/* 0x0a35: idle_loop */ - 0xf4580104, -/* 0x0a3a: idle_proc */ -/* 0x0a3a: idle_proc_exec */ - 0x10f90232, - 0xa87e1eb2, - 0x10fc0002, - 0xf40911f4, - 0x0ef40231, -/* 0x0a4d: idle_proc_next */ - 0x5810b6f0, - 0x1bf41fa6, - 0xe002f4e8, - 0xf40028f4, - 0x0000c60e, +/* 0x09f5: test_recv */ + 0x04584100, + 0xb60011cf, + 0x58400110, + 0x0001f604, + 0x00de04bd, + 0x7e134fd9, + 0xf80001de, +/* 0x0a11: test_init */ + 0x08004e00, + 0x0001de7e, +/* 0x0a1a: idle_recv */ + 0x00f800f8, +/* 0x0a1c: idle */ + 0x410031f4, + 0x11cf0454, + 0x0110b600, + 0xf6045440, + 0x04bd0001, +/* 0x0a30: idle_loop */ + 0x32f45801, +/* 0x0a35: idle_proc */ +/* 0x0a35: idle_proc_exec */ + 0xb210f902, + 0x02a87e1e, + 0xf410fc00, + 0x31f40911, + 0xf00ef402, +/* 0x0a48: idle_proc_next */ + 0xa65810b6, + 0xe81bf41f, + 0xf4e002f4, + 0x0ef40028, + 0x000000c6, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h index 6a2572e8945a..defddf5957ee 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h @@ -47,8 +47,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x584d454d, - 0x0000083a, - 0x0000082c, + 0x00000833, + 0x00000825, 0x00000000, 0x00000000, 0x00000000, @@ -69,8 +69,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x46524550, - 0x0000083e, - 0x0000083c, + 0x00000837, + 0x00000835, 0x00000000, 0x00000000, 0x00000000, @@ -91,8 +91,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x5f433249, - 0x00000c6e, - 0x00000b11, + 0x00000c67, + 0x00000b0a, 0x00000000, 0x00000000, 0x00000000, @@ -113,8 +113,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x54534554, - 0x00000c97, - 0x00000c70, + 0x00000c90, + 0x00000c69, 0x00000000, 0x00000000, 0x00000000, @@ -135,8 +135,8 @@ static uint32_t gt215_pmu_data[] = { 0x00000000, 0x00000000, 0x454c4449, - 0x00000ca3, - 0x00000ca1, + 0x00000c9c, + 0x00000c9a, 0x00000000, 0x00000000, 0x00000000, @@ -234,22 +234,22 @@ static uint32_t gt215_pmu_data[] = { /* 0x037c: memx_func_next */ 0x00000002, 0x00000000, - 0x000005a0, + 0x0000059f, 0x00000003, 0x00000002, - 0x00000632, + 0x0000062f, 0x00040004, 0x00000000, - 0x0000064e, + 0x0000064b, 0x00010005, 0x00000000, - 0x0000066b, + 0x00000668, 0x00010006, 0x00000000, - 0x000005f0, + 0x000005ef, 0x00000007, 0x00000000, - 0x00000676, + 0x00000673, /* 0x03c4: memx_func_tail */ /* 0x03c4: memx_ts_start */ 0x00000000, @@ -1305,560 +1305,560 @@ static uint32_t gt215_pmu_code[] = { 0x67f102d7, 0x63f1fffc, 0x76fdffff, - 0x0267f104, - 0x0576fd00, - 0x70f980f9, - 0xe0fcd0fc, - 0xf04021f4, + 0x0267f004, + 0xf90576fd, + 0xfc70f980, + 0xf4e0fcd0, + 0x67f04021, + 0xe007f104, + 0x0604b607, + 0xbd0006d0, +/* 0x0581: memx_func_enter_wait */ + 0xc067f104, + 0x0664b607, + 0xf00066cf, + 0x0bf40464, + 0x2c67f0f3, + 0xcf0664b6, + 0x06800066, +/* 0x059f: memx_func_leave */ + 0xf000f8f1, + 0x64b62c67, + 0x0066cf06, + 0xf0f20680, 0x07f10467, - 0x04b607e0, + 0x04b607e4, 0x0006d006, -/* 0x0582: memx_func_enter_wait */ +/* 0x05ba: memx_func_leave_wait */ 0x67f104bd, 0x64b607c0, 0x0066cf06, 0xf40464f0, - 0x67f0f30b, - 0x0664b62c, - 0x800066cf, - 0x00f8f106, -/* 0x05a0: memx_func_leave */ - 0xb62c67f0, - 0x66cf0664, - 0xf2068000, - 0xf10467f0, - 0xb607e407, - 0x06d00604, -/* 0x05bb: memx_func_leave_wait */ - 0xf104bd00, - 0xb607c067, - 0x66cf0664, - 0x0464f000, - 0xf1f31bf4, - 0xb9161087, - 0x21f4028e, - 0x02d7b904, - 0xffcc67f1, - 0xffff63f1, - 0xf90476fd, - 0xfc70f980, - 0xf4e0fcd0, - 0x00f84021, -/* 0x05f0: memx_func_wait_vblank */ - 0xb0001698, - 0x0bf40066, - 0x0166b013, - 0xf4060bf4, -/* 0x0602: memx_func_wait_vblank_head1 */ - 0x77f12e0e, - 0x0ef40020, -/* 0x0609: memx_func_wait_vblank_head0 */ - 0x0877f107, -/* 0x060d: memx_func_wait_vblank_0 */ - 0xc467f100, - 0x0664b607, - 0xfd0066cf, - 0x1bf40467, -/* 0x061d: memx_func_wait_vblank_1 */ - 0xc467f1f3, - 0x0664b607, - 0xfd0066cf, - 0x0bf40467, -/* 0x062d: memx_func_wait_vblank_fini */ - 0x0410b6f3, -/* 0x0632: memx_func_wr32 */ - 0x169800f8, - 0x01159800, - 0xf90810b6, - 0xfc50f960, - 0xf4e0fcd0, - 0x42b64021, - 0xe91bf402, -/* 0x064e: memx_func_wait */ - 0x87f000f8, - 0x0684b62c, - 0x980088cf, - 0x1d98001e, - 0x021c9801, - 0xb6031b98, - 0x21f41010, -/* 0x066b: memx_func_delay */ - 0x9800f8a3, - 0x10b6001e, - 0x7e21f404, -/* 0x0676: memx_func_train */ - 0x57f100f8, - 0x77f10003, - 0x97f10000, - 0x93f00000, - 0x029eb970, - 0xb90421f4, - 0xe7f102d8, - 0x21f42710, -/* 0x0695: memx_func_train_loop_outer */ - 0x0158e07e, - 0x0083f101, - 0xe097f102, - 0x1193f011, - 0x80f990f9, + 0x87f1f31b, + 0x8eb91610, + 0x0421f402, + 0xf102d7b9, + 0xf1ffcc67, + 0xfdffff63, + 0x80f90476, + 0xd0fc70f9, + 0x21f4e0fc, +/* 0x05ef: memx_func_wait_vblank */ + 0x9800f840, + 0x66b00016, + 0x120bf400, + 0xf40166b0, + 0x0ef4060b, +/* 0x0601: memx_func_wait_vblank_head1 */ + 0x2077f02c, +/* 0x0607: memx_func_wait_vblank_head0 */ + 0xf0060ef4, +/* 0x060a: memx_func_wait_vblank_0 */ + 0x67f10877, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x061a: memx_func_wait_vblank_1 */ + 0x67f1f31b, + 0x64b607c4, + 0x0066cf06, + 0xf40467fd, +/* 0x062a: memx_func_wait_vblank_fini */ + 0x10b6f30b, +/* 0x062f: memx_func_wr32 */ + 0x9800f804, + 0x15980016, + 0x0810b601, + 0x50f960f9, 0xe0fcd0fc, - 0xf94021f4, - 0x0067f150, -/* 0x06b5: memx_func_train_loop_inner */ - 0x1187f100, - 0x9068ff11, - 0xfd109894, - 0x97f10589, - 0x93f00720, - 0xf990f910, - 0xfcd0fc80, - 0x4021f4e0, - 0x008097f1, - 0xb91093f0, - 0x21f4029e, - 0x02d8b904, - 0xf92088c5, + 0xb64021f4, + 0x1bf40242, +/* 0x064b: memx_func_wait */ + 0xf000f8e9, + 0x84b62c87, + 0x0088cf06, + 0x98001e98, + 0x1c98011d, + 0x031b9802, + 0xf41010b6, + 0x00f8a321, +/* 0x0668: memx_func_delay */ + 0xb6001e98, + 0x21f40410, +/* 0x0673: memx_func_train */ + 0xf000f87e, + 0x77f00357, + 0x0097f100, + 0x7093f000, + 0xf4029eb9, + 0xd8b90421, + 0x10e7f102, + 0x7e21f427, +/* 0x0690: memx_func_train_loop_outer */ + 0x010158e0, + 0x020083f1, + 0x11e097f1, + 0xf91193f0, + 0xfc80f990, + 0xf4e0fcd0, + 0x50f94021, +/* 0x06af: memx_func_train_loop_inner */ + 0xf10067f0, + 0xff111187, + 0x98949068, + 0x0589fd10, + 0x072097f1, + 0xf91093f0, 0xfc80f990, 0xf4e0fcd0, 0x97f14021, - 0x93f0053c, - 0x0287f110, - 0x0083f130, - 0xf990f980, + 0x93f00080, + 0x029eb910, + 0xb90421f4, + 0x88c502d8, + 0xf990f920, 0xfcd0fc80, 0x4021f4e0, - 0x0560e7f1, - 0xf110e3f0, - 0xf10000d7, - 0x908000d3, - 0xb7f100dc, - 0xb3f08480, - 0xa321f41e, - 0x000057f1, - 0xffff97f1, - 0x830093f1, -/* 0x0734: memx_func_train_loop_4x */ - 0x0080a7f1, - 0xb910a3f0, - 0x21f402ae, - 0x02d8b904, - 0xffdfb7f1, - 0xffffb3f1, - 0xf9048bfd, - 0xfc80f9a0, + 0x053c97f1, + 0xf11093f0, + 0xf1300287, + 0xf9800083, + 0xfc80f990, 0xf4e0fcd0, - 0xa7f14021, - 0xa3f0053c, - 0x0287f110, - 0x0083f130, - 0xf9a0f980, - 0xfcd0fc80, - 0x4021f4e0, - 0x0560e7f1, - 0xf110e3f0, - 0xf10000d7, - 0xb98000d3, - 0xb7f102dc, - 0xb3f02710, - 0xa321f400, - 0xf402eeb9, - 0xddb90421, - 0x949dff02, + 0xe7f14021, + 0xe3f00560, + 0x00d7f110, + 0x00d3f100, + 0x00dc9080, + 0x8480b7f1, + 0xf41eb3f0, + 0x57f0a321, + 0xff97f100, + 0x0093f1ff, +/* 0x072d: memx_func_train_loop_4x */ + 0x80a7f183, + 0x10a3f000, + 0xf402aeb9, + 0xd8b90421, + 0xdfb7f102, + 0xffb3f1ff, + 0x048bfdff, + 0x80f9a0f9, + 0xe0fcd0fc, + 0xf14021f4, + 0xf0053ca7, + 0x87f110a3, + 0x83f13002, + 0xa0f98000, + 0xd0fc80f9, + 0x21f4e0fc, + 0x60e7f140, + 0x10e3f005, + 0x0000d7f1, + 0x8000d3f1, + 0xf102dcb9, + 0xf02710b7, + 0x21f400b3, + 0x02eeb9a3, + 0xb90421f4, + 0x9dff02dd, + 0x0150b694, + 0xf4045670, + 0x7aa0921e, + 0xa9800bcc, + 0x0160b600, + 0x700470b6, + 0x1ef51066, + 0x50fcff01, 0x700150b6, - 0x1ef40456, - 0xcc7aa092, - 0x00a9800b, - 0xb60160b6, - 0x66700470, - 0x001ef510, - 0xb650fcff, - 0x56700150, - 0xd41ef507, -/* 0x07c7: memx_exec */ - 0xf900f8fe, - 0xb9d0f9e0, - 0xb2b902c1, -/* 0x07d1: memx_exec_next */ - 0x00139802, - 0xe70410b6, - 0xe701f034, - 0xb601e033, - 0x30f00132, - 0xde35980c, - 0x12b855f9, - 0xe41ef406, - 0x98f10b98, - 0xcbbbf20c, - 0xc4b7f102, - 0x06b4b607, - 0xfc00bbcf, - 0xf5e0fcd0, + 0x1ef50756, + 0x00f8fed6, +/* 0x07c0: memx_exec */ + 0xd0f9e0f9, + 0xb902c1b9, +/* 0x07ca: memx_exec_next */ + 0x139802b2, + 0x0410b600, + 0x01f034e7, + 0x01e033e7, + 0xf00132b6, + 0x35980c30, + 0xb855f9de, + 0x1ef40612, + 0xf10b98e4, + 0xbbf20c98, + 0xb7f102cb, + 0xb4b607c4, + 0x00bbcf06, + 0xe0fcd0fc, + 0x033621f5, +/* 0x0806: memx_info */ + 0xc67000f8, + 0x0e0bf401, +/* 0x080c: memx_info_data */ + 0x03ccc7f1, + 0x0800b7f1, +/* 0x0817: memx_info_train */ + 0xf10b0ef4, + 0xf10bccc7, +/* 0x081f: memx_info_send */ + 0xf50100b7, 0xf8033621, -/* 0x080d: memx_info */ - 0x01c67000, -/* 0x0813: memx_info_data */ - 0xf10e0bf4, - 0xf103ccc7, - 0xf40800b7, -/* 0x081e: memx_info_train */ - 0xc7f10b0e, - 0xb7f10bcc, -/* 0x0826: memx_info_send */ - 0x21f50100, - 0x00f80336, -/* 0x082c: memx_recv */ - 0xf401d6b0, - 0xd6b0980b, - 0xd80bf400, -/* 0x083a: memx_init */ - 0x00f800f8, -/* 0x083c: perf_recv */ -/* 0x083e: perf_init */ - 0x00f800f8, -/* 0x0840: i2c_drive_scl */ - 0xf40036b0, - 0x07f1110b, - 0x04b607e0, - 0x0001d006, - 0x00f804bd, -/* 0x0854: i2c_drive_scl_lo */ - 0x07e407f1, - 0xd00604b6, - 0x04bd0001, -/* 0x0862: i2c_drive_sda */ - 0x36b000f8, - 0x110bf400, - 0x07e007f1, - 0xd00604b6, - 0x04bd0002, -/* 0x0876: i2c_drive_sda_lo */ - 0x07f100f8, - 0x04b607e4, - 0x0002d006, - 0x00f804bd, -/* 0x0884: i2c_sense_scl */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0431fd00, - 0xf4060bf4, -/* 0x089a: i2c_sense_scl_done */ - 0x00f80131, -/* 0x089c: i2c_sense_sda */ - 0xf10132f4, - 0xb607c437, - 0x33cf0634, - 0x0432fd00, - 0xf4060bf4, -/* 0x08b2: i2c_sense_sda_done */ - 0x00f80131, -/* 0x08b4: i2c_raise_scl */ - 0x47f140f9, - 0x37f00898, - 0x4021f501, -/* 0x08c1: i2c_raise_scl_wait */ +/* 0x0825: memx_recv */ + 0x01d6b000, + 0xb0980bf4, + 0x0bf400d6, +/* 0x0833: memx_init */ + 0xf800f8d8, +/* 0x0835: perf_recv */ +/* 0x0837: perf_init */ + 0xf800f800, +/* 0x0839: i2c_drive_scl */ + 0x0036b000, + 0xf1110bf4, + 0xb607e007, + 0x01d00604, + 0xf804bd00, +/* 0x084d: i2c_drive_scl_lo */ + 0xe407f100, + 0x0604b607, + 0xbd0001d0, +/* 0x085b: i2c_drive_sda */ + 0xb000f804, + 0x0bf40036, + 0xe007f111, + 0x0604b607, + 0xbd0002d0, +/* 0x086f: i2c_drive_sda_lo */ + 0xf100f804, + 0xb607e407, + 0x02d00604, + 0xf804bd00, +/* 0x087d: i2c_sense_scl */ + 0x0132f400, + 0x07c437f1, + 0xcf0634b6, + 0x31fd0033, + 0x060bf404, +/* 0x0893: i2c_sense_scl_done */ + 0xf80131f4, +/* 0x0895: i2c_sense_sda */ + 0x0132f400, + 0x07c437f1, + 0xcf0634b6, + 0x32fd0033, + 0x060bf404, +/* 0x08ab: i2c_sense_sda_done */ + 0xf80131f4, +/* 0x08ad: i2c_raise_scl */ + 0xf140f900, + 0xf0089847, + 0x21f50137, +/* 0x08ba: i2c_raise_scl_wait */ + 0xe7f10839, + 0x21f403e8, + 0x7d21f57e, + 0x0901f408, + 0xf40142b6, +/* 0x08ce: i2c_raise_scl_done */ + 0x40fcef1b, +/* 0x08d2: i2c_start */ + 0x21f500f8, + 0x11f4087d, + 0x9521f50d, + 0x0611f408, +/* 0x08e3: i2c_start_rep */ + 0xf0300ef4, + 0x21f50037, + 0x37f00839, + 0x5b21f501, + 0x0076bb08, + 0xf90465b6, + 0x04659450, + 0xbd0256bb, + 0x0475fd50, + 0x21f550fc, + 0x64b608ad, + 0x1f11f404, +/* 0x0910: i2c_start_send */ + 0xf50037f0, + 0xf1085b21, + 0xf41388e7, + 0x37f07e21, + 0x3921f500, + 0x88e7f108, + 0x7e21f413, +/* 0x092c: i2c_start_out */ +/* 0x092e: i2c_stop */ + 0x37f000f8, + 0x3921f500, + 0x0037f008, + 0x085b21f5, + 0x03e8e7f1, + 0xf07e21f4, + 0x21f50137, + 0xe7f10839, + 0x21f41388, + 0x0137f07e, + 0x085b21f5, + 0x1388e7f1, + 0xf87e21f4, +/* 0x0961: i2c_bitw */ + 0x5b21f500, 0xe8e7f108, 0x7e21f403, - 0x088421f5, - 0xb60901f4, - 0x1bf40142, -/* 0x08d5: i2c_raise_scl_done */ - 0xf840fcef, -/* 0x08d9: i2c_start */ - 0x8421f500, - 0x0d11f408, - 0x089c21f5, - 0xf40611f4, -/* 0x08ea: i2c_start_rep */ - 0x37f0300e, - 0x4021f500, - 0x0137f008, - 0x086221f5, 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0xb421f550, + 0xad21f550, 0x0464b608, -/* 0x0917: i2c_start_send */ - 0xf01f11f4, - 0x21f50037, - 0xe7f10862, - 0x21f41388, - 0x0037f07e, - 0x084021f5, - 0x1388e7f1, -/* 0x0933: i2c_start_out */ - 0xf87e21f4, -/* 0x0935: i2c_stop */ - 0x0037f000, - 0x084021f5, - 0xf50037f0, - 0xf1086221, - 0xf403e8e7, + 0xf11811f4, + 0xf41388e7, 0x37f07e21, - 0x4021f501, + 0x3921f500, 0x88e7f108, 0x7e21f413, - 0xf50137f0, - 0xf1086221, - 0xf41388e7, - 0x00f87e21, -/* 0x0968: i2c_bitw */ - 0x086221f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x08b421f5, - 0xf40464b6, - 0xe7f11811, +/* 0x09a0: i2c_bitw_out */ +/* 0x09a2: i2c_bitr */ + 0x37f000f8, + 0x5b21f501, + 0xe8e7f108, + 0x7e21f403, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0xad21f550, + 0x0464b608, + 0xf51b11f4, + 0xf0089521, + 0x21f50037, + 0xe7f10839, 0x21f41388, - 0x0037f07e, - 0x084021f5, - 0x1388e7f1, -/* 0x09a7: i2c_bitw_out */ - 0xf87e21f4, -/* 0x09a9: i2c_bitr */ - 0x0137f000, - 0x086221f5, - 0x03e8e7f1, - 0xbb7e21f4, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x08b421f5, - 0xf40464b6, - 0x21f51b11, - 0x37f0089c, - 0x4021f500, - 0x88e7f108, - 0x7e21f413, - 0xf4013cf0, -/* 0x09ee: i2c_bitr_done */ - 0x00f80131, -/* 0x09f0: i2c_get_byte */ - 0xf00057f0, -/* 0x09f6: i2c_get_byte_next */ - 0x54b60847, + 0x013cf07e, +/* 0x09e7: i2c_bitr_done */ + 0xf80131f4, +/* 0x09e9: i2c_get_byte */ + 0x0057f000, +/* 0x09ef: i2c_get_byte_next */ + 0xb60847f0, + 0x76bb0154, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb609a221, + 0x11f40464, + 0x0553fd2b, + 0xf40142b6, + 0x37f0d81b, 0x0076bb01, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b609a9, - 0x2b11f404, - 0xb60553fd, - 0x1bf40142, - 0x0137f0d8, - 0xb60076bb, - 0x50f90465, - 0xbb046594, - 0x50bd0256, - 0xfc0475fd, - 0x6821f550, - 0x0464b609, -/* 0x0a40: i2c_get_byte_done */ -/* 0x0a42: i2c_put_byte */ - 0x47f000f8, -/* 0x0a45: i2c_put_byte_next */ - 0x0142b608, - 0xbb3854ff, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x096821f5, - 0xf40464b6, - 0x46b03411, - 0xd81bf400, + 0x64b60961, +/* 0x0a39: i2c_get_byte_done */ +/* 0x0a3b: i2c_put_byte */ + 0xf000f804, +/* 0x0a3e: i2c_put_byte_next */ + 0x42b60847, + 0x3854ff01, 0xb60076bb, 0x50f90465, 0xbb046594, 0x50bd0256, 0xfc0475fd, - 0xa921f550, + 0x6121f550, 0x0464b609, - 0xbb0f11f4, - 0x36b00076, - 0x061bf401, -/* 0x0a9b: i2c_put_byte_done */ - 0xf80132f4, -/* 0x0a9d: i2c_addr */ - 0x0076bb00, + 0xb03411f4, + 0x1bf40046, + 0x0076bbd8, 0xf90465b6, 0x04659450, 0xbd0256bb, 0x0475fd50, 0x21f550fc, - 0x64b608d9, - 0x2911f404, - 0x012ec3e7, - 0xfd0134b6, - 0x76bb0553, + 0x64b609a2, + 0x0f11f404, + 0xb00076bb, + 0x1bf40136, + 0x0132f406, +/* 0x0a94: i2c_put_byte_done */ +/* 0x0a96: i2c_addr */ + 0x76bb00f8, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0xf550fc04, - 0xb60a4221, -/* 0x0ae2: i2c_addr_done */ - 0x00f80464, -/* 0x0ae4: i2c_acquire_addr */ - 0xb6f8cec7, - 0xe0b702e4, - 0xee980d1c, -/* 0x0af3: i2c_acquire */ - 0xf500f800, - 0xf40ae421, - 0xd9f00421, - 0x4021f403, -/* 0x0b02: i2c_release */ - 0x21f500f8, - 0x21f40ae4, - 0x03daf004, - 0xf84021f4, -/* 0x0b11: i2c_recv */ - 0x0132f400, - 0xb6f8c1c7, - 0x16b00214, - 0x3a1ff528, - 0xf413a001, - 0x0032980c, - 0x0ccc13a0, - 0xf4003198, - 0xd0f90231, - 0xd0f9e0f9, - 0x000067f1, - 0x100063f1, - 0xbb016792, + 0xb608d221, + 0x11f40464, + 0x2ec3e729, + 0x0134b601, + 0xbb0553fd, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0af321f5, - 0xfc0464b6, - 0x00d6b0d0, - 0x00b31bf5, - 0xbb0057f0, + 0x0a3b21f5, +/* 0x0adb: i2c_addr_done */ + 0xf80464b6, +/* 0x0add: i2c_acquire_addr */ + 0xf8cec700, + 0xb702e4b6, + 0x980d1ce0, + 0x00f800ee, +/* 0x0aec: i2c_acquire */ + 0x0add21f5, + 0xf00421f4, + 0x21f403d9, +/* 0x0afb: i2c_release */ + 0xf500f840, + 0xf40add21, + 0xdaf00421, + 0x4021f403, +/* 0x0b0a: i2c_recv */ + 0x32f400f8, + 0xf8c1c701, + 0xb00214b6, + 0x1ff52816, + 0x13a0013a, + 0x32980cf4, + 0xcc13a000, + 0x0031980c, + 0xf90231f4, + 0xf9e0f9d0, + 0x0067f1d0, + 0x0063f100, + 0x01679210, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0xec21f550, + 0x0464b60a, + 0xd6b0d0fc, + 0xb31bf500, + 0x0057f000, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x9621f550, + 0x0464b60a, + 0x00d011f5, + 0xbbe0c5c7, 0x65b60076, 0x9450f904, 0x56bb0465, 0xfd50bd02, 0x50fc0475, - 0x0a9d21f5, + 0x0a3b21f5, 0xf50464b6, - 0xc700d011, - 0x76bbe0c5, + 0xf000ad11, + 0x76bb0157, 0x0465b600, 0x659450f9, 0x0256bb04, 0x75fd50bd, 0xf550fc04, - 0xb60a4221, + 0xb60a9621, 0x11f50464, - 0x57f000ad, - 0x0076bb01, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0x21f550fc, - 0x64b60a9d, - 0x8a11f504, - 0x0076bb00, - 0xf90465b6, - 0x04659450, - 0xbd0256bb, - 0x0475fd50, - 0x21f550fc, - 0x64b609f0, - 0x6a11f404, - 0xbbe05bcb, - 0x65b60076, - 0x9450f904, - 0x56bb0465, - 0xfd50bd02, - 0x50fc0475, - 0x093521f5, - 0xb90464b6, - 0x74bd025b, -/* 0x0c17: i2c_recv_not_rd08 */ - 0xb0430ef4, - 0x1bf401d6, - 0x0057f03d, - 0x0a9d21f5, - 0xc73311f4, - 0x21f5e0c5, - 0x11f40a42, - 0x0057f029, - 0x0a9d21f5, - 0xc71f11f4, - 0x21f5e0b5, - 0x11f40a42, - 0x3521f515, - 0xc774bd09, - 0x1bf408c5, - 0x0232f409, -/* 0x0c57: i2c_recv_not_wr08 */ -/* 0x0c57: i2c_recv_done */ - 0xc7030ef4, - 0x21f5f8ce, - 0xe0fc0b02, - 0x12f4d0fc, - 0x027cb90a, - 0x033621f5, -/* 0x0c6c: i2c_recv_exit */ -/* 0x0c6e: i2c_init */ + 0x76bb008a, + 0x0465b600, + 0x659450f9, + 0x0256bb04, + 0x75fd50bd, + 0xf550fc04, + 0xb609e921, + 0x11f40464, + 0xe05bcb6a, + 0xb60076bb, + 0x50f90465, + 0xbb046594, + 0x50bd0256, + 0xfc0475fd, + 0x2e21f550, + 0x0464b609, + 0xbd025bb9, + 0x430ef474, +/* 0x0c10: i2c_recv_not_rd08 */ + 0xf401d6b0, + 0x57f03d1b, + 0x9621f500, + 0x3311f40a, + 0xf5e0c5c7, + 0xf40a3b21, + 0x57f02911, + 0x9621f500, + 0x1f11f40a, + 0xf5e0b5c7, + 0xf40a3b21, + 0x21f51511, + 0x74bd092e, + 0xf408c5c7, + 0x32f4091b, + 0x030ef402, +/* 0x0c50: i2c_recv_not_wr08 */ +/* 0x0c50: i2c_recv_done */ + 0xf5f8cec7, + 0xfc0afb21, + 0xf4d0fce0, + 0x7cb90a12, + 0x3621f502, +/* 0x0c65: i2c_recv_exit */ +/* 0x0c67: i2c_init */ + 0xf800f803, +/* 0x0c69: test_recv */ + 0xd817f100, + 0x0614b605, + 0xb60011cf, + 0x07f10110, + 0x04b605d8, + 0x0001d006, + 0xe7f104bd, + 0xe3f1d900, + 0x21f5134f, + 0x00f80256, +/* 0x0c90: test_init */ + 0x0800e7f1, + 0x025621f5, +/* 0x0c9a: idle_recv */ 0x00f800f8, -/* 0x0c70: test_recv */ - 0x05d817f1, - 0xcf0614b6, - 0x10b60011, - 0xd807f101, - 0x0604b605, - 0xbd0001d0, - 0x00e7f104, - 0x4fe3f1d9, - 0x5621f513, -/* 0x0c97: test_init */ - 0xf100f802, - 0xf50800e7, - 0xf8025621, -/* 0x0ca1: idle_recv */ -/* 0x0ca3: idle */ - 0xf400f800, - 0x17f10031, - 0x14b605d4, - 0x0011cf06, - 0xf10110b6, - 0xb605d407, - 0x01d00604, -/* 0x0cbf: idle_loop */ - 0xf004bd00, - 0x32f45817, -/* 0x0cc5: idle_proc */ -/* 0x0cc5: idle_proc_exec */ - 0xb910f902, - 0x21f5021e, - 0x10fc033f, - 0xf40911f4, - 0x0ef40231, -/* 0x0cd9: idle_proc_next */ - 0x5810b6ef, - 0xf4061fb8, - 0x02f4e61b, - 0x0028f4dd, - 0x00bb0ef4, +/* 0x0c9c: idle */ + 0xf10031f4, + 0xb605d417, + 0x11cf0614, + 0x0110b600, + 0x05d407f1, + 0xd00604b6, + 0x04bd0001, +/* 0x0cb8: idle_loop */ + 0xf45817f0, +/* 0x0cbe: idle_proc */ +/* 0x0cbe: idle_proc_exec */ + 0x10f90232, + 0xf5021eb9, + 0xfc033f21, + 0x0911f410, + 0xf40231f4, +/* 0x0cd2: idle_proc_next */ + 0x10b6ef0e, + 0x061fb858, + 0xf4e61bf4, + 0x28f4dd02, + 0xbb0ef400, + 0x00000000, + 0x00000000, 0x00000000, 0x00000000, 0x00000000, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc index ec03f9a4290b..1663bf943d77 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc @@ -82,15 +82,15 @@ memx_train_tail: // $r0 - zero memx_func_enter: #if NVKM_PPWR_CHIPSET == GT215 - movw $r8 0x1610 + mov $r8 0x1610 nv_rd32($r7, $r8) imm32($r6, 0xfffffffc) and $r7 $r6 - movw $r6 0x2 + mov $r6 0x2 or $r7 $r6 nv_wr32($r8, $r7) #else - movw $r6 0x001620 + mov $r6 0x001620 imm32($r7, ~0x00000aa2); nv_rd32($r8, $r6) and $r8 $r7 @@ -101,7 +101,7 @@ memx_func_enter: and $r8 $r7 nv_wr32($r6, $r8) - movw $r6 0x0026f0 + mov $r6 0x0026f0 nv_rd32($r8, $r6) and $r8 $r7 nv_wr32($r6, $r8) @@ -136,19 +136,19 @@ memx_func_leave: bra nz #memx_func_leave_wait #if NVKM_PPWR_CHIPSET == GT215 - movw $r8 0x1610 + mov $r8 0x1610 nv_rd32($r7, $r8) imm32($r6, 0xffffffcc) and $r7 $r6 nv_wr32($r8, $r7) #else - movw $r6 0x0026f0 + mov $r6 0x0026f0 imm32($r7, 0x00000001) nv_rd32($r8, $r6) or $r8 $r7 nv_wr32($r6, $r8) - movw $r6 0x001620 + mov $r6 0x001620 nv_rd32($r8, $r6) or $r8 $r7 nv_wr32($r6, $r8) @@ -177,11 +177,11 @@ memx_func_wait_vblank: bra #memx_func_wait_vblank_fini memx_func_wait_vblank_head1: - movw $r7 0x20 + mov $r7 0x20 bra #memx_func_wait_vblank_0 memx_func_wait_vblank_head0: - movw $r7 0x8 + mov $r7 0x8 memx_func_wait_vblank_0: nv_iord($r6, NV_PPWR_INPUT) @@ -273,13 +273,13 @@ memx_func_train: // $r5 - outer loop counter // $r6 - inner loop counter // $r7 - entry counter (#memx_train_head + $r7) - movw $r5 0x3 - movw $r7 0x0 + mov $r5 0x3 + mov $r7 0x0 // Read random memory to wake up... things imm32($r9, 0x700000) nv_rd32($r8,$r9) - movw $r14 0x2710 + mov $r14 0x2710 call(nsec) memx_func_train_loop_outer: @@ -289,9 +289,9 @@ memx_func_train: nv_wr32($r9, $r8) push $r5 - movw $r6 0x0 + mov $r6 0x0 memx_func_train_loop_inner: - movw $r8 0x1111 + mov $r8 0x1111 mulu $r9 $r6 $r8 shl b32 $r8 $r9 0x10 or $r8 $r9 @@ -315,7 +315,7 @@ memx_func_train: // $r5 - inner inner loop counter // $r9 - result - movw $r5 0 + mov $r5 0 imm32($r9, 0x8300ffff) memx_func_train_loop_4x: imm32($r10, 0x100080) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild index e698f4836521..ed08120eefe0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild @@ -7,8 +7,10 @@ nvkm-y += nvkm/subdev/secboot/acr_r352.o nvkm-y += nvkm/subdev/secboot/acr_r361.o nvkm-y += nvkm/subdev/secboot/acr_r364.o nvkm-y += nvkm/subdev/secboot/acr_r367.o +nvkm-y += nvkm/subdev/secboot/acr_r370.o nvkm-y += nvkm/subdev/secboot/acr_r375.o nvkm-y += nvkm/subdev/secboot/gm200.o nvkm-y += nvkm/subdev/secboot/gm20b.o nvkm-y += nvkm/subdev/secboot/gp102.o +nvkm-y += nvkm/subdev/secboot/gp108.o nvkm-y += nvkm/subdev/secboot/gp10b.o diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h index b615fc81aca4..73a2ac81ac69 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h @@ -64,6 +64,7 @@ struct nvkm_acr *acr_r352_new(unsigned long); struct nvkm_acr *acr_r361_new(unsigned long); struct nvkm_acr *acr_r364_new(unsigned long); struct nvkm_acr *acr_r367_new(enum nvkm_secboot_falcon, unsigned long); +struct nvkm_acr *acr_r370_new(enum nvkm_secboot_falcon, unsigned long); struct nvkm_acr *acr_r375_new(enum nvkm_secboot_falcon, unsigned long); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c new file mode 100644 index 000000000000..2f890dfae7fc --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c @@ -0,0 +1,144 @@ +/* + * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#include "acr_r370.h" +#include "acr_r367.h" + +#include <core/msgqueue.h> +#include <engine/falcon.h> +#include <engine/sec2.h> + +static void +acr_r370_generate_flcn_bl_desc(const struct nvkm_acr *acr, + const struct ls_ucode_img *img, u64 wpr_addr, + void *_desc) +{ + struct acr_r370_flcn_bl_desc *desc = _desc; + const struct ls_ucode_img_desc *pdesc = &img->ucode_desc; + u64 base, addr_code, addr_data; + + base = wpr_addr + img->ucode_off + pdesc->app_start_offset; + addr_code = base + pdesc->app_resident_code_offset; + addr_data = base + pdesc->app_resident_data_offset; + + desc->ctx_dma = FALCON_DMAIDX_UCODE; + desc->code_dma_base = u64_to_flcn64(addr_code); + desc->non_sec_code_off = pdesc->app_resident_code_offset; + desc->non_sec_code_size = pdesc->app_resident_code_size; + desc->code_entry_point = pdesc->app_imem_entry; + desc->data_dma_base = u64_to_flcn64(addr_data); + desc->data_size = pdesc->app_resident_data_size; +} + +const struct acr_r352_ls_func +acr_r370_ls_fecs_func = { + .load = acr_ls_ucode_load_fecs, + .generate_bl_desc = acr_r370_generate_flcn_bl_desc, + .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc), +}; + +const struct acr_r352_ls_func +acr_r370_ls_gpccs_func = { + .load = acr_ls_ucode_load_gpccs, + .generate_bl_desc = acr_r370_generate_flcn_bl_desc, + .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc), + /* GPCCS will be loaded using PRI */ + .lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD, +}; + +static void +acr_r370_generate_sec2_bl_desc(const struct nvkm_acr *acr, + const struct ls_ucode_img *img, u64 wpr_addr, + void *_desc) +{ + const struct ls_ucode_img_desc *pdesc = &img->ucode_desc; + const struct nvkm_sec2 *sec = acr->subdev->device->sec2; + struct acr_r370_flcn_bl_desc *desc = _desc; + u64 base, addr_code, addr_data; + u32 addr_args; + + base = wpr_addr + img->ucode_off + pdesc->app_start_offset; + /* For some reason we should not add app_resident_code_offset here */ + addr_code = base; + addr_data = base + pdesc->app_resident_data_offset; + addr_args = sec->falcon->data.limit; + addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE; + + desc->ctx_dma = FALCON_SEC2_DMAIDX_UCODE; + desc->code_dma_base = u64_to_flcn64(addr_code); + desc->non_sec_code_off = pdesc->app_resident_code_offset; + desc->non_sec_code_size = pdesc->app_resident_code_size; + desc->code_entry_point = pdesc->app_imem_entry; + desc->data_dma_base = u64_to_flcn64(addr_data); + desc->data_size = pdesc->app_resident_data_size; + desc->argc = 1; + /* args are stored at the beginning of EMEM */ + desc->argv = 0x01000000; +} + +const struct acr_r352_ls_func +acr_r370_ls_sec2_func = { + .load = acr_ls_ucode_load_sec2, + .generate_bl_desc = acr_r370_generate_sec2_bl_desc, + .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc), + .post_run = acr_ls_sec2_post_run, +}; + +void +acr_r370_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc, + u64 offset) +{ + struct acr_r370_flcn_bl_desc *bl_desc = _bl_desc; + + bl_desc->ctx_dma = FALCON_DMAIDX_VIRT; + bl_desc->non_sec_code_off = hdr->non_sec_code_off; + bl_desc->non_sec_code_size = hdr->non_sec_code_size; + bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0); + bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0); + bl_desc->code_entry_point = 0; + bl_desc->code_dma_base = u64_to_flcn64(offset); + bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base); + bl_desc->data_size = hdr->data_size; +} + +const struct acr_r352_func +acr_r370_func = { + .fixup_hs_desc = acr_r367_fixup_hs_desc, + .generate_hs_bl_desc = acr_r370_generate_hs_bl_desc, + .hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc), + .shadow_blob = true, + .ls_ucode_img_load = acr_r367_ls_ucode_img_load, + .ls_fill_headers = acr_r367_ls_fill_headers, + .ls_write_wpr = acr_r367_ls_write_wpr, + .ls_func = { + [NVKM_SECBOOT_FALCON_SEC2] = &acr_r370_ls_sec2_func, + [NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func, + [NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func, + }, +}; + +struct nvkm_acr * +acr_r370_new(enum nvkm_secboot_falcon boot_falcon, + unsigned long managed_falcons) +{ + return acr_r352_new_(&acr_r370_func, boot_falcon, managed_falcons); +} diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h new file mode 100644 index 000000000000..3426f86a15e4 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h @@ -0,0 +1,49 @@ +/* + * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef __NVKM_SECBOOT_ACR_R370_H__ +#define __NVKM_SECBOOT_ACR_R370_H__ + +#include "priv.h" +struct hsf_load_header; + +/* Same as acr_r361_flcn_bl_desc, plus argc/argv */ +struct acr_r370_flcn_bl_desc { + u32 reserved[4]; + u32 signature[4]; + u32 ctx_dma; + struct flcn_u64 code_dma_base; + u32 non_sec_code_off; + u32 non_sec_code_size; + u32 sec_code_off; + u32 sec_code_size; + u32 code_entry_point; + struct flcn_u64 data_dma_base; + u32 data_size; + u32 argc; + u32 argv; +}; + +void acr_r370_generate_hs_bl_desc(const struct hsf_load_header *, void *, u64); +extern const struct acr_r352_ls_func acr_r370_ls_fecs_func; +extern const struct acr_r352_ls_func acr_r370_ls_gpccs_func; +#endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c index ddb795bb007b..7bdef93cb7ae 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c @@ -20,90 +20,12 @@ * DEALINGS IN THE SOFTWARE. */ +#include "acr_r370.h" #include "acr_r367.h" -#include <engine/falcon.h> #include <core/msgqueue.h> #include <subdev/pmu.h> -/* - * r375 ACR: similar to r367, but with a unified bootloader descriptor - * structure for GR and PMU falcons. - */ - -/* Same as acr_r361_flcn_bl_desc, plus argc/argv */ -struct acr_r375_flcn_bl_desc { - u32 reserved[4]; - u32 signature[4]; - u32 ctx_dma; - struct flcn_u64 code_dma_base; - u32 non_sec_code_off; - u32 non_sec_code_size; - u32 sec_code_off; - u32 sec_code_size; - u32 code_entry_point; - struct flcn_u64 data_dma_base; - u32 data_size; - u32 argc; - u32 argv; -}; - -static void -acr_r375_generate_flcn_bl_desc(const struct nvkm_acr *acr, - const struct ls_ucode_img *img, u64 wpr_addr, - void *_desc) -{ - struct acr_r375_flcn_bl_desc *desc = _desc; - const struct ls_ucode_img_desc *pdesc = &img->ucode_desc; - u64 base, addr_code, addr_data; - - base = wpr_addr + img->ucode_off + pdesc->app_start_offset; - addr_code = base + pdesc->app_resident_code_offset; - addr_data = base + pdesc->app_resident_data_offset; - - desc->ctx_dma = FALCON_DMAIDX_UCODE; - desc->code_dma_base = u64_to_flcn64(addr_code); - desc->non_sec_code_off = pdesc->app_resident_code_offset; - desc->non_sec_code_size = pdesc->app_resident_code_size; - desc->code_entry_point = pdesc->app_imem_entry; - desc->data_dma_base = u64_to_flcn64(addr_data); - desc->data_size = pdesc->app_resident_data_size; -} - -static void -acr_r375_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc, - u64 offset) -{ - struct acr_r375_flcn_bl_desc *bl_desc = _bl_desc; - - bl_desc->ctx_dma = FALCON_DMAIDX_VIRT; - bl_desc->non_sec_code_off = hdr->non_sec_code_off; - bl_desc->non_sec_code_size = hdr->non_sec_code_size; - bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0); - bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0); - bl_desc->code_entry_point = 0; - bl_desc->code_dma_base = u64_to_flcn64(offset); - bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base); - bl_desc->data_size = hdr->data_size; -} - -const struct acr_r352_ls_func -acr_r375_ls_fecs_func = { - .load = acr_ls_ucode_load_fecs, - .generate_bl_desc = acr_r375_generate_flcn_bl_desc, - .bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc), -}; - -const struct acr_r352_ls_func -acr_r375_ls_gpccs_func = { - .load = acr_ls_ucode_load_gpccs, - .generate_bl_desc = acr_r375_generate_flcn_bl_desc, - .bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc), - /* GPCCS will be loaded using PRI */ - .lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD, -}; - - static void acr_r375_generate_pmu_bl_desc(const struct nvkm_acr *acr, const struct ls_ucode_img *img, u64 wpr_addr, @@ -111,7 +33,7 @@ acr_r375_generate_pmu_bl_desc(const struct nvkm_acr *acr, { const struct ls_ucode_img_desc *pdesc = &img->ucode_desc; const struct nvkm_pmu *pmu = acr->subdev->device->pmu; - struct acr_r375_flcn_bl_desc *desc = _desc; + struct acr_r370_flcn_bl_desc *desc = _desc; u64 base, addr_code, addr_data; u32 addr_args; @@ -136,23 +58,22 @@ const struct acr_r352_ls_func acr_r375_ls_pmu_func = { .load = acr_ls_ucode_load_pmu, .generate_bl_desc = acr_r375_generate_pmu_bl_desc, - .bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc), + .bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc), .post_run = acr_ls_pmu_post_run, }; - const struct acr_r352_func acr_r375_func = { .fixup_hs_desc = acr_r367_fixup_hs_desc, - .generate_hs_bl_desc = acr_r375_generate_hs_bl_desc, - .hs_bl_desc_size = sizeof(struct acr_r375_flcn_bl_desc), + .generate_hs_bl_desc = acr_r370_generate_hs_bl_desc, + .hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc), .shadow_blob = true, .ls_ucode_img_load = acr_r367_ls_ucode_img_load, .ls_fill_headers = acr_r367_ls_fill_headers, .ls_write_wpr = acr_r367_ls_write_wpr, .ls_func = { - [NVKM_SECBOOT_FALCON_FECS] = &acr_r375_ls_fecs_func, - [NVKM_SECBOOT_FALCON_GPCCS] = &acr_r375_ls_gpccs_func, + [NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func, + [NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func, [NVKM_SECBOOT_FALCON_PMU] = &acr_r375_ls_pmu_func, }, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c index f3b3c66349d2..1f7a3c1a7f50 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c @@ -133,7 +133,7 @@ gp102_secboot_run_blob(struct nvkm_secboot *sb, struct nvkm_gpuobj *blob, return gm200_secboot_run_blob(sb, blob, falcon); } -static const struct nvkm_secboot_func +const struct nvkm_secboot_func gp102_secboot = { .dtor = gm200_secboot_dtor, .oneinit = gm200_secboot_oneinit, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c new file mode 100644 index 000000000000..e8c27ec700de --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c @@ -0,0 +1,67 @@ +/* + * Copyright 2017 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ +#include "gm200.h" +#include "acr.h" + +int +gp108_secboot_new(struct nvkm_device *device, int index, + struct nvkm_secboot **psb) +{ + struct gm200_secboot *gsb; + struct nvkm_acr *acr; + + acr = acr_r370_new(NVKM_SECBOOT_FALCON_SEC2, + BIT(NVKM_SECBOOT_FALCON_FECS) | + BIT(NVKM_SECBOOT_FALCON_GPCCS) | + BIT(NVKM_SECBOOT_FALCON_SEC2)); + if (IS_ERR(acr)) + return PTR_ERR(acr); + + if (!(gsb = kzalloc(sizeof(*gsb), GFP_KERNEL))) { + acr->func->dtor(acr); + return -ENOMEM; + } + *psb = &gsb->base; + + return nvkm_secboot_ctor(&gp102_secboot, acr, device, index, &gsb->base); +} + +MODULE_FIRMWARE("nvidia/gp108/acr/bl.bin"); +MODULE_FIRMWARE("nvidia/gp108/acr/unload_bl.bin"); +MODULE_FIRMWARE("nvidia/gp108/acr/ucode_load.bin"); +MODULE_FIRMWARE("nvidia/gp108/acr/ucode_unload.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/fecs_bl.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/fecs_inst.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/fecs_data.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/fecs_sig.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_bl.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_inst.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_data.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_sig.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/sw_ctx.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/sw_nonctx.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/sw_bundle_init.bin"); +MODULE_FIRMWARE("nvidia/gp108/gr/sw_method_init.bin"); +MODULE_FIRMWARE("nvidia/gp108/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin"); +MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin"); +MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h index d9091f029506..959a7b2dbdc9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h @@ -40,6 +40,8 @@ int nvkm_secboot_ctor(const struct nvkm_secboot_func *, struct nvkm_acr *, int nvkm_secboot_falcon_reset(struct nvkm_secboot *); int nvkm_secboot_falcon_run(struct nvkm_secboot *); +extern const struct nvkm_secboot_func gp102_secboot; + struct flcn_u64 { u32 lo; u32 hi; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild index 7ba56b12badd..550702eab0b1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/Kbuild @@ -9,7 +9,9 @@ nvkm-y += nvkm/subdev/therm/nv40.o nvkm-y += nvkm/subdev/therm/nv50.o nvkm-y += nvkm/subdev/therm/g84.o nvkm-y += nvkm/subdev/therm/gt215.o +nvkm-y += nvkm/subdev/therm/gf100.o nvkm-y += nvkm/subdev/therm/gf119.o +nvkm-y += nvkm/subdev/therm/gk104.o nvkm-y += nvkm/subdev/therm/gm107.o nvkm-y += nvkm/subdev/therm/gm200.o nvkm-y += nvkm/subdev/therm/gp100.o diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c index f27fc6d0d4c6..bf62303571b3 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c @@ -21,6 +21,7 @@ * * Authors: Martin Peres */ +#include <nvkm/core/option.h> #include "priv.h" int @@ -297,6 +298,38 @@ nvkm_therm_attr_set(struct nvkm_therm *therm, return -EINVAL; } +void +nvkm_therm_clkgate_enable(struct nvkm_therm *therm) +{ + if (!therm->func->clkgate_enable || !therm->clkgating_enabled) + return; + + nvkm_debug(&therm->subdev, + "Enabling clockgating\n"); + therm->func->clkgate_enable(therm); +} + +void +nvkm_therm_clkgate_fini(struct nvkm_therm *therm, bool suspend) +{ + if (!therm->func->clkgate_fini || !therm->clkgating_enabled) + return; + + nvkm_debug(&therm->subdev, + "Preparing clockgating for %s\n", + suspend ? "suspend" : "fini"); + therm->func->clkgate_fini(therm, suspend); +} + +static void +nvkm_therm_clkgate_oneinit(struct nvkm_therm *therm) +{ + if (!therm->func->clkgate_enable || !therm->clkgating_enabled) + return; + + nvkm_info(&therm->subdev, "Clockgating enabled\n"); +} + static void nvkm_therm_intr(struct nvkm_subdev *subdev) { @@ -333,6 +366,7 @@ nvkm_therm_oneinit(struct nvkm_subdev *subdev) nvkm_therm_fan_ctor(therm); nvkm_therm_fan_mode(therm, NVKM_THERM_CTRL_AUTO); nvkm_therm_sensor_preinit(therm); + nvkm_therm_clkgate_oneinit(therm); return 0; } @@ -357,6 +391,16 @@ nvkm_therm_init(struct nvkm_subdev *subdev) return 0; } +void +nvkm_therm_clkgate_init(struct nvkm_therm *therm, + const struct nvkm_therm_clkgate_pack *p) +{ + if (!therm->func->clkgate_init || !therm->clkgating_enabled) + return; + + therm->func->clkgate_init(therm, p); +} + static void * nvkm_therm_dtor(struct nvkm_subdev *subdev) { @@ -374,15 +418,10 @@ nvkm_therm = { .intr = nvkm_therm_intr, }; -int -nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device, - int index, struct nvkm_therm **ptherm) +void +nvkm_therm_ctor(struct nvkm_therm *therm, struct nvkm_device *device, + int index, const struct nvkm_therm_func *func) { - struct nvkm_therm *therm; - - if (!(therm = *ptherm = kzalloc(sizeof(*therm), GFP_KERNEL))) - return -ENOMEM; - nvkm_subdev_ctor(&nvkm_therm, device, index, &therm->subdev); therm->func = func; @@ -395,5 +434,20 @@ nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device, therm->attr_get = nvkm_therm_attr_get; therm->attr_set = nvkm_therm_attr_set; therm->mode = therm->suspend = -1; /* undefined */ + + therm->clkgating_enabled = nvkm_boolopt(device->cfgopt, + "NvPmEnableGating", false); +} + +int +nvkm_therm_new_(const struct nvkm_therm_func *func, struct nvkm_device *device, + int index, struct nvkm_therm **ptherm) +{ + struct nvkm_therm *therm; + + if (!(therm = *ptherm = kzalloc(sizeof(*therm), GFP_KERNEL))) + return -ENOMEM; + + nvkm_therm_ctor(therm, device, index, func); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.c new file mode 100644 index 000000000000..5ae6913320e8 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.c @@ -0,0 +1,58 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Lyude Paul + */ +#include <core/device.h> + +#include "priv.h" + +#define pack_for_each_init(init, pack, head) \ + for (pack = head; pack && pack->init; pack++) \ + for (init = pack->init; init && init->count; init++) +void +gf100_clkgate_init(struct nvkm_therm *therm, + const struct nvkm_therm_clkgate_pack *p) +{ + struct nvkm_device *device = therm->subdev.device; + const struct nvkm_therm_clkgate_pack *pack; + const struct nvkm_therm_clkgate_init *init; + u32 next, addr; + + pack_for_each_init(init, pack, p) { + next = init->addr + init->count * 8; + addr = init->addr; + + nvkm_trace(&therm->subdev, "{ 0x%06x, %d, 0x%08x }\n", + init->addr, init->count, init->data); + while (addr < next) { + nvkm_trace(&therm->subdev, "\t0x%06x = 0x%08x\n", + addr, init->data); + nvkm_wr32(device, addr, init->data); + addr += 8; + } + } +} + +/* + * TODO: Fermi clockgating isn't understood fully yet, so we don't specify any + * clockgate functions to use + */ diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.h b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.h new file mode 100644 index 000000000000..cfb25af77c60 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf100.h @@ -0,0 +1,35 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Lyude Paul + */ + +#ifndef __GF100_THERM_H__ +#define __GF100_THERM_H__ + +#include <core/device.h> + +struct gf100_idle_filter { + u32 fecs; + u32 hubmmu; +}; + +#endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c index 06dcfd6ee966..0981b02790e2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gf119.c @@ -49,7 +49,7 @@ pwm_info(struct nvkm_therm *therm, int line) return -ENODEV; } -static int +int gf119_fan_pwm_ctrl(struct nvkm_therm *therm, int line, bool enable) { struct nvkm_device *device = therm->subdev.device; @@ -63,7 +63,7 @@ gf119_fan_pwm_ctrl(struct nvkm_therm *therm, int line, bool enable) return 0; } -static int +int gf119_fan_pwm_get(struct nvkm_therm *therm, int line, u32 *divs, u32 *duty) { struct nvkm_device *device = therm->subdev.device; @@ -85,7 +85,7 @@ gf119_fan_pwm_get(struct nvkm_therm *therm, int line, u32 *divs, u32 *duty) return -EINVAL; } -static int +int gf119_fan_pwm_set(struct nvkm_therm *therm, int line, u32 divs, u32 duty) { struct nvkm_device *device = therm->subdev.device; @@ -102,7 +102,7 @@ gf119_fan_pwm_set(struct nvkm_therm *therm, int line, u32 divs, u32 duty) return 0; } -static int +int gf119_fan_pwm_clock(struct nvkm_therm *therm, int line) { struct nvkm_device *device = therm->subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.c new file mode 100644 index 000000000000..4e03971d2e3d --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.c @@ -0,0 +1,136 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Lyude Paul + */ +#include <core/device.h> + +#include "priv.h" +#include "gk104.h" + +void +gk104_clkgate_enable(struct nvkm_therm *base) +{ + struct gk104_therm *therm = gk104_therm(base); + struct nvkm_device *dev = therm->base.subdev.device; + const struct gk104_clkgate_engine_info *order = therm->clkgate_order; + int i; + + /* Program ENG_MANT, ENG_FILTER */ + for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) { + if (!nvkm_device_subdev(dev, order[i].engine)) + continue; + + nvkm_mask(dev, 0x20200 + order[i].offset, 0xff00, 0x4500); + } + + /* magic */ + nvkm_wr32(dev, 0x020288, therm->idle_filter->fecs); + nvkm_wr32(dev, 0x02028c, therm->idle_filter->hubmmu); + + /* Enable clockgating (ENG_CLK = RUN->AUTO) */ + for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) { + if (!nvkm_device_subdev(dev, order[i].engine)) + continue; + + nvkm_mask(dev, 0x20200 + order[i].offset, 0x00ff, 0x0045); + } +} + +void +gk104_clkgate_fini(struct nvkm_therm *base, bool suspend) +{ + struct gk104_therm *therm = gk104_therm(base); + struct nvkm_device *dev = therm->base.subdev.device; + const struct gk104_clkgate_engine_info *order = therm->clkgate_order; + int i; + + /* ENG_CLK = AUTO->RUN, ENG_PWR = RUN->AUTO */ + for (i = 0; order[i].engine != NVKM_SUBDEV_NR; i++) { + if (!nvkm_device_subdev(dev, order[i].engine)) + continue; + + nvkm_mask(dev, 0x20200 + order[i].offset, 0xff, 0x54); + } +} + +const struct gk104_clkgate_engine_info gk104_clkgate_engine_info[] = { + { NVKM_ENGINE_GR, 0x00 }, + { NVKM_ENGINE_MSPDEC, 0x04 }, + { NVKM_ENGINE_MSPPP, 0x08 }, + { NVKM_ENGINE_MSVLD, 0x0c }, + { NVKM_ENGINE_CE0, 0x10 }, + { NVKM_ENGINE_CE1, 0x14 }, + { NVKM_ENGINE_MSENC, 0x18 }, + { NVKM_ENGINE_CE2, 0x1c }, + { NVKM_SUBDEV_NR, 0 }, +}; + +const struct gf100_idle_filter gk104_idle_filter = { + .fecs = 0x00001000, + .hubmmu = 0x00001000, +}; + +static const struct nvkm_therm_func +gk104_therm_func = { + .init = gf119_therm_init, + .fini = g84_therm_fini, + .pwm_ctrl = gf119_fan_pwm_ctrl, + .pwm_get = gf119_fan_pwm_get, + .pwm_set = gf119_fan_pwm_set, + .pwm_clock = gf119_fan_pwm_clock, + .temp_get = g84_temp_get, + .fan_sense = gt215_therm_fan_sense, + .program_alarms = nvkm_therm_program_alarms_polling, + .clkgate_init = gf100_clkgate_init, + .clkgate_enable = gk104_clkgate_enable, + .clkgate_fini = gk104_clkgate_fini, +}; + +static int +gk104_therm_new_(const struct nvkm_therm_func *func, + struct nvkm_device *device, + int index, + const struct gk104_clkgate_engine_info *clkgate_order, + const struct gf100_idle_filter *idle_filter, + struct nvkm_therm **ptherm) +{ + struct gk104_therm *therm = kzalloc(sizeof(*therm), GFP_KERNEL); + + if (!therm) + return -ENOMEM; + + nvkm_therm_ctor(&therm->base, device, index, func); + *ptherm = &therm->base; + therm->clkgate_order = clkgate_order; + therm->idle_filter = idle_filter; + + return 0; +} + +int +gk104_therm_new(struct nvkm_device *device, + int index, struct nvkm_therm **ptherm) +{ + return gk104_therm_new_(&gk104_therm_func, device, index, + gk104_clkgate_engine_info, &gk104_idle_filter, + ptherm); +} diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.h b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.h new file mode 100644 index 000000000000..293e7743b19b --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gk104.h @@ -0,0 +1,48 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: Lyude Paul + */ + +#ifndef __GK104_THERM_H__ +#define __GK104_THERM_H__ +#define gk104_therm(p) (container_of((p), struct gk104_therm, base)) + +#include <subdev/therm.h> +#include "priv.h" +#include "gf100.h" + +struct gk104_clkgate_engine_info { + enum nvkm_devidx engine; + u8 offset; +}; + +struct gk104_therm { + struct nvkm_therm base; + + const struct gk104_clkgate_engine_info *clkgate_order; + const struct gf100_idle_filter *idle_filter; +}; + +extern const struct gk104_clkgate_engine_info gk104_clkgate_engine_info[]; +extern const struct gf100_idle_filter gk104_idle_filter; + +#endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c index c08097f2aff5..4caf401d001a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/gt215.c @@ -36,7 +36,7 @@ gt215_therm_fan_sense(struct nvkm_therm *therm) return -ENODEV; } -static void +void gt215_therm_init(struct nvkm_therm *therm) { struct nvkm_device *device = therm->subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h index 1f46e371d7c4..21659daf1864 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/priv.h @@ -32,6 +32,8 @@ int nvkm_therm_new_(const struct nvkm_therm_func *, struct nvkm_device *, int index, struct nvkm_therm **); +void nvkm_therm_ctor(struct nvkm_therm *therm, struct nvkm_device *device, + int index, const struct nvkm_therm_func *func); struct nvkm_fan { struct nvkm_therm *parent; @@ -66,8 +68,6 @@ int nvkm_therm_fan_set(struct nvkm_therm *, bool now, int percent); int nvkm_therm_fan_user_get(struct nvkm_therm *); int nvkm_therm_fan_user_set(struct nvkm_therm *, int percent); -int nvkm_therm_preinit(struct nvkm_therm *); - int nvkm_therm_sensor_init(struct nvkm_therm *); int nvkm_therm_sensor_fini(struct nvkm_therm *, bool suspend); void nvkm_therm_sensor_preinit(struct nvkm_therm *); @@ -96,6 +96,11 @@ struct nvkm_therm_func { int (*fan_sense)(struct nvkm_therm *); void (*program_alarms)(struct nvkm_therm *); + + void (*clkgate_init)(struct nvkm_therm *, + const struct nvkm_therm_clkgate_pack *); + void (*clkgate_enable)(struct nvkm_therm *); + void (*clkgate_fini)(struct nvkm_therm *, bool); }; void nv40_therm_intr(struct nvkm_therm *); @@ -111,9 +116,21 @@ void g84_therm_fini(struct nvkm_therm *); int gt215_therm_fan_sense(struct nvkm_therm *); +void gf100_clkgate_init(struct nvkm_therm *, + const struct nvkm_therm_clkgate_pack *); + void g84_therm_init(struct nvkm_therm *); + +int gf119_fan_pwm_ctrl(struct nvkm_therm *, int, bool); +int gf119_fan_pwm_get(struct nvkm_therm *, int, u32 *, u32 *); +int gf119_fan_pwm_set(struct nvkm_therm *, int, u32, u32); +int gf119_fan_pwm_clock(struct nvkm_therm *, int); void gf119_therm_init(struct nvkm_therm *); +void gk104_therm_init(struct nvkm_therm *); +void gk104_clkgate_enable(struct nvkm_therm *); +void gk104_clkgate_fini(struct nvkm_therm *, bool); + int nvkm_fanpwm_create(struct nvkm_therm *, struct dcb_gpio_func *); int nvkm_fantog_create(struct nvkm_therm *, struct dcb_gpio_func *); int nvkm_fannil_create(struct nvkm_therm *); diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index d34d1cf33895..95f4db70dd22 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -995,7 +995,7 @@ int radeon_uvd_calc_upll_dividers(struct radeon_device *rdev, /* calc dclk divider with current vco freq */ dclk_div = radeon_uvd_calc_upll_post_div(vco_freq, dclk, pd_min, pd_even); - if (vclk_div > pd_max) + if (dclk_div > pd_max) break; /* vco is too big, it has to stop */ /* calc score with current vco freq */ diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 893003fc76a1..2fef09a56d16 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1727,7 +1727,7 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx) kref_get(&bo->list_kref); if (!list_empty(&bo->ddestroy)) { - ret = ttm_bo_cleanup_refs(bo, false, false, true); + ret = ttm_bo_cleanup_refs(bo, false, false, locked); kref_put(&bo->list_kref, ttm_bo_release_list); return ret; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 08a3c324242e..60fcef1593dd 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -316,7 +316,7 @@ static void ttm_bo_vm_close(struct vm_area_struct *vma) static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo, unsigned long offset, - void *buf, int len, int write) + uint8_t *buf, int len, int write) { unsigned long page = offset >> PAGE_SHIFT; unsigned long bytes_left = len; @@ -345,6 +345,7 @@ static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo, ttm_bo_kunmap(&map); page++; + buf += bytes; bytes_left -= bytes; offset = 0; } while (bytes_left); diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c index dfd8d0048980..1c5e74cb9279 100644 --- a/drivers/gpu/vga/vgaarb.c +++ b/drivers/gpu/vga/vgaarb.c @@ -1271,7 +1271,7 @@ static __poll_t vga_arb_fpoll(struct file *file, poll_table *wait) pr_debug("%s\n", __func__); poll_wait(file, &vga_wait_queue, wait); - return POLLIN; + return EPOLLIN; } static int vga_arb_open(struct inode *inode, struct file *file) diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index c783fd5ef809..4f4e7a08a07b 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -1185,9 +1185,9 @@ static __poll_t hid_debug_events_poll(struct file *file, poll_table *wait) poll_wait(file, &list->hdev->debug_wait, wait); if (list->head != list->tail) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; if (!list->hdev->debug) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; return 0; } diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c index b7e86aba6f33..5be8de70c651 100644 --- a/drivers/hid/hid-roccat.c +++ b/drivers/hid/hid-roccat.c @@ -142,9 +142,9 @@ static __poll_t roccat_poll(struct file *file, poll_table *wait) struct roccat_reader *reader = file->private_data; poll_wait(file, &reader->device->wait, wait); if (reader->cbuf_start != reader->device->cbuf_end) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; if (!reader->device->exist) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; return 0; } diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index 21ed6c55c40a..e8a114157f87 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -714,7 +714,7 @@ static __poll_t hid_sensor_custom_poll(struct file *file, poll_wait(file, &sensor_inst->wait, wait); if (!kfifo_is_empty(&sensor_inst->data_fifo)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index be210219f982..fbfcc8009432 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -255,9 +255,9 @@ static __poll_t hidraw_poll(struct file *file, poll_table *wait) poll_wait(file, &list->hidraw->wait, wait); if (list->head != list->tail) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; if (!list->hidraw->exist) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; return 0; } diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c index fc43850a155e..4e0e7baf8513 100644 --- a/drivers/hid/uhid.c +++ b/drivers/hid/uhid.c @@ -760,7 +760,7 @@ static __poll_t uhid_char_poll(struct file *file, poll_table *wait) poll_wait(file, &uhid->waitq, wait); if (uhid->head != uhid->tail) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 0ff3e7e70c8d..e3ce233f8bdc 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -428,9 +428,9 @@ static __poll_t hiddev_poll(struct file *file, poll_table *wait) poll_wait(file, &list->hiddev->wait, wait); if (list->head != list->tail) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; if (!list->hiddev->exist) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; return 0; } diff --git a/drivers/hsi/clients/cmt_speech.c b/drivers/hsi/clients/cmt_speech.c index 8fbbacb0fe21..324cb8ec9405 100644 --- a/drivers/hsi/clients/cmt_speech.c +++ b/drivers/hsi/clients/cmt_speech.c @@ -1132,9 +1132,9 @@ static __poll_t cs_char_poll(struct file *file, poll_table *wait) poll_wait(file, &cs_char_data.wait, wait); spin_lock_bh(&csdata->lock); if (!list_empty(&csdata->chardev_queue)) - ret = POLLIN | POLLRDNORM; + ret = EPOLLIN | EPOLLRDNORM; else if (!list_empty(&csdata->dataind_queue)) - ret = POLLIN | POLLRDNORM; + ret = EPOLLIN | EPOLLRDNORM; spin_unlock_bh(&csdata->lock); return ret; diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c index 047959e74bb1..832777527936 100644 --- a/drivers/hv/hv_utils_transport.c +++ b/drivers/hv/hv_utils_transport.c @@ -113,10 +113,10 @@ static __poll_t hvt_op_poll(struct file *file, poll_table *wait) poll_wait(file, &hvt->outmsg_q, wait); if (hvt->mode == HVUTIL_TRANSPORT_DESTROY) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; if (hvt->outmsg_len > 0) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c index ff03324dee13..05e0c353e089 100644 --- a/drivers/iio/buffer/industrialio-buffer-dma.c +++ b/drivers/iio/buffer/industrialio-buffer-dma.c @@ -222,7 +222,7 @@ void iio_dma_buffer_block_done(struct iio_dma_buffer_block *block) spin_unlock_irqrestore(&queue->list_lock, flags); iio_buffer_block_put_atomic(block); - wake_up_interruptible_poll(&queue->buffer.pollq, POLLIN | POLLRDNORM); + wake_up_interruptible_poll(&queue->buffer.pollq, EPOLLIN | EPOLLRDNORM); } EXPORT_SYMBOL_GPL(iio_dma_buffer_block_done); @@ -251,7 +251,7 @@ void iio_dma_buffer_block_list_abort(struct iio_dma_buffer_queue *queue, } spin_unlock_irqrestore(&queue->list_lock, flags); - wake_up_interruptible_poll(&queue->buffer.pollq, POLLIN | POLLRDNORM); + wake_up_interruptible_poll(&queue->buffer.pollq, EPOLLIN | EPOLLRDNORM); } EXPORT_SYMBOL_GPL(iio_dma_buffer_block_list_abort); diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 6184c100a94a..79abf70a126d 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -166,7 +166,7 @@ ssize_t iio_buffer_read_first_n_outer(struct file *filp, char __user *buf, * @wait: Poll table structure pointer for which the driver adds * a wait queue * - * Return: (POLLIN | POLLRDNORM) if data is available for reading + * Return: (EPOLLIN | EPOLLRDNORM) if data is available for reading * or 0 for other cases */ __poll_t iio_buffer_poll(struct file *filp, @@ -180,7 +180,7 @@ __poll_t iio_buffer_poll(struct file *filp, poll_wait(filp, &rb->pollq, wait); if (iio_buffer_ready(indio_dev, rb, rb->watermark, 0)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } @@ -1396,7 +1396,7 @@ static int iio_push_to_buffer(struct iio_buffer *buffer, const void *data) * We can't just test for watermark to decide if we wake the poll queue * because read may request less samples than the watermark. */ - wake_up_interruptible_poll(&buffer->pollq, POLLIN | POLLRDNORM); + wake_up_interruptible_poll(&buffer->pollq, EPOLLIN | EPOLLRDNORM); return 0; } diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c index 0bcf073e46db..c6dfdf0aaac5 100644 --- a/drivers/iio/industrialio-event.c +++ b/drivers/iio/industrialio-event.c @@ -80,7 +80,7 @@ int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp) copied = kfifo_put(&ev_int->det_events, ev); if (copied != 0) - wake_up_poll(&ev_int->wait, POLLIN); + wake_up_poll(&ev_int->wait, EPOLLIN); } return 0; @@ -92,7 +92,7 @@ EXPORT_SYMBOL(iio_push_event); * @filep: File structure pointer to identify the device * @wait: Poll table pointer to add the wait queue on * - * Return: (POLLIN | POLLRDNORM) if data is available for reading + * Return: (EPOLLIN | EPOLLRDNORM) if data is available for reading * or a negative error code on failure */ static __poll_t iio_event_poll(struct file *filep, @@ -108,7 +108,7 @@ static __poll_t iio_event_poll(struct file *filep, poll_wait(filep, &ev_int->wait, wait); if (!kfifo_is_empty(&ev_int->det_events)) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; return events; } diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 8ae636bb09e5..01702265c1e1 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -1144,7 +1144,7 @@ static __poll_t ib_ucm_poll(struct file *filp, poll_wait(filp, &file->poll_wait, wait); if (!list_empty(&file->events)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 6ba4231f2b07..f015f1bf88c9 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1639,7 +1639,7 @@ static __poll_t ucma_poll(struct file *filp, struct poll_table_struct *wait) poll_wait(filp, &file->poll_wait, wait); if (!list_empty(&file->event_list)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index 78c77962422e..bb98c9e4a7fd 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -633,12 +633,12 @@ static __poll_t ib_umad_poll(struct file *filp, struct poll_table_struct *wait) struct ib_umad_file *file = filp->private_data; /* we will always be able to post a MAD send */ - __poll_t mask = POLLOUT | POLLWRNORM; + __poll_t mask = EPOLLOUT | EPOLLWRNORM; poll_wait(filp, &file->recv_wait, wait); if (!list_empty(&file->recv_list)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 5b811bf574d6..395a3b091229 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -351,7 +351,7 @@ static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue, spin_lock_irq(&ev_queue->lock); if (!list_empty(&ev_queue->event_list)) - pollflags = POLLIN | POLLRDNORM; + pollflags = EPOLLIN | EPOLLRDNORM; spin_unlock_irq(&ev_queue->lock); return pollflags; diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index d9a0f2590294..41fafebe3b0d 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -612,13 +612,13 @@ static __poll_t hfi1_poll(struct file *fp, struct poll_table_struct *pt) uctxt = ((struct hfi1_filedata *)fp->private_data)->uctxt; if (!uctxt) - pollflag = POLLERR; + pollflag = EPOLLERR; else if (uctxt->poll_type == HFI1_POLL_TYPE_URGENT) pollflag = poll_urgent(fp, pt); else if (uctxt->poll_type == HFI1_POLL_TYPE_ANYRCV) pollflag = poll_next(fp, pt); else /* invalid */ - pollflag = POLLERR; + pollflag = EPOLLERR; return pollflag; } @@ -1435,7 +1435,7 @@ static __poll_t poll_urgent(struct file *fp, spin_lock_irq(&dd->uctxt_lock); if (uctxt->urgent != uctxt->urgent_poll) { - pollflag = POLLIN | POLLRDNORM; + pollflag = EPOLLIN | EPOLLRDNORM; uctxt->urgent_poll = uctxt->urgent; } else { pollflag = 0; @@ -1462,7 +1462,7 @@ static __poll_t poll_next(struct file *fp, hfi1_rcvctrl(dd, HFI1_RCVCTRL_INTRAVAIL_ENB, uctxt); pollflag = 0; } else { - pollflag = POLLIN | POLLRDNORM; + pollflag = EPOLLIN | EPOLLRDNORM; } spin_unlock_irq(&dd->uctxt_lock); diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index f7593b5e2b76..52c29db3a2f4 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -1085,7 +1085,7 @@ static __poll_t qib_poll_urgent(struct qib_ctxtdata *rcd, spin_lock_irq(&dd->uctxt_lock); if (rcd->urgent != rcd->urgent_poll) { - pollflag = POLLIN | POLLRDNORM; + pollflag = EPOLLIN | EPOLLRDNORM; rcd->urgent_poll = rcd->urgent; } else { pollflag = 0; @@ -1111,7 +1111,7 @@ static __poll_t qib_poll_next(struct qib_ctxtdata *rcd, dd->f_rcvctrl(rcd->ppd, QIB_RCVCTRL_INTRAVAIL_ENB, rcd->ctxt); pollflag = 0; } else - pollflag = POLLIN | POLLRDNORM; + pollflag = EPOLLIN | EPOLLRDNORM; spin_unlock_irq(&dd->uctxt_lock); return pollflag; @@ -1124,13 +1124,13 @@ static __poll_t qib_poll(struct file *fp, struct poll_table_struct *pt) rcd = ctxt_fp(fp); if (!rcd) - pollflag = POLLERR; + pollflag = EPOLLERR; else if (rcd->poll_type == QIB_POLL_TYPE_URGENT) pollflag = qib_poll_urgent(rcd, fp, pt); else if (rcd->poll_type == QIB_POLL_TYPE_ANYRCV) pollflag = qib_poll_next(rcd, fp, pt); else /* invalid */ - pollflag = POLLERR; + pollflag = EPOLLERR; return pollflag; } diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 19624e023ebd..0336643c2ed6 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -874,7 +874,7 @@ iscsi_iser_ep_poll(struct iscsi_endpoint *ep, int timeout_ms) iser_info("iser conn %p rc = %d\n", iser_conn, rc); if (rc > 0) - return 1; /* success, this is the equivalent of POLLOUT */ + return 1; /* success, this is the equivalent of EPOLLOUT */ else if (!rc) return 0; /* timeout */ else diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 94049fdc583c..c81c79d01d93 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -650,12 +650,12 @@ static __poll_t evdev_poll(struct file *file, poll_table *wait) poll_wait(file, &evdev->wait, wait); if (evdev->exist && !client->revoked) - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; else - mask = POLLHUP | POLLERR; + mask = EPOLLHUP | EPOLLERR; if (client->packet_head != client->tail) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/input/input.c b/drivers/input/input.c index 0d0b2ab1bb6b..9785546420a7 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -1053,7 +1053,7 @@ static __poll_t input_proc_devices_poll(struct file *file, poll_table *wait) poll_wait(file, &input_devices_poll_wait, wait); if (file->f_version != input_devices_state) { file->f_version = input_devices_state; - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } return 0; diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index fe3255572886..4c1e427dfabb 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -442,8 +442,8 @@ static __poll_t joydev_poll(struct file *file, poll_table *wait) struct joydev *joydev = client->joydev; poll_wait(file, &joydev->wait, wait); - return (joydev_data_pending(client) ? (POLLIN | POLLRDNORM) : 0) | - (joydev->exist ? 0 : (POLLHUP | POLLERR)); + return (joydev_data_pending(client) ? (EPOLLIN | EPOLLRDNORM) : 0) | + (joydev->exist ? 0 : (EPOLLHUP | EPOLLERR)); } static int joydev_handle_JSIOCSAXMAP(struct joydev *joydev, diff --git a/drivers/input/misc/hp_sdc_rtc.c b/drivers/input/misc/hp_sdc_rtc.c index 9c3f7ec3bd3d..49b34de0aed4 100644 --- a/drivers/input/misc/hp_sdc_rtc.c +++ b/drivers/input/misc/hp_sdc_rtc.c @@ -414,7 +414,7 @@ static __poll_t hp_sdc_rtc_poll(struct file *file, poll_table *wait) l = 0; if (l != 0) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index f640c591ef23..96a887f33698 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -704,7 +704,7 @@ static __poll_t uinput_poll(struct file *file, poll_table *wait) poll_wait(file, &udev->waitq, wait); if (udev->head != udev->tail) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c index 731d84ae5101..e08228061bcd 100644 --- a/drivers/input/mousedev.c +++ b/drivers/input/mousedev.c @@ -765,9 +765,9 @@ static __poll_t mousedev_poll(struct file *file, poll_table *wait) poll_wait(file, &mousedev->wait, wait); - mask = mousedev->exist ? POLLOUT | POLLWRNORM : POLLHUP | POLLERR; + mask = mousedev->exist ? EPOLLOUT | EPOLLWRNORM : EPOLLHUP | EPOLLERR; if (client->ready || client->buffer) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/input/serio/serio_raw.c b/drivers/input/serio/serio_raw.c index fccf55a380b2..17b7fbecd9fe 100644 --- a/drivers/input/serio/serio_raw.c +++ b/drivers/input/serio/serio_raw.c @@ -247,9 +247,9 @@ static __poll_t serio_raw_poll(struct file *file, poll_table *wait) poll_wait(file, &serio_raw->wait, wait); - mask = serio_raw->dead ? POLLHUP | POLLERR : POLLOUT | POLLWRNORM; + mask = serio_raw->dead ? EPOLLHUP | EPOLLERR : EPOLLOUT | EPOLLWRNORM; if (serio_raw->head != serio_raw->tail) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c index a63de06b08bc..9ab5c45c3a9f 100644 --- a/drivers/input/serio/userio.c +++ b/drivers/input/serio/userio.c @@ -255,7 +255,7 @@ static __poll_t userio_char_poll(struct file *file, poll_table *wait) poll_wait(file, &userio->waitq, wait); if (userio->head != userio->tail) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index fba4ec168bd5..74788fdeb773 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -617,7 +617,9 @@ retry: address, flags); break; default: - printk(KERN_ERR "UNKNOWN type=0x%02x]\n", type); + printk(KERN_ERR "UNKNOWN type=0x%02x event[0]=0x%08x " + "event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n", + type, event[0], event[1], event[2], event[3]); } memset(__evt, 0, 4 * sizeof(u32)); @@ -1816,7 +1818,8 @@ static bool dma_ops_domain(struct protection_domain *domain) return domain->flags & PD_DMA_OPS_MASK; } -static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats) +static void set_dte_entry(u16 devid, struct protection_domain *domain, + bool ats, bool ppr) { u64 pte_root = 0; u64 flags = 0; @@ -1833,6 +1836,13 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats) if (ats) flags |= DTE_FLAG_IOTLB; + if (ppr) { + struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; + + if (iommu_feature(iommu, FEATURE_EPHSUP)) + pte_root |= 1ULL << DEV_ENTRY_PPR; + } + if (domain->flags & PD_IOMMUV2_MASK) { u64 gcr3 = iommu_virt_to_phys(domain->gcr3_tbl); u64 glx = domain->glx; @@ -1895,9 +1905,9 @@ static void do_attach(struct iommu_dev_data *dev_data, domain->dev_cnt += 1; /* Update device table */ - set_dte_entry(dev_data->devid, domain, ats); + set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2); if (alias != dev_data->devid) - set_dte_entry(alias, domain, ats); + set_dte_entry(alias, domain, ats, dev_data->iommu_v2); device_flush_dte(dev_data); } @@ -2276,13 +2286,15 @@ static void update_device_table(struct protection_domain *domain) struct iommu_dev_data *dev_data; list_for_each_entry(dev_data, &domain->dev_list, list) { - set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled); + set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled, + dev_data->iommu_v2); if (dev_data->devid == dev_data->alias) continue; /* There is an alias, update device table entry for it */ - set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled); + set_dte_entry(dev_data->alias, domain, dev_data->ats.enabled, + dev_data->iommu_v2); } } diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index f6b24c7d8b70..6a877ebd058b 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -98,6 +98,7 @@ #define FEATURE_HE (1ULL<<8) #define FEATURE_PC (1ULL<<9) #define FEATURE_GAM_VAPIC (1ULL<<21) +#define FEATURE_EPHSUP (1ULL<<50) #define FEATURE_PASID_SHIFT 32 #define FEATURE_PASID_MASK (0x1fULL << FEATURE_PASID_SHIFT) @@ -192,6 +193,7 @@ /* macros and definitions for device table entries */ #define DEV_ENTRY_VALID 0x00 #define DEV_ENTRY_TRANSLATION 0x01 +#define DEV_ENTRY_PPR 0x34 #define DEV_ENTRY_IR 0x3d #define DEV_ENTRY_IW 0x3e #define DEV_ENTRY_NO_PAGE_FAULT 0x62 diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 744592d330ca..3f2f1fc68b52 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2971,7 +2971,7 @@ static struct platform_driver arm_smmu_driver = { }; module_platform_driver(arm_smmu_driver); -IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", NULL); +IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3"); MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations"); MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>"); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 78d4c6b8f1ba..69e7c60792a8 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -2211,12 +2211,12 @@ static struct platform_driver arm_smmu_driver = { }; module_platform_driver(arm_smmu_driver); -IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1", NULL); -IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2", NULL); -IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400", NULL); -IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401", NULL); -IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", NULL); -IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", NULL); +IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1"); +IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2"); +IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400"); +IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401"); +IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500"); +IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2"); MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations"); MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>"); diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 79c45650f8de..2138102ef611 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1353,8 +1353,15 @@ static const struct iommu_ops exynos_iommu_ops = { static int __init exynos_iommu_init(void) { + struct device_node *np; int ret; + np = of_find_matching_node(NULL, sysmmu_of_match); + if (!np) + return 0; + + of_node_put(np); + lv2table_kmem_cache = kmem_cache_create("exynos-iommu-lv2table", LV2TABLE_SIZE, LV2TABLE_SIZE, 0, NULL); if (!lv2table_kmem_cache) { @@ -1394,4 +1401,4 @@ err_reg_driver: } core_initcall(exynos_iommu_init); -IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu", NULL); +IOMMU_OF_DECLARE(exynos_iommu_of, "samsung,exynos-sysmmu"); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a1373cf34326..582fd01cb7d1 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -64,7 +64,7 @@ #define IOAPIC_RANGE_END (0xfeefffff) #define IOVA_START_ADDR (0x1000) -#define DEFAULT_DOMAIN_ADDRESS_WIDTH 48 +#define DEFAULT_DOMAIN_ADDRESS_WIDTH 57 #define MAX_AGAW_WIDTH 64 #define MAX_AGAW_PFN_WIDTH (MAX_AGAW_WIDTH - VTD_PAGE_SHIFT) @@ -1601,8 +1601,7 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, * flush. However, device IOTLB doesn't need to be flushed in this case. */ if (!cap_caching_mode(iommu->cap) || !map) - iommu_flush_dev_iotlb(get_iommu_domain(iommu, did), - addr, mask); + iommu_flush_dev_iotlb(domain, addr, mask); } static void iommu_flush_iova(struct iova_domain *iovad) diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 0a826eb7fe48..35a408d0ae4f 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -26,6 +26,10 @@ #include <linux/interrupt.h> #include <asm/page.h> +#define PASID_ENTRY_P BIT_ULL(0) +#define PASID_ENTRY_FLPM_5LP BIT_ULL(9) +#define PASID_ENTRY_SRE BIT_ULL(11) + static irqreturn_t prq_event_thread(int irq, void *d); struct pasid_entry { @@ -41,6 +45,14 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) struct page *pages; int order; + if (cpu_feature_enabled(X86_FEATURE_GBPAGES) && + !cap_fl1gp_support(iommu->cap)) + return -EINVAL; + + if (cpu_feature_enabled(X86_FEATURE_LA57) && + !cap_5lp_support(iommu->cap)) + return -EINVAL; + /* Start at 2 because it's defined as 2^(1+PSS) */ iommu->pasid_max = 2 << ecap_pss(iommu->ecap); @@ -129,6 +141,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu) pr_err("IOMMU: %s: Failed to request IRQ for page request queue\n", iommu->name); dmar_free_hwirq(irq); + iommu->pr_irq = 0; goto err; } dmar_writeq(iommu->reg + DMAR_PQH_REG, 0ULL); @@ -144,9 +157,11 @@ int intel_svm_finish_prq(struct intel_iommu *iommu) dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL); dmar_writeq(iommu->reg + DMAR_PQA_REG, 0ULL); - free_irq(iommu->pr_irq, iommu); - dmar_free_hwirq(iommu->pr_irq); - iommu->pr_irq = 0; + if (iommu->pr_irq) { + free_irq(iommu->pr_irq, iommu); + dmar_free_hwirq(iommu->pr_irq); + iommu->pr_irq = 0; + } free_pages((unsigned long)iommu->prq, PRQ_ORDER); iommu->prq = NULL; @@ -290,6 +305,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ struct intel_svm_dev *sdev; struct intel_svm *svm = NULL; struct mm_struct *mm = NULL; + u64 pasid_entry_val; int pasid_max; int ret; @@ -396,9 +412,15 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ kfree(sdev); goto out; } - iommu->pasid_table[svm->pasid].val = (u64)__pa(mm->pgd) | 1; + pasid_entry_val = (u64)__pa(mm->pgd) | PASID_ENTRY_P; } else - iommu->pasid_table[svm->pasid].val = (u64)__pa(init_mm.pgd) | 1 | (1ULL << 11); + pasid_entry_val = (u64)__pa(init_mm.pgd) | + PASID_ENTRY_P | PASID_ENTRY_SRE; + if (cpu_feature_enabled(X86_FEATURE_LA57)) + pasid_entry_val |= PASID_ENTRY_FLPM_5LP; + + iommu->pasid_table[svm->pasid].val = pasid_entry_val; + wmb(); /* In caching mode, we still have to flush with PASID 0 when * a PASID table entry becomes present. Not entirely clear diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3de5c0bcb5cc..69fef991c651 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1303,6 +1303,9 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev) int ret; group = iommu_group_get(dev); + if (!group) + return -ENODEV; + /* * Lock the group to make sure the device-count doesn't * change while we are attaching @@ -1341,6 +1344,8 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev) struct iommu_group *group; group = iommu_group_get(dev); + if (!group) + return; mutex_lock(&group->mutex); if (iommu_group_device_count(group) != 1) { diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 8dce3a9de9d8..40ae6e87cb88 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -1108,18 +1108,8 @@ static void __exit ipmmu_exit(void) subsys_initcall(ipmmu_init); module_exit(ipmmu_exit); -#ifdef CONFIG_IOMMU_DMA -static int __init ipmmu_vmsa_iommu_of_setup(struct device_node *np) -{ - ipmmu_init(); - return 0; -} - -IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa", - ipmmu_vmsa_iommu_of_setup); -IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795", - ipmmu_vmsa_iommu_of_setup); -#endif +IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa"); +IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795"); MODULE_DESCRIPTION("IOMMU API for Renesas VMSA-compatible IPMMU"); MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>"); diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 04f4d51ffacb..0d3350463a3f 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -823,6 +823,8 @@ static int msm_iommu_probe(struct platform_device *pdev) goto fail; } + bus_set_iommu(&platform_bus_type, &msm_iommu_ops); + pr_info("device mapped at %p, irq %d with %d ctx banks\n", iommu->base, iommu->irq, iommu->ncb); @@ -875,19 +877,7 @@ static void __exit msm_iommu_driver_exit(void) subsys_initcall(msm_iommu_driver_init); module_exit(msm_iommu_driver_exit); -static int __init msm_iommu_init(void) -{ - bus_set_iommu(&platform_bus_type, &msm_iommu_ops); - return 0; -} - -static int __init msm_iommu_of_setup(struct device_node *np) -{ - msm_iommu_init(); - return 0; -} - -IOMMU_OF_DECLARE(msm_iommu_of, "qcom,apq8064-iommu", msm_iommu_of_setup); +IOMMU_OF_DECLARE(msm_iommu_of, "qcom,apq8064-iommu"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Stepan Moskovchenko <stepanm@codeaurora.org>"); diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 50947ebb6d17..5c36a8b7656a 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -231,19 +231,3 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, return ops; } - -static int __init of_iommu_init(void) -{ - struct device_node *np; - const struct of_device_id *match, *matches = &__iommu_of_table; - - for_each_matching_node_and_match(np, matches, &match) { - const of_iommu_init_fn init_fn = match->data; - - if (init_fn && init_fn(np)) - pr_err("Failed to initialise IOMMU %pOF\n", np); - } - - return 0; -} -postcore_initcall_sync(of_iommu_init); diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index 505548aafeff..50217548c3b8 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -274,8 +274,8 @@ void omap_iommu_debugfs_add(struct omap_iommu *obj) if (!obj->debug_dir) return; - d = debugfs_create_u8("nr_tlb_entries", 0400, obj->debug_dir, - (u8 *)&obj->nr_tlb_entries); + d = debugfs_create_u32("nr_tlb_entries", 0400, obj->debug_dir, + &obj->nr_tlb_entries); if (!d) return; diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index e07f02d00c68..65b9c99707f8 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -947,7 +947,7 @@ static void __exit qcom_iommu_exit(void) module_init(qcom_iommu_init); module_exit(qcom_iommu_exit); -IOMMU_OF_DECLARE(qcom_iommu_dev, "qcom,msm-iommu-v1", NULL); +IOMMU_OF_DECLARE(qcom_iommu_dev, "qcom,msm-iommu-v1"); MODULE_DESCRIPTION("IOMMU API for QCOM IOMMU v1 implementations"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index e268811dc544..19cd93783c87 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -731,12 +731,12 @@ capi_poll(struct file *file, poll_table *wait) __poll_t mask = 0; if (!cdev->ap.applid) - return POLLERR; + return EPOLLERR; poll_wait(file, &(cdev->recvwait), wait); - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; if (!skb_queue_empty(&cdev->recvqueue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/isdn/divert/divert_procfs.c b/drivers/isdn/divert/divert_procfs.c index 34b7704042a4..342585e04fd3 100644 --- a/drivers/isdn/divert/divert_procfs.c +++ b/drivers/isdn/divert/divert_procfs.c @@ -125,9 +125,9 @@ isdn_divert_poll(struct file *file, poll_table *wait) __poll_t mask = 0; poll_wait(file, &(rd_queue), wait); - /* mask = POLLOUT | POLLWRNORM; */ + /* mask = EPOLLOUT | EPOLLWRNORM; */ if (*((struct divert_info **) file->private_data)) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } return mask; } /* isdn_divert_poll */ diff --git a/drivers/isdn/hardware/eicon/divamnt.c b/drivers/isdn/hardware/eicon/divamnt.c index 70f16102a001..5a95587b3117 100644 --- a/drivers/isdn/hardware/eicon/divamnt.c +++ b/drivers/isdn/hardware/eicon/divamnt.c @@ -103,9 +103,9 @@ static __poll_t maint_poll(struct file *file, poll_table *wait) __poll_t mask = 0; poll_wait(file, &msgwaitq, wait); - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; if (file->private_data || diva_dbg_q_length()) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } return (mask); } diff --git a/drivers/isdn/hardware/eicon/divasi.c b/drivers/isdn/hardware/eicon/divasi.c index da5cc5ab7e2d..525518c945fe 100644 --- a/drivers/isdn/hardware/eicon/divasi.c +++ b/drivers/isdn/hardware/eicon/divasi.c @@ -370,31 +370,31 @@ static __poll_t um_idi_poll(struct file *file, poll_table *wait) diva_um_idi_os_context_t *p_os; if (!file->private_data) { - return (POLLERR); + return (EPOLLERR); } if ((!(p_os = (diva_um_idi_os_context_t *) diva_um_id_get_os_context(file->private_data))) || p_os->aborted) { - return (POLLERR); + return (EPOLLERR); } poll_wait(file, &p_os->read_wait, wait); if (p_os->aborted) { - return (POLLERR); + return (EPOLLERR); } switch (diva_user_mode_idi_ind_ready(file->private_data, file)) { case (-1): - return (POLLERR); + return (EPOLLERR); case 0: return (0); } - return (POLLIN | POLLRDNORM); + return (EPOLLIN | EPOLLRDNORM); } static int um_idi_open(struct inode *inode, struct file *file) diff --git a/drivers/isdn/hardware/eicon/divasmain.c b/drivers/isdn/hardware/eicon/divasmain.c index fbc788e6f0db..b9980e84f9db 100644 --- a/drivers/isdn/hardware/eicon/divasmain.c +++ b/drivers/isdn/hardware/eicon/divasmain.c @@ -653,9 +653,9 @@ static ssize_t divas_read(struct file *file, char __user *buf, static __poll_t divas_poll(struct file *file, poll_table *wait) { if (!file->private_data) { - return (POLLERR); + return (EPOLLERR); } - return (POLLIN | POLLRDNORM); + return (EPOLLIN | EPOLLRDNORM); } static const struct file_operations divas_fops = { diff --git a/drivers/isdn/hardware/eicon/divasproc.c b/drivers/isdn/hardware/eicon/divasproc.c index 3478f6f099eb..f52f4622b10b 100644 --- a/drivers/isdn/hardware/eicon/divasproc.c +++ b/drivers/isdn/hardware/eicon/divasproc.c @@ -101,7 +101,7 @@ divas_write(struct file *file, const char __user *buf, size_t count, loff_t *off static __poll_t divas_poll(struct file *file, poll_table *wait) { - return (POLLERR); + return (EPOLLERR); } static int divas_open(struct inode *inode, struct file *file) diff --git a/drivers/isdn/hysdn/hysdn_proclog.c b/drivers/isdn/hysdn/hysdn_proclog.c index 6abea6915f49..6e898b90e86e 100644 --- a/drivers/isdn/hysdn/hysdn_proclog.c +++ b/drivers/isdn/hysdn/hysdn_proclog.c @@ -294,7 +294,7 @@ hysdn_log_poll(struct file *file, poll_table *wait) poll_wait(file, &(pd->rd_queue), wait); if (*((struct log_data **) file->private_data)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } /* hysdn_log_poll */ diff --git a/drivers/isdn/i4l/isdn_common.c b/drivers/isdn/i4l/isdn_common.c index 0521c32949d4..7c6f3f5d9d9a 100644 --- a/drivers/isdn/i4l/isdn_common.c +++ b/drivers/isdn/i4l/isdn_common.c @@ -1237,22 +1237,22 @@ isdn_poll(struct file *file, poll_table *wait) mutex_lock(&isdn_mutex); if (minor == ISDN_MINOR_STATUS) { poll_wait(file, &(dev->info_waitq), wait); - /* mask = POLLOUT | POLLWRNORM; */ + /* mask = EPOLLOUT | EPOLLWRNORM; */ if (file->private_data) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } goto out; } if (minor >= ISDN_MINOR_CTRL && minor <= ISDN_MINOR_CTRLMAX) { if (drvidx < 0) { /* driver deregistered while file open */ - mask = POLLHUP; + mask = EPOLLHUP; goto out; } poll_wait(file, &(dev->drv[drvidx]->st_waitq), wait); - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; if (dev->drv[drvidx]->stavail) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } goto out; } @@ -1262,7 +1262,7 @@ isdn_poll(struct file *file, poll_table *wait) goto out; } #endif - mask = POLLERR; + mask = EPOLLERR; out: mutex_unlock(&isdn_mutex); return mask; diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c index 57884319b4b1..a7b275ea5de1 100644 --- a/drivers/isdn/i4l/isdn_ppp.c +++ b/drivers/isdn/i4l/isdn_ppp.c @@ -704,12 +704,12 @@ isdn_ppp_poll(struct file *file, poll_table *wait) if (!(is->state & IPPP_OPEN)) { if (is->state == IPPP_CLOSEWAIT) - return POLLHUP; + return EPOLLHUP; printk(KERN_DEBUG "isdn_ppp: device not open\n"); - return POLLERR; + return EPOLLERR; } /* we're always ready to send .. */ - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; spin_lock_irqsave(&is->buflock, flags); bl = is->last; @@ -719,7 +719,7 @@ isdn_ppp_poll(struct file *file, poll_table *wait) */ if (bf->next != bl || (is->state & IPPP_NOBLOCK)) { is->state &= ~IPPP_NOBLOCK; - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } spin_unlock_irqrestore(&is->buflock, flags); return mask; diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index f4272d4e0a26..211ed6cffd10 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -145,7 +145,7 @@ static __poll_t mISDN_poll(struct file *filep, poll_table *wait) { struct mISDNtimerdev *dev = filep->private_data; - __poll_t mask = POLLERR; + __poll_t mask = EPOLLERR; if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s(%p, %p)\n", __func__, filep, wait); @@ -153,7 +153,7 @@ mISDN_poll(struct file *filep, poll_table *wait) poll_wait(filep, &dev->wait, wait); mask = 0; if (dev->work || !list_empty(&dev->expired)) - mask |= (POLLIN | POLLRDNORM); + mask |= (EPOLLIN | EPOLLRDNORM); if (*debug & DEBUG_TIMER) printk(KERN_DEBUG "%s work(%d) empty(%d)\n", __func__, dev->work, list_empty(&dev->expired)); diff --git a/drivers/leds/uleds.c b/drivers/leds/uleds.c index 5beacab05ed7..0c43bfac9598 100644 --- a/drivers/leds/uleds.c +++ b/drivers/leds/uleds.c @@ -183,7 +183,7 @@ static __poll_t uleds_poll(struct file *file, poll_table *wait) poll_wait(file, &udev->waitq, wait); if (udev->new_data) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 346e6f5f77be..e8ae2e54151c 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -1259,7 +1259,7 @@ static __poll_t smu_fpoll(struct file *file, poll_table *wait) spin_lock_irqsave(&pp->lock, flags); if (pp->busy && pp->cmd.status != 1) - mask |= POLLIN; + mask |= EPOLLIN; spin_unlock_irqrestore(&pp->lock, flags); } if (pp->mode == smu_file_events) { diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index 08849e33c567..94c0f3f7df69 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -2169,7 +2169,7 @@ pmu_fpoll(struct file *filp, poll_table *wait) poll_wait(filp, &pp->wait, wait); spin_lock_irqsave(&pp->lock, flags); if (pp->rb_get != pp->rb_put) - mask |= POLLIN; + mask |= EPOLLIN; spin_unlock_irqrestore(&pp->lock, flags); return mask; } diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index f84730d63b1f..58bfafc34bc4 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -243,7 +243,7 @@ mbox_test_message_poll(struct file *filp, struct poll_table_struct *wait) poll_wait(filp, &tdev->waitq, wait); if (mbox_test_message_data_ready(tdev)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 3f6791afd3e4..a89fd8f44453 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1937,7 +1937,7 @@ static __poll_t dm_poll(struct file *filp, poll_table *wait) poll_wait(filp, &dm_global_eventq, wait); if ((int)(atomic_read(&dm_global_event_nr) - priv->global_event_nr) > 0) - mask |= POLLIN; + mask |= EPOLLIN; return mask; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 0081ace39a64..bc67ab6844f0 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7891,14 +7891,14 @@ static __poll_t mdstat_poll(struct file *filp, poll_table *wait) __poll_t mask; if (md_unloading) - return POLLIN|POLLRDNORM|POLLERR|POLLPRI; + return EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; poll_wait(filp, &md_event_waiters, wait); /* always allow read */ - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; if (seq->poll_event != atomic_read(&md_event_count)) - mask |= POLLERR | POLLPRI; + mask |= EPOLLERR | EPOLLPRI; return mask; } diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c index ecc89d9a279b..492db12b8c4d 100644 --- a/drivers/media/cec/cec-api.c +++ b/drivers/media/cec/cec-api.c @@ -51,15 +51,15 @@ static __poll_t cec_poll(struct file *filp, __poll_t res = 0; if (!cec_is_registered(adap)) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; mutex_lock(&adap->lock); if (adap->is_configured && adap->transmit_queue_sz < CEC_MAX_MSG_TX_QUEUE_SZ) - res |= POLLOUT | POLLWRNORM; + res |= EPOLLOUT | EPOLLWRNORM; if (fh->queued_msgs) - res |= POLLIN | POLLRDNORM; + res |= EPOLLIN | EPOLLRDNORM; if (fh->total_queued_events) - res |= POLLPRI; + res |= EPOLLPRI; poll_wait(filp, &fh->wait, poll); mutex_unlock(&adap->lock); return res; diff --git a/drivers/media/common/saa7146/saa7146_fops.c b/drivers/media/common/saa7146/saa7146_fops.c index 8ee3eebef4db..d4987fd05d05 100644 --- a/drivers/media/common/saa7146/saa7146_fops.c +++ b/drivers/media/common/saa7146/saa7146_fops.c @@ -332,7 +332,7 @@ static __poll_t __fops_poll(struct file *file, struct poll_table_struct *wait) if (vdev->vfl_type == VFL_TYPE_VBI) { if (fh->dev->ext_vv_data->capabilities & V4L2_CAP_SLICED_VBI_OUTPUT) - return res | POLLOUT | POLLWRNORM; + return res | EPOLLOUT | EPOLLWRNORM; if( 0 == fh->vbi_q.streaming ) return res | videobuf_poll_stream(file, &fh->vbi_q, wait); q = &fh->vbi_q; @@ -346,13 +346,13 @@ static __poll_t __fops_poll(struct file *file, struct poll_table_struct *wait) if (!buf) { DEB_D("buf == NULL!\n"); - return res | POLLERR; + return res | EPOLLERR; } poll_wait(file, &buf->done, wait); if (buf->state == VIDEOBUF_DONE || buf->state == VIDEOBUF_ERROR) { DEB_D("poll succeeded!\n"); - return res | POLLIN | POLLRDNORM; + return res | EPOLLIN | EPOLLRDNORM; } DEB_D("nothing to poll for, buf->state:%d\n", buf->state); diff --git a/drivers/media/common/siano/smsdvb-debugfs.c b/drivers/media/common/siano/smsdvb-debugfs.c index 403645fe9079..40891f4f842b 100644 --- a/drivers/media/common/siano/smsdvb-debugfs.c +++ b/drivers/media/common/siano/smsdvb-debugfs.c @@ -371,7 +371,7 @@ static __poll_t smsdvb_stats_poll(struct file *file, poll_table *wait) rc = smsdvb_stats_wait_read(debug_data); kref_put(&debug_data->refcount, smsdvb_debugfs_data_release); - return rc > 0 ? POLLIN | POLLRDNORM : 0; + return rc > 0 ? EPOLLIN | EPOLLRDNORM : 0; } static ssize_t smsdvb_stats_read(struct file *file, char __user *user_buf, diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 9a84c7092714..debe35fc66b4 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -2038,9 +2038,9 @@ __poll_t vb2_core_poll(struct vb2_queue *q, struct file *file, struct vb2_buffer *vb = NULL; unsigned long flags; - if (!q->is_output && !(req_events & (POLLIN | POLLRDNORM))) + if (!q->is_output && !(req_events & (EPOLLIN | EPOLLRDNORM))) return 0; - if (q->is_output && !(req_events & (POLLOUT | POLLWRNORM))) + if (q->is_output && !(req_events & (EPOLLOUT | EPOLLWRNORM))) return 0; /* @@ -2048,18 +2048,18 @@ __poll_t vb2_core_poll(struct vb2_queue *q, struct file *file, */ if (q->num_buffers == 0 && !vb2_fileio_is_active(q)) { if (!q->is_output && (q->io_modes & VB2_READ) && - (req_events & (POLLIN | POLLRDNORM))) { + (req_events & (EPOLLIN | EPOLLRDNORM))) { if (__vb2_init_fileio(q, 1)) - return POLLERR; + return EPOLLERR; } if (q->is_output && (q->io_modes & VB2_WRITE) && - (req_events & (POLLOUT | POLLWRNORM))) { + (req_events & (EPOLLOUT | EPOLLWRNORM))) { if (__vb2_init_fileio(q, 0)) - return POLLERR; + return EPOLLERR; /* * Write to OUTPUT queue can be done immediately. */ - return POLLOUT | POLLWRNORM; + return EPOLLOUT | EPOLLWRNORM; } } @@ -2068,24 +2068,24 @@ __poll_t vb2_core_poll(struct vb2_queue *q, struct file *file, * error flag is set. */ if (!vb2_is_streaming(q) || q->error) - return POLLERR; + return EPOLLERR; /* * If this quirk is set and QBUF hasn't been called yet then - * return POLLERR as well. This only affects capture queues, output + * return EPOLLERR as well. This only affects capture queues, output * queues will always initialize waiting_for_buffers to false. * This quirk is set by V4L2 for backwards compatibility reasons. */ if (q->quirk_poll_must_check_waiting_for_buffers && - q->waiting_for_buffers && (req_events & (POLLIN | POLLRDNORM))) - return POLLERR; + q->waiting_for_buffers && (req_events & (EPOLLIN | EPOLLRDNORM))) + return EPOLLERR; /* * For output streams you can call write() as long as there are fewer * buffers queued than there are buffers available. */ if (q->is_output && q->fileio && q->queued_count < q->num_buffers) - return POLLOUT | POLLWRNORM; + return EPOLLOUT | EPOLLWRNORM; if (list_empty(&q->done_list)) { /* @@ -2093,7 +2093,7 @@ __poll_t vb2_core_poll(struct vb2_queue *q, struct file *file, * return immediately. DQBUF will return -EPIPE. */ if (q->last_buffer_dequeued) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; poll_wait(file, &q->done_wq, wait); } @@ -2110,8 +2110,8 @@ __poll_t vb2_core_poll(struct vb2_queue *q, struct file *file, if (vb && (vb->state == VB2_BUF_STATE_DONE || vb->state == VB2_BUF_STATE_ERROR)) { return (q->is_output) ? - POLLOUT | POLLWRNORM : - POLLIN | POLLRDNORM; + EPOLLOUT | EPOLLWRNORM : + EPOLLIN | EPOLLRDNORM; } return 0; } diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index d9a487aab99c..886a2d8d5c6c 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -658,7 +658,7 @@ int vb2_queue_init(struct vb2_queue *q) == V4L2_BUF_FLAG_TIMESTAMP_COPY; /* * For compatibility with vb1: if QBUF hasn't been called yet, then - * return POLLERR as well. This only affects capture queues, output + * return EPOLLERR as well. This only affects capture queues, output * queues will always initialize waiting_for_buffers to false. */ q->quirk_poll_must_check_waiting_for_buffers = true; @@ -683,8 +683,8 @@ __poll_t vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait) struct v4l2_fh *fh = file->private_data; if (v4l2_event_pending(fh)) - res = POLLPRI; - else if (req_events & POLLPRI) + res = EPOLLPRI; + else if (req_events & EPOLLPRI) poll_wait(file, &fh->wait, wait); } @@ -921,7 +921,7 @@ __poll_t vb2_fop_poll(struct file *file, poll_table *wait) WARN_ON(!lock); if (lock && mutex_lock_interruptible(lock)) - return POLLERR; + return EPOLLERR; fileio = q->fileio; diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c index bc198f84b9cd..6d53af00190e 100644 --- a/drivers/media/dvb-core/dmxdev.c +++ b/drivers/media/dvb-core/dmxdev.c @@ -1179,7 +1179,7 @@ static __poll_t dvb_demux_poll(struct file *file, poll_table *wait) __poll_t mask = 0; if ((!dmxdevfilter) || dmxdevfilter->dev->exit) - return POLLERR; + return EPOLLERR; if (dvb_vb2_is_streaming(&dmxdevfilter->vb2_ctx)) return dvb_vb2_poll(&dmxdevfilter->vb2_ctx, file, wait); @@ -1191,10 +1191,10 @@ static __poll_t dvb_demux_poll(struct file *file, poll_table *wait) return 0; if (dmxdevfilter->buffer.error) - mask |= (POLLIN | POLLRDNORM | POLLPRI | POLLERR); + mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI | EPOLLERR); if (!dvb_ringbuffer_empty(&dmxdevfilter->buffer)) - mask |= (POLLIN | POLLRDNORM | POLLPRI); + mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI); return mask; } @@ -1331,7 +1331,7 @@ static __poll_t dvb_dvr_poll(struct file *file, poll_table *wait) dprintk("%s\n", __func__); if (dmxdev->exit) - return POLLERR; + return EPOLLERR; if (dvb_vb2_is_streaming(&dmxdev->dvr_vb2_ctx)) return dvb_vb2_poll(&dmxdev->dvr_vb2_ctx, file, wait); @@ -1343,12 +1343,12 @@ static __poll_t dvb_dvr_poll(struct file *file, poll_table *wait) #endif if (need_ringbuffer) { if (dmxdev->dvr_buffer.error) - mask |= (POLLIN | POLLRDNORM | POLLPRI | POLLERR); + mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI | EPOLLERR); if (!dvb_ringbuffer_empty(&dmxdev->dvr_buffer)) - mask |= (POLLIN | POLLRDNORM | POLLPRI); + mask |= (EPOLLIN | EPOLLRDNORM | EPOLLPRI); } else - mask |= (POLLOUT | POLLWRNORM | POLLPRI); + mask |= (EPOLLOUT | EPOLLWRNORM | EPOLLPRI); return mask; } diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index b462ebc0c544..204d0f6c678d 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -1796,7 +1796,7 @@ static __poll_t dvb_ca_en50221_io_poll(struct file *file, poll_table *wait) dprintk("%s\n", __func__); if (dvb_ca_en50221_io_read_condition(ca, &result, &slot) == 1) - mask |= POLLIN; + mask |= EPOLLIN; /* if there is something, return now */ if (mask) @@ -1806,7 +1806,7 @@ static __poll_t dvb_ca_en50221_io_poll(struct file *file, poll_table *wait) poll_wait(file, &ca->wait_queue, wait); if (dvb_ca_en50221_io_read_condition(ca, &result, &slot) == 1) - mask |= POLLIN; + mask |= EPOLLIN; return mask; } diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 87fc1bcae5ae..a7ed16e0841d 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -2646,7 +2646,7 @@ static __poll_t dvb_frontend_poll(struct file *file, struct poll_table_struct *w poll_wait (file, &fepriv->events.wait_queue, wait); if (fepriv->events.eventw != fepriv->events.eventr) - return (POLLIN | POLLRDNORM | POLLPRI); + return (EPOLLIN | EPOLLRDNORM | EPOLLPRI); return 0; } diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c index 889abf9becd8..763145d74e83 100644 --- a/drivers/media/dvb-core/dvb_vb2.c +++ b/drivers/media/dvb-core/dvb_vb2.c @@ -421,8 +421,8 @@ int dvb_vb2_mmap(struct dvb_vb2_ctx *ctx, struct vm_area_struct *vma) return 0; } -unsigned int dvb_vb2_poll(struct dvb_vb2_ctx *ctx, struct file *file, - poll_table *wait) +__poll_t dvb_vb2_poll(struct dvb_vb2_ctx *ctx, struct file *file, + poll_table *wait) { dprintk(3, "[%s]\n", ctx->name); return vb2_core_poll(&ctx->vb_q, file, wait); diff --git a/drivers/media/firewire/firedtv-ci.c b/drivers/media/firewire/firedtv-ci.c index b4ddfff74267..8dc5a7495abe 100644 --- a/drivers/media/firewire/firedtv-ci.c +++ b/drivers/media/firewire/firedtv-ci.c @@ -209,7 +209,7 @@ static int fdtv_ca_ioctl(struct file *file, unsigned int cmd, void *arg) static __poll_t fdtv_ca_io_poll(struct file *file, poll_table *wait) { - return POLLIN; + return EPOLLIN; } static const struct file_operations fdtv_ca_fops = { diff --git a/drivers/media/i2c/saa6588.c b/drivers/media/i2c/saa6588.c index 00640233a5e3..c3089bd34df2 100644 --- a/drivers/media/i2c/saa6588.c +++ b/drivers/media/i2c/saa6588.c @@ -413,7 +413,7 @@ static long saa6588_ioctl(struct v4l2_subdev *sd, unsigned int cmd, void *arg) case SAA6588_CMD_POLL: a->result = 0; if (s->data_available_for_read) - a->result |= POLLIN | POLLRDNORM; + a->result |= EPOLLIN | EPOLLRDNORM; poll_wait(a->instance, &s->read_queue, a->event_list); break; diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c index 3049b1f505e5..67ac51eff15c 100644 --- a/drivers/media/media-devnode.c +++ b/drivers/media/media-devnode.c @@ -105,7 +105,7 @@ static __poll_t media_poll(struct file *filp, struct media_devnode *devnode = media_devnode_data(filp); if (!media_devnode_is_registered(devnode)) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; if (!devnode->fops->poll) return DEFAULT_POLLMASK; return devnode->fops->poll(filp, poll); diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c index c988669e22ff..f697698fe38d 100644 --- a/drivers/media/pci/bt8xx/bttv-driver.c +++ b/drivers/media/pci/bt8xx/bttv-driver.c @@ -2964,39 +2964,39 @@ static __poll_t bttv_poll(struct file *file, poll_table *wait) __poll_t req_events = poll_requested_events(wait); if (v4l2_event_pending(&fh->fh)) - rc = POLLPRI; - else if (req_events & POLLPRI) + rc = EPOLLPRI; + else if (req_events & EPOLLPRI) poll_wait(file, &fh->fh.wait, wait); - if (!(req_events & (POLLIN | POLLRDNORM))) + if (!(req_events & (EPOLLIN | EPOLLRDNORM))) return rc; if (V4L2_BUF_TYPE_VBI_CAPTURE == fh->type) { if (!check_alloc_btres_lock(fh->btv,fh,RESOURCE_VBI)) - return rc | POLLERR; + return rc | EPOLLERR; return rc | videobuf_poll_stream(file, &fh->vbi, wait); } if (check_btres(fh,RESOURCE_VIDEO_STREAM)) { /* streaming capture */ if (list_empty(&fh->cap.stream)) - return rc | POLLERR; + return rc | EPOLLERR; buf = list_entry(fh->cap.stream.next,struct bttv_buffer,vb.stream); } else { /* read() capture */ if (NULL == fh->cap.read_buf) { /* need to capture a new frame */ if (locked_btres(fh->btv,RESOURCE_VIDEO_STREAM)) - return rc | POLLERR; + return rc | EPOLLERR; fh->cap.read_buf = videobuf_sg_alloc(fh->cap.msize); if (NULL == fh->cap.read_buf) - return rc | POLLERR; + return rc | EPOLLERR; fh->cap.read_buf->memory = V4L2_MEMORY_USERPTR; field = videobuf_next_field(&fh->cap); if (0 != fh->cap.ops->buf_prepare(&fh->cap,fh->cap.read_buf,field)) { kfree (fh->cap.read_buf); fh->cap.read_buf = NULL; - return rc | POLLERR; + return rc | EPOLLERR; } fh->cap.ops->buf_queue(&fh->cap,fh->cap.read_buf); fh->cap.read_off = 0; @@ -3007,7 +3007,7 @@ static __poll_t bttv_poll(struct file *file, poll_table *wait) poll_wait(file, &buf->vb.done, wait); if (buf->vb.state == VIDEOBUF_DONE || buf->vb.state == VIDEOBUF_ERROR) - rc = rc | POLLIN|POLLRDNORM; + rc = rc | EPOLLIN|EPOLLRDNORM; return rc; } @@ -3338,8 +3338,8 @@ static __poll_t radio_poll(struct file *file, poll_table *wait) __poll_t res = 0; if (v4l2_event_pending(&fh->fh)) - res = POLLPRI; - else if (req_events & POLLPRI) + res = EPOLLPRI; + else if (req_events & EPOLLPRI) poll_wait(file, &fh->fh.wait, wait); radio_enable(btv); cmd.instance = file; diff --git a/drivers/media/pci/cx18/cx18-fileops.c b/drivers/media/pci/cx18/cx18-fileops.c index a8dbb922ba4b..a3f44e30f821 100644 --- a/drivers/media/pci/cx18/cx18-fileops.c +++ b/drivers/media/pci/cx18/cx18-fileops.c @@ -613,7 +613,7 @@ __poll_t cx18_v4l2_enc_poll(struct file *filp, poll_table *wait) /* Start a capture if there is none */ if (!eof && !test_bit(CX18_F_S_STREAMING, &s->s_flags) && - (req_events & (POLLIN | POLLRDNORM))) { + (req_events & (EPOLLIN | EPOLLRDNORM))) { int rc; mutex_lock(&cx->serialize_lock); @@ -622,7 +622,7 @@ __poll_t cx18_v4l2_enc_poll(struct file *filp, poll_table *wait) if (rc) { CX18_DEBUG_INFO("Could not start capture for %s (%d)\n", s->name, rc); - return POLLERR; + return EPOLLERR; } CX18_DEBUG_FILE("Encoder poll started capture\n"); } @@ -632,23 +632,23 @@ __poll_t cx18_v4l2_enc_poll(struct file *filp, poll_table *wait) __poll_t videobuf_poll = videobuf_poll_stream(filp, &s->vbuf_q, wait); if (v4l2_event_pending(&id->fh)) - res |= POLLPRI; - if (eof && videobuf_poll == POLLERR) - return res | POLLHUP; + res |= EPOLLPRI; + if (eof && videobuf_poll == EPOLLERR) + return res | EPOLLHUP; return res | videobuf_poll; } /* add stream's waitq to the poll list */ CX18_DEBUG_HI_FILE("Encoder poll\n"); if (v4l2_event_pending(&id->fh)) - res |= POLLPRI; + res |= EPOLLPRI; else poll_wait(filp, &s->waitq, wait); if (atomic_read(&s->q_full.depth)) - return res | POLLIN | POLLRDNORM; + return res | EPOLLIN | EPOLLRDNORM; if (eof) - return res | POLLHUP; + return res | EPOLLHUP; return res; } diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c index 42b42824382c..f9bee36f1cad 100644 --- a/drivers/media/pci/ddbridge/ddbridge-core.c +++ b/drivers/media/pci/ddbridge/ddbridge-core.c @@ -745,9 +745,9 @@ static __poll_t ts_poll(struct file *file, poll_table *wait) poll_wait(file, &input->dma->wq, wait); poll_wait(file, &output->dma->wq, wait); if (ddb_input_avail(input) >= 188) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (ddb_output_free(output) >= 188) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/drivers/media/pci/ivtv/ivtv-fileops.c b/drivers/media/pci/ivtv/ivtv-fileops.c index 4aa773507201..6196daae4b3e 100644 --- a/drivers/media/pci/ivtv/ivtv-fileops.c +++ b/drivers/media/pci/ivtv/ivtv-fileops.c @@ -747,7 +747,7 @@ __poll_t ivtv_v4l2_dec_poll(struct file *filp, poll_table *wait) /* Turn off the old-style vsync events */ clear_bit(IVTV_F_I_EV_VSYNC_ENABLED, &itv->i_flags); if (v4l2_event_pending(&id->fh)) - res = POLLPRI; + res = EPOLLPRI; } else { /* This is the old-style API which is here only for backwards compatibility. */ @@ -755,12 +755,12 @@ __poll_t ivtv_v4l2_dec_poll(struct file *filp, poll_table *wait) set_bit(IVTV_F_I_EV_VSYNC_ENABLED, &itv->i_flags); if (test_bit(IVTV_F_I_EV_VSYNC, &itv->i_flags) || test_bit(IVTV_F_I_EV_DEC_STOPPED, &itv->i_flags)) - res = POLLPRI; + res = EPOLLPRI; } /* Allow write if buffers are available for writing */ if (s->q_free.buffers) - res |= POLLOUT | POLLWRNORM; + res |= EPOLLOUT | EPOLLWRNORM; return res; } @@ -776,7 +776,7 @@ __poll_t ivtv_v4l2_enc_poll(struct file *filp, poll_table *wait) /* Start a capture if there is none */ if (!eof && !test_bit(IVTV_F_S_STREAMING, &s->s_flags) && s->type != IVTV_ENC_STREAM_TYPE_RAD && - (req_events & (POLLIN | POLLRDNORM))) { + (req_events & (EPOLLIN | EPOLLRDNORM))) { int rc; mutex_lock(&itv->serialize_lock); @@ -785,7 +785,7 @@ __poll_t ivtv_v4l2_enc_poll(struct file *filp, poll_table *wait) if (rc) { IVTV_DEBUG_INFO("Could not start capture for %s (%d)\n", s->name, rc); - return POLLERR; + return EPOLLERR; } IVTV_DEBUG_FILE("Encoder poll started capture\n"); } @@ -794,14 +794,14 @@ __poll_t ivtv_v4l2_enc_poll(struct file *filp, poll_table *wait) IVTV_DEBUG_HI_FILE("Encoder poll\n"); poll_wait(filp, &s->waitq, wait); if (v4l2_event_pending(&id->fh)) - res |= POLLPRI; + res |= EPOLLPRI; else poll_wait(filp, &id->fh.wait, wait); if (s->q_full.length || s->q_io.length) - return res | POLLIN | POLLRDNORM; + return res | EPOLLIN | EPOLLRDNORM; if (eof) - return res | POLLHUP; + return res | EPOLLHUP; return res; } diff --git a/drivers/media/pci/meye/meye.c b/drivers/media/pci/meye/meye.c index ae83293723ba..dedcdb573427 100644 --- a/drivers/media/pci/meye/meye.c +++ b/drivers/media/pci/meye/meye.c @@ -1430,7 +1430,7 @@ static __poll_t meye_poll(struct file *file, poll_table *wait) mutex_lock(&meye.lock); poll_wait(file, &meye.proc_list, wait); if (kfifo_len(&meye.doneq)) - res |= POLLIN | POLLRDNORM; + res |= EPOLLIN | EPOLLRDNORM; mutex_unlock(&meye.lock); return res; } diff --git a/drivers/media/pci/saa7164/saa7164-encoder.c b/drivers/media/pci/saa7164/saa7164-encoder.c index e7b31a5b14fd..32136ebe4f61 100644 --- a/drivers/media/pci/saa7164/saa7164-encoder.c +++ b/drivers/media/pci/saa7164/saa7164-encoder.c @@ -925,13 +925,13 @@ static __poll_t fops_poll(struct file *file, poll_table *wait) saa7164_histogram_update(&port->poll_interval, port->last_poll_msecs_diff); - if (!(req_events & (POLLIN | POLLRDNORM))) + if (!(req_events & (EPOLLIN | EPOLLRDNORM))) return mask; if (atomic_cmpxchg(&fh->v4l_reading, 0, 1) == 0) { if (atomic_inc_return(&port->v4l_reader_count) == 1) { if (saa7164_encoder_initialize(port) < 0) - return mask | POLLERR; + return mask | EPOLLERR; saa7164_encoder_start_streaming(port); msleep(200); } @@ -939,7 +939,7 @@ static __poll_t fops_poll(struct file *file, poll_table *wait) /* Pull the first buffer from the used list */ if (!list_empty(&port->list_buf_used.list)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/media/pci/saa7164/saa7164-vbi.c b/drivers/media/pci/saa7164/saa7164-vbi.c index 6f97c8f2e00d..64ab91c24c18 100644 --- a/drivers/media/pci/saa7164/saa7164-vbi.c +++ b/drivers/media/pci/saa7164/saa7164-vbi.c @@ -650,7 +650,7 @@ static __poll_t fops_poll(struct file *file, poll_table *wait) /* Pull the first buffer from the used list */ if (!list_empty(&port->list_buf_used.list)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/media/pci/ttpci/av7110_av.c b/drivers/media/pci/ttpci/av7110_av.c index 4d10e2f979d2..4daba76ec240 100644 --- a/drivers/media/pci/ttpci/av7110_av.c +++ b/drivers/media/pci/ttpci/av7110_av.c @@ -951,15 +951,15 @@ static __poll_t dvb_video_poll(struct file *file, poll_table *wait) poll_wait(file, &av7110->video_events.wait_queue, wait); if (av7110->video_events.eventw != av7110->video_events.eventr) - mask = POLLPRI; + mask = EPOLLPRI; if ((file->f_flags & O_ACCMODE) != O_RDONLY) { if (av7110->playing) { if (FREE_COND) - mask |= (POLLOUT | POLLWRNORM); + mask |= (EPOLLOUT | EPOLLWRNORM); } else { /* if not playing: may play if asked for */ - mask |= (POLLOUT | POLLWRNORM); + mask |= (EPOLLOUT | EPOLLWRNORM); } } @@ -1001,9 +1001,9 @@ static __poll_t dvb_audio_poll(struct file *file, poll_table *wait) if (av7110->playing) { if (dvb_ringbuffer_free(&av7110->aout) >= 20 * 1024) - mask |= (POLLOUT | POLLWRNORM); + mask |= (EPOLLOUT | EPOLLWRNORM); } else /* if not playing: may play if asked for */ - mask = (POLLOUT | POLLWRNORM); + mask = (EPOLLOUT | EPOLLWRNORM); return mask; } diff --git a/drivers/media/pci/ttpci/av7110_ca.c b/drivers/media/pci/ttpci/av7110_ca.c index 96ca227cf51b..d8c2f1b34d74 100644 --- a/drivers/media/pci/ttpci/av7110_ca.c +++ b/drivers/media/pci/ttpci/av7110_ca.c @@ -237,10 +237,10 @@ static __poll_t dvb_ca_poll (struct file *file, poll_table *wait) poll_wait(file, &wbuf->queue, wait); if (!dvb_ringbuffer_empty(rbuf)) - mask |= (POLLIN | POLLRDNORM); + mask |= (EPOLLIN | EPOLLRDNORM); if (dvb_ringbuffer_free(wbuf) > 1024) - mask |= (POLLOUT | POLLWRNORM); + mask |= (EPOLLOUT | EPOLLWRNORM); return mask; } diff --git a/drivers/media/pci/zoran/zoran_driver.c b/drivers/media/pci/zoran/zoran_driver.c index c464dae0389c..8d4e7d930a66 100644 --- a/drivers/media/pci/zoran/zoran_driver.c +++ b/drivers/media/pci/zoran/zoran_driver.c @@ -2513,10 +2513,10 @@ zoran_poll (struct file *file, /* we should check whether buffers are ready to be synced on * (w/o waits - O_NONBLOCK) here - * if ready for read (sync), return POLLIN|POLLRDNORM, - * if ready for write (sync), return POLLOUT|POLLWRNORM, - * if error, return POLLERR, - * if no buffers queued or so, return POLLNVAL + * if ready for read (sync), return EPOLLIN|EPOLLRDNORM, + * if ready for write (sync), return EPOLLOUT|EPOLLWRNORM, + * if error, return EPOLLERR, + * if no buffers queued or so, return EPOLLNVAL */ switch (fh->map_mode) { @@ -2536,7 +2536,7 @@ zoran_poll (struct file *file, if (fh->buffers.active != ZORAN_FREE && /* Buffer ready to DQBUF? */ zr->v4l_buffers.buffer[frame].state == BUZ_STATE_DONE) - res |= POLLIN | POLLRDNORM; + res |= EPOLLIN | EPOLLRDNORM; spin_unlock_irqrestore(&zr->spinlock, flags); break; @@ -2557,9 +2557,9 @@ zoran_poll (struct file *file, if (fh->buffers.active != ZORAN_FREE && zr->jpg_buffers.buffer[frame].state == BUZ_STATE_DONE) { if (fh->map_mode == ZORAN_MAP_MODE_JPG_REC) - res |= POLLIN | POLLRDNORM; + res |= EPOLLIN | EPOLLRDNORM; else - res |= POLLOUT | POLLWRNORM; + res |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_irqrestore(&zr->spinlock, flags); @@ -2570,7 +2570,7 @@ zoran_poll (struct file *file, KERN_ERR "%s: %s - internal error, unknown map_mode=%d\n", ZR_DEVNAME(zr), __func__, fh->map_mode); - res |= POLLERR; + res |= EPOLLERR; } return res; diff --git a/drivers/media/platform/fsl-viu.c b/drivers/media/platform/fsl-viu.c index de285a269390..200c47c69a75 100644 --- a/drivers/media/platform/fsl-viu.c +++ b/drivers/media/platform/fsl-viu.c @@ -1272,9 +1272,9 @@ static __poll_t viu_poll(struct file *file, struct poll_table_struct *wait) __poll_t res = v4l2_ctrl_poll(file, wait); if (V4L2_BUF_TYPE_VIDEO_CAPTURE != fh->type) - return POLLERR; + return EPOLLERR; - if (!(req_events & (POLLIN | POLLRDNORM))) + if (!(req_events & (EPOLLIN | EPOLLRDNORM))) return res; mutex_lock(&dev->lock); diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c index f15cf24c1c63..d5b94fc0040e 100644 --- a/drivers/media/platform/s5p-mfc/s5p_mfc.c +++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c @@ -1008,7 +1008,7 @@ static __poll_t s5p_mfc_poll(struct file *file, */ if ((!src_q->streaming || list_empty(&src_q->queued_list)) && (!dst_q->streaming || list_empty(&dst_q->queued_list))) { - rc = POLLERR; + rc = EPOLLERR; goto end; } mutex_unlock(&dev->mfc_mutex); @@ -1017,14 +1017,14 @@ static __poll_t s5p_mfc_poll(struct file *file, poll_wait(file, &dst_q->done_wq, wait); mutex_lock(&dev->mfc_mutex); if (v4l2_event_pending(&ctx->fh)) - rc |= POLLPRI; + rc |= EPOLLPRI; spin_lock_irqsave(&src_q->done_lock, flags); if (!list_empty(&src_q->done_list)) src_vb = list_first_entry(&src_q->done_list, struct vb2_buffer, done_entry); if (src_vb && (src_vb->state == VB2_BUF_STATE_DONE || src_vb->state == VB2_BUF_STATE_ERROR)) - rc |= POLLOUT | POLLWRNORM; + rc |= EPOLLOUT | EPOLLWRNORM; spin_unlock_irqrestore(&src_q->done_lock, flags); spin_lock_irqsave(&dst_q->done_lock, flags); if (!list_empty(&dst_q->done_list)) @@ -1032,7 +1032,7 @@ static __poll_t s5p_mfc_poll(struct file *file, done_entry); if (dst_vb && (dst_vb->state == VB2_BUF_STATE_DONE || dst_vb->state == VB2_BUF_STATE_ERROR)) - rc |= POLLIN | POLLRDNORM; + rc |= EPOLLIN | EPOLLRDNORM; spin_unlock_irqrestore(&dst_q->done_lock, flags); end: mutex_unlock(&dev->mfc_mutex); diff --git a/drivers/media/platform/soc_camera/soc_camera.c b/drivers/media/platform/soc_camera/soc_camera.c index 70fc5f01942d..c86dd2fdab84 100644 --- a/drivers/media/platform/soc_camera/soc_camera.c +++ b/drivers/media/platform/soc_camera/soc_camera.c @@ -809,10 +809,10 @@ static __poll_t soc_camera_poll(struct file *file, poll_table *pt) { struct soc_camera_device *icd = file->private_data; struct soc_camera_host *ici = to_soc_camera_host(icd->parent); - __poll_t res = POLLERR; + __poll_t res = EPOLLERR; if (icd->streamer != file) - return POLLERR; + return EPOLLERR; mutex_lock(&ici->host_lock); res = ici->ops->poll(file, pt); diff --git a/drivers/media/platform/vivid/vivid-radio-rx.c b/drivers/media/platform/vivid/vivid-radio-rx.c index fcb7a9f015b6..f834f7df8cf9 100644 --- a/drivers/media/platform/vivid/vivid-radio-rx.c +++ b/drivers/media/platform/vivid/vivid-radio-rx.c @@ -142,7 +142,7 @@ retry: __poll_t vivid_radio_rx_poll(struct file *file, struct poll_table_struct *wait) { - return POLLIN | POLLRDNORM | v4l2_ctrl_poll(file, wait); + return EPOLLIN | EPOLLRDNORM | v4l2_ctrl_poll(file, wait); } int vivid_radio_rx_enum_freq_bands(struct file *file, void *fh, struct v4l2_frequency_band *band) diff --git a/drivers/media/platform/vivid/vivid-radio-tx.c b/drivers/media/platform/vivid/vivid-radio-tx.c index af4907a197a3..308b13f85dc0 100644 --- a/drivers/media/platform/vivid/vivid-radio-tx.c +++ b/drivers/media/platform/vivid/vivid-radio-tx.c @@ -105,7 +105,7 @@ retry: __poll_t vivid_radio_tx_poll(struct file *file, struct poll_table_struct *wait) { - return POLLOUT | POLLWRNORM | v4l2_ctrl_poll(file, wait); + return EPOLLOUT | EPOLLWRNORM | v4l2_ctrl_poll(file, wait); } int vidioc_g_modulator(struct file *file, void *fh, struct v4l2_modulator *a) diff --git a/drivers/media/radio/radio-cadet.c b/drivers/media/radio/radio-cadet.c index af7c68b344d1..5b82e63885cd 100644 --- a/drivers/media/radio/radio-cadet.c +++ b/drivers/media/radio/radio-cadet.c @@ -488,14 +488,14 @@ static __poll_t cadet_poll(struct file *file, struct poll_table_struct *wait) __poll_t res = v4l2_ctrl_poll(file, wait); poll_wait(file, &dev->read_queue, wait); - if (dev->rdsstat == 0 && (req_events & (POLLIN | POLLRDNORM))) { + if (dev->rdsstat == 0 && (req_events & (EPOLLIN | EPOLLRDNORM))) { mutex_lock(&dev->lock); if (dev->rdsstat == 0) cadet_start_rds(dev); mutex_unlock(&dev->lock); } if (cadet_has_rds_data(dev)) - res |= POLLIN | POLLRDNORM; + res |= EPOLLIN | EPOLLRDNORM; return res; } diff --git a/drivers/media/radio/radio-si476x.c b/drivers/media/radio/radio-si476x.c index bff9789ae9bc..b52e678c6901 100644 --- a/drivers/media/radio/radio-si476x.c +++ b/drivers/media/radio/radio-si476x.c @@ -1158,15 +1158,15 @@ static __poll_t si476x_radio_fops_poll(struct file *file, __poll_t req_events = poll_requested_events(pts); __poll_t err = v4l2_ctrl_poll(file, pts); - if (req_events & (POLLIN | POLLRDNORM)) { + if (req_events & (EPOLLIN | EPOLLRDNORM)) { if (atomic_read(&radio->core->is_alive)) poll_wait(file, &radio->core->rds_read_queue, pts); if (!atomic_read(&radio->core->is_alive)) - err = POLLHUP; + err = EPOLLHUP; if (!kfifo_is_empty(&radio->core->rds_fifo)) - err = POLLIN | POLLRDNORM; + err = EPOLLIN | EPOLLRDNORM; } return err; diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c index f92b0f9241a9..58e944591602 100644 --- a/drivers/media/radio/radio-wl1273.c +++ b/drivers/media/radio/radio-wl1273.c @@ -1104,10 +1104,10 @@ static __poll_t wl1273_fm_fops_poll(struct file *file, poll_wait(file, &radio->read_queue, pts); if (radio->rd_index != radio->wr_index) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } else if (core->mode == WL1273_MODE_TX) { - return POLLOUT | POLLWRNORM; + return EPOLLOUT | EPOLLWRNORM; } return 0; diff --git a/drivers/media/radio/si470x/radio-si470x-common.c b/drivers/media/radio/si470x/radio-si470x-common.c index 5b477b7d6a66..e0054e0f410d 100644 --- a/drivers/media/radio/si470x/radio-si470x-common.c +++ b/drivers/media/radio/si470x/radio-si470x-common.c @@ -514,7 +514,7 @@ static __poll_t si470x_fops_poll(struct file *file, __poll_t req_events = poll_requested_events(pts); __poll_t retval = v4l2_ctrl_poll(file, pts); - if (req_events & (POLLIN | POLLRDNORM)) { + if (req_events & (EPOLLIN | EPOLLRDNORM)) { /* switch on rds reception */ if ((radio->registers[SYSCONFIG1] & SYSCONFIG1_RDS) == 0) si470x_rds_on(radio); @@ -522,7 +522,7 @@ static __poll_t si470x_fops_poll(struct file *file, poll_wait(file, &radio->read_queue, pts); if (radio->rd_index != radio->wr_index) - retval |= POLLIN | POLLRDNORM; + retval |= EPOLLIN | EPOLLRDNORM; } return retval; diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.c b/drivers/media/radio/wl128x/fmdrv_v4l2.c index fd603c1b96bb..dccdf6558e6a 100644 --- a/drivers/media/radio/wl128x/fmdrv_v4l2.c +++ b/drivers/media/radio/wl128x/fmdrv_v4l2.c @@ -112,7 +112,7 @@ static __poll_t fm_v4l2_fops_poll(struct file *file, struct poll_table_struct *p ret = fmc_is_rds_data_available(fmdev, file, pts); mutex_unlock(&fmdev->mutex); if (ret < 0) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index b3544988586e..cc863044c880 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -109,7 +109,7 @@ void ir_lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev) if (LIRC_IS_TIMEOUT(sample) && !fh->send_timeout_reports) continue; if (kfifo_put(&fh->rawir, sample)) - wake_up_poll(&fh->wait_poll, POLLIN | POLLRDNORM); + wake_up_poll(&fh->wait_poll, EPOLLIN | EPOLLRDNORM); } spin_unlock_irqrestore(&dev->lirc_fh_lock, flags); } @@ -130,7 +130,7 @@ void ir_lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc) spin_lock_irqsave(&dev->lirc_fh_lock, flags); list_for_each_entry(fh, &dev->lirc_fh, list) { if (kfifo_put(&fh->scancodes, *lsc)) - wake_up_poll(&fh->wait_poll, POLLIN | POLLRDNORM); + wake_up_poll(&fh->wait_poll, EPOLLIN | EPOLLRDNORM); } spin_unlock_irqrestore(&dev->lirc_fh_lock, flags); } @@ -603,15 +603,15 @@ static __poll_t ir_lirc_poll(struct file *file, struct poll_table_struct *wait) poll_wait(file, &fh->wait_poll, wait); if (!rcdev->registered) { - events = POLLHUP | POLLERR; + events = EPOLLHUP | EPOLLERR; } else if (rcdev->driver_type != RC_DRIVER_IR_RAW_TX) { if (fh->rec_mode == LIRC_MODE_SCANCODE && !kfifo_is_empty(&fh->scancodes)) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; if (fh->rec_mode == LIRC_MODE_MODE2 && !kfifo_is_empty(&fh->rawir)) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; } return events; @@ -779,7 +779,7 @@ void ir_lirc_unregister(struct rc_dev *dev) spin_lock_irqsave(&dev->lirc_fh_lock, flags); list_for_each_entry(fh, &dev->lirc_fh, list) - wake_up_poll(&fh->wait_poll, POLLHUP | POLLERR); + wake_up_poll(&fh->wait_poll, EPOLLHUP | EPOLLERR); spin_unlock_irqrestore(&dev->lirc_fh_lock, flags); cdev_device_del(&dev->lirc_cdev, &dev->lirc_dev); diff --git a/drivers/media/usb/cpia2/cpia2_core.c b/drivers/media/usb/cpia2/cpia2_core.c index e7524920c618..3dfbb545c0e3 100644 --- a/drivers/media/usb/cpia2/cpia2_core.c +++ b/drivers/media/usb/cpia2/cpia2_core.c @@ -2375,7 +2375,7 @@ __poll_t cpia2_poll(struct camera_data *cam, struct file *filp, { __poll_t status = v4l2_ctrl_poll(filp, wait); - if ((poll_requested_events(wait) & (POLLIN | POLLRDNORM)) && + if ((poll_requested_events(wait) & (EPOLLIN | EPOLLRDNORM)) && !cam->streaming) { /* Start streaming */ cpia2_usb_stream_start(cam, @@ -2385,7 +2385,7 @@ __poll_t cpia2_poll(struct camera_data *cam, struct file *filp, poll_wait(filp, &cam->wq_stream, wait); if (cam->curbuff->status == FRAME_READY) - status |= POLLIN | POLLRDNORM; + status |= EPOLLIN | EPOLLRDNORM; return status; } diff --git a/drivers/media/usb/cx231xx/cx231xx-417.c b/drivers/media/usb/cx231xx/cx231xx-417.c index 103e3299b77f..b80e6857e2eb 100644 --- a/drivers/media/usb/cx231xx/cx231xx-417.c +++ b/drivers/media/usb/cx231xx/cx231xx-417.c @@ -1821,11 +1821,11 @@ static __poll_t mpeg_poll(struct file *file, __poll_t res = 0; if (v4l2_event_pending(&fh->fh)) - res |= POLLPRI; + res |= EPOLLPRI; else poll_wait(file, &fh->fh.wait, wait); - if (!(req_events & (POLLIN | POLLRDNORM))) + if (!(req_events & (EPOLLIN | EPOLLRDNORM))) return res; mutex_lock(&dev->lock); diff --git a/drivers/media/usb/cx231xx/cx231xx-video.c b/drivers/media/usb/cx231xx/cx231xx-video.c index 271f35208c49..5b321b8ada3a 100644 --- a/drivers/media/usb/cx231xx/cx231xx-video.c +++ b/drivers/media/usb/cx231xx/cx231xx-video.c @@ -2018,19 +2018,19 @@ static __poll_t cx231xx_v4l2_poll(struct file *filp, poll_table *wait) rc = check_dev(dev); if (rc < 0) - return POLLERR; + return EPOLLERR; rc = res_get(fh); if (unlikely(rc < 0)) - return POLLERR; + return EPOLLERR; if (v4l2_event_pending(&fh->fh)) - res |= POLLPRI; + res |= EPOLLPRI; else poll_wait(filp, &fh->fh.wait, wait); - if (!(req_events & (POLLIN | POLLRDNORM))) + if (!(req_events & (EPOLLIN | EPOLLRDNORM))) return res; if ((V4L2_BUF_TYPE_VIDEO_CAPTURE == fh->type) || @@ -2040,7 +2040,7 @@ static __poll_t cx231xx_v4l2_poll(struct file *filp, poll_table *wait) mutex_unlock(&dev->lock); return res; } - return res | POLLERR; + return res | EPOLLERR; } /* diff --git a/drivers/media/usb/gspca/gspca.c b/drivers/media/usb/gspca/gspca.c index 87e18d0c5766..d29773b8f696 100644 --- a/drivers/media/usb/gspca/gspca.c +++ b/drivers/media/usb/gspca/gspca.c @@ -1877,14 +1877,14 @@ static __poll_t dev_poll(struct file *file, poll_table *wait) gspca_dbg(gspca_dev, D_FRAM, "poll\n"); - if (req_events & POLLPRI) + if (req_events & EPOLLPRI) ret |= v4l2_ctrl_poll(file, wait); - if (req_events & (POLLIN | POLLRDNORM)) { + if (req_events & (EPOLLIN | EPOLLRDNORM)) { /* if reqbufs is not done, the user would use read() */ if (gspca_dev->memory == GSPCA_MEMORY_NO) { if (read_alloc(gspca_dev, file) != 0) { - ret |= POLLERR; + ret |= EPOLLERR; goto out; } } @@ -1893,17 +1893,17 @@ static __poll_t dev_poll(struct file *file, poll_table *wait) /* check if an image has been received */ if (mutex_lock_interruptible(&gspca_dev->queue_lock) != 0) { - ret |= POLLERR; + ret |= EPOLLERR; goto out; } if (gspca_dev->fr_o != atomic_read(&gspca_dev->fr_i)) - ret |= POLLIN | POLLRDNORM; + ret |= EPOLLIN | EPOLLRDNORM; mutex_unlock(&gspca_dev->queue_lock); } out: if (!gspca_dev->present) - ret |= POLLHUP; + ret |= EPOLLHUP; return ret; } diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c index 660d4a65401f..77c3d331ff31 100644 --- a/drivers/media/usb/hdpvr/hdpvr-video.c +++ b/drivers/media/usb/hdpvr/hdpvr-video.c @@ -528,7 +528,7 @@ static __poll_t hdpvr_poll(struct file *filp, poll_table *wait) struct hdpvr_device *dev = video_drvdata(filp); __poll_t mask = v4l2_ctrl_poll(filp, wait); - if (!(req_events & (POLLIN | POLLRDNORM))) + if (!(req_events & (EPOLLIN | EPOLLRDNORM))) return mask; mutex_lock(&dev->io_mutex); @@ -553,7 +553,7 @@ static __poll_t hdpvr_poll(struct file *filp, poll_table *wait) buf = hdpvr_get_next_buffer(dev); } if (buf && buf->status == BUFSTAT_READY) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c index ad6290e1b699..9fdc57c1658f 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c @@ -1181,19 +1181,19 @@ static __poll_t pvr2_v4l2_poll(struct file *file, poll_table *wait) int ret; if (fh->fw_mode_flag) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } if (!fh->rhp) { ret = pvr2_v4l2_iosetup(fh); - if (ret) return POLLERR; + if (ret) return EPOLLERR; } poll_wait(file,&fh->wait_data,wait); if (pvr2_ioread_avail(fh->rhp) >= 0) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } return mask; diff --git a/drivers/media/usb/stkwebcam/stk-webcam.c b/drivers/media/usb/stkwebcam/stk-webcam.c index 17ad978c0172..22389b56ec24 100644 --- a/drivers/media/usb/stkwebcam/stk-webcam.c +++ b/drivers/media/usb/stkwebcam/stk-webcam.c @@ -729,10 +729,10 @@ static __poll_t v4l_stk_poll(struct file *fp, poll_table *wait) poll_wait(fp, &dev->wait_frame, wait); if (!is_present(dev)) - return POLLERR; + return EPOLLERR; if (!list_empty(&dev->sio_full)) - return res | POLLIN | POLLRDNORM; + return res | EPOLLIN | EPOLLRDNORM; return res; } diff --git a/drivers/media/usb/tm6000/tm6000-video.c b/drivers/media/usb/tm6000/tm6000-video.c index 96266fa4738c..8314d3fa9241 100644 --- a/drivers/media/usb/tm6000/tm6000-video.c +++ b/drivers/media/usb/tm6000/tm6000-video.c @@ -1424,25 +1424,25 @@ __tm6000_poll(struct file *file, struct poll_table_struct *wait) __poll_t res = 0; if (v4l2_event_pending(&fh->fh)) - res = POLLPRI; - else if (req_events & POLLPRI) + res = EPOLLPRI; + else if (req_events & EPOLLPRI) poll_wait(file, &fh->fh.wait, wait); if (V4L2_BUF_TYPE_VIDEO_CAPTURE != fh->type) - return res | POLLERR; + return res | EPOLLERR; if (!!is_res_streaming(fh->dev, fh)) - return res | POLLERR; + return res | EPOLLERR; if (!is_res_read(fh->dev, fh)) { /* streaming capture */ if (list_empty(&fh->vb_vidq.stream)) - return res | POLLERR; + return res | EPOLLERR; buf = list_entry(fh->vb_vidq.stream.next, struct tm6000_buffer, vb.stream); poll_wait(file, &buf->vb.done, wait); if (buf->vb.state == VIDEOBUF_DONE || buf->vb.state == VIDEOBUF_ERROR) - return res | POLLIN | POLLRDNORM; - } else if (req_events & (POLLIN | POLLRDNORM)) { + return res | EPOLLIN | EPOLLRDNORM; + } else if (req_events & (EPOLLIN | EPOLLRDNORM)) { /* read() capture */ return res | videobuf_poll_stream(file, &fh->vb_vidq, wait); } diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index b07657149434..ce08b50b8290 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -3462,7 +3462,7 @@ __poll_t v4l2_ctrl_poll(struct file *file, struct poll_table_struct *wait) struct v4l2_fh *fh = file->private_data; if (v4l2_event_pending(fh)) - return POLLPRI; + return EPOLLPRI; poll_wait(file, &fh->wait, wait); return 0; } diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index cd8127d3f863..0301fe426a43 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -334,7 +334,7 @@ static ssize_t v4l2_write(struct file *filp, const char __user *buf, static __poll_t v4l2_poll(struct file *filp, struct poll_table_struct *poll) { struct video_device *vdev = video_devdata(filp); - __poll_t res = POLLERR | POLLHUP; + __poll_t res = EPOLLERR | EPOLLHUP; if (!vdev->fops->poll) return DEFAULT_POLLMASK; diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c index 186156f8952a..c4f963d96a79 100644 --- a/drivers/media/v4l2-core/v4l2-mem2mem.c +++ b/drivers/media/v4l2-core/v4l2-mem2mem.c @@ -514,10 +514,10 @@ __poll_t v4l2_m2m_poll(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, struct v4l2_fh *fh = file->private_data; if (v4l2_event_pending(fh)) - rc = POLLPRI; - else if (req_events & POLLPRI) + rc = EPOLLPRI; + else if (req_events & EPOLLPRI) poll_wait(file, &fh->wait, wait); - if (!(req_events & (POLLOUT | POLLWRNORM | POLLIN | POLLRDNORM))) + if (!(req_events & (EPOLLOUT | EPOLLWRNORM | EPOLLIN | EPOLLRDNORM))) return rc; } @@ -531,7 +531,7 @@ __poll_t v4l2_m2m_poll(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, */ if ((!src_q->streaming || list_empty(&src_q->queued_list)) && (!dst_q->streaming || list_empty(&dst_q->queued_list))) { - rc |= POLLERR; + rc |= EPOLLERR; goto end; } @@ -548,7 +548,7 @@ __poll_t v4l2_m2m_poll(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, */ if (dst_q->last_buffer_dequeued) { spin_unlock_irqrestore(&dst_q->done_lock, flags); - return rc | POLLIN | POLLRDNORM; + return rc | EPOLLIN | EPOLLRDNORM; } poll_wait(file, &dst_q->done_wq, wait); @@ -561,7 +561,7 @@ __poll_t v4l2_m2m_poll(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, done_entry); if (src_vb && (src_vb->state == VB2_BUF_STATE_DONE || src_vb->state == VB2_BUF_STATE_ERROR)) - rc |= POLLOUT | POLLWRNORM; + rc |= EPOLLOUT | EPOLLWRNORM; spin_unlock_irqrestore(&src_q->done_lock, flags); spin_lock_irqsave(&dst_q->done_lock, flags); @@ -570,7 +570,7 @@ __poll_t v4l2_m2m_poll(struct file *file, struct v4l2_m2m_ctx *m2m_ctx, done_entry); if (dst_vb && (dst_vb->state == VB2_BUF_STATE_DONE || dst_vb->state == VB2_BUF_STATE_ERROR)) - rc |= POLLIN | POLLRDNORM; + rc |= EPOLLIN | EPOLLRDNORM; spin_unlock_irqrestore(&dst_q->done_lock, flags); end: diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 28966fa8c610..c5639817db34 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -476,12 +476,12 @@ static __poll_t subdev_poll(struct file *file, poll_table *wait) struct v4l2_fh *fh = file->private_data; if (!(sd->flags & V4L2_SUBDEV_FL_HAS_EVENTS)) - return POLLERR; + return EPOLLERR; poll_wait(file, &fh->wait, wait); if (v4l2_event_pending(fh)) - return POLLPRI; + return EPOLLPRI; return 0; } diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c index 9a89d3ae170f..2b3981842b4b 100644 --- a/drivers/media/v4l2-core/videobuf-core.c +++ b/drivers/media/v4l2-core/videobuf-core.c @@ -1131,11 +1131,11 @@ __poll_t videobuf_poll_stream(struct file *file, if (!list_empty(&q->stream)) buf = list_entry(q->stream.next, struct videobuf_buffer, stream); - } else if (req_events & (POLLIN | POLLRDNORM)) { + } else if (req_events & (EPOLLIN | EPOLLRDNORM)) { if (!q->reading) __videobuf_read_start(q); if (!q->reading) { - rc = POLLERR; + rc = EPOLLERR; } else if (NULL == q->read_buf) { q->read_buf = list_entry(q->stream.next, struct videobuf_buffer, @@ -1146,7 +1146,7 @@ __poll_t videobuf_poll_stream(struct file *file, buf = q->read_buf; } if (!buf) - rc = POLLERR; + rc = EPOLLERR; if (0 == rc) { poll_wait(file, &buf->done, wait); @@ -1157,10 +1157,10 @@ __poll_t videobuf_poll_stream(struct file *file, case V4L2_BUF_TYPE_VBI_OUTPUT: case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT: case V4L2_BUF_TYPE_SDR_OUTPUT: - rc = POLLOUT | POLLWRNORM; + rc = EPOLLOUT | EPOLLWRNORM; break; default: - rc = POLLIN | POLLRDNORM; + rc = EPOLLIN | EPOLLRDNORM; break; } } diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c index 1afa27de7191..8ba41073dd89 100644 --- a/drivers/mfd/ab8500-debugfs.c +++ b/drivers/mfd/ab8500-debugfs.c @@ -1258,20 +1258,6 @@ static struct ab8500_prcmu_ranges ab8540_debug_ranges[AB8500_NUM_BANKS] = { }, }; -#define DEFINE_SHOW_ATTRIBUTE(__name) \ -static int __name ## _open(struct inode *inode, struct file *file) \ -{ \ - return single_open(file, __name ## _show, inode->i_private); \ -} \ - \ -static const struct file_operations __name ## _fops = { \ - .owner = THIS_MODULE, \ - .open = __name ## _open, \ - .read = seq_read, \ - .llseek = seq_lseek, \ - .release = single_release, \ -} \ - static irqreturn_t ab8500_debug_handler(int irq, void *data) { char buf[16]; @@ -1281,7 +1267,7 @@ static irqreturn_t ab8500_debug_handler(int irq, void *data) if (irq_abb < num_irqs) irq_count[irq_abb]++; /* - * This makes it possible to use poll for events (POLLPRI | POLLERR) + * This makes it possible to use poll for events (EPOLLPRI | EPOLLERR) * from userspace on sysfs file named <irq-nr> */ sprintf(buf, "%d", irq); diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c index 0162516f5e57..bd6ddbdb5cd1 100644 --- a/drivers/misc/cxl/file.c +++ b/drivers/misc/cxl/file.c @@ -378,11 +378,11 @@ __poll_t afu_poll(struct file *file, struct poll_table_struct *poll) spin_lock_irqsave(&ctx->lock, flags); if (ctx_event_pending(ctx)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; else if (ctx->status == CLOSED) /* Only error on closed when there are no futher events pending */ - mask |= POLLERR; + mask |= EPOLLERR; spin_unlock_irqrestore(&ctx->lock, flags); pr_devel("afu_poll pe: %i returning %#x\n", ctx->pe, mask); diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c index 35693c0a78e2..e9c9ef52c76a 100644 --- a/drivers/misc/hpilo.c +++ b/drivers/misc/hpilo.c @@ -519,9 +519,9 @@ static __poll_t ilo_poll(struct file *fp, poll_table *wait) poll_wait(fp, &data->ccb_waitq, wait); if (is_channel_reset(driver_ccb)) - return POLLERR; + return EPOLLERR; else if (ilo_pkt_recv(data->ilo_hw, driver_ccb)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c index e49888eab87d..e9bb1cfa6a7a 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d.c +++ b/drivers/misc/lis3lv02d/lis3lv02d.c @@ -658,7 +658,7 @@ static __poll_t lis3lv02d_misc_poll(struct file *file, poll_table *wait) poll_wait(file, &lis3->misc_wait, wait); if (atomic_read(&lis3->count)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 505b710291e6..758dc73602d5 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -551,31 +551,31 @@ static __poll_t mei_poll(struct file *file, poll_table *wait) bool notify_en; if (WARN_ON(!cl || !cl->dev)) - return POLLERR; + return EPOLLERR; dev = cl->dev; mutex_lock(&dev->device_lock); - notify_en = cl->notify_en && (req_events & POLLPRI); + notify_en = cl->notify_en && (req_events & EPOLLPRI); if (dev->dev_state != MEI_DEV_ENABLED || !mei_cl_is_connected(cl)) { - mask = POLLERR; + mask = EPOLLERR; goto out; } if (notify_en) { poll_wait(file, &cl->ev_wait, wait); if (cl->notify_ev) - mask |= POLLPRI; + mask |= EPOLLPRI; } - if (req_events & (POLLIN | POLLRDNORM)) { + if (req_events & (EPOLLIN | EPOLLRDNORM)) { poll_wait(file, &cl->rx_wait, wait); if (!list_empty(&cl->rd_completed)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; else mei_cl_read_start(cl, mei_cl_mtu(cl), file); } diff --git a/drivers/misc/mic/cosm/cosm_scif_server.c b/drivers/misc/mic/cosm/cosm_scif_server.c index 85f7d09cc65f..05a63286741c 100644 --- a/drivers/misc/mic/cosm/cosm_scif_server.c +++ b/drivers/misc/mic/cosm/cosm_scif_server.c @@ -55,7 +55,7 @@ * message being sent to host SCIF. SCIF_DISCNCT message processing on the * host SCIF sets the host COSM SCIF endpoint state to DISCONNECTED and wakes * up the host COSM thread blocked in scif_poll(..) resulting in - * scif_poll(..) returning POLLHUP. + * scif_poll(..) returning EPOLLHUP. * 5. On the card, scif_peer_release_dev is next called which results in an * SCIF_EXIT message being sent to the host and after receiving the * SCIF_EXIT_ACK from the host the peer device teardown on the card is @@ -79,7 +79,7 @@ * processing. This results in the COSM endpoint on the card being closed and * the SCIF host peer device on the card getting unregistered similar to * steps 3, 4 and 5 for the card shutdown case above. scif_poll(..) on the - * host returns POLLHUP as a result. + * host returns EPOLLHUP as a result. * 4. On the host, card peer device unregister and SCIF HW remove(..) also * subsequently complete. * @@ -87,11 +87,11 @@ * ---------- * If a reset is issued after the card has crashed, there is no SCIF_DISCNT * message from the card which would result in scif_poll(..) returning - * POLLHUP. In this case when the host SCIF driver sends a SCIF_REMOVE_NODE + * EPOLLHUP. In this case when the host SCIF driver sends a SCIF_REMOVE_NODE * message to itself resulting in the card SCIF peer device being unregistered, * this results in a scif_peer_release_dev -> scif_cleanup_scifdev-> * scif_invalidate_ep call sequence which sets the endpoint state to - * DISCONNECTED and results in scif_poll(..) returning POLLHUP. + * DISCONNECTED and results in scif_poll(..) returning EPOLLHUP. */ #define COSM_SCIF_BACKLOG 16 @@ -190,7 +190,7 @@ static void cosm_send_time(struct cosm_device *cdev) /* * Close this cosm_device's endpoint after its peer endpoint on the card has - * been closed. In all cases except MIC card crash POLLHUP on the host is + * been closed. In all cases except MIC card crash EPOLLHUP on the host is * triggered by the client's endpoint being closed. */ static void cosm_scif_close(struct cosm_device *cdev) @@ -252,7 +252,7 @@ void cosm_scif_work(struct work_struct *work) while (1) { pollepd.epd = cdev->epd; - pollepd.events = POLLIN; + pollepd.events = EPOLLIN; /* Drop the mutex before blocking in scif_poll(..) */ mutex_unlock(&cdev->cosm_mutex); @@ -266,11 +266,11 @@ void cosm_scif_work(struct work_struct *work) } /* There is a message from the card */ - if (pollepd.revents & POLLIN) + if (pollepd.revents & EPOLLIN) cosm_scif_recv(cdev); /* The peer endpoint is closed or this endpoint disconnected */ - if (pollepd.revents & POLLHUP) { + if (pollepd.revents & EPOLLHUP) { cosm_scif_close(cdev); break; } diff --git a/drivers/misc/mic/cosm_client/cosm_scif_client.c b/drivers/misc/mic/cosm_client/cosm_scif_client.c index aa530fcceaa9..beafc0da4027 100644 --- a/drivers/misc/mic/cosm_client/cosm_scif_client.c +++ b/drivers/misc/mic/cosm_client/cosm_scif_client.c @@ -160,7 +160,7 @@ static int cosm_scif_client(void *unused) while (!kthread_should_stop()) { pollepd.epd = client_epd; - pollepd.events = POLLIN; + pollepd.events = EPOLLIN; rc = scif_poll(&pollepd, 1, COSM_HEARTBEAT_SEND_MSEC); if (rc < 0) { @@ -171,7 +171,7 @@ static int cosm_scif_client(void *unused) continue; } - if (pollepd.revents & POLLIN) + if (pollepd.revents & EPOLLIN) cosm_client_recv(); msg.id = COSM_MSG_HEARTBEAT; diff --git a/drivers/misc/mic/scif/scif_api.c b/drivers/misc/mic/scif/scif_api.c index 8a3e48ec37dd..7b2dddcdd46d 100644 --- a/drivers/misc/mic/scif/scif_api.c +++ b/drivers/misc/mic/scif/scif_api.c @@ -1328,7 +1328,7 @@ __scif_pollfd(struct file *f, poll_table *wait, struct scif_endpt *ep) if (ep->state == SCIFEP_CONNECTED || ep->state == SCIFEP_DISCONNECTED || ep->conn_err) - mask |= POLLOUT; + mask |= EPOLLOUT; goto exit; } } @@ -1338,34 +1338,34 @@ __scif_pollfd(struct file *f, poll_table *wait, struct scif_endpt *ep) _scif_poll_wait(f, &ep->conwq, wait, ep); if (ep->state == SCIFEP_LISTENING) { if (ep->conreqcnt) - mask |= POLLIN; + mask |= EPOLLIN; goto exit; } } /* Endpoint is connected or disconnected */ if (ep->state == SCIFEP_CONNECTED || ep->state == SCIFEP_DISCONNECTED) { - if (poll_requested_events(wait) & POLLIN) + if (poll_requested_events(wait) & EPOLLIN) _scif_poll_wait(f, &ep->recvwq, wait, ep); - if (poll_requested_events(wait) & POLLOUT) + if (poll_requested_events(wait) & EPOLLOUT) _scif_poll_wait(f, &ep->sendwq, wait, ep); if (ep->state == SCIFEP_CONNECTED || ep->state == SCIFEP_DISCONNECTED) { /* Data can be read without blocking */ if (scif_rb_count(&ep->qp_info.qp->inbound_q, 1)) - mask |= POLLIN; + mask |= EPOLLIN; /* Data can be written without blocking */ if (scif_rb_space(&ep->qp_info.qp->outbound_q)) - mask |= POLLOUT; - /* Return POLLHUP if endpoint is disconnected */ + mask |= EPOLLOUT; + /* Return EPOLLHUP if endpoint is disconnected */ if (ep->state == SCIFEP_DISCONNECTED) - mask |= POLLHUP; + mask |= EPOLLHUP; goto exit; } } - /* Return POLLERR if the endpoint is in none of the above states */ - mask |= POLLERR; + /* Return EPOLLERR if the endpoint is in none of the above states */ + mask |= EPOLLERR; exit: spin_unlock(&ep->lock); return mask; @@ -1398,10 +1398,10 @@ scif_poll(struct scif_pollepd *ufds, unsigned int nfds, long timeout_msecs) pt = &table.pt; while (1) { for (i = 0; i < nfds; i++) { - pt->_key = ufds[i].events | POLLERR | POLLHUP; + pt->_key = ufds[i].events | EPOLLERR | EPOLLHUP; mask = __scif_pollfd(ufds[i].epd->anon, pt, ufds[i].epd); - mask &= ufds[i].events | POLLERR | POLLHUP; + mask &= ufds[i].events | EPOLLERR | EPOLLHUP; if (mask) { count++; pt->_qproc = NULL; diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index a341938c7e2c..3633202e18f4 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -452,10 +452,12 @@ static irqreturn_t vop_virtio_intr_handler(int irq, void *data) static void vop_virtio_release_dev(struct device *_d) { - /* - * No need for a release method similar to virtio PCI. - * Provide an empty one to avoid getting a warning from core. - */ + struct virtio_device *vdev = + container_of(_d, struct virtio_device, dev); + struct _vop_vdev *vop_vdev = + container_of(vdev, struct _vop_vdev, vdev); + + kfree(vop_vdev); } /* @@ -466,7 +468,7 @@ static int _vop_add_device(struct mic_device_desc __iomem *d, unsigned int offset, struct vop_device *vpdev, int dnode) { - struct _vop_vdev *vdev; + struct _vop_vdev *vdev, *reg_dev = NULL; int ret; u8 type = ioread8(&d->type); @@ -497,6 +499,7 @@ static int _vop_add_device(struct mic_device_desc __iomem *d, vdev->c2h_vdev_db = ioread8(&vdev->dc->c2h_vdev_db); ret = register_virtio_device(&vdev->vdev); + reg_dev = vdev; if (ret) { dev_err(_vop_dev(vdev), "Failed to register vop device %u type %u\n", @@ -512,7 +515,10 @@ static int _vop_add_device(struct mic_device_desc __iomem *d, free_irq: vpdev->hw_ops->free_irq(vpdev, vdev->virtio_cookie, vdev); kfree: - kfree(vdev); + if (reg_dev) + put_device(&vdev->vdev.dev); + else + kfree(vdev); return ret; } @@ -568,7 +574,7 @@ static int _vop_remove_device(struct mic_device_desc __iomem *d, iowrite8(-1, &dc->h2c_vdev_db); if (status & VIRTIO_CONFIG_S_DRIVER_OK) wait_for_completion(&vdev->reset_done); - kfree(vdev); + put_device(&vdev->vdev.dev); iowrite8(1, &dc->guest_ack); dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n", __func__, __LINE__, ioread8(&dc->guest_ack)); diff --git a/drivers/misc/mic/vop/vop_vringh.c b/drivers/misc/mic/vop/vop_vringh.c index 01d1f2ba7bb8..cbc8ebcff5cf 100644 --- a/drivers/misc/mic/vop/vop_vringh.c +++ b/drivers/misc/mic/vop/vop_vringh.c @@ -1010,7 +1010,7 @@ __unlock_ret: } /* - * We return POLLIN | POLLOUT from poll when new buffers are enqueued, and + * We return EPOLLIN | EPOLLOUT from poll when new buffers are enqueued, and * not when previously enqueued buffers may be available. This means that * in the card->host (TX) path, when userspace is unblocked by poll it * must drain all available descriptors or it can stall. @@ -1022,15 +1022,15 @@ static __poll_t vop_poll(struct file *f, poll_table *wait) mutex_lock(&vdev->vdev_mutex); if (vop_vdev_inited(vdev)) { - mask = POLLERR; + mask = EPOLLERR; goto done; } poll_wait(f, &vdev->waitq, wait); if (vop_vdev_inited(vdev)) { - mask = POLLERR; + mask = EPOLLERR; } else if (vdev->poll_wake) { vdev->poll_wake = 0; - mask = POLLIN | POLLOUT; + mask = EPOLLIN | EPOLLOUT; } done: mutex_unlock(&vdev->vdev_mutex); diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index c90c1a578d2f..d9aa407db06a 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -215,9 +215,9 @@ static unsigned int afu_poll(struct file *file, struct poll_table_struct *wait) mutex_unlock(&ctx->status_mutex); if (afu_events_pending(ctx)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; else if (closed) - mask = POLLERR; + mask = EPOLLERR; return mask; } diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index 8fa68cf308e0..b084245f6238 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -265,9 +265,9 @@ static __poll_t phantom_poll(struct file *file, poll_table *wait) poll_wait(file, &dev->wait, wait); if (!(dev->status & PHB_RUNNING)) - mask = POLLERR; + mask = EPOLLERR; else if (atomic_read(&dev->counter)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; pr_debug("phantom_poll end: %x/%d\n", mask, atomic_read(&dev->counter)); diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c index 6640e7651533..83e0c95d20a4 100644 --- a/drivers/misc/vmw_vmci/vmci_host.c +++ b/drivers/misc/vmw_vmci/vmci_host.c @@ -182,7 +182,7 @@ static __poll_t vmci_host_poll(struct file *filp, poll_table *wait) if (context->pending_datagrams > 0 || vmci_handle_arr_get_size( context->pending_doorbell_array) > 0) { - mask = POLLIN; + mask = EPOLLIN; } spin_unlock(&context->lock); } diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 0eae619419d9..620c2d90a646 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -874,7 +874,6 @@ config MMC_CQHCI config MMC_TOSHIBA_PCI tristate "Toshiba Type A SD/MMC Card Interface Driver" depends on PCI - help config MMC_BCM2835 tristate "Broadcom BCM2835 SDHOST MMC Controller support" diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 7a3ebfd236f5..100adee778df 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -595,7 +595,7 @@ isr_done: reissue_mask = 1 << 0; if (!pdata->per_channel_irq) - reissue_mask |= 0xffff < 4; + reissue_mask |= 0xffff << 4; XP_IOWRITE(pdata, XP_INT_REISSUE_EN, reissue_mask); } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 7d1e4e2aaad0..ce1eed7a6d63 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -213,7 +213,7 @@ struct rx_tx_queue_stats { struct q_desc_mem { dma_addr_t dma; u64 size; - u16 q_len; + u32 q_len; dma_addr_t phys_base; void *base; void *unalign_base; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 1ca2a39ed0f8..56bc626ef006 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5166,7 +5166,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->regs = regs; err = t4_wait_dev_ready(regs); if (err < 0) - goto out_unmap_bar0; + goto out_free_adapter; /* We control everything through one PF */ whoami = readl(regs + PL_WHOAMI_A); diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 8984c4938881..382891f81e09 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -248,6 +248,7 @@ struct be_tx_stats { u32 tx_spoof_check_err; u32 tx_qinq_err; u32 tx_internal_parity_err; + u32 tx_sge_err; struct u64_stats_sync sync; struct u64_stats_sync sync_compl; }; @@ -944,8 +945,10 @@ static inline bool is_ipv6_ext_hdr(struct sk_buff *skb) #define BE_ERROR_EEH 1 #define BE_ERROR_UE BIT(1) #define BE_ERROR_FW BIT(2) -#define BE_ERROR_HW (BE_ERROR_EEH | BE_ERROR_UE) -#define BE_ERROR_ANY (BE_ERROR_EEH | BE_ERROR_UE | BE_ERROR_FW) +#define BE_ERROR_TX BIT(3) +#define BE_ERROR_HW (BE_ERROR_EEH | BE_ERROR_UE | BE_ERROR_TX) +#define BE_ERROR_ANY (BE_ERROR_EEH | BE_ERROR_UE | BE_ERROR_FW | \ + BE_ERROR_TX) #define BE_CLEAR_ALL 0xFF static inline u8 be_check_error(struct be_adapter *adapter, u32 err_type) diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 7d1819c9e8cc..7f7e206f95f8 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -189,6 +189,7 @@ static const struct be_ethtool_stat et_tx_stats[] = { * packet data. This counter is applicable only for Lancer adapters. */ {DRVSTAT_TX_INFO(tx_internal_parity_err)}, + {DRVSTAT_TX_INFO(tx_sge_err)}, {DRVSTAT_TX_INFO(tx_bytes)}, {DRVSTAT_TX_INFO(tx_pkts)}, {DRVSTAT_TX_INFO(tx_vxlan_offload_pkts)}, diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h index c967f45705d9..db5f92fb87e0 100644 --- a/drivers/net/ethernet/emulex/benet/be_hw.h +++ b/drivers/net/ethernet/emulex/benet/be_hw.h @@ -261,6 +261,7 @@ struct be_eth_hdr_wrb { #define LANCER_TX_COMP_HSW_DROP_MAC_ERR 0x3 #define LANCER_TX_COMP_HSW_DROP_VLAN_ERR 0x5 #define LANCER_TX_COMP_QINQ_ERR 0x7 +#define LANCER_TX_COMP_SGE_ERR 0x9 #define LANCER_TX_COMP_PARITY_ERR 0xb #define LANCER_TX_COMP_DMA_ERR 0xd diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index d81e2d37bc3d..5774fb6f8aa0 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2583,7 +2583,48 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp, u32 frags_needed) } } -static struct be_tx_compl_info *be_tx_compl_get(struct be_tx_obj *txo) +static inline void be_update_tx_err(struct be_tx_obj *txo, u8 status) +{ + switch (status) { + case BE_TX_COMP_HDR_PARSE_ERR: + tx_stats(txo)->tx_hdr_parse_err++; + break; + case BE_TX_COMP_NDMA_ERR: + tx_stats(txo)->tx_dma_err++; + break; + case BE_TX_COMP_ACL_ERR: + tx_stats(txo)->tx_spoof_check_err++; + break; + } +} + +static inline void lancer_update_tx_err(struct be_tx_obj *txo, u8 status) +{ + switch (status) { + case LANCER_TX_COMP_LSO_ERR: + tx_stats(txo)->tx_tso_err++; + break; + case LANCER_TX_COMP_HSW_DROP_MAC_ERR: + case LANCER_TX_COMP_HSW_DROP_VLAN_ERR: + tx_stats(txo)->tx_spoof_check_err++; + break; + case LANCER_TX_COMP_QINQ_ERR: + tx_stats(txo)->tx_qinq_err++; + break; + case LANCER_TX_COMP_PARITY_ERR: + tx_stats(txo)->tx_internal_parity_err++; + break; + case LANCER_TX_COMP_DMA_ERR: + tx_stats(txo)->tx_dma_err++; + break; + case LANCER_TX_COMP_SGE_ERR: + tx_stats(txo)->tx_sge_err++; + break; + } +} + +static struct be_tx_compl_info *be_tx_compl_get(struct be_adapter *adapter, + struct be_tx_obj *txo) { struct be_queue_info *tx_cq = &txo->cq; struct be_tx_compl_info *txcp = &txo->txcp; @@ -2599,6 +2640,24 @@ static struct be_tx_compl_info *be_tx_compl_get(struct be_tx_obj *txo) txcp->status = GET_TX_COMPL_BITS(status, compl); txcp->end_index = GET_TX_COMPL_BITS(wrb_index, compl); + if (txcp->status) { + if (lancer_chip(adapter)) { + lancer_update_tx_err(txo, txcp->status); + /* Reset the adapter incase of TSO, + * SGE or Parity error + */ + if (txcp->status == LANCER_TX_COMP_LSO_ERR || + txcp->status == LANCER_TX_COMP_PARITY_ERR || + txcp->status == LANCER_TX_COMP_SGE_ERR) + be_set_error(adapter, BE_ERROR_TX); + } else { + be_update_tx_err(txo, txcp->status); + } + } + + if (be_check_error(adapter, BE_ERROR_TX)) + return NULL; + compl->dw[offsetof(struct amap_eth_tx_compl, valid) / 32] = 0; queue_tail_inc(tx_cq); return txcp; @@ -2741,7 +2800,7 @@ static void be_tx_compl_clean(struct be_adapter *adapter) cmpl = 0; num_wrbs = 0; txq = &txo->q; - while ((txcp = be_tx_compl_get(txo))) { + while ((txcp = be_tx_compl_get(adapter, txo))) { num_wrbs += be_tx_compl_process(adapter, txo, txcp->end_index); @@ -3120,42 +3179,6 @@ loop_continue: return work_done; } -static inline void be_update_tx_err(struct be_tx_obj *txo, u8 status) -{ - switch (status) { - case BE_TX_COMP_HDR_PARSE_ERR: - tx_stats(txo)->tx_hdr_parse_err++; - break; - case BE_TX_COMP_NDMA_ERR: - tx_stats(txo)->tx_dma_err++; - break; - case BE_TX_COMP_ACL_ERR: - tx_stats(txo)->tx_spoof_check_err++; - break; - } -} - -static inline void lancer_update_tx_err(struct be_tx_obj *txo, u8 status) -{ - switch (status) { - case LANCER_TX_COMP_LSO_ERR: - tx_stats(txo)->tx_tso_err++; - break; - case LANCER_TX_COMP_HSW_DROP_MAC_ERR: - case LANCER_TX_COMP_HSW_DROP_VLAN_ERR: - tx_stats(txo)->tx_spoof_check_err++; - break; - case LANCER_TX_COMP_QINQ_ERR: - tx_stats(txo)->tx_qinq_err++; - break; - case LANCER_TX_COMP_PARITY_ERR: - tx_stats(txo)->tx_internal_parity_err++; - break; - case LANCER_TX_COMP_DMA_ERR: - tx_stats(txo)->tx_dma_err++; - break; - } -} static void be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo, int idx) @@ -3163,16 +3186,9 @@ static void be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo, int num_wrbs = 0, work_done = 0; struct be_tx_compl_info *txcp; - while ((txcp = be_tx_compl_get(txo))) { + while ((txcp = be_tx_compl_get(adapter, txo))) { num_wrbs += be_tx_compl_process(adapter, txo, txcp->end_index); work_done++; - - if (txcp->status) { - if (lancer_chip(adapter)) - lancer_update_tx_err(txo, txcp->status); - else - be_update_tx_err(txo, txcp->status); - } } if (work_done) { @@ -5104,9 +5120,12 @@ static netdev_features_t be_features_check(struct sk_buff *skb, features &= ~NETIF_F_TSO6; /* Lancer cannot handle the packet with MSS less than 256. + * Also it can't handle a TSO packet with a single segment * Disable the GSO support in such cases */ - if (lancer_chip(adapter) && skb_shinfo(skb)->gso_size < 256) + if (lancer_chip(adapter) && + (skb_shinfo(skb)->gso_size < 256 || + skb_shinfo(skb)->gso_segs == 1)) features &= ~NETIF_F_GSO_MASK; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5caaa9033841..27447260215d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -354,6 +354,8 @@ static void release_stats_buffers(struct ibmvnic_adapter *adapter) { kfree(adapter->tx_stats_buffers); kfree(adapter->rx_stats_buffers); + adapter->tx_stats_buffers = NULL; + adapter->rx_stats_buffers = NULL; } static int init_stats_buffers(struct ibmvnic_adapter *adapter) @@ -599,6 +601,8 @@ static void release_vpd_data(struct ibmvnic_adapter *adapter) kfree(adapter->vpd->buff); kfree(adapter->vpd); + + adapter->vpd = NULL; } static void release_tx_pools(struct ibmvnic_adapter *adapter) @@ -909,6 +913,7 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter) if (dma_mapping_error(dev, adapter->vpd->dma_addr)) { dev_err(dev, "Could not map VPD buffer\n"); kfree(adapter->vpd->buff); + adapter->vpd->buff = NULL; return -ENOMEM; } @@ -1414,10 +1419,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) hdrs += 2; } /* determine if l2/3/4 headers are sent to firmware */ - if ((*hdrs >> 7) & 1 && - (skb->protocol == htons(ETH_P_IP) || - skb->protocol == htons(ETH_P_IPV6) || - skb->protocol == htons(ETH_P_ARP))) { + if ((*hdrs >> 7) & 1) { build_hdr_descs_arr(tx_buff, &num_entries, *hdrs); tx_crq.v1.n_crq_elem = num_entries; tx_buff->indir_arr[0] = tx_crq; @@ -1639,6 +1641,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, return rc; } else if (adapter->req_rx_queues != old_num_rx_queues || adapter->req_tx_queues != old_num_tx_queues) { + adapter->map_id = 1; release_rx_pools(adapter); release_tx_pools(adapter); init_rx_pools(netdev); @@ -1831,7 +1834,8 @@ restart_poll: u16 offset; u8 flags = 0; - if (unlikely(adapter->resetting)) { + if (unlikely(adapter->resetting && + adapter->reset_reason != VNIC_RESET_NON_FATAL)) { enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]); napi_complete_done(napi, frames_processed); return frames_processed; @@ -2908,8 +2912,12 @@ static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter, cpu_to_be64(u64_crq[1])); if (rc) { - if (rc == H_CLOSED) + if (rc == H_CLOSED) { dev_warn(dev, "CRQ Queue closed\n"); + if (adapter->resetting) + ibmvnic_reset(adapter, VNIC_RESET_FATAL); + } + dev_warn(dev, "Send error (rc=%d)\n", rc); } @@ -3286,7 +3294,7 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq, struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; - unsigned char *substr = NULL, *ptr = NULL; + unsigned char *substr = NULL; u8 fw_level_len = 0; memset(adapter->fw_version, 0, 32); @@ -3306,10 +3314,6 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq, substr = strnstr(adapter->vpd->buff, "RM", adapter->vpd->len); if (!substr) { dev_info(dev, "Warning - No FW level has been provided in the VPD buffer by the VIOS Server\n"); - ptr = strncpy((char *)adapter->fw_version, "N/A", - 3 * sizeof(char)); - if (!ptr) - dev_err(dev, "Failed to inform that firmware version is unavailable to the adapter\n"); goto complete; } @@ -3324,16 +3328,14 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq, /* copy firmware version string from vpd into adapter */ if ((substr + 3 + fw_level_len) < (adapter->vpd->buff + adapter->vpd->len)) { - ptr = strncpy((char *)adapter->fw_version, - substr + 3, fw_level_len); - - if (!ptr) - dev_err(dev, "Failed to isolate FW level string\n"); + strncpy((char *)adapter->fw_version, substr + 3, fw_level_len); } else { dev_info(dev, "FW substr extrapolated VPD buff\n"); } complete: + if (adapter->fw_version[0] == '\0') + strncpy((char *)adapter->fw_version, "N/A", 3 * sizeof(char)); complete(&adapter->fw_done); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f95ce9b5e4fb..e31adbc75f9c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1785,7 +1785,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; u16 sections = 0; u8 netdev_tc = 0; - u16 numtc = 0; + u16 numtc = 1; u16 qcount; u8 offset; u16 qmap; @@ -1795,9 +1795,11 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; offset = 0; + /* Number of queues per enabled TC */ + num_tc_qps = vsi->alloc_queue_pairs; if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) { /* Find numtc from enabled TC bitmap */ - for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { if (enabled_tc & BIT(i)) /* TC is enabled */ numtc++; } @@ -1805,18 +1807,13 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, dev_warn(&pf->pdev->dev, "DCB is enabled but no TC enabled, forcing TC0\n"); numtc = 1; } - } else { - /* At least TC0 is enabled in non-DCB, non-MQPRIO case */ - numtc = 1; + num_tc_qps = num_tc_qps / numtc; + num_tc_qps = min_t(int, num_tc_qps, + i40e_pf_get_max_q_per_tc(pf)); } vsi->tc_config.numtc = numtc; vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1; - /* Number of queues per enabled TC */ - qcount = vsi->alloc_queue_pairs; - - num_tc_qps = qcount / numtc; - num_tc_qps = min_t(int, num_tc_qps, i40e_pf_get_max_q_per_tc(pf)); /* Do not allow use more TC queue pairs than MSI-X vectors exist */ if (pf->flags & I40E_FLAG_MSIX_ENABLED) @@ -1831,9 +1828,13 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, switch (vsi->type) { case I40E_VSI_MAIN: - qcount = min_t(int, pf->alloc_rss_size, - num_tc_qps); - break; + if (!(pf->flags & (I40E_FLAG_FD_SB_ENABLED | + I40E_FLAG_FD_ATR_ENABLED)) || + vsi->tc_config.enabled_tc != 1) { + qcount = min_t(int, pf->alloc_rss_size, + num_tc_qps); + break; + } case I40E_VSI_FDIR: case I40E_VSI_SRIOV: case I40E_VSI_VMDQ2: diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 322027792fe8..34e98aa6b956 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -35,6 +35,7 @@ #include "../nfpcore/nfp_cpp.h" #include "../nfpcore/nfp_nffw.h" +#include "../nfpcore/nfp_nsp.h" #include "../nfp_app.h" #include "../nfp_main.h" #include "../nfp_net.h" @@ -87,9 +88,20 @@ static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn) static int nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) { + struct nfp_pf *pf = app->pf; struct nfp_bpf_vnic *bv; int err; + if (!pf->eth_tbl) { + nfp_err(pf->cpp, "No ETH table\n"); + return -EINVAL; + } + if (pf->max_data_vnics != pf->eth_tbl->count) { + nfp_err(pf->cpp, "ETH entries don't match vNICs (%d vs %d)\n", + pf->max_data_vnics, pf->eth_tbl->count); + return -EINVAL; + } + bv = kzalloc(sizeof(*bv), GFP_KERNEL); if (!bv) return -ENOMEM; @@ -170,6 +182,7 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, return err; bv->tc_prog = cls_bpf->prog; + nn->port->tc_offload_cnt = !!bv->tc_prog; return 0; } @@ -207,13 +220,6 @@ static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev, } } -static bool nfp_bpf_tc_busy(struct nfp_app *app, struct nfp_net *nn) -{ - struct nfp_bpf_vnic *bv = nn->app_priv; - - return !!bv->tc_prog; -} - static int nfp_bpf_change_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu) { @@ -417,7 +423,6 @@ const struct nfp_app_type app_bpf = { .ctrl_msg_rx = nfp_bpf_ctrl_msg_rx, .setup_tc = nfp_bpf_setup_tc, - .tc_busy = nfp_bpf_tc_busy, .bpf = nfp_ndo_bpf, .xdp_offload = nfp_bpf_xdp_offload, }; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 424fe8338105..054df3dc0698 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -112,22 +112,22 @@ enum pkt_vec { * @map_elems_in_use: number of elements allocated to offloaded maps * * @adjust_head: adjust head capability - * @flags: extra flags for adjust head - * @off_min: minimal packet offset within buffer required - * @off_max: maximum packet offset within buffer required - * @guaranteed_sub: amount of negative adjustment guaranteed possible - * @guaranteed_add: amount of positive adjustment guaranteed possible + * @adjust_head.flags: extra flags for adjust head + * @adjust_head.off_min: minimal packet offset within buffer required + * @adjust_head.off_max: maximum packet offset within buffer required + * @adjust_head.guaranteed_sub: negative adjustment guaranteed possible + * @adjust_head.guaranteed_add: positive adjustment guaranteed possible * * @maps: map capability - * @types: supported map types - * @max_maps: max number of maps supported - * @max_elems: max number of entries in each map - * @max_key_sz: max size of map key - * @max_val_sz: max size of map value - * @max_elem_sz: max size of map entry (key + value) + * @maps.types: supported map types + * @maps.max_maps: max number of maps supported + * @maps.max_elems: max number of entries in each map + * @maps.max_key_sz: max size of map key + * @maps.max_val_sz: max size of map value + * @maps.max_elem_sz: max size of map entry (key + value) * * @helpers: helper addressess for various calls - * @map_lookup: map lookup helper address + * @helpers.map_lookup: map lookup helper address */ struct nfp_app_bpf { struct nfp_app *app; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 08c4c6dc5f7f..eb5c13dea8f5 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -349,6 +349,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, struct tc_cls_flower_offload *flow, bool egress) { enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE; + struct nfp_port *port = nfp_port_from_netdev(netdev); struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload *flow_pay; struct nfp_fl_key_ls *key_layer; @@ -390,6 +391,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, INIT_HLIST_NODE(&flow_pay->link); flow_pay->tc_flower_cookie = flow->cookie; hash_add_rcu(priv->flow_table, &flow_pay->link, flow->cookie); + port->tc_offload_cnt++; /* Deallocate flow payload when flower rule has been destroyed. */ kfree(key_layer); @@ -421,6 +423,7 @@ static int nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, struct tc_cls_flower_offload *flow) { + struct nfp_port *port = nfp_port_from_netdev(netdev); struct nfp_fl_payload *nfp_flow; int err; @@ -442,6 +445,7 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, err_free_flow: hash_del_rcu(&nfp_flow->link); + port->tc_offload_cnt--; kfree(nfp_flow->action_data); kfree(nfp_flow->mask_data); kfree(nfp_flow->unmasked_data); diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index b03f22f29612..ec524d97869d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -50,9 +50,9 @@ * @seq: sequence number of the message * @count: number of tunnels report in message * @flags: options part of the request - * @ipv4: dest IPv4 address of active route - * @egress_port: port the encapsulated packet egressed - * @extra: reserved for future use + * @tun_info.ipv4: dest IPv4 address of active route + * @tun_info.egress_port: port the encapsulated packet egressed + * @tun_info.extra: reserved for future use * @tun_info: tunnels that have sent traffic in reported period */ struct nfp_tun_active_tuns { @@ -132,8 +132,8 @@ struct nfp_ipv4_addr_entry { * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP * @reserved: reserved for future use * @count: number of MAC addresses in the message - * @index: index of MAC address in the lookup table - * @addr: interface MAC address + * @addresses.index: index of MAC address in the lookup table + * @addresses.addr: interface MAC address * @addresses: series of MACs to offload */ struct nfp_tun_mac_addr { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index 437964afa8ee..20546ae67909 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -92,7 +92,6 @@ extern const struct nfp_app_type app_flower; * @stop: stop application logic * @ctrl_msg_rx: control message handler * @setup_tc: setup TC ndo - * @tc_busy: TC HW offload busy (rules loaded) * @bpf: BPF ndo offload-related calls * @xdp_offload: offload an XDP program * @eswitch_mode_get: get SR-IOV eswitch mode @@ -135,7 +134,6 @@ struct nfp_app_type { int (*setup_tc)(struct nfp_app *app, struct net_device *netdev, enum tc_setup_type type, void *type_data); - bool (*tc_busy)(struct nfp_app *app, struct nfp_net *nn); int (*bpf)(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *xdp); int (*xdp_offload)(struct nfp_app *app, struct nfp_net *nn, @@ -301,13 +299,6 @@ static inline bool nfp_app_has_tc(struct nfp_app *app) return app && app->type->setup_tc; } -static inline bool nfp_app_tc_busy(struct nfp_app *app, struct nfp_net *nn) -{ - if (!app || !app->type->tc_busy) - return false; - return app->type->tc_busy(app, nn); -} - static inline int nfp_app_setup_tc(struct nfp_app *app, struct net_device *netdev, enum tc_setup_type type, void *type_data) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index 3f6952b66a49..1e597600c693 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -107,7 +107,7 @@ u16 immed_get_value(u64 instr) if (!unreg_is_imm(reg)) reg = FIELD_GET(OP_IMMED_B_SRC, instr); - return (reg & 0xff) | FIELD_GET(OP_IMMED_IMM, instr); + return (reg & 0xff) | FIELD_GET(OP_IMMED_IMM, instr) << 8; } void immed_set_value(u64 *instr, u16 immed) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index cc570bb6563c..ab301d56430b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -649,3 +649,4 @@ MODULE_FIRMWARE("netronome/nic_AMDA0099-0001_2x25.nffw"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("The Netronome Flow Processor (NFP) driver."); +MODULE_VERSION(UTS_RELEASE); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index d88eda9707e6..787df47ec430 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -193,7 +193,8 @@ struct nfp_net_tx_desc { /** * struct nfp_net_tx_buf - software TX buffer descriptor - * @skb: sk_buff associated with this buffer + * @skb: normal ring, sk_buff associated with this buffer + * @frag: XDP ring, page frag associated with this buffer * @dma_addr: DMA mapping address of the buffer * @fidx: Fragment index (-1 for the head and [0..nr_frags-1] for frags) * @pkt_cnt: Number of packets to be produced out of the skb associated @@ -377,6 +378,9 @@ struct nfp_net_rx_ring { * struct nfp_net_r_vector - Per ring interrupt vector configuration * @nfp_net: Backpointer to nfp_net structure * @napi: NAPI structure for this ring vec + * @tasklet: ctrl vNIC, tasklet for servicing the r_vec + * @queue: ctrl vNIC, send queue + * @lock: ctrl vNIC, r_vec lock protects @queue * @tx_ring: Pointer to TX ring * @rx_ring: Pointer to RX ring * @xdp_ring: Pointer to an extra TX ring for XDP diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index c0fd351c86b1..a05be0ab2713 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3210,10 +3210,9 @@ static int nfp_net_set_features(struct net_device *netdev, new_ctrl &= ~NFP_NET_CFG_CTRL_GATHER; } - if (changed & NETIF_F_HW_TC && nfp_app_tc_busy(nn->app, nn)) { - nn_err(nn, "Cannot disable HW TC offload while in use\n"); - return -EBUSY; - } + err = nfp_port_set_features(netdev, features); + if (err) + return err; nn_dbg(nn, "Feature change 0x%llx -> 0x%llx (changed=0x%llx)\n", netdev->features, features, changed); @@ -3734,7 +3733,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn) netdev->features = netdev->hw_features; - if (nfp_app_has_tc(nn->app)) + if (nfp_app_has_tc(nn->app) && nn->port) netdev->hw_features |= NETIF_F_HW_TC; /* Advertise but disable TSO by default. */ @@ -3751,6 +3750,8 @@ static void nfp_net_netdev_init(struct nfp_net *nn) netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = nn->max_mtu; + netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS; + netif_carrier_off(netdev); nfp_net_set_ethtool_ops(netdev); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index eeecef2caac6..4499a7333078 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -59,9 +59,12 @@ #define NFP_NET_RX_OFFSET 32 /** - * Maximum header size supported for LSO frames + * LSO parameters + * %NFP_NET_LSO_MAX_HDR_SZ: Maximum header size supported for LSO frames + * %NFP_NET_LSO_MAX_SEGS: Maximum number of segments LSO frame can produce */ #define NFP_NET_LSO_MAX_HDR_SZ 255 +#define NFP_NET_LSO_MAX_SEGS 64 /** * Prepend field types diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index f67da6bde9da..619570524d2a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -265,6 +265,7 @@ const struct net_device_ops nfp_repr_netdev_ops = { .ndo_set_vf_spoofchk = nfp_app_set_vf_spoofchk, .ndo_get_vf_config = nfp_app_get_vf_config, .ndo_set_vf_link_state = nfp_app_set_vf_link_state, + .ndo_set_features = nfp_port_set_features, }; static void nfp_repr_clean(struct nfp_repr *repr) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.c b/drivers/net/ethernet/netronome/nfp/nfp_port.c index 34a6e035fe9a..7bd8be5c833b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.c @@ -32,6 +32,7 @@ */ #include <linux/lockdep.h> +#include <linux/netdevice.h> #include <net/switchdev.h> #include "nfpcore/nfp_cpp.h" @@ -100,6 +101,23 @@ int nfp_port_setup_tc(struct net_device *netdev, enum tc_setup_type type, return nfp_app_setup_tc(port->app, netdev, type, type_data); } +int nfp_port_set_features(struct net_device *netdev, netdev_features_t features) +{ + struct nfp_port *port; + + port = nfp_port_from_netdev(netdev); + if (!port) + return 0; + + if ((netdev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC) && + port->tc_offload_cnt) { + netdev_err(netdev, "Cannot disable HW TC offload while offloads active\n"); + return -EBUSY; + } + + return 0; +} + struct nfp_port * nfp_port_from_id(struct nfp_pf *pf, enum nfp_port_type type, unsigned int id) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index 21bd4aa32646..fa7e669a969c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -72,6 +72,8 @@ enum nfp_port_flags { * @netdev: backpointer to associated netdev * @type: what port type does the entity represent * @flags: port flags + * @tc_offload_cnt: number of active TC offloads, how offloads are counted + * is not defined, use as a boolean * @app: backpointer to the app structure * @dl_port: devlink port structure * @eth_id: for %NFP_PORT_PHYS_PORT port ID in NFP enumeration scheme @@ -87,6 +89,7 @@ struct nfp_port { enum nfp_port_type type; unsigned long flags; + unsigned long tc_offload_cnt; struct nfp_app *app; @@ -121,6 +124,9 @@ static inline bool nfp_port_is_vnic(const struct nfp_port *port) return port->type == NFP_PORT_PF_PORT || port->type == NFP_PORT_VF_PORT; } +int +nfp_port_set_features(struct net_device *netdev, netdev_features_t features); + struct nfp_port *nfp_port_from_netdev(struct net_device *netdev); struct nfp_port * nfp_port_from_id(struct nfp_pf *pf, enum nfp_port_type type, unsigned int id); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index e983c9d7f86c..f23d9e06f097 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -98,28 +98,29 @@ enum nfp_eth_fec { * @max_index: max of @index fields of all @ports * @ports: table of ports * - * @eth_index: port index according to legacy ethX numbering - * @index: chip-wide first channel index - * @nbi: NBI index - * @base: first channel index (within NBI) - * @lanes: number of channels - * @speed: interface speed (in Mbps) - * @interface: interface (module) plugged in - * @media: media type of the @interface - * @fec: forward error correction mode - * @aneg: auto negotiation mode - * @mac_addr: interface MAC address - * @label_port: port id - * @label_subport: id of interface within port (for split ports) - * @enabled: is enabled? - * @tx_enabled: is TX enabled? - * @rx_enabled: is RX enabled? - * @override_changed: is media reconfig pending? + * @ports.eth_index: port index according to legacy ethX numbering + * @ports.index: chip-wide first channel index + * @ports.nbi: NBI index + * @ports.base: first channel index (within NBI) + * @ports.lanes: number of channels + * @ports.speed: interface speed (in Mbps) + * @ports.interface: interface (module) plugged in + * @ports.media: media type of the @interface + * @ports.fec: forward error correction mode + * @ports.aneg: auto negotiation mode + * @ports.mac_addr: interface MAC address + * @ports.label_port: port id + * @ports.label_subport: id of interface within port (for split ports) + * @ports.enabled: is enabled? + * @ports.tx_enabled: is TX enabled? + * @ports.rx_enabled: is RX enabled? + * @ports.override_changed: is media reconfig pending? * - * @port_type: one of %PORT_* defines for ethtool - * @port_lanes: total number of lanes on the port (sum of lanes of all subports) - * @is_split: is interface part of a split port - * @fec_modes_supported: bitmap of FEC modes supported + * @ports.port_type: one of %PORT_* defines for ethtool + * @ports.port_lanes: total number of lanes on the port (sum of lanes of all + * subports) + * @ports.is_split: is interface part of a split port + * @ports.fec_modes_supported: bitmap of FEC modes supported */ struct nfp_eth_table { unsigned int count; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c index b1dd13ff282b..7e14725055c7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c @@ -56,16 +56,17 @@ /** * struct nfp_resource_entry - Resource table entry - * @owner: NFP CPP Lock, interface owner - * @key: NFP CPP Lock, posix_crc32(name, 8) - * @region: Memory region descriptor - * @name: ASCII, zero padded name - * @reserved - * @cpp_action: CPP Action - * @cpp_token: CPP Token - * @cpp_target: CPP Target ID - * @page_offset: 256-byte page offset into target's CPP address - * @page_size: size, in 256-byte pages + * @mutex: NFP CPP Lock + * @mutex.owner: NFP CPP Lock, interface owner + * @mutex.key: NFP CPP Lock, posix_crc32(name, 8) + * @region: Memory region descriptor + * @region.name: ASCII, zero padded name + * @region.reserved: padding + * @region.cpp_action: CPP Action + * @region.cpp_token: CPP Token + * @region.cpp_target: CPP Target ID + * @region.page_offset: 256-byte page offset into target's CPP address + * @region.page_size: size, in 256-byte pages */ struct nfp_resource_entry { struct nfp_resource_entry_mutex { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 540d21786a43..ef10baf14186 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -74,8 +74,6 @@ static void dwmac1000_core_init(struct mac_device_info *hw, /* Mask GMAC interrupts */ value = GMAC_INT_DEFAULT_MASK; - if (hw->pmt) - value &= ~GMAC_INT_DISABLE_PMT; if (hw->pcs) value &= ~GMAC_INT_DISABLE_PCS; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 789dad8a07b5..7761a26ec9c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -98,7 +98,7 @@ #define GMAC_PCS_IRQ_DEFAULT (GMAC_INT_RGSMIIS | GMAC_INT_PCS_LINK | \ GMAC_INT_PCS_ANE) -#define GMAC_INT_DEFAULT_MASK (GMAC_INT_PMT_EN | GMAC_INT_LPI_EN) +#define GMAC_INT_DEFAULT_ENABLE (GMAC_INT_PMT_EN | GMAC_INT_LPI_EN) enum dwmac4_irq_status { time_stamp_irq = 0x00001000, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index ed222b20fcf1..63795ecafc8d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -61,10 +61,9 @@ static void dwmac4_core_init(struct mac_device_info *hw, writel(value, ioaddr + GMAC_CONFIG); - /* Mask GMAC interrupts */ - value = GMAC_INT_DEFAULT_MASK; - if (hw->pmt) - value |= GMAC_INT_PMT_EN; + /* Enable GMAC interrupts */ + value = GMAC_INT_DEFAULT_ENABLE; + if (hw->pcs) value |= GMAC_PCS_IRQ_DEFAULT; @@ -572,10 +571,12 @@ static int dwmac4_irq_status(struct mac_device_info *hw, struct stmmac_extra_stats *x) { void __iomem *ioaddr = hw->pcsr; - u32 intr_status; + u32 intr_status = readl(ioaddr + GMAC_INT_STATUS); + u32 intr_enable = readl(ioaddr + GMAC_INT_EN); int ret = 0; - intr_status = readl(ioaddr + GMAC_INT_STATUS); + /* Discard disabled bits */ + intr_status &= intr_enable; /* Not used events (e.g. MMC interrupts) are not handled. */ if ((intr_status & mmc_tx_irq)) diff --git a/drivers/net/ethernet/sun/Kconfig b/drivers/net/ethernet/sun/Kconfig index b2caf5132bd2..7b982e02ea3a 100644 --- a/drivers/net/ethernet/sun/Kconfig +++ b/drivers/net/ethernet/sun/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Sun network device configuration # diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 113bd57e2ea0..9020b084b953 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* cassini.c: Sun Microsystems Cassini(+) ethernet driver. * * Copyright (C) 2004 Sun Microsystems Inc. diff --git a/drivers/net/ethernet/sun/cassini.h b/drivers/net/ethernet/sun/cassini.h index 882ce168a799..13f3860496a8 100644 --- a/drivers/net/ethernet/sun/cassini.h +++ b/drivers/net/ethernet/sun/cassini.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* $Id: cassini.h,v 1.16 2004/08/17 21:15:16 zaumen Exp $ * cassini.h: Definitions for Sun Microsystems Cassini(+) ethernet driver. * diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 5ea037672e6f..a5dd627fe2f9 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* ldmvsw.c: Sun4v LDOM Virtual Switch Driver. * * Copyright (C) 2016-2017 Oracle. All rights reserved. diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 06001bacbe0f..8dd545fed30d 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* niu.c: Neptune ethernet driver. * * Copyright (C) 2007, 2008 David S. Miller (davem@davemloft.net) diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 0b1f41f6bceb..f047b2797156 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* sunbmac.c: Driver for Sparc BigMAC 100baseT ethernet adapters. * * Copyright (C) 1997, 1998, 1999, 2003, 2008 David S. Miller (davem@davemloft.net) diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index a7afcee3c5ae..7a16d40a72d1 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* $Id: sungem.c,v 1.44.2.22 2002/03/13 01:18:12 davem Exp $ * sungem.c: Sun GEM ethernet driver. * diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 0431f1e5f511..06da2f59fcbf 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* sunhme.c: Sparc HME/BigMac 10/100baseT half/full duplex auto switching, * auto carrier detecting ethernet driver. Also known as the * "Happy Meal Ethernet" found on SunSwift SBUS cards. diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index a6bcdcdd947e..7fe0d5e33922 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* sunqe.c: Sparc QuadEthernet 10baseT SBUS card driver. * Once again I am out to prove that every ethernet * controller out there can be most efficiently programmed diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 27fb22638885..63d3d6b215f3 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* sunvnet.c: Sun LDOM Virtual Network Driver. * * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net> diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index 8aa3ce46bb81..d8f4c3f28150 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* sunvnet.c: Sun LDOM Virtual Network Driver. * * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net> diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 3c85a0885f9b..1b1b78fdc138 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1636,6 +1636,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb, q_idx = q_idx % cpsw->tx_ch_num; txch = cpsw->txv[q_idx].ch; + txq = netdev_get_tx_queue(ndev, q_idx); ret = cpsw_tx_packet_submit(priv, skb, txch); if (unlikely(ret != 0)) { cpsw_err(priv, tx_err, "desc submit failed\n"); @@ -1646,15 +1647,26 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb, * tell the kernel to stop sending us tx frames. */ if (unlikely(!cpdma_check_free_tx_desc(txch))) { - txq = netdev_get_tx_queue(ndev, q_idx); netif_tx_stop_queue(txq); + + /* Barrier, so that stop_queue visible to other cpus */ + smp_mb__after_atomic(); + + if (cpdma_check_free_tx_desc(txch)) + netif_tx_wake_queue(txq); } return NETDEV_TX_OK; fail: ndev->stats.tx_dropped++; - txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb)); netif_tx_stop_queue(txq); + + /* Barrier, so that stop_queue visible to other cpus */ + smp_mb__after_atomic(); + + if (cpdma_check_free_tx_desc(txch)) + netif_tx_wake_queue(txq); + return NETDEV_TX_BUSY; } diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index e412dfdda7dd..377af43b81b3 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -2648,11 +2648,11 @@ static __poll_t ca8210_test_int_poll( poll_wait(filp, &priv->test.readq, ptable); if (!kfifo_is_empty(&priv->test.up_fifo)) - return_flags |= (POLLIN | POLLRDNORM); + return_flags |= (EPOLLIN | EPOLLRDNORM); if (wait_event_interruptible( priv->test.readq, !kfifo_is_empty(&priv->test.up_fifo))) { - return POLLERR; + return EPOLLERR; } return return_flags; } diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index de73c1ff0939..75c25306d234 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -480,8 +480,7 @@ static int nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) { struct nsim_bpf_bound_map *nmap; - unsigned int i; - int err; + int i, err; if (WARN_ON(offmap->map.map_type != BPF_MAP_TYPE_ARRAY && offmap->map.map_type != BPF_MAP_TYPE_HASH)) @@ -518,7 +517,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) return 0; err_free: - while (--i) { + while (--i >= 0) { kfree(nmap->entry[i].key); kfree(nmap->entry[i].value); } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 88272b3ac2e2..24b5511222c8 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -56,7 +56,8 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev) gpiod = fwnode_get_named_gpiod(&mdiodev->dev.of_node->fwnode, "reset-gpios", 0, GPIOD_OUT_LOW, "PHY reset"); - if (PTR_ERR(gpiod) == -ENOENT) + if (PTR_ERR(gpiod) == -ENOENT || + PTR_ERR(gpiod) == -ENOSYS) gpiod = NULL; else if (IS_ERR(gpiod)) return PTR_ERR(gpiod); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index f3313a129531..e3e29c2b028b 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -822,7 +822,7 @@ void phy_start(struct phy_device *phydev) phy_resume(phydev); /* make sure interrupts are re-enabled for the PHY */ - if (phydev->irq != PHY_POLL) { + if (phy_interrupt_is_valid(phydev)) { err = phy_enable_interrupts(phydev); if (err < 0) break; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index ef6b2126b23a..255a5def56e9 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -539,11 +539,11 @@ static __poll_t ppp_poll(struct file *file, poll_table *wait) if (!pf) return 0; poll_wait(file, &pf->rwait, wait); - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; if (skb_peek(&pf->rq)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (pf->dead) - mask |= POLLHUP; + mask |= EPOLLHUP; else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); @@ -551,7 +551,7 @@ static __poll_t ppp_poll(struct file *file, poll_table *wait) ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; ppp_recv_unlock(ppp); } diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 0a5ed004781c..9b6cb780affe 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -377,7 +377,7 @@ rx_handler_result_t tap_handle_frame(struct sk_buff **pskb) } wake_up: - wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND); + wake_up_interruptible_poll(sk_sleep(&q->sk), EPOLLIN | EPOLLRDNORM | EPOLLRDBAND); return RX_HANDLER_CONSUMED; drop: @@ -487,7 +487,7 @@ static void tap_sock_write_space(struct sock *sk) wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) - wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND); + wake_up_interruptible_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); } static void tap_sock_destruct(struct sock *sk) @@ -572,7 +572,7 @@ static int tap_release(struct inode *inode, struct file *file) static __poll_t tap_poll(struct file *file, poll_table *wait) { struct tap_queue *q = file->private_data; - __poll_t mask = POLLERR; + __poll_t mask = EPOLLERR; if (!q) goto out; @@ -581,12 +581,12 @@ static __poll_t tap_poll(struct file *file, poll_table *wait) poll_wait(file, &q->wq.wait, wait); if (!ptr_ring_empty(&q->ring)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (sock_writeable(&q->sk) || (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) && sock_writeable(&q->sk))) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; out: return mask; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 0dc66e4fbb2c..81e6cc951e7f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -181,6 +181,7 @@ struct tun_file { struct tun_struct *detached; struct ptr_ring tx_ring; struct xdp_rxq_info xdp_rxq; + int xdp_pending_pkts; }; struct tun_flow_entry { @@ -1436,7 +1437,7 @@ static __poll_t tun_chr_poll(struct file *file, poll_table *wait) __poll_t mask = 0; if (!tun) - return POLLERR; + return EPOLLERR; sk = tfile->socket.sk; @@ -1445,16 +1446,16 @@ static __poll_t tun_chr_poll(struct file *file, poll_table *wait) poll_wait(file, sk_sleep(sk), wait); if (!ptr_ring_empty(&tfile->tx_ring)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (tun->dev->flags & IFF_UP && (sock_writeable(sk) || (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags) && sock_writeable(sk)))) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; if (tun->dev->reg_state != NETREG_REGISTERED) - mask = POLLERR; + mask = EPOLLERR; tun_put(tun); return mask; @@ -1665,6 +1666,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, case XDP_REDIRECT: get_page(alloc_frag->page); alloc_frag->offset += buflen; + ++tfile->xdp_pending_pkts; err = xdp_do_redirect(tun->dev, &xdp, xdp_prog); if (err) goto err_redirect; @@ -1986,6 +1988,11 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) result = tun_get_user(tun, tfile, NULL, from, file->f_flags & O_NONBLOCK, false); + if (tfile->xdp_pending_pkts) { + tfile->xdp_pending_pkts = 0; + xdp_do_flush_map(); + } + tun_put(tun); return result; } @@ -2303,8 +2310,8 @@ static void tun_sock_write_space(struct sock *sk) wqueue = sk_sleep(sk); if (wqueue && waitqueue_active(wqueue)) - wake_up_interruptible_sync_poll(wqueue, POLLOUT | - POLLWRNORM | POLLWRBAND); + wake_up_interruptible_sync_poll(wqueue, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); tfile = container_of(sk, struct tun_file, sk); kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); @@ -2322,6 +2329,13 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); + + if (tfile->xdp_pending_pkts >= NAPI_POLL_WEIGHT || + !(m->msg_flags & MSG_MORE)) { + tfile->xdp_pending_pkts = 0; + xdp_do_flush_map(); + } + tun_put(tun); return ret; } @@ -3153,6 +3167,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); memset(&tfile->tx_ring, 0, sizeof(tfile->tx_ring)); + tfile->xdp_pending_pkts = 0; return 0; } diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index b0fdc1023619..f3ec13b80b20 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -91,6 +91,35 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { .rx_ring_fill_level = HTT_RX_RING_FILL_LEVEL, }, { + .id = QCA988X_HW_2_0_VERSION, + .dev_id = QCA988X_2_0_DEVICE_ID_UBNT, + .name = "qca988x hw2.0 ubiquiti", + .patch_load_addr = QCA988X_HW_2_0_PATCH_LOAD_ADDR, + .uart_pin = 7, + .cc_wraparound_type = ATH10K_HW_CC_WRAP_SHIFTED_ALL, + .otp_exe_param = 0, + .channel_counters_freq_hz = 88000, + .max_probe_resp_desc_thres = 0, + .cal_data_len = 2116, + .fw = { + .dir = QCA988X_HW_2_0_FW_DIR, + .board = QCA988X_HW_2_0_BOARD_DATA_FILE, + .board_size = QCA988X_BOARD_DATA_SZ, + .board_ext_size = QCA988X_BOARD_EXT_DATA_SZ, + }, + .hw_ops = &qca988x_ops, + .decap_align_bytes = 4, + .spectral_bin_discard = 0, + .vht160_mcs_rx_highest = 0, + .vht160_mcs_tx_highest = 0, + .n_cipher_suites = 8, + .num_peers = TARGET_TLV_NUM_PEERS, + .ast_skid_limit = 0x10, + .num_wds_entries = 0x20, + .target_64bit = false, + .rx_ring_fill_level = HTT_RX_RING_FILL_LEVEL, + }, + { .id = QCA9887_HW_1_0_VERSION, .dev_id = QCA9887_1_0_DEVICE_ID, .name = "qca9887 hw1.0", @@ -1276,10 +1305,7 @@ static int ath10k_core_fetch_board_data_api_n(struct ath10k *ar, len -= sizeof(*hdr); data = hdr->data; - /* jump over the padding */ - ie_len = ALIGN(ie_len, 4); - - if (len < ie_len) { + if (len < ALIGN(ie_len, 4)) { ath10k_err(ar, "invalid length for board ie_id %d ie_len %zu len %zu\n", ie_id, ie_len, len); ret = -EINVAL; @@ -1318,6 +1344,9 @@ static int ath10k_core_fetch_board_data_api_n(struct ath10k *ar, goto out; } + /* jump over the padding */ + ie_len = ALIGN(ie_len, 4); + len -= ie_len; data += ie_len; } @@ -1448,9 +1477,6 @@ int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name, len -= sizeof(*hdr); data += sizeof(*hdr); - /* jump over the padding */ - ie_len = ALIGN(ie_len, 4); - if (len < ie_len) { ath10k_err(ar, "invalid length for FW IE %d (%zu < %zu)\n", ie_id, len, ie_len); @@ -1556,6 +1582,9 @@ int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name, break; } + /* jump over the padding */ + ie_len = ALIGN(ie_len, 4); + len -= ie_len; data += ie_len; } diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c index 4dde126dab17..7173b3743b43 100644 --- a/drivers/net/wireless/ath/ath10k/coredump.c +++ b/drivers/net/wireless/ath/ath10k/coredump.c @@ -1,5 +1,6 @@ /* * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. + * Copyright (c) 2018, The Linux Foundation. All rights reserved. * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -616,7 +617,7 @@ static const struct ath10k_mem_region qca6174_hw30_mem_regions[] = { { .type = ATH10K_MEM_REGION_TYPE_DRAM, .start = 0x400000, - .len = 0x90000, + .len = 0xa8000, .name = "DRAM", .section_table = { .sections = NULL, diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index 6d836a26272f..554cd7856cb6 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -1,6 +1,7 @@ /* * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. + * Copyright (c) 2018, The Linux Foundation. All rights reserved. * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -81,6 +82,8 @@ void ath10k_debug_print_hwfw_info(struct ath10k *ar) void ath10k_debug_print_board_info(struct ath10k *ar) { char boardinfo[100]; + const struct firmware *board; + u32 crc; if (ar->id.bmi_ids_valid) scnprintf(boardinfo, sizeof(boardinfo), "%d:%d", @@ -88,11 +91,16 @@ void ath10k_debug_print_board_info(struct ath10k *ar) else scnprintf(boardinfo, sizeof(boardinfo), "N/A"); + board = ar->normal_mode_fw.board; + if (!IS_ERR_OR_NULL(board)) + crc = crc32_le(0, board->data, board->size); + else + crc = 0; + ath10k_info(ar, "board_file api %d bmi_id %s crc32 %08x", ar->bd_api, boardinfo, - crc32_le(0, ar->normal_mode_fw.board->data, - ar->normal_mode_fw.board->size)); + crc); } void ath10k_debug_print_boot_info(struct ath10k *ar) diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h index 6203bc65799b..413b1b4321f7 100644 --- a/drivers/net/wireless/ath/ath10k/hw.h +++ b/drivers/net/wireless/ath/ath10k/hw.h @@ -22,6 +22,7 @@ #define ATH10K_FW_DIR "ath10k" +#define QCA988X_2_0_DEVICE_ID_UBNT (0x11ac) #define QCA988X_2_0_DEVICE_ID (0x003c) #define QCA6164_2_1_DEVICE_ID (0x0041) #define QCA6174_2_1_DEVICE_ID (0x003e) diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index 355db6a0fcf3..1b266cd0c2ec 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -58,6 +58,9 @@ MODULE_PARM_DESC(reset_mode, "0: auto, 1: warm only (default: 0)"); #define ATH10K_DIAG_TRANSFER_LIMIT 0x5000 static const struct pci_device_id ath10k_pci_id_table[] = { + /* PCI-E QCA988X V2 (Ubiquiti branded) */ + { PCI_VDEVICE(UBIQUITI, QCA988X_2_0_DEVICE_ID_UBNT) }, + { PCI_VDEVICE(ATHEROS, QCA988X_2_0_DEVICE_ID) }, /* PCI-E QCA988X V2 */ { PCI_VDEVICE(ATHEROS, QCA6164_2_1_DEVICE_ID) }, /* PCI-E QCA6164 V2.1 */ { PCI_VDEVICE(ATHEROS, QCA6174_2_1_DEVICE_ID) }, /* PCI-E QCA6174 V2.1 */ @@ -74,6 +77,7 @@ static const struct ath10k_pci_supp_chip ath10k_pci_supp_chips[] = { * hacks. ath10k doesn't have them and these devices crash horribly * because of that. */ + { QCA988X_2_0_DEVICE_ID_UBNT, QCA988X_HW_2_0_CHIP_ID_REV }, { QCA988X_2_0_DEVICE_ID, QCA988X_HW_2_0_CHIP_ID_REV }, { QCA6164_2_1_DEVICE_ID, QCA6174_HW_2_1_CHIP_ID_REV }, @@ -2193,6 +2197,7 @@ static int ath10k_pci_get_num_banks(struct ath10k *ar) struct ath10k_pci *ar_pci = ath10k_pci_priv(ar); switch (ar_pci->pdev->device) { + case QCA988X_2_0_DEVICE_ID_UBNT: case QCA988X_2_0_DEVICE_ID: case QCA99X0_2_0_DEVICE_ID: case QCA9888_2_0_DEVICE_ID: @@ -3424,6 +3429,7 @@ static int ath10k_pci_probe(struct pci_dev *pdev, u32 (*targ_cpu_to_ce_addr)(struct ath10k *ar, u32 addr); switch (pci_dev->device) { + case QCA988X_2_0_DEVICE_ID_UBNT: case QCA988X_2_0_DEVICE_ID: hw_rev = ATH10K_HW_QCA988X; pci_ps = false; diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c index 3d9447e21025..695c779ae8cf 100644 --- a/drivers/net/wireless/ath/ath9k/calib.c +++ b/drivers/net/wireless/ath/ath9k/calib.c @@ -72,7 +72,7 @@ static s16 ath9k_hw_get_default_nf(struct ath_hw *ah, s16 ath9k_hw_getchan_noise(struct ath_hw *ah, struct ath9k_channel *chan, s16 nf) { - s8 noise = ath9k_hw_get_default_nf(ah, chan, 0); + s8 noise = ATH_DEFAULT_NOISE_FLOOR; if (nf) { s8 delta = nf - ATH9K_NF_CAL_NOISE_THRESH - diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c index 56676eaff24c..cb0eef13af1c 100644 --- a/drivers/net/wireless/ath/ath9k/hif_usb.c +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c @@ -24,6 +24,7 @@ static const struct usb_device_id ath9k_hif_usb_ids[] = { { USB_DEVICE(0x0cf3, 0x9271) }, /* Atheros */ { USB_DEVICE(0x0cf3, 0x1006) }, /* Atheros */ { USB_DEVICE(0x0846, 0x9030) }, /* Netgear N150 */ + { USB_DEVICE(0x07b8, 0x9271) }, /* Altai WA1011N-GU */ { USB_DEVICE(0x07D1, 0x3A10) }, /* Dlink Wireless 150 */ { USB_DEVICE(0x13D3, 0x3327) }, /* Azurewave */ { USB_DEVICE(0x13D3, 0x3328) }, /* Azurewave */ diff --git a/drivers/net/wireless/mediatek/mt76/agg-rx.c b/drivers/net/wireless/mediatek/mt76/agg-rx.c index 8027bb7c03c2..fcb208d1f276 100644 --- a/drivers/net/wireless/mediatek/mt76/agg-rx.c +++ b/drivers/net/wireless/mediatek/mt76/agg-rx.c @@ -98,6 +98,7 @@ mt76_rx_aggr_reorder_work(struct work_struct *work) reorder_work.work); struct mt76_dev *dev = tid->dev; struct sk_buff_head frames; + int nframes; __skb_queue_head_init(&frames); @@ -105,14 +106,44 @@ mt76_rx_aggr_reorder_work(struct work_struct *work) spin_lock(&tid->lock); mt76_rx_aggr_check_release(tid, &frames); + nframes = tid->nframes; spin_unlock(&tid->lock); - ieee80211_queue_delayed_work(tid->dev->hw, &tid->reorder_work, REORDER_TIMEOUT); + if (nframes) + ieee80211_queue_delayed_work(tid->dev->hw, &tid->reorder_work, + REORDER_TIMEOUT); mt76_rx_complete(dev, &frames, -1); local_bh_enable(); } +static void +mt76_rx_aggr_check_ctl(struct sk_buff *skb, struct sk_buff_head *frames) +{ + struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb; + struct ieee80211_bar *bar = (struct ieee80211_bar *) skb->data; + struct mt76_wcid *wcid = status->wcid; + struct mt76_rx_tid *tid; + u16 seqno; + + if (!ieee80211_is_ctl(bar->frame_control)) + return; + + if (!ieee80211_is_back_req(bar->frame_control)) + return; + + status->tid = le16_to_cpu(bar->control) >> 12; + seqno = le16_to_cpu(bar->start_seq_num) >> 4; + tid = rcu_dereference(wcid->aggr[status->tid]); + if (!tid) + return; + + spin_lock_bh(&tid->lock); + mt76_rx_aggr_release_frames(tid, frames, seqno); + mt76_rx_aggr_release_head(tid, frames); + spin_unlock_bh(&tid->lock); +} + void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames) { struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb; @@ -126,9 +157,14 @@ void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames) __skb_queue_tail(frames, skb); sta = wcid_to_sta(wcid); - if (!sta || !status->aggr) + if (!sta) return; + if (!status->aggr) { + mt76_rx_aggr_check_ctl(skb, frames); + return; + } + tid = rcu_dereference(wcid->aggr[status->tid]); if (!tid) return; diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 5fcb2deb89a2..85f8d324ebf8 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -276,6 +276,7 @@ int mt76_register_device(struct mt76_dev *dev, bool vht, ieee80211_hw_set(hw, TX_AMSDU); ieee80211_hw_set(hw, TX_FRAG_LIST); ieee80211_hw_set(hw, MFP_CAPABLE); + ieee80211_hw_set(hw, AP_LINK_PS); wiphy->flags |= WIPHY_FLAG_IBSS_RSN; @@ -470,6 +471,53 @@ mt76_check_ccmp_pn(struct sk_buff *skb) return 0; } +static void +mt76_check_ps(struct mt76_dev *dev, struct sk_buff *skb) +{ + struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_sta *sta; + struct mt76_wcid *wcid = status->wcid; + bool ps; + + if (!wcid || !wcid->sta) + return; + + sta = container_of((void *) wcid, struct ieee80211_sta, drv_priv); + + if (!test_bit(MT_WCID_FLAG_CHECK_PS, &wcid->flags)) + return; + + if (ieee80211_is_pspoll(hdr->frame_control)) { + ieee80211_sta_pspoll(sta); + return; + } + + if (ieee80211_has_morefrags(hdr->frame_control) || + !(ieee80211_is_mgmt(hdr->frame_control) || + ieee80211_is_data(hdr->frame_control))) + return; + + ps = ieee80211_has_pm(hdr->frame_control); + + if (ps && (ieee80211_is_data_qos(hdr->frame_control) || + ieee80211_is_qos_nullfunc(hdr->frame_control))) + ieee80211_sta_uapsd_trigger(sta, status->tid); + + if (!!test_bit(MT_WCID_FLAG_PS, &wcid->flags) == ps) + return; + + if (ps) { + set_bit(MT_WCID_FLAG_PS, &wcid->flags); + mt76_stop_tx_queues(dev, sta, true); + } else { + clear_bit(MT_WCID_FLAG_PS, &wcid->flags); + } + + ieee80211_sta_ps_transition(sta, ps); + dev->drv->sta_ps(dev, sta, ps); +} + void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames, int queue) { @@ -498,8 +546,10 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q) __skb_queue_head_init(&frames); - while ((skb = __skb_dequeue(&dev->rx_skb[q])) != NULL) + while ((skb = __skb_dequeue(&dev->rx_skb[q])) != NULL) { + mt76_check_ps(dev, skb); mt76_rx_aggr_reorder(skb, &frames); + } mt76_rx_complete(dev, &frames, q); } diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 129015c9d116..d2ce15093edd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -121,11 +121,18 @@ struct mt76_queue_ops { void (*kick)(struct mt76_dev *dev, struct mt76_queue *q); }; +enum mt76_wcid_flags { + MT_WCID_FLAG_CHECK_PS, + MT_WCID_FLAG_PS, +}; + struct mt76_wcid { struct mt76_rx_tid __rcu *aggr[IEEE80211_NUM_TIDS]; struct work_struct aggr_work; + unsigned long flags; + u8 idx; u8 hw_key_idx; @@ -206,6 +213,9 @@ struct mt76_driver_ops { struct sk_buff *skb); void (*rx_poll_complete)(struct mt76_dev *dev, enum mt76_rxq_id q); + + void (*sta_ps)(struct mt76_dev *dev, struct ieee80211_sta *sta, + bool ps); }; struct mt76_channel_state { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h index 17df17afd9bf..e62131b88102 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h @@ -218,6 +218,8 @@ void mt76x2_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q); void mt76x2_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb); +void mt76x2_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps); + void mt76x2_update_channel(struct mt76_dev *mdev); s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c index 1b00ae4465a2..9dbf94947324 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c @@ -630,6 +630,7 @@ struct mt76x2_dev *mt76x2_alloc_device(struct device *pdev) .tx_complete_skb = mt76x2_tx_complete_skb, .rx_skb = mt76x2_queue_rx_skb, .rx_poll_complete = mt76x2_rx_poll_complete, + .sta_ps = mt76x2_sta_ps, }; struct ieee80211_hw *hw; struct mt76x2_dev *dev; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c index 6c30b5eaa9ca..7ea3d841918e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c @@ -341,7 +341,7 @@ int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb, mt76x2_remove_hdr_pad(skb, pad_len); - if (rxinfo & MT_RXINFO_BA) + if ((rxinfo & MT_RXINFO_BA) && !(rxinfo & MT_RXINFO_NULL)) status->aggr = true; if (WARN_ON_ONCE(len > skb->len)) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c index bf26284b9989..205043b470b2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c @@ -282,6 +282,9 @@ mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, for (i = 0; i < ARRAY_SIZE(sta->txq); i++) mt76x2_txq_init(dev, sta->txq[i]); + if (vif->type == NL80211_IFTYPE_AP) + set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags); + rcu_assign_pointer(dev->wcid[idx], &msta->wcid); out: @@ -311,23 +314,14 @@ mt76x2_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, return 0; } -static void -mt76x2_sta_notify(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum sta_notify_cmd cmd, struct ieee80211_sta *sta) +void +mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps) { struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv; - struct mt76x2_dev *dev = hw->priv; + struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76); int idx = msta->wcid.idx; - switch (cmd) { - case STA_NOTIFY_SLEEP: - mt76x2_mac_wcid_set_drop(dev, idx, true); - mt76_stop_tx_queues(&dev->mt76, sta, true); - break; - case STA_NOTIFY_AWAKE: - mt76x2_mac_wcid_set_drop(dev, idx, false); - break; - } + mt76x2_mac_wcid_set_drop(dev, idx, ps); } static int @@ -549,6 +543,12 @@ static void mt76x2_set_coverage_class(struct ieee80211_hw *hw, mutex_unlock(&dev->mutex); } +static int +mt76x2_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set) +{ + return 0; +} + const struct ieee80211_ops mt76x2_ops = { .tx = mt76x2_tx, .start = mt76x2_start, @@ -560,7 +560,6 @@ const struct ieee80211_ops mt76x2_ops = { .bss_info_changed = mt76x2_bss_info_changed, .sta_add = mt76x2_sta_add, .sta_remove = mt76x2_sta_remove, - .sta_notify = mt76x2_sta_notify, .set_key = mt76x2_set_key, .conf_tx = mt76x2_conf_tx, .sw_scan_start = mt76x2_sw_scan, @@ -573,5 +572,6 @@ const struct ieee80211_ops mt76x2_ops = { .release_buffered_frames = mt76_release_buffered_frames, .set_coverage_class = mt76x2_set_coverage_class, .get_survey = mt76_get_survey, + .set_tim = mt76x2_set_tim, }; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c index 72c55d1f8903..ac2572943ed0 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c @@ -309,7 +309,7 @@ static __poll_t rt2x00debug_poll_queue_dump(struct file *file, poll_wait(file, &intf->frame_dump_waitqueue, wait); if (!skb_queue_empty(&intf->frame_dump_skbqueue)) - return POLLOUT | POLLWRNORM; + return EPOLLOUT | EPOLLWRNORM; return 0; } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c index f20e77b4bb65..317c1b3101da 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/hw.c @@ -1123,7 +1123,7 @@ static u8 _rtl8821ae_dbi_read(struct rtl_priv *rtlpriv, u16 addr) } if (0 == tmp) { read_addr = REG_DBI_RDATA + addr % 4; - ret = rtl_read_word(rtlpriv, read_addr); + ret = rtl_read_byte(rtlpriv, read_addr); } return ret; } @@ -1165,7 +1165,8 @@ static void _rtl8821ae_enable_aspm_back_door(struct ieee80211_hw *hw) } tmp = _rtl8821ae_dbi_read(rtlpriv, 0x70f); - _rtl8821ae_dbi_write(rtlpriv, 0x70f, tmp | BIT(7)); + _rtl8821ae_dbi_write(rtlpriv, 0x70f, tmp | BIT(7) | + ASPM_L1_LATENCY << 3); tmp = _rtl8821ae_dbi_read(rtlpriv, 0x719); _rtl8821ae_dbi_write(rtlpriv, 0x719, tmp | BIT(3) | BIT(4)); diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h index a7aacbc3984e..46dcb7fef195 100644 --- a/drivers/net/wireless/realtek/rtlwifi/wifi.h +++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h @@ -99,6 +99,7 @@ #define RTL_USB_MAX_RX_COUNT 100 #define QBSS_LOAD_SIZE 5 #define MAX_WMMELE_LENGTH 64 +#define ASPM_L1_LATENCY 7 #define TOTAL_CAM_ENTRY 32 diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 9bd7ddeeb6a5..8328d395e332 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -351,6 +351,9 @@ static int xennet_open(struct net_device *dev) unsigned int i = 0; struct netfront_queue *queue = NULL; + if (!np->queues) + return -ENODEV; + for (i = 0; i < num_queues; ++i) { queue = &np->queues[i]; napi_enable(&queue->napi); @@ -1358,18 +1361,8 @@ static int netfront_probe(struct xenbus_device *dev, #ifdef CONFIG_SYSFS info->netdev->sysfs_groups[0] = &xennet_dev_group; #endif - err = register_netdev(info->netdev); - if (err) { - pr_warn("%s: register_netdev err=%d\n", __func__, err); - goto fail; - } return 0; - - fail: - xennet_free_netdev(netdev); - dev_set_drvdata(&dev->dev, NULL); - return err; } static void xennet_end_access(int ref, void *page) @@ -1737,8 +1730,6 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i; - rtnl_lock(); - for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i]; @@ -1747,8 +1738,6 @@ static void xennet_destroy_queues(struct netfront_info *info) netif_napi_del(&queue->napi); } - rtnl_unlock(); - kfree(info->queues); info->queues = NULL; } @@ -1764,8 +1753,6 @@ static int xennet_create_queues(struct netfront_info *info, if (!info->queues) return -ENOMEM; - rtnl_lock(); - for (i = 0; i < *num_queues; i++) { struct netfront_queue *queue = &info->queues[i]; @@ -1774,7 +1761,7 @@ static int xennet_create_queues(struct netfront_info *info, ret = xennet_init_queue(queue); if (ret < 0) { - dev_warn(&info->netdev->dev, + dev_warn(&info->xbdev->dev, "only created %d queues\n", i); *num_queues = i; break; @@ -1788,10 +1775,8 @@ static int xennet_create_queues(struct netfront_info *info, netif_set_real_num_tx_queues(info->netdev, *num_queues); - rtnl_unlock(); - if (*num_queues == 0) { - dev_err(&info->netdev->dev, "no queues\n"); + dev_err(&info->xbdev->dev, "no queues\n"); return -EINVAL; } return 0; @@ -1828,6 +1813,7 @@ static int talk_to_netback(struct xenbus_device *dev, goto out; } + rtnl_lock(); if (info->queues) xennet_destroy_queues(info); @@ -1838,6 +1824,7 @@ static int talk_to_netback(struct xenbus_device *dev, info->queues = NULL; goto out; } + rtnl_unlock(); /* Create shared ring, alloc event channel -- for each queue */ for (i = 0; i < num_queues; ++i) { @@ -1934,8 +1921,10 @@ abort_transaction_no_dev_fatal: xenbus_transaction_end(xbt, 1); destroy_ring: xennet_disconnect_backend(info); + rtnl_lock(); xennet_destroy_queues(info); out: + rtnl_unlock(); device_unregister(&dev->dev); return err; } @@ -1965,6 +1954,15 @@ static int xennet_connect(struct net_device *dev) netdev_update_features(dev); rtnl_unlock(); + if (dev->reg_state == NETREG_UNINITIALIZED) { + err = register_netdev(dev); + if (err) { + pr_warn("%s: register_netdev err=%d\n", __func__, err); + device_unregister(&np->xbdev->dev); + return err; + } + } + /* * All public and private state should now be sane. Get * ready to start sending and receiving packets and give the driver @@ -2150,10 +2148,14 @@ static int xennet_remove(struct xenbus_device *dev) xennet_disconnect_backend(info); - unregister_netdev(info->netdev); + if (info->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(info->netdev); - if (info->queues) + if (info->queues) { + rtnl_lock(); xennet_destroy_queues(info); + rtnl_unlock(); + } xennet_free_netdev(info->netdev); return 0; diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c index 3903d90fe51c..41713f16ff97 100644 --- a/drivers/pci/hotplug/acpiphp_ibm.c +++ b/drivers/pci/hotplug/acpiphp_ibm.c @@ -385,6 +385,7 @@ static acpi_status __init ibm_find_acpi_device(acpi_handle handle, u32 lvl, void *context, void **rv) { acpi_handle *phandle = (acpi_handle *)context; + unsigned long long current_status = 0; acpi_status status; struct acpi_device_info *info; int retval = 0; @@ -396,7 +397,9 @@ static acpi_status __init ibm_find_acpi_device(acpi_handle handle, return retval; } - if (info->current_status && (info->valid & ACPI_VALID_HID) && + acpi_bus_get_status_handle(handle, ¤t_status); + + if (current_status && (info->valid & ACPI_VALID_HID) && (!strcmp(info->hardware_id.string, IBM_HARDWARE_ID1) || !strcmp(info->hardware_id.string, IBM_HARDWARE_ID2))) { pr_debug("found hardware: %s, handle: %p\n", diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index a60c0ab7883d..47cd0c037433 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -511,15 +511,15 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait) poll_wait(filp, &stdev->event_wq, wait); if (lock_mutex_and_test_alive(stdev)) - return POLLIN | POLLRDHUP | POLLOUT | POLLERR | POLLHUP; + return EPOLLIN | EPOLLRDHUP | EPOLLOUT | EPOLLERR | EPOLLHUP; mutex_unlock(&stdev->mrpc_mutex); if (try_wait_for_completion(&stuser->comp)) - ret |= POLLIN | POLLRDNORM; + ret |= EPOLLIN | EPOLLRDNORM; if (stuser->event_cnt != atomic_read(&stdev->event_cnt)) - ret |= POLLPRI | POLLRDBAND; + ret |= EPOLLPRI | EPOLLRDBAND; return ret; } diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c index 5ef7b46a2578..49377d502b74 100644 --- a/drivers/pcmcia/rsrc_nonstatic.c +++ b/drivers/pcmcia/rsrc_nonstatic.c @@ -367,7 +367,7 @@ static int do_validate_mem(struct pcmcia_socket *s, } } - dev_dbg(&s->dev, "cs: memory probe 0x%06lx-0x%06lx: %p %p %u %u %u", + dev_dbg(&s->dev, "cs: memory probe 0x%06lx-0x%06lx: %pr %pr %u %u %u", base, base+size-1, res1, res2, ret, info1, info2); free_region(res2); diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c index 764650eb8897..c5f2344c189b 100644 --- a/drivers/pcmcia/soc_common.c +++ b/drivers/pcmcia/soc_common.c @@ -191,12 +191,16 @@ static int soc_pcmcia_hw_init(struct soc_pcmcia_socket *skt) { int ret = 0, i; - clk_prepare_enable(skt->clk); + ret = clk_prepare_enable(skt->clk); + if (ret) + return ret; if (skt->ops->hw_init) { ret = skt->ops->hw_init(skt); - if (ret) + if (ret) { + clk_disable_unprepare(skt->clk); return ret; + } } for (i = 0; i < ARRAY_SIZE(skt->stat); i++) { diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c index 93c50e377507..38f2cc2a6c74 100644 --- a/drivers/perf/arm_dsu_pmu.c +++ b/drivers/perf/arm_dsu_pmu.c @@ -658,10 +658,8 @@ static void dsu_pmu_probe_pmu(struct dsu_pmu *dsu_pmu) return; cpmceid[0] = __dsu_pmu_read_pmceid(0); cpmceid[1] = __dsu_pmu_read_pmceid(1); - bitmap_from_u32array(dsu_pmu->cpmceid_bitmap, - DSU_PMU_MAX_COMMON_EVENTS, - cpmceid, - ARRAY_SIZE(cpmceid)); + bitmap_from_arr32(dsu_pmu->cpmceid_bitmap, cpmceid, + DSU_PMU_MAX_COMMON_EVENTS); } static void dsu_pmu_set_active_cpu(int cpu, struct dsu_pmu *dsu_pmu) diff --git a/drivers/platform/Kconfig b/drivers/platform/Kconfig index c11db8bceea1..d4c2e424a700 100644 --- a/drivers/platform/Kconfig +++ b/drivers/platform/Kconfig @@ -8,3 +8,5 @@ endif source "drivers/platform/goldfish/Kconfig" source "drivers/platform/chrome/Kconfig" + +source "drivers/platform/mellanox/Kconfig" diff --git a/drivers/platform/Makefile b/drivers/platform/Makefile index d3a6630266a0..4b2ce58bcd9c 100644 --- a/drivers/platform/Makefile +++ b/drivers/platform/Makefile @@ -4,6 +4,7 @@ # obj-$(CONFIG_X86) += x86/ +obj-$(CONFIG_MELLANOX_PLATFORM) += mellanox/ obj-$(CONFIG_MIPS) += mips/ obj-$(CONFIG_OLPC) += olpc/ obj-$(CONFIG_GOLDFISH) += goldfish/ diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c index d8599736a41a..6dec6ab13300 100644 --- a/drivers/platform/chrome/chromeos_laptop.c +++ b/drivers/platform/chrome/chromeos_laptop.c @@ -423,7 +423,7 @@ static int chromeos_laptop_probe(struct platform_device *pdev) return ret; } -static struct chromeos_laptop samsung_series_5_550 = { +static const struct chromeos_laptop samsung_series_5_550 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, @@ -432,14 +432,14 @@ static struct chromeos_laptop samsung_series_5_550 = { }, }; -static struct chromeos_laptop samsung_series_5 = { +static const struct chromeos_laptop samsung_series_5 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2583_als, I2C_ADAPTER_SMBUS }, }, }; -static struct chromeos_laptop chromebook_pixel = { +static const struct chromeos_laptop chromebook_pixel = { .i2c_peripherals = { /* Touch Screen. */ { .add = setup_atmel_1664s_ts, I2C_ADAPTER_PANEL }, @@ -450,14 +450,14 @@ static struct chromeos_laptop chromebook_pixel = { }, }; -static struct chromeos_laptop hp_chromebook_14 = { +static const struct chromeos_laptop hp_chromebook_14 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, }, }; -static struct chromeos_laptop dell_chromebook_11 = { +static const struct chromeos_laptop dell_chromebook_11 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, @@ -466,28 +466,28 @@ static struct chromeos_laptop dell_chromebook_11 = { }, }; -static struct chromeos_laptop toshiba_cb35 = { +static const struct chromeos_laptop toshiba_cb35 = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_DESIGNWARE_0 }, }, }; -static struct chromeos_laptop acer_c7_chromebook = { +static const struct chromeos_laptop acer_c7_chromebook = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, }, }; -static struct chromeos_laptop acer_ac700 = { +static const struct chromeos_laptop acer_ac700 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS }, }, }; -static struct chromeos_laptop acer_c720 = { +static const struct chromeos_laptop acer_c720 = { .i2c_peripherals = { /* Touchscreen. */ { .add = setup_atmel_1664s_ts, I2C_ADAPTER_DESIGNWARE_1 }, @@ -500,14 +500,14 @@ static struct chromeos_laptop acer_c720 = { }, }; -static struct chromeos_laptop hp_pavilion_14_chromebook = { +static const struct chromeos_laptop hp_pavilion_14_chromebook = { .i2c_peripherals = { /* Touchpad. */ { .add = setup_cyapa_tp, I2C_ADAPTER_SMBUS }, }, }; -static struct chromeos_laptop cr48 = { +static const struct chromeos_laptop cr48 = { .i2c_peripherals = { /* Light Sensor. */ { .add = setup_tsl2563_als, I2C_ADAPTER_SMBUS }, diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c index 5473e602f7e0..0e88e18362c1 100644 --- a/drivers/platform/chrome/cros_ec_debugfs.c +++ b/drivers/platform/chrome/cros_ec_debugfs.c @@ -200,7 +200,7 @@ static __poll_t cros_ec_console_log_poll(struct file *file, if (CIRC_CNT(debug_info->log_buffer.head, debug_info->log_buffer.tail, LOG_SIZE)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; mutex_unlock(&debug_info->log_mutex); return mask; diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 1baf720faf69..af89e82eecd2 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -35,6 +35,9 @@ #define DRV_NAME "cros_ec_lpcs" #define ACPI_DRV_NAME "GOOG0004" +/* True if ACPI device is present */ +static bool cros_ec_lpc_acpi_device_found; + static int ec_response_timed_out(void) { unsigned long one_second = jiffies + HZ; @@ -54,7 +57,6 @@ static int ec_response_timed_out(void) static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, struct cros_ec_command *msg) { - struct ec_host_request *request; struct ec_host_response response; u8 sum; int ret = 0; @@ -65,8 +67,6 @@ static int cros_ec_pkt_xfer_lpc(struct cros_ec_device *ec, /* Write buffer */ cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_PACKET, ret, ec->dout); - request = (struct ec_host_request *)ec->dout; - /* Here we go */ sum = EC_COMMAND_PROTOCOL_3; cros_ec_lpc_write_bytes(EC_LPC_ADDR_HOST_CMD, 1, &sum); @@ -362,6 +362,13 @@ static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "Peppy"), }, }, + { + /* x86-glimmer, the Lenovo Thinkpad Yoga 11e. */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), + DMI_MATCH(DMI_PRODUCT_NAME, "Glimmer"), + }, + }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(dmi, cros_ec_lpc_dmi_table); @@ -396,9 +403,21 @@ static struct platform_driver cros_ec_lpc_driver = { .remove = cros_ec_lpc_remove, }; +static struct platform_device cros_ec_lpc_device = { + .name = DRV_NAME +}; + +static acpi_status cros_ec_lpc_parse_device(acpi_handle handle, u32 level, + void *context, void **retval) +{ + *(bool *)context = true; + return AE_CTRL_TERMINATE; +} + static int __init cros_ec_lpc_init(void) { int ret; + acpi_status status; if (!dmi_check_system(cros_ec_lpc_dmi_table)) { pr_err(DRV_NAME ": unsupported system.\n"); @@ -415,11 +434,28 @@ static int __init cros_ec_lpc_init(void) return ret; } - return 0; + status = acpi_get_devices(ACPI_DRV_NAME, cros_ec_lpc_parse_device, + &cros_ec_lpc_acpi_device_found, NULL); + if (ACPI_FAILURE(status)) + pr_warn(DRV_NAME ": Looking for %s failed\n", ACPI_DRV_NAME); + + if (!cros_ec_lpc_acpi_device_found) { + /* Register the device, and it'll get hooked up automatically */ + ret = platform_device_register(&cros_ec_lpc_device); + if (ret) { + pr_err(DRV_NAME ": can't register device: %d\n", ret); + platform_driver_unregister(&cros_ec_lpc_driver); + cros_ec_lpc_reg_destroy(); + } + } + + return ret; } static void __exit cros_ec_lpc_exit(void) { + if (!cros_ec_lpc_acpi_device_found) + platform_device_unregister(&cros_ec_lpc_device); platform_driver_unregister(&cros_ec_lpc_driver); cros_ec_lpc_reg_destroy(); } diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 8dfa7fcb1248..e7bbdf947bbc 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -60,12 +60,14 @@ static int send_command(struct cros_ec_device *ec_dev, struct cros_ec_command *msg) { int ret; + int (*xfer_fxn)(struct cros_ec_device *ec, struct cros_ec_command *msg); if (ec_dev->proto_version > 2) - ret = ec_dev->pkt_xfer(ec_dev, msg); + xfer_fxn = ec_dev->pkt_xfer; else - ret = ec_dev->cmd_xfer(ec_dev, msg); + xfer_fxn = ec_dev->cmd_xfer; + ret = (*xfer_fxn)(ec_dev, msg); if (msg->result == EC_RES_IN_PROGRESS) { int i; struct cros_ec_command *status_msg; @@ -88,7 +90,7 @@ static int send_command(struct cros_ec_device *ec_dev, for (i = 0; i < EC_COMMAND_RETRIES; i++) { usleep_range(10000, 11000); - ret = ec_dev->cmd_xfer(ec_dev, status_msg); + ret = (*xfer_fxn)(ec_dev, status_msg); if (ret < 0) break; diff --git a/drivers/platform/chrome/cros_ec_sysfs.c b/drivers/platform/chrome/cros_ec_sysfs.c index d6eebe872187..da0a719d32f7 100644 --- a/drivers/platform/chrome/cros_ec_sysfs.c +++ b/drivers/platform/chrome/cros_ec_sysfs.c @@ -185,7 +185,7 @@ static ssize_t show_ec_version(struct device *dev, count += scnprintf(buf + count, PAGE_SIZE - count, "Build info: EC error %d\n", msg->result); else { - msg->data[sizeof(msg->data) - 1] = '\0'; + msg->data[EC_HOST_PARAM_SIZE - 1] = '\0'; count += scnprintf(buf + count, PAGE_SIZE - count, "Build info: %s\n", msg->data); } diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c index 999f1152655a..3e32a4c14d5f 100644 --- a/drivers/platform/goldfish/goldfish_pipe.c +++ b/drivers/platform/goldfish/goldfish_pipe.c @@ -549,13 +549,13 @@ static __poll_t goldfish_pipe_poll(struct file *filp, poll_table *wait) return -ERESTARTSYS; if (status & PIPE_POLL_IN) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (status & PIPE_POLL_OUT) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; if (status & PIPE_POLL_HUP) - mask |= POLLHUP; + mask |= EPOLLHUP; if (test_bit(BIT_CLOSED_ON_HOST, &pipe->flags)) - mask |= POLLERR; + mask |= EPOLLERR; return mask; } diff --git a/drivers/platform/mellanox/Kconfig b/drivers/platform/mellanox/Kconfig new file mode 100644 index 000000000000..591bccdeaff9 --- /dev/null +++ b/drivers/platform/mellanox/Kconfig @@ -0,0 +1,26 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Platform support for Mellanox hardware +# + +menuconfig MELLANOX_PLATFORM + bool "Platform support for Mellanox hardware" + depends on X86 || ARM || COMPILE_TEST + ---help--- + Say Y here to get to see options for platform support for + Mellanox systems. This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped and disabled. + +if MELLANOX_PLATFORM + +config MLXREG_HOTPLUG + tristate "Mellanox platform hotplug driver support" + depends on REGMAP + depends on HWMON + depends on I2C + ---help--- + This driver handles hot-plug events for the power suppliers, power + cables and fans on the wide range Mellanox IB and Ethernet systems. + +endif # MELLANOX_PLATFORM diff --git a/drivers/platform/mellanox/Makefile b/drivers/platform/mellanox/Makefile new file mode 100644 index 000000000000..7c8385e497a8 --- /dev/null +++ b/drivers/platform/mellanox/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for linux/drivers/platform/mellanox +# Mellanox Platform-Specific Drivers +# +obj-$(CONFIG_MLXREG_HOTPLUG) += mlxreg-hotplug.o diff --git a/drivers/platform/mellanox/mlxreg-hotplug.c b/drivers/platform/mellanox/mlxreg-hotplug.c new file mode 100644 index 000000000000..313cf8ad77bf --- /dev/null +++ b/drivers/platform/mellanox/mlxreg-hotplug.c @@ -0,0 +1,638 @@ +/* + * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2018 Vadim Pasternak <vadimp@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/bitops.h> +#include <linux/device.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/platform_data/mlxreg.h> +#include <linux/platform_device.h> +#include <linux/spinlock.h> +#include <linux/regmap.h> +#include <linux/workqueue.h> + +/* Offset of event and mask registers from status register. */ +#define MLXREG_HOTPLUG_EVENT_OFF 1 +#define MLXREG_HOTPLUG_MASK_OFF 2 +#define MLXREG_HOTPLUG_AGGR_MASK_OFF 1 + +/* ASIC health parameters. */ +#define MLXREG_HOTPLUG_HEALTH_MASK 0x02 +#define MLXREG_HOTPLUG_RST_CNTR 3 + +#define MLXREG_HOTPLUG_ATTRS_MAX 24 + +/** + * struct mlxreg_hotplug_priv_data - platform private data: + * @irq: platform device interrupt number; + * @pdev: platform device; + * @plat: platform data; + * @dwork: delayed work template; + * @lock: spin lock; + * @hwmon: hwmon device; + * @mlxreg_hotplug_attr: sysfs attributes array; + * @mlxreg_hotplug_dev_attr: sysfs sensor device attribute array; + * @group: sysfs attribute group; + * @groups: list of sysfs attribute group for hwmon registration; + * @cell: location of top aggregation interrupt register; + * @mask: top aggregation interrupt common mask; + * @aggr_cache: last value of aggregation register status; + */ +struct mlxreg_hotplug_priv_data { + int irq; + struct device *dev; + struct platform_device *pdev; + struct mlxreg_hotplug_platform_data *plat; + struct regmap *regmap; + struct delayed_work dwork_irq; + struct delayed_work dwork; + spinlock_t lock; /* sync with interrupt */ + struct device *hwmon; + struct attribute *mlxreg_hotplug_attr[MLXREG_HOTPLUG_ATTRS_MAX + 1]; + struct sensor_device_attribute_2 + mlxreg_hotplug_dev_attr[MLXREG_HOTPLUG_ATTRS_MAX]; + struct attribute_group group; + const struct attribute_group *groups[2]; + u32 cell; + u32 mask; + u32 aggr_cache; + bool after_probe; +}; + +static int mlxreg_hotplug_device_create(struct device *dev, + struct mlxreg_core_data *data) +{ + /* + * Return if adapter number is negative. It could be in case hotplug + * event is not associated with hotplug device. + */ + if (data->hpdev.nr < 0) + return 0; + + data->hpdev.adapter = i2c_get_adapter(data->hpdev.nr); + if (!data->hpdev.adapter) { + dev_err(dev, "Failed to get adapter for bus %d\n", + data->hpdev.nr); + return -EFAULT; + } + + data->hpdev.client = i2c_new_device(data->hpdev.adapter, + data->hpdev.brdinfo); + if (!data->hpdev.client) { + dev_err(dev, "Failed to create client %s at bus %d at addr 0x%02x\n", + data->hpdev.brdinfo->type, data->hpdev.nr, + data->hpdev.brdinfo->addr); + + i2c_put_adapter(data->hpdev.adapter); + data->hpdev.adapter = NULL; + return -EFAULT; + } + + return 0; +} + +static void mlxreg_hotplug_device_destroy(struct mlxreg_core_data *data) +{ + if (data->hpdev.client) { + i2c_unregister_device(data->hpdev.client); + data->hpdev.client = NULL; + } + + if (data->hpdev.adapter) { + i2c_put_adapter(data->hpdev.adapter); + data->hpdev.adapter = NULL; + } +} + +static ssize_t mlxreg_hotplug_attr_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxreg_hotplug_priv_data *priv = dev_get_drvdata(dev); + struct mlxreg_core_hotplug_platform_data *pdata; + int index = to_sensor_dev_attr_2(attr)->index; + int nr = to_sensor_dev_attr_2(attr)->nr; + struct mlxreg_core_item *item; + struct mlxreg_core_data *data; + u32 regval; + int ret; + + pdata = dev_get_platdata(&priv->pdev->dev); + item = pdata->items + nr; + data = item->data + index; + + ret = regmap_read(priv->regmap, data->reg, ®val); + if (ret) + return ret; + + if (item->health) { + regval &= data->mask; + } else { + /* Bit = 0 : functional if item->inversed is true. */ + if (item->inversed) + regval = !(regval & data->mask); + else + regval = !!(regval & data->mask); + } + + return sprintf(buf, "%u\n", regval); +} + +#define PRIV_ATTR(i) priv->mlxreg_hotplug_attr[i] +#define PRIV_DEV_ATTR(i) priv->mlxreg_hotplug_dev_attr[i] + +static int mlxreg_hotplug_attr_init(struct mlxreg_hotplug_priv_data *priv) +{ + struct mlxreg_core_hotplug_platform_data *pdata; + struct mlxreg_core_item *item; + struct mlxreg_core_data *data; + int num_attrs = 0, id = 0, i, j; + + pdata = dev_get_platdata(&priv->pdev->dev); + item = pdata->items; + + /* Go over all kinds of items - psu, pwr, fan. */ + for (i = 0; i < pdata->counter; i++, item++) { + num_attrs += item->count; + data = item->data; + /* Go over all units within the item. */ + for (j = 0; j < item->count; j++, data++, id++) { + PRIV_ATTR(id) = &PRIV_DEV_ATTR(id).dev_attr.attr; + PRIV_ATTR(id)->name = devm_kasprintf(&priv->pdev->dev, + GFP_KERNEL, + data->label); + + if (!PRIV_ATTR(id)->name) { + dev_err(priv->dev, "Memory allocation failed for attr %d.\n", + id); + return -ENOMEM; + } + + PRIV_DEV_ATTR(id).dev_attr.attr.name = + PRIV_ATTR(id)->name; + PRIV_DEV_ATTR(id).dev_attr.attr.mode = 0444; + PRIV_DEV_ATTR(id).dev_attr.show = + mlxreg_hotplug_attr_show; + PRIV_DEV_ATTR(id).nr = i; + PRIV_DEV_ATTR(id).index = j; + sysfs_attr_init(&PRIV_DEV_ATTR(id).dev_attr.attr); + } + } + + priv->group.attrs = devm_kzalloc(&priv->pdev->dev, num_attrs * + sizeof(struct attribute *), + GFP_KERNEL); + if (!priv->group.attrs) + return -ENOMEM; + + priv->group.attrs = priv->mlxreg_hotplug_attr; + priv->groups[0] = &priv->group; + priv->groups[1] = NULL; + + return 0; +} + +static void +mlxreg_hotplug_work_helper(struct mlxreg_hotplug_priv_data *priv, + struct mlxreg_core_item *item) +{ + struct mlxreg_core_data *data; + u32 asserted, regval, bit; + int ret; + + /* + * Validate if item related to received signal type is valid. + * It should never happen, excepted the situation when some + * piece of hardware is broken. In such situation just produce + * error message and return. Caller must continue to handle the + * signals from other devices if any. + */ + if (unlikely(!item)) { + dev_err(priv->dev, "False signal: at offset:mask 0x%02x:0x%02x.\n", + item->reg, item->mask); + + return; + } + + /* Mask event. */ + ret = regmap_write(priv->regmap, item->reg + MLXREG_HOTPLUG_MASK_OFF, + 0); + if (ret) + goto out; + + /* Read status. */ + ret = regmap_read(priv->regmap, item->reg, ®val); + if (ret) + goto out; + + /* Set asserted bits and save last status. */ + regval &= item->mask; + asserted = item->cache ^ regval; + item->cache = regval; + + for_each_set_bit(bit, (unsigned long *)&asserted, 8) { + data = item->data + bit; + if (regval & BIT(bit)) { + if (item->inversed) + mlxreg_hotplug_device_destroy(data); + else + mlxreg_hotplug_device_create(priv->dev, data); + } else { + if (item->inversed) + mlxreg_hotplug_device_create(priv->dev, data); + else + mlxreg_hotplug_device_destroy(data); + } + } + + /* Acknowledge event. */ + ret = regmap_write(priv->regmap, item->reg + MLXREG_HOTPLUG_EVENT_OFF, + 0); + if (ret) + goto out; + + /* Unmask event. */ + ret = regmap_write(priv->regmap, item->reg + MLXREG_HOTPLUG_MASK_OFF, + item->mask); + + out: + if (ret) + dev_err(priv->dev, "Failed to complete workqueue.\n"); +} + +static void +mlxreg_hotplug_health_work_helper(struct mlxreg_hotplug_priv_data *priv, + struct mlxreg_core_item *item) +{ + struct mlxreg_core_data *data = item->data; + u32 regval; + int i, ret = 0; + + for (i = 0; i < item->count; i++, data++) { + /* Mask event. */ + ret = regmap_write(priv->regmap, data->reg + + MLXREG_HOTPLUG_MASK_OFF, 0); + if (ret) + goto out; + + /* Read status. */ + ret = regmap_read(priv->regmap, data->reg, ®val); + if (ret) + goto out; + + regval &= data->mask; + item->cache = regval; + if (regval == MLXREG_HOTPLUG_HEALTH_MASK) { + if ((data->health_cntr++ == MLXREG_HOTPLUG_RST_CNTR) || + !priv->after_probe) { + mlxreg_hotplug_device_create(priv->dev, data); + data->attached = true; + } + } else { + if (data->attached) { + mlxreg_hotplug_device_destroy(data); + data->attached = false; + data->health_cntr = 0; + } + } + + /* Acknowledge event. */ + ret = regmap_write(priv->regmap, data->reg + + MLXREG_HOTPLUG_EVENT_OFF, 0); + if (ret) + goto out; + + /* Unmask event. */ + ret = regmap_write(priv->regmap, data->reg + + MLXREG_HOTPLUG_MASK_OFF, data->mask); + if (ret) + goto out; + } + + out: + if (ret) + dev_err(priv->dev, "Failed to complete workqueue.\n"); +} + +/* + * mlxreg_hotplug_work_handler - performs traversing of device interrupt + * registers according to the below hierarchy schema: + * + * Aggregation registers (status/mask) + * PSU registers: *---* + * *-----------------* | | + * |status/event/mask|-----> | * | + * *-----------------* | | + * Power registers: | | + * *-----------------* | | + * |status/event/mask|-----> | * | + * *-----------------* | | + * FAN registers: | |--> CPU + * *-----------------* | | + * |status/event/mask|-----> | * | + * *-----------------* | | + * ASIC registers: | | + * *-----------------* | | + * |status/event/mask|-----> | * | + * *-----------------* | | + * *---* + * + * In case some system changed are detected: FAN in/out, PSU in/out, power + * cable attached/detached, ASIC health good/bad, relevant device is created + * or destroyed. + */ +static void mlxreg_hotplug_work_handler(struct work_struct *work) +{ + struct mlxreg_core_hotplug_platform_data *pdata; + struct mlxreg_hotplug_priv_data *priv; + struct mlxreg_core_item *item; + u32 regval, aggr_asserted; + unsigned long flags; + int i, ret; + + priv = container_of(work, struct mlxreg_hotplug_priv_data, + dwork_irq.work); + pdata = dev_get_platdata(&priv->pdev->dev); + item = pdata->items; + + /* Mask aggregation event. */ + ret = regmap_write(priv->regmap, pdata->cell + + MLXREG_HOTPLUG_AGGR_MASK_OFF, 0); + if (ret < 0) + goto out; + + /* Read aggregation status. */ + ret = regmap_read(priv->regmap, pdata->cell, ®val); + if (ret) + goto out; + + regval &= pdata->mask; + aggr_asserted = priv->aggr_cache ^ regval; + priv->aggr_cache = regval; + + /* Handle topology and health configuration changes. */ + for (i = 0; i < pdata->counter; i++, item++) { + if (aggr_asserted & item->aggr_mask) { + if (item->health) + mlxreg_hotplug_health_work_helper(priv, item); + else + mlxreg_hotplug_work_helper(priv, item); + } + } + + if (aggr_asserted) { + spin_lock_irqsave(&priv->lock, flags); + + /* + * It is possible, that some signals have been inserted, while + * interrupt has been masked by mlxreg_hotplug_work_handler. + * In this case such signals will be missed. In order to handle + * these signals delayed work is canceled and work task + * re-scheduled for immediate execution. It allows to handle + * missed signals, if any. In other case work handler just + * validates that no new signals have been received during + * masking. + */ + cancel_delayed_work(&priv->dwork_irq); + schedule_delayed_work(&priv->dwork_irq, 0); + + spin_unlock_irqrestore(&priv->lock, flags); + + return; + } + + /* Unmask aggregation event (no need acknowledge). */ + ret = regmap_write(priv->regmap, pdata->cell + + MLXREG_HOTPLUG_AGGR_MASK_OFF, pdata->mask); + + out: + if (ret) + dev_err(priv->dev, "Failed to complete workqueue.\n"); +} + +static int mlxreg_hotplug_set_irq(struct mlxreg_hotplug_priv_data *priv) +{ + struct mlxreg_core_hotplug_platform_data *pdata; + struct mlxreg_core_item *item; + int i, ret; + + pdata = dev_get_platdata(&priv->pdev->dev); + item = pdata->items; + + for (i = 0; i < pdata->counter; i++, item++) { + /* Clear group presense event. */ + ret = regmap_write(priv->regmap, item->reg + + MLXREG_HOTPLUG_EVENT_OFF, 0); + if (ret) + goto out; + + /* Set group initial status as mask and unmask group event. */ + if (item->inversed) { + item->cache = item->mask; + ret = regmap_write(priv->regmap, item->reg + + MLXREG_HOTPLUG_MASK_OFF, + item->mask); + if (ret) + goto out; + } + } + + /* Keep aggregation initial status as zero and unmask events. */ + ret = regmap_write(priv->regmap, pdata->cell + + MLXREG_HOTPLUG_AGGR_MASK_OFF, pdata->mask); + if (ret) + goto out; + + /* Keep low aggregation initial status as zero and unmask events. */ + if (pdata->cell_low) { + ret = regmap_write(priv->regmap, pdata->cell_low + + MLXREG_HOTPLUG_AGGR_MASK_OFF, + pdata->mask_low); + if (ret) + goto out; + } + + /* Invoke work handler for initializing hot plug devices setting. */ + mlxreg_hotplug_work_handler(&priv->dwork_irq.work); + + out: + if (ret) + dev_err(priv->dev, "Failed to set interrupts.\n"); + enable_irq(priv->irq); + return ret; +} + +static void mlxreg_hotplug_unset_irq(struct mlxreg_hotplug_priv_data *priv) +{ + struct mlxreg_core_hotplug_platform_data *pdata; + struct mlxreg_core_item *item; + struct mlxreg_core_data *data; + int count, i, j; + + pdata = dev_get_platdata(&priv->pdev->dev); + item = pdata->items; + disable_irq(priv->irq); + cancel_delayed_work_sync(&priv->dwork_irq); + + /* Mask low aggregation event, if defined. */ + if (pdata->cell_low) + regmap_write(priv->regmap, pdata->cell_low + + MLXREG_HOTPLUG_AGGR_MASK_OFF, 0); + + /* Mask aggregation event. */ + regmap_write(priv->regmap, pdata->cell + MLXREG_HOTPLUG_AGGR_MASK_OFF, + 0); + + /* Clear topology configurations. */ + for (i = 0; i < pdata->counter; i++, item++) { + data = item->data; + /* Mask group presense event. */ + regmap_write(priv->regmap, data->reg + MLXREG_HOTPLUG_MASK_OFF, + 0); + /* Clear group presense event. */ + regmap_write(priv->regmap, data->reg + + MLXREG_HOTPLUG_EVENT_OFF, 0); + + /* Remove all the attached devices in group. */ + count = item->count; + for (j = 0; j < count; j++, data++) + mlxreg_hotplug_device_destroy(data); + } +} + +static irqreturn_t mlxreg_hotplug_irq_handler(int irq, void *dev) +{ + struct mlxreg_hotplug_priv_data *priv; + + priv = (struct mlxreg_hotplug_priv_data *)dev; + + /* Schedule work task for immediate execution.*/ + schedule_delayed_work(&priv->dwork_irq, 0); + + return IRQ_HANDLED; +} + +static int mlxreg_hotplug_probe(struct platform_device *pdev) +{ + struct mlxreg_core_hotplug_platform_data *pdata; + struct mlxreg_hotplug_priv_data *priv; + int err; + + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + dev_err(&pdev->dev, "Failed to get platform data.\n"); + return -EINVAL; + } + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + if (pdata->irq) { + priv->irq = pdata->irq; + } else { + priv->irq = platform_get_irq(pdev, 0); + if (priv->irq < 0) { + dev_err(&pdev->dev, "Failed to get platform irq: %d\n", + priv->irq); + return priv->irq; + } + } + + priv->regmap = pdata->regmap; + priv->dev = pdev->dev.parent; + priv->pdev = pdev; + + err = devm_request_irq(&pdev->dev, priv->irq, + mlxreg_hotplug_irq_handler, IRQF_TRIGGER_FALLING + | IRQF_SHARED, "mlxreg-hotplug", priv); + if (err) { + dev_err(&pdev->dev, "Failed to request irq: %d\n", err); + return err; + } + + disable_irq(priv->irq); + spin_lock_init(&priv->lock); + INIT_DELAYED_WORK(&priv->dwork_irq, mlxreg_hotplug_work_handler); + /* Perform initial interrupts setup. */ + mlxreg_hotplug_set_irq(priv); + + priv->after_probe = true; + dev_set_drvdata(&pdev->dev, priv); + + err = mlxreg_hotplug_attr_init(priv); + if (err) { + dev_err(&pdev->dev, "Failed to allocate attributes: %d\n", + err); + return err; + } + + priv->hwmon = devm_hwmon_device_register_with_groups(&pdev->dev, + "mlxreg_hotplug", priv, priv->groups); + if (IS_ERR(priv->hwmon)) { + dev_err(&pdev->dev, "Failed to register hwmon device %ld\n", + PTR_ERR(priv->hwmon)); + return PTR_ERR(priv->hwmon); + } + + return 0; +} + +static int mlxreg_hotplug_remove(struct platform_device *pdev) +{ + struct mlxreg_hotplug_priv_data *priv = dev_get_drvdata(&pdev->dev); + + /* Clean interrupts setup. */ + mlxreg_hotplug_unset_irq(priv); + + return 0; +} + +static struct platform_driver mlxreg_hotplug_driver = { + .driver = { + .name = "mlxreg-hotplug", + }, + .probe = mlxreg_hotplug_probe, + .remove = mlxreg_hotplug_remove, +}; + +module_platform_driver(mlxreg_hotplug_driver); + +MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>"); +MODULE_DESCRIPTION("Mellanox regmap hotplug platform driver"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("platform:mlxreg-hotplug"); diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 2c745e8ccad6..9a8f96465cdc 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -36,6 +36,20 @@ config ACER_WMI If you have an ACPI-WMI compatible Acer/ Wistron laptop, say Y or M here. +config ACER_WIRELESS + tristate "Acer Wireless Radio Control Driver" + depends on ACPI + depends on INPUT + ---help--- + The Acer Wireless Radio Control handles the airplane mode hotkey + present on new Acer laptops. + + Say Y or M here if you have an Acer notebook with an airplane mode + hotkey. + + If you choose to compile this driver as a module the module will be + called acer-wireless. + config ACERHDF tristate "Acer Aspire One temperature and fan driver" depends on ACPI && THERMAL @@ -244,6 +258,18 @@ config AMILO_RFKILL This is a driver for enabling wifi on some Fujitsu-Siemens Amilo laptops. +config GPD_POCKET_FAN + tristate "GPD Pocket Fan Controller support" + depends on ACPI + depends on THERMAL + ---help--- + Driver for the GPD Pocket vendor specific FAN02501 ACPI device + which controls the fan speed on the GPD Pocket. + + Without this driver the fan on the Pocket will stay off independent + of the CPU temperature. Say Y or M if the kernel may be used on a + GPD pocket. + config TC1100_WMI tristate "HP Compaq TC1100 Tablet WMI Extras" depends on !X86_64 @@ -812,9 +838,8 @@ config TOSHIBA_WMI config ACPI_CMPC tristate "CMPC Laptop Extras" - depends on ACPI + depends on ACPI && INPUT depends on RFKILL || RFKILL=n - select INPUT select BACKLIGHT_CLASS_DEVICE help Support for Intel Classmate PC ACPI devices, including some @@ -949,7 +974,7 @@ config INTEL_IMR If you are running on a Galileo/Quark say Y here. config INTEL_PMC_CORE - bool "Intel PMC Core driver" + tristate "Intel PMC Core driver" depends on PCI ---help--- The Intel Platform Controller Hub for Intel Core SoCs provides access @@ -958,7 +983,10 @@ config INTEL_PMC_CORE exposed by the Power Management Controller. Supported features: - - SLP_S0_RESIDENCY counter. + - SLP_S0_RESIDENCY counter + - PCH IP Power Gating status + - LTR Ignore + - MPHY/PLL gating status (Sunrisepoint PCH only) config IBM_RTL tristate "Device driver to enable PRTL support" @@ -1131,7 +1159,6 @@ config INTEL_TELEMETRY config MLX_PLATFORM tristate "Mellanox Technologies platform support" - depends on X86_64 ---help--- This option enables system support for the Mellanox Technologies platform. The Mellanox systems provide data center networking @@ -1141,14 +1168,6 @@ config MLX_PLATFORM If you have a Mellanox system, say Y or M here. -config MLX_CPLD_PLATFORM - tristate "Mellanox platform hotplug driver support" - select HWMON - select I2C - ---help--- - This driver handles hot-plug events for the power suppliers, power - cables and fans on the wide range Mellanox IB and Ethernet systems. - config INTEL_TURBO_MAX_3 bool "Intel Turbo Boost Max Technology 3.0 enumeration driver" depends on X86_64 && SCHED_MC_PRIO @@ -1170,6 +1189,17 @@ config SILEAD_DMI with the OS-image for the device. This option supplies the missing information. Enable this for x86 tablets with Silead touchscreens. +config INTEL_CHTDC_TI_PWRBTN + tristate "Intel Cherry Trail Dollar Cove TI power button driver" + depends on INTEL_SOC_PMIC_CHTDC_TI + depends on INPUT + ---help--- + This option adds a power button driver driver for Dollar Cove TI + PMIC on Intel Cherry Trail devices. + + To compile this driver as a module, choose M here: the module + will be called intel_chtdc_ti_pwrbtn. + endif # X86_PLATFORM_DEVICES config PMC_ATOM diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index c32b34a72467..c388608ad2a3 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -23,11 +23,13 @@ obj-$(CONFIG_DELL_WMI_LED) += dell-wmi-led.o obj-$(CONFIG_DELL_SMO8800) += dell-smo8800.o obj-$(CONFIG_DELL_RBTN) += dell-rbtn.o obj-$(CONFIG_ACER_WMI) += acer-wmi.o +obj-$(CONFIG_ACER_WIRELESS) += acer-wireless.o obj-$(CONFIG_ACERHDF) += acerhdf.o obj-$(CONFIG_HP_ACCEL) += hp_accel.o obj-$(CONFIG_HP_WIRELESS) += hp-wireless.o obj-$(CONFIG_HP_WMI) += hp-wmi.o obj-$(CONFIG_AMILO_RFKILL) += amilo-rfkill.o +obj-$(CONFIG_GPD_POCKET_FAN) += gpd-pocket-fan.o obj-$(CONFIG_TC1100_WMI) += tc1100-wmi.o obj-$(CONFIG_SONY_LAPTOP) += sony-laptop.o obj-$(CONFIG_IDEAPAD_LAPTOP) += ideapad-laptop.o @@ -86,5 +88,5 @@ obj-$(CONFIG_INTEL_TELEMETRY) += intel_telemetry_core.o \ obj-$(CONFIG_INTEL_PMC_CORE) += intel_pmc_core.o obj-$(CONFIG_PMC_ATOM) += pmc_atom.o obj-$(CONFIG_MLX_PLATFORM) += mlx-platform.o -obj-$(CONFIG_MLX_CPLD_PLATFORM) += mlxcpld-hotplug.o obj-$(CONFIG_INTEL_TURBO_MAX_3) += intel_turbo_max_3.o +obj-$(CONFIG_INTEL_CHTDC_TI_PWRBTN) += intel_chtdc_ti_pwrbtn.o diff --git a/drivers/platform/x86/acer-wireless.c b/drivers/platform/x86/acer-wireless.c new file mode 100644 index 000000000000..858037987b33 --- /dev/null +++ b/drivers/platform/x86/acer-wireless.c @@ -0,0 +1,71 @@ +/* + * Acer Wireless Radio Control Driver + * + * Copyright (C) 2017 Endless Mobile, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/acpi.h> +#include <linux/input.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci_ids.h> +#include <linux/types.h> + +static const struct acpi_device_id acer_wireless_acpi_ids[] = { + {"10251229", 0}, + {"", 0}, +}; +MODULE_DEVICE_TABLE(acpi, acer_wireless_acpi_ids); + +static void acer_wireless_notify(struct acpi_device *adev, u32 event) +{ + struct input_dev *idev = acpi_driver_data(adev); + + dev_dbg(&adev->dev, "event=%#x\n", event); + if (event != 0x80) { + dev_notice(&adev->dev, "Unknown SMKB event: %#x\n", event); + return; + } + input_report_key(idev, KEY_RFKILL, 1); + input_report_key(idev, KEY_RFKILL, 0); + input_sync(idev); +} + +static int acer_wireless_add(struct acpi_device *adev) +{ + struct input_dev *idev; + + idev = devm_input_allocate_device(&adev->dev); + if (!idev) + return -ENOMEM; + + adev->driver_data = idev; + idev->name = "Acer Wireless Radio Control"; + idev->phys = "acer-wireless/input0"; + idev->id.bustype = BUS_HOST; + idev->id.vendor = PCI_VENDOR_ID_AI; + idev->id.product = 0x1229; + set_bit(EV_KEY, idev->evbit); + set_bit(KEY_RFKILL, idev->keybit); + + return input_register_device(idev); +} + +static struct acpi_driver acer_wireless_driver = { + .name = "Acer Wireless Radio Control Driver", + .class = "hotkey", + .ids = acer_wireless_acpi_ids, + .ops = { + .add = acer_wireless_add, + .notify = acer_wireless_notify, + }, +}; +module_acpi_driver(acer_wireless_driver); + +MODULE_DESCRIPTION("Acer Wireless Radio Control Driver"); +MODULE_AUTHOR("Chris Chiu <chiu@gmail.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/alienware-wmi.c b/drivers/platform/x86/alienware-wmi.c index 4eb8e1a472b2..9d7dbd925065 100644 --- a/drivers/platform/x86/alienware-wmi.c +++ b/drivers/platform/x86/alienware-wmi.c @@ -68,6 +68,14 @@ struct quirk_entry { static struct quirk_entry *quirks; + +static struct quirk_entry quirk_inspiron5675 = { + .num_zones = 2, + .hdmi_mux = 0, + .amplifier = 0, + .deepslp = 0, +}; + static struct quirk_entry quirk_unknown = { .num_zones = 2, .hdmi_mux = 0, @@ -171,6 +179,15 @@ static const struct dmi_system_id alienware_quirks[] __initconst = { }, .driver_data = &quirk_asm201, }, + { + .callback = dmi_matched, + .ident = "Dell Inc. Inspiron 5675", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5675"), + }, + .driver_data = &quirk_inspiron5675, + }, {} }; diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c index 623d322447a2..7c4eb86c851e 100644 --- a/drivers/platform/x86/apple-gmux.c +++ b/drivers/platform/x86/apple-gmux.c @@ -24,7 +24,6 @@ #include <linux/delay.h> #include <linux/pci.h> #include <linux/vga_switcheroo.h> -#include <linux/vgaarb.h> #include <acpi/video.h> #include <asm/io.h> @@ -54,7 +53,6 @@ struct apple_gmux_data { bool indexed; struct mutex index_lock; - struct pci_dev *pdev; struct backlight_device *bdev; /* switcheroo data */ @@ -599,23 +597,6 @@ static int gmux_resume(struct device *dev) return 0; } -static struct pci_dev *gmux_get_io_pdev(void) -{ - struct pci_dev *pdev = NULL; - - while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev))) { - u16 cmd; - - pci_read_config_word(pdev, PCI_COMMAND, &cmd); - if (!(cmd & PCI_COMMAND_IO)) - continue; - - return pdev; - } - - return NULL; -} - static int is_thunderbolt(struct device *dev, void *data) { return to_pci_dev(dev)->is_thunderbolt; @@ -631,7 +612,6 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) int ret = -ENXIO; acpi_status status; unsigned long long gpe; - struct pci_dev *pdev = NULL; if (apple_gmux_data) return -EBUSY; @@ -682,7 +662,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) ver_minor = (version >> 16) & 0xff; ver_release = (version >> 8) & 0xff; } else { - pr_info("gmux device not present or IO disabled\n"); + pr_info("gmux device not present\n"); ret = -ENODEV; goto err_release; } @@ -690,23 +670,6 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) pr_info("Found gmux version %d.%d.%d [%s]\n", ver_major, ver_minor, ver_release, (gmux_data->indexed ? "indexed" : "classic")); - /* - * Apple systems with gmux are EFI based and normally don't use - * VGA. In addition changing IO+MEM ownership between IGP and dGPU - * disables IO/MEM used for backlight control on some systems. - * Lock IO+MEM to GPU with active IO to prevent switch. - */ - pdev = gmux_get_io_pdev(); - if (pdev && vga_tryget(pdev, - VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM)) { - pr_err("IO+MEM vgaarb-locking for PCI:%s failed\n", - pci_name(pdev)); - ret = -EBUSY; - goto err_release; - } else if (pdev) - pr_info("locked IO for PCI:%s\n", pci_name(pdev)); - gmux_data->pdev = pdev; - memset(&props, 0, sizeof(props)); props.type = BACKLIGHT_PLATFORM; props.max_brightness = gmux_read32(gmux_data, GMUX_PORT_MAX_BRIGHTNESS); @@ -822,10 +785,6 @@ err_enable_gpe: err_notify: backlight_device_unregister(bdev); err_release: - if (gmux_data->pdev) - vga_put(gmux_data->pdev, - VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM); - pci_dev_put(pdev); release_region(gmux_data->iostart, gmux_data->iolen); err_free: kfree(gmux_data); @@ -845,11 +804,6 @@ static void gmux_remove(struct pnp_dev *pnp) &gmux_notify_handler); } - if (gmux_data->pdev) { - vga_put(gmux_data->pdev, - VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM); - pci_dev_put(gmux_data->pdev); - } backlight_device_unregister(gmux_data->bdev); release_region(gmux_data->iostart, gmux_data->iolen); diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 5269a01d9bdd..136ff2b4cce5 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -111,7 +111,7 @@ static struct quirk_entry quirk_asus_x550lb = { .xusb2pr = 0x01D9, }; -static struct quirk_entry quirk_asus_ux330uak = { +static struct quirk_entry quirk_asus_forceals = { .wmi_force_als_set = true, }; @@ -387,7 +387,7 @@ static const struct dmi_system_id asus_quirks[] = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "UX330UAK"), }, - .driver_data = &quirk_asus_ux330uak, + .driver_data = &quirk_asus_forceals, }, { .callback = dmi_matched, @@ -398,6 +398,15 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_x550lb, }, + { + .callback = dmi_matched, + .ident = "ASUSTeK COMPUTER INC. UX430UQ", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "UX430UQ"), + }, + .driver_data = &quirk_asus_forceals, + }, {}, }; diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index cd4725e7e0b5..2a68f59d2228 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -36,10 +36,10 @@ #include "dell-smbios.h" struct quirk_entry { - u8 touchpad_led; - u8 kbd_led_levels_off_1; + bool touchpad_led; + bool kbd_led_levels_off_1; - int needs_kbd_timeouts; + bool needs_kbd_timeouts; /* * Ordered list of timeouts expressed in seconds. * The list must end with -1 @@ -50,7 +50,7 @@ struct quirk_entry { static struct quirk_entry *quirks; static struct quirk_entry quirk_dell_vostro_v130 = { - .touchpad_led = 1, + .touchpad_led = true, }; static int __init dmi_matched(const struct dmi_system_id *dmi) @@ -64,12 +64,12 @@ static int __init dmi_matched(const struct dmi_system_id *dmi) * is used then BIOS silently set timeout to 0 without any error message. */ static struct quirk_entry quirk_dell_xps13_9333 = { - .needs_kbd_timeouts = 1, + .needs_kbd_timeouts = true, .kbd_timeouts = { 0, 5, 15, 60, 5 * 60, 15 * 60, -1 }, }; static struct quirk_entry quirk_dell_latitude_e6410 = { - .kbd_led_levels_off_1 = 1, + .kbd_led_levels_off_1 = true, }; static struct platform_driver platform_driver = { @@ -78,7 +78,6 @@ static struct platform_driver platform_driver = { } }; -static struct calling_interface_buffer *buffer; static struct platform_device *platform_device; static struct backlight_device *dell_backlight_device; static struct rfkill *wifi_rfkill; @@ -110,6 +109,42 @@ static const struct dmi_system_id dell_device_table[] __initconst = { }, }, { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_CHASSIS_TYPE, "30"), /*Tablet*/ + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /*Convertible*/ + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_CHASSIS_TYPE, "32"), /*Detachable*/ + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_CHASSIS_TYPE, "30"), /*Tablet*/ + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /*Convertible*/ + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_CHASSIS_TYPE, "32"), /*Detachable*/ + }, + }, + { .ident = "Dell Computer Corporation", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), @@ -286,7 +321,8 @@ static const struct dmi_system_id dell_quirks[] __initconst = { { } }; -void dell_set_arguments(u32 arg0, u32 arg1, u32 arg2, u32 arg3) +static void dell_fill_request(struct calling_interface_buffer *buffer, + u32 arg0, u32 arg1, u32 arg2, u32 arg3) { memset(buffer, 0, sizeof(struct calling_interface_buffer)); buffer->input[0] = arg0; @@ -295,7 +331,8 @@ void dell_set_arguments(u32 arg0, u32 arg1, u32 arg2, u32 arg3) buffer->input[3] = arg3; } -int dell_send_request(u16 class, u16 select) +static int dell_send_request(struct calling_interface_buffer *buffer, + u16 class, u16 select) { int ret; @@ -432,21 +469,22 @@ static int dell_rfkill_set(void *data, bool blocked) int disable = blocked ? 1 : 0; unsigned long radio = (unsigned long)data; int hwswitch_bit = (unsigned long)data - 1; + struct calling_interface_buffer buffer; int hwswitch; int status; int ret; - dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (ret) return ret; - status = buffer->output[1]; + status = buffer.output[1]; - dell_set_arguments(0x2, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0x2, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (ret) return ret; - hwswitch = buffer->output[1]; + hwswitch = buffer.output[1]; /* If the hardware switch controls this radio, and the hardware switch is disabled, always disable the radio */ @@ -454,8 +492,8 @@ static int dell_rfkill_set(void *data, bool blocked) (status & BIT(0)) && !(status & BIT(16))) disable = 1; - dell_set_arguments(1 | (radio<<8) | (disable << 16), 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 1 | (radio<<8) | (disable << 16), 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); return ret; } @@ -464,9 +502,11 @@ static void dell_rfkill_update_sw_state(struct rfkill *rfkill, int radio, { if (status & BIT(0)) { /* Has hw-switch, sync sw_state to BIOS */ + struct calling_interface_buffer buffer; int block = rfkill_blocked(rfkill); - dell_set_arguments(1 | (radio << 8) | (block << 16), 0, 0, 0); - dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, + 1 | (radio << 8) | (block << 16), 0, 0, 0); + dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); } else { /* No hw-switch, sync BIOS state to sw_state */ rfkill_set_sw_state(rfkill, !!(status & BIT(radio + 16))); @@ -483,21 +523,22 @@ static void dell_rfkill_update_hw_state(struct rfkill *rfkill, int radio, static void dell_rfkill_query(struct rfkill *rfkill, void *data) { int radio = ((unsigned long)data & 0xF); + struct calling_interface_buffer buffer; int hwswitch; int status; int ret; - dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - status = buffer->output[1]; + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + status = buffer.output[1]; if (ret != 0 || !(status & BIT(0))) { return; } - dell_set_arguments(0, 0x2, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - hwswitch = buffer->output[1]; + dell_fill_request(&buffer, 0, 0x2, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + hwswitch = buffer.output[1]; if (ret != 0) return; @@ -514,22 +555,23 @@ static struct dentry *dell_laptop_dir; static int dell_debugfs_show(struct seq_file *s, void *data) { + struct calling_interface_buffer buffer; int hwswitch_state; int hwswitch_ret; int status; int ret; - dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (ret) return ret; - status = buffer->output[1]; + status = buffer.output[1]; - dell_set_arguments(0, 0x2, 0, 0); - hwswitch_ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0x2, 0, 0); + hwswitch_ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (hwswitch_ret) return hwswitch_ret; - hwswitch_state = buffer->output[1]; + hwswitch_state = buffer.output[1]; seq_printf(s, "return:\t%d\n", ret); seq_printf(s, "status:\t0x%X\n", status); @@ -594,38 +636,27 @@ static int dell_debugfs_show(struct seq_file *s, void *data) return 0; } - -static int dell_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, dell_debugfs_show, inode->i_private); -} - -static const struct file_operations dell_debugfs_fops = { - .owner = THIS_MODULE, - .open = dell_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(dell_debugfs); static void dell_update_rfkill(struct work_struct *ignored) { + struct calling_interface_buffer buffer; int hwswitch = 0; int status; int ret; - dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - status = buffer->output[1]; + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + status = buffer.output[1]; if (ret != 0) return; - dell_set_arguments(0, 0x2, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); + dell_fill_request(&buffer, 0, 0x2, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); if (ret == 0 && (status & BIT(0))) - hwswitch = buffer->output[1]; + hwswitch = buffer.output[1]; if (wifi_rfkill) { dell_rfkill_update_hw_state(wifi_rfkill, 1, status, hwswitch); @@ -683,6 +714,7 @@ static struct notifier_block dell_laptop_rbtn_notifier = { static int __init dell_setup_rfkill(void) { + struct calling_interface_buffer buffer; int status, ret, whitelisted; const char *product; @@ -698,9 +730,9 @@ static int __init dell_setup_rfkill(void) if (!force_rfkill && !whitelisted) return 0; - dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_INFO, SELECT_RFKILL); - status = buffer->output[1]; + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_INFO, SELECT_RFKILL); + status = buffer.output[1]; /* dell wireless info smbios call is not supported */ if (ret != 0) @@ -853,6 +885,7 @@ static void dell_cleanup_rfkill(void) static int dell_send_intensity(struct backlight_device *bd) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret; @@ -860,17 +893,21 @@ static int dell_send_intensity(struct backlight_device *bd) if (!token) return -ENODEV; - dell_set_arguments(token->location, bd->props.brightness, 0, 0); + dell_fill_request(&buffer, + token->location, bd->props.brightness, 0, 0); if (power_supply_is_system_supplied() > 0) - ret = dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_AC); + ret = dell_send_request(&buffer, + CLASS_TOKEN_WRITE, SELECT_TOKEN_AC); else - ret = dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_BAT); + ret = dell_send_request(&buffer, + CLASS_TOKEN_WRITE, SELECT_TOKEN_BAT); return ret; } static int dell_get_intensity(struct backlight_device *bd) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret; @@ -878,14 +915,17 @@ static int dell_get_intensity(struct backlight_device *bd) if (!token) return -ENODEV; - dell_set_arguments(token->location, 0, 0, 0); + dell_fill_request(&buffer, token->location, 0, 0, 0); if (power_supply_is_system_supplied() > 0) - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_AC); + ret = dell_send_request(&buffer, + CLASS_TOKEN_READ, SELECT_TOKEN_AC); else - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_BAT); + ret = dell_send_request(&buffer, + CLASS_TOKEN_READ, SELECT_TOKEN_BAT); if (ret == 0) - ret = buffer->output[1]; + ret = buffer.output[1]; + return ret; } @@ -1133,6 +1173,7 @@ static u8 kbd_previous_mode_bit; static bool kbd_led_present; static DEFINE_MUTEX(kbd_led_mutex); +static enum led_brightness kbd_led_level; /* * NOTE: there are three ways to set the keyboard backlight level. @@ -1149,31 +1190,33 @@ static DEFINE_MUTEX(kbd_led_mutex); static int kbd_get_info(struct kbd_info *info) { + struct calling_interface_buffer buffer; u8 units; int ret; - dell_set_arguments(0, 0, 0, 0); - ret = dell_send_request(CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, + CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); if (ret) return ret; - info->modes = buffer->output[1] & 0xFFFF; - info->type = (buffer->output[1] >> 24) & 0xFF; - info->triggers = buffer->output[2] & 0xFF; - units = (buffer->output[2] >> 8) & 0xFF; - info->levels = (buffer->output[2] >> 16) & 0xFF; + info->modes = buffer.output[1] & 0xFFFF; + info->type = (buffer.output[1] >> 24) & 0xFF; + info->triggers = buffer.output[2] & 0xFF; + units = (buffer.output[2] >> 8) & 0xFF; + info->levels = (buffer.output[2] >> 16) & 0xFF; if (quirks && quirks->kbd_led_levels_off_1 && info->levels) info->levels--; if (units & BIT(0)) - info->seconds = (buffer->output[3] >> 0) & 0xFF; + info->seconds = (buffer.output[3] >> 0) & 0xFF; if (units & BIT(1)) - info->minutes = (buffer->output[3] >> 8) & 0xFF; + info->minutes = (buffer.output[3] >> 8) & 0xFF; if (units & BIT(2)) - info->hours = (buffer->output[3] >> 16) & 0xFF; + info->hours = (buffer.output[3] >> 16) & 0xFF; if (units & BIT(3)) - info->days = (buffer->output[3] >> 24) & 0xFF; + info->days = (buffer.output[3] >> 24) & 0xFF; return ret; } @@ -1233,31 +1276,34 @@ static int kbd_set_level(struct kbd_state *state, u8 level) static int kbd_get_state(struct kbd_state *state) { + struct calling_interface_buffer buffer; int ret; - dell_set_arguments(0x1, 0, 0, 0); - ret = dell_send_request(CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); + dell_fill_request(&buffer, 0, 0, 0, 0); + ret = dell_send_request(&buffer, + CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); if (ret) return ret; - state->mode_bit = ffs(buffer->output[1] & 0xFFFF); + state->mode_bit = ffs(buffer.output[1] & 0xFFFF); if (state->mode_bit != 0) state->mode_bit--; - state->triggers = (buffer->output[1] >> 16) & 0xFF; - state->timeout_value = (buffer->output[1] >> 24) & 0x3F; - state->timeout_unit = (buffer->output[1] >> 30) & 0x3; - state->als_setting = buffer->output[2] & 0xFF; - state->als_value = (buffer->output[2] >> 8) & 0xFF; - state->level = (buffer->output[2] >> 16) & 0xFF; - state->timeout_value_ac = (buffer->output[2] >> 24) & 0x3F; - state->timeout_unit_ac = (buffer->output[2] >> 30) & 0x3; + state->triggers = (buffer.output[1] >> 16) & 0xFF; + state->timeout_value = (buffer.output[1] >> 24) & 0x3F; + state->timeout_unit = (buffer.output[1] >> 30) & 0x3; + state->als_setting = buffer.output[2] & 0xFF; + state->als_value = (buffer.output[2] >> 8) & 0xFF; + state->level = (buffer.output[2] >> 16) & 0xFF; + state->timeout_value_ac = (buffer.output[2] >> 24) & 0x3F; + state->timeout_unit_ac = (buffer.output[2] >> 30) & 0x3; return ret; } static int kbd_set_state(struct kbd_state *state) { + struct calling_interface_buffer buffer; int ret; u32 input1; u32 input2; @@ -1270,8 +1316,9 @@ static int kbd_set_state(struct kbd_state *state) input2 |= (state->level & 0xFF) << 16; input2 |= (state->timeout_value_ac & 0x3F) << 24; input2 |= (state->timeout_unit_ac & 0x3) << 30; - dell_set_arguments(0x2, input1, input2, 0); - ret = dell_send_request(CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); + dell_fill_request(&buffer, 0x2, input1, input2, 0); + ret = dell_send_request(&buffer, + CLASS_KBD_BACKLIGHT, SELECT_KBD_BACKLIGHT); return ret; } @@ -1298,6 +1345,7 @@ static int kbd_set_state_safe(struct kbd_state *state, struct kbd_state *old) static int kbd_set_token_bit(u8 bit) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret; @@ -1308,14 +1356,15 @@ static int kbd_set_token_bit(u8 bit) if (!token) return -EINVAL; - dell_set_arguments(token->location, token->value, 0, 0); - ret = dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_STD); + dell_fill_request(&buffer, token->location, token->value, 0, 0); + ret = dell_send_request(&buffer, CLASS_TOKEN_WRITE, SELECT_TOKEN_STD); return ret; } static int kbd_get_token_bit(u8 bit) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; int ret; int val; @@ -1327,9 +1376,9 @@ static int kbd_get_token_bit(u8 bit) if (!token) return -EINVAL; - dell_set_arguments(token->location, 0, 0, 0); - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_STD); - val = buffer->output[1]; + dell_fill_request(&buffer, token->location, 0, 0, 0); + ret = dell_send_request(&buffer, CLASS_TOKEN_READ, SELECT_TOKEN_STD); + val = buffer.output[1]; if (ret) return ret; @@ -1947,6 +1996,7 @@ static enum led_brightness kbd_led_level_get(struct led_classdev *led_cdev) static int kbd_led_level_set(struct led_classdev *led_cdev, enum led_brightness value) { + enum led_brightness new_value = value; struct kbd_state state; struct kbd_state new_state; u16 num; @@ -1976,6 +2026,9 @@ static int kbd_led_level_set(struct led_classdev *led_cdev, } out: + if (ret == 0) + kbd_led_level = new_value; + mutex_unlock(&kbd_led_mutex); return ret; } @@ -2003,6 +2056,9 @@ static int __init kbd_led_init(struct device *dev) if (kbd_led.max_brightness) kbd_led.max_brightness--; } + + kbd_led_level = kbd_led_level_get(NULL); + ret = led_classdev_register(dev, &kbd_led); if (ret) kbd_led_present = false; @@ -2027,13 +2083,25 @@ static void kbd_led_exit(void) static int dell_laptop_notifier_call(struct notifier_block *nb, unsigned long action, void *data) { + bool changed = false; + enum led_brightness new_kbd_led_level; + switch (action) { case DELL_LAPTOP_KBD_BACKLIGHT_BRIGHTNESS_CHANGED: if (!kbd_led_present) break; - led_classdev_notify_brightness_hw_changed(&kbd_led, - kbd_led_level_get(&kbd_led)); + mutex_lock(&kbd_led_mutex); + new_kbd_led_level = kbd_led_level_get(&kbd_led); + if (kbd_led_level != new_kbd_led_level) { + kbd_led_level = new_kbd_led_level; + changed = true; + } + mutex_unlock(&kbd_led_mutex); + + if (changed) + led_classdev_notify_brightness_hw_changed(&kbd_led, + kbd_led_level); break; } @@ -2046,6 +2114,7 @@ static struct notifier_block dell_laptop_notifier = { int dell_micmute_led_set(int state) { + struct calling_interface_buffer buffer; struct calling_interface_token *token; if (state == 0) @@ -2058,8 +2127,8 @@ int dell_micmute_led_set(int state) if (!token) return -ENODEV; - dell_set_arguments(token->location, token->value, 0, 0); - dell_send_request(CLASS_TOKEN_WRITE, SELECT_TOKEN_STD); + dell_fill_request(&buffer, token->location, token->value, 0, 0); + dell_send_request(&buffer, CLASS_TOKEN_WRITE, SELECT_TOKEN_STD); return state; } @@ -2090,13 +2159,6 @@ static int __init dell_init(void) if (ret) goto fail_platform_device2; - buffer = kzalloc(sizeof(struct calling_interface_buffer), GFP_KERNEL); - if (!buffer) { - ret = -ENOMEM; - goto fail_buffer; - } - - ret = dell_setup_rfkill(); if (ret) { @@ -2121,10 +2183,13 @@ static int __init dell_init(void) token = dell_smbios_find_token(BRIGHTNESS_TOKEN); if (token) { - dell_set_arguments(token->location, 0, 0, 0); - ret = dell_send_request(CLASS_TOKEN_READ, SELECT_TOKEN_AC); + struct calling_interface_buffer buffer; + + dell_fill_request(&buffer, token->location, 0, 0, 0); + ret = dell_send_request(&buffer, + CLASS_TOKEN_READ, SELECT_TOKEN_AC); if (ret) - max_intensity = buffer->output[3]; + max_intensity = buffer.output[3]; } if (max_intensity) { @@ -2158,8 +2223,6 @@ static int __init dell_init(void) fail_get_brightness: backlight_device_unregister(dell_backlight_device); fail_backlight: - kfree(buffer); -fail_buffer: dell_cleanup_rfkill(); fail_rfkill: platform_device_del(platform_device); @@ -2179,7 +2242,6 @@ static void __exit dell_exit(void) touchpad_led_exit(); kbd_led_exit(); backlight_device_unregister(dell_backlight_device); - kfree(buffer); dell_cleanup_rfkill(); if (platform_device) { platform_device_unregister(platform_device); diff --git a/drivers/platform/x86/dell-smbios.c b/drivers/platform/x86/dell-smbios.c index 6a60db515bda..8541cde4cb7d 100644 --- a/drivers/platform/x86/dell-smbios.c +++ b/drivers/platform/x86/dell-smbios.c @@ -65,10 +65,10 @@ static struct smbios_call call_whitelist[] = { /* calls that are explicitly blacklisted */ static struct smbios_call call_blacklist[] = { - {0x0000, 01, 07}, /* manufacturing use */ - {0x0000, 06, 05}, /* manufacturing use */ - {0x0000, 11, 03}, /* write once */ - {0x0000, 11, 07}, /* write once */ + {0x0000, 1, 7}, /* manufacturing use */ + {0x0000, 6, 5}, /* manufacturing use */ + {0x0000, 11, 3}, /* write once */ + {0x0000, 11, 7}, /* write once */ {0x0000, 11, 11}, /* write once */ {0x0000, 19, -1}, /* diagnostics */ /* handled by kernel: dell-laptop */ diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index fb25b20df316..2c9927430d85 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -261,6 +261,9 @@ static const u16 bios_to_linux_keycode[256] = { * override them. */ static const struct key_entry dell_wmi_keymap_type_0010[] = { + /* Mic mute */ + { KE_KEY, 0x150, { KEY_MICMUTE } }, + /* Fn-lock */ { KE_IGNORE, 0x151, { KEY_RESERVED } }, diff --git a/drivers/platform/x86/gpd-pocket-fan.c b/drivers/platform/x86/gpd-pocket-fan.c new file mode 100644 index 000000000000..2d645c505f81 --- /dev/null +++ b/drivers/platform/x86/gpd-pocket-fan.c @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * GPD Pocket fan controller driver + * + * Copyright (C) 2017 Hans de Goede <hdegoede@redhat.com> + */ + +#include <linux/acpi.h> +#include <linux/gpio/consumer.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/platform_device.h> +#include <linux/power_supply.h> +#include <linux/thermal.h> +#include <linux/workqueue.h> + +#define MAX_SPEED 3 + +static int temp_limits[3] = { 55000, 60000, 65000 }; +module_param_array(temp_limits, int, NULL, 0444); +MODULE_PARM_DESC(temp_limits, + "Milli-celcius values above which the fan speed increases"); + +static int hysteresis = 3000; +module_param(hysteresis, int, 0444); +MODULE_PARM_DESC(hysteresis, + "Hysteresis in milli-celcius before lowering the fan speed"); + +static int speed_on_ac = 2; +module_param(speed_on_ac, int, 0444); +MODULE_PARM_DESC(speed_on_ac, + "minimum fan speed to allow when system is powered by AC"); + +struct gpd_pocket_fan_data { + struct device *dev; + struct thermal_zone_device *dts0; + struct thermal_zone_device *dts1; + struct gpio_desc *gpio0; + struct gpio_desc *gpio1; + struct delayed_work work; + int last_speed; +}; + +static void gpd_pocket_fan_set_speed(struct gpd_pocket_fan_data *fan, int speed) +{ + if (speed == fan->last_speed) + return; + + gpiod_direction_output(fan->gpio0, !!(speed & 1)); + gpiod_direction_output(fan->gpio1, !!(speed & 2)); + + fan->last_speed = speed; +} + +static int gpd_pocket_fan_min_speed(void) +{ + if (power_supply_is_system_supplied()) + return speed_on_ac; + else + return 0; +} + +static void gpd_pocket_fan_worker(struct work_struct *work) +{ + struct gpd_pocket_fan_data *fan = + container_of(work, struct gpd_pocket_fan_data, work.work); + int t0, t1, temp, speed, min_speed, i; + + if (thermal_zone_get_temp(fan->dts0, &t0) || + thermal_zone_get_temp(fan->dts1, &t1)) { + dev_warn(fan->dev, "Error getting temperature\n"); + speed = MAX_SPEED; + goto set_speed; + } + + temp = max(t0, t1); + + speed = fan->last_speed; + min_speed = gpd_pocket_fan_min_speed(); + + /* Determine minimum speed */ + for (i = min_speed; i < ARRAY_SIZE(temp_limits); i++) { + if (temp < temp_limits[i]) + break; + } + if (speed < i) + speed = i; + + /* Use hysteresis before lowering speed again */ + for (i = min_speed; i < ARRAY_SIZE(temp_limits); i++) { + if (temp <= (temp_limits[i] - hysteresis)) + break; + } + if (speed > i) + speed = i; + + if (fan->last_speed <= 0 && speed) + speed = MAX_SPEED; /* kick start motor */ + +set_speed: + gpd_pocket_fan_set_speed(fan, speed); + + /* When mostly idle (low temp/speed), slow down the poll interval. */ + queue_delayed_work(system_wq, &fan->work, + msecs_to_jiffies(4000 / (speed + 1))); +} + +static void gpd_pocket_fan_force_update(struct gpd_pocket_fan_data *fan) +{ + fan->last_speed = -1; + mod_delayed_work(system_wq, &fan->work, 0); +} + +static int gpd_pocket_fan_probe(struct platform_device *pdev) +{ + struct gpd_pocket_fan_data *fan; + int i; + + for (i = 0; i < ARRAY_SIZE(temp_limits); i++) { + if (temp_limits[i] < 40000 || temp_limits[i] > 70000) { + dev_err(&pdev->dev, "Invalid temp-limit %d (must be between 40000 and 70000)\n", + temp_limits[i]); + return -EINVAL; + } + } + if (hysteresis < 1000 || hysteresis > 10000) { + dev_err(&pdev->dev, "Invalid hysteresis %d (must be between 1000 and 10000)\n", + hysteresis); + return -EINVAL; + } + if (speed_on_ac < 0 || speed_on_ac > MAX_SPEED) { + dev_err(&pdev->dev, "Invalid speed_on_ac %d (must be between 0 and 3)\n", + speed_on_ac); + return -EINVAL; + } + + fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL); + if (!fan) + return -ENOMEM; + + fan->dev = &pdev->dev; + INIT_DELAYED_WORK(&fan->work, gpd_pocket_fan_worker); + + /* Note this returns a "weak" reference which we don't need to free */ + fan->dts0 = thermal_zone_get_zone_by_name("soc_dts0"); + if (IS_ERR(fan->dts0)) + return -EPROBE_DEFER; + + fan->dts1 = thermal_zone_get_zone_by_name("soc_dts1"); + if (IS_ERR(fan->dts1)) + return -EPROBE_DEFER; + + fan->gpio0 = devm_gpiod_get_index(fan->dev, NULL, 0, GPIOD_ASIS); + if (IS_ERR(fan->gpio0)) + return PTR_ERR(fan->gpio0); + + fan->gpio1 = devm_gpiod_get_index(fan->dev, NULL, 1, GPIOD_ASIS); + if (IS_ERR(fan->gpio1)) + return PTR_ERR(fan->gpio1); + + gpd_pocket_fan_force_update(fan); + + platform_set_drvdata(pdev, fan); + return 0; +} + +static int gpd_pocket_fan_remove(struct platform_device *pdev) +{ + struct gpd_pocket_fan_data *fan = platform_get_drvdata(pdev); + + cancel_delayed_work_sync(&fan->work); + return 0; +} + +#ifdef CONFIG_PM_SLEEP +static int gpd_pocket_fan_suspend(struct device *dev) +{ + struct gpd_pocket_fan_data *fan = dev_get_drvdata(dev); + + cancel_delayed_work_sync(&fan->work); + gpd_pocket_fan_set_speed(fan, gpd_pocket_fan_min_speed()); + return 0; +} + +static int gpd_pocket_fan_resume(struct device *dev) +{ + struct gpd_pocket_fan_data *fan = dev_get_drvdata(dev); + + gpd_pocket_fan_force_update(fan); + return 0; +} +#endif +static SIMPLE_DEV_PM_OPS(gpd_pocket_fan_pm_ops, + gpd_pocket_fan_suspend, + gpd_pocket_fan_resume); + +static struct acpi_device_id gpd_pocket_fan_acpi_match[] = { + { "FAN02501" }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, gpd_pocket_fan_acpi_match); + +static struct platform_driver gpd_pocket_fan_driver = { + .probe = gpd_pocket_fan_probe, + .remove = gpd_pocket_fan_remove, + .driver = { + .name = "gpd_pocket_fan", + .acpi_match_table = gpd_pocket_fan_acpi_match, + .pm = &gpd_pocket_fan_pm_ops, + }, +}; + +module_platform_driver(gpd_pocket_fan_driver); +MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com"); +MODULE_DESCRIPTION("GPD pocket fan driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 53ab4e0f8962..5b6f18b18801 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -124,10 +124,10 @@ static int read_method_int(acpi_handle handle, const char *method, int *val) if (ACPI_FAILURE(status)) { *val = -1; return -1; - } else { - *val = result; - return 0; } + *val = result; + return 0; + } static int method_gbmd(acpi_handle handle, unsigned long *ret) @@ -164,10 +164,10 @@ static int method_vpcr(acpi_handle handle, int cmd, int *ret) if (ACPI_FAILURE(status)) { *ret = -1; return -1; - } else { - *ret = result; - return 0; } + *ret = result; + return 0; + } static int method_vpcw(acpi_handle handle, int cmd, int data) @@ -231,7 +231,7 @@ static int write_ec_cmd(acpi_handle handle, int cmd, unsigned long data) if (val == 0) return 0; } - pr_err("timeout in write_ec_cmd\n"); + pr_err("timeout in %s\n", __func__); return -1; } @@ -284,19 +284,7 @@ static int debugfs_status_show(struct seq_file *s, void *data) return 0; } - -static int debugfs_status_open(struct inode *inode, struct file *file) -{ - return single_open(file, debugfs_status_show, inode->i_private); -} - -static const struct file_operations debugfs_status_fops = { - .owner = THIS_MODULE, - .open = debugfs_status_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(debugfs_status); static int debugfs_cfg_show(struct seq_file *s, void *data) { @@ -337,19 +325,7 @@ static int debugfs_cfg_show(struct seq_file *s, void *data) } return 0; } - -static int debugfs_cfg_open(struct inode *inode, struct file *file) -{ - return single_open(file, debugfs_cfg_show, inode->i_private); -} - -static const struct file_operations debugfs_cfg_fops = { - .owner = THIS_MODULE, - .open = debugfs_cfg_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(debugfs_cfg); static int ideapad_debugfs_init(struct ideapad_private *priv) { @@ -964,6 +940,13 @@ static void ideapad_wmi_notify(u32 value, void *context) */ static const struct dmi_system_id no_hw_rfkill_list[] = { { + .ident = "Lenovo RESCUER R720-15IKBN", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_BOARD_NAME, "80WW"), + }, + }, + { .ident = "Lenovo G40-30", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), @@ -1104,6 +1087,13 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { }, }, { + .ident = "Lenovo Legion Y720-15IKB", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Y720-15IKB"), + }, + }, + { .ident = "Lenovo Legion Y720-15IKBN", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index f470279c4c10..d1a01311c1a2 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -25,6 +25,7 @@ #include <linux/acpi.h> #include <linux/suspend.h> #include <acpi/acpi_bus.h> +#include <linux/dmi.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Alex Hung"); @@ -73,6 +74,24 @@ static const struct key_entry intel_array_keymap[] = { { KE_END }, }; +static const struct dmi_system_id button_array_table[] = { + { + .ident = "Wacom MobileStudio Pro 13", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Wacom Co.,Ltd"), + DMI_MATCH(DMI_PRODUCT_NAME, "Wacom MobileStudio Pro 13"), + }, + }, + { + .ident = "Wacom MobileStudio Pro 16", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Wacom Co.,Ltd"), + DMI_MATCH(DMI_PRODUCT_NAME, "Wacom MobileStudio Pro 16"), + }, + }, + { } +}; + struct intel_hid_priv { struct input_dev *input_dev; struct input_dev *array; @@ -263,10 +282,27 @@ wakeup: ev_index); } +static bool button_array_present(struct platform_device *device) +{ + acpi_handle handle = ACPI_HANDLE(&device->dev); + unsigned long long event_cap; + acpi_status status; + bool supported = false; + + status = acpi_evaluate_integer(handle, "HEBC", NULL, &event_cap); + if (ACPI_SUCCESS(status) && (event_cap & 0x20000)) + supported = true; + + if (dmi_check_system(button_array_table)) + supported = true; + + return supported; +} + static int intel_hid_probe(struct platform_device *device) { acpi_handle handle = ACPI_HANDLE(&device->dev); - unsigned long long event_cap, mode; + unsigned long long mode; struct intel_hid_priv *priv; acpi_status status; int err; @@ -299,8 +335,7 @@ static int intel_hid_probe(struct platform_device *device) } /* Setup 5 button array */ - status = acpi_evaluate_integer(handle, "HEBC", NULL, &event_cap); - if (ACPI_SUCCESS(status) && (event_cap & 0x20000)) { + if (button_array_present(device)) { dev_info(&device->dev, "platform supports 5 button array\n"); err = intel_button_array_input_setup(device); if (err) diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index 58c5ff36523a..b703d6f5b099 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -1,30 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Intel Virtual Button driver for Windows 8.1+ * * Copyright (C) 2016 AceLan Kao <acelan.kao@canonical.com> * Copyright (C) 2016 Alex Hung <alex.hung@canonical.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ +#include <linux/acpi.h> +#include <linux/input.h> +#include <linux/input/sparse-keymap.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/init.h> -#include <linux/input.h> #include <linux/platform_device.h> -#include <linux/input/sparse-keymap.h> -#include <linux/acpi.h> #include <linux/suspend.h> -#include <acpi/acpi_bus.h> + +/* When NOT in tablet mode, VGBS returns with the flag 0x40 */ +#define TABLET_MODE_FLAG 0x40 MODULE_LICENSE("GPL"); MODULE_AUTHOR("AceLan Kao"); @@ -38,10 +29,16 @@ static const struct acpi_device_id intel_vbtn_ids[] = { static const struct key_entry intel_vbtn_keymap[] = { { KE_KEY, 0xC0, { KEY_POWER } }, /* power key press */ { KE_IGNORE, 0xC1, { KEY_POWER } }, /* power key release */ + { KE_KEY, 0xC2, { KEY_LEFTMETA } }, /* 'Windows' key press */ + { KE_KEY, 0xC3, { KEY_LEFTMETA } }, /* 'Windows' key release */ { KE_KEY, 0xC4, { KEY_VOLUMEUP } }, /* volume-up key press */ { KE_IGNORE, 0xC5, { KEY_VOLUMEUP } }, /* volume-up key release */ { KE_KEY, 0xC6, { KEY_VOLUMEDOWN } }, /* volume-down key press */ { KE_IGNORE, 0xC7, { KEY_VOLUMEDOWN } }, /* volume-down key release */ + { KE_KEY, 0xC8, { KEY_ROTATE_LOCK_TOGGLE } }, /* rotate-lock key press */ + { KE_KEY, 0xC9, { KEY_ROTATE_LOCK_TOGGLE } }, /* rotate-lock key release */ + { KE_SW, 0xCC, { .sw = { SW_TABLET_MODE, 1 } } }, /* Tablet */ + { KE_SW, 0xCD, { .sw = { SW_TABLET_MODE, 0 } } }, /* Laptop */ { KE_END }, }; @@ -74,20 +71,35 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) { struct platform_device *device = context; struct intel_vbtn_priv *priv = dev_get_drvdata(&device->dev); + unsigned int val = !(event & 1); /* Even=press, Odd=release */ + const struct key_entry *ke_rel; + bool autorelease; if (priv->wakeup_mode) { if (sparse_keymap_entry_from_scancode(priv->input_dev, event)) { pm_wakeup_hard_event(&device->dev); return; } - } else if (sparse_keymap_report_event(priv->input_dev, event, 1, true)) { - return; + goto out_unknown; } + + /* + * Even press events are autorelease if there is no corresponding odd + * release event, or if the odd event is KE_IGNORE. + */ + ke_rel = sparse_keymap_entry_from_scancode(priv->input_dev, event | 1); + autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE); + + if (sparse_keymap_report_event(priv->input_dev, event, val, autorelease)) + return; + +out_unknown: dev_dbg(&device->dev, "unknown event index 0x%x\n", event); } static int intel_vbtn_probe(struct platform_device *device) { + struct acpi_buffer vgbs_output = { ACPI_ALLOCATE_BUFFER, NULL }; acpi_handle handle = ACPI_HANDLE(&device->dev); struct intel_vbtn_priv *priv; acpi_status status; @@ -110,6 +122,23 @@ static int intel_vbtn_probe(struct platform_device *device) return err; } + /* + * VGBS being present and returning something means we have + * a tablet mode switch. + */ + status = acpi_evaluate_object(handle, "VGBS", NULL, &vgbs_output); + if (ACPI_SUCCESS(status)) { + union acpi_object *obj = vgbs_output.pointer; + + if (obj && obj->type == ACPI_TYPE_INTEGER) { + int m = !(obj->integer.value & TABLET_MODE_FLAG); + + input_report_switch(priv->input_dev, SW_TABLET_MODE, m); + } + } + + kfree(vgbs_output.pointer); + status = acpi_install_notify_handler(handle, ACPI_DEVICE_NOTIFY, notify_handler, diff --git a/drivers/platform/x86/intel_chtdc_ti_pwrbtn.c b/drivers/platform/x86/intel_chtdc_ti_pwrbtn.c new file mode 100644 index 000000000000..38b8e7cfe88c --- /dev/null +++ b/drivers/platform/x86/intel_chtdc_ti_pwrbtn.c @@ -0,0 +1,93 @@ +/* + * Power-button driver for Dollar Cove TI PMIC + * Copyright (C) 2014 Intel Corp + * Copyright (c) 2017 Takashi Iwai <tiwai@suse.de> + */ + +#include <linux/input.h> +#include <linux/interrupt.h> +#include <linux/device.h> +#include <linux/mfd/intel_soc_pmic.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/pm_wakeirq.h> +#include <linux/slab.h> + +#define CHTDC_TI_SIRQ_REG 0x3 +#define SIRQ_PWRBTN_REL BIT(0) + +static irqreturn_t chtdc_ti_pwrbtn_interrupt(int irq, void *dev_id) +{ + struct input_dev *input = dev_id; + struct device *dev = input->dev.parent; + struct regmap *regmap = dev_get_drvdata(dev); + int state; + + if (!regmap_read(regmap, CHTDC_TI_SIRQ_REG, &state)) { + dev_dbg(dev, "SIRQ_REG=0x%x\n", state); + input_report_key(input, KEY_POWER, !(state & SIRQ_PWRBTN_REL)); + input_sync(input); + } + + return IRQ_HANDLED; +} + +static int chtdc_ti_pwrbtn_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct intel_soc_pmic *pmic = dev_get_drvdata(dev->parent); + struct input_dev *input; + int irq, err; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + input = devm_input_allocate_device(dev); + if (!input) + return -ENOMEM; + input->name = pdev->name; + input->phys = "power-button/input0"; + input->id.bustype = BUS_HOST; + input_set_capability(input, EV_KEY, KEY_POWER); + err = input_register_device(input); + if (err) + return err; + + dev_set_drvdata(dev, pmic->regmap); + + err = devm_request_threaded_irq(dev, irq, NULL, + chtdc_ti_pwrbtn_interrupt, + 0, KBUILD_MODNAME, input); + if (err) + return err; + + device_init_wakeup(dev, true); + dev_pm_set_wake_irq(dev, irq); + return 0; +} + +static int chtdc_ti_pwrbtn_remove(struct platform_device *pdev) +{ + dev_pm_clear_wake_irq(&pdev->dev); + device_init_wakeup(&pdev->dev, false); + return 0; +} + +static const struct platform_device_id chtdc_ti_pwrbtn_id_table[] = { + { .name = "chtdc_ti_pwrbtn" }, + {}, +}; +MODULE_DEVICE_TABLE(platform, chtdc_ti_pwrbtn_id_table); + +static struct platform_driver chtdc_ti_pwrbtn_driver = { + .driver = { + .name = KBUILD_MODNAME, + }, + .probe = chtdc_ti_pwrbtn_probe, + .remove = chtdc_ti_pwrbtn_remove, + .id_table = chtdc_ti_pwrbtn_id_table, +}; +module_platform_driver(chtdc_ti_pwrbtn_driver); + +MODULE_DESCRIPTION("Power-button driver for Dollar Cove TI PMIC"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_int0002_vgpio.c b/drivers/platform/x86/intel_int0002_vgpio.c index f7b67e898abc..a473dc51b18d 100644 --- a/drivers/platform/x86/intel_int0002_vgpio.c +++ b/drivers/platform/x86/intel_int0002_vgpio.c @@ -180,7 +180,7 @@ static int int0002_probe(struct platform_device *pdev) * to gpiochip_set_chained_irqchip, because the irq is shared. */ ret = devm_request_irq(dev, irq, int0002_irq, - IRQF_SHARED | IRQF_NO_THREAD, "INT0002", chip); + IRQF_SHARED, "INT0002", chip); if (ret) { dev_err(dev, "Error requesting IRQ %d: %d\n", irq, ret); return ret; diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index 17e08b42b0a9..43bbe74743d9 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -18,20 +18,24 @@ * */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/acpi.h> #include <linux/debugfs.h> #include <linux/delay.h> -#include <linux/device.h> -#include <linux/init.h> #include <linux/io.h> +#include <linux/module.h> #include <linux/pci.h> #include <linux/uaccess.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> -#include <asm/pmc_core.h> #include "intel_pmc_core.h" +#define ICPU(model, data) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT, (kernel_ulong_t)data } + static struct pmc_dev pmc; static const struct pmc_bit_map spt_pll_map[] = { @@ -119,10 +123,88 @@ static const struct pmc_reg_map spt_reg_map = { .pm_read_disable_bit = SPT_PMC_READ_DISABLE_BIT, }; -static const struct pci_device_id pmc_pci_ids[] = { - { PCI_VDEVICE(INTEL, SPT_PMC_PCI_DEVICE_ID), - (kernel_ulong_t)&spt_reg_map }, - { 0, }, +/* Cannonlake: PGD PFET Enable Ack Status Register(s) bitmap */ +static const struct pmc_bit_map cnp_pfear_map[] = { + {"PMC", BIT(0)}, + {"OPI-DMI", BIT(1)}, + {"SPI/eSPI", BIT(2)}, + {"XHCI", BIT(3)}, + {"SPA", BIT(4)}, + {"SPB", BIT(5)}, + {"SPC", BIT(6)}, + {"GBE", BIT(7)}, + + {"SATA", BIT(0)}, + {"HDA_PGD0", BIT(1)}, + {"HDA_PGD1", BIT(2)}, + {"HDA_PGD2", BIT(3)}, + {"HDA_PGD3", BIT(4)}, + {"SPD", BIT(5)}, + {"LPSS", BIT(6)}, + {"LPC", BIT(7)}, + + {"SMB", BIT(0)}, + {"ISH", BIT(1)}, + {"P2SB", BIT(2)}, + {"NPK_VNN", BIT(3)}, + {"SDX", BIT(4)}, + {"SPE", BIT(5)}, + {"Fuse", BIT(6)}, + {"Res_23", BIT(7)}, + + {"CSME_FSC", BIT(0)}, + {"USB3_OTG", BIT(1)}, + {"EXI", BIT(2)}, + {"CSE", BIT(3)}, + {"csme_kvm", BIT(4)}, + {"csme_pmt", BIT(5)}, + {"csme_clink", BIT(6)}, + {"csme_ptio", BIT(7)}, + + {"csme_usbr", BIT(0)}, + {"csme_susram", BIT(1)}, + {"csme_smt1", BIT(2)}, + {"CSME_SMT4", BIT(3)}, + {"csme_sms2", BIT(4)}, + {"csme_sms1", BIT(5)}, + {"csme_rtc", BIT(6)}, + {"csme_psf", BIT(7)}, + + {"SBR0", BIT(0)}, + {"SBR1", BIT(1)}, + {"SBR2", BIT(2)}, + {"SBR3", BIT(3)}, + {"SBR4", BIT(4)}, + {"SBR5", BIT(5)}, + {"CSME_PECI", BIT(6)}, + {"PSF1", BIT(7)}, + + {"PSF2", BIT(0)}, + {"PSF3", BIT(1)}, + {"PSF4", BIT(2)}, + {"CNVI", BIT(3)}, + {"UFS0", BIT(4)}, + {"EMMC", BIT(5)}, + {"Res_6", BIT(6)}, + {"SBR6", BIT(7)}, + + {"SBR7", BIT(0)}, + {"NPK_AON", BIT(1)}, + {"HDA_PGD4", BIT(2)}, + {"HDA_PGD5", BIT(3)}, + {"HDA_PGD6", BIT(4)}, + {} +}; + +static const struct pmc_reg_map cnp_reg_map = { + .pfear_sts = cnp_pfear_map, + .slp_s0_offset = CNP_PMC_SLP_S0_RES_COUNTER_OFFSET, + .ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET, + .regmap_length = CNP_PMC_MMIO_REG_LEN, + .ppfear0_offset = CNP_PMC_HOST_PPFEAR0A, + .ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES, + .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, + .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, }; static inline u8 pmc_core_reg_read_byte(struct pmc_dev *pmcdev, int offset) @@ -146,37 +228,6 @@ static inline u32 pmc_core_adjust_slp_s0_step(u32 value) return value * SPT_PMC_SLP_S0_RES_COUNTER_STEP; } -/** - * intel_pmc_slp_s0_counter_read() - Read SLP_S0 residency. - * @data: Out param that contains current SLP_S0 count. - * - * This API currently supports Intel Skylake SoC and Sunrise - * Point Platform Controller Hub. Future platform support - * should be added for platforms that support low power modes - * beyond Package C10 state. - * - * SLP_S0_RESIDENCY counter counts in 100 us granularity per - * step hence function populates the multiplied value in out - * parameter @data. - * - * Return: an error code or 0 on success. - */ -int intel_pmc_slp_s0_counter_read(u32 *data) -{ - struct pmc_dev *pmcdev = &pmc; - const struct pmc_reg_map *map = pmcdev->map; - u32 value; - - if (!pmcdev->has_slp_s0_res) - return -EACCES; - - value = pmc_core_reg_read(pmcdev, map->slp_s0_offset); - *data = pmc_core_adjust_slp_s0_step(value); - - return 0; -} -EXPORT_SYMBOL_GPL(intel_pmc_slp_s0_counter_read); - static int pmc_core_dev_state_get(void *data, u64 *val) { struct pmc_dev *pmcdev = data; @@ -437,47 +488,33 @@ static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev) static int pmc_core_dbgfs_register(struct pmc_dev *pmcdev) { - struct dentry *dir, *file; + struct dentry *dir; dir = debugfs_create_dir("pmc_core", NULL); if (!dir) return -ENOMEM; pmcdev->dbgfs_dir = dir; - file = debugfs_create_file("slp_s0_residency_usec", S_IFREG | S_IRUGO, - dir, pmcdev, &pmc_core_dev_state); - if (!file) - goto err; - - file = debugfs_create_file("pch_ip_power_gating_status", - S_IFREG | S_IRUGO, dir, pmcdev, - &pmc_core_ppfear_ops); - if (!file) - goto err; - - file = debugfs_create_file("mphy_core_lanes_power_gating_status", - S_IFREG | S_IRUGO, dir, pmcdev, - &pmc_core_mphy_pg_ops); - if (!file) - goto err; - - file = debugfs_create_file("pll_status", - S_IFREG | S_IRUGO, dir, pmcdev, - &pmc_core_pll_ops); - if (!file) - goto err; - - file = debugfs_create_file("ltr_ignore", - S_IFREG | S_IRUGO, dir, pmcdev, - &pmc_core_ltr_ignore_ops); - - if (!file) - goto err; + + debugfs_create_file("slp_s0_residency_usec", 0444, dir, pmcdev, + &pmc_core_dev_state); + + debugfs_create_file("pch_ip_power_gating_status", 0444, dir, pmcdev, + &pmc_core_ppfear_ops); + + debugfs_create_file("ltr_ignore", 0644, dir, pmcdev, + &pmc_core_ltr_ignore_ops); + + if (pmcdev->map->pll_sts) + debugfs_create_file("pll_status", 0444, dir, pmcdev, + &pmc_core_pll_ops); + + if (pmcdev->map->mphy_sts) + debugfs_create_file("mphy_core_lanes_power_gating_status", + 0444, dir, pmcdev, + &pmc_core_mphy_pg_ops); return 0; -err: - pmc_core_dbgfs_unregister(pmcdev); - return -ENODEV; } #else static inline int pmc_core_dbgfs_register(struct pmc_dev *pmcdev) @@ -491,71 +528,76 @@ static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev) #endif /* CONFIG_DEBUG_FS */ static const struct x86_cpu_id intel_pmc_core_ids[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_MOBILE, X86_FEATURE_MWAIT, - (kernel_ulong_t)NULL}, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_SKYLAKE_DESKTOP, X86_FEATURE_MWAIT, - (kernel_ulong_t)NULL}, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_KABYLAKE_MOBILE, X86_FEATURE_MWAIT, - (kernel_ulong_t)NULL}, - { X86_VENDOR_INTEL, 6, INTEL_FAM6_KABYLAKE_DESKTOP, X86_FEATURE_MWAIT, - (kernel_ulong_t)NULL}, + ICPU(INTEL_FAM6_SKYLAKE_MOBILE, &spt_reg_map), + ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, &spt_reg_map), + ICPU(INTEL_FAM6_KABYLAKE_MOBILE, &spt_reg_map), + ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, &spt_reg_map), + ICPU(INTEL_FAM6_CANNONLAKE_MOBILE, &cnp_reg_map), {} }; -static int pmc_core_probe(struct pci_dev *dev, const struct pci_device_id *id) +MODULE_DEVICE_TABLE(x86cpu, intel_pmc_core_ids); + +static const struct pci_device_id pmc_pci_ids[] = { + { PCI_VDEVICE(INTEL, SPT_PMC_PCI_DEVICE_ID), 0}, + { 0, }, +}; + +static int __init pmc_core_probe(void) { - struct device *ptr_dev = &dev->dev; struct pmc_dev *pmcdev = &pmc; const struct x86_cpu_id *cpu_id; - const struct pmc_reg_map *map = (struct pmc_reg_map *)id->driver_data; + u64 slp_s0_addr; int err; cpu_id = x86_match_cpu(intel_pmc_core_ids); - if (!cpu_id) { - dev_dbg(&dev->dev, "PMC Core: cpuid mismatch.\n"); - return -EINVAL; - } - - err = pcim_enable_device(dev); - if (err < 0) { - dev_dbg(&dev->dev, "PMC Core: failed to enable Power Management Controller.\n"); - return err; - } - - err = pci_read_config_dword(dev, - SPT_PMC_BASE_ADDR_OFFSET, - &pmcdev->base_addr); - if (err < 0) { - dev_dbg(&dev->dev, "PMC Core: failed to read PCI config space.\n"); - return err; - } - pmcdev->base_addr &= PMC_BASE_ADDR_MASK; - dev_dbg(&dev->dev, "PMC Core: PWRMBASE is %#x\n", pmcdev->base_addr); - - pmcdev->regbase = devm_ioremap_nocache(ptr_dev, - pmcdev->base_addr, - SPT_PMC_MMIO_REG_LEN); - if (!pmcdev->regbase) { - dev_dbg(&dev->dev, "PMC Core: ioremap failed.\n"); + if (!cpu_id) + return -ENODEV; + + pmcdev->map = (struct pmc_reg_map *)cpu_id->driver_data; + + /* + * Coffeelake has CPU ID of Kabylake and Cannonlake PCH. So here + * Sunrisepoint PCH regmap can't be used. Use Cannonlake PCH regmap + * in this case. + */ + if (!pci_dev_present(pmc_pci_ids)) + pmcdev->map = &cnp_reg_map; + + if (lpit_read_residency_count_address(&slp_s0_addr)) + pmcdev->base_addr = PMC_BASE_ADDR_DEFAULT; + else + pmcdev->base_addr = slp_s0_addr - pmcdev->map->slp_s0_offset; + + pmcdev->regbase = ioremap(pmcdev->base_addr, + pmcdev->map->regmap_length); + if (!pmcdev->regbase) return -ENOMEM; - } mutex_init(&pmcdev->lock); - pmcdev->map = map; pmcdev->pmc_xram_read_bit = pmc_core_check_read_lock_bit(); err = pmc_core_dbgfs_register(pmcdev); - if (err < 0) - dev_warn(&dev->dev, "PMC Core: debugfs register failed.\n"); + if (err < 0) { + pr_warn(" debugfs register failed.\n"); + iounmap(pmcdev->regbase); + return err; + } - pmc.has_slp_s0_res = true; + pr_info(" initialized\n"); return 0; } +module_init(pmc_core_probe) -static struct pci_driver intel_pmc_core_driver = { - .name = "intel_pmc_core", - .id_table = pmc_pci_ids, - .probe = pmc_core_probe, -}; +static void __exit pmc_core_remove(void) +{ + struct pmc_dev *pmcdev = &pmc; + + pmc_core_dbgfs_unregister(pmcdev); + mutex_destroy(&pmcdev->lock); + iounmap(pmcdev->regbase); +} +module_exit(pmc_core_remove) -builtin_pci_driver(intel_pmc_core_driver); +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Intel PMC Core Driver"); diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h index 3d225a9cc09f..5fa5f97870aa 100644 --- a/drivers/platform/x86/intel_pmc_core.h +++ b/drivers/platform/x86/intel_pmc_core.h @@ -21,9 +21,10 @@ #ifndef PMC_CORE_H #define PMC_CORE_H +#define PMC_BASE_ADDR_DEFAULT 0xFE000000 + /* Sunrise Point Power Management Controller PCI Device ID */ #define SPT_PMC_PCI_DEVICE_ID 0x9d21 - #define SPT_PMC_BASE_ADDR_OFFSET 0x48 #define SPT_PMC_SLP_S0_RES_COUNTER_OFFSET 0x13c #define SPT_PMC_PM_CFG_OFFSET 0x18 @@ -122,6 +123,17 @@ enum ppfear_regs { #define SPT_PMC_BIT_MPHY_CMN_LANE2 BIT(2) #define SPT_PMC_BIT_MPHY_CMN_LANE3 BIT(3) +/* Cannonlake Power Management Controller register offsets */ +#define CNP_PMC_SLP_S0_RES_COUNTER_OFFSET 0x193C +#define CNP_PMC_LTR_IGNORE_OFFSET 0x1B0C +#define CNP_PMC_PM_CFG_OFFSET 0x1818 +/* Cannonlake: PGD PFET Enable Ack Status Register(s) start */ +#define CNP_PMC_HOST_PPFEAR0A 0x1D90 + +#define CNP_PMC_MMIO_REG_LEN 0x2000 +#define CNP_PPFEAR_NUM_ENTRIES 8 +#define CNP_PMC_READ_DISABLE_BIT 22 + struct pmc_bit_map { const char *name; u32 bit_mask; @@ -135,7 +147,6 @@ struct pmc_bit_map { * @pll_sts: Maps name of PLL to corresponding bit status * @slp_s0_offset: PWRMBASE offset to read SLP_S0 residency * @ltr_ignore_offset: PWRMBASE offset to read/write LTR ignore bit - * @base_address: Base address of PWRMBASE defined in BIOS writer guide * @regmap_length: Length of memory to map from PWRMBASE address to access * @ppfear0_offset: PWRMBASE offset to to read PPFEAR* * @ppfear_buckets: Number of 8 bits blocks to read all IP blocks from @@ -152,7 +163,6 @@ struct pmc_reg_map { const struct pmc_bit_map *pll_sts; const u32 slp_s0_offset; const u32 ltr_ignore_offset; - const u32 base_address; const int regmap_length; const u32 ppfear0_offset; const int ppfear_buckets; @@ -162,12 +172,14 @@ struct pmc_reg_map { /** * struct pmc_dev - pmc device structure - * @base_addr: comtains pmc base address + * @base_addr: contains pmc base address * @regbase: pointer to io-remapped memory location - * @dbgfs_dir: path to debug fs interface - * @feature_available: flag to indicate whether - * the feature is available - * on a particular platform or not. + * @map: pointer to pmc_reg_map struct that contains platform + * specific attributes + * @dbgfs_dir: path to debugfs interface + * @pmc_xram_read_bit: flag to indicate whether PMC XRAM shadow registers + * used to read MPHY PG and PLL status are available + * @mutex_lock: mutex to complete one transcation * * pmc_dev contains info about power management controller device. */ @@ -178,7 +190,6 @@ struct pmc_dev { #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ - bool has_slp_s0_res; int pmc_xram_read_bit; struct mutex lock; /* generic mutex lock for PMC Core */ }; diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c index e03fa31446ca..e7edc8c63936 100644 --- a/drivers/platform/x86/intel_pmc_ipc.c +++ b/drivers/platform/x86/intel_pmc_ipc.c @@ -215,11 +215,11 @@ static inline int is_gcr_valid(u32 offset) } /** - * intel_pmc_gcr_read() - Read PMC GCR register + * intel_pmc_gcr_read() - Read a 32-bit PMC GCR register * @offset: offset of GCR register from GCR address base * @data: data pointer for storing the register output * - * Reads the PMC GCR register of given offset. + * Reads the 32-bit PMC GCR register at given offset. * * Return: negative value on error or 0 on success. */ @@ -244,6 +244,35 @@ int intel_pmc_gcr_read(u32 offset, u32 *data) EXPORT_SYMBOL_GPL(intel_pmc_gcr_read); /** + * intel_pmc_gcr_read64() - Read a 64-bit PMC GCR register + * @offset: offset of GCR register from GCR address base + * @data: data pointer for storing the register output + * + * Reads the 64-bit PMC GCR register at given offset. + * + * Return: negative value on error or 0 on success. + */ +int intel_pmc_gcr_read64(u32 offset, u64 *data) +{ + int ret; + + spin_lock(&ipcdev.gcr_lock); + + ret = is_gcr_valid(offset); + if (ret < 0) { + spin_unlock(&ipcdev.gcr_lock); + return ret; + } + + *data = readq(ipcdev.gcr_mem_base + offset); + + spin_unlock(&ipcdev.gcr_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(intel_pmc_gcr_read64); + +/** * intel_pmc_gcr_write() - Write PMC GCR register * @offset: offset of GCR register from GCR address base * @data: register update value diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c index 4249e8267bbc..ffd0474b0531 100644 --- a/drivers/platform/x86/intel_telemetry_debugfs.c +++ b/drivers/platform/x86/intel_telemetry_debugfs.c @@ -23,7 +23,6 @@ */ #include <linux/debugfs.h> #include <linux/device.h> -#include <linux/io.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/seq_file.h> @@ -32,11 +31,10 @@ #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/intel_pmc_ipc.h> -#include <asm/intel_punit_ipc.h> #include <asm/intel_telemetry.h> -#define DRIVER_NAME "telemetry_soc_debugfs" -#define DRIVER_VERSION "1.0.0" +#define DRIVER_NAME "telemetry_soc_debugfs" +#define DRIVER_VERSION "1.0.0" /* ApolloLake SoC Event-IDs */ #define TELEM_APL_PSS_PSTATES_ID 0x2802 @@ -98,10 +96,6 @@ static u32 suspend_shlw_ctr_temp, suspend_deep_ctr_temp; static u64 suspend_shlw_res_temp, suspend_deep_res_temp; struct telemetry_susp_stats { - u32 shlw_swake_ctr; - u32 deep_swake_ctr; - u64 shlw_swake_res; - u64 deep_swake_res; u32 shlw_ctr; u32 deep_ctr; u64 shlw_res; @@ -250,7 +244,6 @@ static struct telem_ioss_pg_info telem_apl_ioss_pg_data[] = { {"PRTC", 25}, }; - struct telemetry_debugfs_conf { struct telemetry_susp_stats suspend_stats; struct dentry *telemetry_dbg_dir; @@ -385,7 +378,6 @@ static int telem_pss_states_show(struct seq_file *s, void *unused) TELEM_APL_MASK_PCS_STATE; } - TELEM_CHECK_AND_PARSE_EVTS(conf->pss_idle_id, conf->pss_idle_evts - 1, pss_idle, evtlog[index].telem_evtlog, @@ -405,7 +397,6 @@ static int telem_pss_states_show(struct seq_file *s, void *unused) conf->pcs_s0ix_blkd_data, TELEM_MASK_BYTE); - TELEM_CHECK_AND_PARSE_EVTS(conf->pss_wakeup_id, conf->pss_wakeup_evts, pss_s0ix_wakeup, @@ -498,7 +489,6 @@ static const struct file_operations telem_pss_ops = { .release = single_release, }; - static int telem_ioss_states_show(struct seq_file *s, void *unused) { struct telemetry_evtlog evtlog[TELEM_MAX_OS_ALLOCATED_EVENTS]; @@ -598,19 +588,15 @@ static int telem_soc_states_show(struct seq_file *s, void *unused) seq_printf(s, "S0IX Shallow\t\t\t %10u\t %10llu\n", s0ix_shlw_ctr - - conf->suspend_stats.shlw_ctr - - conf->suspend_stats.shlw_swake_ctr, + conf->suspend_stats.shlw_ctr, (u64)((s0ix_shlw_res - - conf->suspend_stats.shlw_res - - conf->suspend_stats.shlw_swake_res)*10/192)); + conf->suspend_stats.shlw_res)*10/192)); seq_printf(s, "S0IX Deep\t\t\t %10u\t %10llu\n", s0ix_deep_ctr - - conf->suspend_stats.deep_ctr - - conf->suspend_stats.deep_swake_ctr, + conf->suspend_stats.deep_ctr, (u64)((s0ix_deep_res - - conf->suspend_stats.deep_res - - conf->suspend_stats.deep_swake_res)*10/192)); + conf->suspend_stats.deep_res)*10/192)); seq_printf(s, "Suspend(With S0ixShallow)\t %10u\t %10llu\n", conf->suspend_stats.shlw_ctr, @@ -620,14 +606,8 @@ static int telem_soc_states_show(struct seq_file *s, void *unused) conf->suspend_stats.deep_ctr, (u64)(conf->suspend_stats.deep_res*10)/192); - seq_printf(s, "Suspend(With Shallow-Wakes)\t %10u\t %10llu\n", - conf->suspend_stats.shlw_swake_ctr + - conf->suspend_stats.deep_swake_ctr, - (u64)((conf->suspend_stats.shlw_swake_res + - conf->suspend_stats.deep_swake_res)*10/192)); - - seq_printf(s, "S0IX+Suspend Total\t\t %10u\t %10llu\n", s0ix_total_ctr, - (u64)(s0ix_total_res*10/192)); + seq_printf(s, "TOTAL S0IX\t\t\t %10u\t %10llu\n", s0ix_total_ctr, + (u64)(s0ix_total_res*10/192)); seq_puts(s, "\n-------------------------------------------------\n"); seq_puts(s, "\t\tDEVICE STATES\n"); seq_puts(s, "-------------------------------------------------\n"); @@ -772,7 +752,6 @@ static const struct file_operations telem_pss_trc_verb_ops = { .release = single_release, }; - static int telem_ioss_trc_verb_show(struct seq_file *s, void *unused) { u32 verbosity; @@ -890,28 +869,45 @@ static int pm_suspend_exit_cb(void) goto out; } + /* + * Due to some design limitations in the firmware, sometimes the + * counters do not get updated by the time we reach here. As a + * workaround, we try to see if this was a genuine case of sleep + * failure or not by cross-checking from PMC GCR registers directly. + */ + if (suspend_shlw_ctr_exit == suspend_shlw_ctr_temp && + suspend_deep_ctr_exit == suspend_deep_ctr_temp) { + ret = intel_pmc_gcr_read64(PMC_GCR_TELEM_SHLW_S0IX_REG, + &suspend_shlw_res_exit); + if (ret < 0) + goto out; + + ret = intel_pmc_gcr_read64(PMC_GCR_TELEM_DEEP_S0IX_REG, + &suspend_deep_res_exit); + if (ret < 0) + goto out; + + if (suspend_shlw_res_exit > suspend_shlw_res_temp) + suspend_shlw_ctr_exit++; + + if (suspend_deep_res_exit > suspend_deep_res_temp) + suspend_deep_ctr_exit++; + } + suspend_shlw_ctr_exit -= suspend_shlw_ctr_temp; suspend_deep_ctr_exit -= suspend_deep_ctr_temp; suspend_shlw_res_exit -= suspend_shlw_res_temp; suspend_deep_res_exit -= suspend_deep_res_temp; - if (suspend_shlw_ctr_exit == 1) { + if (suspend_shlw_ctr_exit != 0) { conf->suspend_stats.shlw_ctr += suspend_shlw_ctr_exit; conf->suspend_stats.shlw_res += suspend_shlw_res_exit; } - /* Shallow Wakes Case */ - else if (suspend_shlw_ctr_exit > 1) { - conf->suspend_stats.shlw_swake_ctr += - suspend_shlw_ctr_exit; - conf->suspend_stats.shlw_swake_res += - suspend_shlw_res_exit; - } - - if (suspend_deep_ctr_exit == 1) { + if (suspend_deep_ctr_exit != 0) { conf->suspend_stats.deep_ctr += suspend_deep_ctr_exit; @@ -919,15 +915,6 @@ static int pm_suspend_exit_cb(void) suspend_deep_res_exit; } - /* Shallow Wakes Case */ - else if (suspend_deep_ctr_exit > 1) { - conf->suspend_stats.deep_swake_ctr += - suspend_deep_ctr_exit; - - conf->suspend_stats.deep_swake_res += - suspend_deep_res_exit; - } - out: suspend_prep_ok = 0; return NOTIFY_OK; diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 504256c3660d..454e14f02285 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -35,20 +35,31 @@ #include <linux/dmi.h> #include <linux/i2c.h> #include <linux/i2c-mux.h> +#include <linux/io.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/platform_data/i2c-mux-reg.h> -#include <linux/platform_data/mlxcpld-hotplug.h> +#include <linux/platform_data/mlxreg.h> +#include <linux/regmap.h> #define MLX_PLAT_DEVICE_NAME "mlxplat" /* LPC bus IO offsets */ #define MLXPLAT_CPLD_LPC_I2C_BASE_ADRR 0x2000 #define MLXPLAT_CPLD_LPC_REG_BASE_ADRR 0x2500 -#define MLXPLAT_CPLD_LPC_REG_AGGR_ADRR 0x253a -#define MLXPLAT_CPLD_LPC_REG_PSU_ADRR 0x2558 -#define MLXPLAT_CPLD_LPC_REG_PWR_ADRR 0x2564 -#define MLXPLAT_CPLD_LPC_REG_FAN_ADRR 0x2588 +#define MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET 0x3a +#define MLXPLAT_CPLD_LPC_REG_AGGR_MASK_OFFSET 0x3b +#define MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET 0x40 +#define MLXPLAT_CPLD_LPC_REG_AGGRLO_MASK_OFFSET 0x41 +#define MLXPLAT_CPLD_LPC_REG_PSU_OFFSET 0x58 +#define MLXPLAT_CPLD_LPC_REG_PSU_EVENT_OFFSET 0x59 +#define MLXPLAT_CPLD_LPC_REG_PSU_MASK_OFFSET 0x5a +#define MLXPLAT_CPLD_LPC_REG_PWR_OFFSET 0x64 +#define MLXPLAT_CPLD_LPC_REG_PWR_EVENT_OFFSET 0x65 +#define MLXPLAT_CPLD_LPC_REG_PWR_MASK_OFFSET 0x66 +#define MLXPLAT_CPLD_LPC_REG_FAN_OFFSET 0x88 +#define MLXPLAT_CPLD_LPC_REG_FAN_EVENT_OFFSET 0x89 +#define MLXPLAT_CPLD_LPC_REG_FAN_MASK_OFFSET 0x8a #define MLXPLAT_CPLD_LPC_IO_RANGE 0x100 #define MLXPLAT_CPLD_LPC_I2C_CH1_OFF 0xdb #define MLXPLAT_CPLD_LPC_I2C_CH2_OFF 0xda @@ -66,10 +77,13 @@ #define MLXPLAT_CPLD_AGGR_FAN_MASK_DEF 0x40 #define MLXPLAT_CPLD_AGGR_MASK_DEF (MLXPLAT_CPLD_AGGR_PSU_MASK_DEF | \ MLXPLAT_CPLD_AGGR_FAN_MASK_DEF) +#define MLXPLAT_CPLD_AGGR_MASK_NG_DEF 0x04 +#define MLXPLAT_CPLD_LOW_AGGR_MASK_LOW 0xc0 #define MLXPLAT_CPLD_AGGR_MASK_MSN21XX 0x04 #define MLXPLAT_CPLD_PSU_MASK GENMASK(1, 0) #define MLXPLAT_CPLD_PWR_MASK GENMASK(1, 0) #define MLXPLAT_CPLD_FAN_MASK GENMASK(3, 0) +#define MLXPLAT_CPLD_FAN_NG_MASK GENMASK(5, 0) /* Start channel numbers */ #define MLXPLAT_CPLD_CH1 2 @@ -78,9 +92,19 @@ /* Number of LPC attached MUX platform devices */ #define MLXPLAT_CPLD_LPC_MUX_DEVS 2 +/* Hotplug devices adapter numbers */ +#define MLXPLAT_CPLD_NR_NONE -1 +#define MLXPLAT_CPLD_PSU_DEFAULT_NR 10 +#define MLXPLAT_CPLD_PSU_MSNXXXX_NR 4 +#define MLXPLAT_CPLD_FAN1_DEFAULT_NR 11 +#define MLXPLAT_CPLD_FAN2_DEFAULT_NR 12 +#define MLXPLAT_CPLD_FAN3_DEFAULT_NR 13 +#define MLXPLAT_CPLD_FAN4_DEFAULT_NR 14 + /* mlxplat_priv - platform private data * @pdev_i2c - i2c controller platform device * @pdev_mux - array of mux platform devices + * @pdev_hotplug - hotplug platform devices */ struct mlxplat_priv { struct platform_device *pdev_i2c; @@ -138,86 +162,527 @@ static struct i2c_mux_reg_platform_data mlxplat_mux_data[] = { }; /* Platform hotplug devices */ -static struct mlxcpld_hotplug_device mlxplat_mlxcpld_psu[] = { +static struct i2c_board_info mlxplat_mlxcpld_psu[] = { + { + I2C_BOARD_INFO("24c02", 0x51), + }, + { + I2C_BOARD_INFO("24c02", 0x50), + }, +}; + +static struct i2c_board_info mlxplat_mlxcpld_ng_psu[] = { { - .brdinfo = { I2C_BOARD_INFO("24c02", 0x51) }, - .bus = 10, + I2C_BOARD_INFO("24c32", 0x51), }, { - .brdinfo = { I2C_BOARD_INFO("24c02", 0x50) }, - .bus = 10, + I2C_BOARD_INFO("24c32", 0x50), }, }; -static struct mlxcpld_hotplug_device mlxplat_mlxcpld_pwr[] = { +static struct i2c_board_info mlxplat_mlxcpld_pwr[] = { { - .brdinfo = { I2C_BOARD_INFO("dps460", 0x59) }, - .bus = 10, + I2C_BOARD_INFO("dps460", 0x59), }, { - .brdinfo = { I2C_BOARD_INFO("dps460", 0x58) }, - .bus = 10, + I2C_BOARD_INFO("dps460", 0x58), }, }; -static struct mlxcpld_hotplug_device mlxplat_mlxcpld_fan[] = { +static struct i2c_board_info mlxplat_mlxcpld_fan[] = { { - .brdinfo = { I2C_BOARD_INFO("24c32", 0x50) }, - .bus = 11, + I2C_BOARD_INFO("24c32", 0x50), }, { - .brdinfo = { I2C_BOARD_INFO("24c32", 0x50) }, - .bus = 12, + I2C_BOARD_INFO("24c32", 0x50), }, { - .brdinfo = { I2C_BOARD_INFO("24c32", 0x50) }, - .bus = 13, + I2C_BOARD_INFO("24c32", 0x50), }, { - .brdinfo = { I2C_BOARD_INFO("24c32", 0x50) }, - .bus = 14, + I2C_BOARD_INFO("24c32", 0x50), }, }; /* Platform hotplug default data */ +static struct mlxreg_core_data mlxplat_mlxcpld_default_psu_items_data[] = { + { + .label = "psu1", + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &mlxplat_mlxcpld_psu[0], + .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR, + }, + { + .label = "psu2", + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &mlxplat_mlxcpld_psu[1], + .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR, + }, +}; + +static struct mlxreg_core_data mlxplat_mlxcpld_default_pwr_items_data[] = { + { + .label = "pwr1", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[0], + .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR, + }, + { + .label = "pwr2", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[1], + .hpdev.nr = MLXPLAT_CPLD_PSU_DEFAULT_NR, + }, +}; + +static struct mlxreg_core_data mlxplat_mlxcpld_default_fan_items_data[] = { + { + .label = "fan1", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &mlxplat_mlxcpld_fan[0], + .hpdev.nr = MLXPLAT_CPLD_FAN1_DEFAULT_NR, + }, + { + .label = "fan2", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &mlxplat_mlxcpld_fan[1], + .hpdev.nr = MLXPLAT_CPLD_FAN2_DEFAULT_NR, + }, + { + .label = "fan3", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(2), + .hpdev.brdinfo = &mlxplat_mlxcpld_fan[2], + .hpdev.nr = MLXPLAT_CPLD_FAN3_DEFAULT_NR, + }, + { + .label = "fan4", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(3), + .hpdev.brdinfo = &mlxplat_mlxcpld_fan[3], + .hpdev.nr = MLXPLAT_CPLD_FAN4_DEFAULT_NR, + }, +}; + +static struct mlxreg_core_item mlxplat_mlxcpld_default_items[] = { + { + .data = mlxplat_mlxcpld_default_psu_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_PSU_MASK_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = MLXPLAT_CPLD_PSU_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_psu), + .inversed = 1, + .health = false, + }, + { + .data = mlxplat_mlxcpld_default_pwr_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_PWR_MASK_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = MLXPLAT_CPLD_PWR_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_pwr), + .inversed = 0, + .health = false, + }, + { + .data = mlxplat_mlxcpld_default_fan_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_FAN_MASK_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = MLXPLAT_CPLD_FAN_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_fan), + .inversed = 1, + .health = false, + }, +}; + static -struct mlxcpld_hotplug_platform_data mlxplat_mlxcpld_default_data = { - .top_aggr_offset = MLXPLAT_CPLD_LPC_REG_AGGR_ADRR, - .top_aggr_mask = MLXPLAT_CPLD_AGGR_MASK_DEF, - .top_aggr_psu_mask = MLXPLAT_CPLD_AGGR_PSU_MASK_DEF, - .psu_reg_offset = MLXPLAT_CPLD_LPC_REG_PSU_ADRR, - .psu_mask = MLXPLAT_CPLD_PSU_MASK, - .psu_count = ARRAY_SIZE(mlxplat_mlxcpld_psu), - .psu = mlxplat_mlxcpld_psu, - .top_aggr_pwr_mask = MLXPLAT_CPLD_AGGR_PWR_MASK_DEF, - .pwr_reg_offset = MLXPLAT_CPLD_LPC_REG_PWR_ADRR, - .pwr_mask = MLXPLAT_CPLD_PWR_MASK, - .pwr_count = ARRAY_SIZE(mlxplat_mlxcpld_pwr), - .pwr = mlxplat_mlxcpld_pwr, - .top_aggr_fan_mask = MLXPLAT_CPLD_AGGR_FAN_MASK_DEF, - .fan_reg_offset = MLXPLAT_CPLD_LPC_REG_FAN_ADRR, - .fan_mask = MLXPLAT_CPLD_FAN_MASK, - .fan_count = ARRAY_SIZE(mlxplat_mlxcpld_fan), - .fan = mlxplat_mlxcpld_fan, +struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_default_data = { + .items = mlxplat_mlxcpld_default_items, + .counter = ARRAY_SIZE(mlxplat_mlxcpld_default_items), + .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET, + .mask = MLXPLAT_CPLD_AGGR_MASK_DEF, +}; + +static struct mlxreg_core_data mlxplat_mlxcpld_msn21xx_pwr_items_data[] = { + { + .label = "pwr1", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(0), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "pwr2", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(1), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, }; /* Platform hotplug MSN21xx system family data */ +static struct mlxreg_core_item mlxplat_mlxcpld_msn21xx_items[] = { + { + .data = mlxplat_mlxcpld_msn21xx_pwr_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_PWR_MASK_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = MLXPLAT_CPLD_PWR_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_msn21xx_pwr_items_data), + .inversed = 0, + .health = false, + }, +}; + +static +struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_msn21xx_data = { + .items = mlxplat_mlxcpld_msn21xx_items, + .counter = ARRAY_SIZE(mlxplat_mlxcpld_msn21xx_items), + .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET, + .mask = MLXPLAT_CPLD_AGGR_MASK_DEF, + .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET, + .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW, +}; + +/* Platform hotplug msn274x system family data */ +static struct mlxreg_core_data mlxplat_mlxcpld_msn274x_psu_items_data[] = { + { + .label = "psu1", + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &mlxplat_mlxcpld_psu[0], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + }, + { + .label = "psu2", + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &mlxplat_mlxcpld_psu[1], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + }, +}; + +static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_pwr_items_data[] = { + { + .label = "pwr1", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[0], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + }, + { + .label = "pwr2", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[1], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + }, +}; + +static struct mlxreg_core_data mlxplat_mlxcpld_msn274x_fan_items_data[] = { + { + .label = "fan1", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(0), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan2", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(1), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan3", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(2), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan4", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(3), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, +}; + +static struct mlxreg_core_item mlxplat_mlxcpld_msn274x_items[] = { + { + .data = mlxplat_mlxcpld_msn274x_psu_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = MLXPLAT_CPLD_PSU_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_msn274x_psu_items_data), + .inversed = 1, + .health = false, + }, + { + .data = mlxplat_mlxcpld_default_ng_pwr_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = MLXPLAT_CPLD_PWR_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_pwr_items_data), + .inversed = 0, + .health = false, + }, + { + .data = mlxplat_mlxcpld_msn274x_fan_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = MLXPLAT_CPLD_FAN_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_msn274x_fan_items_data), + .inversed = 1, + .health = false, + }, +}; + +static +struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_msn274x_data = { + .items = mlxplat_mlxcpld_msn274x_items, + .counter = ARRAY_SIZE(mlxplat_mlxcpld_msn274x_items), + .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET, + .mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET, + .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW, +}; + +/* Platform hotplug MSN201x system family data */ +static struct mlxreg_core_data mlxplat_mlxcpld_msn201x_pwr_items_data[] = { + { + .label = "pwr1", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(0), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "pwr2", + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = BIT(1), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, +}; + +static struct mlxreg_core_item mlxplat_mlxcpld_msn201x_items[] = { + { + .data = mlxplat_mlxcpld_msn201x_pwr_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_PWR_MASK_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = MLXPLAT_CPLD_PWR_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_msn201x_pwr_items_data), + .inversed = 0, + .health = false, + }, +}; + +static +struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_msn201x_data = { + .items = mlxplat_mlxcpld_msn21xx_items, + .counter = ARRAY_SIZE(mlxplat_mlxcpld_msn201x_items), + .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET, + .mask = MLXPLAT_CPLD_AGGR_MASK_DEF, + .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET, + .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW, +}; + +/* Platform hotplug next generation system family data */ +static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_psu_items_data[] = { + { + .label = "psu1", + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = BIT(0), + .hpdev.brdinfo = &mlxplat_mlxcpld_ng_psu[0], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + }, + { + .label = "psu2", + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = BIT(1), + .hpdev.brdinfo = &mlxplat_mlxcpld_ng_psu[1], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, + }, +}; + +static struct mlxreg_core_data mlxplat_mlxcpld_default_ng_fan_items_data[] = { + { + .label = "fan1", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(0), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan2", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(1), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan3", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(2), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan4", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(3), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan5", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(4), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, + { + .label = "fan6", + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = BIT(5), + .hpdev.nr = MLXPLAT_CPLD_NR_NONE, + }, +}; + +static struct mlxreg_core_item mlxplat_mlxcpld_default_ng_items[] = { + { + .data = mlxplat_mlxcpld_default_ng_psu_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PSU_OFFSET, + .mask = MLXPLAT_CPLD_PSU_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_psu_items_data), + .inversed = 1, + .health = false, + }, + { + .data = mlxplat_mlxcpld_default_ng_pwr_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, + .mask = MLXPLAT_CPLD_PWR_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_pwr_items_data), + .inversed = 0, + .health = false, + }, + { + .data = mlxplat_mlxcpld_default_ng_fan_items_data, + .aggr_mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .reg = MLXPLAT_CPLD_LPC_REG_FAN_OFFSET, + .mask = MLXPLAT_CPLD_FAN_NG_MASK, + .count = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_fan_items_data), + .inversed = 1, + .health = false, + }, +}; + static -struct mlxcpld_hotplug_platform_data mlxplat_mlxcpld_msn21xx_data = { - .top_aggr_offset = MLXPLAT_CPLD_LPC_REG_AGGR_ADRR, - .top_aggr_mask = MLXPLAT_CPLD_AGGR_MASK_MSN21XX, - .top_aggr_pwr_mask = MLXPLAT_CPLD_AGGR_MASK_MSN21XX, - .pwr_reg_offset = MLXPLAT_CPLD_LPC_REG_PWR_ADRR, - .pwr_mask = MLXPLAT_CPLD_PWR_MASK, - .pwr_count = ARRAY_SIZE(mlxplat_mlxcpld_pwr), +struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_default_ng_data = { + .items = mlxplat_mlxcpld_default_ng_items, + .counter = ARRAY_SIZE(mlxplat_mlxcpld_default_ng_items), + .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET, + .mask = MLXPLAT_CPLD_AGGR_MASK_NG_DEF, + .cell_low = MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET, + .mask_low = MLXPLAT_CPLD_LOW_AGGR_MASK_LOW, +}; + +static bool mlxplat_mlxcpld_writeable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case MLXPLAT_CPLD_LPC_REG_AGGR_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_AGGRLO_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_MASK_OFFSET: + return true; + } + return false; +} + +static bool mlxplat_mlxcpld_readable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET: + case MLXPLAT_CPLD_LPC_REG_AGGR_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET: + case MLXPLAT_CPLD_LPC_REG_AGGRLO_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_MASK_OFFSET: + return true; + } + return false; +} + +static bool mlxplat_mlxcpld_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET: + case MLXPLAT_CPLD_LPC_REG_AGGR_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_AGGRLO_OFFSET: + case MLXPLAT_CPLD_LPC_REG_AGGRLO_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PSU_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_PWR_MASK_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_EVENT_OFFSET: + case MLXPLAT_CPLD_LPC_REG_FAN_MASK_OFFSET: + return true; + } + return false; +} + +struct mlxplat_mlxcpld_regmap_context { + void __iomem *base; +}; + +static struct mlxplat_mlxcpld_regmap_context mlxplat_mlxcpld_regmap_ctx; + +static int +mlxplat_mlxcpld_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct mlxplat_mlxcpld_regmap_context *ctx = context; + + *val = ioread8(ctx->base + reg); + return 0; +} + +static int +mlxplat_mlxcpld_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct mlxplat_mlxcpld_regmap_context *ctx = context; + + iowrite8(val, ctx->base + reg); + return 0; +} + +static const struct regmap_config mlxplat_mlxcpld_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 255, + .cache_type = REGCACHE_FLAT, + .writeable_reg = mlxplat_mlxcpld_writeable_reg, + .readable_reg = mlxplat_mlxcpld_readable_reg, + .volatile_reg = mlxplat_mlxcpld_volatile_reg, + .reg_read = mlxplat_mlxcpld_reg_read, + .reg_write = mlxplat_mlxcpld_reg_write, }; static struct resource mlxplat_mlxcpld_resources[] = { - [0] = DEFINE_RES_IRQ_NAMED(17, "mlxcpld-hotplug"), + [0] = DEFINE_RES_IRQ_NAMED(17, "mlxreg-hotplug"), }; static struct platform_device *mlxplat_dev; -static struct mlxcpld_hotplug_platform_data *mlxplat_hotplug; +static struct mlxreg_core_hotplug_platform_data *mlxplat_hotplug; static int __init mlxplat_dmi_default_matched(const struct dmi_system_id *dmi) { @@ -247,8 +712,57 @@ static int __init mlxplat_dmi_msn21xx_matched(const struct dmi_system_id *dmi) return 1; }; +static int __init mlxplat_dmi_msn274x_matched(const struct dmi_system_id *dmi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) { + mlxplat_mux_data[i].values = mlxplat_msn21xx_channels; + mlxplat_mux_data[i].n_values = + ARRAY_SIZE(mlxplat_msn21xx_channels); + } + mlxplat_hotplug = &mlxplat_mlxcpld_msn274x_data; + + return 1; +}; + +static int __init mlxplat_dmi_msn201x_matched(const struct dmi_system_id *dmi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) { + mlxplat_mux_data[i].values = mlxplat_msn21xx_channels; + mlxplat_mux_data[i].n_values = + ARRAY_SIZE(mlxplat_msn21xx_channels); + } + mlxplat_hotplug = &mlxplat_mlxcpld_msn201x_data; + + return 1; +}; + +static int __init mlxplat_dmi_qmb7xx_matched(const struct dmi_system_id *dmi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxplat_mux_data); i++) { + mlxplat_mux_data[i].values = mlxplat_msn21xx_channels; + mlxplat_mux_data[i].n_values = + ARRAY_SIZE(mlxplat_msn21xx_channels); + } + mlxplat_hotplug = &mlxplat_mlxcpld_default_ng_data; + + return 1; +}; + static const struct dmi_system_id mlxplat_dmi_table[] __initconst = { { + .callback = mlxplat_dmi_msn274x_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "MSN274"), + }, + }, + { .callback = mlxplat_dmi_default_matched, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), @@ -283,9 +797,39 @@ static const struct dmi_system_id mlxplat_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "MSN21"), }, }, + { + .callback = mlxplat_dmi_msn201x_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "MSN201"), + }, + }, + { + .callback = mlxplat_dmi_qmb7xx_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "QMB7"), + }, + }, + { + .callback = mlxplat_dmi_qmb7xx_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "SN37"), + }, + }, + { + .callback = mlxplat_dmi_qmb7xx_matched, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Mellanox Technologies"), + DMI_MATCH(DMI_PRODUCT_NAME, "SN34"), + }, + }, { } }; +MODULE_DEVICE_TABLE(dmi, mlxplat_dmi_table); + static int __init mlxplat_init(void) { struct mlxplat_priv *priv; @@ -328,8 +872,23 @@ static int __init mlxplat_init(void) } } + mlxplat_mlxcpld_regmap_ctx.base = devm_ioport_map(&mlxplat_dev->dev, + mlxplat_lpc_resources[1].start, 1); + if (!mlxplat_mlxcpld_regmap_ctx.base) { + err = -ENOMEM; + goto fail_platform_mux_register; + } + + mlxplat_hotplug->regmap = devm_regmap_init(&mlxplat_dev->dev, NULL, + &mlxplat_mlxcpld_regmap_ctx, + &mlxplat_mlxcpld_regmap_config); + if (IS_ERR(mlxplat_hotplug->regmap)) { + err = PTR_ERR(mlxplat_hotplug->regmap); + goto fail_platform_mux_register; + } + priv->pdev_hotplug = platform_device_register_resndata( - &mlxplat_dev->dev, "mlxcpld-hotplug", + &mlxplat_dev->dev, "mlxreg-hotplug", PLATFORM_DEVID_NONE, mlxplat_mlxcpld_resources, ARRAY_SIZE(mlxplat_mlxcpld_resources), @@ -339,8 +898,16 @@ static int __init mlxplat_init(void) goto fail_platform_mux_register; } + /* Sync registers with hardware. */ + regcache_mark_dirty(mlxplat_hotplug->regmap); + err = regcache_sync(mlxplat_hotplug->regmap); + if (err) + goto fail_platform_hotplug_register; + return 0; +fail_platform_hotplug_register: + platform_device_unregister(priv->pdev_hotplug); fail_platform_mux_register: while (--i >= 0) platform_device_unregister(priv->pdev_mux[i]); @@ -370,8 +937,3 @@ module_exit(mlxplat_exit); MODULE_AUTHOR("Vadim Pasternak (vadimp@mellanox.com)"); MODULE_DESCRIPTION("Mellanox platform driver"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_ALIAS("dmi:*:*Mellanox*:MSN24*:"); -MODULE_ALIAS("dmi:*:*Mellanox*:MSN27*:"); -MODULE_ALIAS("dmi:*:*Mellanox*:MSB*:"); -MODULE_ALIAS("dmi:*:*Mellanox*:MSX*:"); -MODULE_ALIAS("dmi:*:*Mellanox*:MSN21*:"); diff --git a/drivers/platform/x86/mlxcpld-hotplug.c b/drivers/platform/x86/mlxcpld-hotplug.c deleted file mode 100644 index aff3686b3b37..000000000000 --- a/drivers/platform/x86/mlxcpld-hotplug.c +++ /dev/null @@ -1,515 +0,0 @@ -/* - * drivers/platform/x86/mlxcpld-hotplug.c - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. - * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com> - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#include <linux/bitops.h> -#include <linux/device.h> -#include <linux/hwmon.h> -#include <linux/hwmon-sysfs.h> -#include <linux/i2c.h> -#include <linux/interrupt.h> -#include <linux/io.h> -#include <linux/module.h> -#include <linux/platform_data/mlxcpld-hotplug.h> -#include <linux/platform_device.h> -#include <linux/spinlock.h> -#include <linux/wait.h> -#include <linux/workqueue.h> - -/* Offset of event and mask registers from status register */ -#define MLXCPLD_HOTPLUG_EVENT_OFF 1 -#define MLXCPLD_HOTPLUG_MASK_OFF 2 -#define MLXCPLD_HOTPLUG_AGGR_MASK_OFF 1 - -#define MLXCPLD_HOTPLUG_ATTRS_NUM 8 - -/** - * enum mlxcpld_hotplug_attr_type - sysfs attributes for hotplug events: - * @MLXCPLD_HOTPLUG_ATTR_TYPE_PSU: power supply unit attribute; - * @MLXCPLD_HOTPLUG_ATTR_TYPE_PWR: power cable attribute; - * @MLXCPLD_HOTPLUG_ATTR_TYPE_FAN: FAN drawer attribute; - */ -enum mlxcpld_hotplug_attr_type { - MLXCPLD_HOTPLUG_ATTR_TYPE_PSU, - MLXCPLD_HOTPLUG_ATTR_TYPE_PWR, - MLXCPLD_HOTPLUG_ATTR_TYPE_FAN, -}; - -/** - * struct mlxcpld_hotplug_priv_data - platform private data: - * @irq: platform interrupt number; - * @pdev: platform device; - * @plat: platform data; - * @hwmon: hwmon device; - * @mlxcpld_hotplug_attr: sysfs attributes array; - * @mlxcpld_hotplug_dev_attr: sysfs sensor device attribute array; - * @group: sysfs attribute group; - * @groups: list of sysfs attribute group for hwmon registration; - * @dwork: delayed work template; - * @lock: spin lock; - * @aggr_cache: last value of aggregation register status; - * @psu_cache: last value of PSU register status; - * @pwr_cache: last value of power register status; - * @fan_cache: last value of FAN register status; - */ -struct mlxcpld_hotplug_priv_data { - int irq; - struct platform_device *pdev; - struct mlxcpld_hotplug_platform_data *plat; - struct device *hwmon; - struct attribute *mlxcpld_hotplug_attr[MLXCPLD_HOTPLUG_ATTRS_NUM + 1]; - struct sensor_device_attribute_2 - mlxcpld_hotplug_dev_attr[MLXCPLD_HOTPLUG_ATTRS_NUM]; - struct attribute_group group; - const struct attribute_group *groups[2]; - struct delayed_work dwork; - spinlock_t lock; - u8 aggr_cache; - u8 psu_cache; - u8 pwr_cache; - u8 fan_cache; -}; - -static ssize_t mlxcpld_hotplug_attr_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct platform_device *pdev = to_platform_device(dev); - struct mlxcpld_hotplug_priv_data *priv = platform_get_drvdata(pdev); - int index = to_sensor_dev_attr_2(attr)->index; - int nr = to_sensor_dev_attr_2(attr)->nr; - u8 reg_val = 0; - - switch (nr) { - case MLXCPLD_HOTPLUG_ATTR_TYPE_PSU: - /* Bit = 0 : PSU is present. */ - reg_val = !!!(inb(priv->plat->psu_reg_offset) & BIT(index)); - break; - - case MLXCPLD_HOTPLUG_ATTR_TYPE_PWR: - /* Bit = 1 : power cable is attached. */ - reg_val = !!(inb(priv->plat->pwr_reg_offset) & BIT(index % - priv->plat->pwr_count)); - break; - - case MLXCPLD_HOTPLUG_ATTR_TYPE_FAN: - /* Bit = 0 : FAN is present. */ - reg_val = !!!(inb(priv->plat->fan_reg_offset) & BIT(index % - priv->plat->fan_count)); - break; - } - - return sprintf(buf, "%u\n", reg_val); -} - -#define PRIV_ATTR(i) priv->mlxcpld_hotplug_attr[i] -#define PRIV_DEV_ATTR(i) priv->mlxcpld_hotplug_dev_attr[i] -static int mlxcpld_hotplug_attr_init(struct mlxcpld_hotplug_priv_data *priv) -{ - int num_attrs = priv->plat->psu_count + priv->plat->pwr_count + - priv->plat->fan_count; - int i; - - priv->group.attrs = devm_kzalloc(&priv->pdev->dev, num_attrs * - sizeof(struct attribute *), - GFP_KERNEL); - if (!priv->group.attrs) - return -ENOMEM; - - for (i = 0; i < num_attrs; i++) { - PRIV_ATTR(i) = &PRIV_DEV_ATTR(i).dev_attr.attr; - - if (i < priv->plat->psu_count) { - PRIV_ATTR(i)->name = devm_kasprintf(&priv->pdev->dev, - GFP_KERNEL, "psu%u", i + 1); - PRIV_DEV_ATTR(i).nr = MLXCPLD_HOTPLUG_ATTR_TYPE_PSU; - } else if (i < priv->plat->psu_count + priv->plat->pwr_count) { - PRIV_ATTR(i)->name = devm_kasprintf(&priv->pdev->dev, - GFP_KERNEL, "pwr%u", i % - priv->plat->pwr_count + 1); - PRIV_DEV_ATTR(i).nr = MLXCPLD_HOTPLUG_ATTR_TYPE_PWR; - } else { - PRIV_ATTR(i)->name = devm_kasprintf(&priv->pdev->dev, - GFP_KERNEL, "fan%u", i % - priv->plat->fan_count + 1); - PRIV_DEV_ATTR(i).nr = MLXCPLD_HOTPLUG_ATTR_TYPE_FAN; - } - - if (!PRIV_ATTR(i)->name) { - dev_err(&priv->pdev->dev, "Memory allocation failed for sysfs attribute %d.\n", - i + 1); - return -ENOMEM; - } - - PRIV_DEV_ATTR(i).dev_attr.attr.name = PRIV_ATTR(i)->name; - PRIV_DEV_ATTR(i).dev_attr.attr.mode = S_IRUGO; - PRIV_DEV_ATTR(i).dev_attr.show = mlxcpld_hotplug_attr_show; - PRIV_DEV_ATTR(i).index = i; - sysfs_attr_init(&PRIV_DEV_ATTR(i).dev_attr.attr); - } - - priv->group.attrs = priv->mlxcpld_hotplug_attr; - priv->groups[0] = &priv->group; - priv->groups[1] = NULL; - - return 0; -} - -static int mlxcpld_hotplug_device_create(struct device *dev, - struct mlxcpld_hotplug_device *item) -{ - item->adapter = i2c_get_adapter(item->bus); - if (!item->adapter) { - dev_err(dev, "Failed to get adapter for bus %d\n", - item->bus); - return -EFAULT; - } - - item->client = i2c_new_device(item->adapter, &item->brdinfo); - if (!item->client) { - dev_err(dev, "Failed to create client %s at bus %d at addr 0x%02x\n", - item->brdinfo.type, item->bus, item->brdinfo.addr); - i2c_put_adapter(item->adapter); - item->adapter = NULL; - return -EFAULT; - } - - return 0; -} - -static void mlxcpld_hotplug_device_destroy(struct mlxcpld_hotplug_device *item) -{ - if (item->client) { - i2c_unregister_device(item->client); - item->client = NULL; - } - - if (item->adapter) { - i2c_put_adapter(item->adapter); - item->adapter = NULL; - } -} - -static inline void -mlxcpld_hotplug_work_helper(struct device *dev, - struct mlxcpld_hotplug_device *item, u8 is_inverse, - u16 offset, u8 mask, u8 *cache) -{ - u8 val, asserted; - int bit; - - /* Mask event. */ - outb(0, offset + MLXCPLD_HOTPLUG_MASK_OFF); - /* Read status. */ - val = inb(offset) & mask; - asserted = *cache ^ val; - *cache = val; - - /* - * Validate if item related to received signal type is valid. - * It should never happen, excepted the situation when some - * piece of hardware is broken. In such situation just produce - * error message and return. Caller must continue to handle the - * signals from other devices if any. - */ - if (unlikely(!item)) { - dev_err(dev, "False signal is received: register at offset 0x%02x, mask 0x%02x.\n", - offset, mask); - return; - } - - for_each_set_bit(bit, (unsigned long *)&asserted, 8) { - if (val & BIT(bit)) { - if (is_inverse) - mlxcpld_hotplug_device_destroy(item + bit); - else - mlxcpld_hotplug_device_create(dev, item + bit); - } else { - if (is_inverse) - mlxcpld_hotplug_device_create(dev, item + bit); - else - mlxcpld_hotplug_device_destroy(item + bit); - } - } - - /* Acknowledge event. */ - outb(0, offset + MLXCPLD_HOTPLUG_EVENT_OFF); - /* Unmask event. */ - outb(mask, offset + MLXCPLD_HOTPLUG_MASK_OFF); -} - -/* - * mlxcpld_hotplug_work_handler - performs traversing of CPLD interrupt - * registers according to the below hierarchy schema: - * - * Aggregation registers (status/mask) - * PSU registers: *---* - * *-----------------* | | - * |status/event/mask|----->| * | - * *-----------------* | | - * Power registers: | | - * *-----------------* | | - * |status/event/mask|----->| * |---> CPU - * *-----------------* | | - * FAN registers: - * *-----------------* | | - * |status/event/mask|----->| * | - * *-----------------* | | - * *---* - * In case some system changed are detected: FAN in/out, PSU in/out, power - * cable attached/detached, relevant device is created or destroyed. - */ -static void mlxcpld_hotplug_work_handler(struct work_struct *work) -{ - struct mlxcpld_hotplug_priv_data *priv = container_of(work, - struct mlxcpld_hotplug_priv_data, dwork.work); - u8 val, aggr_asserted; - unsigned long flags; - - /* Mask aggregation event. */ - outb(0, priv->plat->top_aggr_offset + MLXCPLD_HOTPLUG_AGGR_MASK_OFF); - /* Read aggregation status. */ - val = inb(priv->plat->top_aggr_offset) & priv->plat->top_aggr_mask; - aggr_asserted = priv->aggr_cache ^ val; - priv->aggr_cache = val; - - /* Handle PSU configuration changes. */ - if (aggr_asserted & priv->plat->top_aggr_psu_mask) - mlxcpld_hotplug_work_helper(&priv->pdev->dev, priv->plat->psu, - 1, priv->plat->psu_reg_offset, - priv->plat->psu_mask, - &priv->psu_cache); - - /* Handle power cable configuration changes. */ - if (aggr_asserted & priv->plat->top_aggr_pwr_mask) - mlxcpld_hotplug_work_helper(&priv->pdev->dev, priv->plat->pwr, - 0, priv->plat->pwr_reg_offset, - priv->plat->pwr_mask, - &priv->pwr_cache); - - /* Handle FAN configuration changes. */ - if (aggr_asserted & priv->plat->top_aggr_fan_mask) - mlxcpld_hotplug_work_helper(&priv->pdev->dev, priv->plat->fan, - 1, priv->plat->fan_reg_offset, - priv->plat->fan_mask, - &priv->fan_cache); - - if (aggr_asserted) { - spin_lock_irqsave(&priv->lock, flags); - - /* - * It is possible, that some signals have been inserted, while - * interrupt has been masked by mlxcpld_hotplug_work_handler. - * In this case such signals will be missed. In order to handle - * these signals delayed work is canceled and work task - * re-scheduled for immediate execution. It allows to handle - * missed signals, if any. In other case work handler just - * validates that no new signals have been received during - * masking. - */ - cancel_delayed_work(&priv->dwork); - schedule_delayed_work(&priv->dwork, 0); - - spin_unlock_irqrestore(&priv->lock, flags); - - return; - } - - /* Unmask aggregation event (no need acknowledge). */ - outb(priv->plat->top_aggr_mask, priv->plat->top_aggr_offset + - MLXCPLD_HOTPLUG_AGGR_MASK_OFF); -} - -static void mlxcpld_hotplug_set_irq(struct mlxcpld_hotplug_priv_data *priv) -{ - /* Clear psu presense event. */ - outb(0, priv->plat->psu_reg_offset + MLXCPLD_HOTPLUG_EVENT_OFF); - /* Set psu initial status as mask and unmask psu event. */ - priv->psu_cache = priv->plat->psu_mask; - outb(priv->plat->psu_mask, priv->plat->psu_reg_offset + - MLXCPLD_HOTPLUG_MASK_OFF); - - /* Clear power cable event. */ - outb(0, priv->plat->pwr_reg_offset + MLXCPLD_HOTPLUG_EVENT_OFF); - /* Keep power initial status as zero and unmask power event. */ - outb(priv->plat->pwr_mask, priv->plat->pwr_reg_offset + - MLXCPLD_HOTPLUG_MASK_OFF); - - /* Clear fan presense event. */ - outb(0, priv->plat->fan_reg_offset + MLXCPLD_HOTPLUG_EVENT_OFF); - /* Set fan initial status as mask and unmask fan event. */ - priv->fan_cache = priv->plat->fan_mask; - outb(priv->plat->fan_mask, priv->plat->fan_reg_offset + - MLXCPLD_HOTPLUG_MASK_OFF); - - /* Keep aggregation initial status as zero and unmask events. */ - outb(priv->plat->top_aggr_mask, priv->plat->top_aggr_offset + - MLXCPLD_HOTPLUG_AGGR_MASK_OFF); - - /* Invoke work handler for initializing hot plug devices setting. */ - mlxcpld_hotplug_work_handler(&priv->dwork.work); - - enable_irq(priv->irq); -} - -static void mlxcpld_hotplug_unset_irq(struct mlxcpld_hotplug_priv_data *priv) -{ - int i; - - disable_irq(priv->irq); - cancel_delayed_work_sync(&priv->dwork); - - /* Mask aggregation event. */ - outb(0, priv->plat->top_aggr_offset + MLXCPLD_HOTPLUG_AGGR_MASK_OFF); - - /* Mask psu presense event. */ - outb(0, priv->plat->psu_reg_offset + MLXCPLD_HOTPLUG_MASK_OFF); - /* Clear psu presense event. */ - outb(0, priv->plat->psu_reg_offset + MLXCPLD_HOTPLUG_EVENT_OFF); - - /* Mask power cable event. */ - outb(0, priv->plat->pwr_reg_offset + MLXCPLD_HOTPLUG_MASK_OFF); - /* Clear power cable event. */ - outb(0, priv->plat->pwr_reg_offset + MLXCPLD_HOTPLUG_EVENT_OFF); - - /* Mask fan presense event. */ - outb(0, priv->plat->fan_reg_offset + MLXCPLD_HOTPLUG_MASK_OFF); - /* Clear fan presense event. */ - outb(0, priv->plat->fan_reg_offset + MLXCPLD_HOTPLUG_EVENT_OFF); - - /* Remove all the attached devices. */ - for (i = 0; i < priv->plat->psu_count; i++) - mlxcpld_hotplug_device_destroy(priv->plat->psu + i); - - for (i = 0; i < priv->plat->pwr_count; i++) - mlxcpld_hotplug_device_destroy(priv->plat->pwr + i); - - for (i = 0; i < priv->plat->fan_count; i++) - mlxcpld_hotplug_device_destroy(priv->plat->fan + i); -} - -static irqreturn_t mlxcpld_hotplug_irq_handler(int irq, void *dev) -{ - struct mlxcpld_hotplug_priv_data *priv = - (struct mlxcpld_hotplug_priv_data *)dev; - - /* Schedule work task for immediate execution.*/ - schedule_delayed_work(&priv->dwork, 0); - - return IRQ_HANDLED; -} - -static int mlxcpld_hotplug_probe(struct platform_device *pdev) -{ - struct mlxcpld_hotplug_platform_data *pdata; - struct mlxcpld_hotplug_priv_data *priv; - int err; - - pdata = dev_get_platdata(&pdev->dev); - if (!pdata) { - dev_err(&pdev->dev, "Failed to get platform data.\n"); - return -EINVAL; - } - - priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - priv->pdev = pdev; - priv->plat = pdata; - - priv->irq = platform_get_irq(pdev, 0); - if (priv->irq < 0) { - dev_err(&pdev->dev, "Failed to get platform irq: %d\n", - priv->irq); - return priv->irq; - } - - err = devm_request_irq(&pdev->dev, priv->irq, - mlxcpld_hotplug_irq_handler, 0, pdev->name, - priv); - if (err) { - dev_err(&pdev->dev, "Failed to request irq: %d\n", err); - return err; - } - disable_irq(priv->irq); - - INIT_DELAYED_WORK(&priv->dwork, mlxcpld_hotplug_work_handler); - spin_lock_init(&priv->lock); - - err = mlxcpld_hotplug_attr_init(priv); - if (err) { - dev_err(&pdev->dev, "Failed to allocate attributes: %d\n", err); - return err; - } - - priv->hwmon = devm_hwmon_device_register_with_groups(&pdev->dev, - "mlxcpld_hotplug", priv, priv->groups); - if (IS_ERR(priv->hwmon)) { - dev_err(&pdev->dev, "Failed to register hwmon device %ld\n", - PTR_ERR(priv->hwmon)); - return PTR_ERR(priv->hwmon); - } - - platform_set_drvdata(pdev, priv); - - /* Perform initial interrupts setup. */ - mlxcpld_hotplug_set_irq(priv); - - return 0; -} - -static int mlxcpld_hotplug_remove(struct platform_device *pdev) -{ - struct mlxcpld_hotplug_priv_data *priv = platform_get_drvdata(pdev); - - /* Clean interrupts setup. */ - mlxcpld_hotplug_unset_irq(priv); - - return 0; -} - -static struct platform_driver mlxcpld_hotplug_driver = { - .driver = { - .name = "mlxcpld-hotplug", - }, - .probe = mlxcpld_hotplug_probe, - .remove = mlxcpld_hotplug_remove, -}; - -module_platform_driver(mlxcpld_hotplug_driver); - -MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>"); -MODULE_DESCRIPTION("Mellanox CPLD hotplug platform driver"); -MODULE_LICENSE("Dual BSD/GPL"); -MODULE_ALIAS("platform:mlxcpld-hotplug"); diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c index 77bac859342d..8f018b3f3cd4 100644 --- a/drivers/platform/x86/pmc_atom.c +++ b/drivers/platform/x86/pmc_atom.c @@ -309,17 +309,7 @@ static int pmc_dev_state_show(struct seq_file *s, void *unused) return 0; } -static int pmc_dev_state_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmc_dev_state_show, inode->i_private); -} - -static const struct file_operations pmc_dev_state_ops = { - .open = pmc_dev_state_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(pmc_dev_state); static int pmc_pss_state_show(struct seq_file *s, void *unused) { @@ -336,17 +326,7 @@ static int pmc_pss_state_show(struct seq_file *s, void *unused) return 0; } -static int pmc_pss_state_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmc_pss_state_show, inode->i_private); -} - -static const struct file_operations pmc_pss_state_ops = { - .open = pmc_pss_state_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(pmc_pss_state); static int pmc_sleep_tmr_show(struct seq_file *s, void *unused) { @@ -367,17 +347,7 @@ static int pmc_sleep_tmr_show(struct seq_file *s, void *unused) return 0; } -static int pmc_sleep_tmr_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmc_sleep_tmr_show, inode->i_private); -} - -static const struct file_operations pmc_sleep_tmr_ops = { - .open = pmc_sleep_tmr_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(pmc_sleep_tmr); static void pmc_dbgfs_unregister(struct pmc_dev *pmc) { @@ -395,17 +365,17 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc) pmc->dbgfs_dir = dir; f = debugfs_create_file("dev_state", S_IFREG | S_IRUGO, - dir, pmc, &pmc_dev_state_ops); + dir, pmc, &pmc_dev_state_fops); if (!f) goto err; f = debugfs_create_file("pss_state", S_IFREG | S_IRUGO, - dir, pmc, &pmc_pss_state_ops); + dir, pmc, &pmc_pss_state_fops); if (!f) goto err; f = debugfs_create_file("sleep_state", S_IFREG | S_IRUGO, - dir, pmc, &pmc_sleep_tmr_ops); + dir, pmc, &pmc_sleep_tmr_fops); if (!f) goto err; diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index d3cb26f6df73..03305e0b89ff 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -1252,7 +1252,7 @@ static int __init samsung_sysfs_init(struct samsung_laptop *samsung) } -static int show_call(struct seq_file *m, void *data) +static int samsung_laptop_call_show(struct seq_file *m, void *data) { struct samsung_laptop *samsung = m->private; struct sabi_data *sdata = &samsung->debug.data; @@ -1274,19 +1274,7 @@ static int show_call(struct seq_file *m, void *data) sdata->d0, sdata->d1, sdata->d2, sdata->d3); return 0; } - -static int samsung_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_call, inode->i_private); -} - -static const struct file_operations samsung_laptop_call_io_ops = { - .owner = THIS_MODULE, - .open = samsung_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(samsung_laptop_call); static void samsung_debugfs_exit(struct samsung_laptop *samsung) { @@ -1351,7 +1339,7 @@ static int samsung_debugfs_init(struct samsung_laptop *samsung) dent = debugfs_create_file("call", S_IFREG | S_IRUGO, samsung->debug.root, samsung, - &samsung_laptop_call_io_ops); + &samsung_laptop_call_fops); if (!dent) goto error_debugfs; diff --git a/drivers/platform/x86/silead_dmi.c b/drivers/platform/x86/silead_dmi.c index 266535c2a72f..3a624090191d 100644 --- a/drivers/platform/x86/silead_dmi.c +++ b/drivers/platform/x86/silead_dmi.c @@ -67,6 +67,21 @@ static const struct silead_ts_dmi_data dexp_ursus_7w_data = { .properties = dexp_ursus_7w_props, }; +static const struct property_entry surftab_twin_10_1_st10432_8_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1900), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), + PROPERTY_ENTRY_U32("touchscreen-inverted-y", 1), + PROPERTY_ENTRY_STRING("firmware-name", + "gsl3670-surftab-twin-10-1-st10432-8.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct silead_ts_dmi_data surftab_twin_10_1_st10432_8_data = { + .acpi_name = "MSSL1680:00", + .properties = surftab_twin_10_1_st10432_8_props, +}; + static const struct property_entry surftab_wintron70_st70416_6_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 884), PROPERTY_ENTRY_U32("touchscreen-size-y", 632), @@ -171,6 +186,97 @@ static const struct silead_ts_dmi_data digma_citi_e200_data = { .properties = digma_citi_e200_props, }; +static const struct property_entry onda_obook_20_plus_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1148), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-onda-obook-20-plus.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct silead_ts_dmi_data onda_obook_20_plus_data = { + .acpi_name = "MSSL1680:00", + .properties = onda_obook_20_plus_props, +}; + +static const struct property_entry chuwi_hi8_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1665), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_BOOL("silead,home-button"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-chuwi-hi8.fw"), + { } +}; + +static const struct silead_ts_dmi_data chuwi_hi8_data = { + .acpi_name = "MSSL0001:00", + .properties = chuwi_hi8_props, +}; + +static const struct property_entry chuwi_vi8_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1724), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-chuwi-vi8.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct silead_ts_dmi_data chuwi_vi8_data = { + .acpi_name = "MSSL1680:00", + .properties = chuwi_vi8_props, +}; + +static const struct property_entry trekstor_primebook_c13_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 2624), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1920), + PROPERTY_ENTRY_STRING("firmware-name", + "gsl1680-trekstor-primebook-c13.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct silead_ts_dmi_data trekstor_primebook_c13_data = { + .acpi_name = "MSSL1680:00", + .properties = trekstor_primebook_c13_props, +}; + +static const struct property_entry teclast_x98plus2_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 2048), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_STRING("firmware-name", + "gsl1686-teclast_x98plus2.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct silead_ts_dmi_data teclast_x98plus2_data = { + .acpi_name = "MSSL1680:00", + .properties = teclast_x98plus2_props, +}; + +static const struct property_entry teclast_x3_plus_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-teclast-x3-plus.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct silead_ts_dmi_data teclast_x3_plus_data = { + .acpi_name = "MSSL1680:00", + .properties = teclast_x3_plus_props, +}; + static const struct dmi_system_id silead_ts_dmi_table[] = { { /* CUBE iwork8 Air */ @@ -199,6 +305,14 @@ static const struct dmi_system_id silead_ts_dmi_table[] = { }, }, { + /* TrekStor SurfTab twin 10.1 ST10432-8 */ + .driver_data = (void *)&surftab_twin_10_1_st10432_8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TrekStor"), + DMI_MATCH(DMI_PRODUCT_NAME, "SurfTab twin 10.1"), + }, + }, + { /* Trekstor Surftab Wintron 7.0 ST70416-6 */ .driver_data = (void *)&surftab_wintron70_st70416_6_data, .matches = { @@ -209,6 +323,17 @@ static const struct dmi_system_id silead_ts_dmi_table[] = { }, }, { + /* Trekstor Surftab Wintron 7.0 ST70416-6, newer BIOS */ + .driver_data = (void *)&surftab_wintron70_st70416_6_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TrekStor"), + DMI_MATCH(DMI_PRODUCT_NAME, + "SurfTab wintron 7.0 ST70416-6"), + /* Exact match, different versions need different fw */ + DMI_MATCH(DMI_BIOS_VERSION, "TREK.G.WI71C.JGBMRBA05"), + }, + }, + { /* Ployer Momo7w (same hardware as the Trekstor ST70416-6) */ .driver_data = (void *)&surftab_wintron70_st70416_6_data, .matches = { @@ -271,6 +396,56 @@ static const struct dmi_system_id silead_ts_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"), }, }, + { + /* Onda oBook 20 Plus */ + .driver_data = (void *)&onda_obook_20_plus_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ONDA"), + DMI_MATCH(DMI_PRODUCT_NAME, "OBOOK 20 PLUS"), + }, + }, + { + /* Chuwi Hi8 */ + .driver_data = (void *)&chuwi_hi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ilife"), + DMI_MATCH(DMI_PRODUCT_NAME, "S806"), + }, + }, + { + /* Chuwi Vi8 (CWI506) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.D86JLBNR"), + }, + }, + { + /* Trekstor Primebook C13 */ + .driver_data = (void *)&trekstor_primebook_c13_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_MATCH(DMI_PRODUCT_NAME, "Primebook C13"), + }, + }, + { + /* Teclast X98 Plus II */ + .driver_data = (void *)&teclast_x98plus2_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_MATCH(DMI_PRODUCT_NAME, "X98 Plus II"), + }, + }, + { + /* Teclast X3 Plus */ + .driver_data = (void *)&teclast_x3_plus_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TECLAST"), + DMI_MATCH(DMI_PRODUCT_NAME, "X3 Plus"), + DMI_MATCH(DMI_BOARD_NAME, "X3 Plus"), + }, + }, { }, }; diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index a4fabf9d75f3..b205b037fd61 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -4128,7 +4128,7 @@ static __poll_t sonypi_misc_poll(struct file *file, poll_table *wait) { poll_wait(file, &sonypi_compat.fifo_proc_list, wait); if (kfifo_len(&sonypi_compat.fifo)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 117be48ff4de..d5eaf3b1edba 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -214,6 +214,10 @@ enum tpacpi_hkey_event_t { /* AC-related events */ TP_HKEY_EV_AC_CHANGED = 0x6040, /* AC status changed */ + /* Further user-interface events */ + TP_HKEY_EV_PALM_DETECTED = 0x60b0, /* palm hoveres keyboard */ + TP_HKEY_EV_PALM_UNDETECTED = 0x60b1, /* palm removed */ + /* Misc */ TP_HKEY_EV_RFKILL_CHANGED = 0x7000, /* rfkill switch changed */ }; @@ -2113,12 +2117,10 @@ static int hotkey_gmms_get_tablet_mode(int s, int *has_tablet_mode) TP_ACPI_MULTI_MODE_FLAT; break; case 4: - valid_modes = TP_ACPI_MULTI_MODE_LAPTOP | - TP_ACPI_MULTI_MODE_TABLET | - TP_ACPI_MULTI_MODE_STAND | - TP_ACPI_MULTI_MODE_TENT; - break; case 5: + /* In mode 4, FLAT is not specified as a valid mode. However, + * it can be seen at least on the X1 Yoga 2nd Generation. + */ valid_modes = TP_ACPI_MULTI_MODE_LAPTOP | TP_ACPI_MULTI_MODE_FLAT | TP_ACPI_MULTI_MODE_TABLET | @@ -4079,6 +4081,12 @@ static bool hotkey_notify_6xxx(const u32 hkey, *send_acpi_ev = false; break; + case TP_HKEY_EV_PALM_DETECTED: + case TP_HKEY_EV_PALM_UNDETECTED: + /* palm detected hovering the keyboard, forward to user-space + * via netlink for consumption */ + return true; + default: pr_warn("unknown possible thermal alarm or keyboard event received\n"); known = false; diff --git a/drivers/pps/generators/pps_gen_parport.c b/drivers/pps/generators/pps_gen_parport.c index dcd39fba6ddd..51cfde6afffd 100644 --- a/drivers/pps/generators/pps_gen_parport.c +++ b/drivers/pps/generators/pps_gen_parport.c @@ -70,7 +70,7 @@ static long hrtimer_error = SAFETY_INTERVAL; /* the kernel hrtimer event */ static enum hrtimer_restart hrtimer_event(struct hrtimer *timer) { - struct timespec expire_time, ts1, ts2, ts3, dts; + struct timespec64 expire_time, ts1, ts2, ts3, dts; struct pps_generator_pp *dev; struct parport *port; long lim, delta; @@ -78,7 +78,7 @@ static enum hrtimer_restart hrtimer_event(struct hrtimer *timer) /* We have to disable interrupts here. The idea is to prevent * other interrupts on the same processor to introduce random - * lags while polling the clock. getnstimeofday() takes <1us on + * lags while polling the clock. ktime_get_real_ts64() takes <1us on * most machines while other interrupt handlers can take much * more potentially. * @@ -88,22 +88,22 @@ static enum hrtimer_restart hrtimer_event(struct hrtimer *timer) local_irq_save(flags); /* first of all we get the time stamp... */ - getnstimeofday(&ts1); - expire_time = ktime_to_timespec(hrtimer_get_softexpires(timer)); + ktime_get_real_ts64(&ts1); + expire_time = ktime_to_timespec64(hrtimer_get_softexpires(timer)); dev = container_of(timer, struct pps_generator_pp, timer); lim = NSEC_PER_SEC - send_delay - dev->port_write_time; /* check if we are late */ if (expire_time.tv_sec != ts1.tv_sec || ts1.tv_nsec > lim) { local_irq_restore(flags); - pr_err("we are late this time %ld.%09ld\n", - ts1.tv_sec, ts1.tv_nsec); + pr_err("we are late this time %lld.%09ld\n", + (s64)ts1.tv_sec, ts1.tv_nsec); goto done; } /* busy loop until the time is right for an assert edge */ do { - getnstimeofday(&ts2); + ktime_get_real_ts64(&ts2); } while (expire_time.tv_sec == ts2.tv_sec && ts2.tv_nsec < lim); /* set the signal */ @@ -113,25 +113,25 @@ static enum hrtimer_restart hrtimer_event(struct hrtimer *timer) /* busy loop until the time is right for a clear edge */ lim = NSEC_PER_SEC - dev->port_write_time; do { - getnstimeofday(&ts2); + ktime_get_real_ts64(&ts2); } while (expire_time.tv_sec == ts2.tv_sec && ts2.tv_nsec < lim); /* unset the signal */ port->ops->write_control(port, NO_SIGNAL); - getnstimeofday(&ts3); + ktime_get_real_ts64(&ts3); local_irq_restore(flags); /* update calibrated port write time */ - dts = timespec_sub(ts3, ts2); + dts = timespec64_sub(ts3, ts2); dev->port_write_time = - (dev->port_write_time + timespec_to_ns(&dts)) >> 1; + (dev->port_write_time + timespec64_to_ns(&dts)) >> 1; done: /* update calibrated hrtimer error */ - dts = timespec_sub(ts1, expire_time); - delta = timespec_to_ns(&dts); + dts = timespec64_sub(ts1, expire_time); + delta = timespec64_to_ns(&dts); /* If the new error value is bigger then the old, use the new * value, if not then slowly move towards the new value. This * way it should be safe in bad conditions and efficient in @@ -161,17 +161,17 @@ static void calibrate_port(struct pps_generator_pp *dev) long acc = 0; for (i = 0; i < (1 << PORT_NTESTS_SHIFT); i++) { - struct timespec a, b; + struct timespec64 a, b; unsigned long irq_flags; local_irq_save(irq_flags); - getnstimeofday(&a); + ktime_get_real_ts64(&a); port->ops->write_control(port, NO_SIGNAL); - getnstimeofday(&b); + ktime_get_real_ts64(&b); local_irq_restore(irq_flags); - b = timespec_sub(b, a); - acc += timespec_to_ns(&b); + b = timespec64_sub(b, a); + acc += timespec64_to_ns(&b); } dev->port_write_time = acc >> PORT_NTESTS_SHIFT; @@ -180,9 +180,9 @@ static void calibrate_port(struct pps_generator_pp *dev) static inline ktime_t next_intr_time(struct pps_generator_pp *dev) { - struct timespec ts; + struct timespec64 ts; - getnstimeofday(&ts); + ktime_get_real_ts64(&ts); return ktime_set(ts.tv_sec + ((ts.tv_nsec > 990 * NSEC_PER_MSEC) ? 1 : 0), diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 1d42385b1aa5..8febacb8fc54 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -55,7 +55,7 @@ static __poll_t pps_cdev_poll(struct file *file, poll_table *wait) poll_wait(file, &pps->queue, wait); - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } static int pps_cdev_fasync(int fd, struct file *file, int on) diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index a593b4cf47bf..767c485af59b 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -286,7 +286,7 @@ __poll_t ptp_poll(struct posix_clock *pc, struct file *fp, poll_table *wait) poll_wait(fp, &ptp->tsev_wq, wait); - return queue_cnt(&ptp->tsevq) ? POLLIN : 0; + return queue_cnt(&ptp->tsevq) ? EPOLLIN : 0; } #define EXTTS_BUFSIZE (PTP_BUF_TIMESTAMPS * sizeof(struct ptp_extts_event)) diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 6092b3a5978e..cfb54e01d758 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -2325,7 +2325,7 @@ static __poll_t mport_cdev_poll(struct file *filp, poll_table *wait) poll_wait(filp, &priv->event_rx_wait, wait); if (kfifo_len(&priv->event_fifo)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c index e2a418598129..006ea5a45020 100644 --- a/drivers/rapidio/devices/tsi721_dma.c +++ b/drivers/rapidio/devices/tsi721_dma.c @@ -222,7 +222,7 @@ static int tsi721_bdma_ch_free(struct tsi721_bdma_chan *bdma_chan) struct tsi721_device *priv = to_tsi721(bdma_chan->dchan.device); #endif - if (bdma_chan->bd_base == NULL) + if (!bdma_chan->bd_base) return 0; /* Check if DMA channel still running */ @@ -346,7 +346,7 @@ tsi721_desc_fill_init(struct tsi721_tx_desc *desc, { u64 rio_addr; - if (bd_ptr == NULL) + if (!bd_ptr) return -EINVAL; /* Initialize DMA descriptor */ @@ -370,7 +370,7 @@ tsi721_desc_fill_init(struct tsi721_tx_desc *desc, static int tsi721_desc_fill_end(struct tsi721_dma_desc *bd_ptr, u32 bcount, bool interrupt) { - if (bd_ptr == NULL) + if (!bd_ptr) return -EINVAL; /* Update DMA descriptor */ @@ -555,9 +555,7 @@ static void tsi721_advance_work(struct tsi721_bdma_chan *bdma_chan, * If there is no data transfer in progress, fetch new descriptor from * the pending queue. */ - - if (desc == NULL && bdma_chan->active_tx == NULL && - !list_empty(&bdma_chan->queue)) { + if (!desc && !bdma_chan->active_tx && !list_empty(&bdma_chan->queue)) { desc = list_first_entry(&bdma_chan->queue, struct tsi721_tx_desc, desc_node); list_del_init((&desc->desc_node)); @@ -735,7 +733,7 @@ static dma_cookie_t tsi721_tx_submit(struct dma_async_tx_descriptor *txd) static int tsi721_alloc_chan_resources(struct dma_chan *dchan) { struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan); - struct tsi721_tx_desc *desc = NULL; + struct tsi721_tx_desc *desc; int i; tsi_debug(DMA, &dchan->dev->device, "DMAC%d", bdma_chan->id); @@ -754,9 +752,6 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan) desc = kcalloc(dma_txqueue_sz, sizeof(struct tsi721_tx_desc), GFP_ATOMIC); if (!desc) { - tsi_err(&dchan->dev->device, - "DMAC%d Failed to allocate logical descriptors", - bdma_chan->id); tsi721_bdma_ch_free(bdma_chan); return -ENOMEM; } @@ -799,7 +794,7 @@ static void tsi721_free_chan_resources(struct dma_chan *dchan) tsi_debug(DMA, &dchan->dev->device, "DMAC%d", bdma_chan->id); - if (bdma_chan->bd_base == NULL) + if (!bdma_chan->bd_base) return; tsi721_bdma_interrupt_enable(bdma_chan, 0); diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c index 38d949405618..83406696c7aa 100644 --- a/drivers/rapidio/rio.c +++ b/drivers/rapidio/rio.c @@ -81,6 +81,7 @@ u16 rio_local_get_device_id(struct rio_mport *port) return (RIO_GET_DID(port->sys_size, result)); } +EXPORT_SYMBOL_GPL(rio_local_get_device_id); /** * rio_query_mport - Query mport device attributes @@ -110,9 +111,8 @@ EXPORT_SYMBOL(rio_query_mport); */ struct rio_net *rio_alloc_net(struct rio_mport *mport) { - struct rio_net *net; + struct rio_net *net = kzalloc(sizeof(*net), GFP_KERNEL); - net = kzalloc(sizeof(struct rio_net), GFP_KERNEL); if (net) { INIT_LIST_HEAD(&net->node); INIT_LIST_HEAD(&net->devices); @@ -243,18 +243,17 @@ int rio_request_inb_mbox(struct rio_mport *mport, int rc = -ENOSYS; struct resource *res; - if (mport->ops->open_inb_mbox == NULL) + if (!mport->ops->open_inb_mbox) goto out; - res = kzalloc(sizeof(struct resource), GFP_KERNEL); - + res = kzalloc(sizeof(*res), GFP_KERNEL); if (res) { rio_init_mbox_res(res, mbox, mbox); /* Make sure this mailbox isn't in use */ - if ((rc = - request_resource(&mport->riores[RIO_INB_MBOX_RESOURCE], - res)) < 0) { + rc = request_resource(&mport->riores[RIO_INB_MBOX_RESOURCE], + res); + if (rc < 0) { kfree(res); goto out; } @@ -277,6 +276,7 @@ int rio_request_inb_mbox(struct rio_mport *mport, out: return rc; } +EXPORT_SYMBOL_GPL(rio_request_inb_mbox); /** * rio_release_inb_mbox - release inbound mailbox message service @@ -305,6 +305,7 @@ int rio_release_inb_mbox(struct rio_mport *mport, int mbox) return 0; } +EXPORT_SYMBOL_GPL(rio_release_inb_mbox); /** * rio_request_outb_mbox - request outbound mailbox service @@ -326,18 +327,17 @@ int rio_request_outb_mbox(struct rio_mport *mport, int rc = -ENOSYS; struct resource *res; - if (mport->ops->open_outb_mbox == NULL) + if (!mport->ops->open_outb_mbox) goto out; - res = kzalloc(sizeof(struct resource), GFP_KERNEL); - + res = kzalloc(sizeof(*res), GFP_KERNEL); if (res) { rio_init_mbox_res(res, mbox, mbox); /* Make sure this outbound mailbox isn't in use */ - if ((rc = - request_resource(&mport->riores[RIO_OUTB_MBOX_RESOURCE], - res)) < 0) { + rc = request_resource(&mport->riores[RIO_OUTB_MBOX_RESOURCE], + res); + if (rc < 0) { kfree(res); goto out; } @@ -360,6 +360,7 @@ int rio_request_outb_mbox(struct rio_mport *mport, out: return rc; } +EXPORT_SYMBOL_GPL(rio_request_outb_mbox); /** * rio_release_outb_mbox - release outbound mailbox message service @@ -388,6 +389,7 @@ int rio_release_outb_mbox(struct rio_mport *mport, int mbox) return 0; } +EXPORT_SYMBOL_GPL(rio_release_outb_mbox); /** * rio_setup_inb_dbell - bind inbound doorbell callback @@ -405,13 +407,10 @@ rio_setup_inb_dbell(struct rio_mport *mport, void *dev_id, struct resource *res, void (*dinb) (struct rio_mport * mport, void *dev_id, u16 src, u16 dst, u16 info)) { - int rc = 0; - struct rio_dbell *dbell; + struct rio_dbell *dbell = kmalloc(sizeof(*dbell), GFP_KERNEL); - if (!(dbell = kmalloc(sizeof(struct rio_dbell), GFP_KERNEL))) { - rc = -ENOMEM; - goto out; - } + if (!dbell) + return -ENOMEM; dbell->res = res; dbell->dinb = dinb; @@ -420,9 +419,7 @@ rio_setup_inb_dbell(struct rio_mport *mport, void *dev_id, struct resource *res, mutex_lock(&mport->lock); list_add_tail(&dbell->node, &mport->dbells); mutex_unlock(&mport->lock); - - out: - return rc; + return 0; } /** @@ -444,17 +441,16 @@ int rio_request_inb_dbell(struct rio_mport *mport, void (*dinb) (struct rio_mport * mport, void *dev_id, u16 src, u16 dst, u16 info)) { - int rc = 0; - - struct resource *res = kzalloc(sizeof(struct resource), GFP_KERNEL); + int rc; + struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); if (res) { rio_init_dbell_res(res, start, end); /* Make sure these doorbells aren't in use */ - if ((rc = - request_resource(&mport->riores[RIO_DOORBELL_RESOURCE], - res)) < 0) { + rc = request_resource(&mport->riores[RIO_DOORBELL_RESOURCE], + res); + if (rc < 0) { kfree(res); goto out; } @@ -467,6 +463,7 @@ int rio_request_inb_dbell(struct rio_mport *mport, out: return rc; } +EXPORT_SYMBOL_GPL(rio_request_inb_dbell); /** * rio_release_inb_dbell - release inbound doorbell message service @@ -508,6 +505,7 @@ int rio_release_inb_dbell(struct rio_mport *mport, u16 start, u16 end) out: return rc; } +EXPORT_SYMBOL_GPL(rio_release_inb_dbell); /** * rio_request_outb_dbell - request outbound doorbell message range @@ -536,6 +534,7 @@ struct resource *rio_request_outb_dbell(struct rio_dev *rdev, u16 start, return res; } +EXPORT_SYMBOL_GPL(rio_request_outb_dbell); /** * rio_release_outb_dbell - release outbound doorbell message range @@ -553,6 +552,7 @@ int rio_release_outb_dbell(struct rio_dev *rdev, struct resource *res) return rc; } +EXPORT_SYMBOL_GPL(rio_release_outb_dbell); /** * rio_add_mport_pw_handler - add port-write message handler into the list @@ -567,22 +567,17 @@ int rio_add_mport_pw_handler(struct rio_mport *mport, void *context, int (*pwcback)(struct rio_mport *mport, void *context, union rio_pw_msg *msg, int step)) { - int rc = 0; - struct rio_pwrite *pwrite; + struct rio_pwrite *pwrite = kzalloc(sizeof(*pwrite), GFP_KERNEL); - pwrite = kzalloc(sizeof(struct rio_pwrite), GFP_KERNEL); - if (!pwrite) { - rc = -ENOMEM; - goto out; - } + if (!pwrite) + return -ENOMEM; pwrite->pwcback = pwcback; pwrite->context = context; mutex_lock(&mport->lock); list_add_tail(&pwrite->node, &mport->pwrites); mutex_unlock(&mport->lock); -out: - return rc; + return 0; } EXPORT_SYMBOL_GPL(rio_add_mport_pw_handler); @@ -632,7 +627,7 @@ int rio_request_inb_pwrite(struct rio_dev *rdev, int rc = 0; spin_lock(&rio_global_list_lock); - if (rdev->pwcback != NULL) + if (rdev->pwcback) rc = -ENOMEM; else rdev->pwcback = pwcback; @@ -698,7 +693,7 @@ EXPORT_SYMBOL_GPL(rio_pw_enable); int rio_map_inb_region(struct rio_mport *mport, dma_addr_t local, u64 rbase, u32 size, u32 rflags) { - int rc = 0; + int rc; unsigned long flags; if (!mport->ops->map_inb) @@ -742,7 +737,7 @@ EXPORT_SYMBOL_GPL(rio_unmap_inb_region); int rio_map_outb_region(struct rio_mport *mport, u16 destid, u64 rbase, u32 size, u32 rflags, dma_addr_t *local) { - int rc = 0; + int rc; unsigned long flags; if (!mport->ops->map_outb) @@ -975,7 +970,7 @@ rio_chk_dev_route(struct rio_dev *rdev, struct rio_dev **nrdev, int *npnum) rdev = rdev->prev; } - if (prev == NULL) + if (!prev) goto err_out; p_port = prev->rswitch->route_table[rdev->destid]; @@ -1054,7 +1049,7 @@ rio_get_input_status(struct rio_dev *rdev, int pnum, u32 *lnkresp) RIO_MNT_REQ_CMD_IS); /* Exit if the response is not expected */ - if (lnkresp == NULL) + if (!lnkresp) return 0; checkcount = 3; @@ -1411,7 +1406,9 @@ rio_mport_get_feature(struct rio_mport * port, int local, u16 destid, ext_ftr_ptr, &ftr_header); if (RIO_GET_BLOCK_ID(ftr_header) == ftr) return ext_ftr_ptr; - if (!(ext_ftr_ptr = RIO_GET_BLOCK_PTR(ftr_header))) + + ext_ftr_ptr = RIO_GET_BLOCK_PTR(ftr_header); + if (!ext_ftr_ptr) break; } @@ -1462,6 +1459,7 @@ struct rio_dev *rio_get_asm(u16 vid, u16 did, spin_unlock(&rio_global_list_lock); return rdev; } +EXPORT_SYMBOL_GPL(rio_get_asm); /** * rio_get_device - Begin or continue searching for a RIO device by vid/did @@ -1481,6 +1479,7 @@ struct rio_dev *rio_get_device(u16 vid, u16 did, struct rio_dev *from) { return rio_get_asm(vid, did, RIO_ANY_ID, RIO_ANY_ID, from); } +EXPORT_SYMBOL_GPL(rio_get_device); /** * rio_std_route_add_entry - Add switch route table entry using standard @@ -1696,7 +1695,7 @@ int rio_route_add_entry(struct rio_dev *rdev, spin_lock(&rdev->rswitch->lock); - if (ops == NULL || ops->add_entry == NULL) { + if (!ops || !ops->add_entry) { rc = rio_std_route_add_entry(rdev->net->hport, rdev->destid, rdev->hopcount, table, route_destid, route_port); @@ -1749,7 +1748,7 @@ int rio_route_get_entry(struct rio_dev *rdev, u16 table, spin_lock(&rdev->rswitch->lock); - if (ops == NULL || ops->get_entry == NULL) { + if (!ops || !ops->get_entry) { rc = rio_std_route_get_entry(rdev->net->hport, rdev->destid, rdev->hopcount, table, route_destid, route_port); @@ -1797,7 +1796,7 @@ int rio_route_clr_table(struct rio_dev *rdev, u16 table, int lock) spin_lock(&rdev->rswitch->lock); - if (ops == NULL || ops->clr_table == NULL) { + if (!ops || !ops->clr_table) { rc = rio_std_route_clr_table(rdev->net->hport, rdev->destid, rdev->hopcount, table); } else if (try_module_get(ops->owner)) { @@ -1889,7 +1888,7 @@ struct dma_async_tx_descriptor *rio_dma_prep_xfer(struct dma_chan *dchan, { struct rio_dma_ext rio_ext; - if (dchan->device->device_prep_slave_sg == NULL) { + if (!dchan->device->device_prep_slave_sg) { pr_err("%s: prep_rio_sg == NULL\n", __func__); return NULL; } @@ -2189,7 +2188,6 @@ int rio_init_mports(void) work = kcalloc(n, sizeof *work, GFP_KERNEL); if (!work) { - pr_err("RIO: no memory for work struct\n"); destroy_workqueue(rio_wq); goto no_disc; } @@ -2216,6 +2214,7 @@ no_disc: return 0; } +EXPORT_SYMBOL_GPL(rio_init_mports); static int rio_get_hdid(int index) { @@ -2330,16 +2329,3 @@ int rio_unregister_mport(struct rio_mport *port) return 0; } EXPORT_SYMBOL_GPL(rio_unregister_mport); - -EXPORT_SYMBOL_GPL(rio_local_get_device_id); -EXPORT_SYMBOL_GPL(rio_get_device); -EXPORT_SYMBOL_GPL(rio_get_asm); -EXPORT_SYMBOL_GPL(rio_request_inb_dbell); -EXPORT_SYMBOL_GPL(rio_release_inb_dbell); -EXPORT_SYMBOL_GPL(rio_request_outb_dbell); -EXPORT_SYMBOL_GPL(rio_release_outb_dbell); -EXPORT_SYMBOL_GPL(rio_request_inb_mbox); -EXPORT_SYMBOL_GPL(rio_release_inb_mbox); -EXPORT_SYMBOL_GPL(rio_request_outb_mbox); -EXPORT_SYMBOL_GPL(rio_release_outb_mbox); -EXPORT_SYMBOL_GPL(rio_init_mports); diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 42681c10cbe4..dd4708c58480 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -758,7 +758,7 @@ static int suspend_set_state(struct regulator_dev *rdev, rstate = regulator_get_suspend_state(rdev, state); if (rstate == NULL) - return -EINVAL; + return 0; /* If we have no suspend mode configration don't set anything; * only warn if the driver implements set_suspend_voltage or diff --git a/drivers/rpmsg/qcom_smd.c b/drivers/rpmsg/qcom_smd.c index 8428eba8cb73..92d0c6a7a837 100644 --- a/drivers/rpmsg/qcom_smd.c +++ b/drivers/rpmsg/qcom_smd.c @@ -967,7 +967,7 @@ static __poll_t qcom_smd_poll(struct rpmsg_endpoint *ept, poll_wait(filp, &channel->fblockread_event, wait); if (qcom_smd_get_tx_avail(channel) > 20) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c index e622fcda30fa..64b6de9763ee 100644 --- a/drivers/rpmsg/rpmsg_char.c +++ b/drivers/rpmsg/rpmsg_char.c @@ -262,12 +262,12 @@ static __poll_t rpmsg_eptdev_poll(struct file *filp, poll_table *wait) __poll_t mask = 0; if (!eptdev->ept) - return POLLERR; + return EPOLLERR; poll_wait(filp, &eptdev->readq, wait); if (!skb_queue_empty(&eptdev->queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; mask |= rpmsg_poll(eptdev->ept, filp, wait); diff --git a/drivers/rtc/rtc-dev.c b/drivers/rtc/rtc-dev.c index 5a7b30d0773b..efa221e8bc22 100644 --- a/drivers/rtc/rtc-dev.c +++ b/drivers/rtc/rtc-dev.c @@ -203,7 +203,7 @@ static __poll_t rtc_dev_poll(struct file *file, poll_table *wait) data = rtc->irq_data; - return (data != 0) ? (POLLIN | POLLRDNORM) : 0; + return (data != 0) ? (EPOLLIN | EPOLLRDNORM) : 0; } static long rtc_dev_ioctl(struct file *file, diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c index 0c075d100252..fb2c3599d95c 100644 --- a/drivers/s390/block/dasd_eer.c +++ b/drivers/s390/block/dasd_eer.c @@ -671,7 +671,7 @@ static __poll_t dasd_eer_poll(struct file *filp, poll_table *ptable) poll_wait(filp, &dasd_eer_read_wait_queue, ptable); spin_lock_irqsave(&bufferlock, flags); if (eerb->head != eerb->tail) - mask = POLLIN | POLLRDNORM ; + mask = EPOLLIN | EPOLLRDNORM ; else mask = 0; spin_unlock_irqrestore(&bufferlock, flags); diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile index 614b44e70a28..a2b33a22c82a 100644 --- a/drivers/s390/char/Makefile +++ b/drivers/s390/char/Makefile @@ -19,6 +19,8 @@ endif CFLAGS_sclp_early_core.o += -D__NO_FORTIFY +CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_EXPOLINE) + obj-y += ctrlchar.o keyboard.o defkeymap.o sclp.o sclp_rw.o sclp_quiesce.o \ sclp_cmd.o sclp_config.o sclp_cpi_sys.o sclp_ocf.o sclp_ctl.o \ sclp_early.o sclp_early_core.o diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c index 956f662908a6..7bc616b253f1 100644 --- a/drivers/s390/char/monreader.c +++ b/drivers/s390/char/monreader.c @@ -435,9 +435,9 @@ static __poll_t mon_poll(struct file *filp, struct poll_table_struct *p) poll_wait(filp, &mon_read_wait_queue, p); if (unlikely(atomic_read(&monpriv->iucv_severed))) - return POLLERR; + return EPOLLERR; if (atomic_read(&monpriv->read_ready)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index d06bc5674e5f..6b1891539c84 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -49,7 +49,7 @@ struct read_info_sccb { u8 _pad_112[116 - 112]; /* 112-115 */ u8 fac116; /* 116 */ u8 fac117; /* 117 */ - u8 _pad_118; /* 118 */ + u8 fac118; /* 118 */ u8 fac119; /* 119 */ u16 hcpua; /* 120-121 */ u8 _pad_122[124 - 122]; /* 122-123 */ @@ -100,6 +100,7 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb) sclp.has_esca = !!(sccb->fac116 & 0x08); sclp.has_pfmfi = !!(sccb->fac117 & 0x40); sclp.has_ibs = !!(sccb->fac117 & 0x20); + sclp.has_gisaf = !!(sccb->fac118 & 0x08); sclp.has_hvs = !!(sccb->fac119 & 0x80); sclp.has_kss = !!(sccb->fac98 & 0x01); if (sccb->fac85 & 0x02) diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 5c94a3aec4dd..f95b452b8bbc 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -412,7 +412,7 @@ static void chp_release(struct device *dev) /** * chp_update_desc - update channel-path description - * @chp - channel-path + * @chp: channel-path * * Update the channel-path description of the specified channel-path * including channel measurement related information. @@ -438,7 +438,7 @@ int chp_update_desc(struct channel_path *chp) /** * chp_new - register a new channel-path - * @chpid - channel-path ID + * @chpid: channel-path ID * * Create and register data structure representing new channel-path. Return * zero on success, non-zero otherwise. @@ -730,8 +730,8 @@ static void cfg_func(struct work_struct *work) /** * chp_cfg_schedule - schedule chpid configuration request - * @chpid - channel-path ID - * @configure - Non-zero for configure, zero for deconfigure + * @chpid: channel-path ID + * @configure: Non-zero for configure, zero for deconfigure * * Schedule a channel-path configuration/deconfiguration request. */ @@ -747,7 +747,7 @@ void chp_cfg_schedule(struct chp_id chpid, int configure) /** * chp_cfg_cancel_deconfigure - cancel chpid deconfiguration request - * @chpid - channel-path ID + * @chpid: channel-path ID * * Cancel an active channel-path deconfiguration request if it has not yet * been performed. diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index 987bf9a8c9f7..6886b3d34cf8 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -1059,7 +1059,7 @@ EXPORT_SYMBOL_GPL(cio_tm_start_key); /** * cio_tm_intrg - perform interrogate function - * @sch - subchannel on which to perform the interrogate function + * @sch: subchannel on which to perform the interrogate function * * If the specified subchannel is running in transport-mode, perform the * interrogate function. Return zero on success, non-zero otherwie. diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c index 5e495c62cfa7..8af4948dae80 100644 --- a/drivers/s390/cio/cmf.c +++ b/drivers/s390/cio/cmf.c @@ -1118,9 +1118,10 @@ int ccw_set_cmf(struct ccw_device *cdev, int enable) * enable_cmf() - switch on the channel measurement for a specific device * @cdev: The ccw device to be enabled * - * Returns %0 for success or a negative error value. - * Note: If this is called on a device for which channel measurement is already - * enabled a reset of the measurement data is triggered. + * Enable channel measurements for @cdev. If this is called on a device + * for which channel measurement is already enabled a reset of the + * measurement data is triggered. + * Returns: %0 for success or a negative error value. * Context: * non-atomic */ @@ -1160,7 +1161,7 @@ out_unlock: * __disable_cmf() - switch off the channel measurement for a specific device * @cdev: The ccw device to be disabled * - * Returns %0 for success or a negative error value. + * Returns: %0 for success or a negative error value. * * Context: * non-atomic, device_lock() held. @@ -1184,7 +1185,7 @@ int __disable_cmf(struct ccw_device *cdev) * disable_cmf() - switch off the channel measurement for a specific device * @cdev: The ccw device to be disabled * - * Returns %0 for success or a negative error value. + * Returns: %0 for success or a negative error value. * * Context: * non-atomic @@ -1205,7 +1206,7 @@ int disable_cmf(struct ccw_device *cdev) * @cdev: the channel to be read * @index: the index of the value to be read * - * Returns the value read or %0 if the value cannot be read. + * Returns: The value read or %0 if the value cannot be read. * * Context: * any @@ -1220,7 +1221,7 @@ u64 cmf_read(struct ccw_device *cdev, int index) * @cdev: the channel to be read * @data: a pointer to a data block that will be filled * - * Returns %0 on success, a negative error value otherwise. + * Returns: %0 on success, a negative error value otherwise. * * Context: * any diff --git a/drivers/s390/cio/itcw.c b/drivers/s390/cio/itcw.c index deaf59f93326..19e46363348c 100644 --- a/drivers/s390/cio/itcw.c +++ b/drivers/s390/cio/itcw.c @@ -15,7 +15,7 @@ #include <asm/fcx.h> #include <asm/itcw.h> -/** +/* * struct itcw - incremental tcw helper data type * * This structure serves as a handle for the incremental construction of a diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 95b0efe28afb..d5b02de02a3a 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -72,6 +72,7 @@ static inline int do_siga_input(unsigned long schid, unsigned int mask, * @mask: which output queues to process * @bb: busy bit indicator, set only if SIGA-w/wt could not access a buffer * @fc: function code to perform + * @aob: asynchronous operation block * * Returns condition code. * Note: For IQDC unicast queues only the highest priority queue is processed. @@ -1761,9 +1762,6 @@ EXPORT_SYMBOL(qdio_stop_irq); * @response: Response code will be stored at this address * @cb: Callback function will be executed for each element * of the address list - * @priv: Pointer passed from the caller to qdio_pnso_brinfo() - * @type: Type of the address entry passed to the callback - * @entry: Entry containg the address of the specified type * @priv: Pointer to pass to the callback function. * * Performs "Store-network-bridging-information list" operation and calls diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index d9a2fffd034b..2c7550797ec2 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -835,7 +835,7 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw) /** * cp_iova_pinned() - check if an iova is pinned for a ccw chain. - * @cmd: ccwchain command on which to perform the operation + * @cp: channel_program on which to perform the operation * @iova: the iova to check * * If the @iova is currently pinned for the ccw chain, return true; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index db42107bf2f5..959c65cf75d9 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -591,6 +591,11 @@ struct qeth_cmd_buffer { void (*callback) (struct qeth_channel *, struct qeth_cmd_buffer *); }; +static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob) +{ + return (struct qeth_ipa_cmd *)(iob->data + IPA_PDU_HEADER_SIZE); +} + /** * definition of a qeth channel, used for read and write */ @@ -846,7 +851,7 @@ struct qeth_trap_id { */ static inline int qeth_get_elements_for_range(addr_t start, addr_t end) { - return PFN_UP(end - 1) - PFN_DOWN(start); + return PFN_UP(end) - PFN_DOWN(start); } static inline int qeth_get_micros(void) diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 6abd3bc285e4..ca72f3311004 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2120,7 +2120,7 @@ int qeth_send_control_data(struct qeth_card *card, int len, unsigned long flags; struct qeth_reply *reply = NULL; unsigned long timeout, event_timeout; - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = NULL; QETH_CARD_TEXT(card, 2, "sendctl"); @@ -2146,10 +2146,13 @@ int qeth_send_control_data(struct qeth_card *card, int len, while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ; qeth_prepare_control_data(card, len, iob); - if (IS_IPA(iob->data)) + if (IS_IPA(iob->data)) { + cmd = __ipa_cmd(iob); event_timeout = QETH_IPA_TIMEOUT; - else + } else { event_timeout = QETH_TIMEOUT; + } + timeout = jiffies + event_timeout; QETH_CARD_TEXT(card, 6, "noirqpnd"); @@ -2174,9 +2177,8 @@ int qeth_send_control_data(struct qeth_card *card, int len, /* we have only one long running ipassist, since we can ensure process context of this command we can sleep */ - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); - if ((cmd->hdr.command == IPA_CMD_SETIP) && - (cmd->hdr.prot_version == QETH_PROT_IPV4)) { + if (cmd && cmd->hdr.command == IPA_CMD_SETIP && + cmd->hdr.prot_version == QETH_PROT_IPV4) { if (!wait_event_timeout(reply->wait_q, atomic_read(&reply->received), event_timeout)) goto time_err; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 2791141bd035..a71ee67df084 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -7041,7 +7041,7 @@ static __poll_t megasas_mgmt_poll(struct file *file, poll_table *wait) poll_wait(file, &megasas_poll_wait, wait); spin_lock_irqsave(&poll_aen_lock, flags); if (megasas_poll_wait_aen) - mask = (POLLIN | POLLRDNORM); + mask = (EPOLLIN | EPOLLRDNORM); else mask = 0; megasas_poll_wait_aen = 0; diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 9cddc3074cd1..523971aeb4c1 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -546,7 +546,7 @@ _ctl_poll(struct file *filep, poll_table *wait) list_for_each_entry(ioc, &mpt3sas_ioc_list, list) { if (ioc->aen_event_read_flag) { spin_unlock(&gioc_lock); - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } } spin_unlock(&gioc_lock); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 0c434453aab3..c198b96368dd 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1152,27 +1152,27 @@ sg_poll(struct file *filp, poll_table * wait) sfp = filp->private_data; if (!sfp) - return POLLERR; + return EPOLLERR; sdp = sfp->parentdp; if (!sdp) - return POLLERR; + return EPOLLERR; poll_wait(filp, &sfp->read_wait, wait); read_lock_irqsave(&sfp->rq_list_lock, iflags); list_for_each_entry(srp, &sfp->rq_list, entry) { /* if any read waiting, flag it */ if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned)) - res = POLLIN | POLLRDNORM; + res = EPOLLIN | EPOLLRDNORM; ++count; } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (atomic_read(&sdp->detaching)) - res |= POLLHUP; + res |= EPOLLHUP; else if (!sfp->cmd_q) { if (0 == count) - res |= POLLOUT | POLLWRNORM; + res |= EPOLLOUT | EPOLLWRNORM; } else if (count < SG_MAX_QUEUE) - res |= POLLOUT | POLLWRNORM; + res |= EPOLLOUT | EPOLLWRNORM; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_poll: res=0x%x\n", (__force u32) res)); return res; diff --git a/drivers/sh/clk/core.c b/drivers/sh/clk/core.c index 92863e3818e5..9475353f49d6 100644 --- a/drivers/sh/clk/core.c +++ b/drivers/sh/clk/core.c @@ -197,10 +197,11 @@ int clk_rate_table_find(struct clk *clk, unsigned long rate) { struct cpufreq_frequency_table *pos; + int idx; - cpufreq_for_each_valid_entry(pos, freq_table) + cpufreq_for_each_valid_entry_idx(pos, freq_table, idx) if (pos->frequency == rate) - return pos - freq_table; + return idx; return -ENOENT; } diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig index ee18428a051f..b3f5cae98ea6 100644 --- a/drivers/ssb/Kconfig +++ b/drivers/ssb/Kconfig @@ -31,7 +31,7 @@ config SSB_BLOCKIO config SSB_PCIHOST_POSSIBLE bool - depends on SSB && (PCI = y || PCI = SSB) && PCI_DRIVERS_LEGACY + depends on SSB && (PCI = y || PCI = SSB) && (PCI_DRIVERS_LEGACY || !MIPS) default y config SSB_PCIHOST diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c index ef733847eebe..c13772a0df58 100644 --- a/drivers/staging/comedi/comedi_fops.c +++ b/drivers/staging/comedi/comedi_fops.c @@ -2288,7 +2288,7 @@ static __poll_t comedi_poll(struct file *file, poll_table *wait) if (s->busy != file || !comedi_is_subdevice_running(s) || (s->async->cmd.flags & CMDF_WRITE) || comedi_buf_read_n_available(s) > 0) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } s = comedi_file_write_subdevice(file); @@ -2300,7 +2300,7 @@ static __poll_t comedi_poll(struct file *file, poll_table *wait) if (s->busy != file || !comedi_is_subdevice_running(s) || !(s->async->cmd.flags & CMDF_WRITE) || comedi_buf_write_n_available(s) >= bps) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } done: diff --git a/drivers/staging/comedi/drivers/serial2002.c b/drivers/staging/comedi/drivers/serial2002.c index ab69eeb2c1f1..b3f3b4a201af 100644 --- a/drivers/staging/comedi/drivers/serial2002.c +++ b/drivers/staging/comedi/drivers/serial2002.c @@ -114,8 +114,8 @@ static void serial2002_tty_read_poll_wait(struct file *f, int timeout) __poll_t mask; mask = f->f_op->poll(f, &table.pt); - if (mask & (POLLRDNORM | POLLRDBAND | POLLIN | - POLLHUP | POLLERR)) { + if (mask & (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | + EPOLLHUP | EPOLLERR)) { break; } now = ktime_get(); diff --git a/drivers/staging/fwserial/fwserial.c b/drivers/staging/fwserial/fwserial.c index 1993b03a6f2d..e8bfe5520bc7 100644 --- a/drivers/staging/fwserial/fwserial.c +++ b/drivers/staging/fwserial/fwserial.c @@ -37,7 +37,7 @@ module_param_named(loop, create_loop_dev, bool, 0644); /* * Threshold below which the tty is woken for writing * - should be equal to WAKEUP_CHARS in drivers/tty/n_tty.c because - * even if the writer is woken, n_tty_poll() won't set POLLOUT until + * even if the writer is woken, n_tty_poll() won't set EPOLLOUT until * our fifo is below this level */ #define WAKEUP_CHARS 256 diff --git a/drivers/staging/greybus/tools/loopback_test.c b/drivers/staging/greybus/tools/loopback_test.c index c51610ce24af..b82e2befe935 100644 --- a/drivers/staging/greybus/tools/loopback_test.c +++ b/drivers/staging/greybus/tools/loopback_test.c @@ -663,7 +663,7 @@ static int open_poll_files(struct loopback_test *t) goto err; } read(t->fds[fds_idx].fd, &dummy, 1); - t->fds[fds_idx].events = POLLERR|POLLPRI; + t->fds[fds_idx].events = EPOLLERR|EPOLLPRI; t->fds[fds_idx].revents = 0; fds_idx++; } @@ -756,7 +756,7 @@ static int wait_for_complete(struct loopback_test *t) } for (i = 0; i < t->poll_count; i++) { - if (t->fds[i].revents & POLLPRI) { + if (t->fds[i].revents & EPOLLPRI) { /* Dummy read to clear the event */ read(t->fds[i].fd, &dummy, 1); number_of_events++; diff --git a/drivers/staging/irda/drivers/sh_sir.c b/drivers/staging/irda/drivers/sh_sir.c index fede6864c737..0d0687cc454a 100644 --- a/drivers/staging/irda/drivers/sh_sir.c +++ b/drivers/staging/irda/drivers/sh_sir.c @@ -226,7 +226,7 @@ static u32 sh_sir_find_sclk(struct clk *irda_clk) clk_put(pclk); /* IrDA can not set over peripheral_clk */ - cpufreq_for_each_valid_entry(pos, freq_table) { + cpufreq_for_each_valid_entry_idx(pos, freq_table, index) { u32 freq = pos->frequency; /* IrDA should not over peripheral_clk */ @@ -236,7 +236,7 @@ static u32 sh_sir_find_sclk(struct clk *irda_clk) tmp = freq % SCLK_BASE; if (tmp < min) { min = tmp; - index = pos - freq_table; + break; } } diff --git a/drivers/staging/irda/net/af_irda.c b/drivers/staging/irda/net/af_irda.c index f1d128b2dae9..2f1e9ab3d6d0 100644 --- a/drivers/staging/irda/net/af_irda.c +++ b/drivers/staging/irda/net/af_irda.c @@ -1749,16 +1749,16 @@ static __poll_t irda_poll(struct file * file, struct socket *sock, /* Exceptional events? */ if (sk->sk_err) - mask |= POLLERR; + mask |= EPOLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) { pr_debug("%s(), POLLHUP\n", __func__); - mask |= POLLHUP; + mask |= EPOLLHUP; } /* Readable? */ if (!skb_queue_empty(&sk->sk_receive_queue)) { pr_debug("Socket is readable\n"); - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } /* Connection-based need to check for termination and startup */ @@ -1766,14 +1766,14 @@ static __poll_t irda_poll(struct file * file, struct socket *sock, case SOCK_STREAM: if (sk->sk_state == TCP_CLOSE) { pr_debug("%s(), POLLHUP\n", __func__); - mask |= POLLHUP; + mask |= EPOLLHUP; } if (sk->sk_state == TCP_ESTABLISHED) { if ((self->tx_flow == FLOW_START) && sock_writeable(sk)) { - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } } break; @@ -1781,12 +1781,12 @@ static __poll_t irda_poll(struct file * file, struct socket *sock, if ((self->tx_flow == FLOW_START) && sock_writeable(sk)) { - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } break; case SOCK_DGRAM: if (sock_writeable(sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; break; default: break; diff --git a/drivers/staging/irda/net/irnet/irnet_ppp.c b/drivers/staging/irda/net/irnet/irnet_ppp.c index 75bf9e34311d..c90a158af4b7 100644 --- a/drivers/staging/irda/net/irnet/irnet_ppp.c +++ b/drivers/staging/irda/net/irnet/irnet_ppp.c @@ -429,10 +429,10 @@ irnet_ctrl_poll(irnet_socket * ap, DENTER(CTRL_TRACE, "(ap=0x%p)\n", ap); poll_wait(file, &irnet_events.rwait, wait); - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; /* If there is unread events */ if(ap->event_index != irnet_events.index) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; #ifdef INITIAL_DISCOVERY if(ap->disco_number != -1) { @@ -441,7 +441,7 @@ irnet_ctrl_poll(irnet_socket * ap, irnet_get_discovery_log(ap); /* Recheck */ if(ap->disco_number != -1) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } #endif /* INITIAL_DISCOVERY */ @@ -618,7 +618,7 @@ dev_irnet_poll(struct file * file, DENTER(FS_TRACE, "(file=0x%p, ap=0x%p)\n", file, ap); - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; DABORT(ap == NULL, mask, FS_ERROR, "ap is NULL !!!\n"); /* If we are connected to ppp_generic, let it handle the job */ diff --git a/drivers/staging/media/atomisp/pci/atomisp2/atomisp_fops.c b/drivers/staging/media/atomisp/pci/atomisp2/atomisp_fops.c index 6657ebbe068a..4f9f9dca5e6a 100644 --- a/drivers/staging/media/atomisp/pci/atomisp2/atomisp_fops.c +++ b/drivers/staging/media/atomisp/pci/atomisp2/atomisp_fops.c @@ -1265,7 +1265,7 @@ static __poll_t atomisp_poll(struct file *file, rt_mutex_lock(&isp->mutex); if (pipe->capq.streaming != 1) { rt_mutex_unlock(&isp->mutex); - return POLLERR; + return EPOLLERR; } rt_mutex_unlock(&isp->mutex); diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c index 4ffff6f8b809..06d1920150da 100644 --- a/drivers/staging/media/bcm2048/radio-bcm2048.c +++ b/drivers/staging/media/bcm2048/radio-bcm2048.c @@ -2183,7 +2183,7 @@ static __poll_t bcm2048_fops_poll(struct file *file, poll_wait(file, &bdev->read_queue, pts); if (bdev->rds_data_available) - retval = POLLIN | POLLRDNORM; + retval = EPOLLIN | EPOLLRDNORM; return retval; } diff --git a/drivers/staging/most/cdev/cdev.c b/drivers/staging/most/cdev/cdev.c index c183489c4a1c..4d7fce8731fe 100644 --- a/drivers/staging/most/cdev/cdev.c +++ b/drivers/staging/most/cdev/cdev.c @@ -292,10 +292,10 @@ static __poll_t comp_poll(struct file *filp, poll_table *wait) if (c->cfg->direction == MOST_CH_RX) { if (!kfifo_is_empty(&c->fifo)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } else { if (!kfifo_is_empty(&c->fifo) || ch_has_mbo(c)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } diff --git a/drivers/staging/most/video/video.c b/drivers/staging/most/video/video.c index ef23e8524b1e..9d7e747519d9 100644 --- a/drivers/staging/most/video/video.c +++ b/drivers/staging/most/video/video.c @@ -213,7 +213,7 @@ static __poll_t comp_vdev_poll(struct file *filp, poll_table *wait) if (!data_ready(mdev)) poll_wait(filp, &mdev->wait_data, wait); if (data_ready(mdev)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/drivers/staging/rtl8192e/rtl8192e/Kconfig b/drivers/staging/rtl8192e/rtl8192e/Kconfig index 282e293da18f..7ac42a590e21 100644 --- a/drivers/staging/rtl8192e/rtl8192e/Kconfig +++ b/drivers/staging/rtl8192e/rtl8192e/Kconfig @@ -6,4 +6,3 @@ config RTL8192E select WEXT_PRIV select CRYPTO select FW_LOADER - ---help--- diff --git a/drivers/staging/rtl8192u/Kconfig b/drivers/staging/rtl8192u/Kconfig index 3ee9d0d00fb6..97df6507a485 100644 --- a/drivers/staging/rtl8192u/Kconfig +++ b/drivers/staging/rtl8192u/Kconfig @@ -5,4 +5,3 @@ config RTL8192U select WIRELESS_EXT select WEXT_PRIV select CRYPTO - ---help--- diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c index 0e74d09e18ea..0a1a7c259ab0 100644 --- a/drivers/staging/speakup/speakup_soft.c +++ b/drivers/staging/speakup/speakup_soft.c @@ -325,7 +325,7 @@ static __poll_t softsynth_poll(struct file *fp, struct poll_table_struct *wait) spin_lock_irqsave(&speakup_info.spinlock, flags); if (!synth_buffer_empty() || speakup_info.flushing) - ret = POLLIN | POLLRDNORM; + ret = EPOLLIN | EPOLLRDNORM; spin_unlock_irqrestore(&speakup_info.spinlock, flags); return ret; } diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index 92eb57e2adaf..8de16016b6de 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -893,6 +893,9 @@ cxgbit_offload_init(struct cxgbit_sock *csk, int iptype, __u8 *peer_ip, return -ENODEV; rcu_read_lock(); + if (!(n->nud_state & NUD_VALID)) + neigh_event_send(n, NULL); + ret = -ENOMEM; if (n->dev->flags & IFF_LOOPBACK) { if (iptype == 4) diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c index f9bc8ec6fb6b..9518ffd8b8ba 100644 --- a/drivers/target/iscsi/iscsi_target_auth.c +++ b/drivers/target/iscsi/iscsi_target_auth.c @@ -421,7 +421,8 @@ static int chap_server_compute_md5( auth_ret = 0; out: kzfree(desc); - crypto_free_shash(tfm); + if (tfm) + crypto_free_shash(tfm); kfree(challenge); kfree(challenge_binhex); return auth_ret; diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index b686e2ce9c0e..8a5e8d17a942 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -432,6 +432,9 @@ static void iscsi_target_sk_data_ready(struct sock *sk) if (test_and_set_bit(LOGIN_FLAGS_READ_ACTIVE, &conn->login_flags)) { write_unlock_bh(&sk->sk_callback_lock); pr_debug("Got LOGIN_FLAGS_READ_ACTIVE=1, conn: %p >>>>\n", conn); + if (iscsi_target_sk_data_ready == conn->orig_data_ready) + return; + conn->orig_data_ready(sk); return; } diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index b6a913e38b30..9cd4ffe76c07 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -64,7 +64,7 @@ static void tcm_loop_release_cmd(struct se_cmd *se_cmd) static int tcm_loop_show_info(struct seq_file *m, struct Scsi_Host *host) { - seq_printf(m, "tcm_loop_proc_info()\n"); + seq_puts(m, "tcm_loop_proc_info()\n"); return 0; } @@ -123,8 +123,8 @@ static void tcm_loop_submission_work(struct work_struct *work) } tl_nexus = tl_tpg->tl_nexus; if (!tl_nexus) { - scmd_printk(KERN_ERR, sc, "TCM_Loop I_T Nexus" - " does not exist\n"); + scmd_printk(KERN_ERR, sc, + "TCM_Loop I_T Nexus does not exist\n"); set_host_byte(sc, DID_ERROR); goto out_done; } @@ -166,7 +166,6 @@ static void tcm_loop_submission_work(struct work_struct *work) out_done: kmem_cache_free(tcm_loop_cmd_cache, tl_cmd); sc->scsi_done(sc); - return; } /* @@ -177,14 +176,13 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc) { struct tcm_loop_cmd *tl_cmd; - pr_debug("tcm_loop_queuecommand() %d:%d:%d:%llu got CDB: 0x%02x" - " scsi_buf_len: %u\n", sc->device->host->host_no, - sc->device->id, sc->device->channel, sc->device->lun, - sc->cmnd[0], scsi_bufflen(sc)); + pr_debug("%s() %d:%d:%d:%llu got CDB: 0x%02x scsi_buf_len: %u\n", + __func__, sc->device->host->host_no, sc->device->id, + sc->device->channel, sc->device->lun, sc->cmnd[0], + scsi_bufflen(sc)); tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_ATOMIC); if (!tl_cmd) { - pr_err("Unable to allocate struct tcm_loop_cmd\n"); set_host_byte(sc, DID_ERROR); sc->scsi_done(sc); return 0; @@ -204,10 +202,10 @@ static int tcm_loop_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc) static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, u64 lun, int task, enum tcm_tmreq_table tmr) { - struct se_cmd *se_cmd = NULL; + struct se_cmd *se_cmd; struct se_session *se_sess; struct tcm_loop_nexus *tl_nexus; - struct tcm_loop_cmd *tl_cmd = NULL; + struct tcm_loop_cmd *tl_cmd; int ret = TMR_FUNCTION_FAILED, rc; /* @@ -215,16 +213,13 @@ static int tcm_loop_issue_tmr(struct tcm_loop_tpg *tl_tpg, */ tl_nexus = tl_tpg->tl_nexus; if (!tl_nexus) { - pr_err("Unable to perform device reset without" - " active I_T Nexus\n"); + pr_err("Unable to perform device reset without active I_T Nexus\n"); return ret; } tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL); - if (!tl_cmd) { - pr_err("Unable to allocate memory for tl_cmd\n"); + if (!tl_cmd) return ret; - } init_completion(&tl_cmd->tmr_done); @@ -298,8 +293,7 @@ static int tcm_loop_target_reset(struct scsi_cmnd *sc) */ tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host); if (!tl_hba) { - pr_err("Unable to perform device reset without" - " active I_T Nexus\n"); + pr_err("Unable to perform device reset without active I_T Nexus\n"); return FAILED; } /* @@ -417,8 +411,7 @@ static int tcm_loop_setup_hba_bus(struct tcm_loop_hba *tl_hba, int tcm_loop_host ret = device_register(&tl_hba->dev); if (ret) { - pr_err("device_register() failed for" - " tl_hba->dev: %d\n", ret); + pr_err("device_register() failed for tl_hba->dev: %d\n", ret); return -ENODEV; } @@ -447,8 +440,7 @@ static int tcm_loop_alloc_core_bus(void) ret = driver_register(&tcm_loop_driverfs); if (ret) { - pr_err("driver_register() failed for" - "tcm_loop_driverfs\n"); + pr_err("driver_register() failed for tcm_loop_driverfs\n"); goto bus_unreg; } @@ -587,8 +579,8 @@ static int tcm_loop_queue_data_in(struct se_cmd *se_cmd) struct tcm_loop_cmd, tl_se_cmd); struct scsi_cmnd *sc = tl_cmd->sc; - pr_debug("tcm_loop_queue_data_in() called for scsi_cmnd: %p" - " cdb: 0x%02x\n", sc, sc->cmnd[0]); + pr_debug("%s() called for scsi_cmnd: %p cdb: 0x%02x\n", + __func__, sc, sc->cmnd[0]); sc->result = SAM_STAT_GOOD; set_host_byte(sc, DID_OK); @@ -605,8 +597,8 @@ static int tcm_loop_queue_status(struct se_cmd *se_cmd) struct tcm_loop_cmd, tl_se_cmd); struct scsi_cmnd *sc = tl_cmd->sc; - pr_debug("tcm_loop_queue_status() called for scsi_cmnd: %p" - " cdb: 0x%02x\n", sc, sc->cmnd[0]); + pr_debug("%s() called for scsi_cmnd: %p cdb: 0x%02x\n", + __func__, sc, sc->cmnd[0]); if (se_cmd->sense_buffer && ((se_cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) || @@ -691,8 +683,8 @@ static void tcm_loop_port_unlink( sd = scsi_device_lookup(tl_hba->sh, 0, tl_tpg->tl_tpgt, se_lun->unpacked_lun); if (!sd) { - pr_err("Unable to locate struct scsi_device for %d:%d:" - "%llu\n", 0, tl_tpg->tl_tpgt, se_lun->unpacked_lun); + pr_err("Unable to locate struct scsi_device for %d:%d:%llu\n", + 0, tl_tpg->tl_tpgt, se_lun->unpacked_lun); return; } /* @@ -772,11 +764,9 @@ static int tcm_loop_make_nexus( return -EEXIST; } - tl_nexus = kzalloc(sizeof(struct tcm_loop_nexus), GFP_KERNEL); - if (!tl_nexus) { - pr_err("Unable to allocate struct tcm_loop_nexus\n"); + tl_nexus = kzalloc(sizeof(*tl_nexus), GFP_KERNEL); + if (!tl_nexus) return -ENOMEM; - } tl_nexus->se_sess = target_alloc_session(&tl_tpg->tl_se_tpg, 0, 0, TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS, @@ -787,9 +777,8 @@ static int tcm_loop_make_nexus( return ret; } - pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated" - " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba), - name); + pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated %s Initiator Port: %s\n", + tcm_loop_dump_proto_id(tl_hba), name); return 0; } @@ -808,15 +797,14 @@ static int tcm_loop_drop_nexus( return -ENODEV; if (atomic_read(&tpg->tl_tpg_port_count)) { - pr_err("Unable to remove TCM_Loop I_T Nexus with" - " active TPG port count: %d\n", - atomic_read(&tpg->tl_tpg_port_count)); + pr_err("Unable to remove TCM_Loop I_T Nexus with active TPG port count: %d\n", + atomic_read(&tpg->tl_tpg_port_count)); return -EPERM; } - pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated" - " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tpg->tl_hba), - tl_nexus->se_sess->se_node_acl->initiatorname); + pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated %s Initiator Port: %s\n", + tcm_loop_dump_proto_id(tpg->tl_hba), + tl_nexus->se_sess->se_node_acl->initiatorname); /* * Release the SCSI I_T Nexus to the emulated Target Port */ @@ -868,8 +856,8 @@ static ssize_t tcm_loop_tpg_nexus_store(struct config_item *item, * tcm_loop_make_nexus() */ if (strlen(page) >= TL_WWN_ADDR_LEN) { - pr_err("Emulated NAA Sas Address: %s, exceeds" - " max: %d\n", page, TL_WWN_ADDR_LEN); + pr_err("Emulated NAA Sas Address: %s, exceeds max: %d\n", + page, TL_WWN_ADDR_LEN); return -EINVAL; } snprintf(&i_port[0], TL_WWN_ADDR_LEN, "%s", page); @@ -877,9 +865,8 @@ static ssize_t tcm_loop_tpg_nexus_store(struct config_item *item, ptr = strstr(i_port, "naa."); if (ptr) { if (tl_hba->tl_proto_id != SCSI_PROTOCOL_SAS) { - pr_err("Passed SAS Initiator Port %s does not" - " match target port protoid: %s\n", i_port, - tcm_loop_dump_proto_id(tl_hba)); + pr_err("Passed SAS Initiator Port %s does not match target port protoid: %s\n", + i_port, tcm_loop_dump_proto_id(tl_hba)); return -EINVAL; } port_ptr = &i_port[0]; @@ -888,9 +875,8 @@ static ssize_t tcm_loop_tpg_nexus_store(struct config_item *item, ptr = strstr(i_port, "fc."); if (ptr) { if (tl_hba->tl_proto_id != SCSI_PROTOCOL_FCP) { - pr_err("Passed FCP Initiator Port %s does not" - " match target port protoid: %s\n", i_port, - tcm_loop_dump_proto_id(tl_hba)); + pr_err("Passed FCP Initiator Port %s does not match target port protoid: %s\n", + i_port, tcm_loop_dump_proto_id(tl_hba)); return -EINVAL; } port_ptr = &i_port[3]; /* Skip over "fc." */ @@ -899,16 +885,15 @@ static ssize_t tcm_loop_tpg_nexus_store(struct config_item *item, ptr = strstr(i_port, "iqn."); if (ptr) { if (tl_hba->tl_proto_id != SCSI_PROTOCOL_ISCSI) { - pr_err("Passed iSCSI Initiator Port %s does not" - " match target port protoid: %s\n", i_port, - tcm_loop_dump_proto_id(tl_hba)); + pr_err("Passed iSCSI Initiator Port %s does not match target port protoid: %s\n", + i_port, tcm_loop_dump_proto_id(tl_hba)); return -EINVAL; } port_ptr = &i_port[0]; goto check_newline; } - pr_err("Unable to locate prefix for emulated Initiator Port:" - " %s\n", i_port); + pr_err("Unable to locate prefix for emulated Initiator Port: %s\n", + i_port); return -EINVAL; /* * Clear any trailing newline for the NAA WWN @@ -1010,16 +995,15 @@ static struct se_portal_group *tcm_loop_make_naa_tpg( unsigned long tpgt; if (strstr(name, "tpgt_") != name) { - pr_err("Unable to locate \"tpgt_#\" directory" - " group\n"); + pr_err("Unable to locate \"tpgt_#\" directory group\n"); return ERR_PTR(-EINVAL); } if (kstrtoul(name+5, 10, &tpgt)) return ERR_PTR(-EINVAL); if (tpgt >= TL_TPGS_PER_HBA) { - pr_err("Passed tpgt: %lu exceeds TL_TPGS_PER_HBA:" - " %u\n", tpgt, TL_TPGS_PER_HBA); + pr_err("Passed tpgt: %lu exceeds TL_TPGS_PER_HBA: %u\n", + tpgt, TL_TPGS_PER_HBA); return ERR_PTR(-EINVAL); } tl_tpg = &tl_hba->tl_hba_tpgs[tpgt]; @@ -1032,10 +1016,9 @@ static struct se_portal_group *tcm_loop_make_naa_tpg( if (ret < 0) return ERR_PTR(-ENOMEM); - pr_debug("TCM_Loop_ConfigFS: Allocated Emulated %s" - " Target Port %s,t,0x%04lx\n", tcm_loop_dump_proto_id(tl_hba), - config_item_name(&wwn->wwn_group.cg_item), tpgt); - + pr_debug("TCM_Loop_ConfigFS: Allocated Emulated %s Target Port %s,t,0x%04lx\n", + tcm_loop_dump_proto_id(tl_hba), + config_item_name(&wwn->wwn_group.cg_item), tpgt); return &tl_tpg->tl_se_tpg; } @@ -1062,9 +1045,9 @@ static void tcm_loop_drop_naa_tpg( tl_tpg->tl_hba = NULL; tl_tpg->tl_tpgt = 0; - pr_debug("TCM_Loop_ConfigFS: Deallocated Emulated %s" - " Target Port %s,t,0x%04x\n", tcm_loop_dump_proto_id(tl_hba), - config_item_name(&wwn->wwn_group.cg_item), tpgt); + pr_debug("TCM_Loop_ConfigFS: Deallocated Emulated %s Target Port %s,t,0x%04x\n", + tcm_loop_dump_proto_id(tl_hba), + config_item_name(&wwn->wwn_group.cg_item), tpgt); } /* End items for tcm_loop_naa_cit */ @@ -1081,11 +1064,10 @@ static struct se_wwn *tcm_loop_make_scsi_hba( char *ptr; int ret, off = 0; - tl_hba = kzalloc(sizeof(struct tcm_loop_hba), GFP_KERNEL); - if (!tl_hba) { - pr_err("Unable to allocate struct tcm_loop_hba\n"); + tl_hba = kzalloc(sizeof(*tl_hba), GFP_KERNEL); + if (!tl_hba) return ERR_PTR(-ENOMEM); - } + /* * Determine the emulated Protocol Identifier and Target Port Name * based on the incoming configfs directory name. @@ -1103,8 +1085,8 @@ static struct se_wwn *tcm_loop_make_scsi_hba( } ptr = strstr(name, "iqn."); if (!ptr) { - pr_err("Unable to locate prefix for emulated Target " - "Port: %s\n", name); + pr_err("Unable to locate prefix for emulated Target Port: %s\n", + name); ret = -EINVAL; goto out; } @@ -1112,9 +1094,8 @@ static struct se_wwn *tcm_loop_make_scsi_hba( check_len: if (strlen(name) >= TL_WWN_ADDR_LEN) { - pr_err("Emulated NAA %s Address: %s, exceeds" - " max: %d\n", name, tcm_loop_dump_proto_id(tl_hba), - TL_WWN_ADDR_LEN); + pr_err("Emulated NAA %s Address: %s, exceeds max: %d\n", + name, tcm_loop_dump_proto_id(tl_hba), TL_WWN_ADDR_LEN); ret = -EINVAL; goto out; } @@ -1131,10 +1112,8 @@ check_len: sh = tl_hba->sh; tcm_loop_hba_no_cnt++; - pr_debug("TCM_Loop_ConfigFS: Allocated emulated Target" - " %s Address: %s at Linux/SCSI Host ID: %d\n", - tcm_loop_dump_proto_id(tl_hba), name, sh->host_no); - + pr_debug("TCM_Loop_ConfigFS: Allocated emulated Target %s Address: %s at Linux/SCSI Host ID: %d\n", + tcm_loop_dump_proto_id(tl_hba), name, sh->host_no); return &tl_hba->tl_hba_wwn; out: kfree(tl_hba); @@ -1147,10 +1126,9 @@ static void tcm_loop_drop_scsi_hba( struct tcm_loop_hba *tl_hba = container_of(wwn, struct tcm_loop_hba, tl_hba_wwn); - pr_debug("TCM_Loop_ConfigFS: Deallocating emulated Target" - " %s Address: %s at Linux/SCSI Host ID: %d\n", - tcm_loop_dump_proto_id(tl_hba), tl_hba->tl_wwn_address, - tl_hba->sh->host_no); + pr_debug("TCM_Loop_ConfigFS: Deallocating emulated Target %s Address: %s at Linux/SCSI Host ID: %d\n", + tcm_loop_dump_proto_id(tl_hba), tl_hba->tl_wwn_address, + tl_hba->sh->host_no); /* * Call device_unregister() on the original tl_hba->dev. * tcm_loop_fabric_scsi.c:tcm_loop_release_adapter() will @@ -1223,8 +1201,7 @@ static int __init tcm_loop_fabric_init(void) __alignof__(struct tcm_loop_cmd), 0, NULL); if (!tcm_loop_cmd_cache) { - pr_debug("kmem_cache_create() for" - " tcm_loop_cmd_cache failed\n"); + pr_debug("kmem_cache_create() for tcm_loop_cmd_cache failed\n"); goto out_destroy_workqueue; } diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index e5c3e5f827d0..fb1003921d85 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -201,10 +201,9 @@ static struct sbp_session *sbp_session_create( snprintf(guid_str, sizeof(guid_str), "%016llx", guid); sess = kmalloc(sizeof(*sess), GFP_KERNEL); - if (!sess) { - pr_err("failed to allocate session descriptor\n"); + if (!sess) return ERR_PTR(-ENOMEM); - } + spin_lock_init(&sess->lock); INIT_LIST_HEAD(&sess->login_list); INIT_DELAYED_WORK(&sess->maint_work, session_maintenance_work); @@ -2029,10 +2028,8 @@ static struct se_portal_group *sbp_make_tpg( } tpg = kzalloc(sizeof(*tpg), GFP_KERNEL); - if (!tpg) { - pr_err("Unable to allocate struct sbp_tpg\n"); + if (!tpg) return ERR_PTR(-ENOMEM); - } tpg->tport = tport; tpg->tport_tpgt = tpgt; @@ -2088,10 +2085,8 @@ static struct se_wwn *sbp_make_tport( return ERR_PTR(-EINVAL); tport = kzalloc(sizeof(*tport), GFP_KERNEL); - if (!tport) { - pr_err("Unable to allocate struct sbp_tport\n"); + if (!tport) return ERR_PTR(-ENOMEM); - } tport->guid = guid; sbp_format_wwn(tport->tport_name, SBP_NAMELEN, guid); diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 72b1cd1bf9d9..3f4bf126eed0 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -1197,6 +1197,7 @@ struct configfs_attribute *passthrough_attrib_attrs[] = { EXPORT_SYMBOL(passthrough_attrib_attrs); TB_CIT_SETUP_DRV(dev_attrib, NULL, NULL); +TB_CIT_SETUP_DRV(dev_action, NULL, NULL); /* End functions for struct config_item_type tb_dev_attrib_cit */ @@ -2940,6 +2941,10 @@ static struct config_group *target_core_make_subdev( config_group_init_type_name(&dev->dev_group, name, &tb->tb_dev_cit); + config_group_init_type_name(&dev->dev_action_group, "action", + &tb->tb_dev_action_cit); + configfs_add_default_group(&dev->dev_action_group, &dev->dev_group); + config_group_init_type_name(&dev->dev_attrib.da_group, "attrib", &tb->tb_dev_attrib_cit); configfs_add_default_group(&dev->dev_attrib.da_group, &dev->dev_group); @@ -3200,6 +3205,7 @@ static const struct config_item_type target_core_cit = { void target_setup_backend_cits(struct target_backend *tb) { target_core_setup_dev_cit(tb); + target_core_setup_dev_action_cit(tb); target_core_setup_dev_attrib_cit(tb); target_core_setup_dev_pr_cit(tb); target_core_setup_dev_wwn_cit(tb); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index e8dd6da164b2..e27db4d45a9d 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -997,7 +997,7 @@ int target_configure_device(struct se_device *dev) ret = core_setup_alua(dev); if (ret) - goto out_free_index; + goto out_destroy_device; /* * Startup the struct se_device processing thread @@ -1041,6 +1041,8 @@ int target_configure_device(struct se_device *dev) out_free_alua: core_alua_free_lu_gp_mem(dev); +out_destroy_device: + dev->transport->destroy_device(dev); out_free_index: mutex_lock(&device_mutex); idr_remove(&devices_idr, dev->dev_index); diff --git a/drivers/target/target_core_fabric_lib.c b/drivers/target/target_core_fabric_lib.c index 508da345b73f..71a80257a052 100644 --- a/drivers/target/target_core_fabric_lib.c +++ b/drivers/target/target_core_fabric_lib.c @@ -273,7 +273,7 @@ static int iscsi_get_pr_transport_id_len( static char *iscsi_parse_pr_out_transport_id( struct se_portal_group *se_tpg, - const char *buf, + char *buf, u32 *out_tid_len, char **port_nexus_ptr) { @@ -356,7 +356,7 @@ static char *iscsi_parse_pr_out_transport_id( } } - return (char *)&buf[4]; + return &buf[4]; } int target_get_pr_transport_id_len(struct se_node_acl *nacl, @@ -405,7 +405,7 @@ int target_get_pr_transport_id(struct se_node_acl *nacl, } const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg, - const char *buf, u32 *out_tid_len, char **port_nexus_ptr) + char *buf, u32 *out_tid_len, char **port_nexus_ptr) { u32 offset; diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h index 9384d19a7326..1d5afc3ae017 100644 --- a/drivers/target/target_core_internal.h +++ b/drivers/target/target_core_internal.h @@ -17,6 +17,7 @@ struct target_backend { struct config_item_type tb_dev_cit; struct config_item_type tb_dev_attrib_cit; + struct config_item_type tb_dev_action_cit; struct config_item_type tb_dev_pr_cit; struct config_item_type tb_dev_wwn_cit; struct config_item_type tb_dev_alua_tg_pt_gps_cit; @@ -102,7 +103,7 @@ int target_get_pr_transport_id(struct se_node_acl *nacl, struct t10_pr_registration *pr_reg, int *format_code, unsigned char *buf); const char *target_parse_pr_out_transport_id(struct se_portal_group *tpg, - const char *buf, u32 *out_tid_len, char **port_nexus_ptr); + char *buf, u32 *out_tid_len, char **port_nexus_ptr); /* target_core_hba.c */ struct se_hba *core_alloc_hba(const char *, u32, u32); diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index b024613f9217..01ac306131c1 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -1601,7 +1601,7 @@ core_scsi3_decode_spec_i_port( dest_rtpi = tmp_lun->lun_rtpi; i_str = target_parse_pr_out_transport_id(tmp_tpg, - (const char *)ptr, &tid_len, &iport_ptr); + ptr, &tid_len, &iport_ptr); if (!i_str) continue; @@ -3287,7 +3287,7 @@ core_scsi3_emulate_pro_register_and_move(struct se_cmd *cmd, u64 res_key, goto out; } initiator_str = target_parse_pr_out_transport_id(dest_se_tpg, - (const char *)&buf[24], &tmp_tid_len, &iport_ptr); + &buf[24], &tmp_tid_len, &iport_ptr); if (!initiator_str) { pr_err("SPC-3 PR REGISTER_AND_MOVE: Unable to locate" " initiator_str from Transport ID\n"); diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index 750a04ed0e93..b054682e974f 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -1216,9 +1216,11 @@ sbc_execute_unmap(struct se_cmd *cmd) goto err; } - ret = ops->execute_unmap(cmd, lba, range); - if (ret) - goto err; + if (range) { + ret = ops->execute_unmap(cmd, lba, range); + if (ret) + goto err; + } ptr += 16; size -= 16; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index c03a78ee26cd..4558f2e1fe1b 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1774,6 +1774,9 @@ void transport_generic_request_failure(struct se_cmd *cmd, case TCM_OUT_OF_RESOURCES: cmd->scsi_status = SAM_STAT_TASK_SET_FULL; goto queue_status; + case TCM_LUN_BUSY: + cmd->scsi_status = SAM_STAT_BUSY; + goto queue_status; case TCM_RESERVATION_CONFLICT: /* * No SENSE Data payload for this case, set SCSI Status diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index a415d87f22d2..4ad89ea71a70 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -32,7 +32,7 @@ #include <linux/highmem.h> #include <linux/configfs.h> #include <linux/mutex.h> -#include <linux/kthread.h> +#include <linux/workqueue.h> #include <net/genetlink.h> #include <scsi/scsi_common.h> #include <scsi/scsi_proto.h> @@ -77,15 +77,21 @@ * the total size is 256K * PAGE_SIZE. */ #define DATA_BLOCK_SIZE PAGE_SIZE -#define DATA_BLOCK_BITS (256 * 1024) +#define DATA_BLOCK_SHIFT PAGE_SHIFT +#define DATA_BLOCK_BITS_DEF (256 * 1024) #define DATA_SIZE (DATA_BLOCK_BITS * DATA_BLOCK_SIZE) -#define DATA_BLOCK_INIT_BITS 128 + +#define TCMU_MBS_TO_BLOCKS(_mbs) (_mbs << (20 - DATA_BLOCK_SHIFT)) +#define TCMU_BLOCKS_TO_MBS(_blocks) (_blocks >> (20 - DATA_BLOCK_SHIFT)) /* The total size of the ring is 8M + 256K * PAGE_SIZE */ #define TCMU_RING_SIZE (CMDR_SIZE + DATA_SIZE) -/* Default maximum of the global data blocks(512K * PAGE_SIZE) */ -#define TCMU_GLOBAL_MAX_BLOCKS (512 * 1024) +/* + * Default number of global data blocks(512K * PAGE_SIZE) + * when the unmap thread will be started. + */ +#define TCMU_GLOBAL_MAX_BLOCKS_DEF (512 * 1024) static u8 tcmu_kern_cmd_reply_supported; @@ -107,6 +113,7 @@ struct tcmu_nl_cmd { struct tcmu_dev { struct list_head node; struct kref kref; + struct se_device se_dev; char *name; @@ -114,6 +121,7 @@ struct tcmu_dev { #define TCMU_DEV_BIT_OPEN 0 #define TCMU_DEV_BIT_BROKEN 1 +#define TCMU_DEV_BIT_BLOCKED 2 unsigned long flags; struct uio_info uio_info; @@ -128,22 +136,27 @@ struct tcmu_dev { /* Must add data_off and mb_addr to get the address */ size_t data_off; size_t data_size; + uint32_t max_blocks; + size_t ring_size; - wait_queue_head_t wait_cmdr; struct mutex cmdr_lock; + struct list_head cmdr_queue; - bool waiting_global; uint32_t dbi_max; uint32_t dbi_thresh; - DECLARE_BITMAP(data_bitmap, DATA_BLOCK_BITS); + unsigned long *data_bitmap; struct radix_tree_root data_blocks; struct idr commands; - spinlock_t commands_lock; - struct timer_list timeout; + struct timer_list cmd_timer; unsigned int cmd_time_out; + struct timer_list qfull_timer; + int qfull_time_out; + + struct list_head timedout_entry; + spinlock_t nl_cmd_lock; struct tcmu_nl_cmd curr_nl_cmd; /* wake up threads waiting on curr_nl_cmd */ @@ -161,6 +174,7 @@ struct tcmu_dev { struct tcmu_cmd { struct se_cmd *se_cmd; struct tcmu_dev *tcmu_dev; + struct list_head cmdr_queue_entry; uint16_t cmd_id; @@ -175,16 +189,68 @@ struct tcmu_cmd { #define TCMU_CMD_BIT_EXPIRED 0 unsigned long flags; }; - -static struct task_struct *unmap_thread; -static wait_queue_head_t unmap_wait; +/* + * To avoid dead lock the mutex lock order should always be: + * + * mutex_lock(&root_udev_mutex); + * ... + * mutex_lock(&tcmu_dev->cmdr_lock); + * mutex_unlock(&tcmu_dev->cmdr_lock); + * ... + * mutex_unlock(&root_udev_mutex); + */ static DEFINE_MUTEX(root_udev_mutex); static LIST_HEAD(root_udev); -static atomic_t global_db_count = ATOMIC_INIT(0); +static DEFINE_SPINLOCK(timed_out_udevs_lock); +static LIST_HEAD(timed_out_udevs); static struct kmem_cache *tcmu_cmd_cache; +static atomic_t global_db_count = ATOMIC_INIT(0); +static struct delayed_work tcmu_unmap_work; +static int tcmu_global_max_blocks = TCMU_GLOBAL_MAX_BLOCKS_DEF; + +static int tcmu_set_global_max_data_area(const char *str, + const struct kernel_param *kp) +{ + int ret, max_area_mb; + + ret = kstrtoint(str, 10, &max_area_mb); + if (ret) + return -EINVAL; + + if (max_area_mb <= 0) { + pr_err("global_max_data_area must be larger than 0.\n"); + return -EINVAL; + } + + tcmu_global_max_blocks = TCMU_MBS_TO_BLOCKS(max_area_mb); + if (atomic_read(&global_db_count) > tcmu_global_max_blocks) + schedule_delayed_work(&tcmu_unmap_work, 0); + else + cancel_delayed_work_sync(&tcmu_unmap_work); + + return 0; +} + +static int tcmu_get_global_max_data_area(char *buffer, + const struct kernel_param *kp) +{ + return sprintf(buffer, "%d", TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks)); +} + +static const struct kernel_param_ops tcmu_global_max_data_area_op = { + .set = tcmu_set_global_max_data_area, + .get = tcmu_get_global_max_data_area, +}; + +module_param_cb(global_max_data_area_mb, &tcmu_global_max_data_area_op, NULL, + S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(global_max_data_area_mb, + "Max MBs allowed to be allocated to all the tcmu device's " + "data areas."); + /* multicast group */ enum tcmu_multicast_groups { TCMU_MCGRP_CONFIG, @@ -345,10 +411,8 @@ static inline bool tcmu_get_empty_block(struct tcmu_dev *udev, page = radix_tree_lookup(&udev->data_blocks, dbi); if (!page) { if (atomic_add_return(1, &global_db_count) > - TCMU_GLOBAL_MAX_BLOCKS) { - atomic_dec(&global_db_count); - return false; - } + tcmu_global_max_blocks) + schedule_delayed_work(&tcmu_unmap_work, 0); /* try to get new page from the mm */ page = alloc_page(GFP_KERNEL); @@ -379,19 +443,11 @@ static bool tcmu_get_empty_blocks(struct tcmu_dev *udev, { int i; - udev->waiting_global = false; - for (i = tcmu_cmd->dbi_cur; i < tcmu_cmd->dbi_cnt; i++) { if (!tcmu_get_empty_block(udev, tcmu_cmd)) - goto err; + return false; } return true; - -err: - udev->waiting_global = true; - /* Try to wake up the unmap thread */ - wake_up(&unmap_wait); - return false; } static inline struct page * @@ -437,6 +493,7 @@ static struct tcmu_cmd *tcmu_alloc_cmd(struct se_cmd *se_cmd) if (!tcmu_cmd) return NULL; + INIT_LIST_HEAD(&tcmu_cmd->cmdr_queue_entry); tcmu_cmd->se_cmd = se_cmd; tcmu_cmd->tcmu_dev = udev; @@ -455,12 +512,13 @@ static struct tcmu_cmd *tcmu_alloc_cmd(struct se_cmd *se_cmd) static inline void tcmu_flush_dcache_range(void *vaddr, size_t size) { unsigned long offset = offset_in_page(vaddr); + void *start = vaddr - offset; size = round_up(size+offset, PAGE_SIZE); - vaddr -= offset; while (size) { - flush_dcache_page(virt_to_page(vaddr)); + flush_dcache_page(virt_to_page(start)); + start += PAGE_SIZE; size -= PAGE_SIZE; } } @@ -490,8 +548,7 @@ static inline size_t head_to_end(size_t head, size_t size) return size - head; } -static inline void new_iov(struct iovec **iov, int *iov_cnt, - struct tcmu_dev *udev) +static inline void new_iov(struct iovec **iov, int *iov_cnt) { struct iovec *iovec; @@ -518,7 +575,7 @@ static inline size_t iov_tail(struct iovec *iov) return (size_t)iov->iov_base + iov->iov_len; } -static int scatter_data_area(struct tcmu_dev *udev, +static void scatter_data_area(struct tcmu_dev *udev, struct tcmu_cmd *tcmu_cmd, struct scatterlist *data_sg, unsigned int data_nents, struct iovec **iov, int *iov_cnt, bool copy_data) @@ -544,19 +601,38 @@ static int scatter_data_area(struct tcmu_dev *udev, to = kmap_atomic(page); } - copy_bytes = min_t(size_t, sg_remaining, - block_remaining); + /* + * Covert to virtual offset of the ring data area. + */ to_offset = get_block_offset_user(udev, dbi, block_remaining); + /* + * The following code will gather and map the blocks + * to the same iovec when the blocks are all next to + * each other. + */ + copy_bytes = min_t(size_t, sg_remaining, + block_remaining); if (*iov_cnt != 0 && to_offset == iov_tail(*iov)) { + /* + * Will append to the current iovec, because + * the current block page is next to the + * previous one. + */ (*iov)->iov_len += copy_bytes; } else { - new_iov(iov, iov_cnt, udev); + /* + * Will allocate a new iovec because we are + * first time here or the current block page + * is not next to the previous one. + */ + new_iov(iov, iov_cnt); (*iov)->iov_base = (void __user *)to_offset; (*iov)->iov_len = copy_bytes; } + if (copy_data) { offset = DATA_BLOCK_SIZE - block_remaining; memcpy(to + offset, @@ -564,15 +640,15 @@ static int scatter_data_area(struct tcmu_dev *udev, copy_bytes); tcmu_flush_dcache_range(to, copy_bytes); } + sg_remaining -= copy_bytes; block_remaining -= copy_bytes; } kunmap_atomic(from - sg->offset); } + if (to) kunmap_atomic(to); - - return 0; } static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd, @@ -637,7 +713,7 @@ static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd, static inline size_t spc_bitmap_free(unsigned long *bitmap, uint32_t thresh) { - return DATA_BLOCK_SIZE * (thresh - bitmap_weight(bitmap, thresh)); + return thresh - bitmap_weight(bitmap, thresh); } /* @@ -677,9 +753,9 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, struct tcmu_cmd *cmd, /* try to check and get the data blocks as needed */ space = spc_bitmap_free(udev->data_bitmap, udev->dbi_thresh); - if (space < data_needed) { - unsigned long blocks_left = DATA_BLOCK_BITS - udev->dbi_thresh; - unsigned long grow; + if ((space * DATA_BLOCK_SIZE) < data_needed) { + unsigned long blocks_left = + (udev->max_blocks - udev->dbi_thresh) + space; if (blocks_left < blocks_needed) { pr_debug("no data space: only %lu available, but ask for %zu\n", @@ -688,23 +764,9 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, struct tcmu_cmd *cmd, return false; } - /* Try to expand the thresh */ - if (!udev->dbi_thresh) { - /* From idle state */ - uint32_t init_thresh = DATA_BLOCK_INIT_BITS; - - udev->dbi_thresh = max(blocks_needed, init_thresh); - } else { - /* - * Grow the data area by max(blocks needed, - * dbi_thresh / 2), but limited to the max - * DATA_BLOCK_BITS size. - */ - grow = max(blocks_needed, udev->dbi_thresh / 2); - udev->dbi_thresh += grow; - if (udev->dbi_thresh > DATA_BLOCK_BITS) - udev->dbi_thresh = DATA_BLOCK_BITS; - } + udev->dbi_thresh += blocks_needed; + if (udev->dbi_thresh > udev->max_blocks) + udev->dbi_thresh = udev->max_blocks; } return tcmu_get_empty_blocks(udev, cmd); @@ -731,14 +793,14 @@ static inline size_t tcmu_cmd_get_cmd_size(struct tcmu_cmd *tcmu_cmd, return command_size; } -static int tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd) +static int tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd, unsigned int tmo, + struct timer_list *timer) { struct tcmu_dev *udev = tcmu_cmd->tcmu_dev; - unsigned long tmo = udev->cmd_time_out; int cmd_id; if (tcmu_cmd->cmd_id) - return 0; + goto setup_timer; cmd_id = idr_alloc(&udev->commands, tcmu_cmd, 1, USHRT_MAX, GFP_NOWAIT); if (cmd_id < 0) { @@ -747,16 +809,58 @@ static int tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd) } tcmu_cmd->cmd_id = cmd_id; + pr_debug("allocated cmd %u for dev %s tmo %lu\n", tcmu_cmd->cmd_id, + udev->name, tmo / MSEC_PER_SEC); + +setup_timer: if (!tmo) return 0; tcmu_cmd->deadline = round_jiffies_up(jiffies + msecs_to_jiffies(tmo)); - mod_timer(&udev->timeout, tcmu_cmd->deadline); + mod_timer(timer, tcmu_cmd->deadline); return 0; } -static sense_reason_t -tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) +static int add_to_cmdr_queue(struct tcmu_cmd *tcmu_cmd) +{ + struct tcmu_dev *udev = tcmu_cmd->tcmu_dev; + unsigned int tmo; + int ret; + + /* + * For backwards compat if qfull_time_out is not set use + * cmd_time_out and if that's not set use the default time out. + */ + if (!udev->qfull_time_out) + return -ETIMEDOUT; + else if (udev->qfull_time_out > 0) + tmo = udev->qfull_time_out; + else if (udev->cmd_time_out) + tmo = udev->cmd_time_out; + else + tmo = TCMU_TIME_OUT; + + ret = tcmu_setup_cmd_timer(tcmu_cmd, tmo, &udev->qfull_timer); + if (ret) + return ret; + + list_add_tail(&tcmu_cmd->cmdr_queue_entry, &udev->cmdr_queue); + pr_debug("adding cmd %u on dev %s to ring space wait queue\n", + tcmu_cmd->cmd_id, udev->name); + return 0; +} + +/** + * queue_cmd_ring - queue cmd to ring or internally + * @tcmu_cmd: cmd to queue + * @scsi_err: TCM error code if failure (-1) returned. + * + * Returns: + * -1 we cannot queue internally or to the ring. + * 0 success + * 1 internally queued to wait for ring memory to free. + */ +static sense_reason_t queue_cmd_ring(struct tcmu_cmd *tcmu_cmd, int *scsi_err) { struct tcmu_dev *udev = tcmu_cmd->tcmu_dev; struct se_cmd *se_cmd = tcmu_cmd->se_cmd; @@ -770,8 +874,17 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) bool copy_to_data_area; size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd); - if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags)) - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + *scsi_err = TCM_NO_SENSE; + + if (test_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags)) { + *scsi_err = TCM_LUN_BUSY; + return -1; + } + + if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags)) { + *scsi_err = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; + return -1; + } /* * Must be a certain minimum size for response sense info, but @@ -788,7 +901,8 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) base_command_size = tcmu_cmd_get_base_cmd_size(tcmu_cmd->dbi_cnt); command_size = tcmu_cmd_get_cmd_size(tcmu_cmd, base_command_size); - mutex_lock(&udev->cmdr_lock); + if (!list_empty(&udev->cmdr_queue)) + goto queue; mb = udev->mb_addr; cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */ @@ -797,33 +911,18 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu " "cmd ring/data area\n", command_size, data_length, udev->cmdr_size, udev->data_size); - mutex_unlock(&udev->cmdr_lock); - return TCM_INVALID_CDB_FIELD; + *scsi_err = TCM_INVALID_CDB_FIELD; + return -1; } - while (!is_ring_space_avail(udev, tcmu_cmd, command_size, data_length)) { - int ret; - DEFINE_WAIT(__wait); - - prepare_to_wait(&udev->wait_cmdr, &__wait, TASK_INTERRUPTIBLE); - - pr_debug("sleeping for ring space\n"); - mutex_unlock(&udev->cmdr_lock); - if (udev->cmd_time_out) - ret = schedule_timeout( - msecs_to_jiffies(udev->cmd_time_out)); - else - ret = schedule_timeout(msecs_to_jiffies(TCMU_TIME_OUT)); - finish_wait(&udev->wait_cmdr, &__wait); - if (!ret) { - pr_warn("tcmu: command timed out\n"); - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - } - - mutex_lock(&udev->cmdr_lock); - - /* We dropped cmdr_lock, cmd_head is stale */ - cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */ + if (!is_ring_space_avail(udev, tcmu_cmd, command_size, data_length)) { + /* + * Don't leave commands partially setup because the unmap + * thread might need the blocks to make forward progress. + */ + tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cur); + tcmu_cmd_reset_dbi_cur(tcmu_cmd); + goto queue; } /* Insert a PAD if end-of-ring space is too small */ @@ -855,41 +954,29 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) iov_cnt = 0; copy_to_data_area = (se_cmd->data_direction == DMA_TO_DEVICE || se_cmd->se_cmd_flags & SCF_BIDI); - ret = scatter_data_area(udev, tcmu_cmd, se_cmd->t_data_sg, - se_cmd->t_data_nents, &iov, &iov_cnt, - copy_to_data_area); - if (ret) { - tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt); - mutex_unlock(&udev->cmdr_lock); - - pr_err("tcmu: alloc and scatter data failed\n"); - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - } + scatter_data_area(udev, tcmu_cmd, se_cmd->t_data_sg, + se_cmd->t_data_nents, &iov, &iov_cnt, + copy_to_data_area); entry->req.iov_cnt = iov_cnt; /* Handle BIDI commands */ iov_cnt = 0; if (se_cmd->se_cmd_flags & SCF_BIDI) { iov++; - ret = scatter_data_area(udev, tcmu_cmd, - se_cmd->t_bidi_data_sg, - se_cmd->t_bidi_data_nents, - &iov, &iov_cnt, false); - if (ret) { - tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt); - mutex_unlock(&udev->cmdr_lock); - - pr_err("tcmu: alloc and scatter bidi data failed\n"); - return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - } + scatter_data_area(udev, tcmu_cmd, se_cmd->t_bidi_data_sg, + se_cmd->t_bidi_data_nents, &iov, &iov_cnt, + false); } entry->req.iov_bidi_cnt = iov_cnt; - ret = tcmu_setup_cmd_timer(tcmu_cmd); + ret = tcmu_setup_cmd_timer(tcmu_cmd, udev->cmd_time_out, + &udev->cmd_timer); if (ret) { tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt); mutex_unlock(&udev->cmdr_lock); - return TCM_OUT_OF_RESOURCES; + + *scsi_err = TCM_OUT_OF_RESOURCES; + return -1; } entry->hdr.cmd_id = tcmu_cmd->cmd_id; @@ -911,36 +998,40 @@ tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd) UPDATE_HEAD(mb->cmd_head, command_size, udev->cmdr_size); tcmu_flush_dcache_range(mb, sizeof(*mb)); - mutex_unlock(&udev->cmdr_lock); /* TODO: only if FLUSH and FUA? */ uio_event_notify(&udev->uio_info); - if (udev->cmd_time_out) - mod_timer(&udev->timeout, round_jiffies_up(jiffies + - msecs_to_jiffies(udev->cmd_time_out))); + return 0; + +queue: + if (add_to_cmdr_queue(tcmu_cmd)) { + *scsi_err = TCM_OUT_OF_RESOURCES; + return -1; + } - return TCM_NO_SENSE; + return 1; } static sense_reason_t tcmu_queue_cmd(struct se_cmd *se_cmd) { + struct se_device *se_dev = se_cmd->se_dev; + struct tcmu_dev *udev = TCMU_DEV(se_dev); struct tcmu_cmd *tcmu_cmd; - sense_reason_t ret; + sense_reason_t scsi_ret; + int ret; tcmu_cmd = tcmu_alloc_cmd(se_cmd); if (!tcmu_cmd) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; - ret = tcmu_queue_cmd_ring(tcmu_cmd); - if (ret != TCM_NO_SENSE) { - pr_err("TCMU: Could not queue command\n"); - + mutex_lock(&udev->cmdr_lock); + ret = queue_cmd_ring(tcmu_cmd, &scsi_ret); + mutex_unlock(&udev->cmdr_lock); + if (ret < 0) tcmu_free_cmd(tcmu_cmd); - } - - return ret; + return scsi_ret; } static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *entry) @@ -1011,12 +1102,10 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) } WARN_ON(tcmu_hdr_get_op(entry->hdr.len_op) != TCMU_OP_CMD); - spin_lock(&udev->commands_lock); cmd = idr_remove(&udev->commands, entry->hdr.cmd_id); - spin_unlock(&udev->commands_lock); - if (!cmd) { - pr_err("cmd_id not found, ring is broken\n"); + pr_err("cmd_id %u not found, ring is broken\n", + entry->hdr.cmd_id); set_bit(TCMU_DEV_BIT_BROKEN, &udev->flags); break; } @@ -1030,10 +1119,20 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) handled++; } - if (mb->cmd_tail == mb->cmd_head) - del_timer(&udev->timeout); /* no more pending cmds */ + if (mb->cmd_tail == mb->cmd_head) { + /* no more pending commands */ + del_timer(&udev->cmd_timer); - wake_up(&udev->wait_cmdr); + if (list_empty(&udev->cmdr_queue)) { + /* + * no more pending or waiting commands so try to + * reclaim blocks if needed. + */ + if (atomic_read(&global_db_count) > + tcmu_global_max_blocks) + schedule_delayed_work(&tcmu_unmap_work, 0); + } + } return handled; } @@ -1041,6 +1140,10 @@ static unsigned int tcmu_handle_completions(struct tcmu_dev *udev) static int tcmu_check_expired_cmd(int id, void *p, void *data) { struct tcmu_cmd *cmd = p; + struct tcmu_dev *udev = cmd->tcmu_dev; + u8 scsi_status; + struct se_cmd *se_cmd; + bool is_running; if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) return 0; @@ -1048,29 +1151,61 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data) if (!time_after(jiffies, cmd->deadline)) return 0; - set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags); - target_complete_cmd(cmd->se_cmd, SAM_STAT_CHECK_CONDITION); - cmd->se_cmd = NULL; + is_running = list_empty(&cmd->cmdr_queue_entry); + se_cmd = cmd->se_cmd; + + if (is_running) { + /* + * If cmd_time_out is disabled but qfull is set deadline + * will only reflect the qfull timeout. Ignore it. + */ + if (!udev->cmd_time_out) + return 0; + + set_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags); + /* + * target_complete_cmd will translate this to LUN COMM FAILURE + */ + scsi_status = SAM_STAT_CHECK_CONDITION; + } else { + list_del_init(&cmd->cmdr_queue_entry); + + idr_remove(&udev->commands, id); + tcmu_free_cmd(cmd); + scsi_status = SAM_STAT_TASK_SET_FULL; + } + + pr_debug("Timing out cmd %u on dev %s that is %s.\n", + id, udev->name, is_running ? "inflight" : "queued"); + target_complete_cmd(se_cmd, scsi_status); return 0; } -static void tcmu_device_timedout(struct timer_list *t) +static void tcmu_device_timedout(struct tcmu_dev *udev) { - struct tcmu_dev *udev = from_timer(udev, t, timeout); - unsigned long flags; + spin_lock(&timed_out_udevs_lock); + if (list_empty(&udev->timedout_entry)) + list_add_tail(&udev->timedout_entry, &timed_out_udevs); + spin_unlock(&timed_out_udevs_lock); - spin_lock_irqsave(&udev->commands_lock, flags); - idr_for_each(&udev->commands, tcmu_check_expired_cmd, NULL); - spin_unlock_irqrestore(&udev->commands_lock, flags); + schedule_delayed_work(&tcmu_unmap_work, 0); +} - /* Try to wake up the ummap thread */ - wake_up(&unmap_wait); +static void tcmu_cmd_timedout(struct timer_list *t) +{ + struct tcmu_dev *udev = from_timer(udev, t, cmd_timer); - /* - * We don't need to wakeup threads on wait_cmdr since they have their - * own timeout. - */ + pr_debug("%s cmd timeout has expired\n", udev->name); + tcmu_device_timedout(udev); +} + +static void tcmu_qfull_timedout(struct timer_list *t) +{ + struct tcmu_dev *udev = from_timer(udev, t, qfull_timer); + + pr_debug("%s qfull timeout has expired\n", udev->name); + tcmu_device_timedout(udev); } static int tcmu_attach_hba(struct se_hba *hba, u32 host_id) @@ -1110,14 +1245,17 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name) udev->hba = hba; udev->cmd_time_out = TCMU_TIME_OUT; + udev->qfull_time_out = -1; - init_waitqueue_head(&udev->wait_cmdr); + udev->max_blocks = DATA_BLOCK_BITS_DEF; mutex_init(&udev->cmdr_lock); + INIT_LIST_HEAD(&udev->timedout_entry); + INIT_LIST_HEAD(&udev->cmdr_queue); idr_init(&udev->commands); - spin_lock_init(&udev->commands_lock); - timer_setup(&udev->timeout, tcmu_device_timedout, 0); + timer_setup(&udev->qfull_timer, tcmu_qfull_timedout, 0); + timer_setup(&udev->cmd_timer, tcmu_cmd_timedout, 0); init_waitqueue_head(&udev->nl_cmd_wq); spin_lock_init(&udev->nl_cmd_lock); @@ -1127,13 +1265,79 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name) return &udev->se_dev; } +static bool run_cmdr_queue(struct tcmu_dev *udev, bool fail) +{ + struct tcmu_cmd *tcmu_cmd, *tmp_cmd; + LIST_HEAD(cmds); + bool drained = true; + sense_reason_t scsi_ret; + int ret; + + if (list_empty(&udev->cmdr_queue)) + return true; + + pr_debug("running %s's cmdr queue forcefail %d\n", udev->name, fail); + + list_splice_init(&udev->cmdr_queue, &cmds); + + list_for_each_entry_safe(tcmu_cmd, tmp_cmd, &cmds, cmdr_queue_entry) { + list_del_init(&tcmu_cmd->cmdr_queue_entry); + + pr_debug("removing cmd %u on dev %s from queue\n", + tcmu_cmd->cmd_id, udev->name); + + if (fail) { + idr_remove(&udev->commands, tcmu_cmd->cmd_id); + /* + * We were not able to even start the command, so + * fail with busy to allow a retry in case runner + * was only temporarily down. If the device is being + * removed then LIO core will do the right thing and + * fail the retry. + */ + target_complete_cmd(tcmu_cmd->se_cmd, SAM_STAT_BUSY); + tcmu_free_cmd(tcmu_cmd); + continue; + } + + ret = queue_cmd_ring(tcmu_cmd, &scsi_ret); + if (ret < 0) { + pr_debug("cmd %u on dev %s failed with %u\n", + tcmu_cmd->cmd_id, udev->name, scsi_ret); + + idr_remove(&udev->commands, tcmu_cmd->cmd_id); + /* + * Ignore scsi_ret for now. target_complete_cmd + * drops it. + */ + target_complete_cmd(tcmu_cmd->se_cmd, + SAM_STAT_CHECK_CONDITION); + tcmu_free_cmd(tcmu_cmd); + } else if (ret > 0) { + pr_debug("ran out of space during cmdr queue run\n"); + /* + * cmd was requeued, so just put all cmds back in + * the queue + */ + list_splice_tail(&cmds, &udev->cmdr_queue); + drained = false; + goto done; + } + } + if (list_empty(&udev->cmdr_queue)) + del_timer(&udev->qfull_timer); +done: + return drained; +} + static int tcmu_irqcontrol(struct uio_info *info, s32 irq_on) { - struct tcmu_dev *tcmu_dev = container_of(info, struct tcmu_dev, uio_info); + struct tcmu_dev *udev = container_of(info, struct tcmu_dev, uio_info); - mutex_lock(&tcmu_dev->cmdr_lock); - tcmu_handle_completions(tcmu_dev); - mutex_unlock(&tcmu_dev->cmdr_lock); + mutex_lock(&udev->cmdr_lock); + tcmu_handle_completions(udev); + run_cmdr_queue(udev, false); + mutex_unlock(&udev->cmdr_lock); return 0; } @@ -1158,7 +1362,6 @@ static int tcmu_find_mem_index(struct vm_area_struct *vma) static struct page *tcmu_try_get_block_page(struct tcmu_dev *udev, uint32_t dbi) { struct page *page; - int ret; mutex_lock(&udev->cmdr_lock); page = tcmu_get_block_page(udev, dbi); @@ -1168,42 +1371,12 @@ static struct page *tcmu_try_get_block_page(struct tcmu_dev *udev, uint32_t dbi) } /* - * Normally it shouldn't be here: - * Only when the userspace has touched the blocks which - * are out of the tcmu_cmd's data iov[], and will return - * one zeroed page. + * Userspace messed up and passed in a address not in the + * data iov passed to it. */ - pr_warn("Block(%u) out of cmd's iov[] has been touched!\n", dbi); - pr_warn("Mostly it will be a bug of userspace, please have a check!\n"); - - if (dbi >= udev->dbi_thresh) { - /* Extern the udev->dbi_thresh to dbi + 1 */ - udev->dbi_thresh = dbi + 1; - udev->dbi_max = dbi; - } - - page = radix_tree_lookup(&udev->data_blocks, dbi); - if (!page) { - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - mutex_unlock(&udev->cmdr_lock); - return NULL; - } - - ret = radix_tree_insert(&udev->data_blocks, dbi, page); - if (ret) { - mutex_unlock(&udev->cmdr_lock); - __free_page(page); - return NULL; - } - - /* - * Since this case is rare in page fault routine, here we - * will allow the global_db_count >= TCMU_GLOBAL_MAX_BLOCKS - * to reduce possible page fault call trace. - */ - atomic_inc(&global_db_count); - } + pr_err("Invalid addr to data block mapping (dbi %u) on device %s\n", + dbi, udev->name); + page = NULL; mutex_unlock(&udev->cmdr_lock); return page; @@ -1238,7 +1411,7 @@ static int tcmu_vma_fault(struct vm_fault *vmf) dbi = (offset - udev->data_off) / DATA_BLOCK_SIZE; page = tcmu_try_get_block_page(udev, dbi); if (!page) - return VM_FAULT_NOPAGE; + return VM_FAULT_SIGBUS; } get_page(page); @@ -1260,7 +1433,7 @@ static int tcmu_mmap(struct uio_info *info, struct vm_area_struct *vma) vma->vm_private_data = udev; /* Ensure the mmap is exactly the right size */ - if (vma_pages(vma) != (TCMU_RING_SIZE >> PAGE_SHIFT)) + if (vma_pages(vma) != (udev->ring_size >> PAGE_SHIFT)) return -EINVAL; return 0; @@ -1301,21 +1474,19 @@ static int tcmu_check_and_free_pending_cmd(struct tcmu_cmd *cmd) return -EINVAL; } -static void tcmu_blocks_release(struct tcmu_dev *udev) +static void tcmu_blocks_release(struct radix_tree_root *blocks, + int start, int end) { int i; struct page *page; - /* Try to release all block pages */ - mutex_lock(&udev->cmdr_lock); - for (i = 0; i <= udev->dbi_max; i++) { - page = radix_tree_delete(&udev->data_blocks, i); + for (i = start; i < end; i++) { + page = radix_tree_delete(blocks, i); if (page) { __free_page(page); atomic_dec(&global_db_count); } } - mutex_unlock(&udev->cmdr_lock); } static void tcmu_dev_kref_release(struct kref *kref) @@ -1329,17 +1500,23 @@ static void tcmu_dev_kref_release(struct kref *kref) vfree(udev->mb_addr); udev->mb_addr = NULL; + spin_lock_bh(&timed_out_udevs_lock); + if (!list_empty(&udev->timedout_entry)) + list_del(&udev->timedout_entry); + spin_unlock_bh(&timed_out_udevs_lock); + /* Upper layer should drain all requests before calling this */ - spin_lock_irq(&udev->commands_lock); + mutex_lock(&udev->cmdr_lock); idr_for_each_entry(&udev->commands, cmd, i) { if (tcmu_check_and_free_pending_cmd(cmd) != 0) all_expired = false; } idr_destroy(&udev->commands); - spin_unlock_irq(&udev->commands_lock); WARN_ON(!all_expired); - tcmu_blocks_release(udev); + tcmu_blocks_release(&udev->data_blocks, 0, udev->dbi_max + 1); + kfree(udev->data_bitmap); + mutex_unlock(&udev->cmdr_lock); call_rcu(&dev->rcu_head, tcmu_dev_call_rcu); } @@ -1406,7 +1583,7 @@ static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev) wake_up_all(&udev->nl_cmd_wq); - return ret;; + return ret; } static int tcmu_netlink_event(struct tcmu_dev *udev, enum tcmu_genl_cmd cmd, @@ -1515,6 +1692,13 @@ static int tcmu_configure_device(struct se_device *dev) info = &udev->uio_info; + udev->data_bitmap = kzalloc(BITS_TO_LONGS(udev->max_blocks) * + sizeof(unsigned long), GFP_KERNEL); + if (!udev->data_bitmap) { + ret = -ENOMEM; + goto err_bitmap_alloc; + } + udev->mb_addr = vzalloc(CMDR_SIZE); if (!udev->mb_addr) { ret = -ENOMEM; @@ -1524,9 +1708,8 @@ static int tcmu_configure_device(struct se_device *dev) /* mailbox fits in first part of CMDR space */ udev->cmdr_size = CMDR_SIZE - CMDR_OFF; udev->data_off = CMDR_SIZE; - udev->data_size = DATA_SIZE; + udev->data_size = udev->max_blocks * DATA_BLOCK_SIZE; udev->dbi_thresh = 0; /* Default in Idle state */ - udev->waiting_global = false; /* Initialise the mailbox of the ring buffer */ mb = udev->mb_addr; @@ -1543,7 +1726,7 @@ static int tcmu_configure_device(struct se_device *dev) info->mem[0].name = "tcm-user command & data buffer"; info->mem[0].addr = (phys_addr_t)(uintptr_t)udev->mb_addr; - info->mem[0].size = TCMU_RING_SIZE; + info->mem[0].size = udev->ring_size = udev->data_size + CMDR_SIZE; info->mem[0].memtype = UIO_MEM_NONE; info->irqcontrol = tcmu_irqcontrol; @@ -1596,6 +1779,9 @@ err_register: vfree(udev->mb_addr); udev->mb_addr = NULL; err_vzalloc: + kfree(udev->data_bitmap); + udev->data_bitmap = NULL; +err_bitmap_alloc: kfree(info->name); info->name = NULL; @@ -1619,7 +1805,8 @@ static void tcmu_destroy_device(struct se_device *dev) { struct tcmu_dev *udev = TCMU_DEV(dev); - del_timer_sync(&udev->timeout); + del_timer_sync(&udev->cmd_timer); + del_timer_sync(&udev->qfull_timer); mutex_lock(&root_udev_mutex); list_del(&udev->node); @@ -1633,9 +1820,81 @@ static void tcmu_destroy_device(struct se_device *dev) kref_put(&udev->kref, tcmu_dev_kref_release); } +static void tcmu_unblock_dev(struct tcmu_dev *udev) +{ + mutex_lock(&udev->cmdr_lock); + clear_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags); + mutex_unlock(&udev->cmdr_lock); +} + +static void tcmu_block_dev(struct tcmu_dev *udev) +{ + mutex_lock(&udev->cmdr_lock); + + if (test_and_set_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags)) + goto unlock; + + /* complete IO that has executed successfully */ + tcmu_handle_completions(udev); + /* fail IO waiting to be queued */ + run_cmdr_queue(udev, true); + +unlock: + mutex_unlock(&udev->cmdr_lock); +} + +static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level) +{ + struct tcmu_mailbox *mb; + struct tcmu_cmd *cmd; + int i; + + mutex_lock(&udev->cmdr_lock); + + idr_for_each_entry(&udev->commands, cmd, i) { + if (!list_empty(&cmd->cmdr_queue_entry)) + continue; + + pr_debug("removing cmd %u on dev %s from ring (is expired %d)\n", + cmd->cmd_id, udev->name, + test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)); + + idr_remove(&udev->commands, i); + if (!test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) { + if (err_level == 1) { + /* + * Userspace was not able to start the + * command or it is retryable. + */ + target_complete_cmd(cmd->se_cmd, SAM_STAT_BUSY); + } else { + /* hard failure */ + target_complete_cmd(cmd->se_cmd, + SAM_STAT_CHECK_CONDITION); + } + } + tcmu_cmd_free_data(cmd, cmd->dbi_cnt); + tcmu_free_cmd(cmd); + } + + mb = udev->mb_addr; + tcmu_flush_dcache_range(mb, sizeof(*mb)); + pr_debug("mb last %u head %u tail %u\n", udev->cmdr_last_cleaned, + mb->cmd_tail, mb->cmd_head); + + udev->cmdr_last_cleaned = 0; + mb->cmd_tail = 0; + mb->cmd_head = 0; + tcmu_flush_dcache_range(mb, sizeof(*mb)); + + del_timer(&udev->cmd_timer); + + mutex_unlock(&udev->cmdr_lock); +} + enum { Opt_dev_config, Opt_dev_size, Opt_hw_block_size, Opt_hw_max_sectors, - Opt_nl_reply_supported, Opt_err, + Opt_nl_reply_supported, Opt_max_data_area_mb, Opt_err, }; static match_table_t tokens = { @@ -1644,6 +1903,7 @@ static match_table_t tokens = { {Opt_hw_block_size, "hw_block_size=%u"}, {Opt_hw_max_sectors, "hw_max_sectors=%u"}, {Opt_nl_reply_supported, "nl_reply_supported=%d"}, + {Opt_max_data_area_mb, "max_data_area_mb=%u"}, {Opt_err, NULL} }; @@ -1677,7 +1937,7 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev, struct tcmu_dev *udev = TCMU_DEV(dev); char *orig, *ptr, *opts, *arg_p; substring_t args[MAX_OPT_ARGS]; - int ret = 0, token; + int ret = 0, token, tmpval; opts = kstrdup(page, GFP_KERNEL); if (!opts) @@ -1729,6 +1989,39 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev, if (ret < 0) pr_err("kstrtoint() failed for nl_reply_supported=\n"); break; + case Opt_max_data_area_mb: + if (dev->export_count) { + pr_err("Unable to set max_data_area_mb while exports exist\n"); + ret = -EINVAL; + break; + } + + arg_p = match_strdup(&args[0]); + if (!arg_p) { + ret = -ENOMEM; + break; + } + ret = kstrtoint(arg_p, 0, &tmpval); + kfree(arg_p); + if (ret < 0) { + pr_err("kstrtoint() failed for max_data_area_mb=\n"); + break; + } + + if (tmpval <= 0) { + pr_err("Invalid max_data_area %d\n", tmpval); + ret = -EINVAL; + break; + } + + udev->max_blocks = TCMU_MBS_TO_BLOCKS(tmpval); + if (udev->max_blocks > tcmu_global_max_blocks) { + pr_err("%d is too large. Adjusting max_data_area_mb to global limit of %u\n", + tmpval, + TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks)); + udev->max_blocks = tcmu_global_max_blocks; + } + break; default: break; } @@ -1748,7 +2041,9 @@ static ssize_t tcmu_show_configfs_dev_params(struct se_device *dev, char *b) bl = sprintf(b + bl, "Config: %s ", udev->dev_config[0] ? udev->dev_config : "NULL"); - bl += sprintf(b + bl, "Size: %zu\n", udev->dev_size); + bl += sprintf(b + bl, "Size: %zu ", udev->dev_size); + bl += sprintf(b + bl, "MaxDataAreaMB: %u\n", + TCMU_BLOCKS_TO_MBS(udev->max_blocks)); return bl; } @@ -1800,6 +2095,51 @@ static ssize_t tcmu_cmd_time_out_store(struct config_item *item, const char *pag } CONFIGFS_ATTR(tcmu_, cmd_time_out); +static ssize_t tcmu_qfull_time_out_show(struct config_item *item, char *page) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); + + return snprintf(page, PAGE_SIZE, "%ld\n", udev->qfull_time_out <= 0 ? + udev->qfull_time_out : + udev->qfull_time_out / MSEC_PER_SEC); +} + +static ssize_t tcmu_qfull_time_out_store(struct config_item *item, + const char *page, size_t count) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); + s32 val; + int ret; + + ret = kstrtos32(page, 0, &val); + if (ret < 0) + return ret; + + if (val >= 0) { + udev->qfull_time_out = val * MSEC_PER_SEC; + } else { + printk(KERN_ERR "Invalid qfull timeout value %d\n", val); + return -EINVAL; + } + return count; +} +CONFIGFS_ATTR(tcmu_, qfull_time_out); + +static ssize_t tcmu_max_data_area_mb_show(struct config_item *item, char *page) +{ + struct se_dev_attrib *da = container_of(to_config_group(item), + struct se_dev_attrib, da_group); + struct tcmu_dev *udev = TCMU_DEV(da->da_dev); + + return snprintf(page, PAGE_SIZE, "%u\n", + TCMU_BLOCKS_TO_MBS(udev->max_blocks)); +} +CONFIGFS_ATTR_RO(tcmu_, max_data_area_mb); + static ssize_t tcmu_dev_config_show(struct config_item *item, char *page) { struct se_dev_attrib *da = container_of(to_config_group(item), @@ -1943,8 +2283,74 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item, } CONFIGFS_ATTR(tcmu_, emulate_write_cache); +static ssize_t tcmu_block_dev_show(struct config_item *item, char *page) +{ + struct se_device *se_dev = container_of(to_config_group(item), + struct se_device, + dev_action_group); + struct tcmu_dev *udev = TCMU_DEV(se_dev); + + if (test_bit(TCMU_DEV_BIT_BLOCKED, &udev->flags)) + return snprintf(page, PAGE_SIZE, "%s\n", "blocked"); + else + return snprintf(page, PAGE_SIZE, "%s\n", "unblocked"); +} + +static ssize_t tcmu_block_dev_store(struct config_item *item, const char *page, + size_t count) +{ + struct se_device *se_dev = container_of(to_config_group(item), + struct se_device, + dev_action_group); + struct tcmu_dev *udev = TCMU_DEV(se_dev); + u8 val; + int ret; + + ret = kstrtou8(page, 0, &val); + if (ret < 0) + return ret; + + if (val > 1) { + pr_err("Invalid block value %d\n", val); + return -EINVAL; + } + + if (!val) + tcmu_unblock_dev(udev); + else + tcmu_block_dev(udev); + return count; +} +CONFIGFS_ATTR(tcmu_, block_dev); + +static ssize_t tcmu_reset_ring_store(struct config_item *item, const char *page, + size_t count) +{ + struct se_device *se_dev = container_of(to_config_group(item), + struct se_device, + dev_action_group); + struct tcmu_dev *udev = TCMU_DEV(se_dev); + u8 val; + int ret; + + ret = kstrtou8(page, 0, &val); + if (ret < 0) + return ret; + + if (val != 1 && val != 2) { + pr_err("Invalid reset ring value %d\n", val); + return -EINVAL; + } + + tcmu_reset_ring(udev, val); + return count; +} +CONFIGFS_ATTR_WO(tcmu_, reset_ring); + static struct configfs_attribute *tcmu_attrib_attrs[] = { &tcmu_attr_cmd_time_out, + &tcmu_attr_qfull_time_out, + &tcmu_attr_max_data_area_mb, &tcmu_attr_dev_config, &tcmu_attr_dev_size, &tcmu_attr_emulate_write_cache, @@ -1954,6 +2360,12 @@ static struct configfs_attribute *tcmu_attrib_attrs[] = { static struct configfs_attribute **tcmu_attrs; +static struct configfs_attribute *tcmu_action_attrs[] = { + &tcmu_attr_block_dev, + &tcmu_attr_reset_ring, + NULL, +}; + static struct target_backend_ops tcmu_ops = { .name = "user", .owner = THIS_MODULE, @@ -1969,85 +2381,93 @@ static struct target_backend_ops tcmu_ops = { .show_configfs_dev_params = tcmu_show_configfs_dev_params, .get_device_type = sbc_get_device_type, .get_blocks = tcmu_get_blocks, - .tb_dev_attrib_attrs = NULL, + .tb_dev_action_attrs = tcmu_action_attrs, }; -static int unmap_thread_fn(void *data) +static void find_free_blocks(void) { struct tcmu_dev *udev; loff_t off; - uint32_t start, end, block; - struct page *page; - int i; + u32 start, end, block, total_freed = 0; - while (!kthread_should_stop()) { - DEFINE_WAIT(__wait); + if (atomic_read(&global_db_count) <= tcmu_global_max_blocks) + return; - prepare_to_wait(&unmap_wait, &__wait, TASK_INTERRUPTIBLE); - schedule(); - finish_wait(&unmap_wait, &__wait); + mutex_lock(&root_udev_mutex); + list_for_each_entry(udev, &root_udev, node) { + mutex_lock(&udev->cmdr_lock); - if (kthread_should_stop()) - break; + /* Try to complete the finished commands first */ + tcmu_handle_completions(udev); - mutex_lock(&root_udev_mutex); - list_for_each_entry(udev, &root_udev, node) { - mutex_lock(&udev->cmdr_lock); + /* Skip the udevs in idle */ + if (!udev->dbi_thresh) { + mutex_unlock(&udev->cmdr_lock); + continue; + } - /* Try to complete the finished commands first */ - tcmu_handle_completions(udev); + end = udev->dbi_max + 1; + block = find_last_bit(udev->data_bitmap, end); + if (block == udev->dbi_max) { + /* + * The last bit is dbi_max, so it is not possible + * reclaim any blocks. + */ + mutex_unlock(&udev->cmdr_lock); + continue; + } else if (block == end) { + /* The current udev will goto idle state */ + udev->dbi_thresh = start = 0; + udev->dbi_max = 0; + } else { + udev->dbi_thresh = start = block + 1; + udev->dbi_max = block; + } - /* Skip the udevs waiting the global pool or in idle */ - if (udev->waiting_global || !udev->dbi_thresh) { - mutex_unlock(&udev->cmdr_lock); - continue; - } + /* Here will truncate the data area from off */ + off = udev->data_off + start * DATA_BLOCK_SIZE; + unmap_mapping_range(udev->inode->i_mapping, off, 0, 1); - end = udev->dbi_max + 1; - block = find_last_bit(udev->data_bitmap, end); - if (block == udev->dbi_max) { - /* - * The last bit is dbi_max, so there is - * no need to shrink any blocks. - */ - mutex_unlock(&udev->cmdr_lock); - continue; - } else if (block == end) { - /* The current udev will goto idle state */ - udev->dbi_thresh = start = 0; - udev->dbi_max = 0; - } else { - udev->dbi_thresh = start = block + 1; - udev->dbi_max = block; - } + /* Release the block pages */ + tcmu_blocks_release(&udev->data_blocks, start, end); + mutex_unlock(&udev->cmdr_lock); - /* Here will truncate the data area from off */ - off = udev->data_off + start * DATA_BLOCK_SIZE; - unmap_mapping_range(udev->inode->i_mapping, off, 0, 1); - - /* Release the block pages */ - for (i = start; i < end; i++) { - page = radix_tree_delete(&udev->data_blocks, i); - if (page) { - __free_page(page); - atomic_dec(&global_db_count); - } - } - mutex_unlock(&udev->cmdr_lock); - } + total_freed += end - start; + pr_debug("Freed %u blocks (total %u) from %s.\n", end - start, + total_freed, udev->name); + } + mutex_unlock(&root_udev_mutex); - /* - * Try to wake up the udevs who are waiting - * for the global data pool. - */ - list_for_each_entry(udev, &root_udev, node) { - if (udev->waiting_global) - wake_up(&udev->wait_cmdr); - } - mutex_unlock(&root_udev_mutex); + if (atomic_read(&global_db_count) > tcmu_global_max_blocks) + schedule_delayed_work(&tcmu_unmap_work, msecs_to_jiffies(5000)); +} + +static void check_timedout_devices(void) +{ + struct tcmu_dev *udev, *tmp_dev; + LIST_HEAD(devs); + + spin_lock_bh(&timed_out_udevs_lock); + list_splice_init(&timed_out_udevs, &devs); + + list_for_each_entry_safe(udev, tmp_dev, &devs, timedout_entry) { + list_del_init(&udev->timedout_entry); + spin_unlock_bh(&timed_out_udevs_lock); + + mutex_lock(&udev->cmdr_lock); + idr_for_each(&udev->commands, tcmu_check_expired_cmd, NULL); + mutex_unlock(&udev->cmdr_lock); + + spin_lock_bh(&timed_out_udevs_lock); } - return 0; + spin_unlock_bh(&timed_out_udevs_lock); +} + +static void tcmu_unmap_work_fn(struct work_struct *work) +{ + check_timedout_devices(); + find_free_blocks(); } static int __init tcmu_module_init(void) @@ -2056,6 +2476,8 @@ static int __init tcmu_module_init(void) BUILD_BUG_ON((sizeof(struct tcmu_cmd_entry) % TCMU_OP_ALIGN_SIZE) != 0); + INIT_DELAYED_WORK(&tcmu_unmap_work, tcmu_unmap_work_fn); + tcmu_cmd_cache = kmem_cache_create("tcmu_cmd_cache", sizeof(struct tcmu_cmd), __alignof__(struct tcmu_cmd), @@ -2101,17 +2523,8 @@ static int __init tcmu_module_init(void) if (ret) goto out_attrs; - init_waitqueue_head(&unmap_wait); - unmap_thread = kthread_run(unmap_thread_fn, NULL, "tcmu_unmap"); - if (IS_ERR(unmap_thread)) { - ret = PTR_ERR(unmap_thread); - goto out_unreg_transport; - } - return 0; -out_unreg_transport: - target_backend_unregister(&tcmu_ops); out_attrs: kfree(tcmu_attrs); out_unreg_genl: @@ -2126,7 +2539,7 @@ out_free_cache: static void __exit tcmu_module_exit(void) { - kthread_stop(unmap_thread); + cancel_delayed_work_sync(&tcmu_unmap_work); target_backend_unregister(&tcmu_ops); kfree(tcmu_attrs); genl_unregister_family(&tcmu_genl_family); diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index 315ae2926e20..b6adc54b96f1 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -301,13 +301,13 @@ config DB8500_THERMAL thermal zone if trip points reached. config ARMADA_THERMAL - tristate "Armada 370/XP thermal management" + tristate "Marvell EBU Armada SoCs thermal management" depends on ARCH_MVEBU || COMPILE_TEST depends on HAS_IOMEM depends on OF help Enable this option if you want to have support for thermal management - controller present in Armada 370 and Armada XP SoC. + controller present in Marvell EBU Armada SoCs (370,375,XP,38x,7K,8K). config DA9062_THERMAL tristate "DA9062/DA9061 Dialog Semiconductor thermal driver" diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c index 706d74798cbe..4c275ec10ac5 100644 --- a/drivers/thermal/armada_thermal.c +++ b/drivers/thermal/armada_thermal.c @@ -1,5 +1,5 @@ /* - * Marvell Armada 370/XP thermal sensor driver + * Marvell EBU Armada SoCs thermal sensor driver * * Copyright (C) 2013 Marvell * @@ -23,8 +23,7 @@ #include <linux/platform_device.h> #include <linux/of_device.h> #include <linux/thermal.h> - -#define THERMAL_VALID_MASK 0x1 +#include <linux/iopoll.h> /* Thermal Manager Control and Status Register */ #define PMU_TDC0_SW_RST_MASK (0x1 << 1) @@ -39,14 +38,38 @@ #define A375_UNIT_CONTROL_MASK 0x7 #define A375_READOUT_INVERT BIT(15) #define A375_HW_RESETn BIT(8) -#define A380_HW_RESET BIT(8) + +/* Legacy bindings */ +#define LEGACY_CONTROL_MEM_LEN 0x4 + +/* Current bindings with the 2 control registers under the same memory area */ +#define LEGACY_CONTROL1_OFFSET 0x0 +#define CONTROL0_OFFSET 0x0 +#define CONTROL1_OFFSET 0x4 + +/* Errata fields */ +#define CONTROL0_TSEN_TC_TRIM_MASK 0x7 +#define CONTROL0_TSEN_TC_TRIM_VAL 0x3 + +/* TSEN refers to the temperature sensors within the AP */ +#define CONTROL0_TSEN_START BIT(0) +#define CONTROL0_TSEN_RESET BIT(1) +#define CONTROL0_TSEN_ENABLE BIT(2) + +/* EXT_TSEN refers to the external temperature sensors, out of the AP */ +#define CONTROL1_EXT_TSEN_SW_RESET BIT(7) +#define CONTROL1_EXT_TSEN_HW_RESETn BIT(8) + +#define STATUS_POLL_PERIOD_US 1000 +#define STATUS_POLL_TIMEOUT_US 100000 struct armada_thermal_data; /* Marvell EBU Thermal Sensor Dev Structure */ struct armada_thermal_priv { - void __iomem *sensor; - void __iomem *control; + void __iomem *status; + void __iomem *control0; + void __iomem *control1; struct armada_thermal_data *data; }; @@ -59,107 +82,142 @@ struct armada_thermal_data { bool (*is_valid)(struct armada_thermal_priv *); /* Formula coeficients: temp = (b - m * reg) / div */ - unsigned long coef_b; - unsigned long coef_m; - unsigned long coef_div; + s64 coef_b; + s64 coef_m; + u32 coef_div; bool inverted; + bool signed_sample; /* Register shift and mask to access the sensor temperature */ unsigned int temp_shift; unsigned int temp_mask; - unsigned int is_valid_shift; + u32 is_valid_bit; + bool needs_control0; }; static void armadaxp_init_sensor(struct platform_device *pdev, struct armada_thermal_priv *priv) { - unsigned long reg; + u32 reg; - reg = readl_relaxed(priv->control); + reg = readl_relaxed(priv->control1); reg |= PMU_TDC0_OTF_CAL_MASK; - writel(reg, priv->control); + writel(reg, priv->control1); /* Reference calibration value */ reg &= ~PMU_TDC0_REF_CAL_CNT_MASK; reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS); - writel(reg, priv->control); + writel(reg, priv->control1); /* Reset the sensor */ - reg = readl_relaxed(priv->control); - writel((reg | PMU_TDC0_SW_RST_MASK), priv->control); + reg = readl_relaxed(priv->control1); + writel((reg | PMU_TDC0_SW_RST_MASK), priv->control1); - writel(reg, priv->control); + writel(reg, priv->control1); /* Enable the sensor */ - reg = readl_relaxed(priv->sensor); + reg = readl_relaxed(priv->status); reg &= ~PMU_TM_DISABLE_MASK; - writel(reg, priv->sensor); + writel(reg, priv->status); } static void armada370_init_sensor(struct platform_device *pdev, struct armada_thermal_priv *priv) { - unsigned long reg; + u32 reg; - reg = readl_relaxed(priv->control); + reg = readl_relaxed(priv->control1); reg |= PMU_TDC0_OTF_CAL_MASK; - writel(reg, priv->control); + writel(reg, priv->control1); /* Reference calibration value */ reg &= ~PMU_TDC0_REF_CAL_CNT_MASK; reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS); - writel(reg, priv->control); + writel(reg, priv->control1); reg &= ~PMU_TDC0_START_CAL_MASK; - writel(reg, priv->control); + writel(reg, priv->control1); - mdelay(10); + msleep(10); } static void armada375_init_sensor(struct platform_device *pdev, struct armada_thermal_priv *priv) { - unsigned long reg; + u32 reg; - reg = readl(priv->control + 4); + reg = readl(priv->control1); reg &= ~(A375_UNIT_CONTROL_MASK << A375_UNIT_CONTROL_SHIFT); reg &= ~A375_READOUT_INVERT; reg &= ~A375_HW_RESETn; - writel(reg, priv->control + 4); - mdelay(20); + writel(reg, priv->control1); + msleep(20); reg |= A375_HW_RESETn; - writel(reg, priv->control + 4); - mdelay(50); + writel(reg, priv->control1); + msleep(50); +} + +static void armada_wait_sensor_validity(struct armada_thermal_priv *priv) +{ + u32 reg; + + readl_relaxed_poll_timeout(priv->status, reg, + reg & priv->data->is_valid_bit, + STATUS_POLL_PERIOD_US, + STATUS_POLL_TIMEOUT_US); } static void armada380_init_sensor(struct platform_device *pdev, struct armada_thermal_priv *priv) { - unsigned long reg = readl_relaxed(priv->control); - - /* Reset hardware once */ - if (!(reg & A380_HW_RESET)) { - reg |= A380_HW_RESET; - writel(reg, priv->control); - mdelay(10); + u32 reg = readl_relaxed(priv->control1); + + /* Disable the HW/SW reset */ + reg |= CONTROL1_EXT_TSEN_HW_RESETn; + reg &= ~CONTROL1_EXT_TSEN_SW_RESET; + writel(reg, priv->control1); + + /* Set Tsen Tc Trim to correct default value (errata #132698) */ + if (priv->control0) { + reg = readl_relaxed(priv->control0); + reg &= ~CONTROL0_TSEN_TC_TRIM_MASK; + reg |= CONTROL0_TSEN_TC_TRIM_VAL; + writel(reg, priv->control0); } + + /* Wait the sensors to be valid or the core will warn the user */ + armada_wait_sensor_validity(priv); +} + +static void armada_ap806_init_sensor(struct platform_device *pdev, + struct armada_thermal_priv *priv) +{ + u32 reg; + + reg = readl_relaxed(priv->control0); + reg &= ~CONTROL0_TSEN_RESET; + reg |= CONTROL0_TSEN_START | CONTROL0_TSEN_ENABLE; + writel(reg, priv->control0); + + /* Wait the sensors to be valid or the core will warn the user */ + armada_wait_sensor_validity(priv); } static bool armada_is_valid(struct armada_thermal_priv *priv) { - unsigned long reg = readl_relaxed(priv->sensor); + u32 reg = readl_relaxed(priv->status); - return (reg >> priv->data->is_valid_shift) & THERMAL_VALID_MASK; + return reg & priv->data->is_valid_bit; } static int armada_get_temp(struct thermal_zone_device *thermal, - int *temp) + int *temp) { struct armada_thermal_priv *priv = thermal->devdata; - unsigned long reg; - unsigned long m, b, div; + u32 reg, div; + s64 sample, b, m; /* Valid check */ if (priv->data->is_valid && !priv->data->is_valid(priv)) { @@ -168,8 +226,13 @@ static int armada_get_temp(struct thermal_zone_device *thermal, return -EIO; } - reg = readl_relaxed(priv->sensor); + reg = readl_relaxed(priv->status); reg = (reg >> priv->data->temp_shift) & priv->data->temp_mask; + if (priv->data->signed_sample) + /* The most significant bit is the sign bit */ + sample = sign_extend32(reg, fls(priv->data->temp_mask) - 1); + else + sample = reg; /* Get formula coeficients */ b = priv->data->coef_b; @@ -177,9 +240,10 @@ static int armada_get_temp(struct thermal_zone_device *thermal, div = priv->data->coef_div; if (priv->data->inverted) - *temp = ((m * reg) - b) / div; + *temp = div_s64((m * sample) - b, div); else - *temp = (b - (m * reg)) / div; + *temp = div_s64(b - (m * sample), div); + return 0; } @@ -191,45 +255,73 @@ static const struct armada_thermal_data armadaxp_data = { .init_sensor = armadaxp_init_sensor, .temp_shift = 10, .temp_mask = 0x1ff, - .coef_b = 3153000000UL, - .coef_m = 10000000UL, + .coef_b = 3153000000ULL, + .coef_m = 10000000ULL, .coef_div = 13825, }; static const struct armada_thermal_data armada370_data = { .is_valid = armada_is_valid, .init_sensor = armada370_init_sensor, - .is_valid_shift = 9, + .is_valid_bit = BIT(9), .temp_shift = 10, .temp_mask = 0x1ff, - .coef_b = 3153000000UL, - .coef_m = 10000000UL, + .coef_b = 3153000000ULL, + .coef_m = 10000000ULL, .coef_div = 13825, }; static const struct armada_thermal_data armada375_data = { .is_valid = armada_is_valid, .init_sensor = armada375_init_sensor, - .is_valid_shift = 10, + .is_valid_bit = BIT(10), .temp_shift = 0, .temp_mask = 0x1ff, - .coef_b = 3171900000UL, - .coef_m = 10000000UL, + .coef_b = 3171900000ULL, + .coef_m = 10000000ULL, .coef_div = 13616, + .needs_control0 = true, }; static const struct armada_thermal_data armada380_data = { .is_valid = armada_is_valid, .init_sensor = armada380_init_sensor, - .is_valid_shift = 10, + .is_valid_bit = BIT(10), .temp_shift = 0, .temp_mask = 0x3ff, - .coef_b = 1172499100UL, - .coef_m = 2000096UL, + .coef_b = 1172499100ULL, + .coef_m = 2000096ULL, .coef_div = 4201, .inverted = true, }; +static const struct armada_thermal_data armada_ap806_data = { + .is_valid = armada_is_valid, + .init_sensor = armada_ap806_init_sensor, + .is_valid_bit = BIT(16), + .temp_shift = 0, + .temp_mask = 0x3ff, + .coef_b = -150000LL, + .coef_m = 423ULL, + .coef_div = 1, + .inverted = true, + .signed_sample = true, + .needs_control0 = true, +}; + +static const struct armada_thermal_data armada_cp110_data = { + .is_valid = armada_is_valid, + .init_sensor = armada380_init_sensor, + .is_valid_bit = BIT(10), + .temp_shift = 0, + .temp_mask = 0x3ff, + .coef_b = 1172499100ULL, + .coef_m = 2000096ULL, + .coef_div = 4201, + .inverted = true, + .needs_control0 = true, +}; + static const struct of_device_id armada_thermal_id_table[] = { { .compatible = "marvell,armadaxp-thermal", @@ -248,6 +340,14 @@ static const struct of_device_id armada_thermal_id_table[] = { .data = &armada380_data, }, { + .compatible = "marvell,armada-ap806-thermal", + .data = &armada_ap806_data, + }, + { + .compatible = "marvell,armada-cp110-thermal", + .data = &armada_cp110_data, + }, + { /* sentinel */ }, }; @@ -255,6 +355,7 @@ MODULE_DEVICE_TABLE(of, armada_thermal_id_table); static int armada_thermal_probe(struct platform_device *pdev) { + void __iomem *control = NULL; struct thermal_zone_device *thermal; const struct of_device_id *match; struct armada_thermal_priv *priv; @@ -269,20 +370,40 @@ static int armada_thermal_probe(struct platform_device *pdev) return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->sensor = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(priv->sensor)) - return PTR_ERR(priv->sensor); + priv->status = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->status)) + return PTR_ERR(priv->status); res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - priv->control = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(priv->control)) - return PTR_ERR(priv->control); + control = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(control)) + return PTR_ERR(control); priv->data = (struct armada_thermal_data *)match->data; + + /* + * Legacy DT bindings only described "control1" register (also referred + * as "control MSB" on old documentation). New bindings cover + * "control0/control LSB" and "control1/control MSB" registers within + * the same resource, which is then of size 8 instead of 4. + */ + if (resource_size(res) == LEGACY_CONTROL_MEM_LEN) { + /* ->control0 unavailable in this configuration */ + if (priv->data->needs_control0) { + dev_err(&pdev->dev, "No access to control0 register\n"); + return -EINVAL; + } + + priv->control1 = control + LEGACY_CONTROL1_OFFSET; + } else { + priv->control0 = control + CONTROL0_OFFSET; + priv->control1 = control + CONTROL1_OFFSET; + } + priv->data->init_sensor(pdev, priv); - thermal = thermal_zone_device_register("armada_thermal", 0, 0, - priv, &ops, NULL, 0, 0); + thermal = thermal_zone_device_register(dev_name(&pdev->dev), 0, 0, priv, + &ops, NULL, 0, 0); if (IS_ERR(thermal)) { dev_err(&pdev->dev, "Failed to register thermal zone device\n"); @@ -316,5 +437,5 @@ static struct platform_driver armada_thermal_driver = { module_platform_driver(armada_thermal_driver); MODULE_AUTHOR("Ezequiel Garcia <ezequiel.garcia@free-electrons.com>"); -MODULE_DESCRIPTION("Armada 370/XP thermal driver"); +MODULE_DESCRIPTION("Marvell EBU Armada SoCs thermal driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index 2d855a96cdd9..761d0559c268 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -527,7 +527,7 @@ static void hisi_thermal_toggle_sensor(struct hisi_thermal_sensor *sensor, static int hisi_thermal_probe(struct platform_device *pdev) { struct hisi_thermal_data *data; - int const (*platform_probe)(struct hisi_thermal_data *); + int (*platform_probe)(struct hisi_thermal_data *); struct device *dev = &pdev->dev; int ret; diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index e7d4ffc3de7f..a67781b7a0b2 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -70,10 +70,6 @@ enum imx_thermal_trip { #define IMX_POLLING_DELAY 2000 /* millisecond */ #define IMX_PASSIVE_DELAY 1000 -#define FACTOR0 10000000 -#define FACTOR1 15976 -#define FACTOR2 4297157 - #define TEMPMON_IMX6Q 1 #define TEMPMON_IMX6SX 2 @@ -347,78 +343,74 @@ static struct thermal_zone_device_ops imx_tz_ops = { .set_trip_temp = imx_set_trip_temp, }; -static int imx_init_calib(struct platform_device *pdev, u32 val) +static int imx_init_calib(struct platform_device *pdev, u32 ocotp_ana1) { struct imx_thermal_data *data = platform_get_drvdata(pdev); - int t1, n1; + int n1; u64 temp64; - if (val == 0 || val == ~0) { + if (ocotp_ana1 == 0 || ocotp_ana1 == ~0) { dev_err(&pdev->dev, "invalid sensor calibration data\n"); return -EINVAL; } /* - * Sensor data layout: - * [31:20] - sensor value @ 25C - * Use universal formula now and only need sensor value @ 25C - * slope = 0.4297157 - (0.0015976 * 25C fuse) + * The sensor is calibrated at 25 °C (aka T1) and the value measured + * (aka N1) at this temperature is provided in bits [31:20] in the + * i.MX's OCOTP value ANA1. + * To find the actual temperature T, the following formula has to be used + * when reading value n from the sensor: + * + * T = T1 + (N - N1) / (0.4148468 - 0.0015423 * N1) °C + 3.580661 °C + * = [T1' - N1 / (0.4148468 - 0.0015423 * N1) °C] + N / (0.4148468 - 0.0015423 * N1) °C + * = [T1' + N1 / (0.0015423 * N1 - 0.4148468) °C] - N / (0.0015423 * N1 - 0.4148468) °C + * = c2 - c1 * N + * + * with + * + * T1' = 28.580661 °C + * c1 = 1 / (0.0015423 * N1 - 0.4297157) °C + * c2 = T1' + N1 / (0.0015423 * N1 - 0.4148468) °C + * = T1' + N1 * c1 */ - n1 = val >> 20; - t1 = 25; /* t1 always 25C */ + n1 = ocotp_ana1 >> 20; - /* - * Derived from linear interpolation: - * slope = 0.4297157 - (0.0015976 * 25C fuse) - * slope = (FACTOR2 - FACTOR1 * n1) / FACTOR0 - * (Nmeas - n1) / (Tmeas - t1) = slope - * We want to reduce this down to the minimum computation necessary - * for each temperature read. Also, we want Tmeas in millicelsius - * and we don't want to lose precision from integer division. So... - * Tmeas = (Nmeas - n1) / slope + t1 - * milli_Tmeas = 1000 * (Nmeas - n1) / slope + 1000 * t1 - * milli_Tmeas = -1000 * (n1 - Nmeas) / slope + 1000 * t1 - * Let constant c1 = (-1000 / slope) - * milli_Tmeas = (n1 - Nmeas) * c1 + 1000 * t1 - * Let constant c2 = n1 *c1 + 1000 * t1 - * milli_Tmeas = c2 - Nmeas * c1 - */ - temp64 = FACTOR0; - temp64 *= 1000; - do_div(temp64, FACTOR1 * n1 - FACTOR2); + temp64 = 10000000; /* use 10^7 as fixed point constant for values in formula */ + temp64 *= 1000; /* to get result in °mC */ + do_div(temp64, 15423 * n1 - 4148468); data->c1 = temp64; - data->c2 = n1 * data->c1 + 1000 * t1; + data->c2 = n1 * data->c1 + 28581; return 0; } -static void imx_init_temp_grade(struct platform_device *pdev, u32 val) +static void imx_init_temp_grade(struct platform_device *pdev, u32 ocotp_mem0) { struct imx_thermal_data *data = platform_get_drvdata(pdev); /* The maximum die temp is specified by the Temperature Grade */ - switch ((val >> 6) & 0x3) { - case 0: /* Commercial (0 to 95C) */ + switch ((ocotp_mem0 >> 6) & 0x3) { + case 0: /* Commercial (0 to 95 °C) */ data->temp_grade = "Commercial"; data->temp_max = 95000; break; - case 1: /* Extended Commercial (-20 to 105C) */ + case 1: /* Extended Commercial (-20 °C to 105 °C) */ data->temp_grade = "Extended Commercial"; data->temp_max = 105000; break; - case 2: /* Industrial (-40 to 105C) */ + case 2: /* Industrial (-40 °C to 105 °C) */ data->temp_grade = "Industrial"; data->temp_max = 105000; break; - case 3: /* Automotive (-40 to 125C) */ + case 3: /* Automotive (-40 °C to 125 °C) */ data->temp_grade = "Automotive"; data->temp_max = 125000; break; } /* - * Set the critical trip point at 5C under max - * Set the passive trip point at 10C under max (can change via sysfs) + * Set the critical trip point at 5 °C under max + * Set the passive trip point at 10 °C under max (changeable via sysfs) */ data->temp_critical = data->temp_max - (1000 * 5); data->temp_passive = data->temp_max - (1000 * 10); diff --git a/drivers/thermal/int340x_thermal/int3400_thermal.c b/drivers/thermal/int340x_thermal/int3400_thermal.c index 8ee38f55c7f3..e26b01c05e82 100644 --- a/drivers/thermal/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/int340x_thermal/int3400_thermal.c @@ -211,7 +211,7 @@ static void int3400_notify(acpi_handle handle, thermal_prop); break; default: - dev_err(&priv->adev->dev, "Unsupported event [0x%x]\n", event); + /* Ignore unknown notification codes sent to INT3400 device */ break; } } @@ -319,17 +319,21 @@ static int int3400_thermal_probe(struct platform_device *pdev) result = sysfs_create_group(&pdev->dev.kobj, &uuid_attribute_group); if (result) - goto free_zone; + goto free_rel_misc; result = acpi_install_notify_handler( priv->adev->handle, ACPI_DEVICE_NOTIFY, int3400_notify, (void *)priv); if (result) - goto free_zone; + goto free_sysfs; return 0; -free_zone: +free_sysfs: + sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group); +free_rel_misc: + if (!priv->rel_misc_dev_res) + acpi_thermal_rel_misc_device_remove(priv->adev->handle); thermal_zone_device_unregister(priv->thermal); free_art_trt: kfree(priv->trts); diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c index 1e61c09153c9..c75661a3801a 100644 --- a/drivers/thermal/mtk_thermal.c +++ b/drivers/thermal/mtk_thermal.c @@ -32,15 +32,10 @@ #include <linux/types.h> /* AUXADC Registers */ -#define AUXADC_CON0_V 0x000 -#define AUXADC_CON1_V 0x004 #define AUXADC_CON1_SET_V 0x008 #define AUXADC_CON1_CLR_V 0x00c #define AUXADC_CON2_V 0x010 #define AUXADC_DATA(channel) (0x14 + (channel) * 4) -#define AUXADC_MISC_V 0x094 - -#define AUXADC_CON1_CHANNEL(x) BIT(x) #define APMIXED_SYS_TS_CON1 0x604 @@ -158,8 +153,6 @@ /* The number of sensing points per bank */ #define MT2712_NUM_SENSORS_PER_ZONE 4 -#define THERMAL_NAME "mtk-thermal" - struct mtk_thermal; struct thermal_bank_cfg { @@ -765,7 +758,7 @@ static struct platform_driver mtk_thermal_driver = { .probe = mtk_thermal_probe, .remove = mtk_thermal_remove, .driver = { - .name = THERMAL_NAME, + .name = "mtk-thermal", .of_match_table = mtk_thermal_of_match, }, }; diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index d04ec3b9e5ff..e09f0354a4bc 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -30,7 +30,6 @@ #include <linux/err.h> #include <linux/export.h> #include <linux/string.h> -#include <linux/thermal.h> #include "thermal_core.h" diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c index b4d3116cfdaf..3055f9a12a17 100644 --- a/drivers/thermal/power_allocator.c +++ b/drivers/thermal/power_allocator.c @@ -523,6 +523,7 @@ static void allow_maximum_power(struct thermal_zone_device *tz) struct thermal_instance *instance; struct power_allocator_params *params = tz->governor_data; + mutex_lock(&tz->lock); list_for_each_entry(instance, &tz->thermal_instances, tz_node) { if ((instance->trip != params->trip_max_desired_temperature) || (!cdev_is_power_actor(instance->cdev))) @@ -534,6 +535,7 @@ static void allow_maximum_power(struct thermal_zone_device *tz) mutex_unlock(&instance->cdev->lock); thermal_cdev_update(instance->cdev); } + mutex_unlock(&tz->lock); } /** diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c index 075db1de5e53..455b58ce2652 100644 --- a/drivers/thermal/tegra/soctherm.c +++ b/drivers/thermal/tegra/soctherm.c @@ -341,62 +341,6 @@ static int tegra_thermctl_get_temp(void *data, int *out_temp) return 0; } -static int -thermtrip_program(struct device *dev, const struct tegra_tsensor_group *sg, - int trip_temp); -static int -throttrip_program(struct device *dev, const struct tegra_tsensor_group *sg, - struct soctherm_throt_cfg *stc, int trip_temp); -static struct soctherm_throt_cfg * -find_throttle_cfg_by_name(struct tegra_soctherm *ts, const char *name); - -static int tegra_thermctl_set_trip_temp(void *data, int trip, int temp) -{ - struct tegra_thermctl_zone *zone = data; - struct thermal_zone_device *tz = zone->tz; - struct tegra_soctherm *ts = zone->ts; - const struct tegra_tsensor_group *sg = zone->sg; - struct device *dev = zone->dev; - enum thermal_trip_type type; - int ret; - - if (!tz) - return -EINVAL; - - ret = tz->ops->get_trip_type(tz, trip, &type); - if (ret) - return ret; - - if (type == THERMAL_TRIP_CRITICAL) { - return thermtrip_program(dev, sg, temp); - } else if (type == THERMAL_TRIP_HOT) { - int i; - - for (i = 0; i < THROTTLE_SIZE; i++) { - struct thermal_cooling_device *cdev; - struct soctherm_throt_cfg *stc; - - if (!ts->throt_cfgs[i].init) - continue; - - cdev = ts->throt_cfgs[i].cdev; - if (get_thermal_instance(tz, cdev, trip)) - stc = find_throttle_cfg_by_name(ts, cdev->type); - else - continue; - - return throttrip_program(dev, sg, stc, temp); - } - } - - return 0; -} - -static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = { - .get_temp = tegra_thermctl_get_temp, - .set_trip_temp = tegra_thermctl_set_trip_temp, -}; - /** * enforce_temp_range() - check and enforce temperature range [min, max] * @trip_temp: the trip temperature to check @@ -527,6 +471,53 @@ find_throttle_cfg_by_name(struct tegra_soctherm *ts, const char *name) return NULL; } +static int tegra_thermctl_set_trip_temp(void *data, int trip, int temp) +{ + struct tegra_thermctl_zone *zone = data; + struct thermal_zone_device *tz = zone->tz; + struct tegra_soctherm *ts = zone->ts; + const struct tegra_tsensor_group *sg = zone->sg; + struct device *dev = zone->dev; + enum thermal_trip_type type; + int ret; + + if (!tz) + return -EINVAL; + + ret = tz->ops->get_trip_type(tz, trip, &type); + if (ret) + return ret; + + if (type == THERMAL_TRIP_CRITICAL) { + return thermtrip_program(dev, sg, temp); + } else if (type == THERMAL_TRIP_HOT) { + int i; + + for (i = 0; i < THROTTLE_SIZE; i++) { + struct thermal_cooling_device *cdev; + struct soctherm_throt_cfg *stc; + + if (!ts->throt_cfgs[i].init) + continue; + + cdev = ts->throt_cfgs[i].cdev; + if (get_thermal_instance(tz, cdev, trip)) + stc = find_throttle_cfg_by_name(ts, cdev->type); + else + continue; + + return throttrip_program(dev, sg, stc, temp); + } + } + + return 0; +} + +static const struct thermal_zone_of_device_ops tegra_of_thermal_ops = { + .get_temp = tegra_thermctl_get_temp, + .set_trip_temp = tegra_thermctl_set_trip_temp, +}; + static int get_hot_temp(struct thermal_zone_device *tz, int *trip, int *temp) { int ntrips, i, ret; diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index 541af5946203..c4a508a124dc 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -59,14 +59,6 @@ static LIST_HEAD(thermal_hwmon_list); static DEFINE_MUTEX(thermal_hwmon_list_lock); static ssize_t -name_show(struct device *dev, struct device_attribute *attr, char *buf) -{ - struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", hwmon->type); -} -static DEVICE_ATTR_RO(name); - -static ssize_t temp_input_show(struct device *dev, struct device_attribute *attr, char *buf) { int temperature; @@ -165,15 +157,12 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) INIT_LIST_HEAD(&hwmon->tz_list); strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH); - hwmon->device = hwmon_device_register(NULL); + hwmon->device = hwmon_device_register_with_info(NULL, hwmon->type, + hwmon, NULL, NULL); if (IS_ERR(hwmon->device)) { result = PTR_ERR(hwmon->device); goto free_mem; } - dev_set_drvdata(hwmon->device, hwmon); - result = device_create_file(hwmon->device, &dev_attr_name); - if (result) - goto free_mem; register_sys_interface: temp = kzalloc(sizeof(*temp), GFP_KERNEL); @@ -222,10 +211,8 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) free_temp_mem: kfree(temp); unregister_name: - if (new_hwmon_device) { - device_remove_file(hwmon->device, &dev_attr_name); + if (new_hwmon_device) hwmon_device_unregister(hwmon->device); - } free_mem: if (new_hwmon_device) kfree(hwmon); @@ -267,7 +254,6 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) list_del(&hwmon->node); mutex_unlock(&thermal_hwmon_list_lock); - device_remove_file(hwmon->device, &dev_attr_name); hwmon_device_unregister(hwmon->device); kfree(hwmon); } diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c index d93eee2f101b..1a6c88b10a39 100644 --- a/drivers/thermal/x86_pkg_temp_thermal.c +++ b/drivers/thermal/x86_pkg_temp_thermal.c @@ -96,12 +96,12 @@ static int pkg_temp_debugfs_init(void) return -ENOENT; d = debugfs_create_u32("pkg_thres_interrupt", S_IRUGO, debugfs, - (u32 *)&pkg_interrupt_cnt); + &pkg_interrupt_cnt); if (!d) goto err_out; d = debugfs_create_u32("pkg_thres_work", S_IRUGO, debugfs, - (u32 *)&pkg_work_cnt); + &pkg_work_cnt); if (!d) goto err_out; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 3b3af7e0ce1c..3b3e1f6632d7 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2477,11 +2477,11 @@ static __poll_t gsmld_poll(struct tty_struct *tty, struct file *file, poll_wait(file, &tty->read_wait, wait); poll_wait(file, &tty->write_wait, wait); if (tty_hung_up_p(file)) - mask |= POLLHUP; + mask |= EPOLLHUP; if (!tty_is_writelocked(tty) && tty_write_room(tty) > 0) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; if (gsm->dead) - mask |= POLLHUP; + mask |= EPOLLHUP; return mask; } diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 929434ebee50..dabb391909aa 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -814,14 +814,14 @@ static __poll_t n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp, /* set bits for operations that won't block */ if (!list_empty(&n_hdlc->rx_buf_list.list)) - mask |= POLLIN | POLLRDNORM; /* readable */ + mask |= EPOLLIN | EPOLLRDNORM; /* readable */ if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) - mask |= POLLHUP; + mask |= EPOLLHUP; if (tty_hung_up_p(filp)) - mask |= POLLHUP; + mask |= EPOLLHUP; if (!tty_is_writelocked(tty) && !list_empty(&n_hdlc->tx_free_buf_list.list)) - mask |= POLLOUT | POLLWRNORM; /* writable */ + mask |= EPOLLOUT | EPOLLWRNORM; /* writable */ } return mask; } /* end of n_hdlc_tty_poll() */ diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c index e81d3db8ad63..dbf1ab36758e 100644 --- a/drivers/tty/n_r3964.c +++ b/drivers/tty/n_r3964.c @@ -1223,7 +1223,7 @@ static __poll_t r3964_poll(struct tty_struct *tty, struct file *file, struct r3964_client_info *pClient; struct r3964_message *pMsg = NULL; unsigned long flags; - __poll_t result = POLLOUT; + __poll_t result = EPOLLOUT; TRACE_L("POLL"); @@ -1234,7 +1234,7 @@ static __poll_t r3964_poll(struct tty_struct *tty, struct file *file, pMsg = pClient->first_msg; spin_unlock_irqrestore(&pInfo->lock, flags); if (pMsg) - result |= POLLIN | POLLRDNORM; + result |= EPOLLIN | EPOLLRDNORM; } else { result = -EINVAL; } diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 478a9b40fd03..5c0e59e8fe46 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1344,7 +1344,7 @@ handle_newline: put_tty_queue(c, ldata); smp_store_release(&ldata->canon_head, ldata->read_head); kill_fasync(&tty->fasync, SIGIO, POLL_IN); - wake_up_interruptible_poll(&tty->read_wait, POLLIN); + wake_up_interruptible_poll(&tty->read_wait, EPOLLIN); return 0; } } @@ -1625,7 +1625,7 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp, if (read_cnt(ldata)) { kill_fasync(&tty->fasync, SIGIO, POLL_IN); - wake_up_interruptible_poll(&tty->read_wait, POLLIN); + wake_up_interruptible_poll(&tty->read_wait, EPOLLIN); } } @@ -2376,22 +2376,22 @@ static __poll_t n_tty_poll(struct tty_struct *tty, struct file *file, poll_wait(file, &tty->read_wait, wait); poll_wait(file, &tty->write_wait, wait); if (input_available_p(tty, 1)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; else { tty_buffer_flush_work(tty->port); if (input_available_p(tty, 1)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } if (tty->packet && tty->link->ctrl_status) - mask |= POLLPRI | POLLIN | POLLRDNORM; + mask |= EPOLLPRI | EPOLLIN | EPOLLRDNORM; if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) - mask |= POLLHUP; + mask |= EPOLLHUP; if (tty_hung_up_p(file)) - mask |= POLLHUP; + mask |= EPOLLHUP; if (tty->ops->write && !tty_is_writelocked(tty) && tty_chars_in_buffer(tty) < WAKEUP_CHARS && tty_write_room(tty) > 0) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 64338442050e..6c7151edd715 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -344,7 +344,7 @@ static void pty_start(struct tty_struct *tty) tty->ctrl_status &= ~TIOCPKT_STOP; tty->ctrl_status |= TIOCPKT_START; spin_unlock_irqrestore(&tty->ctrl_lock, flags); - wake_up_interruptible_poll(&tty->link->read_wait, POLLIN); + wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } } @@ -357,7 +357,7 @@ static void pty_stop(struct tty_struct *tty) tty->ctrl_status &= ~TIOCPKT_START; tty->ctrl_status |= TIOCPKT_STOP; spin_unlock_irqrestore(&tty->ctrl_lock, flags); - wake_up_interruptible_poll(&tty->link->read_wait, POLLIN); + wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } } diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c index 4c8b80f1c688..870e84fb6e39 100644 --- a/drivers/tty/serial/earlycon.c +++ b/drivers/tty/serial/earlycon.c @@ -197,25 +197,20 @@ int __init setup_earlycon(char *buf) } /* - * When CONFIG_ACPI_SPCR_TABLE is defined, "earlycon" without parameters in - * command line does not start DT earlycon immediately, instead it defers - * starting it until DT/ACPI decision is made. At that time if ACPI is enabled - * call parse_spcr(), else call early_init_dt_scan_chosen_stdout() + * This defers the initialization of the early console until after ACPI has + * been initialized. */ -bool earlycon_init_is_deferred __initdata; +bool earlycon_acpi_spcr_enable __initdata; /* early_param wrapper for setup_earlycon() */ static int __init param_setup_earlycon(char *buf) { int err; - /* - * Just 'earlycon' is a valid param for devicetree earlycons; - * don't generate a warning from parse_early_params() in that case - */ + /* Just 'earlycon' is a valid param for devicetree and ACPI SPCR. */ if (!buf || !buf[0]) { if (IS_ENABLED(CONFIG_ACPI_SPCR_TABLE)) { - earlycon_init_is_deferred = true; + earlycon_acpi_spcr_enable = true; return 0; } else if (!buf) { return early_init_dt_scan_chosen_stdout(); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 6a89835453d3..eb9133b472f4 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -445,7 +445,7 @@ static ssize_t hung_up_tty_write(struct file *file, const char __user *buf, /* No kernel lock held - none needed ;) */ static __poll_t hung_up_tty_poll(struct file *filp, poll_table *wait) { - return POLLIN | POLLOUT | POLLERR | POLLHUP | POLLRDNORM | POLLWRNORM; + return EPOLLIN | EPOLLOUT | EPOLLERR | EPOLLHUP | EPOLLRDNORM | EPOLLWRNORM; } static long hung_up_tty_ioctl(struct file *file, unsigned int cmd, @@ -533,7 +533,7 @@ void tty_wakeup(struct tty_struct *tty) tty_ldisc_deref(ld); } } - wake_up_interruptible_poll(&tty->write_wait, POLLOUT); + wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); } EXPORT_SYMBOL_GPL(tty_wakeup); @@ -867,7 +867,7 @@ static ssize_t tty_read(struct file *file, char __user *buf, size_t count, static void tty_write_unlock(struct tty_struct *tty) { mutex_unlock(&tty->atomic_write_lock); - wake_up_interruptible_poll(&tty->write_wait, POLLOUT); + wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); } static int tty_write_lock(struct tty_struct *tty, int ndelay) @@ -1667,21 +1667,21 @@ int tty_release(struct inode *inode, struct file *filp) if (tty->count <= 1) { if (waitqueue_active(&tty->read_wait)) { - wake_up_poll(&tty->read_wait, POLLIN); + wake_up_poll(&tty->read_wait, EPOLLIN); do_sleep++; } if (waitqueue_active(&tty->write_wait)) { - wake_up_poll(&tty->write_wait, POLLOUT); + wake_up_poll(&tty->write_wait, EPOLLOUT); do_sleep++; } } if (o_tty && o_tty->count <= 1) { if (waitqueue_active(&o_tty->read_wait)) { - wake_up_poll(&o_tty->read_wait, POLLIN); + wake_up_poll(&o_tty->read_wait, EPOLLIN); do_sleep++; } if (waitqueue_active(&o_tty->write_wait)) { - wake_up_poll(&o_tty->write_wait, POLLOUT); + wake_up_poll(&o_tty->write_wait, EPOLLOUT); do_sleep++; } } diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 4e7946c0484b..050f4d650891 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -735,8 +735,8 @@ void tty_ldisc_hangup(struct tty_struct *tty, bool reinit) tty_ldisc_deref(ld); } - wake_up_interruptible_poll(&tty->write_wait, POLLOUT); - wake_up_interruptible_poll(&tty->read_wait, POLLIN); + wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); + wake_up_interruptible_poll(&tty->read_wait, EPOLLIN); /* * Shutdown the current line discipline, and reset it to diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 3e64ccd0040f..e4a66e1fd05f 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -563,7 +563,7 @@ static __poll_t vcs_poll(struct file *file, poll_table *wait) { struct vcs_poll_data *poll = vcs_poll_data_get(file); - __poll_t ret = DEFAULT_POLLMASK|POLLERR|POLLPRI; + __poll_t ret = DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (poll) { poll_wait(file, &poll->waitq, wait); diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 85bc1aaea4a4..fd4848392e0d 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -506,7 +506,7 @@ static __poll_t uio_poll(struct file *filep, poll_table *wait) poll_wait(filep, &idev->wait, wait); if (listener->event_count != atomic_read(&idev->event)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 9627ea6ec3ae..a0d284ef3f40 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -603,16 +603,16 @@ static __poll_t wdm_poll(struct file *file, struct poll_table_struct *wait) spin_lock_irqsave(&desc->iuspin, flags); if (test_bit(WDM_DISCONNECTING, &desc->flags)) { - mask = POLLHUP | POLLERR; + mask = EPOLLHUP | EPOLLERR; spin_unlock_irqrestore(&desc->iuspin, flags); goto desc_out; } if (test_bit(WDM_READ, &desc->flags)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; if (desc->rerr || desc->werr) - mask |= POLLERR; + mask |= EPOLLERR; if (!test_bit(WDM_IN_USE, &desc->flags)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; spin_unlock_irqrestore(&desc->iuspin, flags); poll_wait(file, &desc->wait, wait); diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 425247b7f728..d058d7a31e7c 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -479,8 +479,8 @@ static __poll_t usblp_poll(struct file *file, struct poll_table_struct *wait) poll_wait(file, &usblp->rwait, wait); poll_wait(file, &usblp->wwait, wait); spin_lock_irqsave(&usblp->lock, flags); - ret = ((usblp->bidir && usblp->rcomplete) ? POLLIN | POLLRDNORM : 0) | - ((usblp->no_paper || usblp->wcomplete) ? POLLOUT | POLLWRNORM : 0); + ret = ((usblp->bidir && usblp->rcomplete) ? EPOLLIN | EPOLLRDNORM : 0) | + ((usblp->no_paper || usblp->wcomplete) ? EPOLLOUT | EPOLLWRNORM : 0); spin_unlock_irqrestore(&usblp->lock, flags); return ret; } diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 7ea67a55be10..bdb1de0c0cef 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1265,13 +1265,13 @@ static __poll_t usbtmc_poll(struct file *file, poll_table *wait) mutex_lock(&data->io_mutex); if (data->zombie) { - mask = POLLHUP | POLLERR; + mask = EPOLLHUP | EPOLLERR; goto no_poll; } poll_wait(file, &data->waitq, wait); - mask = (atomic_read(&data->srq_asserted)) ? POLLIN | POLLRDNORM : 0; + mask = (atomic_read(&data->srq_asserted)) ? EPOLLIN | EPOLLRDNORM : 0; no_poll: mutex_unlock(&data->io_mutex); diff --git a/drivers/usb/core/devices.c b/drivers/usb/core/devices.c index e2cec448779e..3de3c750b5f6 100644 --- a/drivers/usb/core/devices.c +++ b/drivers/usb/core/devices.c @@ -632,7 +632,7 @@ static __poll_t usb_device_poll(struct file *file, event_count = atomic_read(&device_event.count); if (file->f_version != event_count) { file->f_version = event_count; - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } return 0; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index bf00166cbee0..d526595bc959 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -2578,11 +2578,11 @@ static __poll_t usbdev_poll(struct file *file, poll_wait(file, &ps->wait, wait); if (file->f_mode & FMODE_WRITE && !list_empty(&ps->async_completed)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; if (!connected(ps)) - mask |= POLLHUP; + mask |= EPOLLHUP; if (list_empty(&ps->list)) - mask |= POLLERR; + mask |= EPOLLERR; return mask; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 67564725e371..8f2cf3baa19c 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -644,7 +644,7 @@ static long ffs_ep0_ioctl(struct file *file, unsigned code, unsigned long value) static __poll_t ffs_ep0_poll(struct file *file, poll_table *wait) { struct ffs_data *ffs = file->private_data; - __poll_t mask = POLLWRNORM; + __poll_t mask = EPOLLWRNORM; int ret; poll_wait(file, &ffs->ev.waitq, wait); @@ -656,19 +656,19 @@ static __poll_t ffs_ep0_poll(struct file *file, poll_table *wait) switch (ffs->state) { case FFS_READ_DESCRIPTORS: case FFS_READ_STRINGS: - mask |= POLLOUT; + mask |= EPOLLOUT; break; case FFS_ACTIVE: switch (ffs->setup_state) { case FFS_NO_SETUP: if (ffs->ev.count) - mask |= POLLIN; + mask |= EPOLLIN; break; case FFS_SETUP_PENDING: case FFS_SETUP_CANCELLED: - mask |= (POLLIN | POLLOUT); + mask |= (EPOLLIN | EPOLLOUT); break; } case FFS_CLOSING: diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index a73efb1c47d0..54e859dcb25c 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -422,10 +422,10 @@ static __poll_t f_hidg_poll(struct file *file, poll_table *wait) poll_wait(file, &hidg->write_queue, wait); if (WRITE_COND) - ret |= POLLOUT | POLLWRNORM; + ret |= EPOLLOUT | EPOLLWRNORM; if (READ_COND) - ret |= POLLIN | POLLRDNORM; + ret |= EPOLLIN | EPOLLRDNORM; return ret; } diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 453578c4af69..d359efe06c76 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -698,11 +698,11 @@ printer_poll(struct file *fd, poll_table *wait) spin_lock_irqsave(&dev->lock, flags); if (likely(!list_empty(&dev->tx_reqs))) - status |= POLLOUT | POLLWRNORM; + status |= EPOLLOUT | EPOLLWRNORM; if (likely(dev->current_rx_bytes) || likely(!list_empty(&dev->rx_buffers))) - status |= POLLIN | POLLRDNORM; + status |= EPOLLIN | EPOLLRDNORM; spin_unlock_irqrestore(&dev->lock, flags); diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 5960e76f4c75..37ca0e669bd8 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1225,16 +1225,16 @@ ep0_poll (struct file *fd, poll_table *wait) /* report fd mode change before acting on it */ if (dev->setup_abort) { dev->setup_abort = 0; - mask = POLLHUP; + mask = EPOLLHUP; goto out; } if (dev->state == STATE_DEV_SETUP) { if (dev->setup_in || dev->setup_can_stall) - mask = POLLOUT; + mask = EPOLLOUT; } else { if (dev->ev_next != 0) - mask = POLLIN; + mask = EPOLLIN; } out: spin_unlock_irq(&dev->lock); diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index 1fa00b35f4ad..8d33187ce2af 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -683,19 +683,19 @@ static __poll_t iowarrior_poll(struct file *file, poll_table * wait) __poll_t mask = 0; if (!dev->present) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; poll_wait(file, &dev->read_wait, wait); poll_wait(file, &dev->write_wait, wait); if (!dev->present) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; if (read_index(dev) != -1) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (atomic_read(&dev->write_busy) < MAX_WRITES_IN_FLIGHT) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index 074398c1e410..63b9e85dc0e9 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -417,15 +417,15 @@ static __poll_t ld_usb_poll(struct file *file, poll_table *wait) dev = file->private_data; if (!dev->intf) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; poll_wait(file, &dev->read_wait, wait); poll_wait(file, &dev->write_wait, wait); if (dev->ring_head != dev->ring_tail) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (!dev->interrupt_out_busy) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c index 941c45028828..bf47bd8bc76f 100644 --- a/drivers/usb/misc/legousbtower.c +++ b/drivers/usb/misc/legousbtower.c @@ -517,17 +517,17 @@ static __poll_t tower_poll (struct file *file, poll_table *wait) dev = file->private_data; if (!dev->udev) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; poll_wait(file, &dev->read_wait, wait); poll_wait(file, &dev->write_wait, wait); tower_check_for_read_packet(dev); if (dev->read_packet_length > 0) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } if (!dev->interrupt_out_busy) { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } return mask; diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index cc5b296bff3f..2761fad66b95 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1203,7 +1203,7 @@ mon_bin_poll(struct file *file, struct poll_table_struct *wait) spin_lock_irqsave(&rp->b_lock, flags); if (!MON_RING_EMPTY(rp)) - mask |= POLLIN | POLLRDNORM; /* readable */ + mask |= EPOLLIN | EPOLLRDNORM; /* readable */ spin_unlock_irqrestore(&rp->b_lock, flags); return mask; } diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 8cc4b48ff127..085700f1be10 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -48,7 +48,7 @@ static int virqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void struct virqfd *virqfd = container_of(wait, struct virqfd, wait); __poll_t flags = key_to_poll(key); - if (flags & POLLIN) { + if (flags & EPOLLIN) { /* An event has been signaled, call function */ if ((!virqfd->handler || virqfd->handler(virqfd->opaque, virqfd->data)) && @@ -56,7 +56,7 @@ static int virqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void schedule_work(&virqfd->inject); } - if (flags & POLLHUP) { + if (flags & EPOLLHUP) { unsigned long flags; spin_lock_irqsave(&virqfd_lock, flags); @@ -172,14 +172,14 @@ int vfio_virqfd_enable(void *opaque, * Check if there was an event already pending on the eventfd * before we registered and trigger it as if we didn't miss it. */ - if (events & POLLIN) { + if (events & EPOLLIN) { if ((!handler || handler(opaque, data)) && thread) schedule_work(&virqfd->inject); } /* * Do not drop the file until the irqfd is fully initialized, - * otherwise we might race against the POLLHUP. + * otherwise we might race against the EPOLLHUP. */ fdput(irqfd); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 9c3f8160ef24..610cba276d47 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -952,8 +952,8 @@ static int vhost_net_open(struct inode *inode, struct file *f) } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); - vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev); - vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev); + vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); + vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); f->private_data = n; @@ -1015,7 +1015,7 @@ static int vhost_net_release(struct inode *inode, struct file *f) vhost_net_stop(n, &tx_sock, &rx_sock); vhost_net_flush(n); vhost_dev_stop(&n->dev); - vhost_dev_cleanup(&n->dev, false); + vhost_dev_cleanup(&n->dev); vhost_net_vq_reset(n); if (tx_sock) sockfd_put(tx_sock); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 71517b3c5558..7ad57094d736 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -586,8 +586,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, sg = cmd->tvc_sgl; prot_sg = cmd->tvc_prot_sgl; pages = cmd->tvc_upages; - memset(cmd, 0, sizeof(struct vhost_scsi_cmd)); - + memset(cmd, 0, sizeof(*cmd)); cmd->tvc_sgl = sg; cmd->tvc_prot_sgl = prot_sg; cmd->tvc_upages = pages; @@ -1420,7 +1419,7 @@ static int vhost_scsi_release(struct inode *inode, struct file *f) mutex_unlock(&vs->dev.mutex); vhost_scsi_clear_endpoint(vs, &t); vhost_dev_stop(&vs->dev); - vhost_dev_cleanup(&vs->dev, false); + vhost_dev_cleanup(&vs->dev); /* Jobs can re-queue themselves in evt kick handler. Do extra flush. */ vhost_scsi_flush(vs); kfree(vs->dev.vqs); @@ -1725,7 +1724,7 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, return -EEXIST; } - tv_nexus = kzalloc(sizeof(struct vhost_scsi_nexus), GFP_KERNEL); + tv_nexus = kzalloc(sizeof(*tv_nexus), GFP_KERNEL); if (!tv_nexus) { mutex_unlock(&tpg->tv_tpg_mutex); pr_err("Unable to allocate struct vhost_scsi_nexus\n"); @@ -1926,7 +1925,7 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, if (kstrtou16(name + 5, 10, &tpgt) || tpgt >= VHOST_SCSI_MAX_TARGET) return ERR_PTR(-EINVAL); - tpg = kzalloc(sizeof(struct vhost_scsi_tpg), GFP_KERNEL); + tpg = kzalloc(sizeof(*tpg), GFP_KERNEL); if (!tpg) { pr_err("Unable to allocate struct vhost_scsi_tpg"); return ERR_PTR(-ENOMEM); @@ -1980,7 +1979,7 @@ vhost_scsi_make_tport(struct target_fabric_configfs *tf, /* if (vhost_scsi_parse_wwn(name, &wwpn, 1) < 0) return ERR_PTR(-EINVAL); */ - tport = kzalloc(sizeof(struct vhost_scsi_tport), GFP_KERNEL); + tport = kzalloc(sizeof(*tport), GFP_KERNEL); if (!tport) { pr_err("Unable to allocate struct vhost_scsi_tport"); return ERR_PTR(-ENOMEM); diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 3cc98c07dcd3..906b8f0f19f7 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -157,7 +157,7 @@ static int vhost_test_release(struct inode *inode, struct file *f) vhost_test_stop(n, &private); vhost_test_flush(n); - vhost_dev_cleanup(&n->dev, false); + vhost_dev_cleanup(&n->dev); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ vhost_test_flush(n); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 8d4374606756..1b3e8d2d5c8b 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -181,7 +181,6 @@ void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn) { clear_bit(VHOST_WORK_QUEUED, &work->flags); work->fn = fn; - init_waitqueue_head(&work->done); } EXPORT_SYMBOL_GPL(vhost_work_init); @@ -212,7 +211,7 @@ int vhost_poll_start(struct vhost_poll *poll, struct file *file) mask = file->f_op->poll(file, &poll->table); if (mask) vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask)); - if (mask & POLLERR) { + if (mask & EPOLLERR) { if (poll->wqh) remove_wait_queue(poll->wqh, &poll->wait); ret = -EINVAL; @@ -319,10 +318,8 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->acked_features = 0; vq->log_base = NULL; vq->error_ctx = NULL; - vq->error = NULL; vq->kick = NULL; vq->call_ctx = NULL; - vq->call = NULL; vq->log_ctx = NULL; vhost_reset_is_le(vq); vhost_disable_cross_endian(vq); @@ -422,7 +419,6 @@ void vhost_dev_init(struct vhost_dev *dev, dev->nvqs = nvqs; mutex_init(&dev->mutex); dev->log_ctx = NULL; - dev->log_file = NULL; dev->umem = NULL; dev->iotlb = NULL; dev->mm = NULL; @@ -444,7 +440,7 @@ void vhost_dev_init(struct vhost_dev *dev, vhost_vq_reset(dev, vq); if (vq->handle_kick) vhost_poll_init(&vq->poll, vq->handle_kick, - POLLIN, dev); + EPOLLIN, dev); } } EXPORT_SYMBOL_GPL(vhost_dev_init); @@ -544,7 +540,7 @@ void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_umem *umem) { int i; - vhost_dev_cleanup(dev, true); + vhost_dev_cleanup(dev); /* Restore memory to default empty mapping. */ INIT_LIST_HEAD(&umem->umem_list); @@ -611,38 +607,30 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } -/* Caller should have device mutex if and only if locked is set */ -void vhost_dev_cleanup(struct vhost_dev *dev, bool locked) +void vhost_dev_cleanup(struct vhost_dev *dev) { int i; for (i = 0; i < dev->nvqs; ++i) { if (dev->vqs[i]->error_ctx) eventfd_ctx_put(dev->vqs[i]->error_ctx); - if (dev->vqs[i]->error) - fput(dev->vqs[i]->error); if (dev->vqs[i]->kick) fput(dev->vqs[i]->kick); if (dev->vqs[i]->call_ctx) eventfd_ctx_put(dev->vqs[i]->call_ctx); - if (dev->vqs[i]->call) - fput(dev->vqs[i]->call); vhost_vq_reset(dev, dev->vqs[i]); } vhost_dev_free_iovecs(dev); if (dev->log_ctx) eventfd_ctx_put(dev->log_ctx); dev->log_ctx = NULL; - if (dev->log_file) - fput(dev->log_file); - dev->log_file = NULL; /* No one will access memory at this point */ vhost_umem_clean(dev->umem); dev->umem = NULL; vhost_umem_clean(dev->iotlb); dev->iotlb = NULL; vhost_clear_msg(dev); - wake_up_interruptible_poll(&dev->wait, POLLIN | POLLRDNORM); + wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM); WARN_ON(!llist_empty(&dev->work_list)); if (dev->worker) { kthread_stop(dev->worker); @@ -1069,7 +1057,7 @@ __poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev, poll_wait(file, &dev->wait, wait); if (!list_empty(&dev->read_list)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } @@ -1492,38 +1480,24 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) r = -EFAULT; break; } - eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd); - if (IS_ERR(eventfp)) { - r = PTR_ERR(eventfp); + ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd); + if (IS_ERR(ctx)) { + r = PTR_ERR(ctx); break; } - if (eventfp != vq->call) { - filep = vq->call; - ctx = vq->call_ctx; - vq->call = eventfp; - vq->call_ctx = eventfp ? - eventfd_ctx_fileget(eventfp) : NULL; - } else - filep = eventfp; + swap(ctx, vq->call_ctx); break; case VHOST_SET_VRING_ERR: if (copy_from_user(&f, argp, sizeof f)) { r = -EFAULT; break; } - eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd); - if (IS_ERR(eventfp)) { - r = PTR_ERR(eventfp); + ctx = f.fd == -1 ? NULL : eventfd_ctx_fdget(f.fd); + if (IS_ERR(ctx)) { + r = PTR_ERR(ctx); break; } - if (eventfp != vq->error) { - filep = vq->error; - vq->error = eventfp; - ctx = vq->error_ctx; - vq->error_ctx = eventfp ? - eventfd_ctx_fileget(eventfp) : NULL; - } else - filep = eventfp; + swap(ctx, vq->error_ctx); break; case VHOST_SET_VRING_ENDIAN: r = vhost_set_vring_endian(vq, argp); @@ -1551,7 +1525,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) if (pollstop && vq->handle_kick) vhost_poll_stop(&vq->poll); - if (ctx) + if (!IS_ERR_OR_NULL(ctx)) eventfd_ctx_put(ctx); if (filep) fput(filep); @@ -1594,8 +1568,7 @@ EXPORT_SYMBOL_GPL(vhost_init_device_iotlb); /* Caller must have device mutex */ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) { - struct file *eventfp, *filep = NULL; - struct eventfd_ctx *ctx = NULL; + struct eventfd_ctx *ctx; u64 p; long r; int i, fd; @@ -1641,19 +1614,12 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) r = get_user(fd, (int __user *)argp); if (r < 0) break; - eventfp = fd == -1 ? NULL : eventfd_fget(fd); - if (IS_ERR(eventfp)) { - r = PTR_ERR(eventfp); + ctx = fd == -1 ? NULL : eventfd_ctx_fdget(fd); + if (IS_ERR(ctx)) { + r = PTR_ERR(ctx); break; } - if (eventfp != d->log_file) { - filep = d->log_file; - d->log_file = eventfp; - ctx = d->log_ctx; - d->log_ctx = eventfp ? - eventfd_ctx_fileget(eventfp) : NULL; - } else - filep = eventfp; + swap(ctx, d->log_ctx); for (i = 0; i < d->nvqs; ++i) { mutex_lock(&d->vqs[i]->mutex); d->vqs[i]->log_ctx = d->log_ctx; @@ -1661,8 +1627,6 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) } if (ctx) eventfd_ctx_put(ctx); - if (filep) - fput(filep); break; default: r = -ENOIOCTLCMD; @@ -2392,7 +2356,7 @@ void vhost_enqueue_msg(struct vhost_dev *dev, struct list_head *head, list_add_tail(&node->node, head); spin_unlock(&dev->iotlb_lock); - wake_up_interruptible_poll(&dev->wait, POLLIN | POLLRDNORM); + wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM); } EXPORT_SYMBOL_GPL(vhost_enqueue_msg); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 7876a3d7d1b3..ac4b6056f19a 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -20,10 +20,6 @@ typedef void (*vhost_work_fn_t)(struct vhost_work *work); struct vhost_work { struct llist_node node; vhost_work_fn_t fn; - wait_queue_head_t done; - int flushing; - unsigned queue_seq; - unsigned done_seq; unsigned long flags; }; @@ -96,8 +92,6 @@ struct vhost_virtqueue { struct vring_used __user *used; const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS]; struct file *kick; - struct file *call; - struct file *error; struct eventfd_ctx *call_ctx; struct eventfd_ctx *error_ctx; struct eventfd_ctx *log_ctx; @@ -163,7 +157,6 @@ struct vhost_dev { struct mutex mutex; struct vhost_virtqueue **vqs; int nvqs; - struct file *log_file; struct eventfd_ctx *log_ctx; struct llist_head work_list; struct task_struct *worker; @@ -181,7 +174,7 @@ bool vhost_dev_has_owner(struct vhost_dev *dev); long vhost_dev_check_owner(struct vhost_dev *); struct vhost_umem *vhost_dev_reset_owner_prepare(void); void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *); -void vhost_dev_cleanup(struct vhost_dev *, bool locked); +void vhost_dev_cleanup(struct vhost_dev *); void vhost_dev_stop(struct vhost_dev *); long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp); long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 5a5e981bd8e4..0d14e2ff19f1 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -599,7 +599,7 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file) } spin_unlock_bh(&vsock->send_pkt_list_lock); - vhost_dev_cleanup(&vsock->dev, false); + vhost_dev_cleanup(&vsock->dev); kfree(vsock->dev.vqs); vhost_vsock_free(vsock); return 0; diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c index 9269d5685239..b90ef96e43d6 100644 --- a/drivers/video/console/dummycon.c +++ b/drivers/video/console/dummycon.c @@ -67,7 +67,6 @@ const struct consw dummy_con = { .con_switch = DUMMY, .con_blank = DUMMY, .con_font_set = DUMMY, - .con_font_get = DUMMY, .con_font_default = DUMMY, .con_font_copy = DUMMY, }; diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 2566cfbdebfb..11e699f1062b 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -1156,7 +1156,6 @@ config FB_I810_I2C bool "Enable DDC Support" depends on FB_I810 && FB_I810_GTF select FB_DDC - help config FB_LE80578 tristate "Intel LE80578 (Vermilion) support" @@ -1188,7 +1187,7 @@ config FB_INTEL 830M/845G/852GM/855GM/865G/915G/915GM/945G/945GM/965G/965GM chipsets. Say Y if you have and plan to use such a board. - To make FB_INTELFB=Y work you need to say AGP_INTEL=y too. + To make FB_INTEL=Y work you need to say AGP_INTEL=y too. To compile this driver as a module, choose M here: the module will be called intelfb. diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index e06358da4b99..3dee267d7c75 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -1119,7 +1119,7 @@ static int atmel_lcdfb_of_init(struct atmel_lcdfb_info *sinfo) goto put_display_node; } - timings_np = of_find_node_by_name(display_np, "display-timings"); + timings_np = of_get_child_by_name(display_np, "display-timings"); if (!timings_np) { dev_err(dev, "failed to find display-timings node\n"); ret = -ENODEV; @@ -1140,6 +1140,12 @@ static int atmel_lcdfb_of_init(struct atmel_lcdfb_info *sinfo) fb_add_videomode(&fb_vm, &info->modelist); } + /* + * FIXME: Make sure we are not referencing any fields in display_np + * and timings_np and drop our references to them before returning to + * avoid leaking the nodes on probe deferral and driver unbind. + */ + return 0; put_timings_node: diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c index 4d77daeecf99..87608c0b2351 100644 --- a/drivers/video/fbdev/aty/radeon_base.c +++ b/drivers/video/fbdev/aty/radeon_base.c @@ -583,8 +583,8 @@ static int radeon_probe_pll_params(struct radeonfb_info *rinfo) int hTotal, vTotal, num, denom, m, n; unsigned long long hz, vclk; long xtal; - struct timeval start_tv, stop_tv; - long total_secs, total_usecs; + ktime_t start_time, stop_time; + u64 total_usecs; int i; /* Ugh, we cut interrupts, bad bad bad, but we want some precision @@ -600,7 +600,7 @@ static int radeon_probe_pll_params(struct radeonfb_info *rinfo) if (((INREG(CRTC_VLINE_CRNT_VLINE) >> 16) & 0x3ff) == 0) break; - do_gettimeofday(&start_tv); + start_time = ktime_get(); for(i=0; i<1000000; i++) if (((INREG(CRTC_VLINE_CRNT_VLINE) >> 16) & 0x3ff) != 0) @@ -610,18 +610,14 @@ static int radeon_probe_pll_params(struct radeonfb_info *rinfo) if (((INREG(CRTC_VLINE_CRNT_VLINE) >> 16) & 0x3ff) == 0) break; - do_gettimeofday(&stop_tv); + stop_time = ktime_get(); local_irq_enable(); - total_secs = stop_tv.tv_sec - start_tv.tv_sec; - if (total_secs > 10) + total_usecs = ktime_us_delta(stop_time, start_time); + if (total_usecs >= 10 * USEC_PER_SEC || total_usecs == 0) return -1; - total_usecs = stop_tv.tv_usec - start_tv.tv_usec; - total_usecs += total_secs * 1000000; - if (total_usecs < 0) - total_usecs = -total_usecs; - hz = 1000000/total_usecs; + hz = USEC_PER_SEC/(u32)total_usecs; hTotal = ((INREG(CRTC_H_TOTAL_DISP) & 0x1ff) + 1) * 8; vTotal = ((INREG(CRTC_V_TOTAL_DISP) & 0x3ff) + 1); diff --git a/drivers/video/fbdev/au1200fb.h b/drivers/video/fbdev/au1200fb.h index e2672714d8d4..b34fff342a1a 100644 --- a/drivers/video/fbdev/au1200fb.h +++ b/drivers/video/fbdev/au1200fb.h @@ -284,289 +284,3 @@ struct au1200_lcd { /********************************************************************/ #endif /* _AU1200LCD_H */ -/* - * BRIEF MODULE DESCRIPTION - * Hardware definitions for the Au1200 LCD controller - * - * Copyright 2004 AMD - * Author: AMD - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN - * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, - * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT - * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF - * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON - * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF - * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef _AU1200LCD_H -#define _AU1200LCD_H - -/********************************************************************/ -#define AU1200_LCD_ADDR 0xB5000000 - -#define uint8 unsigned char -#define uint32 unsigned int - -struct au1200_lcd { - volatile uint32 reserved0; - volatile uint32 screen; - volatile uint32 backcolor; - volatile uint32 horztiming; - volatile uint32 verttiming; - volatile uint32 clkcontrol; - volatile uint32 pwmdiv; - volatile uint32 pwmhi; - volatile uint32 reserved1; - volatile uint32 winenable; - volatile uint32 colorkey; - volatile uint32 colorkeymsk; - struct - { - volatile uint32 cursorctrl; - volatile uint32 cursorpos; - volatile uint32 cursorcolor0; - volatile uint32 cursorcolor1; - volatile uint32 cursorcolor2; - uint32 cursorcolor3; - } hwc; - volatile uint32 intstatus; - volatile uint32 intenable; - volatile uint32 outmask; - volatile uint32 fifoctrl; - uint32 reserved2[(0x0100-0x0058)/4]; - struct - { - volatile uint32 winctrl0; - volatile uint32 winctrl1; - volatile uint32 winctrl2; - volatile uint32 winbuf0; - volatile uint32 winbuf1; - volatile uint32 winbufctrl; - uint32 winreserved0; - uint32 winreserved1; - } window[4]; - - uint32 reserved3[(0x0400-0x0180)/4]; - - volatile uint32 palette[(0x0800-0x0400)/4]; - - volatile uint8 cursorpattern[256]; -}; - -/* lcd_screen */ -#define LCD_SCREEN_SEN (1<<31) -#define LCD_SCREEN_SX (0x07FF<<19) -#define LCD_SCREEN_SY (0x07FF<< 8) -#define LCD_SCREEN_SWP (1<<7) -#define LCD_SCREEN_SWD (1<<6) -#define LCD_SCREEN_PT (7<<0) -#define LCD_SCREEN_PT_TFT (0<<0) -#define LCD_SCREEN_SX_N(WIDTH) ((WIDTH-1)<<19) -#define LCD_SCREEN_SY_N(HEIGHT) ((HEIGHT-1)<<8) -#define LCD_SCREEN_PT_CSTN (1<<0) -#define LCD_SCREEN_PT_CDSTN (2<<0) -#define LCD_SCREEN_PT_M8STN (3<<0) -#define LCD_SCREEN_PT_M4STN (4<<0) - -/* lcd_backcolor */ -#define LCD_BACKCOLOR_SBGR (0xFF<<16) -#define LCD_BACKCOLOR_SBGG (0xFF<<8) -#define LCD_BACKCOLOR_SBGB (0xFF<<0) -#define LCD_BACKCOLOR_SBGR_N(N) ((N)<<16) -#define LCD_BACKCOLOR_SBGG_N(N) ((N)<<8) -#define LCD_BACKCOLOR_SBGB_N(N) ((N)<<0) - -/* lcd_winenable */ -#define LCD_WINENABLE_WEN3 (1<<3) -#define LCD_WINENABLE_WEN2 (1<<2) -#define LCD_WINENABLE_WEN1 (1<<1) -#define LCD_WINENABLE_WEN0 (1<<0) - -/* lcd_colorkey */ -#define LCD_COLORKEY_CKR (0xFF<<16) -#define LCD_COLORKEY_CKG (0xFF<<8) -#define LCD_COLORKEY_CKB (0xFF<<0) -#define LCD_COLORKEY_CKR_N(N) ((N)<<16) -#define LCD_COLORKEY_CKG_N(N) ((N)<<8) -#define LCD_COLORKEY_CKB_N(N) ((N)<<0) - -/* lcd_colorkeymsk */ -#define LCD_COLORKEYMSK_CKMR (0xFF<<16) -#define LCD_COLORKEYMSK_CKMG (0xFF<<8) -#define LCD_COLORKEYMSK_CKMB (0xFF<<0) -#define LCD_COLORKEYMSK_CKMR_N(N) ((N)<<16) -#define LCD_COLORKEYMSK_CKMG_N(N) ((N)<<8) -#define LCD_COLORKEYMSK_CKMB_N(N) ((N)<<0) - -/* lcd windows control 0 */ -#define LCD_WINCTRL0_OX (0x07FF<<21) -#define LCD_WINCTRL0_OY (0x07FF<<10) -#define LCD_WINCTRL0_A (0x00FF<<2) -#define LCD_WINCTRL0_AEN (1<<1) -#define LCD_WINCTRL0_OX_N(N) ((N)<<21) -#define LCD_WINCTRL0_OY_N(N) ((N)<<10) -#define LCD_WINCTRL0_A_N(N) ((N)<<2) - -/* lcd windows control 1 */ -#define LCD_WINCTRL1_PRI (3<<30) -#define LCD_WINCTRL1_PIPE (1<<29) -#define LCD_WINCTRL1_FRM (0xF<<25) -#define LCD_WINCTRL1_CCO (1<<24) -#define LCD_WINCTRL1_PO (3<<22) -#define LCD_WINCTRL1_SZX (0x07FF<<11) -#define LCD_WINCTRL1_SZY (0x07FF<<0) -#define LCD_WINCTRL1_FRM_1BPP (0<<25) -#define LCD_WINCTRL1_FRM_2BPP (1<<25) -#define LCD_WINCTRL1_FRM_4BPP (2<<25) -#define LCD_WINCTRL1_FRM_8BPP (3<<25) -#define LCD_WINCTRL1_FRM_12BPP (4<<25) -#define LCD_WINCTRL1_FRM_16BPP655 (5<<25) -#define LCD_WINCTRL1_FRM_16BPP565 (6<<25) -#define LCD_WINCTRL1_FRM_16BPP556 (7<<25) -#define LCD_WINCTRL1_FRM_16BPPI1555 (8<<25) -#define LCD_WINCTRL1_FRM_16BPPI5551 (9<<25) -#define LCD_WINCTRL1_FRM_16BPPA1555 (10<<25) -#define LCD_WINCTRL1_FRM_16BPPA5551 (11<<25) -#define LCD_WINCTRL1_FRM_24BPP (12<<25) -#define LCD_WINCTRL1_FRM_32BPP (13<<25) -#define LCD_WINCTRL1_PRI_N(N) ((N)<<30) -#define LCD_WINCTRL1_PO_00 (0<<22) -#define LCD_WINCTRL1_PO_01 (1<<22) -#define LCD_WINCTRL1_PO_10 (2<<22) -#define LCD_WINCTRL1_PO_11 (3<<22) -#define LCD_WINCTRL1_SZX_N(N) ((N-1)<<11) -#define LCD_WINCTRL1_SZY_N(N) ((N-1)<<0) - -/* lcd windows control 2 */ -#define LCD_WINCTRL2_CKMODE (3<<24) -#define LCD_WINCTRL2_DBM (1<<23) -#define LCD_WINCTRL2_RAM (3<<21) -#define LCD_WINCTRL2_BX (0x1FFF<<8) -#define LCD_WINCTRL2_SCX (0xF<<4) -#define LCD_WINCTRL2_SCY (0xF<<0) -#define LCD_WINCTRL2_CKMODE_00 (0<<24) -#define LCD_WINCTRL2_CKMODE_01 (1<<24) -#define LCD_WINCTRL2_CKMODE_10 (2<<24) -#define LCD_WINCTRL2_CKMODE_11 (3<<24) -#define LCD_WINCTRL2_RAM_NONE (0<<21) -#define LCD_WINCTRL2_RAM_PALETTE (1<<21) -#define LCD_WINCTRL2_RAM_GAMMA (2<<21) -#define LCD_WINCTRL2_RAM_BUFFER (3<<21) -#define LCD_WINCTRL2_BX_N(N) ((N)<<8) -#define LCD_WINCTRL2_SCX_1 (0<<4) -#define LCD_WINCTRL2_SCX_2 (1<<4) -#define LCD_WINCTRL2_SCX_4 (2<<4) -#define LCD_WINCTRL2_SCY_1 (0<<0) -#define LCD_WINCTRL2_SCY_2 (1<<0) -#define LCD_WINCTRL2_SCY_4 (2<<0) - -/* lcd windows buffer control */ -#define LCD_WINBUFCTRL_DB (1<<1) -#define LCD_WINBUFCTRL_DBN (1<<0) - -/* lcd_intstatus, lcd_intenable */ -#define LCD_INT_IFO (0xF<<14) -#define LCD_INT_IFU (0xF<<10) -#define LCD_INT_OFO (1<<9) -#define LCD_INT_OFU (1<<8) -#define LCD_INT_WAIT (1<<3) -#define LCD_INT_SD (1<<2) -#define LCD_INT_SA (1<<1) -#define LCD_INT_SS (1<<0) - -/* lcd_horztiming */ -#define LCD_HORZTIMING_HND2 (0x1FF<<18) -#define LCD_HORZTIMING_HND1 (0x1FF<<9) -#define LCD_HORZTIMING_HPW (0x1FF<<0) -#define LCD_HORZTIMING_HND2_N(N)(((N)-1)<<18) -#define LCD_HORZTIMING_HND1_N(N)(((N)-1)<<9) -#define LCD_HORZTIMING_HPW_N(N) (((N)-1)<<0) - -/* lcd_verttiming */ -#define LCD_VERTTIMING_VND2 (0x1FF<<18) -#define LCD_VERTTIMING_VND1 (0x1FF<<9) -#define LCD_VERTTIMING_VPW (0x1FF<<0) -#define LCD_VERTTIMING_VND2_N(N)(((N)-1)<<18) -#define LCD_VERTTIMING_VND1_N(N)(((N)-1)<<9) -#define LCD_VERTTIMING_VPW_N(N) (((N)-1)<<0) - -/* lcd_clkcontrol */ -#define LCD_CLKCONTROL_EXT (1<<22) -#define LCD_CLKCONTROL_DELAY (3<<20) -#define LCD_CLKCONTROL_CDD (1<<19) -#define LCD_CLKCONTROL_IB (1<<18) -#define LCD_CLKCONTROL_IC (1<<17) -#define LCD_CLKCONTROL_IH (1<<16) -#define LCD_CLKCONTROL_IV (1<<15) -#define LCD_CLKCONTROL_BF (0x1F<<10) -#define LCD_CLKCONTROL_PCD (0x3FF<<0) -#define LCD_CLKCONTROL_BF_N(N) (((N)-1)<<10) -#define LCD_CLKCONTROL_PCD_N(N) ((N)<<0) - -/* lcd_pwmdiv */ -#define LCD_PWMDIV_EN (1<<31) -#define LCD_PWMDIV_PWMDIV (0x1FFFF<<0) -#define LCD_PWMDIV_PWMDIV_N(N) ((N)<<0) - -/* lcd_pwmhi */ -#define LCD_PWMHI_PWMHI1 (0xFFFF<<16) -#define LCD_PWMHI_PWMHI0 (0xFFFF<<0) -#define LCD_PWMHI_PWMHI1_N(N) ((N)<<16) -#define LCD_PWMHI_PWMHI0_N(N) ((N)<<0) - -/* lcd_hwccon */ -#define LCD_HWCCON_EN (1<<0) - -/* lcd_cursorpos */ -#define LCD_CURSORPOS_HWCXOFF (0x1F<<27) -#define LCD_CURSORPOS_HWCXPOS (0x07FF<<16) -#define LCD_CURSORPOS_HWCYOFF (0x1F<<11) -#define LCD_CURSORPOS_HWCYPOS (0x07FF<<0) -#define LCD_CURSORPOS_HWCXOFF_N(N) ((N)<<27) -#define LCD_CURSORPOS_HWCXPOS_N(N) ((N)<<16) -#define LCD_CURSORPOS_HWCYOFF_N(N) ((N)<<11) -#define LCD_CURSORPOS_HWCYPOS_N(N) ((N)<<0) - -/* lcd_cursorcolor */ -#define LCD_CURSORCOLOR_HWCA (0xFF<<24) -#define LCD_CURSORCOLOR_HWCR (0xFF<<16) -#define LCD_CURSORCOLOR_HWCG (0xFF<<8) -#define LCD_CURSORCOLOR_HWCB (0xFF<<0) -#define LCD_CURSORCOLOR_HWCA_N(N) ((N)<<24) -#define LCD_CURSORCOLOR_HWCR_N(N) ((N)<<16) -#define LCD_CURSORCOLOR_HWCG_N(N) ((N)<<8) -#define LCD_CURSORCOLOR_HWCB_N(N) ((N)<<0) - -/* lcd_fifoctrl */ -#define LCD_FIFOCTRL_F3IF (1<<29) -#define LCD_FIFOCTRL_F3REQ (0x1F<<24) -#define LCD_FIFOCTRL_F2IF (1<<29) -#define LCD_FIFOCTRL_F2REQ (0x1F<<16) -#define LCD_FIFOCTRL_F1IF (1<<29) -#define LCD_FIFOCTRL_F1REQ (0x1F<<8) -#define LCD_FIFOCTRL_F0IF (1<<29) -#define LCD_FIFOCTRL_F0REQ (0x1F<<0) -#define LCD_FIFOCTRL_F3REQ_N(N) ((N-1)<<24) -#define LCD_FIFOCTRL_F2REQ_N(N) ((N-1)<<16) -#define LCD_FIFOCTRL_F1REQ_N(N) ((N-1)<<8) -#define LCD_FIFOCTRL_F0REQ_N(N) ((N-1)<<0) - -/* lcd_outmask */ -#define LCD_OUTMASK_MASK (0x00FFFFFF) - -/********************************************************************/ -#endif /* _AU1200LCD_H */ diff --git a/drivers/video/fbdev/auo_k190x.c b/drivers/video/fbdev/auo_k190x.c index 1e383c547633..9d24d1b3e9ef 100644 --- a/drivers/video/fbdev/auo_k190x.c +++ b/drivers/video/fbdev/auo_k190x.c @@ -1056,13 +1056,12 @@ int auok190x_common_probe(struct platform_device *pdev, /* videomemory handling */ videomemorysize = roundup((panel->w * panel->h) * 2, PAGE_SIZE); - videomemory = vmalloc(videomemorysize); + videomemory = vzalloc(videomemorysize); if (!videomemory) { ret = -ENOMEM; goto err_irq; } - memset(videomemory, 0, videomemorysize); info->screen_base = (char *)videomemory; info->fix.smem_len = videomemorysize; diff --git a/drivers/video/fbdev/mmp/core.c b/drivers/video/fbdev/mmp/core.c index a0f496049db7..3a6bb6561ba0 100644 --- a/drivers/video/fbdev/mmp/core.c +++ b/drivers/video/fbdev/mmp/core.c @@ -23,6 +23,7 @@ #include <linux/slab.h> #include <linux/dma-mapping.h> #include <linux/export.h> +#include <linux/module.h> #include <video/mmp_disp.h> static struct mmp_overlay *path_get_overlay(struct mmp_path *path, @@ -249,3 +250,7 @@ void mmp_unregister_path(struct mmp_path *path) mutex_unlock(&disp_lock); } EXPORT_SYMBOL_GPL(mmp_unregister_path); + +MODULE_AUTHOR("Zhou Zhu <zzhu3@marvell.com>"); +MODULE_DESCRIPTION("Marvell MMP display framework"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/fbdev/mxsfb.c b/drivers/video/fbdev/mxsfb.c index 79b1dc7f042b..246bea3a7d9b 100644 --- a/drivers/video/fbdev/mxsfb.c +++ b/drivers/video/fbdev/mxsfb.c @@ -169,7 +169,6 @@ struct mxsfb_devdata { }; struct mxsfb_info { - struct fb_info fb_info; struct platform_device *pdev; struct clk *clk; struct clk *clk_axi; @@ -208,8 +207,6 @@ static const struct mxsfb_devdata mxsfb_devdata[] = { }, }; -#define to_imxfb_host(x) (container_of(x, struct mxsfb_info, fb_info)) - /* mask and shift depends on architecture */ static inline u32 set_hsync_pulse_width(struct mxsfb_info *host, unsigned val) { @@ -269,7 +266,7 @@ static inline unsigned chan_to_field(unsigned chan, struct fb_bitfield *bf) static int mxsfb_check_var(struct fb_var_screeninfo *var, struct fb_info *fb_info) { - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; const struct fb_bitfield *rgb = NULL; if (var->xres < MIN_XRES) @@ -330,7 +327,7 @@ static inline void mxsfb_disable_axi_clk(struct mxsfb_info *host) static void mxsfb_enable_controller(struct fb_info *fb_info) { - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; u32 reg; int ret; @@ -367,7 +364,7 @@ static void mxsfb_enable_controller(struct fb_info *fb_info) static void mxsfb_disable_controller(struct fb_info *fb_info) { - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; unsigned loop; u32 reg; int ret; @@ -409,7 +406,7 @@ static void mxsfb_disable_controller(struct fb_info *fb_info) static int mxsfb_set_par(struct fb_info *fb_info) { - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; u32 ctrl, vdctrl0, vdctrl4; int line_size, fb_size; int reenable = 0; @@ -569,7 +566,7 @@ static int mxsfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, static int mxsfb_blank(int blank, struct fb_info *fb_info) { - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; switch (blank) { case FB_BLANK_POWERDOWN: @@ -591,7 +588,7 @@ static int mxsfb_blank(int blank, struct fb_info *fb_info) static int mxsfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *fb_info) { - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; unsigned offset; if (var->xoffset != 0) @@ -622,10 +619,10 @@ static struct fb_ops mxsfb_ops = { .fb_imageblit = cfb_imageblit, }; -static int mxsfb_restore_mode(struct mxsfb_info *host, +static int mxsfb_restore_mode(struct fb_info *fb_info, struct fb_videomode *vmode) { - struct fb_info *fb_info = &host->fb_info; + struct mxsfb_info *host = fb_info->par; unsigned line_count; unsigned period; unsigned long pa, fbsize; @@ -726,10 +723,10 @@ err: return ret; } -static int mxsfb_init_fbinfo_dt(struct mxsfb_info *host, +static int mxsfb_init_fbinfo_dt(struct fb_info *fb_info, struct fb_videomode *vmode) { - struct fb_info *fb_info = &host->fb_info; + struct mxsfb_info *host = fb_info->par; struct fb_var_screeninfo *var = &fb_info->var; struct device *dev = &host->pdev->dev; struct device_node *np = host->pdev->dev.of_node; @@ -805,12 +802,12 @@ put_display_node: return ret; } -static int mxsfb_init_fbinfo(struct mxsfb_info *host, +static int mxsfb_init_fbinfo(struct fb_info *fb_info, struct fb_videomode *vmode) { int ret; + struct mxsfb_info *host = fb_info->par; struct device *dev = &host->pdev->dev; - struct fb_info *fb_info = &host->fb_info; struct fb_var_screeninfo *var = &fb_info->var; dma_addr_t fb_phys; void *fb_virt; @@ -824,7 +821,7 @@ static int mxsfb_init_fbinfo(struct mxsfb_info *host, fb_info->fix.visual = FB_VISUAL_TRUECOLOR, fb_info->fix.accel = FB_ACCEL_NONE; - ret = mxsfb_init_fbinfo_dt(host, vmode); + ret = mxsfb_init_fbinfo_dt(fb_info, vmode); if (ret) return ret; @@ -843,16 +840,16 @@ static int mxsfb_init_fbinfo(struct mxsfb_info *host, fb_info->screen_base = fb_virt; fb_info->screen_size = fb_info->fix.smem_len = fb_size; - if (mxsfb_restore_mode(host, vmode)) + if (mxsfb_restore_mode(fb_info, vmode)) memset(fb_virt, 0, fb_size); return 0; } -static void mxsfb_free_videomem(struct mxsfb_info *host) +static void mxsfb_free_videomem(struct fb_info *fb_info) { + struct mxsfb_info *host = fb_info->par; struct device *dev = &host->pdev->dev; - struct fb_info *fb_info = &host->fb_info; dma_free_wc(dev, fb_info->screen_size, fb_info->screen_base, fb_info->fix.smem_start); @@ -902,7 +899,7 @@ static int mxsfb_probe(struct platform_device *pdev) if (mode == NULL) return -ENOMEM; - host = to_imxfb_host(fb_info); + host = fb_info->par; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); host->base = devm_ioremap_resource(&pdev->dev, res); @@ -941,7 +938,7 @@ static int mxsfb_probe(struct platform_device *pdev) goto fb_release; } - ret = mxsfb_init_fbinfo(host, mode); + ret = mxsfb_init_fbinfo(fb_info, mode); if (ret != 0) goto fb_release; @@ -982,13 +979,13 @@ fb_release: static int mxsfb_remove(struct platform_device *pdev) { struct fb_info *fb_info = platform_get_drvdata(pdev); - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; if (host->enabled) mxsfb_disable_controller(fb_info); unregister_framebuffer(fb_info); - mxsfb_free_videomem(host); + mxsfb_free_videomem(fb_info); framebuffer_release(fb_info); @@ -998,7 +995,7 @@ static int mxsfb_remove(struct platform_device *pdev) static void mxsfb_shutdown(struct platform_device *pdev) { struct fb_info *fb_info = platform_get_drvdata(pdev); - struct mxsfb_info *host = to_imxfb_host(fb_info); + struct mxsfb_info *host = fb_info->par; mxsfb_enable_axi_clk(host); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c index 7a75dfda9845..fb605aefd9b1 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c @@ -3976,52 +3976,33 @@ static const struct dispc_features omap54xx_dispc_feats = { .has_writeback = true, }; -static int dispc_init_features(struct platform_device *pdev) +static const struct dispc_features *dispc_get_features(void) { - const struct dispc_features *src; - struct dispc_features *dst; - - dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL); - if (!dst) { - dev_err(&pdev->dev, "Failed to allocate DISPC Features\n"); - return -ENOMEM; - } - switch (omapdss_get_version()) { case OMAPDSS_VER_OMAP24xx: - src = &omap24xx_dispc_feats; - break; + return &omap24xx_dispc_feats; case OMAPDSS_VER_OMAP34xx_ES1: - src = &omap34xx_rev1_0_dispc_feats; - break; + return &omap34xx_rev1_0_dispc_feats; case OMAPDSS_VER_OMAP34xx_ES3: case OMAPDSS_VER_OMAP3630: case OMAPDSS_VER_AM35xx: case OMAPDSS_VER_AM43xx: - src = &omap34xx_rev3_0_dispc_feats; - break; + return &omap34xx_rev3_0_dispc_feats; case OMAPDSS_VER_OMAP4430_ES1: case OMAPDSS_VER_OMAP4430_ES2: case OMAPDSS_VER_OMAP4: - src = &omap44xx_dispc_feats; - break; + return &omap44xx_dispc_feats; case OMAPDSS_VER_OMAP5: case OMAPDSS_VER_DRA7xx: - src = &omap54xx_dispc_feats; - break; + return &omap54xx_dispc_feats; default: - return -ENODEV; + return NULL; } - - memcpy(dst, src, sizeof(*dst)); - dispc.feat = dst; - - return 0; } static irqreturn_t dispc_irq_handler(int irq, void *arg) @@ -4078,9 +4059,9 @@ static int dispc_bind(struct device *dev, struct device *master, void *data) spin_lock_init(&dispc.control_lock); - r = dispc_init_features(dispc.pdev); - if (r) - return r; + dispc.feat = dispc_get_features(); + if (!dispc.feat) + return -ENODEV; dispc_mem = platform_get_resource(dispc.pdev, IORESOURCE_MEM, 0); if (!dispc_mem) { diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss.c b/drivers/video/fbdev/omap2/omapfb/dss/dss.c index 48c6500c24e1..f0cac9e0eb94 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dss.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dss.c @@ -40,6 +40,7 @@ #include <linux/regulator/consumer.h> #include <linux/suspend.h> #include <linux/component.h> +#include <linux/pinctrl/consumer.h> #include <video/omapfb_dss.h> @@ -887,58 +888,37 @@ static const struct dss_features dra7xx_dss_feats = { .num_ports = ARRAY_SIZE(dra7xx_ports), }; -static int dss_init_features(struct platform_device *pdev) +static const struct dss_features *dss_get_features(void) { - const struct dss_features *src; - struct dss_features *dst; - - dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL); - if (!dst) { - dev_err(&pdev->dev, "Failed to allocate local DSS Features\n"); - return -ENOMEM; - } - switch (omapdss_get_version()) { case OMAPDSS_VER_OMAP24xx: - src = &omap24xx_dss_feats; - break; + return &omap24xx_dss_feats; case OMAPDSS_VER_OMAP34xx_ES1: case OMAPDSS_VER_OMAP34xx_ES3: case OMAPDSS_VER_AM35xx: - src = &omap34xx_dss_feats; - break; + return &omap34xx_dss_feats; case OMAPDSS_VER_OMAP3630: - src = &omap3630_dss_feats; - break; + return &omap3630_dss_feats; case OMAPDSS_VER_OMAP4430_ES1: case OMAPDSS_VER_OMAP4430_ES2: case OMAPDSS_VER_OMAP4: - src = &omap44xx_dss_feats; - break; + return &omap44xx_dss_feats; case OMAPDSS_VER_OMAP5: - src = &omap54xx_dss_feats; - break; + return &omap54xx_dss_feats; case OMAPDSS_VER_AM43xx: - src = &am43xx_dss_feats; - break; + return &am43xx_dss_feats; case OMAPDSS_VER_DRA7xx: - src = &dra7xx_dss_feats; - break; + return &dra7xx_dss_feats; default: - return -ENODEV; + return NULL; } - - memcpy(dst, src, sizeof(*dst)); - dss.feat = dst; - - return 0; } static void dss_uninit_ports(struct platform_device *pdev); @@ -1104,9 +1084,9 @@ static int dss_bind(struct device *dev) dss.pdev = pdev; - r = dss_init_features(dss.pdev); - if (r) - return r; + dss.feat = dss_get_features(); + if (!dss.feat) + return -ENODEV; dss_mem = platform_get_resource(dss.pdev, IORESOURCE_MEM, 0); if (!dss_mem) { diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c index ec78d61bc551..28de56e21c74 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi4.c @@ -673,10 +673,7 @@ static int hdmi_audio_register(struct device *dev) dev, "omap-hdmi-audio", PLATFORM_DEVID_AUTO, &pdata, sizeof(pdata)); - if (IS_ERR(hdmi.audio_pdev)) - return PTR_ERR(hdmi.audio_pdev); - - return 0; + return PTR_ERR_OR_ZERO(hdmi.audio_pdev); } /* HDMI HW IP initialisation */ diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c index 9a13c35fd6d8..11dbc05d5720 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_phy.c @@ -13,6 +13,8 @@ #include <linux/io.h> #include <linux/platform_device.h> #include <linux/slab.h> +#include <linux/seq_file.h> + #include <video/omapfb_dss.h> #include "dss.h" @@ -189,47 +191,30 @@ static const struct hdmi_phy_features omap54xx_phy_feats = { .max_phy = 186000000, }; -static int hdmi_phy_init_features(struct platform_device *pdev) +static const struct hdmi_phy_features *hdmi_phy_get_features(void) { - struct hdmi_phy_features *dst; - const struct hdmi_phy_features *src; - - dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL); - if (!dst) { - dev_err(&pdev->dev, "Failed to allocate HDMI PHY Features\n"); - return -ENOMEM; - } - switch (omapdss_get_version()) { case OMAPDSS_VER_OMAP4430_ES1: case OMAPDSS_VER_OMAP4430_ES2: case OMAPDSS_VER_OMAP4: - src = &omap44xx_phy_feats; - break; + return &omap44xx_phy_feats; case OMAPDSS_VER_OMAP5: case OMAPDSS_VER_DRA7xx: - src = &omap54xx_phy_feats; - break; + return &omap54xx_phy_feats; default: - return -ENODEV; + return NULL; } - - memcpy(dst, src, sizeof(*dst)); - phy_feat = dst; - - return 0; } int hdmi_phy_init(struct platform_device *pdev, struct hdmi_phy_data *phy) { - int r; struct resource *res; - r = hdmi_phy_init_features(pdev); - if (r) - return r; + phy_feat = hdmi_phy_get_features(); + if (!phy_feat) + return -ENODEV; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "phy"); if (!res) { diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c index eac3665aba6c..bc591fc12aef 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_pll.c @@ -16,6 +16,7 @@ #include <linux/io.h> #include <linux/platform_device.h> #include <linux/clk.h> +#include <linux/seq_file.h> #include <video/omapfb_dss.h> diff --git a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c index 705373e4cf38..4af6ba220744 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/hdmi_wp.c @@ -14,6 +14,8 @@ #include <linux/err.h> #include <linux/io.h> #include <linux/platform_device.h> +#include <linux/seq_file.h> + #include <video/omapfb_dss.h> #include "dss.h" diff --git a/drivers/video/fbdev/pxa3xx-gcu.c b/drivers/video/fbdev/pxa3xx-gcu.c index 55fbb432c053..0955622a1227 100644 --- a/drivers/video/fbdev/pxa3xx-gcu.c +++ b/drivers/video/fbdev/pxa3xx-gcu.c @@ -104,7 +104,7 @@ struct pxa3xx_gcu_priv { wait_queue_head_t wait_idle; wait_queue_head_t wait_free; spinlock_t spinlock; - struct timeval base_time; + struct timespec64 base_time; struct pxa3xx_gcu_batch *free; struct pxa3xx_gcu_batch *ready; @@ -126,18 +126,20 @@ gc_writel(struct pxa3xx_gcu_priv *priv, unsigned int off, unsigned long val) #define QPRINT(priv, level, msg) \ do { \ - struct timeval tv; \ + struct timespec64 ts; \ struct pxa3xx_gcu_shared *shared = priv->shared; \ u32 base = gc_readl(priv, REG_GCRBBR); \ \ - do_gettimeofday(&tv); \ + ktime_get_ts64(&ts); \ + ts = timespec64_sub(ts, priv->base_time); \ \ - printk(level "%ld.%03ld.%03ld - %-17s: %-21s (%s, " \ + printk(level "%lld.%03ld.%03ld - %-17s: %-21s (%s, " \ "STATUS " \ "0x%02lx, B 0x%08lx [%ld], E %5ld, H %5ld, " \ "T %5ld)\n", \ - tv.tv_sec - priv->base_time.tv_sec, \ - tv.tv_usec / 1000, tv.tv_usec % 1000, \ + (s64)(ts.tv_sec), \ + ts.tv_nsec / NSEC_PER_MSEC, \ + (ts.tv_nsec % NSEC_PER_MSEC) / USEC_PER_MSEC, \ __func__, msg, \ shared->hw_running ? "running" : " idle", \ gc_readl(priv, REG_GCISCR), \ @@ -164,7 +166,7 @@ pxa3xx_gcu_reset(struct pxa3xx_gcu_priv *priv) priv->shared->buffer_phys = priv->shared_phys; priv->shared->magic = PXA3XX_GCU_SHARED_MAGIC; - do_gettimeofday(&priv->base_time); + ktime_get_ts64(&priv->base_time); /* set up the ring buffer pointers */ gc_writel(priv, REG_GCRBLR, 0); diff --git a/drivers/video/fbdev/smscufx.c b/drivers/video/fbdev/smscufx.c index 2275e80b5776..8db7085e5d1a 100644 --- a/drivers/video/fbdev/smscufx.c +++ b/drivers/video/fbdev/smscufx.c @@ -1086,8 +1086,7 @@ static int ufx_ops_open(struct fb_info *info, int user) struct fb_deferred_io *fbdefio; - fbdefio = kzalloc(sizeof(struct fb_deferred_io), GFP_KERNEL); - + fbdefio = kzalloc(sizeof(*fbdefio), GFP_KERNEL); if (fbdefio) { fbdefio->delay = UFX_DEFIO_WRITE_DELAY; fbdefio->deferred_io = ufx_dpy_deferred_io; @@ -1875,7 +1874,7 @@ static int ufx_alloc_urb_list(struct ufx_data *dev, int count, size_t size) INIT_LIST_HEAD(&dev->urbs.list); while (i < count) { - unode = kzalloc(sizeof(struct urb_node), GFP_KERNEL); + unode = kzalloc(sizeof(*unode), GFP_KERNEL); if (!unode) break; unode->dev = dev; diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index d44f14242016..452a4207ac1b 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -16,8 +16,6 @@ * from Florian Echtler, Henrik Bjerregaard Pedersen, and others. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> @@ -32,7 +30,7 @@ #include <video/udlfb.h> #include "edid.h" -static struct fb_fix_screeninfo dlfb_fix = { +static const struct fb_fix_screeninfo dlfb_fix = { .id = "udlfb", .type = FB_TYPE_PACKED_PIXELS, .visual = FB_VISUAL_TRUECOLOR, @@ -76,10 +74,10 @@ static int pixel_limit; /* Optionally force a pixel resolution limit */ /* dlfb keeps a list of urbs for efficient bulk transfers */ static void dlfb_urb_completion(struct urb *urb); -static struct urb *dlfb_get_urb(struct dlfb_data *dev); -static int dlfb_submit_urb(struct dlfb_data *dev, struct urb * urb, size_t len); -static int dlfb_alloc_urb_list(struct dlfb_data *dev, int count, size_t size); -static void dlfb_free_urb_list(struct dlfb_data *dev); +static struct urb *dlfb_get_urb(struct dlfb_data *dlfb); +static int dlfb_submit_urb(struct dlfb_data *dlfb, struct urb * urb, size_t len); +static int dlfb_alloc_urb_list(struct dlfb_data *dlfb, int count, size_t size); +static void dlfb_free_urb_list(struct dlfb_data *dlfb); /* * All DisplayLink bulk operations start with 0xAF, followed by specific code @@ -274,7 +272,7 @@ static char *dlfb_set_vid_cmds(char *wrptr, struct fb_var_screeninfo *var) * and then generates the appropriate command sequence that then drives the * display controller. */ -static int dlfb_set_video_mode(struct dlfb_data *dev, +static int dlfb_set_video_mode(struct dlfb_data *dlfb, struct fb_var_screeninfo *var) { char *buf; @@ -283,10 +281,10 @@ static int dlfb_set_video_mode(struct dlfb_data *dev, int writesize; struct urb *urb; - if (!atomic_read(&dev->usb_active)) + if (!atomic_read(&dlfb->usb_active)) return -EPERM; - urb = dlfb_get_urb(dev); + urb = dlfb_get_urb(dlfb); if (!urb) return -ENOMEM; @@ -302,7 +300,7 @@ static int dlfb_set_video_mode(struct dlfb_data *dev, /* set base for 16bpp segment to 0 */ wrptr = dlfb_set_base16bpp(wrptr, 0); /* set base for 8bpp segment to end of fb */ - wrptr = dlfb_set_base8bpp(wrptr, dev->info->fix.smem_len); + wrptr = dlfb_set_base8bpp(wrptr, dlfb->info->fix.smem_len); wrptr = dlfb_set_vid_cmds(wrptr, var); wrptr = dlfb_blanking(wrptr, FB_BLANK_UNBLANK); @@ -310,9 +308,9 @@ static int dlfb_set_video_mode(struct dlfb_data *dev, writesize = wrptr - buf; - retval = dlfb_submit_urb(dev, urb, writesize); + retval = dlfb_submit_urb(dlfb, urb, writesize); - dev->blank_mode = FB_BLANK_UNBLANK; + dlfb->blank_mode = FB_BLANK_UNBLANK; return retval; } @@ -333,8 +331,8 @@ static int dlfb_ops_mmap(struct fb_info *info, struct vm_area_struct *vma) pos = (unsigned long)info->fix.smem_start + offset; - pr_notice("mmap() framebuffer addr:%lu size:%lu\n", - pos, size); + dev_dbg(info->dev, "mmap() framebuffer addr:%lu size:%lu\n", + pos, size); while (size > 0) { page = vmalloc_to_pfn((void *)pos); @@ -505,8 +503,6 @@ static void dlfb_compress_hline( *command_buffer_ptr = cmd; *pixel_start_ptr = pixel; *device_address_ptr = dev_addr; - - return; } /* @@ -515,13 +511,13 @@ static void dlfb_compress_hline( * (that we can only write to, slowly, and can never read), and (optionally) * our shadow copy that tracks what's been sent to that hardware buffer. */ -static int dlfb_render_hline(struct dlfb_data *dev, struct urb **urb_ptr, +static int dlfb_render_hline(struct dlfb_data *dlfb, struct urb **urb_ptr, const char *front, char **urb_buf_ptr, u32 byte_offset, u32 byte_width, int *ident_ptr, int *sent_ptr) { const u8 *line_start, *line_end, *next_pixel; - u32 dev_addr = dev->base16 + byte_offset; + u32 dev_addr = dlfb->base16 + byte_offset; struct urb *urb = *urb_ptr; u8 *cmd = *urb_buf_ptr; u8 *cmd_end = (u8 *) urb->transfer_buffer + urb->transfer_buffer_length; @@ -530,9 +526,9 @@ static int dlfb_render_hline(struct dlfb_data *dev, struct urb **urb_ptr, next_pixel = line_start; line_end = next_pixel + byte_width; - if (dev->backing_buffer) { + if (dlfb->backing_buffer) { int offset; - const u8 *back_start = (u8 *) (dev->backing_buffer + const u8 *back_start = (u8 *) (dlfb->backing_buffer + byte_offset); *ident_ptr += dlfb_trim_hline(back_start, &next_pixel, @@ -556,10 +552,10 @@ static int dlfb_render_hline(struct dlfb_data *dev, struct urb **urb_ptr, if (cmd >= cmd_end) { int len = cmd - (u8 *) urb->transfer_buffer; - if (dlfb_submit_urb(dev, urb, len)) + if (dlfb_submit_urb(dlfb, urb, len)) return 1; /* lost pixels is set */ *sent_ptr += len; - urb = dlfb_get_urb(dev); + urb = dlfb_get_urb(dlfb); if (!urb) return 1; /* lost_pixels is set */ *urb_ptr = urb; @@ -573,7 +569,7 @@ static int dlfb_render_hline(struct dlfb_data *dev, struct urb **urb_ptr, return 0; } -static int dlfb_handle_damage(struct dlfb_data *dev, int x, int y, +static int dlfb_handle_damage(struct dlfb_data *dlfb, int x, int y, int width, int height, char *data) { int i, ret; @@ -591,24 +587,24 @@ static int dlfb_handle_damage(struct dlfb_data *dev, int x, int y, x = aligned_x; if ((width <= 0) || - (x + width > dev->info->var.xres) || - (y + height > dev->info->var.yres)) + (x + width > dlfb->info->var.xres) || + (y + height > dlfb->info->var.yres)) return -EINVAL; - if (!atomic_read(&dev->usb_active)) + if (!atomic_read(&dlfb->usb_active)) return 0; - urb = dlfb_get_urb(dev); + urb = dlfb_get_urb(dlfb); if (!urb) return 0; cmd = urb->transfer_buffer; for (i = y; i < y + height ; i++) { - const int line_offset = dev->info->fix.line_length * i; + const int line_offset = dlfb->info->fix.line_length * i; const int byte_offset = line_offset + (x * BPP); - if (dlfb_render_hline(dev, &urb, - (char *) dev->info->fix.smem_start, + if (dlfb_render_hline(dlfb, &urb, + (char *) dlfb->info->fix.smem_start, &cmd, byte_offset, width * BPP, &bytes_identical, &bytes_sent)) goto error; @@ -617,19 +613,19 @@ static int dlfb_handle_damage(struct dlfb_data *dev, int x, int y, if (cmd > (char *) urb->transfer_buffer) { /* Send partial buffer remaining before exiting */ int len = cmd - (char *) urb->transfer_buffer; - ret = dlfb_submit_urb(dev, urb, len); + ret = dlfb_submit_urb(dlfb, urb, len); bytes_sent += len; } else dlfb_urb_completion(urb); error: - atomic_add(bytes_sent, &dev->bytes_sent); - atomic_add(bytes_identical, &dev->bytes_identical); - atomic_add(width*height*2, &dev->bytes_rendered); + atomic_add(bytes_sent, &dlfb->bytes_sent); + atomic_add(bytes_identical, &dlfb->bytes_identical); + atomic_add(width*height*2, &dlfb->bytes_rendered); end_cycles = get_cycles(); atomic_add(((unsigned int) ((end_cycles - start_cycles) >> 10)), /* Kcycles */ - &dev->cpu_kcycles_used); + &dlfb->cpu_kcycles_used); return 0; } @@ -644,7 +640,7 @@ static ssize_t dlfb_ops_write(struct fb_info *info, const char __user *buf, size_t count, loff_t *ppos) { ssize_t result; - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; u32 offset = (u32) *ppos; result = fb_sys_write(info, buf, count, ppos); @@ -654,7 +650,7 @@ static ssize_t dlfb_ops_write(struct fb_info *info, const char __user *buf, int lines = min((u32)((result / info->fix.line_length) + 1), (u32)info->var.yres); - dlfb_handle_damage(dev, 0, start, info->var.xres, + dlfb_handle_damage(dlfb, 0, start, info->var.xres, lines, info->screen_base); } @@ -666,33 +662,33 @@ static void dlfb_ops_copyarea(struct fb_info *info, const struct fb_copyarea *area) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; sys_copyarea(info, area); - dlfb_handle_damage(dev, area->dx, area->dy, + dlfb_handle_damage(dlfb, area->dx, area->dy, area->width, area->height, info->screen_base); } static void dlfb_ops_imageblit(struct fb_info *info, const struct fb_image *image) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; sys_imageblit(info, image); - dlfb_handle_damage(dev, image->dx, image->dy, + dlfb_handle_damage(dlfb, image->dx, image->dy, image->width, image->height, info->screen_base); } static void dlfb_ops_fillrect(struct fb_info *info, const struct fb_fillrect *rect) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; sys_fillrect(info, rect); - dlfb_handle_damage(dev, rect->dx, rect->dy, rect->width, + dlfb_handle_damage(dlfb, rect->dx, rect->dy, rect->width, rect->height, info->screen_base); } @@ -707,7 +703,7 @@ static void dlfb_dpy_deferred_io(struct fb_info *info, { struct page *cur; struct fb_deferred_io *fbdefio = info->fbdefio; - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; struct urb *urb; char *cmd; cycles_t start_cycles, end_cycles; @@ -718,12 +714,12 @@ static void dlfb_dpy_deferred_io(struct fb_info *info, if (!fb_defio) return; - if (!atomic_read(&dev->usb_active)) + if (!atomic_read(&dlfb->usb_active)) return; start_cycles = get_cycles(); - urb = dlfb_get_urb(dev); + urb = dlfb_get_urb(dlfb); if (!urb) return; @@ -732,7 +728,7 @@ static void dlfb_dpy_deferred_io(struct fb_info *info, /* walk the written page list and render each to device */ list_for_each_entry(cur, &fbdefio->pagelist, lru) { - if (dlfb_render_hline(dev, &urb, (char *) info->fix.smem_start, + if (dlfb_render_hline(dlfb, &urb, (char *) info->fix.smem_start, &cmd, cur->index << PAGE_SHIFT, PAGE_SIZE, &bytes_identical, &bytes_sent)) goto error; @@ -742,25 +738,24 @@ static void dlfb_dpy_deferred_io(struct fb_info *info, if (cmd > (char *) urb->transfer_buffer) { /* Send partial buffer remaining before exiting */ int len = cmd - (char *) urb->transfer_buffer; - dlfb_submit_urb(dev, urb, len); + dlfb_submit_urb(dlfb, urb, len); bytes_sent += len; } else dlfb_urb_completion(urb); error: - atomic_add(bytes_sent, &dev->bytes_sent); - atomic_add(bytes_identical, &dev->bytes_identical); - atomic_add(bytes_rendered, &dev->bytes_rendered); + atomic_add(bytes_sent, &dlfb->bytes_sent); + atomic_add(bytes_identical, &dlfb->bytes_identical); + atomic_add(bytes_rendered, &dlfb->bytes_rendered); end_cycles = get_cycles(); atomic_add(((unsigned int) ((end_cycles - start_cycles) >> 10)), /* Kcycles */ - &dev->cpu_kcycles_used); + &dlfb->cpu_kcycles_used); } -static int dlfb_get_edid(struct dlfb_data *dev, char *edid, int len) +static int dlfb_get_edid(struct dlfb_data *dlfb, char *edid, int len) { - int i; - int ret; + int i, ret; char *rbuf; rbuf = kmalloc(2, GFP_KERNEL); @@ -768,12 +763,13 @@ static int dlfb_get_edid(struct dlfb_data *dev, char *edid, int len) return 0; for (i = 0; i < len; i++) { - ret = usb_control_msg(dev->udev, - usb_rcvctrlpipe(dev->udev, 0), 0x02, + ret = usb_control_msg(dlfb->udev, + usb_rcvctrlpipe(dlfb->udev, 0), 0x02, (0x80 | (0x02 << 5)), i << 8, 0xA1, rbuf, 2, USB_CTRL_GET_TIMEOUT); if (ret < 2) { - pr_err("Read EDID byte %d failed: %d\n", i, ret); + dev_err(&dlfb->udev->dev, + "Read EDID byte %d failed: %d\n", i, ret); i--; break; } @@ -789,15 +785,15 @@ static int dlfb_ops_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; - if (!atomic_read(&dev->usb_active)) + if (!atomic_read(&dlfb->usb_active)) return 0; /* TODO: Update X server to get this from sysfs instead */ if (cmd == DLFB_IOCTL_RETURN_EDID) { void __user *edid = (void __user *)arg; - if (copy_to_user(edid, dev->edid, dev->edid_size)) + if (copy_to_user(edid, dlfb->edid, dlfb->edid_size)) return -EFAULT; return 0; } @@ -832,7 +828,7 @@ static int dlfb_ops_ioctl(struct fb_info *info, unsigned int cmd, if (area.y > info->var.yres) area.y = info->var.yres; - dlfb_handle_damage(dev, area.x, area.y, area.w, area.h, + dlfb_handle_damage(dlfb, area.x, area.y, area.w, area.h, info->screen_base); } @@ -873,7 +869,7 @@ dlfb_ops_setcolreg(unsigned regno, unsigned red, unsigned green, */ static int dlfb_ops_open(struct fb_info *info, int user) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; /* * fbcon aggressively connects to first framebuffer it finds, @@ -884,12 +880,12 @@ static int dlfb_ops_open(struct fb_info *info, int user) return -EBUSY; /* If the USB device is gone, we don't accept new opens */ - if (dev->virtualized) + if (dlfb->virtualized) return -ENODEV; - dev->fb_count++; + dlfb->fb_count++; - kref_get(&dev->kref); + kref_get(&dlfb->kref); if (fb_defio && (info->fbdefio == NULL)) { /* enable defio at last moment if not disabled by client */ @@ -907,8 +903,8 @@ static int dlfb_ops_open(struct fb_info *info, int user) fb_deferred_io_init(info); } - pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n", - info->node, user, info, dev->fb_count); + dev_dbg(info->dev, "open, user=%d fb_info=%p count=%d\n", + user, info, dlfb->fb_count); return 0; } @@ -920,15 +916,11 @@ static int dlfb_ops_open(struct fb_info *info, int user) */ static void dlfb_free(struct kref *kref) { - struct dlfb_data *dev = container_of(kref, struct dlfb_data, kref); + struct dlfb_data *dlfb = container_of(kref, struct dlfb_data, kref); - vfree(dev->backing_buffer); - - kfree(dev->edid); - - pr_warn("freeing dlfb_data %p\n", dev); - - kfree(dev); + vfree(dlfb->backing_buffer); + kfree(dlfb->edid); + kfree(dlfb); } static void dlfb_release_urb_work(struct work_struct *work) @@ -936,16 +928,14 @@ static void dlfb_release_urb_work(struct work_struct *work) struct urb_node *unode = container_of(work, struct urb_node, release_urb_work.work); - up(&unode->dev->urbs.limit_sem); + up(&unode->dlfb->urbs.limit_sem); } -static void dlfb_free_framebuffer(struct dlfb_data *dev) +static void dlfb_free_framebuffer(struct dlfb_data *dlfb) { - struct fb_info *info = dev->info; + struct fb_info *info = dlfb->info; if (info) { - int node = info->node; - unregister_framebuffer(info); if (info->cmap.len != 0) @@ -956,48 +946,45 @@ static void dlfb_free_framebuffer(struct dlfb_data *dev) fb_destroy_modelist(&info->modelist); - dev->info = NULL; + dlfb->info = NULL; /* Assume info structure is freed after this point */ framebuffer_release(info); - - pr_warn("fb_info for /dev/fb%d has been freed\n", node); } /* ref taken in probe() as part of registering framebfufer */ - kref_put(&dev->kref, dlfb_free); + kref_put(&dlfb->kref, dlfb_free); } static void dlfb_free_framebuffer_work(struct work_struct *work) { - struct dlfb_data *dev = container_of(work, struct dlfb_data, + struct dlfb_data *dlfb = container_of(work, struct dlfb_data, free_framebuffer_work.work); - dlfb_free_framebuffer(dev); + dlfb_free_framebuffer(dlfb); } /* * Assumes caller is holding info->lock mutex (for open and release at least) */ static int dlfb_ops_release(struct fb_info *info, int user) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; - dev->fb_count--; + dlfb->fb_count--; /* We can't free fb_info here - fbmem will touch it when we return */ - if (dev->virtualized && (dev->fb_count == 0)) - schedule_delayed_work(&dev->free_framebuffer_work, HZ); + if (dlfb->virtualized && (dlfb->fb_count == 0)) + schedule_delayed_work(&dlfb->free_framebuffer_work, HZ); - if ((dev->fb_count == 0) && (info->fbdefio)) { + if ((dlfb->fb_count == 0) && (info->fbdefio)) { fb_deferred_io_cleanup(info); kfree(info->fbdefio); info->fbdefio = NULL; info->fbops->fb_mmap = dlfb_ops_mmap; } - pr_warn("released /dev/fb%d user=%d count=%d\n", - info->node, user, dev->fb_count); + dev_dbg(info->dev, "release, user=%d count=%d\n", user, dlfb->fb_count); - kref_put(&dev->kref, dlfb_free); + kref_put(&dlfb->kref, dlfb_free); return 0; } @@ -1006,19 +993,10 @@ static int dlfb_ops_release(struct fb_info *info, int user) * Check whether a video mode is supported by the DisplayLink chip * We start from monitor's modes, so don't need to filter that here */ -static int dlfb_is_valid_mode(struct fb_videomode *mode, - struct fb_info *info) +static int dlfb_is_valid_mode(struct fb_videomode *mode, struct dlfb_data *dlfb) { - struct dlfb_data *dev = info->par; - - if (mode->xres * mode->yres > dev->sku_pixel_limit) { - pr_warn("%dx%d beyond chip capabilities\n", - mode->xres, mode->yres); + if (mode->xres * mode->yres > dlfb->sku_pixel_limit) return 0; - } - - pr_info("%dx%d @ %d Hz valid mode\n", mode->xres, mode->yres, - mode->refresh); return 1; } @@ -1039,6 +1017,7 @@ static int dlfb_ops_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { struct fb_videomode mode; + struct dlfb_data *dlfb = info->par; /* TODO: support dynamically changing framebuffer size */ if ((var->xres * var->yres * 2) > info->fix.smem_len) @@ -1049,7 +1028,7 @@ static int dlfb_ops_check_var(struct fb_var_screeninfo *var, fb_var_to_videomode(&mode, var); - if (!dlfb_is_valid_mode(&mode, info)) + if (!dlfb_is_valid_mode(&mode, dlfb)) return -EINVAL; return 0; @@ -1057,16 +1036,14 @@ static int dlfb_ops_check_var(struct fb_var_screeninfo *var, static int dlfb_ops_set_par(struct fb_info *info) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; int result; u16 *pix_framebuffer; int i; - pr_notice("set_par mode %dx%d\n", info->var.xres, info->var.yres); + result = dlfb_set_video_mode(dlfb, &info->var); - result = dlfb_set_video_mode(dev, &info->var); - - if ((result == 0) && (dev->fb_count == 0)) { + if ((result == 0) && (dlfb->fb_count == 0)) { /* paint greenscreen */ @@ -1074,7 +1051,7 @@ static int dlfb_ops_set_par(struct fb_info *info) for (i = 0; i < info->fix.smem_len / 2; i++) pix_framebuffer[i] = 0x37e6; - dlfb_handle_damage(dev, 0, 0, info->var.xres, info->var.yres, + dlfb_handle_damage(dlfb, 0, 0, info->var.xres, info->var.yres, info->screen_base); } @@ -1101,21 +1078,21 @@ static char *dlfb_dummy_render(char *buf) */ static int dlfb_ops_blank(int blank_mode, struct fb_info *info) { - struct dlfb_data *dev = info->par; + struct dlfb_data *dlfb = info->par; char *bufptr; struct urb *urb; - pr_debug("/dev/fb%d FB_BLANK mode %d --> %d\n", - info->node, dev->blank_mode, blank_mode); + dev_dbg(info->dev, "blank, mode %d --> %d\n", + dlfb->blank_mode, blank_mode); - if ((dev->blank_mode == FB_BLANK_POWERDOWN) && + if ((dlfb->blank_mode == FB_BLANK_POWERDOWN) && (blank_mode != FB_BLANK_POWERDOWN)) { /* returning from powerdown requires a fresh modeset */ - dlfb_set_video_mode(dev, &info->var); + dlfb_set_video_mode(dlfb, &info->var); } - urb = dlfb_get_urb(dev); + urb = dlfb_get_urb(dlfb); if (!urb) return 0; @@ -1127,10 +1104,10 @@ static int dlfb_ops_blank(int blank_mode, struct fb_info *info) /* seems like a render op is needed to have blank change take effect */ bufptr = dlfb_dummy_render(bufptr); - dlfb_submit_urb(dev, urb, bufptr - + dlfb_submit_urb(dlfb, urb, bufptr - (char *) urb->transfer_buffer); - dev->blank_mode = blank_mode; + dlfb->blank_mode = blank_mode; return 0; } @@ -1157,7 +1134,7 @@ static struct fb_ops dlfb_ops = { * Assumes &info->lock held by caller * Assumes no active clients have framebuffer open */ -static int dlfb_realloc_framebuffer(struct dlfb_data *dev, struct fb_info *info) +static int dlfb_realloc_framebuffer(struct dlfb_data *dlfb, struct fb_info *info) { int retval = -ENOMEM; int old_len = info->fix.smem_len; @@ -1166,8 +1143,6 @@ static int dlfb_realloc_framebuffer(struct dlfb_data *dev, struct fb_info *info) unsigned char *new_fb; unsigned char *new_back = NULL; - pr_warn("Reallocating framebuffer. Addresses will change!\n"); - new_len = info->fix.line_length * info->var.yres; if (PAGE_ALIGN(new_len) > old_len) { @@ -1176,7 +1151,7 @@ static int dlfb_realloc_framebuffer(struct dlfb_data *dev, struct fb_info *info) */ new_fb = vmalloc(new_len); if (!new_fb) { - pr_err("Virtual framebuffer alloc failed\n"); + dev_err(info->dev, "Virtual framebuffer alloc failed\n"); goto error; } @@ -1199,10 +1174,11 @@ static int dlfb_realloc_framebuffer(struct dlfb_data *dev, struct fb_info *info) if (shadow) new_back = vzalloc(new_len); if (!new_back) - pr_info("No shadow/backing buffer allocated\n"); + dev_info(info->dev, + "No shadow/backing buffer allocated\n"); else { - vfree(dev->backing_buffer); - dev->backing_buffer = new_back; + vfree(dlfb->backing_buffer); + dlfb->backing_buffer = new_back; } } @@ -1226,18 +1202,22 @@ error: * monspecs is NULL, and fb_var_screeninfo is set to safe VESA mode * Returns 0 if successful */ -static int dlfb_setup_modes(struct dlfb_data *dev, +static int dlfb_setup_modes(struct dlfb_data *dlfb, struct fb_info *info, char *default_edid, size_t default_edid_size) { - int i; - const struct fb_videomode *default_vmode = NULL; - int result = 0; char *edid; - int tries = 3; + int i, result = 0, tries = 3; + struct device *dev = info->device; + struct fb_videomode *mode; + const struct fb_videomode *default_vmode = NULL; - if (info->dev) /* only use mutex if info has been registered */ + if (info->dev) { + /* only use mutex if info has been registered */ mutex_lock(&info->lock); + /* parent device is used otherwise */ + dev = info->dev; + } edid = kmalloc(EDID_LENGTH, GFP_KERNEL); if (!edid) { @@ -1255,27 +1235,26 @@ static int dlfb_setup_modes(struct dlfb_data *dev, */ while (tries--) { - i = dlfb_get_edid(dev, edid, EDID_LENGTH); + i = dlfb_get_edid(dlfb, edid, EDID_LENGTH); if (i >= EDID_LENGTH) fb_edid_to_monspecs(edid, &info->monspecs); if (info->monspecs.modedb_len > 0) { - dev->edid = edid; - dev->edid_size = i; + dlfb->edid = edid; + dlfb->edid_size = i; break; } } /* If that fails, use a previously returned EDID if available */ if (info->monspecs.modedb_len == 0) { + dev_err(dev, "Unable to get valid EDID from device/display\n"); - pr_err("Unable to get valid EDID from device/display\n"); - - if (dev->edid) { - fb_edid_to_monspecs(dev->edid, &info->monspecs); + if (dlfb->edid) { + fb_edid_to_monspecs(dlfb->edid, &info->monspecs); if (info->monspecs.modedb_len > 0) - pr_err("Using previously queried EDID\n"); + dev_err(dev, "Using previously queried EDID\n"); } } @@ -1285,9 +1264,9 @@ static int dlfb_setup_modes(struct dlfb_data *dev, fb_edid_to_monspecs(default_edid, &info->monspecs); if (info->monspecs.modedb_len > 0) { memcpy(edid, default_edid, default_edid_size); - dev->edid = edid; - dev->edid_size = default_edid_size; - pr_err("Using default/backup EDID\n"); + dlfb->edid = edid; + dlfb->edid_size = default_edid_size; + dev_err(dev, "Using default/backup EDID\n"); } } } @@ -1296,10 +1275,12 @@ static int dlfb_setup_modes(struct dlfb_data *dev, if (info->monspecs.modedb_len > 0) { for (i = 0; i < info->monspecs.modedb_len; i++) { - if (dlfb_is_valid_mode(&info->monspecs.modedb[i], info)) - fb_add_videomode(&info->monspecs.modedb[i], - &info->modelist); - else { + mode = &info->monspecs.modedb[i]; + if (dlfb_is_valid_mode(mode, dlfb)) { + fb_add_videomode(mode, &info->modelist); + } else { + dev_dbg(dev, "Specified mode %dx%d too big\n", + mode->xres, mode->yres); if (i == 0) /* if we've removed top/best mode */ info->monspecs.misc @@ -1323,10 +1304,12 @@ static int dlfb_setup_modes(struct dlfb_data *dev, * But at least the user has a chance to choose */ for (i = 0; i < VESA_MODEDB_SIZE; i++) { - if (dlfb_is_valid_mode((struct fb_videomode *) - &vesa_modes[i], info)) - fb_add_videomode(&vesa_modes[i], - &info->modelist); + mode = (struct fb_videomode *)&vesa_modes[i]; + if (dlfb_is_valid_mode(mode, dlfb)) + fb_add_videomode(mode, &info->modelist); + else + dev_dbg(dev, "VESA mode %dx%d too big\n", + mode->xres, mode->yres); } /* @@ -1341,7 +1324,7 @@ static int dlfb_setup_modes(struct dlfb_data *dev, } /* If we have good mode and no active clients*/ - if ((default_vmode != NULL) && (dev->fb_count == 0)) { + if ((default_vmode != NULL) && (dlfb->fb_count == 0)) { fb_videomode_to_var(&info->var, default_vmode); dlfb_var_color_format(&info->var); @@ -1353,13 +1336,13 @@ static int dlfb_setup_modes(struct dlfb_data *dev, info->fix.line_length = info->var.xres * (info->var.bits_per_pixel / 8); - result = dlfb_realloc_framebuffer(dev, info); + result = dlfb_realloc_framebuffer(dlfb, info); } else result = -EINVAL; error: - if (edid && (dev->edid != edid)) + if (edid && (dlfb->edid != edid)) kfree(edid); if (info->dev) @@ -1371,33 +1354,33 @@ error: static ssize_t metrics_bytes_rendered_show(struct device *fbdev, struct device_attribute *a, char *buf) { struct fb_info *fb_info = dev_get_drvdata(fbdev); - struct dlfb_data *dev = fb_info->par; + struct dlfb_data *dlfb = fb_info->par; return snprintf(buf, PAGE_SIZE, "%u\n", - atomic_read(&dev->bytes_rendered)); + atomic_read(&dlfb->bytes_rendered)); } static ssize_t metrics_bytes_identical_show(struct device *fbdev, struct device_attribute *a, char *buf) { struct fb_info *fb_info = dev_get_drvdata(fbdev); - struct dlfb_data *dev = fb_info->par; + struct dlfb_data *dlfb = fb_info->par; return snprintf(buf, PAGE_SIZE, "%u\n", - atomic_read(&dev->bytes_identical)); + atomic_read(&dlfb->bytes_identical)); } static ssize_t metrics_bytes_sent_show(struct device *fbdev, struct device_attribute *a, char *buf) { struct fb_info *fb_info = dev_get_drvdata(fbdev); - struct dlfb_data *dev = fb_info->par; + struct dlfb_data *dlfb = fb_info->par; return snprintf(buf, PAGE_SIZE, "%u\n", - atomic_read(&dev->bytes_sent)); + atomic_read(&dlfb->bytes_sent)); } static ssize_t metrics_cpu_kcycles_used_show(struct device *fbdev, struct device_attribute *a, char *buf) { struct fb_info *fb_info = dev_get_drvdata(fbdev); - struct dlfb_data *dev = fb_info->par; + struct dlfb_data *dlfb = fb_info->par; return snprintf(buf, PAGE_SIZE, "%u\n", - atomic_read(&dev->cpu_kcycles_used)); + atomic_read(&dlfb->cpu_kcycles_used)); } static ssize_t edid_show( @@ -1406,21 +1389,18 @@ static ssize_t edid_show( char *buf, loff_t off, size_t count) { struct device *fbdev = container_of(kobj, struct device, kobj); struct fb_info *fb_info = dev_get_drvdata(fbdev); - struct dlfb_data *dev = fb_info->par; + struct dlfb_data *dlfb = fb_info->par; - if (dev->edid == NULL) + if (dlfb->edid == NULL) return 0; - if ((off >= dev->edid_size) || (count > dev->edid_size)) + if ((off >= dlfb->edid_size) || (count > dlfb->edid_size)) return 0; - if (off + count > dev->edid_size) - count = dev->edid_size - off; - - pr_info("sysfs edid copy %p to %p, %d bytes\n", - dev->edid, buf, (int) count); + if (off + count > dlfb->edid_size) + count = dlfb->edid_size - off; - memcpy(buf, dev->edid, count); + memcpy(buf, dlfb->edid, count); return count; } @@ -1431,21 +1411,20 @@ static ssize_t edid_store( char *src, loff_t src_off, size_t src_size) { struct device *fbdev = container_of(kobj, struct device, kobj); struct fb_info *fb_info = dev_get_drvdata(fbdev); - struct dlfb_data *dev = fb_info->par; + struct dlfb_data *dlfb = fb_info->par; int ret; /* We only support write of entire EDID at once, no offset*/ if ((src_size != EDID_LENGTH) || (src_off != 0)) return -EINVAL; - ret = dlfb_setup_modes(dev, fb_info, src, src_size); + ret = dlfb_setup_modes(dlfb, fb_info, src, src_size); if (ret) return ret; - if (!dev->edid || memcmp(src, dev->edid, src_size)) + if (!dlfb->edid || memcmp(src, dlfb->edid, src_size)) return -EINVAL; - pr_info("sysfs written EDID is new default\n"); dlfb_ops_set_par(fb_info); return src_size; } @@ -1455,12 +1434,12 @@ static ssize_t metrics_reset_store(struct device *fbdev, const char *buf, size_t count) { struct fb_info *fb_info = dev_get_drvdata(fbdev); - struct dlfb_data *dev = fb_info->par; + struct dlfb_data *dlfb = fb_info->par; - atomic_set(&dev->bytes_rendered, 0); - atomic_set(&dev->bytes_identical, 0); - atomic_set(&dev->bytes_sent, 0); - atomic_set(&dev->cpu_kcycles_used, 0); + atomic_set(&dlfb->bytes_rendered, 0); + atomic_set(&dlfb->bytes_identical, 0); + atomic_set(&dlfb->bytes_sent, 0); + atomic_set(&dlfb->cpu_kcycles_used, 0); return count; } @@ -1473,7 +1452,7 @@ static const struct bin_attribute edid_attr = { .write = edid_store }; -static struct device_attribute fb_device_attrs[] = { +static const struct device_attribute fb_device_attrs[] = { __ATTR_RO(metrics_bytes_rendered), __ATTR_RO(metrics_bytes_identical), __ATTR_RO(metrics_bytes_sent), @@ -1484,7 +1463,7 @@ static struct device_attribute fb_device_attrs[] = { /* * This is necessary before we can communicate with the display controller. */ -static int dlfb_select_std_channel(struct dlfb_data *dev) +static int dlfb_select_std_channel(struct dlfb_data *dlfb) { int ret; void *buf; @@ -1499,7 +1478,7 @@ static int dlfb_select_std_channel(struct dlfb_data *dev) if (!buf) return -ENOMEM; - ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), + ret = usb_control_msg(dlfb->udev, usb_sndctrlpipe(dlfb->udev, 0), NR_USB_REQUEST_CHANNEL, (USB_DIR_OUT | USB_TYPE_VENDOR), 0, 0, buf, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT); @@ -1509,8 +1488,8 @@ static int dlfb_select_std_channel(struct dlfb_data *dev) return ret; } -static int dlfb_parse_vendor_descriptor(struct dlfb_data *dev, - struct usb_interface *interface) +static int dlfb_parse_vendor_descriptor(struct dlfb_data *dlfb, + struct usb_interface *intf) { char *desc; char *buf; @@ -1522,20 +1501,21 @@ static int dlfb_parse_vendor_descriptor(struct dlfb_data *dev, return false; desc = buf; - total_len = usb_get_descriptor(interface_to_usbdev(interface), + total_len = usb_get_descriptor(interface_to_usbdev(intf), 0x5f, /* vendor specific */ 0, desc, MAX_VENDOR_DESCRIPTOR_SIZE); /* if not found, look in configuration descriptor */ if (total_len < 0) { - if (0 == usb_get_extra_descriptor(interface->cur_altsetting, + if (0 == usb_get_extra_descriptor(intf->cur_altsetting, 0x5f, &desc)) total_len = (int) desc[0]; } if (total_len > 5) { - pr_info("vendor descriptor length:%x data:%11ph\n", total_len, - desc); + dev_info(&intf->dev, + "vendor descriptor length: %d data: %11ph\n", + total_len, desc); if ((desc[0] != total_len) || /* descriptor length */ (desc[1] != 0x5f) || /* vendor descriptor type */ @@ -1560,9 +1540,10 @@ static int dlfb_parse_vendor_descriptor(struct dlfb_data *dev, case 0x0200: { /* max_area */ u32 max_area; max_area = le32_to_cpu(*((u32 *)desc)); - pr_warn("DL chip limited to %d pixel modes\n", - max_area); - dev->sku_pixel_limit = max_area; + dev_warn(&intf->dev, + "DL chip limited to %d pixel modes\n", + max_area); + dlfb->sku_pixel_limit = max_area; break; } default: @@ -1571,14 +1552,15 @@ static int dlfb_parse_vendor_descriptor(struct dlfb_data *dev, desc += length; } } else { - pr_info("vendor descriptor not available (%d)\n", total_len); + dev_info(&intf->dev, "vendor descriptor not available (%d)\n", + total_len); } goto success; unrecognized: /* allow udlfb to load for now even if firmware unrecognized */ - pr_err("Unrecognized vendor firmware descriptor\n"); + dev_err(&intf->dev, "Unrecognized vendor firmware descriptor\n"); success: kfree(buf); @@ -1587,75 +1569,66 @@ success: static void dlfb_init_framebuffer_work(struct work_struct *work); -static int dlfb_usb_probe(struct usb_interface *interface, - const struct usb_device_id *id) +static int dlfb_usb_probe(struct usb_interface *intf, + const struct usb_device_id *id) { - struct usb_device *usbdev; - struct dlfb_data *dev; + struct dlfb_data *dlfb; int retval = -ENOMEM; + struct usb_device *usbdev = interface_to_usbdev(intf); /* usb initialization */ - - usbdev = interface_to_usbdev(interface); - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (dev == NULL) { - dev_err(&interface->dev, "dlfb_usb_probe: failed alloc of dev struct\n"); + dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); + if (!dlfb) { + dev_err(&intf->dev, "%s: failed to allocate dlfb\n", __func__); goto error; } - kref_init(&dev->kref); /* matching kref_put in usb .disconnect fn */ + kref_init(&dlfb->kref); /* matching kref_put in usb .disconnect fn */ - dev->udev = usbdev; - dev->gdev = &usbdev->dev; /* our generic struct device * */ - usb_set_intfdata(interface, dev); + dlfb->udev = usbdev; + usb_set_intfdata(intf, dlfb); - pr_info("%s %s - serial #%s\n", - usbdev->manufacturer, usbdev->product, usbdev->serial); - pr_info("vid_%04x&pid_%04x&rev_%04x driver's dlfb_data struct at %p\n", - le16_to_cpu(usbdev->descriptor.idVendor), - le16_to_cpu(usbdev->descriptor.idProduct), - le16_to_cpu(usbdev->descriptor.bcdDevice), dev); - pr_info("console enable=%d\n", console); - pr_info("fb_defio enable=%d\n", fb_defio); - pr_info("shadow enable=%d\n", shadow); + dev_dbg(&intf->dev, "console enable=%d\n", console); + dev_dbg(&intf->dev, "fb_defio enable=%d\n", fb_defio); + dev_dbg(&intf->dev, "shadow enable=%d\n", shadow); - dev->sku_pixel_limit = 2048 * 1152; /* default to maximum */ + dlfb->sku_pixel_limit = 2048 * 1152; /* default to maximum */ - if (!dlfb_parse_vendor_descriptor(dev, interface)) { - pr_err("firmware not recognized. Assume incompatible device\n"); + if (!dlfb_parse_vendor_descriptor(dlfb, intf)) { + dev_err(&intf->dev, + "firmware not recognized, incompatible device?\n"); goto error; } if (pixel_limit) { - pr_warn("DL chip limit of %d overridden" - " by module param to %d\n", - dev->sku_pixel_limit, pixel_limit); - dev->sku_pixel_limit = pixel_limit; + dev_warn(&intf->dev, + "DL chip limit of %d overridden to %d\n", + dlfb->sku_pixel_limit, pixel_limit); + dlfb->sku_pixel_limit = pixel_limit; } - if (!dlfb_alloc_urb_list(dev, WRITES_IN_FLIGHT, MAX_TRANSFER)) { + if (!dlfb_alloc_urb_list(dlfb, WRITES_IN_FLIGHT, MAX_TRANSFER)) { retval = -ENOMEM; - pr_err("dlfb_alloc_urb_list failed\n"); + dev_err(&intf->dev, "unable to allocate urb list\n"); goto error; } - kref_get(&dev->kref); /* matching kref_put in free_framebuffer_work */ + kref_get(&dlfb->kref); /* matching kref_put in free_framebuffer_work */ - /* We don't register a new USB class. Our client interface is fbdev */ + /* We don't register a new USB class. Our client interface is dlfbev */ /* Workitem keep things fast & simple during USB enumeration */ - INIT_DELAYED_WORK(&dev->init_framebuffer_work, + INIT_DELAYED_WORK(&dlfb->init_framebuffer_work, dlfb_init_framebuffer_work); - schedule_delayed_work(&dev->init_framebuffer_work, 0); + schedule_delayed_work(&dlfb->init_framebuffer_work, 0); return 0; error: - if (dev) { + if (dlfb) { - kref_put(&dev->kref, dlfb_free); /* last ref from kref_init */ + kref_put(&dlfb->kref, dlfb_free); /* last ref from kref_init */ /* dev has been deallocated. Do not dereference */ } @@ -1665,97 +1638,101 @@ error: static void dlfb_init_framebuffer_work(struct work_struct *work) { - struct dlfb_data *dev = container_of(work, struct dlfb_data, - init_framebuffer_work.work); + int i, retval; struct fb_info *info; - int retval; - int i; + const struct device_attribute *attr; + struct dlfb_data *dlfb = container_of(work, struct dlfb_data, + init_framebuffer_work.work); /* allocates framebuffer driver structure, not framebuffer memory */ - info = framebuffer_alloc(0, dev->gdev); + info = framebuffer_alloc(0, &dlfb->udev->dev); if (!info) { - pr_err("framebuffer_alloc failed\n"); + dev_err(&dlfb->udev->dev, "framebuffer_alloc failed\n"); goto error; } - dev->info = info; - info->par = dev; - info->pseudo_palette = dev->pseudo_palette; + dlfb->info = info; + info->par = dlfb; + info->pseudo_palette = dlfb->pseudo_palette; info->fbops = &dlfb_ops; retval = fb_alloc_cmap(&info->cmap, 256, 0); if (retval < 0) { - pr_err("fb_alloc_cmap failed %x\n", retval); + dev_err(info->device, "cmap allocation failed: %d\n", retval); goto error; } - INIT_DELAYED_WORK(&dev->free_framebuffer_work, + INIT_DELAYED_WORK(&dlfb->free_framebuffer_work, dlfb_free_framebuffer_work); INIT_LIST_HEAD(&info->modelist); - retval = dlfb_setup_modes(dev, info, NULL, 0); + retval = dlfb_setup_modes(dlfb, info, NULL, 0); if (retval != 0) { - pr_err("unable to find common mode for display and adapter\n"); + dev_err(info->device, + "unable to find common mode for display and adapter\n"); goto error; } /* ready to begin using device */ - atomic_set(&dev->usb_active, 1); - dlfb_select_std_channel(dev); + atomic_set(&dlfb->usb_active, 1); + dlfb_select_std_channel(dlfb); dlfb_ops_check_var(&info->var, info); dlfb_ops_set_par(info); retval = register_framebuffer(info); if (retval < 0) { - pr_err("register_framebuffer failed %d\n", retval); + dev_err(info->device, "unable to register framebuffer: %d\n", + retval); goto error; } for (i = 0; i < ARRAY_SIZE(fb_device_attrs); i++) { - retval = device_create_file(info->dev, &fb_device_attrs[i]); - if (retval) { - pr_warn("device_create_file failed %d\n", retval); - } + attr = &fb_device_attrs[i]; + retval = device_create_file(info->dev, attr); + if (retval) + dev_warn(info->device, + "failed to create '%s' attribute: %d\n", + attr->attr.name, retval); } retval = device_create_bin_file(info->dev, &edid_attr); - if (retval) { - pr_warn("device_create_bin_file failed %d\n", retval); - } - - pr_info("DisplayLink USB device /dev/fb%d attached. %dx%d resolution." - " Using %dK framebuffer memory\n", info->node, - info->var.xres, info->var.yres, - ((dev->backing_buffer) ? - info->fix.smem_len * 2 : info->fix.smem_len) >> 10); + if (retval) + dev_warn(info->device, "failed to create '%s' attribute: %d\n", + edid_attr.attr.name, retval); + + dev_info(info->device, + "%s is DisplayLink USB device (%dx%d, %dK framebuffer memory)\n", + dev_name(info->dev), info->var.xres, info->var.yres, + ((dlfb->backing_buffer) ? + info->fix.smem_len * 2 : info->fix.smem_len) >> 10); return; error: - dlfb_free_framebuffer(dev); + dlfb_free_framebuffer(dlfb); } -static void dlfb_usb_disconnect(struct usb_interface *interface) +static void dlfb_usb_disconnect(struct usb_interface *intf) { - struct dlfb_data *dev; + struct dlfb_data *dlfb; struct fb_info *info; int i; - dev = usb_get_intfdata(interface); - info = dev->info; + dlfb = usb_get_intfdata(intf); + info = dlfb->info; - pr_info("USB disconnect starting\n"); + dev_dbg(&intf->dev, "USB disconnect starting\n"); /* we virtualize until all fb clients release. Then we free */ - dev->virtualized = true; + dlfb->virtualized = true; /* When non-active we'll update virtual framebuffer, but no new urbs */ - atomic_set(&dev->usb_active, 0); + atomic_set(&dlfb->usb_active, 0); /* this function will wait for all in-flight urbs to complete */ - dlfb_free_urb_list(dev); + dlfb_free_urb_list(dlfb); if (info) { /* remove udlfb's sysfs interfaces */ @@ -1765,20 +1742,17 @@ static void dlfb_usb_disconnect(struct usb_interface *interface) unlink_framebuffer(info); } - usb_set_intfdata(interface, NULL); - dev->udev = NULL; - dev->gdev = NULL; + usb_set_intfdata(intf, NULL); + dlfb->udev = NULL; /* if clients still have us open, will be freed on last close */ - if (dev->fb_count == 0) - schedule_delayed_work(&dev->free_framebuffer_work, 0); + if (dlfb->fb_count == 0) + schedule_delayed_work(&dlfb->free_framebuffer_work, 0); /* release reference taken by kref_init in probe() */ - kref_put(&dev->kref, dlfb_free); + kref_put(&dlfb->kref, dlfb_free); /* consider dlfb_data freed */ - - return; } static struct usb_driver dlfb_driver = { @@ -1793,26 +1767,32 @@ module_usb_driver(dlfb_driver); static void dlfb_urb_completion(struct urb *urb) { struct urb_node *unode = urb->context; - struct dlfb_data *dev = unode->dev; + struct dlfb_data *dlfb = unode->dlfb; unsigned long flags; - /* sync/async unlink faults aren't errors */ - if (urb->status) { - if (!(urb->status == -ENOENT || - urb->status == -ECONNRESET || - urb->status == -ESHUTDOWN)) { - pr_err("%s - nonzero write bulk status received: %d\n", - __func__, urb->status); - atomic_set(&dev->lost_pixels, 1); - } + switch (urb->status) { + case 0: + /* success */ + break; + case -ECONNRESET: + case -ENOENT: + case -ESHUTDOWN: + /* sync/async unlink faults aren't errors */ + break; + default: + dev_err(&dlfb->udev->dev, + "%s - nonzero write bulk status received: %d\n", + __func__, urb->status); + atomic_set(&dlfb->lost_pixels, 1); + break; } - urb->transfer_buffer_length = dev->urbs.size; /* reset to actual */ + urb->transfer_buffer_length = dlfb->urbs.size; /* reset to actual */ - spin_lock_irqsave(&dev->urbs.lock, flags); - list_add_tail(&unode->entry, &dev->urbs.list); - dev->urbs.available++; - spin_unlock_irqrestore(&dev->urbs.lock, flags); + spin_lock_irqsave(&dlfb->urbs.lock, flags); + list_add_tail(&unode->entry, &dlfb->urbs.list); + dlfb->urbs.available++; + spin_unlock_irqrestore(&dlfb->urbs.lock, flags); /* * When using fb_defio, we deadlock if up() is called @@ -1821,65 +1801,63 @@ static void dlfb_urb_completion(struct urb *urb) if (fb_defio) schedule_delayed_work(&unode->release_urb_work, 0); else - up(&dev->urbs.limit_sem); + up(&dlfb->urbs.limit_sem); } -static void dlfb_free_urb_list(struct dlfb_data *dev) +static void dlfb_free_urb_list(struct dlfb_data *dlfb) { - int count = dev->urbs.count; + int count = dlfb->urbs.count; struct list_head *node; struct urb_node *unode; struct urb *urb; int ret; unsigned long flags; - pr_notice("Freeing all render urbs\n"); - /* keep waiting and freeing, until we've got 'em all */ while (count--) { /* Getting interrupted means a leak, but ok at disconnect */ - ret = down_interruptible(&dev->urbs.limit_sem); + ret = down_interruptible(&dlfb->urbs.limit_sem); if (ret) break; - spin_lock_irqsave(&dev->urbs.lock, flags); + spin_lock_irqsave(&dlfb->urbs.lock, flags); - node = dev->urbs.list.next; /* have reserved one with sem */ + node = dlfb->urbs.list.next; /* have reserved one with sem */ list_del_init(node); - spin_unlock_irqrestore(&dev->urbs.lock, flags); + spin_unlock_irqrestore(&dlfb->urbs.lock, flags); unode = list_entry(node, struct urb_node, entry); urb = unode->urb; /* Free each separately allocated piece */ - usb_free_coherent(urb->dev, dev->urbs.size, + usb_free_coherent(urb->dev, dlfb->urbs.size, urb->transfer_buffer, urb->transfer_dma); usb_free_urb(urb); kfree(node); } - dev->urbs.count = 0; + dlfb->urbs.count = 0; } -static int dlfb_alloc_urb_list(struct dlfb_data *dev, int count, size_t size) +static int dlfb_alloc_urb_list(struct dlfb_data *dlfb, int count, size_t size) { int i = 0; struct urb *urb; struct urb_node *unode; char *buf; - spin_lock_init(&dev->urbs.lock); + spin_lock_init(&dlfb->urbs.lock); - dev->urbs.size = size; - INIT_LIST_HEAD(&dev->urbs.list); + dlfb->urbs.size = size; + INIT_LIST_HEAD(&dlfb->urbs.list); while (i < count) { - unode = kzalloc(sizeof(struct urb_node), GFP_KERNEL); + unode = kzalloc(sizeof(*unode), GFP_KERNEL); if (!unode) break; - unode->dev = dev; + unode->dlfb = dlfb; INIT_DELAYED_WORK(&unode->release_urb_work, dlfb_release_urb_work); @@ -1891,7 +1869,7 @@ static int dlfb_alloc_urb_list(struct dlfb_data *dev, int count, size_t size) } unode->urb = urb; - buf = usb_alloc_coherent(dev->udev, MAX_TRANSFER, GFP_KERNEL, + buf = usb_alloc_coherent(dlfb->udev, MAX_TRANSFER, GFP_KERNEL, &urb->transfer_dma); if (!buf) { kfree(unode); @@ -1900,69 +1878,64 @@ static int dlfb_alloc_urb_list(struct dlfb_data *dev, int count, size_t size) } /* urb->transfer_buffer_length set to actual before submit */ - usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 1), + usb_fill_bulk_urb(urb, dlfb->udev, usb_sndbulkpipe(dlfb->udev, 1), buf, size, dlfb_urb_completion, unode); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; - list_add_tail(&unode->entry, &dev->urbs.list); + list_add_tail(&unode->entry, &dlfb->urbs.list); i++; } - sema_init(&dev->urbs.limit_sem, i); - dev->urbs.count = i; - dev->urbs.available = i; - - pr_notice("allocated %d %d byte urbs\n", i, (int) size); + sema_init(&dlfb->urbs.limit_sem, i); + dlfb->urbs.count = i; + dlfb->urbs.available = i; return i; } -static struct urb *dlfb_get_urb(struct dlfb_data *dev) +static struct urb *dlfb_get_urb(struct dlfb_data *dlfb) { int ret; struct list_head *entry; struct urb_node *unode; - struct urb *urb = NULL; unsigned long flags; /* Wait for an in-flight buffer to complete and get re-queued */ - ret = down_timeout(&dev->urbs.limit_sem, GET_URB_TIMEOUT); + ret = down_timeout(&dlfb->urbs.limit_sem, GET_URB_TIMEOUT); if (ret) { - atomic_set(&dev->lost_pixels, 1); - pr_warn("wait for urb interrupted: %x available: %d\n", - ret, dev->urbs.available); - goto error; + atomic_set(&dlfb->lost_pixels, 1); + dev_warn(&dlfb->udev->dev, + "wait for urb interrupted: %d available: %d\n", + ret, dlfb->urbs.available); + return NULL; } - spin_lock_irqsave(&dev->urbs.lock, flags); + spin_lock_irqsave(&dlfb->urbs.lock, flags); - BUG_ON(list_empty(&dev->urbs.list)); /* reserved one with limit_sem */ - entry = dev->urbs.list.next; + BUG_ON(list_empty(&dlfb->urbs.list)); /* reserved one with limit_sem */ + entry = dlfb->urbs.list.next; list_del_init(entry); - dev->urbs.available--; + dlfb->urbs.available--; - spin_unlock_irqrestore(&dev->urbs.lock, flags); + spin_unlock_irqrestore(&dlfb->urbs.lock, flags); unode = list_entry(entry, struct urb_node, entry); - urb = unode->urb; - -error: - return urb; + return unode->urb; } -static int dlfb_submit_urb(struct dlfb_data *dev, struct urb *urb, size_t len) +static int dlfb_submit_urb(struct dlfb_data *dlfb, struct urb *urb, size_t len) { int ret; - BUG_ON(len > dev->urbs.size); + BUG_ON(len > dlfb->urbs.size); urb->transfer_buffer_length = len; /* set to actual payload len */ ret = usb_submit_urb(urb, GFP_KERNEL); if (ret) { dlfb_urb_completion(urb); /* because no one else will */ - atomic_set(&dev->lost_pixels, 1); - pr_err("usb_submit_urb error %x\n", ret); + atomic_set(&dlfb->lost_pixels, 1); + dev_err(&dlfb->udev->dev, "submit urb error: %d\n", ret); } return ret; } diff --git a/drivers/video/fbdev/vfb.c b/drivers/video/fbdev/vfb.c index da653a080394..54127905bfe7 100644 --- a/drivers/video/fbdev/vfb.c +++ b/drivers/video/fbdev/vfb.c @@ -239,8 +239,23 @@ static int vfb_check_var(struct fb_var_screeninfo *var, */ static int vfb_set_par(struct fb_info *info) { + switch (info->var.bits_per_pixel) { + case 1: + info->fix.visual = FB_VISUAL_MONO01; + break; + case 8: + info->fix.visual = FB_VISUAL_PSEUDOCOLOR; + break; + case 16: + case 24: + case 32: + info->fix.visual = FB_VISUAL_TRUECOLOR; + break; + } + info->fix.line_length = get_line_length(info->var.xres_virtual, info->var.bits_per_pixel); + return 0; } @@ -450,6 +465,8 @@ static int vfb_probe(struct platform_device *dev) goto err2; platform_set_drvdata(dev, info); + vfb_set_par(info); + fb_info(info, "Virtual frame buffer device, using %ldK of video memory\n", videomemorysize >> 10); return 0; diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c index 5f0690c8fc93..2c6a576ed84c 100644 --- a/drivers/video/fbdev/vga16fb.c +++ b/drivers/video/fbdev/vga16fb.c @@ -1055,7 +1055,6 @@ static void vga16fb_copyarea(struct fb_info *info, const struct fb_copyarea *are case FB_TYPE_VGA_PLANES: if (info->fix.type_aux == FB_AUX_VGA_PLANES_VGA4) { width = width/8; - height = height; line_ofs = info->fix.line_length - width; setmode(1); diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c index 1a1176bf0906..5c5cd2923041 100644 --- a/drivers/video/fbdev/vt8500lcdfb.c +++ b/drivers/video/fbdev/vt8500lcdfb.c @@ -289,10 +289,8 @@ static int vt8500lcd_probe(struct platform_device *pdev) fbi = devm_kzalloc(&pdev->dev, sizeof(struct vt8500lcd_info) + sizeof(u32) * 16, GFP_KERNEL); - if (!fbi) { - dev_err(&pdev->dev, "Failed to initialize framebuffer device\n"); + if (!fbi) return -ENOMEM; - } strcpy(fbi->fb.fix.id, "VT8500 LCD"); diff --git a/drivers/video/fbdev/wm8505fb.c b/drivers/video/fbdev/wm8505fb.c index 253ffe9baab2..8f0d5379861d 100644 --- a/drivers/video/fbdev/wm8505fb.c +++ b/drivers/video/fbdev/wm8505fb.c @@ -276,10 +276,8 @@ static int wm8505fb_probe(struct platform_device *pdev) fbi = devm_kzalloc(&pdev->dev, sizeof(struct wm8505fb_info) + sizeof(u32) * 16, GFP_KERNEL); - if (!fbi) { - dev_err(&pdev->dev, "Failed to initialize framebuffer device\n"); + if (!fbi) return -ENOMEM; - } strcpy(fbi->fb.fix.id, DRIVER_NAME); diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c index b0597bef4555..4e05d7f711fe 100644 --- a/drivers/virt/fsl_hypervisor.c +++ b/drivers/virt/fsl_hypervisor.c @@ -574,7 +574,7 @@ static __poll_t fsl_hv_poll(struct file *filp, struct poll_table_struct *p) spin_lock_irqsave(&dbq->lock, flags); poll_wait(filp, &dbq->wait, p); - mask = (dbq->head == dbq->tail) ? 0 : (POLLIN | POLLRDNORM); + mask = (dbq->head == dbq->tail) ? 0 : (EPOLLIN | EPOLLRDNORM); spin_unlock_irqrestore(&dbq->lock, flags); diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index cff773f15b7e..35897649c24f 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -5,7 +5,11 @@ config VIRTIO bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG or CONFIG_S390_GUEST. -menu "Virtio drivers" +menuconfig VIRTIO_MENU + bool "Virtio drivers" + default y + +if VIRTIO_MENU config VIRTIO_PCI tristate "PCI driver for virtio devices" @@ -79,4 +83,4 @@ config VIRTIO_MMIO_CMDLINE_DEVICES If unsure, say 'N'. -endmenu +endif # VIRTIO_MENU diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index bf7ff3934d7f..59e36ef4920f 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -303,11 +303,21 @@ void unregister_virtio_driver(struct virtio_driver *driver) } EXPORT_SYMBOL_GPL(unregister_virtio_driver); +/** + * register_virtio_device - register virtio device + * @dev : virtio device to be registered + * + * On error, the caller must call put_device on &@dev->dev (and not kfree), + * as another code path may have obtained a reference to @dev. + * + * Returns: 0 on suceess, -error on failure + */ int register_virtio_device(struct virtio_device *dev) { int err; dev->dev.bus = &virtio_bus; + device_initialize(&dev->dev); /* Assign a unique device index and hence name. */ err = ida_simple_get(&virtio_index_ida, 0, 0, GFP_KERNEL); @@ -330,9 +340,11 @@ int register_virtio_device(struct virtio_device *dev) INIT_LIST_HEAD(&dev->vqs); - /* device_register() causes the bus infrastructure to look for a - * matching driver. */ - err = device_register(&dev->dev); + /* + * device_add() causes the bus infrastructure to look for a matching + * driver. + */ + err = device_add(&dev->dev); if (err) ida_simple_remove(&virtio_index_ida, dev->index); out: diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index a1fb52cb3f0a..dfe5684000be 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -257,11 +257,13 @@ static unsigned int update_balloon_stats(struct virtio_balloon *vb) struct sysinfo i; unsigned int idx = 0; long available; + unsigned long caches; all_vm_events(events); si_meminfo(&i); available = si_mem_available(); + caches = global_node_page_state(NR_FILE_PAGES); #ifdef CONFIG_VM_EVENT_COUNTERS update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN, @@ -277,6 +279,8 @@ static unsigned int update_balloon_stats(struct virtio_balloon *vb) pages_to_bytes(i.totalram)); update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL, pages_to_bytes(available)); + update_stat(vb, idx++, VIRTIO_BALLOON_S_CACHES, + pages_to_bytes(caches)); return idx; } diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index c92131edfaba..67763d3c7abf 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -662,10 +662,8 @@ static int vm_cmdline_set(const char *device, pdev = platform_device_register_resndata(&vm_cmdline_parent, "virtio-mmio", vm_cmdline_id++, resources, ARRAY_SIZE(resources), NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_ERR_OR_ZERO(pdev); } static int vm_cmdline_get_device(struct device *dev, void *data) @@ -725,7 +723,7 @@ static void vm_unregister_cmdline_devices(void) /* Platform driver */ -static struct of_device_id virtio_mmio_match[] = { +static const struct of_device_id virtio_mmio_match[] = { { .compatible = "virtio,mmio", }, {}, }; diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 1c4797e53f68..48d4d1cf1cb6 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -513,7 +513,7 @@ static void virtio_pci_release_dev(struct device *_d) static int virtio_pci_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) { - struct virtio_pci_device *vp_dev; + struct virtio_pci_device *vp_dev, *reg_dev = NULL; int rc; /* allocate our structure and fill it out */ @@ -551,6 +551,7 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, pci_set_master(pci_dev); rc = register_virtio_device(&vp_dev->vdev); + reg_dev = vp_dev; if (rc) goto err_register; @@ -564,7 +565,10 @@ err_register: err_probe: pci_disable_device(pci_dev); err_enable_device: - kfree(vp_dev); + if (reg_dev) + put_device(&vp_dev->vdev.dev); + else + kfree(vp_dev); return rc; } diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 5bf613d3b7d6..aff773bcebdb 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -328,16 +328,18 @@ config 977_WATCHDOG Not sure? It's safe to say N. -config GEMINI_WATCHDOG - tristate "Gemini watchdog" - depends on ARCH_GEMINI +config FTWDT010_WATCHDOG + tristate "Faraday Technology FTWDT010 watchdog" + depends on ARM || COMPILE_TEST select WATCHDOG_CORE + default ARCH_GEMINI help - Say Y here if to include support for the watchdog timer - embedded in the Cortina Systems Gemini family of devices. + Say Y here if to include support for the Faraday Technology + FTWDT010 watchdog timer embedded in the Cortina Systems Gemini + family of devices. To compile this driver as a module, choose M here: the - module will be called gemini_wdt. + module will be called ftwdt010_wdt. config IXP4XX_WATCHDOG tristate "IXP4xx Watchdog" @@ -748,12 +750,12 @@ config RENESAS_RZAWDT Renesas RZ/A SoCs. These watchdogs can be used to reset a system. config ASPEED_WATCHDOG - tristate "Aspeed 2400 watchdog support" + tristate "Aspeed BMC watchdog support" depends on ARCH_ASPEED || COMPILE_TEST select WATCHDOG_CORE help Say Y here to include support for the watchdog timer - in Apseed BMC SoCs. + in Aspeed BMC SoCs. This driver is required to reboot the SoC. @@ -794,14 +796,23 @@ config UNIPHIER_WATCHDOG To compile this driver as a module, choose M here: the module will be called uniphier_wdt. -# AVR32 Architecture +config RTD119X_WATCHDOG + bool "Realtek RTD119x/RTD129x watchdog support" + depends on ARCH_REALTEK || COMPILE_TEST + depends on OF + select WATCHDOG_CORE + default ARCH_REALTEK + help + Say Y here to include support for the watchdog timer in + Realtek RTD1295 SoCs. -config AT32AP700X_WDT - tristate "AT32AP700x watchdog" - depends on CPU_AT32AP700X || COMPILE_TEST +config SPRD_WATCHDOG + tristate "Spreadtrum watchdog support" + depends on ARCH_SPRD || COMPILE_TEST + select WATCHDOG_CORE help - Watchdog timer embedded into AT32AP700x devices. This will reboot - your system when the timeout is reached. + Say Y here to include watchdog timer supported + by Spreadtrum system. # BLACKFIN Architecture @@ -1458,7 +1469,7 @@ config RC32434_WDT config INDYDOG tristate "Indy/I2 Hardware Watchdog" - depends on SGI_HAS_INDYDOG || (MIPS && COMPILE_TEST) + depends on SGI_HAS_INDYDOG help Hardware driver for the Indy's/I2's watchdog. This is a watchdog timer that will reboot the machine after a 60 second diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index 135c5e81f25e..0474d38aa854 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -46,7 +46,7 @@ obj-$(CONFIG_OMAP_WATCHDOG) += omap_wdt.o obj-$(CONFIG_TWL4030_WATCHDOG) += twl4030_wdt.o obj-$(CONFIG_21285_WATCHDOG) += wdt285.o obj-$(CONFIG_977_WATCHDOG) += wdt977.o -obj-$(CONFIG_GEMINI_WATCHDOG) += gemini_wdt.o +obj-$(CONFIG_FTWDT010_WATCHDOG) += ftwdt010_wdt.o obj-$(CONFIG_IXP4XX_WATCHDOG) += ixp4xx_wdt.o obj-$(CONFIG_KS8695_WATCHDOG) += ks8695_wdt.o obj-$(CONFIG_S3C2410_WATCHDOG) += s3c2410_wdt.o @@ -88,9 +88,8 @@ obj-$(CONFIG_ASPEED_WATCHDOG) += aspeed_wdt.o obj-$(CONFIG_ZX2967_WATCHDOG) += zx2967_wdt.o obj-$(CONFIG_STM32_WATCHDOG) += stm32_iwdg.o obj-$(CONFIG_UNIPHIER_WATCHDOG) += uniphier_wdt.o - -# AVR32 Architecture -obj-$(CONFIG_AT32AP700X_WDT) += at32ap700x_wdt.o +obj-$(CONFIG_RTD119X_WATCHDOG) += rtd119x_wdt.o +obj-$(CONFIG_SPRD_WATCHDOG) += sprd_wdt.o # BLACKFIN Architecture obj-$(CONFIG_BFIN_WDT) += bfin_wdt.o diff --git a/drivers/watchdog/advantechwdt.c b/drivers/watchdog/advantechwdt.c index 7d7db0c5a64e..f61944369c1a 100644 --- a/drivers/watchdog/advantechwdt.c +++ b/drivers/watchdog/advantechwdt.c @@ -181,7 +181,7 @@ static long advwdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (advwdt_set_heartbeat(new_timeout)) return -EINVAL; advwdt_ping(); - /* Fall */ + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(timeout, p); default: diff --git a/drivers/watchdog/alim1535_wdt.c b/drivers/watchdog/alim1535_wdt.c index 3a17fbd39f8a..60f0c2eb8531 100644 --- a/drivers/watchdog/alim1535_wdt.c +++ b/drivers/watchdog/alim1535_wdt.c @@ -223,8 +223,8 @@ static long ali_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (ali_settimer(new_timeout)) return -EINVAL; ali_keepalive(); - /* Fall */ } + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(timeout, p); default: diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c index 79cc766cd30f..ca5b91e2eb92 100644 --- a/drivers/watchdog/aspeed_wdt.c +++ b/drivers/watchdog/aspeed_wdt.c @@ -243,9 +243,13 @@ static int aspeed_wdt_probe(struct platform_device *pdev) if (of_property_read_bool(np, "aspeed,external-signal")) wdt->ctrl |= WDT_CTRL_WDT_EXT; - writel(wdt->ctrl, wdt->base + WDT_CTRL); - if (readl(wdt->base + WDT_CTRL) & WDT_CTRL_ENABLE) { + /* + * The watchdog is running, but invoke aspeed_wdt_start() to + * write wdt->ctrl to WDT_CTRL to ensure the watchdog's + * configuration conforms to the driver's expectations. + * Primarily, ensure we're using the 1MHz clock source. + */ aspeed_wdt_start(&wdt->wdd); set_bit(WDOG_HW_RUNNING, &wdt->wdd.status); } @@ -312,7 +316,18 @@ static struct platform_driver aspeed_watchdog_driver = { .of_match_table = of_match_ptr(aspeed_wdt_of_table), }, }; -module_platform_driver(aspeed_watchdog_driver); + +static int __init aspeed_wdt_init(void) +{ + return platform_driver_register(&aspeed_watchdog_driver); +} +arch_initcall(aspeed_wdt_init); + +static void __exit aspeed_wdt_exit(void) +{ + platform_driver_unregister(&aspeed_watchdog_driver); +} +module_exit(aspeed_wdt_exit); MODULE_DESCRIPTION("Aspeed Watchdog Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/watchdog/at32ap700x_wdt.c b/drivers/watchdog/at32ap700x_wdt.c deleted file mode 100644 index 81ba8920f127..000000000000 --- a/drivers/watchdog/at32ap700x_wdt.c +++ /dev/null @@ -1,433 +0,0 @@ -/* - * Watchdog driver for Atmel AT32AP700X devices - * - * Copyright (C) 2005-2006 Atmel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * - * Errata: WDT Clear is blocked after WDT Reset - * - * A watchdog timer event will, after reset, block writes to the WDT_CLEAR - * register, preventing the program to clear the next Watchdog Timer Reset. - * - * If you still want to use the WDT after a WDT reset a small code can be - * insterted at the startup checking the AVR32_PM.rcause register for WDT reset - * and use a GPIO pin to reset the system. This method requires that one of the - * GPIO pins are available and connected externally to the RESET_N pin. After - * the GPIO pin has pulled down the reset line the GPIO will be reset and leave - * the pin tristated with pullup. - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/miscdevice.h> -#include <linux/fs.h> -#include <linux/platform_device.h> -#include <linux/watchdog.h> -#include <linux/uaccess.h> -#include <linux/io.h> -#include <linux/spinlock.h> -#include <linux/slab.h> - -#define TIMEOUT_MIN 1 -#define TIMEOUT_MAX 2 -#define TIMEOUT_DEFAULT TIMEOUT_MAX - -/* module parameters */ -static int timeout = TIMEOUT_DEFAULT; -module_param(timeout, int, 0); -MODULE_PARM_DESC(timeout, - "Timeout value. Limited to be 1 or 2 seconds. (default=" - __MODULE_STRING(TIMEOUT_DEFAULT) ")"); - -static bool nowayout = WATCHDOG_NOWAYOUT; -module_param(nowayout, bool, 0); -MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" - __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); - -/* Watchdog registers and write/read macro */ -#define WDT_CTRL 0x00 -#define WDT_CTRL_EN 0 -#define WDT_CTRL_PSEL 8 -#define WDT_CTRL_KEY 24 - -#define WDT_CLR 0x04 - -#define WDT_RCAUSE 0x10 -#define WDT_RCAUSE_POR 0 -#define WDT_RCAUSE_EXT 2 -#define WDT_RCAUSE_WDT 3 -#define WDT_RCAUSE_JTAG 4 -#define WDT_RCAUSE_SERP 5 - -#define WDT_BIT(name) (1 << WDT_##name) -#define WDT_BF(name, value) ((value) << WDT_##name) - -#define wdt_readl(dev, reg) \ - __raw_readl((dev)->regs + WDT_##reg) -#define wdt_writel(dev, reg, value) \ - __raw_writel((value), (dev)->regs + WDT_##reg) - -struct wdt_at32ap700x { - void __iomem *regs; - spinlock_t io_lock; - int timeout; - int boot_status; - unsigned long users; - struct miscdevice miscdev; -}; - -static struct wdt_at32ap700x *wdt; -static char expect_release; - -/* - * Disable the watchdog. - */ -static inline void at32_wdt_stop(void) -{ - unsigned long psel; - - spin_lock(&wdt->io_lock); - psel = wdt_readl(wdt, CTRL) & WDT_BF(CTRL_PSEL, 0x0f); - wdt_writel(wdt, CTRL, psel | WDT_BF(CTRL_KEY, 0x55)); - wdt_writel(wdt, CTRL, psel | WDT_BF(CTRL_KEY, 0xaa)); - spin_unlock(&wdt->io_lock); -} - -/* - * Enable and reset the watchdog. - */ -static inline void at32_wdt_start(void) -{ - /* 0xf is 2^16 divider = 2 sec, 0xe is 2^15 divider = 1 sec */ - unsigned long psel = (wdt->timeout > 1) ? 0xf : 0xe; - - spin_lock(&wdt->io_lock); - wdt_writel(wdt, CTRL, WDT_BIT(CTRL_EN) - | WDT_BF(CTRL_PSEL, psel) - | WDT_BF(CTRL_KEY, 0x55)); - wdt_writel(wdt, CTRL, WDT_BIT(CTRL_EN) - | WDT_BF(CTRL_PSEL, psel) - | WDT_BF(CTRL_KEY, 0xaa)); - spin_unlock(&wdt->io_lock); -} - -/* - * Pat the watchdog timer. - */ -static inline void at32_wdt_pat(void) -{ - spin_lock(&wdt->io_lock); - wdt_writel(wdt, CLR, 0x42); - spin_unlock(&wdt->io_lock); -} - -/* - * Watchdog device is opened, and watchdog starts running. - */ -static int at32_wdt_open(struct inode *inode, struct file *file) -{ - if (test_and_set_bit(1, &wdt->users)) - return -EBUSY; - - at32_wdt_start(); - return nonseekable_open(inode, file); -} - -/* - * Close the watchdog device. - */ -static int at32_wdt_close(struct inode *inode, struct file *file) -{ - if (expect_release == 42) { - at32_wdt_stop(); - } else { - dev_dbg(wdt->miscdev.parent, - "unexpected close, not stopping watchdog!\n"); - at32_wdt_pat(); - } - clear_bit(1, &wdt->users); - expect_release = 0; - return 0; -} - -/* - * Change the watchdog time interval. - */ -static int at32_wdt_settimeout(int time) -{ - /* - * All counting occurs at 1 / SLOW_CLOCK (32 kHz) and max prescaler is - * 2 ^ 16 allowing up to 2 seconds timeout. - */ - if ((time < TIMEOUT_MIN) || (time > TIMEOUT_MAX)) - return -EINVAL; - - /* - * Set new watchdog time. It will be used when at32_wdt_start() is - * called. - */ - wdt->timeout = time; - return 0; -} - -/* - * Get the watchdog status. - */ -static int at32_wdt_get_status(void) -{ - int rcause; - int status = 0; - - rcause = wdt_readl(wdt, RCAUSE); - - switch (rcause) { - case WDT_BIT(RCAUSE_EXT): - status = WDIOF_EXTERN1; - break; - case WDT_BIT(RCAUSE_WDT): - status = WDIOF_CARDRESET; - break; - case WDT_BIT(RCAUSE_POR): /* fall through */ - case WDT_BIT(RCAUSE_JTAG): /* fall through */ - case WDT_BIT(RCAUSE_SERP): /* fall through */ - default: - break; - } - - return status; -} - -static const struct watchdog_info at32_wdt_info = { - .identity = "at32ap700x watchdog", - .options = WDIOF_SETTIMEOUT | - WDIOF_KEEPALIVEPING | - WDIOF_MAGICCLOSE, -}; - -/* - * Handle commands from user-space. - */ -static long at32_wdt_ioctl(struct file *file, - unsigned int cmd, unsigned long arg) -{ - int ret = -ENOTTY; - int time; - void __user *argp = (void __user *)arg; - int __user *p = argp; - - switch (cmd) { - case WDIOC_GETSUPPORT: - ret = copy_to_user(argp, &at32_wdt_info, - sizeof(at32_wdt_info)) ? -EFAULT : 0; - break; - case WDIOC_GETSTATUS: - ret = put_user(0, p); - break; - case WDIOC_GETBOOTSTATUS: - ret = put_user(wdt->boot_status, p); - break; - case WDIOC_SETOPTIONS: - ret = get_user(time, p); - if (ret) - break; - if (time & WDIOS_DISABLECARD) - at32_wdt_stop(); - if (time & WDIOS_ENABLECARD) - at32_wdt_start(); - ret = 0; - break; - case WDIOC_KEEPALIVE: - at32_wdt_pat(); - ret = 0; - break; - case WDIOC_SETTIMEOUT: - ret = get_user(time, p); - if (ret) - break; - ret = at32_wdt_settimeout(time); - if (ret) - break; - /* Enable new time value */ - at32_wdt_start(); - /* fall through */ - case WDIOC_GETTIMEOUT: - ret = put_user(wdt->timeout, p); - break; - } - - return ret; -} - -static ssize_t at32_wdt_write(struct file *file, const char __user *data, - size_t len, loff_t *ppos) -{ - /* See if we got the magic character 'V' and reload the timer */ - if (len) { - if (!nowayout) { - size_t i; - - /* - * note: just in case someone wrote the magic - * character five months ago... - */ - expect_release = 0; - - /* - * scan to see whether or not we got the magic - * character - */ - for (i = 0; i != len; i++) { - char c; - if (get_user(c, data + i)) - return -EFAULT; - if (c == 'V') - expect_release = 42; - } - } - /* someone wrote to us, we should pat the watchdog */ - at32_wdt_pat(); - } - return len; -} - -static const struct file_operations at32_wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .unlocked_ioctl = at32_wdt_ioctl, - .open = at32_wdt_open, - .release = at32_wdt_close, - .write = at32_wdt_write, -}; - -static int __init at32_wdt_probe(struct platform_device *pdev) -{ - struct resource *regs; - int ret; - - if (wdt) { - dev_dbg(&pdev->dev, "only 1 wdt instance supported.\n"); - return -EBUSY; - } - - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!regs) { - dev_dbg(&pdev->dev, "missing mmio resource\n"); - return -ENXIO; - } - - wdt = devm_kzalloc(&pdev->dev, sizeof(struct wdt_at32ap700x), - GFP_KERNEL); - if (!wdt) - return -ENOMEM; - - wdt->regs = devm_ioremap(&pdev->dev, regs->start, resource_size(regs)); - if (!wdt->regs) { - ret = -ENOMEM; - dev_dbg(&pdev->dev, "could not map I/O memory\n"); - goto err_free; - } - - spin_lock_init(&wdt->io_lock); - wdt->boot_status = at32_wdt_get_status(); - - /* Work-around for watchdog silicon errata. */ - if (wdt->boot_status & WDIOF_CARDRESET) { - dev_info(&pdev->dev, "CPU must be reset with external " - "reset or POR due to silicon errata.\n"); - ret = -EIO; - goto err_free; - } else { - wdt->users = 0; - } - - wdt->miscdev.minor = WATCHDOG_MINOR; - wdt->miscdev.name = "watchdog"; - wdt->miscdev.fops = &at32_wdt_fops; - wdt->miscdev.parent = &pdev->dev; - - platform_set_drvdata(pdev, wdt); - - if (at32_wdt_settimeout(timeout)) { - at32_wdt_settimeout(TIMEOUT_DEFAULT); - dev_dbg(&pdev->dev, - "default timeout invalid, set to %d sec.\n", - TIMEOUT_DEFAULT); - } - - ret = misc_register(&wdt->miscdev); - if (ret) { - dev_dbg(&pdev->dev, "failed to register wdt miscdev\n"); - goto err_free; - } - - dev_info(&pdev->dev, - "AT32AP700X WDT at 0x%p, timeout %d sec (nowayout=%d)\n", - wdt->regs, wdt->timeout, nowayout); - - return 0; - -err_free: - wdt = NULL; - return ret; -} - -static int __exit at32_wdt_remove(struct platform_device *pdev) -{ - if (wdt && platform_get_drvdata(pdev) == wdt) { - /* Stop the timer before we leave */ - if (!nowayout) - at32_wdt_stop(); - - misc_deregister(&wdt->miscdev); - wdt = NULL; - } - return 0; -} - -static void at32_wdt_shutdown(struct platform_device *pdev) -{ - at32_wdt_stop(); -} - -#ifdef CONFIG_PM -static int at32_wdt_suspend(struct platform_device *pdev, pm_message_t message) -{ - at32_wdt_stop(); - return 0; -} - -static int at32_wdt_resume(struct platform_device *pdev) -{ - if (wdt->users) - at32_wdt_start(); - return 0; -} -#else -#define at32_wdt_suspend NULL -#define at32_wdt_resume NULL -#endif - -/* work with hotplug and coldplug */ -MODULE_ALIAS("platform:at32_wdt"); - -static struct platform_driver at32_wdt_driver = { - .remove = __exit_p(at32_wdt_remove), - .suspend = at32_wdt_suspend, - .resume = at32_wdt_resume, - .driver = { - .name = "at32_wdt", - }, - .shutdown = at32_wdt_shutdown, -}; - -module_platform_driver_probe(at32_wdt_driver, at32_wdt_probe); - -MODULE_AUTHOR("Hans-Christian Egtvedt <egtvedt@samfundet.no>"); -MODULE_DESCRIPTION("Watchdog driver for Atmel AT32AP700X"); -MODULE_LICENSE("GPL"); diff --git a/drivers/watchdog/da9062_wdt.c b/drivers/watchdog/da9062_wdt.c index 9083d3d922b0..814dff6045a4 100644 --- a/drivers/watchdog/da9062_wdt.c +++ b/drivers/watchdog/da9062_wdt.c @@ -46,22 +46,6 @@ static void da9062_set_window_start(struct da9062_watchdog *wdt) wdt->j_time_stamp = jiffies; } -static void da9062_apply_window_protection(struct da9062_watchdog *wdt) -{ - unsigned long delay = msecs_to_jiffies(DA9062_RESET_PROTECTION_MS); - unsigned long timeout = wdt->j_time_stamp + delay; - unsigned long now = jiffies; - unsigned int diff_ms; - - /* if time-limit has not elapsed then wait for remainder */ - if (time_before(now, timeout)) { - diff_ms = jiffies_to_msecs(timeout-now); - dev_dbg(wdt->hw->dev, - "Kicked too quickly. Delaying %u msecs\n", diff_ms); - msleep(diff_ms); - } -} - static unsigned int da9062_wdt_timeout_to_sel(unsigned int secs) { unsigned int i; @@ -78,8 +62,6 @@ static int da9062_reset_watchdog_timer(struct da9062_watchdog *wdt) { int ret; - da9062_apply_window_protection(wdt); - ret = regmap_update_bits(wdt->hw->regmap, DA9062AA_CONTROL_F, DA9062AA_WATCHDOG_MASK, @@ -100,6 +82,13 @@ static int da9062_wdt_update_timeout_register(struct da9062_watchdog *wdt, if (ret) return ret; + regmap_update_bits(chip->regmap, + DA9062AA_CONTROL_D, + DA9062AA_TWDSCALE_MASK, + DA9062_TWDSCALE_DISABLE); + + usleep_range(150, 300); + return regmap_update_bits(chip->regmap, DA9062AA_CONTROL_D, DA9062AA_TWDSCALE_MASK, @@ -175,6 +164,25 @@ static int da9062_wdt_set_timeout(struct watchdog_device *wdd, return ret; } +static int da9062_wdt_restart(struct watchdog_device *wdd, unsigned long action, + void *data) +{ + struct da9062_watchdog *wdt = watchdog_get_drvdata(wdd); + int ret; + + ret = regmap_write(wdt->hw->regmap, + DA9062AA_CONTROL_F, + DA9062AA_SHUTDOWN_MASK); + if (ret) + dev_alert(wdt->hw->dev, "Failed to shutdown (err = %d)\n", + ret); + + /* wait for reset to assert... */ + mdelay(500); + + return ret; +} + static const struct watchdog_info da9062_watchdog_info = { .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING, .identity = "DA9062 WDT", @@ -186,6 +194,7 @@ static const struct watchdog_ops da9062_watchdog_ops = { .stop = da9062_wdt_stop, .ping = da9062_wdt_ping, .set_timeout = da9062_wdt_set_timeout, + .restart = da9062_wdt_restart, }; static const struct of_device_id da9062_compatible_id_table[] = { @@ -215,10 +224,13 @@ static int da9062_wdt_probe(struct platform_device *pdev) wdt->wdtdev.ops = &da9062_watchdog_ops; wdt->wdtdev.min_timeout = DA9062_WDT_MIN_TIMEOUT; wdt->wdtdev.max_timeout = DA9062_WDT_MAX_TIMEOUT; + wdt->wdtdev.min_hw_heartbeat_ms = DA9062_RESET_PROTECTION_MS; wdt->wdtdev.timeout = DA9062_WDG_DEFAULT_TIMEOUT; wdt->wdtdev.status = WATCHDOG_NOWAYOUT_INIT_STATUS; wdt->wdtdev.parent = &pdev->dev; + watchdog_set_restart_priority(&wdt->wdtdev, 128); + watchdog_set_drvdata(&wdt->wdtdev, wdt); ret = devm_watchdog_register_device(&pdev->dev, &wdt->wdtdev); diff --git a/drivers/watchdog/davinci_wdt.c b/drivers/watchdog/davinci_wdt.c index 2f46487af86d..3e4c592c239f 100644 --- a/drivers/watchdog/davinci_wdt.c +++ b/drivers/watchdog/davinci_wdt.c @@ -140,6 +140,42 @@ static unsigned int davinci_wdt_get_timeleft(struct watchdog_device *wdd) return wdd->timeout - timer_counter; } +static int davinci_wdt_restart(struct watchdog_device *wdd, + unsigned long action, void *data) +{ + struct davinci_wdt_device *davinci_wdt = watchdog_get_drvdata(wdd); + u32 tgcr, wdtcr; + + /* disable, internal clock source */ + iowrite32(0, davinci_wdt->base + TCR); + + /* reset timer, set mode to 64-bit watchdog, and unreset */ + tgcr = 0; + iowrite32(tgcr, davinci_wdt->base + TGCR); + tgcr = TIMMODE_64BIT_WDOG | TIM12RS_UNRESET | TIM34RS_UNRESET; + iowrite32(tgcr, davinci_wdt->base + TGCR); + + /* clear counter and period regs */ + iowrite32(0, davinci_wdt->base + TIM12); + iowrite32(0, davinci_wdt->base + TIM34); + iowrite32(0, davinci_wdt->base + PRD12); + iowrite32(0, davinci_wdt->base + PRD34); + + /* put watchdog in pre-active state */ + wdtcr = WDKEY_SEQ0 | WDEN; + iowrite32(wdtcr, davinci_wdt->base + WDTCR); + + /* put watchdog in active state */ + wdtcr = WDKEY_SEQ1 | WDEN; + iowrite32(wdtcr, davinci_wdt->base + WDTCR); + + /* write an invalid value to the WDKEY field to trigger a restart */ + wdtcr = 0x00004000; + iowrite32(wdtcr, davinci_wdt->base + WDTCR); + + return 0; +} + static const struct watchdog_info davinci_wdt_info = { .options = WDIOF_KEEPALIVEPING, .identity = "DaVinci/Keystone Watchdog", @@ -151,6 +187,7 @@ static const struct watchdog_ops davinci_wdt_ops = { .stop = davinci_wdt_ping, .ping = davinci_wdt_ping, .get_timeleft = davinci_wdt_get_timeleft, + .restart = davinci_wdt_restart, }; static int davinci_wdt_probe(struct platform_device *pdev) @@ -195,6 +232,7 @@ static int davinci_wdt_probe(struct platform_device *pdev) watchdog_set_drvdata(wdd, davinci_wdt); watchdog_set_nowayout(wdd, 1); + watchdog_set_restart_priority(wdd, 128); wdt_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); davinci_wdt->base = devm_ioremap_resource(dev, wdt_mem); diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c index 36be987ff9ef..c2f4ff516230 100644 --- a/drivers/watchdog/dw_wdt.c +++ b/drivers/watchdog/dw_wdt.c @@ -127,14 +127,27 @@ static int dw_wdt_start(struct watchdog_device *wdd) dw_wdt_set_timeout(wdd, wdd->timeout); - set_bit(WDOG_HW_RUNNING, &wdd->status); - writel(WDOG_CONTROL_REG_WDT_EN_MASK, dw_wdt->regs + WDOG_CONTROL_REG_OFFSET); return 0; } +static int dw_wdt_stop(struct watchdog_device *wdd) +{ + struct dw_wdt *dw_wdt = to_dw_wdt(wdd); + + if (!dw_wdt->rst) { + set_bit(WDOG_HW_RUNNING, &wdd->status); + return 0; + } + + reset_control_assert(dw_wdt->rst); + reset_control_deassert(dw_wdt->rst); + + return 0; +} + static int dw_wdt_restart(struct watchdog_device *wdd, unsigned long action, void *data) { @@ -173,6 +186,7 @@ static const struct watchdog_info dw_wdt_ident = { static const struct watchdog_ops dw_wdt_ops = { .owner = THIS_MODULE, .start = dw_wdt_start, + .stop = dw_wdt_stop, .ping = dw_wdt_ping, .set_timeout = dw_wdt_set_timeout, .get_timeleft = dw_wdt_get_timeleft, diff --git a/drivers/watchdog/eurotechwdt.c b/drivers/watchdog/eurotechwdt.c index 38e96712264f..47f77a6fdfd6 100644 --- a/drivers/watchdog/eurotechwdt.c +++ b/drivers/watchdog/eurotechwdt.c @@ -290,7 +290,7 @@ static long eurwdt_ioctl(struct file *file, eurwdt_timeout = time; eurwdt_set_timeout(time); spin_unlock(&eurwdt_lock); - /* Fall */ + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(eurwdt_timeout, p); diff --git a/drivers/watchdog/f71808e_wdt.c b/drivers/watchdog/f71808e_wdt.c index 8658dba21768..e0678c14480f 100644 --- a/drivers/watchdog/f71808e_wdt.c +++ b/drivers/watchdog/f71808e_wdt.c @@ -627,7 +627,7 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd, if (new_options & WDIOS_ENABLECARD) return watchdog_start(); - + /* fall through */ case WDIOC_KEEPALIVE: watchdog_keepalive(); @@ -641,7 +641,7 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd, return -EINVAL; watchdog_keepalive(); - /* Fall */ + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(watchdog.timeout, uarg.i); diff --git a/drivers/watchdog/ftwdt010_wdt.c b/drivers/watchdog/ftwdt010_wdt.c new file mode 100644 index 000000000000..a9c2912ee280 --- /dev/null +++ b/drivers/watchdog/ftwdt010_wdt.c @@ -0,0 +1,236 @@ +/* + * Watchdog driver for Faraday Technology FTWDT010 + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * + * Inspired by the out-of-tree drivers from OpenWRT: + * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/bitops.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/watchdog.h> + +#define FTWDT010_WDCOUNTER 0x0 +#define FTWDT010_WDLOAD 0x4 +#define FTWDT010_WDRESTART 0x8 +#define FTWDT010_WDCR 0xC + +#define WDRESTART_MAGIC 0x5AB9 + +#define WDCR_CLOCK_5MHZ BIT(4) +#define WDCR_WDEXT BIT(3) +#define WDCR_WDINTR BIT(2) +#define WDCR_SYS_RST BIT(1) +#define WDCR_ENABLE BIT(0) + +#define WDT_CLOCK 5000000 /* 5 MHz */ + +struct ftwdt010_wdt { + struct watchdog_device wdd; + struct device *dev; + void __iomem *base; + bool has_irq; +}; + +static inline +struct ftwdt010_wdt *to_ftwdt010_wdt(struct watchdog_device *wdd) +{ + return container_of(wdd, struct ftwdt010_wdt, wdd); +} + +static int ftwdt010_wdt_start(struct watchdog_device *wdd) +{ + struct ftwdt010_wdt *gwdt = to_ftwdt010_wdt(wdd); + u32 enable; + + writel(wdd->timeout * WDT_CLOCK, gwdt->base + FTWDT010_WDLOAD); + writel(WDRESTART_MAGIC, gwdt->base + FTWDT010_WDRESTART); + /* set clock before enabling */ + enable = WDCR_CLOCK_5MHZ | WDCR_SYS_RST; + writel(enable, gwdt->base + FTWDT010_WDCR); + if (gwdt->has_irq) + enable |= WDCR_WDINTR; + enable |= WDCR_ENABLE; + writel(enable, gwdt->base + FTWDT010_WDCR); + + return 0; +} + +static int ftwdt010_wdt_stop(struct watchdog_device *wdd) +{ + struct ftwdt010_wdt *gwdt = to_ftwdt010_wdt(wdd); + + writel(0, gwdt->base + FTWDT010_WDCR); + + return 0; +} + +static int ftwdt010_wdt_ping(struct watchdog_device *wdd) +{ + struct ftwdt010_wdt *gwdt = to_ftwdt010_wdt(wdd); + + writel(WDRESTART_MAGIC, gwdt->base + FTWDT010_WDRESTART); + + return 0; +} + +static int ftwdt010_wdt_set_timeout(struct watchdog_device *wdd, + unsigned int timeout) +{ + wdd->timeout = timeout; + if (watchdog_active(wdd)) + ftwdt010_wdt_start(wdd); + + return 0; +} + +static irqreturn_t ftwdt010_wdt_interrupt(int irq, void *data) +{ + struct ftwdt010_wdt *gwdt = data; + + watchdog_notify_pretimeout(&gwdt->wdd); + + return IRQ_HANDLED; +} + +static const struct watchdog_ops ftwdt010_wdt_ops = { + .start = ftwdt010_wdt_start, + .stop = ftwdt010_wdt_stop, + .ping = ftwdt010_wdt_ping, + .set_timeout = ftwdt010_wdt_set_timeout, + .owner = THIS_MODULE, +}; + +static const struct watchdog_info ftwdt010_wdt_info = { + .options = WDIOF_KEEPALIVEPING + | WDIOF_MAGICCLOSE + | WDIOF_SETTIMEOUT, + .identity = KBUILD_MODNAME, +}; + + +static int ftwdt010_wdt_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *res; + struct ftwdt010_wdt *gwdt; + unsigned int reg; + int irq; + int ret; + + gwdt = devm_kzalloc(dev, sizeof(*gwdt), GFP_KERNEL); + if (!gwdt) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + gwdt->base = devm_ioremap_resource(dev, res); + if (IS_ERR(gwdt->base)) + return PTR_ERR(gwdt->base); + + gwdt->dev = dev; + gwdt->wdd.info = &ftwdt010_wdt_info; + gwdt->wdd.ops = &ftwdt010_wdt_ops; + gwdt->wdd.min_timeout = 1; + gwdt->wdd.max_timeout = 0xFFFFFFFF / WDT_CLOCK; + gwdt->wdd.parent = dev; + + /* + * If 'timeout-sec' unspecified in devicetree, assume a 13 second + * default. + */ + gwdt->wdd.timeout = 13U; + watchdog_init_timeout(&gwdt->wdd, 0, dev); + + reg = readw(gwdt->base + FTWDT010_WDCR); + if (reg & WDCR_ENABLE) { + /* Watchdog was enabled by the bootloader, disable it. */ + reg &= ~WDCR_ENABLE; + writel(reg, gwdt->base + FTWDT010_WDCR); + } + + irq = platform_get_irq(pdev, 0); + if (irq) { + ret = devm_request_irq(dev, irq, ftwdt010_wdt_interrupt, 0, + "watchdog bark", gwdt); + if (ret) + return ret; + gwdt->has_irq = true; + } + + ret = devm_watchdog_register_device(dev, &gwdt->wdd); + if (ret) { + dev_err(&pdev->dev, "failed to register watchdog\n"); + return ret; + } + + /* Set up platform driver data */ + platform_set_drvdata(pdev, gwdt); + dev_info(dev, "FTWDT010 watchdog driver enabled\n"); + + return 0; +} + +static int __maybe_unused ftwdt010_wdt_suspend(struct device *dev) +{ + struct ftwdt010_wdt *gwdt = dev_get_drvdata(dev); + unsigned int reg; + + reg = readw(gwdt->base + FTWDT010_WDCR); + reg &= ~WDCR_ENABLE; + writel(reg, gwdt->base + FTWDT010_WDCR); + + return 0; +} + +static int __maybe_unused ftwdt010_wdt_resume(struct device *dev) +{ + struct ftwdt010_wdt *gwdt = dev_get_drvdata(dev); + unsigned int reg; + + if (watchdog_active(&gwdt->wdd)) { + reg = readw(gwdt->base + FTWDT010_WDCR); + reg |= WDCR_ENABLE; + writel(reg, gwdt->base + FTWDT010_WDCR); + } + + return 0; +} + +static const struct dev_pm_ops ftwdt010_wdt_dev_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(ftwdt010_wdt_suspend, + ftwdt010_wdt_resume) +}; + +#ifdef CONFIG_OF +static const struct of_device_id ftwdt010_wdt_match[] = { + { .compatible = "faraday,ftwdt010" }, + { .compatible = "cortina,gemini-watchdog" }, + {}, +}; +MODULE_DEVICE_TABLE(of, ftwdt010_wdt_match); +#endif + +static struct platform_driver ftwdt010_wdt_driver = { + .probe = ftwdt010_wdt_probe, + .driver = { + .name = "ftwdt010-wdt", + .of_match_table = of_match_ptr(ftwdt010_wdt_match), + .pm = &ftwdt010_wdt_dev_pm_ops, + }, +}; +module_platform_driver(ftwdt010_wdt_driver); +MODULE_AUTHOR("Linus Walleij"); +MODULE_DESCRIPTION("Watchdog driver for Faraday Technology FTWDT010"); +MODULE_LICENSE("GPL"); diff --git a/drivers/watchdog/gemini_wdt.c b/drivers/watchdog/gemini_wdt.c deleted file mode 100644 index 8155aa619e4c..000000000000 --- a/drivers/watchdog/gemini_wdt.c +++ /dev/null @@ -1,229 +0,0 @@ -/* - * Watchdog driver for Cortina Systems Gemini SoC - * - * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> - * - * Inspired by the out-of-tree drivers from OpenWRT: - * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/bitops.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/io.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/of_device.h> -#include <linux/platform_device.h> -#include <linux/slab.h> -#include <linux/watchdog.h> - -#define GEMINI_WDCOUNTER 0x0 -#define GEMINI_WDLOAD 0x4 -#define GEMINI_WDRESTART 0x8 -#define GEMINI_WDCR 0xC - -#define WDRESTART_MAGIC 0x5AB9 - -#define WDCR_CLOCK_5MHZ BIT(4) -#define WDCR_SYS_RST BIT(1) -#define WDCR_ENABLE BIT(0) - -#define WDT_CLOCK 5000000 /* 5 MHz */ - -struct gemini_wdt { - struct watchdog_device wdd; - struct device *dev; - void __iomem *base; -}; - -static inline -struct gemini_wdt *to_gemini_wdt(struct watchdog_device *wdd) -{ - return container_of(wdd, struct gemini_wdt, wdd); -} - -static int gemini_wdt_start(struct watchdog_device *wdd) -{ - struct gemini_wdt *gwdt = to_gemini_wdt(wdd); - - writel(wdd->timeout * WDT_CLOCK, gwdt->base + GEMINI_WDLOAD); - writel(WDRESTART_MAGIC, gwdt->base + GEMINI_WDRESTART); - /* set clock before enabling */ - writel(WDCR_CLOCK_5MHZ | WDCR_SYS_RST, - gwdt->base + GEMINI_WDCR); - writel(WDCR_CLOCK_5MHZ | WDCR_SYS_RST | WDCR_ENABLE, - gwdt->base + GEMINI_WDCR); - - return 0; -} - -static int gemini_wdt_stop(struct watchdog_device *wdd) -{ - struct gemini_wdt *gwdt = to_gemini_wdt(wdd); - - writel(0, gwdt->base + GEMINI_WDCR); - - return 0; -} - -static int gemini_wdt_ping(struct watchdog_device *wdd) -{ - struct gemini_wdt *gwdt = to_gemini_wdt(wdd); - - writel(WDRESTART_MAGIC, gwdt->base + GEMINI_WDRESTART); - - return 0; -} - -static int gemini_wdt_set_timeout(struct watchdog_device *wdd, - unsigned int timeout) -{ - wdd->timeout = timeout; - if (watchdog_active(wdd)) - gemini_wdt_start(wdd); - - return 0; -} - -static irqreturn_t gemini_wdt_interrupt(int irq, void *data) -{ - struct gemini_wdt *gwdt = data; - - watchdog_notify_pretimeout(&gwdt->wdd); - - return IRQ_HANDLED; -} - -static const struct watchdog_ops gemini_wdt_ops = { - .start = gemini_wdt_start, - .stop = gemini_wdt_stop, - .ping = gemini_wdt_ping, - .set_timeout = gemini_wdt_set_timeout, - .owner = THIS_MODULE, -}; - -static const struct watchdog_info gemini_wdt_info = { - .options = WDIOF_KEEPALIVEPING - | WDIOF_MAGICCLOSE - | WDIOF_SETTIMEOUT, - .identity = KBUILD_MODNAME, -}; - - -static int gemini_wdt_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct resource *res; - struct gemini_wdt *gwdt; - unsigned int reg; - int irq; - int ret; - - gwdt = devm_kzalloc(dev, sizeof(*gwdt), GFP_KERNEL); - if (!gwdt) - return -ENOMEM; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - gwdt->base = devm_ioremap_resource(dev, res); - if (IS_ERR(gwdt->base)) - return PTR_ERR(gwdt->base); - - irq = platform_get_irq(pdev, 0); - if (!irq) - return -EINVAL; - - gwdt->dev = dev; - gwdt->wdd.info = &gemini_wdt_info; - gwdt->wdd.ops = &gemini_wdt_ops; - gwdt->wdd.min_timeout = 1; - gwdt->wdd.max_timeout = 0xFFFFFFFF / WDT_CLOCK; - gwdt->wdd.parent = dev; - - /* - * If 'timeout-sec' unspecified in devicetree, assume a 13 second - * default. - */ - gwdt->wdd.timeout = 13U; - watchdog_init_timeout(&gwdt->wdd, 0, dev); - - reg = readw(gwdt->base + GEMINI_WDCR); - if (reg & WDCR_ENABLE) { - /* Watchdog was enabled by the bootloader, disable it. */ - reg &= ~WDCR_ENABLE; - writel(reg, gwdt->base + GEMINI_WDCR); - } - - ret = devm_request_irq(dev, irq, gemini_wdt_interrupt, 0, - "watchdog bark", gwdt); - if (ret) - return ret; - - ret = devm_watchdog_register_device(dev, &gwdt->wdd); - if (ret) { - dev_err(&pdev->dev, "failed to register watchdog\n"); - return ret; - } - - /* Set up platform driver data */ - platform_set_drvdata(pdev, gwdt); - dev_info(dev, "Gemini watchdog driver enabled\n"); - - return 0; -} - -static int __maybe_unused gemini_wdt_suspend(struct device *dev) -{ - struct gemini_wdt *gwdt = dev_get_drvdata(dev); - unsigned int reg; - - reg = readw(gwdt->base + GEMINI_WDCR); - reg &= ~WDCR_ENABLE; - writel(reg, gwdt->base + GEMINI_WDCR); - - return 0; -} - -static int __maybe_unused gemini_wdt_resume(struct device *dev) -{ - struct gemini_wdt *gwdt = dev_get_drvdata(dev); - unsigned int reg; - - if (watchdog_active(&gwdt->wdd)) { - reg = readw(gwdt->base + GEMINI_WDCR); - reg |= WDCR_ENABLE; - writel(reg, gwdt->base + GEMINI_WDCR); - } - - return 0; -} - -static const struct dev_pm_ops gemini_wdt_dev_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(gemini_wdt_suspend, - gemini_wdt_resume) -}; - -#ifdef CONFIG_OF -static const struct of_device_id gemini_wdt_match[] = { - { .compatible = "cortina,gemini-watchdog" }, - {}, -}; -MODULE_DEVICE_TABLE(of, gemini_wdt_match); -#endif - -static struct platform_driver gemini_wdt_driver = { - .probe = gemini_wdt_probe, - .driver = { - .name = "gemini-wdt", - .of_match_table = of_match_ptr(gemini_wdt_match), - .pm = &gemini_wdt_dev_pm_ops, - }, -}; -module_platform_driver(gemini_wdt_driver); -MODULE_AUTHOR("Linus Walleij"); -MODULE_DESCRIPTION("Watchdog driver for Gemini"); -MODULE_LICENSE("GPL"); diff --git a/drivers/watchdog/gpio_wdt.c b/drivers/watchdog/gpio_wdt.c index cb66c2f99ff1..3ade28190341 100644 --- a/drivers/watchdog/gpio_wdt.c +++ b/drivers/watchdog/gpio_wdt.c @@ -12,7 +12,8 @@ #include <linux/err.h> #include <linux/delay.h> #include <linux/module.h> -#include <linux/of_gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/watchdog.h> @@ -25,8 +26,7 @@ enum { }; struct gpio_wdt_priv { - int gpio; - bool active_low; + struct gpio_desc *gpiod; bool state; bool always_running; unsigned int hw_algo; @@ -35,11 +35,12 @@ struct gpio_wdt_priv { static void gpio_wdt_disable(struct gpio_wdt_priv *priv) { - gpio_set_value_cansleep(priv->gpio, !priv->active_low); + /* Eternal ping */ + gpiod_set_value_cansleep(priv->gpiod, 1); /* Put GPIO back to tristate */ if (priv->hw_algo == HW_ALGO_TOGGLE) - gpio_direction_input(priv->gpio); + gpiod_direction_input(priv->gpiod); } static int gpio_wdt_ping(struct watchdog_device *wdd) @@ -50,13 +51,13 @@ static int gpio_wdt_ping(struct watchdog_device *wdd) case HW_ALGO_TOGGLE: /* Toggle output pin */ priv->state = !priv->state; - gpio_set_value_cansleep(priv->gpio, priv->state); + gpiod_set_value_cansleep(priv->gpiod, priv->state); break; case HW_ALGO_LEVEL: /* Pulse */ - gpio_set_value_cansleep(priv->gpio, !priv->active_low); + gpiod_set_value_cansleep(priv->gpiod, 1); udelay(1); - gpio_set_value_cansleep(priv->gpio, priv->active_low); + gpiod_set_value_cansleep(priv->gpiod, 0); break; } return 0; @@ -66,8 +67,8 @@ static int gpio_wdt_start(struct watchdog_device *wdd) { struct gpio_wdt_priv *priv = watchdog_get_drvdata(wdd); - priv->state = priv->active_low; - gpio_direction_output(priv->gpio, priv->state); + priv->state = 0; + gpiod_direction_output(priv->gpiod, priv->state); set_bit(WDOG_HW_RUNNING, &wdd->status); @@ -80,7 +81,8 @@ static int gpio_wdt_stop(struct watchdog_device *wdd) if (!priv->always_running) { gpio_wdt_disable(priv); - clear_bit(WDOG_HW_RUNNING, &wdd->status); + } else { + set_bit(WDOG_HW_RUNNING, &wdd->status); } return 0; @@ -101,44 +103,38 @@ static const struct watchdog_ops gpio_wdt_ops = { static int gpio_wdt_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; struct gpio_wdt_priv *priv; - enum of_gpio_flags flags; + enum gpiod_flags gflags; unsigned int hw_margin; - unsigned long f = 0; const char *algo; int ret; - priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; platform_set_drvdata(pdev, priv); - priv->gpio = of_get_gpio_flags(pdev->dev.of_node, 0, &flags); - if (!gpio_is_valid(priv->gpio)) - return priv->gpio; - - priv->active_low = flags & OF_GPIO_ACTIVE_LOW; - - ret = of_property_read_string(pdev->dev.of_node, "hw_algo", &algo); + ret = of_property_read_string(np, "hw_algo", &algo); if (ret) return ret; if (!strcmp(algo, "toggle")) { priv->hw_algo = HW_ALGO_TOGGLE; - f = GPIOF_IN; + gflags = GPIOD_IN; } else if (!strcmp(algo, "level")) { priv->hw_algo = HW_ALGO_LEVEL; - f = priv->active_low ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW; + gflags = GPIOD_OUT_LOW; } else { return -EINVAL; } - ret = devm_gpio_request_one(&pdev->dev, priv->gpio, f, - dev_name(&pdev->dev)); - if (ret) - return ret; + priv->gpiod = devm_gpiod_get(dev, NULL, gflags); + if (IS_ERR(priv->gpiod)) + return PTR_ERR(priv->gpiod); - ret = of_property_read_u32(pdev->dev.of_node, + ret = of_property_read_u32(np, "hw_margin_ms", &hw_margin); if (ret) return ret; @@ -146,7 +142,7 @@ static int gpio_wdt_probe(struct platform_device *pdev) if (hw_margin < 2 || hw_margin > 65535) return -EINVAL; - priv->always_running = of_property_read_bool(pdev->dev.of_node, + priv->always_running = of_property_read_bool(np, "always-running"); watchdog_set_drvdata(&priv->wdd, priv); @@ -155,9 +151,9 @@ static int gpio_wdt_probe(struct platform_device *pdev) priv->wdd.ops = &gpio_wdt_ops; priv->wdd.min_timeout = SOFT_TIMEOUT_MIN; priv->wdd.max_hw_heartbeat_ms = hw_margin; - priv->wdd.parent = &pdev->dev; + priv->wdd.parent = dev; - if (watchdog_init_timeout(&priv->wdd, 0, &pdev->dev) < 0) + if (watchdog_init_timeout(&priv->wdd, 0, dev) < 0) priv->wdd.timeout = SOFT_TIMEOUT_DEF; watchdog_stop_on_reboot(&priv->wdd); diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index 67fbe35ce7cf..f1f00dfc0e68 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -52,6 +52,7 @@ static char expect_release; static unsigned long hpwdt_is_open; static void __iomem *pci_mem_addr; /* the PCI-memory address */ +static unsigned long __iomem *hpwdt_nmistat; static unsigned long __iomem *hpwdt_timer_reg; static unsigned long __iomem *hpwdt_timer_con; @@ -475,6 +476,11 @@ static int hpwdt_time_left(void) } #ifdef CONFIG_HPWDT_NMI_DECODING +static int hpwdt_my_nmi(void) +{ + return ioread8(hpwdt_nmistat) & 0x6; +} + /* * NMI Handler */ @@ -486,6 +492,9 @@ static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs) if (!hpwdt_nmi_decoding) return NMI_DONE; + if ((ulReason == NMI_UNKNOWN) && !hpwdt_my_nmi()) + return NMI_DONE; + spin_lock_irqsave(&rom_lock, rom_pl); if (!die_nmi_called && !is_icru && !is_uefi) asminline_call(&cmn_regs, cru_rom_addr); @@ -700,7 +709,7 @@ static void dmi_find_icru(const struct dmi_header *dm, void *dummy) smbios_proliant_ptr = (struct smbios_proliant_info *) dm; if (smbios_proliant_ptr->misc_features & 0x01) is_icru = 1; - if (smbios_proliant_ptr->misc_features & 0x408) + if (smbios_proliant_ptr->misc_features & 0x1400) is_uefi = 1; } } @@ -842,6 +851,7 @@ static int hpwdt_init_one(struct pci_dev *dev, retval = -ENOMEM; goto error_pci_iomap; } + hpwdt_nmistat = pci_mem_addr + 0x6e; hpwdt_timer_reg = pci_mem_addr + 0x70; hpwdt_timer_con = pci_mem_addr + 0x72; diff --git a/drivers/watchdog/i6300esb.c b/drivers/watchdog/i6300esb.c index d7befd58b391..950c71a8bb22 100644 --- a/drivers/watchdog/i6300esb.c +++ b/drivers/watchdog/i6300esb.c @@ -21,14 +21,15 @@ * Version 0.02 * 20050210 David Härdeman <david@2gen.com> * Ported driver to kernel 2.6 + * 20171016 Radu Rendec <rrendec@arista.com> + * Change driver to use the watchdog subsystem + * Add support for multiple 6300ESB devices */ /* * Includes, defines, variables, module parameters, ... */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -42,19 +43,17 @@ #include <linux/io.h> /* Module and version information */ -#define ESB_VERSION "0.05" #define ESB_MODULE_NAME "i6300ESB timer" -#define ESB_DRIVER_NAME ESB_MODULE_NAME ", v" ESB_VERSION /* PCI configuration registers */ #define ESB_CONFIG_REG 0x60 /* Config register */ #define ESB_LOCK_REG 0x68 /* WDT lock register */ /* Memory mapped registers */ -#define ESB_TIMER1_REG (BASEADDR + 0x00)/* Timer1 value after each reset */ -#define ESB_TIMER2_REG (BASEADDR + 0x04)/* Timer2 value after each reset */ -#define ESB_GINTSR_REG (BASEADDR + 0x08)/* General Interrupt Status Register */ -#define ESB_RELOAD_REG (BASEADDR + 0x0c)/* Reload register */ +#define ESB_TIMER1_REG(w) ((w)->base + 0x00)/* Timer1 value after each reset */ +#define ESB_TIMER2_REG(w) ((w)->base + 0x04)/* Timer2 value after each reset */ +#define ESB_GINTSR_REG(w) ((w)->base + 0x08)/* General Interrupt Status Reg */ +#define ESB_RELOAD_REG(w) ((w)->base + 0x0c)/* Reload register */ /* Lock register bits */ #define ESB_WDT_FUNC (0x01 << 2) /* Watchdog functionality */ @@ -74,25 +73,18 @@ #define ESB_UNLOCK1 0x80 /* Step 1 to unlock reset registers */ #define ESB_UNLOCK2 0x86 /* Step 2 to unlock reset registers */ -/* internal variables */ -static void __iomem *BASEADDR; -static DEFINE_SPINLOCK(esb_lock); /* Guards the hardware */ -static unsigned long timer_alive; -static struct pci_dev *esb_pci; -static unsigned short triggered; /* The status of the watchdog upon boot */ -static char esb_expect_close; - -/* We can only use 1 card due to the /dev/watchdog restriction */ -static int cards_found; - /* module parameters */ /* 30 sec default heartbeat (1 < heartbeat < 2*1023) */ -#define WATCHDOG_HEARTBEAT 30 -static int heartbeat = WATCHDOG_HEARTBEAT; /* in seconds */ +#define ESB_HEARTBEAT_MIN 1 +#define ESB_HEARTBEAT_MAX 2046 +#define ESB_HEARTBEAT_DEFAULT 30 +#define ESB_HEARTBEAT_RANGE __MODULE_STRING(ESB_HEARTBEAT_MIN) \ + "<heartbeat<" __MODULE_STRING(ESB_HEARTBEAT_MAX) +static int heartbeat; /* in seconds */ module_param(heartbeat, int, 0); MODULE_PARM_DESC(heartbeat, - "Watchdog heartbeat in seconds. (1<heartbeat<2046, default=" - __MODULE_STRING(WATCHDOG_HEARTBEAT) ")"); + "Watchdog heartbeat in seconds. (" ESB_HEARTBEAT_RANGE + ", default=" __MODULE_STRING(ESB_HEARTBEAT_DEFAULT) ")"); static bool nowayout = WATCHDOG_NOWAYOUT; module_param(nowayout, bool, 0); @@ -100,6 +92,15 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); +/* internal variables */ +struct esb_dev { + struct watchdog_device wdd; + void __iomem *base; + struct pci_dev *pdev; +}; + +#define to_esb_dev(wptr) container_of(wptr, struct esb_dev, wdd) + /* * Some i6300ESB specific functions */ @@ -110,61 +111,58 @@ MODULE_PARM_DESC(nowayout, * reload register. After this the appropriate registers can be written * to once before they need to be unlocked again. */ -static inline void esb_unlock_registers(void) +static inline void esb_unlock_registers(struct esb_dev *edev) { - writew(ESB_UNLOCK1, ESB_RELOAD_REG); - writew(ESB_UNLOCK2, ESB_RELOAD_REG); + writew(ESB_UNLOCK1, ESB_RELOAD_REG(edev)); + writew(ESB_UNLOCK2, ESB_RELOAD_REG(edev)); } -static int esb_timer_start(void) +static int esb_timer_start(struct watchdog_device *wdd) { + struct esb_dev *edev = to_esb_dev(wdd); + int _wdd_nowayout = test_bit(WDOG_NO_WAY_OUT, &wdd->status); u8 val; - spin_lock(&esb_lock); - esb_unlock_registers(); - writew(ESB_WDT_RELOAD, ESB_RELOAD_REG); + esb_unlock_registers(edev); + writew(ESB_WDT_RELOAD, ESB_RELOAD_REG(edev)); /* Enable or Enable + Lock? */ - val = ESB_WDT_ENABLE | (nowayout ? ESB_WDT_LOCK : 0x00); - pci_write_config_byte(esb_pci, ESB_LOCK_REG, val); - spin_unlock(&esb_lock); + val = ESB_WDT_ENABLE | (_wdd_nowayout ? ESB_WDT_LOCK : 0x00); + pci_write_config_byte(edev->pdev, ESB_LOCK_REG, val); return 0; } -static int esb_timer_stop(void) +static int esb_timer_stop(struct watchdog_device *wdd) { + struct esb_dev *edev = to_esb_dev(wdd); u8 val; - spin_lock(&esb_lock); /* First, reset timers as suggested by the docs */ - esb_unlock_registers(); - writew(ESB_WDT_RELOAD, ESB_RELOAD_REG); + esb_unlock_registers(edev); + writew(ESB_WDT_RELOAD, ESB_RELOAD_REG(edev)); /* Then disable the WDT */ - pci_write_config_byte(esb_pci, ESB_LOCK_REG, 0x0); - pci_read_config_byte(esb_pci, ESB_LOCK_REG, &val); - spin_unlock(&esb_lock); + pci_write_config_byte(edev->pdev, ESB_LOCK_REG, 0x0); + pci_read_config_byte(edev->pdev, ESB_LOCK_REG, &val); /* Returns 0 if the timer was disabled, non-zero otherwise */ return val & ESB_WDT_ENABLE; } -static void esb_timer_keepalive(void) +static int esb_timer_keepalive(struct watchdog_device *wdd) { - spin_lock(&esb_lock); - esb_unlock_registers(); - writew(ESB_WDT_RELOAD, ESB_RELOAD_REG); + struct esb_dev *edev = to_esb_dev(wdd); + + esb_unlock_registers(edev); + writew(ESB_WDT_RELOAD, ESB_RELOAD_REG(edev)); /* FIXME: Do we need to flush anything here? */ - spin_unlock(&esb_lock); + return 0; } -static int esb_timer_set_heartbeat(int time) +static int esb_timer_set_heartbeat(struct watchdog_device *wdd, + unsigned int time) { + struct esb_dev *edev = to_esb_dev(wdd); u32 val; - if (time < 0x1 || time > (2 * 0x03ff)) - return -EINVAL; - - spin_lock(&esb_lock); - /* We shift by 9, so if we are passed a value of 1 sec, * val will be 1 << 9 = 512, then write that to two * timers => 2 * 512 = 1024 (which is decremented at 1KHz) @@ -172,162 +170,39 @@ static int esb_timer_set_heartbeat(int time) val = time << 9; /* Write timer 1 */ - esb_unlock_registers(); - writel(val, ESB_TIMER1_REG); + esb_unlock_registers(edev); + writel(val, ESB_TIMER1_REG(edev)); /* Write timer 2 */ - esb_unlock_registers(); - writel(val, ESB_TIMER2_REG); + esb_unlock_registers(edev); + writel(val, ESB_TIMER2_REG(edev)); /* Reload */ - esb_unlock_registers(); - writew(ESB_WDT_RELOAD, ESB_RELOAD_REG); + esb_unlock_registers(edev); + writew(ESB_WDT_RELOAD, ESB_RELOAD_REG(edev)); /* FIXME: Do we need to flush everything out? */ /* Done */ - heartbeat = time; - spin_unlock(&esb_lock); - return 0; -} - -/* - * /dev/watchdog handling - */ - -static int esb_open(struct inode *inode, struct file *file) -{ - /* /dev/watchdog can only be opened once */ - if (test_and_set_bit(0, &timer_alive)) - return -EBUSY; - - /* Reload and activate timer */ - esb_timer_start(); - - return nonseekable_open(inode, file); -} - -static int esb_release(struct inode *inode, struct file *file) -{ - /* Shut off the timer. */ - if (esb_expect_close == 42) - esb_timer_stop(); - else { - pr_crit("Unexpected close, not stopping watchdog!\n"); - esb_timer_keepalive(); - } - clear_bit(0, &timer_alive); - esb_expect_close = 0; + wdd->timeout = time; return 0; } -static ssize_t esb_write(struct file *file, const char __user *data, - size_t len, loff_t *ppos) -{ - /* See if we got the magic character 'V' and reload the timer */ - if (len) { - if (!nowayout) { - size_t i; - - /* note: just in case someone wrote the magic character - * five months ago... */ - esb_expect_close = 0; - - /* scan to see whether or not we got the - * magic character */ - for (i = 0; i != len; i++) { - char c; - if (get_user(c, data + i)) - return -EFAULT; - if (c == 'V') - esb_expect_close = 42; - } - } - - /* someone wrote to us, we should reload the timer */ - esb_timer_keepalive(); - } - return len; -} - -static long esb_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - int new_options, retval = -EINVAL; - int new_heartbeat; - void __user *argp = (void __user *)arg; - int __user *p = argp; - static const struct watchdog_info ident = { - .options = WDIOF_SETTIMEOUT | - WDIOF_KEEPALIVEPING | - WDIOF_MAGICCLOSE, - .firmware_version = 0, - .identity = ESB_MODULE_NAME, - }; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(argp, &ident, - sizeof(ident)) ? -EFAULT : 0; - - case WDIOC_GETSTATUS: - return put_user(0, p); - - case WDIOC_GETBOOTSTATUS: - return put_user(triggered, p); - - case WDIOC_SETOPTIONS: - { - if (get_user(new_options, p)) - return -EFAULT; - - if (new_options & WDIOS_DISABLECARD) { - esb_timer_stop(); - retval = 0; - } - - if (new_options & WDIOS_ENABLECARD) { - esb_timer_start(); - retval = 0; - } - return retval; - } - case WDIOC_KEEPALIVE: - esb_timer_keepalive(); - return 0; - - case WDIOC_SETTIMEOUT: - { - if (get_user(new_heartbeat, p)) - return -EFAULT; - if (esb_timer_set_heartbeat(new_heartbeat)) - return -EINVAL; - esb_timer_keepalive(); - /* Fall */ - } - case WDIOC_GETTIMEOUT: - return put_user(heartbeat, p); - default: - return -ENOTTY; - } -} - /* - * Kernel Interfaces + * Watchdog Subsystem Interfaces */ -static const struct file_operations esb_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .write = esb_write, - .unlocked_ioctl = esb_ioctl, - .open = esb_open, - .release = esb_release, +static struct watchdog_info esb_info = { + .identity = ESB_MODULE_NAME, + .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, }; -static struct miscdevice esb_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &esb_fops, +static const struct watchdog_ops esb_ops = { + .owner = THIS_MODULE, + .start = esb_timer_start, + .stop = esb_timer_stop, + .set_timeout = esb_timer_set_heartbeat, + .ping = esb_timer_keepalive, }; /* @@ -343,38 +218,38 @@ MODULE_DEVICE_TABLE(pci, esb_pci_tbl); * Init & exit routines */ -static unsigned char esb_getdevice(struct pci_dev *pdev) +static unsigned char esb_getdevice(struct esb_dev *edev) { - if (pci_enable_device(pdev)) { - pr_err("failed to enable device\n"); + if (pci_enable_device(edev->pdev)) { + dev_err(&edev->pdev->dev, "failed to enable device\n"); goto err_devput; } - if (pci_request_region(pdev, 0, ESB_MODULE_NAME)) { - pr_err("failed to request region\n"); + if (pci_request_region(edev->pdev, 0, ESB_MODULE_NAME)) { + dev_err(&edev->pdev->dev, "failed to request region\n"); goto err_disable; } - BASEADDR = pci_ioremap_bar(pdev, 0); - if (BASEADDR == NULL) { + edev->base = pci_ioremap_bar(edev->pdev, 0); + if (edev->base == NULL) { /* Something's wrong here, BASEADDR has to be set */ - pr_err("failed to get BASEADDR\n"); + dev_err(&edev->pdev->dev, "failed to get BASEADDR\n"); goto err_release; } /* Done */ - esb_pci = pdev; + dev_set_drvdata(&edev->pdev->dev, edev); return 1; err_release: - pci_release_region(pdev, 0); + pci_release_region(edev->pdev, 0); err_disable: - pci_disable_device(pdev); + pci_disable_device(edev->pdev); err_devput: return 0; } -static void esb_initdevice(void) +static void esb_initdevice(struct esb_dev *edev) { u8 val1; u16 val2; @@ -391,96 +266,87 @@ static void esb_initdevice(void) * any interrupts as there is not much we can do with it * right now. */ - pci_write_config_word(esb_pci, ESB_CONFIG_REG, 0x0003); + pci_write_config_word(edev->pdev, ESB_CONFIG_REG, 0x0003); /* Check that the WDT isn't already locked */ - pci_read_config_byte(esb_pci, ESB_LOCK_REG, &val1); + pci_read_config_byte(edev->pdev, ESB_LOCK_REG, &val1); if (val1 & ESB_WDT_LOCK) - pr_warn("nowayout already set\n"); + dev_warn(&edev->pdev->dev, "nowayout already set\n"); /* Set the timer to watchdog mode and disable it for now */ - pci_write_config_byte(esb_pci, ESB_LOCK_REG, 0x00); + pci_write_config_byte(edev->pdev, ESB_LOCK_REG, 0x00); /* Check if the watchdog was previously triggered */ - esb_unlock_registers(); - val2 = readw(ESB_RELOAD_REG); + esb_unlock_registers(edev); + val2 = readw(ESB_RELOAD_REG(edev)); if (val2 & ESB_WDT_TIMEOUT) - triggered = WDIOF_CARDRESET; + edev->wdd.bootstatus = WDIOF_CARDRESET; /* Reset WDT_TIMEOUT flag and timers */ - esb_unlock_registers(); - writew((ESB_WDT_TIMEOUT | ESB_WDT_RELOAD), ESB_RELOAD_REG); + esb_unlock_registers(edev); + writew((ESB_WDT_TIMEOUT | ESB_WDT_RELOAD), ESB_RELOAD_REG(edev)); /* And set the correct timeout value */ - esb_timer_set_heartbeat(heartbeat); + esb_timer_set_heartbeat(&edev->wdd, edev->wdd.timeout); } static int esb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { + struct esb_dev *edev; int ret; - cards_found++; - if (cards_found == 1) - pr_info("Intel 6300ESB WatchDog Timer Driver v%s\n", - ESB_VERSION); - - if (cards_found > 1) { - pr_err("This driver only supports 1 device\n"); - return -ENODEV; - } + edev = devm_kzalloc(&pdev->dev, sizeof(*edev), GFP_KERNEL); + if (!edev) + return -ENOMEM; /* Check whether or not the hardware watchdog is there */ - if (!esb_getdevice(pdev) || esb_pci == NULL) + edev->pdev = pdev; + if (!esb_getdevice(edev)) return -ENODEV; - /* Check that the heartbeat value is within it's range; - if not reset to the default */ - if (heartbeat < 0x1 || heartbeat > 2 * 0x03ff) { - heartbeat = WATCHDOG_HEARTBEAT; - pr_info("heartbeat value must be 1<heartbeat<2046, using %d\n", - heartbeat); - } - /* Initialize the watchdog and make sure it does not run */ - esb_initdevice(); + edev->wdd.info = &esb_info; + edev->wdd.ops = &esb_ops; + edev->wdd.min_timeout = ESB_HEARTBEAT_MIN; + edev->wdd.max_timeout = ESB_HEARTBEAT_MAX; + edev->wdd.timeout = ESB_HEARTBEAT_DEFAULT; + if (watchdog_init_timeout(&edev->wdd, heartbeat, NULL)) + dev_info(&pdev->dev, + "heartbeat value must be " ESB_HEARTBEAT_RANGE + ", using %u\n", edev->wdd.timeout); + watchdog_set_nowayout(&edev->wdd, nowayout); + watchdog_stop_on_reboot(&edev->wdd); + watchdog_stop_on_unregister(&edev->wdd); + esb_initdevice(edev); /* Register the watchdog so that userspace has access to it */ - ret = misc_register(&esb_miscdev); + ret = watchdog_register_device(&edev->wdd); if (ret != 0) { - pr_err("cannot register miscdev on minor=%d (err=%d)\n", - WATCHDOG_MINOR, ret); + dev_err(&pdev->dev, + "cannot register watchdog device (err=%d)\n", ret); goto err_unmap; } - pr_info("initialized (0x%p). heartbeat=%d sec (nowayout=%d)\n", - BASEADDR, heartbeat, nowayout); + dev_info(&pdev->dev, + "initialized (0x%p). heartbeat=%d sec (nowayout=%d)\n", + edev->base, edev->wdd.timeout, nowayout); return 0; err_unmap: - iounmap(BASEADDR); - pci_release_region(esb_pci, 0); - pci_disable_device(esb_pci); - esb_pci = NULL; + iounmap(edev->base); + pci_release_region(edev->pdev, 0); + pci_disable_device(edev->pdev); return ret; } static void esb_remove(struct pci_dev *pdev) { - /* Stop the timer before we leave */ - if (!nowayout) - esb_timer_stop(); - - /* Deregister */ - misc_deregister(&esb_miscdev); - iounmap(BASEADDR); - pci_release_region(esb_pci, 0); - pci_disable_device(esb_pci); - esb_pci = NULL; -} + struct esb_dev *edev = dev_get_drvdata(&pdev->dev); -static void esb_shutdown(struct pci_dev *pdev) -{ - esb_timer_stop(); + watchdog_unregister_device(&edev->wdd); + iounmap(edev->base); + pci_release_region(edev->pdev, 0); + pci_disable_device(edev->pdev); } static struct pci_driver esb_driver = { @@ -488,7 +354,6 @@ static struct pci_driver esb_driver = { .id_table = esb_pci_tbl, .probe = esb_probe, .remove = esb_remove, - .shutdown = esb_shutdown, }; module_pci_driver(esb_driver); diff --git a/drivers/watchdog/ib700wdt.c b/drivers/watchdog/ib700wdt.c index f2e4e1eeb8dd..cc262284a6aa 100644 --- a/drivers/watchdog/ib700wdt.c +++ b/drivers/watchdog/ib700wdt.c @@ -218,7 +218,7 @@ static long ibwdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (ibwdt_set_heartbeat(new_margin)) return -EINVAL; ibwdt_ping(); - /* Fall */ + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(timeout, p); diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c index 4874b0f18650..518dfa1047cb 100644 --- a/drivers/watchdog/imx2_wdt.c +++ b/drivers/watchdog/imx2_wdt.c @@ -169,15 +169,21 @@ static int imx2_wdt_ping(struct watchdog_device *wdog) return 0; } -static int imx2_wdt_set_timeout(struct watchdog_device *wdog, - unsigned int new_timeout) +static void __imx2_wdt_set_timeout(struct watchdog_device *wdog, + unsigned int new_timeout) { struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog); - wdog->timeout = new_timeout; - regmap_update_bits(wdev->regmap, IMX2_WDT_WCR, IMX2_WDT_WCR_WT, WDOG_SEC_TO_COUNT(new_timeout)); +} + +static int imx2_wdt_set_timeout(struct watchdog_device *wdog, + unsigned int new_timeout) +{ + __imx2_wdt_set_timeout(wdog, new_timeout); + + wdog->timeout = new_timeout; return 0; } @@ -371,7 +377,11 @@ static int imx2_wdt_suspend(struct device *dev) /* The watchdog IP block is running */ if (imx2_wdt_is_running(wdev)) { - imx2_wdt_set_timeout(wdog, IMX2_WDT_MAX_TIME); + /* + * Don't update wdog->timeout, we'll restore the current value + * during resume. + */ + __imx2_wdt_set_timeout(wdog, IMX2_WDT_MAX_TIME); imx2_wdt_ping(wdog); } diff --git a/drivers/watchdog/jz4740_wdt.c b/drivers/watchdog/jz4740_wdt.c index 20627f22baf6..aafbeb96561b 100644 --- a/drivers/watchdog/jz4740_wdt.c +++ b/drivers/watchdog/jz4740_wdt.c @@ -146,6 +146,7 @@ static const struct watchdog_ops jz4740_wdt_ops = { #ifdef CONFIG_OF static const struct of_device_id jz4740_wdt_of_matches[] = { { .compatible = "ingenic,jz4740-watchdog", }, + { .compatible = "ingenic,jz4780-watchdog", }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, jz4740_wdt_of_matches); diff --git a/drivers/watchdog/mei_wdt.c b/drivers/watchdog/mei_wdt.c index ea60b29494fb..b8194b02abe0 100644 --- a/drivers/watchdog/mei_wdt.c +++ b/drivers/watchdog/mei_wdt.c @@ -526,12 +526,11 @@ static ssize_t mei_dbgfs_read_state(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos) { struct mei_wdt *wdt = file->private_data; - const size_t bufsz = 32; - char buf[bufsz]; + char buf[32]; ssize_t pos; - pos = scnprintf(buf, bufsz, "state: %s\n", - mei_wdt_state_str(wdt->state)); + pos = scnprintf(buf, sizeof(buf), "state: %s\n", + mei_wdt_state_str(wdt->state)); return simple_read_from_buffer(ubuf, cnt, ppos, buf, pos); } diff --git a/drivers/watchdog/mpc8xxx_wdt.c b/drivers/watchdog/mpc8xxx_wdt.c index 6610e9217dbc..aca2d6323f8a 100644 --- a/drivers/watchdog/mpc8xxx_wdt.c +++ b/drivers/watchdog/mpc8xxx_wdt.c @@ -22,7 +22,6 @@ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> -#include <linux/timer.h> #include <linux/of_address.h> #include <linux/of_platform.h> #include <linux/module.h> @@ -31,10 +30,13 @@ #include <linux/uaccess.h> #include <sysdev/fsl_soc.h> +#define WATCHDOG_TIMEOUT 10 + struct mpc8xxx_wdt { __be32 res0; __be32 swcrr; /* System watchdog control register */ #define SWCRR_SWTC 0xFFFF0000 /* Software Watchdog Time Count. */ +#define SWCRR_SWF 0x00000008 /* Software Watchdog Freeze (mpc8xx). */ #define SWCRR_SWEN 0x00000004 /* Watchdog Enable bit. */ #define SWCRR_SWRI 0x00000002 /* Software Watchdog Reset/Interrupt Select bit.*/ #define SWCRR_SWPR 0x00000001 /* Software Watchdog Counter Prescale bit. */ @@ -52,14 +54,15 @@ struct mpc8xxx_wdt_type { struct mpc8xxx_wdt_ddata { struct mpc8xxx_wdt __iomem *base; struct watchdog_device wdd; - struct timer_list timer; spinlock_t lock; + u16 swtc; }; -static u16 timeout = 0xffff; +static u16 timeout; module_param(timeout, ushort, 0); MODULE_PARM_DESC(timeout, - "Watchdog timeout in ticks. (0<timeout<65536, default=65535)"); + "Watchdog timeout in seconds. (1<timeout<65535, default=" + __MODULE_STRING(WATCHDOG_TIMEOUT) ")"); static bool reset = 1; module_param(reset, bool, 0); @@ -80,31 +83,27 @@ static void mpc8xxx_wdt_keepalive(struct mpc8xxx_wdt_ddata *ddata) spin_unlock(&ddata->lock); } -static void mpc8xxx_wdt_timer_ping(struct timer_list *t) -{ - struct mpc8xxx_wdt_ddata *ddata = from_timer(ddata, t, timer); - - mpc8xxx_wdt_keepalive(ddata); - /* We're pinging it twice faster than needed, just to be sure. */ - mod_timer(&ddata->timer, jiffies + HZ * ddata->wdd.timeout / 2); -} - static int mpc8xxx_wdt_start(struct watchdog_device *w) { struct mpc8xxx_wdt_ddata *ddata = container_of(w, struct mpc8xxx_wdt_ddata, wdd); - - u32 tmp = SWCRR_SWEN | SWCRR_SWPR; + u32 tmp = in_be32(&ddata->base->swcrr); /* Good, fire up the show */ + tmp &= ~(SWCRR_SWTC | SWCRR_SWF | SWCRR_SWEN | SWCRR_SWRI | SWCRR_SWPR); + tmp |= SWCRR_SWEN | SWCRR_SWPR | (ddata->swtc << 16); + if (reset) tmp |= SWCRR_SWRI; - tmp |= timeout << 16; - out_be32(&ddata->base->swcrr, tmp); - del_timer_sync(&ddata->timer); + tmp = in_be32(&ddata->base->swcrr); + if (!(tmp & SWCRR_SWEN)) + return -EOPNOTSUPP; + + ddata->swtc = tmp >> 16; + set_bit(WDOG_HW_RUNNING, &ddata->wdd.status); return 0; } @@ -118,17 +117,8 @@ static int mpc8xxx_wdt_ping(struct watchdog_device *w) return 0; } -static int mpc8xxx_wdt_stop(struct watchdog_device *w) -{ - struct mpc8xxx_wdt_ddata *ddata = - container_of(w, struct mpc8xxx_wdt_ddata, wdd); - - mod_timer(&ddata->timer, jiffies); - return 0; -} - static struct watchdog_info mpc8xxx_wdt_info = { - .options = WDIOF_KEEPALIVEPING, + .options = WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE | WDIOF_SETTIMEOUT, .firmware_version = 1, .identity = "MPC8xxx", }; @@ -137,7 +127,6 @@ static struct watchdog_ops mpc8xxx_wdt_ops = { .owner = THIS_MODULE, .start = mpc8xxx_wdt_start, .ping = mpc8xxx_wdt_ping, - .stop = mpc8xxx_wdt_stop, }; static int mpc8xxx_wdt_probe(struct platform_device *ofdev) @@ -148,7 +137,6 @@ static int mpc8xxx_wdt_probe(struct platform_device *ofdev) struct mpc8xxx_wdt_ddata *ddata; u32 freq = fsl_get_sys_freq(); bool enabled; - unsigned int timeout_sec; wdt_type = of_device_get_match_data(&ofdev->dev); if (!wdt_type) @@ -173,26 +161,17 @@ static int mpc8xxx_wdt_probe(struct platform_device *ofdev) } spin_lock_init(&ddata->lock); - timer_setup(&ddata->timer, mpc8xxx_wdt_timer_ping, 0); ddata->wdd.info = &mpc8xxx_wdt_info, ddata->wdd.ops = &mpc8xxx_wdt_ops, - /* Calculate the timeout in seconds */ - timeout_sec = (timeout * wdt_type->prescaler) / freq; - - ddata->wdd.timeout = timeout_sec; + ddata->wdd.timeout = WATCHDOG_TIMEOUT; + watchdog_init_timeout(&ddata->wdd, timeout, &ofdev->dev); watchdog_set_nowayout(&ddata->wdd, nowayout); - ret = watchdog_register_device(&ddata->wdd); - if (ret) { - pr_err("cannot register watchdog device (err=%d)\n", ret); - return ret; - } - - pr_info("WDT driver for MPC8xxx initialized. mode:%s timeout=%d (%d seconds)\n", - reset ? "reset" : "interrupt", timeout, timeout_sec); + ddata->swtc = min(ddata->wdd.timeout * freq / wdt_type->prescaler, + 0xffffU); /* * If the watchdog was previously enabled or we're running on @@ -200,7 +179,22 @@ static int mpc8xxx_wdt_probe(struct platform_device *ofdev) * userspace handles it. */ if (enabled) - mod_timer(&ddata->timer, jiffies); + mpc8xxx_wdt_start(&ddata->wdd); + + ddata->wdd.max_hw_heartbeat_ms = (ddata->swtc * wdt_type->prescaler) / + (freq / 1000); + ddata->wdd.min_timeout = ddata->wdd.max_hw_heartbeat_ms / 1000; + if (ddata->wdd.timeout < ddata->wdd.min_timeout) + ddata->wdd.timeout = ddata->wdd.min_timeout; + + ret = watchdog_register_device(&ddata->wdd); + if (ret) { + pr_err("cannot register watchdog device (err=%d)\n", ret); + return ret; + } + + pr_info("WDT driver for MPC8xxx initialized. mode:%s timeout=%d sec\n", + reset ? "reset" : "interrupt", ddata->wdd.timeout); platform_set_drvdata(ofdev, ddata); return 0; @@ -212,7 +206,6 @@ static int mpc8xxx_wdt_remove(struct platform_device *ofdev) pr_crit("Watchdog removed, expect the %s soon!\n", reset ? "reset" : "machine check exception"); - del_timer_sync(&ddata->timer); watchdog_unregister_device(&ddata->wdd); return 0; diff --git a/drivers/watchdog/mt7621_wdt.c b/drivers/watchdog/mt7621_wdt.c index db38f8017218..5c4a764717c4 100644 --- a/drivers/watchdog/mt7621_wdt.c +++ b/drivers/watchdog/mt7621_wdt.c @@ -105,6 +105,11 @@ static int mt7621_wdt_bootcause(void) return 0; } +static int mt7621_wdt_is_running(struct watchdog_device *w) +{ + return !!(rt_wdt_r32(TIMER_REG_TMR1CTL) & TMR1CTL_ENABLE); +} + static const struct watchdog_info mt7621_wdt_info = { .identity = "Mediatek Watchdog", .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, @@ -128,7 +133,6 @@ static struct watchdog_device mt7621_wdt_dev = { static int mt7621_wdt_probe(struct platform_device *pdev) { struct resource *res; - int ret; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); mt7621_wdt_base = devm_ioremap_resource(&pdev->dev, res); @@ -144,17 +148,22 @@ static int mt7621_wdt_probe(struct platform_device *pdev) watchdog_init_timeout(&mt7621_wdt_dev, mt7621_wdt_dev.max_timeout, &pdev->dev); watchdog_set_nowayout(&mt7621_wdt_dev, nowayout); - - ret = watchdog_register_device(&mt7621_wdt_dev); - - return 0; -} - -static int mt7621_wdt_remove(struct platform_device *pdev) -{ - watchdog_unregister_device(&mt7621_wdt_dev); - - return 0; + if (mt7621_wdt_is_running(&mt7621_wdt_dev)) { + /* + * Make sure to apply timeout from watchdog core, taking + * the prescaler of this driver here into account (the + * boot loader might be using a different prescaler). + * + * To avoid spurious resets because of different scaling, + * we first disable the watchdog, set the new prescaler + * and timeout, and then re-enable the watchdog. + */ + mt7621_wdt_stop(&mt7621_wdt_dev); + mt7621_wdt_start(&mt7621_wdt_dev); + set_bit(WDOG_HW_RUNNING, &mt7621_wdt_dev.status); + } + + return devm_watchdog_register_device(&pdev->dev, &mt7621_wdt_dev); } static void mt7621_wdt_shutdown(struct platform_device *pdev) @@ -170,7 +179,6 @@ MODULE_DEVICE_TABLE(of, mt7621_wdt_match); static struct platform_driver mt7621_wdt_driver = { .probe = mt7621_wdt_probe, - .remove = mt7621_wdt_remove, .shutdown = mt7621_wdt_shutdown, .driver = { .name = KBUILD_MODNAME, diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c index 83af7d6cc37c..ea676d233e1e 100644 --- a/drivers/watchdog/orion_wdt.c +++ b/drivers/watchdog/orion_wdt.c @@ -576,7 +576,7 @@ static int orion_wdt_probe(struct platform_device *pdev) /* * Let's make sure the watchdog is fully stopped, unless it's * explicitly enabled. This may be the case if the module was - * removed and re-insterted, or if the bootloader explicitly + * removed and re-inserted, or if the bootloader explicitly * set a running watchdog before booting the kernel. */ if (!orion_wdt_enabled(&dev->wdt)) diff --git a/drivers/watchdog/pcwd_pci.c b/drivers/watchdog/pcwd_pci.c index c0d07eef2640..1f78f0908621 100644 --- a/drivers/watchdog/pcwd_pci.c +++ b/drivers/watchdog/pcwd_pci.c @@ -545,8 +545,8 @@ static long pcipcwd_ioctl(struct file *file, unsigned int cmd, return -EINVAL; pcipcwd_keepalive(); - /* Fall */ } + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(heartbeat, p); diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c index b9e376c8e2e3..4d02f26156f9 100644 --- a/drivers/watchdog/pcwd_usb.c +++ b/drivers/watchdog/pcwd_usb.c @@ -49,12 +49,11 @@ #define DRIVER_VERSION "1.02" #define DRIVER_AUTHOR "Wim Van Sebroeck <wim@iguana.be>" #define DRIVER_DESC "Berkshire USB-PC Watchdog driver" -#define DRIVER_LICENSE "GPL" #define DRIVER_NAME "pcwd_usb" MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); -MODULE_LICENSE(DRIVER_LICENSE); +MODULE_LICENSE("GPL"); #define WATCHDOG_HEARTBEAT 0 /* default heartbeat = delay-time from dip-switches */ @@ -456,8 +455,8 @@ static long usb_pcwd_ioctl(struct file *file, unsigned int cmd, return -EINVAL; usb_pcwd_keepalive(usb_pcwd_device); - /* Fall */ } + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(heartbeat, p); diff --git a/drivers/watchdog/rtd119x_wdt.c b/drivers/watchdog/rtd119x_wdt.c new file mode 100644 index 000000000000..d001c17ddfde --- /dev/null +++ b/drivers/watchdog/rtd119x_wdt.c @@ -0,0 +1,168 @@ +/* + * Realtek RTD129x watchdog + * + * Copyright (c) 2017 Andreas Färber + * + * SPDX-License-Identifier: GPL-2.0+ + */ + +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/watchdog.h> + +#define RTD119X_TCWCR 0x0 +#define RTD119X_TCWTR 0x4 +#define RTD119X_TCWOV 0xc + +#define RTD119X_TCWCR_WDEN_DISABLED 0xa5 +#define RTD119X_TCWCR_WDEN_ENABLED 0xff +#define RTD119X_TCWCR_WDEN_MASK 0xff + +#define RTD119X_TCWTR_WDCLR BIT(0) + +struct rtd119x_watchdog_device { + struct watchdog_device wdt_dev; + void __iomem *base; + struct clk *clk; +}; + +static int rtd119x_wdt_start(struct watchdog_device *wdev) +{ + struct rtd119x_watchdog_device *data = watchdog_get_drvdata(wdev); + u32 val; + + val = readl_relaxed(data->base + RTD119X_TCWCR); + val &= ~RTD119X_TCWCR_WDEN_MASK; + val |= RTD119X_TCWCR_WDEN_ENABLED; + writel(val, data->base + RTD119X_TCWCR); + + return 0; +} + +static int rtd119x_wdt_stop(struct watchdog_device *wdev) +{ + struct rtd119x_watchdog_device *data = watchdog_get_drvdata(wdev); + u32 val; + + val = readl_relaxed(data->base + RTD119X_TCWCR); + val &= ~RTD119X_TCWCR_WDEN_MASK; + val |= RTD119X_TCWCR_WDEN_DISABLED; + writel(val, data->base + RTD119X_TCWCR); + + return 0; +} + +static int rtd119x_wdt_ping(struct watchdog_device *wdev) +{ + struct rtd119x_watchdog_device *data = watchdog_get_drvdata(wdev); + + writel_relaxed(RTD119X_TCWTR_WDCLR, data->base + RTD119X_TCWTR); + + return rtd119x_wdt_start(wdev); +} + +static int rtd119x_wdt_set_timeout(struct watchdog_device *wdev, unsigned int val) +{ + struct rtd119x_watchdog_device *data = watchdog_get_drvdata(wdev); + + writel(val * clk_get_rate(data->clk), data->base + RTD119X_TCWOV); + + data->wdt_dev.timeout = val; + + return 0; +} + +static const struct watchdog_ops rtd119x_wdt_ops = { + .owner = THIS_MODULE, + .start = rtd119x_wdt_start, + .stop = rtd119x_wdt_stop, + .ping = rtd119x_wdt_ping, + .set_timeout = rtd119x_wdt_set_timeout, +}; + +static const struct watchdog_info rtd119x_wdt_info = { + .identity = "rtd119x-wdt", + .options = 0, +}; + +static const struct of_device_id rtd119x_wdt_dt_ids[] = { + { .compatible = "realtek,rtd1295-watchdog" }, + { } +}; + +static int rtd119x_wdt_probe(struct platform_device *pdev) +{ + struct rtd119x_watchdog_device *data; + struct resource *res; + int ret; + + data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + data->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(data->base)) + return PTR_ERR(data->base); + + data->clk = of_clk_get(pdev->dev.of_node, 0); + if (IS_ERR(data->clk)) + return PTR_ERR(data->clk); + + ret = clk_prepare_enable(data->clk); + if (ret) { + clk_put(data->clk); + return ret; + } + + data->wdt_dev.info = &rtd119x_wdt_info; + data->wdt_dev.ops = &rtd119x_wdt_ops; + data->wdt_dev.timeout = 120; + data->wdt_dev.max_timeout = 0xffffffff / clk_get_rate(data->clk); + data->wdt_dev.min_timeout = 1; + data->wdt_dev.parent = &pdev->dev; + + watchdog_stop_on_reboot(&data->wdt_dev); + watchdog_set_drvdata(&data->wdt_dev, data); + platform_set_drvdata(pdev, data); + + writel_relaxed(RTD119X_TCWTR_WDCLR, data->base + RTD119X_TCWTR); + rtd119x_wdt_set_timeout(&data->wdt_dev, data->wdt_dev.timeout); + rtd119x_wdt_stop(&data->wdt_dev); + + ret = devm_watchdog_register_device(&pdev->dev, &data->wdt_dev); + if (ret) { + clk_disable_unprepare(data->clk); + clk_put(data->clk); + return ret; + } + + return 0; +} + +static int rtd119x_wdt_remove(struct platform_device *pdev) +{ + struct rtd119x_watchdog_device *data = platform_get_drvdata(pdev); + + watchdog_unregister_device(&data->wdt_dev); + + clk_disable_unprepare(data->clk); + clk_put(data->clk); + + return 0; +} + +static struct platform_driver rtd119x_wdt_driver = { + .probe = rtd119x_wdt_probe, + .remove = rtd119x_wdt_remove, + .driver = { + .name = "rtd1295-watchdog", + .of_match_table = rtd119x_wdt_dt_ids, + }, +}; +builtin_platform_driver(rtd119x_wdt_driver); diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c index 028618c5eeba..41aaae2d5287 100644 --- a/drivers/watchdog/sp5100_tco.c +++ b/drivers/watchdog/sp5100_tco.c @@ -16,6 +16,11 @@ * See AMD Publication 43009 "AMD SB700/710/750 Register Reference Guide", * AMD Publication 45482 "AMD SB800-Series Southbridges Register * Reference Guide" + * AMD Publication 48751 "BIOS and Kernel Developer’s Guide (BKDG) + * for AMD Family 16h Models 00h-0Fh Processors" + * AMD Publication 51192 "AMD Bolton FCH Register Reference Guide" + * AMD Publication 52740 "BIOS and Kernel Developer’s Guide (BKDG) + * for AMD Family 16h Models 30h-3Fh Processors" */ /* @@ -24,38 +29,36 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/init.h> +#include <linux/io.h> +#include <linux/ioport.h> #include <linux/module.h> #include <linux/moduleparam.h> -#include <linux/types.h> -#include <linux/miscdevice.h> -#include <linux/watchdog.h> -#include <linux/init.h> -#include <linux/fs.h> #include <linux/pci.h> -#include <linux/ioport.h> #include <linux/platform_device.h> -#include <linux/uaccess.h> -#include <linux/io.h> +#include <linux/types.h> +#include <linux/watchdog.h> #include "sp5100_tco.h" -/* Module and version information */ -#define TCO_VERSION "0.05" -#define TCO_MODULE_NAME "SP5100 TCO timer" -#define TCO_DRIVER_NAME TCO_MODULE_NAME ", v" TCO_VERSION +#define TCO_DRIVER_NAME "sp5100-tco" /* internal variables */ -static u32 tcobase_phys; -static u32 tco_wdt_fired; -static void __iomem *tcobase; -static unsigned int pm_iobase; -static DEFINE_SPINLOCK(tco_lock); /* Guards the hardware */ -static unsigned long timer_alive; -static char tco_expect_close; -static struct pci_dev *sp5100_tco_pci; + +enum tco_reg_layout { + sp5100, sb800, efch +}; + +struct sp5100_tco { + struct watchdog_device wdd; + void __iomem *tcobase; + enum tco_reg_layout tco_reg_layout; +}; /* the watchdog platform device */ static struct platform_device *sp5100_tco_platform_device; +/* the associated PCI device */ +static struct pci_dev *sp5100_tco_pci; /* module parameters */ @@ -74,83 +77,105 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started." * Some TCO specific functions */ -static bool tco_has_sp5100_reg_layout(struct pci_dev *dev) +static enum tco_reg_layout tco_reg_layout(struct pci_dev *dev) { - return dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS && - dev->revision < 0x40; + if (dev->vendor == PCI_VENDOR_ID_ATI && + dev->device == PCI_DEVICE_ID_ATI_SBX00_SMBUS && + dev->revision < 0x40) { + return sp5100; + } else if (dev->vendor == PCI_VENDOR_ID_AMD && + ((dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS && + dev->revision >= 0x41) || + (dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS && + dev->revision >= 0x49))) { + return efch; + } + return sb800; } -static void tco_timer_start(void) +static int tco_timer_start(struct watchdog_device *wdd) { + struct sp5100_tco *tco = watchdog_get_drvdata(wdd); u32 val; - unsigned long flags; - spin_lock_irqsave(&tco_lock, flags); - val = readl(SP5100_WDT_CONTROL(tcobase)); + val = readl(SP5100_WDT_CONTROL(tco->tcobase)); val |= SP5100_WDT_START_STOP_BIT; - writel(val, SP5100_WDT_CONTROL(tcobase)); - spin_unlock_irqrestore(&tco_lock, flags); + writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + + return 0; } -static void tco_timer_stop(void) +static int tco_timer_stop(struct watchdog_device *wdd) { + struct sp5100_tco *tco = watchdog_get_drvdata(wdd); u32 val; - unsigned long flags; - spin_lock_irqsave(&tco_lock, flags); - val = readl(SP5100_WDT_CONTROL(tcobase)); + val = readl(SP5100_WDT_CONTROL(tco->tcobase)); val &= ~SP5100_WDT_START_STOP_BIT; - writel(val, SP5100_WDT_CONTROL(tcobase)); - spin_unlock_irqrestore(&tco_lock, flags); + writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + + return 0; } -static void tco_timer_keepalive(void) +static int tco_timer_ping(struct watchdog_device *wdd) { + struct sp5100_tco *tco = watchdog_get_drvdata(wdd); u32 val; - unsigned long flags; - spin_lock_irqsave(&tco_lock, flags); - val = readl(SP5100_WDT_CONTROL(tcobase)); + val = readl(SP5100_WDT_CONTROL(tco->tcobase)); val |= SP5100_WDT_TRIGGER_BIT; - writel(val, SP5100_WDT_CONTROL(tcobase)); - spin_unlock_irqrestore(&tco_lock, flags); + writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + + return 0; } -static int tco_timer_set_heartbeat(int t) +static int tco_timer_set_timeout(struct watchdog_device *wdd, + unsigned int t) { - unsigned long flags; - - if (t < 0 || t > 0xffff) - return -EINVAL; + struct sp5100_tco *tco = watchdog_get_drvdata(wdd); /* Write new heartbeat to watchdog */ - spin_lock_irqsave(&tco_lock, flags); - writel(t, SP5100_WDT_COUNT(tcobase)); - spin_unlock_irqrestore(&tco_lock, flags); + writel(t, SP5100_WDT_COUNT(tco->tcobase)); + + wdd->timeout = t; - heartbeat = t; return 0; } -static void tco_timer_enable(void) +static u8 sp5100_tco_read_pm_reg8(u8 index) +{ + outb(index, SP5100_IO_PM_INDEX_REG); + return inb(SP5100_IO_PM_DATA_REG); +} + +static void sp5100_tco_update_pm_reg8(u8 index, u8 reset, u8 set) +{ + u8 val; + + outb(index, SP5100_IO_PM_INDEX_REG); + val = inb(SP5100_IO_PM_DATA_REG); + val &= reset; + val |= set; + outb(val, SP5100_IO_PM_DATA_REG); +} + +static void tco_timer_enable(struct sp5100_tco *tco) { - int val; + u32 val; - if (!tco_has_sp5100_reg_layout(sp5100_tco_pci)) { + switch (tco->tco_reg_layout) { + case sb800: /* For SB800 or later */ /* Set the Watchdog timer resolution to 1 sec */ - outb(SB800_PM_WATCHDOG_CONFIG, SB800_IO_PM_INDEX_REG); - val = inb(SB800_IO_PM_DATA_REG); - val |= SB800_PM_WATCHDOG_SECOND_RES; - outb(val, SB800_IO_PM_DATA_REG); + sp5100_tco_update_pm_reg8(SB800_PM_WATCHDOG_CONFIG, + 0xff, SB800_PM_WATCHDOG_SECOND_RES); /* Enable watchdog decode bit and watchdog timer */ - outb(SB800_PM_WATCHDOG_CONTROL, SB800_IO_PM_INDEX_REG); - val = inb(SB800_IO_PM_DATA_REG); - val |= SB800_PCI_WATCHDOG_DECODE_EN; - val &= ~SB800_PM_WATCHDOG_DISABLE; - outb(val, SB800_IO_PM_DATA_REG); - } else { + sp5100_tco_update_pm_reg8(SB800_PM_WATCHDOG_CONTROL, + ~SB800_PM_WATCHDOG_DISABLE, + SB800_PCI_WATCHDOG_DECODE_EN); + break; + case sp5100: /* For SP5100 or SB7x0 */ /* Enable watchdog decode bit */ pci_read_config_dword(sp5100_tco_pci, @@ -164,409 +189,287 @@ static void tco_timer_enable(void) val); /* Enable Watchdog timer and set the resolution to 1 sec */ - outb(SP5100_PM_WATCHDOG_CONTROL, SP5100_IO_PM_INDEX_REG); - val = inb(SP5100_IO_PM_DATA_REG); - val |= SP5100_PM_WATCHDOG_SECOND_RES; - val &= ~SP5100_PM_WATCHDOG_DISABLE; - outb(val, SP5100_IO_PM_DATA_REG); + sp5100_tco_update_pm_reg8(SP5100_PM_WATCHDOG_CONTROL, + ~SP5100_PM_WATCHDOG_DISABLE, + SP5100_PM_WATCHDOG_SECOND_RES); + break; + case efch: + /* Set the Watchdog timer resolution to 1 sec and enable */ + sp5100_tco_update_pm_reg8(EFCH_PM_DECODEEN3, + ~EFCH_PM_WATCHDOG_DISABLE, + EFCH_PM_DECODEEN_SECOND_RES); + break; } } -/* - * /dev/watchdog handling - */ - -static int sp5100_tco_open(struct inode *inode, struct file *file) +static u32 sp5100_tco_read_pm_reg32(u8 index) { - /* /dev/watchdog can only be opened once */ - if (test_and_set_bit(0, &timer_alive)) - return -EBUSY; - - /* Reload and activate timer */ - tco_timer_start(); - tco_timer_keepalive(); - return nonseekable_open(inode, file); -} - -static int sp5100_tco_release(struct inode *inode, struct file *file) -{ - /* Shut off the timer. */ - if (tco_expect_close == 42) { - tco_timer_stop(); - } else { - pr_crit("Unexpected close, not stopping watchdog!\n"); - tco_timer_keepalive(); - } - clear_bit(0, &timer_alive); - tco_expect_close = 0; - return 0; -} - -static ssize_t sp5100_tco_write(struct file *file, const char __user *data, - size_t len, loff_t *ppos) -{ - /* See if we got the magic character 'V' and reload the timer */ - if (len) { - if (!nowayout) { - size_t i; - - /* note: just in case someone wrote the magic character - * five months ago... */ - tco_expect_close = 0; + u32 val = 0; + int i; - /* scan to see whether or not we got the magic character - */ - for (i = 0; i != len; i++) { - char c; - if (get_user(c, data + i)) - return -EFAULT; - if (c == 'V') - tco_expect_close = 42; - } - } + for (i = 3; i >= 0; i--) + val = (val << 8) + sp5100_tco_read_pm_reg8(index + i); - /* someone wrote to us, we should reload the timer */ - tco_timer_keepalive(); - } - return len; + return val; } -static long sp5100_tco_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) +static int sp5100_tco_setupdevice(struct device *dev, + struct watchdog_device *wdd) { - int new_options, retval = -EINVAL; - int new_heartbeat; - void __user *argp = (void __user *)arg; - int __user *p = argp; - static const struct watchdog_info ident = { - .options = WDIOF_SETTIMEOUT | - WDIOF_KEEPALIVEPING | - WDIOF_MAGICCLOSE, - .firmware_version = 0, - .identity = TCO_MODULE_NAME, - }; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(argp, &ident, - sizeof(ident)) ? -EFAULT : 0; - case WDIOC_GETSTATUS: - case WDIOC_GETBOOTSTATUS: - return put_user(0, p); - case WDIOC_SETOPTIONS: - if (get_user(new_options, p)) - return -EFAULT; - if (new_options & WDIOS_DISABLECARD) { - tco_timer_stop(); - retval = 0; - } - if (new_options & WDIOS_ENABLECARD) { - tco_timer_start(); - tco_timer_keepalive(); - retval = 0; - } - return retval; - case WDIOC_KEEPALIVE: - tco_timer_keepalive(); - return 0; - case WDIOC_SETTIMEOUT: - if (get_user(new_heartbeat, p)) - return -EFAULT; - if (tco_timer_set_heartbeat(new_heartbeat)) - return -EINVAL; - tco_timer_keepalive(); - /* Fall through */ - case WDIOC_GETTIMEOUT: - return put_user(heartbeat, p); - default: - return -ENOTTY; - } -} - -/* - * Kernel Interfaces - */ - -static const struct file_operations sp5100_tco_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .write = sp5100_tco_write, - .unlocked_ioctl = sp5100_tco_ioctl, - .open = sp5100_tco_open, - .release = sp5100_tco_release, -}; - -static struct miscdevice sp5100_tco_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &sp5100_tco_fops, -}; - -/* - * Data for PCI driver interface - * - * This data only exists for exporting the supported - * PCI ids via MODULE_DEVICE_TABLE. We do not actually - * register a pci_driver, because someone else might - * want to register another driver on the same PCI id. - */ -static const struct pci_device_id sp5100_tco_pci_tbl[] = { - { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, PCI_ANY_ID, - PCI_ANY_ID, }, - { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, PCI_ANY_ID, - PCI_ANY_ID, }, - { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, PCI_ANY_ID, - PCI_ANY_ID, }, - { 0, }, /* End of list */ -}; -MODULE_DEVICE_TABLE(pci, sp5100_tco_pci_tbl); - -/* - * Init & exit routines - */ -static unsigned char sp5100_tco_setupdevice(void) -{ - struct pci_dev *dev = NULL; - const char *dev_name = NULL; - u32 val; - u32 index_reg, data_reg, base_addr; + struct sp5100_tco *tco = watchdog_get_drvdata(wdd); + const char *dev_name; + u32 mmio_addr = 0, val; + int ret; - /* Match the PCI device */ - for_each_pci_dev(dev) { - if (pci_match_id(sp5100_tco_pci_tbl, dev) != NULL) { - sp5100_tco_pci = dev; - break; - } + /* Request the IO ports used by this driver */ + if (!request_muxed_region(SP5100_IO_PM_INDEX_REG, + SP5100_PM_IOPORTS_SIZE, "sp5100_tco")) { + dev_err(dev, "I/O address 0x%04x already in use\n", + SP5100_IO_PM_INDEX_REG); + return -EBUSY; } - if (!sp5100_tco_pci) - return 0; - - pr_info("PCI Vendor ID: 0x%x, Device ID: 0x%x, Revision ID: 0x%x\n", - sp5100_tco_pci->vendor, sp5100_tco_pci->device, - sp5100_tco_pci->revision); - /* * Determine type of southbridge chipset. */ - if (tco_has_sp5100_reg_layout(sp5100_tco_pci)) { + switch (tco->tco_reg_layout) { + case sp5100: dev_name = SP5100_DEVNAME; - index_reg = SP5100_IO_PM_INDEX_REG; - data_reg = SP5100_IO_PM_DATA_REG; - base_addr = SP5100_PM_WATCHDOG_BASE; - } else { + mmio_addr = sp5100_tco_read_pm_reg32(SP5100_PM_WATCHDOG_BASE) & + 0xfffffff8; + break; + case sb800: dev_name = SB800_DEVNAME; - index_reg = SB800_IO_PM_INDEX_REG; - data_reg = SB800_IO_PM_DATA_REG; - base_addr = SB800_PM_WATCHDOG_BASE; - } - - /* Request the IO ports used by this driver */ - pm_iobase = SP5100_IO_PM_INDEX_REG; - if (!request_region(pm_iobase, SP5100_PM_IOPORTS_SIZE, dev_name)) { - pr_err("I/O address 0x%04x already in use\n", pm_iobase); - goto exit; + mmio_addr = sp5100_tco_read_pm_reg32(SB800_PM_WATCHDOG_BASE) & + 0xfffffff8; + break; + case efch: + dev_name = SB800_DEVNAME; + val = sp5100_tco_read_pm_reg8(EFCH_PM_DECODEEN); + if (val & EFCH_PM_DECODEEN_WDT_TMREN) + mmio_addr = EFCH_PM_WDT_ADDR; + break; + default: + return -ENODEV; } - /* - * First, Find the watchdog timer MMIO address from indirect I/O. - */ - outb(base_addr+3, index_reg); - val = inb(data_reg); - outb(base_addr+2, index_reg); - val = val << 8 | inb(data_reg); - outb(base_addr+1, index_reg); - val = val << 8 | inb(data_reg); - outb(base_addr+0, index_reg); - /* Low three bits of BASE are reserved */ - val = val << 8 | (inb(data_reg) & 0xf8); - - pr_debug("Got 0x%04x from indirect I/O\n", val); - /* Check MMIO address conflict */ - if (request_mem_region_exclusive(val, SP5100_WDT_MEM_MAP_SIZE, - dev_name)) - goto setup_wdt; - else - pr_debug("MMIO address 0x%04x already in use\n", val); - - /* - * Secondly, Find the watchdog timer MMIO address - * from SBResource_MMIO register. - */ - if (tco_has_sp5100_reg_layout(sp5100_tco_pci)) { - /* Read SBResource_MMIO from PCI config(PCI_Reg: 9Ch) */ - pci_read_config_dword(sp5100_tco_pci, - SP5100_SB_RESOURCE_MMIO_BASE, &val); - } else { - /* Read SBResource_MMIO from AcpiMmioEn(PM_Reg: 24h) */ - outb(SB800_PM_ACPI_MMIO_EN+3, SB800_IO_PM_INDEX_REG); - val = inb(SB800_IO_PM_DATA_REG); - outb(SB800_PM_ACPI_MMIO_EN+2, SB800_IO_PM_INDEX_REG); - val = val << 8 | inb(SB800_IO_PM_DATA_REG); - outb(SB800_PM_ACPI_MMIO_EN+1, SB800_IO_PM_INDEX_REG); - val = val << 8 | inb(SB800_IO_PM_DATA_REG); - outb(SB800_PM_ACPI_MMIO_EN+0, SB800_IO_PM_INDEX_REG); - val = val << 8 | inb(SB800_IO_PM_DATA_REG); + if (!mmio_addr || + !devm_request_mem_region(dev, mmio_addr, SP5100_WDT_MEM_MAP_SIZE, + dev_name)) { + if (mmio_addr) + dev_dbg(dev, "MMIO address 0x%08x already in use\n", + mmio_addr); + switch (tco->tco_reg_layout) { + case sp5100: + /* + * Secondly, Find the watchdog timer MMIO address + * from SBResource_MMIO register. + */ + /* Read SBResource_MMIO from PCI config(PCI_Reg: 9Ch) */ + pci_read_config_dword(sp5100_tco_pci, + SP5100_SB_RESOURCE_MMIO_BASE, + &mmio_addr); + if ((mmio_addr & (SB800_ACPI_MMIO_DECODE_EN | + SB800_ACPI_MMIO_SEL)) != + SB800_ACPI_MMIO_DECODE_EN) { + ret = -ENODEV; + goto unreg_region; + } + mmio_addr &= ~0xFFF; + mmio_addr += SB800_PM_WDT_MMIO_OFFSET; + break; + case sb800: + /* Read SBResource_MMIO from AcpiMmioEn(PM_Reg: 24h) */ + mmio_addr = + sp5100_tco_read_pm_reg32(SB800_PM_ACPI_MMIO_EN); + if ((mmio_addr & (SB800_ACPI_MMIO_DECODE_EN | + SB800_ACPI_MMIO_SEL)) != + SB800_ACPI_MMIO_DECODE_EN) { + ret = -ENODEV; + goto unreg_region; + } + mmio_addr &= ~0xFFF; + mmio_addr += SB800_PM_WDT_MMIO_OFFSET; + break; + case efch: + val = sp5100_tco_read_pm_reg8(EFCH_PM_ISACONTROL); + if (!(val & EFCH_PM_ISACONTROL_MMIOEN)) { + ret = -ENODEV; + goto unreg_region; + } + mmio_addr = EFCH_PM_ACPI_MMIO_ADDR + + EFCH_PM_ACPI_MMIO_WDT_OFFSET; + break; + } + dev_dbg(dev, "Got 0x%08x from SBResource_MMIO register\n", + mmio_addr); + if (!devm_request_mem_region(dev, mmio_addr, + SP5100_WDT_MEM_MAP_SIZE, + dev_name)) { + dev_dbg(dev, "MMIO address 0x%08x already in use\n", + mmio_addr); + ret = -EBUSY; + goto unreg_region; + } } - /* The SBResource_MMIO is enabled and mapped memory space? */ - if ((val & (SB800_ACPI_MMIO_DECODE_EN | SB800_ACPI_MMIO_SEL)) == - SB800_ACPI_MMIO_DECODE_EN) { - /* Clear unnecessary the low twelve bits */ - val &= ~0xFFF; - /* Add the Watchdog Timer offset to base address. */ - val += SB800_PM_WDT_MMIO_OFFSET; - /* Check MMIO address conflict */ - if (request_mem_region_exclusive(val, SP5100_WDT_MEM_MAP_SIZE, - dev_name)) { - pr_debug("Got 0x%04x from SBResource_MMIO register\n", - val); - goto setup_wdt; - } else - pr_debug("MMIO address 0x%04x already in use\n", val); - } else - pr_debug("SBResource_MMIO is disabled(0x%04x)\n", val); - - pr_notice("failed to find MMIO address, giving up.\n"); - goto unreg_region; - -setup_wdt: - tcobase_phys = val; - - tcobase = ioremap(val, SP5100_WDT_MEM_MAP_SIZE); - if (!tcobase) { - pr_err("failed to get tcobase address\n"); - goto unreg_mem_region; + tco->tcobase = devm_ioremap(dev, mmio_addr, SP5100_WDT_MEM_MAP_SIZE); + if (!tco->tcobase) { + dev_err(dev, "failed to get tcobase address\n"); + ret = -ENOMEM; + goto unreg_region; } - pr_info("Using 0x%04x for watchdog MMIO address\n", val); + dev_info(dev, "Using 0x%08x for watchdog MMIO address\n", mmio_addr); /* Setup the watchdog timer */ - tco_timer_enable(); + tco_timer_enable(tco); + + val = readl(SP5100_WDT_CONTROL(tco->tcobase)); + if (val & SP5100_WDT_DISABLED) { + dev_err(dev, "Watchdog hardware is disabled\n"); + ret = -ENODEV; + goto unreg_region; + } - /* Check that the watchdog action is set to reset the system */ - val = readl(SP5100_WDT_CONTROL(tcobase)); /* * Save WatchDogFired status, because WatchDogFired flag is * cleared here. */ - tco_wdt_fired = val & SP5100_PM_WATCHDOG_FIRED; - val &= ~SP5100_PM_WATCHDOG_ACTION_RESET; - writel(val, SP5100_WDT_CONTROL(tcobase)); + if (val & SP5100_WDT_FIRED) + wdd->bootstatus = WDIOF_CARDRESET; + /* Set watchdog action to reset the system */ + val &= ~SP5100_WDT_ACTION_RESET; + writel(val, SP5100_WDT_CONTROL(tco->tcobase)); /* Set a reasonable heartbeat before we stop the timer */ - tco_timer_set_heartbeat(heartbeat); + tco_timer_set_timeout(wdd, wdd->timeout); /* * Stop the TCO before we change anything so we don't race with * a zeroed timer. */ - tco_timer_stop(); + tco_timer_stop(wdd); - /* Done */ - return 1; + release_region(SP5100_IO_PM_INDEX_REG, SP5100_PM_IOPORTS_SIZE); -unreg_mem_region: - release_mem_region(tcobase_phys, SP5100_WDT_MEM_MAP_SIZE); -unreg_region: - release_region(pm_iobase, SP5100_PM_IOPORTS_SIZE); -exit: return 0; -} -static int sp5100_tco_init(struct platform_device *dev) -{ - int ret; +unreg_region: + release_region(SP5100_IO_PM_INDEX_REG, SP5100_PM_IOPORTS_SIZE); + return ret; +} - /* - * Check whether or not the hardware watchdog is there. If found, then - * set it up. - */ - if (!sp5100_tco_setupdevice()) - return -ENODEV; +static struct watchdog_info sp5100_tco_wdt_info = { + .identity = "SP5100 TCO timer", + .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, +}; - /* Check to see if last reboot was due to watchdog timeout */ - pr_info("Last reboot was %striggered by watchdog.\n", - tco_wdt_fired ? "" : "not "); +static const struct watchdog_ops sp5100_tco_wdt_ops = { + .owner = THIS_MODULE, + .start = tco_timer_start, + .stop = tco_timer_stop, + .ping = tco_timer_ping, + .set_timeout = tco_timer_set_timeout, +}; - /* - * Check that the heartbeat value is within it's range. - * If not, reset to the default. - */ - if (tco_timer_set_heartbeat(heartbeat)) { - heartbeat = WATCHDOG_HEARTBEAT; - tco_timer_set_heartbeat(heartbeat); - } +static int sp5100_tco_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct watchdog_device *wdd; + struct sp5100_tco *tco; + int ret; - ret = misc_register(&sp5100_tco_miscdev); - if (ret != 0) { - pr_err("cannot register miscdev on minor=%d (err=%d)\n", - WATCHDOG_MINOR, ret); - goto exit; + tco = devm_kzalloc(dev, sizeof(*tco), GFP_KERNEL); + if (!tco) + return -ENOMEM; + + tco->tco_reg_layout = tco_reg_layout(sp5100_tco_pci); + + wdd = &tco->wdd; + wdd->parent = dev; + wdd->info = &sp5100_tco_wdt_info; + wdd->ops = &sp5100_tco_wdt_ops; + wdd->timeout = WATCHDOG_HEARTBEAT; + wdd->min_timeout = 1; + wdd->max_timeout = 0xffff; + + if (watchdog_init_timeout(wdd, heartbeat, NULL)) + dev_info(dev, "timeout value invalid, using %d\n", + wdd->timeout); + watchdog_set_nowayout(wdd, nowayout); + watchdog_stop_on_reboot(wdd); + watchdog_stop_on_unregister(wdd); + watchdog_set_drvdata(wdd, tco); + + ret = sp5100_tco_setupdevice(dev, wdd); + if (ret) + return ret; + + ret = devm_watchdog_register_device(dev, wdd); + if (ret) { + dev_err(dev, "cannot register watchdog device (err=%d)\n", ret); + return ret; } - clear_bit(0, &timer_alive); - /* Show module parameters */ - pr_info("initialized (0x%p). heartbeat=%d sec (nowayout=%d)\n", - tcobase, heartbeat, nowayout); - - return 0; - -exit: - iounmap(tcobase); - release_mem_region(tcobase_phys, SP5100_WDT_MEM_MAP_SIZE); - release_region(pm_iobase, SP5100_PM_IOPORTS_SIZE); - return ret; -} - -static void sp5100_tco_cleanup(void) -{ - /* Stop the timer before we leave */ - if (!nowayout) - tco_timer_stop(); - - /* Deregister */ - misc_deregister(&sp5100_tco_miscdev); - iounmap(tcobase); - release_mem_region(tcobase_phys, SP5100_WDT_MEM_MAP_SIZE); - release_region(pm_iobase, SP5100_PM_IOPORTS_SIZE); -} + dev_info(dev, "initialized. heartbeat=%d sec (nowayout=%d)\n", + wdd->timeout, nowayout); -static int sp5100_tco_remove(struct platform_device *dev) -{ - if (tcobase) - sp5100_tco_cleanup(); return 0; } -static void sp5100_tco_shutdown(struct platform_device *dev) -{ - tco_timer_stop(); -} - static struct platform_driver sp5100_tco_driver = { - .probe = sp5100_tco_init, - .remove = sp5100_tco_remove, - .shutdown = sp5100_tco_shutdown, + .probe = sp5100_tco_probe, .driver = { - .name = TCO_MODULE_NAME, + .name = TCO_DRIVER_NAME, }, }; -static int __init sp5100_tco_init_module(void) +/* + * Data for PCI driver interface + * + * This data only exists for exporting the supported + * PCI ids via MODULE_DEVICE_TABLE. We do not actually + * register a pci_driver, because someone else might + * want to register another driver on the same PCI id. + */ +static const struct pci_device_id sp5100_tco_pci_tbl[] = { + { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, PCI_ANY_ID, + PCI_ANY_ID, }, + { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SMBUS, PCI_ANY_ID, + PCI_ANY_ID, }, + { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, PCI_ANY_ID, + PCI_ANY_ID, }, + { 0, }, /* End of list */ +}; +MODULE_DEVICE_TABLE(pci, sp5100_tco_pci_tbl); + +static int __init sp5100_tco_init(void) { + struct pci_dev *dev = NULL; int err; - pr_info("SP5100/SB800 TCO WatchDog Timer Driver v%s\n", TCO_VERSION); + /* Match the PCI device */ + for_each_pci_dev(dev) { + if (pci_match_id(sp5100_tco_pci_tbl, dev) != NULL) { + sp5100_tco_pci = dev; + break; + } + } + + if (!sp5100_tco_pci) + return -ENODEV; + + pr_info("SP5100/SB800 TCO WatchDog Timer Driver\n"); err = platform_driver_register(&sp5100_tco_driver); if (err) return err; - sp5100_tco_platform_device = platform_device_register_simple( - TCO_MODULE_NAME, -1, NULL, 0); + sp5100_tco_platform_device = + platform_device_register_simple(TCO_DRIVER_NAME, -1, NULL, 0); if (IS_ERR(sp5100_tco_platform_device)) { err = PTR_ERR(sp5100_tco_platform_device); goto unreg_platform_driver; @@ -579,15 +482,14 @@ unreg_platform_driver: return err; } -static void __exit sp5100_tco_cleanup_module(void) +static void __exit sp5100_tco_exit(void) { platform_device_unregister(sp5100_tco_platform_device); platform_driver_unregister(&sp5100_tco_driver); - pr_info("SP5100/SB800 TCO Watchdog Module Unloaded\n"); } -module_init(sp5100_tco_init_module); -module_exit(sp5100_tco_cleanup_module); +module_init(sp5100_tco_init); +module_exit(sp5100_tco_exit); MODULE_AUTHOR("Priyanka Gupta"); MODULE_DESCRIPTION("TCO timer driver for SP5100/SB800 chipset"); diff --git a/drivers/watchdog/sp5100_tco.h b/drivers/watchdog/sp5100_tco.h index 1af4dee71337..87eaf357ae01 100644 --- a/drivers/watchdog/sp5100_tco.h +++ b/drivers/watchdog/sp5100_tco.h @@ -7,6 +7,8 @@ * TCO timer driver for sp5100 chipsets */ +#include <linux/bitops.h> + /* * Some address definitions for the Watchdog */ @@ -14,8 +16,11 @@ #define SP5100_WDT_CONTROL(base) ((base) + 0x00) /* Watchdog Control */ #define SP5100_WDT_COUNT(base) ((base) + 0x04) /* Watchdog Count */ -#define SP5100_WDT_START_STOP_BIT (1 << 0) -#define SP5100_WDT_TRIGGER_BIT (1 << 7) +#define SP5100_WDT_START_STOP_BIT BIT(0) +#define SP5100_WDT_FIRED BIT(1) +#define SP5100_WDT_ACTION_RESET BIT(2) +#define SP5100_WDT_DISABLED BIT(3) +#define SP5100_WDT_TRIGGER_BIT BIT(7) #define SP5100_PM_IOPORTS_SIZE 0x02 @@ -24,43 +29,57 @@ * read them from a register. */ -/* For SP5100/SB7x0 chipset */ +/* For SP5100/SB7x0/SB8x0 chipset */ #define SP5100_IO_PM_INDEX_REG 0xCD6 #define SP5100_IO_PM_DATA_REG 0xCD7 +/* For SP5100/SB7x0 chipset */ #define SP5100_SB_RESOURCE_MMIO_BASE 0x9C #define SP5100_PM_WATCHDOG_CONTROL 0x69 #define SP5100_PM_WATCHDOG_BASE 0x6C -#define SP5100_PM_WATCHDOG_FIRED (1 << 1) -#define SP5100_PM_WATCHDOG_ACTION_RESET (1 << 2) - #define SP5100_PCI_WATCHDOG_MISC_REG 0x41 -#define SP5100_PCI_WATCHDOG_DECODE_EN (1 << 3) +#define SP5100_PCI_WATCHDOG_DECODE_EN BIT(3) -#define SP5100_PM_WATCHDOG_DISABLE (1 << 0) -#define SP5100_PM_WATCHDOG_SECOND_RES (3 << 1) +#define SP5100_PM_WATCHDOG_DISABLE ((u8)BIT(0)) +#define SP5100_PM_WATCHDOG_SECOND_RES GENMASK(2, 1) #define SP5100_DEVNAME "SP5100 TCO" - /* For SB8x0(or later) chipset */ -#define SB800_IO_PM_INDEX_REG 0xCD6 -#define SB800_IO_PM_DATA_REG 0xCD7 - #define SB800_PM_ACPI_MMIO_EN 0x24 #define SB800_PM_WATCHDOG_CONTROL 0x48 #define SB800_PM_WATCHDOG_BASE 0x48 #define SB800_PM_WATCHDOG_CONFIG 0x4C -#define SB800_PCI_WATCHDOG_DECODE_EN (1 << 0) -#define SB800_PM_WATCHDOG_DISABLE (1 << 2) -#define SB800_PM_WATCHDOG_SECOND_RES (3 << 0) -#define SB800_ACPI_MMIO_DECODE_EN (1 << 0) -#define SB800_ACPI_MMIO_SEL (1 << 1) - +#define SB800_PCI_WATCHDOG_DECODE_EN BIT(0) +#define SB800_PM_WATCHDOG_DISABLE ((u8)BIT(1)) +#define SB800_PM_WATCHDOG_SECOND_RES GENMASK(1, 0) +#define SB800_ACPI_MMIO_DECODE_EN BIT(0) +#define SB800_ACPI_MMIO_SEL BIT(1) #define SB800_PM_WDT_MMIO_OFFSET 0xB00 #define SB800_DEVNAME "SB800 TCO" + +/* For recent chips with embedded FCH (rev 40+) */ + +#define EFCH_PM_DECODEEN 0x00 + +#define EFCH_PM_DECODEEN_WDT_TMREN BIT(7) + + +#define EFCH_PM_DECODEEN3 0x00 +#define EFCH_PM_DECODEEN_SECOND_RES GENMASK(1, 0) +#define EFCH_PM_WATCHDOG_DISABLE ((u8)GENMASK(3, 2)) + +/* WDT MMIO if enabled with PM00_DECODEEN_WDT_TMREN */ +#define EFCH_PM_WDT_ADDR 0xfeb00000 + +#define EFCH_PM_ISACONTROL 0x04 + +#define EFCH_PM_ISACONTROL_MMIOEN BIT(1) + +#define EFCH_PM_ACPI_MMIO_ADDR 0xfed80000 +#define EFCH_PM_ACPI_MMIO_WDT_OFFSET 0x00000b00 diff --git a/drivers/watchdog/sprd_wdt.c b/drivers/watchdog/sprd_wdt.c new file mode 100644 index 000000000000..a8b280ff33e0 --- /dev/null +++ b/drivers/watchdog/sprd_wdt.c @@ -0,0 +1,399 @@ +/* + * Spreadtrum watchdog driver + * Copyright (C) 2017 Spreadtrum - http://www.spreadtrum.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> +#include <linux/watchdog.h> + +#define SPRD_WDT_LOAD_LOW 0x0 +#define SPRD_WDT_LOAD_HIGH 0x4 +#define SPRD_WDT_CTRL 0x8 +#define SPRD_WDT_INT_CLR 0xc +#define SPRD_WDT_INT_RAW 0x10 +#define SPRD_WDT_INT_MSK 0x14 +#define SPRD_WDT_CNT_LOW 0x18 +#define SPRD_WDT_CNT_HIGH 0x1c +#define SPRD_WDT_LOCK 0x20 +#define SPRD_WDT_IRQ_LOAD_LOW 0x2c +#define SPRD_WDT_IRQ_LOAD_HIGH 0x30 + +/* WDT_CTRL */ +#define SPRD_WDT_INT_EN_BIT BIT(0) +#define SPRD_WDT_CNT_EN_BIT BIT(1) +#define SPRD_WDT_NEW_VER_EN BIT(2) +#define SPRD_WDT_RST_EN_BIT BIT(3) + +/* WDT_INT_CLR */ +#define SPRD_WDT_INT_CLEAR_BIT BIT(0) +#define SPRD_WDT_RST_CLEAR_BIT BIT(3) + +/* WDT_INT_RAW */ +#define SPRD_WDT_INT_RAW_BIT BIT(0) +#define SPRD_WDT_RST_RAW_BIT BIT(3) +#define SPRD_WDT_LD_BUSY_BIT BIT(4) + +/* 1s equal to 32768 counter steps */ +#define SPRD_WDT_CNT_STEP 32768 + +#define SPRD_WDT_UNLOCK_KEY 0xe551 +#define SPRD_WDT_MIN_TIMEOUT 3 +#define SPRD_WDT_MAX_TIMEOUT 60 + +#define SPRD_WDT_CNT_HIGH_SHIFT 16 +#define SPRD_WDT_LOW_VALUE_MASK GENMASK(15, 0) +#define SPRD_WDT_LOAD_TIMEOUT 1000 + +struct sprd_wdt { + void __iomem *base; + struct watchdog_device wdd; + struct clk *enable; + struct clk *rtc_enable; + int irq; +}; + +static inline struct sprd_wdt *to_sprd_wdt(struct watchdog_device *wdd) +{ + return container_of(wdd, struct sprd_wdt, wdd); +} + +static inline void sprd_wdt_lock(void __iomem *addr) +{ + writel_relaxed(0x0, addr + SPRD_WDT_LOCK); +} + +static inline void sprd_wdt_unlock(void __iomem *addr) +{ + writel_relaxed(SPRD_WDT_UNLOCK_KEY, addr + SPRD_WDT_LOCK); +} + +static irqreturn_t sprd_wdt_isr(int irq, void *dev_id) +{ + struct sprd_wdt *wdt = (struct sprd_wdt *)dev_id; + + sprd_wdt_unlock(wdt->base); + writel_relaxed(SPRD_WDT_INT_CLEAR_BIT, wdt->base + SPRD_WDT_INT_CLR); + sprd_wdt_lock(wdt->base); + watchdog_notify_pretimeout(&wdt->wdd); + return IRQ_HANDLED; +} + +static u32 sprd_wdt_get_cnt_value(struct sprd_wdt *wdt) +{ + u32 val; + + val = readl_relaxed(wdt->base + SPRD_WDT_CNT_HIGH) << + SPRD_WDT_CNT_HIGH_SHIFT; + val |= readl_relaxed(wdt->base + SPRD_WDT_CNT_LOW) & + SPRD_WDT_LOW_VALUE_MASK; + + return val; +} + +static int sprd_wdt_load_value(struct sprd_wdt *wdt, u32 timeout, + u32 pretimeout) +{ + u32 val, delay_cnt = 0; + u32 tmr_step = timeout * SPRD_WDT_CNT_STEP; + u32 prtmr_step = pretimeout * SPRD_WDT_CNT_STEP; + + sprd_wdt_unlock(wdt->base); + writel_relaxed((tmr_step >> SPRD_WDT_CNT_HIGH_SHIFT) & + SPRD_WDT_LOW_VALUE_MASK, wdt->base + SPRD_WDT_LOAD_HIGH); + writel_relaxed((tmr_step & SPRD_WDT_LOW_VALUE_MASK), + wdt->base + SPRD_WDT_LOAD_LOW); + writel_relaxed((prtmr_step >> SPRD_WDT_CNT_HIGH_SHIFT) & + SPRD_WDT_LOW_VALUE_MASK, + wdt->base + SPRD_WDT_IRQ_LOAD_HIGH); + writel_relaxed(prtmr_step & SPRD_WDT_LOW_VALUE_MASK, + wdt->base + SPRD_WDT_IRQ_LOAD_LOW); + sprd_wdt_lock(wdt->base); + + /* + * Waiting the load value operation done, + * it needs two or three RTC clock cycles. + */ + do { + val = readl_relaxed(wdt->base + SPRD_WDT_INT_RAW); + if (!(val & SPRD_WDT_LD_BUSY_BIT)) + break; + + cpu_relax(); + } while (delay_cnt++ < SPRD_WDT_LOAD_TIMEOUT); + + if (delay_cnt >= SPRD_WDT_LOAD_TIMEOUT) + return -EBUSY; + return 0; +} + +static int sprd_wdt_enable(struct sprd_wdt *wdt) +{ + u32 val; + int ret; + + ret = clk_prepare_enable(wdt->enable); + if (ret) + return ret; + ret = clk_prepare_enable(wdt->rtc_enable); + if (ret) + return ret; + + sprd_wdt_unlock(wdt->base); + val = readl_relaxed(wdt->base + SPRD_WDT_CTRL); + val |= SPRD_WDT_NEW_VER_EN; + writel_relaxed(val, wdt->base + SPRD_WDT_CTRL); + sprd_wdt_lock(wdt->base); + return 0; +} + +static void sprd_wdt_disable(void *_data) +{ + struct sprd_wdt *wdt = _data; + + sprd_wdt_unlock(wdt->base); + writel_relaxed(0x0, wdt->base + SPRD_WDT_CTRL); + sprd_wdt_lock(wdt->base); + + clk_disable_unprepare(wdt->rtc_enable); + clk_disable_unprepare(wdt->enable); +} + +static int sprd_wdt_start(struct watchdog_device *wdd) +{ + struct sprd_wdt *wdt = to_sprd_wdt(wdd); + u32 val; + int ret; + + ret = sprd_wdt_load_value(wdt, wdd->timeout, wdd->pretimeout); + if (ret) + return ret; + + sprd_wdt_unlock(wdt->base); + val = readl_relaxed(wdt->base + SPRD_WDT_CTRL); + val |= SPRD_WDT_CNT_EN_BIT | SPRD_WDT_INT_EN_BIT | SPRD_WDT_RST_EN_BIT; + writel_relaxed(val, wdt->base + SPRD_WDT_CTRL); + sprd_wdt_lock(wdt->base); + set_bit(WDOG_HW_RUNNING, &wdd->status); + + return 0; +} + +static int sprd_wdt_stop(struct watchdog_device *wdd) +{ + struct sprd_wdt *wdt = to_sprd_wdt(wdd); + u32 val; + + sprd_wdt_unlock(wdt->base); + val = readl_relaxed(wdt->base + SPRD_WDT_CTRL); + val &= ~(SPRD_WDT_CNT_EN_BIT | SPRD_WDT_RST_EN_BIT | + SPRD_WDT_INT_EN_BIT); + writel_relaxed(val, wdt->base + SPRD_WDT_CTRL); + sprd_wdt_lock(wdt->base); + return 0; +} + +static int sprd_wdt_set_timeout(struct watchdog_device *wdd, + u32 timeout) +{ + struct sprd_wdt *wdt = to_sprd_wdt(wdd); + + if (timeout == wdd->timeout) + return 0; + + wdd->timeout = timeout; + + return sprd_wdt_load_value(wdt, timeout, wdd->pretimeout); +} + +static int sprd_wdt_set_pretimeout(struct watchdog_device *wdd, + u32 new_pretimeout) +{ + struct sprd_wdt *wdt = to_sprd_wdt(wdd); + + if (new_pretimeout < wdd->min_timeout) + return -EINVAL; + + wdd->pretimeout = new_pretimeout; + + return sprd_wdt_load_value(wdt, wdd->timeout, new_pretimeout); +} + +static u32 sprd_wdt_get_timeleft(struct watchdog_device *wdd) +{ + struct sprd_wdt *wdt = to_sprd_wdt(wdd); + u32 val; + + val = sprd_wdt_get_cnt_value(wdt); + val = val / SPRD_WDT_CNT_STEP; + + return val; +} + +static const struct watchdog_ops sprd_wdt_ops = { + .owner = THIS_MODULE, + .start = sprd_wdt_start, + .stop = sprd_wdt_stop, + .set_timeout = sprd_wdt_set_timeout, + .set_pretimeout = sprd_wdt_set_pretimeout, + .get_timeleft = sprd_wdt_get_timeleft, +}; + +static const struct watchdog_info sprd_wdt_info = { + .options = WDIOF_SETTIMEOUT | + WDIOF_PRETIMEOUT | + WDIOF_MAGICCLOSE | + WDIOF_KEEPALIVEPING, + .identity = "Spreadtrum Watchdog Timer", +}; + +static int sprd_wdt_probe(struct platform_device *pdev) +{ + struct resource *wdt_res; + struct sprd_wdt *wdt; + int ret; + + wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL); + if (!wdt) + return -ENOMEM; + + wdt_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + wdt->base = devm_ioremap_resource(&pdev->dev, wdt_res); + if (IS_ERR(wdt->base)) { + dev_err(&pdev->dev, "failed to map memory resource\n"); + return PTR_ERR(wdt->base); + } + + wdt->enable = devm_clk_get(&pdev->dev, "enable"); + if (IS_ERR(wdt->enable)) { + dev_err(&pdev->dev, "can't get the enable clock\n"); + return PTR_ERR(wdt->enable); + } + + wdt->rtc_enable = devm_clk_get(&pdev->dev, "rtc_enable"); + if (IS_ERR(wdt->rtc_enable)) { + dev_err(&pdev->dev, "can't get the rtc enable clock\n"); + return PTR_ERR(wdt->rtc_enable); + } + + wdt->irq = platform_get_irq(pdev, 0); + if (wdt->irq < 0) { + dev_err(&pdev->dev, "failed to get IRQ resource\n"); + return wdt->irq; + } + + ret = devm_request_irq(&pdev->dev, wdt->irq, sprd_wdt_isr, + IRQF_NO_SUSPEND, "sprd-wdt", (void *)wdt); + if (ret) { + dev_err(&pdev->dev, "failed to register irq\n"); + return ret; + } + + wdt->wdd.info = &sprd_wdt_info; + wdt->wdd.ops = &sprd_wdt_ops; + wdt->wdd.parent = &pdev->dev; + wdt->wdd.min_timeout = SPRD_WDT_MIN_TIMEOUT; + wdt->wdd.max_timeout = SPRD_WDT_MAX_TIMEOUT; + wdt->wdd.timeout = SPRD_WDT_MAX_TIMEOUT; + + ret = sprd_wdt_enable(wdt); + if (ret) { + dev_err(&pdev->dev, "failed to enable wdt\n"); + return ret; + } + ret = devm_add_action(&pdev->dev, sprd_wdt_disable, wdt); + if (ret) { + sprd_wdt_disable(wdt); + dev_err(&pdev->dev, "Failed to add wdt disable action\n"); + return ret; + } + + watchdog_set_nowayout(&wdt->wdd, WATCHDOG_NOWAYOUT); + watchdog_init_timeout(&wdt->wdd, 0, &pdev->dev); + + ret = devm_watchdog_register_device(&pdev->dev, &wdt->wdd); + if (ret) { + sprd_wdt_disable(wdt); + dev_err(&pdev->dev, "failed to register watchdog\n"); + return ret; + } + platform_set_drvdata(pdev, wdt); + + return 0; +} + +static int __maybe_unused sprd_wdt_pm_suspend(struct device *dev) +{ + struct watchdog_device *wdd = dev_get_drvdata(dev); + struct sprd_wdt *wdt = dev_get_drvdata(dev); + + if (watchdog_active(wdd)) + sprd_wdt_stop(&wdt->wdd); + sprd_wdt_disable(wdt); + + return 0; +} + +static int __maybe_unused sprd_wdt_pm_resume(struct device *dev) +{ + struct watchdog_device *wdd = dev_get_drvdata(dev); + struct sprd_wdt *wdt = dev_get_drvdata(dev); + int ret; + + ret = sprd_wdt_enable(wdt); + if (ret) + return ret; + + if (watchdog_active(wdd)) { + ret = sprd_wdt_start(&wdt->wdd); + if (ret) { + sprd_wdt_disable(wdt); + return ret; + } + } + + return 0; +} + +static const struct dev_pm_ops sprd_wdt_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(sprd_wdt_pm_suspend, + sprd_wdt_pm_resume) +}; + +static const struct of_device_id sprd_wdt_match_table[] = { + { .compatible = "sprd,sp9860-wdt", }, + {}, +}; +MODULE_DEVICE_TABLE(of, sprd_wdt_match_table); + +static struct platform_driver sprd_watchdog_driver = { + .probe = sprd_wdt_probe, + .driver = { + .name = "sprd-wdt", + .of_match_table = sprd_wdt_match_table, + .pm = &sprd_wdt_pm_ops, + }, +}; +module_platform_driver(sprd_watchdog_driver); + +MODULE_AUTHOR("Eric Long <eric.long@spreadtrum.com>"); +MODULE_DESCRIPTION("Spreadtrum Watchdog Timer Controller Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index be64a8699de3..c97ad5619cb0 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -1,12 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Driver for STM32 Independent Watchdog * - * Copyright (C) Yannick Fertre 2017 - * Author: Yannick Fertre <yannick.fertre@st.com> + * Copyright (C) STMicroelectronics 2017 + * Author: Yannick Fertre <yannick.fertre@st.com> for STMicroelectronics. * * This driver is based on tegra_wdt.c * - * License terms: GNU General Public License (GPL), version 2 */ #include <linux/clk.h> diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c index 9728fa32c357..802e31b1416d 100644 --- a/drivers/watchdog/sunxi_wdt.c +++ b/drivers/watchdog/sunxi_wdt.c @@ -234,7 +234,6 @@ MODULE_DEVICE_TABLE(of, sunxi_wdt_dt_ids); static int sunxi_wdt_probe(struct platform_device *pdev) { struct sunxi_wdt_dev *sunxi_wdt; - const struct of_device_id *device; struct resource *res; int err; @@ -242,12 +241,10 @@ static int sunxi_wdt_probe(struct platform_device *pdev) if (!sunxi_wdt) return -EINVAL; - device = of_match_device(sunxi_wdt_dt_ids, &pdev->dev); - if (!device) + sunxi_wdt->wdt_regs = of_device_get_match_data(&pdev->dev); + if (!sunxi_wdt->wdt_regs) return -ENODEV; - sunxi_wdt->wdt_regs = device->data; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); sunxi_wdt->wdt_base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(sunxi_wdt->wdt_base)) diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index 8a8d952f8df9..eb8fa25f8eb2 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -97,6 +97,7 @@ static void watchdog_check_min_max_timeout(struct watchdog_device *wdd) /** * watchdog_init_timeout() - initialize the timeout field + * @wdd: watchdog device * @timeout_parm: timeout module parameter * @dev: Device that stores the timeout-sec property * diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 1e971a50d7fb..ffbdc4642ea5 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -36,9 +36,10 @@ #include <linux/errno.h> /* For the -ENODEV/... values */ #include <linux/fs.h> /* For file operations */ #include <linux/init.h> /* For __init/__exit/... */ -#include <linux/jiffies.h> /* For timeout functions */ +#include <linux/hrtimer.h> /* For hrtimers */ #include <linux/kernel.h> /* For printk/panic/... */ #include <linux/kref.h> /* For data references */ +#include <linux/kthread.h> /* For kthread_work */ #include <linux/miscdevice.h> /* For handling misc devices */ #include <linux/module.h> /* For module stuff/... */ #include <linux/mutex.h> /* For mutexes */ @@ -46,9 +47,10 @@ #include <linux/slab.h> /* For memory functions */ #include <linux/types.h> /* For standard types (like size_t) */ #include <linux/watchdog.h> /* For watchdog specific items */ -#include <linux/workqueue.h> /* For workqueue */ #include <linux/uaccess.h> /* For copy_to_user/put_user/... */ +#include <uapi/linux/sched/types.h> /* For struct sched_param */ + #include "watchdog_core.h" #include "watchdog_pretimeout.h" @@ -65,9 +67,10 @@ struct watchdog_core_data { struct cdev cdev; struct watchdog_device *wdd; struct mutex lock; - unsigned long last_keepalive; - unsigned long last_hw_keepalive; - struct delayed_work work; + ktime_t last_keepalive; + ktime_t last_hw_keepalive; + struct hrtimer timer; + struct kthread_work work; unsigned long status; /* Internal status bits */ #define _WDOG_DEV_OPEN 0 /* Opened ? */ #define _WDOG_ALLOW_RELEASE 1 /* Did we receive the magic char ? */ @@ -79,7 +82,7 @@ static dev_t watchdog_devt; /* Reference to watchdog device behind /dev/watchdog */ static struct watchdog_core_data *old_wd_data; -static struct workqueue_struct *watchdog_wq; +static struct kthread_worker *watchdog_kworker; static bool handle_boot_enabled = IS_ENABLED(CONFIG_WATCHDOG_HANDLE_BOOT_ENABLED); @@ -107,18 +110,19 @@ static inline bool watchdog_need_worker(struct watchdog_device *wdd) (t && !watchdog_active(wdd) && watchdog_hw_running(wdd)); } -static long watchdog_next_keepalive(struct watchdog_device *wdd) +static ktime_t watchdog_next_keepalive(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; unsigned int timeout_ms = wdd->timeout * 1000; - unsigned long keepalive_interval; - unsigned long last_heartbeat; - unsigned long virt_timeout; + ktime_t keepalive_interval; + ktime_t last_heartbeat, latest_heartbeat; + ktime_t virt_timeout; unsigned int hw_heartbeat_ms; - virt_timeout = wd_data->last_keepalive + msecs_to_jiffies(timeout_ms); + virt_timeout = ktime_add(wd_data->last_keepalive, + ms_to_ktime(timeout_ms)); hw_heartbeat_ms = min_not_zero(timeout_ms, wdd->max_hw_heartbeat_ms); - keepalive_interval = msecs_to_jiffies(hw_heartbeat_ms / 2); + keepalive_interval = ms_to_ktime(hw_heartbeat_ms / 2); if (!watchdog_active(wdd)) return keepalive_interval; @@ -128,8 +132,11 @@ static long watchdog_next_keepalive(struct watchdog_device *wdd) * after the most recent ping from userspace, the last * worker ping has to come in hw_heartbeat_ms before this timeout. */ - last_heartbeat = virt_timeout - msecs_to_jiffies(hw_heartbeat_ms); - return min_t(long, last_heartbeat - jiffies, keepalive_interval); + last_heartbeat = ktime_sub(virt_timeout, ms_to_ktime(hw_heartbeat_ms)); + latest_heartbeat = ktime_sub(last_heartbeat, ktime_get()); + if (ktime_before(latest_heartbeat, keepalive_interval)) + return latest_heartbeat; + return keepalive_interval; } static inline void watchdog_update_worker(struct watchdog_device *wdd) @@ -137,29 +144,33 @@ static inline void watchdog_update_worker(struct watchdog_device *wdd) struct watchdog_core_data *wd_data = wdd->wd_data; if (watchdog_need_worker(wdd)) { - long t = watchdog_next_keepalive(wdd); + ktime_t t = watchdog_next_keepalive(wdd); if (t > 0) - mod_delayed_work(watchdog_wq, &wd_data->work, t); + hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL); } else { - cancel_delayed_work(&wd_data->work); + hrtimer_cancel(&wd_data->timer); } } static int __watchdog_ping(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; - unsigned long earliest_keepalive = wd_data->last_hw_keepalive + - msecs_to_jiffies(wdd->min_hw_heartbeat_ms); + ktime_t earliest_keepalive, now; int err; - if (time_is_after_jiffies(earliest_keepalive)) { - mod_delayed_work(watchdog_wq, &wd_data->work, - earliest_keepalive - jiffies); + earliest_keepalive = ktime_add(wd_data->last_hw_keepalive, + ms_to_ktime(wdd->min_hw_heartbeat_ms)); + now = ktime_get(); + + if (ktime_after(earliest_keepalive, now)) { + hrtimer_start(&wd_data->timer, + ktime_sub(earliest_keepalive, now), + HRTIMER_MODE_REL); return 0; } - wd_data->last_hw_keepalive = jiffies; + wd_data->last_hw_keepalive = now; if (wdd->ops->ping) err = wdd->ops->ping(wdd); /* ping the watchdog */ @@ -192,7 +203,7 @@ static int watchdog_ping(struct watchdog_device *wdd) set_bit(_WDOG_KEEPALIVE, &wd_data->status); - wd_data->last_keepalive = jiffies; + wd_data->last_keepalive = ktime_get(); return __watchdog_ping(wdd); } @@ -203,12 +214,11 @@ static bool watchdog_worker_should_ping(struct watchdog_core_data *wd_data) return wdd && (watchdog_active(wdd) || watchdog_hw_running(wdd)); } -static void watchdog_ping_work(struct work_struct *work) +static void watchdog_ping_work(struct kthread_work *work) { struct watchdog_core_data *wd_data; - wd_data = container_of(to_delayed_work(work), struct watchdog_core_data, - work); + wd_data = container_of(work, struct watchdog_core_data, work); mutex_lock(&wd_data->lock); if (watchdog_worker_should_ping(wd_data)) @@ -216,6 +226,16 @@ static void watchdog_ping_work(struct work_struct *work) mutex_unlock(&wd_data->lock); } +static enum hrtimer_restart watchdog_timer_expired(struct hrtimer *timer) +{ + struct watchdog_core_data *wd_data; + + wd_data = container_of(timer, struct watchdog_core_data, timer); + + kthread_queue_work(watchdog_kworker, &wd_data->work); + return HRTIMER_NORESTART; +} + /* * watchdog_start: wrapper to start the watchdog. * @wdd: the watchdog device to start @@ -230,7 +250,7 @@ static void watchdog_ping_work(struct work_struct *work) static int watchdog_start(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; - unsigned long started_at; + ktime_t started_at; int err; if (watchdog_active(wdd)) @@ -238,7 +258,7 @@ static int watchdog_start(struct watchdog_device *wdd) set_bit(_WDOG_KEEPALIVE, &wd_data->status); - started_at = jiffies; + started_at = ktime_get(); if (watchdog_hw_running(wdd) && wdd->ops->ping) err = wdd->ops->ping(wdd); else @@ -720,7 +740,7 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd, err = watchdog_ping(wdd); if (err < 0) break; - /* Fall */ + /* fall through */ case WDIOC_GETTIMEOUT: /* timeout == 0 means that we don't know the timeout */ if (wdd->timeout == 0) { @@ -769,6 +789,7 @@ static int watchdog_open(struct inode *inode, struct file *file) { struct watchdog_core_data *wd_data; struct watchdog_device *wdd; + bool hw_running; int err; /* Get the corresponding watchdog device */ @@ -788,7 +809,8 @@ static int watchdog_open(struct inode *inode, struct file *file) * If the /dev/watchdog device is open, we don't want the module * to be unloaded. */ - if (!watchdog_hw_running(wdd) && !try_module_get(wdd->ops->owner)) { + hw_running = watchdog_hw_running(wdd); + if (!hw_running && !try_module_get(wdd->ops->owner)) { err = -EBUSY; goto out_clear; } @@ -799,7 +821,7 @@ static int watchdog_open(struct inode *inode, struct file *file) file->private_data = wd_data; - if (!watchdog_hw_running(wdd)) + if (!hw_running) kref_get(&wd_data->kref); /* dev/watchdog is a virtual (and thus non-seekable) filesystem */ @@ -919,10 +941,12 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) wd_data->wdd = wdd; wdd->wd_data = wd_data; - if (!watchdog_wq) + if (IS_ERR_OR_NULL(watchdog_kworker)) return -ENODEV; - INIT_DELAYED_WORK(&wd_data->work, watchdog_ping_work); + kthread_init_work(&wd_data->work, watchdog_ping_work); + hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + wd_data->timer.function = watchdog_timer_expired; if (wdd->id == 0) { old_wd_data = wd_data; @@ -958,21 +982,20 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno) } /* Record time of most recent heartbeat as 'just before now'. */ - wd_data->last_hw_keepalive = jiffies - 1; + wd_data->last_hw_keepalive = ktime_sub(ktime_get(), 1); /* * If the watchdog is running, prevent its driver from being unloaded, * and schedule an immediate ping. */ if (watchdog_hw_running(wdd)) { - if (handle_boot_enabled) { - __module_get(wdd->ops->owner); - kref_get(&wd_data->kref); - queue_delayed_work(watchdog_wq, &wd_data->work, 0); - } else { + __module_get(wdd->ops->owner); + kref_get(&wd_data->kref); + if (handle_boot_enabled) + hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL); + else pr_info("watchdog%d running and kernel based pre-userspace handler disabled\n", - wdd->id); - } + wdd->id); } return 0; @@ -1006,7 +1029,8 @@ static void watchdog_cdev_unregister(struct watchdog_device *wdd) watchdog_stop(wdd); } - cancel_delayed_work_sync(&wd_data->work); + hrtimer_cancel(&wd_data->timer); + kthread_cancel_work_sync(&wd_data->work); kref_put(&wd_data->kref, watchdog_core_data_release); } @@ -1110,13 +1134,14 @@ void watchdog_dev_unregister(struct watchdog_device *wdd) int __init watchdog_dev_init(void) { int err; + struct sched_param param = {.sched_priority = MAX_RT_PRIO - 1,}; - watchdog_wq = alloc_workqueue("watchdogd", - WQ_HIGHPRI | WQ_MEM_RECLAIM, 0); - if (!watchdog_wq) { - pr_err("Failed to create watchdog workqueue\n"); - return -ENOMEM; + watchdog_kworker = kthread_create_worker(0, "watchdogd"); + if (IS_ERR(watchdog_kworker)) { + pr_err("Failed to create watchdog kworker\n"); + return PTR_ERR(watchdog_kworker); } + sched_setscheduler(watchdog_kworker->task, SCHED_FIFO, ¶m); err = class_register(&watchdog_class); if (err < 0) { @@ -1135,7 +1160,7 @@ int __init watchdog_dev_init(void) err_alloc: class_unregister(&watchdog_class); err_register: - destroy_workqueue(watchdog_wq); + kthread_destroy_worker(watchdog_kworker); return err; } @@ -1149,7 +1174,7 @@ void __exit watchdog_dev_exit(void) { unregister_chrdev_region(watchdog_devt, MAX_DOGS); class_unregister(&watchdog_class); - destroy_workqueue(watchdog_wq); + kthread_destroy_worker(watchdog_kworker); } module_param(handle_boot_enabled, bool, 0444); diff --git a/drivers/watchdog/wdt_pci.c b/drivers/watchdog/wdt_pci.c index bc7addc2dc06..10e2cda0ee5a 100644 --- a/drivers/watchdog/wdt_pci.c +++ b/drivers/watchdog/wdt_pci.c @@ -430,7 +430,7 @@ static long wdtpci_ioctl(struct file *file, unsigned int cmd, if (wdtpci_set_heartbeat(new_heartbeat)) return -EINVAL; wdtpci_ping(); - /* Fall */ + /* fall through */ case WDIOC_GETTIMEOUT: return put_user(heartbeat, p); default: diff --git a/drivers/watchdog/xen_wdt.c b/drivers/watchdog/xen_wdt.c index cf0e650c2015..f1c016d015b3 100644 --- a/drivers/watchdog/xen_wdt.c +++ b/drivers/watchdog/xen_wdt.c @@ -9,10 +9,7 @@ * 2 of the License, or (at your option) any later version. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#define DRV_NAME "wdt" -#define DRV_VERSION "0.01" +#define DRV_NAME "xen_wdt" #include <linux/bug.h> #include <linux/errno.h> @@ -21,25 +18,20 @@ #include <linux/kernel.h> #include <linux/ktime.h> #include <linux/init.h> -#include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/platform_device.h> -#include <linux/spinlock.h> -#include <linux/uaccess.h> #include <linux/watchdog.h> #include <xen/xen.h> #include <asm/xen/hypercall.h> #include <xen/interface/sched.h> static struct platform_device *platform_device; -static DEFINE_SPINLOCK(wdt_lock); static struct sched_watchdog wdt; -static __kernel_time_t wdt_expires; -static bool is_active, expect_release; +static time64_t wdt_expires; #define WATCHDOG_TIMEOUT 60 /* in seconds */ -static unsigned int timeout = WATCHDOG_TIMEOUT; +static unsigned int timeout; module_param(timeout, uint, S_IRUGO); MODULE_PARM_DESC(timeout, "Watchdog timeout in seconds " "(default=" __MODULE_STRING(WATCHDOG_TIMEOUT) ")"); @@ -49,20 +41,18 @@ module_param(nowayout, bool, S_IRUGO); MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started " "(default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -static inline __kernel_time_t set_timeout(void) +static inline time64_t set_timeout(struct watchdog_device *wdd) { - wdt.timeout = timeout; - return ktime_to_timespec(ktime_get()).tv_sec + timeout; + wdt.timeout = wdd->timeout; + return ktime_get_seconds() + wdd->timeout; } -static int xen_wdt_start(void) +static int xen_wdt_start(struct watchdog_device *wdd) { - __kernel_time_t expires; + time64_t expires; int err; - spin_lock(&wdt_lock); - - expires = set_timeout(); + expires = set_timeout(wdd); if (!wdt.id) err = HYPERVISOR_sched_op(SCHEDOP_watchdog, &wdt); else @@ -74,36 +64,28 @@ static int xen_wdt_start(void) } else BUG_ON(!err); - spin_unlock(&wdt_lock); - return err; } -static int xen_wdt_stop(void) +static int xen_wdt_stop(struct watchdog_device *wdd) { int err = 0; - spin_lock(&wdt_lock); - wdt.timeout = 0; if (wdt.id) err = HYPERVISOR_sched_op(SCHEDOP_watchdog, &wdt); if (!err) wdt.id = 0; - spin_unlock(&wdt_lock); - return err; } -static int xen_wdt_kick(void) +static int xen_wdt_kick(struct watchdog_device *wdd) { - __kernel_time_t expires; + time64_t expires; int err; - spin_lock(&wdt_lock); - - expires = set_timeout(); + expires = set_timeout(wdd); if (wdt.id) err = HYPERVISOR_sched_op(SCHEDOP_watchdog, &wdt); else @@ -111,195 +93,72 @@ static int xen_wdt_kick(void) if (!err) wdt_expires = expires; - spin_unlock(&wdt_lock); - - return err; -} - -static int xen_wdt_open(struct inode *inode, struct file *file) -{ - int err; - - /* /dev/watchdog can only be opened once */ - if (xchg(&is_active, true)) - return -EBUSY; - - err = xen_wdt_start(); - if (err == -EBUSY) - err = xen_wdt_kick(); - return err ?: nonseekable_open(inode, file); -} - -static int xen_wdt_release(struct inode *inode, struct file *file) -{ - int err = 0; - - if (expect_release) - err = xen_wdt_stop(); - else { - pr_crit("unexpected close, not stopping watchdog!\n"); - xen_wdt_kick(); - } - is_active = err; - expect_release = false; return err; } -static ssize_t xen_wdt_write(struct file *file, const char __user *data, - size_t len, loff_t *ppos) +static unsigned int xen_wdt_get_timeleft(struct watchdog_device *wdd) { - /* See if we got the magic character 'V' and reload the timer */ - if (len) { - if (!nowayout) { - size_t i; - - /* in case it was set long ago */ - expect_release = false; - - /* scan to see whether or not we got the magic - character */ - for (i = 0; i != len; i++) { - char c; - if (get_user(c, data + i)) - return -EFAULT; - if (c == 'V') - expect_release = true; - } - } - - /* someone wrote to us, we should reload the timer */ - xen_wdt_kick(); - } - return len; + return wdt_expires - ktime_get_seconds(); } -static long xen_wdt_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) -{ - int new_options, retval = -EINVAL; - int new_timeout; - int __user *argp = (void __user *)arg; - static const struct watchdog_info ident = { - .options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE, - .firmware_version = 0, - .identity = DRV_NAME, - }; - - switch (cmd) { - case WDIOC_GETSUPPORT: - return copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0; - - case WDIOC_GETSTATUS: - case WDIOC_GETBOOTSTATUS: - return put_user(0, argp); - - case WDIOC_SETOPTIONS: - if (get_user(new_options, argp)) - return -EFAULT; - - if (new_options & WDIOS_DISABLECARD) - retval = xen_wdt_stop(); - if (new_options & WDIOS_ENABLECARD) { - retval = xen_wdt_start(); - if (retval == -EBUSY) - retval = xen_wdt_kick(); - } - return retval; - - case WDIOC_KEEPALIVE: - xen_wdt_kick(); - return 0; - - case WDIOC_SETTIMEOUT: - if (get_user(new_timeout, argp)) - return -EFAULT; - if (!new_timeout) - return -EINVAL; - timeout = new_timeout; - xen_wdt_kick(); - /* fall through */ - case WDIOC_GETTIMEOUT: - return put_user(timeout, argp); - - case WDIOC_GETTIMELEFT: - retval = wdt_expires - ktime_to_timespec(ktime_get()).tv_sec; - return put_user(retval, argp); - } - - return -ENOTTY; -} +static struct watchdog_info xen_wdt_info = { + .identity = DRV_NAME, + .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, +}; -static const struct file_operations xen_wdt_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .write = xen_wdt_write, - .unlocked_ioctl = xen_wdt_ioctl, - .open = xen_wdt_open, - .release = xen_wdt_release, +static const struct watchdog_ops xen_wdt_ops = { + .owner = THIS_MODULE, + .start = xen_wdt_start, + .stop = xen_wdt_stop, + .ping = xen_wdt_kick, + .get_timeleft = xen_wdt_get_timeleft, }; -static struct miscdevice xen_wdt_miscdev = { - .minor = WATCHDOG_MINOR, - .name = "watchdog", - .fops = &xen_wdt_fops, +static struct watchdog_device xen_wdt_dev = { + .info = &xen_wdt_info, + .ops = &xen_wdt_ops, + .timeout = WATCHDOG_TIMEOUT, }; -static int xen_wdt_probe(struct platform_device *dev) +static int xen_wdt_probe(struct platform_device *pdev) { struct sched_watchdog wd = { .id = ~0 }; int ret = HYPERVISOR_sched_op(SCHEDOP_watchdog, &wd); - switch (ret) { - case -EINVAL: - if (!timeout) { - timeout = WATCHDOG_TIMEOUT; - pr_info("timeout value invalid, using %d\n", timeout); - } - - ret = misc_register(&xen_wdt_miscdev); - if (ret) { - pr_err("cannot register miscdev on minor=%d (%d)\n", - WATCHDOG_MINOR, ret); - break; - } - - pr_info("initialized (timeout=%ds, nowayout=%d)\n", - timeout, nowayout); - break; - - case -ENOSYS: - pr_info("not supported\n"); - ret = -ENODEV; - break; - - default: - pr_info("bogus return value %d\n", ret); - break; + if (ret == -ENOSYS) { + dev_err(&pdev->dev, "watchdog not supported by hypervisor\n"); + return -ENODEV; } - return ret; -} + if (ret != -EINVAL) { + dev_err(&pdev->dev, "unexpected hypervisor error (%d)\n", ret); + return -ENODEV; + } -static int xen_wdt_remove(struct platform_device *dev) -{ - /* Stop the timer before we leave */ - if (!nowayout) - xen_wdt_stop(); + if (watchdog_init_timeout(&xen_wdt_dev, timeout, NULL)) + dev_info(&pdev->dev, "timeout value invalid, using %d\n", + xen_wdt_dev.timeout); + watchdog_set_nowayout(&xen_wdt_dev, nowayout); + watchdog_stop_on_reboot(&xen_wdt_dev); + watchdog_stop_on_unregister(&xen_wdt_dev); + + ret = devm_watchdog_register_device(&pdev->dev, &xen_wdt_dev); + if (ret) { + dev_err(&pdev->dev, "cannot register watchdog device (%d)\n", + ret); + return ret; + } - misc_deregister(&xen_wdt_miscdev); + dev_info(&pdev->dev, "initialized (timeout=%ds, nowayout=%d)\n", + xen_wdt_dev.timeout, nowayout); return 0; } -static void xen_wdt_shutdown(struct platform_device *dev) -{ - xen_wdt_stop(); -} - static int xen_wdt_suspend(struct platform_device *dev, pm_message_t state) { typeof(wdt.id) id = wdt.id; - int rc = xen_wdt_stop(); + int rc = xen_wdt_stop(&xen_wdt_dev); wdt.id = id; return rc; @@ -310,13 +169,11 @@ static int xen_wdt_resume(struct platform_device *dev) if (!wdt.id) return 0; wdt.id = 0; - return xen_wdt_start(); + return xen_wdt_start(&xen_wdt_dev); } static struct platform_driver xen_wdt_driver = { .probe = xen_wdt_probe, - .remove = xen_wdt_remove, - .shutdown = xen_wdt_shutdown, .suspend = xen_wdt_suspend, .resume = xen_wdt_resume, .driver = { @@ -331,8 +188,6 @@ static int __init xen_wdt_init_module(void) if (!xen_domain()) return -ENODEV; - pr_info("Xen WatchDog Timer Driver v%s\n", DRV_VERSION); - err = platform_driver_register(&xen_wdt_driver); if (err) return err; @@ -351,7 +206,6 @@ static void __exit xen_wdt_cleanup_module(void) { platform_device_unregister(platform_device); platform_driver_unregister(&xen_wdt_driver); - pr_info("module unloaded\n"); } module_init(xen_wdt_init_module); @@ -359,5 +213,4 @@ module_exit(xen_wdt_cleanup_module); MODULE_AUTHOR("Jan Beulich <jbeulich@novell.com>"); MODULE_DESCRIPTION("Xen WatchDog Timer Driver"); -MODULE_VERSION(DRV_VERSION); MODULE_LICENSE("GPL"); diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 72c0416a01cc..8cac07ab60ab 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -623,14 +623,14 @@ static long evtchn_ioctl(struct file *file, static __poll_t evtchn_poll(struct file *file, poll_table *wait) { - __poll_t mask = POLLOUT | POLLWRNORM; + __poll_t mask = EPOLLOUT | EPOLLWRNORM; struct per_user_data *u = file->private_data; poll_wait(file, &u->evtchn_wait, wait); if (u->ring_cons != u->ring_prod) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (u->ring_overflow) - mask = POLLERR; + mask = EPOLLERR; return mask; } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index f45114fd8e1e..27be107d6480 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -382,7 +382,7 @@ static void gnttab_handle_deferred(struct timer_list *unused) if (entry->page) { pr_debug("freeing g.e. %#x (pfn %#lx)\n", entry->ref, page_to_pfn(entry->page)); - __free_page(entry->page); + put_page(entry->page); } else pr_info("freeing g.e. %#x\n", entry->ref); kfree(entry); @@ -438,7 +438,7 @@ void gnttab_end_foreign_access(grant_ref_t ref, int readonly, if (gnttab_end_foreign_access_ref(ref, readonly)) { put_free_entry(ref); if (page != 0) - free_page(page); + put_page(virt_to_page(page)); } else gnttab_add_deferred(ref, readonly, page ? virt_to_page(page) : NULL); diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c index 9ade533d9e40..262835ace35d 100644 --- a/drivers/xen/mcelog.c +++ b/drivers/xen/mcelog.c @@ -144,7 +144,7 @@ static __poll_t xen_mce_chrdev_poll(struct file *file, poll_table *wait) poll_wait(file, &xen_mce_chrdev_wait, wait); if (xen_mcelog.next) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index c7822d8078b9..156e5aea36db 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -548,7 +548,7 @@ static void __pvcalls_back_accept(struct work_struct *work) ret = inet_accept(mappass->sock, sock, O_NONBLOCK, true); if (ret == -EAGAIN) { sock_release(sock); - goto out_error; + return; } map = pvcalls_new_active_socket(fedata, diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 78804e71f9a6..753d9cb437d0 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -892,7 +892,7 @@ static __poll_t pvcalls_front_poll_passive(struct file *file, if (req_id != PVCALLS_INVALID_ID && READ_ONCE(bedata->rsp[req_id].req_id) == req_id) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; poll_wait(file, &map->passive.inflight_accept_req, wait); return 0; @@ -900,7 +900,7 @@ static __poll_t pvcalls_front_poll_passive(struct file *file, if (test_and_clear_bit(PVCALLS_FLAG_POLL_RET, (void *)&map->passive.flags)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; /* * First check RET, then INFLIGHT. No barriers necessary to @@ -949,11 +949,11 @@ static __poll_t pvcalls_front_poll_active(struct file *file, poll_wait(file, &map->active.inflight_conn_req, wait); if (pvcalls_front_write_todo(map)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; if (pvcalls_front_read_todo(map)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (in_error != 0 || out_error != 0) - mask |= POLLERR; + mask |= EPOLLERR; return mask; } @@ -968,14 +968,14 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock, pvcalls_enter(); if (!pvcalls_front_dev) { pvcalls_exit(); - return POLLNVAL; + return EPOLLNVAL; } bedata = dev_get_drvdata(&pvcalls_front_dev->dev); map = (struct sock_mapping *) sock->sk->sk_send_head; if (!map) { pvcalls_exit(); - return POLLNVAL; + return EPOLLNVAL; } if (map->active_socket) ret = pvcalls_front_poll_active(file, bedata, map, wait); diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index 3332978f4fcd..f694ad77379f 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -20,7 +20,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); -unsigned int pvcalls_front_poll(struct file *file, +__poll_t pvcalls_front_poll(struct file *file, struct socket *sock, poll_table *wait); int pvcalls_front_release(struct socket *sock); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index e17ec3fce590..a493e99bed21 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -651,7 +651,7 @@ static __poll_t xenbus_file_poll(struct file *file, poll_table *wait) poll_wait(file, &u->read_waitq, wait); if (!list_empty(&u->read_buffers)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/fs/affs/dir.c b/fs/affs/dir.c index d180b46453cf..b2bf7016e1b3 100644 --- a/fs/affs/dir.c +++ b/fs/affs/dir.c @@ -81,7 +81,7 @@ affs_readdir(struct file *file, struct dir_context *ctx) * we can jump directly to where we left off. */ ino = (u32)(long)file->private_data; - if (ino && inode_cmp_iversion(inode, file->f_version) == 0) { + if (ino && inode_eq_iversion(inode, file->f_version)) { pr_debug("readdir() left off=%d\n", ino); goto inside; } diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index a537368ba0db..fd9f28b8a933 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -332,11 +332,18 @@ bool afs_iterate_addresses(struct afs_addr_cursor *ac) */ int afs_end_cursor(struct afs_addr_cursor *ac) { - if (ac->responded && ac->index != ac->start) - WRITE_ONCE(ac->alist->index, ac->index); + struct afs_addr_list *alist; + + alist = ac->alist; + if (alist) { + if (ac->responded && ac->index != ac->start) + WRITE_ONCE(alist->index, ac->index); + afs_put_addrlist(alist); + } - afs_put_addrlist(ac->alist); + ac->addr = NULL; ac->alist = NULL; + ac->begun = false; return ac->error; } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 23c7f395d718..ba2b458b36d1 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -17,10 +17,13 @@ #include <linux/pagemap.h> #include <linux/ctype.h> #include <linux/sched.h> +#include <linux/dns_resolver.h> #include "internal.h" static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); +static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags); static int afs_dir_open(struct inode *inode, struct file *file); static int afs_readdir(struct file *file, struct dir_context *ctx); static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); @@ -64,6 +67,17 @@ const struct inode_operations afs_dir_inode_operations = { .listxattr = afs_listxattr, }; +const struct file_operations afs_dynroot_file_operations = { + .open = dcache_dir_open, + .release = dcache_dir_close, + .iterate_shared = dcache_readdir, + .llseek = dcache_dir_lseek, +}; + +const struct inode_operations afs_dynroot_inode_operations = { + .lookup = afs_dynroot_lookup, +}; + const struct dentry_operations afs_fs_dentry_operations = { .d_revalidate = afs_d_revalidate, .d_delete = afs_d_delete, @@ -468,25 +482,58 @@ static int afs_do_lookup(struct inode *dir, struct dentry *dentry, } /* + * Probe to see if a cell may exist. This prevents positive dentries from + * being created unnecessarily. + */ +static int afs_probe_cell_name(struct dentry *dentry) +{ + struct afs_cell *cell; + const char *name = dentry->d_name.name; + size_t len = dentry->d_name.len; + int ret; + + /* Names prefixed with a dot are R/W mounts. */ + if (name[0] == '.') { + if (len == 1) + return -EINVAL; + name++; + len--; + } + + cell = afs_lookup_cell_rcu(afs_d2net(dentry), name, len); + if (!IS_ERR(cell)) { + afs_put_cell(afs_d2net(dentry), cell); + return 0; + } + + ret = dns_query("afsdb", name, len, "ipv4", NULL, NULL); + if (ret == -ENODATA) + ret = -EDESTADDRREQ; + return ret; +} + +/* * Try to auto mount the mountpoint with pseudo directory, if the autocell * operation is setted. */ -static struct inode *afs_try_auto_mntpt( - int ret, struct dentry *dentry, struct inode *dir, struct key *key, - struct afs_fid *fid) +static struct inode *afs_try_auto_mntpt(struct dentry *dentry, + struct inode *dir, struct afs_fid *fid) { - const char *devname = dentry->d_name.name; struct afs_vnode *vnode = AFS_FS_I(dir); struct inode *inode; + int ret = -ENOENT; - _enter("%d, %p{%pd}, {%x:%u}, %p", - ret, dentry, dentry, vnode->fid.vid, vnode->fid.vnode, key); + _enter("%p{%pd}, {%x:%u}", + dentry, dentry, vnode->fid.vid, vnode->fid.vnode); + + if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags)) + goto out; - if (ret != -ENOENT || - !test_bit(AFS_VNODE_AUTOCELL, &vnode->flags)) + ret = afs_probe_cell_name(dentry); + if (ret < 0) goto out; - inode = afs_iget_autocell(dir, devname, strlen(devname), key); + inode = afs_iget_pseudo_dir(dir->i_sb, false); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto out; @@ -545,13 +592,16 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, ret = afs_do_lookup(dir, dentry, &fid, key); if (ret < 0) { - inode = afs_try_auto_mntpt(ret, dentry, dir, key, &fid); - if (!IS_ERR(inode)) { - key_put(key); - goto success; + if (ret == -ENOENT) { + inode = afs_try_auto_mntpt(dentry, dir, &fid); + if (!IS_ERR(inode)) { + key_put(key); + goto success; + } + + ret = PTR_ERR(inode); } - ret = PTR_ERR(inode); key_put(key); if (ret == -ENOENT) { d_add(dentry, NULL); @@ -583,12 +633,53 @@ success: } /* + * Look up an entry in a dynroot directory. + */ +static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct afs_vnode *vnode; + struct afs_fid fid; + struct inode *inode; + int ret; + + vnode = AFS_FS_I(dir); + + _enter("%pd", dentry); + + ASSERTCMP(d_inode(dentry), ==, NULL); + + if (dentry->d_name.len >= AFSNAMEMAX) { + _leave(" = -ENAMETOOLONG"); + return ERR_PTR(-ENAMETOOLONG); + } + + inode = afs_try_auto_mntpt(dentry, dir, &fid); + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + if (ret == -ENOENT) { + d_add(dentry, NULL); + _leave(" = NULL [negative]"); + return NULL; + } + _leave(" = %d [do]", ret); + return ERR_PTR(ret); + } + + d_add(dentry, inode); + _leave(" = 0 { ino=%lu v=%u }", + d_inode(dentry)->i_ino, d_inode(dentry)->i_generation); + return NULL; +} + +/* * check that a dentry lookup hit has found a valid entry * - NOTE! the hit can be a negative hit too, so we can't assume we have an * inode */ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) { + struct afs_super_info *as = dentry->d_sb->s_fs_info; struct afs_vnode *vnode, *dir; struct afs_fid uninitialized_var(fid); struct dentry *parent; @@ -600,6 +691,9 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (flags & LOOKUP_RCU) return -ECHILD; + if (as->dyn_root) + return 1; + if (d_really_is_positive(dentry)) { vnode = AFS_FS_I(d_inode(dentry)); _enter("{v={%x:%u} n=%pd fl=%lx},", diff --git a/fs/afs/inode.c b/fs/afs/inode.c index c7f17c44c7ce..6b39d0255b72 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -147,7 +147,7 @@ int afs_iget5_test(struct inode *inode, void *opaque) * * These pseudo inodes don't match anything. */ -static int afs_iget5_autocell_test(struct inode *inode, void *opaque) +static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque) { return 0; } @@ -169,31 +169,34 @@ static int afs_iget5_set(struct inode *inode, void *opaque) } /* - * inode retrieval for autocell + * Create an inode for a dynamic root directory or an autocell dynamic + * automount dir. */ -struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name, - int namesz, struct key *key) +struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) { struct afs_iget_data data; struct afs_super_info *as; struct afs_vnode *vnode; - struct super_block *sb; struct inode *inode; static atomic_t afs_autocell_ino; - _enter("{%x:%u},%*.*s,", - AFS_FS_I(dir)->fid.vid, AFS_FS_I(dir)->fid.vnode, - namesz, namesz, dev_name ?: ""); + _enter(""); - sb = dir->i_sb; as = sb->s_fs_info; - data.volume = as->volume; - data.fid.vid = as->volume->vid; - data.fid.unique = 0; - data.fid.vnode = 0; + if (as->volume) { + data.volume = as->volume; + data.fid.vid = as->volume->vid; + } + if (root) { + data.fid.vnode = 1; + data.fid.unique = 1; + } else { + data.fid.vnode = atomic_inc_return(&afs_autocell_ino); + data.fid.unique = 0; + } - inode = iget5_locked(sb, atomic_inc_return(&afs_autocell_ino), - afs_iget5_autocell_test, afs_iget5_set, + inode = iget5_locked(sb, data.fid.vnode, + afs_iget5_pseudo_dir_test, afs_iget5_set, &data); if (!inode) { _leave(" = -ENOMEM"); @@ -211,7 +214,12 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name, inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; - inode->i_op = &afs_autocell_inode_operations; + if (root) { + inode->i_op = &afs_dynroot_inode_operations; + inode->i_fop = &afs_dynroot_file_operations; + } else { + inode->i_op = &afs_autocell_inode_operations; + } set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; @@ -223,8 +231,12 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name, inode->i_generation = 0; set_bit(AFS_VNODE_PSEUDODIR, &vnode->flags); - set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); - inode->i_flags |= S_AUTOMOUNT | S_NOATIME; + if (!root) { + set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); + inode->i_flags |= S_AUTOMOUNT; + } + + inode->i_flags |= S_NOATIME; unlock_new_inode(inode); _leave(" = %p", inode); return inode; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 804d1f905622..f38d6a561a84 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -36,6 +36,7 @@ struct afs_mount_params { bool rwpath; /* T if the parent should be considered R/W */ bool force; /* T to force cell type */ bool autocell; /* T if set auto mount operation */ + bool dyn_root; /* T if dynamic root */ afs_voltype_t type; /* type of volume requested */ int volnamesz; /* size of volume name */ const char *volname; /* name of volume to mount */ @@ -186,6 +187,7 @@ struct afs_super_info { struct afs_net *net; /* Network namespace */ struct afs_cell *cell; /* The cell in which the volume resides */ struct afs_volume *volume; /* volume record */ + bool dyn_root; /* True if dynamic root */ }; static inline struct afs_super_info *AFS_FS_S(struct super_block *sb) @@ -634,10 +636,13 @@ extern bool afs_cm_incoming_call(struct afs_call *); /* * dir.c */ -extern bool afs_dir_check_page(struct inode *, struct page *); +extern const struct file_operations afs_dir_file_operations; extern const struct inode_operations afs_dir_inode_operations; +extern const struct file_operations afs_dynroot_file_operations; +extern const struct inode_operations afs_dynroot_inode_operations; extern const struct dentry_operations afs_fs_dentry_operations; -extern const struct file_operations afs_dir_file_operations; + +extern bool afs_dir_check_page(struct inode *, struct page *); /* * file.c @@ -695,8 +700,7 @@ extern int afs_fs_get_capabilities(struct afs_net *, struct afs_server *, */ extern int afs_fetch_status(struct afs_vnode *, struct key *); extern int afs_iget5_test(struct inode *, void *); -extern struct inode *afs_iget_autocell(struct inode *, const char *, int, - struct key *); +extern struct inode *afs_iget_pseudo_dir(struct super_block *, bool); extern struct inode *afs_iget(struct super_block *, struct key *, struct afs_fid *, struct afs_file_status *, struct afs_callback *, diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 690fea9d84c3..99fd13500a97 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -72,7 +72,7 @@ static int afs_mntpt_open(struct inode *inode, struct file *file) */ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) { - struct afs_super_info *super; + struct afs_super_info *as; struct vfsmount *mnt; struct afs_vnode *vnode; struct page *page; @@ -104,13 +104,13 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) goto error_no_page; if (mntpt->d_name.name[0] == '.') { - devname[0] = '#'; - memcpy(devname + 1, mntpt->d_name.name, size - 1); + devname[0] = '%'; + memcpy(devname + 1, mntpt->d_name.name + 1, size - 1); memcpy(devname + size, afs_root_cell, sizeof(afs_root_cell)); rwpath = true; } else { - devname[0] = '%'; + devname[0] = '#'; memcpy(devname + 1, mntpt->d_name.name, size); memcpy(devname + size + 1, afs_root_cell, sizeof(afs_root_cell)); @@ -142,11 +142,13 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) } /* work out what options we want */ - super = AFS_FS_S(mntpt->d_sb); - memcpy(options, "cell=", 5); - strcpy(options + 5, super->volume->cell->name); - if (super->volume->type == AFSVL_RWVOL || rwpath) - strcat(options, ",rwpath"); + as = AFS_FS_S(mntpt->d_sb); + if (as->cell) { + memcpy(options, "cell=", 5); + strcpy(options + 5, as->cell->name); + if ((as->volume && as->volume->type == AFSVL_RWVOL) || rwpath) + strcat(options, ",rwpath"); + } /* try and do the mount */ _debug("--- attempting mount %s -o %s ---", devname, options); diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index d04511fb3879..ad1328d85526 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -330,26 +330,6 @@ start: if (!afs_start_fs_iteration(fc, vnode)) goto failed; - goto use_server; - -next_server: - _debug("next"); - afs_put_cb_interest(afs_v2net(vnode), fc->cbi); - fc->cbi = NULL; - fc->index++; - if (fc->index >= fc->server_list->nr_servers) - fc->index = 0; - if (fc->index != fc->start) - goto use_server; - - /* That's all the servers poked to no good effect. Try again if some - * of them were busy. - */ - if (fc->flags & AFS_FS_CURSOR_VBUSY) - goto restart_from_beginning; - - fc->ac.error = -EDESTADDRREQ; - goto failed; use_server: _debug("use"); @@ -383,6 +363,7 @@ use_server: afs_get_addrlist(alist); read_unlock(&server->fs_lock); + memset(&fc->ac, 0, sizeof(fc->ac)); /* Probe the current fileserver if we haven't done so yet. */ if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) { @@ -397,12 +378,8 @@ use_server: else afs_put_addrlist(alist); - fc->ac.addr = NULL; fc->ac.start = READ_ONCE(alist->index); fc->ac.index = fc->ac.start; - fc->ac.error = 0; - fc->ac.begun = false; - goto iterate_address; iterate_address: ASSERT(fc->ac.alist); @@ -410,16 +387,35 @@ iterate_address: /* Iterate over the current server's address list to try and find an * address on which it will respond to us. */ - if (afs_iterate_addresses(&fc->ac)) { - _leave(" = t"); - return true; - } + if (!afs_iterate_addresses(&fc->ac)) + goto next_server; + + _leave(" = t"); + return true; +next_server: + _debug("next"); afs_end_cursor(&fc->ac); - goto next_server; + afs_put_cb_interest(afs_v2net(vnode), fc->cbi); + fc->cbi = NULL; + fc->index++; + if (fc->index >= fc->server_list->nr_servers) + fc->index = 0; + if (fc->index != fc->start) + goto use_server; + + /* That's all the servers poked to no good effect. Try again if some + * of them were busy. + */ + if (fc->flags & AFS_FS_CURSOR_VBUSY) + goto restart_from_beginning; + + fc->ac.error = -EDESTADDRREQ; + goto failed; failed: fc->flags |= AFS_FS_CURSOR_STOP; + afs_end_cursor(&fc->ac); _leave(" = f [failed %d]", fc->ac.error); return false; } @@ -458,12 +454,10 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) return false; } + memset(&fc->ac, 0, sizeof(fc->ac)); fc->ac.alist = alist; - fc->ac.addr = NULL; fc->ac.start = READ_ONCE(alist->index); fc->ac.index = fc->ac.start; - fc->ac.error = 0; - fc->ac.begun = false; goto iterate_address; case 0: @@ -520,238 +514,3 @@ int afs_end_vnode_operation(struct afs_fs_cursor *fc) return fc->ac.error; } - -#if 0 -/* - * Set a filesystem server cursor for using a specific FS server. - */ -int afs_set_fs_cursor(struct afs_fs_cursor *fc, struct afs_vnode *vnode) -{ - afs_init_fs_cursor(fc, vnode); - - read_seqlock_excl(&vnode->cb_lock); - if (vnode->cb_interest) { - if (vnode->cb_interest->server->fs_state == 0) - fc->server = afs_get_server(vnode->cb_interest->server); - else - fc->ac.error = vnode->cb_interest->server->fs_state; - } else { - fc->ac.error = -ESTALE; - } - read_sequnlock_excl(&vnode->cb_lock); - - return fc->ac.error; -} - -/* - * pick a server to use to try accessing this volume - * - returns with an elevated usage count on the server chosen - */ -bool afs_volume_pick_fileserver(struct afs_fs_cursor *fc, struct afs_vnode *vnode) -{ - struct afs_volume *volume = vnode->volume; - struct afs_server *server; - int ret, state, loop; - - _enter("%s", volume->vlocation->vldb.name); - - /* stick with the server we're already using if we can */ - if (vnode->cb_interest && vnode->cb_interest->server->fs_state == 0) { - fc->server = afs_get_server(vnode->cb_interest->server); - goto set_server; - } - - down_read(&volume->server_sem); - - /* handle the no-server case */ - if (volume->nservers == 0) { - fc->ac.error = volume->rjservers ? -ENOMEDIUM : -ESTALE; - up_read(&volume->server_sem); - _leave(" = f [no servers %d]", fc->ac.error); - return false; - } - - /* basically, just search the list for the first live server and use - * that */ - ret = 0; - for (loop = 0; loop < volume->nservers; loop++) { - server = volume->servers[loop]; - state = server->fs_state; - - _debug("consider %d [%d]", loop, state); - - switch (state) { - case 0: - goto picked_server; - - case -ENETUNREACH: - if (ret == 0) - ret = state; - break; - - case -EHOSTUNREACH: - if (ret == 0 || - ret == -ENETUNREACH) - ret = state; - break; - - case -ECONNREFUSED: - if (ret == 0 || - ret == -ENETUNREACH || - ret == -EHOSTUNREACH) - ret = state; - break; - - default: - case -EREMOTEIO: - if (ret == 0 || - ret == -ENETUNREACH || - ret == -EHOSTUNREACH || - ret == -ECONNREFUSED) - ret = state; - break; - } - } - -error: - fc->ac.error = ret; - - /* no available servers - * - TODO: handle the no active servers case better - */ - up_read(&volume->server_sem); - _leave(" = f [%d]", fc->ac.error); - return false; - -picked_server: - /* Found an apparently healthy server. We need to register an interest - * in receiving callbacks before we talk to it. - */ - ret = afs_register_server_cb_interest(vnode, - &volume->cb_interests[loop], server); - if (ret < 0) - goto error; - - fc->server = afs_get_server(server); - up_read(&volume->server_sem); -set_server: - fc->ac.alist = afs_get_addrlist(fc->server->addrs); - fc->ac.addr = &fc->ac.alist->addrs[0]; - _debug("USING SERVER: %pIS\n", &fc->ac.addr->transport); - _leave(" = t (picked %pIS)", &fc->ac.addr->transport); - return true; -} - -/* - * release a server after use - * - releases the ref on the server struct that was acquired by picking - * - records result of using a particular server to access a volume - * - return true to try again, false if okay or to issue error - * - the caller must release the server struct if result was false - */ -bool afs_iterate_fs_cursor(struct afs_fs_cursor *fc, - struct afs_vnode *vnode) -{ - struct afs_volume *volume = vnode->volume; - struct afs_server *server = fc->server; - unsigned loop; - - _enter("%s,%pIS,%d", - volume->vlocation->vldb.name, &fc->ac.addr->transport, - fc->ac.error); - - switch (fc->ac.error) { - /* success */ - case 0: - server->fs_state = 0; - _leave(" = f"); - return false; - - /* the fileserver denied all knowledge of the volume */ - case -ENOMEDIUM: - down_write(&volume->server_sem); - - /* firstly, find where the server is in the active list (if it - * is) */ - for (loop = 0; loop < volume->nservers; loop++) - if (volume->servers[loop] == server) - goto present; - - /* no longer there - may have been discarded by another op */ - goto try_next_server_upw; - - present: - volume->nservers--; - memmove(&volume->servers[loop], - &volume->servers[loop + 1], - sizeof(volume->servers[loop]) * - (volume->nservers - loop)); - volume->servers[volume->nservers] = NULL; - afs_put_server(afs_v2net(vnode), server); - volume->rjservers++; - - if (volume->nservers > 0) - /* another server might acknowledge its existence */ - goto try_next_server_upw; - - /* handle the case where all the fileservers have rejected the - * volume - * - TODO: try asking the fileservers for volume information - * - TODO: contact the VL server again to see if the volume is - * no longer registered - */ - up_write(&volume->server_sem); - afs_put_server(afs_v2net(vnode), server); - fc->server = NULL; - _leave(" = f [completely rejected]"); - return false; - - /* problem reaching the server */ - case -ENETUNREACH: - case -EHOSTUNREACH: - case -ECONNREFUSED: - case -ETIME: - case -ETIMEDOUT: - case -EREMOTEIO: - /* mark the server as dead - * TODO: vary dead timeout depending on error - */ - spin_lock(&server->fs_lock); - if (!server->fs_state) { - server->fs_state = fc->ac.error; - printk("kAFS: SERVER DEAD state=%d\n", fc->ac.error); - } - spin_unlock(&server->fs_lock); - goto try_next_server; - - /* miscellaneous error */ - default: - case -ENOMEM: - case -ENONET: - /* tell the caller to accept the result */ - afs_put_server(afs_v2net(vnode), server); - fc->server = NULL; - _leave(" = f [local failure]"); - return false; - } - - /* tell the caller to loop around and try the next server */ -try_next_server_upw: - up_write(&volume->server_sem); -try_next_server: - afs_put_server(afs_v2net(vnode), server); - _leave(" = t [try next server]"); - return true; -} - -/* - * Clean up a fileserver cursor. - */ -int afs_end_fs_cursor(struct afs_fs_cursor *fc, struct afs_net *net) -{ - afs_end_cursor(&fc->ac); - afs_put_server(net, fc->server); - return fc->ac.error; -} - -#endif diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 0ab3f8457839..0f8dc4c8f07c 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -58,7 +58,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, server = afs_lookup_server(cell, key, &vldb->fs_server[i]); if (IS_ERR(server)) { ret = PTR_ERR(server); - if (ret == -ENOENT) + if (ret == -ENOENT || + ret == -ENOMEDIUM) continue; goto error_2; } diff --git a/fs/afs/super.c b/fs/afs/super.c index 1037dd41a622..3623c952b6ff 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -64,6 +64,7 @@ static atomic_t afs_count_active_inodes; enum { afs_no_opt, afs_opt_cell, + afs_opt_dyn, afs_opt_rwpath, afs_opt_vol, afs_opt_autocell, @@ -71,6 +72,7 @@ enum { static const match_table_t afs_options_list = { { afs_opt_cell, "cell=%s" }, + { afs_opt_dyn, "dyn" }, { afs_opt_rwpath, "rwpath" }, { afs_opt_vol, "vol=%s" }, { afs_opt_autocell, "autocell" }, @@ -148,6 +150,11 @@ static int afs_show_devname(struct seq_file *m, struct dentry *root) const char *suf = ""; char pref = '%'; + if (as->dyn_root) { + seq_puts(m, "none"); + return 0; + } + switch (volume->type) { case AFSVL_RWVOL: break; @@ -171,8 +178,12 @@ static int afs_show_devname(struct seq_file *m, struct dentry *root) */ static int afs_show_options(struct seq_file *m, struct dentry *root) { + struct afs_super_info *as = AFS_FS_S(root->d_sb); + + if (as->dyn_root) + seq_puts(m, ",dyn"); if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags)) - seq_puts(m, "autocell"); + seq_puts(m, ",autocell"); return 0; } @@ -212,7 +223,7 @@ static int afs_parse_options(struct afs_mount_params *params, break; case afs_opt_rwpath: - params->rwpath = 1; + params->rwpath = true; break; case afs_opt_vol: @@ -220,7 +231,11 @@ static int afs_parse_options(struct afs_mount_params *params, break; case afs_opt_autocell: - params->autocell = 1; + params->autocell = true; + break; + + case afs_opt_dyn: + params->dyn_root = true; break; default: @@ -254,7 +269,7 @@ static int afs_parse_device_name(struct afs_mount_params *params, int cellnamesz; _enter(",%s", name); - + if (!name) { printk(KERN_ERR "kAFS: no volume name specified\n"); return -EINVAL; @@ -336,7 +351,14 @@ static int afs_test_super(struct super_block *sb, void *data) struct afs_super_info *as1 = data; struct afs_super_info *as = AFS_FS_S(sb); - return as->net == as1->net && as->volume->vid == as1->volume->vid; + return (as->net == as1->net && + as->volume && + as->volume->vid == as1->volume->vid); +} + +static int afs_dynroot_test_super(struct super_block *sb, void *data) +{ + return false; } static int afs_set_super(struct super_block *sb, void *data) @@ -365,24 +387,30 @@ static int afs_fill_super(struct super_block *sb, sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; - sb->s_xattr = afs_xattr_handlers; + if (!as->dyn_root) + sb->s_xattr = afs_xattr_handlers; ret = super_setup_bdi(sb); if (ret) return ret; sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE; - sprintf(sb->s_id, "%u", as->volume->vid); - - afs_activate_volume(as->volume); /* allocate the root inode and dentry */ - fid.vid = as->volume->vid; - fid.vnode = 1; - fid.unique = 1; - inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL); + if (as->dyn_root) { + inode = afs_iget_pseudo_dir(sb, true); + sb->s_flags |= SB_RDONLY; + } else { + sprintf(sb->s_id, "%u", as->volume->vid); + afs_activate_volume(as->volume); + fid.vid = as->volume->vid; + fid.vnode = 1; + fid.unique = 1; + inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL); + } + if (IS_ERR(inode)) return PTR_ERR(inode); - if (params->autocell) + if (params->autocell || params->dyn_root) set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags); ret = -ENOMEM; @@ -407,7 +435,10 @@ static struct afs_super_info *afs_alloc_sbi(struct afs_mount_params *params) as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL); if (as) { as->net = afs_get_net(params->net); - as->cell = afs_get_cell(params->cell); + if (params->dyn_root) + as->dyn_root = true; + else + as->cell = afs_get_cell(params->cell); } return as; } @@ -451,18 +482,20 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, goto error; } - ret = afs_parse_device_name(¶ms, dev_name); - if (ret < 0) - goto error; + if (!params.dyn_root) { + ret = afs_parse_device_name(¶ms, dev_name); + if (ret < 0) + goto error; - /* try and do the mount securely */ - key = afs_request_key(params.cell); - if (IS_ERR(key)) { - _leave(" = %ld [key]", PTR_ERR(key)); - ret = PTR_ERR(key); - goto error; + /* try and do the mount securely */ + key = afs_request_key(params.cell); + if (IS_ERR(key)) { + _leave(" = %ld [key]", PTR_ERR(key)); + ret = PTR_ERR(key); + goto error; + } + params.key = key; } - params.key = key; /* allocate a superblock info record */ ret = -ENOMEM; @@ -470,20 +503,25 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, if (!as) goto error_key; - /* Assume we're going to need a volume record; at the very least we can - * use it to update the volume record if we have one already. This - * checks that the volume exists within the cell. - */ - candidate = afs_create_volume(¶ms); - if (IS_ERR(candidate)) { - ret = PTR_ERR(candidate); - goto error_as; - } + if (!params.dyn_root) { + /* Assume we're going to need a volume record; at the very + * least we can use it to update the volume record if we have + * one already. This checks that the volume exists within the + * cell. + */ + candidate = afs_create_volume(¶ms); + if (IS_ERR(candidate)) { + ret = PTR_ERR(candidate); + goto error_as; + } - as->volume = candidate; + as->volume = candidate; + } /* allocate a deviceless superblock */ - sb = sget(fs_type, afs_test_super, afs_set_super, flags, as); + sb = sget(fs_type, + as->dyn_root ? afs_dynroot_test_super : afs_test_super, + afs_set_super, flags, as); if (IS_ERR(sb)) { ret = PTR_ERR(sb); goto error_as; @@ -529,9 +567,11 @@ static void afs_kill_super(struct super_block *sb) /* Clear the callback interests (which will do ilookup5) before * deactivating the superblock. */ - afs_clear_callback_interests(as->net, as->volume->servers); + if (as->volume) + afs_clear_callback_interests(as->net, as->volume->servers); kill_anon_super(sb); - afs_deactivate_volume(as->volume); + if (as->volume) + afs_deactivate_volume(as->volume); afs_destroy_sbi(as); } @@ -619,12 +659,24 @@ static void afs_destroy_inode(struct inode *inode) */ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) { + struct afs_super_info *as = AFS_FS_S(dentry->d_sb); struct afs_fs_cursor fc; struct afs_volume_status vs; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); struct key *key; int ret; + buf->f_type = dentry->d_sb->s_magic; + buf->f_bsize = AFS_BLOCK_SIZE; + buf->f_namelen = AFSNAMEMAX - 1; + + if (as->dyn_root) { + buf->f_blocks = 1; + buf->f_bavail = 0; + buf->f_bfree = 0; + return 0; + } + key = afs_request_key(vnode->volume->cell); if (IS_ERR(key)) return PTR_ERR(key); @@ -645,10 +697,6 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) key_put(key); if (ret == 0) { - buf->f_type = dentry->d_sb->s_magic; - buf->f_bsize = AFS_BLOCK_SIZE; - buf->f_namelen = AFSNAMEMAX - 1; - if (vs.max_quota == 0) buf->f_blocks = vs.part_max_blocks; else diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index e372f89fd36a..5d8562f1ad4a 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -23,7 +23,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) struct afs_uvldbentry__xdr *uvldb; struct afs_vldb_entry *entry; bool new_only = false; - u32 tmp; + u32 tmp, nr_servers; int i, ret; _enter(""); @@ -36,6 +36,10 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) uvldb = call->buffer; entry = call->reply[0]; + nr_servers = ntohl(uvldb->nServers); + if (nr_servers > AFS_NMAXNSERVERS) + nr_servers = AFS_NMAXNSERVERS; + for (i = 0; i < ARRAY_SIZE(uvldb->name) - 1; i++) entry->name[i] = (u8)ntohl(uvldb->name[i]); entry->name[i] = 0; @@ -44,14 +48,14 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) /* If there is a new replication site that we can use, ignore all the * sites that aren't marked as new. */ - for (i = 0; i < AFS_NMAXNSERVERS; i++) { + for (i = 0; i < nr_servers; i++) { tmp = ntohl(uvldb->serverFlags[i]); if (!(tmp & AFS_VLSF_DONTUSE) && (tmp & AFS_VLSF_NEWREPSITE)) new_only = true; } - for (i = 0; i < AFS_NMAXNSERVERS; i++) { + for (i = 0; i < nr_servers; i++) { struct afs_uuid__xdr *xdr; struct afs_uuid *uuid; int j; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 684c48293353..b517a588781f 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -26,9 +26,8 @@ static struct afs_volume *afs_alloc_volume(struct afs_mount_params *params, unsigned long type_mask) { struct afs_server_list *slist; - struct afs_server *server; struct afs_volume *volume; - int ret = -ENOMEM, nr_servers = 0, i, j; + int ret = -ENOMEM, nr_servers = 0, i; for (i = 0; i < vldb->nr_servers; i++) if (vldb->fs_mask[i] & type_mask) @@ -58,50 +57,10 @@ static struct afs_volume *afs_alloc_volume(struct afs_mount_params *params, refcount_set(&slist->usage, 1); volume->servers = slist; - - /* Make sure a records exists for each server this volume occupies. */ - for (i = 0; i < nr_servers; i++) { - if (!(vldb->fs_mask[i] & type_mask)) - continue; - - server = afs_lookup_server(params->cell, params->key, - &vldb->fs_server[i]); - if (IS_ERR(server)) { - ret = PTR_ERR(server); - if (ret == -ENOENT) - continue; - goto error_2; - } - - /* Insertion-sort by server pointer */ - for (j = 0; j < slist->nr_servers; j++) - if (slist->servers[j].server >= server) - break; - if (j < slist->nr_servers) { - if (slist->servers[j].server == server) { - afs_put_server(params->net, server); - continue; - } - - memmove(slist->servers + j + 1, - slist->servers + j, - (slist->nr_servers - j) * sizeof(struct afs_server_entry)); - } - - slist->servers[j].server = server; - slist->nr_servers++; - } - - if (slist->nr_servers == 0) { - ret = -EDESTADDRREQ; - goto error_2; - } - return volume; -error_2: - afs_put_serverlist(params->net, slist); error_1: + afs_put_cell(params->net, volume->cell); kfree(volume); error_0: return ERR_PTR(ret); @@ -327,7 +286,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* See if the volume's server list got updated. */ new = afs_alloc_server_list(volume->cell, key, - vldb, (1 << volume->type)); + vldb, (1 << volume->type)); if (IS_ERR(new)) { ret = PTR_ERR(new); goto error_vldb; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 83732fef510d..bdb201230bae 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1599,6 +1599,8 @@ static int fill_files_note(struct memelfnote *note) /* *Estimated* file count and total data size needed */ count = current->mm->map_count; + if (count > UINT_MAX / 64) + return -EINVAL; size = count * 64; names_ofs = (2 + 3 * count) * sizeof(data[0]); diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 7edbd0679952..3fdee214a5bb 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -289,7 +289,7 @@ found_command: /* * poll for culling state - * - use POLLOUT to indicate culling state + * - use EPOLLOUT to indicate culling state */ static __poll_t cachefiles_daemon_poll(struct file *file, struct poll_table_struct *poll) @@ -301,10 +301,10 @@ static __poll_t cachefiles_daemon_poll(struct file *file, mask = 0; if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags)) - mask |= POLLIN; + mask |= EPOLLIN; if (test_bit(CACHEFILES_CULLING, &cache->flags)) - mask |= POLLOUT; + mask |= EPOLLOUT; return mask; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index dbf07051aacd..b4336b42ce3b 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -299,7 +299,8 @@ unlock: * start an async read(ahead) operation. return nr_pages we submitted * a read for on success, or negative error code. */ -static int start_read(struct inode *inode, struct list_head *page_list, int max) +static int start_read(struct inode *inode, struct ceph_rw_context *rw_ctx, + struct list_head *page_list, int max) { struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->client->osdc; @@ -316,7 +317,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) int got = 0; int ret = 0; - if (!current->journal_info) { + if (!rw_ctx) { /* caller of readpages does not hold buffer and read caps * (fadvise, madvise and readahead cases) */ int want = CEPH_CAP_FILE_CACHE; @@ -437,6 +438,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, { struct inode *inode = file_inode(file); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_file_info *ci = file->private_data; + struct ceph_rw_context *rw_ctx; int rc = 0; int max = 0; @@ -449,11 +452,12 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, if (rc == 0) goto out; + rw_ctx = ceph_find_rw_context(ci); max = fsc->mount_options->rsize >> PAGE_SHIFT; - dout("readpages %p file %p nr_pages %d max %d\n", - inode, file, nr_pages, max); + dout("readpages %p file %p ctx %p nr_pages %d max %d\n", + inode, file, rw_ctx, nr_pages, max); while (!list_empty(page_list)) { - rc = start_read(inode, page_list, max); + rc = start_read(inode, rw_ctx, page_list, max); if (rc < 0) goto out; } @@ -574,7 +578,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) struct ceph_fs_client *fsc; struct ceph_snap_context *snapc, *oldest; loff_t page_off = page_offset(page); - long writeback_stat; int err, len = PAGE_SIZE; struct ceph_writeback_ctl ceph_wbc; @@ -615,8 +618,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %p page %p index %lu on %llu~%u snapc %p seq %lld\n", inode, page, page->index, page_off, len, snapc, snapc->seq); - writeback_stat = atomic_long_inc_return(&fsc->writeback_count); - if (writeback_stat > + if (atomic_long_inc_return(&fsc->writeback_count) > CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb)) set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); @@ -651,6 +653,11 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) end_page_writeback(page); ceph_put_wrbuffer_cap_refs(ci, 1, snapc); ceph_put_snap_context(snapc); /* page's reference */ + + if (atomic_long_dec_return(&fsc->writeback_count) < + CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb)) + clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); + return err; } @@ -1450,9 +1457,10 @@ static int ceph_filemap_fault(struct vm_fault *vmf) if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) || ci->i_inline_version == CEPH_INLINE_NONE) { - current->journal_info = vma->vm_file; + CEPH_DEFINE_RW_CONTEXT(rw_ctx, got); + ceph_add_rw_context(fi, &rw_ctx); ret = filemap_fault(vmf); - current->journal_info = NULL; + ceph_del_rw_context(fi, &rw_ctx); } else ret = -EAGAIN; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index a14b2c974c9e..6582c4507e6c 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -154,13 +154,19 @@ void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta) spin_unlock(&mdsc->caps_list_lock); } -void ceph_reserve_caps(struct ceph_mds_client *mdsc, +/* + * Called under mdsc->mutex. + */ +int ceph_reserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx, int need) { - int i; + int i, j; struct ceph_cap *cap; int have; int alloc = 0; + int max_caps; + bool trimmed = false; + struct ceph_mds_session *s; LIST_HEAD(newcaps); dout("reserve caps ctx=%p need=%d\n", ctx, need); @@ -179,16 +185,37 @@ void ceph_reserve_caps(struct ceph_mds_client *mdsc, spin_unlock(&mdsc->caps_list_lock); for (i = have; i < need; i++) { +retry: cap = kmem_cache_alloc(ceph_cap_cachep, GFP_NOFS); - if (!cap) - break; + if (!cap) { + if (!trimmed) { + for (j = 0; j < mdsc->max_sessions; j++) { + s = __ceph_lookup_mds_session(mdsc, j); + if (!s) + continue; + mutex_unlock(&mdsc->mutex); + + mutex_lock(&s->s_mutex); + max_caps = s->s_nr_caps - (need - i); + ceph_trim_caps(mdsc, s, max_caps); + mutex_unlock(&s->s_mutex); + + ceph_put_mds_session(s); + mutex_lock(&mdsc->mutex); + } + trimmed = true; + goto retry; + } else { + pr_warn("reserve caps ctx=%p ENOMEM " + "need=%d got=%d\n", + ctx, need, have + alloc); + goto out_nomem; + } + } list_add(&cap->caps_item, &newcaps); alloc++; } - /* we didn't manage to reserve as much as we needed */ - if (have + alloc != need) - pr_warn("reserve caps ctx=%p ENOMEM need=%d got=%d\n", - ctx, need, have + alloc); + BUG_ON(have + alloc != need); spin_lock(&mdsc->caps_list_lock); mdsc->caps_total_count += alloc; @@ -204,6 +231,24 @@ void ceph_reserve_caps(struct ceph_mds_client *mdsc, dout("reserve caps ctx=%p %d = %d used + %d resv + %d avail\n", ctx, mdsc->caps_total_count, mdsc->caps_use_count, mdsc->caps_reserve_count, mdsc->caps_avail_count); + return 0; + +out_nomem: + while (!list_empty(&newcaps)) { + cap = list_first_entry(&newcaps, + struct ceph_cap, caps_item); + list_del(&cap->caps_item); + kmem_cache_free(ceph_cap_cachep, cap); + } + + spin_lock(&mdsc->caps_list_lock); + mdsc->caps_avail_count += have; + mdsc->caps_reserve_count -= have; + BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count + + mdsc->caps_reserve_count + + mdsc->caps_avail_count); + spin_unlock(&mdsc->caps_list_lock); + return -ENOMEM; } int ceph_unreserve_caps(struct ceph_mds_client *mdsc, @@ -498,7 +543,7 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, */ if ((issued & CEPH_CAP_FILE_SHARED) != (had & CEPH_CAP_FILE_SHARED)) { if (issued & CEPH_CAP_FILE_SHARED) - ci->i_shared_gen++; + atomic_inc(&ci->i_shared_gen); if (S_ISDIR(ci->vfs_inode.i_mode)) { dout(" marking %p NOT complete\n", &ci->vfs_inode); __ceph_dir_clear_complete(ci); @@ -577,18 +622,30 @@ void ceph_add_cap(struct inode *inode, } } - if (!ci->i_snap_realm) { + if (!ci->i_snap_realm || + ((flags & CEPH_CAP_FLAG_AUTH) && + realmino != (u64)-1 && ci->i_snap_realm->ino != realmino)) { /* * add this inode to the appropriate snap realm */ struct ceph_snap_realm *realm = ceph_lookup_snap_realm(mdsc, realmino); if (realm) { + struct ceph_snap_realm *oldrealm = ci->i_snap_realm; + if (oldrealm) { + spin_lock(&oldrealm->inodes_with_caps_lock); + list_del_init(&ci->i_snap_realm_item); + spin_unlock(&oldrealm->inodes_with_caps_lock); + } + spin_lock(&realm->inodes_with_caps_lock); ci->i_snap_realm = realm; list_add(&ci->i_snap_realm_item, &realm->inodes_with_caps); spin_unlock(&realm->inodes_with_caps_lock); + + if (oldrealm) + ceph_put_snap_realm(mdsc, oldrealm); } else { pr_err("ceph_add_cap: couldn't find snap realm %llx\n", realmino); @@ -890,6 +947,11 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check) /* * called under i_ceph_lock */ +static int __ceph_is_single_caps(struct ceph_inode_info *ci) +{ + return rb_first(&ci->i_caps) == rb_last(&ci->i_caps); +} + static int __ceph_is_any_caps(struct ceph_inode_info *ci) { return !RB_EMPTY_ROOT(&ci->i_caps); @@ -1703,21 +1765,24 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags, int mds = -1; /* keep track of how far we've gone through i_caps list to avoid an infinite loop on retry */ struct rb_node *p; - int delayed = 0, sent = 0, num; - bool is_delayed = flags & CHECK_CAPS_NODELAY; + int delayed = 0, sent = 0; + bool no_delay = flags & CHECK_CAPS_NODELAY; bool queue_invalidate = false; - bool force_requeue = false; bool tried_invalidate = false; /* if we are unmounting, flush any unused caps immediately. */ if (mdsc->stopping) - is_delayed = true; + no_delay = true; spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_FLUSH) flags |= CHECK_CAPS_FLUSH; + if (!(flags & CHECK_CAPS_AUTHONLY) || + (ci->i_auth_cap && __ceph_is_single_caps(ci))) + __cap_delay_cancel(mdsc, ci); + goto retry_locked; retry: spin_lock(&ci->i_ceph_lock); @@ -1772,7 +1837,7 @@ retry_locked: * have cached pages, but don't want them, then try to invalidate. * If we fail, it's because pages are locked.... try again later. */ - if ((!is_delayed || mdsc->stopping) && + if ((!no_delay || mdsc->stopping) && !S_ISDIR(inode->i_mode) && /* ignore readdir cache */ !(ci->i_wb_ref || ci->i_wrbuffer_ref) && /* no dirty pages... */ inode->i_data.nrpages && /* have cached pages */ @@ -1781,27 +1846,16 @@ retry_locked: !tried_invalidate) { dout("check_caps trying to invalidate on %p\n", inode); if (try_nonblocking_invalidate(inode) < 0) { - if (revoking & (CEPH_CAP_FILE_CACHE| - CEPH_CAP_FILE_LAZYIO)) { - dout("check_caps queuing invalidate\n"); - queue_invalidate = true; - ci->i_rdcache_revoking = ci->i_rdcache_gen; - } else { - dout("check_caps failed to invalidate pages\n"); - /* we failed to invalidate pages. check these - caps again later. */ - force_requeue = true; - __cap_set_timeouts(mdsc, ci); - } + dout("check_caps queuing invalidate\n"); + queue_invalidate = true; + ci->i_rdcache_revoking = ci->i_rdcache_gen; } tried_invalidate = true; goto retry_locked; } - num = 0; for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) { cap = rb_entry(p, struct ceph_cap, ci_node); - num++; /* avoid looping forever */ if (mds >= cap->mds || @@ -1864,7 +1918,7 @@ retry_locked: cap->mds_wanted == want) continue; /* nope, all good */ - if (is_delayed) + if (no_delay) goto ack; /* delay? */ @@ -1955,15 +2009,8 @@ ack: goto retry; /* retake i_ceph_lock and restart our cap scan. */ } - /* - * Reschedule delayed caps release if we delayed anything, - * otherwise cancel. - */ - if (delayed && is_delayed) - force_requeue = true; /* __send_cap delayed release; requeue */ - if (!delayed && !is_delayed) - __cap_delay_cancel(mdsc, ci); - else if (!is_delayed || force_requeue) + /* Reschedule delayed caps release if we delayed anything */ + if (delayed) __cap_delay_requeue(mdsc, ci); spin_unlock(&ci->i_ceph_lock); @@ -2160,7 +2207,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc) u64 flush_tid; int err = 0; int dirty; - int wait = wbc->sync_mode == WB_SYNC_ALL; + int wait = (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync); dout("write_inode %p wait=%d\n", inode, wait); if (wait) { @@ -3426,7 +3473,14 @@ retry: */ issued = cap->issued; - WARN_ON(issued != cap->implemented); + if (issued != cap->implemented) + pr_err_ratelimited("handle_cap_export: issued != implemented: " + "ino (%llx.%llx) mds%d seq %d mseq %d " + "issued %s implemented %s\n", + ceph_vinop(inode), mds, cap->seq, cap->mseq, + ceph_cap_string(issued), + ceph_cap_string(cap->implemented)); + tcap = __get_cap_for_mds(ci, target); if (tcap) { @@ -3572,12 +3626,13 @@ retry: if ((ph->flags & CEPH_CAP_FLAG_AUTH) && (ocap->seq != le32_to_cpu(ph->seq) || ocap->mseq != le32_to_cpu(ph->mseq))) { - pr_err("handle_cap_import: mismatched seq/mseq: " - "ino (%llx.%llx) mds%d seq %d mseq %d " - "importer mds%d has peer seq %d mseq %d\n", - ceph_vinop(inode), peer, ocap->seq, - ocap->mseq, mds, le32_to_cpu(ph->seq), - le32_to_cpu(ph->mseq)); + pr_err_ratelimited("handle_cap_import: " + "mismatched seq/mseq: ino (%llx.%llx) " + "mds%d seq %d mseq %d importer mds%d " + "has peer seq %d mseq %d\n", + ceph_vinop(inode), peer, ocap->seq, + ocap->mseq, mds, le32_to_cpu(ph->seq), + le32_to_cpu(ph->mseq)); } __ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE)); } @@ -3939,11 +3994,20 @@ int ceph_encode_inode_release(void **p, struct inode *inode, cap = __get_cap_for_mds(ci, mds); if (cap && __cap_is_valid(cap)) { - if (force || - ((cap->issued & drop) && - (cap->issued & unless) == 0)) { - if ((cap->issued & drop) && - (cap->issued & unless) == 0) { + unless &= cap->issued; + if (unless) { + if (unless & CEPH_CAP_AUTH_EXCL) + drop &= ~CEPH_CAP_AUTH_SHARED; + if (unless & CEPH_CAP_LINK_EXCL) + drop &= ~CEPH_CAP_LINK_SHARED; + if (unless & CEPH_CAP_XATTR_EXCL) + drop &= ~CEPH_CAP_XATTR_SHARED; + if (unless & CEPH_CAP_FILE_EXCL) + drop &= ~CEPH_CAP_FILE_SHARED; + } + + if (force || (cap->issued & drop)) { + if (cap->issued & drop) { int wanted = __ceph_caps_wanted(ci); if ((ci->i_ceph_flags & CEPH_I_NODELAY) == 0) wanted |= cap->mds_wanted; @@ -3975,7 +4039,7 @@ int ceph_encode_inode_release(void **p, struct inode *inode, *p += sizeof(*rel); ret = 1; } else { - dout("encode_inode_release %p cap %p %s\n", + dout("encode_inode_release %p cap %p %s (noop)\n", inode, cap, ceph_cap_string(cap->issued)); } } diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 8a5266699b67..0c4346806e17 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -173,7 +173,7 @@ __dcache_find_get_entry(struct dentry *parent, u64 idx, * the MDS if/when the directory is modified). */ static int __dcache_readdir(struct file *file, struct dir_context *ctx, - u32 shared_gen) + int shared_gen) { struct ceph_file_info *fi = file->private_data; struct dentry *parent = file->f_path.dentry; @@ -184,7 +184,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, u64 idx = 0; int err = 0; - dout("__dcache_readdir %p v%u at %llx\n", dir, shared_gen, ctx->pos); + dout("__dcache_readdir %p v%u at %llx\n", dir, (unsigned)shared_gen, ctx->pos); /* search start position */ if (ctx->pos > 2) { @@ -231,11 +231,17 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, goto out; } - di = ceph_dentry(dentry); spin_lock(&dentry->d_lock); - if (di->lease_shared_gen == shared_gen && - d_really_is_positive(dentry) && - fpos_cmp(ctx->pos, di->offset) <= 0) { + di = ceph_dentry(dentry); + if (d_unhashed(dentry) || + d_really_is_negative(dentry) || + di->lease_shared_gen != shared_gen) { + spin_unlock(&dentry->d_lock); + dput(dentry); + err = -EAGAIN; + goto out; + } + if (fpos_cmp(ctx->pos, di->offset) <= 0) { emit_dentry = true; } spin_unlock(&dentry->d_lock); @@ -333,7 +339,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) ceph_snap(inode) != CEPH_SNAPDIR && __ceph_dir_is_complete_ordered(ci) && __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) { - u32 shared_gen = ci->i_shared_gen; + int shared_gen = atomic_read(&ci->i_shared_gen); spin_unlock(&ci->i_ceph_lock); err = __dcache_readdir(file, ctx, shared_gen); if (err != -EAGAIN) @@ -381,6 +387,7 @@ more: if (op == CEPH_MDS_OP_READDIR) { req->r_direct_hash = ceph_frag_value(frag); __set_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags); + req->r_inode_drop = CEPH_CAP_FILE_EXCL; } if (fi->last_name) { req->r_path2 = kstrdup(fi->last_name, GFP_KERNEL); @@ -750,7 +757,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry, spin_unlock(&ci->i_ceph_lock); dout(" dir %p complete, -ENOENT\n", dir); d_add(dentry, NULL); - di->lease_shared_gen = ci->i_shared_gen; + di->lease_shared_gen = atomic_read(&ci->i_shared_gen); return NULL; } spin_unlock(&ci->i_ceph_lock); @@ -835,7 +842,7 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry, set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_args.mknod.mode = cpu_to_le32(mode); req->r_args.mknod.rdev = cpu_to_le32(rdev); - req->r_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (acls.pagelist) { req->r_pagelist = acls.pagelist; @@ -887,7 +894,7 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_dentry = dget(dentry); req->r_num_caps = 2; - req->r_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; err = ceph_mdsc_do_request(mdsc, dir, req); if (!err && !req->r_reply_info.head->is_dentry) @@ -936,7 +943,7 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) req->r_parent = dir; set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_args.mkdir.mode = cpu_to_le32(mode); - req->r_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (acls.pagelist) { req->r_pagelist = acls.pagelist; @@ -983,7 +990,7 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, req->r_dentry_drop = CEPH_CAP_FILE_SHARED; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; /* release LINK_SHARED on source inode (mds will lock it) */ - req->r_old_inode_drop = CEPH_CAP_LINK_SHARED; + req->r_old_inode_drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL; err = ceph_mdsc_do_request(mdsc, dir, req); if (err) { d_drop(dentry); @@ -1096,7 +1103,7 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, req->r_dentry_drop = CEPH_CAP_FILE_SHARED; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; /* release LINK_RDCACHE on source inode (mds will lock it) */ - req->r_old_inode_drop = CEPH_CAP_LINK_SHARED; + req->r_old_inode_drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL; if (d_really_is_positive(new_dentry)) req->r_inode_drop = drop_caps_for_unlink(d_inode(new_dentry)); err = ceph_mdsc_do_request(mdsc, old_dir, req); @@ -1106,16 +1113,7 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, * do_request, above). If there is no trace, we need * to do it here. */ - - /* d_move screws up sibling dentries' offsets */ - ceph_dir_clear_complete(old_dir); - ceph_dir_clear_complete(new_dir); - d_move(old_dentry, new_dentry); - - /* ensure target dentry is invalidated, despite - rehashing bug in vfs_rename_dir */ - ceph_invalidate_dentry_lease(new_dentry); } ceph_mdsc_put_request(req); return err; @@ -1199,12 +1197,12 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry) int valid = 0; spin_lock(&ci->i_ceph_lock); - if (ci->i_shared_gen == di->lease_shared_gen) + if (atomic_read(&ci->i_shared_gen) == di->lease_shared_gen) valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1); spin_unlock(&ci->i_ceph_lock); dout("dir_lease_is_valid dir %p v%u dentry %p v%u = %d\n", - dir, (unsigned)ci->i_shared_gen, dentry, - (unsigned)di->lease_shared_gen, valid); + dir, (unsigned)atomic_read(&ci->i_shared_gen), + dentry, (unsigned)di->lease_shared_gen, valid); return valid; } @@ -1332,24 +1330,37 @@ static void ceph_d_release(struct dentry *dentry) */ static void ceph_d_prune(struct dentry *dentry) { - dout("ceph_d_prune %p\n", dentry); + struct ceph_inode_info *dir_ci; + struct ceph_dentry_info *di; + + dout("ceph_d_prune %pd %p\n", dentry, dentry); /* do we have a valid parent? */ if (IS_ROOT(dentry)) return; - /* if we are not hashed, we don't affect dir's completeness */ - if (d_unhashed(dentry)) + /* we hold d_lock, so d_parent is stable */ + dir_ci = ceph_inode(d_inode(dentry->d_parent)); + if (dir_ci->i_vino.snap == CEPH_SNAPDIR) return; - if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_SNAPDIR) + /* who calls d_delete() should also disable dcache readdir */ + if (d_really_is_negative(dentry)) return; - /* - * we hold d_lock, so d_parent is stable, and d_fsdata is never - * cleared until d_release - */ - ceph_dir_clear_complete(d_inode(dentry->d_parent)); + /* d_fsdata does not get cleared until d_release */ + if (!d_unhashed(dentry)) { + __ceph_dir_clear_complete(dir_ci); + return; + } + + /* Disable dcache readdir just in case that someone called d_drop() + * or d_invalidate(), but MDS didn't revoke CEPH_CAP_FILE_SHARED + * properly (dcache readdir is still enabled) */ + di = ceph_dentry(dentry); + if (di->offset > 0 && + di->lease_shared_gen == atomic_read(&dir_ci->i_shared_gen)) + __ceph_dir_clear_ordered(dir_ci); } /* diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 5c17125f45c7..6639926eed4e 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -181,6 +181,10 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) return -ENOMEM; } cf->fmode = fmode; + + spin_lock_init(&cf->rw_contexts_lock); + INIT_LIST_HEAD(&cf->rw_contexts); + cf->next_offset = 2; cf->readdir_cache_idx = -1; file->private_data = cf; @@ -396,7 +400,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, req->r_dentry = dget(dentry); req->r_num_caps = 2; if (flags & O_CREAT) { - req->r_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (acls.pagelist) { req->r_pagelist = acls.pagelist; @@ -464,6 +468,7 @@ int ceph_release(struct inode *inode, struct file *file) ceph_mdsc_put_request(cf->last_readdir); kfree(cf->last_name); kfree(cf->dir_info); + WARN_ON(!list_empty(&cf->rw_contexts)); kmem_cache_free(ceph_file_cachep, cf); /* wake up anyone waiting for caps on this inode */ @@ -1199,12 +1204,13 @@ again: retry_op = READ_INLINE; } } else { + CEPH_DEFINE_RW_CONTEXT(rw_ctx, got); dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, ceph_cap_string(got)); - current->journal_info = filp; + ceph_add_rw_context(fi, &rw_ctx); ret = generic_file_read_iter(iocb, to); - current->journal_info = NULL; + ceph_del_rw_context(fi, &rw_ctx); } dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n", inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index ab81652198c4..c6ec5aa46100 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -494,7 +494,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) ci->i_wrbuffer_ref = 0; ci->i_wrbuffer_ref_head = 0; atomic_set(&ci->i_filelock_ref, 0); - ci->i_shared_gen = 0; + atomic_set(&ci->i_shared_gen, 0); ci->i_rdcache_gen = 0; ci->i_rdcache_revoking = 0; @@ -1041,7 +1041,7 @@ static void update_dentry_lease(struct dentry *dentry, if (ceph_snap(dir) != CEPH_NOSNAP) goto out_unlock; - di->lease_shared_gen = ceph_inode(dir)->i_shared_gen; + di->lease_shared_gen = atomic_read(&ceph_inode(dir)->i_shared_gen); if (duration == 0) goto out_unlock; @@ -1080,6 +1080,27 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in) BUG_ON(d_inode(dn)); + if (S_ISDIR(in->i_mode)) { + /* If inode is directory, d_splice_alias() below will remove + * 'realdn' from its origin parent. We need to ensure that + * origin parent's readdir cache will not reference 'realdn' + */ + realdn = d_find_any_alias(in); + if (realdn) { + struct ceph_dentry_info *di = ceph_dentry(realdn); + spin_lock(&realdn->d_lock); + + realdn->d_op->d_prune(realdn); + + di->time = jiffies; + di->lease_shared_gen = 0; + di->offset = 0; + + spin_unlock(&realdn->d_lock); + dput(realdn); + } + } + /* dn must be unhashed */ if (!d_unhashed(dn)) d_drop(dn); @@ -1295,8 +1316,8 @@ retry_lookup: if (!rinfo->head->is_target) { dout("fill_trace null dentry\n"); if (d_really_is_positive(dn)) { - ceph_dir_clear_ordered(dir); dout("d_delete %p\n", dn); + ceph_dir_clear_ordered(dir); d_delete(dn); } else if (have_lease) { if (d_unhashed(dn)) @@ -1323,7 +1344,6 @@ retry_lookup: dout(" %p links to %p %llx.%llx, not %llx.%llx\n", dn, d_inode(dn), ceph_vinop(d_inode(dn)), ceph_vinop(in)); - ceph_dir_clear_ordered(dir); d_invalidate(dn); have_lease = false; } @@ -1573,9 +1593,19 @@ retry_lookup: } else if (d_really_is_positive(dn) && (ceph_ino(d_inode(dn)) != tvino.ino || ceph_snap(d_inode(dn)) != tvino.snap)) { + struct ceph_dentry_info *di = ceph_dentry(dn); dout(" dn %p points to wrong inode %p\n", dn, d_inode(dn)); - __ceph_dir_clear_ordered(ci); + + spin_lock(&dn->d_lock); + if (di->offset > 0 && + di->lease_shared_gen == + atomic_read(&ci->i_shared_gen)) { + __ceph_dir_clear_ordered(ci); + di->offset = 0; + } + spin_unlock(&dn->d_lock); + d_delete(dn); dput(dn); goto retry_lookup; @@ -1600,9 +1630,7 @@ retry_lookup: &req->r_caps_reservation); if (ret < 0) { pr_err("fill_inode badness on %p\n", in); - if (d_really_is_positive(dn)) - __ceph_dir_clear_ordered(ci); - else + if (d_really_is_negative(dn)) iput(in); d_drop(dn); err = ret; @@ -2000,8 +2028,8 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) ceph_encode_timespec(&req->r_args.setattr.atime, &attr->ia_atime); mask |= CEPH_SETATTR_ATIME; - release |= CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR; + release |= CEPH_CAP_FILE_SHARED | + CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; } } if (ia_valid & ATTR_MTIME) { @@ -2022,8 +2050,8 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) ceph_encode_timespec(&req->r_args.setattr.mtime, &attr->ia_mtime); mask |= CEPH_SETATTR_MTIME; - release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR; + release |= CEPH_CAP_FILE_SHARED | + CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; } } if (ia_valid & ATTR_SIZE) { @@ -2041,8 +2069,8 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) req->r_args.setattr.old_size = cpu_to_le64(inode->i_size); mask |= CEPH_SETATTR_SIZE; - release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR; + release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL | + CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; } } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1b468250e947..2e8f90f96540 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -604,10 +604,20 @@ static void __register_request(struct ceph_mds_client *mdsc, struct ceph_mds_request *req, struct inode *dir) { + int ret = 0; + req->r_tid = ++mdsc->last_tid; - if (req->r_num_caps) - ceph_reserve_caps(mdsc, &req->r_caps_reservation, - req->r_num_caps); + if (req->r_num_caps) { + ret = ceph_reserve_caps(mdsc, &req->r_caps_reservation, + req->r_num_caps); + if (ret < 0) { + pr_err("__register_request %p " + "failed to reserve caps: %d\n", req, ret); + /* set req->r_err to fail early from __do_request */ + req->r_err = ret; + return; + } + } dout("__register_request %p tid %lld\n", req, req->r_tid); ceph_mdsc_get_request(req); insert_request(&mdsc->request_tree, req); @@ -1545,9 +1555,9 @@ out: /* * Trim session cap count down to some max number. */ -static int trim_caps(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session, - int max_caps) +int ceph_trim_caps(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session, + int max_caps) { int trim_caps = session->s_nr_caps - max_caps; @@ -2438,11 +2448,14 @@ out: */ void ceph_invalidate_dir_request(struct ceph_mds_request *req) { - struct inode *inode = req->r_parent; + struct inode *dir = req->r_parent; + struct inode *old_dir = req->r_old_dentry_dir; - dout("invalidate_dir_request %p (complete, lease(s))\n", inode); + dout("invalidate_dir_request %p %p (complete, lease(s))\n", dir, old_dir); - ceph_dir_clear_complete(inode); + ceph_dir_clear_complete(dir); + if (old_dir) + ceph_dir_clear_complete(old_dir); if (req->r_dentry) ceph_invalidate_dentry_lease(req->r_dentry); if (req->r_old_dentry) @@ -2773,7 +2786,7 @@ static void handle_session(struct ceph_mds_session *session, break; case CEPH_SESSION_RECALL_STATE: - trim_caps(mdsc, session, le32_to_cpu(h->max_caps)); + ceph_trim_caps(mdsc, session, le32_to_cpu(h->max_caps)); break; case CEPH_SESSION_FLUSHMSG: diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 837ac4b087a0..71e3b783ee6f 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -444,4 +444,7 @@ ceph_mdsc_open_export_target_session(struct ceph_mds_client *mdsc, int target); extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); +extern int ceph_trim_caps(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session, + int max_caps); #endif diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 8a2ca41e4b97..07cf95e6413d 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -922,13 +922,17 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, /* * Move the inode to the new realm */ - spin_lock(&realm->inodes_with_caps_lock); + oldrealm = ci->i_snap_realm; + spin_lock(&oldrealm->inodes_with_caps_lock); list_del_init(&ci->i_snap_realm_item); + spin_unlock(&oldrealm->inodes_with_caps_lock); + + spin_lock(&realm->inodes_with_caps_lock); list_add(&ci->i_snap_realm_item, &realm->inodes_with_caps); - oldrealm = ci->i_snap_realm; ci->i_snap_realm = realm; spin_unlock(&realm->inodes_with_caps_lock); + spin_unlock(&ci->i_ceph_lock); ceph_get_snap_realm(mdsc, realm); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 2beeec07fa76..21b2e5b004eb 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -256,7 +256,8 @@ struct ceph_inode_xattr { */ struct ceph_dentry_info { struct ceph_mds_session *lease_session; - u32 lease_gen, lease_shared_gen; + int lease_shared_gen; + u32 lease_gen; u32 lease_seq; unsigned long lease_renew_after, lease_renew_from; struct list_head lru; @@ -353,7 +354,7 @@ struct ceph_inode_info { int i_rd_ref, i_rdcache_ref, i_wr_ref, i_wb_ref; int i_wrbuffer_ref, i_wrbuffer_ref_head; atomic_t i_filelock_ref; - u32 i_shared_gen; /* increment each time we get FILE_SHARED */ + atomic_t i_shared_gen; /* increment each time we get FILE_SHARED */ u32 i_rdcache_gen; /* incremented each time we get FILE_CACHE. */ u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */ @@ -648,7 +649,7 @@ extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check); extern void ceph_caps_init(struct ceph_mds_client *mdsc); extern void ceph_caps_finalize(struct ceph_mds_client *mdsc); extern void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta); -extern void ceph_reserve_caps(struct ceph_mds_client *mdsc, +extern int ceph_reserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx, int need); extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc, struct ceph_cap_reservation *ctx); @@ -668,6 +669,9 @@ struct ceph_file_info { short fmode; /* initialized on open */ short flags; /* CEPH_F_* */ + spinlock_t rw_contexts_lock; + struct list_head rw_contexts; + /* readdir: position within the dir */ u32 frag; struct ceph_mds_request *last_readdir; @@ -684,6 +688,49 @@ struct ceph_file_info { int dir_info_len; }; +struct ceph_rw_context { + struct list_head list; + struct task_struct *thread; + int caps; +}; + +#define CEPH_DEFINE_RW_CONTEXT(_name, _caps) \ + struct ceph_rw_context _name = { \ + .thread = current, \ + .caps = _caps, \ + } + +static inline void ceph_add_rw_context(struct ceph_file_info *cf, + struct ceph_rw_context *ctx) +{ + spin_lock(&cf->rw_contexts_lock); + list_add(&ctx->list, &cf->rw_contexts); + spin_unlock(&cf->rw_contexts_lock); +} + +static inline void ceph_del_rw_context(struct ceph_file_info *cf, + struct ceph_rw_context *ctx) +{ + spin_lock(&cf->rw_contexts_lock); + list_del(&ctx->list); + spin_unlock(&cf->rw_contexts_lock); +} + +static inline struct ceph_rw_context* +ceph_find_rw_context(struct ceph_file_info *cf) +{ + struct ceph_rw_context *ctx, *found = NULL; + spin_lock(&cf->rw_contexts_lock); + list_for_each_entry(ctx, &cf->rw_contexts, list) { + if (ctx->thread == current) { + found = ctx; + break; + } + } + spin_unlock(&cf->rw_contexts_lock); + return found; +} + struct ceph_readdir_cache_control { struct page *page; struct dentry **dentries; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index c7a863219fa3..e35e711db68e 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -128,6 +128,10 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon) seq_puts(m, " type: CDROM "); else seq_printf(m, " type: %d ", dev_type); + if (tcon->seal) + seq_printf(m, " Encrypted"); + if (tcon->unix_ext) + seq_printf(m, " POSIX Extensions"); if (tcon->ses->server->ops->dump_share_caps) tcon->ses->server->ops->dump_share_caps(m, tcon); @@ -246,7 +250,10 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) atomic_read(&server->smbd_conn->mr_used_count)); skip_rdma: #endif - seq_printf(m, "\nNumber of credits: %d", server->credits); + seq_printf(m, "\nNumber of credits: %d Dialect 0x%x", + server->credits, server->dialect); + if (server->sign) + seq_printf(m, " signed"); i++; list_for_each(tmp2, &server->smb_ses_list) { ses = list_entry(tmp2, struct cifs_ses, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 4e0922d24eb2..9ceebf30eb22 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -6343,9 +6343,7 @@ SetEARetry: pSMB->InformationLevel = cpu_to_le16(SMB_SET_FILE_EA); - parm_data = - (struct fealist *) (((char *) &pSMB->hdr.Protocol) + - offset); + parm_data = (void *)pSMB + offsetof(struct smb_hdr, Protocol) + offset; pSMB->ParameterOffset = cpu_to_le16(param_offset); pSMB->DataOffset = cpu_to_le16(offset); pSMB->SetupCount = 1; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 6eb9f9691ed4..2a2b34ccaf49 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -192,6 +192,35 @@ struct smb2_symlink_err_rsp { __u8 PathBuffer[0]; } __packed; +/* SMB 3.1.1 and later dialects. See MS-SMB2 section 2.2.2.1 */ +struct smb2_error_context_rsp { + __le32 ErrorDataLength; + __le32 ErrorId; + __u8 ErrorContextData; /* ErrorDataLength long array */ +} __packed; + +/* Defines for Type field below (see MS-SMB2 2.2.2.2.2.1) */ +#define MOVE_DST_IPADDR_V4 cpu_to_le32(0x00000001) +#define MOVE_DST_IPADDR_V6 cpu_to_le32(0x00000002) + +struct move_dst_ipaddr { + __le32 Type; + __u32 Reserved; + __u8 address[16]; /* IPv4 followed by 12 bytes rsvd or IPv6 address */ +} __packed; + +struct share_redirect_error_context_rsp { + __le32 StructureSize; + __le32 NotificationType; + __le32 ResourceNameOffset; + __le32 ResourceNameLength; + __le16 Flags; + __le16 TargetType; + __le32 IPAddrCount; + struct move_dst_ipaddr IpAddrMoveList[0]; + /* __u8 ResourceName[] */ /* Name of share as counted Unicode string */ +} __packed; + #define SMB2_CLIENT_GUID_SIZE 16 struct smb2_negotiate_req { @@ -320,7 +349,9 @@ struct smb2_logoff_rsp { } __packed; /* Flags/Reserved for SMB3.1.1 */ -#define SMB2_SHAREFLAG_CLUSTER_RECONNECT 0x0001 +#define SMB2_TREE_CONNECT_FLAG_CLUSTER_RECONNECT cpu_to_le16(0x0001) +#define SMB2_TREE_CONNECT_FLAG_REDIRECT_TO_OWNER cpu_to_le16(0x0002) +#define SMB2_TREE_CONNECT_FLAG_EXTENSION_PRESENT cpu_to_le16(0x0004) struct smb2_tree_connect_req { struct smb2_sync_hdr sync_hdr; @@ -331,6 +362,82 @@ struct smb2_tree_connect_req { __u8 Buffer[1]; /* variable length */ } __packed; +/* See MS-SMB2 section 2.2.9.2 */ +/* Context Types */ +#define SMB2_RESERVED_TREE_CONNECT_CONTEXT_ID 0x0000 +#define SMB2_REMOTED_IDENTITY_TREE_CONNECT_CONTEXT_ID cpu_to_le16(0x0001) + +struct tree_connect_contexts { + __le16 ContextType; + __le16 DataLength; + __le32 Reserved; + __u8 Data[0]; +} __packed; + +/* Remoted identity tree connect context structures - see MS-SMB2 2.2.9.2.1 */ +struct smb3_blob_data { + __le16 BlobSize; + __u8 BlobData[0]; +} __packed; + +/* Valid values for Attr */ +#define SE_GROUP_MANDATORY 0x00000001 +#define SE_GROUP_ENABLED_BY_DEFAULT 0x00000002 +#define SE_GROUP_ENABLED 0x00000004 +#define SE_GROUP_OWNER 0x00000008 +#define SE_GROUP_USE_FOR_DENY_ONLY 0x00000010 +#define SE_GROUP_INTEGRITY 0x00000020 +#define SE_GROUP_INTEGRITY_ENABLED 0x00000040 +#define SE_GROUP_RESOURCE 0x20000000 +#define SE_GROUP_LOGON_ID 0xC0000000 + +/* struct sid_attr_data is SidData array in BlobData format then le32 Attr */ + +struct sid_array_data { + __le16 SidAttrCount; + /* SidAttrList - array of sid_attr_data structs */ +} __packed; + +struct luid_attr_data { + +} __packed; + +/* + * struct privilege_data is the same as BLOB_DATA - see MS-SMB2 2.2.9.2.1.5 + * but with size of LUID_ATTR_DATA struct and BlobData set to LUID_ATTR DATA + */ + +struct privilege_array_data { + __le16 PrivilegeCount; + /* array of privilege_data structs */ +} __packed; + +struct remoted_identity_tcon_context { + __le16 TicketType; /* must be 0x0001 */ + __le16 TicketSize; /* total size of this struct */ + __le16 User; /* offset to SID_ATTR_DATA struct with user info */ + __le16 UserName; /* offset to null terminated Unicode username string */ + __le16 Domain; /* offset to null terminated Unicode domain name */ + __le16 Groups; /* offset to SID_ARRAY_DATA struct with group info */ + __le16 RestrictedGroups; /* similar to above */ + __le16 Privileges; /* offset to PRIVILEGE_ARRAY_DATA struct */ + __le16 PrimaryGroup; /* offset to SID_ARRAY_DATA struct */ + __le16 Owner; /* offset to BLOB_DATA struct */ + __le16 DefaultDacl; /* offset to BLOB_DATA struct */ + __le16 DeviceGroups; /* offset to SID_ARRAY_DATA struct */ + __le16 UserClaims; /* offset to BLOB_DATA struct */ + __le16 DeviceClaims; /* offset to BLOB_DATA struct */ + __u8 TicketInfo[0]; /* variable length buf - remoted identity data */ +} __packed; + +struct smb2_tree_connect_req_extension { + __le32 TreeConnectContextOffset; + __le16 TreeConnectContextCount; + __u8 Reserved[10]; + __u8 PathName[0]; /* variable sized array */ + /* followed by array of TreeConnectContexts */ +} __packed; + struct smb2_tree_connect_rsp { struct smb2_hdr hdr; __le16 StructureSize; /* Must be 16 */ @@ -365,7 +472,8 @@ struct smb2_tree_connect_rsp { #define SHI1005_FLAGS_ENABLE_HASH_V1 0x00002000 #define SHI1005_FLAGS_ENABLE_HASH_V2 0x00004000 #define SHI1005_FLAGS_ENCRYPT_DATA 0x00008000 -#define SHI1005_FLAGS_ALL 0x0000FF33 +#define SMB2_SHAREFLAG_IDENTITY_REMOTING 0x00040000 /* 3.1.1 */ +#define SHI1005_FLAGS_ALL 0x0004FF33 /* Possible share capabilities */ #define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) /* all dialects */ @@ -373,6 +481,7 @@ struct smb2_tree_connect_rsp { #define SMB2_SHARE_CAP_SCALEOUT cpu_to_le32(0x00000020) /* 3.0 */ #define SMB2_SHARE_CAP_CLUSTER cpu_to_le32(0x00000040) /* 3.0 */ #define SMB2_SHARE_CAP_ASYMMETRIC cpu_to_le32(0x00000080) /* 3.02 */ +#define SMB2_SHARE_CAP_REDIRECT_TO_OWNER cpu_to_le32(0x00000100) /* 3.1.1 */ struct smb2_tree_disconnect_req { struct smb2_sync_hdr sync_hdr; @@ -556,6 +665,7 @@ struct create_context { #define SMB2_LEASE_WRITE_CACHING cpu_to_le32(0x04) #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS cpu_to_le32(0x02) +#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET cpu_to_le32(0x00000004) #define SMB2_LEASE_KEY_SIZE 16 diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 5130492847eb..91710eb571fb 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -217,9 +217,10 @@ static void smbd_destroy_rdma_work(struct work_struct *work) spin_unlock_irqrestore( &info->reassembly_queue_lock, flags); put_receive_buffer(info, response); - } + } else + spin_unlock_irqrestore(&info->reassembly_queue_lock, flags); } while (response); - spin_unlock_irqrestore(&info->reassembly_queue_lock, flags); + info->reassembly_data_length = 0; log_rdma_event(INFO, "free receive buffers\n"); @@ -1934,15 +1935,16 @@ again: * No need to lock if we are not at the * end of the queue */ - if (!queue_length) + if (queue_length) + list_del(&response->list); + else { spin_lock_irq( &info->reassembly_queue_lock); - list_del(&response->list); - queue_removed++; - if (!queue_length) + list_del(&response->list); spin_unlock_irq( &info->reassembly_queue_lock); - + } + queue_removed++; info->count_reassembly_queue--; info->count_dequeue_reassembly_queue++; put_receive_buffer(info, response); diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index 49d3c6fda89a..c5234c21b539 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -39,7 +39,7 @@ #include <linux/device.h> #include <linux/pid_namespace.h> #include <asm/io.h> -#include <asm/poll.h> +#include <linux/poll.h> #include <linux/uaccess.h> #include <linux/coda.h> @@ -64,12 +64,12 @@ static struct class *coda_psdev_class; static __poll_t coda_psdev_poll(struct file *file, poll_table * wait) { struct venus_comm *vcp = (struct venus_comm *) file->private_data; - __poll_t mask = POLLOUT | POLLWRNORM; + __poll_t mask = EPOLLOUT | EPOLLWRNORM; poll_wait(file, &vcp->vc_waitq, wait); mutex_lock(&vcp->vc_mutex); if (!list_empty(&vcp->vc_pending)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; mutex_unlock(&vcp->vc_mutex); return mask; diff --git a/fs/cramfs/Kconfig b/fs/cramfs/Kconfig index 58e2fe40b2a0..5933f995309a 100644 --- a/fs/cramfs/Kconfig +++ b/fs/cramfs/Kconfig @@ -33,8 +33,7 @@ config CRAMFS_BLOCKDEV config CRAMFS_MTD bool "Support CramFs image directly mapped in physical memory" - depends on CRAMFS && MTD - depends on CRAMFS=m || MTD=y + depends on CRAMFS && CRAMFS <= MTD default y if !CRAMFS_BLOCKDEV help This option allows the CramFs driver to load data directly from diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 6fdbf21be318..1f99678ff5d3 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -18,7 +18,7 @@ #include <linux/slab.h> #include <linux/atomic.h> #include <linux/device.h> -#include <asm/poll.h> +#include <linux/poll.h> #include "internal.h" @@ -214,7 +214,7 @@ static __poll_t full_proxy_poll(struct file *filp, const struct file_operations *real_fops; if (debugfs_file_get(dentry)) - return POLLHUP; + return EPOLLHUP; real_fops = debugfs_real_fops(filp); r = real_fops->poll(filp, wait); diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index a4c63e9e6385..c7d5a2ea3d03 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -471,7 +471,7 @@ static __poll_t dev_poll(struct file *file, poll_table *wait) spin_lock(&ops_lock); if (!list_empty(&send_list)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; spin_unlock(&ops_lock); return mask; diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 662432af8ce8..2a669390cd7f 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -896,7 +896,7 @@ static __poll_t device_poll(struct file *file, poll_table *wait) spin_lock(&proc->asts_spin); if (!list_empty(&proc->asts)) { spin_unlock(&proc->asts_spin); - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } spin_unlock(&proc->asts_spin); return 0; diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 7423e792a092..2d1158e5f950 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -59,7 +59,7 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt) poll_wait(file, &daemon->wait, pt); mutex_lock(&daemon->mux); if (!list_empty(&daemon->msg_ctx_out_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; out_unlock_daemon: daemon->flags &= ~ECRYPTFS_DAEMON_IN_POLL; mutex_unlock(&daemon->mux); diff --git a/fs/eventfd.c b/fs/eventfd.c index 04fd824142a1..012f5bd46dfa 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -45,7 +45,7 @@ struct eventfd_ctx { * * This function is supposed to be called by the kernel in paths that do not * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX - * value, and we signal this as overflow condition by returning a POLLERR + * value, and we signal this as overflow condition by returning a EPOLLERR * to poll(2). * * Returns the amount by which the counter was incremented. This will be less @@ -60,7 +60,7 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) - wake_up_locked_poll(&ctx->wqh, POLLIN); + wake_up_locked_poll(&ctx->wqh, EPOLLIN); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return n; @@ -96,7 +96,7 @@ static int eventfd_release(struct inode *inode, struct file *file) { struct eventfd_ctx *ctx = file->private_data; - wake_up_poll(&ctx->wqh, POLLHUP); + wake_up_poll(&ctx->wqh, EPOLLHUP); eventfd_ctx_put(ctx); return 0; } @@ -150,11 +150,11 @@ static __poll_t eventfd_poll(struct file *file, poll_table *wait) count = READ_ONCE(ctx->count); if (count > 0) - events |= POLLIN; + events |= EPOLLIN; if (count == ULLONG_MAX) - events |= POLLERR; + events |= EPOLLERR; if (ULLONG_MAX - 1 > count) - events |= POLLOUT; + events |= EPOLLOUT; return events; } @@ -187,7 +187,7 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *w eventfd_ctx_do_read(ctx, cnt); __remove_wait_queue(&ctx->wqh, wait); if (*cnt != 0 && waitqueue_active(&ctx->wqh)) - wake_up_locked_poll(&ctx->wqh, POLLOUT); + wake_up_locked_poll(&ctx->wqh, EPOLLOUT); spin_unlock_irqrestore(&ctx->wqh.lock, flags); return *cnt != 0 ? 0 : -EAGAIN; @@ -231,7 +231,7 @@ static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count, if (likely(res > 0)) { eventfd_ctx_do_read(ctx, &ucnt); if (waitqueue_active(&ctx->wqh)) - wake_up_locked_poll(&ctx->wqh, POLLOUT); + wake_up_locked_poll(&ctx->wqh, EPOLLOUT); } spin_unlock_irq(&ctx->wqh.lock); @@ -281,7 +281,7 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c if (likely(res > 0)) { ctx->count += ucnt; if (waitqueue_active(&ctx->wqh)) - wake_up_locked_poll(&ctx->wqh, POLLIN); + wake_up_locked_poll(&ctx->wqh, EPOLLIN); } spin_unlock_irq(&ctx->wqh.lock); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 42e35a6977c9..0f3494ed3ed0 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -95,9 +95,9 @@ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) -#define EPOLLINOUT_BITS (POLLIN | POLLOUT) +#define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) -#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | POLLERR | POLLHUP | \ +#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ @@ -260,6 +260,7 @@ struct ep_pqueue { struct ep_send_events_data { int maxevents; struct epoll_event __user *events; + int res; }; /* @@ -554,7 +555,7 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests) wait_queue_head_t *wqueue = (wait_queue_head_t *)cookie; spin_lock_irqsave_nested(&wqueue->lock, flags, call_nests + 1); - wake_up_locked_poll(wqueue, POLLIN); + wake_up_locked_poll(wqueue, EPOLLIN); spin_unlock_irqrestore(&wqueue->lock, flags); return 0; @@ -574,7 +575,7 @@ static void ep_poll_safewake(wait_queue_head_t *wq) static void ep_poll_safewake(wait_queue_head_t *wq) { - wake_up_poll(wq, POLLIN); + wake_up_poll(wq, EPOLLIN); } #endif @@ -660,12 +661,13 @@ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) * * Returns: The same integer error code returned by the @sproc callback. */ -static int ep_scan_ready_list(struct eventpoll *ep, - int (*sproc)(struct eventpoll *, +static __poll_t ep_scan_ready_list(struct eventpoll *ep, + __poll_t (*sproc)(struct eventpoll *, struct list_head *, void *), void *priv, int depth, bool ep_locked) { - int error, pwake = 0; + __poll_t res; + int pwake = 0; unsigned long flags; struct epitem *epi, *nepi; LIST_HEAD(txlist); @@ -694,7 +696,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, /* * Now call the callback function. */ - error = (*sproc)(ep, &txlist, priv); + res = (*sproc)(ep, &txlist, priv); spin_lock_irqsave(&ep->lock, flags); /* @@ -747,7 +749,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, if (pwake) ep_poll_safewake(&ep->poll_wait); - return error; + return res; } static void epi_rcu_free(struct rcu_head *head) @@ -864,7 +866,7 @@ static int ep_eventpoll_release(struct inode *inode, struct file *file) return 0; } -static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, +static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head, void *priv); static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt); @@ -874,7 +876,7 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ -static unsigned int ep_item_poll(const struct epitem *epi, poll_table *pt, +static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct eventpoll *ep; @@ -894,7 +896,7 @@ static unsigned int ep_item_poll(const struct epitem *epi, poll_table *pt, locked) & epi->event.events; } -static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, +static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head, void *priv) { struct epitem *epi, *tmp; @@ -906,7 +908,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, list_for_each_entry_safe(epi, tmp, head, rdllink) { if (ep_item_poll(epi, &pt, depth)) { - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } else { /* * Item has been dropped into the ready list by the poll @@ -1179,12 +1181,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { - case POLLIN: - if (epi->event.events & POLLIN) + case EPOLLIN: + if (epi->event.events & EPOLLIN) ewake = 1; break; - case POLLOUT: - if (epi->event.events & POLLOUT) + case EPOLLOUT: + if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: @@ -1414,7 +1416,8 @@ static noinline void ep_destroy_wakeup_source(struct epitem *epi) static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, struct file *tfile, int fd, int full_check) { - int error, revents, pwake = 0; + int error, pwake = 0; + __poll_t revents; unsigned long flags; long user_watches; struct epitem *epi; @@ -1612,12 +1615,11 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, return 0; } -static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, +static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head, void *priv) { struct ep_send_events_data *esed = priv; - int eventcnt; - unsigned int revents; + __poll_t revents; struct epitem *epi; struct epoll_event __user *uevent; struct wakeup_source *ws; @@ -1630,8 +1632,8 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, * Items cannot vanish during the loop because ep_scan_ready_list() is * holding "mtx" during this call. */ - for (eventcnt = 0, uevent = esed->events; - !list_empty(head) && eventcnt < esed->maxevents;) { + for (esed->res = 0, uevent = esed->events; + !list_empty(head) && esed->res < esed->maxevents;) { epi = list_first_entry(head, struct epitem, rdllink); /* @@ -1665,9 +1667,11 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, __put_user(epi->event.data, &uevent->data)) { list_add(&epi->rdllink, head); ep_pm_stay_awake(epi); - return eventcnt ? eventcnt : -EFAULT; + if (!esed->res) + esed->res = -EFAULT; + return 0; } - eventcnt++; + esed->res++; uevent++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; @@ -1689,7 +1693,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, } } - return eventcnt; + return 0; } static int ep_send_events(struct eventpoll *ep, @@ -1700,7 +1704,8 @@ static int ep_send_events(struct eventpoll *ep, esed.maxevents = maxevents; esed.events = events; - return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false); + ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false); + return esed.res; } static inline struct timespec64 ep_set_mstimeout(long ms) @@ -2100,7 +2105,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, switch (op) { case EPOLL_CTL_ADD: if (!epi) { - epds.events |= POLLERR | POLLHUP; + epds.events |= EPOLLERR | EPOLLHUP; error = ep_insert(ep, &epds, tf.file, fd, full_check); } else error = -EEXIST; @@ -2116,7 +2121,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { - epds.events |= POLLERR | POLLHUP; + epds.events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, &epds); } } else diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c index c5a53fcc43ea..f0138674c1ed 100644 --- a/fs/exofs/dir.c +++ b/fs/exofs/dir.c @@ -242,7 +242,7 @@ exofs_readdir(struct file *file, struct dir_context *ctx) unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(exofs_chunk_size(inode)-1); - bool need_revalidate = inode_cmp_iversion(inode, file->f_version); + bool need_revalidate = !inode_eq_iversion(inode, file->f_version); if (pos > inode->i_size - EXOFS_DIR_REC_LEN(1)) return 0; diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 4111085a129f..3b8114def693 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -294,7 +294,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx) unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(ext2_chunk_size(inode)-1); unsigned char *types = NULL; - bool need_revalidate = inode_cmp_iversion(inode, file->f_version); + bool need_revalidate = !inode_eq_iversion(inode, file->f_version); if (pos > inode->i_size - EXT2_DIR_REC_LEN(1)) return 0; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 0a638e79bf7c..7666c065b96f 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1231,7 +1231,7 @@ static void ext2_clear_super_error(struct super_block *sb) * write and hope for the best. */ ext2_msg(sb, KERN_ERR, - "previous I/O error to superblock detected\n"); + "previous I/O error to superblock detected"); clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index afda0a0499ce..da87cf757f7d 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -209,7 +209,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ - if (inode_cmp_iversion(inode, file->f_version)) { + if (!inode_eq_iversion(inode, file->f_version)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ext4_dir_entry_2 *) (bh->b_data + i); @@ -569,7 +569,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) * cached entries. */ if ((!info->curr_node) || - inode_cmp_iversion(inode, file->f_version)) { + !inode_eq_iversion(inode, file->f_version)) { info->curr_node = NULL; free_rb_tree_fname(&info->root); file->f_version = inode_query_iversion(inode); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 7c4165b88505..70cf4c7b268a 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1487,7 +1487,7 @@ int ext4_read_inline_dir(struct file *file, * dirent right now. Scan from the start of the inline * dir to make sure. */ - if (inode_cmp_iversion(inode, file->f_version)) { + if (!inode_eq_iversion(inode, file->f_version)) { for (i = 0; i < extra_size && i < offset;) { /* * "." is with offset 0 and diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index cefea792cde8..2649759c478a 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -46,7 +46,7 @@ static int vfat_revalidate_shortname(struct dentry *dentry) { int ret = 1; spin_lock(&dentry->d_lock); - if (inode_cmp_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry))) + if (!inode_eq_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry))) ret = 0; spin_unlock(&dentry->d_lock); return ret; diff --git a/fs/fcntl.c b/fs/fcntl.c index e95fa0a352ea..1e97f1fda90c 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -26,7 +26,7 @@ #include <linux/shmem_fs.h> #include <linux/compat.h> -#include <asm/poll.h> +#include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> @@ -691,12 +691,12 @@ COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { - POLLIN | POLLRDNORM, /* POLL_IN */ - POLLOUT | POLLWRNORM | POLLWRBAND, /* POLL_OUT */ - POLLIN | POLLRDNORM | POLLMSG, /* POLL_MSG */ - POLLERR, /* POLL_ERR */ - POLLPRI | POLLRDBAND, /* POLL_PRI */ - POLLHUP | POLLERR /* POLL_HUP */ + EPOLLIN | EPOLLRDNORM, /* POLL_IN */ + EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ + EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ + EPOLLERR, /* POLL_ERR */ + EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ + EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index aa089a6925d0..5d06384c2cae 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2006,21 +2006,21 @@ out: static __poll_t fuse_dev_poll(struct file *file, poll_table *wait) { - __poll_t mask = POLLOUT | POLLWRNORM; + __poll_t mask = EPOLLOUT | EPOLLWRNORM; struct fuse_iqueue *fiq; struct fuse_dev *fud = fuse_get_dev(file); if (!fud) - return POLLERR; + return EPOLLERR; fiq = &fud->fc->iq; poll_wait(file, &fiq->waitq, wait); spin_lock(&fiq->waitq.lock); if (!fiq->connected) - mask = POLLERR; + mask = EPOLLERR; else if (request_pending(fiq)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; spin_unlock(&fiq->waitq.lock); return mask; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index e85e974dd211..a201fb0ac64f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2791,7 +2791,7 @@ __poll_t fuse_file_poll(struct file *file, poll_table *wait) fc->no_poll = 1; return DEFAULT_POLLMASK; } - return POLLERR; + return EPOLLERR; } EXPORT_SYMBOL_GPL(fuse_file_poll); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index e8120a282435..15e06fb552da 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -444,7 +444,7 @@ static int hfsplus_symlink(struct inode *dir, struct dentry *dentry, int res = -ENOMEM; mutex_lock(&sbi->vh_mutex); - inode = hfsplus_new_inode(dir->i_sb, S_IFLNK | S_IRWXUGO); + inode = hfsplus_new_inode(dir->i_sb, dir, S_IFLNK | S_IRWXUGO); if (!inode) goto out; @@ -486,7 +486,7 @@ static int hfsplus_mknod(struct inode *dir, struct dentry *dentry, int res = -ENOMEM; mutex_lock(&sbi->vh_mutex); - inode = hfsplus_new_inode(dir->i_sb, mode); + inode = hfsplus_new_inode(dir->i_sb, dir, mode); if (!inode) goto out; diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index a015044daa05..d9255abafb81 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -478,7 +478,8 @@ extern const struct address_space_operations hfsplus_aops; extern const struct address_space_operations hfsplus_btree_aops; extern const struct dentry_operations hfsplus_dentry_operations; -struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode); +struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, + umode_t mode); void hfsplus_delete_inode(struct inode *inode); void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 190c60efbc99..c0c8d433864f 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -354,7 +354,8 @@ static const struct file_operations hfsplus_file_operations = { .unlocked_ioctl = hfsplus_ioctl, }; -struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) +struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir, + umode_t mode) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct inode *inode = new_inode(sb); @@ -364,9 +365,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) return NULL; inode->i_ino = sbi->next_cnid++; - inode->i_mode = mode; - inode->i_uid = current_fsuid(); - inode->i_gid = current_fsgid(); + inode_init_owner(inode, dir, mode); set_nlink(inode, 1); inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 1d458b716957..513c357c734b 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -549,7 +549,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if (!sbi->hidden_dir) { mutex_lock(&sbi->vh_mutex); - sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR); + sbi->hidden_dir = hfsplus_new_inode(sb, root, S_IFDIR); if (!sbi->hidden_dir) { mutex_unlock(&sbi->vh_mutex); err = -ENOMEM; diff --git a/fs/inode.c b/fs/inode.c index e2ca0f4b5151..ef362364d396 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -498,7 +498,6 @@ EXPORT_SYMBOL(__remove_inode_hash); void clear_inode(struct inode *inode) { - might_sleep(); /* * We have to cycle tree_lock here because reclaim can be still in the * process of removing the last page (in __delete_from_page_cache()) diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index c53d9cc5ae7a..fd5ce883072e 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -275,7 +275,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; - size_t len; + ssize_t len; char *buf; if (of->atomic_write_len) { @@ -823,7 +823,7 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * the content and then you use 'poll' or 'select' to wait for * the content to change. When the content changes (assuming the * manager for the kobject supports notification), poll will - * return POLLERR|POLLPRI, and select will return the fd whether + * return EPOLLERR|EPOLLPRI, and select will return the fd whether * it is waiting for read, write, or exceptions. * Once poll/select indicates that the value has changed, you * need to close and re-open the file, or seek to 0 and read again. @@ -851,7 +851,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) return DEFAULT_POLLMASK; trigger: - return DEFAULT_POLLMASK|POLLERR|POLLPRI; + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; } static void kernfs_notify_workfn(struct work_struct *work) diff --git a/fs/locks.c b/fs/locks.c index 21b4dfa289ee..d6ff4beb70ce 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1554,9 +1554,9 @@ out: EXPORT_SYMBOL(__break_lease); /** - * lease_get_mtime - get the last modified time of an inode + * lease_get_mtime - update modified time of an inode with exclusive lease * @inode: the inode - * @time: pointer to a timespec which will contain the last modified time + * @time: pointer to a timespec which contains the last modified time * * This is to force NFS clients to flush their caches for files with * exclusive leases. The justification is that if someone has an @@ -1580,8 +1580,6 @@ void lease_get_mtime(struct inode *inode, struct timespec *time) if (has_lease) *time = current_time(inode); - else - *time = inode->i_mtime; } EXPORT_SYMBOL(lease_get_mtime); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index ceeaf0fb6657..7d893543cf3b 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1314,7 +1314,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) - && !inode_cmp_iversion_raw(inode, fattr->pre_change_attr)) { + && inode_eq_iversion_raw(inode, fattr->pre_change_attr)) { inode_set_iversion_raw(inode, fattr->change_attr); if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); @@ -1373,7 +1373,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ - if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && inode_cmp_iversion_raw(inode, fattr->change_attr)) + if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr)) invalid |= NFS_INO_INVALID_ATTR | NFS_INO_REVAL_PAGECACHE; if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime)) @@ -1803,7 +1803,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { - if (inode_cmp_iversion_raw(inode, fattr->change_attr)) { + if (!inode_eq_iversion_raw(inode, fattr->change_attr)) { dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); /* Could it be a race with writeback? */ diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 2758480555fa..1a70581e1cb2 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -251,6 +251,34 @@ encode_wcc_data(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp) } /* + * Fill in the pre_op attr for the wcc data + */ +void fill_pre_wcc(struct svc_fh *fhp) +{ + struct inode *inode; + struct kstat stat; + __be32 err; + + if (fhp->fh_pre_saved) + return; + + inode = d_inode(fhp->fh_dentry); + err = fh_getattr(fhp, &stat); + if (err) { + /* Grab the times from inode anyway */ + stat.mtime = inode->i_mtime; + stat.ctime = inode->i_ctime; + stat.size = inode->i_size; + } + + fhp->fh_pre_mtime = stat.mtime; + fhp->fh_pre_ctime = stat.ctime; + fhp->fh_pre_size = stat.size; + fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); + fhp->fh_pre_saved = true; +} + +/* * Fill in the post_op attr for the wcc data */ void fill_post_wcc(struct svc_fh *fhp) @@ -261,7 +289,8 @@ void fill_post_wcc(struct svc_fh *fhp) printk("nfsd: inode locked twice during operation.\n"); err = fh_getattr(fhp, &fhp->fh_post_attr); - fhp->fh_post_change = nfsd4_change_attribute(d_inode(fhp->fh_dentry)); + fhp->fh_post_change = nfsd4_change_attribute(&fhp->fh_post_attr, + d_inode(fhp->fh_dentry)); if (err) { fhp->fh_post_saved = false; /* Grab the ctime anyway - set_change_info might use it */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 008ea0b627d0..a0bed2b2004d 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1363,14 +1363,14 @@ nfsd4_layoutget(struct svc_rqst *rqstp, const struct nfsd4_layout_ops *ops; struct nfs4_layout_stateid *ls; __be32 nfserr; - int accmode; + int accmode = NFSD_MAY_READ_IF_EXEC; switch (lgp->lg_seg.iomode) { case IOMODE_READ: - accmode = NFSD_MAY_READ; + accmode |= NFSD_MAY_READ; break; case IOMODE_RW: - accmode = NFSD_MAY_READ | NFSD_MAY_WRITE; + accmode |= NFSD_MAY_READ | NFSD_MAY_WRITE; break; default: dprintk("%s: invalid iomode %d\n", @@ -1703,6 +1703,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) status = nfserr_minor_vers_mismatch; if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0) goto out; + status = nfserr_resource; + if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND) + goto out; status = nfs41_check_op_ordering(args); if (status) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index b29b5a185a2c..150521c9671b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3590,6 +3590,7 @@ nfsd4_verify_open_stid(struct nfs4_stid *s) switch (s->sc_type) { default: break; + case 0: case NFS4_CLOSED_STID: case NFS4_CLOSED_DELEG_STID: ret = nfserr_bad_stateid; @@ -5182,7 +5183,6 @@ nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) lockowner(stp->st_stateowner))) goto out; - stp->st_stid.sc_type = NFS4_CLOSED_STID; release_lock_stateid(stp); ret = nfs_ok; @@ -6078,10 +6078,8 @@ out: * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. */ - if (status && new) { - lock_stp->st_stid.sc_type = NFS4_CLOSED_STID; + if (status && new) release_lock_stateid(lock_stp); - } mutex_unlock(&lock_stp->st_mutex); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2c61c6b8ae09..e502fd16246b 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -455,8 +455,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, } label->len = 0; -#ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (IS_ENABLED(CONFIG_NFSD_V4_SECURITY_LABEL) && + bmval[2] & FATTR4_WORD2_SECURITY_LABEL) { READ_BUF(4); len += 4; dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */ @@ -476,7 +476,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, if (!label->data) return nfserr_jukebox; } -#endif if (bmval[2] & FATTR4_WORD2_MODE_UMASK) { if (!umask) goto xdr_error; @@ -1918,8 +1917,13 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) if (argp->taglen > NFSD4_MAX_TAGLEN) goto xdr_error; - if (argp->opcnt > 100) - goto xdr_error; + /* + * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS + * here, so we return success at the xdr level so that + * nfsd4_proc can handle this is an NFS-level error. + */ + if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND) + return 0; if (argp->opcnt > ARRAY_SIZE(argp->iops)) { argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL); @@ -1991,7 +1995,7 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, *p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time)); *p++ = 0; } else if (IS_I_VERSION(inode)) { - p = xdr_encode_hyper(p, nfsd4_change_attribute(inode)); + p = xdr_encode_hyper(p, nfsd4_change_attribute(stat, inode)); } else { *p++ = cpu_to_be32(stat->ctime.tv_sec); *p++ = cpu_to_be32(stat->ctime.tv_nsec); diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index b8444189223b..755e256a9103 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -253,36 +253,20 @@ fh_clear_wcc(struct svc_fh *fhp) * By using both ctime and the i_version counter we guarantee that as * long as time doesn't go backwards we never reuse an old value. */ -static inline u64 nfsd4_change_attribute(struct inode *inode) +static inline u64 nfsd4_change_attribute(struct kstat *stat, + struct inode *inode) { u64 chattr; - chattr = inode->i_ctime.tv_sec; + chattr = stat->ctime.tv_sec; chattr <<= 30; - chattr += inode->i_ctime.tv_nsec; + chattr += stat->ctime.tv_nsec; chattr += inode_query_iversion(inode); return chattr; } -/* - * Fill in the pre_op attr for the wcc data - */ -static inline void -fill_pre_wcc(struct svc_fh *fhp) -{ - struct inode *inode; - - inode = d_inode(fhp->fh_dentry); - if (!fhp->fh_pre_saved) { - fhp->fh_pre_mtime = inode->i_mtime; - fhp->fh_pre_ctime = inode->i_ctime; - fhp->fh_pre_size = inode->i_size; - fhp->fh_pre_change = nfsd4_change_attribute(inode); - fhp->fh_pre_saved = true; - } -} - -extern void fill_post_wcc(struct svc_fh *); +extern void fill_pre_wcc(struct svc_fh *fhp); +extern void fill_post_wcc(struct svc_fh *fhp); #else #define fh_clear_wcc(ignored) #define fill_pre_wcc(ignored) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 644a0342f0e0..79b6064f8977 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -188,6 +188,7 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, *p++ = htonl((u32) stat->ino); *p++ = htonl((u32) stat->atime.tv_sec); *p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0); + time = stat->mtime; lease_get_mtime(d_inode(dentry), &time); *p++ = htonl((u32) time.tv_sec); *p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0); diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 6c5009cc4e6f..68cb9e4740b4 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -130,7 +130,7 @@ int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *segbuf, } int nilfs_segbuf_reset(struct nilfs_segment_buffer *segbuf, unsigned int flags, - time_t ctime, __u64 cno) + time64_t ctime, __u64 cno) { int err; diff --git a/fs/nilfs2/segbuf.h b/fs/nilfs2/segbuf.h index 7bbccc099709..10e16935fff6 100644 --- a/fs/nilfs2/segbuf.h +++ b/fs/nilfs2/segbuf.h @@ -46,7 +46,7 @@ struct nilfs_segsum_info { unsigned long nfileblk; u64 seg_seq; __u64 cno; - time_t ctime; + time64_t ctime; sector_t next; }; @@ -120,7 +120,7 @@ void nilfs_segbuf_map_cont(struct nilfs_segment_buffer *segbuf, struct nilfs_segment_buffer *prev); void nilfs_segbuf_set_next_segnum(struct nilfs_segment_buffer *, __u64, struct the_nilfs *); -int nilfs_segbuf_reset(struct nilfs_segment_buffer *, unsigned int, time_t, +int nilfs_segbuf_reset(struct nilfs_segment_buffer *, unsigned int, time64_t, __u64); int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *); int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *, diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 9f3ffba41533..0953635e7d48 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2040,7 +2040,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) goto out; /* Update time stamp */ - sci->sc_seg_ctime = get_seconds(); + sci->sc_seg_ctime = ktime_get_real_seconds(); err = nilfs_segctor_collect(sci, nilfs, mode); if (unlikely(err)) diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 84084a4d9b3e..04634e3e3d58 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -157,7 +157,7 @@ struct nilfs_sc_info { unsigned long sc_blk_cnt; unsigned long sc_datablk_cnt; unsigned long sc_nblk_this_inc; - time_t sc_seg_ctime; + time64_t sc_seg_ctime; __u64 sc_cno; unsigned long sc_flags; diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 1341a41e7b43..c7fa139d50e8 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -526,7 +526,7 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) * @modtime: modification time (option) */ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, - unsigned long nblocks, time_t modtime) + unsigned long nblocks, time64_t modtime) { struct buffer_head *bh; struct nilfs_segment_usage *su; diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index 158a9190c8ec..673a891350f4 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -35,7 +35,7 @@ int nilfs_sufile_set_alloc_range(struct inode *sufile, __u64 start, __u64 end); int nilfs_sufile_alloc(struct inode *, __u64 *); int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum); int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, - unsigned long nblocks, time_t modtime); + unsigned long nblocks, time64_t modtime); int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *); ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned int, size_t); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 3073b646e1ba..6ffeca84d7c3 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -283,10 +283,10 @@ int nilfs_commit_super(struct super_block *sb, int flag) { struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_super_block **sbp = nilfs->ns_sbp; - time_t t; + time64_t t; /* nilfs->ns_sem must be locked by the caller. */ - t = get_seconds(); + t = ktime_get_real_seconds(); nilfs->ns_sbwtime = t; sbp[0]->s_wtime = cpu_to_le64(t); sbp[0]->s_sum = 0; diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 490303e3d517..4b25837e7724 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -31,7 +31,7 @@ static struct kset *nilfs_kset; #define NILFS_SHOW_TIME(time_t_val, buf) ({ \ struct tm res; \ int count = 0; \ - time_to_tm(time_t_val, 0, &res); \ + time64_to_tm(time_t_val, 0, &res); \ res.tm_year += 1900; \ res.tm_mon += 1; \ count = scnprintf(buf, PAGE_SIZE, \ @@ -579,7 +579,7 @@ nilfs_segctor_last_seg_write_time_show(struct nilfs_segctor_attr *attr, struct the_nilfs *nilfs, char *buf) { - time_t ctime; + time64_t ctime; down_read(&nilfs->ns_segctor_sem); ctime = nilfs->ns_ctime; @@ -593,13 +593,13 @@ nilfs_segctor_last_seg_write_time_secs_show(struct nilfs_segctor_attr *attr, struct the_nilfs *nilfs, char *buf) { - time_t ctime; + time64_t ctime; down_read(&nilfs->ns_segctor_sem); ctime = nilfs->ns_ctime; up_read(&nilfs->ns_segctor_sem); - return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)ctime); + return snprintf(buf, PAGE_SIZE, "%llu\n", ctime); } static ssize_t @@ -607,7 +607,7 @@ nilfs_segctor_last_nongc_write_time_show(struct nilfs_segctor_attr *attr, struct the_nilfs *nilfs, char *buf) { - time_t nongc_ctime; + time64_t nongc_ctime; down_read(&nilfs->ns_segctor_sem); nongc_ctime = nilfs->ns_nongc_ctime; @@ -621,14 +621,13 @@ nilfs_segctor_last_nongc_write_time_secs_show(struct nilfs_segctor_attr *attr, struct the_nilfs *nilfs, char *buf) { - time_t nongc_ctime; + time64_t nongc_ctime; down_read(&nilfs->ns_segctor_sem); nongc_ctime = nilfs->ns_nongc_ctime; up_read(&nilfs->ns_segctor_sem); - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)nongc_ctime); + return snprintf(buf, PAGE_SIZE, "%llu\n", nongc_ctime); } static ssize_t @@ -728,7 +727,7 @@ nilfs_superblock_sb_write_time_show(struct nilfs_superblock_attr *attr, struct the_nilfs *nilfs, char *buf) { - time_t sbwtime; + time64_t sbwtime; down_read(&nilfs->ns_sem); sbwtime = nilfs->ns_sbwtime; @@ -742,13 +741,13 @@ nilfs_superblock_sb_write_time_secs_show(struct nilfs_superblock_attr *attr, struct the_nilfs *nilfs, char *buf) { - time_t sbwtime; + time64_t sbwtime; down_read(&nilfs->ns_sem); sbwtime = nilfs->ns_sbwtime; up_read(&nilfs->ns_sem); - return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long)sbwtime); + return snprintf(buf, PAGE_SIZE, "%llu\n", sbwtime); } static ssize_t diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 883d732b0259..36da1779f976 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -116,7 +116,7 @@ struct the_nilfs { */ struct buffer_head *ns_sbh[2]; struct nilfs_super_block *ns_sbp[2]; - time_t ns_sbwtime; + time64_t ns_sbwtime; unsigned int ns_sbwcount; unsigned int ns_sbsize; unsigned int ns_mount_state; @@ -131,8 +131,8 @@ struct the_nilfs { __u64 ns_nextnum; unsigned long ns_pseg_offset; __u64 ns_cno; - time_t ns_ctime; - time_t ns_nongc_ctime; + time64_t ns_ctime; + time64_t ns_nongc_ctime; atomic_t ns_ndirtyblks; /* @@ -267,7 +267,7 @@ struct nilfs_root { static inline int nilfs_sb_need_update(struct the_nilfs *nilfs) { - u64 t = get_seconds(); + u64 t = ktime_get_real_seconds(); return t < nilfs->ns_sbwtime || t > nilfs->ns_sbwtime + nilfs->ns_sb_update_freq; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index ef08d64c84b8..c07eb3d655ea 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -247,7 +247,7 @@ static __poll_t fanotify_poll(struct file *file, poll_table *wait) poll_wait(file, &group->notification_waitq, wait); spin_lock(&group->notification_lock); if (!fsnotify_notify_queue_is_empty(group)) - ret = POLLIN | POLLRDNORM; + ret = EPOLLIN | EPOLLRDNORM; spin_unlock(&group->notification_lock); return ret; diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 5c29bf16814f..2c908b31d6c9 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -115,7 +115,7 @@ static __poll_t inotify_poll(struct file *file, poll_table *wait) poll_wait(file, &group->notification_waitq, wait); spin_lock(&group->notification_lock); if (!fsnotify_notify_queue_is_empty(group)) - ret = POLLIN | POLLRDNORM; + ret = EPOLLIN | EPOLLRDNORM; spin_unlock(&group->notification_lock); return ret; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index b7520e20a770..977763d4c27d 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1776,7 +1776,7 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode, * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ - if (inode_cmp_iversion(inode, *f_version)) { + if (!inode_eq_iversion(inode, *f_version)) { for (i = 0; i < i_size_read(inode) && i < offset; ) { de = (struct ocfs2_dir_entry *) (data->id_data + i); @@ -1870,7 +1870,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, * readdir(2), then we might be pointing to an invalid * dirent right now. Scan from the start of the block * to make sure. */ - if (inode_cmp_iversion(inode, *f_version)) { + if (!inode_eq_iversion(inode, *f_version)) { for (i = 0; i < sb->s_blocksize && i < offset; ) { de = (struct ocfs2_dir_entry *) (bh->b_data + i); /* It's too expensive to do a full diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 385fcefa8bc5..602c71f32740 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -71,7 +71,7 @@ struct workqueue_struct *user_dlm_worker; * Over time, dlmfs has added some features that were not part of the * initial ABI. Unfortunately, some of these features are not detectable * via standard usage. For example, Linux's default poll always returns - * POLLIN, so there is no way for a caller of poll(2) to know when dlmfs + * EPOLLIN, so there is no way for a caller of poll(2) to know when dlmfs * added poll support. Instead, we provide this list of new capabilities. * * Capabilities is a read-only attribute. We do it as a module parameter @@ -83,7 +83,7 @@ struct workqueue_struct *user_dlm_worker; * interaction. * * Capabilities: - * - bast : POLLIN against the file descriptor of a held lock + * - bast : EPOLLIN against the file descriptor of a held lock * signifies a bast fired on the lock. */ #define DLMFS_CAPABILITIES "bast stackglue" @@ -230,7 +230,7 @@ static __poll_t dlmfs_file_poll(struct file *file, poll_table *wait) spin_lock(&ip->ip_lockres.l_lock); if (ip->ip_lockres.l_flags & USER_LOCK_BLOCKED) - event = POLLIN | POLLRDNORM; + event = EPOLLIN | EPOLLRDNORM; spin_unlock(&ip->ip_lockres.l_lock); return event; diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c index ae782df5c063..fe484cf93e5c 100644 --- a/fs/orangefs/dcache.c +++ b/fs/orangefs/dcache.c @@ -33,7 +33,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) new_op->upcall.req.lookup.parent_refn = parent->refn; strncpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name, - ORANGEFS_NAME_MAX); + ORANGEFS_NAME_MAX - 1); gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d interrupt flag [%d]\n", @@ -118,8 +118,12 @@ static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags) return 0; /* We do not need to continue with negative dentries. */ - if (!dentry->d_inode) - goto out; + if (!dentry->d_inode) { + gossip_debug(GOSSIP_DCACHE_DEBUG, + "%s: negative dentry or positive dentry and inode valid.\n", + __func__); + return 1; + } /* Now we must perform a getattr to validate the inode contents. */ @@ -129,14 +133,7 @@ static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags) __FILE__, __func__, __LINE__); return 0; } - if (ret == 0) - return 0; - -out: - gossip_debug(GOSSIP_DCACHE_DEBUG, - "%s: negative dentry or positive dentry and inode valid.\n", - __func__); - return 1; + return !ret; } const struct dentry_operations orangefs_dentry_operations = { diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index f073cd9e6687..b03057afac2a 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -823,7 +823,7 @@ static __poll_t orangefs_devreq_poll(struct file *file, poll_wait(file, &orangefs_request_list_waitq, poll_table); if (!list_empty(&orangefs_request_list)) - poll_revent_mask |= POLLIN; + poll_revent_mask |= EPOLLIN; return poll_revent_mask; } diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index c98bba2dbc94..6e3134e6d98a 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -41,7 +41,7 @@ static int orangefs_create(struct inode *dir, ORANGEFS_TYPE_METAFILE, mode); strncpy(new_op->upcall.req.create.d_name, - dentry->d_name.name, ORANGEFS_NAME_MAX); + dentry->d_name.name, ORANGEFS_NAME_MAX - 1); ret = service_operation(new_op, __func__, get_interruptible_flag(dir)); @@ -142,7 +142,7 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry, new_op->upcall.req.lookup.parent_refn = parent->refn; strncpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name, - ORANGEFS_NAME_MAX); + ORANGEFS_NAME_MAX - 1); gossip_debug(GOSSIP_NAME_DEBUG, "%s: doing lookup on %s under %pU,%d\n", @@ -244,7 +244,7 @@ static int orangefs_unlink(struct inode *dir, struct dentry *dentry) new_op->upcall.req.remove.parent_refn = parent->refn; strncpy(new_op->upcall.req.remove.d_name, dentry->d_name.name, - ORANGEFS_NAME_MAX); + ORANGEFS_NAME_MAX - 1); ret = service_operation(new_op, "orangefs_unlink", get_interruptible_flag(inode)); @@ -300,8 +300,8 @@ static int orangefs_symlink(struct inode *dir, strncpy(new_op->upcall.req.sym.entry_name, dentry->d_name.name, - ORANGEFS_NAME_MAX); - strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX); + ORANGEFS_NAME_MAX - 1); + strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX - 1); ret = service_operation(new_op, __func__, get_interruptible_flag(dir)); @@ -372,7 +372,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode ORANGEFS_TYPE_DIRECTORY, mode); strncpy(new_op->upcall.req.mkdir.d_name, - dentry->d_name.name, ORANGEFS_NAME_MAX); + dentry->d_name.name, ORANGEFS_NAME_MAX - 1); ret = service_operation(new_op, __func__, get_interruptible_flag(dir)); @@ -453,10 +453,10 @@ static int orangefs_rename(struct inode *old_dir, strncpy(new_op->upcall.req.rename.d_old_name, old_dentry->d_name.name, - ORANGEFS_NAME_MAX); + ORANGEFS_NAME_MAX - 1); strncpy(new_op->upcall.req.rename.d_new_name, new_dentry->d_name.name, - ORANGEFS_NAME_MAX); + ORANGEFS_NAME_MAX - 1); ret = service_operation(new_op, "orangefs_rename", diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 1c59dff530de..6e35f2f3c897 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -328,7 +328,7 @@ static int help_show(struct seq_file *m, void *v) /* * initialize the client-debug file. */ -int orangefs_client_debug_init(void) +static int orangefs_client_debug_init(void) { int rc = -ENOMEM; @@ -1056,7 +1056,7 @@ int orangefs_debugfs_new_debug(void __user *arg) client_debug_string, llu(mask_info.mask_value)); } else { - gossip_lerr("Invalid mask type....\n"); + gossip_err("Invalid mask type....\n"); return -EINVAL; } diff --git a/fs/orangefs/orangefs-debugfs.h b/fs/orangefs/orangefs-debugfs.h index b5fd9cd4960f..51147f9ce3d6 100644 --- a/fs/orangefs/orangefs-debugfs.h +++ b/fs/orangefs/orangefs-debugfs.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ int orangefs_debugfs_init(int); void orangefs_debugfs_cleanup(void); -int orangefs_client_debug_init(void); int orangefs_prepare_debugfs_help_string(int); int orangefs_debugfs_new_client_mask(void __user *); int orangefs_debugfs_new_client_string(void __user *); diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 2595453fe737..eebbaece85ef 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -56,11 +56,7 @@ #include "orangefs-dev-proto.h" -#ifdef ORANGEFS_KERNEL_DEBUG -#define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS 10 -#else #define ORANGEFS_DEFAULT_OP_TIMEOUT_SECS 20 -#endif #define ORANGEFS_BUFMAP_WAIT_TIMEOUT_SECS 30 @@ -104,11 +100,11 @@ enum orangefs_vfs_op_states { * orangefs kernel memory related flags */ -#if ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB)) +#if (defined CONFIG_DEBUG_SLAB) #define ORANGEFS_CACHE_CREATE_FLAGS SLAB_RED_ZONE #else #define ORANGEFS_CACHE_CREATE_FLAGS 0 -#endif /* ((defined ORANGEFS_KERNEL_DEBUG) && (defined CONFIG_DEBUG_SLAB)) */ +#endif extern int orangefs_init_acl(struct inode *inode, struct inode *dir); extern const struct xattr_handler *orangefs_xattr_handlers[]; @@ -471,8 +467,6 @@ int orangefs_inode_check_changed(struct inode *inode); int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr); -void orangefs_make_bad_inode(struct inode *inode); - int orangefs_unmount_sb(struct super_block *sb); bool orangefs_cancel_op_in_progress(struct orangefs_kernel_op_s *op); diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c index 97fe93129f38..ea6256d136d1 100644 --- a/fs/orangefs/orangefs-utils.c +++ b/fs/orangefs/orangefs-utils.c @@ -230,25 +230,42 @@ static int orangefs_inode_type(enum orangefs_ds_type objtype) return -1; } -static int orangefs_inode_is_stale(struct inode *inode, int new, +static void orangefs_make_bad_inode(struct inode *inode) +{ + if (is_root_handle(inode)) { + /* + * if this occurs, the pvfs2-client-core was killed but we + * can't afford to lose the inode operations and such + * associated with the root handle in any case. + */ + gossip_debug(GOSSIP_UTILS_DEBUG, + "*** NOT making bad root inode %pU\n", + get_khandle_from_ino(inode)); + } else { + gossip_debug(GOSSIP_UTILS_DEBUG, + "*** making bad inode %pU\n", + get_khandle_from_ino(inode)); + make_bad_inode(inode); + } +} + +static int orangefs_inode_is_stale(struct inode *inode, struct ORANGEFS_sys_attr_s *attrs, char *link_target) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); int type = orangefs_inode_type(attrs->objtype); - if (!new) { - /* - * If the inode type or symlink target have changed then this - * inode is stale. - */ - if (type == -1 || !(inode->i_mode & type)) { - orangefs_make_bad_inode(inode); - return 1; - } - if (type == S_IFLNK && strncmp(orangefs_inode->link_target, - link_target, ORANGEFS_NAME_MAX)) { - orangefs_make_bad_inode(inode); - return 1; - } + /* + * If the inode type or symlink target have changed then this + * inode is stale. + */ + if (type == -1 || !(inode->i_mode & type)) { + orangefs_make_bad_inode(inode); + return 1; + } + if (type == S_IFLNK && strncmp(orangefs_inode->link_target, + link_target, ORANGEFS_NAME_MAX)) { + orangefs_make_bad_inode(inode); + return 1; } return 0; } @@ -294,16 +311,18 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, if (ret != 0) goto out; - type = orangefs_inode_type(new_op-> - downcall.resp.getattr.attributes.objtype); - ret = orangefs_inode_is_stale(inode, new, - &new_op->downcall.resp.getattr.attributes, - new_op->downcall.resp.getattr.link_target); - if (ret) { - ret = -ESTALE; - goto out; + if (!new) { + ret = orangefs_inode_is_stale(inode, + &new_op->downcall.resp.getattr.attributes, + new_op->downcall.resp.getattr.link_target); + if (ret) { + ret = -ESTALE; + goto out; + } } + type = orangefs_inode_type(new_op-> + downcall.resp.getattr.attributes.objtype); switch (type) { case S_IFREG: inode->i_flags = orangefs_inode_flags(&new_op-> @@ -348,6 +367,12 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass, inode->i_link = orangefs_inode->link_target; } break; + /* i.e. -1 */ + default: + /* XXX: ESTALE? This is what is done if it is not new. */ + orangefs_make_bad_inode(inode); + ret = -ESTALE; + goto out; } inode->i_uid = make_kuid(&init_user_ns, new_op-> @@ -401,7 +426,7 @@ int orangefs_inode_check_changed(struct inode *inode) if (ret != 0) goto out; - ret = orangefs_inode_is_stale(inode, 0, + ret = orangefs_inode_is_stale(inode, &new_op->downcall.resp.getattr.attributes, new_op->downcall.resp.getattr.link_target); out: @@ -444,25 +469,6 @@ int orangefs_inode_setattr(struct inode *inode, struct iattr *iattr) return ret; } -void orangefs_make_bad_inode(struct inode *inode) -{ - if (is_root_handle(inode)) { - /* - * if this occurs, the pvfs2-client-core was killed but we - * can't afford to lose the inode operations and such - * associated with the root handle in any case. - */ - gossip_debug(GOSSIP_UTILS_DEBUG, - "*** NOT making bad root inode %pU\n", - get_khandle_from_ino(inode)); - } else { - gossip_debug(GOSSIP_UTILS_DEBUG, - "*** making bad inode %pU\n", - get_khandle_from_ino(inode)); - make_bad_inode(inode); - } -} - /* * The following is a very dirty hack that is now a permanent part of the * ORANGEFS protocol. See protocol.h for more error definitions. @@ -537,6 +543,7 @@ int orangefs_normalize_to_errno(__s32 error_code) */ } else { gossip_err("orangefs: orangefs_normalize_to_errno: got error code which is not from ORANGEFS.\n"); + error_code = -EINVAL; } return error_code; } diff --git a/fs/orangefs/protocol.h b/fs/orangefs/protocol.h index e0bf5e4dce0d..dc6e3e6269c3 100644 --- a/fs/orangefs/protocol.h +++ b/fs/orangefs/protocol.h @@ -395,13 +395,6 @@ struct ORANGEFS_dev_map_desc { /* gossip.h *****************************************************************/ -#ifdef GOSSIP_DISABLE_DEBUG -#define gossip_debug(mask, fmt, ...) \ -do { \ - if (0) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ -} while (0) -#else extern __u64 orangefs_gossip_debug_mask; /* try to avoid function call overhead by checking masks in macro */ @@ -410,13 +403,5 @@ do { \ if (orangefs_gossip_debug_mask & (mask)) \ printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ } while (0) -#endif /* GOSSIP_DISABLE_DEBUG */ - -/* do file and line number printouts w/ the GNU preprocessor */ -#define gossip_ldebug(mask, fmt, ...) \ - gossip_debug(mask, "%s: " fmt, __func__, ##__VA_ARGS__) #define gossip_err pr_err -#define gossip_lerr(fmt, ...) \ - gossip_err("%s line %d: " fmt, \ - __FILE__, __LINE__, ##__VA_ARGS__) diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 62d49e53061c..3ae5fdba0225 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -335,7 +335,7 @@ static int orangefs_encode_fh(struct inode *inode, struct orangefs_object_kref refn; if (*max_len < len) { - gossip_lerr("fh buffer is too small for encoding\n"); + gossip_err("fh buffer is too small for encoding\n"); *max_len = len; type = 255; goto out; @@ -383,7 +383,7 @@ static int orangefs_unmount(int id, __s32 fs_id, const char *devname) op->upcall.req.fs_umount.id = id; op->upcall.req.fs_umount.fs_id = fs_id; strncpy(op->upcall.req.fs_umount.orangefs_config_server, - devname, ORANGEFS_MAX_SERVER_ADDR_LEN); + devname, ORANGEFS_MAX_SERVER_ADDR_LEN - 1); r = service_operation(op, "orangefs_fs_umount", 0); /* Not much to do about an error here. */ if (r) @@ -478,7 +478,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, strncpy(new_op->upcall.req.fs_mount.orangefs_config_server, devname, - ORANGEFS_MAX_SERVER_ADDR_LEN); + ORANGEFS_MAX_SERVER_ADDR_LEN - 1); gossip_debug(GOSSIP_SUPER_DEBUG, "Attempting ORANGEFS Mount via host %s\n", @@ -520,7 +520,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst, */ strncpy(ORANGEFS_SB(sb)->devname, devname, - ORANGEFS_MAX_SERVER_ADDR_LEN); + ORANGEFS_MAX_SERVER_ADDR_LEN - 1); /* mount_pending must be cleared */ ORANGEFS_SB(sb)->mount_pending = 0; diff --git a/fs/pipe.c b/fs/pipe.c index a449ca0ec0c6..7b1954caf388 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -35,11 +35,6 @@ */ unsigned int pipe_max_size = 1048576; -/* - * Minimum pipe size, as required by POSIX - */ -unsigned int pipe_min_size = PAGE_SIZE; - /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ @@ -332,7 +327,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) break; } if (do_wakeup) { - wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM); + wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } pipe_wait(pipe); @@ -341,7 +336,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) /* Signal writers asynchronously that there is more room. */ if (do_wakeup) { - wake_up_interruptible_sync_poll(&pipe->wait, POLLOUT | POLLWRNORM); + wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } if (ret > 0) @@ -468,7 +463,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) break; } if (do_wakeup) { - wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); + wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); do_wakeup = 0; } @@ -479,7 +474,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) out: __pipe_unlock(pipe); if (do_wakeup) { - wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); + wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { @@ -528,19 +523,19 @@ pipe_poll(struct file *filp, poll_table *wait) nrbufs = pipe->nrbufs; mask = 0; if (filp->f_mode & FMODE_READ) { - mask = (nrbufs > 0) ? POLLIN | POLLRDNORM : 0; + mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0; if (!pipe->writers && filp->f_version != pipe->w_counter) - mask |= POLLHUP; + mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { - mask |= (nrbufs < pipe->buffers) ? POLLOUT | POLLWRNORM : 0; + mask |= (nrbufs < pipe->buffers) ? EPOLLOUT | EPOLLWRNORM : 0; /* - * Most Unices do not set POLLERR for FIFOs but on Linux they + * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) - mask |= POLLERR; + mask |= EPOLLERR; } return mask; @@ -573,7 +568,7 @@ pipe_release(struct inode *inode, struct file *file) pipe->writers--; if (pipe->readers || pipe->writers) { - wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM | POLLERR | POLLHUP); + wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM | EPOLLERR | EPOLLHUP); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } @@ -610,12 +605,21 @@ static unsigned long account_pipe_buffers(struct user_struct *user, static bool too_many_pipe_buffers_soft(unsigned long user_bufs) { - return pipe_user_pages_soft && user_bufs >= pipe_user_pages_soft; + unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); + + return soft_limit && user_bufs > soft_limit; } static bool too_many_pipe_buffers_hard(unsigned long user_bufs) { - return pipe_user_pages_hard && user_bufs >= pipe_user_pages_hard; + unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); + + return hard_limit && user_bufs > hard_limit; +} + +static bool is_unprivileged_user(void) +{ + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) @@ -624,22 +628,23 @@ struct pipe_inode_info *alloc_pipe_info(void) unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; + unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; - if (pipe_bufs * PAGE_SIZE > pipe_max_size && !capable(CAP_SYS_RESOURCE)) - pipe_bufs = pipe_max_size >> PAGE_SHIFT; + if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) + pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); - if (too_many_pipe_buffers_soft(user_bufs)) { + if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, 1); pipe_bufs = 1; } - if (too_many_pipe_buffers_hard(user_bufs)) + if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), @@ -931,7 +936,7 @@ static int fifo_open(struct inode *inode, struct file *filp) if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { - /* suppress POLLHUP until we have + /* suppress EPOLLHUP until we have * seen a writer */ filp->f_version = pipe->w_counter; } else { @@ -1020,18 +1025,16 @@ const struct file_operations pipefifo_fops = { * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ -unsigned int round_pipe_size(unsigned int size) +unsigned int round_pipe_size(unsigned long size) { - unsigned long nr_pages; - - if (size < pipe_min_size) - size = pipe_min_size; - - nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (nr_pages == 0) + if (size > (1U << 31)) return 0; - return roundup_pow_of_two(nr_pages) << PAGE_SHIFT; + /* Minimum pipe size, as required by POSIX */ + if (size < PAGE_SIZE) + return PAGE_SIZE; + + return roundup_pow_of_two(size); } /* @@ -1046,8 +1049,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) long ret = 0; size = round_pipe_size(arg); - if (size == 0) - return -EINVAL; nr_pages = size >> PAGE_SHIFT; if (!nr_pages) @@ -1069,7 +1070,7 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) if (nr_pages > pipe->buffers && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && - !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { + is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } @@ -1125,16 +1126,6 @@ out_revert_acct: } /* - * This should work even if CONFIG_PROC_FS isn't set, as proc_dopipe_max_size - * will return an error. - */ -int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, - size_t *lenp, loff_t *ppos) -{ - return proc_dopipe_max_size(table, write, buf, lenp, ppos); -} - -/* * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same * location, so checking ->i_pipe is not enough to verify that this is a * pipe. diff --git a/fs/proc/array.c b/fs/proc/array.c index d67a72dcb92c..598803576e4c 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -736,16 +736,10 @@ static int children_seq_open(struct inode *inode, struct file *file) return ret; } -int children_seq_release(struct inode *inode, struct file *file) -{ - seq_release(inode, file); - return 0; -} - const struct file_operations proc_tid_children_operations = { .open = children_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = children_seq_release, + .release = seq_release, }; #endif /* CONFIG_PROC_CHILDREN */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 60316b52d659..9298324325ed 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -75,6 +75,7 @@ #include <linux/ptrace.h> #include <linux/tracehook.h> #include <linux/printk.h> +#include <linux/cache.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> @@ -100,6 +101,8 @@ #include "internal.h" #include "fd.h" +#include "../../lib/kstrtox.h" + /* NOTE: * Implementing inode permission operations in /proc is almost * certainly an error. Permission checks need to happen during @@ -110,8 +113,8 @@ * in /proc for a task before it execs a suid executable. */ -static u8 nlink_tid; -static u8 nlink_tgid; +static u8 nlink_tid __ro_after_init; +static u8 nlink_tgid __ro_after_init; struct pid_entry { const char *name; @@ -1370,7 +1373,7 @@ static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; - WRITE_ONCE(task->fail_nth, n); + task->fail_nth = n; put_task_struct(task); return count; @@ -1386,8 +1389,7 @@ static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, task = get_proc_task(file_inode(file)); if (!task) return -ESRCH; - len = snprintf(numbuf, sizeof(numbuf), "%u\n", - READ_ONCE(task->fail_nth)); + len = snprintf(numbuf, sizeof(numbuf), "%u\n", task->fail_nth); len = simple_read_from_buffer(buf, count, ppos, numbuf, len); put_task_struct(task); @@ -1907,8 +1909,33 @@ end_instantiate: static int dname_to_vma_addr(struct dentry *dentry, unsigned long *start, unsigned long *end) { - if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2) + const char *str = dentry->d_name.name; + unsigned long long sval, eval; + unsigned int len; + + len = _parse_integer(str, 16, &sval); + if (len & KSTRTOX_OVERFLOW) + return -EINVAL; + if (sval != (unsigned long)sval) return -EINVAL; + str += len; + + if (*str != '-') + return -EINVAL; + str++; + + len = _parse_integer(str, 16, &eval); + if (len & KSTRTOX_OVERFLOW) + return -EINVAL; + if (eval != (unsigned long)eval) + return -EINVAL; + str += len; + + if (*str != '\0') + return -EINVAL; + + *start = sval; + *end = eval; return 0; } @@ -2000,9 +2027,9 @@ out: } struct map_files_info { + unsigned long start; + unsigned long end; fmode_t mode; - unsigned int len; - unsigned char name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */ }; /* @@ -2172,10 +2199,9 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) if (++pos <= ctx->pos) continue; + info.start = vma->vm_start; + info.end = vma->vm_end; info.mode = vma->vm_file->f_mode; - info.len = snprintf(info.name, - sizeof(info.name), "%lx-%lx", - vma->vm_start, vma->vm_end); if (flex_array_put(fa, i++, &info, GFP_KERNEL)) BUG(); } @@ -2183,9 +2209,13 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) up_read(&mm->mmap_sem); for (i = 0; i < nr_files; i++) { + char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */ + unsigned int len; + p = flex_array_get(fa, i); + len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end); if (!proc_fill_cache(file, ctx, - p->name, p->len, + buf, len, proc_map_files_instantiate, task, (void *)(unsigned long)p->mode)) @@ -3018,11 +3048,11 @@ static const struct inode_operations proc_tgid_base_inode_operations = { static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) { struct dentry *dentry, *leader, *dir; - char buf[PROC_NUMBUF]; + char buf[10 + 1]; struct qstr name; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", pid); + name.len = snprintf(buf, sizeof(buf), "%u", pid); /* no ->d_hash() rejects on procfs */ dentry = d_hash_and_lookup(mnt->mnt_root, &name); if (dentry) { @@ -3034,7 +3064,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) return; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", tgid); + name.len = snprintf(buf, sizeof(buf), "%u", tgid); leader = d_hash_and_lookup(mnt->mnt_root, &name); if (!leader) goto out; @@ -3046,7 +3076,7 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) goto out_put_leader; name.name = buf; - name.len = snprintf(buf, sizeof(buf), "%d", pid); + name.len = snprintf(buf, sizeof(buf), "%u", pid); dentry = d_hash_and_lookup(dir, &name); if (dentry) { d_invalidate(dentry); @@ -3225,14 +3255,14 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) for (iter = next_tgid(ns, iter); iter.task; iter.tgid += 1, iter = next_tgid(ns, iter)) { - char name[PROC_NUMBUF]; + char name[10 + 1]; int len; cond_resched(); if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE)) continue; - len = snprintf(name, sizeof(name), "%d", iter.tgid); + len = snprintf(name, sizeof(name), "%u", iter.tgid); ctx->pos = iter.tgid + TGID_OFFSET; if (!proc_fill_cache(file, ctx, name, len, proc_pid_instantiate, iter.task, NULL)) { @@ -3560,10 +3590,10 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); task; task = next_tid(task), ctx->pos++) { - char name[PROC_NUMBUF]; + char name[10 + 1]; int len; tid = task_pid_nr_ns(task, ns); - len = snprintf(name, sizeof(name), "%d", tid); + len = snprintf(name, sizeof(name), "%u", tid); if (!proc_fill_cache(file, ctx, name, len, proc_task_instantiate, task, NULL)) { /* returning this tgid failed, save it as the first diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c index 290ba85cb900..a8ac48aebd59 100644 --- a/fs/proc/consoles.c +++ b/fs/proc/consoles.c @@ -55,8 +55,7 @@ static int show_console_dev(struct seq_file *m, void *v) if (dev) seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev)); - seq_printf(m, "\n"); - + seq_putc(m, '\n'); return 0; } diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 96fc70225e54..6b80cd1e419a 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -236,7 +236,7 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, for (fd = ctx->pos - 2; fd < files_fdtable(files)->max_fds; fd++, ctx->pos++) { - char name[PROC_NUMBUF]; + char name[10 + 1]; int len; if (!fcheck_files(files, fd)) diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 793a67574668..5d709fa8f3a2 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -28,7 +28,7 @@ static DEFINE_RWLOCK(proc_subdir_lock); -static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de) +static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len) { if (len < de->namelen) return -1; @@ -60,7 +60,7 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, struct proc_dir_entry *de = rb_entry(node, struct proc_dir_entry, subdir_node); - int result = proc_match(len, name, de); + int result = proc_match(name, de, len); if (result < 0) node = node->rb_left; @@ -84,7 +84,7 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, struct proc_dir_entry *this = rb_entry(*new, struct proc_dir_entry, subdir_node); - int result = proc_match(de->namelen, de->name, this); + int result = proc_match(de->name, this, de->namelen); parent = *new; if (result < 0) @@ -211,8 +211,8 @@ void proc_free_inum(unsigned int inum) * Don't create negative dentries here, return -ENOENT by hand * instead. */ -struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, - struct dentry *dentry) +struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, + struct proc_dir_entry *de) { struct inode *inode; @@ -235,7 +235,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir, struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - return proc_lookup_de(PDE(dir), dir, dentry); + return proc_lookup_de(dir, dentry, PDE(dir)); } /* @@ -247,8 +247,8 @@ struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry, * value of the readdir() call, as long as it's non-negative * for success.. */ -int proc_readdir_de(struct proc_dir_entry *de, struct file *file, - struct dir_context *ctx) +int proc_readdir_de(struct file *file, struct dir_context *ctx, + struct proc_dir_entry *de) { int i; @@ -292,7 +292,7 @@ int proc_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); - return proc_readdir_de(PDE(inode), file, ctx); + return proc_readdir_de(file, ctx, PDE(inode)); } /* diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 8dacaabb9f37..6e8724958116 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -5,6 +5,7 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ +#include <linux/cache.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/kernel.h> @@ -52,7 +53,7 @@ static void proc_evict_inode(struct inode *inode) } } -static struct kmem_cache * proc_inode_cachep; +static struct kmem_cache *proc_inode_cachep __ro_after_init; static struct inode *proc_alloc_inode(struct super_block *sb) { @@ -128,12 +129,12 @@ enum {BIAS = -1U<<31}; static inline int use_pde(struct proc_dir_entry *pde) { - return atomic_inc_unless_negative(&pde->in_use); + return likely(atomic_inc_unless_negative(&pde->in_use)); } static void unuse_pde(struct proc_dir_entry *pde) { - if (atomic_dec_return(&pde->in_use) == BIAS) + if (unlikely(atomic_dec_return(&pde->in_use) == BIAS)) complete(pde->pde_unload_completion); } @@ -166,7 +167,7 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) spin_lock(&pde->pde_unload_lock); /* After ->release. */ list_del(&pdeo->lh); - if (pdeo->c) + if (unlikely(pdeo->c)) complete(pdeo->c); kfree(pdeo); } @@ -420,7 +421,7 @@ static const char *proc_get_link(struct dentry *dentry, struct delayed_call *done) { struct proc_dir_entry *pde = PDE(inode); - if (unlikely(!use_pde(pde))) + if (!use_pde(pde)) return ERR_PTR(-EINVAL); set_delayed_call(done, proc_put_link, pde); return pde->data; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 4a67188c8d74..d697c8ab0a14 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -31,24 +31,28 @@ struct mempolicy; * subdir_node is used to build the rb tree "subdir" of the parent. */ struct proc_dir_entry { + /* + * number of callers into module in progress; + * negative -> it's going away RSN + */ + atomic_t in_use; + atomic_t count; /* use count */ + struct list_head pde_openers; /* who did ->open, but not ->release */ + /* protects ->pde_openers and all struct pde_opener instances */ + spinlock_t pde_unload_lock; + struct completion *pde_unload_completion; + const struct inode_operations *proc_iops; + const struct file_operations *proc_fops; + void *data; unsigned int low_ino; - umode_t mode; nlink_t nlink; kuid_t uid; kgid_t gid; loff_t size; - const struct inode_operations *proc_iops; - const struct file_operations *proc_fops; struct proc_dir_entry *parent; struct rb_root_cached subdir; struct rb_node subdir_node; - void *data; - atomic_t count; /* use count */ - atomic_t in_use; /* number of callers into module in progress; */ - /* negative -> it's going away RSN */ - struct completion *pde_unload_completion; - struct list_head pde_openers; /* who did ->open, but not ->release */ - spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ + umode_t mode; u8 namelen; char name[]; } __randomize_layout; @@ -149,10 +153,9 @@ extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, i * generic.c */ extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); -extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *, - struct dentry *); +struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *); extern int proc_readdir(struct file *, struct dir_context *); -extern int proc_readdir_de(struct proc_dir_entry *, struct file *, struct dir_context *); +int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *); static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde) { diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 4bc85cb8be6a..e8a93bc8285d 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -512,23 +512,15 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) return -EFAULT; } else { if (kern_addr_valid(start)) { - unsigned long n; - /* * Using bounce buffer to bypass the * hardened user copy kernel text checks. */ - memcpy(buf, (char *) start, tsz); - n = copy_to_user(buffer, buf, tsz); - /* - * We cannot distinguish between fault on source - * and fault on destination. When this happens - * we clear too and hope it will trigger the - * EFAULT again. - */ - if (n) { - if (clear_user(buffer + tsz - n, - n)) + if (probe_kernel_read(buf, (void *) start, tsz)) { + if (clear_user(buffer, tsz)) + return -EFAULT; + } else { + if (copy_to_user(buffer, buf, tsz)) return -EFAULT; } } else { diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index f0bfb45c3f9f..4f4a2abb225e 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -44,7 +44,7 @@ static __poll_t kmsg_poll(struct file *file, poll_table *wait) { poll_wait(file, &log_wait, wait); if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index a2bf369c923d..68c06ae7888c 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -135,7 +135,7 @@ static struct dentry *proc_tgid_net_lookup(struct inode *dir, de = ERR_PTR(-ENOENT); net = get_proc_task_net(dir); if (net != NULL) { - de = proc_lookup_de(net->proc_net, dir, dentry); + de = proc_lookup_de(dir, dentry, net->proc_net); put_net(net); } return de; @@ -172,7 +172,7 @@ static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx) ret = -EINVAL; net = get_proc_task_net(file_inode(file)); if (net != NULL) { - ret = proc_readdir_de(net->proc_net, file, ctx); + ret = proc_readdir_de(file, ctx, net->proc_net); put_net(net); } return ret; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 63325377621a..c41ab261397d 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -640,7 +640,7 @@ static __poll_t proc_sys_poll(struct file *filp, poll_table *wait) /* sysctl was unregistered */ if (IS_ERR(head)) - return POLLERR | POLLHUP; + return EPOLLERR | EPOLLHUP; if (!table->proc_handler) goto out; @@ -653,7 +653,7 @@ static __poll_t proc_sys_poll(struct file *filp, poll_table *wait) if (event != atomic_read(&table->poll->event)) { filp->private_data = proc_sys_poll_event(table->poll); - ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI; + ret = EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } out: diff --git a/fs/proc/self.c b/fs/proc/self.c index 31326bb23b8b..4d7d061696b3 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> @@ -17,11 +18,11 @@ static const char *proc_self_get_link(struct dentry *dentry, if (!tgid) return ERR_PTR(-ENOENT); - /* 11 for max length of signed int in decimal + NULL term */ - name = kmalloc(12, dentry ? GFP_KERNEL : GFP_ATOMIC); + /* max length of unsigned int in decimal + NULL term */ + name = kmalloc(10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); - sprintf(name, "%d", tgid); + sprintf(name, "%u", tgid); set_delayed_call(done, kfree_link, name); return name; } @@ -30,7 +31,7 @@ static const struct inode_operations proc_self_inode_operations = { .get_link = proc_self_get_link, }; -static unsigned self_inum; +static unsigned self_inum __ro_after_init; int proc_setup_self(struct super_block *s) { diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index b813e3b529f2..9d2efaca499f 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> @@ -18,11 +19,10 @@ static const char *proc_thread_self_get_link(struct dentry *dentry, if (!pid) return ERR_PTR(-ENOENT); - name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, - dentry ? GFP_KERNEL : GFP_ATOMIC); + name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); - sprintf(name, "%d/task/%d", tgid, pid); + sprintf(name, "%u/task/%u", tgid, pid); set_delayed_call(done, kfree_link, name); return name; } @@ -31,7 +31,7 @@ static const struct inode_operations proc_thread_self_inode_operations = { .get_link = proc_thread_self_get_link, }; -static unsigned thread_self_inum; +static unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 885d445afa0d..a45f0af22a60 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -1178,18 +1178,16 @@ fs_initcall(vmcore_init); /* Cleanup function for vmcore module. */ void vmcore_cleanup(void) { - struct list_head *pos, *next; - if (proc_vmcore) { proc_remove(proc_vmcore); proc_vmcore = NULL; } /* clear the vmcore list. */ - list_for_each_safe(pos, next, &vmcore_list) { + while (!list_empty(&vmcore_list)) { struct vmcore *m; - m = list_entry(pos, struct vmcore, list); + m = list_first_entry(&vmcore_list, struct vmcore, list); list_del(&m->list); kfree(m); } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index c8528d587e09..e16fb8f2049e 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -23,7 +23,7 @@ static __poll_t mounts_poll(struct file *file, poll_table *wait) struct seq_file *m = file->private_data; struct proc_mounts *p = m->private; struct mnt_namespace *ns = p->ns; - __poll_t res = POLLIN | POLLRDNORM; + __poll_t res = EPOLLIN | EPOLLRDNORM; int event; poll_wait(file, &p->ns->poll, wait); @@ -31,7 +31,7 @@ static __poll_t mounts_poll(struct file *file, poll_table *wait) event = READ_ONCE(ns->event); if (m->poll_event != event) { m->poll_event = event; - res |= POLLERR | POLLPRI; + res |= EPOLLERR | EPOLLPRI; } return res; diff --git a/fs/select.c b/fs/select.c index ec14171dd78a..b6c36254028a 100644 --- a/fs/select.c +++ b/fs/select.c @@ -432,9 +432,9 @@ get_max: return max; } -#define POLLIN_SET (POLLRDNORM | POLLRDBAND | POLLIN | POLLHUP | POLLERR) -#define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR) -#define POLLEX_SET (POLLPRI) +#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR) +#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR) +#define POLLEX_SET (EPOLLPRI) static inline void wait_key_set(poll_table *wait, unsigned long in, unsigned long out, unsigned long bit, @@ -814,11 +814,11 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, fd = pollfd->fd; if (fd >= 0) { struct fd f = fdget(fd); - mask = POLLNVAL; + mask = EPOLLNVAL; if (f.file) { /* userland u16 ->events contains POLL... bitmap */ __poll_t filter = demangle_poll(pollfd->events) | - POLLERR | POLLHUP; + EPOLLERR | EPOLLHUP; mask = DEFAULT_POLLMASK; if (f.file->f_op->poll) { pwait->_key = filter; diff --git a/fs/seq_file.c b/fs/seq_file.c index 4be761c1a03d..eea09f6d8830 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -181,8 +181,11 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) * if request is to read from zero offset, reset iterator to first * record as it might have been already advanced by previous requests */ - if (*ppos == 0) + if (*ppos == 0) { m->index = 0; + m->version = 0; + m->count = 0; + } /* Don't assume *ppos is where we left it */ if (unlikely(*ppos != m->read_pos)) { diff --git a/fs/signalfd.c b/fs/signalfd.c index 31e923bec99a..9990957264e3 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -45,7 +45,7 @@ void signalfd_cleanup(struct sighand_struct *sighand) return; /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */ - wake_up_poll(wqh, POLLHUP | POLLFREE); + wake_up_poll(wqh, EPOLLHUP | POLLFREE); } struct signalfd_ctx { @@ -69,7 +69,7 @@ static __poll_t signalfd_poll(struct file *file, poll_table *wait) if (next_signal(¤t->pending, &ctx->sigmask) || next_signal(¤t->signal->shared_pending, &ctx->sigmask)) - events |= POLLIN; + events |= EPOLLIN; spin_unlock_irq(¤t->sighand->siglock); return events; diff --git a/fs/timerfd.c b/fs/timerfd.c index 0510717f3a53..cdad49da3ff7 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -237,7 +237,7 @@ static __poll_t timerfd_poll(struct file *file, poll_table *wait) spin_lock_irqsave(&ctx->wqh.lock, flags); if (ctx->ticks) - events |= POLLIN; + events |= EPOLLIN; spin_unlock_irqrestore(&ctx->wqh.lock, flags); return events; diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c index 14626b34d13e..0927a4b2ecaf 100644 --- a/fs/udf/udftime.c +++ b/fs/udf/udftime.c @@ -62,6 +62,11 @@ udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) dest->tv_sec -= offset * 60; dest->tv_nsec = 1000 * (src.centiseconds * 10000 + src.hundredsOfMicroseconds * 100 + src.microseconds); + /* + * Sanitize nanosecond field since reportedly some filesystems are + * recorded with bogus sub-second values. + */ + dest->tv_nsec %= NSEC_PER_SEC; return dest; } diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 50dfce000864..b721d0bda5e5 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -429,7 +429,7 @@ ufs_readdir(struct file *file, struct dir_context *ctx) unsigned long n = pos >> PAGE_SHIFT; unsigned long npages = dir_pages(inode); unsigned chunk_mask = ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1); - bool need_revalidate = inode_cmp_iversion(inode, file->f_version); + bool need_revalidate = !inode_eq_iversion(inode, file->f_version); unsigned flags = UFS_SB(sb)->s_flags; UFSD("BEGIN\n"); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 87a13a7c8270..cec550c8468f 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -483,7 +483,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) if (likely(must_wait && !READ_ONCE(ctx->released) && (return_to_userland ? !signal_pending(current) : !fatal_signal_pending(current)))) { - wake_up_poll(&ctx->fd_wqh, POLLIN); + wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); ret |= VM_FAULT_MAJOR; @@ -614,7 +614,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, spin_unlock(&ctx->event_wqh.lock); - wake_up_poll(&ctx->fd_wqh, POLLIN); + wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); spin_lock(&ctx->event_wqh.lock); @@ -904,7 +904,7 @@ wakeup: /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); - wake_up_poll(&ctx->fd_wqh, POLLHUP); + wake_up_poll(&ctx->fd_wqh, EPOLLHUP); userfaultfd_ctx_put(ctx); return 0; } @@ -949,14 +949,14 @@ static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) switch (ctx->state) { case UFFD_STATE_WAIT_API: - return POLLERR; + return EPOLLERR; case UFFD_STATE_RUNNING: /* * poll() never guarantees that read won't block. * userfaults can be waken before they're read(). */ if (unlikely(!(file->f_flags & O_NONBLOCK))) - return POLLERR; + return EPOLLERR; /* * lockless access to see if there are pending faults * __pollwait last action is the add_wait_queue but @@ -970,14 +970,14 @@ static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) ret = 0; smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) - ret = POLLIN; + ret = EPOLLIN; else if (waitqueue_active(&ctx->event_wqh)) - ret = POLLIN; + ret = EPOLLIN; return ret; default: WARN_ON_ONCE(1); - return POLLERR; + return EPOLLERR; } } diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index c77b91ff1149..f2eac81bfbd2 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index ffe364fa4040..1adcda4bfb54 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index 3c46f0ef5f7a..bb3e746dad34 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h index d8dd3bf51ca7..d497b9bcd84e 100644 --- a/include/acpi/acnames.h +++ b/include/acpi/acnames.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index c2e664e74075..6eceb69cffc4 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h index 0887d7cbb7e1..fae98927052f 100644 --- a/include/acpi/acpi.h +++ b/include/acpi/acpi.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index d5c0f5153c4e..d6345e9870a1 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -7,7 +7,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index c589c3e12d90..c2bf1255f5aa 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -46,7 +46,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20171215 +#define ACPI_CA_VERSION 0x20180105 #include <acpi/acconfig.h> #include <acpi/actypes.h> diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h index 343dbdcef20c..1becc88da82f 100644 --- a/include/acpi/acrestyp.h +++ b/include/acpi/acrestyp.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h index 89509b86cb54..17c4d1fdc88d 100644 --- a/include/acpi/actbl.h +++ b/include/acpi/actbl.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 4c304bf4d591..a398d5938f34 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 0d60d5df14f8..366a491f2af0 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h index 5bde2e700530..ebad40eda9b7 100644 --- a/include/acpi/actbl3.h +++ b/include/acpi/actbl3.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 31f1be74dd16..310b542abe23 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -485,7 +485,7 @@ typedef u8 acpi_owner_id; /* * Constants with special meanings */ -#define ACPI_ROOT_OBJECT ACPI_ADD_PTR (acpi_handle, NULL, ACPI_MAX_PTR) +#define ACPI_ROOT_OBJECT ((acpi_handle) ACPI_TO_POINTER (ACPI_MAX_PTR)) #define ACPI_WAIT_FOREVER 0xFFFF /* u16, as per ACPI spec */ #define ACPI_DO_NOT_WAIT 0 @@ -532,13 +532,13 @@ typedef u64 acpi_integer; #define ACPI_CAST_INDIRECT_PTR(t, p) ((t **) (acpi_uintptr_t) (p)) #define ACPI_ADD_PTR(t, a, b) ACPI_CAST_PTR (t, (ACPI_CAST_PTR (u8, (a)) + (acpi_size)(b))) #define ACPI_SUB_PTR(t, a, b) ACPI_CAST_PTR (t, (ACPI_CAST_PTR (u8, (a)) - (acpi_size)(b))) -#define ACPI_PTR_DIFF(a, b) (acpi_size) (ACPI_CAST_PTR (u8, (a)) - ACPI_CAST_PTR (u8, (b))) +#define ACPI_PTR_DIFF(a, b) ((acpi_size) (ACPI_CAST_PTR (u8, (a)) - ACPI_CAST_PTR (u8, (b)))) /* Pointer/Integer type conversions */ -#define ACPI_TO_POINTER(i) ACPI_ADD_PTR (void, (void *) NULL,(acpi_size) i) -#define ACPI_TO_INTEGER(p) ACPI_PTR_DIFF (p, (void *) NULL) -#define ACPI_OFFSET(d, f) ACPI_PTR_DIFF (&(((d *) 0)->f), (void *) NULL) +#define ACPI_TO_POINTER(i) ACPI_ADD_PTR (void, (void *) 0, (acpi_size) (i)) +#define ACPI_TO_INTEGER(p) ACPI_PTR_DIFF (p, (void *) 0) +#define ACPI_OFFSET(d, f) ACPI_PTR_DIFF (&(((d *) 0)->f), (void *) 0) #define ACPI_PHYSADDR_TO_PTR(i) ACPI_TO_POINTER(i) #define ACPI_PTR_TO_PHYSADDR(i) ACPI_TO_INTEGER(i) diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h index b1a0a8a64c3d..f0ba9bca2b12 100644 --- a/include/acpi/acuuid.h +++ b/include/acpi/acuuid.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h index 043fd559de6e..c33ec562b585 100644 --- a/include/acpi/platform/acenv.h +++ b/include/acpi/platform/acenv.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h index 127c848a1ba7..c4b1b110aeb9 100644 --- a/include/acpi/platform/acenvex.h +++ b/include/acpi/platform/acenvex.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h index 9c8f8b79644e..666256f6c97d 100644 --- a/include/acpi/platform/acgcc.h +++ b/include/acpi/platform/acgcc.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/acgccex.h b/include/acpi/platform/acgccex.h index 4f701b288cec..e7baa58b0e31 100644 --- a/include/acpi/platform/acgccex.h +++ b/include/acpi/platform/acgccex.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h index bdb6858e2458..f0c5be8ba4d5 100644 --- a/include/acpi/platform/acintel.h +++ b/include/acpi/platform/acintel.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 1b473efd9eb6..adee92c38c43 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -206,7 +206,7 @@ #define ACPI_FLUSH_CPU_CACHE() #define ACPI_CAST_PTHREAD_T(pthread) ((acpi_thread_id) (pthread)) -#if defined(__ia64__) || defined(__x86_64__) ||\ +#if defined(__ia64__) || (defined(__x86_64__) && !defined(__ILP32__)) ||\ defined(__aarch64__) || defined(__PPC64__) ||\ defined(__s390x__) #define ACPI_MACHINE_WIDTH 64 diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index efdff527f8fc..b066d75a9359 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/include/asm-generic/audit_dir_write.h b/include/asm-generic/audit_dir_write.h index da09fb986459..dd5a9dd7a102 100644 --- a/include/asm-generic/audit_dir_write.h +++ b/include/asm-generic/audit_dir_write.h @@ -27,7 +27,9 @@ __NR_mknod, __NR_mkdirat, __NR_mknodat, __NR_unlinkat, +#ifdef __NR_renameat __NR_renameat, +#endif __NR_linkat, __NR_symlinkat, #endif diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h index 1ba611e16fa0..8a1ee10014de 100644 --- a/include/asm-generic/bitops/find.h +++ b/include/asm-generic/bitops/find.h @@ -16,6 +16,22 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset); #endif +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +extern unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset); +#endif + #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region @@ -55,8 +71,12 @@ extern unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size); #else /* CONFIG_GENERIC_FIND_FIRST_BIT */ +#ifndef find_first_bit #define find_first_bit(addr, size) find_next_bit((addr), (size), 0) +#endif +#ifndef find_first_zero_bit #define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) +#endif #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h index 137ecdd16daa..c36f1d5a2572 100644 --- a/include/asm-generic/qrwlock_types.h +++ b/include/asm-generic/qrwlock_types.h @@ -3,6 +3,7 @@ #define __ASM_GENERIC_QRWLOCK_TYPES_H #include <linux/types.h> +#include <asm/byteorder.h> #include <asm/spinlock_types.h> /* diff --git a/include/dt-bindings/clock/jz4770-cgu.h b/include/dt-bindings/clock/jz4770-cgu.h new file mode 100644 index 000000000000..d68a7695a1f8 --- /dev/null +++ b/include/dt-bindings/clock/jz4770-cgu.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This header provides clock numbers for the ingenic,jz4770-cgu DT binding. + */ + +#ifndef __DT_BINDINGS_CLOCK_JZ4770_CGU_H__ +#define __DT_BINDINGS_CLOCK_JZ4770_CGU_H__ + +#define JZ4770_CLK_EXT 0 +#define JZ4770_CLK_OSC32K 1 +#define JZ4770_CLK_PLL0 2 +#define JZ4770_CLK_PLL1 3 +#define JZ4770_CLK_CCLK 4 +#define JZ4770_CLK_H0CLK 5 +#define JZ4770_CLK_H1CLK 6 +#define JZ4770_CLK_H2CLK 7 +#define JZ4770_CLK_C1CLK 8 +#define JZ4770_CLK_PCLK 9 +#define JZ4770_CLK_MMC0_MUX 10 +#define JZ4770_CLK_MMC0 11 +#define JZ4770_CLK_MMC1_MUX 12 +#define JZ4770_CLK_MMC1 13 +#define JZ4770_CLK_MMC2_MUX 14 +#define JZ4770_CLK_MMC2 15 +#define JZ4770_CLK_CIM 16 +#define JZ4770_CLK_UHC 17 +#define JZ4770_CLK_GPU 18 +#define JZ4770_CLK_BCH 19 +#define JZ4770_CLK_LPCLK_MUX 20 +#define JZ4770_CLK_GPS 21 +#define JZ4770_CLK_SSI_MUX 22 +#define JZ4770_CLK_PCM_MUX 23 +#define JZ4770_CLK_I2S 24 +#define JZ4770_CLK_OTG 25 +#define JZ4770_CLK_SSI0 26 +#define JZ4770_CLK_SSI1 27 +#define JZ4770_CLK_SSI2 28 +#define JZ4770_CLK_PCM0 29 +#define JZ4770_CLK_PCM1 30 +#define JZ4770_CLK_DMA 31 +#define JZ4770_CLK_I2C0 32 +#define JZ4770_CLK_I2C1 33 +#define JZ4770_CLK_I2C2 34 +#define JZ4770_CLK_UART0 35 +#define JZ4770_CLK_UART1 36 +#define JZ4770_CLK_UART2 37 +#define JZ4770_CLK_UART3 38 +#define JZ4770_CLK_IPU 39 +#define JZ4770_CLK_ADC 40 +#define JZ4770_CLK_AIC 41 +#define JZ4770_CLK_AUX 42 +#define JZ4770_CLK_VPU 43 +#define JZ4770_CLK_UHC_PHY 44 +#define JZ4770_CLK_OTG_PHY 45 +#define JZ4770_CLK_EXT512 46 +#define JZ4770_CLK_RTC 47 + +#endif /* __DT_BINDINGS_CLOCK_JZ4770_CGU_H__ */ diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 9da6ce22803f..6502feb9524b 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -90,6 +90,8 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu); void kvm_timer_init_vhe(void); +bool kvm_arch_timer_get_input_level(int vintid); + #define vcpu_vtimer(v) (&(v)->arch.timer_cpu.vtimer) #define vcpu_ptimer(v) (&(v)->arch.timer_cpu.ptimer) diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h new file mode 100644 index 000000000000..e518e4e3dfb5 --- /dev/null +++ b/include/kvm/arm_psci.h @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __KVM_ARM_PSCI_H__ +#define __KVM_ARM_PSCI_H__ + +#include <linux/kvm_host.h> +#include <uapi/linux/psci.h> + +#define KVM_ARM_PSCI_0_1 PSCI_VERSION(0, 1) +#define KVM_ARM_PSCI_0_2 PSCI_VERSION(0, 2) +#define KVM_ARM_PSCI_1_0 PSCI_VERSION(1, 0) + +#define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_0 + +/* + * We need the KVM pointer independently from the vcpu as we can call + * this from HYP, and need to apply kern_hyp_va on it... + */ +static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm) +{ + /* + * Our PSCI implementation stays the same across versions from + * v0.2 onward, only adding the few mandatory functions (such + * as FEATURES with 1.0) that are required by newer + * revisions. It is thus safe to return the latest. + */ + if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) + return KVM_ARM_PSCI_LATEST; + + return KVM_ARM_PSCI_0_1; +} + + +int kvm_hvc_call_handler(struct kvm_vcpu *vcpu); + +#endif /* __KVM_ARM_PSCI_H__ */ diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 8c896540a72c..cdbd142ca7f2 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -130,6 +130,17 @@ struct vgic_irq { u8 priority; enum vgic_irq_config config; /* Level or edge */ + /* + * Callback function pointer to in-kernel devices that can tell us the + * state of the input level of mapped level-triggered IRQ faster than + * peaking into the physical GIC. + * + * Always called in non-preemptible section and the functions can use + * kvm_arm_get_running_vcpu() to get the vcpu pointer for private + * IRQs. + */ + bool (*get_input_level)(int vintid); + void *owner; /* Opaque pointer to reserve an interrupt for in-kernel devices. */ }; @@ -331,7 +342,7 @@ void kvm_vgic_init_cpu_hardware(void); int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, bool level, void *owner); int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, - u32 vintid); + u32 vintid, bool (*get_input_level)(int vindid)); int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid); bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e6d41b65d396..64e10746f282 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1263,9 +1263,12 @@ static inline bool acpi_has_watchdog(void) { return false; } #ifdef CONFIG_ACPI_SPCR_TABLE extern bool qdf2400_e44_present; -int parse_spcr(bool earlycon); +int acpi_parse_spcr(bool enable_earlycon, bool enable_console); #else -static inline int parse_spcr(bool earlycon) { return 0; } +static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) +{ + return 0; +} #endif #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 4c5bca38c653..a031897fca76 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -14,14 +14,16 @@ #ifndef __LINUX_ARM_SMCCC_H #define __LINUX_ARM_SMCCC_H +#include <uapi/linux/const.h> + /* * This file provides common defines for ARM SMC Calling Convention as * specified in * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html */ -#define ARM_SMCCC_STD_CALL 0 -#define ARM_SMCCC_FAST_CALL 1 +#define ARM_SMCCC_STD_CALL _AC(0,U) +#define ARM_SMCCC_FAST_CALL _AC(1,U) #define ARM_SMCCC_TYPE_SHIFT 31 #define ARM_SMCCC_SMC_32 0 @@ -60,6 +62,24 @@ #define ARM_SMCCC_QUIRK_NONE 0 #define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */ +#define ARM_SMCCC_VERSION_1_0 0x10000 +#define ARM_SMCCC_VERSION_1_1 0x10001 + +#define ARM_SMCCC_VERSION_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0) + +#define ARM_SMCCC_ARCH_FEATURES_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 1) + +#define ARM_SMCCC_ARCH_WORKAROUND_1 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x8000) + #ifndef __ASSEMBLY__ #include <linux/linkage.h> @@ -130,5 +150,146 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define arm_smccc_hvc_quirk(...) __arm_smccc_hvc(__VA_ARGS__) +/* SMCCC v1.1 implementation madness follows */ +#ifdef CONFIG_ARM64 + +#define SMCCC_SMC_INST "smc #0" +#define SMCCC_HVC_INST "hvc #0" + +#elif defined(CONFIG_ARM) +#include <asm/opcodes-sec.h> +#include <asm/opcodes-virt.h> + +#define SMCCC_SMC_INST __SMC(0) +#define SMCCC_HVC_INST __HVC(0) + +#endif + +#define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x + +#define __count_args(...) \ + ___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0) + +#define __constraint_write_0 \ + "+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3) +#define __constraint_write_1 \ + "+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3) +#define __constraint_write_2 \ + "+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3) +#define __constraint_write_3 \ + "+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3) +#define __constraint_write_4 __constraint_write_3 +#define __constraint_write_5 __constraint_write_4 +#define __constraint_write_6 __constraint_write_5 +#define __constraint_write_7 __constraint_write_6 + +#define __constraint_read_0 +#define __constraint_read_1 +#define __constraint_read_2 +#define __constraint_read_3 +#define __constraint_read_4 "r" (r4) +#define __constraint_read_5 __constraint_read_4, "r" (r5) +#define __constraint_read_6 __constraint_read_5, "r" (r6) +#define __constraint_read_7 __constraint_read_6, "r" (r7) + +#define __declare_arg_0(a0, res) \ + struct arm_smccc_res *___res = res; \ + register u32 r0 asm("r0") = a0; \ + register unsigned long r1 asm("r1"); \ + register unsigned long r2 asm("r2"); \ + register unsigned long r3 asm("r3") + +#define __declare_arg_1(a0, a1, res) \ + struct arm_smccc_res *___res = res; \ + register u32 r0 asm("r0") = a0; \ + register typeof(a1) r1 asm("r1") = a1; \ + register unsigned long r2 asm("r2"); \ + register unsigned long r3 asm("r3") + +#define __declare_arg_2(a0, a1, a2, res) \ + struct arm_smccc_res *___res = res; \ + register u32 r0 asm("r0") = a0; \ + register typeof(a1) r1 asm("r1") = a1; \ + register typeof(a2) r2 asm("r2") = a2; \ + register unsigned long r3 asm("r3") + +#define __declare_arg_3(a0, a1, a2, a3, res) \ + struct arm_smccc_res *___res = res; \ + register u32 r0 asm("r0") = a0; \ + register typeof(a1) r1 asm("r1") = a1; \ + register typeof(a2) r2 asm("r2") = a2; \ + register typeof(a3) r3 asm("r3") = a3 + +#define __declare_arg_4(a0, a1, a2, a3, a4, res) \ + __declare_arg_3(a0, a1, a2, a3, res); \ + register typeof(a4) r4 asm("r4") = a4 + +#define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \ + __declare_arg_4(a0, a1, a2, a3, a4, res); \ + register typeof(a5) r5 asm("r5") = a5 + +#define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \ + __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \ + register typeof(a6) r6 asm("r6") = a6 + +#define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \ + __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \ + register typeof(a7) r7 asm("r7") = a7 + +#define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__) +#define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__) + +#define ___constraints(count) \ + : __constraint_write_ ## count \ + : __constraint_read_ ## count \ + : "memory" +#define __constraints(count) ___constraints(count) + +/* + * We have an output list that is not necessarily used, and GCC feels + * entitled to optimise the whole sequence away. "volatile" is what + * makes it stick. + */ +#define __arm_smccc_1_1(inst, ...) \ + do { \ + __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ + asm volatile(inst "\n" \ + __constraints(__count_args(__VA_ARGS__))); \ + if (___res) \ + *___res = (typeof(*___res)){r0, r1, r2, r3}; \ + } while (0) + +/* + * arm_smccc_1_1_smc() - make an SMCCC v1.1 compliant SMC call + * + * This is a variadic macro taking one to eight source arguments, and + * an optional return structure. + * + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This macro is used to make SMC calls following SMC Calling Convention v1.1. + * The content of the supplied param are copied to registers 0 to 7 prior + * to the SMC instruction. The return values are updated with the content + * from register 0 to 3 on return from the SMC instruction if not NULL. + */ +#define arm_smccc_1_1_smc(...) __arm_smccc_1_1(SMCCC_SMC_INST, __VA_ARGS__) + +/* + * arm_smccc_1_1_hvc() - make an SMCCC v1.1 compliant HVC call + * + * This is a variadic macro taking one to eight source arguments, and + * an optional return structure. + * + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This macro is used to make HVC calls following SMC Calling Convention v1.1. + * The content of the supplied param are copied to registers 0 to 7 prior + * to the HVC instruction. The return values are updated with the content + * from register 0 to 3 on return from the HVC instruction if not NULL. + */ +#define arm_smccc_1_1_hvc(...) __arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__) + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 3489253e38fc..5f11fbdc27f8 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -64,9 +64,14 @@ * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region - * bitmap_from_u32array(dst, nbits, buf, nwords) *dst = *buf (nwords 32b words) - * bitmap_to_u32array(buf, nwords, src, nbits) *buf = *dst (nwords 32b words) + * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst + * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst * + * Note, bitmap_zero() and bitmap_fill() operate over the region of + * unsigned longs, that is, bits behind bitmap till the unsigned long + * boundary will be zeroed or filled as well. Consider to use + * bitmap_clear() or bitmap_set() to make explicit zeroing or filling + * respectively. */ /** @@ -83,8 +88,12 @@ * test_and_change_bit(bit, addr) Change bit and return old value * find_first_zero_bit(addr, nbits) Position first zero bit in *addr * find_first_bit(addr, nbits) Position first set bit in *addr - * find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit + * find_next_zero_bit(addr, nbits, bit) + * Position next zero bit in *addr >= bit * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit + * find_next_and_bit(addr1, addr2, nbits, bit) + * Same as find_next_bit, but in + * (*addr1 & *addr2) * */ @@ -174,14 +183,7 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); -extern unsigned int bitmap_from_u32array(unsigned long *bitmap, - unsigned int nbits, - const u32 *buf, - unsigned int nwords); -extern unsigned int bitmap_to_u32array(u32 *buf, - unsigned int nwords, - const unsigned long *bitmap, - unsigned int nbits); + #ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else @@ -209,12 +211,12 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int nlongs = BITS_TO_LONGS(nbits); - if (!small_const_nbits(nbits)) { - unsigned int len = (nlongs - 1) * sizeof(unsigned long); - memset(dst, 0xff, len); + if (small_const_nbits(nbits)) + *dst = ~0UL; + else { + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0xff, len); } - dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, @@ -228,6 +230,35 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, } } +/* + * Copy bitmap and clear tail bits in last word. + */ +static inline void bitmap_copy_clear_tail(unsigned long *dst, + const unsigned long *src, unsigned int nbits) +{ + bitmap_copy(dst, src, nbits); + if (nbits % BITS_PER_LONG) + dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); +} + +/* + * On 32-bit systems bitmaps are represented as u32 arrays internally, and + * therefore conversion is not needed when copying data from/to arrays of u32. + */ +#if BITS_PER_LONG == 64 +extern void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, + unsigned int nbits); +extern void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, + unsigned int nbits); +#else +#define bitmap_from_arr32(bitmap, buf, nbits) \ + bitmap_copy_clear_tail((unsigned long *) (bitmap), \ + (const unsigned long *) (buf), (nbits)) +#define bitmap_to_arr32(buf, bitmap, nbits) \ + bitmap_copy_clear_tail((unsigned long *) (buf), \ + (const unsigned long *) (bitmap), (nbits)) +#endif + static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 3efed0d742a0..43d1fd50d433 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -8,7 +8,6 @@ #define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) #define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) #define BUILD_BUG_ON_ZERO(e) (0) -#define BUILD_BUG_ON_NULL(e) ((void *)0) #define BUILD_BUG_ON_INVALID(e) (0) #define BUILD_BUG_ON_MSG(cond, msg) (0) #define BUILD_BUG_ON(condition) (0) @@ -28,7 +27,6 @@ * aren't permitted). */ #define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) -#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); })) /* * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 3b609edffa8f..d02a4df3f473 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -19,3 +19,11 @@ #define randomized_struct_fields_start struct { #define randomized_struct_fields_end }; + +/* all clang versions usable with the kernel support KASAN ABI version 5 */ +#define KASAN_ABI_VERSION 5 + +/* emulate gcc's __SANITIZE_ADDRESS__ flag */ +#if __has_feature(address_sanitizer) +#define __SANITIZE_ADDRESS__ +#endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 631354acfa72..73bc63e0a1c4 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -167,8 +167,6 @@ #if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) - -#define __nostackprotector __attribute__((__optimize__("no-stack-protector"))) #endif #if GCC_VERSION >= 40300 @@ -196,6 +194,11 @@ #endif /* __CHECKER__ */ #endif /* GCC_VERSION >= 40300 */ +#if GCC_VERSION >= 40400 +#define __optimize(level) __attribute__((__optimize__(level))) +#define __nostackprotector __optimize("no-stack-protector") +#endif /* GCC_VERSION >= 40400 */ + #if GCC_VERSION >= 40500 #ifndef __CHECKER__ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c2cc57a2f508..e835fc0423ec 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -277,6 +277,10 @@ unsigned long read_word_at_a_time(const void *addr) #endif /* __ASSEMBLY__ */ +#ifndef __optimize +# define __optimize(level) +#endif + /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 065f3a8eb486..21e8d248d956 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -629,6 +629,18 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, for (pos = table; pos->frequency != CPUFREQ_TABLE_END; pos++) /* + * cpufreq_for_each_entry_idx - iterate over a cpufreq_frequency_table + * with index + * @pos: the cpufreq_frequency_table * to use as a loop cursor. + * @table: the cpufreq_frequency_table * to iterate over. + * @idx: the table entry currently being processed + */ + +#define cpufreq_for_each_entry_idx(pos, table, idx) \ + for (pos = table, idx = 0; pos->frequency != CPUFREQ_TABLE_END; \ + pos++, idx++) + +/* * cpufreq_for_each_valid_entry - iterate over a cpufreq_frequency_table * excluding CPUFREQ_ENTRY_INVALID frequencies. * @pos: the cpufreq_frequency_table * to use as a loop cursor. @@ -641,6 +653,21 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, continue; \ else +/* + * cpufreq_for_each_valid_entry_idx - iterate with index over a cpufreq + * frequency_table excluding CPUFREQ_ENTRY_INVALID frequencies. + * @pos: the cpufreq_frequency_table * to use as a loop cursor. + * @table: the cpufreq_frequency_table * to iterate over. + * @idx: the table entry currently being processed + */ + +#define cpufreq_for_each_valid_entry_idx(pos, table, idx) \ + cpufreq_for_each_entry_idx(pos, table, idx) \ + if (pos->frequency == CPUFREQ_ENTRY_INVALID) \ + continue; \ + else + + int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); @@ -667,19 +694,20 @@ static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy, unsigned int target_freq) { struct cpufreq_frequency_table *table = policy->freq_table; - struct cpufreq_frequency_table *pos, *best = table - 1; + struct cpufreq_frequency_table *pos; unsigned int freq; + int idx, best = -1; - cpufreq_for_each_valid_entry(pos, table) { + cpufreq_for_each_valid_entry_idx(pos, table, idx) { freq = pos->frequency; if (freq >= target_freq) - return pos - table; + return idx; - best = pos; + best = idx; } - return best - table; + return best; } /* Find lowest freq at or above target in a table in descending order */ @@ -687,28 +715,29 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy, unsigned int target_freq) { struct cpufreq_frequency_table *table = policy->freq_table; - struct cpufreq_frequency_table *pos, *best = table - 1; + struct cpufreq_frequency_table *pos; unsigned int freq; + int idx, best = -1; - cpufreq_for_each_valid_entry(pos, table) { + cpufreq_for_each_valid_entry_idx(pos, table, idx) { freq = pos->frequency; if (freq == target_freq) - return pos - table; + return idx; if (freq > target_freq) { - best = pos; + best = idx; continue; } /* No freq found above target_freq */ - if (best == table - 1) - return pos - table; + if (best == -1) + return idx; - return best - table; + return best; } - return best - table; + return best; } /* Works only on sorted freq-tables */ @@ -728,28 +757,29 @@ static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy, unsigned int target_freq) { struct cpufreq_frequency_table *table = policy->freq_table; - struct cpufreq_frequency_table *pos, *best = table - 1; + struct cpufreq_frequency_table *pos; unsigned int freq; + int idx, best = -1; - cpufreq_for_each_valid_entry(pos, table) { + cpufreq_for_each_valid_entry_idx(pos, table, idx) { freq = pos->frequency; if (freq == target_freq) - return pos - table; + return idx; if (freq < target_freq) { - best = pos; + best = idx; continue; } /* No freq found below target_freq */ - if (best == table - 1) - return pos - table; + if (best == -1) + return idx; - return best - table; + return best; } - return best - table; + return best; } /* Find highest freq at or below target in a table in descending order */ @@ -757,19 +787,20 @@ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy, unsigned int target_freq) { struct cpufreq_frequency_table *table = policy->freq_table; - struct cpufreq_frequency_table *pos, *best = table - 1; + struct cpufreq_frequency_table *pos; unsigned int freq; + int idx, best = -1; - cpufreq_for_each_valid_entry(pos, table) { + cpufreq_for_each_valid_entry_idx(pos, table, idx) { freq = pos->frequency; if (freq <= target_freq) - return pos - table; + return idx; - best = pos; + best = idx; } - return best - table; + return best; } /* Works only on sorted freq-tables */ @@ -789,32 +820,33 @@ static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy, unsigned int target_freq) { struct cpufreq_frequency_table *table = policy->freq_table; - struct cpufreq_frequency_table *pos, *best = table - 1; + struct cpufreq_frequency_table *pos; unsigned int freq; + int idx, best = -1; - cpufreq_for_each_valid_entry(pos, table) { + cpufreq_for_each_valid_entry_idx(pos, table, idx) { freq = pos->frequency; if (freq == target_freq) - return pos - table; + return idx; if (freq < target_freq) { - best = pos; + best = idx; continue; } /* No freq found below target_freq */ - if (best == table - 1) - return pos - table; + if (best == -1) + return idx; /* Choose the closest freq */ - if (target_freq - best->frequency > freq - target_freq) - return pos - table; + if (target_freq - table[best].frequency > freq - target_freq) + return idx; - return best - table; + return best; } - return best - table; + return best; } /* Find closest freq to target in a table in descending order */ @@ -822,32 +854,33 @@ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy, unsigned int target_freq) { struct cpufreq_frequency_table *table = policy->freq_table; - struct cpufreq_frequency_table *pos, *best = table - 1; + struct cpufreq_frequency_table *pos; unsigned int freq; + int idx, best = -1; - cpufreq_for_each_valid_entry(pos, table) { + cpufreq_for_each_valid_entry_idx(pos, table, idx) { freq = pos->frequency; if (freq == target_freq) - return pos - table; + return idx; if (freq > target_freq) { - best = pos; + best = idx; continue; } /* No freq found above target_freq */ - if (best == table - 1) - return pos - table; + if (best == -1) + return idx; /* Choose the closest freq */ - if (best->frequency - target_freq > target_freq - freq) - return pos - table; + if (table[best].frequency - target_freq > target_freq - freq) + return idx; - return best - table; + return best; } - return best - table; + return best; } /* Works only on sorted freq-tables */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 75b565194437..d4a2a7dcd72d 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -640,7 +640,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) /** * cpumask_size - size to allocate for a 'struct cpumask' in bytes */ -static inline size_t cpumask_size(void) +static inline unsigned int cpumask_size(void) { return BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long); } diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 1b8e41597ef5..934633a05d20 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -112,7 +112,7 @@ static inline int cpuset_do_slab_mem_spread(void) return task_spread_slab(current); } -extern int current_cpuset_is_being_rebound(void); +extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); @@ -247,9 +247,9 @@ static inline int cpuset_do_slab_mem_spread(void) return 0; } -static inline int current_cpuset_is_being_rebound(void) +static inline bool current_cpuset_is_being_rebound(void) { - return 0; + return false; } static inline void rebuild_sched_domains(void) diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index a992e6ca2f1c..f7ac2aa93269 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -2,13 +2,13 @@ #ifndef LINUX_CRASH_DUMP_H #define LINUX_CRASH_DUMP_H -#ifdef CONFIG_CRASH_DUMP #include <linux/kexec.h> #include <linux/proc_fs.h> #include <linux/elf.h> #include <asm/pgtable.h> /* for pgprot_t */ +#ifdef CONFIG_CRASH_DUMP #define ELFCORE_ADDR_MAX (-1ULL) #define ELFCORE_ADDR_ERR (-2ULL) @@ -52,13 +52,13 @@ void vmcore_cleanup(void); * has passed the elf core header address on command line. * * This is not just a test if CONFIG_CRASH_DUMP is enabled or not. It will - * return 1 if CONFIG_CRASH_DUMP=y and if kernel is booting after a panic of - * previous kernel. + * return true if CONFIG_CRASH_DUMP=y and if kernel is booting after a panic + * of previous kernel. */ -static inline int is_kdump_kernel(void) +static inline bool is_kdump_kernel(void) { - return (elfcorehdr_addr != ELFCORE_ADDR_MAX) ? 1 : 0; + return elfcorehdr_addr != ELFCORE_ADDR_MAX; } /* is_vmcore_usable() checks if the kernel is booting after a panic and @@ -89,7 +89,7 @@ extern int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)); extern void unregister_oldmem_pfn_is_ram(void); #else /* !CONFIG_CRASH_DUMP */ -static inline int is_kdump_kernel(void) { return 0; } +static inline bool is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ extern unsigned long saved_max_pfn; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 263dbcad22fc..79563840c295 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -31,7 +31,7 @@ #ifdef __KERNEL__ struct device; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); -unsigned char *arch_get_platform_get_mac_address(void); +unsigned char *arch_get_platform_mac_address(void); u32 eth_get_headlen(void *data, unsigned int max_len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; diff --git a/include/linux/fb.h b/include/linux/fb.h index d1e5bed39140..f577d3c89618 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -569,7 +569,10 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { #define fb_memcpy_fromfb sbus_memcpy_fromio #define fb_memcpy_tofb sbus_memcpy_toio -#elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || defined(__avr32__) || defined(__bfin__) || defined(__arm__) +#elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || \ + defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || \ + defined(__avr32__) || defined(__bfin__) || defined(__arm__) || \ + defined(__aarch64__) #define fb_readb __raw_readb #define fb_readw __raw_readw diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 604967609e55..83f81ac53282 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -2,6 +2,7 @@ #ifndef GENL_MAGIC_FUNC_H #define GENL_MAGIC_FUNC_H +#include <linux/build_bug.h> #include <linux/genl_magic_struct.h> /* @@ -132,17 +133,6 @@ static void dprint_array(const char *dir, int nla_type, * use one static buffer for parsing of nested attributes */ static struct nlattr *nested_attr_tb[128]; -#ifndef BUILD_BUG_ON -/* Force a compilation error if condition is true */ -#define BUILD_BUG_ON(condition) ((void)BUILD_BUG_ON_ZERO(condition)) -/* Force a compilation error if condition is true, but also produce a - result (of value 0 and type size_t), so the expression can be used - e.g. in a structure initializer (or where-ever else comma expressions - aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) -#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) -#endif - #undef GENL_struct #define GENL_struct(tag_name, tag_number, s_name, s_fields) \ /* *_from_attrs functions are static, but potentially unused */ \ diff --git a/include/linux/idr.h b/include/linux/idr.h index fa14f834e4ed..7d6a6313f0ab 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -15,10 +15,10 @@ #include <linux/radix-tree.h> #include <linux/gfp.h> #include <linux/percpu.h> -#include <linux/bug.h> struct idr { struct radix_tree_root idr_rt; + unsigned int idr_base; unsigned int idr_next; }; @@ -31,10 +31,26 @@ struct idr { /* Set the IDR flag and the IDR_FREE tag */ #define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT)) -#define IDR_INIT \ -{ \ - .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER) \ +#define IDR_INIT_BASE(base) { \ + .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER), \ + .idr_base = (base), \ + .idr_next = 0, \ } + +/** + * IDR_INIT() - Initialise an IDR. + * + * A freshly-initialised IDR contains no IDs. + */ +#define IDR_INIT IDR_INIT_BASE(0) + +/** + * DEFINE_IDR() - Define a statically-allocated IDR + * @name: Name of IDR + * + * An IDR defined using this macro is ready for use with no additional + * initialisation required. It contains no IDs. + */ #define DEFINE_IDR(name) struct idr name = IDR_INIT /** @@ -82,80 +98,52 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) void idr_preload(gfp_t gfp_mask); -int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index, - unsigned long start, unsigned long end, gfp_t gfp, - bool ext); - -/** - * idr_alloc - allocate an id - * @idr: idr handle - * @ptr: pointer to be associated with the new id - * @start: the minimum id (inclusive) - * @end: the maximum id (exclusive) - * @gfp: memory allocation flags - * - * Allocates an unused ID in the range [start, end). Returns -ENOSPC - * if there are no unused IDs in that range. - * - * Note that @end is treated as max when <= 0. This is to always allow - * using @start + N as @end as long as N is inside integer range. - * - * Simultaneous modifications to the @idr are not allowed and should be - * prevented by the user, usually with a lock. idr_alloc() may be called - * concurrently with read-only accesses to the @idr, such as idr_find() and - * idr_for_each_entry(). - */ -static inline int idr_alloc(struct idr *idr, void *ptr, - int start, int end, gfp_t gfp) -{ - unsigned long id; - int ret; - - if (WARN_ON_ONCE(start < 0)) - return -EINVAL; - - ret = idr_alloc_cmn(idr, ptr, &id, start, end, gfp, false); - - if (ret) - return ret; - - return id; -} - -static inline int idr_alloc_ext(struct idr *idr, void *ptr, - unsigned long *index, - unsigned long start, - unsigned long end, - gfp_t gfp) -{ - return idr_alloc_cmn(idr, ptr, index, start, end, gfp, true); -} - -int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t); +int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t); +int __must_check idr_alloc_u32(struct idr *, void *ptr, u32 *id, + unsigned long max, gfp_t); +int idr_alloc_cyclic(struct idr *, void *ptr, int start, int end, gfp_t); +void *idr_remove(struct idr *, unsigned long id); +void *idr_find(const struct idr *, unsigned long id); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); -void *idr_get_next_ext(struct idr *idr, unsigned long *nextid); -void *idr_replace(struct idr *, void *, int id); -void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id); +void *idr_get_next_ul(struct idr *, unsigned long *nextid); +void *idr_replace(struct idr *, void *, unsigned long id); void idr_destroy(struct idr *); -static inline void *idr_remove_ext(struct idr *idr, unsigned long id) -{ - return radix_tree_delete_item(&idr->idr_rt, id, NULL); -} - -static inline void *idr_remove(struct idr *idr, int id) +/** + * idr_init_base() - Initialise an IDR. + * @idr: IDR handle. + * @base: The base value for the IDR. + * + * This variation of idr_init() creates an IDR which will allocate IDs + * starting at %base. + */ +static inline void idr_init_base(struct idr *idr, int base) { - return idr_remove_ext(idr, id); + INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); + idr->idr_base = base; + idr->idr_next = 0; } +/** + * idr_init() - Initialise an IDR. + * @idr: IDR handle. + * + * Initialise a dynamically allocated IDR. To initialise a + * statically allocated IDR, use DEFINE_IDR(). + */ static inline void idr_init(struct idr *idr) { - INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); - idr->idr_next = 0; + idr_init_base(idr, 0); } +/** + * idr_is_empty() - Are there any IDs allocated? + * @idr: IDR handle. + * + * Return: %true if any IDs have been allocated from this IDR. + */ static inline bool idr_is_empty(const struct idr *idr) { return radix_tree_empty(&idr->idr_rt) && @@ -174,50 +162,38 @@ static inline void idr_preload_end(void) } /** - * idr_find - return pointer for given id - * @idr: idr handle - * @id: lookup key - * - * Return the pointer given the id it has been registered with. A %NULL - * return indicates that @id is not valid or you passed %NULL in - * idr_get_new(). + * idr_for_each_entry() - Iterate over an IDR's elements of a given type. + * @idr: IDR handle. + * @entry: The type * to use as cursor + * @id: Entry ID. * - * This function can be called under rcu_read_lock(), given that the leaf - * pointers lifetimes are correctly managed. + * @entry and @id do not need to be initialized before the loop, and + * after normal termination @entry is left with the value NULL. This + * is convenient for a "not found" value. */ -static inline void *idr_find_ext(const struct idr *idr, unsigned long id) -{ - return radix_tree_lookup(&idr->idr_rt, id); -} - -static inline void *idr_find(const struct idr *idr, int id) -{ - return idr_find_ext(idr, id); -} +#define idr_for_each_entry(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) /** - * idr_for_each_entry - iterate over an idr's elements of a given type - * @idr: idr handle - * @entry: the type * to use as cursor - * @id: id entry's key + * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. + * @idr: IDR handle. + * @entry: The type * to use as cursor. + * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and - * after normal terminatinon @entry is left with the value NULL. This + * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ -#define idr_for_each_entry(idr, entry, id) \ - for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) -#define idr_for_each_entry_ext(idr, entry, id) \ - for (id = 0; ((entry) = idr_get_next_ext(idr, &(id))) != NULL; ++id) +#define idr_for_each_entry_ul(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next_ul(idr, &(id))) != NULL; ++id) /** - * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type - * @idr: idr handle - * @entry: the type * to use as cursor - * @id: id entry's key + * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type + * @idr: IDR handle. + * @entry: The type * to use as a cursor. + * @id: Entry ID. * - * Continue to iterate over list of given type, continuing after - * the current position. + * Continue to iterate over entries, continuing after the current position. */ #define idr_for_each_entry_continue(idr, entry, id) \ for ((entry) = idr_get_next((idr), &(id)); \ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index f3274d9f46a2..8dad3dd26eae 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -83,7 +83,9 @@ /* * Decoding Capability Register */ +#define cap_5lp_support(c) (((c) >> 60) & 1) #define cap_pi_support(c) (((c) >> 59) & 1) +#define cap_fl1gp_support(c) (((c) >> 56) & 1) #define cap_read_drain(c) (((c) >> 55) & 1) #define cap_write_drain(c) (((c) >> 54) & 1) #define cap_max_amask_val(c) (((c) >> 48) & 0x3f) diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 93b4183cf53d..da0ebaec25f0 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -265,7 +265,7 @@ extern struct resource * __devm_request_region(struct device *dev, extern void __devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n); extern int iomem_map_sanity_check(resource_size_t addr, unsigned long size); -extern int iomem_is_exclusive(u64 addr); +extern bool iomem_is_exclusive(u64 addr); extern int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, diff --git a/include/linux/iversion.h b/include/linux/iversion.h index 3d2fd06495ec..be50ef7cedab 100644 --- a/include/linux/iversion.h +++ b/include/linux/iversion.h @@ -45,7 +45,7 @@ * * With this implementation, the value should always appear to observers to * increase over time if the file has changed. It's recommended to use - * inode_cmp_iversion() helper to compare values. + * inode_eq_iversion() helper to compare values. * * Note that some filesystems (e.g. NFS and AFS) just use the field to store * a server-provided value (for the most part). For that reason, those @@ -305,33 +305,33 @@ inode_query_iversion(struct inode *inode) } /** - * inode_cmp_iversion_raw - check whether the raw i_version counter has changed + * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * - * Compare the current raw i_version counter with a previous one. Returns false - * if they are the same or true if they are different. + * Compare the current raw i_version counter with a previous one. Returns true + * if they are the same or false if they are different. */ static inline bool -inode_cmp_iversion_raw(const struct inode *inode, u64 old) +inode_eq_iversion_raw(const struct inode *inode, u64 old) { - return inode_peek_iversion_raw(inode) != old; + return inode_peek_iversion_raw(inode) == old; } /** - * inode_cmp_iversion - check whether the i_version counter has changed + * inode_eq_iversion - check whether the i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * - * Compare an i_version counter with a previous one. Returns false if they are - * the same, and true if they are different. + * Compare an i_version counter with a previous one. Returns true if they are + * the same, and false if they are different. * * Note that we don't need to set the QUERIED flag in this case, as the value * in the inode is not being recorded for later use. */ static inline bool -inode_cmp_iversion(const struct inode *inode, u64 old) +inode_eq_iversion(const struct inode *inode, u64 old) { - return inode_peek_iversion(inode) != old; + return inode_peek_iversion(inode) == old; } #endif diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index e0340ca08d98..b6a29c126cc4 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -393,7 +393,7 @@ extern bool ____wrong_branch_error(void); branch = !arch_static_branch_jump(&(x)->key, true); \ else \ branch = ____wrong_branch_error(); \ - branch; \ + likely(branch); \ }) #define static_branch_unlikely(x) \ @@ -405,7 +405,7 @@ extern bool ____wrong_branch_error(void); branch = arch_static_branch(&(x)->key, false); \ else \ branch = ____wrong_branch_error(); \ - branch; \ + unlikely(branch); \ }) #else /* !HAVE_JUMP_LABEL */ diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index d79d1e7486bd..657a83b943f0 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -167,7 +167,7 @@ static inline int kallsyms_show_value(void) static inline void print_ip_sym(unsigned long ip) { - printk("[<%p>] %pS\n", (void *) ip, (void *) ip); + printk("[<%px>] %pS\n", (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index e3eb834c9a35..adc13474a53b 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -11,8 +11,6 @@ struct task_struct; #ifdef CONFIG_KASAN -#define KASAN_SHADOW_SCALE_SHIFT 3 - #include <asm/kasan.h> #include <asm/pgtable.h> @@ -56,14 +54,14 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object); void kasan_init_slab_obj(struct kmem_cache *cache, const void *object); void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); -void kasan_kfree_large(const void *ptr); -void kasan_poison_kfree(void *ptr); +void kasan_kfree_large(void *ptr, unsigned long ip); +void kasan_poison_kfree(void *ptr, unsigned long ip); void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags); void kasan_krealloc(const void *object, size_t new_size, gfp_t flags); void kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags); -bool kasan_slab_free(struct kmem_cache *s, void *object); +bool kasan_slab_free(struct kmem_cache *s, void *object, unsigned long ip); struct kasan_cache { int alloc_meta_offset; @@ -108,8 +106,8 @@ static inline void kasan_init_slab_obj(struct kmem_cache *cache, const void *object) {} static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {} -static inline void kasan_kfree_large(const void *ptr) {} -static inline void kasan_poison_kfree(void *ptr) {} +static inline void kasan_kfree_large(void *ptr, unsigned long ip) {} +static inline void kasan_poison_kfree(void *ptr, unsigned long ip) {} static inline void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size, gfp_t flags) {} static inline void kasan_krealloc(const void *object, size_t new_size, @@ -117,7 +115,8 @@ static inline void kasan_krealloc(const void *object, size_t new_size, static inline void kasan_slab_alloc(struct kmem_cache *s, void *object, gfp_t flags) {} -static inline bool kasan_slab_free(struct kmem_cache *s, void *object) +static inline bool kasan_slab_free(struct kmem_cache *s, void *object, + unsigned long ip) { return false; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6bdd4b9f6611..ac0062b74aed 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -533,7 +533,7 @@ static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); -int __must_check vcpu_load(struct kvm_vcpu *vcpu); +void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_IOAPIC @@ -1260,4 +1260,16 @@ static inline bool vcpu_valid_wakeup(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_INVALID_WAKEUPS */ +#ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL +long kvm_arch_vcpu_async_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg); +#else +static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, + unsigned int ioctl, + unsigned long arg) +{ + return -ENOIOCTLCMD; +} +#endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */ + #endif diff --git a/include/linux/lockref.h b/include/linux/lockref.h index ef3c9342e119..2eac32095113 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -44,7 +44,7 @@ extern void lockref_mark_dead(struct lockref *); extern int lockref_get_not_dead(struct lockref *); /* Must be called under spinlock for reliable results */ -static inline int __lockref_is_dead(const struct lockref *l) +static inline bool __lockref_is_dead(const struct lockref *l) { return ((int)l->count < 0); } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 7ed0f7782d16..8be5077efb5f 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -332,8 +332,8 @@ void memblock_enforce_memory_limit(phys_addr_t memory_limit); void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size); void memblock_mem_limit_remove_map(phys_addr_t limit); bool memblock_is_memory(phys_addr_t addr); -int memblock_is_map_memory(phys_addr_t addr); -int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); +bool memblock_is_map_memory(phys_addr_t addr); +bool memblock_is_region_memory(phys_addr_t base, phys_addr_t size); bool memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/module.h b/include/linux/module.h index 8dc7065d904d..d44df9b2c131 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -491,7 +491,7 @@ extern struct mutex module_mutex; /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ -static inline int module_is_live(struct module *mod) +static inline bool module_is_live(struct module *mod) { return mod->state != MODULE_STATE_GOING; } diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 153274f78402..f25c13423bd4 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -138,9 +138,9 @@ extern void __mutex_init(struct mutex *lock, const char *name, * mutex_is_locked - is the mutex locked * @lock: the mutex to be queried * - * Returns 1 if the mutex is locked, 0 if unlocked. + * Returns true if the mutex is locked, false if unlocked. */ -static inline int mutex_is_locked(struct mutex *lock) +static inline bool mutex_is_locked(struct mutex *lock) { /* * XXX think about spin_is_locked diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4c77f39ebd65..5eef6c8e2741 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3228,6 +3228,12 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev, } #endif +static inline struct netdev_rx_queue * +__netif_get_rx_queue(struct net_device *dev, unsigned int rxq) +{ + return dev->_rx + rxq; +} + #ifdef CONFIG_SYSFS static inline unsigned int get_netdev_rx_queue_index( struct netdev_rx_queue *queue) diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index cddfaff4d0b7..4fa654e4b5a9 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -34,9 +34,6 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev, extern struct of_device_id __iommu_of_table; -typedef int (*of_iommu_init_fn)(struct device_node *); - -#define IOMMU_OF_DECLARE(name, compat, fn) \ - _OF_DECLARE(iommu, name, compat, fn, of_iommu_init_fn) +#define IOMMU_OF_DECLARE(name, compat) OF_DECLARE_1(iommu, name, compat, NULL) #endif /* __OF_IOMMU_H */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index eb13e84e1fef..a6b30667a331 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -149,6 +149,8 @@ #define PCI_VENDOR_ID_DYNALINK 0x0675 #define PCI_DEVICE_ID_DYNALINK_IS64PH 0x1702 +#define PCI_VENDOR_ID_UBIQUITI 0x0777 + #define PCI_VENDOR_ID_BERKOM 0x0871 #define PCI_DEVICE_ID_BERKOM_A1T 0xffa1 #define PCI_DEVICE_ID_BERKOM_T_CONCEPT 0xffa2 diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 2dc5e9870fcd..5a3bb3b7c9ad 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -167,10 +167,9 @@ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); -extern unsigned int pipe_max_size, pipe_min_size; +extern unsigned int pipe_max_size; extern unsigned long pipe_user_pages_hard; extern unsigned long pipe_user_pages_soft; -int pipe_proc_fn(struct ctl_table *, int, void __user *, size_t *, loff_t *); /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe); @@ -191,6 +190,6 @@ long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file); int create_pipe_files(struct file **, int); -unsigned int round_pipe_size(unsigned int size); +unsigned int round_pipe_size(unsigned long size); #endif diff --git a/include/linux/platform_data/mlxcpld-hotplug.h b/include/linux/platform_data/mlxcpld-hotplug.h deleted file mode 100644 index e4cfcffaa6f4..000000000000 --- a/include/linux/platform_data/mlxcpld-hotplug.h +++ /dev/null @@ -1,99 +0,0 @@ -/* - * include/linux/platform_data/mlxcpld-hotplug.h - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. - * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com> - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef __LINUX_PLATFORM_DATA_MLXCPLD_HOTPLUG_H -#define __LINUX_PLATFORM_DATA_MLXCPLD_HOTPLUG_H - -/** - * struct mlxcpld_hotplug_device - I2C device data: - * @adapter: I2C device adapter; - * @client: I2C device client; - * @brdinfo: device board information; - * @bus: I2C bus, where device is attached; - * - * Structure represents I2C hotplug device static data (board topology) and - * dynamic data (related kernel objects handles). - */ -struct mlxcpld_hotplug_device { - struct i2c_adapter *adapter; - struct i2c_client *client; - struct i2c_board_info brdinfo; - u16 bus; -}; - -/** - * struct mlxcpld_hotplug_platform_data - device platform data: - * @top_aggr_offset: offset of top aggregation interrupt register; - * @top_aggr_mask: top aggregation interrupt common mask; - * @top_aggr_psu_mask: top aggregation interrupt PSU mask; - * @psu_reg_offset: offset of PSU interrupt register; - * @psu_mask: PSU interrupt mask; - * @psu_count: number of equipped replaceable PSUs; - * @psu: pointer to PSU devices data array; - * @top_aggr_pwr_mask: top aggregation interrupt power mask; - * @pwr_reg_offset: offset of power interrupt register - * @pwr_mask: power interrupt mask; - * @pwr_count: number of power sources; - * @pwr: pointer to power devices data array; - * @top_aggr_fan_mask: top aggregation interrupt FAN mask; - * @fan_reg_offset: offset of FAN interrupt register; - * @fan_mask: FAN interrupt mask; - * @fan_count: number of equipped replaceable FANs; - * @fan: pointer to FAN devices data array; - * - * Structure represents board platform data, related to system hotplug events, - * like FAN, PSU, power cable insertion and removing. This data provides the - * number of hot-pluggable devices and hardware description for event handling. - */ -struct mlxcpld_hotplug_platform_data { - u16 top_aggr_offset; - u8 top_aggr_mask; - u8 top_aggr_psu_mask; - u16 psu_reg_offset; - u8 psu_mask; - u8 psu_count; - struct mlxcpld_hotplug_device *psu; - u8 top_aggr_pwr_mask; - u16 pwr_reg_offset; - u8 pwr_mask; - u8 pwr_count; - struct mlxcpld_hotplug_device *pwr; - u8 top_aggr_fan_mask; - u16 fan_reg_offset; - u8 fan_mask; - u8 fan_count; - struct mlxcpld_hotplug_device *fan; -}; - -#endif /* __LINUX_PLATFORM_DATA_MLXCPLD_HOTPLUG_H */ diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h new file mode 100644 index 000000000000..fcdc707eab99 --- /dev/null +++ b/include/linux/platform_data/mlxreg.h @@ -0,0 +1,144 @@ +/* + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Vadim Pasternak <vadimp@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __LINUX_PLATFORM_DATA_MLXREG_H +#define __LINUX_PLATFORM_DATA_MLXREG_H + +#define MLXREG_CORE_LABEL_MAX_SIZE 32 + +/** + * struct mlxreg_hotplug_device - I2C device data: + * + * @adapter: I2C device adapter; + * @client: I2C device client; + * @brdinfo: device board information; + * @nr: I2C device adapter number, to which device is to be attached; + * + * Structure represents I2C hotplug device static data (board topology) and + * dynamic data (related kernel objects handles). + */ +struct mlxreg_hotplug_device { + struct i2c_adapter *adapter; + struct i2c_client *client; + struct i2c_board_info *brdinfo; + int nr; +}; + +/** + * struct mlxreg_core_data - attributes control data: + * + * @label: attribute label; + * @label: attribute register offset; + * @reg: attribute register; + * @mask: attribute access mask; + * @mode: access mode; + * @bit: attribute effective bit; + * @np - pointer to node platform associated with attribute; + * @hpdev - hotplug device data; + * @health_cntr: dynamic device health indication counter; + * @attached: true if device has been attached after good health indication; + */ +struct mlxreg_core_data { + char label[MLXREG_CORE_LABEL_MAX_SIZE]; + u32 reg; + u32 mask; + u32 bit; + umode_t mode; + struct device_node *np; + struct mlxreg_hotplug_device hpdev; + u8 health_cntr; + bool attached; +}; + +/** + * struct mlxreg_core_item - same type components controlled by the driver: + * + * @data: component data; + * @aggr_mask: group aggregation mask; + * @reg: group interrupt status register; + * @mask: group interrupt mask; + * @cache: last status value for elements fro the same group; + * @count: number of available elements in the group; + * @ind: element's index inside the group; + * @inversed: if 0: 0 for signal status is OK, if 1 - 1 is OK; + * @health: true if device has health indication, false in other case; + */ +struct mlxreg_core_item { + struct mlxreg_core_data *data; + u32 aggr_mask; + u32 reg; + u32 mask; + u32 cache; + u8 count; + u8 ind; + u8 inversed; + u8 health; +}; + +/** + * struct mlxreg_core_platform_data - platform data: + * + * @led_data: led private data; + * @regmap: register map of parent device; + * @counter: number of led instances; + */ +struct mlxreg_core_platform_data { + struct mlxreg_core_data *data; + void *regmap; + int counter; +}; + +/** + * struct mlxreg_core_hotplug_platform_data - hotplug platform data: + * + * @items: same type components with the hotplug capability; + * @irq: platform interrupt number; + * @regmap: register map of parent device; + * @counter: number of the components with the hotplug capability; + * @cell: location of top aggregation interrupt register; + * @mask: top aggregation interrupt common mask; + * @cell_low: location of low aggregation interrupt register; + * @mask_low: low aggregation interrupt common mask; + */ +struct mlxreg_core_hotplug_platform_data { + struct mlxreg_core_item *items; + int irq; + void *regmap; + int counter; + u32 cell; + u32 mask; + u32 cell_low; + u32 mask_low; +}; + +#endif /* __LINUX_PLATFORM_DATA_MLXREG_H */ diff --git a/include/linux/poll.h b/include/linux/poll.h index 04781a753326..f45ebd017eaa 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -11,6 +11,7 @@ #include <linux/sysctl.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> +#include <uapi/linux/eventpoll.h> extern struct ctl_table epoll_table[]; /* for sysctl */ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating @@ -22,7 +23,7 @@ extern struct ctl_table epoll_table[]; /* for sysctl */ #define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) #define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) -#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM) +#define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM) struct poll_table_struct; @@ -107,4 +108,28 @@ extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec); +#define __MAP(v, from, to) \ + (from < to ? (v & from) * (to/from) : (v & from) / (from/to)) + +static inline __u16 mangle_poll(__poll_t val) +{ + __u16 v = (__force __u16)val; +#define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X) + return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | + M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | + M(HUP) | M(RDHUP) | M(MSG); +#undef M +} + +static inline __poll_t demangle_poll(u16 val) +{ +#define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X) + return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | + M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | + M(HUP) | M(RDHUP) | M(MSG); +#undef M +} +#undef __MAP + + #endif /* _LINUX_POLL_H */ diff --git a/include/linux/psci.h b/include/linux/psci.h index f724fd8c78e8..8b1b3b5935ab 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -25,6 +25,17 @@ bool psci_tos_resident_on(int cpu); int psci_cpu_init_idle(unsigned int cpu); int psci_cpu_suspend_enter(unsigned long index); +enum psci_conduit { + PSCI_CONDUIT_NONE, + PSCI_CONDUIT_SMC, + PSCI_CONDUIT_HVC, +}; + +enum smccc_version { + SMCCC_VERSION_1_0, + SMCCC_VERSION_1_1, +}; + struct psci_operations { u32 (*get_version)(void); int (*cpu_suspend)(u32 state, unsigned long entry_point); @@ -34,6 +45,8 @@ struct psci_operations { int (*affinity_info)(unsigned long target_affinity, unsigned long lowest_affinity_level); int (*migrate_info_type)(void); + enum psci_conduit conduit; + enum smccc_version smccc_version; }; extern struct psci_operations psci_ops; diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h new file mode 100644 index 000000000000..93addfa34061 --- /dev/null +++ b/include/linux/psp-sev.h @@ -0,0 +1,606 @@ +/* + * AMD Secure Encrypted Virtualization (SEV) driver interface + * + * Copyright (C) 2016-2017 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * SEV spec 0.14 is available at: + * http://support.amd.com/TechDocs/55766_SEV-KM API_Specification.pdf + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __PSP_SEV_H__ +#define __PSP_SEV_H__ + +#include <uapi/linux/psp-sev.h> + +#ifdef CONFIG_X86 +#include <linux/mem_encrypt.h> + +#define __psp_pa(x) __sme_pa(x) +#else +#define __psp_pa(x) __pa(x) +#endif + +#define SEV_FW_BLOB_MAX_SIZE 0x4000 /* 16KB */ + +/** + * SEV platform state + */ +enum sev_state { + SEV_STATE_UNINIT = 0x0, + SEV_STATE_INIT = 0x1, + SEV_STATE_WORKING = 0x2, + + SEV_STATE_MAX +}; + +/** + * SEV platform and guest management commands + */ +enum sev_cmd { + /* platform commands */ + SEV_CMD_INIT = 0x001, + SEV_CMD_SHUTDOWN = 0x002, + SEV_CMD_FACTORY_RESET = 0x003, + SEV_CMD_PLATFORM_STATUS = 0x004, + SEV_CMD_PEK_GEN = 0x005, + SEV_CMD_PEK_CSR = 0x006, + SEV_CMD_PEK_CERT_IMPORT = 0x007, + SEV_CMD_PDH_CERT_EXPORT = 0x008, + SEV_CMD_PDH_GEN = 0x009, + SEV_CMD_DF_FLUSH = 0x00A, + + /* Guest commands */ + SEV_CMD_DECOMMISSION = 0x020, + SEV_CMD_ACTIVATE = 0x021, + SEV_CMD_DEACTIVATE = 0x022, + SEV_CMD_GUEST_STATUS = 0x023, + + /* Guest launch commands */ + SEV_CMD_LAUNCH_START = 0x030, + SEV_CMD_LAUNCH_UPDATE_DATA = 0x031, + SEV_CMD_LAUNCH_UPDATE_VMSA = 0x032, + SEV_CMD_LAUNCH_MEASURE = 0x033, + SEV_CMD_LAUNCH_UPDATE_SECRET = 0x034, + SEV_CMD_LAUNCH_FINISH = 0x035, + + /* Guest migration commands (outgoing) */ + SEV_CMD_SEND_START = 0x040, + SEV_CMD_SEND_UPDATE_DATA = 0x041, + SEV_CMD_SEND_UPDATE_VMSA = 0x042, + SEV_CMD_SEND_FINISH = 0x043, + + /* Guest migration commands (incoming) */ + SEV_CMD_RECEIVE_START = 0x050, + SEV_CMD_RECEIVE_UPDATE_DATA = 0x051, + SEV_CMD_RECEIVE_UPDATE_VMSA = 0x052, + SEV_CMD_RECEIVE_FINISH = 0x053, + + /* Guest debug commands */ + SEV_CMD_DBG_DECRYPT = 0x060, + SEV_CMD_DBG_ENCRYPT = 0x061, + + SEV_CMD_MAX, +}; + +/** + * struct sev_data_init - INIT command parameters + * + * @flags: processing flags + * @tmr_address: system physical address used for SEV-ES + * @tmr_len: len of tmr_address + */ +struct sev_data_init { + u32 flags; /* In */ + u32 reserved; /* In */ + u64 tmr_address; /* In */ + u32 tmr_len; /* In */ +} __packed; + +/** + * struct sev_data_pek_csr - PEK_CSR command parameters + * + * @address: PEK certificate chain + * @len: len of certificate + */ +struct sev_data_pek_csr { + u64 address; /* In */ + u32 len; /* In/Out */ +} __packed; + +/** + * struct sev_data_cert_import - PEK_CERT_IMPORT command parameters + * + * @pek_address: PEK certificate chain + * @pek_len: len of PEK certificate + * @oca_address: OCA certificate chain + * @oca_len: len of OCA certificate + */ +struct sev_data_pek_cert_import { + u64 pek_cert_address; /* In */ + u32 pek_cert_len; /* In */ + u32 reserved; /* In */ + u64 oca_cert_address; /* In */ + u32 oca_cert_len; /* In */ +} __packed; + +/** + * struct sev_data_pdh_cert_export - PDH_CERT_EXPORT command parameters + * + * @pdh_address: PDH certificate address + * @pdh_len: len of PDH certificate + * @cert_chain_address: PDH certificate chain + * @cert_chain_len: len of PDH certificate chain + */ +struct sev_data_pdh_cert_export { + u64 pdh_cert_address; /* In */ + u32 pdh_cert_len; /* In/Out */ + u32 reserved; /* In */ + u64 cert_chain_address; /* In */ + u32 cert_chain_len; /* In/Out */ +} __packed; + +/** + * struct sev_data_decommission - DECOMMISSION command parameters + * + * @handle: handle of the VM to decommission + */ +struct sev_data_decommission { + u32 handle; /* In */ +} __packed; + +/** + * struct sev_data_activate - ACTIVATE command parameters + * + * @handle: handle of the VM to activate + * @asid: asid assigned to the VM + */ +struct sev_data_activate { + u32 handle; /* In */ + u32 asid; /* In */ +} __packed; + +/** + * struct sev_data_deactivate - DEACTIVATE command parameters + * + * @handle: handle of the VM to deactivate + */ +struct sev_data_deactivate { + u32 handle; /* In */ +} __packed; + +/** + * struct sev_data_guest_status - SEV GUEST_STATUS command parameters + * + * @handle: handle of the VM to retrieve status + * @policy: policy information for the VM + * @asid: current ASID of the VM + * @state: current state of the VM + */ +struct sev_data_guest_status { + u32 handle; /* In */ + u32 policy; /* Out */ + u32 asid; /* Out */ + u8 state; /* Out */ +} __packed; + +/** + * struct sev_data_launch_start - LAUNCH_START command parameters + * + * @handle: handle assigned to the VM + * @policy: guest launch policy + * @dh_cert_address: physical address of DH certificate blob + * @dh_cert_len: len of DH certificate blob + * @session_address: physical address of session parameters + * @session_len: len of session parameters + */ +struct sev_data_launch_start { + u32 handle; /* In/Out */ + u32 policy; /* In */ + u64 dh_cert_address; /* In */ + u32 dh_cert_len; /* In */ + u32 reserved; /* In */ + u64 session_address; /* In */ + u32 session_len; /* In */ +} __packed; + +/** + * struct sev_data_launch_update_data - LAUNCH_UPDATE_DATA command parameter + * + * @handle: handle of the VM to update + * @len: len of memory to be encrypted + * @address: physical address of memory region to encrypt + */ +struct sev_data_launch_update_data { + u32 handle; /* In */ + u32 reserved; + u64 address; /* In */ + u32 len; /* In */ +} __packed; + +/** + * struct sev_data_launch_update_vmsa - LAUNCH_UPDATE_VMSA command + * + * @handle: handle of the VM + * @address: physical address of memory region to encrypt + * @len: len of memory region to encrypt + */ +struct sev_data_launch_update_vmsa { + u32 handle; /* In */ + u32 reserved; + u64 address; /* In */ + u32 len; /* In */ +} __packed; + +/** + * struct sev_data_launch_measure - LAUNCH_MEASURE command parameters + * + * @handle: handle of the VM to process + * @address: physical address containing the measurement blob + * @len: len of measurement blob + */ +struct sev_data_launch_measure { + u32 handle; /* In */ + u32 reserved; + u64 address; /* In */ + u32 len; /* In/Out */ +} __packed; + +/** + * struct sev_data_launch_secret - LAUNCH_SECRET command parameters + * + * @handle: handle of the VM to process + * @hdr_address: physical address containing the packet header + * @hdr_len: len of packet header + * @guest_address: system physical address of guest memory region + * @guest_len: len of guest_paddr + * @trans_address: physical address of transport memory buffer + * @trans_len: len of transport memory buffer + */ +struct sev_data_launch_secret { + u32 handle; /* In */ + u32 reserved1; + u64 hdr_address; /* In */ + u32 hdr_len; /* In */ + u32 reserved2; + u64 guest_address; /* In */ + u32 guest_len; /* In */ + u32 reserved3; + u64 trans_address; /* In */ + u32 trans_len; /* In */ +} __packed; + +/** + * struct sev_data_launch_finish - LAUNCH_FINISH command parameters + * + * @handle: handle of the VM to process + */ +struct sev_data_launch_finish { + u32 handle; /* In */ +} __packed; + +/** + * struct sev_data_send_start - SEND_START command parameters + * + * @handle: handle of the VM to process + * @policy: policy information for the VM + * @pdh_cert_address: physical address containing PDH certificate + * @pdh_cert_len: len of PDH certificate + * @plat_certs_address: physical address containing platform certificate + * @plat_certs_len: len of platform certificate + * @amd_certs_address: physical address containing AMD certificate + * @amd_certs_len: len of AMD certificate + * @session_address: physical address containing Session data + * @session_len: len of session data + */ +struct sev_data_send_start { + u32 handle; /* In */ + u32 policy; /* Out */ + u64 pdh_cert_address; /* In */ + u32 pdh_cert_len; /* In */ + u32 reserved1; + u64 plat_cert_address; /* In */ + u32 plat_cert_len; /* In */ + u32 reserved2; + u64 amd_cert_address; /* In */ + u32 amd_cert_len; /* In */ + u32 reserved3; + u64 session_address; /* In */ + u32 session_len; /* In/Out */ +} __packed; + +/** + * struct sev_data_send_update - SEND_UPDATE_DATA command + * + * @handle: handle of the VM to process + * @hdr_address: physical address containing packet header + * @hdr_len: len of packet header + * @guest_address: physical address of guest memory region to send + * @guest_len: len of guest memory region to send + * @trans_address: physical address of host memory region + * @trans_len: len of host memory region + */ +struct sev_data_send_update_data { + u32 handle; /* In */ + u32 reserved1; + u64 hdr_address; /* In */ + u32 hdr_len; /* In/Out */ + u32 reserved2; + u64 guest_address; /* In */ + u32 guest_len; /* In */ + u32 reserved3; + u64 trans_address; /* In */ + u32 trans_len; /* In */ +} __packed; + +/** + * struct sev_data_send_update - SEND_UPDATE_VMSA command + * + * @handle: handle of the VM to process + * @hdr_address: physical address containing packet header + * @hdr_len: len of packet header + * @guest_address: physical address of guest memory region to send + * @guest_len: len of guest memory region to send + * @trans_address: physical address of host memory region + * @trans_len: len of host memory region + */ +struct sev_data_send_update_vmsa { + u32 handle; /* In */ + u64 hdr_address; /* In */ + u32 hdr_len; /* In/Out */ + u32 reserved2; + u64 guest_address; /* In */ + u32 guest_len; /* In */ + u32 reserved3; + u64 trans_address; /* In */ + u32 trans_len; /* In */ +} __packed; + +/** + * struct sev_data_send_finish - SEND_FINISH command parameters + * + * @handle: handle of the VM to process + */ +struct sev_data_send_finish { + u32 handle; /* In */ +} __packed; + +/** + * struct sev_data_receive_start - RECEIVE_START command parameters + * + * @handle: handle of the VM to perform receive operation + * @pdh_cert_address: system physical address containing PDH certificate blob + * @pdh_cert_len: len of PDH certificate blob + * @session_address: system physical address containing session blob + * @session_len: len of session blob + */ +struct sev_data_receive_start { + u32 handle; /* In/Out */ + u32 policy; /* In */ + u64 pdh_cert_address; /* In */ + u32 pdh_cert_len; /* In */ + u32 reserved1; + u64 session_address; /* In */ + u32 session_len; /* In */ +} __packed; + +/** + * struct sev_data_receive_update_data - RECEIVE_UPDATE_DATA command parameters + * + * @handle: handle of the VM to update + * @hdr_address: physical address containing packet header blob + * @hdr_len: len of packet header + * @guest_address: system physical address of guest memory region + * @guest_len: len of guest memory region + * @trans_address: system physical address of transport buffer + * @trans_len: len of transport buffer + */ +struct sev_data_receive_update_data { + u32 handle; /* In */ + u32 reserved1; + u64 hdr_address; /* In */ + u32 hdr_len; /* In */ + u32 reserved2; + u64 guest_address; /* In */ + u32 guest_len; /* In */ + u32 reserved3; + u64 trans_address; /* In */ + u32 trans_len; /* In */ +} __packed; + +/** + * struct sev_data_receive_update_vmsa - RECEIVE_UPDATE_VMSA command parameters + * + * @handle: handle of the VM to update + * @hdr_address: physical address containing packet header blob + * @hdr_len: len of packet header + * @guest_address: system physical address of guest memory region + * @guest_len: len of guest memory region + * @trans_address: system physical address of transport buffer + * @trans_len: len of transport buffer + */ +struct sev_data_receive_update_vmsa { + u32 handle; /* In */ + u32 reserved1; + u64 hdr_address; /* In */ + u32 hdr_len; /* In */ + u32 reserved2; + u64 guest_address; /* In */ + u32 guest_len; /* In */ + u32 reserved3; + u64 trans_address; /* In */ + u32 trans_len; /* In */ +} __packed; + +/** + * struct sev_data_receive_finish - RECEIVE_FINISH command parameters + * + * @handle: handle of the VM to finish + */ +struct sev_data_receive_finish { + u32 handle; /* In */ +} __packed; + +/** + * struct sev_data_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters + * + * @handle: handle of the VM to perform debug operation + * @src_addr: source address of data to operate on + * @dst_addr: destination address of data to operate on + * @len: len of data to operate on + */ +struct sev_data_dbg { + u32 handle; /* In */ + u32 reserved; + u64 src_addr; /* In */ + u64 dst_addr; /* In */ + u32 len; /* In */ +} __packed; + +#ifdef CONFIG_CRYPTO_DEV_SP_PSP + +/** + * sev_platform_init - perform SEV INIT command + * + * @error: SEV command return code + * + * Returns: + * 0 if the SEV successfully processed the command + * -%ENODEV if the SEV device is not available + * -%ENOTSUPP if the SEV does not support SEV + * -%ETIMEDOUT if the SEV command timed out + * -%EIO if the SEV returned a non-zero return code + */ +int sev_platform_init(int *error); + +/** + * sev_platform_status - perform SEV PLATFORM_STATUS command + * + * @status: sev_user_data_status structure to be processed + * @error: SEV command return code + * + * Returns: + * 0 if the SEV successfully processed the command + * -%ENODEV if the SEV device is not available + * -%ENOTSUPP if the SEV does not support SEV + * -%ETIMEDOUT if the SEV command timed out + * -%EIO if the SEV returned a non-zero return code + */ +int sev_platform_status(struct sev_user_data_status *status, int *error); + +/** + * sev_issue_cmd_external_user - issue SEV command by other driver with a file + * handle. + * + * This function can be used by other drivers to issue a SEV command on + * behalf of userspace. The caller must pass a valid SEV file descriptor + * so that we know that it has access to SEV device. + * + * @filep - SEV device file pointer + * @cmd - command to issue + * @data - command buffer + * @error: SEV command return code + * + * Returns: + * 0 if the SEV successfully processed the command + * -%ENODEV if the SEV device is not available + * -%ENOTSUPP if the SEV does not support SEV + * -%ETIMEDOUT if the SEV command timed out + * -%EIO if the SEV returned a non-zero return code + * -%EINVAL if the SEV file descriptor is not valid + */ +int sev_issue_cmd_external_user(struct file *filep, unsigned int id, + void *data, int *error); + +/** + * sev_guest_deactivate - perform SEV DEACTIVATE command + * + * @deactivate: sev_data_deactivate structure to be processed + * @sev_ret: sev command return code + * + * Returns: + * 0 if the sev successfully processed the command + * -%ENODEV if the sev device is not available + * -%ENOTSUPP if the sev does not support SEV + * -%ETIMEDOUT if the sev command timed out + * -%EIO if the sev returned a non-zero return code + */ +int sev_guest_deactivate(struct sev_data_deactivate *data, int *error); + +/** + * sev_guest_activate - perform SEV ACTIVATE command + * + * @activate: sev_data_activate structure to be processed + * @sev_ret: sev command return code + * + * Returns: + * 0 if the sev successfully processed the command + * -%ENODEV if the sev device is not available + * -%ENOTSUPP if the sev does not support SEV + * -%ETIMEDOUT if the sev command timed out + * -%EIO if the sev returned a non-zero return code + */ +int sev_guest_activate(struct sev_data_activate *data, int *error); + +/** + * sev_guest_df_flush - perform SEV DF_FLUSH command + * + * @sev_ret: sev command return code + * + * Returns: + * 0 if the sev successfully processed the command + * -%ENODEV if the sev device is not available + * -%ENOTSUPP if the sev does not support SEV + * -%ETIMEDOUT if the sev command timed out + * -%EIO if the sev returned a non-zero return code + */ +int sev_guest_df_flush(int *error); + +/** + * sev_guest_decommission - perform SEV DECOMMISSION command + * + * @decommission: sev_data_decommission structure to be processed + * @sev_ret: sev command return code + * + * Returns: + * 0 if the sev successfully processed the command + * -%ENODEV if the sev device is not available + * -%ENOTSUPP if the sev does not support SEV + * -%ETIMEDOUT if the sev command timed out + * -%EIO if the sev returned a non-zero return code + */ +int sev_guest_decommission(struct sev_data_decommission *data, int *error); + +void *psp_copy_user_blob(u64 __user uaddr, u32 len); + +#else /* !CONFIG_CRYPTO_DEV_SP_PSP */ + +static inline int +sev_platform_status(struct sev_user_data_status *status, int *error) { return -ENODEV; } + +static inline int sev_platform_init(int *error) { return -ENODEV; } + +static inline int +sev_guest_deactivate(struct sev_data_deactivate *data, int *error) { return -ENODEV; } + +static inline int +sev_guest_decommission(struct sev_data_decommission *data, int *error) { return -ENODEV; } + +static inline int +sev_guest_activate(struct sev_data_activate *data, int *error) { return -ENODEV; } + +static inline int sev_guest_df_flush(int *error) { return -ENODEV; } + +static inline int +sev_issue_cmd_external_user(struct file *filep, unsigned int id, void *data, int *error) { return -ENODEV; } + +static inline void *psp_copy_user_blob(u64 __user uaddr, u32 len) { return ERR_PTR(-EINVAL); } + +#endif /* CONFIG_CRYPTO_DEV_SP_PSP */ + +#endif /* __PSP_SEV_H__ */ diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 1883d6137e9b..b884b7794187 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -464,9 +464,14 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, __PTR_RING_PEEK_CALL_v; \ }) +/* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See + * documentation for vmalloc for which of them are legal. + */ static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) { - return kcalloc(size, sizeof(void *), gfp); + if (size * sizeof(void *) > KMALLOC_MAX_SIZE) + return NULL; + return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) @@ -601,7 +606,7 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, spin_unlock(&(r)->producer_lock); spin_unlock_irqrestore(&(r)->consumer_lock, flags); - kfree(old); + kvfree(old); return 0; } @@ -641,7 +646,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, } for (i = 0; i < nrings; ++i) - kfree(queues[i]); + kvfree(queues[i]); kfree(queues); @@ -649,7 +654,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, nomem: while (--i >= 0) - kfree(queues[i]); + kvfree(queues[i]); kfree(queues); @@ -664,7 +669,7 @@ static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) if (destroy) while ((ptr = ptr_ring_consume(r))) destroy(ptr); - kfree(r->queue); + kvfree(r->queue); } #endif /* _LINUX_PTR_RING_H */ diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 23a9c89c7ad9..fc55ff31eca7 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -356,24 +356,9 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index, int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); -void __rcu **idr_get_free_cmn(struct radix_tree_root *root, +void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); -static inline void __rcu **idr_get_free(struct radix_tree_root *root, - struct radix_tree_iter *iter, - gfp_t gfp, - int end) -{ - return idr_get_free_cmn(root, iter, gfp, end > 0 ? end - 1 : INT_MAX); -} - -static inline void __rcu **idr_get_free_ext(struct radix_tree_root *root, - struct radix_tree_iter *iter, - gfp_t gfp, - unsigned long end) -{ - return idr_get_free_cmn(root, iter, gfp, end - 1); -} enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 166144c04ef6..b161ef8a902e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -555,6 +555,14 @@ struct task_struct { unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; + /* + * recent_used_cpu is initially set as the last CPU used by a task + * that wakes affine another task. Waker/wakee relationships can + * push tasks around a CPU where each wakeup moves to the next one. + * Tracking a recently used CPU allows a quick search for a recently + * used CPU that may be idle. + */ + int recent_used_cpu; int wake_cpu; #endif int on_rq; @@ -1489,6 +1497,11 @@ static inline struct thread_info *task_thread_info(struct task_struct *task) extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); +/* + * find a task by its virtual pid and get the task struct + */ +extern struct task_struct *find_get_task_by_vpid(pid_t nr); + extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index bd422561a75e..1149533aa2fa 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/gfp.h> +#include <linux/sync_core.h> /* * Routines for handling mm_structs @@ -194,18 +195,48 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) #ifdef CONFIG_MEMBARRIER enum { - MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), - MEMBARRIER_STATE_SWITCH_MM = (1U << 1), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), + MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), + MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), + MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), }; +enum { + MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), +}; + +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS +#include <asm/membarrier.h> +#endif + +static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) +{ + if (likely(!(atomic_read(&mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) + return; + sync_core_before_usermode(); +} + static inline void membarrier_execve(struct task_struct *t) { atomic_set(&t->mm->membarrier_state, 0); } #else +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ +} +#endif static inline void membarrier_execve(struct task_struct *t) { } +static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) +{ +} #endif #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/scif.h b/include/linux/scif.h index 7046111b8d0a..eeb250b73c4b 100644 --- a/include/linux/scif.h +++ b/include/linux/scif.h @@ -1266,8 +1266,8 @@ int scif_put_pages(struct scif_range *pages); * events is a bitmask specifying the events which the application is * interested in. The field revents is an output parameter, filled by the * kernel with the events that actually occurred. The bits returned in revents - * can include any of those specified in events, or one of the values POLLERR, - * POLLHUP, or POLLNVAL. (These three bits are meaningless in the events + * can include any of those specified in events, or one of the values EPOLLERR, + * EPOLLHUP, or EPOLLNVAL. (These three bits are meaningless in the events * field, and will be set in the revents field whenever the corresponding * condition is true.) * @@ -1279,20 +1279,20 @@ int scif_put_pages(struct scif_range *pages); * timeout means an infinite timeout. * * The following bits may be set in events and returned in revents. - * POLLIN - Data may be received without blocking. For a connected + * EPOLLIN - Data may be received without blocking. For a connected * endpoint, this means that scif_recv() may be called without blocking. For a * listening endpoint, this means that scif_accept() may be called without * blocking. - * POLLOUT - Data may be sent without blocking. For a connected endpoint, this - * means that scif_send() may be called without blocking. POLLOUT may also be + * EPOLLOUT - Data may be sent without blocking. For a connected endpoint, this + * means that scif_send() may be called without blocking. EPOLLOUT may also be * used to block waiting for a non-blocking connect to complete. This bit value * has no meaning for a listening endpoint and is ignored if specified. * * The following bits are only returned in revents, and are ignored if set in * events. - * POLLERR - An error occurred on the endpoint - * POLLHUP - The connection to the peer endpoint was disconnected - * POLLNVAL - The specified endpoint descriptor is invalid. + * EPOLLERR - An error occurred on the endpoint + * EPOLLHUP - The connection to the peer endpoint was disconnected + * EPOLLNVAL - The specified endpoint descriptor is invalid. * * Return: * Upon successful completion, scif_poll() returns a non-negative value. A diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 09c6e28746f9..ab437dd2e3b9 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -140,6 +140,20 @@ void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); +#define DEFINE_SHOW_ATTRIBUTE(__name) \ +static int __name ## _open(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, __name ## _show, inode->i_private); \ +} \ + \ +static const struct file_operations __name ## _fops = { \ + .owner = THIS_MODULE, \ + .open = __name ## _open, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ +} + static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { #ifdef CONFIG_USER_NS diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 4c310c34ddad..b32df49a3bd5 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -376,10 +376,10 @@ extern int of_setup_earlycon(const struct earlycon_id *match, const char *options); #ifdef CONFIG_SERIAL_EARLYCON -extern bool earlycon_init_is_deferred __initdata; +extern bool earlycon_acpi_spcr_enable __initdata; int setup_earlycon(char *buf); #else -static const bool earlycon_init_is_deferred; +static const bool earlycon_acpi_spcr_enable; static inline int setup_earlycon(char *buf) { return 0; } #endif diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index d96e74e114c0..592653becd91 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -229,6 +229,9 @@ void rpc_sleep_on_priority(struct rpc_wait_queue *, struct rpc_task *, rpc_action action, int priority); +void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq, + struct rpc_wait_queue *queue, + struct rpc_task *task); void rpc_wake_up_queued_task(struct rpc_wait_queue *, struct rpc_task *); void rpc_wake_up(struct rpc_wait_queue *); diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 995c6fe9ee90..4b731b046bcd 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -185,8 +185,6 @@ extern void svc_rdma_wc_reg(struct ib_cq *, struct ib_wc *); extern void svc_rdma_wc_read(struct ib_cq *, struct ib_wc *); extern void svc_rdma_wc_inv(struct ib_cq *, struct ib_wc *); extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *); -extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t); -extern int svc_rdma_repost_recv(struct svcxprt_rdma *, gfp_t); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); diff --git a/include/linux/sync_core.h b/include/linux/sync_core.h new file mode 100644 index 000000000000..013da4b8b327 --- /dev/null +++ b/include/linux/sync_core.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SYNC_CORE_H +#define _LINUX_SYNC_CORE_H + +#ifdef CONFIG_ARCH_HAS_SYNC_CORE_BEFORE_USERMODE +#include <asm/sync_core.h> +#else +/* + * This is a dummy sync_core_before_usermode() implementation that can be used + * on all architectures which return to user-space through core serializing + * instructions. + * If your architecture returns to user-space through non-core-serializing + * instructions, you need to write your own functions. + */ +static inline void sync_core_before_usermode(void) +{ +} +#endif + +#endif /* _LINUX_SYNC_CORE_H */ + diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 992bc9948232..b769ecfcc3bd 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -51,9 +51,6 @@ extern int proc_dointvec_minmax(struct ctl_table *, int, extern int proc_douintvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -extern int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 33b0bdbb613c..d9c4a6cce3c2 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -17,6 +17,7 @@ #define _LINUX_UUID_H_ #include <uapi/linux/uuid.h> +#include <linux/string.h> #define UUID_SIZE 16 diff --git a/include/media/dvb_vb2.h b/include/media/dvb_vb2.h index dda61af7c4cd..01d1202d1a55 100644 --- a/include/media/dvb_vb2.h +++ b/include/media/dvb_vb2.h @@ -116,9 +116,9 @@ static inline int dvb_vb2_release(struct dvb_vb2_ctx *ctx) #define dvb_vb2_is_streaming(ctx) (0) #define dvb_vb2_fill_buffer(ctx, file, wait) (0) -static inline unsigned int dvb_vb2_poll(struct dvb_vb2_ctx *ctx, - struct file *file, - poll_table *wait) +static inline __poll_t dvb_vb2_poll(struct dvb_vb2_ctx *ctx, + struct file *file, + poll_table *wait) { return 0; } @@ -169,8 +169,8 @@ int dvb_vb2_fill_buffer(struct dvb_vb2_ctx *ctx, * * Implements poll syscall() logic. */ -unsigned int dvb_vb2_poll(struct dvb_vb2_ctx *ctx, struct file *file, - poll_table *wait); +__poll_t dvb_vb2_poll(struct dvb_vb2_ctx *ctx, struct file *file, + poll_table *wait); #endif /** diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index aa16c064294f..5b6c541e4e1b 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -443,7 +443,7 @@ struct vb2_buf_ops { * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call * @allow_zero_bytesused: allow bytesused == 0 to be passed to the driver - * @quirk_poll_must_check_waiting_for_buffers: Return %POLLERR at poll when QBUF + * @quirk_poll_must_check_waiting_for_buffers: Return %EPOLLERR at poll when QBUF * has not been called. This is a vb1 idiom that has been adopted * also by vb2. * @lock: pointer to a mutex that protects the &struct vb2_queue. The @@ -493,7 +493,7 @@ struct vb2_buf_ops { * @error: a fatal error occurred on the queue * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for * buffers. Only set for capture queues if qbuf has not yet been - * called since poll() needs to return %POLLERR in that situation. + * called since poll() needs to return %EPOLLERR in that situation. * @is_multiplanar: set if buffer type is multiplanar * @is_output: set if buffer type is output * @copy_timestamp: set if vb2-core should set timestamps @@ -869,7 +869,7 @@ void vb2_core_queue_release(struct vb2_queue *q); * @q: pointer to &struct vb2_queue with videobuf2 queue. * * Flag that a fatal unrecoverable error has occurred and wake up all processes - * waiting on the queue. Polling will now set %POLLERR and queuing and dequeuing + * waiting on the queue. Polling will now set %EPOLLERR and queuing and dequeuing * buffers will return %-EIO. * * The error flag will be cleared when canceling the queue, either from diff --git a/include/net/erspan.h b/include/net/erspan.h index 5daa4866412b..d044aa60cc76 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -159,13 +159,13 @@ static inline void erspan_build_header(struct sk_buff *skb, struct ethhdr *eth = (struct ethhdr *)skb->data; enum erspan_encap_type enc_type; struct erspan_base_hdr *ershdr; - struct erspan_metadata *ersmd; struct qtag_prefix { __be16 eth_type; __be16 tci; } *qp; u16 vlan_tci = 0; u8 tos; + __be32 *idx; tos = is_ipv4 ? ip_hdr(skb)->tos : (ipv6_hdr(skb)->priority << 4) + @@ -195,8 +195,8 @@ static inline void erspan_build_header(struct sk_buff *skb, set_session_id(ershdr, id); /* Build metadata */ - ersmd = (struct erspan_metadata *)(ershdr + 1); - ersmd->u.index = htonl(index & INDEX_MASK); + idx = (__be32 *)(ershdr + 1); + *idx = htonl(index & INDEX_MASK); } /* ERSPAN GRA: timestamp granularity @@ -225,7 +225,7 @@ static inline void erspan_build_header_v2(struct sk_buff *skb, { struct ethhdr *eth = (struct ethhdr *)skb->data; struct erspan_base_hdr *ershdr; - struct erspan_metadata *md; + struct erspan_md2 *md2; struct qtag_prefix { __be16 eth_type; __be16 tci; @@ -261,15 +261,15 @@ static inline void erspan_build_header_v2(struct sk_buff *skb, set_session_id(ershdr, id); /* Build metadata */ - md = (struct erspan_metadata *)(ershdr + 1); - md->u.md2.timestamp = erspan_get_timestamp(); - md->u.md2.sgt = htons(sgt); - md->u.md2.p = 1; - md->u.md2.ft = 0; - md->u.md2.dir = direction; - md->u.md2.gra = gra; - md->u.md2.o = 0; - set_hwid(&md->u.md2, hwid); + md2 = (struct erspan_md2 *)(ershdr + 1); + md2->timestamp = erspan_get_timestamp(); + md2->sgt = htons(sgt); + md2->p = 1; + md2->ft = 0; + md2->dir = direction; + md2->gra = gra; + md2->o = 0; + set_hwid(md2, hwid); } #endif diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 6692d67e9245..c1a93ce35e62 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -310,7 +310,7 @@ void inet_csk_prepare_forced_close(struct sock *sk); static inline __poll_t inet_csk_listen_poll(const struct sock *sk) { return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ? - (POLLIN | POLLRDNORM) : 0; + (EPOLLIN | EPOLLRDNORM) : 0; } int inet_csk_listen_start(struct sock *sk, int backlog); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index f5223bf2c420..062dc19b5840 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -213,11 +213,6 @@ static inline bool nf_ct_kill(struct nf_conn *ct) return nf_ct_delete(ct, 0, 0); } -/* These are for NAT. Icky. */ -extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, - enum ip_conntrack_dir dir, - u32 seq); - /* Set all unconfirmed conntrack as dying */ void nf_ct_unconfirmed_destroy(struct net *); diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index b22b22082733..833752dd0c58 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -14,6 +14,7 @@ struct nf_flowtable_type { struct list_head list; int family; void (*gc)(struct work_struct *work); + void (*free)(struct nf_flowtable *ft); const struct rhashtable_params *params; nf_hookfn *hook; struct module *owner; @@ -89,12 +90,15 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct, void flow_offload_free(struct flow_offload *flow); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); -void flow_offload_del(struct nf_flowtable *flow_table, struct flow_offload *flow); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); int nf_flow_table_iterate(struct nf_flowtable *flow_table, void (*iter)(struct flow_offload *flow, void *data), void *data); + +void nf_flow_table_cleanup(struct net *net, struct net_device *dev); + +void nf_flow_table_free(struct nf_flowtable *flow_table); void nf_flow_offload_work_gc(struct work_struct *work); extern const struct rhashtable_params nf_flow_offload_rhash_params; diff --git a/include/net/tcp.h b/include/net/tcp.h index 58278669cc55..e3fc667f9ac2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1983,6 +1983,11 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); #define TCP_ULP_MAX 128 #define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) +enum { + TCP_ULP_TLS, + TCP_ULP_BPF, +}; + struct tcp_ulp_ops { struct list_head list; @@ -1991,12 +1996,15 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); + int uid; char name[TCP_ULP_NAME_MAX]; + bool user_visible; struct module *owner; }; int tcp_register_ulp(struct tcp_ulp_ops *type); void tcp_unregister_ulp(struct tcp_ulp_ops *type); int tcp_set_ulp(struct sock *sk, const char *name); +int tcp_set_ulp_id(struct sock *sk, const int ulp); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); diff --git a/include/sound/soc.h b/include/sound/soc.h index b655d987fbe7..747fd583b9dc 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -841,7 +841,7 @@ struct snd_soc_component_driver { /* bits */ unsigned int idle_bias_on:1; unsigned int suspend_bias_off:1; - unsigned int pmdown_time:1; /* care pmdown_time at stop */ + unsigned int use_pmdown_time:1; /* care pmdown_time at stop */ unsigned int endianness:1; unsigned int non_legacy_dai_naming:1; }; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index b6b3fb444a92..34a15d59ed88 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -53,6 +53,7 @@ struct target_backend_ops { void (*free_prot)(struct se_device *); struct configfs_attribute **tb_dev_attrib_attrs; + struct configfs_attribute **tb_dev_action_attrs; }; struct sbc_ops { diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 2c8d8115469d..9f9f5902af38 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -183,6 +183,7 @@ enum tcm_sense_reason_table { TCM_TOO_MANY_SEGMENT_DESCS = R(0x1b), TCM_UNSUPPORTED_SEGMENT_DESC_TYPE_CODE = R(0x1c), TCM_INSUFFICIENT_REGISTRATION_RESOURCES = R(0x1d), + TCM_LUN_BUSY = R(0x1e), #undef R }; @@ -808,6 +809,7 @@ struct se_device { /* T10 SPC-2 + SPC-3 Reservations */ struct t10_reservation t10_pr; struct se_dev_attrib dev_attrib; + struct config_group dev_action_group; struct config_group dev_group; struct config_group dev_pr_group; struct se_dev_stat_grps dev_stat_grps; diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 639fade14b23..41b509f410bf 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -3,50 +3,36 @@ #define __ASM_GENERIC_POLL_H /* These are specified by iBCS2 */ -#define POLLIN (__force __poll_t)0x0001 -#define POLLPRI (__force __poll_t)0x0002 -#define POLLOUT (__force __poll_t)0x0004 -#define POLLERR (__force __poll_t)0x0008 -#define POLLHUP (__force __poll_t)0x0010 -#define POLLNVAL (__force __poll_t)0x0020 +#define POLLIN 0x0001 +#define POLLPRI 0x0002 +#define POLLOUT 0x0004 +#define POLLERR 0x0008 +#define POLLHUP 0x0010 +#define POLLNVAL 0x0020 /* The rest seem to be more-or-less nonstandard. Check them! */ -#define POLLRDNORM (__force __poll_t)0x0040 -#define POLLRDBAND (__force __poll_t)0x0080 +#define POLLRDNORM 0x0040 +#define POLLRDBAND 0x0080 #ifndef POLLWRNORM -#define POLLWRNORM (__force __poll_t)0x0100 +#define POLLWRNORM 0x0100 #endif #ifndef POLLWRBAND -#define POLLWRBAND (__force __poll_t)0x0200 +#define POLLWRBAND 0x0200 #endif #ifndef POLLMSG -#define POLLMSG (__force __poll_t)0x0400 +#define POLLMSG 0x0400 #endif #ifndef POLLREMOVE -#define POLLREMOVE (__force __poll_t)0x1000 +#define POLLREMOVE 0x1000 #endif #ifndef POLLRDHUP -#define POLLRDHUP (__force __poll_t)0x2000 +#define POLLRDHUP 0x2000 #endif #define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */ #define POLL_BUSY_LOOP (__force __poll_t)0x8000 -#ifdef __KERNEL__ -#ifndef __ARCH_HAS_MANGLED_POLL -static inline __u16 mangle_poll(__poll_t val) -{ - return (__force __u16)val; -} - -static inline __poll_t demangle_poll(__u16 v) -{ - return (__force __poll_t)v; -} -#endif -#endif - struct pollfd { int fd; short events; diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 254afc31e3be..85dc965afd89 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -280,8 +280,8 @@ typedef struct siginfo { #define NSIGTRAP 4 /* - * There are an additional set of SIGTRAP si_codes used by ptrace - * that of the form: ((PTRACE_EVENT_XXX << 8) | SIGTRAP) + * There is an additional set of SIGTRAP si_codes used by ptrace + * that are of the form: ((PTRACE_EVENT_XXX << 8) | SIGTRAP) */ /* diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index 63e21be30f15..bf48e71f2634 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -28,20 +28,21 @@ #define EPOLL_CTL_MOD 3 /* Epoll event masks */ -#define EPOLLIN 0x00000001 -#define EPOLLPRI 0x00000002 -#define EPOLLOUT 0x00000004 -#define EPOLLERR 0x00000008 -#define EPOLLHUP 0x00000010 -#define EPOLLRDNORM 0x00000040 -#define EPOLLRDBAND 0x00000080 -#define EPOLLWRNORM 0x00000100 -#define EPOLLWRBAND 0x00000200 -#define EPOLLMSG 0x00000400 -#define EPOLLRDHUP 0x00002000 +#define EPOLLIN (__force __poll_t)0x00000001 +#define EPOLLPRI (__force __poll_t)0x00000002 +#define EPOLLOUT (__force __poll_t)0x00000004 +#define EPOLLERR (__force __poll_t)0x00000008 +#define EPOLLHUP (__force __poll_t)0x00000010 +#define EPOLLNVAL (__force __poll_t)0x00000020 +#define EPOLLRDNORM (__force __poll_t)0x00000040 +#define EPOLLRDBAND (__force __poll_t)0x00000080 +#define EPOLLWRNORM (__force __poll_t)0x00000100 +#define EPOLLWRBAND (__force __poll_t)0x00000200 +#define EPOLLMSG (__force __poll_t)0x00000400 +#define EPOLLRDHUP (__force __poll_t)0x00002000 /* Set exclusive wakeup mode for the target file descriptor */ -#define EPOLLEXCLUSIVE (1U << 28) +#define EPOLLEXCLUSIVE (__force __poll_t)(1U << 28) /* * Request the handling of system wakeup events so as to prevent system suspends @@ -53,13 +54,13 @@ * * Requires CAP_BLOCK_SUSPEND */ -#define EPOLLWAKEUP (1U << 29) +#define EPOLLWAKEUP (__force __poll_t)(1U << 29) /* Set the One Shot behaviour for the target file descriptor */ -#define EPOLLONESHOT (1U << 30) +#define EPOLLONESHOT (__force __poll_t)(1U << 30) /* Set the Edge Triggered behaviour for the target file descriptor */ -#define EPOLLET (1U << 31) +#define EPOLLET (__force __poll_t)(1U << 31) /* * On x86-64 make the 64bit structure have the same alignment as the @@ -74,7 +75,7 @@ #endif struct epoll_event { - __u32 events; + __poll_t events; __u64 data; } EPOLL_PACKED; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 061fa62958a2..53fbae27b280 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -594,6 +594,7 @@ #define BTN_DPAD_RIGHT 0x223 #define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ +#define KEY_ROTATE_LOCK_TOGGLE 0x231 /* Display rotation lock */ #define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ #define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8fb90a0819c3..0fb5ef939732 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1362,6 +1362,96 @@ struct kvm_s390_ucas_mapping { /* Available with KVM_CAP_S390_CMMA_MIGRATION */ #define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) #define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) +/* Memory Encryption Commands */ +#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long) + +struct kvm_enc_region { + __u64 addr; + __u64 size; +}; + +#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region) +#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region) + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; +}; #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 4e01ad7ffe98..5891d7614c8c 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -31,7 +31,7 @@ * enum membarrier_cmd - membarrier system call command * @MEMBARRIER_CMD_QUERY: Query the set of supported commands. It returns * a bitmask of valid commands. - * @MEMBARRIER_CMD_SHARED: Execute a memory barrier on all running threads. + * @MEMBARRIER_CMD_GLOBAL: Execute a memory barrier on all running threads. * Upon return from system call, the caller thread * is ensured that all running threads have passed * through a state where all memory accesses to @@ -40,6 +40,28 @@ * (non-running threads are de facto in such a * state). This covers threads from all processes * running on the system. This command returns 0. + * @MEMBARRIER_CMD_GLOBAL_EXPEDITED: + * Execute a memory barrier on all running threads + * of all processes which previously registered + * with MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED. + * Upon return from system call, the caller thread + * is ensured that all running threads have passed + * through a state where all memory accesses to + * user-space addresses match program order between + * entry to and return from the system call + * (non-running threads are de facto in such a + * state). This only covers threads from processes + * which registered with + * MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED. + * This command returns 0. Given that + * registration is about the intent to receive + * the barriers, it is valid to invoke + * MEMBARRIER_CMD_GLOBAL_EXPEDITED from a + * non-registered process. + * @MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED: + * Register the process intent to receive + * MEMBARRIER_CMD_GLOBAL_EXPEDITED memory + * barriers. Always returns 0. * @MEMBARRIER_CMD_PRIVATE_EXPEDITED: * Execute a memory barrier on each running * thread belonging to the same process as the current @@ -51,7 +73,7 @@ * to and return from the system call * (non-running threads are de facto in such a * state). This only covers threads from the - * same processes as the caller thread. This + * same process as the caller thread. This * command returns 0 on success. The * "expedited" commands complete faster than * the non-expedited ones, they never block, @@ -64,18 +86,54 @@ * Register the process intent to use * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always * returns 0. + * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE: + * In addition to provide memory ordering + * guarantees described in + * MEMBARRIER_CMD_PRIVATE_EXPEDITED, ensure + * the caller thread, upon return from system + * call, that all its running threads siblings + * have executed a core serializing + * instruction. (architectures are required to + * guarantee that non-running threads issue + * core serializing instructions before they + * resume user-space execution). This only + * covers threads from the same process as the + * caller thread. This command returns 0 on + * success. The "expedited" commands complete + * faster than the non-expedited ones, they + * never block, but have the downside of + * causing extra overhead. If this command is + * not implemented by an architecture, -EINVAL + * is returned. A process needs to register its + * intent to use the private expedited sync + * core command prior to using it, otherwise + * this command returns -EPERM. + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE: + * Register the process intent to use + * MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE. + * If this command is not implemented by an + * architecture, -EINVAL is returned. + * Returns 0 on success. + * @MEMBARRIER_CMD_SHARED: + * Alias to MEMBARRIER_CMD_GLOBAL. Provided for + * header backward compatibility. * * Command to be passed to the membarrier system call. The commands need to * be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to * the value 0. */ enum membarrier_cmd { - MEMBARRIER_CMD_QUERY = 0, - MEMBARRIER_CMD_SHARED = (1 << 0), - /* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */ - /* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */ - MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), - MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), + MEMBARRIER_CMD_QUERY = 0, + MEMBARRIER_CMD_GLOBAL = (1 << 0), + MEMBARRIER_CMD_GLOBAL_EXPEDITED = (1 << 1), + MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED = (1 << 2), + MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), + MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 5), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 6), + + /* Alias for header backward compatibility. */ + MEMBARRIER_CMD_SHARED = MEMBARRIER_CMD_GLOBAL, }; #endif /* _UAPI_LINUX_MEMBARRIER_H */ diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 760e52a9640f..b3bcabe380da 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -88,6 +88,9 @@ (((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT) #define PSCI_VERSION_MINOR(ver) \ ((ver) & PSCI_VERSION_MINOR_MASK) +#define PSCI_VERSION(maj, min) \ + ((((maj) << PSCI_VERSION_MAJOR_SHIFT) & PSCI_VERSION_MAJOR_MASK) | \ + ((min) & PSCI_VERSION_MINOR_MASK)) /* PSCI features decoding (>=1.0) */ #define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT 1 diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h new file mode 100644 index 000000000000..3d77fe91239a --- /dev/null +++ b/include/uapi/linux/psp-sev.h @@ -0,0 +1,142 @@ +/* + * Userspace interface for AMD Secure Encrypted Virtualization (SEV) + * platform management commands. + * + * Copyright (C) 2016-2017 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * SEV spec 0.14 is available at: + * http://support.amd.com/TechDocs/55766_SEV-KM%20API_Specification.pdf + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __PSP_SEV_USER_H__ +#define __PSP_SEV_USER_H__ + +#include <linux/types.h> + +/** + * SEV platform commands + */ +enum { + SEV_FACTORY_RESET = 0, + SEV_PLATFORM_STATUS, + SEV_PEK_GEN, + SEV_PEK_CSR, + SEV_PDH_GEN, + SEV_PDH_CERT_EXPORT, + SEV_PEK_CERT_IMPORT, + + SEV_MAX, +}; + +/** + * SEV Firmware status code + */ +typedef enum { + SEV_RET_SUCCESS = 0, + SEV_RET_INVALID_PLATFORM_STATE, + SEV_RET_INVALID_GUEST_STATE, + SEV_RET_INAVLID_CONFIG, + SEV_RET_INVALID_len, + SEV_RET_ALREADY_OWNED, + SEV_RET_INVALID_CERTIFICATE, + SEV_RET_POLICY_FAILURE, + SEV_RET_INACTIVE, + SEV_RET_INVALID_ADDRESS, + SEV_RET_BAD_SIGNATURE, + SEV_RET_BAD_MEASUREMENT, + SEV_RET_ASID_OWNED, + SEV_RET_INVALID_ASID, + SEV_RET_WBINVD_REQUIRED, + SEV_RET_DFFLUSH_REQUIRED, + SEV_RET_INVALID_GUEST, + SEV_RET_INVALID_COMMAND, + SEV_RET_ACTIVE, + SEV_RET_HWSEV_RET_PLATFORM, + SEV_RET_HWSEV_RET_UNSAFE, + SEV_RET_UNSUPPORTED, + SEV_RET_MAX, +} sev_ret_code; + +/** + * struct sev_user_data_status - PLATFORM_STATUS command parameters + * + * @major: major API version + * @minor: minor API version + * @state: platform state + * @flags: platform config flags + * @build: firmware build id for API version + * @guest_count: number of active guests + */ +struct sev_user_data_status { + __u8 api_major; /* Out */ + __u8 api_minor; /* Out */ + __u8 state; /* Out */ + __u32 flags; /* Out */ + __u8 build; /* Out */ + __u32 guest_count; /* Out */ +} __packed; + +/** + * struct sev_user_data_pek_csr - PEK_CSR command parameters + * + * @address: PEK certificate chain + * @length: length of certificate + */ +struct sev_user_data_pek_csr { + __u64 address; /* In */ + __u32 length; /* In/Out */ +} __packed; + +/** + * struct sev_user_data_cert_import - PEK_CERT_IMPORT command parameters + * + * @pek_address: PEK certificate chain + * @pek_len: length of PEK certificate + * @oca_address: OCA certificate chain + * @oca_len: length of OCA certificate + */ +struct sev_user_data_pek_cert_import { + __u64 pek_cert_address; /* In */ + __u32 pek_cert_len; /* In */ + __u64 oca_cert_address; /* In */ + __u32 oca_cert_len; /* In */ +} __packed; + +/** + * struct sev_user_data_pdh_cert_export - PDH_CERT_EXPORT command parameters + * + * @pdh_address: PDH certificate address + * @pdh_len: length of PDH certificate + * @cert_chain_address: PDH certificate chain + * @cert_chain_len: length of PDH certificate chain + */ +struct sev_user_data_pdh_cert_export { + __u64 pdh_cert_address; /* In */ + __u32 pdh_cert_len; /* In/Out */ + __u64 cert_chain_address; /* In */ + __u32 cert_chain_len; /* In/Out */ +} __packed; + +/** + * struct sev_issue_cmd - SEV ioctl parameters + * + * @cmd: SEV commands to execute + * @opaque: pointer to the command structure + * @error: SEV FW return code on failure + */ +struct sev_issue_cmd { + __u32 cmd; /* In */ + __u64 data; /* In */ + __u32 error; /* Out */ +} __packed; + +#define SEV_IOC_TYPE 'S' +#define SEV_ISSUE_CMD _IOWR(SEV_IOC_TYPE, 0x0, struct sev_issue_cmd) + +#endif /* __PSP_USER_SEV_H */ diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index 5c04130bb524..e5a7eecef7c3 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -19,7 +19,6 @@ #define _UAPI_LINUX_UUID_H_ #include <linux/types.h> -#include <linux/string.h> typedef struct { __u8 b[16]; diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index 343d7ddefe04..4e8b8304b793 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -52,7 +52,8 @@ struct virtio_balloon_config { #define VIRTIO_BALLOON_S_MEMFREE 4 /* Total amount of free memory */ #define VIRTIO_BALLOON_S_MEMTOT 5 /* Total amount of memory */ #define VIRTIO_BALLOON_S_AVAIL 6 /* Available memory as in /proc */ -#define VIRTIO_BALLOON_S_NR 7 +#define VIRTIO_BALLOON_S_CACHES 7 /* Disk caches */ +#define VIRTIO_BALLOON_S_NR 8 /* * Memory statistics structure. diff --git a/include/video/udlfb.h b/include/video/udlfb.h index 1252a7a89bc0..0cabe6b09095 100644 --- a/include/video/udlfb.h +++ b/include/video/udlfb.h @@ -19,7 +19,7 @@ struct dloarea { struct urb_node { struct list_head entry; - struct dlfb_data *dev; + struct dlfb_data *dlfb; struct delayed_work release_urb_work; struct urb *urb; }; @@ -35,7 +35,6 @@ struct urb_list { struct dlfb_data { struct usb_device *udev; - struct device *gdev; /* &udev->dev */ struct fb_info *info; struct urb_list urbs; struct kref kref; diff --git a/init/Kconfig b/init/Kconfig index a9a2e2c86671..e37f4b2a6445 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1412,6 +1412,12 @@ config USERFAULTFD Enable the userfaultfd() system call that allows to intercept and handle page faults in userland. +config ARCH_HAS_MEMBARRIER_CALLBACKS + bool + +config ARCH_HAS_MEMBARRIER_SYNC_CORE + bool + config EMBEDDED bool "Embedded system" option allnoconfig_y @@ -1915,3 +1921,6 @@ config ASN1 functions to call on what tags. source "kernel/Kconfig.locks" + +config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE + bool diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 690ae6665500..d7f309f74dec 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -578,10 +578,10 @@ static __poll_t mqueue_poll_file(struct file *filp, struct poll_table_struct *po spin_lock(&info->lock); if (info->attr.mq_curmsgs) - retval = POLLIN | POLLRDNORM; + retval = EPOLLIN | EPOLLRDNORM; if (info->attr.mq_curmsgs < info->attr.mq_maxmsg) - retval |= POLLOUT | POLLWRNORM; + retval |= EPOLLOUT | EPOLLWRNORM; spin_unlock(&info->lock); return retval; @@ -596,7 +596,7 @@ static void wq_add(struct mqueue_inode_info *info, int sr, ewp->task = current; list_for_each_entry(walk, &info->e_wait_q[sr].list, list) { - if (walk->task->static_prio <= current->static_prio) { + if (walk->task->prio <= current->prio) { list_add_tail(&ewp->list, &walk->list); return; } diff --git a/ipc/msg.c b/ipc/msg.c index 1bbc029d2b17..0dcc6699dc53 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -476,9 +476,9 @@ static int msgctl_info(struct ipc_namespace *ns, int msqid, static int msgctl_stat(struct ipc_namespace *ns, int msqid, int cmd, struct msqid64_ds *p) { - int err; struct msg_queue *msq; - int success_return; + int id = 0; + int err; memset(p, 0, sizeof(*p)); @@ -489,14 +489,13 @@ static int msgctl_stat(struct ipc_namespace *ns, int msqid, err = PTR_ERR(msq); goto out_unlock; } - success_return = msq->q_perm.id; + id = msq->q_perm.id; } else { msq = msq_obtain_object_check(ns, msqid); if (IS_ERR(msq)) { err = PTR_ERR(msq); goto out_unlock; } - success_return = 0; } err = -EACCES; @@ -507,6 +506,14 @@ static int msgctl_stat(struct ipc_namespace *ns, int msqid, if (err) goto out_unlock; + ipc_lock_object(&msq->q_perm); + + if (!ipc_valid_object(&msq->q_perm)) { + ipc_unlock_object(&msq->q_perm); + err = -EIDRM; + goto out_unlock; + } + kernel_to_ipc64_perm(&msq->q_perm, &p->msg_perm); p->msg_stime = msq->q_stime; p->msg_rtime = msq->q_rtime; @@ -516,9 +523,10 @@ static int msgctl_stat(struct ipc_namespace *ns, int msqid, p->msg_qbytes = msq->q_qbytes; p->msg_lspid = msq->q_lspid; p->msg_lrpid = msq->q_lrpid; - rcu_read_unlock(); - return success_return; + ipc_unlock_object(&msq->q_perm); + rcu_read_unlock(); + return id; out_unlock: rcu_read_unlock(); diff --git a/ipc/sem.c b/ipc/sem.c index 87bd38f38dc3..a4af04979fd2 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1213,10 +1213,20 @@ static int semctl_stat(struct ipc_namespace *ns, int semid, if (err) goto out_unlock; + ipc_lock_object(&sma->sem_perm); + + if (!ipc_valid_object(&sma->sem_perm)) { + ipc_unlock_object(&sma->sem_perm); + err = -EIDRM; + goto out_unlock; + } + kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm); semid64->sem_otime = get_semotime(sma); semid64->sem_ctime = sma->sem_ctime; semid64->sem_nsems = sma->sem_nsems; + + ipc_unlock_object(&sma->sem_perm); rcu_read_unlock(); return id; diff --git a/ipc/shm.c b/ipc/shm.c index 7acda23430aa..4643865e9171 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -909,9 +909,11 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *tbuf) { struct shmid_kernel *shp; - int result; + int id = 0; int err; + memset(tbuf, 0, sizeof(*tbuf)); + rcu_read_lock(); if (cmd == SHM_STAT) { shp = shm_obtain_object(ns, shmid); @@ -919,14 +921,13 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid, err = PTR_ERR(shp); goto out_unlock; } - result = shp->shm_perm.id; + id = shp->shm_perm.id; } else { shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } - result = 0; } err = -EACCES; @@ -937,7 +938,14 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid, if (err) goto out_unlock; - memset(tbuf, 0, sizeof(*tbuf)); + ipc_lock_object(&shp->shm_perm); + + if (!ipc_valid_object(&shp->shm_perm)) { + ipc_unlock_object(&shp->shm_perm); + err = -EIDRM; + goto out_unlock; + } + kernel_to_ipc64_perm(&shp->shm_perm, &tbuf->shm_perm); tbuf->shm_segsz = shp->shm_segsz; tbuf->shm_atime = shp->shm_atim; @@ -946,8 +954,10 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid, tbuf->shm_cpid = shp->shm_cprid; tbuf->shm_lpid = shp->shm_lprid; tbuf->shm_nattch = shp->shm_nattch; + + ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); - return result; + return id; out_unlock: rcu_read_unlock(); diff --git a/ipc/util.c b/ipc/util.c index ff045fec8d83..4ed5a17dd06f 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -23,9 +23,12 @@ * tree. * - perform initial checks (capabilities, auditing and permission, * etc). - * - perform read-only operations, such as STAT, INFO commands. + * - perform read-only operations, such as INFO command, that + * do not demand atomicity * acquire the ipc lock (kern_ipc_perm.lock) through * ipc_lock_object() + * - perform read-only operations that demand atomicity, + * such as STAT command. * - perform data updates, such as SET, RMID commands and * mechanism-specific operations (semop/semtimedop, * msgsnd/msgrcv, shmat/shmdt). diff --git a/kernel/async.c b/kernel/async.c index 2cbd3dd5940d..a893d6170944 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -84,20 +84,24 @@ static atomic_t entry_count; static async_cookie_t lowest_in_progress(struct async_domain *domain) { - struct list_head *pending; + struct async_entry *first = NULL; async_cookie_t ret = ASYNC_COOKIE_MAX; unsigned long flags; spin_lock_irqsave(&async_lock, flags); - if (domain) - pending = &domain->pending; - else - pending = &async_global_pending; + if (domain) { + if (!list_empty(&domain->pending)) + first = list_first_entry(&domain->pending, + struct async_entry, domain_list); + } else { + if (!list_empty(&async_global_pending)) + first = list_first_entry(&async_global_pending, + struct async_entry, global_list); + } - if (!list_empty(pending)) - ret = list_first_entry(pending, struct async_entry, - domain_list)->cookie; + if (first) + ret = first->cookie; spin_unlock_irqrestore(&async_lock, flags); return ret; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5f35f93dcab2..29ca9208dcfa 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1576,25 +1576,41 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, __u32 __user *prog_ids, u32 cnt) { struct bpf_prog **prog; - u32 i = 0, id; - + unsigned long err = 0; + u32 i = 0, *ids; + bool nospc; + + /* users of this function are doing: + * cnt = bpf_prog_array_length(); + * if (cnt > 0) + * bpf_prog_array_copy_to_user(..., cnt); + * so below kcalloc doesn't need extra cnt > 0 check, but + * bpf_prog_array_length() releases rcu lock and + * prog array could have been swapped with empty or larger array, + * so always copy 'cnt' prog_ids to the user. + * In a rare race the user will see zero prog_ids + */ + ids = kcalloc(cnt, sizeof(u32), GFP_USER); + if (!ids) + return -ENOMEM; rcu_read_lock(); prog = rcu_dereference(progs)->progs; for (; *prog; prog++) { if (*prog == &dummy_bpf_prog.prog) continue; - id = (*prog)->aux->id; - if (copy_to_user(prog_ids + i, &id, sizeof(id))) { - rcu_read_unlock(); - return -EFAULT; - } + ids[i] = (*prog)->aux->id; if (++i == cnt) { prog++; break; } } + nospc = !!(*prog); rcu_read_unlock(); - if (*prog) + err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); + kfree(ids); + if (err) + return -EFAULT; + if (nospc) return -ENOSPC; return 0; } diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 0314d1783d77..48c33417d13c 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -86,9 +86,10 @@ struct smap_psock { struct work_struct tx_work; struct work_struct gc_work; + struct proto *sk_proto; + void (*save_close)(struct sock *sk, long timeout); void (*save_data_ready)(struct sock *sk); void (*save_write_space)(struct sock *sk); - void (*save_state_change)(struct sock *sk); }; static inline struct smap_psock *smap_psock_sk(const struct sock *sk) @@ -96,12 +97,102 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +static struct proto tcp_bpf_proto; +static int bpf_tcp_init(struct sock *sk) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + return -EINVAL; + } + + if (unlikely(psock->sk_proto)) { + rcu_read_unlock(); + return -EBUSY; + } + + psock->save_close = sk->sk_prot->close; + psock->sk_proto = sk->sk_prot; + sk->sk_prot = &tcp_bpf_proto; + rcu_read_unlock(); + return 0; +} + +static void bpf_tcp_release(struct sock *sk) +{ + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + + if (likely(psock)) { + sk->sk_prot = psock->sk_proto; + psock->sk_proto = NULL; + } + rcu_read_unlock(); +} + +static void smap_release_sock(struct smap_psock *psock, struct sock *sock); + +static void bpf_tcp_close(struct sock *sk, long timeout) +{ + void (*close_fun)(struct sock *sk, long timeout); + struct smap_psock_map_entry *e, *tmp; + struct smap_psock *psock; + struct sock *osk; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + return sk->sk_prot->close(sk, timeout); + } + + /* The psock may be destroyed anytime after exiting the RCU critial + * section so by the time we use close_fun the psock may no longer + * be valid. However, bpf_tcp_close is called with the sock lock + * held so the close hook and sk are still valid. + */ + close_fun = psock->save_close; + + write_lock_bh(&sk->sk_callback_lock); + list_for_each_entry_safe(e, tmp, &psock->maps, list) { + osk = cmpxchg(e->entry, sk, NULL); + if (osk == sk) { + list_del(&e->list); + smap_release_sock(psock, sk); + } + } + write_unlock_bh(&sk->sk_callback_lock); + rcu_read_unlock(); + close_fun(sk, timeout); +} + enum __sk_action { __SK_DROP = 0, __SK_PASS, __SK_REDIRECT, }; +static struct tcp_ulp_ops bpf_tcp_ulp_ops __read_mostly = { + .name = "bpf_tcp", + .uid = TCP_ULP_BPF, + .user_visible = false, + .owner = NULL, + .init = bpf_tcp_init, + .release = bpf_tcp_release, +}; + +static int bpf_tcp_ulp_register(void) +{ + tcp_bpf_proto = tcp_prot; + tcp_bpf_proto.close = bpf_tcp_close; + return tcp_register_ulp(&bpf_tcp_ulp_ops); +} + static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) { struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); @@ -166,68 +257,6 @@ static void smap_report_sk_error(struct smap_psock *psock, int err) sk->sk_error_report(sk); } -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); - -/* Called with lock_sock(sk) held */ -static void smap_state_change(struct sock *sk) -{ - struct smap_psock_map_entry *e, *tmp; - struct smap_psock *psock; - struct socket_wq *wq; - struct sock *osk; - - rcu_read_lock(); - - /* Allowing transitions into an established syn_recv states allows - * for early binding sockets to a smap object before the connection - * is established. - */ - switch (sk->sk_state) { - case TCP_SYN_SENT: - case TCP_SYN_RECV: - case TCP_ESTABLISHED: - break; - case TCP_CLOSE_WAIT: - case TCP_CLOSING: - case TCP_LAST_ACK: - case TCP_FIN_WAIT1: - case TCP_FIN_WAIT2: - case TCP_LISTEN: - break; - case TCP_CLOSE: - /* Only release if the map entry is in fact the sock in - * question. There is a case where the operator deletes - * the sock from the map, but the TCP sock is closed before - * the psock is detached. Use cmpxchg to verify correct - * sock is removed. - */ - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - break; - write_lock_bh(&sk->sk_callback_lock); - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - osk = cmpxchg(e->entry, sk, NULL); - if (osk == sk) { - list_del(&e->list); - smap_release_sock(psock, sk); - } - } - write_unlock_bh(&sk->sk_callback_lock); - break; - default: - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - break; - smap_report_sk_error(psock, EPIPE); - break; - } - - wq = rcu_dereference(sk->sk_wq); - if (skwq_has_sleeper(wq)) - wake_up_interruptible_all(&wq->wait); - rcu_read_unlock(); -} - static void smap_read_sock_strparser(struct strparser *strp, struct sk_buff *skb) { @@ -322,10 +351,8 @@ static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) return; sk->sk_data_ready = psock->save_data_ready; sk->sk_write_space = psock->save_write_space; - sk->sk_state_change = psock->save_state_change; psock->save_data_ready = NULL; psock->save_write_space = NULL; - psock->save_state_change = NULL; strp_stop(&psock->strp); psock->strp_enabled = false; } @@ -350,6 +377,7 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock) if (psock->refcnt) return; + tcp_cleanup_ulp(sock); smap_stop_sock(psock, sock); clear_bit(SMAP_TX_RUNNING, &psock->state); rcu_assign_sk_user_data(sock, NULL); @@ -427,10 +455,8 @@ static void smap_start_sock(struct smap_psock *psock, struct sock *sk) return; psock->save_data_ready = sk->sk_data_ready; psock->save_write_space = sk->sk_write_space; - psock->save_state_change = sk->sk_state_change; sk->sk_data_ready = smap_data_ready; sk->sk_write_space = smap_write_space; - sk->sk_state_change = smap_state_change; psock->strp_enabled = true; } @@ -509,6 +535,10 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) if (attr->value_size > KMALLOC_MAX_SIZE) return ERR_PTR(-E2BIG); + err = bpf_tcp_ulp_register(); + if (err && err != -EEXIST) + return ERR_PTR(err); + stab = kzalloc(sizeof(*stab), GFP_USER); if (!stab) return ERR_PTR(-ENOMEM); @@ -590,11 +620,6 @@ static void sock_map_free(struct bpf_map *map) } rcu_read_unlock(); - if (stab->bpf_verdict) - bpf_prog_put(stab->bpf_verdict); - if (stab->bpf_parse) - bpf_prog_put(stab->bpf_parse); - sock_map_remove_complete(stab); } @@ -754,6 +779,10 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, goto out_progs; } + err = tcp_set_ulp_id(sock, TCP_ULP_BPF); + if (err) + goto out_progs; + set_bit(SMAP_TX_RUNNING, &psock->state); } @@ -866,6 +895,19 @@ static int sock_map_update_elem(struct bpf_map *map, return err; } +static void sock_map_release(struct bpf_map *map, struct file *map_file) +{ + struct bpf_stab *stab = container_of(map, struct bpf_stab, map); + struct bpf_prog *orig; + + orig = xchg(&stab->bpf_parse, NULL); + if (orig) + bpf_prog_put(orig); + orig = xchg(&stab->bpf_verdict, NULL); + if (orig) + bpf_prog_put(orig); +} + const struct bpf_map_ops sock_map_ops = { .map_alloc = sock_map_alloc, .map_free = sock_map_free, @@ -873,6 +915,7 @@ const struct bpf_map_ops sock_map_ops = { .map_get_next_key = sock_map_get_next_key, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, + .map_release = sock_map_release, }; BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index f7efa7b4d825..b42037e6e81d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1254,9 +1254,9 @@ done: return retval; } -int current_cpuset_is_being_rebound(void) +bool current_cpuset_is_being_rebound(void) { - int ret; + bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; diff --git a/kernel/compat.c b/kernel/compat.c index d1cee656a7ed..3247fe761f60 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -355,7 +355,7 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - size_t retlen = min_t(size_t, len, cpumask_size()); + unsigned int retlen = min(len, cpumask_size()); if (compat_put_bitmap(user_mask_ptr, cpumask_bits(mask), retlen * 8)) ret = -EFAULT; diff --git a/kernel/configs/kvm_guest.config b/kernel/configs/kvm_guest.config index 8d9643767142..108fecc20fc1 100644 --- a/kernel/configs/kvm_guest.config +++ b/kernel/configs/kvm_guest.config @@ -18,6 +18,7 @@ CONFIG_VIRTUALIZATION=y CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y CONFIG_KVM_GUEST=y +CONFIG_S390_GUEST=y CONFIG_VIRTIO=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BLK=y diff --git a/kernel/configs/tiny.config b/kernel/configs/tiny.config index 7fa0c4ae6394..9bfdffc100da 100644 --- a/kernel/configs/tiny.config +++ b/kernel/configs/tiny.config @@ -10,3 +10,7 @@ CONFIG_OPTIMIZE_INLINING=y # CONFIG_SLAB is not set # CONFIG_SLUB is not set CONFIG_SLOB=y +CONFIG_CC_STACKPROTECTOR_NONE=y +# CONFIG_CC_STACKPROTECTOR_REGULAR is not set +# CONFIG_CC_STACKPROTECTOR_STRONG is not set +# CONFIG_CC_STACKPROTECTOR_AUTO is not set diff --git a/kernel/events/core.c b/kernel/events/core.c index f0549e79978b..96db9ae5d5af 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4524,7 +4524,7 @@ static __poll_t perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; struct ring_buffer *rb; - __poll_t events = POLLHUP; + __poll_t events = EPOLLHUP; poll_wait(file, &event->waitq, wait); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 141aa2ca8728..6c6b3c48db71 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -19,7 +19,7 @@ static void perf_output_wakeup(struct perf_output_handle *handle) { - atomic_set(&handle->rb->poll, POLLIN); + atomic_set(&handle->rb->poll, EPOLLIN); handle->event->pending_wakeup = 1; irq_work_queue(&handle->event->pending); diff --git a/kernel/fork.c b/kernel/fork.c index 5c372c954f3b..be8aa5b98666 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -606,6 +606,11 @@ static void __mmdrop(struct mm_struct *mm) void mmdrop(struct mm_struct *mm) { + /* + * The implicit full barrier implied by atomic_dec_and_test() is + * required by the membarrier system call before returning to + * user-space, after storing to rq->curr. + */ if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } @@ -1587,6 +1592,10 @@ static __latent_entropy struct task_struct *copy_process( int retval; struct task_struct *p; + /* + * Don't allow sharing the root directory with processes in a different + * namespace + */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); @@ -2062,6 +2071,8 @@ long _do_fork(unsigned long clone_flags, int __user *child_tidptr, unsigned long tls) { + struct completion vfork; + struct pid *pid; struct task_struct *p; int trace = 0; long nr; @@ -2087,43 +2098,40 @@ long _do_fork(unsigned long clone_flags, p = copy_process(clone_flags, stack_start, stack_size, child_tidptr, NULL, trace, tls, NUMA_NO_NODE); add_latent_entropy(); + + if (IS_ERR(p)) + return PTR_ERR(p); + /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ - if (!IS_ERR(p)) { - struct completion vfork; - struct pid *pid; - - trace_sched_process_fork(current, p); + trace_sched_process_fork(current, p); - pid = get_task_pid(p, PIDTYPE_PID); - nr = pid_vnr(pid); + pid = get_task_pid(p, PIDTYPE_PID); + nr = pid_vnr(pid); - if (clone_flags & CLONE_PARENT_SETTID) - put_user(nr, parent_tidptr); + if (clone_flags & CLONE_PARENT_SETTID) + put_user(nr, parent_tidptr); - if (clone_flags & CLONE_VFORK) { - p->vfork_done = &vfork; - init_completion(&vfork); - get_task_struct(p); - } - - wake_up_new_task(p); + if (clone_flags & CLONE_VFORK) { + p->vfork_done = &vfork; + init_completion(&vfork); + get_task_struct(p); + } - /* forking complete and child started to run, tell ptracer */ - if (unlikely(trace)) - ptrace_event_pid(trace, pid); + wake_up_new_task(p); - if (clone_flags & CLONE_VFORK) { - if (!wait_for_vfork_done(p, &vfork)) - ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); - } + /* forking complete and child started to run, tell ptracer */ + if (unlikely(trace)) + ptrace_event_pid(trace, pid); - put_pid(pid); - } else { - nr = PTR_ERR(p); + if (clone_flags & CLONE_VFORK) { + if (!wait_for_vfork_done(p, &vfork)) + ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } + + put_pid(pid); return nr; } diff --git a/kernel/futex.c b/kernel/futex.c index 7f719d110908..1f450e092c74 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -862,24 +862,6 @@ static void put_pi_state(struct futex_pi_state *pi_state) } } -/* - * Look up the task based on what TID userspace gave us. - * We dont trust it. - */ -static struct task_struct *futex_find_get_task(pid_t pid) -{ - struct task_struct *p; - - rcu_read_lock(); - p = find_task_by_vpid(pid); - if (p) - get_task_struct(p); - - rcu_read_unlock(); - - return p; -} - #ifdef CONFIG_FUTEX_PI /* @@ -1183,7 +1165,7 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, */ if (!pid) return -ESRCH; - p = futex_find_get_task(pid); + p = find_get_task_by_vpid(pid); if (!p) return -ESRCH; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index ef2a47e0eab6..6cdecc6f4c53 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -10,7 +10,6 @@ #include <linux/jiffies.h> #include <linux/irq.h> #include <linux/module.h> -#include <linux/kallsyms.h> #include <linux/interrupt.h> #include <linux/moduleparam.h> #include <linux/timer.h> diff --git a/kernel/kcov.c b/kernel/kcov.c index 7594c033d98a..2c16f1ab5e10 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -358,7 +358,8 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, */ if (kcov->mode != KCOV_MODE_INIT || !kcov->area) return -EINVAL; - if (kcov->t != NULL) + t = current; + if (kcov->t != NULL || t->kcov != NULL) return -EBUSY; if (arg == KCOV_TRACE_PC) kcov->mode = KCOV_MODE_TRACE_PC; @@ -370,7 +371,6 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, #endif else return -EINVAL; - t = current; /* Cache in task struct for performance. */ t->kcov_size = kcov->size; t->kcov_area = kcov->area; diff --git a/kernel/module.c b/kernel/module.c index ccdf24c4949e..ad2d420024f6 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3804,6 +3804,7 @@ static int load_module(struct load_info *info, const char __user *uargs, module_disable_nx(mod); ddebug_cleanup: + ftrace_release_mod(mod); dynamic_debug_remove(mod, info->debug); synchronize_sched(); kfree(mod->args); @@ -3823,12 +3824,6 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_sched(); mutex_unlock(&module_mutex); free_module: - /* - * Ftrace needs to clean up what it initialized. - * This does nothing if ftrace_module_init() wasn't called, - * but it must be called outside of module_mutex. - */ - ftrace_release_mod(mod); /* Free lock-classes; relies on the preceding sync_rcu() */ lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); diff --git a/kernel/pid.c b/kernel/pid.c index 5d30c87e3c42..ed6c343fe50d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -343,6 +343,19 @@ struct task_struct *find_task_by_vpid(pid_t vnr) return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } +struct task_struct *find_get_task_by_vpid(pid_t nr) +{ + struct task_struct *task; + + rcu_read_lock(); + task = find_task_by_vpid(nr); + if (task) + get_task_struct(task); + rcu_read_unlock(); + + return task; +} + struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index db4b9b8929eb..fc1123583fa6 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -930,7 +930,7 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) __poll_t ret = 0; if (!user) - return POLLERR|POLLNVAL; + return EPOLLERR|EPOLLNVAL; poll_wait(file, &log_wait, wait); @@ -938,9 +938,9 @@ static __poll_t devkmsg_poll(struct file *file, poll_table *wait) if (user->seq < log_next_seq) { /* return error when data has vanished underneath us */ if (user->seq < log_first_seq) - ret = POLLIN|POLLRDNORM|POLLERR|POLLPRI; + ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else - ret = POLLIN|POLLRDNORM; + ret = EPOLLIN|EPOLLRDNORM; } logbuf_unlock_irq(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 5e1d713c8e61..21fec73d45d4 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -1103,21 +1103,6 @@ int ptrace_request(struct task_struct *child, long request, return ret; } -static struct task_struct *ptrace_get_task_struct(pid_t pid) -{ - struct task_struct *child; - - rcu_read_lock(); - child = find_task_by_vpid(pid); - if (child) - get_task_struct(child); - rcu_read_unlock(); - - if (!child) - return ERR_PTR(-ESRCH); - return child; -} - #ifndef arch_ptrace_attach #define arch_ptrace_attach(child) do { } while (0) #endif @@ -1135,9 +1120,9 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, goto out; } - child = ptrace_get_task_struct(pid); - if (IS_ERR(child)) { - ret = PTR_ERR(child); + child = find_get_task_by_vpid(pid); + if (!child) { + ret = -ESRCH; goto out; } @@ -1281,9 +1266,9 @@ COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, goto out; } - child = ptrace_get_task_struct(pid); - if (IS_ERR(child)) { - ret = PTR_ERR(child); + child = find_get_task_by_vpid(pid); + if (!child) { + ret = -ESRCH; goto out; } diff --git a/kernel/relay.c b/kernel/relay.c index 41280033a4c5..c3029402f15c 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -611,7 +611,6 @@ free_bufs: kref_put(&chan->kref, relay_destroy_channel); mutex_unlock(&relay_channels_mutex); - kfree(chan); return NULL; } EXPORT_SYMBOL_GPL(relay_open); @@ -925,12 +924,12 @@ static __poll_t relay_file_poll(struct file *filp, poll_table *wait) struct rchan_buf *buf = filp->private_data; if (buf->finalized) - return POLLERR; + return EPOLLERR; if (filp->f_mode & FMODE_READ) { poll_wait(filp, &buf->read_wait, wait); if (!relay_buf_empty(buf)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } return mask; diff --git a/kernel/resource.c b/kernel/resource.c index 8c527d83ca76..e270b5048988 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1576,17 +1576,17 @@ static int strict_iomem_checks; /* * check if an address is reserved in the iomem resource tree - * returns 1 if reserved, 0 if not reserved. + * returns true if reserved, false if not reserved. */ -int iomem_is_exclusive(u64 addr) +bool iomem_is_exclusive(u64 addr) { struct resource *p = &iomem_resource; - int err = 0; + bool err = false; loff_t l; int size = PAGE_SIZE; if (!strict_iomem_checks) - return 0; + return false; addr = addr & PAGE_MASK; @@ -1609,7 +1609,7 @@ int iomem_is_exclusive(u64 addr) continue; if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM) || p->flags & IORESOURCE_EXCLUSIVE) { - err = 1; + err = true; break; } } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3da7a2444a91..bf724c1952ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1630,16 +1630,16 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) #ifdef CONFIG_SMP if (cpu == rq->cpu) { - schedstat_inc(rq->ttwu_local); - schedstat_inc(p->se.statistics.nr_wakeups_local); + __schedstat_inc(rq->ttwu_local); + __schedstat_inc(p->se.statistics.nr_wakeups_local); } else { struct sched_domain *sd; - schedstat_inc(p->se.statistics.nr_wakeups_remote); + __schedstat_inc(p->se.statistics.nr_wakeups_remote); rcu_read_lock(); for_each_domain(rq->cpu, sd) { if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - schedstat_inc(sd->ttwu_wake_remote); + __schedstat_inc(sd->ttwu_wake_remote); break; } } @@ -1647,14 +1647,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) } if (wake_flags & WF_MIGRATED) - schedstat_inc(p->se.statistics.nr_wakeups_migrate); + __schedstat_inc(p->se.statistics.nr_wakeups_migrate); #endif /* CONFIG_SMP */ - schedstat_inc(rq->ttwu_count); - schedstat_inc(p->se.statistics.nr_wakeups); + __schedstat_inc(rq->ttwu_count); + __schedstat_inc(p->se.statistics.nr_wakeups); if (wake_flags & WF_SYNC) - schedstat_inc(p->se.statistics.nr_wakeups_sync); + __schedstat_inc(p->se.statistics.nr_wakeups_sync); } static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) @@ -2461,6 +2461,7 @@ void wake_up_new_task(struct task_struct *p) * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, * as we're not fully set-up yet. */ + p->recent_used_cpu = task_cpu(p); __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif rq = __task_rq_lock(p, &rf); @@ -2698,23 +2699,27 @@ static struct rq *finish_task_switch(struct task_struct *prev) prev_state = prev->state; vtime_task_switch(prev); perf_event_task_sched_in(prev, current); - /* - * The membarrier system call requires a full memory barrier - * after storing to rq->curr, before going back to user-space. - * - * TODO: This smp_mb__after_unlock_lock can go away if PPC end - * up adding a full barrier to switch_mm(), or we should figure - * out if a smp_mb__after_unlock_lock is really the proper API - * to use. - */ - smp_mb__after_unlock_lock(); finish_task(prev); finish_lock_switch(rq); finish_arch_post_lock_switch(); fire_sched_in_preempt_notifiers(current); - if (mm) + /* + * When switching through a kernel thread, the loop in + * membarrier_{private,global}_expedited() may have observed that + * kernel thread and not issued an IPI. It is therefore possible to + * schedule between user->kernel->user threads without passing though + * switch_mm(). Membarrier requires a barrier after storing to + * rq->curr, before returning to userspace, so provide them here: + * + * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly + * provided by mmdrop(), + * - a sync_core for SYNC_CORE. + */ + if (mm) { + membarrier_mm_sync_core_before_usermode(mm); mmdrop(mm); + } if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); @@ -2818,6 +2823,13 @@ context_switch(struct rq *rq, struct task_struct *prev, */ arch_start_context_switch(prev); + /* + * If mm is non-NULL, we pass through switch_mm(). If mm is + * NULL, we will pass through mmdrop() in finish_task_switch(). + * Both of these contain the full memory barrier required by + * membarrier after storing to rq->curr, before returning to + * user-space. + */ if (!mm) { next->active_mm = oldmm; mmgrab(oldmm); @@ -3354,6 +3366,9 @@ static void __sched notrace __schedule(bool preempt) * Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) * done by the caller to avoid the race with signal_wake_up(). + * + * The membarrier system call requires a full memory barrier + * after coming from user-space, before storing to rq->curr. */ rq_lock(rq, &rf); smp_mb__after_spinlock(); @@ -3401,17 +3416,16 @@ static void __sched notrace __schedule(bool preempt) /* * The membarrier system call requires each architecture * to have a full memory barrier after updating - * rq->curr, before returning to user-space. For TSO - * (e.g. x86), the architecture must provide its own - * barrier in switch_mm(). For weakly ordered machines - * for which spin_unlock() acts as a full memory - * barrier, finish_lock_switch() in common code takes - * care of this barrier. For weakly ordered machines for - * which spin_unlock() acts as a RELEASE barrier (only - * arm64 and PowerPC), arm64 has a full barrier in - * switch_to(), and PowerPC has - * smp_mb__after_unlock_lock() before - * finish_lock_switch(). + * rq->curr, before returning to user-space. + * + * Here are the schemes providing that barrier on the + * various architectures: + * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC. + * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC. + * - finish_lock_switch() for weakly-ordered + * architectures where spin_unlock is a full barrier, + * - switch_to() for arm64 (weakly-ordered, spin_unlock + * is a RELEASE barrier), */ ++*switch_count; @@ -4853,7 +4867,7 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - size_t retlen = min_t(size_t, len, cpumask_size()); + unsigned int retlen = min(len, cpumask_size()); if (copy_to_user(user_mask_ptr, mask, retlen)) ret = -EFAULT; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7b6535987500..5eb3ffc9be84 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -871,7 +871,7 @@ update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) likely(wait_start > prev_wait_start)) wait_start -= prev_wait_start; - schedstat_set(se->statistics.wait_start, wait_start); + __schedstat_set(se->statistics.wait_start, wait_start); } static inline void @@ -893,17 +893,17 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) * time stamp can be adjusted to accumulate wait time * prior to migration. */ - schedstat_set(se->statistics.wait_start, delta); + __schedstat_set(se->statistics.wait_start, delta); return; } trace_sched_stat_wait(p, delta); } - schedstat_set(se->statistics.wait_max, + __schedstat_set(se->statistics.wait_max, max(schedstat_val(se->statistics.wait_max), delta)); - schedstat_inc(se->statistics.wait_count); - schedstat_add(se->statistics.wait_sum, delta); - schedstat_set(se->statistics.wait_start, 0); + __schedstat_inc(se->statistics.wait_count); + __schedstat_add(se->statistics.wait_sum, delta); + __schedstat_set(se->statistics.wait_start, 0); } static inline void @@ -928,10 +928,10 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) delta = 0; if (unlikely(delta > schedstat_val(se->statistics.sleep_max))) - schedstat_set(se->statistics.sleep_max, delta); + __schedstat_set(se->statistics.sleep_max, delta); - schedstat_set(se->statistics.sleep_start, 0); - schedstat_add(se->statistics.sum_sleep_runtime, delta); + __schedstat_set(se->statistics.sleep_start, 0); + __schedstat_add(se->statistics.sum_sleep_runtime, delta); if (tsk) { account_scheduler_latency(tsk, delta >> 10, 1); @@ -945,15 +945,15 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) delta = 0; if (unlikely(delta > schedstat_val(se->statistics.block_max))) - schedstat_set(se->statistics.block_max, delta); + __schedstat_set(se->statistics.block_max, delta); - schedstat_set(se->statistics.block_start, 0); - schedstat_add(se->statistics.sum_sleep_runtime, delta); + __schedstat_set(se->statistics.block_start, 0); + __schedstat_add(se->statistics.sum_sleep_runtime, delta); if (tsk) { if (tsk->in_iowait) { - schedstat_add(se->statistics.iowait_sum, delta); - schedstat_inc(se->statistics.iowait_count); + __schedstat_add(se->statistics.iowait_sum, delta); + __schedstat_inc(se->statistics.iowait_count); trace_sched_stat_iowait(tsk, delta); } @@ -1012,10 +1012,10 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) struct task_struct *tsk = task_of(se); if (tsk->state & TASK_INTERRUPTIBLE) - schedstat_set(se->statistics.sleep_start, + __schedstat_set(se->statistics.sleep_start, rq_clock(rq_of(cfs_rq))); if (tsk->state & TASK_UNINTERRUPTIBLE) - schedstat_set(se->statistics.block_start, + __schedstat_set(se->statistics.block_start, rq_clock(rq_of(cfs_rq))); } } @@ -5692,27 +5692,31 @@ static int wake_wide(struct task_struct *p) * scheduling latency of the CPUs. This seems to work * for the overloaded case. */ - -static bool -wake_affine_idle(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int prev_cpu, int sync) +static int +wake_affine_idle(int this_cpu, int prev_cpu, int sync) { /* * If this_cpu is idle, it implies the wakeup is from interrupt * context. Only allow the move if cache is shared. Otherwise an * interrupt intensive workload could force all tasks onto one * node depending on the IO topology or IRQ affinity settings. + * + * If the prev_cpu is idle and cache affine then avoid a migration. + * There is no guarantee that the cache hot data from an interrupt + * is more important than cache hot data on the prev_cpu and from + * a cpufreq perspective, it's better to have higher utilisation + * on one CPU. */ if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu)) - return true; + return idle_cpu(prev_cpu) ? prev_cpu : this_cpu; if (sync && cpu_rq(this_cpu)->nr_running == 1) - return true; + return this_cpu; - return false; + return nr_cpumask_bits; } -static bool +static int wake_affine_weight(struct sched_domain *sd, struct task_struct *p, int this_cpu, int prev_cpu, int sync) { @@ -5726,7 +5730,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, unsigned long current_load = task_h_load(current); if (current_load > this_eff_load) - return true; + return this_cpu; this_eff_load -= current_load; } @@ -5743,28 +5747,28 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; prev_eff_load *= capacity_of(this_cpu); - return this_eff_load <= prev_eff_load; + return this_eff_load <= prev_eff_load ? this_cpu : nr_cpumask_bits; } static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { int this_cpu = smp_processor_id(); - bool affine = false; + int target = nr_cpumask_bits; - if (sched_feat(WA_IDLE) && !affine) - affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_IDLE)) + target = wake_affine_idle(this_cpu, prev_cpu, sync); - if (sched_feat(WA_WEIGHT) && !affine) - affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits) + target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); - if (affine) { - schedstat_inc(sd->ttwu_move_affine); - schedstat_inc(p->se.statistics.nr_wakeups_affine); - } + if (target == nr_cpumask_bits) + return prev_cpu; - return affine; + schedstat_inc(sd->ttwu_move_affine); + schedstat_inc(p->se.statistics.nr_wakeups_affine); + return target; } static inline unsigned long task_util(struct task_struct *p); @@ -6193,7 +6197,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t static int select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; - int i; + int i, recent_used_cpu; if (idle_cpu(target)) return target; @@ -6204,6 +6208,21 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev)) return prev; + /* Check a recently used CPU as a potential idle candidate */ + recent_used_cpu = p->recent_used_cpu; + if (recent_used_cpu != prev && + recent_used_cpu != target && + cpus_share_cache(recent_used_cpu, target) && + idle_cpu(recent_used_cpu) && + cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { + /* + * Replace recent_used_cpu with prev as it is a potential + * candidate for the next wake. + */ + p->recent_used_cpu = prev; + return recent_used_cpu; + } + sd = rcu_dereference(per_cpu(sd_llc, target)); if (!sd) return target; @@ -6357,8 +6376,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (cpu == prev_cpu) goto pick_cpu; - if (wake_affine(affine_sd, p, prev_cpu, sync)) - new_cpu = cpu; + new_cpu = wake_affine(affine_sd, p, prev_cpu, sync); } if (sd && !(sd_flag & SD_BALANCE_FORK)) { @@ -6372,9 +6390,12 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (!sd) { pick_cpu: - if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */ + if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); + if (want_affine) + current->recent_used_cpu = cpu; + } } else { new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 9bcbacba82a8..5d0762633639 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -26,24 +26,110 @@ * Bitmask made from a "or" of all commands within enum membarrier_cmd, * except MEMBARRIER_CMD_QUERY. */ +#ifdef CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE +#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ + (MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE) +#else +#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK 0 +#endif + #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ - | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \ + | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ + | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK) static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ } -static int membarrier_private_expedited(void) +static int membarrier_global_expedited(void) { int cpu; bool fallback = false; cpumask_var_t tmpmask; - if (!(atomic_read(¤t->mm->membarrier_state) - & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) - return -EPERM; + if (num_online_cpus() == 1) + return 0; + + /* + * Matches memory barriers around rq->curr modification in + * scheduler. + */ + smp_mb(); /* system call entry is not a mb. */ + + /* + * Expedited membarrier commands guarantee that they won't + * block, hence the GFP_NOWAIT allocation flag and fallback + * implementation. + */ + if (!zalloc_cpumask_var(&tmpmask, GFP_NOWAIT)) { + /* Fallback for OOM. */ + fallback = true; + } + + cpus_read_lock(); + for_each_online_cpu(cpu) { + struct task_struct *p; + + /* + * Skipping the current CPU is OK even through we can be + * migrated at any point. The current CPU, at the point + * where we read raw_smp_processor_id(), is ensured to + * be in program order with respect to the caller + * thread. Therefore, we can skip this CPU from the + * iteration. + */ + if (cpu == raw_smp_processor_id()) + continue; + rcu_read_lock(); + p = task_rcu_dereference(&cpu_rq(cpu)->curr); + if (p && p->mm && (atomic_read(&p->mm->membarrier_state) & + MEMBARRIER_STATE_GLOBAL_EXPEDITED)) { + if (!fallback) + __cpumask_set_cpu(cpu, tmpmask); + else + smp_call_function_single(cpu, ipi_mb, NULL, 1); + } + rcu_read_unlock(); + } + if (!fallback) { + preempt_disable(); + smp_call_function_many(tmpmask, ipi_mb, NULL, 1); + preempt_enable(); + free_cpumask_var(tmpmask); + } + cpus_read_unlock(); + + /* + * Memory barrier on the caller thread _after_ we finished + * waiting for the last IPI. Matches memory barriers around + * rq->curr modification in scheduler. + */ + smp_mb(); /* exit from system call is not a mb */ + return 0; +} + +static int membarrier_private_expedited(int flags) +{ + int cpu; + bool fallback = false; + cpumask_var_t tmpmask; + + if (flags & MEMBARRIER_FLAG_SYNC_CORE) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE)) + return -EINVAL; + if (!(atomic_read(¤t->mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY)) + return -EPERM; + } else { + if (!(atomic_read(¤t->mm->membarrier_state) & + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + } if (num_online_cpus() == 1) return 0; @@ -105,21 +191,69 @@ static int membarrier_private_expedited(void) return 0; } -static void membarrier_register_private_expedited(void) +static int membarrier_register_global_expedited(void) { struct task_struct *p = current; struct mm_struct *mm = p->mm; + if (atomic_read(&mm->membarrier_state) & + MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY) + return 0; + atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED, &mm->membarrier_state); + if (atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1) { + /* + * For single mm user, single threaded process, we can + * simply issue a memory barrier after setting + * MEMBARRIER_STATE_GLOBAL_EXPEDITED to guarantee that + * no memory access following registration is reordered + * before registration. + */ + smp_mb(); + } else { + /* + * For multi-mm user threads, we need to ensure all + * future scheduler executions will observe the new + * thread flag state for this mm. + */ + synchronize_sched(); + } + atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY, + &mm->membarrier_state); + return 0; +} + +static int membarrier_register_private_expedited(int flags) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + int state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY; + + if (flags & MEMBARRIER_FLAG_SYNC_CORE) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE)) + return -EINVAL; + state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY; + } + /* * We need to consider threads belonging to different thread * groups, which use the same mm. (CLONE_VM but not * CLONE_THREAD). */ - if (atomic_read(&mm->membarrier_state) - & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) - return; - atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, - &mm->membarrier_state); + if (atomic_read(&mm->membarrier_state) & state) + return 0; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED, &mm->membarrier_state); + if (flags & MEMBARRIER_FLAG_SYNC_CORE) + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE, + &mm->membarrier_state); + if (!(atomic_read(&mm->mm_users) == 1 && get_nr_threads(p) == 1)) { + /* + * Ensure all future scheduler executions will observe the + * new thread flag state for this process. + */ + synchronize_sched(); + } + atomic_or(state, &mm->membarrier_state); + return 0; } /** @@ -159,21 +293,28 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) int cmd_mask = MEMBARRIER_CMD_BITMASK; if (tick_nohz_full_enabled()) - cmd_mask &= ~MEMBARRIER_CMD_SHARED; + cmd_mask &= ~MEMBARRIER_CMD_GLOBAL; return cmd_mask; } - case MEMBARRIER_CMD_SHARED: - /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */ + case MEMBARRIER_CMD_GLOBAL: + /* MEMBARRIER_CMD_GLOBAL is not compatible with nohz_full. */ if (tick_nohz_full_enabled()) return -EINVAL; if (num_online_cpus() > 1) synchronize_sched(); return 0; + case MEMBARRIER_CMD_GLOBAL_EXPEDITED: + return membarrier_global_expedited(); + case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED: + return membarrier_register_global_expedited(); case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - return membarrier_private_expedited(); + return membarrier_private_expedited(0); case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: - membarrier_register_private_expedited(); - return 0; + return membarrier_register_private_expedited(0); + case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE: + return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE: + return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE); default: return -EINVAL; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 862a513adca3..663b2355a3aa 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -950,12 +950,13 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; + u64 now = rq_clock_task(rq); u64 delta_exec; if (curr->sched_class != &rt_sched_class) return; - delta_exec = rq_clock_task(rq) - curr->se.exec_start; + delta_exec = now - curr->se.exec_start; if (unlikely((s64)delta_exec <= 0)) return; @@ -968,7 +969,7 @@ static void update_curr_rt(struct rq *rq) curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); - curr->se.exec_start = rq_clock_task(rq); + curr->se.exec_start = now; cgroup_account_cputime(curr, delta_exec); sched_rt_avg_update(rq, delta_exec); @@ -1907,9 +1908,8 @@ static void push_rt_tasks(struct rq *rq) * the rt_loop_next will cause the iterator to perform another scan. * */ -static int rto_next_cpu(struct rq *rq) +static int rto_next_cpu(struct root_domain *rd) { - struct root_domain *rd = rq->rd; int next; int cpu; @@ -1985,19 +1985,24 @@ static void tell_cpu_to_push(struct rq *rq) * Otherwise it is finishing up and an ipi needs to be sent. */ if (rq->rd->rto_cpu < 0) - cpu = rto_next_cpu(rq); + cpu = rto_next_cpu(rq->rd); raw_spin_unlock(&rq->rd->rto_lock); rto_start_unlock(&rq->rd->rto_loop_start); - if (cpu >= 0) + if (cpu >= 0) { + /* Make sure the rd does not get freed while pushing */ + sched_get_rd(rq->rd); irq_work_queue_on(&rq->rd->rto_push_work, cpu); + } } /* Called from hardirq context */ void rto_push_irq_work_func(struct irq_work *work) { + struct root_domain *rd = + container_of(work, struct root_domain, rto_push_work); struct rq *rq; int cpu; @@ -2013,18 +2018,20 @@ void rto_push_irq_work_func(struct irq_work *work) raw_spin_unlock(&rq->lock); } - raw_spin_lock(&rq->rd->rto_lock); + raw_spin_lock(&rd->rto_lock); /* Pass the IPI to the next rt overloaded queue */ - cpu = rto_next_cpu(rq); + cpu = rto_next_cpu(rd); - raw_spin_unlock(&rq->rd->rto_lock); + raw_spin_unlock(&rd->rto_lock); - if (cpu < 0) + if (cpu < 0) { + sched_put_rd(rd); return; + } /* Try the next RT overloaded CPU */ - irq_work_queue_on(&rq->rd->rto_push_work, cpu); + irq_work_queue_on(&rd->rto_push_work, cpu); } #endif /* HAVE_RT_PUSH_IPI */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2e95505e23c6..fb5fc458547f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -691,6 +691,8 @@ extern struct mutex sched_domains_mutex; extern void init_defrootdomain(void); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); +extern void sched_get_rd(struct root_domain *rd); +extern void sched_put_rd(struct root_domain *rd); #ifdef HAVE_RT_PUSH_IPI extern void rto_push_irq_work_func(struct irq_work *work); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baf500d12b7c..8e7b58de61e7 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -31,8 +31,11 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) rq->rq_sched_info.run_delay += delta; } #define schedstat_enabled() static_branch_unlikely(&sched_schedstats) +#define __schedstat_inc(var) do { var++; } while (0) #define schedstat_inc(var) do { if (schedstat_enabled()) { var++; } } while (0) +#define __schedstat_add(var, amt) do { var += (amt); } while (0) #define schedstat_add(var, amt) do { if (schedstat_enabled()) { var += (amt); } } while (0) +#define __schedstat_set(var, val) do { var = (val); } while (0) #define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0) #define schedstat_val(var) (var) #define schedstat_val_or_zero(var) ((schedstat_enabled()) ? (var) : 0) @@ -48,8 +51,11 @@ static inline void rq_sched_info_depart(struct rq *rq, unsigned long long delta) {} #define schedstat_enabled() 0 +#define __schedstat_inc(var) do { } while (0) #define schedstat_inc(var) do { } while (0) +#define __schedstat_add(var, amt) do { } while (0) #define schedstat_add(var, amt) do { } while (0) +#define __schedstat_set(var, val) do { } while (0) #define schedstat_set(var, val) do { } while (0) #define schedstat_val(var) 0 #define schedstat_val_or_zero(var) 0 diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 034cbed7f88b..519b024f4e94 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -259,6 +259,19 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd) call_rcu_sched(&old_rd->rcu, free_rootdomain); } +void sched_get_rd(struct root_domain *rd) +{ + atomic_inc(&rd->refcount); +} + +void sched_put_rd(struct root_domain *rd) +{ + if (!atomic_dec_and_test(&rd->refcount)) + return; + + call_rcu_sched(&rd->rcu, free_rootdomain); +} + static int init_rootdomain(struct root_domain *rd) { if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2fb4e27c636a..f98f28c12020 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -218,6 +218,8 @@ static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, static int proc_dostring_coredump(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_MAGIC_SYSRQ /* Note: sysrq code uses it's own private copy */ @@ -1812,8 +1814,7 @@ static struct ctl_table fs_table[] = { .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, - .proc_handler = &pipe_proc_fn, - .extra1 = &pipe_min_size, + .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", @@ -2615,29 +2616,17 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, do_proc_douintvec_minmax_conv, ¶m); } -struct do_proc_dopipe_max_size_conv_param { - unsigned int *min; -}; - static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { - struct do_proc_dopipe_max_size_conv_param *param = data; - if (write) { unsigned int val; - if (*lvalp > UINT_MAX) - return -EINVAL; - val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; - if (param->min && *param->min > val) - return -ERANGE; - *valp = val; } else { unsigned int val = *valp; @@ -2647,14 +2636,11 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, return 0; } -int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - struct do_proc_dopipe_max_size_conv_param param = { - .min = (unsigned int *) table->extra1, - }; return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_dopipe_max_size_conv, ¶m); + do_proc_dopipe_max_size_conv, NULL); } static void validate_coredump_safety(void) @@ -3160,12 +3146,6 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } -int proc_dopipe_max_size(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - return -ENOSYS; -} - int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -3209,7 +3189,6 @@ EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL_GPL(proc_douintvec_minmax); -EXPORT_SYMBOL_GPL(proc_dopipe_max_size); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 4559e914452b..4e62a4a8fa91 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -194,11 +194,7 @@ static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) { struct task_struct *tsk; - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (tsk) - get_task_struct(tsk); - rcu_read_unlock(); + tsk = find_get_task_by_vpid(pid); if (!tsk) return -ESRCH; fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index ae0c8a411fe7..23788100e214 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -37,7 +37,6 @@ #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> -#include <linux/kallsyms.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/seq_file.h> diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 94ad46d50b56..fe56c4e06c51 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -74,7 +74,7 @@ static __poll_t posix_clock_poll(struct file *fp, poll_table *wait) __poll_t result = 0; if (!clk) - return POLLERR; + return EPOLLERR; if (clk->ops.poll) result = clk->ops.poll(clk, fp, wait); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index dabd9d167d42..eac9ce2c57a2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4456,7 +4456,6 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, func_g.type = filter_parse_regex(glob, strlen(glob), &func_g.search, ¬); func_g.len = strlen(func_g.search); - func_g.search = glob; /* we do not support '!' for function probes */ if (WARN_ON(not)) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index ca6930e0d25e..dcf1c4dd3efe 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -627,7 +627,7 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full) * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. * - * Returns POLLIN | POLLRDNORM if data exists in the buffers, + * Returns EPOLLIN | EPOLLRDNORM if data exists in the buffers, * zero otherwise. */ __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, @@ -665,7 +665,7 @@ __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 56608538a4ad..20a2300ae4e8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5623,13 +5623,13 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; if (tr->trace_flags & TRACE_ITER_BLOCK) /* * Always select as readable when in blocking mode */ - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; else return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file, filp, poll_table); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 61e7f0678d33..a764aec3c9a1 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -400,7 +400,6 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) for (i = 0; i < len; i++) { if (buff[i] == '*') { if (!i) { - *search = buff + 1; type = MATCH_END_ONLY; } else if (i == len - 1) { if (type == MATCH_END_ONLY) @@ -410,14 +409,14 @@ enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not) buff[i] = 0; break; } else { /* pattern continues, use full glob */ - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } else if (strchr("[?\\", buff[i])) { - type = MATCH_GLOB; - break; + return MATCH_GLOB; } } + if (buff[0] == '*') + *search = buff + 1; return type; } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 64d7c19d3167..6088408ef26c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -217,7 +217,7 @@ config ENABLE_MUST_CHECK config FRAME_WARN int "Warn for stack frames larger than (needs gcc 4.4)" range 0 8192 - default 0 if KASAN + default 3072 if KASAN_EXTRA default 2048 if GCC_PLUGIN_LATENT_ENTROPY default 1280 if (!64BIT && PARISC) default 1024 if (!64BIT && !PARISC) @@ -351,7 +351,6 @@ config SECTION_MISMATCH_WARN_ONLY # config ARCH_WANT_FRAME_POINTERS bool - help config FRAME_POINTER bool "Compile the kernel with frame pointers" @@ -1641,7 +1640,10 @@ config DMA_API_DEBUG If unsure, say N. -menu "Runtime Testing" +menuconfig RUNTIME_TESTING_MENU + bool "Runtime Testing" + +if RUNTIME_TESTING_MENU config LKDTM tristate "Linux Kernel Dump Test Tool Module" @@ -1841,7 +1843,7 @@ config TEST_BPF If unsure, say N. -config TEST_FIND_BIT +config FIND_BIT_BENCHMARK tristate "Test find_bit functions" default n help @@ -1929,7 +1931,7 @@ config TEST_DEBUG_VIRTUAL If unsure, say N. -endmenu # runtime tests +endif # RUNTIME_TESTING_MENU config MEMTEST bool "Memtest" diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index bd38aab05929..3d35d062970d 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -20,6 +20,17 @@ config KASAN Currently CONFIG_KASAN doesn't work with CONFIG_DEBUG_SLAB (the resulting kernel does not boot). +config KASAN_EXTRA + bool "KAsan: extra checks" + depends on KASAN && DEBUG_KERNEL && !COMPILE_TEST + help + This enables further checks in the kernel address sanitizer, for now + it only includes the address-use-after-scope check that can lead + to excessive kernel stack usage, frame size warnings and longer + compile time. + https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715 has more + + choice prompt "Instrumentation type" depends on KASAN diff --git a/lib/Makefile b/lib/Makefile index 7adb066692b3..a90d4fcd748f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -46,8 +46,8 @@ obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += hexdump.o obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o obj-y += kstrtox.o +obj-$(CONFIG_FIND_BIT_BENCHMARK) += find_bit_benchmark.o obj-$(CONFIG_TEST_BPF) += test_bpf.o -obj-$(CONFIG_TEST_FIND_BIT) += test_find_bit.o obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o diff --git a/lib/bitmap.c b/lib/bitmap.c index d8f0c094b18e..9e498c77ed0e 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -1106,111 +1106,80 @@ int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) EXPORT_SYMBOL(bitmap_allocate_region); /** - * bitmap_from_u32array - copy the contents of a u32 array of bits to bitmap - * @bitmap: array of unsigned longs, the destination bitmap, non NULL - * @nbits: number of bits in @bitmap - * @buf: array of u32 (in host byte order), the source bitmap, non NULL - * @nwords: number of u32 words in @buf - * - * copy min(nbits, 32*nwords) bits from @buf to @bitmap, remaining - * bits between nword and nbits in @bitmap (if any) are cleared. In - * last word of @bitmap, the bits beyond nbits (if any) are kept - * unchanged. + * bitmap_copy_le - copy a bitmap, putting the bits into little-endian order. + * @dst: destination buffer + * @src: bitmap to copy + * @nbits: number of bits in the bitmap * - * Return the number of bits effectively copied. + * Require nbits % BITS_PER_LONG == 0. */ -unsigned int -bitmap_from_u32array(unsigned long *bitmap, unsigned int nbits, - const u32 *buf, unsigned int nwords) +#ifdef __BIG_ENDIAN +void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int dst_idx, src_idx; - - for (src_idx = dst_idx = 0; dst_idx < BITS_TO_LONGS(nbits); ++dst_idx) { - unsigned long part = 0; - - if (src_idx < nwords) - part = buf[src_idx++]; - -#if BITS_PER_LONG == 64 - if (src_idx < nwords) - part |= ((unsigned long) buf[src_idx++]) << 32; -#endif - - if (dst_idx < nbits/BITS_PER_LONG) - bitmap[dst_idx] = part; - else { - unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); + unsigned int i; - bitmap[dst_idx] = (bitmap[dst_idx] & ~mask) - | (part & mask); - } + for (i = 0; i < nbits/BITS_PER_LONG; i++) { + if (BITS_PER_LONG == 64) + dst[i] = cpu_to_le64(src[i]); + else + dst[i] = cpu_to_le32(src[i]); } - - return min_t(unsigned int, nbits, 32*nwords); } -EXPORT_SYMBOL(bitmap_from_u32array); +EXPORT_SYMBOL(bitmap_copy_le); +#endif +#if BITS_PER_LONG == 64 /** - * bitmap_to_u32array - copy the contents of bitmap to a u32 array of bits - * @buf: array of u32 (in host byte order), the dest bitmap, non NULL - * @nwords: number of u32 words in @buf - * @bitmap: array of unsigned longs, the source bitmap, non NULL + * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap + * @bitmap: array of unsigned longs, the destination bitmap + * @buf: array of u32 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap - * - * copy min(nbits, 32*nwords) bits from @bitmap to @buf. Remaining - * bits after nbits in @buf (if any) are cleared. - * - * Return the number of bits effectively copied. */ -unsigned int -bitmap_to_u32array(u32 *buf, unsigned int nwords, - const unsigned long *bitmap, unsigned int nbits) +void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, + unsigned int nbits) { - unsigned int dst_idx = 0, src_idx = 0; - - while (dst_idx < nwords) { - unsigned long part = 0; - - if (src_idx < BITS_TO_LONGS(nbits)) { - part = bitmap[src_idx]; - if (src_idx >= nbits/BITS_PER_LONG) - part &= BITMAP_LAST_WORD_MASK(nbits); - src_idx++; - } + unsigned int i, halfwords; - buf[dst_idx++] = part & 0xffffffffUL; + if (!nbits) + return; -#if BITS_PER_LONG == 64 - if (dst_idx < nwords) { - part >>= 32; - buf[dst_idx++] = part & 0xffffffffUL; - } -#endif + halfwords = DIV_ROUND_UP(nbits, 32); + for (i = 0; i < halfwords; i++) { + bitmap[i/2] = (unsigned long) buf[i]; + if (++i < halfwords) + bitmap[i/2] |= ((unsigned long) buf[i]) << 32; } - return min_t(unsigned int, nbits, 32*nwords); + /* Clear tail bits in last word beyond nbits. */ + if (nbits % BITS_PER_LONG) + bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits); } -EXPORT_SYMBOL(bitmap_to_u32array); +EXPORT_SYMBOL(bitmap_from_arr32); /** - * bitmap_copy_le - copy a bitmap, putting the bits into little-endian order. - * @dst: destination buffer - * @src: bitmap to copy - * @nbits: number of bits in the bitmap - * - * Require nbits % BITS_PER_LONG == 0. + * bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits + * @buf: array of u32 (in host byte order), the dest bitmap + * @bitmap: array of unsigned longs, the source bitmap + * @nbits: number of bits in @bitmap */ -#ifdef __BIG_ENDIAN -void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits) +void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits) { - unsigned int i; + unsigned int i, halfwords; - for (i = 0; i < nbits/BITS_PER_LONG; i++) { - if (BITS_PER_LONG == 64) - dst[i] = cpu_to_le64(src[i]); - else - dst[i] = cpu_to_le32(src[i]); + if (!nbits) + return; + + halfwords = DIV_ROUND_UP(nbits, 32); + for (i = 0; i < halfwords; i++) { + buf[i] = (u32) (bitmap[i/2] & UINT_MAX); + if (++i < halfwords) + buf[i] = (u32) (bitmap[i/2] >> 32); } + + /* Clear tail bits in last element of array beyond nbits. */ + if (nbits % BITS_PER_LONG) + buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31)); } -EXPORT_SYMBOL(bitmap_copy_le); +EXPORT_SYMBOL(bitmap_to_arr32); + #endif diff --git a/lib/cpumask.c b/lib/cpumask.c index 35fe142ebb5e..beca6244671a 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -33,10 +33,11 @@ EXPORT_SYMBOL(cpumask_next); int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { - while ((n = cpumask_next(n, src1p)) < nr_cpu_ids) - if (cpumask_test_cpu(n, src2p)) - break; - return n; + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next_and); diff --git a/lib/find_bit.c b/lib/find_bit.c index 6ed74f78380c..ee3df93ba69a 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -21,22 +21,29 @@ #include <linux/export.h> #include <linux/kernel.h> -#if !defined(find_next_bit) || !defined(find_next_zero_bit) +#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ + !defined(find_next_and_bit) /* - * This is a common helper function for find_next_bit and - * find_next_zero_bit. The difference is the "invert" argument, which - * is XORed with each fetched word before searching it for one bits. + * This is a common helper function for find_next_bit, find_next_zero_bit, and + * find_next_and_bit. The differences are: + * - The "invert" argument, which is XORed with each fetched word before + * searching it for one bits. + * - The optional "addr2", which is anded with "addr1" if present. */ -static unsigned long _find_next_bit(const unsigned long *addr, - unsigned long nbits, unsigned long start, unsigned long invert) +static inline unsigned long _find_next_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; /* Handle 1st word. */ tmp &= BITMAP_FIRST_WORD_MASK(start); @@ -47,7 +54,10 @@ static unsigned long _find_next_bit(const unsigned long *addr, if (start >= nbits) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; } return min(start + __ffs(tmp), nbits); @@ -61,7 +71,7 @@ static unsigned long _find_next_bit(const unsigned long *addr, unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, 0UL); + return _find_next_bit(addr, NULL, size, offset, 0UL); } EXPORT_SYMBOL(find_next_bit); #endif @@ -70,11 +80,21 @@ EXPORT_SYMBOL(find_next_bit); unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, ~0UL); + return _find_next_bit(addr, NULL, size, offset, ~0UL); } EXPORT_SYMBOL(find_next_zero_bit); #endif +#if !defined(find_next_and_bit) +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + return _find_next_bit(addr1, addr2, size, offset, 0UL); +} +EXPORT_SYMBOL(find_next_and_bit); +#endif + #ifndef find_first_bit /* * Find the first set bit in a memory region. @@ -146,15 +166,19 @@ static inline unsigned long ext2_swab(const unsigned long y) } #if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) -static unsigned long _find_next_bit_le(const unsigned long *addr, - unsigned long nbits, unsigned long start, unsigned long invert) +static inline unsigned long _find_next_bit_le(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; /* Handle 1st word. */ tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start)); @@ -165,7 +189,10 @@ static unsigned long _find_next_bit_le(const unsigned long *addr, if (start >= nbits) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; } return min(start + __ffs(ext2_swab(tmp)), nbits); @@ -176,7 +203,7 @@ static unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { - return _find_next_bit_le(addr, size, offset, ~0UL); + return _find_next_bit_le(addr, NULL, size, offset, ~0UL); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif @@ -185,7 +212,7 @@ EXPORT_SYMBOL(find_next_zero_bit_le); unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { - return _find_next_bit_le(addr, size, offset, 0UL); + return _find_next_bit_le(addr, NULL, size, offset, 0UL); } EXPORT_SYMBOL(find_next_bit_le); #endif diff --git a/lib/test_find_bit.c b/lib/find_bit_benchmark.c index f4394a36f9aa..5985a25e6cbc 100644 --- a/lib/test_find_bit.c +++ b/lib/find_bit_benchmark.c @@ -35,6 +35,7 @@ #define SPARSE 500 static DECLARE_BITMAP(bitmap, BITMAP_LEN) __initdata; +static DECLARE_BITMAP(bitmap2, BITMAP_LEN) __initdata; /* * This is Schlemiel the Painter's algorithm. It should be called after @@ -43,16 +44,15 @@ static DECLARE_BITMAP(bitmap, BITMAP_LEN) __initdata; static int __init test_find_first_bit(void *bitmap, unsigned long len) { unsigned long i, cnt; - cycles_t cycles; + ktime_t time; - cycles = get_cycles(); + time = ktime_get(); for (cnt = i = 0; i < len; cnt++) { i = find_first_bit(bitmap, len); __clear_bit(i, bitmap); } - cycles = get_cycles() - cycles; - pr_err("find_first_bit:\t\t%llu cycles,\t%ld iterations\n", - (u64)cycles, cnt); + time = ktime_get() - time; + pr_err("find_first_bit: %18llu ns, %6ld iterations\n", time, cnt); return 0; } @@ -60,14 +60,13 @@ static int __init test_find_first_bit(void *bitmap, unsigned long len) static int __init test_find_next_bit(const void *bitmap, unsigned long len) { unsigned long i, cnt; - cycles_t cycles; + ktime_t time; - cycles = get_cycles(); + time = ktime_get(); for (cnt = i = 0; i < BITMAP_LEN; cnt++) i = find_next_bit(bitmap, BITMAP_LEN, i) + 1; - cycles = get_cycles() - cycles; - pr_err("find_next_bit:\t\t%llu cycles,\t%ld iterations\n", - (u64)cycles, cnt); + time = ktime_get() - time; + pr_err("find_next_bit: %18llu ns, %6ld iterations\n", time, cnt); return 0; } @@ -75,14 +74,13 @@ static int __init test_find_next_bit(const void *bitmap, unsigned long len) static int __init test_find_next_zero_bit(const void *bitmap, unsigned long len) { unsigned long i, cnt; - cycles_t cycles; + ktime_t time; - cycles = get_cycles(); + time = ktime_get(); for (cnt = i = 0; i < BITMAP_LEN; cnt++) i = find_next_zero_bit(bitmap, len, i) + 1; - cycles = get_cycles() - cycles; - pr_err("find_next_zero_bit:\t%llu cycles,\t%ld iterations\n", - (u64)cycles, cnt); + time = ktime_get() - time; + pr_err("find_next_zero_bit: %18llu ns, %6ld iterations\n", time, cnt); return 0; } @@ -90,9 +88,9 @@ static int __init test_find_next_zero_bit(const void *bitmap, unsigned long len) static int __init test_find_last_bit(const void *bitmap, unsigned long len) { unsigned long l, cnt = 0; - cycles_t cycles; + ktime_t time; - cycles = get_cycles(); + time = ktime_get(); do { cnt++; l = find_last_bit(bitmap, len); @@ -100,9 +98,24 @@ static int __init test_find_last_bit(const void *bitmap, unsigned long len) break; len = l; } while (len); + time = ktime_get() - time; + pr_err("find_last_bit: %18llu ns, %6ld iterations\n", time, cnt); + + return 0; +} + +static int __init test_find_next_and_bit(const void *bitmap, + const void *bitmap2, unsigned long len) +{ + unsigned long i, cnt; + cycles_t cycles; + + cycles = get_cycles(); + for (cnt = i = 0; i < BITMAP_LEN; cnt++) + i = find_next_and_bit(bitmap, bitmap2, BITMAP_LEN, i+1); cycles = get_cycles() - cycles; - pr_err("find_last_bit:\t\t%llu cycles,\t%ld iterations\n", - (u64)cycles, cnt); + pr_err("find_next_and_bit:\t\t%llu cycles, %ld iterations\n", + (u64)cycles, cnt); return 0; } @@ -114,31 +127,36 @@ static int __init find_bit_test(void) pr_err("\nStart testing find_bit() with random-filled bitmap\n"); get_random_bytes(bitmap, sizeof(bitmap)); + get_random_bytes(bitmap2, sizeof(bitmap2)); test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); + test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); pr_err("\nStart testing find_bit() with sparse bitmap\n"); bitmap_zero(bitmap, BITMAP_LEN); + bitmap_zero(bitmap2, BITMAP_LEN); - while (nbits--) + while (nbits--) { __set_bit(prandom_u32() % BITMAP_LEN, bitmap); + __set_bit(prandom_u32() % BITMAP_LEN, bitmap2); + } test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); + test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); - return 0; + /* + * Everything is OK. Return error just to let user run benchmark + * again without annoying rmmod. + */ + return -EINVAL; } module_init(find_bit_test); -static void __exit test_find_bit_cleanup(void) -{ -} -module_exit(test_find_bit_cleanup); - MODULE_LICENSE("GPL"); diff --git a/lib/idr.c b/lib/idr.c index 2593ce513a18..c98d77fcf393 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -1,4 +1,5 @@ #include <linux/bitmap.h> +#include <linux/bug.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/slab.h> @@ -7,71 +8,184 @@ DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap); static DEFINE_SPINLOCK(simple_ida_lock); -int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index, - unsigned long start, unsigned long end, gfp_t gfp, - bool ext) +/** + * idr_alloc_u32() - Allocate an ID. + * @idr: IDR handle. + * @ptr: Pointer to be associated with the new ID. + * @nextid: Pointer to an ID. + * @max: The maximum ID to allocate (inclusive). + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @nextid and @max. + * Note that @max is inclusive whereas the @end parameter to idr_alloc() + * is exclusive. The new ID is assigned to @nextid before the pointer + * is inserted into the IDR, so if @nextid points into the object pointed + * to by @ptr, a concurrent lookup will not find an uninitialised ID. + * + * The caller should provide their own locking to ensure that two + * concurrent modifications to the IDR are not possible. Read-only + * accesses to the IDR may be done under the RCU read lock or may + * exclude simultaneous writers. + * + * Return: 0 if an ID was allocated, -ENOMEM if memory allocation failed, + * or -ENOSPC if no free IDs could be found. If an error occurred, + * @nextid is unchanged. + */ +int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, + unsigned long max, gfp_t gfp) { struct radix_tree_iter iter; void __rcu **slot; + int base = idr->idr_base; + int id = *nextid; if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr))) return -EINVAL; + if (WARN_ON_ONCE(!(idr->idr_rt.gfp_mask & ROOT_IS_IDR))) + idr->idr_rt.gfp_mask |= IDR_RT_MARKER; - radix_tree_iter_init(&iter, start); - if (ext) - slot = idr_get_free_ext(&idr->idr_rt, &iter, gfp, end); - else - slot = idr_get_free(&idr->idr_rt, &iter, gfp, end); + id = (id < base) ? 0 : id - base; + radix_tree_iter_init(&iter, id); + slot = idr_get_free(&idr->idr_rt, &iter, gfp, max - base); if (IS_ERR(slot)) return PTR_ERR(slot); + *nextid = iter.index + base; + /* there is a memory barrier inside radix_tree_iter_replace() */ radix_tree_iter_replace(&idr->idr_rt, &iter, slot, ptr); radix_tree_iter_tag_clear(&idr->idr_rt, &iter, IDR_FREE); - if (index) - *index = iter.index; return 0; } -EXPORT_SYMBOL_GPL(idr_alloc_cmn); +EXPORT_SYMBOL_GPL(idr_alloc_u32); /** - * idr_alloc_cyclic - allocate new idr entry in a cyclical fashion - * @idr: idr handle - * @ptr: pointer to be associated with the new id - * @start: the minimum id (inclusive) - * @end: the maximum id (exclusive) - * @gfp: memory allocation flags - * - * Allocates an ID larger than the last ID allocated if one is available. - * If not, it will attempt to allocate the smallest ID that is larger or - * equal to @start. + * idr_alloc() - Allocate an ID. + * @idr: IDR handle. + * @ptr: Pointer to be associated with the new ID. + * @start: The minimum ID (inclusive). + * @end: The maximum ID (exclusive). + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @start and @end. If + * @end is <= 0, it is treated as one larger than %INT_MAX. This allows + * callers to use @start + N as @end as long as N is within integer range. + * + * The caller should provide their own locking to ensure that two + * concurrent modifications to the IDR are not possible. Read-only + * accesses to the IDR may be done under the RCU read lock or may + * exclude simultaneous writers. + * + * Return: The newly allocated ID, -ENOMEM if memory allocation failed, + * or -ENOSPC if no free IDs could be found. */ -int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) +int idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) { - int id, curr = idr->idr_next; + u32 id = start; + int ret; + + if (WARN_ON_ONCE(start < 0)) + return -EINVAL; + + ret = idr_alloc_u32(idr, ptr, &id, end > 0 ? end - 1 : INT_MAX, gfp); + if (ret) + return ret; + + return id; +} +EXPORT_SYMBOL_GPL(idr_alloc); - if (curr < start) - curr = start; +/** + * idr_alloc_cyclic() - Allocate an ID cyclically. + * @idr: IDR handle. + * @ptr: Pointer to be associated with the new ID. + * @start: The minimum ID (inclusive). + * @end: The maximum ID (exclusive). + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @nextid and @end. If + * @end is <= 0, it is treated as one larger than %INT_MAX. This allows + * callers to use @start + N as @end as long as N is within integer range. + * The search for an unused ID will start at the last ID allocated and will + * wrap around to @start if no free IDs are found before reaching @end. + * + * The caller should provide their own locking to ensure that two + * concurrent modifications to the IDR are not possible. Read-only + * accesses to the IDR may be done under the RCU read lock or may + * exclude simultaneous writers. + * + * Return: The newly allocated ID, -ENOMEM if memory allocation failed, + * or -ENOSPC if no free IDs could be found. + */ +int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp) +{ + u32 id = idr->idr_next; + int err, max = end > 0 ? end - 1 : INT_MAX; - id = idr_alloc(idr, ptr, curr, end, gfp); - if ((id == -ENOSPC) && (curr > start)) - id = idr_alloc(idr, ptr, start, curr, gfp); + if ((int)id < start) + id = start; - if (id >= 0) - idr->idr_next = id + 1U; + err = idr_alloc_u32(idr, ptr, &id, max, gfp); + if ((err == -ENOSPC) && (id > start)) { + id = start; + err = idr_alloc_u32(idr, ptr, &id, max, gfp); + } + if (err) + return err; + idr->idr_next = id + 1; return id; } EXPORT_SYMBOL(idr_alloc_cyclic); /** - * idr_for_each - iterate through all stored pointers - * @idr: idr handle - * @fn: function to be called for each pointer - * @data: data passed to callback function + * idr_remove() - Remove an ID from the IDR. + * @idr: IDR handle. + * @id: Pointer ID. + * + * Removes this ID from the IDR. If the ID was not previously in the IDR, + * this function returns %NULL. + * + * Since this function modifies the IDR, the caller should provide their + * own locking to ensure that concurrent modification of the same IDR is + * not possible. + * + * Return: The pointer formerly associated with this ID. + */ +void *idr_remove(struct idr *idr, unsigned long id) +{ + return radix_tree_delete_item(&idr->idr_rt, id - idr->idr_base, NULL); +} +EXPORT_SYMBOL_GPL(idr_remove); + +/** + * idr_find() - Return pointer for given ID. + * @idr: IDR handle. + * @id: Pointer ID. + * + * Looks up the pointer associated with this ID. A %NULL pointer may + * indicate that @id is not allocated or that the %NULL pointer was + * associated with this ID. + * + * This function can be called under rcu_read_lock(), given that the leaf + * pointers lifetimes are correctly managed. + * + * Return: The pointer associated with this ID. + */ +void *idr_find(const struct idr *idr, unsigned long id) +{ + return radix_tree_lookup(&idr->idr_rt, id - idr->idr_base); +} +EXPORT_SYMBOL_GPL(idr_find); + +/** + * idr_for_each() - Iterate through all stored pointers. + * @idr: IDR handle. + * @fn: Function to be called for each pointer. + * @data: Data passed to callback function. * * The callback function will be called for each entry in @idr, passing - * the id, the pointer and the data pointer passed to this function. + * the ID, the entry and @data. * * If @fn returns anything other than %0, the iteration stops and that * value is returned from this function. @@ -86,9 +200,14 @@ int idr_for_each(const struct idr *idr, { struct radix_tree_iter iter; void __rcu **slot; + int base = idr->idr_base; radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, 0) { - int ret = fn(iter.index, rcu_dereference_raw(*slot), data); + int ret; + + if (WARN_ON_ONCE(iter.index > INT_MAX)) + break; + ret = fn(iter.index + base, rcu_dereference_raw(*slot), data); if (ret) return ret; } @@ -98,9 +217,9 @@ int idr_for_each(const struct idr *idr, EXPORT_SYMBOL(idr_for_each); /** - * idr_get_next - Find next populated entry - * @idr: idr handle - * @nextid: Pointer to lowest possible ID to return + * idr_get_next() - Find next populated entry. + * @idr: IDR handle. + * @nextid: Pointer to an ID. * * Returns the next populated entry in the tree with an ID greater than * or equal to the value pointed to by @nextid. On exit, @nextid is updated @@ -111,35 +230,55 @@ void *idr_get_next(struct idr *idr, int *nextid) { struct radix_tree_iter iter; void __rcu **slot; + int base = idr->idr_base; + int id = *nextid; - slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid); + id = (id < base) ? 0 : id - base; + slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); if (!slot) return NULL; + id = iter.index + base; + + if (WARN_ON_ONCE(id > INT_MAX)) + return NULL; - *nextid = iter.index; + *nextid = id; return rcu_dereference_raw(*slot); } EXPORT_SYMBOL(idr_get_next); -void *idr_get_next_ext(struct idr *idr, unsigned long *nextid) +/** + * idr_get_next_ul() - Find next populated entry. + * @idr: IDR handle. + * @nextid: Pointer to an ID. + * + * Returns the next populated entry in the tree with an ID greater than + * or equal to the value pointed to by @nextid. On exit, @nextid is updated + * to the ID of the found value. To use in a loop, the value pointed to by + * nextid must be incremented by the user. + */ +void *idr_get_next_ul(struct idr *idr, unsigned long *nextid) { struct radix_tree_iter iter; void __rcu **slot; + unsigned long base = idr->idr_base; + unsigned long id = *nextid; - slot = radix_tree_iter_find(&idr->idr_rt, &iter, *nextid); + id = (id < base) ? 0 : id - base; + slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); if (!slot) return NULL; - *nextid = iter.index; + *nextid = iter.index + base; return rcu_dereference_raw(*slot); } -EXPORT_SYMBOL(idr_get_next_ext); +EXPORT_SYMBOL(idr_get_next_ul); /** - * idr_replace - replace pointer for given id - * @idr: idr handle - * @ptr: New pointer to associate with the ID - * @id: Lookup key + * idr_replace() - replace pointer for given ID. + * @idr: IDR handle. + * @ptr: New pointer to associate with the ID. + * @id: ID to change. * * Replace the pointer registered with an ID and return the old value. * This function can be called under the RCU read lock concurrently with @@ -147,18 +286,9 @@ EXPORT_SYMBOL(idr_get_next_ext); * the one being replaced!). * * Returns: the old value on success. %-ENOENT indicates that @id was not - * found. %-EINVAL indicates that @id or @ptr were not valid. + * found. %-EINVAL indicates that @ptr was not valid. */ -void *idr_replace(struct idr *idr, void *ptr, int id) -{ - if (id < 0) - return ERR_PTR(-EINVAL); - - return idr_replace_ext(idr, ptr, id); -} -EXPORT_SYMBOL(idr_replace); - -void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id) +void *idr_replace(struct idr *idr, void *ptr, unsigned long id) { struct radix_tree_node *node; void __rcu **slot = NULL; @@ -166,6 +296,7 @@ void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id) if (WARN_ON_ONCE(radix_tree_is_internal_node(ptr))) return ERR_PTR(-EINVAL); + id -= idr->idr_base; entry = __radix_tree_lookup(&idr->idr_rt, id, &node, &slot); if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) @@ -175,7 +306,7 @@ void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id) return entry; } -EXPORT_SYMBOL(idr_replace_ext); +EXPORT_SYMBOL(idr_replace); /** * DOC: IDA description @@ -235,7 +366,7 @@ EXPORT_SYMBOL(idr_replace_ext); * bitmap, which is excessive. */ -#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS) +#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS - 1) /** * ida_get_new_above - allocate new ID above or equal to a start id diff --git a/lib/radix-tree.c b/lib/radix-tree.c index c8d55565fafa..0a7ae3288a24 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -24,6 +24,7 @@ #include <linux/bitmap.h> #include <linux/bitops.h> +#include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> @@ -2135,7 +2136,7 @@ int ida_pre_get(struct ida *ida, gfp_t gfp) } EXPORT_SYMBOL(ida_pre_get); -void __rcu **idr_get_free_cmn(struct radix_tree_root *root, +void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { diff --git a/lib/stackdepot.c b/lib/stackdepot.c index f87d138e9672..e513459a5601 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -163,6 +163,21 @@ static inline u32 hash_stack(unsigned long *entries, unsigned int size) STACK_HASH_SEED); } +/* Use our own, non-instrumented version of memcmp(). + * + * We actually don't care about the order, just the equality. + */ +static inline +int stackdepot_memcmp(const unsigned long *u1, const unsigned long *u2, + unsigned int n) +{ + for ( ; n-- ; u1++, u2++) { + if (*u1 != *u2) + return 1; + } + return 0; +} + /* Find a stack that is equal to the one stored in entries in the hash */ static inline struct stack_record *find_stack(struct stack_record *bucket, unsigned long *entries, int size, @@ -173,10 +188,8 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, for (found = bucket; found; found = found->next) { if (found->hash == hash && found->size == size && - !memcmp(entries, found->entries, - size * sizeof(unsigned long))) { + !stackdepot_memcmp(entries, found->entries, size)) return found; - } } return NULL; } diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index aa1f2669bdd5..b3f235baa05d 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -23,7 +23,7 @@ __check_eq_uint(const char *srcfile, unsigned int line, const unsigned int exp_uint, unsigned int x) { if (exp_uint != x) { - pr_warn("[%s:%u] expected %u, got %u\n", + pr_err("[%s:%u] expected %u, got %u\n", srcfile, line, exp_uint, x); return false; } @@ -33,19 +33,13 @@ __check_eq_uint(const char *srcfile, unsigned int line, static bool __init __check_eq_bitmap(const char *srcfile, unsigned int line, - const unsigned long *exp_bmap, unsigned int exp_nbits, - const unsigned long *bmap, unsigned int nbits) + const unsigned long *exp_bmap, const unsigned long *bmap, + unsigned int nbits) { - if (exp_nbits != nbits) { - pr_warn("[%s:%u] bitmap length mismatch: expected %u, got %u\n", - srcfile, line, exp_nbits, nbits); - return false; - } - if (!bitmap_equal(exp_bmap, bmap, nbits)) { pr_warn("[%s:%u] bitmaps contents differ: expected \"%*pbl\", got \"%*pbl\"\n", srcfile, line, - exp_nbits, exp_bmap, nbits, bmap); + nbits, exp_bmap, nbits, bmap); return false; } return true; @@ -69,6 +63,10 @@ __check_eq_pbl(const char *srcfile, unsigned int line, static bool __init __check_eq_u32_array(const char *srcfile, unsigned int line, const u32 *exp_arr, unsigned int exp_len, + const u32 *arr, unsigned int len) __used; +static bool __init +__check_eq_u32_array(const char *srcfile, unsigned int line, + const u32 *exp_arr, unsigned int exp_len, const u32 *arr, unsigned int len) { if (exp_len != len) { @@ -107,7 +105,65 @@ __check_eq_u32_array(const char *srcfile, unsigned int line, #define expect_eq_pbl(...) __expect_eq(pbl, ##__VA_ARGS__) #define expect_eq_u32_array(...) __expect_eq(u32_array, ##__VA_ARGS__) -static void __init test_zero_fill_copy(void) +static void __init test_zero_clear(void) +{ + DECLARE_BITMAP(bmap, 1024); + + /* Known way to set all bits */ + memset(bmap, 0xff, 128); + + expect_eq_pbl("0-22", bmap, 23); + expect_eq_pbl("0-1023", bmap, 1024); + + /* single-word bitmaps */ + bitmap_clear(bmap, 0, 9); + expect_eq_pbl("9-1023", bmap, 1024); + + bitmap_zero(bmap, 35); + expect_eq_pbl("64-1023", bmap, 1024); + + /* cross boundaries operations */ + bitmap_clear(bmap, 79, 19); + expect_eq_pbl("64-78,98-1023", bmap, 1024); + + bitmap_zero(bmap, 115); + expect_eq_pbl("128-1023", bmap, 1024); + + /* Zeroing entire area */ + bitmap_zero(bmap, 1024); + expect_eq_pbl("", bmap, 1024); +} + +static void __init test_fill_set(void) +{ + DECLARE_BITMAP(bmap, 1024); + + /* Known way to clear all bits */ + memset(bmap, 0x00, 128); + + expect_eq_pbl("", bmap, 23); + expect_eq_pbl("", bmap, 1024); + + /* single-word bitmaps */ + bitmap_set(bmap, 0, 9); + expect_eq_pbl("0-8", bmap, 1024); + + bitmap_fill(bmap, 35); + expect_eq_pbl("0-63", bmap, 1024); + + /* cross boundaries operations */ + bitmap_set(bmap, 79, 19); + expect_eq_pbl("0-63,79-97", bmap, 1024); + + bitmap_fill(bmap, 115); + expect_eq_pbl("0-127", bmap, 1024); + + /* Zeroing entire area */ + bitmap_fill(bmap, 1024); + expect_eq_pbl("0-1023", bmap, 1024); +} + +static void __init test_copy(void) { DECLARE_BITMAP(bmap1, 1024); DECLARE_BITMAP(bmap2, 1024); @@ -116,36 +172,20 @@ static void __init test_zero_fill_copy(void) bitmap_zero(bmap2, 1024); /* single-word bitmaps */ - expect_eq_pbl("", bmap1, 23); - - bitmap_fill(bmap1, 19); - expect_eq_pbl("0-18", bmap1, 1024); - + bitmap_set(bmap1, 0, 19); bitmap_copy(bmap2, bmap1, 23); expect_eq_pbl("0-18", bmap2, 1024); - bitmap_fill(bmap2, 23); - expect_eq_pbl("0-22", bmap2, 1024); - + bitmap_set(bmap2, 0, 23); bitmap_copy(bmap2, bmap1, 23); expect_eq_pbl("0-18", bmap2, 1024); - bitmap_zero(bmap1, 23); - expect_eq_pbl("", bmap1, 1024); - /* multi-word bitmaps */ - bitmap_zero(bmap1, 1024); - expect_eq_pbl("", bmap1, 1024); - - bitmap_fill(bmap1, 109); - expect_eq_pbl("0-108", bmap1, 1024); - + bitmap_set(bmap1, 0, 109); bitmap_copy(bmap2, bmap1, 1024); expect_eq_pbl("0-108", bmap2, 1024); bitmap_fill(bmap2, 1024); - expect_eq_pbl("0-1023", bmap2, 1024); - bitmap_copy(bmap2, bmap1, 1024); expect_eq_pbl("0-108", bmap2, 1024); @@ -160,9 +200,6 @@ static void __init test_zero_fill_copy(void) bitmap_fill(bmap2, 1024); bitmap_copy(bmap2, bmap1, 97); /* ... but aligned on word length */ expect_eq_pbl("0-108,128-1023", bmap2, 1024); - - bitmap_zero(bmap2, 97); /* ... but 0-padded til word length */ - expect_eq_pbl("128-1023", bmap2, 1024); } #define PARSE_TIME 0x1 @@ -255,171 +292,29 @@ static void __init test_bitmap_parselist(void) } } -static void __init test_bitmap_u32_array_conversions(void) +static void __init test_bitmap_arr32(void) { - DECLARE_BITMAP(bmap1, 1024); - DECLARE_BITMAP(bmap2, 1024); - u32 exp_arr[32], arr[32]; - unsigned nbits; - - for (nbits = 0 ; nbits < 257 ; ++nbits) { - const unsigned int used_u32s = DIV_ROUND_UP(nbits, 32); - unsigned int i, rv; - - bitmap_zero(bmap1, nbits); - bitmap_set(bmap1, nbits, 1024 - nbits); /* garbage */ - - memset(arr, 0xff, sizeof(arr)); - rv = bitmap_to_u32array(arr, used_u32s, bmap1, nbits); - expect_eq_uint(nbits, rv); - - memset(exp_arr, 0xff, sizeof(exp_arr)); - memset(exp_arr, 0, used_u32s*sizeof(*exp_arr)); - expect_eq_u32_array(exp_arr, 32, arr, 32); - - bitmap_fill(bmap2, 1024); - rv = bitmap_from_u32array(bmap2, nbits, arr, used_u32s); - expect_eq_uint(nbits, rv); - expect_eq_bitmap(bmap1, 1024, bmap2, 1024); - - for (i = 0 ; i < nbits ; ++i) { - /* - * test conversion bitmap -> u32[] - */ - - bitmap_zero(bmap1, 1024); - __set_bit(i, bmap1); - bitmap_set(bmap1, nbits, 1024 - nbits); /* garbage */ - - memset(arr, 0xff, sizeof(arr)); - rv = bitmap_to_u32array(arr, used_u32s, bmap1, nbits); - expect_eq_uint(nbits, rv); - - /* 1st used u32 words contain expected bit set, the - * remaining words are left unchanged (0xff) - */ - memset(exp_arr, 0xff, sizeof(exp_arr)); - memset(exp_arr, 0, used_u32s*sizeof(*exp_arr)); - exp_arr[i/32] = (1U<<(i%32)); - expect_eq_u32_array(exp_arr, 32, arr, 32); - - - /* same, with longer array to fill - */ - memset(arr, 0xff, sizeof(arr)); - rv = bitmap_to_u32array(arr, 32, bmap1, nbits); - expect_eq_uint(nbits, rv); - - /* 1st used u32 words contain expected bit set, the - * remaining words are all 0s - */ - memset(exp_arr, 0, sizeof(exp_arr)); - exp_arr[i/32] = (1U<<(i%32)); - expect_eq_u32_array(exp_arr, 32, arr, 32); - - /* - * test conversion u32[] -> bitmap - */ - - /* the 1st nbits of bmap2 are identical to - * bmap1, the remaining bits of bmap2 are left - * unchanged (all 1s) - */ - bitmap_fill(bmap2, 1024); - rv = bitmap_from_u32array(bmap2, nbits, - exp_arr, used_u32s); - expect_eq_uint(nbits, rv); - - expect_eq_bitmap(bmap1, 1024, bmap2, 1024); - - /* same, with more bits to fill - */ - memset(arr, 0xff, sizeof(arr)); /* garbage */ - memset(arr, 0, used_u32s*sizeof(u32)); - arr[i/32] = (1U<<(i%32)); - - bitmap_fill(bmap2, 1024); - rv = bitmap_from_u32array(bmap2, 1024, arr, used_u32s); - expect_eq_uint(used_u32s*32, rv); - - /* the 1st nbits of bmap2 are identical to - * bmap1, the remaining bits of bmap2 are cleared - */ - bitmap_zero(bmap1, 1024); - __set_bit(i, bmap1); - expect_eq_bitmap(bmap1, 1024, bmap2, 1024); - - - /* - * test short conversion bitmap -> u32[] (1 - * word too short) - */ - if (used_u32s > 1) { - bitmap_zero(bmap1, 1024); - __set_bit(i, bmap1); - bitmap_set(bmap1, nbits, - 1024 - nbits); /* garbage */ - memset(arr, 0xff, sizeof(arr)); - - rv = bitmap_to_u32array(arr, used_u32s - 1, - bmap1, nbits); - expect_eq_uint((used_u32s - 1)*32, rv); - - /* 1st used u32 words contain expected - * bit set, the remaining words are - * left unchanged (0xff) - */ - memset(exp_arr, 0xff, sizeof(exp_arr)); - memset(exp_arr, 0, - (used_u32s-1)*sizeof(*exp_arr)); - if ((i/32) < (used_u32s - 1)) - exp_arr[i/32] = (1U<<(i%32)); - expect_eq_u32_array(exp_arr, 32, arr, 32); - } - - /* - * test short conversion u32[] -> bitmap (3 - * bits too short) - */ - if (nbits > 3) { - memset(arr, 0xff, sizeof(arr)); /* garbage */ - memset(arr, 0, used_u32s*sizeof(*arr)); - arr[i/32] = (1U<<(i%32)); - - bitmap_zero(bmap1, 1024); - rv = bitmap_from_u32array(bmap1, nbits - 3, - arr, used_u32s); - expect_eq_uint(nbits - 3, rv); - - /* we are expecting the bit < nbits - - * 3 (none otherwise), and the rest of - * bmap1 unchanged (0-filled) - */ - bitmap_zero(bmap2, 1024); - if (i < nbits - 3) - __set_bit(i, bmap2); - expect_eq_bitmap(bmap2, 1024, bmap1, 1024); - - /* do the same with bmap1 initially - * 1-filled - */ - - bitmap_fill(bmap1, 1024); - rv = bitmap_from_u32array(bmap1, nbits - 3, - arr, used_u32s); - expect_eq_uint(nbits - 3, rv); - - /* we are expecting the bit < nbits - - * 3 (none otherwise), and the rest of - * bmap1 unchanged (1-filled) - */ - bitmap_zero(bmap2, 1024); - if (i < nbits - 3) - __set_bit(i, bmap2); - bitmap_set(bmap2, nbits-3, 1024 - nbits + 3); - expect_eq_bitmap(bmap2, 1024, bmap1, 1024); - } - } + unsigned int nbits, next_bit, len = sizeof(exp) * 8; + u32 arr[sizeof(exp) / 4]; + DECLARE_BITMAP(bmap2, len); + + memset(arr, 0xa5, sizeof(arr)); + + for (nbits = 0; nbits < len; ++nbits) { + bitmap_to_arr32(arr, exp, nbits); + bitmap_from_arr32(bmap2, arr, nbits); + expect_eq_bitmap(bmap2, exp, nbits); + + next_bit = find_next_bit(bmap2, + round_up(nbits, BITS_PER_LONG), nbits); + if (next_bit < round_up(nbits, BITS_PER_LONG)) + pr_err("bitmap_copy_arr32(nbits == %d:" + " tail is not safely cleared: %d\n", + nbits, next_bit); + + if (nbits < len - 32) + expect_eq_uint(arr[DIV_ROUND_UP(nbits, 32)], + 0xa5a5a5a5); } } @@ -453,8 +348,10 @@ static void noinline __init test_mem_optimisations(void) static int __init test_bitmap_init(void) { - test_zero_fill_copy(); - test_bitmap_u32_array_conversions(); + test_zero_clear(); + test_fill_set(); + test_copy(); + test_bitmap_arr32(); test_bitmap_parselist(); test_mem_optimisations(); diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 4cd9ea9b3449..b4e22345963f 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -83,6 +83,7 @@ struct bpf_test { __u32 result; } test[MAX_SUBTESTS]; int (*fill_helper)(struct bpf_test *self); + int expected_errcode; /* used when FLAG_EXPECTED_FAIL is set in the aux */ __u8 frag_data[MAX_DATA]; int stack_depth; /* for eBPF only, since tests don't call verifier */ }; @@ -2026,7 +2027,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: div_k_0", @@ -2036,7 +2039,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: unknown insn", @@ -2047,7 +2052,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: out of range spill/fill", @@ -2057,7 +2064,9 @@ static struct bpf_test tests[] = { }, CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, - { } + { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "JUMPS + HOLES", @@ -2149,6 +2158,8 @@ static struct bpf_test tests[] = { CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { "check: LDX + RET X", @@ -2159,6 +2170,8 @@ static struct bpf_test tests[] = { CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { /* Mainly checking JIT here. */ "M[]: alt STX + LDX", @@ -2333,6 +2346,8 @@ static struct bpf_test tests[] = { CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, { }, { }, + .fill_helper = NULL, + .expected_errcode = -EINVAL, }, { /* Passes checker but fails during runtime. */ "LD [SKF_AD_OFF-1]", @@ -5395,6 +5410,7 @@ static struct bpf_test tests[] = { { }, { }, .fill_helper = bpf_fill_maxinsns4, + .expected_errcode = -EINVAL, }, { /* Mainly checking JIT here. */ "BPF_MAXINSNS: Very long jump", @@ -5450,10 +5466,15 @@ static struct bpf_test tests[] = { { "BPF_MAXINSNS: Jump, gap, jump, ...", { }, +#ifdef CONFIG_BPF_JIT_ALWAYS_ON + CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL, +#else CLASSIC | FLAG_NO_DATA, +#endif { }, { { 0, 0xababcbac } }, .fill_helper = bpf_fill_maxinsns11, + .expected_errcode = -ENOTSUPP, }, { "BPF_MAXINSNS: ld_abs+get_processor_id", @@ -6344,7 +6365,7 @@ static struct bpf_prog *generate_filter(int which, int *err) *err = bpf_prog_create(&fp, &fprog); if (tests[which].aux & FLAG_EXPECTED_FAIL) { - if (*err == -EINVAL) { + if (*err == tests[which].expected_errcode) { pr_cont("PASS\n"); /* Verifier rejected filter as expected. */ *err = 0; diff --git a/lib/test_kasan.c b/lib/test_kasan.c index ef1a3ac1397e..98854a64b014 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -94,6 +94,37 @@ static noinline void __init kmalloc_pagealloc_oob_right(void) ptr[size] = 0; kfree(ptr); } + +static noinline void __init kmalloc_pagealloc_uaf(void) +{ + char *ptr; + size_t size = KMALLOC_MAX_CACHE_SIZE + 10; + + pr_info("kmalloc pagealloc allocation: use-after-free\n"); + ptr = kmalloc(size, GFP_KERNEL); + if (!ptr) { + pr_err("Allocation failed\n"); + return; + } + + kfree(ptr); + ptr[0] = 0; +} + +static noinline void __init kmalloc_pagealloc_invalid_free(void) +{ + char *ptr; + size_t size = KMALLOC_MAX_CACHE_SIZE + 10; + + pr_info("kmalloc pagealloc allocation: invalid-free\n"); + ptr = kmalloc(size, GFP_KERNEL); + if (!ptr) { + pr_err("Allocation failed\n"); + return; + } + + kfree(ptr + 1); +} #endif static noinline void __init kmalloc_large_oob_right(void) @@ -388,7 +419,7 @@ static noinline void __init kasan_stack_oob(void) static noinline void __init ksize_unpoisons_memory(void) { char *ptr; - size_t size = 123, real_size = size; + size_t size = 123, real_size; pr_info("ksize() unpoisons the whole allocated chunk\n"); ptr = kmalloc(size, GFP_KERNEL); @@ -472,6 +503,74 @@ static noinline void __init use_after_scope_test(void) p[1023] = 1; } +static noinline void __init kasan_alloca_oob_left(void) +{ + volatile int i = 10; + char alloca_array[i]; + char *p = alloca_array - 1; + + pr_info("out-of-bounds to left on alloca\n"); + *(volatile char *)p; +} + +static noinline void __init kasan_alloca_oob_right(void) +{ + volatile int i = 10; + char alloca_array[i]; + char *p = alloca_array + i; + + pr_info("out-of-bounds to right on alloca\n"); + *(volatile char *)p; +} + +static noinline void __init kmem_cache_double_free(void) +{ + char *p; + size_t size = 200; + struct kmem_cache *cache; + + cache = kmem_cache_create("test_cache", size, 0, 0, NULL); + if (!cache) { + pr_err("Cache allocation failed\n"); + return; + } + pr_info("double-free on heap object\n"); + p = kmem_cache_alloc(cache, GFP_KERNEL); + if (!p) { + pr_err("Allocation failed\n"); + kmem_cache_destroy(cache); + return; + } + + kmem_cache_free(cache, p); + kmem_cache_free(cache, p); + kmem_cache_destroy(cache); +} + +static noinline void __init kmem_cache_invalid_free(void) +{ + char *p; + size_t size = 200; + struct kmem_cache *cache; + + cache = kmem_cache_create("test_cache", size, 0, SLAB_TYPESAFE_BY_RCU, + NULL); + if (!cache) { + pr_err("Cache allocation failed\n"); + return; + } + pr_info("invalid-free of heap object\n"); + p = kmem_cache_alloc(cache, GFP_KERNEL); + if (!p) { + pr_err("Allocation failed\n"); + kmem_cache_destroy(cache); + return; + } + + kmem_cache_free(cache, p + 1); + kmem_cache_destroy(cache); +} + static int __init kmalloc_tests_init(void) { /* @@ -485,6 +584,8 @@ static int __init kmalloc_tests_init(void) kmalloc_node_oob_right(); #ifdef CONFIG_SLUB kmalloc_pagealloc_oob_right(); + kmalloc_pagealloc_uaf(); + kmalloc_pagealloc_invalid_free(); #endif kmalloc_large_oob_right(); kmalloc_oob_krealloc_more(); @@ -502,9 +603,13 @@ static int __init kmalloc_tests_init(void) memcg_accounted_kmem_cache(); kasan_stack_oob(); kasan_global_oob(); + kasan_alloca_oob_left(); + kasan_alloca_oob_right(); ksize_unpoisons_memory(); copy_user_test(); use_after_scope_test(); + kmem_cache_double_free(); + kmem_cache_invalid_free(); kasan_restore_multi_shot(multishot); diff --git a/lib/test_sort.c b/lib/test_sort.c index d389c1cc2f6c..385c0ed5202f 100644 --- a/lib/test_sort.c +++ b/lib/test_sort.c @@ -39,5 +39,11 @@ exit: return err; } +static void __exit test_sort_exit(void) +{ +} + module_init(test_sort_init); +module_exit(test_sort_exit); + MODULE_LICENSE("GPL"); diff --git a/lib/ubsan.c b/lib/ubsan.c index fb0409df1bcf..59fee96c29a0 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -141,11 +141,6 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type, } } -static bool location_is_valid(struct source_location *loc) -{ - return loc->file_name != NULL; -} - static DEFINE_SPINLOCK(report_lock); static void ubsan_prologue(struct source_location *location, @@ -265,14 +260,14 @@ void __ubsan_handle_divrem_overflow(struct overflow_data *data, } EXPORT_SYMBOL(__ubsan_handle_divrem_overflow); -static void handle_null_ptr_deref(struct type_mismatch_data *data) +static void handle_null_ptr_deref(struct type_mismatch_data_common *data) { unsigned long flags; - if (suppress_report(&data->location)) + if (suppress_report(data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(data->location, &flags); pr_err("%s null pointer of type %s\n", type_check_kinds[data->type_check_kind], @@ -281,15 +276,15 @@ static void handle_null_ptr_deref(struct type_mismatch_data *data) ubsan_epilogue(&flags); } -static void handle_missaligned_access(struct type_mismatch_data *data, +static void handle_misaligned_access(struct type_mismatch_data_common *data, unsigned long ptr) { unsigned long flags; - if (suppress_report(&data->location)) + if (suppress_report(data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(data->location, &flags); pr_err("%s misaligned address %p for type %s\n", type_check_kinds[data->type_check_kind], @@ -299,15 +294,15 @@ static void handle_missaligned_access(struct type_mismatch_data *data, ubsan_epilogue(&flags); } -static void handle_object_size_mismatch(struct type_mismatch_data *data, +static void handle_object_size_mismatch(struct type_mismatch_data_common *data, unsigned long ptr) { unsigned long flags; - if (suppress_report(&data->location)) + if (suppress_report(data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(data->location, &flags); pr_err("%s address %p with insufficient space\n", type_check_kinds[data->type_check_kind], (void *) ptr); @@ -315,37 +310,46 @@ static void handle_object_size_mismatch(struct type_mismatch_data *data, ubsan_epilogue(&flags); } -void __ubsan_handle_type_mismatch(struct type_mismatch_data *data, +static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data, unsigned long ptr) { if (!ptr) handle_null_ptr_deref(data); else if (data->alignment && !IS_ALIGNED(ptr, data->alignment)) - handle_missaligned_access(data, ptr); + handle_misaligned_access(data, ptr); else handle_object_size_mismatch(data, ptr); } -EXPORT_SYMBOL(__ubsan_handle_type_mismatch); -void __ubsan_handle_nonnull_return(struct nonnull_return_data *data) +void __ubsan_handle_type_mismatch(struct type_mismatch_data *data, + unsigned long ptr) { - unsigned long flags; - - if (suppress_report(&data->location)) - return; - - ubsan_prologue(&data->location, &flags); + struct type_mismatch_data_common common_data = { + .location = &data->location, + .type = data->type, + .alignment = data->alignment, + .type_check_kind = data->type_check_kind + }; + + ubsan_type_mismatch_common(&common_data, ptr); +} +EXPORT_SYMBOL(__ubsan_handle_type_mismatch); - pr_err("null pointer returned from function declared to never return null\n"); +void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data, + unsigned long ptr) +{ - if (location_is_valid(&data->attr_location)) - print_source_location("returns_nonnull attribute specified in", - &data->attr_location); + struct type_mismatch_data_common common_data = { + .location = &data->location, + .type = data->type, + .alignment = 1UL << data->log_alignment, + .type_check_kind = data->type_check_kind + }; - ubsan_epilogue(&flags); + ubsan_type_mismatch_common(&common_data, ptr); } -EXPORT_SYMBOL(__ubsan_handle_nonnull_return); +EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1); void __ubsan_handle_vla_bound_not_positive(struct vla_bound_data *data, unsigned long bound) diff --git a/lib/ubsan.h b/lib/ubsan.h index 88f23557edbe..f4d8d0bd4016 100644 --- a/lib/ubsan.h +++ b/lib/ubsan.h @@ -37,15 +37,24 @@ struct type_mismatch_data { unsigned char type_check_kind; }; -struct nonnull_arg_data { +struct type_mismatch_data_v1 { struct source_location location; - struct source_location attr_location; - int arg_index; + struct type_descriptor *type; + unsigned char log_alignment; + unsigned char type_check_kind; +}; + +struct type_mismatch_data_common { + struct source_location *location; + struct type_descriptor *type; + unsigned long alignment; + unsigned char type_check_kind; }; -struct nonnull_return_data { +struct nonnull_arg_data { struct source_location location; struct source_location attr_location; + int arg_index; }; struct vla_bound_data { diff --git a/mm/bootmem.c b/mm/bootmem.c index 6aef64254203..9e197987b67d 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -410,7 +410,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, /** * free_bootmem - mark a page range as usable - * @addr: starting physical address of the range + * @physaddr: starting physical address of the range * @size: size of the range in bytes * * Partial pages will be considered reserved and left as they are. diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 405bba487df5..e13d911251e7 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -5,7 +5,7 @@ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> * * Some code borrowed from https://github.com/xairy/kasan-prototype by - * Andrey Konovalov <adech.fo@gmail.com> + * Andrey Konovalov <andreyknvl@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -489,21 +489,17 @@ void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags) kasan_kmalloc(cache, object, cache->object_size, flags); } -static void kasan_poison_slab_free(struct kmem_cache *cache, void *object) -{ - unsigned long size = cache->object_size; - unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE); - - /* RCU slabs could be legally used after free within the RCU period */ - if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) - return; - - kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE); -} - -bool kasan_slab_free(struct kmem_cache *cache, void *object) +static bool __kasan_slab_free(struct kmem_cache *cache, void *object, + unsigned long ip, bool quarantine) { s8 shadow_byte; + unsigned long rounded_up_size; + + if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) != + object)) { + kasan_report_invalid_free(object, ip); + return true; + } /* RCU slabs could be legally used after free within the RCU period */ if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU)) @@ -511,14 +507,14 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object) shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object)); if (shadow_byte < 0 || shadow_byte >= KASAN_SHADOW_SCALE_SIZE) { - kasan_report_double_free(cache, object, - __builtin_return_address(1)); + kasan_report_invalid_free(object, ip); return true; } - kasan_poison_slab_free(cache, object); + rounded_up_size = round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE); + kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE); - if (unlikely(!(cache->flags & SLAB_KASAN))) + if (!quarantine || unlikely(!(cache->flags & SLAB_KASAN))) return false; set_track(&get_alloc_info(cache, object)->free_track, GFP_NOWAIT); @@ -526,6 +522,11 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object) return true; } +bool kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip) +{ + return __kasan_slab_free(cache, object, ip, true); +} + void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size, gfp_t flags) { @@ -589,25 +590,29 @@ void kasan_krealloc(const void *object, size_t size, gfp_t flags) kasan_kmalloc(page->slab_cache, object, size, flags); } -void kasan_poison_kfree(void *ptr) +void kasan_poison_kfree(void *ptr, unsigned long ip) { struct page *page; page = virt_to_head_page(ptr); - if (unlikely(!PageSlab(page))) + if (unlikely(!PageSlab(page))) { + if (ptr != page_address(page)) { + kasan_report_invalid_free(ptr, ip); + return; + } kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page), KASAN_FREE_PAGE); - else - kasan_poison_slab_free(page->slab_cache, ptr); + } else { + __kasan_slab_free(page->slab_cache, ptr, ip, false); + } } -void kasan_kfree_large(const void *ptr) +void kasan_kfree_large(void *ptr, unsigned long ip) { - struct page *page = virt_to_page(ptr); - - kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page), - KASAN_FREE_PAGE); + if (ptr != page_address(virt_to_head_page(ptr))) + kasan_report_invalid_free(ptr, ip); + /* The object will be poisoned by page_alloc. */ } int kasan_module_alloc(void *addr, size_t size) @@ -736,6 +741,55 @@ void __asan_unpoison_stack_memory(const void *addr, size_t size) } EXPORT_SYMBOL(__asan_unpoison_stack_memory); +/* Emitted by compiler to poison alloca()ed objects. */ +void __asan_alloca_poison(unsigned long addr, size_t size) +{ + size_t rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE); + size_t padding_size = round_up(size, KASAN_ALLOCA_REDZONE_SIZE) - + rounded_up_size; + size_t rounded_down_size = round_down(size, KASAN_SHADOW_SCALE_SIZE); + + const void *left_redzone = (const void *)(addr - + KASAN_ALLOCA_REDZONE_SIZE); + const void *right_redzone = (const void *)(addr + rounded_up_size); + + WARN_ON(!IS_ALIGNED(addr, KASAN_ALLOCA_REDZONE_SIZE)); + + kasan_unpoison_shadow((const void *)(addr + rounded_down_size), + size - rounded_down_size); + kasan_poison_shadow(left_redzone, KASAN_ALLOCA_REDZONE_SIZE, + KASAN_ALLOCA_LEFT); + kasan_poison_shadow(right_redzone, + padding_size + KASAN_ALLOCA_REDZONE_SIZE, + KASAN_ALLOCA_RIGHT); +} +EXPORT_SYMBOL(__asan_alloca_poison); + +/* Emitted by compiler to unpoison alloca()ed areas when the stack unwinds. */ +void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom) +{ + if (unlikely(!stack_top || stack_top > stack_bottom)) + return; + + kasan_unpoison_shadow(stack_top, stack_bottom - stack_top); +} +EXPORT_SYMBOL(__asan_allocas_unpoison); + +/* Emitted by the compiler to [un]poison local variables. */ +#define DEFINE_ASAN_SET_SHADOW(byte) \ + void __asan_set_shadow_##byte(const void *addr, size_t size) \ + { \ + __memset((void *)addr, 0x##byte, size); \ + } \ + EXPORT_SYMBOL(__asan_set_shadow_##byte) + +DEFINE_ASAN_SET_SHADOW(00); +DEFINE_ASAN_SET_SHADOW(f1); +DEFINE_ASAN_SET_SHADOW(f2); +DEFINE_ASAN_SET_SHADOW(f3); +DEFINE_ASAN_SET_SHADOW(f5); +DEFINE_ASAN_SET_SHADOW(f8); + #ifdef CONFIG_MEMORY_HOTPLUG static int __meminit kasan_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index c70851a9a6a4..c12dcfde2ebd 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -24,6 +24,14 @@ #define KASAN_STACK_PARTIAL 0xF4 #define KASAN_USE_AFTER_SCOPE 0xF8 +/* + * alloca redzone shadow values + */ +#define KASAN_ALLOCA_LEFT 0xCA +#define KASAN_ALLOCA_RIGHT 0xCB + +#define KASAN_ALLOCA_REDZONE_SIZE 32 + /* Don't break randconfig/all*config builds */ #ifndef KASAN_ABI_VERSION #define KASAN_ABI_VERSION 1 @@ -99,8 +107,7 @@ static inline const void *kasan_shadow_to_mem(const void *shadow_addr) void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip); -void kasan_report_double_free(struct kmem_cache *cache, void *object, - void *ip); +void kasan_report_invalid_free(void *object, unsigned long ip); #if defined(CONFIG_SLAB) || defined(CONFIG_SLUB) void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache); @@ -113,4 +120,48 @@ static inline void quarantine_reduce(void) { } static inline void quarantine_remove_cache(struct kmem_cache *cache) { } #endif +/* + * Exported functions for interfaces called from assembly or from generated + * code. Declarations here to avoid warning about missing declarations. + */ +asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); +void __asan_register_globals(struct kasan_global *globals, size_t size); +void __asan_unregister_globals(struct kasan_global *globals, size_t size); +void __asan_loadN(unsigned long addr, size_t size); +void __asan_storeN(unsigned long addr, size_t size); +void __asan_handle_no_return(void); +void __asan_poison_stack_memory(const void *addr, size_t size); +void __asan_unpoison_stack_memory(const void *addr, size_t size); +void __asan_alloca_poison(unsigned long addr, size_t size); +void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom); + +void __asan_load1(unsigned long addr); +void __asan_store1(unsigned long addr); +void __asan_load2(unsigned long addr); +void __asan_store2(unsigned long addr); +void __asan_load4(unsigned long addr); +void __asan_store4(unsigned long addr); +void __asan_load8(unsigned long addr); +void __asan_store8(unsigned long addr); +void __asan_load16(unsigned long addr); +void __asan_store16(unsigned long addr); + +void __asan_load1_noabort(unsigned long addr); +void __asan_store1_noabort(unsigned long addr); +void __asan_load2_noabort(unsigned long addr); +void __asan_store2_noabort(unsigned long addr); +void __asan_load4_noabort(unsigned long addr); +void __asan_store4_noabort(unsigned long addr); +void __asan_load8_noabort(unsigned long addr); +void __asan_store8_noabort(unsigned long addr); +void __asan_load16_noabort(unsigned long addr); +void __asan_store16_noabort(unsigned long addr); + +void __asan_set_shadow_00(const void *addr, size_t size); +void __asan_set_shadow_f1(const void *addr, size_t size); +void __asan_set_shadow_f2(const void *addr, size_t size); +void __asan_set_shadow_f3(const void *addr, size_t size); +void __asan_set_shadow_f5(const void *addr, size_t size); +void __asan_set_shadow_f8(const void *addr, size_t size); + #endif diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 410c8235e671..5c169aa688fd 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -5,7 +5,7 @@ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com> * * Some code borrowed from https://github.com/xairy/kasan-prototype by - * Andrey Konovalov <adech.fo@gmail.com> + * Andrey Konovalov <andreyknvl@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -102,6 +102,10 @@ static const char *get_shadow_bug_type(struct kasan_access_info *info) case KASAN_USE_AFTER_SCOPE: bug_type = "use-after-scope"; break; + case KASAN_ALLOCA_LEFT: + case KASAN_ALLOCA_RIGHT: + bug_type = "alloca-out-of-bounds"; + break; } return bug_type; @@ -322,13 +326,12 @@ static void print_shadow_for_address(const void *addr) } } -void kasan_report_double_free(struct kmem_cache *cache, void *object, - void *ip) +void kasan_report_invalid_free(void *object, unsigned long ip) { unsigned long flags; kasan_start_report(&flags); - pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", ip); + pr_err("BUG: KASAN: double-free or invalid-free in %pS\n", (void *)ip); pr_err("\n"); print_address_description(object); pr_err("\n"); @@ -2302,7 +2302,7 @@ next_mm: /** * ksm_do_scan - the ksm scanner main worker function. - * @scan_npages - number of pages we want to scan before we return. + * @scan_npages: number of pages we want to scan before we return. */ static void ksm_do_scan(unsigned int scan_npages) { diff --git a/mm/maccess.c b/mm/maccess.c index 78f9274dd49d..ec00be51a24f 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(probe_kernel_write); * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. - * @src: Unsafe address. + * @unsafe_addr: Unsafe address. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from unsafe address to kernel buffer. diff --git a/mm/memblock.c b/mm/memblock.c index 46aacdfa4f4d..5a9ca2a1751b 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1654,7 +1654,7 @@ bool __init_memblock memblock_is_memory(phys_addr_t addr) return memblock_search(&memblock.memory, addr) != -1; } -int __init_memblock memblock_is_map_memory(phys_addr_t addr) +bool __init_memblock memblock_is_map_memory(phys_addr_t addr) { int i = memblock_search(&memblock.memory, addr); @@ -1690,13 +1690,13 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn, * RETURNS: * 0 if false, non-zero if true */ -int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) +bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); phys_addr_t end = base + memblock_cap_size(base, &size); if (idx == -1) - return 0; + return false; return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size) >= end; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0937f2c52c7d..670e99b68aa6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -917,7 +917,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, /** * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page * @page: the page - * @zone: zone of the page + * @pgdat: pgdat of the page * * This function is only safe when following the LRU page isolation * and putback protocol: the LRU lock must be held, and the page must @@ -3688,7 +3688,7 @@ static void memcg_event_remove(struct work_struct *work) } /* - * Gets called on POLLHUP on eventfd when user closes it. + * Gets called on EPOLLHUP on eventfd when user closes it. * * Called with wqh->lock held and interrupts disabled. */ @@ -3700,7 +3700,7 @@ static int memcg_event_wake(wait_queue_entry_t *wait, unsigned mode, struct mem_cgroup *memcg = event->memcg; __poll_t flags = key_to_poll(key); - if (flags & POLLHUP) { + if (flags & EPOLLHUP) { /* * If the event has been detached at cgroup removal, we * can simply return knowing the other side will cleanup @@ -5818,8 +5818,8 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) /** * mem_cgroup_uncharge_skmem - uncharge socket memory - * @memcg - memcg to uncharge - * @nr_pages - number of pages to uncharge + * @memcg: memcg to uncharge + * @nr_pages: number of pages to uncharge */ void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) { diff --git a/mm/memory.c b/mm/memory.c index 2248529e71c1..dd8de96f5547 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -59,7 +59,6 @@ #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> -#include <linux/kallsyms.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> @@ -767,9 +766,6 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, dump_page(page, "bad pte"); pr_alert("addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); - /* - * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y - */ pr_alert("file:%pD fault:%pf mmap:%pf readpage:%pf\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, diff --git a/mm/mempool.c b/mm/mempool.c index 7d8c5a0010a2..5c9dce34719b 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -103,10 +103,10 @@ static inline void poison_element(mempool_t *pool, void *element) } #endif /* CONFIG_DEBUG_SLAB || CONFIG_SLUB_DEBUG_ON */ -static void kasan_poison_element(mempool_t *pool, void *element) +static __always_inline void kasan_poison_element(mempool_t *pool, void *element) { if (pool->alloc == mempool_alloc_slab || pool->alloc == mempool_kmalloc) - kasan_poison_kfree(element); + kasan_poison_kfree(element, _RET_IP_); if (pool->alloc == mempool_alloc_pages) kasan_free_pages(element, (unsigned long)pool->pool_data); } @@ -119,7 +119,7 @@ static void kasan_unpoison_element(mempool_t *pool, void *element, gfp_t flags) kasan_alloc_pages(element, (unsigned long)pool->pool_data); } -static void add_element(mempool_t *pool, void *element) +static __always_inline void add_element(mempool_t *pool, void *element) { BUG_ON(pool->curr_nr >= pool->min_nr); poison_element(pool, element); diff --git a/mm/mlock.c b/mm/mlock.c index f7f54fd2e13f..79398200e423 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -157,7 +157,7 @@ static void __munlock_isolation_failed(struct page *page) /** * munlock_vma_page - munlock a vma page - * @page - page to be unlocked, either a normal page or THP page head + * @page: page to be unlocked, either a normal page or THP page head * * returns the size of the page as a page mask (0 for normal page, * HPAGE_PMD_NR - 1 for THP head page) diff --git a/mm/nommu.c b/mm/nommu.c index 4b9864b17cb0..ebb6e618dade 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1836,7 +1836,7 @@ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, } /** - * @access_remote_vm - access another process' address space + * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 23a3e415ac2c..8d2da5dec1e0 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -265,6 +265,7 @@ static int __walk_page_range(unsigned long start, unsigned long end, * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these * callbacks, the associated entries/pages are just ignored. * The return values of these callbacks are commonly defined like below: + * * - 0 : succeeded to handle the current entry, and if you don't reach the * end address yet, continue to walk. * - >0 : succeeded to handle the current entry, and return to the caller diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 8973cd231ece..a447092d4635 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -25,7 +25,7 @@ /** * process_vm_rw_pages - read/write pages from task specified * @pages: array of pointers to pages we want to copy - * @start_offset: offset in page to start copying from/to + * @offset: offset in page to start copying from/to * @len: number of bytes to copy * @iter: where to copy to/from locally * @vm_write: 0 means copy from, 1 means copy to @@ -147,6 +147,7 @@ static int process_vm_rw_single_vec(unsigned long addr, * @riovcnt: size of rvec array * @flags: currently unused * @vm_write: 0 if reading from other process, 1 if writing to other process + * * Returns the number of bytes read/written or error code. May * return less bytes than expected if an error occurs during the copying * process. @@ -197,11 +198,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, } /* Get process information */ - rcu_read_lock(); - task = find_task_by_vpid(pid); - if (task) - get_task_struct(task); - rcu_read_unlock(); + task = find_get_task_by_vpid(pid); if (!task) { rc = -ESRCH; goto free_proc_pages; @@ -253,6 +250,7 @@ free_proc_pages: * @riovcnt: size of rvec array * @flags: currently unused * @vm_write: 0 if reading from other process, 1 if writing to other process + * * Returns the number of bytes read/written or error code. May * return less bytes than expected if an error occurs during the copying * process. diff --git a/mm/slab.c b/mm/slab.c index cd86f15071ad..324446621b3e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3478,11 +3478,11 @@ free_done: * Release an obj back to its cache. If the obj has a constructed state, it must * be in this state _before_ it is released. Called with disabled ints. */ -static inline void __cache_free(struct kmem_cache *cachep, void *objp, - unsigned long caller) +static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp, + unsigned long caller) { /* Put the object into the quarantine, don't touch it for now. */ - if (kasan_slab_free(cachep, objp)) + if (kasan_slab_free(cachep, objp, _RET_IP_)) return; ___cache_free(cachep, objp, caller); diff --git a/mm/slub.c b/mm/slub.c index cc71176c6eef..e381728a3751 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1356,13 +1356,13 @@ static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) kasan_kmalloc_large(ptr, size, flags); } -static inline void kfree_hook(const void *x) +static __always_inline void kfree_hook(void *x) { kmemleak_free(x); - kasan_kfree_large(x); + kasan_kfree_large(x, _RET_IP_); } -static inline void *slab_free_hook(struct kmem_cache *s, void *x) +static __always_inline void *slab_free_hook(struct kmem_cache *s, void *x) { void *freeptr; @@ -1390,7 +1390,7 @@ static inline void *slab_free_hook(struct kmem_cache *s, void *x) * kasan_slab_free() may put x into memory quarantine, delaying its * reuse. In this case the object's freelist pointer is changed. */ - kasan_slab_free(s, x); + kasan_slab_free(s, x, _RET_IP_); return freeptr; } @@ -3910,7 +3910,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { BUG_ON(!PageCompound(page)); - kfree_hook(x); + kfree_hook(object); __free_pages(page, compound_order(page)); return; } diff --git a/mm/swap.c b/mm/swap.c index 10568b1548d4..567a7b96e41d 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -913,11 +913,11 @@ EXPORT_SYMBOL(__pagevec_lru_add); * @pvec: Where the resulting entries are placed * @mapping: The address_space to search * @start: The starting entry index - * @nr_entries: The maximum number of entries + * @nr_pages: The maximum number of pages * @indices: The cache indices corresponding to the entries in @pvec * * pagevec_lookup_entries() will search for and return a group of up - * to @nr_entries pages and shadow entries in the mapping. All + * to @nr_pages pages and shadow entries in the mapping. All * entries are placed in @pvec. pagevec_lookup_entries() takes a * reference against actual pages in @pvec. * diff --git a/mm/swapfile.c b/mm/swapfile.c index 42fe5653814a..c7a33717d079 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2705,10 +2705,10 @@ static __poll_t swaps_poll(struct file *file, poll_table *wait) if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); - return POLLIN | POLLRDNORM | POLLERR | POLLPRI; + return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } /* iterator */ diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 81192701964d..39791b81ede7 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -16,7 +16,6 @@ #include <linux/userfaultfd_k.h> #include <linux/mmu_notifier.h> #include <linux/hugetlb.h> -#include <linux/pagemap.h> #include <linux/shmem_fs.h> #include <asm/tlbflush.h> #include "internal.h" diff --git a/mm/vmscan.c b/mm/vmscan.c index fdd3fc6be862..444749669187 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1595,6 +1595,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, * found will be decremented. * * Restrictions: + * * (1) Must be called with an elevated refcount on the page. This is a * fundamentnal difference from isolate_lru_pages (which is called * without a stable reference). diff --git a/mm/z3fold.c b/mm/z3fold.c index 39e19125d6a0..d589d318727f 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -769,7 +769,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) /** * z3fold_reclaim_page() - evicts allocations from a pool page and frees it * @pool: pool from which a page will attempt to be evicted - * @retires: number of pages on the LRU list for which eviction will + * @retries: number of pages on the LRU list for which eviction will * be attempted before failing * * z3fold reclaim is different from normal system reclaim in that it is done @@ -779,7 +779,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) * z3fold and the user, however. * * To avoid these, this is how z3fold_reclaim_page() should be called: - + * * The user detects a page should be reclaimed and calls z3fold_reclaim_page(). * z3fold_reclaim_page() will remove a z3fold page from the pool LRU list and * call the user-defined eviction handler with the pool and handle as diff --git a/mm/zbud.c b/mm/zbud.c index b42322e50f63..28458f7d1e84 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -466,7 +466,7 @@ void zbud_free(struct zbud_pool *pool, unsigned long handle) /** * zbud_reclaim_page() - evicts allocations from a pool page and frees it * @pool: pool from which a page will attempt to be evicted - * @retires: number of pages on the LRU list for which eviction will + * @retries: number of pages on the LRU list for which eviction will * be attempted before failing * * zbud reclaim is different from normal system reclaim in that the reclaim is @@ -476,7 +476,7 @@ void zbud_free(struct zbud_pool *pool, unsigned long handle) * the user, however. * * To avoid these, this is how zbud_reclaim_page() should be called: - + * * The user detects a page should be reclaimed and calls zbud_reclaim_page(). * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call * the user-defined eviction handler with the pool and handle as arguments. diff --git a/mm/zpool.c b/mm/zpool.c index e1e7aa6d1d06..f8cb83e7699b 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -101,7 +101,7 @@ static void zpool_put_driver(struct zpool_driver *driver) /** * zpool_has_pool() - Check if the pool driver is available - * @type The type of the zpool to check (e.g. zbud, zsmalloc) + * @type: The type of the zpool to check (e.g. zbud, zsmalloc) * * This checks if the @type pool driver is available. This will try to load * the requested module, if needed, but there is no guarantee the module will @@ -136,10 +136,10 @@ EXPORT_SYMBOL(zpool_has_pool); /** * zpool_create_pool() - Create a new zpool - * @type The type of the zpool to create (e.g. zbud, zsmalloc) - * @name The name of the zpool (e.g. zram0, zswap) - * @gfp The GFP flags to use when allocating the pool. - * @ops The optional ops callback. + * @type: The type of the zpool to create (e.g. zbud, zsmalloc) + * @name: The name of the zpool (e.g. zram0, zswap) + * @gfp: The GFP flags to use when allocating the pool. + * @ops: The optional ops callback. * * This creates a new zpool of the specified type. The gfp flags will be * used when allocating memory, if the implementation supports it. If the @@ -201,7 +201,7 @@ struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp, /** * zpool_destroy_pool() - Destroy a zpool - * @pool The zpool to destroy. + * @zpool: The zpool to destroy. * * Implementations must guarantee this to be thread-safe, * however only when destroying different pools. The same @@ -224,7 +224,7 @@ void zpool_destroy_pool(struct zpool *zpool) /** * zpool_get_type() - Get the type of the zpool - * @pool The zpool to check + * @zpool: The zpool to check * * This returns the type of the pool. * @@ -239,10 +239,10 @@ const char *zpool_get_type(struct zpool *zpool) /** * zpool_malloc() - Allocate memory - * @pool The zpool to allocate from. - * @size The amount of memory to allocate. - * @gfp The GFP flags to use when allocating memory. - * @handle Pointer to the handle to set + * @zpool: The zpool to allocate from. + * @size: The amount of memory to allocate. + * @gfp: The GFP flags to use when allocating memory. + * @handle: Pointer to the handle to set * * This allocates the requested amount of memory from the pool. * The gfp flags will be used when allocating memory, if the @@ -261,8 +261,8 @@ int zpool_malloc(struct zpool *zpool, size_t size, gfp_t gfp, /** * zpool_free() - Free previously allocated memory - * @pool The zpool that allocated the memory. - * @handle The handle to the memory to free. + * @zpool: The zpool that allocated the memory. + * @handle: The handle to the memory to free. * * This frees previously allocated memory. This does not guarantee * that the pool will actually free memory, only that the memory @@ -280,9 +280,9 @@ void zpool_free(struct zpool *zpool, unsigned long handle) /** * zpool_shrink() - Shrink the pool size - * @pool The zpool to shrink. - * @pages The number of pages to shrink the pool. - * @reclaimed The number of pages successfully evicted. + * @zpool: The zpool to shrink. + * @pages: The number of pages to shrink the pool. + * @reclaimed: The number of pages successfully evicted. * * This attempts to shrink the actual memory size of the pool * by evicting currently used handle(s). If the pool was @@ -304,11 +304,11 @@ int zpool_shrink(struct zpool *zpool, unsigned int pages, /** * zpool_map_handle() - Map a previously allocated handle into memory - * @pool The zpool that the handle was allocated from - * @handle The handle to map - * @mm How the memory should be mapped + * @zpool: The zpool that the handle was allocated from + * @handle: The handle to map + * @mapmode: How the memory should be mapped * - * This maps a previously allocated handle into memory. The @mm + * This maps a previously allocated handle into memory. The @mapmode * param indicates to the implementation how the memory will be * used, i.e. read-only, write-only, read-write. If the * implementation does not support it, the memory will be treated @@ -332,8 +332,8 @@ void *zpool_map_handle(struct zpool *zpool, unsigned long handle, /** * zpool_unmap_handle() - Unmap a previously mapped handle - * @pool The zpool that the handle was allocated from - * @handle The handle to unmap + * @zpool: The zpool that the handle was allocated from + * @handle: The handle to unmap * * This unmaps a previously mapped handle. Any locks or other * actions that the implementation took in zpool_map_handle() @@ -347,7 +347,7 @@ void zpool_unmap_handle(struct zpool *zpool, unsigned long handle) /** * zpool_get_total_size() - The total size of the pool - * @pool The zpool to check + * @zpool: The zpool to check * * This returns the total size in bytes of the pool. * diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index d6f7f7cb79c4..0cfba919d167 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -240,7 +240,7 @@ p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err) if (!ts) { if (err) *err = -EREMOTEIO; - return POLLERR; + return EPOLLERR; } if (!ts->rd->f_op->poll) @@ -253,7 +253,7 @@ p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err) n = DEFAULT_POLLMASK; else n = ts->wr->f_op->poll(ts->wr, pt); - ret = (ret & ~POLLOUT) | (n & ~POLLIN); + ret = (ret & ~EPOLLOUT) | (n & ~EPOLLIN); } return ret; @@ -396,11 +396,11 @@ end_clear: if (!list_empty(&m->req_list)) { if (test_and_clear_bit(Rpending, &m->wsched)) - n = POLLIN; + n = EPOLLIN; else n = p9_fd_poll(m->client, NULL, NULL); - if ((n & POLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) { + if ((n & EPOLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } @@ -505,11 +505,11 @@ end_clear: if (m->wsize || !list_empty(&m->unsent_req_list)) { if (test_and_clear_bit(Wpending, &m->wsched)) - n = POLLOUT; + n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); - if ((n & POLLOUT) && + if ((n & EPOLLOUT) && !test_and_set_bit(Wworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); @@ -599,12 +599,12 @@ static void p9_conn_create(struct p9_client *client) init_poll_funcptr(&m->pt, p9_pollwait); n = p9_fd_poll(client, &m->pt, NULL); - if (n & POLLIN) { + if (n & EPOLLIN) { p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); set_bit(Rpending, &m->wsched); } - if (n & POLLOUT) { + if (n & EPOLLOUT) { p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); set_bit(Wpending, &m->wsched); } @@ -625,12 +625,12 @@ static void p9_poll_mux(struct p9_conn *m) return; n = p9_fd_poll(m->client, NULL, &err); - if (n & (POLLERR | POLLHUP | POLLNVAL)) { + if (n & (EPOLLERR | EPOLLHUP | EPOLLNVAL)) { p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n); p9_conn_cancel(m, err); } - if (n & POLLIN) { + if (n & EPOLLIN) { set_bit(Rpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); if (!test_and_set_bit(Rworksched, &m->wsched)) { @@ -639,7 +639,7 @@ static void p9_poll_mux(struct p9_conn *m) } } - if (n & POLLOUT) { + if (n & EPOLLOUT) { set_bit(Wpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); if ((m->wsize || !list_empty(&m->unsent_req_list)) && @@ -678,11 +678,11 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req) spin_unlock(&client->lock); if (test_and_clear_bit(Wpending, &m->wsched)) - n = POLLOUT; + n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); - if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched)) + if (n & EPOLLOUT && !test_and_set_bit(Wworksched, &m->wsched)) schedule_work(&m->wq); return 0; diff --git a/net/atm/common.c b/net/atm/common.c index 6523f38c4957..fc78a0508ae1 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -661,15 +661,15 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) /* exceptional events */ if (sk->sk_err) - mask = POLLERR; + mask = EPOLLERR; if (test_bit(ATM_VF_RELEASED, &vcc->flags) || test_bit(ATM_VF_CLOSE, &vcc->flags)) - mask |= POLLHUP; + mask |= EPOLLHUP; /* readable? */ if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* writable? */ if (sock->state == SS_CONNECTING && @@ -678,7 +678,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) if (vcc->qos.txtp.traffic_class != ATM_NONE && vcc_writable(sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; } diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 581375d0eed2..e91f29c7c638 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -304,7 +304,7 @@ static __poll_t batadv_socket_poll(struct file *file, poll_table *wait) poll_wait(file, &socket_client->queue_wait, wait); if (socket_client->queue_len > 0) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 9be74a44e99d..dc9fa37ddd14 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -193,7 +193,7 @@ static __poll_t batadv_log_poll(struct file *file, poll_table *wait) poll_wait(file, &debug_log->queue_wait, wait); if (!batadv_log_empty(debug_log)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index f897681780db..84d92a077834 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -431,7 +431,7 @@ static inline __poll_t bt_accept_poll(struct sock *parent) if (sk->sk_state == BT_CONNECTED || (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) && sk->sk_state == BT_CONNECT2)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } return 0; @@ -451,20 +451,20 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, return bt_accept_poll(sk); if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR | - (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + mask |= EPOLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == BT_CLOSED) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_state == BT_CONNECT || sk->sk_state == BT_CONNECT2 || @@ -472,7 +472,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, return mask; if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 57403bd567d0..418b76e557b0 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -90,19 +90,6 @@ static int __name ## _show(struct seq_file *f, void *ptr) \ \ DEFINE_SHOW_ATTRIBUTE(__name) -#define DEFINE_SHOW_ATTRIBUTE(__name) \ -static int __name ## _open(struct inode *inode, struct file *file) \ -{ \ - return single_open(file, __name ## _show, inode->i_private); \ -} \ - \ -static const struct file_operations __name ## _fops = { \ - .open = __name ## _open, \ - .read = seq_read, \ - .llseek = seq_lseek, \ - .release = single_release, \ -} \ - static int features_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a86e6687026e..2ced48662c1f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -151,6 +151,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, { u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; + struct netdev_rx_queue *rxqueue; struct xdp_buff xdp = {}; u32 retval, duration; void *data; @@ -165,6 +166,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; + rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); + xdp.rxq = &rxqueue->xdp_rxq; + retval = bpf_test_run(prog, &xdp, repeat, &duration); if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN) size = xdp.data_end - xdp.data; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index b109445a1df9..a6fb1b3bcad9 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -924,7 +924,7 @@ static int caif_release(struct socket *sock) caif_disconnect_client(sock_net(sk), &cf_sk->layer); cf_sk->sk.sk_socket->state = SS_DISCONNECTING; - wake_up_interruptible_poll(sk_sleep(sk), POLLERR|POLLHUP); + wake_up_interruptible_poll(sk_sleep(sk), EPOLLERR|EPOLLHUP); sock_orphan(sk); sk_stream_kill_queues(&cf_sk->sk); @@ -946,23 +946,23 @@ static __poll_t caif_poll(struct file *file, /* exceptional events? */ if (sk->sk_err) - mask |= POLLERR; + mask |= EPOLLERR; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= EPOLLRDHUP; /* readable? */ if (!skb_queue_empty(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* * we set writable also when the other side has shut down the * connection. This prevents stuck sockets. */ if (sock_writeable(sk) && tx_flow_is_on(cf_sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 5c036d2f401e..1e492ef2a33d 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -421,6 +421,10 @@ ceph_parse_options(char *options, const char *dev_name, opt->name = kstrndup(argstr[0].from, argstr[0].to-argstr[0].from, GFP_KERNEL); + if (!opt->name) { + err = -ENOMEM; + goto out; + } break; case Opt_secret: opt->key = kzalloc(sizeof(*opt->key), GFP_KERNEL); diff --git a/net/core/datagram.c b/net/core/datagram.c index b7d9293940b5..9938952c5c78 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -75,7 +75,7 @@ static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, i /* * Avoid a wakeup if event not interesting for us */ - if (key && !(key_to_poll(key) & (POLLIN | POLLERR))) + if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR))) return 0; return autoremove_wake_function(wait, mode, sync, key); } @@ -842,22 +842,22 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, /* exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR | - (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + mask |= EPOLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; /* readable? */ if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ if (connection_based(sk)) { if (sk->sk_state == TCP_CLOSE) - mask |= POLLHUP; + mask |= EPOLLHUP; /* connection hasn't started yet? */ if (sk->sk_state == TCP_SYN_SENT) return mask; @@ -865,7 +865,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, /* writable? */ if (sock_writeable(sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 107b122c8969..494e6a5d7306 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -616,18 +616,15 @@ static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to, return -EFAULT; memcpy(&to->base, &link_usettings.base, sizeof(to->base)); - bitmap_from_u32array(to->link_modes.supported, - __ETHTOOL_LINK_MODE_MASK_NBITS, - link_usettings.link_modes.supported, - __ETHTOOL_LINK_MODE_MASK_NU32); - bitmap_from_u32array(to->link_modes.advertising, - __ETHTOOL_LINK_MODE_MASK_NBITS, - link_usettings.link_modes.advertising, - __ETHTOOL_LINK_MODE_MASK_NU32); - bitmap_from_u32array(to->link_modes.lp_advertising, - __ETHTOOL_LINK_MODE_MASK_NBITS, - link_usettings.link_modes.lp_advertising, - __ETHTOOL_LINK_MODE_MASK_NU32); + bitmap_from_arr32(to->link_modes.supported, + link_usettings.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_from_arr32(to->link_modes.advertising, + link_usettings.link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_from_arr32(to->link_modes.lp_advertising, + link_usettings.link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); return 0; } @@ -643,18 +640,15 @@ store_link_ksettings_for_user(void __user *to, struct ethtool_link_usettings link_usettings; memcpy(&link_usettings.base, &from->base, sizeof(link_usettings)); - bitmap_to_u32array(link_usettings.link_modes.supported, - __ETHTOOL_LINK_MODE_MASK_NU32, - from->link_modes.supported, - __ETHTOOL_LINK_MODE_MASK_NBITS); - bitmap_to_u32array(link_usettings.link_modes.advertising, - __ETHTOOL_LINK_MODE_MASK_NU32, - from->link_modes.advertising, - __ETHTOOL_LINK_MODE_MASK_NBITS); - bitmap_to_u32array(link_usettings.link_modes.lp_advertising, - __ETHTOOL_LINK_MODE_MASK_NU32, - from->link_modes.lp_advertising, - __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_arr32(link_usettings.link_modes.supported, + from->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_arr32(link_usettings.link_modes.advertising, + from->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_to_arr32(link_usettings.link_modes.lp_advertising, + from->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); if (copy_to_user(to, &link_usettings, sizeof(link_usettings))) return -EFAULT; @@ -2358,10 +2352,8 @@ static int ethtool_get_per_queue_coalesce(struct net_device *dev, useraddr += sizeof(*per_queue_opt); - bitmap_from_u32array(queue_mask, - MAX_NUM_QUEUE, - per_queue_opt->queue_mask, - DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + bitmap_from_arr32(queue_mask, per_queue_opt->queue_mask, + MAX_NUM_QUEUE); for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; @@ -2393,10 +2385,7 @@ static int ethtool_set_per_queue_coalesce(struct net_device *dev, useraddr += sizeof(*per_queue_opt); - bitmap_from_u32array(queue_mask, - MAX_NUM_QUEUE, - per_queue_opt->queue_mask, - DIV_ROUND_UP(MAX_NUM_QUEUE, 32)); + bitmap_from_arr32(queue_mask, per_queue_opt->queue_mask, MAX_NUM_QUEUE); n_queue = bitmap_weight(queue_mask, MAX_NUM_QUEUE); tmp = backup = kmalloc_array(n_queue, sizeof(*backup), GFP_KERNEL); if (!backup) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 56af8e41abfc..bc290413a49d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1951,6 +1951,38 @@ static struct net *rtnl_link_get_net_capable(const struct sk_buff *skb, return net; } +/* Verify that rtnetlink requests do not pass additional properties + * potentially referring to different network namespaces. + */ +static int rtnl_ensure_unique_netns(struct nlattr *tb[], + struct netlink_ext_ack *extack, + bool netns_id_only) +{ + + if (netns_id_only) { + if (!tb[IFLA_NET_NS_PID] && !tb[IFLA_NET_NS_FD]) + return 0; + + NL_SET_ERR_MSG(extack, "specified netns attribute not supported"); + return -EOPNOTSUPP; + } + + if (tb[IFLA_IF_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])) + goto invalid_attr; + + if (tb[IFLA_NET_NS_PID] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_FD])) + goto invalid_attr; + + if (tb[IFLA_NET_NS_FD] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_PID])) + goto invalid_attr; + + return 0; + +invalid_attr: + NL_SET_ERR_MSG(extack, "multiple netns identifying attributes specified"); + return -EINVAL; +} + static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) { if (dev) { @@ -2553,6 +2585,10 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto errout; + err = rtnl_ensure_unique_netns(tb, extack, false); + if (err < 0) + goto errout; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); else @@ -2649,6 +2685,10 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + err = rtnl_ensure_unique_netns(tb, extack, true); + if (err < 0) + return err; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); @@ -2802,6 +2842,10 @@ replay: if (err < 0) return err; + err = rtnl_ensure_unique_netns(tb, extack, false); + if (err < 0) + return err; + if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); else @@ -3045,6 +3089,10 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + err = rtnl_ensure_unique_netns(tb, extack, true); + if (err < 0) + return err; + if (tb[IFLA_IF_NETNSID]) { netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8c61c27c1b28..09bd89c90a71 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3894,10 +3894,12 @@ EXPORT_SYMBOL_GPL(skb_gro_receive); void __init skb_init(void) { - skbuff_head_cache = kmem_cache_create("skbuff_head_cache", + skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, + offsetof(struct sk_buff, cb), + sizeof_field(struct sk_buff, cb), NULL); skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), diff --git a/net/core/sock.c b/net/core/sock.c index b026e1717df4..c501499a04fe 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2619,7 +2619,7 @@ static void sock_def_error_report(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_poll(&wq->wait, POLLERR); + wake_up_interruptible_poll(&wq->wait, EPOLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } @@ -2631,8 +2631,8 @@ static void sock_def_readable(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI | - POLLRDNORM | POLLRDBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | + EPOLLRDNORM | EPOLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } @@ -2649,8 +2649,8 @@ static void sock_def_write_space(struct sock *sk) if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | - POLLWRNORM | POLLWRBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) diff --git a/net/core/stream.c b/net/core/stream.c index 1cff9c6270c6..7d329fb1f553 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -38,8 +38,8 @@ void sk_stream_write_space(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_poll(&wq->wait, POLLOUT | - POLLWRNORM | POLLWRBAND); + wake_up_interruptible_poll(&wq->wait, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 74685fecfdb9..15bdc002d90c 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -338,21 +338,21 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, mask = 0; if (sk->sk_err) - mask = POLLERR; + mask = EPOLLERR; if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLIN | POLLRDNORM | POLLRDHUP; + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); @@ -362,7 +362,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, * IO signal will be lost. */ if (sk_stream_is_writeable(sk)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } } } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index cc1b505453a8..91dd09f79808 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1216,7 +1216,7 @@ static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wai __poll_t mask = datagram_poll(file, sock, wait); if (!skb_queue_empty(&scp->other_receive_queue)) - mask |= POLLRDBAND; + mask |= EPOLLRDBAND; return mask; } diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c index af781010753b..49da67034f29 100644 --- a/net/dns_resolver/dns_query.c +++ b/net/dns_resolver/dns_query.c @@ -52,11 +52,11 @@ * @name: Name to look up * @namelen: Length of name * @options: Request options (or NULL if no options) - * @_result: Where to place the returned data. + * @_result: Where to place the returned data (or NULL) * @_expiry: Where to store the result expiry time (or NULL) * - * The data will be returned in the pointer at *result, and the caller is - * responsible for freeing it. + * The data will be returned in the pointer at *result, if provided, and the + * caller is responsible for freeing it. * * The description should be of the form "[<query_type>:]<domain_name>", and * the options need to be appropriate for the query type requested. If no @@ -81,7 +81,7 @@ int dns_query(const char *type, const char *name, size_t namelen, kenter("%s,%*.*s,%zu,%s", type, (int)namelen, (int)namelen, name, namelen, options); - if (!name || namelen == 0 || !_result) + if (!name || namelen == 0) return -EINVAL; /* construct the query key description as "[<type>:]<name>" */ @@ -146,13 +146,15 @@ int dns_query(const char *type, const char *name, size_t namelen, upayload = user_key_payload_locked(rkey); len = upayload->datalen; - ret = -ENOMEM; - *_result = kmalloc(len + 1, GFP_KERNEL); - if (!*_result) - goto put; + if (_result) { + ret = -ENOMEM; + *_result = kmalloc(len + 1, GFP_KERNEL); + if (!*_result) + goto put; - memcpy(*_result, upayload->data, len); - (*_result)[len] = '\0'; + memcpy(*_result, upayload->data, len); + (*_result)[len] = '\0'; + } if (_expiry) *_expiry = rkey->expiry; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c24008daa3d8..e4329e161943 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -828,7 +828,7 @@ int inet_shutdown(struct socket *sock, int how) case TCP_CLOSE: err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for - POLLHUP, even on eg. unconnected UDP sockets -- RR */ + EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ /* fall through */ default: sk->sk_shutdown |= how; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 6ec670fbbbdd..45d97e9b2759 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -261,6 +261,7 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; + struct erspan_md2 *md2; int ver; int len; @@ -313,21 +314,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, return PACKET_REJECT; md = ip_tunnel_info_opts(&tun_dst->u.tun_info); - memcpy(md, pkt_md, sizeof(*md)); md->version = ver; + md2 = &md->u.md2; + memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : + ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; info->key.tun_flags |= TUNNEL_ERSPAN_OPT; info->options_len = sizeof(*md); - } else { - tunnel->erspan_ver = ver; - if (ver == 1) { - tunnel->index = ntohl(pkt_md->u.index); - } else { - tunnel->dir = pkt_md->u.md2.dir; - tunnel->hwid = get_hwid(&pkt_md->u.md2); - } - } skb_reset_mac_header(skb); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 5f52236780b4..dfe6fa4ea554 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -80,8 +80,7 @@ endif # NF_TABLES config NF_FLOW_TABLE_IPV4 tristate "Netfilter flow table IPv4 module" - depends on NF_CONNTRACK && NF_TABLES - select NF_FLOW_TABLE + depends on NF_FLOW_TABLE help This option adds the flow table IPv4 support. diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index b2d01eb25f2c..25d2975da156 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -260,6 +260,7 @@ static struct nf_flowtable_type flowtable_ipv4 = { .family = NFPROTO_IPV4, .params = &nf_flow_offload_rhash_params, .gc = nf_flow_offload_work_gc, + .free = nf_flow_table_free, .hook = nf_flow_offload_ip_hook, .owner = THIS_MODULE, }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c059aa7df0a9..48636aee23c3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -512,36 +512,36 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) mask = 0; /* - * POLLHUP is certainly not done right. But poll() doesn't + * EPOLLHUP is certainly not done right. But poll() doesn't * have a notion of HUP in just one direction, and for a * socket the read side is more interesting. * - * Some poll() documentation says that POLLHUP is incompatible - * with the POLLOUT/POLLWR flags, so somebody should check this + * Some poll() documentation says that EPOLLHUP is incompatible + * with the EPOLLOUT/POLLWR flags, so somebody should check this * all. But careful, it tends to be safer to return too many * bits than too few, and you can easily break real applications * if you don't tell them that something has hung up! * * Check-me. * - * Check number 1. POLLHUP is _UNMASKABLE_ event (see UNIX98 and + * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and * our fs/select.c). It means that after we received EOF, * poll always returns immediately, making impossible poll() on write() - * in state CLOSE_WAIT. One solution is evident --- to set POLLHUP + * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP * if and only if shutdown has been made in both directions. * Actually, it is interesting to look how Solaris and DUX - * solve this dilemma. I would prefer, if POLLHUP were maskable, + * solve this dilemma. I would prefer, if EPOLLHUP were maskable, * then we could set it on SND_SHUTDOWN. BTW examples given * in Stevens' books assume exactly this behaviour, it explains - * why POLLHUP is incompatible with POLLOUT. --ANK + * why EPOLLHUP is incompatible with EPOLLOUT. --ANK * * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLIN | POLLRDNORM | POLLRDHUP; + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && @@ -554,11 +554,11 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) target++; if (tp->rcv_nxt - tp->copied_seq >= target) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); @@ -570,24 +570,24 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ smp_mb__after_atomic(); if (sk_stream_is_writeable(sk)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } } else - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; if (tp->urg_data & TCP_URG_VALID) - mask |= POLLPRI; + mask |= EPOLLPRI; } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { /* Active TCP fastopen socket with defer_connect - * Return POLLOUT so application can call write() + * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data */ - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR; + mask |= EPOLLERR; return mask; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index cfa51cfd2d99..575d3c1fb6e8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -315,7 +315,7 @@ static void tcp_sndbuf_expand(struct sock *sk) /* Fast Recovery (RFC 5681 3.2) : * Cubic needs 1.7 factor, rounded to 2 to include - * extra cushion (application might react slowly to POLLOUT) + * extra cushion (application might react slowly to EPOLLOUT) */ sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2; sndmem *= nr_segs * per_mss; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 95738aa0d8a6..f8ad397e285e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -705,7 +705,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) */ if (sk) { arg.bound_dev_if = sk->sk_bound_dev_if; - trace_tcp_send_reset(sk, skb); + if (sk_fullsock(sk)) + trace_tcp_send_reset(sk, skb); } BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 6bb9e14c710a..622caa4039e0 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -29,6 +29,18 @@ static struct tcp_ulp_ops *tcp_ulp_find(const char *name) return NULL; } +static struct tcp_ulp_ops *tcp_ulp_find_id(const int ulp) +{ + struct tcp_ulp_ops *e; + + list_for_each_entry_rcu(e, &tcp_ulp_list, list) { + if (e->uid == ulp) + return e; + } + + return NULL; +} + static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name) { const struct tcp_ulp_ops *ulp = NULL; @@ -51,6 +63,18 @@ static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name) return ulp; } +static const struct tcp_ulp_ops *__tcp_ulp_lookup(const int uid) +{ + const struct tcp_ulp_ops *ulp; + + rcu_read_lock(); + ulp = tcp_ulp_find_id(uid); + if (!ulp || !try_module_get(ulp->owner)) + ulp = NULL; + rcu_read_unlock(); + return ulp; +} + /* Attach new upper layer protocol to the list * of available protocols. */ @@ -59,13 +83,10 @@ int tcp_register_ulp(struct tcp_ulp_ops *ulp) int ret = 0; spin_lock(&tcp_ulp_list_lock); - if (tcp_ulp_find(ulp->name)) { - pr_notice("%s already registered or non-unique name\n", - ulp->name); + if (tcp_ulp_find(ulp->name)) ret = -EEXIST; - } else { + else list_add_tail_rcu(&ulp->list, &tcp_ulp_list); - } spin_unlock(&tcp_ulp_list_lock); return ret; @@ -124,6 +145,34 @@ int tcp_set_ulp(struct sock *sk, const char *name) if (!ulp_ops) return -ENOENT; + if (!ulp_ops->user_visible) { + module_put(ulp_ops->owner); + return -ENOENT; + } + + err = ulp_ops->init(sk); + if (err) { + module_put(ulp_ops->owner); + return err; + } + + icsk->icsk_ulp_ops = ulp_ops; + return 0; +} + +int tcp_set_ulp_id(struct sock *sk, int ulp) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_ulp_ops *ulp_ops; + int err; + + if (icsk->icsk_ulp_ops) + return -EEXIST; + + ulp_ops = __tcp_ulp_lookup(ulp); + if (!ulp_ops) + return -ENOENT; + err = ulp_ops->init(sk); if (err) { module_put(ulp_ops->owner); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f81f969f9c06..bfaefe560b5c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2501,12 +2501,12 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sock *sk = sock->sk; if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ - if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && + if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) && !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) - mask &= ~(POLLIN | POLLRDNORM); + mask &= ~(EPOLLIN | EPOLLRDNORM); return mask; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 05f070e123e4..3c353125546d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -505,6 +505,7 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, struct erspan_base_hdr *ershdr; struct erspan_metadata *pkt_md; const struct ipv6hdr *ipv6h; + struct erspan_md2 *md2; struct ip6_tnl *tunnel; u8 ver; @@ -551,24 +552,16 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, info = &tun_dst->u.tun_info; md = ip_tunnel_info_opts(info); - - memcpy(md, pkt_md, sizeof(*md)); md->version = ver; + md2 = &md->u.md2; + memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : + ERSPAN_V2_MDSIZE); info->key.tun_flags |= TUNNEL_ERSPAN_OPT; info->options_len = sizeof(*md); ip6_tnl_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } else { - tunnel->parms.erspan_ver = ver; - - if (ver == 1) { - tunnel->parms.index = ntohl(pkt_md->u.index); - } else { - tunnel->parms.dir = pkt_md->u.md2.dir; - tunnel->parms.hwid = get_hwid(&pkt_md->u.md2); - } - ip6_tnl_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 6a5d0e39bb87..9b9d2ff01b35 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -65,10 +65,10 @@ #include <net/ip6_checksum.h> /* Ensure that we have struct in6_addr aligned on 32bit word. */ -static void *__mld2_query_bugs[] __attribute__((__unused__)) = { - BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4), - BUILD_BUG_ON_NULL(offsetof(struct mld2_report, mld2r_grec) % 4), - BUILD_BUG_ON_NULL(offsetof(struct mld2_grec, grec_mca) % 4) +static int __mld2_query_bugs[] __attribute__((__unused__)) = { + BUILD_BUG_ON_ZERO(offsetof(struct mld2_query, mld2q_srcs) % 4), + BUILD_BUG_ON_ZERO(offsetof(struct mld2_report, mld2r_grec) % 4), + BUILD_BUG_ON_ZERO(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4a634b7a2c80..d395d1590699 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -73,8 +73,7 @@ endif # NF_TABLES config NF_FLOW_TABLE_IPV6 tristate "Netfilter flow table IPv6 module" - depends on NF_CONNTRACK && NF_TABLES - select NF_FLOW_TABLE + depends on NF_FLOW_TABLE help This option adds the flow table IPv6 support. diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index ce53dcfda88a..b84ce3e6d728 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -264,6 +264,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, * this case. -DaveM */ pr_debug("end of fragment not rounded to 8 bytes.\n"); + inet_frag_kill(&fq->q, &nf_frags); return -EPROTO; } if (end > fq->q.len) { diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index fff21602875a..d346705d6ee6 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -253,6 +253,7 @@ static struct nf_flowtable_type flowtable_ipv6 = { .family = NFPROTO_IPV6, .params = &nf_flow_offload_rhash_params, .gc = nf_flow_offload_work_gc, + .free = nf_flow_table_free, .hook = nf_flow_offload_ipv6_hook, .owner = THIS_MODULE, }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fb2d251c0500..9dcfadddd800 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2479,7 +2479,7 @@ static int ip6_route_check_nh_onlink(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack) { - u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; + u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT; struct rt6_info *grt; @@ -2488,8 +2488,10 @@ static int ip6_route_check_nh_onlink(struct net *net, err = 0; grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0); if (grt) { - if (grt->rt6i_flags & flags || dev != grt->dst.dev) { - NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); + if (!grt->dst.error && + (grt->rt6i_flags & flags || dev != grt->dst.dev)) { + NL_SET_ERR_MSG(extack, + "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index a1ab29e2ab3b..412139f4eccd 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -942,7 +942,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) if (sk) { oif = sk->sk_bound_dev_if; - trace_tcp_send_reset(sk, skb); + if (sk_fullsock(sk)) + trace_tcp_send_reset(sk, skb); } tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 64331158d693..1e8cc7bcbca3 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1483,7 +1483,7 @@ static inline __poll_t iucv_accept_poll(struct sock *parent) sk = (struct sock *) isk; if (sk->sk_state == IUCV_CONNECTED) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } return 0; @@ -1501,27 +1501,27 @@ __poll_t iucv_sock_poll(struct file *file, struct socket *sock, return iucv_accept_poll(sk); if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR | - (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + mask |= EPOLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= EPOLLRDHUP; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; if (!skb_queue_empty(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == IUCV_CLOSED) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_state == IUCV_DISCONN) - mask |= POLLIN; + mask |= EPOLLIN; if (sock_writeable(sk) && iucv_below_msglim(sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 4a8d407f8902..f297d53a11aa 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -396,8 +396,8 @@ static int kcm_read_sock_done(struct strparser *strp, int err) static void psock_state_change(struct sock *sk) { - /* TCP only does a POLLIN for a half close. Do a POLLHUP here - * since application will normally not poll with POLLIN + /* TCP only does a EPOLLIN for a half close. Do a EPOLLHUP here + * since application will normally not poll with EPOLLIN * on the TCP sockets. */ @@ -1338,7 +1338,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so * we set sk_state, otherwise epoll_wait always returns right away with - * POLLHUP + * EPOLLHUP */ kcm->sk.sk_state = TCP_ESTABLISHED; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 5dce8336d33f..e545a3c9365f 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -8,6 +8,7 @@ #include <linux/ipv6.h> #include <linux/mpls.h> #include <linux/netconf.h> +#include <linux/nospec.h> #include <linux/vmalloc.h> #include <linux/percpu.h> #include <net/ip.h> @@ -935,24 +936,27 @@ errout: return err; } -static bool mpls_label_ok(struct net *net, unsigned int index, +static bool mpls_label_ok(struct net *net, unsigned int *index, struct netlink_ext_ack *extack) { + bool is_ok = true; + /* Reserved labels may not be set */ - if (index < MPLS_LABEL_FIRST_UNRESERVED) { + if (*index < MPLS_LABEL_FIRST_UNRESERVED) { NL_SET_ERR_MSG(extack, "Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher"); - return false; + is_ok = false; } /* The full 20 bit range may not be supported. */ - if (index >= net->mpls.platform_labels) { + if (is_ok && *index >= net->mpls.platform_labels) { NL_SET_ERR_MSG(extack, "Label >= configured maximum in platform_labels"); - return false; + is_ok = false; } - return true; + *index = array_index_nospec(*index, net->mpls.platform_labels); + return is_ok; } static int mpls_route_add(struct mpls_route_config *cfg, @@ -975,7 +979,7 @@ static int mpls_route_add(struct mpls_route_config *cfg, index = find_free_label(net); } - if (!mpls_label_ok(net, index, extack)) + if (!mpls_label_ok(net, &index, extack)) goto errout; /* Append makes no sense with mpls */ @@ -1052,7 +1056,7 @@ static int mpls_route_del(struct mpls_route_config *cfg, index = cfg->rc_label; - if (!mpls_label_ok(net, index, extack)) + if (!mpls_label_ok(net, &index, extack)) goto errout; mpls_route_update(net, index, NULL, &cfg->rc_nlinfo); @@ -1810,7 +1814,7 @@ static int rtm_to_route_config(struct sk_buff *skb, goto errout; if (!mpls_label_ok(cfg->rc_nlinfo.nl_net, - cfg->rc_label, extack)) + &cfg->rc_label, extack)) goto errout; break; } @@ -2137,7 +2141,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, goto errout; } - if (!mpls_label_ok(net, in_label, extack)) { + if (!mpls_label_ok(net, &in_label, extack)) { err = -EINVAL; goto errout; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 9019fa98003d..d3220b43c832 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -666,8 +666,8 @@ endif # NF_TABLES config NF_FLOW_TABLE_INET tristate "Netfilter flow table mixed IPv4/IPv6 module" - depends on NF_FLOW_TABLE_IPV4 && NF_FLOW_TABLE_IPV6 - select NF_FLOW_TABLE + depends on NF_FLOW_TABLE_IPV4 + depends on NF_FLOW_TABLE_IPV6 help This option adds the flow table mixed IPv4/IPv6 support. @@ -675,7 +675,9 @@ config NF_FLOW_TABLE_INET config NF_FLOW_TABLE tristate "Netfilter flow table module" - depends on NF_CONNTRACK && NF_TABLES + depends on NETFILTER_INGRESS + depends on NF_CONNTRACK + depends on NF_TABLES help This option adds the flow table core infrastructure. diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table.c index 2f5099cb85b8..ec410cae9307 100644 --- a/net/netfilter/nf_flow_table.c +++ b/net/netfilter/nf_flow_table.c @@ -4,6 +4,7 @@ #include <linux/netfilter.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> +#include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> @@ -124,7 +125,9 @@ void flow_offload_free(struct flow_offload *flow) dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache); dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache); e = container_of(flow, struct flow_offload_entry, flow); - kfree(e); + nf_ct_delete(e->ct, 0, 0); + nf_ct_put(e->ct); + kfree_rcu(e, rcu_head); } EXPORT_SYMBOL_GPL(flow_offload_free); @@ -148,11 +151,9 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) } EXPORT_SYMBOL_GPL(flow_offload_add); -void flow_offload_del(struct nf_flowtable *flow_table, - struct flow_offload *flow) +static void flow_offload_del(struct nf_flowtable *flow_table, + struct flow_offload *flow) { - struct flow_offload_entry *e; - rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node, *flow_table->type->params); @@ -160,10 +161,8 @@ void flow_offload_del(struct nf_flowtable *flow_table, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, *flow_table->type->params); - e = container_of(flow, struct flow_offload_entry, flow); - kfree_rcu(e, rcu_head); + flow_offload_free(flow); } -EXPORT_SYMBOL_GPL(flow_offload_del); struct flow_offload_tuple_rhash * flow_offload_lookup(struct nf_flowtable *flow_table, @@ -174,15 +173,6 @@ flow_offload_lookup(struct nf_flowtable *flow_table, } EXPORT_SYMBOL_GPL(flow_offload_lookup); -static void nf_flow_release_ct(const struct flow_offload *flow) -{ - struct flow_offload_entry *e; - - e = container_of(flow, struct flow_offload_entry, flow); - nf_ct_delete(e->ct, 0, 0); - nf_ct_put(e->ct); -} - int nf_flow_table_iterate(struct nf_flowtable *flow_table, void (*iter)(struct flow_offload *flow, void *data), void *data) @@ -231,19 +221,16 @@ static inline bool nf_flow_is_dying(const struct flow_offload *flow) return flow->flags & FLOW_OFFLOAD_DYING; } -void nf_flow_offload_work_gc(struct work_struct *work) +static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table) { struct flow_offload_tuple_rhash *tuplehash; - struct nf_flowtable *flow_table; struct rhashtable_iter hti; struct flow_offload *flow; int err; - flow_table = container_of(work, struct nf_flowtable, gc_work.work); - err = rhashtable_walk_init(&flow_table->rhashtable, &hti, GFP_KERNEL); if (err) - goto schedule; + return 0; rhashtable_walk_start(&hti); @@ -261,15 +248,22 @@ void nf_flow_offload_work_gc(struct work_struct *work) flow = container_of(tuplehash, struct flow_offload, tuplehash[0]); if (nf_flow_has_expired(flow) || - nf_flow_is_dying(flow)) { + nf_flow_is_dying(flow)) flow_offload_del(flow_table, flow); - nf_flow_release_ct(flow); - } } out: rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); -schedule: + + return 1; +} + +void nf_flow_offload_work_gc(struct work_struct *work) +{ + struct nf_flowtable *flow_table; + + flow_table = container_of(work, struct nf_flowtable, gc_work.work); + nf_flow_offload_gc_step(flow_table); queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc); @@ -425,5 +419,35 @@ int nf_flow_dnat_port(const struct flow_offload *flow, } EXPORT_SYMBOL_GPL(nf_flow_dnat_port); +static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) +{ + struct net_device *dev = data; + + if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex) + return; + + flow_offload_dead(flow); +} + +static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, + void *data) +{ + nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data); + flush_delayed_work(&flowtable->gc_work); +} + +void nf_flow_table_cleanup(struct net *net, struct net_device *dev) +{ + nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev); +} +EXPORT_SYMBOL_GPL(nf_flow_table_cleanup); + +void nf_flow_table_free(struct nf_flowtable *flow_table) +{ + nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); + WARN_ON(!nf_flow_offload_gc_step(flow_table)); +} +EXPORT_SYMBOL_GPL(nf_flow_table_free); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 281209aeba8f..375a1881d93d 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -24,6 +24,7 @@ static struct nf_flowtable_type flowtable_inet = { .family = NFPROTO_INET, .params = &nf_flow_offload_rhash_params, .gc = nf_flow_offload_work_gc, + .free = nf_flow_table_free, .hook = nf_flow_offload_inet_hook, .owner = THIS_MODULE, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0791813a1e7d..8b9fe30de0cd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5006,13 +5006,13 @@ void nft_flow_table_iterate(struct net *net, struct nft_flowtable *flowtable; const struct nft_table *table; - rcu_read_lock(); - list_for_each_entry_rcu(table, &net->nft.tables, list) { - list_for_each_entry_rcu(flowtable, &table->flowtables, list) { + nfnl_lock(NFNL_SUBSYS_NFTABLES); + list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(flowtable, &table->flowtables, list) { iter(&flowtable->data, data); } } - rcu_read_unlock(); + nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_flow_table_iterate); @@ -5399,17 +5399,12 @@ err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); } -static void nft_flowtable_destroy(void *ptr, void *arg) -{ - kfree(ptr); -} - static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { cancel_delayed_work_sync(&flowtable->data.gc_work); kfree(flowtable->name); - rhashtable_free_and_destroy(&flowtable->data.rhashtable, - nft_flowtable_destroy, NULL); + flowtable->data.type->free(&flowtable->data); + rhashtable_destroy(&flowtable->data.rhashtable); module_put(flowtable->data.type->owner); } diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 4503b8dcf9c0..b65829b2be22 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -194,22 +194,6 @@ static struct nft_expr_type nft_flow_offload_type __read_mostly = { .owner = THIS_MODULE, }; -static void flow_offload_iterate_cleanup(struct flow_offload *flow, void *data) -{ - struct net_device *dev = data; - - if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex) - return; - - flow_offload_dead(flow); -} - -static void nft_flow_offload_iterate_cleanup(struct nf_flowtable *flowtable, - void *data) -{ - nf_flow_table_iterate(flowtable, flow_offload_iterate_cleanup, data); -} - static int flow_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -218,7 +202,7 @@ static int flow_offload_netdev_event(struct notifier_block *this, if (event != NETDEV_DOWN) return NOTIFY_DONE; - nft_flow_table_iterate(dev_net(dev), nft_flow_offload_iterate_cleanup, dev); + nf_flow_table_cleanup(dev_net(dev), dev); return NOTIFY_DONE; } @@ -246,14 +230,8 @@ register_expr: static void __exit nft_flow_offload_module_exit(void) { - struct net *net; - nft_unregister_expr(&nft_flow_offload_type); unregister_netdevice_notifier(&flow_offload_netdev_notifier); - rtnl_lock(); - for_each_net(net) - nft_flow_table_iterate(net, nft_flow_offload_iterate_cleanup, NULL); - rtnl_unlock(); } module_init(nft_flow_offload_module_init); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8fa4d37141a7..2f685ee1f9c8 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1008,7 +1008,12 @@ struct xt_table_info *xt_alloc_table_info(unsigned int size) if ((size >> PAGE_SHIFT) + 2 > totalram_pages) return NULL; - info = kvmalloc(sz, GFP_KERNEL); + /* __GFP_NORETRY is not fully supported by kvmalloc but it should + * work reasonably well if sz is too large and bail out rather + * than shoot all processes down before realizing there is nothing + * more to reclaim. + */ + info = kvmalloc(sz, GFP_KERNEL | __GFP_NORETRY); if (!info) return NULL; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 498b54fd04d7..141c295191f6 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -39,23 +39,31 @@ static void xt_rateest_hash_insert(struct xt_rateest *est) hlist_add_head(&est->list, &rateest_hash[h]); } -struct xt_rateest *xt_rateest_lookup(const char *name) +static struct xt_rateest *__xt_rateest_lookup(const char *name) { struct xt_rateest *est; unsigned int h; h = xt_rateest_hash(name); - mutex_lock(&xt_rateest_mutex); hlist_for_each_entry(est, &rateest_hash[h], list) { if (strcmp(est->name, name) == 0) { est->refcnt++; - mutex_unlock(&xt_rateest_mutex); return est; } } - mutex_unlock(&xt_rateest_mutex); + return NULL; } + +struct xt_rateest *xt_rateest_lookup(const char *name) +{ + struct xt_rateest *est; + + mutex_lock(&xt_rateest_mutex); + est = __xt_rateest_lookup(name); + mutex_unlock(&xt_rateest_mutex); + return est; +} EXPORT_SYMBOL_GPL(xt_rateest_lookup); void xt_rateest_put(struct xt_rateest *est) @@ -100,8 +108,10 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) net_get_random_once(&jhash_rnd, sizeof(jhash_rnd)); - est = xt_rateest_lookup(info->name); + mutex_lock(&xt_rateest_mutex); + est = __xt_rateest_lookup(info->name); if (est) { + mutex_unlock(&xt_rateest_mutex); /* * If estimator parameters are specified, they must match the * existing estimator. @@ -139,11 +149,13 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) info->est = est; xt_rateest_hash_insert(est); + mutex_unlock(&xt_rateest_mutex); return 0; err2: kfree(est); err1: + mutex_unlock(&xt_rateest_mutex); return ret; } diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c index 1db1ce59079f..891f4e7e8ea7 100644 --- a/net/netfilter/xt_cgroup.c +++ b/net/netfilter/xt_cgroup.c @@ -52,6 +52,7 @@ static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) return -EINVAL; } + info->priv = NULL; if (info->has_path) { cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d444daf1ac04..6f02499ef007 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1081,6 +1081,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, { struct sk_buff *tmp; struct net *net, *prev = NULL; + bool delivered = false; int err; for_each_net_rcu(net) { @@ -1092,14 +1093,21 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, } err = nlmsg_multicast(prev->genl_sock, tmp, portid, group, flags); - if (err) + if (!err) + delivered = true; + else if (err != -ESRCH) goto error; } prev = net; } - return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); + err = nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); + if (!err) + delivered = true; + else if (err != -ESRCH) + goto error; + return delivered ? 0 : -ESRCH; error: kfree_skb(skb); return err; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 985909f105eb..376040092142 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -543,7 +543,7 @@ static inline __poll_t llcp_accept_poll(struct sock *parent) sk = &llcp_sock->sk; if (sk->sk_state == LLCP_CONNECTED) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } return 0; @@ -563,23 +563,23 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock, return llcp_accept_poll(sk); if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR | - (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + mask |= EPOLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == LLCP_CLOSED) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 1d1483007e46..e0f3f4aeeb4f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4085,7 +4085,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock, if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } if (po->pressure && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) po->pressure = 0; @@ -4093,7 +4093,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock, spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 08f6751d2030..fffcd69f63ff 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -351,18 +351,18 @@ static __poll_t pn_socket_poll(struct file *file, struct socket *sock, poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == TCP_CLOSE) - return POLLERR; + return EPOLLERR; if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (!skb_queue_empty(&pn->ctrlreq_queue)) - mask |= POLLPRI; + mask |= EPOLLPRI; if (!mask && sk->sk_state == TCP_CLOSE_WAIT) - return POLLHUP; + return EPOLLHUP; if (sk->sk_state == TCP_ESTABLISHED && refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf && atomic_read(&pn->tx_credits)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; } diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 88aa8ad0f5b6..744c637c86b0 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -137,17 +137,17 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr, /* * RDS' poll is without a doubt the least intuitive part of the interface, - * as POLLIN and POLLOUT do not behave entirely as you would expect from + * as EPOLLIN and EPOLLOUT do not behave entirely as you would expect from * a network protocol. * - * POLLIN is asserted if + * EPOLLIN is asserted if * - there is data on the receive queue. * - to signal that a previously congested destination may have become * uncongested * - A notification has been queued to the socket (this can be a congestion * update, or a RDMA completion). * - * POLLOUT is asserted if there is room on the send queue. This does not mean + * EPOLLOUT is asserted if there is room on the send queue. This does not mean * however, that the next sendmsg() call will succeed. If the application tries * to send to a congested destination, the system call may still fail (and * return ENOBUFS). @@ -167,22 +167,22 @@ static __poll_t rds_poll(struct file *file, struct socket *sock, read_lock_irqsave(&rs->rs_recv_lock, flags); if (!rs->rs_cong_monitor) { - /* When a congestion map was updated, we signal POLLIN for + /* When a congestion map was updated, we signal EPOLLIN for * "historical" reasons. Applications can also poll for * WRBAND instead. */ if (rds_cong_updated_since(&rs->rs_cong_track)) - mask |= (POLLIN | POLLRDNORM | POLLWRBAND); + mask |= (EPOLLIN | EPOLLRDNORM | EPOLLWRBAND); } else { spin_lock(&rs->rs_lock); if (rs->rs_cong_notify) - mask |= (POLLIN | POLLRDNORM); + mask |= (EPOLLIN | EPOLLRDNORM); spin_unlock(&rs->rs_lock); } if (!list_empty(&rs->rs_recv_queue) || !list_empty(&rs->rs_notify_queue)) - mask |= (POLLIN | POLLRDNORM); + mask |= (EPOLLIN | EPOLLRDNORM); if (rs->rs_snd_bytes < rds_sk_sndbuf(rs)) - mask |= (POLLOUT | POLLWRNORM); + mask |= (EPOLLOUT | EPOLLWRNORM); read_unlock_irqrestore(&rs->rs_recv_lock, flags); /* clear state any time we wake a seen-congested socket */ diff --git a/net/rds/cong.c b/net/rds/cong.c index 8d19fd25dce3..63da9d2f142d 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -223,7 +223,7 @@ void rds_cong_queue_updates(struct rds_cong_map *map) rcu_read_lock(); if (!test_and_set_bit(0, &conn->c_map_queued) && - !test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) { + !rds_destroy_pending(cp->cp_conn)) { rds_stats_inc(s_cong_update_queued); /* We cannot inline the call to rds_send_xmit() here * for two reasons (both pertaining to a TCP transport): diff --git a/net/rds/connection.c b/net/rds/connection.c index b10c0ef36d8d..94e190febfdd 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -220,8 +220,13 @@ static struct rds_connection *__rds_conn_create(struct net *net, is_outgoing); conn->c_path[i].cp_index = i; } - ret = trans->conn_alloc(conn, gfp); + rcu_read_lock(); + if (rds_destroy_pending(conn)) + ret = -ENETDOWN; + else + ret = trans->conn_alloc(conn, gfp); if (ret) { + rcu_read_unlock(); kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(ret); @@ -283,6 +288,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, } } spin_unlock_irqrestore(&rds_conn_lock, flags); + rcu_read_unlock(); out: return conn; @@ -382,13 +388,10 @@ static void rds_conn_path_destroy(struct rds_conn_path *cp) { struct rds_message *rm, *rtmp; - set_bit(RDS_DESTROY_PENDING, &cp->cp_flags); - if (!cp->cp_transport_data) return; /* make sure lingering queued work won't try to ref the conn */ - synchronize_rcu(); cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); @@ -691,7 +694,7 @@ void rds_conn_path_drop(struct rds_conn_path *cp, bool destroy) atomic_set(&cp->cp_state, RDS_CONN_ERROR); rcu_read_lock(); - if (!destroy && test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) { + if (!destroy && rds_destroy_pending(cp->cp_conn)) { rcu_read_unlock(); return; } @@ -714,7 +717,7 @@ EXPORT_SYMBOL_GPL(rds_conn_drop); void rds_conn_path_connect_if_down(struct rds_conn_path *cp) { rcu_read_lock(); - if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) { + if (rds_destroy_pending(cp->cp_conn)) { rcu_read_unlock(); return; } diff --git a/net/rds/ib.c b/net/rds/ib.c index b2a5067b4afe..50a88f3e7e39 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -48,6 +48,7 @@ static unsigned int rds_ib_mr_1m_pool_size = RDS_MR_1M_POOL_SIZE; static unsigned int rds_ib_mr_8k_pool_size = RDS_MR_8K_POOL_SIZE; unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT; +static atomic_t rds_ib_unloading; module_param(rds_ib_mr_1m_pool_size, int, 0444); MODULE_PARM_DESC(rds_ib_mr_1m_pool_size, " Max number of 1M mr per HCA"); @@ -345,7 +346,8 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr) /* Create a CMA ID and try to bind it. This catches both * IB and iWARP capable NICs. */ - cm_id = rdma_create_id(&init_net, NULL, NULL, RDMA_PS_TCP, IB_QPT_RC); + cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, + NULL, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); @@ -377,8 +379,23 @@ static void rds_ib_unregister_client(void) flush_workqueue(rds_wq); } +static void rds_ib_set_unloading(void) +{ + atomic_set(&rds_ib_unloading, 1); +} + +static bool rds_ib_is_unloading(struct rds_connection *conn) +{ + struct rds_conn_path *cp = &conn->c_path[0]; + + return (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags) || + atomic_read(&rds_ib_unloading) != 0); +} + void rds_ib_exit(void) { + rds_ib_set_unloading(); + synchronize_rcu(); rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info); rds_ib_unregister_client(); rds_ib_destroy_nodev_conns(); @@ -412,6 +429,7 @@ struct rds_transport rds_ib_transport = { .flush_mrs = rds_ib_flush_mrs, .t_owner = THIS_MODULE, .t_name = "infiniband", + .t_unloading = rds_ib_is_unloading, .t_type = RDS_TRANS_IB }; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 80fb6f63e768..eea1d8611b20 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -117,6 +117,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even &conn->c_laddr, &conn->c_faddr, RDS_PROTOCOL_MAJOR(conn->c_version), RDS_PROTOCOL_MINOR(conn->c_version)); + set_bit(RDS_DESTROY_PENDING, &conn->c_path[0].cp_flags); rds_conn_destroy(conn); return; } else { diff --git a/net/rds/rds.h b/net/rds/rds.h index 374ae83b60d4..7301b9b01890 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -518,6 +518,7 @@ struct rds_transport { void (*sync_mr)(void *trans_private, int direction); void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); + bool (*t_unloading)(struct rds_connection *conn); }; struct rds_sock { @@ -862,6 +863,12 @@ static inline void rds_mr_put(struct rds_mr *mr) __rds_put_mr_final(mr); } +static inline bool rds_destroy_pending(struct rds_connection *conn) +{ + return !check_net(rds_conn_net(conn)) || + (conn->c_trans->t_unloading && conn->c_trans->t_unloading(conn)); +} + /* stats.c */ DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); #define rds_stats_inc_which(which, member) do { \ diff --git a/net/rds/send.c b/net/rds/send.c index d3e32d1f3c7d..b1b0022b8370 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -162,7 +162,7 @@ restart: goto out; } - if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) { + if (rds_destroy_pending(cp->cp_conn)) { release_in_xmit(cp); ret = -ENETUNREACH; /* dont requeue send work */ goto out; @@ -444,7 +444,7 @@ over_batch: if (batch_count < send_batch_count) goto restart; rcu_read_lock(); - if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) + if (rds_destroy_pending(cp->cp_conn)) ret = -ENETUNREACH; else queue_delayed_work(rds_wq, &cp->cp_send_w, 1); @@ -1162,7 +1162,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) else cpath = &conn->c_path[0]; - if (test_bit(RDS_DESTROY_PENDING, &cpath->cp_flags)) { + if (rds_destroy_pending(conn)) { ret = -EAGAIN; goto out; } @@ -1209,7 +1209,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (ret == -ENOMEM || ret == -EAGAIN) { ret = 0; rcu_read_lock(); - if (test_bit(RDS_DESTROY_PENDING, &cpath->cp_flags)) + if (rds_destroy_pending(cpath->cp_conn)) ret = -ENETUNREACH; else queue_delayed_work(rds_wq, &cpath->cp_send_w, 1); @@ -1295,7 +1295,7 @@ rds_send_probe(struct rds_conn_path *cp, __be16 sport, /* schedule the send work on rds_wq */ rcu_read_lock(); - if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) + if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_send_w, 1); rcu_read_unlock(); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 9920d2f84eff..44c4652721af 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -49,6 +49,7 @@ static unsigned int rds_tcp_tc_count; /* Track rds_tcp_connection structs so they can be cleaned up */ static DEFINE_SPINLOCK(rds_tcp_conn_lock); static LIST_HEAD(rds_tcp_conn_list); +static atomic_t rds_tcp_unloading = ATOMIC_INIT(0); static struct kmem_cache *rds_tcp_conn_slab; @@ -274,14 +275,13 @@ static int rds_tcp_laddr_check(struct net *net, __be32 addr) static void rds_tcp_conn_free(void *arg) { struct rds_tcp_connection *tc = arg; - unsigned long flags; rdsdebug("freeing tc %p\n", tc); - spin_lock_irqsave(&rds_tcp_conn_lock, flags); + spin_lock_bh(&rds_tcp_conn_lock); if (!tc->t_tcp_node_detached) list_del(&tc->t_tcp_node); - spin_unlock_irqrestore(&rds_tcp_conn_lock, flags); + spin_unlock_bh(&rds_tcp_conn_lock); kmem_cache_free(rds_tcp_conn_slab, tc); } @@ -296,7 +296,7 @@ static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp) tc = kmem_cache_alloc(rds_tcp_conn_slab, gfp); if (!tc) { ret = -ENOMEM; - break; + goto fail; } mutex_init(&tc->t_conn_path_lock); tc->t_sock = NULL; @@ -306,14 +306,19 @@ static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp) conn->c_path[i].cp_transport_data = tc; tc->t_cpath = &conn->c_path[i]; + tc->t_tcp_node_detached = true; - spin_lock_irq(&rds_tcp_conn_lock); - tc->t_tcp_node_detached = false; - list_add_tail(&tc->t_tcp_node, &rds_tcp_conn_list); - spin_unlock_irq(&rds_tcp_conn_lock); rdsdebug("rds_conn_path [%d] tc %p\n", i, conn->c_path[i].cp_transport_data); } + spin_lock_bh(&rds_tcp_conn_lock); + for (i = 0; i < RDS_MPATH_WORKERS; i++) { + tc = conn->c_path[i].cp_transport_data; + tc->t_tcp_node_detached = false; + list_add_tail(&tc->t_tcp_node, &rds_tcp_conn_list); + } + spin_unlock_bh(&rds_tcp_conn_lock); +fail: if (ret) { for (j = 0; j < i; j++) rds_tcp_conn_free(conn->c_path[j].cp_transport_data); @@ -332,6 +337,16 @@ static bool list_has_conn(struct list_head *list, struct rds_connection *conn) return false; } +static void rds_tcp_set_unloading(void) +{ + atomic_set(&rds_tcp_unloading, 1); +} + +static bool rds_tcp_is_unloading(struct rds_connection *conn) +{ + return atomic_read(&rds_tcp_unloading) != 0; +} + static void rds_tcp_destroy_conns(void) { struct rds_tcp_connection *tc, *_tc; @@ -370,6 +385,7 @@ struct rds_transport rds_tcp_transport = { .t_type = RDS_TRANS_TCP, .t_prefer_loopback = 1, .t_mp_capable = 1, + .t_unloading = rds_tcp_is_unloading, }; static unsigned int rds_tcp_netid; @@ -513,7 +529,7 @@ static void rds_tcp_kill_sock(struct net *net) rtn->rds_tcp_listen_sock = NULL; rds_tcp_listen_stop(lsock, &rtn->rds_tcp_accept_w); - spin_lock_irq(&rds_tcp_conn_lock); + spin_lock_bh(&rds_tcp_conn_lock); list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net); @@ -526,7 +542,7 @@ static void rds_tcp_kill_sock(struct net *net) tc->t_tcp_node_detached = true; } } - spin_unlock_irq(&rds_tcp_conn_lock); + spin_unlock_bh(&rds_tcp_conn_lock); list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) rds_conn_destroy(tc->t_cpath->cp_conn); } @@ -574,7 +590,7 @@ static void rds_tcp_sysctl_reset(struct net *net) { struct rds_tcp_connection *tc, *_tc; - spin_lock_irq(&rds_tcp_conn_lock); + spin_lock_bh(&rds_tcp_conn_lock); list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net); @@ -584,7 +600,7 @@ static void rds_tcp_sysctl_reset(struct net *net) /* reconnect with new parameters */ rds_conn_path_drop(tc->t_cpath, false); } - spin_unlock_irq(&rds_tcp_conn_lock); + spin_unlock_bh(&rds_tcp_conn_lock); } static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write, @@ -607,6 +623,8 @@ static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write, static void rds_tcp_exit(void) { + rds_tcp_set_unloading(); + synchronize_rcu(); rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); unregister_pernet_subsys(&rds_tcp_net_ops); if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 534c67aeb20f..d999e7075645 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -170,7 +170,7 @@ void rds_tcp_conn_path_shutdown(struct rds_conn_path *cp) cp->cp_conn, tc, sock); if (sock) { - if (test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) + if (rds_destroy_pending(cp->cp_conn)) rds_tcp_set_linger(sock); sock->ops->shutdown(sock, RCV_SHUTDOWN | SEND_SHUTDOWN); lock_sock(sock->sk); diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index dd707b9e73e5..b9fbd2ee74ef 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -323,7 +323,7 @@ void rds_tcp_data_ready(struct sock *sk) if (rds_tcp_read_sock(cp, GFP_ATOMIC) == -ENOMEM) { rcu_read_lock(); - if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) + if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_recv_w, 0); rcu_read_unlock(); } diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 16f65744d984..7df869d37afd 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -204,7 +204,7 @@ void rds_tcp_write_space(struct sock *sk) rcu_read_lock(); if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf && - !test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) + !rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_send_w, 0); rcu_read_unlock(); diff --git a/net/rds/threads.c b/net/rds/threads.c index eb76db1360b0..c52861d77a59 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -88,7 +88,7 @@ void rds_connect_path_complete(struct rds_conn_path *cp, int curr) cp->cp_reconnect_jiffies = 0; set_bit(0, &cp->cp_conn->c_map_queued); rcu_read_lock(); - if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) { + if (!rds_destroy_pending(cp->cp_conn)) { queue_delayed_work(rds_wq, &cp->cp_send_w, 0); queue_delayed_work(rds_wq, &cp->cp_recv_w, 0); } @@ -138,7 +138,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp) if (cp->cp_reconnect_jiffies == 0) { cp->cp_reconnect_jiffies = rds_sysctl_reconnect_min_jiffies; rcu_read_lock(); - if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) + if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_conn_w, 0); rcu_read_unlock(); return; @@ -149,7 +149,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp) rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies, conn, &conn->c_laddr, &conn->c_faddr); rcu_read_lock(); - if (!test_bit(RDS_DESTROY_PENDING, &cp->cp_flags)) + if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_conn_w, rand % cp->cp_reconnect_jiffies); rcu_read_unlock(); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 124c77e9d058..59d0eb960275 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1142,13 +1142,13 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) static __poll_t rfkill_fop_poll(struct file *file, poll_table *wait) { struct rfkill_data *data = file->private_data; - __poll_t res = POLLOUT | POLLWRNORM; + __poll_t res = EPOLLOUT | EPOLLWRNORM; poll_wait(file, &data->read_wait, wait); mutex_lock(&data->mtx); if (!list_empty(&data->events)) - res = POLLIN | POLLRDNORM; + res = EPOLLIN | EPOLLRDNORM; mutex_unlock(&data->mtx); return res; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 21ad6a3a465c..0c9c18aa7c77 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -742,13 +742,13 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock, /* the socket is readable if there are any messages waiting on the Rx * queue */ if (!list_empty(&rx->recvmsg_q)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* the socket is writable if there is space to add new data to the * socket; there is no guarantee that any particular call in progress * on the socket may have space in the Tx ACK window */ if (rxrpc_writable(sk)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 7f74ca3059f8..064175068059 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -834,7 +834,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) * can be skipped if we find a follow-on call. The first DATA packet * of the follow on call will implicitly ACK this call. */ - if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { + if (call->completion == RXRPC_CALL_SUCCEEDED && + test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { unsigned long final_ack_at = jiffies + 2; WRITE_ONCE(chan->final_ack_at, final_ack_at); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 4ca11be6be3c..b1dfae107431 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -460,6 +460,7 @@ void rxrpc_process_connection(struct work_struct *work) case -EKEYEXPIRED: case -EKEYREJECTED: goto protocol_error; + case -ENOMEM: case -EAGAIN: goto requeue_and_leave; case -ECONNABORTED: diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index c628351eb900..ccbac190add1 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -177,13 +177,21 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, * through the channel, whilst disposing of the actual call record. */ trace_rxrpc_disconnect_call(call); - if (call->abort_code) { - chan->last_abort = call->abort_code; - chan->last_type = RXRPC_PACKET_TYPE_ABORT; - } else { + switch (call->completion) { + case RXRPC_CALL_SUCCEEDED: chan->last_seq = call->rx_hard_ack; chan->last_type = RXRPC_PACKET_TYPE_ACK; + break; + case RXRPC_CALL_LOCALLY_ABORTED: + chan->last_abort = call->abort_code; + chan->last_type = RXRPC_PACKET_TYPE_ABORT; + break; + default: + chan->last_abort = RX_USER_ABORT; + chan->last_type = RXRPC_PACKET_TYPE_ABORT; + break; } + /* Sync with rxrpc_conn_retransmit(). */ smp_wmb(); chan->last_call = chan->call_id; diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index c38b3a1de56c..77cb23c7bd0a 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -773,8 +773,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, { const struct rxrpc_key_token *token; struct rxkad_challenge challenge; - struct rxkad_response resp - __attribute__((aligned(8))); /* must be aligned for crypto */ + struct rxkad_response *resp; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); const char *eproto; u32 version, nonce, min_level, abort_code; @@ -818,26 +817,29 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, token = conn->params.key->payload.data[0]; /* build the response packet */ - memset(&resp, 0, sizeof(resp)); - - resp.version = htonl(RXKAD_VERSION); - resp.encrypted.epoch = htonl(conn->proto.epoch); - resp.encrypted.cid = htonl(conn->proto.cid); - resp.encrypted.securityIndex = htonl(conn->security_ix); - resp.encrypted.inc_nonce = htonl(nonce + 1); - resp.encrypted.level = htonl(conn->params.security_level); - resp.kvno = htonl(token->kad->kvno); - resp.ticket_len = htonl(token->kad->ticket_len); - - resp.encrypted.call_id[0] = htonl(conn->channels[0].call_counter); - resp.encrypted.call_id[1] = htonl(conn->channels[1].call_counter); - resp.encrypted.call_id[2] = htonl(conn->channels[2].call_counter); - resp.encrypted.call_id[3] = htonl(conn->channels[3].call_counter); + resp = kzalloc(sizeof(struct rxkad_response), GFP_NOFS); + if (!resp) + return -ENOMEM; + + resp->version = htonl(RXKAD_VERSION); + resp->encrypted.epoch = htonl(conn->proto.epoch); + resp->encrypted.cid = htonl(conn->proto.cid); + resp->encrypted.securityIndex = htonl(conn->security_ix); + resp->encrypted.inc_nonce = htonl(nonce + 1); + resp->encrypted.level = htonl(conn->params.security_level); + resp->kvno = htonl(token->kad->kvno); + resp->ticket_len = htonl(token->kad->ticket_len); + resp->encrypted.call_id[0] = htonl(conn->channels[0].call_counter); + resp->encrypted.call_id[1] = htonl(conn->channels[1].call_counter); + resp->encrypted.call_id[2] = htonl(conn->channels[2].call_counter); + resp->encrypted.call_id[3] = htonl(conn->channels[3].call_counter); /* calculate the response checksum and then do the encryption */ - rxkad_calc_response_checksum(&resp); - rxkad_encrypt_response(conn, &resp, token->kad); - return rxkad_send_response(conn, &sp->hdr, &resp, token->kad); + rxkad_calc_response_checksum(resp); + rxkad_encrypt_response(conn, resp, token->kad); + ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); + kfree(resp); + return ret; protocol_error: trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); @@ -1048,8 +1050,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, struct sk_buff *skb, u32 *_abort_code) { - struct rxkad_response response - __attribute__((aligned(8))); /* must be aligned for crypto */ + struct rxkad_response *response; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt session_key; const char *eproto; @@ -1061,17 +1062,22 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); + ret = -ENOMEM; + response = kzalloc(sizeof(struct rxkad_response), GFP_NOFS); + if (!response) + goto temporary_error; + eproto = tracepoint_string("rxkad_rsp_short"); abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - &response, sizeof(response)) < 0) + response, sizeof(*response)) < 0) goto protocol_error; - if (!pskb_pull(skb, sizeof(response))) + if (!pskb_pull(skb, sizeof(*response))) BUG(); - version = ntohl(response.version); - ticket_len = ntohl(response.ticket_len); - kvno = ntohl(response.kvno); + version = ntohl(response->version); + ticket_len = ntohl(response->ticket_len); + kvno = ntohl(response->kvno); _proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }", sp->hdr.serial, version, kvno, ticket_len); @@ -1105,31 +1111,31 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key, &expiry, _abort_code); if (ret < 0) - goto temporary_error_free; + goto temporary_error_free_resp; /* use the session key from inside the ticket to decrypt the * response */ - rxkad_decrypt_response(conn, &response, &session_key); + rxkad_decrypt_response(conn, response, &session_key); eproto = tracepoint_string("rxkad_rsp_param"); abort_code = RXKADSEALEDINCON; - if (ntohl(response.encrypted.epoch) != conn->proto.epoch) + if (ntohl(response->encrypted.epoch) != conn->proto.epoch) goto protocol_error_free; - if (ntohl(response.encrypted.cid) != conn->proto.cid) + if (ntohl(response->encrypted.cid) != conn->proto.cid) goto protocol_error_free; - if (ntohl(response.encrypted.securityIndex) != conn->security_ix) + if (ntohl(response->encrypted.securityIndex) != conn->security_ix) goto protocol_error_free; - csum = response.encrypted.checksum; - response.encrypted.checksum = 0; - rxkad_calc_response_checksum(&response); + csum = response->encrypted.checksum; + response->encrypted.checksum = 0; + rxkad_calc_response_checksum(response); eproto = tracepoint_string("rxkad_rsp_csum"); - if (response.encrypted.checksum != csum) + if (response->encrypted.checksum != csum) goto protocol_error_free; spin_lock(&conn->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { struct rxrpc_call *call; - u32 call_id = ntohl(response.encrypted.call_id[i]); + u32 call_id = ntohl(response->encrypted.call_id[i]); eproto = tracepoint_string("rxkad_rsp_callid"); if (call_id > INT_MAX) @@ -1153,12 +1159,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, eproto = tracepoint_string("rxkad_rsp_seq"); abort_code = RXKADOUTOFSEQUENCE; - if (ntohl(response.encrypted.inc_nonce) != conn->security_nonce + 1) + if (ntohl(response->encrypted.inc_nonce) != conn->security_nonce + 1) goto protocol_error_free; eproto = tracepoint_string("rxkad_rsp_level"); abort_code = RXKADLEVELFAIL; - level = ntohl(response.encrypted.level); + level = ntohl(response->encrypted.level); if (level > RXRPC_SECURITY_ENCRYPT) goto protocol_error_free; conn->params.security_level = level; @@ -1168,9 +1174,10 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, * as for a client connection */ ret = rxrpc_get_server_data_key(conn, &session_key, expiry, kvno); if (ret < 0) - goto temporary_error_free; + goto temporary_error_free_ticket; kfree(ticket); + kfree(response); _leave(" = 0"); return 0; @@ -1179,12 +1186,15 @@ protocol_error_unlock: protocol_error_free: kfree(ticket); protocol_error: + kfree(response); trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); *_abort_code = abort_code; return -EPROTO; -temporary_error_free: +temporary_error_free_ticket: kfree(ticket); +temporary_error_free_resp: + kfree(response); temporary_error: /* Ignore the response packet if we got a temporary error such as * ENOMEM. We just want to send the challenge again. Note that we diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 52622a3d2517..eba6682727dd 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -78,7 +78,7 @@ static void free_tcf(struct tc_action *p) static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p) { spin_lock_bh(&idrinfo->lock); - idr_remove_ext(&idrinfo->action_idr, p->tcfa_index); + idr_remove(&idrinfo->action_idr, p->tcfa_index); spin_unlock_bh(&idrinfo->lock); gen_kill_estimator(&p->tcfa_rate_est); free_tcf(p); @@ -124,7 +124,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, s_i = cb->args[0]; - idr_for_each_entry_ext(idr, p, id) { + idr_for_each_entry_ul(idr, p, id) { index++; if (index < s_i) continue; @@ -181,7 +181,7 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure; - idr_for_each_entry_ext(idr, p, id) { + idr_for_each_entry_ul(idr, p, id) { ret = __tcf_idr_release(p, false, true); if (ret == ACT_P_DELETED) { module_put(ops->owner); @@ -222,7 +222,7 @@ static struct tc_action *tcf_idr_lookup(u32 index, struct tcf_idrinfo *idrinfo) struct tc_action *p = NULL; spin_lock_bh(&idrinfo->lock); - p = idr_find_ext(&idrinfo->action_idr, index); + p = idr_find(&idrinfo->action_idr, index); spin_unlock_bh(&idrinfo->lock); return p; @@ -274,7 +274,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tcf_idrinfo *idrinfo = tn->idrinfo; struct idr *idr = &idrinfo->action_idr; int err = -ENOMEM; - unsigned long idr_index; if (unlikely(!p)) return -ENOMEM; @@ -284,45 +283,28 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, if (cpustats) { p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); - if (!p->cpu_bstats) { -err1: - kfree(p); - return err; - } - p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); - if (!p->cpu_qstats) { -err2: - free_percpu(p->cpu_bstats); + if (!p->cpu_bstats) goto err1; - } + p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!p->cpu_qstats) + goto err2; } spin_lock_init(&p->tcfa_lock); + idr_preload(GFP_KERNEL); + spin_lock_bh(&idrinfo->lock); /* user doesn't specify an index */ if (!index) { - idr_preload(GFP_KERNEL); - spin_lock_bh(&idrinfo->lock); - err = idr_alloc_ext(idr, NULL, &idr_index, 1, 0, - GFP_ATOMIC); - spin_unlock_bh(&idrinfo->lock); - idr_preload_end(); - if (err) { -err3: - free_percpu(p->cpu_qstats); - goto err2; - } - p->tcfa_index = idr_index; + index = 1; + err = idr_alloc_u32(idr, NULL, &index, UINT_MAX, GFP_ATOMIC); } else { - idr_preload(GFP_KERNEL); - spin_lock_bh(&idrinfo->lock); - err = idr_alloc_ext(idr, NULL, NULL, index, index + 1, - GFP_ATOMIC); - spin_unlock_bh(&idrinfo->lock); - idr_preload_end(); - if (err) - goto err3; - p->tcfa_index = index; + err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC); } + spin_unlock_bh(&idrinfo->lock); + idr_preload_end(); + if (err) + goto err3; + p->tcfa_index = index; p->tcfa_tm.install = jiffies; p->tcfa_tm.lastuse = jiffies; p->tcfa_tm.firstuse = 0; @@ -330,9 +312,8 @@ err3: err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, &p->tcfa_lock, NULL, est); - if (err) { - goto err3; - } + if (err) + goto err4; } p->idrinfo = idrinfo; @@ -340,6 +321,15 @@ err3: INIT_LIST_HEAD(&p->list); *a = p; return 0; +err4: + idr_remove(idr, index); +err3: + free_percpu(p->cpu_qstats); +err2: + free_percpu(p->cpu_bstats); +err1: + kfree(p); + return err; } EXPORT_SYMBOL(tcf_idr_create); @@ -348,7 +338,7 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) struct tcf_idrinfo *idrinfo = tn->idrinfo; spin_lock_bh(&idrinfo->lock); - idr_replace_ext(&idrinfo->action_idr, a, a->tcfa_index); + idr_replace(&idrinfo->action_idr, a, a->tcfa_index); spin_unlock_bh(&idrinfo->lock); } EXPORT_SYMBOL(tcf_idr_insert); @@ -361,7 +351,7 @@ void tcf_idrinfo_destroy(const struct tc_action_ops *ops, int ret; unsigned long id = 1; - idr_for_each_entry_ext(idr, p, id) { + idr_for_each_entry_ul(idr, p, id) { ret = __tcf_idr_release(p, false, true); if (ret == ACT_P_DELETED) module_put(ops->owner); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index bcb4ccb5f894..2bc1bc23d42e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -381,8 +381,8 @@ static int tcf_block_insert(struct tcf_block *block, struct net *net, struct tcf_net *tn = net_generic(net, tcf_net_id); int err; - err = idr_alloc_ext(&tn->idr, block, NULL, block_index, - block_index + 1, GFP_KERNEL); + err = idr_alloc_u32(&tn->idr, block, &block_index, block_index, + GFP_KERNEL); if (err) return err; block->index = block_index; @@ -393,7 +393,7 @@ static void tcf_block_remove(struct tcf_block *block, struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); - idr_remove_ext(&tn->idr, block->index); + idr_remove(&tn->idr, block->index); } static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, @@ -434,7 +434,7 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) { struct tcf_net *tn = net_generic(net, tcf_net_id); - return idr_find_ext(&tn->idr, block_index); + return idr_find(&tn->idr, block_index); } static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index d333f5c5101d..6b7ab3512f5b 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -120,7 +120,7 @@ static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) list_for_each_entry_safe(f, n, &head->flist, link) { list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); - idr_remove_ext(&head->handle_idr, f->handle); + idr_remove(&head->handle_idr, f->handle); if (tcf_exts_get_net(&f->exts)) call_rcu(&f->rcu, basic_delete_filter); else @@ -138,7 +138,7 @@ static int basic_delete(struct tcf_proto *tp, void *arg, bool *last, list_del_rcu(&f->link); tcf_unbind_filter(tp, &f->res); - idr_remove_ext(&head->handle_idr, f->handle); + idr_remove(&head->handle_idr, f->handle); tcf_exts_get_net(&f->exts); call_rcu(&f->rcu, basic_delete_filter); *last = list_empty(&head->flist); @@ -185,7 +185,6 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, struct nlattr *tb[TCA_BASIC_MAX + 1]; struct basic_filter *fold = (struct basic_filter *) *arg; struct basic_filter *fnew; - unsigned long idr_index; if (tca[TCA_OPTIONS] == NULL) return -EINVAL; @@ -208,34 +207,30 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout; - if (handle) { - fnew->handle = handle; - if (!fold) { - err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, - handle, handle + 1, GFP_KERNEL); - if (err) - goto errout; - } - } else { - err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, - 1, 0x7FFFFFFF, GFP_KERNEL); - if (err) - goto errout; - fnew->handle = idr_index; + if (!handle) { + handle = 1; + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + INT_MAX, GFP_KERNEL); + } else if (!fold) { + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + handle, GFP_KERNEL); } + if (err) + goto errout; + fnew->handle = handle; err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr, extack); if (err < 0) { if (!fold) - idr_remove_ext(&head->handle_idr, fnew->handle); + idr_remove(&head->handle_idr, fnew->handle); goto errout; } *arg = fnew; if (fold) { - idr_replace_ext(&head->handle_idr, fnew, fnew->handle); + idr_replace(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->link, &fnew->link); tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 8e5326bc6440..b07c1fa8bc0d 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -295,7 +295,7 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog, { struct cls_bpf_head *head = rtnl_dereference(tp->root); - idr_remove_ext(&head->handle_idr, prog->handle); + idr_remove(&head->handle_idr, prog->handle); cls_bpf_stop_offload(tp, prog, extack); list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); @@ -471,7 +471,6 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; struct cls_bpf_prog *prog; - unsigned long idr_index; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -498,21 +497,18 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, } if (handle == 0) { - ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, - 1, 0x7FFFFFFF, GFP_KERNEL); - if (ret) - goto errout; - prog->handle = idr_index; - } else { - if (!oldprog) { - ret = idr_alloc_ext(&head->handle_idr, prog, &idr_index, - handle, handle + 1, GFP_KERNEL); - if (ret) - goto errout; - } - prog->handle = handle; + handle = 1; + ret = idr_alloc_u32(&head->handle_idr, prog, &handle, + INT_MAX, GFP_KERNEL); + } else if (!oldprog) { + ret = idr_alloc_u32(&head->handle_idr, prog, &handle, + handle, GFP_KERNEL); } + if (ret) + goto errout; + prog->handle = handle; + ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], ovr, extack); if (ret < 0) @@ -526,7 +522,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, prog->gen_flags |= TCA_CLS_FLAGS_NOT_IN_HW; if (oldprog) { - idr_replace_ext(&head->handle_idr, prog, handle); + idr_replace(&head->handle_idr, prog, handle); list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); tcf_exts_get_net(&oldprog->exts); @@ -542,7 +538,7 @@ errout_parms: cls_bpf_free_parms(prog); errout_idr: if (!oldprog) - idr_remove_ext(&head->handle_idr, prog->handle); + idr_remove(&head->handle_idr, prog->handle); errout: tcf_exts_destroy(&prog->exts); kfree(prog); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index dc9acaafc0a8..7d0ce2c40f93 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -288,7 +288,7 @@ static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, { struct cls_fl_head *head = rtnl_dereference(tp->root); - idr_remove_ext(&head->handle_idr, f->handle); + idr_remove(&head->handle_idr, f->handle); list_del_rcu(&f->list); if (!tc_skip_hw(f->flags)) fl_hw_destroy_filter(tp, f, extack); @@ -334,7 +334,7 @@ static void *fl_get(struct tcf_proto *tp, u32 handle) { struct cls_fl_head *head = rtnl_dereference(tp->root); - return idr_find_ext(&head->handle_idr, handle); + return idr_find(&head->handle_idr, handle); } static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { @@ -865,7 +865,6 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_filter *fnew; struct nlattr **tb; struct fl_flow_mask mask = {}; - unsigned long idr_index; int err; if (!tca[TCA_OPTIONS]) @@ -896,21 +895,17 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, goto errout; if (!handle) { - err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, - 1, 0x80000000, GFP_KERNEL); - if (err) - goto errout; - fnew->handle = idr_index; - } - - /* user specifies a handle and it doesn't exist */ - if (handle && !fold) { - err = idr_alloc_ext(&head->handle_idr, fnew, &idr_index, - handle, handle + 1, GFP_KERNEL); - if (err) - goto errout; - fnew->handle = idr_index; + handle = 1; + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + INT_MAX, GFP_KERNEL); + } else if (!fold) { + /* user specifies a handle and it doesn't exist */ + err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + handle, GFP_KERNEL); } + if (err) + goto errout; + fnew->handle = handle; if (tb[TCA_FLOWER_FLAGS]) { fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); @@ -966,8 +961,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, *arg = fnew; if (fold) { - fnew->handle = handle; - idr_replace_ext(&head->handle_idr, fnew, fnew->handle); + idr_replace(&head->handle_idr, fnew, fnew->handle); list_replace_rcu(&fold->list, &fnew->list); tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); @@ -981,7 +975,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, errout_idr: if (fnew->handle) - idr_remove_ext(&head->handle_idr, fnew->handle); + idr_remove(&head->handle_idr, fnew->handle); errout: tcf_exts_destroy(&fnew->exts); kfree(fnew); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index e3c5e390ec23..6c7601a530e3 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -316,19 +316,13 @@ static void *u32_get(struct tcf_proto *tp, u32 handle) return u32_lookup_key(ht, handle); } +/* Protected by rtnl lock */ static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) { - unsigned long idr_index; - int err; - - /* This is only used inside rtnl lock it is safe to increment - * without read _copy_ update semantics - */ - err = idr_alloc_ext(&tp_c->handle_idr, ptr, &idr_index, - 1, 0x7FF, GFP_KERNEL); - if (err) + int id = idr_alloc_cyclic(&tp_c->handle_idr, ptr, 1, 0x7FF, GFP_KERNEL); + if (id < 0) return 0; - return (u32)(idr_index | 0x800) << 20; + return (id | 0x800U) << 20; } static struct hlist_head *tc_u_common_hash; @@ -398,10 +392,12 @@ static int u32_init(struct tcf_proto *tp) static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, bool free_pf) { + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); + tcf_exts_destroy(&n->exts); tcf_exts_put_net(&n->exts); - if (n->ht_down) - n->ht_down->refcnt--; + if (ht && --ht->refcnt == 0) + kfree(ht); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -596,7 +592,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, rtnl_dereference(n->next)); tcf_unbind_filter(tp, &n->res); u32_remove_hw_knode(tp, n, extack); - idr_remove_ext(&ht->handle_idr, n->handle); + idr_remove(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) call_rcu(&n->rcu, u32_delete_key_freepf_rcu); else @@ -623,7 +619,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, if (phn == ht) { u32_clear_hw_hnode(tp, ht, extack); idr_destroy(&ht->handle_idr); - idr_remove_ext(&tp_c->handle_idr, ht->handle); + idr_remove(&tp_c->handle_idr, ht->handle); RCU_INIT_POINTER(*hn, ht->next); kfree_rcu(ht, rcu); return 0; @@ -659,16 +655,15 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) hlist_del(&tp_c->hnode); - for (ht = rtnl_dereference(tp_c->hlist); - ht; - ht = rtnl_dereference(ht->next)) { - ht->refcnt--; - u32_clear_hnode(tp, ht, extack); - } - while ((ht = rtnl_dereference(tp_c->hlist)) != NULL) { + u32_clear_hnode(tp, ht, extack); RCU_INIT_POINTER(tp_c->hlist, ht->next); - kfree_rcu(ht, rcu); + + /* u32_destroy_key() will later free ht for us, if it's + * still referenced by some knode + */ + if (--ht->refcnt == 0) + kfree_rcu(ht, rcu); } idr_destroy(&tp_c->handle_idr); @@ -746,19 +741,17 @@ ret: static u32 gen_new_kid(struct tc_u_hnode *ht, u32 htid) { - unsigned long idr_index; - u32 start = htid | 0x800; + u32 index = htid | 0x800; u32 max = htid | 0xFFF; - u32 min = htid; - if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, - start, max + 1, GFP_KERNEL)) { - if (idr_alloc_ext(&ht->handle_idr, NULL, &idr_index, - min + 1, max + 1, GFP_KERNEL)) - return max; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, GFP_KERNEL)) { + index = htid + 1; + if (idr_alloc_u32(&ht->handle_idr, NULL, &index, max, + GFP_KERNEL)) + index = max; } - return (u32)idr_index; + return index; } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -848,7 +841,7 @@ static void u32_replace_knode(struct tcf_proto *tp, struct tc_u_common *tp_c, if (pins->handle == n->handle) break; - idr_replace_ext(&ht->handle_idr, n, n->handle); + idr_replace(&ht->handle_idr, n, n->handle); RCU_INIT_POINTER(n->next, pins->next); rcu_assign_pointer(*ins, n); } @@ -954,7 +947,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } - if (n->flags != flags) { + if ((n->flags ^ flags) & + ~(TCA_CLS_FLAGS_IN_HW | TCA_CLS_FLAGS_NOT_IN_HW)) { NL_SET_ERR_MSG_MOD(extack, "Key node flags do not match passed flags"); return -EINVAL; } @@ -1009,8 +1003,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -ENOMEM; } } else { - err = idr_alloc_ext(&tp_c->handle_idr, ht, NULL, - handle, handle + 1, GFP_KERNEL); + err = idr_alloc_u32(&tp_c->handle_idr, ht, &handle, + handle, GFP_KERNEL); if (err) { kfree(ht); return err; @@ -1026,7 +1020,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, err = u32_replace_hw_hnode(tp, ht, flags, extack); if (err) { - idr_remove_ext(&tp_c->handle_idr, handle); + idr_remove(&tp_c->handle_idr, handle); kfree(ht); return err; } @@ -1066,8 +1060,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } handle = htid | TC_U32_NODE(handle); - err = idr_alloc_ext(&ht->handle_idr, NULL, NULL, - handle, handle + 1, + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, GFP_KERNEL); if (err) return err; @@ -1162,7 +1155,7 @@ errfree: #endif kfree(n); erridr: - idr_remove_ext(&ht->handle_idr, handle); + idr_remove(&ht->handle_idr, handle); return err; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 7bbc13b8ca47..7c179addebcd 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -327,7 +327,7 @@ static s64 tabledist(s64 mu, s32 sigma, /* default uniform distribution */ if (dist == NULL) - return (rnd % (2 * sigma)) - sigma + mu; + return ((rnd % (2 * sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 5d4c15bf66d2..e35d4f73d2df 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -326,8 +326,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); bdst = ip6_dst_lookup_flow(sk, fl6, final_p); - if (!IS_ERR(bdst) && - ipv6_chk_addr(dev_net(bdst->dev), + if (IS_ERR(bdst)) + continue; + + if (ipv6_chk_addr(dev_net(bdst->dev), &laddr->a.v6.sin6_addr, bdst->dev, 1)) { if (!IS_ERR_OR_NULL(dst)) dst_release(dst); @@ -336,8 +338,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a); - if (matchlen > bmatchlen) + if (matchlen > bmatchlen) { + dst_release(bdst); continue; + } if (!IS_ERR_OR_NULL(dst)) dst_release(dst); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 6a38c2503649..91813e686c67 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -514,22 +514,20 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (IS_ERR(rt)) continue; - if (!dst) - dst = &rt->dst; - /* Ensure the src address belongs to the output * interface. */ odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, false); if (!odev || odev->ifindex != fl4->flowi4_oif) { - if (&rt->dst != dst) + if (!dst) + dst = &rt->dst; + else dst_release(&rt->dst); continue; } - if (dst != &rt->dst) - dst_release(dst); + dst_release(dst); dst = &rt->dst; break; } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 793b05ec692b..d01475f5f710 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1380,9 +1380,14 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, struct sctp_chunk *retval; struct sk_buff *skb; struct sock *sk; + int chunklen; + + chunklen = SCTP_PAD4(sizeof(*chunk_hdr) + paylen); + if (chunklen > SCTP_MAX_CHUNK_LEN) + goto nodata; /* No need to allocate LL here, as this is only a chunk. */ - skb = alloc_skb(SCTP_PAD4(sizeof(*chunk_hdr) + paylen), gfp); + skb = alloc_skb(chunklen, gfp); if (!skb) goto nodata; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ebb8cb9eb0bd..bf271f8c2dc9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -7602,22 +7602,22 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING)) return (!list_empty(&sp->ep->asocs)) ? - (POLLIN | POLLRDNORM) : 0; + (EPOLLIN | EPOLLRDNORM) : 0; mask = 0; /* Is there any exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR | - (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + mask |= EPOLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; /* Is it readable? Reconsider this code with TCP-style support. */ if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* The association is either gone or not ready. */ if (!sctp_style(sk, UDP) && sctp_sstate(sk, CLOSED)) @@ -7625,7 +7625,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Is it writable? */ if (sctp_writeable(sk)) { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* @@ -7637,7 +7637,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) * in the following code to cover it as well. */ if (sctp_writeable(sk)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } @@ -8161,8 +8161,8 @@ void sctp_data_ready(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLIN | - POLLRDNORM | POLLRDBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | + EPOLLRDNORM | EPOLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 3583c8ab1bae..da1a5cdefd13 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1141,11 +1141,11 @@ out: static __poll_t smc_accept_poll(struct sock *parent) { struct smc_sock *isk = smc_sk(parent); - int mask = 0; + __poll_t mask = 0; spin_lock(&isk->accept_q_lock); if (!list_empty(&isk->accept_q)) - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; spin_unlock(&isk->accept_q_lock); return mask; @@ -1160,7 +1160,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, int rc; if (!sk) - return POLLNVAL; + return EPOLLNVAL; smc = smc_sk(sock->sk); sock_hold(sk); @@ -1171,16 +1171,16 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); /* if non-blocking connect finished ... */ lock_sock(sk); - if ((sk->sk_state == SMC_INIT) && (mask & POLLOUT)) { + if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) { sk->sk_err = smc->clcsock->sk->sk_err; if (sk->sk_err) { - mask |= POLLERR; + mask |= EPOLLERR; } else { rc = smc_connect_rdma(smc); if (rc < 0) - mask |= POLLERR; + mask |= EPOLLERR; /* success cases including fallback */ - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } } } else { @@ -1190,27 +1190,27 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, lock_sock(sk); } if (sk->sk_err) - mask |= POLLERR; + mask |= EPOLLERR; if ((sk->sk_shutdown == SHUTDOWN_MASK) || (sk->sk_state == SMC_CLOSED)) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_state == SMC_LISTEN) { /* woken up by sk_data_ready in smc_listen_work() */ mask = smc_accept_poll(sk); } else { if (atomic_read(&smc->conn.sndbuf_space) || sk->sk_shutdown & SEND_SHUTDOWN) { - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); } if (atomic_read(&smc->conn.bytes_to_rcv)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLIN | POLLRDNORM | POLLRDHUP; + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (sk->sk_state == SMC_APPCLOSEWAIT1) - mask |= POLLIN; + mask |= EPOLLIN; } } diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 9dc392ca06bf..eff4e0d0bb31 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -35,8 +35,8 @@ static void smc_rx_data_ready(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI | - POLLRDNORM | POLLRDBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | + EPOLLRDNORM | EPOLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); if ((sk->sk_shutdown == SHUTDOWN_MASK) || (sk->sk_state == SMC_CLOSED)) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 838bce20c361..72f004c9c9b1 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -46,8 +46,8 @@ static void smc_tx_write_space(struct sock *sk) wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, - POLLOUT | POLLWRNORM | - POLLWRBAND); + EPOLLOUT | EPOLLWRNORM | + EPOLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index aa36dad32db1..8a7e1c774f9c 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -940,7 +940,7 @@ static __poll_t cache_poll(struct file *filp, poll_table *wait, poll_wait(filp, &queue_wait, wait); /* alway allow write */ - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; if (!rp) return mask; @@ -950,7 +950,7 @@ static __poll_t cache_poll(struct file *filp, poll_table *wait, for (cq= &rp->q; &cq->list != &cd->queue; cq = list_entry(cq->list.next, struct cache_queue, list)) if (!cq->reader) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; break; } spin_unlock(&queue_lock); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 5c4330325787..fc97fc3ed637 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -345,15 +345,15 @@ rpc_pipe_poll(struct file *filp, struct poll_table_struct *wait) { struct inode *inode = file_inode(filp); struct rpc_inode *rpci = RPC_I(inode); - __poll_t mask = POLLOUT | POLLWRNORM; + __poll_t mask = EPOLLOUT | EPOLLWRNORM; poll_wait(filp, &rpci->waitq, wait); inode_lock(inode); if (rpci->pipe == NULL) - mask |= POLLERR | POLLHUP; + mask |= EPOLLERR | EPOLLHUP; else if (filp->private_data || !list_empty(&rpci->pipe->pipe)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; inode_unlock(inode); return mask; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 896691afbb1a..d9db2eab3a8d 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -461,6 +461,18 @@ static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct r /* * Wake up a task on a specific queue */ +void rpc_wake_up_queued_task_on_wq(struct workqueue_struct *wq, + struct rpc_wait_queue *queue, + struct rpc_task *task) +{ + spin_lock_bh(&queue->lock); + rpc_wake_up_task_on_wq_queue_locked(wq, queue, task); + spin_unlock_bh(&queue->lock); +} + +/* + * Wake up a task on a specific queue + */ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task) { spin_lock_bh(&queue->lock); @@ -1092,12 +1104,12 @@ static int rpciod_start(void) * Create the rpciod thread and wait for it to start. */ dprintk("RPC: creating workqueue rpciod\n"); - wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM, 0); + wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (!wq) goto out_failed; rpciod_workqueue = wq; /* Note: highpri because network receive is latency sensitive */ - wq = alloc_workqueue("xprtiod", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + wq = alloc_workqueue("xprtiod", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_HIGHPRI, 0); if (!wq) goto free_rpciod; xprtiod_workqueue = wq; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5570719e4787..943f2a745cd5 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -384,25 +384,11 @@ static int svc_partial_recvfrom(struct svc_rqst *rqstp, static void svc_sock_setbufsize(struct socket *sock, unsigned int snd, unsigned int rcv) { -#if 0 - mm_segment_t oldfs; - oldfs = get_fs(); set_fs(KERNEL_DS); - sock_setsockopt(sock, SOL_SOCKET, SO_SNDBUF, - (char*)&snd, sizeof(snd)); - sock_setsockopt(sock, SOL_SOCKET, SO_RCVBUF, - (char*)&rcv, sizeof(rcv)); -#else - /* sock_setsockopt limits use to sysctl_?mem_max, - * which isn't acceptable. Until that is made conditional - * on not having CAP_SYS_RESOURCE or similar, we go direct... - * DaveM said I could! - */ lock_sock(sock->sk); sock->sk->sk_sndbuf = snd * 2; sock->sk->sk_rcvbuf = rcv * 2; sock->sk->sk_write_space(sock->sk); release_sock(sock->sk); -#endif } static int svc_sock_secure_port(struct svc_rqst *rqstp) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 2436fd1125fc..8f0ad4f268da 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -517,7 +517,8 @@ void xprt_write_space(struct rpc_xprt *xprt) if (xprt->snd_task) { dprintk("RPC: write space: waking waiting task on " "xprt %p\n", xprt); - rpc_wake_up_queued_task(&xprt->pending, xprt->snd_task); + rpc_wake_up_queued_task_on_wq(xprtiod_workqueue, + &xprt->pending, xprt->snd_task); } spin_unlock_bh(&xprt->transport_lock); } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 162e5dd82466..f0855a959a27 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -143,7 +143,7 @@ static bool rpcrdma_args_inline(struct rpcrdma_xprt *r_xprt, if (xdr->page_len) { remaining = xdr->page_len; offset = offset_in_page(xdr->page_base); - count = 0; + count = RPCRDMA_MIN_SEND_SGES; while (remaining) { remaining -= min_t(unsigned int, PAGE_SIZE - offset, remaining); diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index af7893501e40..a73632ca9048 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -95,7 +95,6 @@ out_shortreply: out_notfound: dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n", xprt, be32_to_cpu(xid)); - goto out_unlock; } @@ -129,10 +128,6 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma, if (ret < 0) goto out_err; - ret = svc_rdma_repost_recv(rdma, GFP_NOIO); - if (ret) - goto out_err; - /* Bump page refcnt so Send completion doesn't release * the rq_buffer before all retransmits are complete. */ diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index ad4bd62eebf1..19e9c6b33042 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -400,10 +400,6 @@ static void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct page *page; int ret; - ret = svc_rdma_repost_recv(xprt, GFP_KERNEL); - if (ret) - return; - page = alloc_page(GFP_KERNEL); if (!page) return; @@ -554,8 +550,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p, &rqstp->rq_arg); svc_rdma_put_context(ctxt, 0); - if (ret) - goto repost; return ret; } @@ -590,6 +584,5 @@ out_postfail: out_drop: svc_rdma_put_context(ctxt, 1); -repost: - return svc_rdma_repost_recv(rdma_xprt, GFP_KERNEL); + return 0; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 9bd04549a1ad..12b9a7e0b6d2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -727,12 +727,16 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp, head->arg.head[0].iov_len - info->ri_position; head->arg.head[0].iov_len = info->ri_position; - /* Read chunk may need XDR roundup (see RFC 5666, s. 3.7). + /* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2). * - * NFSv2/3 write decoders need the length of the tail to - * contain the size of the roundup padding. + * If the client already rounded up the chunk length, the + * length does not change. Otherwise, the length of the page + * list is increased to include XDR round-up. + * + * Currently these chunks always start at page offset 0, + * thus the rounded-up length never crosses a page boundary. */ - head->arg.tail[0].iov_len += 4 - (info->ri_chunklen & 3); + info->ri_chunklen = XDR_QUADLEN(info->ri_chunklen) << 2; head->arg.page_len = info->ri_chunklen; head->arg.len += info->ri_chunklen; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 7c3a211e0e9a..649441d5087d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -674,9 +674,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) svc_rdma_xdr_encode_reply_chunk(rdma_resp, rp_ch, ret); } - ret = svc_rdma_post_recv(rdma, GFP_KERNEL); - if (ret) - goto err1; ret = svc_rdma_send_reply_msg(rdma, rdma_argp, rdma_resp, rqstp, wr_lst, rp_ch); if (ret < 0) @@ -687,9 +684,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) if (ret != -E2BIG && ret != -EINVAL) goto err1; - ret = svc_rdma_post_recv(rdma, GFP_KERNEL); - if (ret) - goto err1; ret = svc_rdma_send_error_msg(rdma, rdma_resp, rqstp); if (ret < 0) goto err0; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 46ec069150d5..9ad12a215b51 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -58,6 +58,7 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +static int svc_rdma_post_recv(struct svcxprt_rdma *xprt); static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *, int); static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, struct net *net, @@ -320,6 +321,8 @@ static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) list_add_tail(&ctxt->list, &xprt->sc_rq_dto_q); spin_unlock(&xprt->sc_rq_dto_lock); + svc_rdma_post_recv(xprt); + set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); if (test_bit(RDMAXPRT_CONN_PENDING, &xprt->sc_flags)) goto out; @@ -404,7 +407,8 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, return cma_xprt; } -int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags) +static int +svc_rdma_post_recv(struct svcxprt_rdma *xprt) { struct ib_recv_wr recv_wr, *bad_recv_wr; struct svc_rdma_op_ctxt *ctxt; @@ -423,7 +427,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags) pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err_put_ctxt; } - page = alloc_page(flags); + page = alloc_page(GFP_KERNEL); if (!page) goto err_put_ctxt; ctxt->pages[sge_no] = page; @@ -459,21 +463,6 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags) return -ENOMEM; } -int svc_rdma_repost_recv(struct svcxprt_rdma *xprt, gfp_t flags) -{ - int ret = 0; - - ret = svc_rdma_post_recv(xprt, flags); - if (ret) { - pr_err("svcrdma: could not post a receive buffer, err=%d.\n", - ret); - pr_err("svcrdma: closing transport %p.\n", xprt); - set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); - ret = -ENOTCONN; - } - return ret; -} - static void svc_rdma_parse_connect_private(struct svcxprt_rdma *newxprt, struct rdma_conn_param *param) @@ -833,7 +822,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Post receive buffers */ for (i = 0; i < newxprt->sc_max_requests; i++) { - ret = svc_rdma_post_recv(newxprt, GFP_KERNEL); + ret = svc_rdma_post_recv(newxprt); if (ret) { dprintk("svcrdma: failure posting receive buffers\n"); goto errout; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index f4eb63e8e689..e6f84a6434a0 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -505,7 +505,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, pr_warn("rpcrdma: HCA provides only %d send SGEs\n", max_sge); return -ENOMEM; } - ia->ri_max_send_sges = max_sge - RPCRDMA_MIN_SEND_SGES; + ia->ri_max_send_sges = max_sge; if (ia->ri_device->attrs.max_qp_wr <= RPCRDMA_BACKWARD_WRS) { dprintk("RPC: %s: insufficient wqe's available\n", @@ -1502,6 +1502,9 @@ __rpcrdma_dma_map_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) static void rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb) { + if (!rb) + return; + if (!rpcrdma_regbuf_is_mapped(rb)) return; @@ -1517,9 +1520,6 @@ rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb) void rpcrdma_free_regbuf(struct rpcrdma_regbuf *rb) { - if (!rb) - return; - rpcrdma_dma_unmap_regbuf(rb); kfree(rb); } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 18803021f242..a6b8c1f8f92a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -807,13 +807,6 @@ static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt) smp_mb__after_atomic(); } -static void xs_sock_mark_closed(struct rpc_xprt *xprt) -{ - xs_sock_reset_connection_flags(xprt); - /* Mark transport as closed and wake up all pending tasks */ - xprt_disconnect_done(xprt); -} - /** * xs_error_report - callback to handle TCP socket state errors * @sk: socket @@ -833,9 +826,6 @@ static void xs_error_report(struct sock *sk) err = -sk->sk_err; if (err == 0) goto out; - /* Is this a reset event? */ - if (sk->sk_state == TCP_CLOSE) - xs_sock_mark_closed(xprt); dprintk("RPC: xs_error_report client %p, error=%d...\n", xprt, -err); trace_rpc_socket_error(xprt, sk->sk_socket, err); @@ -1078,18 +1068,18 @@ static void xs_udp_data_read_skb(struct rpc_xprt *xprt, /* Suck it into the iovec, verify checksum if not done by hw. */ if (csum_partial_copy_to_xdr(&rovr->rq_private_buf, skb)) { - __UDPX_INC_STATS(sk, UDP_MIB_INERRORS); spin_lock(&xprt->recv_lock); + __UDPX_INC_STATS(sk, UDP_MIB_INERRORS); goto out_unpin; } - __UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS); spin_lock_bh(&xprt->transport_lock); xprt_adjust_cwnd(xprt, task, copied); spin_unlock_bh(&xprt->transport_lock); spin_lock(&xprt->recv_lock); xprt_complete_rqst(task, copied); + __UDPX_INC_STATS(sk, UDP_MIB_INDATAGRAMS); out_unpin: xprt_unpin_rqst(rovr); out_unlock: @@ -1655,9 +1645,11 @@ static void xs_tcp_state_change(struct sock *sk) if (test_and_clear_bit(XPRT_SOCK_CONNECTING, &transport->sock_state)) xprt_clear_connecting(xprt); + clear_bit(XPRT_CLOSING, &xprt->state); if (sk->sk_err) xprt_wake_pending_tasks(xprt, -sk->sk_err); - xs_sock_mark_closed(xprt); + /* Trigger the socket release */ + xs_tcp_force_close(xprt); } out: read_unlock_bh(&sk->sk_callback_lock); @@ -2265,14 +2257,19 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct socket *sock = transport->sock; + int skst = transport->inet ? transport->inet->sk_state : TCP_CLOSE; if (sock == NULL) return; - if (xprt_connected(xprt)) { + switch (skst) { + default: kernel_sock_shutdown(sock, SHUT_RDWR); trace_rpc_socket_shutdown(xprt, sock); - } else + break; + case TCP_CLOSE: + case TCP_TIME_WAIT: xs_reset_transport(transport); + } } static void xs_tcp_set_socket_timeouts(struct rpc_xprt *xprt, diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 55d8ba92291d..4e1c6f6450bb 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -208,8 +208,8 @@ bool tipc_msg_validate(struct sk_buff **_skb) int msz, hsz; /* Ensure that flow control ratio condition is satisfied */ - if (unlikely(skb->truesize / buf_roundup_len(skb) > 4)) { - skb = skb_copy(skb, GFP_ATOMIC); + if (unlikely(skb->truesize / buf_roundup_len(skb) >= 4)) { + skb = skb_copy_expand(skb, BUF_HEADROOM, 0, GFP_ATOMIC); if (!skb) return false; kfree_skb(*_skb); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 163f3a547501..b0323ec7971e 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -721,31 +721,31 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_shutdown & RCV_SHUTDOWN) - revents |= POLLRDHUP | POLLIN | POLLRDNORM; + revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - revents |= POLLHUP; + revents |= EPOLLHUP; switch (sk->sk_state) { case TIPC_ESTABLISHED: case TIPC_CONNECTING: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) - revents |= POLLOUT; + revents |= EPOLLOUT; /* fall thru' */ case TIPC_LISTEN: if (!skb_queue_empty(&sk->sk_receive_queue)) - revents |= POLLIN | POLLRDNORM; + revents |= EPOLLIN | EPOLLRDNORM; break; case TIPC_OPEN: if (tsk->group_is_open && !tsk->cong_link_cnt) - revents |= POLLOUT; + revents |= EPOLLOUT; if (!tipc_sk_type_connectionless(sk)) break; if (skb_queue_empty(&sk->sk_receive_queue)) break; - revents |= POLLIN | POLLRDNORM; + revents |= EPOLLIN | EPOLLRDNORM; break; case TIPC_DISCONNECTING: - revents = POLLIN | POLLRDNORM | POLLHUP; + revents = EPOLLIN | EPOLLRDNORM | EPOLLHUP; break; } return revents; @@ -1897,8 +1897,8 @@ static void tipc_write_space(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | - POLLWRNORM | POLLWRBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); rcu_read_unlock(); } @@ -1914,8 +1914,8 @@ static void tipc_data_ready(struct sock *sk) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLIN | - POLLRDNORM | POLLRDBAND); + wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | + EPOLLRDNORM | EPOLLRDBAND); rcu_read_unlock(); } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 736719c8314e..b0d5fcea47e7 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -484,6 +484,8 @@ out: static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .name = "tls", + .uid = TCP_ULP_TLS, + .user_visible = true, .owner = THIS_MODULE, .init = tls_init, }; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0214acbd6bff..d545e1d0dea2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -415,9 +415,9 @@ static void unix_dgram_peer_wake_disconnect_wakeup(struct sock *sk, { unix_dgram_peer_wake_disconnect(sk, other); wake_up_interruptible_poll(sk_sleep(sk), - POLLOUT | - POLLWRNORM | - POLLWRBAND); + EPOLLOUT | + EPOLLWRNORM | + EPOLLWRBAND); } /* preconditions: @@ -454,7 +454,7 @@ static void unix_write_space(struct sock *sk) wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, - POLLOUT | POLLWRNORM | POLLWRBAND); + EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); @@ -2129,8 +2129,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, if (wq_has_sleeper(&u->peer_wait)) wake_up_interruptible_sync_poll(&u->peer_wait, - POLLOUT | POLLWRNORM | - POLLWRBAND); + EPOLLOUT | EPOLLWRNORM | + EPOLLWRBAND); if (msg->msg_name) unix_copy_addr(msg, skb->sk); @@ -2650,27 +2650,27 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa /* exceptional events? */ if (sk->sk_err) - mask |= POLLERR; + mask |= EPOLLERR; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && sk->sk_state == TCP_CLOSE) - mask |= POLLHUP; + mask |= EPOLLHUP; /* * we set writable also when the other side has shut down the * connection. This prevents stuck sockets. */ if (unix_writable(sk)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; return mask; } @@ -2687,29 +2687,29 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, /* exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR | - (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + mask |= EPOLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP | POLLIN | POLLRDNORM; + mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) - mask |= POLLHUP; + mask |= EPOLLHUP; /* readable? */ if (!skb_queue_empty(&sk->sk_receive_queue)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ if (sk->sk_type == SOCK_SEQPACKET) { if (sk->sk_state == TCP_CLOSE) - mask |= POLLHUP; + mask |= EPOLLHUP; /* connection hasn't started yet? */ if (sk->sk_state == TCP_SYN_SENT) return mask; } /* No write status requested, avoid expensive OUT tests. */ - if (!(poll_requested_events(wait) & (POLLWRBAND|POLLWRNORM|POLLOUT))) + if (!(poll_requested_events(wait) & (EPOLLWRBAND|EPOLLWRNORM|EPOLLOUT))) return mask; writable = unix_writable(sk); @@ -2726,7 +2726,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, } if (writable) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9d95e773f4c8..e0fc84daed94 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -865,20 +865,20 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, if (sk->sk_err) /* Signify that there has been an error on this socket. */ - mask |= POLLERR; + mask |= EPOLLERR; /* INET sockets treat local write shutdown and peer write shutdown as a - * case of POLLHUP set. + * case of EPOLLHUP set. */ if ((sk->sk_shutdown == SHUTDOWN_MASK) || ((sk->sk_shutdown & SEND_SHUTDOWN) && (vsk->peer_shutdown & SEND_SHUTDOWN))) { - mask |= POLLHUP; + mask |= EPOLLHUP; } if (sk->sk_shutdown & RCV_SHUTDOWN || vsk->peer_shutdown & SEND_SHUTDOWN) { - mask |= POLLRDHUP; + mask |= EPOLLRDHUP; } if (sock->type == SOCK_DGRAM) { @@ -888,11 +888,11 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, */ if (!skb_queue_empty(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } if (!(sk->sk_shutdown & SEND_SHUTDOWN)) - mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } else if (sock->type == SOCK_STREAM) { lock_sock(sk); @@ -902,7 +902,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, */ if (sk->sk_state == TCP_LISTEN && !vsock_is_accept_queue_empty(sk)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; /* If there is something in the queue then we can read. */ if (transport->stream_is_active(vsk) && @@ -911,10 +911,10 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, int ret = transport->notify_poll_in( vsk, 1, &data_ready_now); if (ret < 0) { - mask |= POLLERR; + mask |= EPOLLERR; } else { if (data_ready_now) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } } @@ -925,7 +925,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, */ if (sk->sk_shutdown & RCV_SHUTDOWN || vsk->peer_shutdown & SEND_SHUTDOWN) { - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } /* Connected sockets that can produce data can be written. */ @@ -935,25 +935,25 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, int ret = transport->notify_poll_out( vsk, 1, &space_avail_now); if (ret < 0) { - mask |= POLLERR; + mask |= EPOLLERR; } else { if (space_avail_now) - /* Remove POLLWRBAND since INET + /* Remove EPOLLWRBAND since INET * sockets are not setting it. */ - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } } } /* Simulate INET socket poll behaviors, which sets - * POLLOUT|POLLWRNORM when peer is closed and nothing to read, + * EPOLLOUT|EPOLLWRNORM when peer is closed and nothing to read, * but local send is not shutdown. */ if (sk->sk_state == TCP_CLOSE || sk->sk_state == TCP_CLOSING) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 64335bb94f9f..ec3fc8d88e87 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -45,7 +45,7 @@ hostprogs-y += xdp_rxq_info hostprogs-y += syscall_tp # Libbpf dependencies -LIBBPF := ../../tools/lib/bpf/bpf.o +LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o test_lru_dist-objs := test_lru_dist.o $(LIBBPF) diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 242631aa4ea2..69806d74fa53 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -695,105 +695,3 @@ struct ksym *ksym_search(long key) return &syms[0]; } -int set_link_xdp_fd(int ifindex, int fd, __u32 flags) -{ - struct sockaddr_nl sa; - int sock, seq = 0, len, ret = -1; - char buf[4096]; - struct nlattr *nla, *nla_xdp; - struct { - struct nlmsghdr nh; - struct ifinfomsg ifinfo; - char attrbuf[64]; - } req; - struct nlmsghdr *nh; - struct nlmsgerr *err; - - memset(&sa, 0, sizeof(sa)); - sa.nl_family = AF_NETLINK; - - sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); - if (sock < 0) { - printf("open netlink socket: %s\n", strerror(errno)); - return -1; - } - - if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { - printf("bind to netlink: %s\n", strerror(errno)); - goto cleanup; - } - - memset(&req, 0, sizeof(req)); - req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); - req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; - req.nh.nlmsg_type = RTM_SETLINK; - req.nh.nlmsg_pid = 0; - req.nh.nlmsg_seq = ++seq; - req.ifinfo.ifi_family = AF_UNSPEC; - req.ifinfo.ifi_index = ifindex; - - /* started nested attribute for XDP */ - nla = (struct nlattr *)(((char *)&req) - + NLMSG_ALIGN(req.nh.nlmsg_len)); - nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/; - nla->nla_len = NLA_HDRLEN; - - /* add XDP fd */ - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = 1/*IFLA_XDP_FD*/; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); - memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); - nla->nla_len += nla_xdp->nla_len; - - /* if user passed in any flags, add those too */ - if (flags) { - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); - memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); - nla->nla_len += nla_xdp->nla_len; - } - - req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); - - if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { - printf("send to netlink: %s\n", strerror(errno)); - goto cleanup; - } - - len = recv(sock, buf, sizeof(buf), 0); - if (len < 0) { - printf("recv from netlink: %s\n", strerror(errno)); - goto cleanup; - } - - for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); - nh = NLMSG_NEXT(nh, len)) { - if (nh->nlmsg_pid != getpid()) { - printf("Wrong pid %d, expected %d\n", - nh->nlmsg_pid, getpid()); - goto cleanup; - } - if (nh->nlmsg_seq != seq) { - printf("Wrong seq %d, expected %d\n", - nh->nlmsg_seq, seq); - goto cleanup; - } - switch (nh->nlmsg_type) { - case NLMSG_ERROR: - err = (struct nlmsgerr *)NLMSG_DATA(nh); - if (!err->error) - continue; - printf("nlmsg error %s\n", strerror(-err->error)); - goto cleanup; - case NLMSG_DONE: - break; - } - } - - ret = 0; - -cleanup: - close(sock); - return ret; -} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index 7d57a4248893..453c200b389b 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -61,5 +61,5 @@ struct ksym { int load_kallsyms(void); struct ksym *ksym_search(long key); -int set_link_xdp_fd(int ifindex, int fd, __u32 flags); +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); #endif diff --git a/samples/bpf/tcbpf2_kern.c b/samples/bpf/tcbpf2_kern.c index f6bbf8f50da3..efdc16d195ff 100644 --- a/samples/bpf/tcbpf2_kern.c +++ b/samples/bpf/tcbpf2_kern.c @@ -15,6 +15,7 @@ #include <uapi/linux/tcp.h> #include <uapi/linux/filter.h> #include <uapi/linux/pkt_cls.h> +#include <uapi/linux/erspan.h> #include <net/ipv6.h> #include "bpf_helpers.h" #include "bpf_endian.h" @@ -35,24 +36,10 @@ struct geneve_opt { u8 opt_data[8]; /* hard-coded to 8 byte */ }; -struct erspan_md2 { - __be32 timestamp; - __be16 sgt; - __be16 flags; -}; - struct vxlan_metadata { u32 gbp; }; -struct erspan_metadata { - union { - __be32 index; - struct erspan_md2 md2; - } u; - int version; -}; - SEC("gre_set_tunnel") int _gre_set_tunnel(struct __sk_buff *skb) { @@ -156,13 +143,15 @@ int _erspan_set_tunnel(struct __sk_buff *skb) __builtin_memset(&md, 0, sizeof(md)); #ifdef ERSPAN_V1 md.version = 1; - md.u.index = htonl(123); + md.u.index = bpf_htonl(123); #else u8 direction = 1; - u16 hwid = 7; + u8 hwid = 7; md.version = 2; - md.u.md2.flags = htons((direction << 3) | (hwid << 4)); + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; #endif ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); @@ -207,9 +196,9 @@ int _erspan_get_tunnel(struct __sk_buff *skb) char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; bpf_trace_printk(fmt2, sizeof(fmt2), - (ntohs(md.u.md2.flags) >> 3) & 0x1, - (ntohs(md.u.md2.flags) >> 4) & 0x3f, - bpf_ntohl(md.u.md2.timestamp)); + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); #endif return TC_ACT_OK; @@ -242,10 +231,12 @@ int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb) md.version = 1; #else u8 direction = 0; - u16 hwid = 17; + u8 hwid = 17; md.version = 2; - md.u.md2.flags = htons((direction << 3) | (hwid << 4)); + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; #endif ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); @@ -290,9 +281,9 @@ int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb) char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; bpf_trace_printk(fmt2, sizeof(fmt2), - (ntohs(md.u.md2.flags) >> 3) & 0x1, - (ntohs(md.u.md2.flags) >> 4) & 0x3f, - bpf_ntohl(md.u.md2.timestamp)); + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); #endif return TC_ACT_OK; diff --git a/samples/bpf/test_tunnel_bpf.sh b/samples/bpf/test_tunnel_bpf.sh index ae7f7c38309b..43ce049996ee 100755 --- a/samples/bpf/test_tunnel_bpf.sh +++ b/samples/bpf/test_tunnel_bpf.sh @@ -68,7 +68,7 @@ function add_erspan_tunnel { ip netns exec at_ns0 \ ip link add dev $DEV_NS type $TYPE seq key 2 \ local 172.16.1.100 remote 172.16.1.200 \ - erspan_ver 2 erspan_dir 1 erspan_hwid 3 + erspan_ver 2 erspan_dir egress erspan_hwid 3 fi ip netns exec at_ns0 ip link set dev $DEV_NS up ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 @@ -97,7 +97,7 @@ function add_ip6erspan_tunnel { ip netns exec at_ns0 \ ip link add dev $DEV_NS type $TYPE seq key 2 \ local ::11 remote ::22 \ - erspan_ver 2 erspan_dir 1 erspan_hwid 7 + erspan_ver 2 erspan_dir egress erspan_hwid 7 fi ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 ip netns exec at_ns0 ip link set dev $DEV_NS up diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index fdaefe91801d..b901ee2b3336 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -25,7 +25,7 @@ static __u32 xdp_flags; static void int_exit(int sig) { - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(0); } @@ -116,7 +116,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { printf("link set xdp fd failed\n"); return 1; } diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 35fec9fecb57..23744a8aaf21 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -26,7 +26,7 @@ static const char *__doc__ = /* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead * use bpf/libbpf.h), but cannot as (currently) needed for XDP - * attaching to a device via set_link_xdp_fd() + * attaching to a device via bpf_set_link_xdp_fd() */ #include "libbpf.h" #include "bpf_load.h" @@ -67,7 +67,7 @@ static void int_exit(int sig) "Interrupted: Removing XDP program on ifindex:%d device:%s\n", ifindex, ifname); if (ifindex > -1) - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(EXIT_OK); } @@ -682,7 +682,7 @@ int main(int argc, char **argv) /* Remove XDP program when program is interrupted */ signal(SIGINT, int_exit); - if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { fprintf(stderr, "link set xdp fd failed\n"); return EXIT_FAIL_XDP; } diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 978a532f0748..7eae07d7293e 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -34,9 +34,9 @@ static __u32 xdp_flags; static void int_exit(int sig) { - set_link_xdp_fd(ifindex_in, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); if (ifindex_out_xdp_dummy_attached) - set_link_xdp_fd(ifindex_out, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); exit(0); } @@ -120,13 +120,13 @@ int main(int argc, char **argv) return 1; } - if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); return 1; } /* Loading dummy XDP prog on out-device */ - if (set_link_xdp_fd(ifindex_out, prog_fd[1], + if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1], (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { printf("WARN: link set xdp fd failed on %d\n", ifindex_out); ifindex_out_xdp_dummy_attached = false; diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 4475d837bf2c..d54e91eb6cbf 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -33,9 +33,9 @@ static __u32 xdp_flags; static void int_exit(int sig) { - set_link_xdp_fd(ifindex_in, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); if (ifindex_out_xdp_dummy_attached) - set_link_xdp_fd(ifindex_out, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); exit(0); } @@ -114,13 +114,13 @@ int main(int argc, char **argv) return 1; } - if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); return 1; } /* Loading dummy XDP prog on out-device */ - if (set_link_xdp_fd(ifindex_out, prog_fd[1], + if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1], (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { printf("WARN: link set xdp fd failed on %d\n", ifindex_out); ifindex_out_xdp_dummy_attached = false; diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index 916462112d55..6296741c1fbd 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -37,7 +37,7 @@ static void int_exit(int sig) int i = 0; for (i = 0; i < total_ifindex; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); exit(0); } @@ -49,7 +49,7 @@ static void close_and_exit(int sig) close(sock_arp); for (i = 0; i < total_ifindex; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); exit(0); } @@ -183,7 +183,7 @@ static void read_route(struct nlmsghdr *nh, int nll) int i = 0; for (i = 0; i < total_ifindex; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); exit(0); } assert(bpf_map_update_elem(map_fd[4], &route.iface, &route.iface, 0) == 0); @@ -633,12 +633,12 @@ int main(int ac, char **argv) } } for (i = 0; i < total_ifindex; i++) { - if (set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) { printf("link set xdp fd failed\n"); int recovery_index = i; for (i = 0; i < recovery_index; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); return 1; } diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 32430e8b3a6a..478d95412de4 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -56,7 +56,7 @@ static void int_exit(int sig) "Interrupted: Removing XDP program on ifindex:%d device:%s\n", ifindex, ifname); if (ifindex > -1) - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(EXIT_OK); } @@ -521,7 +521,7 @@ int main(int argc, char **argv) /* Remove XDP program when program is interrupted */ signal(SIGINT, int_exit); - if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { fprintf(stderr, "link set xdp fd failed\n"); return EXIT_FAIL_XDP; } diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index 715cd12eaca5..f0a787268a87 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -30,7 +30,7 @@ static __u32 xdp_flags = 0; static void int_exit(int sig) { if (ifindex > -1) - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(0); } @@ -254,14 +254,14 @@ int main(int argc, char **argv) } } - if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { printf("link set xdp fd failed\n"); return 1; } poll_stats(kill_after_s); - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); return 0; } diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 1ce7115aa499..69552a39951d 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -10,10 +10,7 @@ KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET) CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address -CFLAGS_KASAN := $(call cc-option, -fsanitize=kernel-address \ - -fasan-shadow-offset=$(KASAN_SHADOW_OFFSET) \ - --param asan-stack=1 --param asan-globals=1 \ - --param asan-instrumentation-with-call-threshold=$(call_threshold)) +cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1))) ifeq ($(call cc-option, $(CFLAGS_KASAN_MINIMAL) -Werror),) ifneq ($(CONFIG_COMPILE_TEST),y) @@ -21,14 +18,30 @@ ifeq ($(call cc-option, $(CFLAGS_KASAN_MINIMAL) -Werror),) -fsanitize=kernel-address is not supported by compiler) endif else - ifeq ($(CFLAGS_KASAN),) - ifneq ($(CONFIG_COMPILE_TEST),y) - $(warning CONFIG_KASAN: compiler does not support all options.\ - Trying minimal configuration) - endif - CFLAGS_KASAN := $(CFLAGS_KASAN_MINIMAL) - endif + # -fasan-shadow-offset fails without -fsanitize + CFLAGS_KASAN_SHADOW := $(call cc-option, -fsanitize=kernel-address \ + -fasan-shadow-offset=$(KASAN_SHADOW_OFFSET), \ + $(call cc-option, -fsanitize=kernel-address \ + -mllvm -asan-mapping-offset=$(KASAN_SHADOW_OFFSET))) + + ifeq ($(strip $(CFLAGS_KASAN_SHADOW)),) + CFLAGS_KASAN := $(CFLAGS_KASAN_MINIMAL) + else + # Now add all the compiler specific options that are valid standalone + CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \ + $(call cc-param,asan-globals=1) \ + $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \ + $(call cc-param,asan-stack=1) \ + $(call cc-param,asan-use-after-scope=1) \ + $(call cc-param,asan-instrument-allocas=1) + endif + endif +ifdef CONFIG_KASAN_EXTRA CFLAGS_KASAN += $(call cc-option, -fsanitize-address-use-after-scope) endif + +CFLAGS_KASAN_NOSANITIZE := -fno-builtin + +endif diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 5fdc1a19b02c..5589bae34af6 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -121,7 +121,7 @@ endif ifeq ($(CONFIG_KASAN),y) _c_flags += $(if $(patsubst n%,, \ $(KASAN_SANITIZE_$(basetarget).o)$(KASAN_SANITIZE)y), \ - $(CFLAGS_KASAN)) + $(CFLAGS_KASAN), $(CFLAGS_KASAN_NOSANITIZE)) endif ifeq ($(CONFIG_UBSAN),y) diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan index 8fd4d44fbcd1..b593b36ccff8 100644 --- a/scripts/Makefile.ubsan +++ b/scripts/Makefile.ubsan @@ -7,7 +7,6 @@ ifdef CONFIG_UBSAN CFLAGS_UBSAN += $(call cc-option, -fsanitize=signed-integer-overflow) CFLAGS_UBSAN += $(call cc-option, -fsanitize=bounds) CFLAGS_UBSAN += $(call cc-option, -fsanitize=object-size) - CFLAGS_UBSAN += $(call cc-option, -fsanitize=returns-nonnull-attribute) CFLAGS_UBSAN += $(call cc-option, -fsanitize=bool) CFLAGS_UBSAN += $(call cc-option, -fsanitize=enum) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index e954df2b2077..3d4040322ae1 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -566,6 +566,7 @@ foreach my $entry (@mode_permission_funcs) { $mode_perms_search .= '|' if ($mode_perms_search ne ""); $mode_perms_search .= $entry->[0]; } +$mode_perms_search = "(?:${mode_perms_search})"; our $mode_perms_world_writable = qr{ S_IWUGO | @@ -600,6 +601,37 @@ foreach my $entry (keys %mode_permission_string_types) { $mode_perms_string_search .= '|' if ($mode_perms_string_search ne ""); $mode_perms_string_search .= $entry; } +our $single_mode_perms_string_search = "(?:${mode_perms_string_search})"; +our $multi_mode_perms_string_search = qr{ + ${single_mode_perms_string_search} + (?:\s*\|\s*${single_mode_perms_string_search})* +}x; + +sub perms_to_octal { + my ($string) = @_; + + return trim($string) if ($string =~ /^\s*0[0-7]{3,3}\s*$/); + + my $val = ""; + my $oval = ""; + my $to = 0; + my $curpos = 0; + my $lastpos = 0; + while ($string =~ /\b(($single_mode_perms_string_search)\b(?:\s*\|\s*)?\s*)/g) { + $curpos = pos($string); + my $match = $2; + my $omatch = $1; + last if ($lastpos > 0 && ($curpos - length($omatch) != $lastpos)); + $lastpos = $curpos; + $to |= $mode_permission_string_types{$match}; + $val .= '\s*\|\s*' if ($val ne ""); + $val .= $match; + $oval .= $omatch; + } + $oval =~ s/^\s*\|\s*//; + $oval =~ s/\s*\|\s*$//; + return sprintf("%04o", $to); +} our $allowed_asm_includes = qr{(?x: irq| @@ -2875,6 +2907,7 @@ sub process { # logging functions like pr_info that end in a string # lines with a single string # #defines that are a single string +# lines with an RFC3986 like URL # # There are 3 different line length message types: # LONG_LINE_COMMENT a comment starts before but extends beyond $max_line_length @@ -2906,6 +2939,10 @@ sub process { $line =~ /^\+\s*(?:\w+)?\s*DEFINE_PER_CPU/) { $msg_type = ""; + # URL ($rawline is used in case the URL is in a comment) + } elsif ($rawline =~ /^\+.*\b[a-z][\w\.\+\-]*:\/\/\S+/i) { + $msg_type = ""; + # Otherwise set the alternate message types # a comment starts before $max_line_length @@ -2983,7 +3020,7 @@ sub process { # check indentation starts on a tab stop if ($^V && $^V ge 5.10.0 && - $sline =~ /^\+\t+( +)(?:$c90_Keywords\b|\{\s*$|\}\s*(?:else\b|while\b|\s*$))/) { + $sline =~ /^\+\t+( +)(?:$c90_Keywords\b|\{\s*$|\}\s*(?:else\b|while\b|\s*$)|$Declare\s*$Ident\s*[;=])/) { my $indent = length($1); if ($indent % 8) { if (WARN("TABSTOP", @@ -3882,10 +3919,12 @@ sub process { # function brace can't be on same line, except for #defines of do while, # or if closed on same line - if (($line=~/$Type\s*$Ident\(.*\).*\s*{/) and - !($line=~/\#\s*define.*do\s\{/) and !($line=~/}/)) { + if ($^V && $^V ge 5.10.0 && + $sline =~ /$Type\s*$Ident\s*$balanced_parens\s*\{/ && + $sline !~ /\#\s*define\b.*do\s*\{/ && + $sline !~ /}/) { if (ERROR("OPEN_BRACE", - "open brace '{' following function declarations go on the next line\n" . $herecurr) && + "open brace '{' following function definitions go on the next line\n" . $herecurr) && $fix) { fix_delete_line($fixlinenr, $rawline); my $fixed_line = $rawline; @@ -4489,7 +4528,9 @@ sub process { } # check for unnecessary parentheses around comparisons in if uses - if ($^V && $^V ge 5.10.0 && defined($stat) && +# when !drivers/staging or command-line uses --strict + if (($realfile !~ m@^(?:drivers/staging/)@ || $check_orig) && + $^V && $^V ge 5.10.0 && defined($stat) && $stat =~ /(^.\s*if\s*($balanced_parens))/) { my $if_stat = $1; my $test = substr($2, 1, -1); @@ -5307,7 +5348,7 @@ sub process { } # check for line continuations in quoted strings with odd counts of " - if ($rawline =~ /\\$/ && $rawline =~ tr/"/"/ % 2) { + if ($rawline =~ /\\$/ && $sline =~ tr/"/"/ % 2) { WARN("LINE_CONTINUATIONS", "Avoid line continuations in quoted strings\n" . $herecurr); } @@ -6269,8 +6310,69 @@ sub process { "Exporting world writable files is usually an error. Consider more restrictive permissions.\n" . $herecurr); } +# check for DEVICE_ATTR uses that could be DEVICE_ATTR_<FOO> +# and whether or not function naming is typical and if +# DEVICE_ATTR permissions uses are unusual too + if ($^V && $^V ge 5.10.0 && + defined $stat && + $stat =~ /\bDEVICE_ATTR\s*\(\s*(\w+)\s*,\s*\(?\s*(\s*(?:${multi_mode_perms_string_search}|0[0-7]{3,3})\s*)\s*\)?\s*,\s*(\w+)\s*,\s*(\w+)\s*\)/) { + my $var = $1; + my $perms = $2; + my $show = $3; + my $store = $4; + my $octal_perms = perms_to_octal($perms); + if ($show =~ /^${var}_show$/ && + $store =~ /^${var}_store$/ && + $octal_perms eq "0644") { + if (WARN("DEVICE_ATTR_RW", + "Use DEVICE_ATTR_RW\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bDEVICE_ATTR\s*\(\s*$var\s*,\s*\Q$perms\E\s*,\s*$show\s*,\s*$store\s*\)/DEVICE_ATTR_RW(${var})/; + } + } elsif ($show =~ /^${var}_show$/ && + $store =~ /^NULL$/ && + $octal_perms eq "0444") { + if (WARN("DEVICE_ATTR_RO", + "Use DEVICE_ATTR_RO\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bDEVICE_ATTR\s*\(\s*$var\s*,\s*\Q$perms\E\s*,\s*$show\s*,\s*NULL\s*\)/DEVICE_ATTR_RO(${var})/; + } + } elsif ($show =~ /^NULL$/ && + $store =~ /^${var}_store$/ && + $octal_perms eq "0200") { + if (WARN("DEVICE_ATTR_WO", + "Use DEVICE_ATTR_WO\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/\bDEVICE_ATTR\s*\(\s*$var\s*,\s*\Q$perms\E\s*,\s*NULL\s*,\s*$store\s*\)/DEVICE_ATTR_WO(${var})/; + } + } elsif ($octal_perms eq "0644" || + $octal_perms eq "0444" || + $octal_perms eq "0200") { + my $newshow = "$show"; + $newshow = "${var}_show" if ($show ne "NULL" && $show ne "${var}_show"); + my $newstore = $store; + $newstore = "${var}_store" if ($store ne "NULL" && $store ne "${var}_store"); + my $rename = ""; + if ($show ne $newshow) { + $rename .= " '$show' to '$newshow'"; + } + if ($store ne $newstore) { + $rename .= " '$store' to '$newstore'"; + } + WARN("DEVICE_ATTR_FUNCTIONS", + "Consider renaming function(s)$rename\n" . $herecurr); + } else { + WARN("DEVICE_ATTR_PERMS", + "DEVICE_ATTR unusual permissions '$perms' used\n" . $herecurr); + } + } + # Mode permission misuses where it seems decimal should be octal # This uses a shortcut match to avoid unnecessary uses of a slow foreach loop +# o Ignore module_param*(...) uses with a decimal 0 permission as that has a +# specific definition of not visible in sysfs. +# o Ignore proc_create*(...) uses with a decimal 0 permission as that means +# use the default permissions if ($^V && $^V ge 5.10.0 && defined $stat && $line =~ /$mode_perms_search/) { @@ -6294,8 +6396,9 @@ sub process { if ($stat =~ /$test/) { my $val = $1; $val = $6 if ($skip_args ne ""); - if (($val =~ /^$Int$/ && $val !~ /^$Octal$/) || - ($val =~ /^$Octal$/ && length($val) ne 4)) { + if (!($func =~ /^(?:module_param|proc_create)/ && $val eq "0") && + (($val =~ /^$Int$/ && $val !~ /^$Octal$/) || + ($val =~ /^$Octal$/ && length($val) ne 4))) { ERROR("NON_OCTAL_PERMISSIONS", "Use 4 digit octal (0777) not decimal permissions\n" . "$here\n" . $stat_real); } @@ -6308,30 +6411,13 @@ sub process { } # check for uses of S_<PERMS> that could be octal for readability - if ($line =~ /\b$mode_perms_string_search\b/) { - my $val = ""; - my $oval = ""; - my $to = 0; - my $curpos = 0; - my $lastpos = 0; - while ($line =~ /\b(($mode_perms_string_search)\b(?:\s*\|\s*)?\s*)/g) { - $curpos = pos($line); - my $match = $2; - my $omatch = $1; - last if ($lastpos > 0 && ($curpos - length($omatch) != $lastpos)); - $lastpos = $curpos; - $to |= $mode_permission_string_types{$match}; - $val .= '\s*\|\s*' if ($val ne ""); - $val .= $match; - $oval .= $omatch; - } - $oval =~ s/^\s*\|\s*//; - $oval =~ s/\s*\|\s*$//; - my $octal = sprintf("%04o", $to); + if ($line =~ /\b($multi_mode_perms_string_search)\b/) { + my $oval = $1; + my $octal = perms_to_octal($oval); if (WARN("SYMBOLIC_PERMS", "Symbolic permissions '$oval' are not preferred. Consider using octal permissions '$octal'.\n" . $herecurr) && $fix) { - $fixed[$fixlinenr] =~ s/$val/$octal/; + $fixed[$fixlinenr] =~ s/\Q$oval\E/$octal/; } } diff --git a/scripts/coccinelle/free/devm_free.cocci b/scripts/coccinelle/free/devm_free.cocci index c990d2c7ee16..b2a2cf8bf81f 100644 --- a/scripts/coccinelle/free/devm_free.cocci +++ b/scripts/coccinelle/free/devm_free.cocci @@ -56,9 +56,62 @@ expression x; x = devm_ioport_map(...) ) +@safe depends on context || org || report exists@ +expression x; +position p; +@@ + +( + x = kmalloc(...) +| + x = kvasprintf(...) +| + x = kasprintf(...) +| + x = kzalloc(...) +| + x = kmalloc_array(...) +| + x = kcalloc(...) +| + x = kstrdup(...) +| + x = kmemdup(...) +| + x = get_free_pages(...) +| + x = request_irq(...) +| + x = ioremap(...) +| + x = ioremap_nocache(...) +| + x = ioport_map(...) +) +... +( + kfree@p(x) +| + kzfree@p(x) +| + __krealloc@p(x, ...) +| + krealloc@p(x, ...) +| + free_pages@p(x, ...) +| + free_page@p(x) +| + free_irq@p(x) +| + iounmap@p(x) +| + ioport_unmap@p(x) +) + @pb@ expression r.x; -position p; +position p != safe.p; @@ ( diff --git a/scripts/coccinelle/null/deref_null.cocci b/scripts/coccinelle/null/deref_null.cocci index f192d6035d02..b16ccb7663a7 100644 --- a/scripts/coccinelle/null/deref_null.cocci +++ b/scripts/coccinelle/null/deref_null.cocci @@ -212,7 +212,7 @@ else S3 // The following three rules are duplicates of ifm, pr1 and pr2 respectively. // It is need because the previous rule as already made a "change". -@ifm1@ +@ifm1 depends on context && !org && !report@ expression *E; statement S1,S2; position p1; @@ -220,7 +220,7 @@ position p1; if@p1 ((E == NULL && ...) || ...) S1 else S2 -@pr11 expression@ +@pr11 depends on context && !org && !report expression@ expression *ifm1.E; identifier f; position p1; @@ -228,7 +228,7 @@ position p1; (E != NULL && ...) ? <+...E->f@p1...+> : ... -@pr12 expression@ +@pr12 depends on context && !org && !report expression@ expression *ifm1.E; identifier f; position p2; diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index ffd1dfaa1cc1..f46750053377 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -97,6 +97,10 @@ #include "predict.h" #include "ipa-utils.h" +#if BUILDING_GCC_VERSION >= 8000 +#include "stringpool.h" +#endif + #if BUILDING_GCC_VERSION >= 4009 #include "attribs.h" #include "varasm.h" diff --git a/scripts/gcc-plugins/latent_entropy_plugin.c b/scripts/gcc-plugins/latent_entropy_plugin.c index 65264960910d..cbe1d6c4b1a5 100644 --- a/scripts/gcc-plugins/latent_entropy_plugin.c +++ b/scripts/gcc-plugins/latent_entropy_plugin.c @@ -255,21 +255,14 @@ static tree handle_latent_entropy_attribute(tree *node, tree name, return NULL_TREE; } -static struct attribute_spec latent_entropy_attr = { - .name = "latent_entropy", - .min_length = 0, - .max_length = 0, - .decl_required = true, - .type_required = false, - .function_type_required = false, - .handler = handle_latent_entropy_attribute, -#if BUILDING_GCC_VERSION >= 4007 - .affects_type_identity = false -#endif -}; +static struct attribute_spec latent_entropy_attr = { }; static void register_attributes(void *event_data __unused, void *data __unused) { + latent_entropy_attr.name = "latent_entropy"; + latent_entropy_attr.decl_required = true; + latent_entropy_attr.handler = handle_latent_entropy_attribute; + register_attribute(&latent_entropy_attr); } diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c index 0073af326449..c4a345c3715b 100644 --- a/scripts/gcc-plugins/randomize_layout_plugin.c +++ b/scripts/gcc-plugins/randomize_layout_plugin.c @@ -580,68 +580,35 @@ static void finish_type(void *event_data, void *data) return; } -static struct attribute_spec randomize_layout_attr = { - .name = "randomize_layout", - // related to args - .min_length = 0, - .max_length = 0, - .decl_required = false, - // need type declaration - .type_required = true, - .function_type_required = false, - .handler = handle_randomize_layout_attr, -#if BUILDING_GCC_VERSION >= 4007 - .affects_type_identity = true -#endif -}; +static struct attribute_spec randomize_layout_attr = { }; +static struct attribute_spec no_randomize_layout_attr = { }; +static struct attribute_spec randomize_considered_attr = { }; +static struct attribute_spec randomize_performed_attr = { }; -static struct attribute_spec no_randomize_layout_attr = { - .name = "no_randomize_layout", - // related to args - .min_length = 0, - .max_length = 0, - .decl_required = false, - // need type declaration - .type_required = true, - .function_type_required = false, - .handler = handle_randomize_layout_attr, +static void register_attributes(void *event_data, void *data) +{ + randomize_layout_attr.name = "randomize_layout"; + randomize_layout_attr.type_required = true; + randomize_layout_attr.handler = handle_randomize_layout_attr; #if BUILDING_GCC_VERSION >= 4007 - .affects_type_identity = true + randomize_layout_attr.affects_type_identity = true; #endif -}; -static struct attribute_spec randomize_considered_attr = { - .name = "randomize_considered", - // related to args - .min_length = 0, - .max_length = 0, - .decl_required = false, - // need type declaration - .type_required = true, - .function_type_required = false, - .handler = handle_randomize_considered_attr, + no_randomize_layout_attr.name = "no_randomize_layout"; + no_randomize_layout_attr.type_required = true; + no_randomize_layout_attr.handler = handle_randomize_layout_attr; #if BUILDING_GCC_VERSION >= 4007 - .affects_type_identity = false + no_randomize_layout_attr.affects_type_identity = true; #endif -}; -static struct attribute_spec randomize_performed_attr = { - .name = "randomize_performed", - // related to args - .min_length = 0, - .max_length = 0, - .decl_required = false, - // need type declaration - .type_required = true, - .function_type_required = false, - .handler = handle_randomize_performed_attr, -#if BUILDING_GCC_VERSION >= 4007 - .affects_type_identity = false -#endif -}; + randomize_considered_attr.name = "randomize_considered"; + randomize_considered_attr.type_required = true; + randomize_considered_attr.handler = handle_randomize_considered_attr; + + randomize_performed_attr.name = "randomize_performed"; + randomize_performed_attr.type_required = true; + randomize_performed_attr.handler = handle_randomize_performed_attr; -static void register_attributes(void *event_data, void *data) -{ register_attribute(&randomize_layout_attr); register_attribute(&no_randomize_layout_attr); register_attribute(&randomize_considered_attr); diff --git a/scripts/gcc-plugins/structleak_plugin.c b/scripts/gcc-plugins/structleak_plugin.c index 3f8dd4868178..10292f791e99 100644 --- a/scripts/gcc-plugins/structleak_plugin.c +++ b/scripts/gcc-plugins/structleak_plugin.c @@ -57,21 +57,16 @@ static tree handle_user_attribute(tree *node, tree name, tree args, int flags, b return NULL_TREE; } -static struct attribute_spec user_attr = { - .name = "user", - .min_length = 0, - .max_length = 0, - .decl_required = false, - .type_required = false, - .function_type_required = false, - .handler = handle_user_attribute, -#if BUILDING_GCC_VERSION >= 4007 - .affects_type_identity = true -#endif -}; +static struct attribute_spec user_attr = { }; static void register_attributes(void *event_data, void *data) { + user_attr.name = "user"; + user_attr.handler = handle_user_attribute; +#if BUILDING_GCC_VERSION >= 4007 + user_attr.affects_type_identity = true; +#endif + register_attribute(&user_attr); } diff --git a/scripts/kconfig/.gitignore b/scripts/kconfig/.gitignore index 51f1c877b543..a76856e559c0 100644 --- a/scripts/kconfig/.gitignore +++ b/scripts/kconfig/.gitignore @@ -1,7 +1,6 @@ # # Generated files # -config* *.lex.c *.tab.c *.tab.h diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c index 307bc3f7b945..822dc51923d6 100644 --- a/scripts/kconfig/conf.c +++ b/scripts/kconfig/conf.c @@ -39,7 +39,6 @@ static enum input_mode input_mode = oldaskconfig; static int indent = 1; static int tty_stdio; -static int valid_stdin = 1; static int sync_kconfig; static int conf_cnt; static char line[PATH_MAX]; @@ -72,21 +71,14 @@ static void strip(char *str) *p-- = 0; } -static void check_stdin(void) -{ - if (!valid_stdin) { - printf(_("aborted!\n\n")); - printf(_("Console input/output is redirected. ")); - printf(_("Run 'make oldconfig' to update configuration.\n\n")); - exit(1); - } -} - /* Helper function to facilitate fgets() by Jean Sacren. */ static void xfgets(char *str, int size, FILE *in) { if (!fgets(str, size, in)) fprintf(stderr, "\nError in reading or end of file.\n"); + + if (!tty_stdio) + printf("%s", str); } static int conf_askvalue(struct symbol *sym, const char *def) @@ -113,13 +105,10 @@ static int conf_askvalue(struct symbol *sym, const char *def) printf("%s\n", def); return 0; } - check_stdin(); /* fall through */ case oldaskconfig: fflush(stdout); xfgets(line, sizeof(line), stdin); - if (!tty_stdio) - printf("\n"); return 1; default: break; @@ -199,9 +188,7 @@ static int conf_sym(struct menu *menu) printf("/m"); if (oldval != yes && sym_tristate_within_range(sym, yes)) printf("/y"); - if (menu_has_help(menu)) - printf("/?"); - printf("] "); + printf("/?] "); if (!conf_askvalue(sym, sym_get_string_value(sym))) return 0; strip(line); @@ -303,10 +290,7 @@ static int conf_choice(struct menu *menu) printf("[1]: 1\n"); goto conf_childs; } - printf("[1-%d", cnt); - if (menu_has_help(menu)) - printf("?"); - printf("]: "); + printf("[1-%d?]: ", cnt); switch (input_mode) { case oldconfig: case silentoldconfig: @@ -315,7 +299,6 @@ static int conf_choice(struct menu *menu) printf("%d\n", cnt); break; } - check_stdin(); /* fall through */ case oldaskconfig: fflush(stdout); @@ -508,7 +491,7 @@ int main(int ac, char **av) bindtextdomain(PACKAGE, LOCALEDIR); textdomain(PACKAGE); - tty_stdio = isatty(0) && isatty(1) && isatty(2); + tty_stdio = isatty(0) && isatty(1); while ((opt = getopt_long(ac, av, "s", long_opts, NULL)) != -1) { if (opt == 's') { @@ -565,7 +548,7 @@ int main(int ac, char **av) } } if (ac == optind) { - printf(_("%s: Kconfig file missing\n"), av[0]); + fprintf(stderr, _("%s: Kconfig file missing\n"), av[0]); conf_usage(progname); exit(1); } @@ -590,9 +573,11 @@ int main(int ac, char **av) if (!defconfig_file) defconfig_file = conf_get_default_confname(); if (conf_read(defconfig_file)) { - printf(_("***\n" - "*** Can't find default configuration \"%s\"!\n" - "***\n"), defconfig_file); + fprintf(stderr, + _("***\n" + "*** Can't find default configuration \"%s\"!\n" + "***\n"), + defconfig_file); exit(1); } break; @@ -650,7 +635,6 @@ int main(int ac, char **av) return 1; } } - valid_stdin = tty_stdio; } switch (input_mode) { diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index f7927391de30..5c12dc91ef34 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -201,7 +201,7 @@ static int add_byte(int c, char **lineptr, size_t slen, size_t *n) if (new_size > *n) { new_size += LINE_GROWTH - 1; new_size *= 2; - nline = realloc(*lineptr, new_size); + nline = xrealloc(*lineptr, new_size); if (!nline) return -1; diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index 2ba332b3fed7..d45381986ac7 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -94,7 +94,7 @@ struct expr *expr_copy(const struct expr *org) e->right.expr = expr_copy(org->right.expr); break; default: - printf("can't copy type %d\n", e->type); + fprintf(stderr, "can't copy type %d\n", e->type); free(e); e = NULL; break; @@ -127,7 +127,7 @@ void expr_free(struct expr *e) expr_free(e->right.expr); break; default: - printf("how to free type %d?\n", e->type); + fprintf(stderr, "how to free type %d?\n", e->type); break; } free(e); diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index 16cb62b92650..4e23febbe4b2 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -114,6 +114,7 @@ struct file *file_lookup(const char *name); int file_write_dep(const char *name); void *xmalloc(size_t size); void *xcalloc(size_t nmemb, size_t size); +void *xrealloc(void *p, size_t size); struct gstr { size_t len; diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h index 5d86e2dfae59..9dc8abfb1dc3 100644 --- a/scripts/kconfig/lkc_proto.h +++ b/scripts/kconfig/lkc_proto.h @@ -31,7 +31,7 @@ extern struct symbol * symbol_hash[SYMBOL_HASHSIZE]; struct symbol * sym_lookup(const char *name, int flags); struct symbol * sym_find(const char *name); -const char * sym_expand_string_value(const char *in); +char *sym_expand_string_value(const char *in); const char * sym_escape_string_value(const char *in); struct symbol ** sym_re_search(const char *pattern); const char * sym_type_name(enum symbol_type type); diff --git a/scripts/kconfig/nconf.gui.c b/scripts/kconfig/nconf.gui.c index a64b1c31253e..88874acfda36 100644 --- a/scripts/kconfig/nconf.gui.c +++ b/scripts/kconfig/nconf.gui.c @@ -6,6 +6,7 @@ * */ #include "nconf.h" +#include "lkc.h" /* a list of all the different widgets we use */ attributes_t attributes[ATTR_MAX+1] = {0}; @@ -374,7 +375,7 @@ int dialog_inputbox(WINDOW *main_window, if (strlen(init)+1 > *result_len) { *result_len = strlen(init)+1; - *resultp = result = realloc(result, *result_len); + *resultp = result = xrealloc(result, *result_len); } /* find the widest line of msg: */ diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index c9123ed2b791..cca9663be5dd 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -371,11 +371,13 @@ void sym_calc_value(struct symbol *sym) sym->curr.tri = no; return; } - if (!sym_is_choice_value(sym)) - sym->flags &= ~SYMBOL_WRITE; + sym->flags &= ~SYMBOL_WRITE; sym_calc_visibility(sym); + if (sym->visible != no) + sym->flags |= SYMBOL_WRITE; + /* set default if recursively called */ sym->curr = newval; @@ -390,7 +392,6 @@ void sym_calc_value(struct symbol *sym) /* if the symbol is visible use the user value * if available, otherwise try the default value */ - sym->flags |= SYMBOL_WRITE; if (sym_has_value(sym)) { newval.tri = EXPR_AND(sym->def[S_DEF_USER].tri, sym->visible); @@ -433,12 +434,9 @@ void sym_calc_value(struct symbol *sym) case S_STRING: case S_HEX: case S_INT: - if (sym->visible != no) { - sym->flags |= SYMBOL_WRITE; - if (sym_has_value(sym)) { - newval.val = sym->def[S_DEF_USER].val; - break; - } + if (sym->visible != no && sym_has_value(sym)) { + newval.val = sym->def[S_DEF_USER].val; + break; } prop = sym_get_default_prop(sym); if (prop) { @@ -901,7 +899,7 @@ struct symbol *sym_find(const char *name) * name to be expanded shall be prefixed by a '$'. Unknown symbol expands to * the empty string. */ -const char *sym_expand_string_value(const char *in) +char *sym_expand_string_value(const char *in) { const char *src; char *res; @@ -938,7 +936,7 @@ const char *sym_expand_string_value(const char *in) newlen = strlen(res) + strlen(symval) + strlen(src) + 1; if (newlen > reslen) { reslen = newlen; - res = realloc(res, reslen); + res = xrealloc(res, reslen); } strcat(res, symval); @@ -1223,7 +1221,7 @@ static struct symbol *sym_check_expr_deps(struct expr *e) default: break; } - printf("Oops! How to check %d?\n", e->type); + fprintf(stderr, "Oops! How to check %d?\n", e->type); return NULL; } diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c index 0e76042473cc..b98a79e30e04 100644 --- a/scripts/kconfig/util.c +++ b/scripts/kconfig/util.c @@ -14,11 +14,11 @@ struct file *file_lookup(const char *name) { struct file *file; - const char *file_name = sym_expand_string_value(name); + char *file_name = sym_expand_string_value(name); for (file = file_list; file; file = file->next) { if (!strcmp(name, file->name)) { - free((void *)file_name); + free(file_name); return file; } } @@ -104,7 +104,7 @@ void str_append(struct gstr *gs, const char *s) if (s) { l = strlen(gs->s) + strlen(s) + 1; if (l > gs->len) { - gs->s = realloc(gs->s, l); + gs->s = xrealloc(gs->s, l); gs->len = l; } strcat(gs->s, s); @@ -145,3 +145,12 @@ void *xcalloc(size_t nmemb, size_t size) fprintf(stderr, "Out of memory.\n"); exit(1); } + +void *xrealloc(void *p, size_t size) +{ + p = realloc(p, size); + if (p) + return p; + fprintf(stderr, "Out of memory.\n"); + exit(1); +} diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l index 07e074dc68a1..02de6fe302a9 100644 --- a/scripts/kconfig/zconf.l +++ b/scripts/kconfig/zconf.l @@ -52,7 +52,7 @@ static void append_string(const char *str, int size) if (new_size > text_asize) { new_size += START_STRSIZE - 1; new_size &= -START_STRSIZE; - text = realloc(text, new_size); + text = xrealloc(text, new_size); text_asize = new_size; } memcpy(text + text_size, str, size); @@ -184,7 +184,9 @@ n [A-Za-z0-9_-] append_string(yytext, 1); } \n { - printf("%s:%d:warning: multi-line strings not supported\n", zconf_curname(), zconf_lineno()); + fprintf(stderr, + "%s:%d:warning: multi-line strings not supported\n", + zconf_curname(), zconf_lineno()); current_file->lineno++; BEGIN(INITIAL); return T_EOL; @@ -294,7 +296,7 @@ void zconf_initscan(const char *name) { yyin = zconf_fopen(name); if (!yyin) { - printf("can't find file %s\n", name); + fprintf(stderr, "can't find file %s\n", name); exit(1); } @@ -315,8 +317,8 @@ void zconf_nextfile(const char *name) current_buf->state = YY_CURRENT_BUFFER; yyin = zconf_fopen(file->name); if (!yyin) { - printf("%s:%d: can't open file \"%s\"\n", - zconf_curname(), zconf_lineno(), file->name); + fprintf(stderr, "%s:%d: can't open file \"%s\"\n", + zconf_curname(), zconf_lineno(), file->name); exit(1); } yy_switch_to_buffer(yy_create_buffer(yyin, YY_BUF_SIZE)); @@ -325,20 +327,21 @@ void zconf_nextfile(const char *name) for (iter = current_file->parent; iter; iter = iter->parent ) { if (!strcmp(current_file->name,iter->name) ) { - printf("%s:%d: recursive inclusion detected. " - "Inclusion path:\n current file : '%s'\n", - zconf_curname(), zconf_lineno(), - zconf_curname()); + fprintf(stderr, + "%s:%d: recursive inclusion detected. " + "Inclusion path:\n current file : '%s'\n", + zconf_curname(), zconf_lineno(), + zconf_curname()); iter = current_file->parent; while (iter && \ strcmp(iter->name,current_file->name)) { - printf(" included from: '%s:%d'\n", - iter->name, iter->lineno-1); + fprintf(stderr, " included from: '%s:%d'\n", + iter->name, iter->lineno-1); iter = iter->parent; } if (iter) - printf(" included from: '%s:%d'\n", - iter->name, iter->lineno+1); + fprintf(stderr, " included from: '%s:%d'\n", + iter->name, iter->lineno+1); exit(1); } } diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y index 21ce883e5d9e..4be98050b961 100644 --- a/scripts/kconfig/zconf.y +++ b/scripts/kconfig/zconf.y @@ -436,6 +436,12 @@ help: help_start T_HELPTEXT zconfprint("warning: '%s' defined with more than one help text -- only the last one will be used", current_entry->sym->name ?: "<choice>"); } + + /* Is the help text empty or all whitespace? */ + if ($2[strspn($2, " \f\n\r\t\v")] == '\0') + zconfprint("warning: '%s' defined with blank help text", + current_entry->sym->name ?: "<choice>"); + current_entry->help = $2; }; diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 6510536c06df..9917f928d0fd 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1685,7 +1685,7 @@ static void extable_mismatch_handler(const char* modname, struct elf_info *elf, static void check_section_mismatch(const char *modname, struct elf_info *elf, Elf_Rela *r, Elf_Sym *sym, const char *fromsec) { - const char *tosec = sec_name(elf, get_secindex(elf, sym));; + const char *tosec = sec_name(elf, get_secindex(elf, sym)); const struct sectioncheck *mismatch = section_mismatch(fromsec, tosec); if (mismatch) { diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 4d202b73a0e1..a9428daa69f3 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -580,7 +580,7 @@ static __poll_t ns_revision_poll(struct file *file, poll_table *pt) mutex_lock_nested(&rev->ns->lock, rev->ns->level); poll_wait(file, &rev->ns->wait, pt); if (rev->last_read < rev->ns->revision) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; mutex_unlock(&rev->ns->lock); } diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 061425dd6400..2cfb0c714967 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -135,7 +135,7 @@ static void ima_check_last_writer(struct integrity_iint_cache *iint, update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if (!IS_I_VERSION(inode) || - inode_cmp_iversion(inode, iint->version) || + !inode_eq_iversion(inode, iint->version) || (iint->flags & IMA_NEW_FILE)) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; diff --git a/security/tomoyo/audit.c b/security/tomoyo/audit.c index 558e3076d38c..479b03a7a17e 100644 --- a/security/tomoyo/audit.c +++ b/security/tomoyo/audit.c @@ -456,14 +456,14 @@ void tomoyo_read_log(struct tomoyo_io_buffer *head) * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * - * Returns POLLIN | POLLRDNORM when ready to read an audit log. + * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log. */ __poll_t tomoyo_poll_log(struct file *file, poll_table *wait) { if (tomoyo_log_count) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_log_wait, wait); if (tomoyo_log_count) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 70c73bf66c88..03923a138ef5 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2116,17 +2116,17 @@ static struct tomoyo_domain_info *tomoyo_find_domain_by_qid * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". * - * Returns POLLIN | POLLRDNORM when ready to read, 0 otherwise. + * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise. * * Waits for access requests which violated policy in enforcing mode. */ static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait) { if (!list_empty(&tomoyo_query_list)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_query_wait, wait); if (!list_empty(&tomoyo_query_list)) - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; return 0; } @@ -2450,15 +2450,15 @@ int tomoyo_open_control(const u8 type, struct file *file) * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * - * Returns POLLIN | POLLRDNORM | POLLOUT | POLLWRNORM if ready to read/write, - * POLLOUT | POLLWRNORM otherwise. + * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write, + * EPOLLOUT | EPOLLWRNORM otherwise. */ __poll_t tomoyo_poll_control(struct file *file, poll_table *wait) { struct tomoyo_io_buffer *head = file->private_data; if (head->poll) - return head->poll(file, wait) | POLLOUT | POLLWRNORM; - return POLLIN | POLLRDNORM | POLLOUT | POLLWRNORM; + return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM; + return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM; } /** diff --git a/security/tomoyo/securityfs_if.c b/security/tomoyo/securityfs_if.c index fb9bf99deb35..1d3d7e7a1f05 100644 --- a/security/tomoyo/securityfs_if.c +++ b/security/tomoyo/securityfs_if.c @@ -154,8 +154,8 @@ static int tomoyo_release(struct inode *inode, struct file *file) * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * - * Returns POLLIN | POLLRDNORM | POLLOUT | POLLWRNORM if ready to read/write, - * POLLOUT | POLLWRNORM otherwise. + * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write, + * EPOLLOUT | EPOLLWRNORM otherwise. */ static __poll_t tomoyo_poll(struct file *file, poll_table *wait) { diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 8298e094f4f7..ffda91a4a1aa 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -250,15 +250,10 @@ int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, } else { struct task_struct *tracer; - rcu_read_lock(); - tracer = find_task_by_vpid(arg2); - if (tracer) - get_task_struct(tracer); - else + tracer = find_get_task_by_vpid(arg2); + if (!tracer) { rc = -EINVAL; - rcu_read_unlock(); - - if (tracer) { + } else { rc = yama_ptracer_add(tracer, myself); put_task_struct(tracer); } diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index a12b9555e910..4563432badba 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -399,9 +399,9 @@ static int snd_compr_mmap(struct file *f, struct vm_area_struct *vma) static __poll_t snd_compr_get_poll(struct snd_compr_stream *stream) { if (stream->direction == SND_COMPRESS_PLAYBACK) - return POLLOUT | POLLWRNORM; + return EPOLLOUT | EPOLLWRNORM; else - return POLLIN | POLLRDNORM; + return EPOLLIN | EPOLLRDNORM; } static __poll_t snd_compr_poll(struct file *f, poll_table *wait) @@ -412,7 +412,7 @@ static __poll_t snd_compr_poll(struct file *f, poll_table *wait) __poll_t retval = 0; if (snd_BUG_ON(!data)) - return POLLERR; + return EPOLLERR; stream = &data->stream; @@ -421,7 +421,7 @@ static __poll_t snd_compr_poll(struct file *f, poll_table *wait) switch (stream->runtime->state) { case SNDRV_PCM_STATE_OPEN: case SNDRV_PCM_STATE_XRUN: - retval = snd_compr_get_poll(stream) | POLLERR; + retval = snd_compr_get_poll(stream) | EPOLLERR; goto out; default: break; @@ -447,7 +447,7 @@ static __poll_t snd_compr_poll(struct file *f, poll_table *wait) retval = snd_compr_get_poll(stream); break; default: - retval = snd_compr_get_poll(stream) | POLLERR; + retval = snd_compr_get_poll(stream) | EPOLLERR; break; } out: diff --git a/sound/core/control.c b/sound/core/control.c index 50fa16022f1f..0b3026d937b1 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1679,7 +1679,7 @@ static __poll_t snd_ctl_poll(struct file *file, poll_table * wait) mask = 0; if (!list_empty(&ctl->events)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; return mask; } diff --git a/sound/core/info.c b/sound/core/info.c index aa86f3f8e056..4b36767af9e1 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -214,9 +214,9 @@ static __poll_t snd_info_entry_poll(struct file *file, poll_table *wait) data->file_private_data, file, wait); if (entry->c.ops->read) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (entry->c.ops->write) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/sound/core/init.c b/sound/core/init.c index 8753440c3a6e..4fa5dd955740 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -346,7 +346,7 @@ static int snd_disconnect_release(struct inode *inode, struct file *file) static __poll_t snd_disconnect_poll(struct file * file, poll_table * wait) { - return POLLERR | POLLNVAL; + return EPOLLERR | EPOLLNVAL; } static long snd_disconnect_ioctl(struct file *file, diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 3ebba9c7f86e..b044c0a5a674 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -2705,7 +2705,7 @@ static __poll_t snd_pcm_oss_poll(struct file *file, poll_table * wait) if (runtime->status->state != SNDRV_PCM_STATE_DRAINING && (runtime->status->state != SNDRV_PCM_STATE_RUNNING || snd_pcm_oss_playback_ready(psubstream))) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; snd_pcm_stream_unlock_irq(psubstream); } if (csubstream != NULL) { @@ -2715,7 +2715,7 @@ static __poll_t snd_pcm_oss_poll(struct file *file, poll_table * wait) snd_pcm_stream_lock_irq(csubstream); if ((ostate = runtime->status->state) != SNDRV_PCM_STATE_RUNNING || snd_pcm_oss_capture_ready(csubstream)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; snd_pcm_stream_unlock_irq(csubstream); if (ostate != SNDRV_PCM_STATE_RUNNING && runtime->oss.trigger) { struct snd_pcm_oss_file ofile; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 51104df924e1..77ba50ddcf9e 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3147,7 +3147,7 @@ static __poll_t snd_pcm_playback_poll(struct file *file, poll_table * wait) substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) - return POLLOUT | POLLWRNORM | POLLERR; + return EPOLLOUT | EPOLLWRNORM | EPOLLERR; runtime = substream->runtime; poll_wait(file, &runtime->sleep, wait); @@ -3159,7 +3159,7 @@ static __poll_t snd_pcm_playback_poll(struct file *file, poll_table * wait) case SNDRV_PCM_STATE_PREPARED: case SNDRV_PCM_STATE_PAUSED: if (avail >= runtime->control->avail_min) { - mask = POLLOUT | POLLWRNORM; + mask = EPOLLOUT | EPOLLWRNORM; break; } /* Fall through */ @@ -3167,7 +3167,7 @@ static __poll_t snd_pcm_playback_poll(struct file *file, poll_table * wait) mask = 0; break; default: - mask = POLLOUT | POLLWRNORM | POLLERR; + mask = EPOLLOUT | EPOLLWRNORM | EPOLLERR; break; } snd_pcm_stream_unlock_irq(substream); @@ -3186,7 +3186,7 @@ static __poll_t snd_pcm_capture_poll(struct file *file, poll_table * wait) substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) - return POLLIN | POLLRDNORM | POLLERR; + return EPOLLIN | EPOLLRDNORM | EPOLLERR; runtime = substream->runtime; poll_wait(file, &runtime->sleep, wait); @@ -3198,19 +3198,19 @@ static __poll_t snd_pcm_capture_poll(struct file *file, poll_table * wait) case SNDRV_PCM_STATE_PREPARED: case SNDRV_PCM_STATE_PAUSED: if (avail >= runtime->control->avail_min) { - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; break; } mask = 0; break; case SNDRV_PCM_STATE_DRAINING: if (avail > 0) { - mask = POLLIN | POLLRDNORM; + mask = EPOLLIN | EPOLLRDNORM; break; } /* Fall through */ default: - mask = POLLIN | POLLRDNORM | POLLERR; + mask = EPOLLIN | EPOLLRDNORM | EPOLLERR; break; } snd_pcm_stream_unlock_irq(substream); diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index fae21311723f..69616d00481c 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1385,11 +1385,11 @@ static __poll_t snd_rawmidi_poll(struct file *file, poll_table * wait) mask = 0; if (rfile->input != NULL) { if (snd_rawmidi_ready(rfile->input)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } if (rfile->output != NULL) { if (snd_rawmidi_ready(rfile->output)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } diff --git a/sound/core/seq/oss/seq_oss_rw.c b/sound/core/seq/oss/seq_oss_rw.c index c538e78ca310..30886f5fb100 100644 --- a/sound/core/seq/oss/seq_oss_rw.c +++ b/sound/core/seq/oss/seq_oss_rw.c @@ -204,13 +204,13 @@ snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wai /* input */ if (dp->readq && is_read_mode(dp->file_mode)) { if (snd_seq_oss_readq_poll(dp->readq, file, wait)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } /* output */ if (dp->writeq && is_write_mode(dp->file_mode)) { if (snd_seq_kernel_client_write_poll(dp->cseq, file, wait)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index b611deef81f5..60db32785f62 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1101,7 +1101,7 @@ static __poll_t snd_seq_poll(struct file *file, poll_table * wait) /* check if data is available in the outqueue */ if (snd_seq_fifo_poll_wait(client->data.user.fifo, file, wait)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; } if (snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_OUTPUT) { @@ -1109,7 +1109,7 @@ static __poll_t snd_seq_poll(struct file *file, poll_table * wait) /* check if data is available in the pool */ if (!snd_seq_write_pool_allocated(client) || snd_seq_pool_poll_wait(client->pool, file, wait)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } return mask; diff --git a/sound/core/timer.c b/sound/core/timer.c index da05e314917f..dc87728c5b74 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -2084,9 +2084,9 @@ static __poll_t snd_timer_user_poll(struct file *file, poll_table * wait) mask = 0; spin_lock_irq(&tu->qlock); if (tu->qused) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (tu->disconnected) - mask |= POLLERR; + mask |= EPOLLERR; spin_unlock_irq(&tu->qlock); return mask; diff --git a/sound/firewire/bebob/bebob_hwdep.c b/sound/firewire/bebob/bebob_hwdep.c index 83e791810c52..04c321e08c62 100644 --- a/sound/firewire/bebob/bebob_hwdep.c +++ b/sound/firewire/bebob/bebob_hwdep.c @@ -63,7 +63,7 @@ hwdep_poll(struct snd_hwdep *hwdep, struct file *file, poll_table *wait) spin_lock_irq(&bebob->lock); if (bebob->dev_lock_changed) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&bebob->lock); diff --git a/sound/firewire/dice/dice-hwdep.c b/sound/firewire/dice/dice-hwdep.c index 7a8af0f91c96..6498bf6909ba 100644 --- a/sound/firewire/dice/dice-hwdep.c +++ b/sound/firewire/dice/dice-hwdep.c @@ -62,7 +62,7 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file, spin_lock_irq(&dice->lock); if (dice->dev_lock_changed || dice->notification_bits != 0) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&dice->lock); diff --git a/sound/firewire/digi00x/digi00x-hwdep.c b/sound/firewire/digi00x/digi00x-hwdep.c index a084c2a834db..426cd39e0233 100644 --- a/sound/firewire/digi00x/digi00x-hwdep.c +++ b/sound/firewire/digi00x/digi00x-hwdep.c @@ -70,7 +70,7 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file, spin_lock_irq(&dg00x->lock); if (dg00x->dev_lock_changed || dg00x->msg) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&dg00x->lock); diff --git a/sound/firewire/fireface/ff-hwdep.c b/sound/firewire/fireface/ff-hwdep.c index 68e273fa5d23..336c0076ec42 100644 --- a/sound/firewire/fireface/ff-hwdep.c +++ b/sound/firewire/fireface/ff-hwdep.c @@ -62,7 +62,7 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file, spin_lock_irq(&ff->lock); if (ff->dev_lock_changed) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&ff->lock); diff --git a/sound/firewire/fireworks/fireworks_hwdep.c b/sound/firewire/fireworks/fireworks_hwdep.c index e0eff9328ee1..5cac26ab20b7 100644 --- a/sound/firewire/fireworks/fireworks_hwdep.c +++ b/sound/firewire/fireworks/fireworks_hwdep.c @@ -194,12 +194,12 @@ hwdep_poll(struct snd_hwdep *hwdep, struct file *file, poll_table *wait) spin_lock_irq(&efw->lock); if (efw->dev_lock_changed || efw->pull_ptr != efw->push_ptr) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&efw->lock); - return events | POLLOUT; + return events | EPOLLOUT; } static int diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c index 7b6a086866e7..5f772eab588b 100644 --- a/sound/firewire/motu/motu-hwdep.c +++ b/sound/firewire/motu/motu-hwdep.c @@ -69,12 +69,12 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file, spin_lock_irq(&motu->lock); if (motu->dev_lock_changed || motu->msg) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&motu->lock); - return events | POLLOUT; + return events | EPOLLOUT; } static int hwdep_get_info(struct snd_motu *motu, void __user *arg) diff --git a/sound/firewire/oxfw/oxfw-hwdep.c b/sound/firewire/oxfw/oxfw-hwdep.c index 6c1828aff672..50a1c03b42b9 100644 --- a/sound/firewire/oxfw/oxfw-hwdep.c +++ b/sound/firewire/oxfw/oxfw-hwdep.c @@ -62,7 +62,7 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file, spin_lock_irq(&oxfw->lock); if (oxfw->dev_lock_changed) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&oxfw->lock); diff --git a/sound/firewire/tascam/tascam-hwdep.c b/sound/firewire/tascam/tascam-hwdep.c index 37b21647b471..4e4c1e9020e8 100644 --- a/sound/firewire/tascam/tascam-hwdep.c +++ b/sound/firewire/tascam/tascam-hwdep.c @@ -60,7 +60,7 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file, spin_lock_irq(&tscm->lock); if (tscm->dev_lock_changed) - events = POLLIN | POLLRDNORM; + events = EPOLLIN | EPOLLRDNORM; else events = 0; spin_unlock_irq(&tscm->lock); diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 6b57f8aac1b7..8c0f8a9ee0ba 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -684,7 +684,7 @@ static __poll_t sq_poll(struct file *file, struct poll_table_struct *wait) poll_wait(file, &write_sq.action_queue, wait); if (file->f_mode & FMODE_WRITE) if (write_sq.count < write_sq.max_active || write_sq.block_size - write_sq.rear_size > 0) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/sound/soc/atmel/sam9g20_wm8731.c b/sound/soc/atmel/sam9g20_wm8731.c index d7469cdd90dc..98f93e79c654 100644 --- a/sound/soc/atmel/sam9g20_wm8731.c +++ b/sound/soc/atmel/sam9g20_wm8731.c @@ -110,16 +110,15 @@ static const struct snd_soc_dapm_route intercon[] = { static int at91sam9g20ek_wm8731_init(struct snd_soc_pcm_runtime *rtd) { struct snd_soc_dai *codec_dai = rtd->codec_dai; + struct device *dev = rtd->dev; int ret; - printk(KERN_DEBUG - "at91sam9g20ek_wm8731 " - ": at91sam9g20ek_wm8731_init() called\n"); + dev_dbg(dev, "%s called\n", __func__); ret = snd_soc_dai_set_sysclk(codec_dai, WM8731_SYSCLK_MCLK, - MCLK_RATE, SND_SOC_CLOCK_IN); + MCLK_RATE, SND_SOC_CLOCK_IN); if (ret < 0) { - printk(KERN_ERR "Failed to set WM8731 SYSCLK: %d\n", ret); + dev_err(dev, "Failed to set WM8731 SYSCLK: %d\n", ret); return ret; } @@ -179,21 +178,21 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) */ mclk = clk_get(NULL, "pck0"); if (IS_ERR(mclk)) { - printk(KERN_ERR "ASoC: Failed to get MCLK\n"); + dev_err(&pdev->dev, "Failed to get MCLK\n"); ret = PTR_ERR(mclk); goto err; } pllb = clk_get(NULL, "pllb"); if (IS_ERR(pllb)) { - printk(KERN_ERR "ASoC: Failed to get PLLB\n"); + dev_err(&pdev->dev, "Failed to get PLLB\n"); ret = PTR_ERR(pllb); goto err_mclk; } ret = clk_set_parent(mclk, pllb); clk_put(pllb); if (ret != 0) { - printk(KERN_ERR "ASoC: Failed to set MCLK parent\n"); + dev_err(&pdev->dev, "Failed to set MCLK parent\n"); goto err_mclk; } @@ -236,7 +235,7 @@ static int at91sam9g20ek_audio_probe(struct platform_device *pdev) ret = snd_soc_register_card(card); if (ret) { - printk(KERN_ERR "ASoC: snd_soc_register_card() failed\n"); + dev_err(&pdev->dev, "snd_soc_register_card() failed\n"); } return ret; diff --git a/sound/soc/atmel/sam9x5_wm8731.c b/sound/soc/atmel/sam9x5_wm8731.c index ccdf547f4d8c..e6c303ab869d 100644 --- a/sound/soc/atmel/sam9x5_wm8731.c +++ b/sound/soc/atmel/sam9x5_wm8731.c @@ -49,13 +49,13 @@ static int sam9x5_wm8731_init(struct snd_soc_pcm_runtime *rtd) struct device *dev = rtd->dev; int ret; - dev_dbg(dev, "ASoC: %s called\n", __func__); + dev_dbg(dev, "%s called\n", __func__); /* set the codec system clock for DAC and ADC */ ret = snd_soc_dai_set_sysclk(codec_dai, WM8731_SYSCLK_XTAL, MCLK_RATE, SND_SOC_CLOCK_IN); if (ret < 0) { - dev_err(dev, "ASoC: Failed to set WM8731 SYSCLK: %d\n", ret); + dev_err(dev, "Failed to set WM8731 SYSCLK: %d\n", ret); return ret; } @@ -146,8 +146,7 @@ static int sam9x5_wm8731_driver_probe(struct platform_device *pdev) ret = atmel_ssc_set_audio(priv->ssc_id); if (ret != 0) { - dev_err(&pdev->dev, - "ASoC: Failed to set SSC %d for audio: %d\n", + dev_err(&pdev->dev, "Failed to set SSC %d for audio: %d\n", ret, priv->ssc_id); goto out; } @@ -157,12 +156,11 @@ static int sam9x5_wm8731_driver_probe(struct platform_device *pdev) ret = snd_soc_register_card(card); if (ret) { - dev_err(&pdev->dev, - "ASoC: Platform device allocation failed\n"); + dev_err(&pdev->dev, "Platform device allocation failed\n"); goto out_put_audio; } - dev_dbg(&pdev->dev, "ASoC: %s ok\n", __func__); + dev_dbg(&pdev->dev, "%s ok\n", __func__); return ret; diff --git a/sound/soc/codecs/ak4613.c b/sound/soc/codecs/ak4613.c index b95bb8b52e51..3d1cf4784e87 100644 --- a/sound/soc/codecs/ak4613.c +++ b/sound/soc/codecs/ak4613.c @@ -15,6 +15,7 @@ */ #include <linux/clk.h> +#include <linux/delay.h> #include <linux/i2c.h> #include <linux/slab.h> #include <linux/of_device.h> @@ -95,6 +96,9 @@ struct ak4613_priv { struct mutex lock; const struct ak4613_interface *iface; struct snd_pcm_hw_constraint_list constraint; + struct work_struct dummy_write_work; + struct snd_soc_component *component; + unsigned int rate; unsigned int sysclk; unsigned int fmt; @@ -392,6 +396,7 @@ static int ak4613_dai_hw_params(struct snd_pcm_substream *substream, default: return -EINVAL; } + priv->rate = rate; /* * FIXME @@ -467,11 +472,83 @@ static int ak4613_set_bias_level(struct snd_soc_codec *codec, return 0; } +static void ak4613_dummy_write(struct work_struct *work) +{ + struct ak4613_priv *priv = container_of(work, + struct ak4613_priv, + dummy_write_work); + struct snd_soc_component *component = priv->component; + unsigned int mgmt1; + unsigned int mgmt3; + + /* + * PW_MGMT1 / PW_MGMT3 needs dummy write at least after 5 LR clocks + * + * Note + * + * To avoid extra delay, we want to avoid preemption here, + * but we can't. Because it uses I2C access which is using IRQ + * and sleep. Thus, delay might be more than 5 LR clocks + * see also + * ak4613_dai_trigger() + */ + udelay(5000000 / priv->rate); + + snd_soc_component_read(component, PW_MGMT1, &mgmt1); + snd_soc_component_read(component, PW_MGMT3, &mgmt3); + + snd_soc_component_write(component, PW_MGMT1, mgmt1); + snd_soc_component_write(component, PW_MGMT3, mgmt3); +} + +static int ak4613_dai_trigger(struct snd_pcm_substream *substream, int cmd, + struct snd_soc_dai *dai) +{ + struct snd_soc_codec *codec = dai->codec; + struct ak4613_priv *priv = snd_soc_codec_get_drvdata(codec); + + /* + * FIXME + * + * PW_MGMT1 / PW_MGMT3 needs dummy write at least after 5 LR clocks + * from Power Down Release. Otherwise, Playback volume will be 0dB. + * To avoid complex multiple delay/dummy_write method from + * ak4613_set_bias_level() / SND_SOC_DAPM_DAC_E("DACx", ...), + * call it once here. + * + * But, unfortunately, we can't "write" here because here is atomic + * context (It uses I2C access for writing). + * Thus, use schedule_work() to switching to normal context + * immediately. + * + * Note + * + * Calling ak4613_dummy_write() function might be delayed. + * In such case, ak4613 volume might be temporarily 0dB when + * beggining of playback. + * see also + * ak4613_dummy_write() + */ + + if ((cmd != SNDRV_PCM_TRIGGER_START) && + (cmd != SNDRV_PCM_TRIGGER_RESUME)) + return 0; + + if (substream->stream != SNDRV_PCM_STREAM_PLAYBACK) + return 0; + + priv->component = &codec->component; + schedule_work(&priv->dummy_write_work); + + return 0; +} + static const struct snd_soc_dai_ops ak4613_dai_ops = { .startup = ak4613_dai_startup, .shutdown = ak4613_dai_shutdown, .set_sysclk = ak4613_dai_set_sysclk, .set_fmt = ak4613_dai_set_fmt, + .trigger = ak4613_dai_trigger, .hw_params = ak4613_dai_hw_params, }; @@ -590,6 +667,7 @@ static int ak4613_i2c_probe(struct i2c_client *i2c, priv->iface = NULL; priv->cnt = 0; priv->sysclk = 0; + INIT_WORK(&priv->dummy_write_work, ak4613_dummy_write); mutex_init(&priv->lock); diff --git a/sound/soc/codecs/dmic.c b/sound/soc/codecs/dmic.c index c88f974ebe3e..cf83c423394d 100644 --- a/sound/soc/codecs/dmic.c +++ b/sound/soc/codecs/dmic.c @@ -113,7 +113,7 @@ static int dmic_dev_probe(struct platform_device *pdev) if (pdev->dev.of_node) { err = of_property_read_u32(pdev->dev.of_node, "num-channels", &chans); - if (err && (err != -ENOENT)) + if (err && (err != -EINVAL)) return err; if (!err) { diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c index 31b0864583e8..562e88765129 100644 --- a/sound/soc/codecs/max98373.c +++ b/sound/soc/codecs/max98373.c @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2017, Maxim Integrated */ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017, Maxim Integrated #include <linux/acpi.h> #include <linux/i2c.h> diff --git a/sound/soc/codecs/max98373.h b/sound/soc/codecs/max98373.h index d0b359d0cf8c..f6a37aa02f26 100644 --- a/sound/soc/codecs/max98373.h +++ b/sound/soc/codecs/max98373.h @@ -1,5 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2017, Maxim Integrated */ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017, Maxim Integrated + #ifndef _MAX98373_H #define _MAX98373_H diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index 633cdcfc933d..e1ab5537d27a 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -1392,7 +1392,7 @@ static int sgtl5000_i2c_probe(struct i2c_client *client, ana_pwr |= SGTL5000_LINEREG_D_POWERUP; dev_info(&client->dev, - "Using internal LDO instead of VDDD: check ER1\n"); + "Using internal LDO instead of VDDD: check ER1 erratum\n"); } else { /* using external LDO for VDDD * Clear startup powerup and simple powerup diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c index 8798182959c1..e4d7f397d361 100644 --- a/sound/soc/codecs/twl4030.c +++ b/sound/soc/codecs/twl4030.c @@ -2195,6 +2195,8 @@ static int twl4030_soc_remove(struct snd_soc_codec *codec) static const struct snd_soc_codec_driver soc_codec_dev_twl4030 = { .probe = twl4030_soc_probe, .remove = twl4030_soc_remove, + .read = twl4030_read, + .write = twl4030_write, .set_bias_level = twl4030_set_bias_level, .idle_bias_off = true, diff --git a/sound/soc/codecs/twl6040.c b/sound/soc/codecs/twl6040.c index 3b895b4b451c..573a523ed0b3 100644 --- a/sound/soc/codecs/twl6040.c +++ b/sound/soc/codecs/twl6040.c @@ -1158,6 +1158,8 @@ static int twl6040_remove(struct snd_soc_codec *codec) static const struct snd_soc_codec_driver soc_codec_dev_twl6040 = { .probe = twl6040_probe, .remove = twl6040_remove, + .read = twl6040_read, + .write = twl6040_write, .set_bias_level = twl6040_set_bias_level, .suspend_bias_off = true, .ignore_pmdown_time = true, diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index f2c9e8c5970a..ceb105cbd461 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -97,6 +97,9 @@ config SND_SST_ATOM_HIFI2_PLATFORM codec, then enable this option by saying Y or m. This is a recommended option +config SND_SOC_INTEL_SKYLAKE_SSP_CLK + tristate + config SND_SOC_INTEL_SKYLAKE tristate "SKL/BXT/KBL/GLK/CNL... Platforms" depends on PCI && ACPI diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig index d4e103615f51..fefb1ee9fec6 100644 --- a/sound/soc/intel/boards/Kconfig +++ b/sound/soc/intel/boards/Kconfig @@ -235,6 +235,7 @@ config SND_SOC_INTEL_KBL_RT5663_MAX98927_MACH select SND_SOC_MAX98927 select SND_SOC_DMIC select SND_SOC_HDAC_HDMI + select SND_SOC_INTEL_SKYLAKE_SSP_CLK help This adds support for ASoC Onboard Codec I2S machine driver. This will create an alsa sound card for RT5663 + MAX98927. diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c index bf7014ca486f..f5df6bca3156 100644 --- a/sound/soc/intel/boards/kbl_rt5663_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c @@ -28,6 +28,9 @@ #include "../../codecs/rt5663.h" #include "../../codecs/hdac_hdmi.h" #include "../skylake/skl.h" +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/clkdev.h> #define KBL_REALTEK_CODEC_DAI "rt5663-aif" #define KBL_MAXIM_CODEC_DAI "max98927-aif1" @@ -48,6 +51,8 @@ struct kbl_hdmi_pcm { struct kbl_rt5663_private { struct snd_soc_jack kabylake_headset; struct list_head hdmi_pcm_list; + struct clk *mclk; + struct clk *sclk; }; enum { @@ -69,6 +74,61 @@ static const struct snd_kcontrol_new kabylake_controls[] = { SOC_DAPM_PIN_SWITCH("Right Spk"), }; +static int platform_clock_control(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *k, int event) +{ + struct snd_soc_dapm_context *dapm = w->dapm; + struct snd_soc_card *card = dapm->card; + struct kbl_rt5663_private *priv = snd_soc_card_get_drvdata(card); + int ret = 0; + + /* + * MCLK/SCLK need to be ON early for a successful synchronization of + * codec internal clock. And the clocks are turned off during + * POST_PMD after the stream is stopped. + */ + switch (event) { + case SND_SOC_DAPM_PRE_PMU: + /* Enable MCLK */ + ret = clk_set_rate(priv->mclk, 24000000); + if (ret < 0) { + dev_err(card->dev, "Can't set rate for mclk, err: %d\n", + ret); + return ret; + } + + ret = clk_prepare_enable(priv->mclk); + if (ret < 0) { + dev_err(card->dev, "Can't enable mclk, err: %d\n", ret); + return ret; + } + + /* Enable SCLK */ + ret = clk_set_rate(priv->sclk, 3072000); + if (ret < 0) { + dev_err(card->dev, "Can't set rate for sclk, err: %d\n", + ret); + clk_disable_unprepare(priv->mclk); + return ret; + } + + ret = clk_prepare_enable(priv->sclk); + if (ret < 0) { + dev_err(card->dev, "Can't enable sclk, err: %d\n", ret); + clk_disable_unprepare(priv->mclk); + } + break; + case SND_SOC_DAPM_POST_PMD: + clk_disable_unprepare(priv->mclk); + clk_disable_unprepare(priv->sclk); + break; + default: + return 0; + } + + return 0; +} + static const struct snd_soc_dapm_widget kabylake_widgets[] = { SND_SOC_DAPM_HP("Headphone Jack", NULL), SND_SOC_DAPM_MIC("Headset Mic", NULL), @@ -78,11 +138,14 @@ static const struct snd_soc_dapm_widget kabylake_widgets[] = { SND_SOC_DAPM_SPK("HDMI1", NULL), SND_SOC_DAPM_SPK("HDMI2", NULL), SND_SOC_DAPM_SPK("HDMI3", NULL), - + SND_SOC_DAPM_SUPPLY("Platform Clock", SND_SOC_NOPM, 0, 0, + platform_clock_control, SND_SOC_DAPM_PRE_PMU | + SND_SOC_DAPM_POST_PMD), }; static const struct snd_soc_dapm_route kabylake_map[] = { /* HP jack connectors - unknown if we have jack detection */ + { "Headphone Jack", NULL, "Platform Clock" }, { "Headphone Jack", NULL, "HPOL" }, { "Headphone Jack", NULL, "HPOR" }, @@ -91,6 +154,7 @@ static const struct snd_soc_dapm_route kabylake_map[] = { { "Right Spk", NULL, "Right BE_OUT" }, /* other jacks */ + { "Headset Mic", NULL, "Platform Clock" }, { "IN1P", NULL, "Headset Mic" }, { "IN1N", NULL, "Headset Mic" }, { "DMic", NULL, "SoC DMIC" }, @@ -901,6 +965,7 @@ static int kabylake_audio_probe(struct platform_device *pdev) { struct kbl_rt5663_private *ctx; struct skl_machine_pdata *pdata; + int ret; ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC); if (!ctx) @@ -919,6 +984,34 @@ static int kabylake_audio_probe(struct platform_device *pdev) dmic_constraints = pdata->dmic_num == 2 ? &constraints_dmic_2ch : &constraints_dmic_channels; + ctx->mclk = devm_clk_get(&pdev->dev, "ssp1_mclk"); + if (IS_ERR(ctx->mclk)) { + ret = PTR_ERR(ctx->mclk); + if (ret == -ENOENT) { + dev_info(&pdev->dev, + "Failed to get ssp1_sclk, defer probe\n"); + return -EPROBE_DEFER; + } + + dev_err(&pdev->dev, "Failed to get ssp1_mclk with err:%d\n", + ret); + return ret; + } + + ctx->sclk = devm_clk_get(&pdev->dev, "ssp1_sclk"); + if (IS_ERR(ctx->sclk)) { + ret = PTR_ERR(ctx->sclk); + if (ret == -ENOENT) { + dev_info(&pdev->dev, + "Failed to get ssp1_sclk, defer probe\n"); + return -EPROBE_DEFER; + } + + dev_err(&pdev->dev, "Failed to get ssp1_sclk with err:%d\n", + ret); + return ret; + } + return devm_snd_soc_register_card(&pdev->dev, kabylake_audio_card); } diff --git a/sound/soc/intel/skylake/Makefile b/sound/soc/intel/skylake/Makefile index d1ccbecd141f..86f6e1d801af 100644 --- a/sound/soc/intel/skylake/Makefile +++ b/sound/soc/intel/skylake/Makefile @@ -14,3 +14,8 @@ snd-soc-skl-ipc-objs := skl-sst-ipc.o skl-sst-dsp.o cnl-sst-dsp.o \ skl-sst-utils.o obj-$(CONFIG_SND_SOC_INTEL_SKYLAKE) += snd-soc-skl-ipc.o + +#Skylake Clock device support +snd-soc-skl-ssp-clk-objs := skl-ssp-clk.o + +obj-$(CONFIG_SND_SOC_INTEL_SKYLAKE_SSP_CLK) += snd-soc-skl-ssp-clk.o diff --git a/sound/soc/intel/skylake/skl-i2s.h b/sound/soc/intel/skylake/skl-i2s.h index dcf819bc688f..ad0a1bbca13c 100644 --- a/sound/soc/intel/skylake/skl-i2s.h +++ b/sound/soc/intel/skylake/skl-i2s.h @@ -27,6 +27,12 @@ #define SKL_SHIFT(x) (ffs(x) - 1) #define SKL_MCLK_DIV_RATIO_MASK GENMASK(11, 0) +#define is_legacy_blob(x) (x.signature != 0xEE) +#define ext_to_legacy_blob(i2s_config_blob_ext) \ + ((struct skl_i2s_config_blob_legacy *) i2s_config_blob_ext) + +#define get_clk_src(mclk, mask) \ + ((mclk.mdivctrl & mask) >> SKL_SHIFT(mask)) struct skl_i2s_config { u32 ssc0; u32 ssc1; @@ -45,6 +51,24 @@ struct skl_i2s_config_mclk { u32 mdivr; }; +struct skl_i2s_config_mclk_ext { + u32 mdivctrl; + u32 mdivr_count; + u32 mdivr[0]; +} __packed; + +struct skl_i2s_config_blob_signature { + u32 minor_ver : 8; + u32 major_ver : 8; + u32 resvdz : 8; + u32 signature : 8; +} __packed; + +struct skl_i2s_config_blob_header { + struct skl_i2s_config_blob_signature sig; + u32 size; +}; + /** * struct skl_i2s_config_blob_legacy - Structure defines I2S Gateway * configuration legacy blob @@ -61,4 +85,11 @@ struct skl_i2s_config_blob_legacy { struct skl_i2s_config_mclk mclk; }; +struct skl_i2s_config_blob_ext { + u32 gtw_attr; + struct skl_i2s_config_blob_header hdr; + u32 tdm_ts_group[SKL_I2S_MAX_TIME_SLOTS]; + struct skl_i2s_config i2s_cfg; + struct skl_i2s_config_mclk_ext mclk; +} __packed; #endif /* __SOUND_SOC_SKL_I2S_H */ diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c index 8cbf080c38b3..60d76adade43 100644 --- a/sound/soc/intel/skylake/skl-messages.c +++ b/sound/soc/intel/skylake/skl-messages.c @@ -675,6 +675,7 @@ int skl_dsp_set_dma_control(struct skl_sst *ctx, u32 *caps, kfree(dma_ctrl); return err; } +EXPORT_SYMBOL_GPL(skl_dsp_set_dma_control); static void skl_setup_out_format(struct skl_sst *ctx, struct skl_module_cfg *mconfig, diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c index 3b1d2b828c1b..b9b140275be0 100644 --- a/sound/soc/intel/skylake/skl-nhlt.c +++ b/sound/soc/intel/skylake/skl-nhlt.c @@ -28,6 +28,7 @@ static guid_t osc_guid = GUID_INIT(0xA69F886E, 0x6CEB, 0x4594, 0xA4, 0x1F, 0x7B, 0x5D, 0xCE, 0x24, 0xC5, 0x53); + struct nhlt_acpi_table *skl_nhlt_init(struct device *dev) { acpi_handle handle; @@ -287,6 +288,7 @@ void skl_nhlt_remove_sysfs(struct skl *skl) static void skl_get_ssp_clks(struct skl *skl, struct skl_ssp_clk *ssp_clks, struct nhlt_fmt *fmt, u8 id) { + struct skl_i2s_config_blob_ext *i2s_config_ext; struct skl_i2s_config_blob_legacy *i2s_config; struct skl_clk_parent_src *parent; struct skl_ssp_clk *sclk, *sclkfs; @@ -347,12 +349,18 @@ static void skl_get_ssp_clks(struct skl *skl, struct skl_ssp_clk *ssp_clks, /* Fill rate and parent for sclk/sclkfs */ if (!present) { - /* MCLK Divider Source Select */ - i2s_config = (struct skl_i2s_config_blob_legacy *) + i2s_config_ext = (struct skl_i2s_config_blob_ext *) fmt->fmt_config[0].config.caps; - clk_src = ((i2s_config->mclk.mdivctrl) - & SKL_MNDSS_DIV_CLK_SRC_MASK) >> - SKL_SHIFT(SKL_MNDSS_DIV_CLK_SRC_MASK); + + /* MCLK Divider Source Select */ + if (is_legacy_blob(i2s_config_ext->hdr.sig)) { + i2s_config = ext_to_legacy_blob(i2s_config_ext); + clk_src = get_clk_src(i2s_config->mclk, + SKL_MNDSS_DIV_CLK_SRC_MASK); + } else { + clk_src = get_clk_src(i2s_config_ext->mclk, + SKL_MNDSS_DIV_CLK_SRC_MASK); + } parent = skl_get_parent_clk(clk_src); @@ -378,6 +386,7 @@ static void skl_get_ssp_clks(struct skl *skl, struct skl_ssp_clk *ssp_clks, static void skl_get_mclk(struct skl *skl, struct skl_ssp_clk *mclk, struct nhlt_fmt *fmt, u8 id) { + struct skl_i2s_config_blob_ext *i2s_config_ext; struct skl_i2s_config_blob_legacy *i2s_config; struct nhlt_specific_cfg *fmt_cfg; struct skl_clk_parent_src *parent; @@ -385,13 +394,21 @@ static void skl_get_mclk(struct skl *skl, struct skl_ssp_clk *mclk, u8 clk_src; fmt_cfg = &fmt->fmt_config[0].config; - i2s_config = (struct skl_i2s_config_blob_legacy *)fmt_cfg->caps; - - /* MCLK Divider Source Select */ - clk_src = ((i2s_config->mclk.mdivctrl) & SKL_MCLK_DIV_CLK_SRC_MASK) >> - SKL_SHIFT(SKL_MCLK_DIV_CLK_SRC_MASK); - - clkdiv = i2s_config->mclk.mdivr & SKL_MCLK_DIV_RATIO_MASK; + i2s_config_ext = (struct skl_i2s_config_blob_ext *)fmt_cfg->caps; + + /* MCLK Divider Source Select and divider */ + if (is_legacy_blob(i2s_config_ext->hdr.sig)) { + i2s_config = ext_to_legacy_blob(i2s_config_ext); + clk_src = get_clk_src(i2s_config->mclk, + SKL_MCLK_DIV_CLK_SRC_MASK); + clkdiv = i2s_config->mclk.mdivr & + SKL_MCLK_DIV_RATIO_MASK; + } else { + clk_src = get_clk_src(i2s_config_ext->mclk, + SKL_MCLK_DIV_CLK_SRC_MASK); + clkdiv = i2s_config_ext->mclk.mdivr[0] & + SKL_MCLK_DIV_RATIO_MASK; + } /* bypass divider */ div_ratio = 1; diff --git a/sound/soc/intel/skylake/skl-ssp-clk.c b/sound/soc/intel/skylake/skl-ssp-clk.c new file mode 100644 index 000000000000..7fbddf5e3b00 --- /dev/null +++ b/sound/soc/intel/skylake/skl-ssp-clk.c @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright(c) 2015-17 Intel Corporation + +/* + * skl-ssp-clk.c - ASoC skylake ssp clock driver + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/err.h> +#include <linux/platform_device.h> +#include <linux/clk-provider.h> +#include <linux/clkdev.h> +#include "skl.h" +#include "skl-ssp-clk.h" +#include "skl-topology.h" + +#define to_skl_clk(_hw) container_of(_hw, struct skl_clk, hw) + +struct skl_clk_parent { + struct clk_hw *hw; + struct clk_lookup *lookup; +}; + +struct skl_clk { + struct clk_hw hw; + struct clk_lookup *lookup; + unsigned long rate; + struct skl_clk_pdata *pdata; + u32 id; +}; + +struct skl_clk_data { + struct skl_clk_parent parent[SKL_MAX_CLK_SRC]; + struct skl_clk *clk[SKL_MAX_CLK_CNT]; + u8 avail_clk_cnt; +}; + +static int skl_get_clk_type(u32 index) +{ + switch (index) { + case 0 ... (SKL_SCLK_OFS - 1): + return SKL_MCLK; + + case SKL_SCLK_OFS ... (SKL_SCLKFS_OFS - 1): + return SKL_SCLK; + + case SKL_SCLKFS_OFS ... (SKL_MAX_CLK_CNT - 1): + return SKL_SCLK_FS; + + default: + return -EINVAL; + } +} + +static int skl_get_vbus_id(u32 index, u8 clk_type) +{ + switch (clk_type) { + case SKL_MCLK: + return index; + + case SKL_SCLK: + return index - SKL_SCLK_OFS; + + case SKL_SCLK_FS: + return index - SKL_SCLKFS_OFS; + + default: + return -EINVAL; + } +} + +static void skl_fill_clk_ipc(struct skl_clk_rate_cfg_table *rcfg, u8 clk_type) +{ + struct nhlt_fmt_cfg *fmt_cfg; + union skl_clk_ctrl_ipc *ipc; + struct wav_fmt *wfmt; + + if (!rcfg) + return; + + ipc = &rcfg->dma_ctl_ipc; + if (clk_type == SKL_SCLK_FS) { + fmt_cfg = (struct nhlt_fmt_cfg *)rcfg->config; + wfmt = &fmt_cfg->fmt_ext.fmt; + + /* Remove TLV Header size */ + ipc->sclk_fs.hdr.size = sizeof(struct skl_dmactrl_sclkfs_cfg) - + sizeof(struct skl_tlv_hdr); + ipc->sclk_fs.sampling_frequency = wfmt->samples_per_sec; + ipc->sclk_fs.bit_depth = wfmt->bits_per_sample; + ipc->sclk_fs.valid_bit_depth = + fmt_cfg->fmt_ext.sample.valid_bits_per_sample; + ipc->sclk_fs.number_of_channels = wfmt->channels; + } else { + ipc->mclk.hdr.type = DMA_CLK_CONTROLS; + /* Remove TLV Header size */ + ipc->mclk.hdr.size = sizeof(struct skl_dmactrl_mclk_cfg) - + sizeof(struct skl_tlv_hdr); + } +} + +/* Sends dma control IPC to turn the clock ON/OFF */ +static int skl_send_clk_dma_control(struct skl *skl, + struct skl_clk_rate_cfg_table *rcfg, + u32 vbus_id, u8 clk_type, + bool enable) +{ + struct nhlt_specific_cfg *sp_cfg; + u32 i2s_config_size, node_id = 0; + struct nhlt_fmt_cfg *fmt_cfg; + union skl_clk_ctrl_ipc *ipc; + void *i2s_config = NULL; + u8 *data, size; + int ret; + + if (!rcfg) + return -EIO; + + ipc = &rcfg->dma_ctl_ipc; + fmt_cfg = (struct nhlt_fmt_cfg *)rcfg->config; + sp_cfg = &fmt_cfg->config; + + if (clk_type == SKL_SCLK_FS) { + ipc->sclk_fs.hdr.type = + enable ? DMA_TRANSMITION_START : DMA_TRANSMITION_STOP; + data = (u8 *)&ipc->sclk_fs; + size = sizeof(struct skl_dmactrl_sclkfs_cfg); + } else { + /* 1 to enable mclk, 0 to enable sclk */ + if (clk_type == SKL_SCLK) + ipc->mclk.mclk = 0; + else + ipc->mclk.mclk = 1; + + ipc->mclk.keep_running = enable; + ipc->mclk.warm_up_over = enable; + ipc->mclk.clk_stop_over = !enable; + data = (u8 *)&ipc->mclk; + size = sizeof(struct skl_dmactrl_mclk_cfg); + } + + i2s_config_size = sp_cfg->size + size; + i2s_config = kzalloc(i2s_config_size, GFP_KERNEL); + if (!i2s_config) + return -ENOMEM; + + /* copy blob */ + memcpy(i2s_config, sp_cfg->caps, sp_cfg->size); + + /* copy additional dma controls information */ + memcpy(i2s_config + sp_cfg->size, data, size); + + node_id = ((SKL_DMA_I2S_LINK_INPUT_CLASS << 8) | (vbus_id << 4)); + ret = skl_dsp_set_dma_control(skl->skl_sst, (u32 *)i2s_config, + i2s_config_size, node_id); + kfree(i2s_config); + + return ret; +} + +static struct skl_clk_rate_cfg_table *skl_get_rate_cfg( + struct skl_clk_rate_cfg_table *rcfg, + unsigned long rate) +{ + int i; + + for (i = 0; (i < SKL_MAX_CLK_RATES) && rcfg[i].rate; i++) { + if (rcfg[i].rate == rate) + return &rcfg[i]; + } + + return NULL; +} + +static int skl_clk_change_status(struct skl_clk *clkdev, + bool enable) +{ + struct skl_clk_rate_cfg_table *rcfg; + int vbus_id, clk_type; + + clk_type = skl_get_clk_type(clkdev->id); + if (clk_type < 0) + return clk_type; + + vbus_id = skl_get_vbus_id(clkdev->id, clk_type); + if (vbus_id < 0) + return vbus_id; + + rcfg = skl_get_rate_cfg(clkdev->pdata->ssp_clks[clkdev->id].rate_cfg, + clkdev->rate); + if (!rcfg) + return -EINVAL; + + return skl_send_clk_dma_control(clkdev->pdata->pvt_data, rcfg, + vbus_id, clk_type, enable); +} + +static int skl_clk_prepare(struct clk_hw *hw) +{ + struct skl_clk *clkdev = to_skl_clk(hw); + + return skl_clk_change_status(clkdev, true); +} + +static void skl_clk_unprepare(struct clk_hw *hw) +{ + struct skl_clk *clkdev = to_skl_clk(hw); + + skl_clk_change_status(clkdev, false); +} + +static int skl_clk_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct skl_clk *clkdev = to_skl_clk(hw); + struct skl_clk_rate_cfg_table *rcfg; + int clk_type; + + if (!rate) + return -EINVAL; + + rcfg = skl_get_rate_cfg(clkdev->pdata->ssp_clks[clkdev->id].rate_cfg, + rate); + if (!rcfg) + return -EINVAL; + + clk_type = skl_get_clk_type(clkdev->id); + if (clk_type < 0) + return clk_type; + + skl_fill_clk_ipc(rcfg, clk_type); + clkdev->rate = rate; + + return 0; +} + +static unsigned long skl_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct skl_clk *clkdev = to_skl_clk(hw); + + if (clkdev->rate) + return clkdev->rate; + + return 0; +} + +/* Not supported by clk driver. Implemented to satisfy clk fw */ +long skl_clk_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + return rate; +} + +/* + * prepare/unprepare are used instead of enable/disable as IPC will be sent + * in non-atomic context. + */ +static const struct clk_ops skl_clk_ops = { + .prepare = skl_clk_prepare, + .unprepare = skl_clk_unprepare, + .set_rate = skl_clk_set_rate, + .round_rate = skl_clk_round_rate, + .recalc_rate = skl_clk_recalc_rate, +}; + +static void unregister_parent_src_clk(struct skl_clk_parent *pclk, + unsigned int id) +{ + while (id--) { + clkdev_drop(pclk[id].lookup); + clk_hw_unregister_fixed_rate(pclk[id].hw); + } +} + +static void unregister_src_clk(struct skl_clk_data *dclk) +{ + u8 cnt = dclk->avail_clk_cnt; + + while (cnt--) + clkdev_drop(dclk->clk[cnt]->lookup); +} + +static int skl_register_parent_clks(struct device *dev, + struct skl_clk_parent *parent, + struct skl_clk_parent_src *pclk) +{ + int i, ret; + + for (i = 0; i < SKL_MAX_CLK_SRC; i++) { + + /* Register Parent clock */ + parent[i].hw = clk_hw_register_fixed_rate(dev, pclk[i].name, + pclk[i].parent_name, 0, pclk[i].rate); + if (IS_ERR(parent[i].hw)) { + ret = PTR_ERR(parent[i].hw); + goto err; + } + + parent[i].lookup = clkdev_hw_create(parent[i].hw, pclk[i].name, + NULL); + if (!parent[i].lookup) { + clk_hw_unregister_fixed_rate(parent[i].hw); + ret = -ENOMEM; + goto err; + } + } + + return 0; +err: + unregister_parent_src_clk(parent, i); + return ret; +} + +/* Assign fmt_config to clk_data */ +static struct skl_clk *register_skl_clk(struct device *dev, + struct skl_ssp_clk *clk, + struct skl_clk_pdata *clk_pdata, int id) +{ + struct clk_init_data init; + struct skl_clk *clkdev; + int ret; + + clkdev = devm_kzalloc(dev, sizeof(*clkdev), GFP_KERNEL); + if (!clkdev) + return ERR_PTR(-ENOMEM); + + init.name = clk->name; + init.ops = &skl_clk_ops; + init.flags = CLK_SET_RATE_GATE; + init.parent_names = &clk->parent_name; + init.num_parents = 1; + clkdev->hw.init = &init; + clkdev->pdata = clk_pdata; + + clkdev->id = id; + ret = devm_clk_hw_register(dev, &clkdev->hw); + if (ret) { + clkdev = ERR_PTR(ret); + return clkdev; + } + + clkdev->lookup = clkdev_hw_create(&clkdev->hw, init.name, NULL); + if (!clkdev->lookup) + clkdev = ERR_PTR(-ENOMEM); + + return clkdev; +} + +static int skl_clk_dev_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device *parent_dev = dev->parent; + struct skl_clk_parent_src *parent_clks; + struct skl_clk_pdata *clk_pdata; + struct skl_clk_data *data; + struct skl_ssp_clk *clks; + int ret, i; + + clk_pdata = dev_get_platdata(&pdev->dev); + parent_clks = clk_pdata->parent_clks; + clks = clk_pdata->ssp_clks; + if (!parent_clks || !clks) + return -EIO; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + /* Register Parent clock */ + ret = skl_register_parent_clks(parent_dev, data->parent, parent_clks); + if (ret < 0) + return ret; + + for (i = 0; i < clk_pdata->num_clks; i++) { + /* + * Only register valid clocks + * i.e. for which nhlt entry is present. + */ + if (clks[i].rate_cfg[0].rate == 0) + continue; + + data->clk[i] = register_skl_clk(dev, &clks[i], clk_pdata, i); + if (IS_ERR(data->clk[i])) { + ret = PTR_ERR(data->clk[i]); + goto err_unreg_skl_clk; + } + + data->avail_clk_cnt++; + } + + platform_set_drvdata(pdev, data); + + return 0; + +err_unreg_skl_clk: + unregister_src_clk(data); + unregister_parent_src_clk(data->parent, SKL_MAX_CLK_SRC); + + return ret; +} + +static int skl_clk_dev_remove(struct platform_device *pdev) +{ + struct skl_clk_data *data; + + data = platform_get_drvdata(pdev); + unregister_src_clk(data); + unregister_parent_src_clk(data->parent, SKL_MAX_CLK_SRC); + + return 0; +} + +static struct platform_driver skl_clk_driver = { + .driver = { + .name = "skl-ssp-clk", + }, + .probe = skl_clk_dev_probe, + .remove = skl_clk_dev_remove, +}; + +module_platform_driver(skl_clk_driver); + +MODULE_DESCRIPTION("Skylake clock driver"); +MODULE_AUTHOR("Jaikrishna Nemallapudi <jaikrishnax.nemallapudi@intel.com>"); +MODULE_AUTHOR("Subhransu S. Prusty <subhransu.s.prusty@intel.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:skl-ssp-clk"); diff --git a/sound/soc/intel/skylake/skl-ssp-clk.h b/sound/soc/intel/skylake/skl-ssp-clk.h index c9ea84004260..d1be50f96c05 100644 --- a/sound/soc/intel/skylake/skl-ssp-clk.h +++ b/sound/soc/intel/skylake/skl-ssp-clk.h @@ -54,8 +54,46 @@ struct skl_clk_parent_src { const char *parent_name; }; +struct skl_tlv_hdr { + u32 type; + u32 size; +}; + +struct skl_dmactrl_mclk_cfg { + struct skl_tlv_hdr hdr; + /* DMA Clk TLV params */ + u32 clk_warm_up:16; + u32 mclk:1; + u32 warm_up_over:1; + u32 rsvd0:14; + u32 clk_stop_delay:16; + u32 keep_running:1; + u32 clk_stop_over:1; + u32 rsvd1:14; +}; + +struct skl_dmactrl_sclkfs_cfg { + struct skl_tlv_hdr hdr; + /* DMA SClk&FS TLV params */ + u32 sampling_frequency; + u32 bit_depth; + u32 channel_map; + u32 channel_config; + u32 interleaving_style; + u32 number_of_channels : 8; + u32 valid_bit_depth : 8; + u32 sample_type : 8; + u32 reserved : 8; +}; + +union skl_clk_ctrl_ipc { + struct skl_dmactrl_mclk_cfg mclk; + struct skl_dmactrl_sclkfs_cfg sclk_fs; +}; + struct skl_clk_rate_cfg_table { unsigned long rate; + union skl_clk_ctrl_ipc dma_ctl_ipc; void *config; }; diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h index f411579bc713..2d13f3fd988a 100644 --- a/sound/soc/intel/skylake/skl.h +++ b/sound/soc/intel/skylake/skl.h @@ -38,6 +38,10 @@ /* D0I3C Register fields */ #define AZX_REG_VS_D0I3C_CIP 0x1 /* Command in progress */ #define AZX_REG_VS_D0I3C_I3 0x4 /* D0i3 enable */ +#define SKL_MAX_DMACTRL_CFG 18 +#define DMA_CLK_CONTROLS 1 +#define DMA_TRANSMITION_START 2 +#define DMA_TRANSMITION_STOP 3 struct skl_dsp_resource { u32 max_mcps; @@ -147,6 +151,8 @@ int skl_nhlt_create_sysfs(struct skl *skl); void skl_nhlt_remove_sysfs(struct skl *skl); void skl_get_clks(struct skl *skl, struct skl_ssp_clk *ssp_clks); struct skl_clk_parent_src *skl_get_parent_clk(u8 clk_id); +int skl_dsp_set_dma_control(struct skl_sst *ctx, u32 *caps, + u32 caps_size, u32 node_id); struct skl_module_cfg; diff --git a/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c b/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c index 5bc4e00a4a29..d68b53f7cefe 100644 --- a/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c +++ b/sound/soc/mediatek/mt2701/mt2701-afe-pcm.c @@ -1405,9 +1405,24 @@ static int mt2701_afe_runtime_resume(struct device *dev) return mt2701_afe_enable_clock(afe); } -static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev) +static int mt2701_afe_add_component(struct mtk_base_afe *afe) { struct snd_soc_component *component; + + component = kzalloc(sizeof(*component), GFP_KERNEL); + if (!component) + return -ENOMEM; + + component->regmap = afe->regmap; + + return snd_soc_add_component(afe->dev, component, + &mt2701_afe_pcm_dai_component, + mt2701_afe_pcm_dais, + ARRAY_SIZE(mt2701_afe_pcm_dais)); +} + +static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev) +{ struct mtk_base_afe *afe; struct mt2701_afe_private *afe_priv; struct device *dev; @@ -1477,12 +1492,6 @@ static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev) = &mt2701_i2s_data[i][I2S_IN]; } - component = kzalloc(sizeof(*component), GFP_KERNEL); - if (!component) - return -ENOMEM; - - component->regmap = afe->regmap; - afe->mtk_afe_hardware = &mt2701_afe_hardware; afe->memif_fs = mt2701_memif_fs; afe->irq_fs = mt2701_irq_fs; @@ -1495,7 +1504,7 @@ static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev) ret = mt2701_init_clock(afe); if (ret) { dev_err(dev, "init clock error\n"); - goto err_init_clock; + return ret; } platform_set_drvdata(pdev, afe); @@ -1514,10 +1523,7 @@ static int mt2701_afe_pcm_dev_probe(struct platform_device *pdev) goto err_platform; } - ret = snd_soc_add_component(dev, component, - &mt2701_afe_pcm_dai_component, - mt2701_afe_pcm_dais, - ARRAY_SIZE(mt2701_afe_pcm_dais)); + ret = mt2701_afe_add_component(afe); if (ret) { dev_warn(dev, "err_dai_component\n"); goto err_dai_component; @@ -1531,8 +1537,6 @@ err_platform: pm_runtime_put_sync(dev); err_pm_disable: pm_runtime_disable(dev); -err_init_clock: - kfree(component); return ret; } diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650.c b/sound/soc/mediatek/mt8173/mt8173-rt5650.c index 40ebefd625c1..679fc8bea0a3 100644 --- a/sound/soc/mediatek/mt8173/mt8173-rt5650.c +++ b/sound/soc/mediatek/mt8173/mt8173-rt5650.c @@ -272,15 +272,10 @@ static int mt8173_rt5650_dev_probe(struct platform_device *pdev) } mt8173_rt5650_codecs[1].of_node = mt8173_rt5650_codecs[0].of_node; - if (of_find_node_by_name(platform_node, "codec-capture")) { - np = of_get_child_by_name(pdev->dev.of_node, "codec-capture"); - if (!np) { - dev_err(&pdev->dev, - "%s: Can't find codec-capture DT node\n", - __func__); - return -EINVAL; - } + np = of_get_child_by_name(pdev->dev.of_node, "codec-capture"); + if (np) { ret = snd_soc_of_get_dai_name(np, &codec_capture_dai); + of_node_put(np); if (ret < 0) { dev_err(&pdev->dev, "%s codec_capture_dai name fail %d\n", diff --git a/sound/soc/rockchip/rk3399_gru_sound.c b/sound/soc/rockchip/rk3399_gru_sound.c index fa6cd1de828b..214bfc78cf5c 100644 --- a/sound/soc/rockchip/rk3399_gru_sound.c +++ b/sound/soc/rockchip/rk3399_gru_sound.c @@ -368,7 +368,8 @@ static const struct snd_soc_dai_link rockchip_dais[] = { [DAILINK_RT5514_DSP] = { .name = "RT5514 DSP", .stream_name = "Wake on Voice", - .codec_dai_name = "rt5514-dsp-cpu-dai", + .codec_name = "snd-soc-dummy", + .codec_dai_name = "snd-soc-dummy-dai", }, }; @@ -529,7 +530,18 @@ static int rockchip_sound_of_parse_dais(struct device *dev, if (index < 0) continue; - np_cpu = (index == DAILINK_CDNDP) ? np_cpu1 : np_cpu0; + switch (index) { + case DAILINK_CDNDP: + np_cpu = np_cpu1; + break; + case DAILINK_RT5514_DSP: + np_cpu = np_codec; + break; + default: + np_cpu = np_cpu0; + break; + } + if (!np_cpu) { dev_err(dev, "Missing 'rockchip,cpu' for %s\n", rockchip_dais[index].name); @@ -539,7 +551,8 @@ static int rockchip_sound_of_parse_dais(struct device *dev, dai = &card->dai_link[card->num_links++]; *dai = rockchip_dais[index]; - dai->codec_of_node = np_codec; + if (!dai->codec_name) + dai->codec_of_node = np_codec; dai->platform_of_node = np_cpu; dai->cpu_of_node = np_cpu; diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index 81232f4ab614..82402688bd8e 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -40,7 +40,8 @@ static int soc_compr_open(struct snd_compr_stream *cstream) if (cpu_dai->driver->cops && cpu_dai->driver->cops->startup) { ret = cpu_dai->driver->cops->startup(cstream, cpu_dai); if (ret < 0) { - dev_err(cpu_dai->dev, "Compress ASoC: can't open interface %s: %d\n", + dev_err(cpu_dai->dev, + "Compress ASoC: can't open interface %s: %d\n", cpu_dai->name, ret); goto out; } @@ -49,8 +50,9 @@ static int soc_compr_open(struct snd_compr_stream *cstream) if (platform && platform->driver->compr_ops && platform->driver->compr_ops->open) { ret = platform->driver->compr_ops->open(cstream); if (ret < 0) { - pr_err("compress asoc: can't open platform %s\n", - platform->component.name); + dev_err(platform->dev, + "Compress ASoC: can't open platform %s: %d\n", + platform->component.name, ret); goto plat_err; } } @@ -68,8 +70,9 @@ static int soc_compr_open(struct snd_compr_stream *cstream) __ret = component->driver->compr_ops->open(cstream); if (__ret < 0) { - pr_err("compress asoc: can't open platform %s\n", - component->name); + dev_err(component->dev, + "Compress ASoC: can't open platform %s: %d\n", + component->name, __ret); ret = __ret; } } @@ -79,7 +82,9 @@ static int soc_compr_open(struct snd_compr_stream *cstream) if (rtd->dai_link->compr_ops && rtd->dai_link->compr_ops->startup) { ret = rtd->dai_link->compr_ops->startup(cstream); if (ret < 0) { - pr_err("compress asoc: %s startup failed\n", rtd->dai_link->name); + dev_err(rtd->dev, + "Compress ASoC: %s startup failed: %d\n", + rtd->dai_link->name, ret); goto machine_err; } } @@ -139,18 +144,19 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) if (cpu_dai->driver->cops && cpu_dai->driver->cops->startup) { ret = cpu_dai->driver->cops->startup(cstream, cpu_dai); if (ret < 0) { - dev_err(cpu_dai->dev, "Compress ASoC: can't open interface %s: %d\n", + dev_err(cpu_dai->dev, + "Compress ASoC: can't open interface %s: %d\n", cpu_dai->name, ret); goto out; } } - if (platform && platform->driver->compr_ops && platform->driver->compr_ops->open) { ret = platform->driver->compr_ops->open(cstream); if (ret < 0) { - pr_err("compress asoc: can't open platform %s\n", - platform->component.name); + dev_err(platform->dev, + "Compress ASoC: can't open platform %s: %d\n", + platform->component.name, ret); goto plat_err; } } @@ -168,8 +174,9 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) __ret = component->driver->compr_ops->open(cstream); if (__ret < 0) { - pr_err("compress asoc: can't open platform %s\n", - component->name); + dev_err(component->dev, + "Compress ASoC: can't open platform %s: %d\n", + component->name, __ret); ret = __ret; } } @@ -179,7 +186,8 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->startup) { ret = fe->dai_link->compr_ops->startup(cstream); if (ret < 0) { - pr_err("compress asoc: %s startup failed\n", fe->dai_link->name); + pr_err("Compress ASoC: %s startup failed: %d\n", + fe->dai_link->name, ret); goto machine_err; } } @@ -190,7 +198,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) if (ret < 0) goto fe_err; else if (ret == 0) - dev_dbg(fe->dev, "ASoC: %s no valid %s route\n", + dev_dbg(fe->dev, "Compress ASoC: %s no valid %s route\n", fe->dai_link->name, stream ? "capture" : "playback"); /* calculate valid and active FE <-> BE dpcms */ @@ -265,10 +273,11 @@ static void close_delayed_work(struct work_struct *work) mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass); - dev_dbg(rtd->dev, "ASoC: pop wq checking: %s status: %s waiting: %s\n", - codec_dai->driver->playback.stream_name, - codec_dai->playback_active ? "active" : "inactive", - rtd->pop_wait ? "yes" : "no"); + dev_dbg(rtd->dev, + "Compress ASoC: pop wq checking: %s status: %s waiting: %s\n", + codec_dai->driver->playback.stream_name, + codec_dai->playback_active ? "active" : "inactive", + rtd->pop_wait ? "yes" : "no"); /* are we waiting on this codec DAI stream */ if (rtd->pop_wait == 1) { @@ -307,7 +316,6 @@ static int soc_compr_free(struct snd_compr_stream *cstream) if (!codec_dai->active) codec_dai->rate = 0; - if (rtd->dai_link->compr_ops && rtd->dai_link->compr_ops->shutdown) rtd->dai_link->compr_ops->shutdown(cstream); @@ -376,7 +384,7 @@ static int soc_compr_free_fe(struct snd_compr_stream *cstream) ret = dpcm_be_dai_hw_free(fe, stream); if (ret < 0) - dev_err(fe->dev, "compressed hw_free failed %d\n", ret); + dev_err(fe->dev, "Compressed ASoC: hw_free failed: %d\n", ret); ret = dpcm_be_dai_shutdown(fe, stream); @@ -460,7 +468,6 @@ static int soc_compr_trigger(struct snd_compr_stream *cstream, int cmd) if (cpu_dai->driver->cops && cpu_dai->driver->cops->trigger) cpu_dai->driver->cops->trigger(cstream, cmd, cpu_dai); - switch (cmd) { case SNDRV_PCM_TRIGGER_START: snd_soc_dai_digital_mute(codec_dai, 0, cstream->direction); @@ -944,7 +951,7 @@ static int soc_compr_copy(struct snd_compr_stream *cstream, struct snd_soc_platform *platform = rtd->platform; struct snd_soc_component *component; struct snd_soc_rtdcom_list *rtdcom; - int ret = 0, __ret; + int ret = 0; mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass); @@ -965,10 +972,10 @@ static int soc_compr_copy(struct snd_compr_stream *cstream, !component->driver->compr_ops->copy) continue; - __ret = component->driver->compr_ops->copy(cstream, buf, count); - if (__ret < 0) - ret = __ret; + ret = component->driver->compr_ops->copy(cstream, buf, count); + break; } + err: mutex_unlock(&rtd->pcm_mutex); return ret; @@ -1108,7 +1115,8 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) int playback = 0, capture = 0; if (rtd->num_codecs > 1) { - dev_err(rtd->card->dev, "Multicodec not supported for compressed stream\n"); + dev_err(rtd->card->dev, + "Compress ASoC: Multicodec not supported\n"); return -EINVAL; } @@ -1126,8 +1134,9 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) * should be set, check for that (xor) */ if (playback + capture != 1) { - dev_err(rtd->card->dev, "Invalid direction for compress P %d, C %d\n", - playback, capture); + dev_err(rtd->card->dev, + "Compress ASoC: Invalid direction for P %d, C %d\n", + playback, capture); return -EINVAL; } @@ -1155,8 +1164,9 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->dai_link->dpcm_playback, rtd->dai_link->dpcm_capture, &be_pcm); if (ret < 0) { - dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n", - rtd->dai_link->name); + dev_err(rtd->card->dev, + "Compress ASoC: can't create compressed for %s: %d\n", + rtd->dai_link->name, ret); goto compr_err; } @@ -1199,8 +1209,9 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) new_name, compr); if (ret < 0) { component = rtd->codec_dai->component; - pr_err("compress asoc: can't create compress for codec %s\n", - component->name); + dev_err(component->dev, + "Compress ASoC: can't create compress for codec %s: %d\n", + component->name, ret); goto compr_err; } @@ -1210,8 +1221,8 @@ int snd_soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num) rtd->compr = compr; compr->private_data = rtd; - printk(KERN_INFO "compress asoc: %s <-> %s mapping ok\n", codec_dai->name, - cpu_dai->name); + dev_info(rtd->card->dev, "Compress ASoC: %s <-> %s mapping ok\n", + codec_dai->name, cpu_dai->name); return ret; compr_err: diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 88efc84f3e7b..96c44f6576c9 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -553,9 +553,17 @@ struct snd_soc_component *snd_soc_rtdcom_lookup(struct snd_soc_pcm_runtime *rtd, { struct snd_soc_rtdcom_list *rtdcom; + if (!driver_name) + return NULL; + for_each_rtdcom(rtd, rtdcom) { - if ((rtdcom->component->driver->name == driver_name) || - strcmp(rtdcom->component->driver->name, driver_name) == 0) + const char *component_name = rtdcom->component->driver->name; + + if (!component_name) + continue; + + if ((component_name == driver_name) || + strcmp(component_name, driver_name) == 0) return rtdcom->component; } diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index d1977ced895f..92894d9cac19 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2026,7 +2026,7 @@ static ssize_t dapm_widget_power_read_file(struct file *file, snd_soc_dapm_for_each_direction(dir) { rdir = SND_SOC_DAPM_DIR_REVERSE(dir); snd_soc_dapm_widget_for_each_path(w, dir, p) { - if (p->connected && !p->connected(w, p->node[rdir])) + if (p->connected && !p->connected(p->source, p->sink)) continue; if (!p->connect) diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 8075856668c2..084125463d10 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -144,7 +144,7 @@ bool snd_soc_runtime_ignore_pmdown_time(struct snd_soc_pcm_runtime *rtd) for_each_rtdcom(rtd, rtdcom) { component = rtdcom->component; - ignore &= !component->driver->pmdown_time; + ignore &= !component->driver->use_pmdown_time; } /* this will be removed */ @@ -2831,10 +2831,9 @@ static void soc_pcm_private_free(struct snd_pcm *pcm) struct snd_soc_rtdcom_list *rtdcom; struct snd_soc_component *component; + /* need to sync the delayed work before releasing resources */ + flush_delayed_work(&rtd->delayed_work); for_each_rtdcom(rtd, rtdcom) { - /* need to sync the delayed work before releasing resources */ - - flush_delayed_work(&rtd->delayed_work); component = rtdcom->component; if (component->pcm_free) diff --git a/sound/soc/stm/Kconfig b/sound/soc/stm/Kconfig index 3ad881fc40a1..48f9ddd94016 100644 --- a/sound/soc/stm/Kconfig +++ b/sound/soc/stm/Kconfig @@ -2,7 +2,7 @@ menu "STMicroelectronics STM32 SOC audio support" config SND_SOC_STM32_SAI tristate "STM32 SAI interface (Serial Audio Interface) support" - depends on ARCH_STM32 || COMPILE_TEST + depends on (ARCH_STM32 && OF) || COMPILE_TEST depends on SND_SOC select SND_SOC_GENERIC_DMAENGINE_PCM select REGMAP_MMIO @@ -11,7 +11,7 @@ config SND_SOC_STM32_SAI config SND_SOC_STM32_I2S tristate "STM32 I2S interface (SPI/I2S block) support" - depends on ARCH_STM32 || COMPILE_TEST + depends on (ARCH_STM32 && OF) || COMPILE_TEST depends on SND_SOC select SND_SOC_GENERIC_DMAENGINE_PCM select REGMAP_MMIO @@ -20,7 +20,7 @@ config SND_SOC_STM32_I2S config SND_SOC_STM32_SPDIFRX tristate "STM32 S/PDIF receiver (SPDIFRX) support" - depends on ARCH_STM32 || COMPILE_TEST + depends on (ARCH_STM32 && OF) || COMPILE_TEST depends on SND_SOC select SND_SOC_GENERIC_DMAENGINE_PCM select REGMAP_MMIO diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c index 3dd183be08a4..7a15df924316 100644 --- a/sound/soc/sunxi/sun8i-codec.c +++ b/sound/soc/sunxi/sun8i-codec.c @@ -37,9 +37,11 @@ #define SUN8I_SYSCLK_CTL_SYSCLK_SRC 0 #define SUN8I_MOD_CLK_ENA 0x010 #define SUN8I_MOD_CLK_ENA_AIF1 15 +#define SUN8I_MOD_CLK_ENA_ADC 3 #define SUN8I_MOD_CLK_ENA_DAC 2 #define SUN8I_MOD_RST_CTL 0x014 #define SUN8I_MOD_RST_CTL_AIF1 15 +#define SUN8I_MOD_RST_CTL_ADC 3 #define SUN8I_MOD_RST_CTL_DAC 2 #define SUN8I_SYS_SR_CTRL 0x018 #define SUN8I_SYS_SR_CTRL_AIF1_FS 12 @@ -54,9 +56,25 @@ #define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ 4 #define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ_16 (1 << 4) #define SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT 2 +#define SUN8I_AIF1_ADCDAT_CTRL 0x044 +#define SUN8I_AIF1_ADCDAT_CTRL_AIF1_DA0L_ENA 15 +#define SUN8I_AIF1_ADCDAT_CTRL_AIF1_DA0R_ENA 14 #define SUN8I_AIF1_DACDAT_CTRL 0x048 #define SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0L_ENA 15 #define SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0R_ENA 14 +#define SUN8I_AIF1_MXR_SRC 0x04c +#define SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_AIF1DA0L 15 +#define SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_AIF2DACL 14 +#define SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_ADCL 13 +#define SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_AIF2DACR 12 +#define SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_AIF1DA0R 11 +#define SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_AIF2DACR 10 +#define SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_ADCR 9 +#define SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_AIF2DACL 8 +#define SUN8I_ADC_DIG_CTRL 0x100 +#define SUN8I_ADC_DIG_CTRL_ENDA 15 +#define SUN8I_ADC_DIG_CTRL_ADOUT_DTS 2 +#define SUN8I_ADC_DIG_CTRL_ADOUT_DLY 1 #define SUN8I_DAC_DIG_CTRL 0x120 #define SUN8I_DAC_DIG_CTRL_ENDA 15 #define SUN8I_DAC_MXR_SRC 0x130 @@ -338,10 +356,30 @@ static const struct snd_kcontrol_new sun8i_dac_mixer_controls[] = { SUN8I_DAC_MXR_SRC_DACR_MXR_SRC_ADCR, 1, 0), }; +static const struct snd_kcontrol_new sun8i_input_mixer_controls[] = { + SOC_DAPM_DOUBLE("AIF1 Slot 0 Digital ADC Capture Switch", + SUN8I_AIF1_MXR_SRC, + SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_AIF1DA0L, + SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_AIF1DA0R, 1, 0), + SOC_DAPM_DOUBLE("AIF2 Digital ADC Capture Switch", SUN8I_AIF1_MXR_SRC, + SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_AIF2DACL, + SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_AIF2DACR, 1, 0), + SOC_DAPM_DOUBLE("AIF1 Data Digital ADC Capture Switch", + SUN8I_AIF1_MXR_SRC, + SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_ADCL, + SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_ADCR, 1, 0), + SOC_DAPM_DOUBLE("AIF2 Inv Digital ADC Capture Switch", + SUN8I_AIF1_MXR_SRC, + SUN8I_AIF1_MXR_SRC_AD0L_MXL_SRC_AIF2DACR, + SUN8I_AIF1_MXR_SRC_AD0R_MXR_SRC_AIF2DACL, 1, 0), +}; + static const struct snd_soc_dapm_widget sun8i_codec_dapm_widgets[] = { - /* Digital parts of the DACs */ + /* Digital parts of the DACs and ADC */ SND_SOC_DAPM_SUPPLY("DAC", SUN8I_DAC_DIG_CTRL, SUN8I_DAC_DIG_CTRL_ENDA, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("ADC", SUN8I_ADC_DIG_CTRL, SUN8I_ADC_DIG_CTRL_ENDA, + 0, NULL, 0), /* Analog DAC AIF */ SND_SOC_DAPM_AIF_IN("AIF1 Slot 0 Left", "Playback", 0, @@ -351,17 +389,31 @@ static const struct snd_soc_dapm_widget sun8i_codec_dapm_widgets[] = { SUN8I_AIF1_DACDAT_CTRL, SUN8I_AIF1_DACDAT_CTRL_AIF1_DA0R_ENA, 0), - /* DAC Mixers */ + /* Analog ADC AIF */ + SND_SOC_DAPM_AIF_IN("AIF1 Slot 0 Left ADC", "Capture", 0, + SUN8I_AIF1_ADCDAT_CTRL, + SUN8I_AIF1_ADCDAT_CTRL_AIF1_DA0L_ENA, 0), + SND_SOC_DAPM_AIF_IN("AIF1 Slot 0 Right ADC", "Capture", 0, + SUN8I_AIF1_ADCDAT_CTRL, + SUN8I_AIF1_ADCDAT_CTRL_AIF1_DA0R_ENA, 0), + + /* DAC and ADC Mixers */ SOC_MIXER_ARRAY("Left Digital DAC Mixer", SND_SOC_NOPM, 0, 0, sun8i_dac_mixer_controls), SOC_MIXER_ARRAY("Right Digital DAC Mixer", SND_SOC_NOPM, 0, 0, sun8i_dac_mixer_controls), + SOC_MIXER_ARRAY("Left Digital ADC Mixer", SND_SOC_NOPM, 0, 0, + sun8i_input_mixer_controls), + SOC_MIXER_ARRAY("Right Digital ADC Mixer", SND_SOC_NOPM, 0, 0, + sun8i_input_mixer_controls), /* Clocks */ SND_SOC_DAPM_SUPPLY("MODCLK AFI1", SUN8I_MOD_CLK_ENA, SUN8I_MOD_CLK_ENA_AIF1, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("MODCLK DAC", SUN8I_MOD_CLK_ENA, SUN8I_MOD_CLK_ENA_DAC, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("MODCLK ADC", SUN8I_MOD_CLK_ENA, + SUN8I_MOD_CLK_ENA_ADC, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("AIF1", SUN8I_SYSCLK_CTL, SUN8I_SYSCLK_CTL_AIF1CLK_ENA, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("SYSCLK", SUN8I_SYSCLK_CTL, @@ -378,6 +430,12 @@ static const struct snd_soc_dapm_widget sun8i_codec_dapm_widgets[] = { SUN8I_MOD_RST_CTL_AIF1, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("RST DAC", SUN8I_MOD_RST_CTL, SUN8I_MOD_RST_CTL_DAC, 0, NULL, 0), + SND_SOC_DAPM_SUPPLY("RST ADC", SUN8I_MOD_RST_CTL, + SUN8I_MOD_RST_CTL_ADC, 0, NULL, 0), + + SND_SOC_DAPM_MIC("Headset Mic", NULL), + SND_SOC_DAPM_MIC("Mic", NULL), + }; static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = { @@ -387,11 +445,16 @@ static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = { { "RST AIF1", NULL, "AIF1 PLL" }, { "MODCLK AFI1", NULL, "RST AIF1" }, { "DAC", NULL, "MODCLK AFI1" }, + { "ADC", NULL, "MODCLK AFI1" }, { "RST DAC", NULL, "SYSCLK" }, { "MODCLK DAC", NULL, "RST DAC" }, { "DAC", NULL, "MODCLK DAC" }, + { "RST ADC", NULL, "SYSCLK" }, + { "MODCLK ADC", NULL, "RST ADC" }, + { "ADC", NULL, "MODCLK ADC" }, + /* DAC Routes */ { "AIF1 Slot 0 Right", NULL, "DAC" }, { "AIF1 Slot 0 Left", NULL, "DAC" }, @@ -401,6 +464,12 @@ static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = { "AIF1 Slot 0 Left"}, { "Right Digital DAC Mixer", "AIF1 Slot 0 Digital DAC Playback Switch", "AIF1 Slot 0 Right"}, + + /* ADC routes */ + { "Left Digital ADC Mixer", "AIF1 Data Digital ADC Capture Switch", + "AIF1 Slot 0 Left ADC" }, + { "Right Digital ADC Mixer", "AIF1 Data Digital ADC Capture Switch", + "AIF1 Slot 0 Right ADC" }, }; static const struct snd_soc_dai_ops sun8i_codec_dai_ops = { @@ -418,6 +487,15 @@ static struct snd_soc_dai_driver sun8i_codec_dai = { .rates = SNDRV_PCM_RATE_8000_192000, .formats = SNDRV_PCM_FMTBIT_S16_LE, }, + /* capture capabilities */ + .capture = { + .stream_name = "Capture", + .channels_min = 1, + .channels_max = 2, + .rates = SNDRV_PCM_RATE_8000_192000, + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .sig_bits = 24, + }, /* pcm operations */ .ops = &sun8i_codec_dai_ops, }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 05ccc7fdcc09..56537a156580 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -246,7 +246,7 @@ static __poll_t snd_usb_sbrc_hwdep_poll(struct snd_hwdep *hw, struct file *file, struct usb_mixer_interface *mixer = hw->private_data; poll_wait(file, &mixer->rc_waitq, wait); - return mixer->rc_code ? POLLIN | POLLRDNORM : 0; + return mixer->rc_code ? EPOLLIN | EPOLLRDNORM : 0; } static int snd_usb_soundblaster_remote_init(struct usb_mixer_interface *mixer) diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index e2be10d17118..ebcab5c5465d 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -280,7 +280,7 @@ static __poll_t usb_stream_hwdep_poll(struct snd_hwdep *hw, poll_wait(file, &us122l->sk.sleep, wait); - mask = POLLIN | POLLOUT | POLLWRNORM | POLLERR; + mask = EPOLLIN | EPOLLOUT | EPOLLWRNORM | EPOLLERR; if (mutex_trylock(&us122l->mutex)) { struct usb_stream *s = us122l->sk.s; if (s && s->state == usb_stream_ready) { @@ -290,7 +290,7 @@ static __poll_t usb_stream_hwdep_poll(struct snd_hwdep *hw, polled = &us122l->second_periods_polled; if (*polled != s->periods_done) { *polled = s->periods_done; - mask = POLLIN | POLLOUT | POLLWRNORM; + mask = EPOLLIN | EPOLLOUT | EPOLLWRNORM; } else mask = 0; } diff --git a/sound/usb/usx2y/usX2Yhwdep.c b/sound/usb/usx2y/usX2Yhwdep.c index 07d15bae75bc..d8bd7c99b48c 100644 --- a/sound/usb/usx2y/usX2Yhwdep.c +++ b/sound/usb/usx2y/usX2Yhwdep.c @@ -92,12 +92,12 @@ static __poll_t snd_us428ctls_poll(struct snd_hwdep *hw, struct file *file, poll struct usX2Ydev *us428 = hw->private_data; struct us428ctls_sharedmem *shm = us428->us428ctls_sharedmem; if (us428->chip_status & USX2Y_STAT_CHIP_HUP) - return POLLHUP; + return EPOLLHUP; poll_wait(file, &us428->us428ctls_wait_queue_head, wait); if (shm != NULL && shm->CtlSnapShotLast != shm->CtlSnapShotRed) - mask |= POLLIN; + mask |= EPOLLIN; return mask; } diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 61d6049f4c1e..637b7263cb86 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info { __u32 ap_encodings[8]; }; +/* For KVM_PPC_GET_CPU_CHAR */ +struct kvm_ppc_cpu_char { + __u64 character; /* characteristics of the CPU */ + __u64 behaviour; /* recommended software behaviour */ + __u64 character_mask; /* valid bits in character */ + __u64 behaviour_mask; /* valid bits in behaviour */ +}; + +/* + * Values for character and character_mask. + * These are identical to the values used by H_GET_CPU_CHARACTERISTICS. + */ +#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 (1ULL << 63) +#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED (1ULL << 62) +#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 (1ULL << 61) +#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 (1ULL << 60) +#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV (1ULL << 59) +#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58) +#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57) +#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56) + +#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63) +#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62) +#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61) + /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 38535a57fef8..4cdaa55fabfe 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -224,6 +224,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_RICCB (1UL << 7) #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) +#define KVM_SYNC_BPBC (1UL << 10) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -247,7 +248,9 @@ struct kvm_sync_regs { }; __u8 reserved[512]; /* for future vector expansion */ __u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */ - __u8 padding1[52]; /* riccb needs to be 64byte aligned */ + __u8 bpbc : 1; /* bp mode */ + __u8 reserved2 : 7; + __u8 padding1[51]; /* riccb needs to be 64byte aligned */ __u8 riccb[64]; /* runtime instrumentation controls block */ __u8 padding2[192]; /* sdnx needs to be 256byte aligned */ union { diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 21ac898df2d8..1d9199e1c2ad 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NCAPINTS 19 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -203,12 +203,15 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ +#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ -#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ -#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ -#define X86_FEATURE_AVX512_4FMAPS ( 7*32+17) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ + +#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -243,6 +246,7 @@ #define X86_FEATURE_AVX512IFMA ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* Intel Processor Trace */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ @@ -268,6 +272,9 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -316,6 +323,13 @@ #define X86_FEATURE_SUCCOR (17*32+ 1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+ 3) /* Scalable MCA */ +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ + /* * BUG word(s) */ @@ -342,5 +356,7 @@ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ #define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index b027633e7300..33833d1909af 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -77,6 +77,7 @@ #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP) #define DISABLED_MASK17 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define DISABLED_MASK18 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index d91ba04dd007..fb3a6de7440b 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -106,6 +106,7 @@ #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 (NEED_LA57) #define REQUIRED_MASK17 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) +#define REQUIRED_MASK18 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index c462a928e03d..a9d47c1558bb 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -23,7 +23,12 @@ DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8)) man: man8 man8: $(DOC_MAN8) +RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) + $(OUTPUT)%.8: %.rst +ifndef RST2MAN_DEP + $(error "rst2man not found, but required to generate man pages") +endif $(QUIET_GEN)rst2man $< > $@ clean: diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 2fe2a1bdbe3e..0e4e923235b6 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -26,8 +26,8 @@ MAP COMMANDS | **bpftool** **cgroup help** | | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *ATTACH_TYPE* := { *ingress* | *egress* | *sock_create* | *sock_ops* | *device* } -| *ATTACH_FLAGS* := { *multi* | *override* } +| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** } +| *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 0ab32b312aec..457e868bd32f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -31,7 +31,8 @@ MAP COMMANDS | **bpftool** **map help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } -| *VALUE* := { *BYTES* | *MAP* | *PROGRAM* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *VALUE* := { *BYTES* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } DESCRIPTION diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 0137866bb8f6..08719c54a614 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -52,16 +52,24 @@ _bpftool_once_attr() done } -# Takes a list of words in argument; adds them all to COMPREPLY if none of them -# is already present on the command line. Returns no value. -_bpftool_one_of_list() +# Takes a list of words as argument; if any of those words is present on the +# command line, return 0. Otherwise, return 1. +_bpftool_search_list() { local w idx for w in $*; do for (( idx=3; idx < ${#words[@]}-1; idx++ )); do - [[ $w == ${words[idx]} ]] && return 1 + [[ $w == ${words[idx]} ]] && return 0 done done + return 1 +} + +# Takes a list of words in argument; adds them all to COMPREPLY if none of them +# is already present on the command line. Returns no value. +_bpftool_one_of_list() +{ + _bpftool_search_list $* && return 1 COMPREPLY+=( $( compgen -W "$*" -- "$cur" ) ) } @@ -230,10 +238,14 @@ _bpftool() fi return 0 ;; + load) + _filedir + return 0 + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'dump help pin show list' -- \ - "$cur" ) ) + COMPREPLY=( $( compgen -W 'dump help pin load \ + show list' -- "$cur" ) ) ;; esac ;; @@ -347,6 +359,54 @@ _bpftool() ;; esac ;; + cgroup) + case $command in + show|list) + _filedir + return 0 + ;; + attach|detach) + local ATTACH_TYPES='ingress egress sock_create sock_ops \ + device' + local ATTACH_FLAGS='multi override' + local PROG_TYPE='id pinned tag' + case $prev in + $command) + _filedir + return 0 + ;; + ingress|egress|sock_create|sock_ops|device) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ + "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_prog_ids + return 0 + ;; + *) + if ! _bpftool_search_list "$ATTACH_TYPES"; then + COMPREPLY=( $( compgen -W "$ATTACH_TYPES" -- \ + "$cur" ) ) + elif [[ "$command" == "attach" ]]; then + # We have an attach type on the command line, + # but it is not the previous word, or + # "id|pinned|tag" (we already checked for + # that). This should only leave the case when + # we need attach flags for "attach" commamnd. + _bpftool_one_of_list "$ATTACH_FLAGS" + fi + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help attach detach \ + show list' -- "$cur" ) ) + ;; + esac + ;; esac } && complete -F _bpftool bpftool diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h index 9311fadaaab2..16ed1982cb34 100644 --- a/tools/include/asm-generic/bitops/find.h +++ b/tools/include/asm-generic/bitops/find.h @@ -16,6 +16,22 @@ extern unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset); #endif +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +extern unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset); +#endif + #ifndef find_next_zero_bit /** diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h index 18be90725ab0..ee97668bdadb 100644 --- a/tools/include/uapi/linux/bpf_common.h +++ b/tools/include/uapi/linux/bpf_common.h @@ -15,9 +15,10 @@ /* ld/ldx fields */ #define BPF_SIZE(code) ((code) & 0x18) -#define BPF_W 0x00 -#define BPF_H 0x08 -#define BPF_B 0x10 +#define BPF_W 0x00 /* 32-bit */ +#define BPF_H 0x08 /* 16-bit */ +#define BPF_B 0x10 /* 8-bit */ +/* eBPF BPF_DW 0x18 64-bit */ #define BPF_MODE(code) ((code) & 0xe0) #define BPF_IMM 0x00 #define BPF_ABS 0x20 diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h new file mode 100644 index 000000000000..8616131e2c61 --- /dev/null +++ b/tools/include/uapi/linux/if_link.h @@ -0,0 +1,943 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IF_LINK_H +#define _UAPI_LINUX_IF_LINK_H + +#include <linux/types.h> +#include <linux/netlink.h> + +/* This struct should be in sync with struct rtnl_link_stats64 */ +struct rtnl_link_stats { + __u32 rx_packets; /* total packets received */ + __u32 tx_packets; /* total packets transmitted */ + __u32 rx_bytes; /* total bytes received */ + __u32 tx_bytes; /* total bytes transmitted */ + __u32 rx_errors; /* bad packets received */ + __u32 tx_errors; /* packet transmit problems */ + __u32 rx_dropped; /* no space in linux buffers */ + __u32 tx_dropped; /* no space available in linux */ + __u32 multicast; /* multicast packets received */ + __u32 collisions; + + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; /* receiver ring buff overflow */ + __u32 rx_crc_errors; /* recved pkt with crc error */ + __u32 rx_frame_errors; /* recv'd frame alignment error */ + __u32 rx_fifo_errors; /* recv'r fifo overrun */ + __u32 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; + + __u32 rx_nohandler; /* dropped, no handler found */ +}; + +/* The main device statistics structure */ +struct rtnl_link_stats64 { + __u64 rx_packets; /* total packets received */ + __u64 tx_packets; /* total packets transmitted */ + __u64 rx_bytes; /* total bytes received */ + __u64 tx_bytes; /* total bytes transmitted */ + __u64 rx_errors; /* bad packets received */ + __u64 tx_errors; /* packet transmit problems */ + __u64 rx_dropped; /* no space in linux buffers */ + __u64 tx_dropped; /* no space available in linux */ + __u64 multicast; /* multicast packets received */ + __u64 collisions; + + /* detailed rx_errors: */ + __u64 rx_length_errors; + __u64 rx_over_errors; /* receiver ring buff overflow */ + __u64 rx_crc_errors; /* recved pkt with crc error */ + __u64 rx_frame_errors; /* recv'd frame alignment error */ + __u64 rx_fifo_errors; /* recv'r fifo overrun */ + __u64 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u64 tx_aborted_errors; + __u64 tx_carrier_errors; + __u64 tx_fifo_errors; + __u64 tx_heartbeat_errors; + __u64 tx_window_errors; + + /* for cslip etc */ + __u64 rx_compressed; + __u64 tx_compressed; + + __u64 rx_nohandler; /* dropped, no handler found */ +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap { + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + +enum { + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + IFLA_LINKINFO, +#define IFLA_LINKINFO IFLA_LINKINFO + IFLA_NET_NS_PID, + IFLA_IFALIAS, + IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ + IFLA_VFINFO_LIST, + IFLA_STATS64, + IFLA_VF_PORTS, + IFLA_PORT_SELF, + IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ + IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ + IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */ +#define IFLA_PROMISCUITY IFLA_PROMISCUITY + IFLA_NUM_TX_QUEUES, + IFLA_NUM_RX_QUEUES, + IFLA_CARRIER, + IFLA_PHYS_PORT_ID, + IFLA_CARRIER_CHANGES, + IFLA_PHYS_SWITCH_ID, + IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, + IFLA_PROTO_DOWN, + IFLA_GSO_MAX_SEGS, + IFLA_GSO_MAX_SIZE, + IFLA_PAD, + IFLA_XDP, + IFLA_EVENT, + IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, + IFLA_CARRIER_UP_COUNT, + IFLA_CARRIER_DOWN_COUNT, + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) +#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) +#endif + +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum { + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ + IFLA_INET6_TOKEN, /* device token */ + IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +enum in6_addr_gen_mode { + IN6_ADDR_GEN_MODE_EUI64, + IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, + IN6_ADDR_GEN_MODE_RANDOM, +}; + +/* Bridge section */ + +enum { + IFLA_BR_UNSPEC, + IFLA_BR_FORWARD_DELAY, + IFLA_BR_HELLO_TIME, + IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, + IFLA_BR_VLAN_FILTERING, + IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, + IFLA_BR_PAD, + IFLA_BR_VLAN_STATS_ENABLED, + IFLA_BR_MCAST_STATS_ENABLED, + IFLA_BR_MCAST_IGMP_VERSION, + IFLA_BR_MCAST_MLD_VERSION, + __IFLA_BR_MAX, +}; + +#define IFLA_BR_MAX (__IFLA_BR_MAX - 1) + +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + +enum { + BRIDGE_MODE_UNSPEC, + BRIDGE_MODE_HAIRPIN, +}; + +enum { + IFLA_BRPORT_UNSPEC, + IFLA_BRPORT_STATE, /* Spanning tree state */ + IFLA_BRPORT_PRIORITY, /* " priority */ + IFLA_BRPORT_COST, /* " cost */ + IFLA_BRPORT_MODE, /* mode (hairpin) */ + IFLA_BRPORT_GUARD, /* bpdu guard */ + IFLA_BRPORT_PROTECT, /* root port protection */ + IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */ + IFLA_BRPORT_LEARNING, /* mac learning */ + IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */ + IFLA_BRPORT_PROXYARP, /* proxy ARP */ + IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ + IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, + IFLA_BRPORT_PAD, + IFLA_BRPORT_MCAST_FLOOD, + IFLA_BRPORT_MCAST_TO_UCAST, + IFLA_BRPORT_VLAN_TUNNEL, + IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, + __IFLA_BRPORT_MAX +}; +#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) + +struct ifla_cacheinfo { + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; + +enum { + IFLA_INFO_UNSPEC, + IFLA_INFO_KIND, + IFLA_INFO_DATA, + IFLA_INFO_XSTATS, + IFLA_INFO_SLAVE_KIND, + IFLA_INFO_SLAVE_DATA, + __IFLA_INFO_MAX, +}; + +#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) + +/* VLAN section */ + +enum { + IFLA_VLAN_UNSPEC, + IFLA_VLAN_ID, + IFLA_VLAN_FLAGS, + IFLA_VLAN_EGRESS_QOS, + IFLA_VLAN_INGRESS_QOS, + IFLA_VLAN_PROTOCOL, + __IFLA_VLAN_MAX, +}; + +#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1) + +struct ifla_vlan_flags { + __u32 flags; + __u32 mask; +}; + +enum { + IFLA_VLAN_QOS_UNSPEC, + IFLA_VLAN_QOS_MAPPING, + __IFLA_VLAN_QOS_MAX +}; + +#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1) + +struct ifla_vlan_qos_mapping { + __u32 from; + __u32 to; +}; + +/* MACVLAN section */ +enum { + IFLA_MACVLAN_UNSPEC, + IFLA_MACVLAN_MODE, + IFLA_MACVLAN_FLAGS, + IFLA_MACVLAN_MACADDR_MODE, + IFLA_MACVLAN_MACADDR, + IFLA_MACVLAN_MACADDR_DATA, + IFLA_MACVLAN_MACADDR_COUNT, + __IFLA_MACVLAN_MAX, +}; + +#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1) + +enum macvlan_mode { + MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ + MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ + MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ + MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */ +}; + +enum macvlan_macaddr_mode { + MACVLAN_MACADDR_ADD, + MACVLAN_MACADDR_DEL, + MACVLAN_MACADDR_FLUSH, + MACVLAN_MACADDR_SET, +}; + +#define MACVLAN_FLAG_NOPROMISC 1 + +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + +enum { + IFLA_VRF_PORT_UNSPEC, + IFLA_VRF_PORT_TABLE, + __IFLA_VRF_PORT_MAX +}; + +#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1) + +/* MACSEC section */ +enum { + IFLA_MACSEC_UNSPEC, + IFLA_MACSEC_SCI, + IFLA_MACSEC_PORT, + IFLA_MACSEC_ICV_LEN, + IFLA_MACSEC_CIPHER_SUITE, + IFLA_MACSEC_WINDOW, + IFLA_MACSEC_ENCODING_SA, + IFLA_MACSEC_ENCRYPT, + IFLA_MACSEC_PROTECT, + IFLA_MACSEC_INC_SCI, + IFLA_MACSEC_ES, + IFLA_MACSEC_SCB, + IFLA_MACSEC_REPLAY_PROTECT, + IFLA_MACSEC_VALIDATION, + IFLA_MACSEC_PAD, + __IFLA_MACSEC_MAX, +}; + +#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) + +enum macsec_validation_type { + MACSEC_VALIDATE_DISABLED = 0, + MACSEC_VALIDATE_CHECK = 1, + MACSEC_VALIDATE_STRICT = 2, + __MACSEC_VALIDATE_END, + MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, +}; + +/* IPVLAN section */ +enum { + IFLA_IPVLAN_UNSPEC, + IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, + __IFLA_IPVLAN_MAX +}; + +#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1) + +enum ipvlan_mode { + IPVLAN_MODE_L2 = 0, + IPVLAN_MODE_L3, + IPVLAN_MODE_L3S, + IPVLAN_MODE_MAX +}; + +#define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 + +/* VXLAN section */ +enum { + IFLA_VXLAN_UNSPEC, + IFLA_VXLAN_ID, + IFLA_VXLAN_GROUP, /* group or remote address */ + IFLA_VXLAN_LINK, + IFLA_VXLAN_LOCAL, + IFLA_VXLAN_TTL, + IFLA_VXLAN_TOS, + IFLA_VXLAN_LEARNING, + IFLA_VXLAN_AGEING, + IFLA_VXLAN_LIMIT, + IFLA_VXLAN_PORT_RANGE, /* source port */ + IFLA_VXLAN_PROXY, + IFLA_VXLAN_RSC, + IFLA_VXLAN_L2MISS, + IFLA_VXLAN_L3MISS, + IFLA_VXLAN_PORT, /* destination port */ + IFLA_VXLAN_GROUP6, + IFLA_VXLAN_LOCAL6, + IFLA_VXLAN_UDP_CSUM, + IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + IFLA_VXLAN_REMCSUM_TX, + IFLA_VXLAN_REMCSUM_RX, + IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, + IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, + IFLA_VXLAN_GPE, + __IFLA_VXLAN_MAX +}; +#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) + +struct ifla_vxlan_port_range { + __be16 low; + __be16 high; +}; + +/* GENEVE section */ +enum { + IFLA_GENEVE_UNSPEC, + IFLA_GENEVE_ID, + IFLA_GENEVE_REMOTE, + IFLA_GENEVE_TTL, + IFLA_GENEVE_TOS, + IFLA_GENEVE_PORT, /* destination port */ + IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, + IFLA_GENEVE_UDP_CSUM, + IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + IFLA_GENEVE_LABEL, + __IFLA_GENEVE_MAX +}; +#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) + +/* PPP section */ +enum { + IFLA_PPP_UNSPEC, + IFLA_PPP_DEV_FD, + __IFLA_PPP_MAX +}; +#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1) + +/* GTP section */ + +enum ifla_gtp_role { + GTP_ROLE_GGSN = 0, + GTP_ROLE_SGSN, +}; + +enum { + IFLA_GTP_UNSPEC, + IFLA_GTP_FD0, + IFLA_GTP_FD1, + IFLA_GTP_PDP_HASHSIZE, + IFLA_GTP_ROLE, + __IFLA_GTP_MAX, +}; +#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) + +/* Bonding section */ + +enum { + IFLA_BOND_UNSPEC, + IFLA_BOND_MODE, + IFLA_BOND_ACTIVE_SLAVE, + IFLA_BOND_MIIMON, + IFLA_BOND_UPDELAY, + IFLA_BOND_DOWNDELAY, + IFLA_BOND_USE_CARRIER, + IFLA_BOND_ARP_INTERVAL, + IFLA_BOND_ARP_IP_TARGET, + IFLA_BOND_ARP_VALIDATE, + IFLA_BOND_ARP_ALL_TARGETS, + IFLA_BOND_PRIMARY, + IFLA_BOND_PRIMARY_RESELECT, + IFLA_BOND_FAIL_OVER_MAC, + IFLA_BOND_XMIT_HASH_POLICY, + IFLA_BOND_RESEND_IGMP, + IFLA_BOND_NUM_PEER_NOTIF, + IFLA_BOND_ALL_SLAVES_ACTIVE, + IFLA_BOND_MIN_LINKS, + IFLA_BOND_LP_INTERVAL, + IFLA_BOND_PACKETS_PER_SLAVE, + IFLA_BOND_AD_LACP_RATE, + IFLA_BOND_AD_SELECT, + IFLA_BOND_AD_INFO, + IFLA_BOND_AD_ACTOR_SYS_PRIO, + IFLA_BOND_AD_USER_PORT_KEY, + IFLA_BOND_AD_ACTOR_SYSTEM, + IFLA_BOND_TLB_DYNAMIC_LB, + __IFLA_BOND_MAX, +}; + +#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1) + +enum { + IFLA_BOND_AD_INFO_UNSPEC, + IFLA_BOND_AD_INFO_AGGREGATOR, + IFLA_BOND_AD_INFO_NUM_PORTS, + IFLA_BOND_AD_INFO_ACTOR_KEY, + IFLA_BOND_AD_INFO_PARTNER_KEY, + IFLA_BOND_AD_INFO_PARTNER_MAC, + __IFLA_BOND_AD_INFO_MAX, +}; + +#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1) + +enum { + IFLA_BOND_SLAVE_UNSPEC, + IFLA_BOND_SLAVE_STATE, + IFLA_BOND_SLAVE_MII_STATUS, + IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, + IFLA_BOND_SLAVE_PERM_HWADDR, + IFLA_BOND_SLAVE_QUEUE_ID, + IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, + IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, + IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + __IFLA_BOND_SLAVE_MAX, +}; + +#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1) + +/* SR-IOV virtual function management section */ + +enum { + IFLA_VF_INFO_UNSPEC, + IFLA_VF_INFO, + __IFLA_VF_INFO_MAX, +}; + +#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1) + +enum { + IFLA_VF_UNSPEC, + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, /* VLAN ID and QoS */ + IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ + IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ + IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ + IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */ + IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query + * on/off switch + */ + IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ + IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ + IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + __IFLA_VF_MAX, +}; + +#define IFLA_VF_MAX (__IFLA_VF_MAX - 1) + +struct ifla_vf_mac { + __u32 vf; + __u8 mac[32]; /* MAX_ADDR_LEN */ +}; + +struct ifla_vf_vlan { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; +}; + +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + +struct ifla_vf_tx_rate { + __u32 vf; + __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ +}; + +struct ifla_vf_rate { + __u32 vf; + __u32 min_tx_rate; /* Min Bandwidth in Mbps */ + __u32 max_tx_rate; /* Max Bandwidth in Mbps */ +}; + +struct ifla_vf_spoofchk { + __u32 vf; + __u32 setting; +}; + +struct ifla_vf_guid { + __u32 vf; + __u64 guid; +}; + +enum { + IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ + IFLA_VF_LINK_STATE_ENABLE, /* link always up */ + IFLA_VF_LINK_STATE_DISABLE, /* link always down */ + __IFLA_VF_LINK_STATE_MAX, +}; + +struct ifla_vf_link_state { + __u32 vf; + __u32 link_state; +}; + +struct ifla_vf_rss_query_en { + __u32 vf; + __u32 setting; +}; + +enum { + IFLA_VF_STATS_RX_PACKETS, + IFLA_VF_STATS_TX_PACKETS, + IFLA_VF_STATS_RX_BYTES, + IFLA_VF_STATS_TX_BYTES, + IFLA_VF_STATS_BROADCAST, + IFLA_VF_STATS_MULTICAST, + IFLA_VF_STATS_PAD, + IFLA_VF_STATS_RX_DROPPED, + IFLA_VF_STATS_TX_DROPPED, + __IFLA_VF_STATS_MAX, +}; + +#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) + +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + +/* VF ports management section + * + * Nested layout of set/get msg is: + * + * [IFLA_NUM_VF] + * [IFLA_VF_PORTS] + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * ... + * [IFLA_PORT_SELF] + * [IFLA_PORT_*], ... + */ + +enum { + IFLA_VF_PORT_UNSPEC, + IFLA_VF_PORT, /* nest */ + __IFLA_VF_PORT_MAX, +}; + +#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1) + +enum { + IFLA_PORT_UNSPEC, + IFLA_PORT_VF, /* __u32 */ + IFLA_PORT_PROFILE, /* string */ + IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */ + IFLA_PORT_INSTANCE_UUID, /* binary UUID */ + IFLA_PORT_HOST_UUID, /* binary UUID */ + IFLA_PORT_REQUEST, /* __u8 */ + IFLA_PORT_RESPONSE, /* __u16, output only */ + __IFLA_PORT_MAX, +}; + +#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1) + +#define PORT_PROFILE_MAX 40 +#define PORT_UUID_MAX 16 +#define PORT_SELF_VF -1 + +enum { + PORT_REQUEST_PREASSOCIATE = 0, + PORT_REQUEST_PREASSOCIATE_RR, + PORT_REQUEST_ASSOCIATE, + PORT_REQUEST_DISASSOCIATE, +}; + +enum { + PORT_VDP_RESPONSE_SUCCESS = 0, + PORT_VDP_RESPONSE_INVALID_FORMAT, + PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_VDP_RESPONSE_UNUSED_VTID, + PORT_VDP_RESPONSE_VTID_VIOLATION, + PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION, + PORT_VDP_RESPONSE_OUT_OF_SYNC, + /* 0x08-0xFF reserved for future VDP use */ + PORT_PROFILE_RESPONSE_SUCCESS = 0x100, + PORT_PROFILE_RESPONSE_INPROGRESS, + PORT_PROFILE_RESPONSE_INVALID, + PORT_PROFILE_RESPONSE_BADSTATE, + PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_PROFILE_RESPONSE_ERROR, +}; + +struct ifla_port_vsi { + __u8 vsi_mgr_id; + __u8 vsi_type_id[3]; + __u8 vsi_type_version; + __u8 pad[3]; +}; + + +/* IPoIB section */ + +enum { + IFLA_IPOIB_UNSPEC, + IFLA_IPOIB_PKEY, + IFLA_IPOIB_MODE, + IFLA_IPOIB_UMCAST, + __IFLA_IPOIB_MAX +}; + +enum { + IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */ + IPOIB_MODE_CONNECTED = 1, /* using connected QPs */ +}; + +#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) + + +/* HSR section */ + +enum { + IFLA_HSR_UNSPEC, + IFLA_HSR_SLAVE1, + IFLA_HSR_SLAVE2, + IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */ + IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ + IFLA_HSR_SEQ_NR, + IFLA_HSR_VERSION, /* HSR version */ + __IFLA_HSR_MAX, +}; + +#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1) + +/* STATS section */ + +struct if_stats_msg { + __u8 family; + __u8 pad1; + __u16 pad2; + __u32 ifindex; + __u32 filter_mask; +}; + +/* A stats attribute can be netdev specific or a global stat. + * For netdev stats, lets use the prefix IFLA_STATS_LINK_* + */ +enum { + IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */ + IFLA_STATS_LINK_64, + IFLA_STATS_LINK_XSTATS, + IFLA_STATS_LINK_XSTATS_SLAVE, + IFLA_STATS_LINK_OFFLOAD_XSTATS, + IFLA_STATS_AF_SPEC, + __IFLA_STATS_MAX, +}; + +#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1) + +#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) + +/* These are embedded into IFLA_STATS_LINK_XSTATS: + * [IFLA_STATS_LINK_XSTATS] + * -> [LINK_XSTATS_TYPE_xxx] + * -> [rtnl link type specific attributes] + */ +enum { + LINK_XSTATS_TYPE_UNSPEC, + LINK_XSTATS_TYPE_BRIDGE, + __LINK_XSTATS_TYPE_MAX +}; +#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) + +/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */ +enum { + IFLA_OFFLOAD_XSTATS_UNSPEC, + IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + __IFLA_OFFLOAD_XSTATS_MAX +}; +#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) + +/* XDP section */ + +#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) +#define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE | \ + XDP_FLAGS_HW_MODE) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ + XDP_FLAGS_MODES) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, + XDP_ATTACHED_HW, +}; + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + IFLA_XDP_FLAGS, + IFLA_XDP_PROG_ID, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + +enum { + IFLA_EVENT_NONE, + IFLA_EVENT_REBOOT, /* internal reset / reboot */ + IFLA_EVENT_FEATURES, /* change in offload features */ + IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */ + IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */ + IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */ + IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ +}; + +#endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 496e59a2738b..8fb90a0819c3 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -932,6 +932,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_HYPERV_SYNIC2 148 #define KVM_CAP_HYPERV_VP_INDEX 149 #define KVM_CAP_S390_AIS_MIGRATION 150 +#define KVM_CAP_PPC_GET_CPU_CHAR 151 +#define KVM_CAP_S390_BPB 152 #ifdef KVM_CAP_IRQ_ROUTING @@ -1261,6 +1263,8 @@ struct kvm_s390_ucas_mapping { #define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) /* Available with KVM_CAP_PPC_RADIX_MMU */ #define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) +/* Available with KVM_CAP_PPC_GET_CPU_CHAR */ +#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h new file mode 100644 index 000000000000..776bc92e9118 --- /dev/null +++ b/tools/include/uapi/linux/netlink.h @@ -0,0 +1,251 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETLINK_H +#define _UAPI__LINUX_NETLINK_H + +#include <linux/kernel.h> +#include <linux/socket.h> /* for __kernel_sa_family_t */ +#include <linux/types.h> + +#define NETLINK_ROUTE 0 /* Routing/device hook */ +#define NETLINK_UNUSED 1 /* Unused number */ +#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ +#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */ +#define NETLINK_SOCK_DIAG 4 /* socket monitoring */ +#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ +#define NETLINK_XFRM 6 /* ipsec */ +#define NETLINK_SELINUX 7 /* SELinux event notifications */ +#define NETLINK_ISCSI 8 /* Open-iSCSI */ +#define NETLINK_AUDIT 9 /* auditing */ +#define NETLINK_FIB_LOOKUP 10 +#define NETLINK_CONNECTOR 11 +#define NETLINK_NETFILTER 12 /* netfilter subsystem */ +#define NETLINK_IP6_FW 13 +#define NETLINK_DNRTMSG 14 /* DECnet routing messages */ +#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */ +#define NETLINK_GENERIC 16 +/* leave room for NETLINK_DM (DM Events) */ +#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */ +#define NETLINK_ECRYPTFS 19 +#define NETLINK_RDMA 20 +#define NETLINK_CRYPTO 21 /* Crypto layer */ +#define NETLINK_SMC 22 /* SMC monitoring */ + +#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG + +#define MAX_LINKS 32 + +struct sockaddr_nl { + __kernel_sa_family_t nl_family; /* AF_NETLINK */ + unsigned short nl_pad; /* zero */ + __u32 nl_pid; /* port ID */ + __u32 nl_groups; /* multicast groups mask */ +}; + +struct nlmsghdr { + __u32 nlmsg_len; /* Length of message including header */ + __u16 nlmsg_type; /* Message content */ + __u16 nlmsg_flags; /* Additional flags */ + __u32 nlmsg_seq; /* Sequence number */ + __u32 nlmsg_pid; /* Sending process port ID */ +}; + +/* Flags values */ + +#define NLM_F_REQUEST 0x01 /* It is request message. */ +#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */ +#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */ +#define NLM_F_ECHO 0x08 /* Echo this request */ +#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */ + +/* Modifiers to GET request */ +#define NLM_F_ROOT 0x100 /* specify tree root */ +#define NLM_F_MATCH 0x200 /* return all matching */ +#define NLM_F_ATOMIC 0x400 /* atomic GET */ +#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH) + +/* Modifiers to NEW request */ +#define NLM_F_REPLACE 0x100 /* Override existing */ +#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */ +#define NLM_F_CREATE 0x400 /* Create, if it does not exist */ +#define NLM_F_APPEND 0x800 /* Add to end of list */ + +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + +/* Flags for ACK message */ +#define NLM_F_CAPPED 0x100 /* request was capped */ +#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ + +/* + 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL + 4.4BSD CHANGE NLM_F_REPLACE + + True CHANGE NLM_F_CREATE|NLM_F_REPLACE + Append NLM_F_CREATE + Check NLM_F_EXCL + */ + +#define NLMSG_ALIGNTO 4U +#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) +#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) +#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) +#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) +#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) +#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ + (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len))) +#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len <= (len)) +#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len))) + +#define NLMSG_NOOP 0x1 /* Nothing. */ +#define NLMSG_ERROR 0x2 /* Error */ +#define NLMSG_DONE 0x3 /* End of a dump */ +#define NLMSG_OVERRUN 0x4 /* Data lost */ + +#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */ + +struct nlmsgerr { + int error; + struct nlmsghdr msg; + /* + * followed by the message contents unless NETLINK_CAP_ACK was set + * or the ACK indicates success (error == 0) + * message length is aligned with NLMSG_ALIGN() + */ + /* + * followed by TLVs defined in enum nlmsgerr_attrs + * if NETLINK_EXT_ACK was set + */ +}; + +/** + * enum nlmsgerr_attrs - nlmsgerr attributes + * @NLMSGERR_ATTR_UNUSED: unused + * @NLMSGERR_ATTR_MSG: error message string (string) + * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original + * message, counting from the beginning of the header (u32) + * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to + * be used - in the success case - to identify a created + * object or operation or similar (binary) + * @__NLMSGERR_ATTR_MAX: number of attributes + * @NLMSGERR_ATTR_MAX: highest attribute number + */ +enum nlmsgerr_attrs { + NLMSGERR_ATTR_UNUSED, + NLMSGERR_ATTR_MSG, + NLMSGERR_ATTR_OFFS, + NLMSGERR_ATTR_COOKIE, + + __NLMSGERR_ATTR_MAX, + NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1 +}; + +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 +#define NETLINK_BROADCAST_ERROR 4 +#define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ +#define NETLINK_RX_RING 6 +#define NETLINK_TX_RING 7 +#endif +#define NETLINK_LISTEN_ALL_NSID 8 +#define NETLINK_LIST_MEMBERSHIPS 9 +#define NETLINK_CAP_ACK 10 +#define NETLINK_EXT_ACK 11 + +struct nl_pktinfo { + __u32 group; +}; + +struct nl_mmap_req { + unsigned int nm_block_size; + unsigned int nm_block_nr; + unsigned int nm_frame_size; + unsigned int nm_frame_nr; +}; + +struct nl_mmap_hdr { + unsigned int nm_status; + unsigned int nm_len; + __u32 nm_group; + /* credentials */ + __u32 nm_pid; + __u32 nm_uid; + __u32 nm_gid; +}; + +#ifndef __KERNEL__ +enum nl_mmap_status { + NL_MMAP_STATUS_UNUSED, + NL_MMAP_STATUS_RESERVED, + NL_MMAP_STATUS_VALID, + NL_MMAP_STATUS_COPY, + NL_MMAP_STATUS_SKIP, +}; + +#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO +#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) +#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif + +#define NET_MAJOR 36 /* Major 36 is reserved for networking */ + +enum { + NETLINK_UNCONNECTED = 0, + NETLINK_CONNECTED, +}; + +/* + * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)--> + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * | Header | Pad | Payload | Pad | + * | (struct nlattr) | ing | | ing | + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * <-------------- nlattr->nla_len --------------> + */ + +struct nlattr { + __u16 nla_len; + __u16 nla_type; +}; + +/* + * nla_type (16 bits) + * +---+---+-------------------------------+ + * | N | O | Attribute Type | + * +---+---+-------------------------------+ + * N := Carries nested attributes + * O := Payload stored in network byte order + * + * Note: The N and O flag are mutually exclusive. + */ +#define NLA_F_NESTED (1 << 15) +#define NLA_F_NET_BYTEORDER (1 << 14) +#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER) + +#define NLA_ALIGNTO 4 +#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) +#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) + +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; + +#endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h index 30a9e51bbb1e..22627f80063e 100644 --- a/tools/include/uapi/linux/sched.h +++ b/tools/include/uapi/linux/sched.h @@ -49,5 +49,10 @@ */ #define SCHED_FLAG_RESET_ON_FORK 0x01 #define SCHED_FLAG_RECLAIM 0x02 +#define SCHED_FLAG_DL_OVERRUN 0x04 + +#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \ + SCHED_FLAG_RECLAIM | \ + SCHED_FLAG_DL_OVERRUN) #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index c227ccba60ae..07d61583fd02 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -214,6 +214,11 @@ typedef int __bitwise snd_pcm_format_t; #define SNDRV_PCM_FORMAT_IMA_ADPCM ((__force snd_pcm_format_t) 22) #define SNDRV_PCM_FORMAT_MPEG ((__force snd_pcm_format_t) 23) #define SNDRV_PCM_FORMAT_GSM ((__force snd_pcm_format_t) 24) +#define SNDRV_PCM_FORMAT_S20_LE ((__force snd_pcm_format_t) 25) /* in four bytes, LSB justified */ +#define SNDRV_PCM_FORMAT_S20_BE ((__force snd_pcm_format_t) 26) /* in four bytes, LSB justified */ +#define SNDRV_PCM_FORMAT_U20_LE ((__force snd_pcm_format_t) 27) /* in four bytes, LSB justified */ +#define SNDRV_PCM_FORMAT_U20_BE ((__force snd_pcm_format_t) 28) /* in four bytes, LSB justified */ +/* gap in the numbering for a future standard linear format */ #define SNDRV_PCM_FORMAT_SPECIAL ((__force snd_pcm_format_t) 31) #define SNDRV_PCM_FORMAT_S24_3LE ((__force snd_pcm_format_t) 32) /* in three bytes */ #define SNDRV_PCM_FORMAT_S24_3BE ((__force snd_pcm_format_t) 33) /* in three bytes */ @@ -248,6 +253,8 @@ typedef int __bitwise snd_pcm_format_t; #define SNDRV_PCM_FORMAT_FLOAT SNDRV_PCM_FORMAT_FLOAT_LE #define SNDRV_PCM_FORMAT_FLOAT64 SNDRV_PCM_FORMAT_FLOAT64_LE #define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_LE +#define SNDRV_PCM_FORMAT_S20 SNDRV_PCM_FORMAT_S20_LE +#define SNDRV_PCM_FORMAT_U20 SNDRV_PCM_FORMAT_U20_LE #endif #ifdef SNDRV_BIG_ENDIAN #define SNDRV_PCM_FORMAT_S16 SNDRV_PCM_FORMAT_S16_BE @@ -259,6 +266,8 @@ typedef int __bitwise snd_pcm_format_t; #define SNDRV_PCM_FORMAT_FLOAT SNDRV_PCM_FORMAT_FLOAT_BE #define SNDRV_PCM_FORMAT_FLOAT64 SNDRV_PCM_FORMAT_FLOAT64_BE #define SNDRV_PCM_FORMAT_IEC958_SUBFRAME SNDRV_PCM_FORMAT_IEC958_SUBFRAME_BE +#define SNDRV_PCM_FORMAT_S20 SNDRV_PCM_FORMAT_S20_BE +#define SNDRV_PCM_FORMAT_U20 SNDRV_PCM_FORMAT_U20_BE #endif typedef int __bitwise snd_pcm_subformat_t; diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index d8749756352d..64c679d67109 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o +libbpf-y := libbpf.o bpf.o nlattr.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 83714ca1f22b..e6d5f8d1477f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -160,6 +160,12 @@ $(BPF_IN): force elfdep bpfdep @(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true + @(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \ + (diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true + @(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \ + (diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf $(OUTPUT)libbpf.so: $(BPF_IN) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 5128677e4117..592a58a2b681 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: LGPL-2.1 + /* * common eBPF ELF operations. * @@ -25,6 +27,16 @@ #include <asm/unistd.h> #include <linux/bpf.h> #include "bpf.h" +#include "libbpf.h" +#include "nlattr.h" +#include <linux/rtnetlink.h> +#include <linux/if_link.h> +#include <sys/socket.h> +#include <errno.h> + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif /* * When building perf, unistd.h is overridden. __NR_bpf is @@ -46,7 +58,9 @@ # endif #endif +#ifndef min #define min(x, y) ((x) < (y) ? (x) : (y)) +#endif static inline __u64 ptr_to_u64(const void *ptr) { @@ -413,3 +427,124 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) return err; } + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +{ + struct sockaddr_nl sa; + int sock, seq = 0, len, ret = -1; + char buf[4096]; + struct nlattr *nla, *nla_xdp; + struct { + struct nlmsghdr nh; + struct ifinfomsg ifinfo; + char attrbuf[64]; + } req; + struct nlmsghdr *nh; + struct nlmsgerr *err; + socklen_t addrlen; + int one = 1; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) { + return -errno; + } + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + fprintf(stderr, "Netlink error reporting not supported\n"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.nh.nlmsg_pid = 0; + req.nh.nlmsg_seq = ++seq; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + + /* started nested attribute for XDP */ + nla = (struct nlattr *)(((char *)&req) + + NLMSG_ALIGN(req.nh.nlmsg_len)); + nla->nla_type = NLA_F_NESTED | IFLA_XDP; + nla->nla_len = NLA_HDRLEN; + + /* add XDP fd */ + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FD; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); + memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); + nla->nla_len += nla_xdp->nla_len; + + /* if user passed in any flags, add those too */ + if (flags) { + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FLAGS; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); + memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); + nla->nla_len += nla_xdp->nla_len; + } + + req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); + + if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { + ret = -errno; + goto cleanup; + } + + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto cleanup; + } + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != sa.nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto cleanup; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto cleanup; + } + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + nla_dump_errormsg(nh); + goto cleanup; + case NLMSG_DONE: + break; + default: + break; + } + } + + ret = 0; + +cleanup: + close(sock); + return ret; +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 9f44c196931e..8d18fb73d7fb 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ + /* * common eBPF ELF operations. * diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 30c776375118..97073d649c1a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: LGPL-2.1 + /* * Common eBPF ELF object loading operations. * @@ -106,6 +108,8 @@ static const char *libbpf_strerror_table[NR_ERRNO] = { [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", + [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", + [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", }; int libbpf_strerror(int err, char *buf, size_t size) @@ -315,8 +319,8 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, prog->section_name = strdup(section_name); if (!prog->section_name) { - pr_warning("failed to alloc name for prog under section %s\n", - section_name); + pr_warning("failed to alloc name for prog under section(%d) %s\n", + idx, section_name); goto errout; } @@ -738,6 +742,24 @@ bpf_object__init_maps(struct bpf_object *obj) return 0; } +static bool section_have_execinstr(struct bpf_object *obj, int idx) +{ + Elf_Scn *scn; + GElf_Shdr sh; + + scn = elf_getscn(obj->efile.elf, idx); + if (!scn) + return false; + + if (gelf_getshdr(scn, &sh) != &sh) + return false; + + if (sh.sh_flags & SHF_EXECINSTR) + return true; + + return false; +} + static int bpf_object__elf_collect(struct bpf_object *obj) { Elf *elf = obj->efile.elf; @@ -759,29 +781,29 @@ static int bpf_object__elf_collect(struct bpf_object *obj) idx++; if (gelf_getshdr(scn, &sh) != &sh) { - pr_warning("failed to get section header from %s\n", - obj->path); + pr_warning("failed to get section(%d) header from %s\n", + idx, obj->path); err = -LIBBPF_ERRNO__FORMAT; goto out; } name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); if (!name) { - pr_warning("failed to get section name from %s\n", - obj->path); + pr_warning("failed to get section(%d) name from %s\n", + idx, obj->path); err = -LIBBPF_ERRNO__FORMAT; goto out; } data = elf_getdata(scn, 0); if (!data) { - pr_warning("failed to get section data from %s(%s)\n", - name, obj->path); + pr_warning("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); err = -LIBBPF_ERRNO__FORMAT; goto out; } - pr_debug("section %s, size %ld, link %d, flags %lx, type=%d\n", - name, (unsigned long)data->d_size, + pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", + idx, name, (unsigned long)data->d_size, (int)sh.sh_link, (unsigned long)sh.sh_flags, (int)sh.sh_type); @@ -821,6 +843,14 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if (sh.sh_type == SHT_REL) { void *reloc = obj->efile.reloc; int nr_reloc = obj->efile.nr_reloc + 1; + int sec = sh.sh_info; /* points to other section */ + + /* Only do relo for section with exec instructions */ + if (!section_have_execinstr(obj, sec)) { + pr_debug("skip relo %s(%d) for section(%d)\n", + name, idx, sec); + continue; + } reloc = realloc(reloc, sizeof(*obj->efile.reloc) * nr_reloc); @@ -836,6 +866,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) obj->efile.reloc[n].shdr = sh; obj->efile.reloc[n].data = data; } + } else { + pr_debug("skip section(%d) %s\n", idx, name); } if (err) goto out; @@ -1115,8 +1147,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) prog = bpf_object__find_prog_by_idx(obj, idx); if (!prog) { - pr_warning("relocation failed: no %d section\n", - idx); + pr_warning("relocation failed: no section(%d)\n", idx); return -LIBBPF_ERRNO__RELOC; } @@ -1812,12 +1843,17 @@ static const struct { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), + BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), BPF_PROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK), BPF_PROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE), + BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), + BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), + BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT), BPF_PROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS), BPF_PROG_SEC("sk_skb", BPF_PROG_TYPE_SK_SKB), }; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 6e20003109e0..f85906533cdd 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ + /* * Common eBPF ELF object loading operations. * @@ -42,6 +44,8 @@ enum libbpf_errno { LIBBPF_ERRNO__PROG2BIG, /* Program too big */ LIBBPF_ERRNO__KVER, /* Incorrect kernel version */ LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */ + LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */ + LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */ __LIBBPF_ERRNO__END, }; @@ -246,4 +250,6 @@ long libbpf_get_error(const void *ptr); int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); #endif diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c new file mode 100644 index 000000000000..4719434278b2 --- /dev/null +++ b/tools/lib/bpf/nlattr.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: LGPL-2.1 + +/* + * NETLINK Netlink attributes + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation version 2.1 + * of the License. + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#include <errno.h> +#include "nlattr.h" +#include <linux/rtnetlink.h> +#include <string.h> +#include <stdio.h> + +static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = { + [NLA_U8] = sizeof(uint8_t), + [NLA_U16] = sizeof(uint16_t), + [NLA_U32] = sizeof(uint32_t), + [NLA_U64] = sizeof(uint64_t), + [NLA_STRING] = 1, + [NLA_FLAG] = 0, +}; + +static int nla_len(const struct nlattr *nla) +{ + return nla->nla_len - NLA_HDRLEN; +} + +static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) +{ + int totlen = NLA_ALIGN(nla->nla_len); + + *remaining -= totlen; + return (struct nlattr *) ((char *) nla + totlen); +} + +static int nla_ok(const struct nlattr *nla, int remaining) +{ + return remaining >= sizeof(*nla) && + nla->nla_len >= sizeof(*nla) && + nla->nla_len <= remaining; +} + +static void *nla_data(const struct nlattr *nla) +{ + return (char *) nla + NLA_HDRLEN; +} + +static int nla_type(const struct nlattr *nla) +{ + return nla->nla_type & NLA_TYPE_MASK; +} + +static int validate_nla(struct nlattr *nla, int maxtype, + struct nla_policy *policy) +{ + struct nla_policy *pt; + unsigned int minlen = 0; + int type = nla_type(nla); + + if (type < 0 || type > maxtype) + return 0; + + pt = &policy[type]; + + if (pt->type > NLA_TYPE_MAX) + return 0; + + if (pt->minlen) + minlen = pt->minlen; + else if (pt->type != NLA_UNSPEC) + minlen = nla_attr_minlen[pt->type]; + + if (nla_len(nla) < minlen) + return -1; + + if (pt->maxlen && nla_len(nla) > pt->maxlen) + return -1; + + if (pt->type == NLA_STRING) { + char *data = nla_data(nla); + if (data[nla_len(nla) - 1] != '\0') + return -1; + } + + return 0; +} + +static inline int nlmsg_len(const struct nlmsghdr *nlh) +{ + return nlh->nlmsg_len - NLMSG_HDRLEN; +} + +/** + * Create attribute index based on a stream of attributes. + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg head Head of attribute stream. + * @arg len Length of attribute stream. + * @arg policy Attribute validation policy. + * + * Iterates over the stream of attributes and stores a pointer to each + * attribute in the index array using the attribute type as index to + * the array. Attribute with a type greater than the maximum type + * specified will be silently ignored in order to maintain backwards + * compatibility. If \a policy is not NULL, the attribute will be + * validated using the specified policy. + * + * @see nla_validate + * @return 0 on success or a negative error code. + */ +static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, + struct nla_policy *policy) +{ + struct nlattr *nla; + int rem, err; + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + + nla_for_each_attr(nla, head, len, rem) { + int type = nla_type(nla); + + if (type > maxtype) + continue; + + if (policy) { + err = validate_nla(nla, maxtype, policy); + if (err < 0) + goto errout; + } + + if (tb[type]) + fprintf(stderr, "Attribute of type %#x found multiple times in message, " + "previous attribute is being ignored.\n", type); + + tb[type] = nla; + } + + err = 0; +errout: + return err; +} + +/* dump netlink extended ack error message */ +int nla_dump_errormsg(struct nlmsghdr *nlh) +{ + struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = { + [NLMSGERR_ATTR_MSG] = { .type = NLA_STRING }, + [NLMSGERR_ATTR_OFFS] = { .type = NLA_U32 }, + }; + struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr; + struct nlmsgerr *err; + char *errmsg = NULL; + int hlen, alen; + + /* no TLVs, nothing to do here */ + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 0; + + err = (struct nlmsgerr *)NLMSG_DATA(nlh); + hlen = sizeof(*err); + + /* if NLM_F_CAPPED is set then the inner err msg was capped */ + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += nlmsg_len(&err->msg); + + attr = (struct nlattr *) ((void *) err + hlen); + alen = nlh->nlmsg_len - hlen; + + if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { + fprintf(stderr, + "Failed to parse extended error attributes\n"); + return 0; + } + + if (tb[NLMSGERR_ATTR_MSG]) + errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]); + + fprintf(stderr, "Kernel error message: %s\n", errmsg); + + return 0; +} diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h new file mode 100644 index 000000000000..931a71f68f93 --- /dev/null +++ b/tools/lib/bpf/nlattr.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ + +/* + * NETLINK Netlink attributes + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation version 2.1 + * of the License. + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#ifndef __NLATTR_H +#define __NLATTR_H + +#include <stdint.h> +#include <linux/netlink.h> +/* avoid multiple definition of netlink features */ +#define __LINUX_NETLINK_H + +/** + * Standard attribute types to specify validation policy + */ +enum { + NLA_UNSPEC, /**< Unspecified type, binary data chunk */ + NLA_U8, /**< 8 bit integer */ + NLA_U16, /**< 16 bit integer */ + NLA_U32, /**< 32 bit integer */ + NLA_U64, /**< 64 bit integer */ + NLA_STRING, /**< NUL terminated character string */ + NLA_FLAG, /**< Flag */ + NLA_MSECS, /**< Micro seconds (64bit) */ + NLA_NESTED, /**< Nested attributes */ + __NLA_TYPE_MAX, +}; + +#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) + +/** + * @ingroup attr + * Attribute validation policy. + * + * See section @core_doc{core_attr_parse,Attribute Parsing} for more details. + */ +struct nla_policy { + /** Type of attribute or NLA_UNSPEC */ + uint16_t type; + + /** Minimal length of payload required */ + uint16_t minlen; + + /** Maximal length of payload allowed */ + uint16_t maxlen; +}; + +/** + * @ingroup attr + * Iterate over a stream of attributes + * @arg pos loop counter, set to current attribute + * @arg head head of attribute stream + * @arg len length of attribute stream + * @arg rem initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_attr(pos, head, len, rem) \ + for (pos = head, rem = len; \ + nla_ok(pos, rem); \ + pos = nla_next(pos, &(rem))) + +int nla_dump_errormsg(struct nlmsghdr *nlh); + +#endif /* __NLATTR_H */ diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index 42c15f906aac..a88bd507091e 100644 --- a/tools/lib/find_bit.c +++ b/tools/lib/find_bit.c @@ -22,22 +22,29 @@ #include <linux/bitmap.h> #include <linux/kernel.h> -#if !defined(find_next_bit) +#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ + !defined(find_next_and_bit) /* - * This is a common helper function for find_next_bit and - * find_next_zero_bit. The difference is the "invert" argument, which - * is XORed with each fetched word before searching it for one bits. + * This is a common helper function for find_next_bit, find_next_zero_bit, and + * find_next_and_bit. The differences are: + * - The "invert" argument, which is XORed with each fetched word before + * searching it for one bits. + * - The optional "addr2", which is anded with "addr1" if present. */ -static unsigned long _find_next_bit(const unsigned long *addr, - unsigned long nbits, unsigned long start, unsigned long invert) +static inline unsigned long _find_next_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; /* Handle 1st word. */ tmp &= BITMAP_FIRST_WORD_MASK(start); @@ -48,7 +55,10 @@ static unsigned long _find_next_bit(const unsigned long *addr, if (start >= nbits) return nbits; - tmp = addr[start / BITS_PER_LONG] ^ invert; + tmp = addr1[start / BITS_PER_LONG]; + if (addr2) + tmp &= addr2[start / BITS_PER_LONG]; + tmp ^= invert; } return min(start + __ffs(tmp), nbits); @@ -62,7 +72,7 @@ static unsigned long _find_next_bit(const unsigned long *addr, unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, 0UL); + return _find_next_bit(addr, NULL, size, offset, 0UL); } #endif @@ -104,6 +114,15 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - return _find_next_bit(addr, size, offset, ~0UL); + return _find_next_bit(addr, NULL, size, offset, ~0UL); +} +#endif + +#ifndef find_next_and_bit +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + return _find_next_bit(addr1, addr2, size, offset, 0UL); } #endif diff --git a/tools/lib/subcmd/pager.c b/tools/lib/subcmd/pager.c index 5ba754d17952..9997a8805a82 100644 --- a/tools/lib/subcmd/pager.c +++ b/tools/lib/subcmd/pager.c @@ -30,10 +30,13 @@ static void pager_preexec(void) * have real input */ fd_set in; + fd_set exception; FD_ZERO(&in); + FD_ZERO(&exception); FD_SET(0, &in); - select(1, &in, NULL, &in, NULL); + FD_SET(0, &exception); + select(1, &in, NULL, &exception, NULL); setenv("LESS", "FRSX", 0); } diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore index 643cc4ba6872..3e5135dded16 100644 --- a/tools/perf/.gitignore +++ b/tools/perf/.gitignore @@ -31,5 +31,6 @@ config.mak.autogen .config-detected util/intel-pt-decoder/inat-tables.c arch/*/include/generated/ +trace/beauty/generated/ pmu-events/pmu-events.c pmu-events/jevents diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 65681a1a292a..bf4ca749d1ac 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1566,7 +1566,8 @@ static struct option __record_options[] = { OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time, &record.opts.sample_time_set, "Record the sample timestamps"), - OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"), + OPT_BOOLEAN_SET('P', "period", &record.opts.period, &record.opts.period_set, + "Record the sample period"), OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples, "don't sample"), OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache, diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 17d11deeb88d..e7f1b182fc15 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1661,9 +1661,12 @@ static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evse struct callchain_cursor *cursor) { struct addr_location al; + int max_stack = evsel->attr.sample_max_stack ? + evsel->attr.sample_max_stack : + trace->max_stack; if (machine__resolve(trace->host, &al, sample) < 0 || - thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, evsel->attr.sample_max_stack)) + thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack)) return -1; return 0; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 2357f4ccc9c7..cfe46236a5e5 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -50,6 +50,7 @@ struct record_opts { bool sample_time_set; bool sample_cpu; bool period; + bool period_set; bool running_time; bool full_auxtrace; bool auxtrace_snapshot_mode; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 66fa45198a11..ff359c9ece2e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -745,12 +745,14 @@ static void apply_config_terms(struct perf_evsel *evsel, if (!(term->weak && opts->user_interval != ULLONG_MAX)) { attr->sample_period = term->val.period; attr->freq = 0; + perf_evsel__reset_sample_bit(evsel, PERIOD); } break; case PERF_EVSEL__CONFIG_TERM_FREQ: if (!(term->weak && opts->user_freq != UINT_MAX)) { attr->sample_freq = term->val.freq; attr->freq = 1; + perf_evsel__set_sample_bit(evsel, PERIOD); } break; case PERF_EVSEL__CONFIG_TERM_TIME: @@ -969,9 +971,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, if (target__has_cpu(&opts->target) || opts->sample_cpu) perf_evsel__set_sample_bit(evsel, CPU); - if (opts->period) - perf_evsel__set_sample_bit(evsel, PERIOD); - /* * When the user explicitly disabled time don't force it here. */ @@ -1073,6 +1072,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, apply_config_terms(evsel, opts, track); evsel->ignore_missing_thread = opts->ignore_missing_thread; + + /* The --period option takes the precedence. */ + if (opts->period_set) { + if (opts->period) + perf_evsel__set_sample_bit(evsel, PERIOD); + else + perf_evsel__reset_sample_bit(evsel, PERIOD); + } } static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c index 5b38dc2fec4f..dfa6fee1b915 100644 --- a/tools/power/acpi/common/cmfsize.c +++ b/tools/power/acpi/common/cmfsize.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c index 6e78413bb2cb..f7032c9ab35e 100644 --- a/tools/power/acpi/common/getopt.c +++ b/tools/power/acpi/common/getopt.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c index 52a39ecf5ca1..e7347edfd4f9 100644 --- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c +++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c index ea14eaeb268f..9b5e61b636d9 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixdir.c +++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c index cf9b5a54df92..8b26924e2602 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixmap.c +++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c index 025c1b07049d..34c044da433c 100644 --- a/tools/power/acpi/os_specific/service_layers/osunixxf.c +++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h index d6aa40fce2b1..3c679607d1c3 100644 --- a/tools/power/acpi/tools/acpidump/acpidump.h +++ b/tools/power/acpi/tools/acpidump/acpidump.h @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c index 0634449156d8..9ad1712e4cf9 100644 --- a/tools/power/acpi/tools/acpidump/apdump.c +++ b/tools/power/acpi/tools/acpidump/apdump.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c index d686e11936c4..856e1b83407b 100644 --- a/tools/power/acpi/tools/acpidump/apfiles.c +++ b/tools/power/acpi/tools/acpidump/apfiles.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c index be418fba9441..f4ef826800cf 100644 --- a/tools/power/acpi/tools/acpidump/apmain.c +++ b/tools/power/acpi/tools/acpidump/apmain.c @@ -5,7 +5,7 @@ *****************************************************************************/ /* - * Copyright (C) 2000 - 2017, Intel Corp. + * Copyright (C) 2000 - 2018, Intel Corp. * All rights reserved. * * Redistribution and use in source and binary forms, with or without diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 30cd0b296f1a..44ef9eba5a7a 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -153,11 +153,12 @@ void idr_nowait_test(void) idr_destroy(&idr); } -void idr_get_next_test(void) +void idr_get_next_test(int base) { unsigned long i; int nextid; DEFINE_IDR(idr); + idr_init_base(&idr, base); int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0}; @@ -207,6 +208,7 @@ void idr_checks(void) assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i); } assert(idr_alloc(&idr, DUMMY_PTR, i - 2, i, GFP_KERNEL) == -ENOSPC); + assert(idr_alloc(&idr, DUMMY_PTR, i - 2, i + 10, GFP_KERNEL) == -ENOSPC); idr_for_each(&idr, item_idr_free, &idr); idr_destroy(&idr); @@ -214,6 +216,23 @@ void idr_checks(void) assert(idr_is_empty(&idr)); + idr_set_cursor(&idr, INT_MAX - 3UL); + for (i = INT_MAX - 3UL; i < INT_MAX + 3UL; i++) { + struct item *item; + unsigned int id; + if (i <= INT_MAX) + item = item_create(i, 0); + else + item = item_create(i - INT_MAX - 1, 0); + + id = idr_alloc_cyclic(&idr, item, 0, 0, GFP_KERNEL); + assert(id == item->index); + } + + idr_for_each(&idr, item_idr_free, &idr); + idr_destroy(&idr); + assert(idr_is_empty(&idr)); + for (i = 1; i < 10000; i++) { struct item *item = item_create(i, 0); assert(idr_alloc(&idr, item, 1, 20000, GFP_KERNEL) == i); @@ -226,7 +245,9 @@ void idr_checks(void) idr_alloc_test(); idr_null_test(); idr_nowait_test(); - idr_get_next_test(); + idr_get_next_test(0); + idr_get_next_test(1); + idr_get_next_test(4); } /* @@ -380,7 +401,7 @@ void ida_check_random(void) do { ida_pre_get(&ida, GFP_KERNEL); err = ida_get_new_above(&ida, bit, &id); - } while (err == -ENOMEM); + } while (err == -EAGAIN); assert(!err); assert(id == bit); } @@ -489,7 +510,7 @@ static void *ida_random_fn(void *arg) void ida_thread_tests(void) { - pthread_t threads[10]; + pthread_t threads[20]; int i; for (i = 0; i < ARRAY_SIZE(threads); i++) diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h index c3bc3f364f68..426f32f28547 100644 --- a/tools/testing/radix-tree/linux/kernel.h +++ b/tools/testing/radix-tree/linux/kernel.h @@ -17,6 +17,4 @@ #define pr_debug printk #define pr_cont printk -#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) - #endif /* _KERNEL_H */ diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1e09d77f1948..cc15af2e54fe 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -8,5 +8,6 @@ fixdep test_align test_dev_cgroup test_progs +test_tcpbpf_user test_verifier_log feature diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index bf05bc5e36e5..5c43c187f27c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -13,6 +13,7 @@ endif CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include LDLIBS += -lcap -lelf -lrt -lpthread +# Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user @@ -22,15 +23,24 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ sample_map_ret0.o test_tcpbpf_kern.o -TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \ +# Order correspond to 'make run_tests' order +TEST_PROGS := test_kmod.sh \ + test_libbpf.sh \ + test_xdp_redirect.sh \ + test_xdp_meta.sh \ test_offload.py +# Compile but not part of 'make run_tests' +TEST_GEN_PROGS_EXTENDED = test_libbpf_open + include ../lib.mk -BPFOBJ := $(OUTPUT)/libbpf.a $(OUTPUT)/cgroup_helpers.c +BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c $(TEST_GEN_PROGS): $(BPFOBJ) +$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a + .PHONY: force # force a rebuild of BPFOBJ when its dependencies are updated @@ -58,7 +68,7 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline -%.o: %.c +$(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh index ed4774d8d6ed..35669ccd4d23 100755 --- a/tools/testing/selftests/bpf/test_kmod.sh +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -10,9 +10,21 @@ test_run() echo "[ JIT enabled:$1 hardened:$2 ]" dmesg -C - insmod $SRC_TREE/lib/test_bpf.ko 2> /dev/null - if [ $? -ne 0 ]; then - rc=1 + if [ -f ${SRC_TREE}/lib/test_bpf.ko ]; then + insmod ${SRC_TREE}/lib/test_bpf.ko 2> /dev/null + if [ $? -ne 0 ]; then + rc=1 + fi + else + # Use modprobe dry run to check for missing test_bpf module + if ! /sbin/modprobe -q -n test_bpf; then + echo "test_bpf: [SKIP]" + elif /sbin/modprobe -q test_bpf; then + echo "test_bpf: ok" + else + echo "test_bpf: [FAIL]" + rc=1 + fi fi rmmod test_bpf 2> /dev/null dmesg | grep FAIL diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh new file mode 100755 index 000000000000..d97dc914cd49 --- /dev/null +++ b/tools/testing/selftests/bpf/test_libbpf.sh @@ -0,0 +1,49 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +export TESTNAME=test_libbpf + +# Determine selftest success via shell exit code +exit_handler() +{ + if (( $? == 0 )); then + echo "selftests: $TESTNAME [PASS]"; + else + echo "$TESTNAME: failed at file $LAST_LOADED" 1>&2 + echo "selftests: $TESTNAME [FAILED]"; + fi +} + +libbpf_open_file() +{ + LAST_LOADED=$1 + if [ -n "$VERBOSE" ]; then + ./test_libbpf_open $1 + else + ./test_libbpf_open --quiet $1 + fi +} + +# Exit script immediately (well catched by trap handler) if any +# program/thing exits with a non-zero status. +set -e + +# (Use 'trap -l' to list meaning of numbers) +trap exit_handler 0 2 3 6 9 + +libbpf_open_file test_l4lb.o + +# TODO: fix libbpf to load noinline functions +# [warning] libbpf: incorrect bpf_call opcode +#libbpf_open_file test_l4lb_noinline.o + +# TODO: fix test_xdp_meta.c to load with libbpf +# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version +#libbpf_open_file test_xdp_meta.o + +# TODO: fix libbpf to handle .eh_frame +# [warning] libbpf: relocation failed: no section(10) +#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o + +# Success +exit 0 diff --git a/tools/testing/selftests/bpf/test_libbpf_open.c b/tools/testing/selftests/bpf/test_libbpf_open.c new file mode 100644 index 000000000000..8fcd1c076add --- /dev/null +++ b/tools/testing/selftests/bpf/test_libbpf_open.c @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Jesper Dangaard Brouer, Red Hat Inc. + */ +static const char *__doc__ = + "Libbpf test program for loading BPF ELF object files"; + +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <stdarg.h> +#include <bpf/libbpf.h> +#include <getopt.h> + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"debug", no_argument, NULL, 'D' }, + {"quiet", no_argument, NULL, 'q' }, + {0, 0, NULL, 0 } +}; + +static void usage(char *argv[]) +{ + int i; + + printf("\nDOCUMENTATION:\n%s\n\n", __doc__); + printf(" Usage: %s (options-see-below) BPF_FILE\n", argv[0]); + printf(" Listing options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + printf(" short-option: -%c", + long_options[i].val); + printf("\n"); + } + printf("\n"); +} + +#define DEFINE_PRINT_FN(name, enabled) \ +static int libbpf_##name(const char *fmt, ...) \ +{ \ + va_list args; \ + int ret; \ + \ + va_start(args, fmt); \ + if (enabled) { \ + fprintf(stderr, "[" #name "] "); \ + ret = vfprintf(stderr, fmt, args); \ + } \ + va_end(args); \ + return ret; \ +} +DEFINE_PRINT_FN(warning, 1) +DEFINE_PRINT_FN(info, 1) +DEFINE_PRINT_FN(debug, 1) + +#define EXIT_FAIL_LIBBPF EXIT_FAILURE +#define EXIT_FAIL_OPTION 2 + +int test_walk_progs(struct bpf_object *obj, bool verbose) +{ + struct bpf_program *prog; + int cnt = 0; + + bpf_object__for_each_program(prog, obj) { + cnt++; + if (verbose) + printf("Prog (count:%d) section_name: %s\n", cnt, + bpf_program__title(prog, false)); + } + return 0; +} + +int test_walk_maps(struct bpf_object *obj, bool verbose) +{ + struct bpf_map *map; + int cnt = 0; + + bpf_map__for_each(map, obj) { + cnt++; + if (verbose) + printf("Map (count:%d) name: %s\n", cnt, + bpf_map__name(map)); + } + return 0; +} + +int test_open_file(char *filename, bool verbose) +{ + struct bpf_object *bpfobj = NULL; + long err; + + if (verbose) + printf("Open BPF ELF-file with libbpf: %s\n", filename); + + /* Load BPF ELF object file and check for errors */ + bpfobj = bpf_object__open(filename); + err = libbpf_get_error(bpfobj); + if (err) { + char err_buf[128]; + libbpf_strerror(err, err_buf, sizeof(err_buf)); + if (verbose) + printf("Unable to load eBPF objects in file '%s': %s\n", + filename, err_buf); + return EXIT_FAIL_LIBBPF; + } + test_walk_progs(bpfobj, verbose); + test_walk_maps(bpfobj, verbose); + + if (verbose) + printf("Close BPF ELF-file with libbpf: %s\n", + bpf_object__name(bpfobj)); + bpf_object__close(bpfobj); + + return 0; +} + +int main(int argc, char **argv) +{ + char filename[1024] = { 0 }; + bool verbose = 1; + int longindex = 0; + int opt; + + libbpf_set_print(libbpf_warning, libbpf_info, NULL); + + /* Parse commands line args */ + while ((opt = getopt_long(argc, argv, "hDq", + long_options, &longindex)) != -1) { + switch (opt) { + case 'D': + libbpf_set_print(libbpf_warning, libbpf_info, + libbpf_debug); + break; + case 'q': /* Use in scripting mode */ + verbose = 0; + break; + case 'h': + default: + usage(argv); + return EXIT_FAIL_OPTION; + } + } + if (optind >= argc) { + usage(argv); + printf("ERROR: Expected BPF_FILE argument after options\n"); + return EXIT_FAIL_OPTION; + } + snprintf(filename, sizeof(filename), "%s", argv[optind]); + + return test_open_file(filename, verbose); +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 697bd83de295..c0f16e93f9bd 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -7780,6 +7780,20 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "XDP, using ifindex from netdev", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, ingress_ifindex)), + BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 1, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .retval = 1, + }, + { "meta access, test1", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index 307aa856cee3..637fcf4fe4e3 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -9,6 +9,7 @@ cleanup() fi set +e + ip link del veth1 2> /dev/null ip netns del ns1 2> /dev/null ip netns del ns2 2> /dev/null } diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index 344a3656dea6..c4b17e08d431 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -19,6 +19,8 @@ cleanup() fi set +e + ip link del veth1 2> /dev/null + ip link del veth2 2> /dev/null ip netns del ns1 2> /dev/null ip netns del ns2 2> /dev/null } diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 589d52b211b7..27a54a17da65 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -29,6 +29,12 @@ ftrace_filter_check '*schedule*' '^.*schedule.*$' # filter by *, end match ftrace_filter_check 'schedule*' '^schedule.*$' +# filter by *mid*end +ftrace_filter_check '*aw*lock' '.*aw.*lock$' + +# filter by start*mid* +ftrace_filter_check 'mutex*try*' '^mutex.*try.*' + # Advanced full-glob matching feature is recently supported. # Skip the tests if we are sure the kernel does not support it. if grep -q 'accepts: .* glob-matching-pattern' README ; then diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc index 0f3f92622e33..68e7a48f5828 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -128,6 +128,43 @@ if check_set_ftrace_filter "$FUNC1" "$FUNC2" ; then fail "Expected $FUNC1 and $FUNC2" fi +test_actual() { # Compares $TMPDIR/expected with set_ftrace_filter + cat set_ftrace_filter | grep -v '#' | cut -d' ' -f1 | cut -d':' -f1 | sort -u > $TMPDIR/actual + DIFF=`diff $TMPDIR/actual $TMPDIR/expected` + test -z "$DIFF" +} + +# Set traceoff trigger for all fuctions with "lock" in their name +cat available_filter_functions | cut -d' ' -f1 | grep 'lock' | sort -u > $TMPDIR/expected +echo '*lock*:traceoff' > set_ftrace_filter +test_actual + +# now remove all with 'try' in it, and end with lock +grep -v 'try.*lock$' $TMPDIR/expected > $TMPDIR/expected2 +mv $TMPDIR/expected2 $TMPDIR/expected +echo '!*try*lock:traceoff' >> set_ftrace_filter +test_actual + +# remove all that start with "m" and end with "lock" +grep -v '^m.*lock$' $TMPDIR/expected > $TMPDIR/expected2 +mv $TMPDIR/expected2 $TMPDIR/expected +echo '!m*lock:traceoff' >> set_ftrace_filter +test_actual + +# remove all that start with "c" and have "unlock" +grep -v '^c.*unlock' $TMPDIR/expected > $TMPDIR/expected2 +mv $TMPDIR/expected2 $TMPDIR/expected +echo '!c*unlock*:traceoff' >> set_ftrace_filter +test_actual + +# clear all the rest +> $TMPDIR/expected +echo '!*:traceoff' >> set_ftrace_filter +test_actual + +rm $TMPDIR/expected +rm $TMPDIR/actual + do_reset exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index f2019b37370d..df3dd7fe5f9b 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -37,17 +37,21 @@ reset_ftrace_filter() { # reset all triggers in set_ftrace_filter if [ "$tr" = "" ]; then continue fi + if ! grep -q "$t" set_ftrace_filter; then + continue; + fi + name=`echo $t | cut -d: -f1 | cut -d' ' -f1` if [ $tr = "enable_event" -o $tr = "disable_event" ]; then - tr=`echo $t | cut -d: -f1-4` + tr=`echo $t | cut -d: -f2-4` limit=`echo $t | cut -d: -f5` else - tr=`echo $t | cut -d: -f1-2` + tr=`echo $t | cut -d: -f2` limit=`echo $t | cut -d: -f3` fi if [ "$limit" != "unlimited" ]; then tr="$tr:$limit" fi - echo "!$tr" > set_ftrace_filter + echo "!$name:$tr" > set_ftrace_filter done } diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c index 9e674d9514d1..22bffd55a523 100644 --- a/tools/testing/selftests/membarrier/membarrier_test.c +++ b/tools/testing/selftests/membarrier/membarrier_test.c @@ -16,49 +16,210 @@ static int sys_membarrier(int cmd, int flags) static int test_membarrier_cmd_fail(void) { int cmd = -1, flags = 0; + const char *test_name = "sys membarrier invalid command"; if (sys_membarrier(cmd, flags) != -1) { ksft_exit_fail_msg( - "sys membarrier invalid command test: command = %d, flags = %d. Should fail, but passed\n", - cmd, flags); + "%s test: command = %d, flags = %d. Should fail, but passed\n", + test_name, cmd, flags); + } + if (errno != EINVAL) { + ksft_exit_fail_msg( + "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n", + test_name, flags, EINVAL, strerror(EINVAL), + errno, strerror(errno)); } ksft_test_result_pass( - "sys membarrier invalid command test: command = %d, flags = %d. Failed as expected\n", - cmd, flags); + "%s test: command = %d, flags = %d, errno = %d. Failed as expected\n", + test_name, cmd, flags, errno); return 0; } static int test_membarrier_flags_fail(void) { int cmd = MEMBARRIER_CMD_QUERY, flags = 1; + const char *test_name = "sys membarrier MEMBARRIER_CMD_QUERY invalid flags"; + + if (sys_membarrier(cmd, flags) != -1) { + ksft_exit_fail_msg( + "%s test: flags = %d. Should fail, but passed\n", + test_name, flags); + } + if (errno != EINVAL) { + ksft_exit_fail_msg( + "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n", + test_name, flags, EINVAL, strerror(EINVAL), + errno, strerror(errno)); + } + + ksft_test_result_pass( + "%s test: flags = %d, errno = %d. Failed as expected\n", + test_name, flags, errno); + return 0; +} + +static int test_membarrier_global_success(void) +{ + int cmd = MEMBARRIER_CMD_GLOBAL, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_GLOBAL"; + + if (sys_membarrier(cmd, flags) != 0) { + ksft_exit_fail_msg( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); + } + + ksft_test_result_pass( + "%s test: flags = %d\n", test_name, flags); + return 0; +} + +static int test_membarrier_private_expedited_fail(void) +{ + int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED not registered failure"; + + if (sys_membarrier(cmd, flags) != -1) { + ksft_exit_fail_msg( + "%s test: flags = %d. Should fail, but passed\n", + test_name, flags); + } + if (errno != EPERM) { + ksft_exit_fail_msg( + "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n", + test_name, flags, EPERM, strerror(EPERM), + errno, strerror(errno)); + } + + ksft_test_result_pass( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); + return 0; +} + +static int test_membarrier_register_private_expedited_success(void) +{ + int cmd = MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED"; + + if (sys_membarrier(cmd, flags) != 0) { + ksft_exit_fail_msg( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); + } + + ksft_test_result_pass( + "%s test: flags = %d\n", + test_name, flags); + return 0; +} + +static int test_membarrier_private_expedited_success(void) +{ + int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED"; + + if (sys_membarrier(cmd, flags) != 0) { + ksft_exit_fail_msg( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); + } + + ksft_test_result_pass( + "%s test: flags = %d\n", + test_name, flags); + return 0; +} + +static int test_membarrier_private_expedited_sync_core_fail(void) +{ + int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE not registered failure"; if (sys_membarrier(cmd, flags) != -1) { ksft_exit_fail_msg( - "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Should fail, but passed\n", - flags); + "%s test: flags = %d. Should fail, but passed\n", + test_name, flags); + } + if (errno != EPERM) { + ksft_exit_fail_msg( + "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n", + test_name, flags, EPERM, strerror(EPERM), + errno, strerror(errno)); + } + + ksft_test_result_pass( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); + return 0; +} + +static int test_membarrier_register_private_expedited_sync_core_success(void) +{ + int cmd = MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE"; + + if (sys_membarrier(cmd, flags) != 0) { + ksft_exit_fail_msg( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); + } + + ksft_test_result_pass( + "%s test: flags = %d\n", + test_name, flags); + return 0; +} + +static int test_membarrier_private_expedited_sync_core_success(void) +{ + int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE"; + + if (sys_membarrier(cmd, flags) != 0) { + ksft_exit_fail_msg( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); } ksft_test_result_pass( - "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Failed as expected\n", - flags); + "%s test: flags = %d\n", + test_name, flags); return 0; } -static int test_membarrier_success(void) +static int test_membarrier_register_global_expedited_success(void) { - int cmd = MEMBARRIER_CMD_SHARED, flags = 0; - const char *test_name = "sys membarrier MEMBARRIER_CMD_SHARED\n"; + int cmd = MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED"; if (sys_membarrier(cmd, flags) != 0) { ksft_exit_fail_msg( - "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n", - flags); + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); } ksft_test_result_pass( - "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n", - flags); + "%s test: flags = %d\n", + test_name, flags); + return 0; +} + +static int test_membarrier_global_expedited_success(void) +{ + int cmd = MEMBARRIER_CMD_GLOBAL_EXPEDITED, flags = 0; + const char *test_name = "sys membarrier MEMBARRIER_CMD_GLOBAL_EXPEDITED"; + + if (sys_membarrier(cmd, flags) != 0) { + ksft_exit_fail_msg( + "%s test: flags = %d, errno = %d\n", + test_name, flags, errno); + } + + ksft_test_result_pass( + "%s test: flags = %d\n", + test_name, flags); return 0; } @@ -72,7 +233,45 @@ static int test_membarrier(void) status = test_membarrier_flags_fail(); if (status) return status; - status = test_membarrier_success(); + status = test_membarrier_global_success(); + if (status) + return status; + status = test_membarrier_private_expedited_fail(); + if (status) + return status; + status = test_membarrier_register_private_expedited_success(); + if (status) + return status; + status = test_membarrier_private_expedited_success(); + if (status) + return status; + status = sys_membarrier(MEMBARRIER_CMD_QUERY, 0); + if (status < 0) { + ksft_test_result_fail("sys_membarrier() failed\n"); + return status; + } + if (status & MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE) { + status = test_membarrier_private_expedited_sync_core_fail(); + if (status) + return status; + status = test_membarrier_register_private_expedited_sync_core_success(); + if (status) + return status; + status = test_membarrier_private_expedited_sync_core_success(); + if (status) + return status; + } + /* + * It is valid to send a global membarrier from a non-registered + * process. + */ + status = test_membarrier_global_expedited_success(); + if (status) + return status; + status = test_membarrier_register_global_expedited_success(); + if (status) + return status; + status = test_membarrier_global_expedited_success(); if (status) return status; return 0; @@ -94,8 +293,10 @@ static int test_membarrier_query(void) } ksft_exit_fail_msg("sys_membarrier() failed\n"); } - if (!(ret & MEMBARRIER_CMD_SHARED)) + if (!(ret & MEMBARRIER_CMD_GLOBAL)) { + ksft_test_result_fail("sys_membarrier() CMD_GLOBAL query failed\n"); ksft_exit_fail_msg("sys_membarrier is not supported.\n"); + } ksft_test_result_pass("sys_membarrier available\n"); return 0; @@ -108,5 +309,5 @@ int main(int argc, char **argv) test_membarrier_query(); test_membarrier(); - ksft_exit_pass(); + return ksft_exit_pass(); } diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c index 4a8217448f20..cad14cd0ea92 100644 --- a/tools/testing/selftests/net/reuseport_bpf.c +++ b/tools/testing/selftests/net/reuseport_bpf.c @@ -21,6 +21,7 @@ #include <sys/epoll.h> #include <sys/types.h> #include <sys/socket.h> +#include <sys/resource.h> #include <unistd.h> #ifndef ARRAY_SIZE @@ -190,11 +191,14 @@ static void send_from(struct test_params p, uint16_t sport, char *buf, struct sockaddr * const saddr = new_any_sockaddr(p.send_family, sport); struct sockaddr * const daddr = new_loopback_sockaddr(p.send_family, p.recv_port); - const int fd = socket(p.send_family, p.protocol, 0); + const int fd = socket(p.send_family, p.protocol, 0), one = 1; if (fd < 0) error(1, errno, "failed to create send socket"); + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one))) + error(1, errno, "failed to set reuseaddr"); + if (bind(fd, saddr, sockaddr_size())) error(1, errno, "failed to bind send socket"); @@ -433,6 +437,21 @@ void enable_fastopen(void) } } +static struct rlimit rlim_old, rlim_new; + +static __attribute__((constructor)) void main_ctor(void) +{ + getrlimit(RLIMIT_MEMLOCK, &rlim_old); + rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20); + rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20); + setrlimit(RLIMIT_MEMLOCK, &rlim_new); +} + +static __attribute__((destructor)) void main_dtor(void) +{ + setrlimit(RLIMIT_MEMLOCK, &rlim_old); +} + int main(void) { fprintf(stderr, "---- IPv4 UDP ----\n"); diff --git a/tools/virtio/ringtest/ring.c b/tools/virtio/ringtest/ring.c index 747c5dd47be8..5a41404aaef5 100644 --- a/tools/virtio/ringtest/ring.c +++ b/tools/virtio/ringtest/ring.c @@ -84,12 +84,11 @@ void alloc_ring(void) perror("Unable to allocate ring buffer.\n"); exit(3); } - event = malloc(sizeof *event); + event = calloc(1, sizeof(*event)); if (!event) { perror("Unable to allocate event buffer.\n"); exit(3); } - memset(event, 0, sizeof *event); guest.avail_idx = 0; guest.kicked_avail_idx = -1; guest.last_used_idx = 0; @@ -102,12 +101,11 @@ void alloc_ring(void) ring[i] = desc; } guest.num_free = ring_size; - data = malloc(ring_size * sizeof *data); + data = calloc(ring_size, sizeof(*data)); if (!data) { perror("Unable to allocate data buffer.\n"); exit(3); } - memset(data, 0, ring_size * sizeof *data); } /* guest side */ @@ -188,16 +186,18 @@ bool enable_call() void kick_available(void) { + bool need; + /* Flush in previous flags write */ /* Barrier C (for pairing) */ smp_mb(); - if (!need_event(event->kick_index, - guest.avail_idx, - guest.kicked_avail_idx)) - return; + need = need_event(event->kick_index, + guest.avail_idx, + guest.kicked_avail_idx); guest.kicked_avail_idx = guest.avail_idx; - kick(); + if (need) + kick(); } /* host side */ @@ -253,14 +253,18 @@ bool use_buf(unsigned *lenp, void **bufp) void call_used(void) { + bool need; + /* Flush in previous flags write */ /* Barrier D (for pairing) */ smp_mb(); - if (!need_event(event->call_index, + + need = need_event(event->call_index, host.used_idx, - host.called_used_idx)) - return; + host.called_used_idx); host.called_used_idx = host.used_idx; - call(); + + if (need) + call(); } diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c index bbc3043b2fb1..5fd3fbcb9e57 100644 --- a/tools/virtio/ringtest/virtio_ring_0_9.c +++ b/tools/virtio/ringtest/virtio_ring_0_9.c @@ -225,16 +225,18 @@ bool enable_call() void kick_available(void) { + bool need; + /* Flush in previous flags write */ /* Barrier C (for pairing) */ smp_mb(); - if (!vring_need_event(vring_avail_event(&ring), - guest.avail_idx, - guest.kicked_avail_idx)) - return; + need = vring_need_event(vring_avail_event(&ring), + guest.avail_idx, + guest.kicked_avail_idx); guest.kicked_avail_idx = guest.avail_idx; - kick(); + if (need) + kick(); } /* host side */ @@ -316,14 +318,16 @@ bool use_buf(unsigned *lenp, void **bufp) void call_used(void) { + bool need; + /* Flush in previous flags write */ /* Barrier D (for pairing) */ smp_mb(); - if (!vring_need_event(vring_used_event(&ring), - host.used_idx, - host.called_used_idx)) - return; + need = vring_need_event(vring_used_event(&ring), + host.used_idx, + host.called_used_idx); host.called_used_idx = host.used_idx; - call(); + if (need) + call(); } diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 70691c08e1ed..cca7e065a075 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -51,3 +51,6 @@ config KVM_COMPAT config HAVE_KVM_IRQ_BYPASS bool + +config HAVE_KVM_VCPU_ASYNC_IOCTL + bool diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index cc29a8148328..70268c0bec79 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -92,7 +92,6 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; struct arch_timer_context *vtimer; - u32 cnt_ctl; /* * We may see a timer interrupt after vcpu_put() has been called which @@ -104,15 +103,11 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) return IRQ_HANDLED; vtimer = vcpu_vtimer(vcpu); - if (!vtimer->irq.level) { - cnt_ctl = read_sysreg_el0(cntv_ctl); - cnt_ctl &= ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_STAT | - ARCH_TIMER_CTRL_IT_MASK; - if (cnt_ctl == (ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_STAT)) - kvm_timer_update_irq(vcpu, true, vtimer); - } + if (kvm_timer_should_fire(vtimer)) + kvm_timer_update_irq(vcpu, true, vtimer); - if (unlikely(!irqchip_in_kernel(vcpu->kvm))) + if (static_branch_unlikely(&userspace_irqchip_in_use) && + unlikely(!irqchip_in_kernel(vcpu->kvm))) kvm_vtimer_update_mask_user(vcpu); return IRQ_HANDLED; @@ -238,6 +233,16 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) { u64 cval, now; + if (timer_ctx->loaded) { + u32 cnt_ctl; + + /* Only the virtual timer can be loaded so far */ + cnt_ctl = read_sysreg_el0(cntv_ctl); + return (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) && + (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) && + !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK); + } + if (!kvm_timer_irq_can_fire(timer_ctx)) return false; @@ -252,15 +257,7 @@ bool kvm_timer_is_pending(struct kvm_vcpu *vcpu) struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - if (vtimer->irq.level || ptimer->irq.level) - return true; - - /* - * When this is called from withing the wait loop of kvm_vcpu_block(), - * the software view of the timer state is up to date (timer->loaded - * is false), and so we can simply check if the timer should fire now. - */ - if (!vtimer->loaded && kvm_timer_should_fire(vtimer)) + if (kvm_timer_should_fire(vtimer)) return true; return kvm_timer_should_fire(ptimer); @@ -278,9 +275,9 @@ void kvm_timer_update_run(struct kvm_vcpu *vcpu) /* Populate the device bitmap with the timer states */ regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER | KVM_ARM_DEV_EL1_PTIMER); - if (vtimer->irq.level) + if (kvm_timer_should_fire(vtimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER; - if (ptimer->irq.level) + if (kvm_timer_should_fire(ptimer)) regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER; } @@ -293,7 +290,8 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level); - if (likely(irqchip_in_kernel(vcpu->kvm))) { + if (!static_branch_unlikely(&userspace_irqchip_in_use) || + likely(irqchip_in_kernel(vcpu->kvm))) { ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, timer_ctx->irq.irq, timer_ctx->irq.level, @@ -331,12 +329,20 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + bool level; if (unlikely(!timer->enabled)) return; - if (kvm_timer_should_fire(vtimer) != vtimer->irq.level) - kvm_timer_update_irq(vcpu, !vtimer->irq.level, vtimer); + /* + * The vtimer virtual interrupt is a 'mapped' interrupt, meaning part + * of its lifecycle is offloaded to the hardware, and we therefore may + * not have lowered the irq.level value before having to signal a new + * interrupt, but have to signal an interrupt every time the level is + * asserted. + */ + level = kvm_timer_should_fire(vtimer); + kvm_timer_update_irq(vcpu, level, vtimer); if (kvm_timer_should_fire(ptimer) != ptimer->irq.level) kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer); @@ -344,6 +350,12 @@ static void kvm_timer_update_state(struct kvm_vcpu *vcpu) phys_timer_emulate(vcpu); } +static void __timer_snapshot_state(struct arch_timer_context *timer) +{ + timer->cnt_ctl = read_sysreg_el0(cntv_ctl); + timer->cnt_cval = read_sysreg_el0(cntv_cval); +} + static void vtimer_save_state(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -355,10 +367,8 @@ static void vtimer_save_state(struct kvm_vcpu *vcpu) if (!vtimer->loaded) goto out; - if (timer->enabled) { - vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); - vtimer->cnt_cval = read_sysreg_el0(cntv_cval); - } + if (timer->enabled) + __timer_snapshot_state(vtimer); /* Disable the virtual timer */ write_sysreg_el0(0, cntv_ctl); @@ -456,8 +466,7 @@ static void kvm_timer_vcpu_load_vgic(struct kvm_vcpu *vcpu) bool phys_active; int ret; - phys_active = vtimer->irq.level || - kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); + phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq); ret = irq_set_irqchip_state(host_vtimer_irq, IRQCHIP_STATE_ACTIVE, @@ -504,8 +513,8 @@ bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER; plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER; - return vtimer->irq.level != vlevel || - ptimer->irq.level != plevel; + return kvm_timer_should_fire(vtimer) != vlevel || + kvm_timer_should_fire(ptimer) != plevel; } void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) @@ -537,54 +546,27 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) set_cntvoff(0); } -static void unmask_vtimer_irq(struct kvm_vcpu *vcpu) +/* + * With a userspace irqchip we have to check if the guest de-asserted the + * timer and if so, unmask the timer irq signal on the host interrupt + * controller to ensure that we see future timer signals. + */ +static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) { struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); if (unlikely(!irqchip_in_kernel(vcpu->kvm))) { - kvm_vtimer_update_mask_user(vcpu); - return; - } - - /* - * If the guest disabled the timer without acking the interrupt, then - * we must make sure the physical and virtual active states are in - * sync by deactivating the physical interrupt, because otherwise we - * wouldn't see the next timer interrupt in the host. - */ - if (!kvm_vgic_map_is_active(vcpu, vtimer->irq.irq)) { - int ret; - ret = irq_set_irqchip_state(host_vtimer_irq, - IRQCHIP_STATE_ACTIVE, - false); - WARN_ON(ret); + __timer_snapshot_state(vtimer); + if (!kvm_timer_should_fire(vtimer)) { + kvm_timer_update_irq(vcpu, false, vtimer); + kvm_vtimer_update_mask_user(vcpu); + } } } -/** - * kvm_timer_sync_hwstate - sync timer state from cpu - * @vcpu: The vcpu pointer - * - * Check if any of the timers have expired while we were running in the guest, - * and inject an interrupt if that was the case. - */ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) { - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - - /* - * If we entered the guest with the vtimer output asserted we have to - * check if the guest has modified the timer so that we should lower - * the line at this point. - */ - if (vtimer->irq.level) { - vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); - vtimer->cnt_cval = read_sysreg_el0(cntv_cval); - if (!kvm_timer_should_fire(vtimer)) { - kvm_timer_update_irq(vcpu, false, vtimer); - unmask_vtimer_irq(vcpu); - } - } + unmask_vtimer_irq_user(vcpu); } int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) @@ -818,6 +800,19 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) return true; } +bool kvm_arch_timer_get_input_level(int vintid) +{ + struct kvm_vcpu *vcpu = kvm_arm_get_running_vcpu(); + struct arch_timer_context *timer; + + if (vintid == vcpu_vtimer(vcpu)->irq.irq) + timer = vcpu_vtimer(vcpu); + else + BUG(); /* We only map the vtimer so far */ + + return kvm_timer_should_fire(timer); +} + int kvm_timer_enable(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; @@ -839,7 +834,8 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) return -EINVAL; } - ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq); + ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq, + kvm_arch_timer_get_input_level); if (ret) return ret; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 08464b2fba1d..86941f6181bb 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -31,6 +31,7 @@ #include <linux/irqbypass.h> #include <trace/events/kvm.h> #include <kvm/arm_pmu.h> +#include <kvm/arm_psci.h> #define CREATE_TRACE_POINTS #include "trace.h" @@ -46,7 +47,6 @@ #include <asm/kvm_mmu.h> #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> -#include <asm/kvm_psci.h> #include <asm/sections.h> #ifdef REQUIRES_VIRT @@ -71,17 +71,17 @@ static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { - BUG_ON(preemptible()); __this_cpu_write(kvm_arm_running_vcpu, vcpu); } +DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); + /** * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU. * Must be called from non-preemptible context */ struct kvm_vcpu *kvm_arm_get_running_vcpu(void) { - BUG_ON(preemptible()); return __this_cpu_read(kvm_arm_running_vcpu); } @@ -295,6 +295,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm))) + static_branch_dec(&userspace_irqchip_in_use); + kvm_mmu_free_memory_caches(vcpu); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); @@ -381,17 +384,24 @@ static void vcpu_power_off(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + vcpu_load(vcpu); + if (vcpu->arch.power_off) mp_state->mp_state = KVM_MP_STATE_STOPPED; else mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + vcpu_put(vcpu); return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { + int ret = 0; + + vcpu_load(vcpu); + switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: vcpu->arch.power_off = false; @@ -400,10 +410,11 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, vcpu_power_off(vcpu); break; default: - return -EINVAL; + ret = -EINVAL; } - return 0; + vcpu_put(vcpu); + return ret; } /** @@ -524,14 +535,22 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) vcpu->arch.has_run_once = true; - /* - * Map the VGIC hardware resources before running a vcpu the first - * time on this VM. - */ - if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) { - ret = kvm_vgic_map_resources(kvm); - if (ret) - return ret; + if (likely(irqchip_in_kernel(kvm))) { + /* + * Map the VGIC hardware resources before running a vcpu the + * first time on this VM. + */ + if (unlikely(!vgic_ready(kvm))) { + ret = kvm_vgic_map_resources(kvm); + if (ret) + return ret; + } + } else { + /* + * Tell the rest of the code that there are userspace irqchip + * VMs in the wild. + */ + static_branch_inc(&userspace_irqchip_in_use); } ret = kvm_timer_enable(vcpu); @@ -619,21 +638,27 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (unlikely(!kvm_vcpu_initialized(vcpu))) return -ENOEXEC; + vcpu_load(vcpu); + ret = kvm_vcpu_first_run_init(vcpu); if (ret) - return ret; + goto out; if (run->exit_reason == KVM_EXIT_MMIO) { ret = kvm_handle_mmio_return(vcpu, vcpu->run); if (ret) - return ret; - if (kvm_arm_handle_step_debug(vcpu, vcpu->run)) - return 0; + goto out; + if (kvm_arm_handle_step_debug(vcpu, vcpu->run)) { + ret = 0; + goto out; + } } - if (run->immediate_exit) - return -EINTR; + if (run->immediate_exit) { + ret = -EINTR; + goto out; + } kvm_sigset_activate(vcpu); @@ -666,19 +691,30 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vgic_flush_hwstate(vcpu); /* - * If we have a singal pending, or need to notify a userspace - * irqchip about timer or PMU level changes, then we exit (and - * update the timer level state in kvm_timer_update_run - * below). + * Exit if we have a signal pending so that we can deliver the + * signal to user space. */ - if (signal_pending(current) || - kvm_timer_should_notify_user(vcpu) || - kvm_pmu_should_notify_user(vcpu)) { + if (signal_pending(current)) { ret = -EINTR; run->exit_reason = KVM_EXIT_INTR; } /* + * If we're using a userspace irqchip, then check if we need + * to tell a userspace irqchip about timer or PMU level + * changes and if so, exit to userspace (the actual level + * state gets updated in kvm_timer_update_run and + * kvm_pmu_update_run below). + */ + if (static_branch_unlikely(&userspace_irqchip_in_use)) { + if (kvm_timer_should_notify_user(vcpu) || + kvm_pmu_should_notify_user(vcpu)) { + ret = -EINTR; + run->exit_reason = KVM_EXIT_INTR; + } + } + + /* * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and @@ -690,7 +726,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_request_pending(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; kvm_pmu_sync_hwstate(vcpu); - kvm_timer_sync_hwstate(vcpu); + if (static_branch_unlikely(&userspace_irqchip_in_use)) + kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); preempt_enable(); @@ -738,7 +775,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) * we don't want vtimer interrupts to race with syncing the * timer virtual interrupt state. */ - kvm_timer_sync_hwstate(vcpu); + if (static_branch_unlikely(&userspace_irqchip_in_use)) + kvm_timer_sync_hwstate(vcpu); /* * We may have taken a host interrupt in HYP mode (ie @@ -779,6 +817,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_sigset_deactivate(vcpu); +out: + vcpu_put(vcpu); return ret; } @@ -994,66 +1034,88 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; struct kvm_device_attr attr; + long r; + + vcpu_load(vcpu); switch (ioctl) { case KVM_ARM_VCPU_INIT: { struct kvm_vcpu_init init; + r = -EFAULT; if (copy_from_user(&init, argp, sizeof(init))) - return -EFAULT; + break; - return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); + r = kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init); + break; } case KVM_SET_ONE_REG: case KVM_GET_ONE_REG: { struct kvm_one_reg reg; + r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) - return -ENOEXEC; + break; + r = -EFAULT; if (copy_from_user(®, argp, sizeof(reg))) - return -EFAULT; + break; + if (ioctl == KVM_SET_ONE_REG) - return kvm_arm_set_reg(vcpu, ®); + r = kvm_arm_set_reg(vcpu, ®); else - return kvm_arm_get_reg(vcpu, ®); + r = kvm_arm_get_reg(vcpu, ®); + break; } case KVM_GET_REG_LIST: { struct kvm_reg_list __user *user_list = argp; struct kvm_reg_list reg_list; unsigned n; + r = -ENOEXEC; if (unlikely(!kvm_vcpu_initialized(vcpu))) - return -ENOEXEC; + break; + r = -EFAULT; if (copy_from_user(®_list, user_list, sizeof(reg_list))) - return -EFAULT; + break; n = reg_list.n; reg_list.n = kvm_arm_num_regs(vcpu); if (copy_to_user(user_list, ®_list, sizeof(reg_list))) - return -EFAULT; + break; + r = -E2BIG; if (n < reg_list.n) - return -E2BIG; - return kvm_arm_copy_reg_indices(vcpu, user_list->reg); + break; + r = kvm_arm_copy_reg_indices(vcpu, user_list->reg); + break; } case KVM_SET_DEVICE_ATTR: { + r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) - return -EFAULT; - return kvm_arm_vcpu_set_attr(vcpu, &attr); + break; + r = kvm_arm_vcpu_set_attr(vcpu, &attr); + break; } case KVM_GET_DEVICE_ATTR: { + r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) - return -EFAULT; - return kvm_arm_vcpu_get_attr(vcpu, &attr); + break; + r = kvm_arm_vcpu_get_attr(vcpu, &attr); + break; } case KVM_HAS_DEVICE_ATTR: { + r = -EFAULT; if (copy_from_user(&attr, argp, sizeof(attr))) - return -EFAULT; - return kvm_arm_vcpu_has_attr(vcpu, &attr); + break; + r = kvm_arm_vcpu_has_attr(vcpu, &attr); + break; } default: - return -EINVAL; + r = -EINVAL; } + + vcpu_put(vcpu); + return r; } /** @@ -1246,6 +1308,7 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, cpu_hyp_reset(); return NOTIFY_OK; + case CPU_PM_ENTER_FAILED: case CPU_PM_EXIT: if (__this_cpu_read(kvm_arm_hardware_enabled)) /* The hardware was enabled before suspend. */ diff --git a/virt/kvm/arm/hyp/vgic-v2-sr.c b/virt/kvm/arm/hyp/vgic-v2-sr.c index d7fd46fe9efb..4fe6e797e8b3 100644 --- a/virt/kvm/arm/hyp/vgic-v2-sr.c +++ b/virt/kvm/arm/hyp/vgic-v2-sr.c @@ -21,6 +21,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> static void __hyp_text save_elrsr(struct kvm_vcpu *vcpu, void __iomem *base) { diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index f8eaf86b740a..ec62d1cccab7 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -924,6 +924,25 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache return 0; } +static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr) +{ + pmd_t *pmdp; + pte_t *ptep; + + pmdp = stage2_get_pmd(kvm, NULL, addr); + if (!pmdp || pmd_none(*pmdp) || !pmd_present(*pmdp)) + return false; + + if (pmd_thp_or_huge(*pmdp)) + return kvm_s2pmd_exec(pmdp); + + ptep = pte_offset_kernel(pmdp, addr); + if (!ptep || pte_none(*ptep) || !pte_present(*ptep)) + return false; + + return kvm_s2pte_exec(ptep); +} + static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, phys_addr_t addr, const pte_t *new_pte, unsigned long flags) @@ -1255,10 +1274,14 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, - unsigned long size) +static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) { - __coherent_cache_guest_page(vcpu, pfn, size); + __clean_dcache_guest_page(pfn, size); +} + +static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size) +{ + __invalidate_icache_guest_page(pfn, size); } static void kvm_send_hwpoison_signal(unsigned long address, @@ -1284,7 +1307,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long fault_status) { int ret; - bool write_fault, writable, hugetlb = false, force_pte = false; + bool write_fault, exec_fault, writable, hugetlb = false, force_pte = false; unsigned long mmu_seq; gfn_t gfn = fault_ipa >> PAGE_SHIFT; struct kvm *kvm = vcpu->kvm; @@ -1296,7 +1319,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, unsigned long flags = 0; write_fault = kvm_is_write_fault(vcpu); - if (fault_status == FSC_PERM && !write_fault) { + exec_fault = kvm_vcpu_trap_is_iabt(vcpu); + VM_BUG_ON(write_fault && exec_fault); + + if (fault_status == FSC_PERM && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; } @@ -1389,7 +1415,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, new_pmd = kvm_s2pmd_mkwrite(new_pmd); kvm_set_pfn_dirty(pfn); } - coherent_cache_guest_page(vcpu, pfn, PMD_SIZE); + + if (fault_status != FSC_PERM) + clean_dcache_guest_page(pfn, PMD_SIZE); + + if (exec_fault) { + new_pmd = kvm_s2pmd_mkexec(new_pmd); + invalidate_icache_guest_page(pfn, PMD_SIZE); + } else if (fault_status == FSC_PERM) { + /* Preserve execute if XN was already cleared */ + if (stage2_is_exec(kvm, fault_ipa)) + new_pmd = kvm_s2pmd_mkexec(new_pmd); + } + ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = pfn_pte(pfn, mem_type); @@ -1399,7 +1437,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, kvm_set_pfn_dirty(pfn); mark_page_dirty(kvm, gfn); } - coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE); + + if (fault_status != FSC_PERM) + clean_dcache_guest_page(pfn, PAGE_SIZE); + + if (exec_fault) { + new_pte = kvm_s2pte_mkexec(new_pte); + invalidate_icache_guest_page(pfn, PAGE_SIZE); + } else if (fault_status == FSC_PERM) { + /* Preserve execute if XN was already cleared */ + if (stage2_is_exec(kvm, fault_ipa)) + new_pte = kvm_s2pte_mkexec(new_pte); + } + ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags); } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index f1e363bab5e8..6919352cbf15 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -15,16 +15,16 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/arm-smccc.h> #include <linux/preempt.h> #include <linux/kvm_host.h> #include <linux/wait.h> #include <asm/cputype.h> #include <asm/kvm_emulate.h> -#include <asm/kvm_psci.h> #include <asm/kvm_host.h> -#include <uapi/linux/psci.h> +#include <kvm/arm_psci.h> /* * This is an implementation of the Power State Coordination Interface @@ -33,6 +33,38 @@ #define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1) +static u32 smccc_get_function(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 0); +} + +static unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 1); +} + +static unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 2); +} + +static unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu) +{ + return vcpu_get_reg(vcpu, 3); +} + +static void smccc_set_retval(struct kvm_vcpu *vcpu, + unsigned long a0, + unsigned long a1, + unsigned long a2, + unsigned long a3) +{ + vcpu_set_reg(vcpu, 0, a0); + vcpu_set_reg(vcpu, 1, a1); + vcpu_set_reg(vcpu, 2, a2); + vcpu_set_reg(vcpu, 3, a3); +} + static unsigned long psci_affinity_mask(unsigned long affinity_level) { if (affinity_level <= 3) @@ -78,7 +110,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) unsigned long context_id; phys_addr_t target_pc; - cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK; + cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK; if (vcpu_mode_is_32bit(source_vcpu)) cpu_id &= ~((u32) 0); @@ -91,14 +123,14 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) if (!vcpu) return PSCI_RET_INVALID_PARAMS; if (!vcpu->arch.power_off) { - if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1) + if (kvm_psci_version(source_vcpu, kvm) != KVM_ARM_PSCI_0_1) return PSCI_RET_ALREADY_ON; else return PSCI_RET_INVALID_PARAMS; } - target_pc = vcpu_get_reg(source_vcpu, 2); - context_id = vcpu_get_reg(source_vcpu, 3); + target_pc = smccc_get_arg2(source_vcpu); + context_id = smccc_get_arg3(source_vcpu); kvm_reset_vcpu(vcpu); @@ -117,7 +149,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) * NOTE: We always update r0 (or x0) because for PSCI v0.1 * the general puspose registers are undefined upon CPU_ON. */ - vcpu_set_reg(vcpu, 0, context_id); + smccc_set_retval(vcpu, context_id, 0, 0, 0); vcpu->arch.power_off = false; smp_mb(); /* Make sure the above is visible */ @@ -137,8 +169,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; - target_affinity = vcpu_get_reg(vcpu, 1); - lowest_affinity_level = vcpu_get_reg(vcpu, 2); + target_affinity = smccc_get_arg1(vcpu); + lowest_affinity_level = smccc_get_arg2(vcpu); /* Determine target affinity mask */ target_affinity_mask = psci_affinity_mask(lowest_affinity_level); @@ -200,18 +232,10 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET); } -int kvm_psci_version(struct kvm_vcpu *vcpu) -{ - if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) - return KVM_ARM_PSCI_0_2; - - return KVM_ARM_PSCI_0_1; -} - static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); + u32 psci_fn = smccc_get_function(vcpu); unsigned long val; int ret = 1; @@ -221,7 +245,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) * Bits[31:16] = Major Version = 0 * Bits[15:0] = Minor Version = 2 */ - val = 2; + val = KVM_ARM_PSCI_0_2; break; case PSCI_0_2_FN_CPU_SUSPEND: case PSCI_0_2_FN64_CPU_SUSPEND: @@ -278,14 +302,56 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } - vcpu_set_reg(vcpu, 0, val); + smccc_set_retval(vcpu, val, 0, 0, 0); + return ret; +} + +static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu) +{ + u32 psci_fn = smccc_get_function(vcpu); + u32 feature; + unsigned long val; + int ret = 1; + + switch(psci_fn) { + case PSCI_0_2_FN_PSCI_VERSION: + val = KVM_ARM_PSCI_1_0; + break; + case PSCI_1_0_FN_PSCI_FEATURES: + feature = smccc_get_arg1(vcpu); + switch(feature) { + case PSCI_0_2_FN_PSCI_VERSION: + case PSCI_0_2_FN_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_SUSPEND: + case PSCI_0_2_FN_CPU_OFF: + case PSCI_0_2_FN_CPU_ON: + case PSCI_0_2_FN64_CPU_ON: + case PSCI_0_2_FN_AFFINITY_INFO: + case PSCI_0_2_FN64_AFFINITY_INFO: + case PSCI_0_2_FN_MIGRATE_INFO_TYPE: + case PSCI_0_2_FN_SYSTEM_OFF: + case PSCI_0_2_FN_SYSTEM_RESET: + case PSCI_1_0_FN_PSCI_FEATURES: + case ARM_SMCCC_VERSION_FUNC_ID: + val = 0; + break; + default: + val = PSCI_RET_NOT_SUPPORTED; + break; + } + break; + default: + return kvm_psci_0_2_call(vcpu); + } + + smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0); + u32 psci_fn = smccc_get_function(vcpu); unsigned long val; switch (psci_fn) { @@ -303,7 +369,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) break; } - vcpu_set_reg(vcpu, 0, val); + smccc_set_retval(vcpu, val, 0, 0, 0); return 1; } @@ -321,9 +387,11 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) * Errors: * -EINVAL: Unrecognized PSCI function */ -int kvm_psci_call(struct kvm_vcpu *vcpu) +static int kvm_psci_call(struct kvm_vcpu *vcpu) { - switch (kvm_psci_version(vcpu)) { + switch (kvm_psci_version(vcpu, vcpu->kvm)) { + case KVM_ARM_PSCI_1_0: + return kvm_psci_1_0_call(vcpu); case KVM_ARM_PSCI_0_2: return kvm_psci_0_2_call(vcpu); case KVM_ARM_PSCI_0_1: @@ -332,3 +400,30 @@ int kvm_psci_call(struct kvm_vcpu *vcpu) return -EINVAL; }; } + +int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) +{ + u32 func_id = smccc_get_function(vcpu); + u32 val = PSCI_RET_NOT_SUPPORTED; + u32 feature; + + switch (func_id) { + case ARM_SMCCC_VERSION_FUNC_ID: + val = ARM_SMCCC_VERSION_1_1; + break; + case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: + feature = smccc_get_arg1(vcpu); + switch(feature) { + case ARM_SMCCC_ARCH_WORKAROUND_1: + if (kvm_arm_harden_branch_predictor()) + val = 0; + break; + } + break; + default: + return kvm_psci_call(vcpu); + } + + smccc_set_retval(vcpu, val, 0, 0, 0); + return 1; +} diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 8e633bd9cc1e..465095355666 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -1034,10 +1034,8 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its, device = vgic_its_alloc_device(its, device_id, itt_addr, num_eventid_bits); - if (IS_ERR(device)) - return PTR_ERR(device); - return 0; + return PTR_ERR_OR_ZERO(device); } /* diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index deb51ee16a3d..83d82bd7dc4e 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -16,6 +16,7 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/iodev.h> +#include <kvm/arm_arch_timer.h> #include <kvm/arm_vgic.h> #include "vgic.h" @@ -122,10 +123,43 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } +/* + * This function will return the VCPU that performed the MMIO access and + * trapped from within the VM, and will return NULL if this is a userspace + * access. + * + * We can disable preemption locally around accessing the per-CPU variable, + * and use the resolved vcpu pointer after enabling preemption again, because + * even if the current thread is migrated to another CPU, reading the per-CPU + * value later will give us the same value as we update the per-CPU variable + * in the preempt notifier handlers. + */ +static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void) +{ + struct kvm_vcpu *vcpu; + + preempt_disable(); + vcpu = kvm_arm_get_running_vcpu(); + preempt_enable(); + return vcpu; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool is_uaccess) +{ + if (is_uaccess) + return; + + irq->pending_latch = true; + vgic_irq_set_phys_active(irq, true); +} + void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { + bool is_uaccess = !vgic_get_mmio_requester_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -134,17 +168,45 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = true; - + if (irq->hw) + vgic_hw_irq_spending(vcpu, irq, is_uaccess); + else + irq->pending_latch = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool is_uaccess) +{ + if (is_uaccess) + return; + + irq->pending_latch = false; + + /* + * We don't want the guest to effectively mask the physical + * interrupt by doing a write to SPENDR followed by a write to + * CPENDR for HW interrupts, so we clear the active state on + * the physical side if the virtual interrupt is not active. + * This may lead to taking an additional interrupt on the + * host, but that should not be a problem as the worst that + * can happen is an additional vgic injection. We also clear + * the pending state to maintain proper semantics for edge HW + * interrupts. + */ + vgic_irq_set_phys_pending(irq, false); + if (!irq->active) + vgic_irq_set_phys_active(irq, false); +} + void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { + bool is_uaccess = !vgic_get_mmio_requester_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -154,7 +216,10 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, spin_lock_irqsave(&irq->irq_lock, flags); - irq->pending_latch = false; + if (irq->hw) + vgic_hw_irq_cpending(vcpu, irq, is_uaccess); + else + irq->pending_latch = false; spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); @@ -181,27 +246,24 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, return value; } +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, + bool active, bool is_uaccess) +{ + if (is_uaccess) + return; + + irq->active = active; + vgic_irq_set_phys_active(irq, active); +} + static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool new_active_state) + bool active) { - struct kvm_vcpu *requester_vcpu; unsigned long flags; - spin_lock_irqsave(&irq->irq_lock, flags); + struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu(); - /* - * The vcpu parameter here can mean multiple things depending on how - * this function is called; when handling a trap from the kernel it - * depends on the GIC version, and these functions are also called as - * part of save/restore from userspace. - * - * Therefore, we have to figure out the requester in a reliable way. - * - * When accessing VGIC state from user space, the requester_vcpu is - * NULL, which is fine, because we guarantee that no VCPUs are running - * when accessing VGIC state from user space so irq->vcpu->cpu is - * always -1. - */ - requester_vcpu = kvm_arm_get_running_vcpu(); + spin_lock_irqsave(&irq->irq_lock, flags); /* * If this virtual IRQ was written into a list register, we @@ -213,14 +275,23 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, * vgic_change_active_prepare) and still has to sync back this IRQ, * so we release and re-acquire the spin_lock to let the other thread * sync back the IRQ. + * + * When accessing VGIC state from user space, requester_vcpu is + * NULL, which is fine, because we guarantee that no VCPUs are running + * when accessing VGIC state from user space so irq->vcpu->cpu is + * always -1. */ while (irq->vcpu && /* IRQ may have state in an LR somewhere */ irq->vcpu != requester_vcpu && /* Current thread is not the VCPU thread */ irq->vcpu->cpu != -1) /* VCPU thread is running */ cond_resched_lock(&irq->irq_lock); - irq->active = new_active_state; - if (new_active_state) + if (irq->hw) + vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); + else + irq->active = active; + + if (irq->active) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else spin_unlock_irqrestore(&irq->irq_lock, flags); diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 80897102da26..c32d7b93ffd1 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -105,6 +105,26 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) irq->pending_latch = false; } + /* + * Level-triggered mapped IRQs are special because we only + * observe rising edges as input to the VGIC. + * + * If the guest never acked the interrupt we have to sample + * the physical line and set the line level, because the + * device state could have changed or we simply need to + * process the still pending interrupt later. + * + * If this causes us to lower the level, we have to also clear + * the physical active state, since we will otherwise never be + * told when the interrupt becomes asserted again. + */ + if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) { + irq->line_level = vgic_get_phys_line_level(irq); + + if (!irq->line_level) + vgic_irq_set_phys_active(irq, false); + } + spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -162,6 +182,15 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) val |= GICH_LR_EOI; } + /* + * Level-triggered mapped IRQs are special because we only observe + * rising edges as input to the VGIC. We therefore lower the line + * level here, so that we can take new virtual IRQs. See + * vgic_v2_fold_lr_state for more info. + */ + if (vgic_irq_is_mapped_level(irq) && (val & GICH_LR_PENDING_BIT)) + irq->line_level = false; + /* The GICv2 LR only holds five bits of priority. */ val |= (irq->priority >> 3) << GICH_LR_PRIORITY_SHIFT; diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index f47e8481fa45..6b329414e57a 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -96,6 +96,26 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) irq->pending_latch = false; } + /* + * Level-triggered mapped IRQs are special because we only + * observe rising edges as input to the VGIC. + * + * If the guest never acked the interrupt we have to sample + * the physical line and set the line level, because the + * device state could have changed or we simply need to + * process the still pending interrupt later. + * + * If this causes us to lower the level, we have to also clear + * the physical active state, since we will otherwise never be + * told when the interrupt becomes asserted again. + */ + if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) { + irq->line_level = vgic_get_phys_line_level(irq); + + if (!irq->line_level) + vgic_irq_set_phys_active(irq, false); + } + spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -146,6 +166,15 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) } /* + * Level-triggered mapped IRQs are special because we only observe + * rising edges as input to the VGIC. We therefore lower the line + * level here, so that we can take new virtual IRQs. See + * vgic_v3_fold_lr_state for more info. + */ + if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) + irq->line_level = false; + + /* * We currently only support Group1 interrupts, which is a * known defect. This needs to be addressed at some point. */ diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index ecb8e25f5fe5..c7c5ef190afa 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -144,6 +144,38 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) kfree(irq); } +void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) +{ + WARN_ON(irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + pending)); +} + +bool vgic_get_phys_line_level(struct vgic_irq *irq) +{ + bool line_level; + + BUG_ON(!irq->hw); + + if (irq->get_input_level) + return irq->get_input_level(irq->intid); + + WARN_ON(irq_get_irqchip_state(irq->host_irq, + IRQCHIP_STATE_PENDING, + &line_level)); + return line_level; +} + +/* Set/Clear the physical active state */ +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active) +{ + + BUG_ON(!irq->hw); + WARN_ON(irq_set_irqchip_state(irq->host_irq, + IRQCHIP_STATE_ACTIVE, + active)); +} + /** * kvm_vgic_target_oracle - compute the target vcpu for an irq * @@ -413,7 +445,8 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, /* @irq->irq_lock must be held */ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - unsigned int host_irq) + unsigned int host_irq, + bool (*get_input_level)(int vindid)) { struct irq_desc *desc; struct irq_data *data; @@ -433,6 +466,7 @@ static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, irq->hw = true; irq->host_irq = host_irq; irq->hwintid = data->hwirq; + irq->get_input_level = get_input_level; return 0; } @@ -441,10 +475,11 @@ static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq) { irq->hw = false; irq->hwintid = 0; + irq->get_input_level = NULL; } int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, - u32 vintid) + u32 vintid, bool (*get_input_level)(int vindid)) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); unsigned long flags; @@ -453,7 +488,7 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, BUG_ON(!irq); spin_lock_irqsave(&irq->irq_lock, flags); - ret = kvm_vgic_map_irq(vcpu, irq, host_irq); + ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level); spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index efbcf8f96f9c..12c37b89f7a3 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -104,6 +104,11 @@ static inline bool irq_is_pending(struct vgic_irq *irq) return irq->pending_latch || irq->line_level; } +static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq) +{ + return irq->config == VGIC_CONFIG_LEVEL && irq->hw; +} + /* * This struct provides an intermediate representation of the fields contained * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC @@ -140,6 +145,9 @@ vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 intid); void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq); +bool vgic_get_phys_line_level(struct vgic_irq *irq); +void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending); +void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active); bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, unsigned long flags); void vgic_kick_vcpus(struct kvm *kvm); diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index a334399fafec..6e865e8b5b10 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -194,7 +194,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) unsigned seq; int idx; - if (flags & POLLIN) { + if (flags & EPOLLIN) { idx = srcu_read_lock(&kvm->irq_srcu); do { seq = read_seqcount_begin(&irqfd->irq_entry_sc); @@ -208,7 +208,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) srcu_read_unlock(&kvm->irq_srcu, idx); } - if (flags & POLLHUP) { + if (flags & EPOLLHUP) { /* The eventfd is closing, detach from KVM */ unsigned long flags; @@ -399,12 +399,12 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args) */ events = f.file->f_op->poll(f.file, &irqfd->pt); - if (events & POLLIN) + if (events & EPOLLIN) schedule_work(&irqfd->inject); /* * do not drop the file until the irqfd is fully initialized, otherwise - * we might race against the POLLHUP + * we might race against the EPOLLHUP */ fdput(f); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 001085b611ad..4501e658e8d6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -151,17 +151,12 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) /* * Switches to specified vcpu, until a matching vcpu_put() */ -int vcpu_load(struct kvm_vcpu *vcpu) +void vcpu_load(struct kvm_vcpu *vcpu) { - int cpu; - - if (mutex_lock_killable(&vcpu->mutex)) - return -EINTR; - cpu = get_cpu(); + int cpu = get_cpu(); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); - return 0; } EXPORT_SYMBOL_GPL(vcpu_load); @@ -171,7 +166,6 @@ void vcpu_put(struct kvm_vcpu *vcpu) kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); preempt_enable(); - mutex_unlock(&vcpu->mutex); } EXPORT_SYMBOL_GPL(vcpu_put); @@ -1416,7 +1410,8 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) static int hva_to_pfn_remapped(struct vm_area_struct *vma, unsigned long addr, bool *async, - bool write_fault, kvm_pfn_t *p_pfn) + bool write_fault, bool *writable, + kvm_pfn_t *p_pfn) { unsigned long pfn; int r; @@ -1442,6 +1437,8 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, } + if (writable) + *writable = true; /* * Get a reference here because callers of *hva_to_pfn* and @@ -1507,7 +1504,7 @@ retry: if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { - r = hva_to_pfn_remapped(vma, addr, async, write_fault, &pfn); + r = hva_to_pfn_remapped(vma, addr, async, write_fault, writable, &pfn); if (r == -EAGAIN) goto retry; if (r < 0) @@ -2400,7 +2397,10 @@ static struct file_operations kvm_vcpu_fops = { */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { - return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); + char name[8 + 1 + ITOA_MAX_LEN + 1]; + + snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id); + return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } static int kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) @@ -2532,19 +2532,16 @@ static long kvm_vcpu_ioctl(struct file *filp, if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) return -EINVAL; -#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) /* - * Special cases: vcpu ioctls that are asynchronous to vcpu execution, - * so vcpu_load() would break it. + * Some architectures have vcpu ioctls that are asynchronous to vcpu + * execution; mutex_lock() would break them. */ - if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_S390_IRQ || ioctl == KVM_INTERRUPT) - return kvm_arch_vcpu_ioctl(filp, ioctl, arg); -#endif - - - r = vcpu_load(vcpu); - if (r) + r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg); + if (r != -ENOIOCTLCMD) return r; + + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; switch (ioctl) { case KVM_RUN: { struct pid *oldpid; @@ -2716,7 +2713,7 @@ out_free1: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: - vcpu_put(vcpu); + mutex_unlock(&vcpu->mutex); kfree(fpu); kfree(kvm_sregs); return r; @@ -3168,21 +3165,18 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) return PTR_ERR(kvm); #ifdef CONFIG_KVM_MMIO r = kvm_coalesced_mmio_init(kvm); - if (r < 0) { - kvm_put_kvm(kvm); - return r; - } + if (r < 0) + goto put_kvm; #endif r = get_unused_fd_flags(O_CLOEXEC); - if (r < 0) { - kvm_put_kvm(kvm); - return r; - } + if (r < 0) + goto put_kvm; + file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (IS_ERR(file)) { put_unused_fd(r); - kvm_put_kvm(kvm); - return PTR_ERR(file); + r = PTR_ERR(file); + goto put_kvm; } /* @@ -3200,6 +3194,10 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) fd_install(r, file); return r; + +put_kvm: + kvm_put_kvm(kvm); + return r; } static long kvm_dev_ioctl(struct file *filp, |