diff options
729 files changed, 9950 insertions, 5092 deletions
diff --git a/Documentation/admin-guide/device-mapper/delay.rst b/Documentation/admin-guide/device-mapper/delay.rst index 917ba8c33359..4d667228e744 100644 --- a/Documentation/admin-guide/device-mapper/delay.rst +++ b/Documentation/admin-guide/device-mapper/delay.rst @@ -3,29 +3,52 @@ dm-delay ======== Device-Mapper's "delay" target delays reads and/or writes -and maps them to different devices. +and/or flushs and optionally maps them to different devices. -Parameters:: +Arguments:: <device> <offset> <delay> [<write_device> <write_offset> <write_delay> [<flush_device> <flush_offset> <flush_delay>]] -With separate write parameters, the first set is only used for reads. +Table line has to either have 3, 6 or 9 arguments: + +3: apply offset and delay to read, write and flush operations on device + +6: apply offset and delay to device, also apply write_offset and write_delay + to write and flush operations on optionally different write_device with + optionally different sector offset + +9: same as 6 arguments plus define flush_offset and flush_delay explicitely + on/with optionally different flush_device/flush_offset. + Offsets are specified in sectors. + Delays are specified in milliseconds. + Example scripts =============== :: - #!/bin/sh - # Create device delaying rw operation for 500ms - echo "0 `blockdev --getsz $1` delay $1 0 500" | dmsetup create delayed + # + # Create mapped device named "delayed" delaying read, write and flush operations for 500ms. + # + dmsetup create delayed --table "0 `blockdev --getsz $1` delay $1 0 500" :: + #!/bin/sh + # + # Create mapped device delaying write and flush operations for 400ms and + # splitting reads to device $1 but writes and flushs to different device $2 + # to different offsets of 2048 and 4096 sectors respectively. + # + dmsetup create delayed --table "0 `blockdev --getsz $1` delay $1 2048 0 $2 4096 400" +:: #!/bin/sh - # Create device delaying only write operation for 500ms and - # splitting reads and writes to different devices $1 $2 - echo "0 `blockdev --getsz $1` delay $1 0 0 $2 0 500" | dmsetup create delayed + # + # Create mapped device delaying reads for 50ms, writes for 100ms and flushs for 333ms + # onto the same backing device at offset 0 sectors. + # + dmsetup create delayed --table "0 `blockdev --getsz $1` delay $1 0 50 $2 0 100 $1 0 333" diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst index 48a48bd09372..9f8139ff97d6 100644 --- a/Documentation/admin-guide/device-mapper/dm-crypt.rst +++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst @@ -160,6 +160,10 @@ iv_large_sectors The <iv_offset> must be multiple of <sector_size> (in 512 bytes units) if this flag is specified. +integrity_key_size:<bytes> + Use an integrity key of <bytes> size instead of using an integrity key size + of the digest size of the used HMAC algorithm. + Module parameters:: max_read_size diff --git a/Documentation/admin-guide/device-mapper/vdo.rst b/Documentation/admin-guide/device-mapper/vdo.rst index c69ac186863a..a14e6d3e787c 100644 --- a/Documentation/admin-guide/device-mapper/vdo.rst +++ b/Documentation/admin-guide/device-mapper/vdo.rst @@ -251,7 +251,12 @@ The messages are: by the vdostats userspace program to interpret the output buffer. - dump: + config: + Outputs useful vdo configuration information. Mostly used + by users who want to recreate a similar VDO volume and + want to know the creation configuration used. + + dump: Dumps many internal structures to the system log. This is not always safe to run, so it should only be used to debug a hung vdo. Optional parameters to specify structures to diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bb48ae24ae69..1518343bbe22 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2677,6 +2677,23 @@ Default is Y (on). + kvm.enable_virt_at_load=[KVM,ARM64,LOONGARCH,MIPS,RISCV,X86] + If enabled, KVM will enable virtualization in hardware + when KVM is loaded, and disable virtualization when KVM + is unloaded (if KVM is built as a module). + + If disabled, KVM will dynamically enable and disable + virtualization on-demand when creating and destroying + VMs, i.e. on the 0=>1 and 1=>0 transitions of the + number of VMs. + + Enabling virtualization at module lode avoids potential + latency for creation of the 0=>1 VM, as KVM serializes + virtualization enabling across all online CPUs. The + "cost" of enabling virtualization when KVM is loaded, + is that doing so may interfere with using out-of-tree + hypervisors that want to "own" virtualization hardware. + kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface. Default is false (don't support). diff --git a/Documentation/arch/loongarch/irq-chip-model.rst b/Documentation/arch/loongarch/irq-chip-model.rst index 7988f4192363..6dd48256e39f 100644 --- a/Documentation/arch/loongarch/irq-chip-model.rst +++ b/Documentation/arch/loongarch/irq-chip-model.rst @@ -85,6 +85,38 @@ to CPUINTC directly:: | Devices | +---------+ +Advanced Extended IRQ model +=========================== + +In this model, IPI (Inter-Processor Interrupt) and CPU Local Timer interrupt go +to CPUINTC directly, CPU UARTS interrupts go to LIOINTC, PCH-MSI interrupts go +to AVECINTC, and then go to CPUINTC directly, while all other devices interrupts +go to PCH-PIC/PCH-LPC and gathered by EIOINTC, and then go to CPUINTC directly:: + + +-----+ +-----------------------+ +-------+ + | IPI | --> | CPUINTC | <-- | Timer | + +-----+ +-----------------------+ +-------+ + ^ ^ ^ + | | | + +---------+ +----------+ +---------+ +-------+ + | EIOINTC | | AVECINTC | | LIOINTC | <-- | UARTs | + +---------+ +----------+ +---------+ +-------+ + ^ ^ + | | + +---------+ +---------+ + | PCH-PIC | | PCH-MSI | + +---------+ +---------+ + ^ ^ ^ + | | | + +---------+ +---------+ +---------+ + | Devices | | PCH-LPC | | Devices | + +---------+ +---------+ +---------+ + ^ + | + +---------+ + | Devices | + +---------+ + ACPI-related definitions ======================== diff --git a/Documentation/arch/s390/vfio-ap.rst b/Documentation/arch/s390/vfio-ap.rst index ea744cbc8687..eba1991fbdba 100644 --- a/Documentation/arch/s390/vfio-ap.rst +++ b/Documentation/arch/s390/vfio-ap.rst @@ -999,6 +999,36 @@ the vfio_ap mediated device to which it is assigned as long as each new APQN resulting from plugging it in references a queue device bound to the vfio_ap device driver. +Driver Features +=============== +The vfio_ap driver exposes a sysfs file containing supported features. +This exists so third party tools (like Libvirt and mdevctl) can query the +availability of specific features. + +The features list can be found here: /sys/bus/matrix/devices/matrix/features + +Entries are space delimited. Each entry consists of a combination of +alphanumeric and underscore characters. + +Example: +cat /sys/bus/matrix/devices/matrix/features +guest_matrix dyn ap_config + +the following features are advertised: + +---------------+---------------------------------------------------------------+ +| Flag | Description | ++==============+===============================================================+ +| guest_matrix | guest_matrix attribute exists. It reports the matrix of | +| | adapters and domains that are or will be passed through to a | +| | guest when the mdev is attached to it. | ++--------------+---------------------------------------------------------------+ +| dyn | Indicates hot plug/unplug of AP adapters, domains and control | +| | domains for a guest to which the mdev is attached. | ++------------+-----------------------------------------------------------------+ +| ap_config | ap_config interface for one-shot modifications to mdev config | ++--------------+---------------------------------------------------------------+ + Limitations =========== Live guest migration is not supported for guests using AP devices without diff --git a/Documentation/core-api/cleanup.rst b/Documentation/core-api/cleanup.rst new file mode 100644 index 000000000000..527eb2f8ec6e --- /dev/null +++ b/Documentation/core-api/cleanup.rst @@ -0,0 +1,8 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== +Scope-based Cleanup Helpers +=========================== + +.. kernel-doc:: include/linux/cleanup.h + :doc: scope-based cleanup helpers diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index e18a2ffe0787..a331d2c814f5 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -35,6 +35,7 @@ Library functionality that is used throughout the kernel. kobject kref + cleanup assoc_array xarray maple_tree diff --git a/Documentation/driver-api/cxl/access-coordinates.rst b/Documentation/driver-api/cxl/access-coordinates.rst new file mode 100644 index 000000000000..b07950ea30c9 --- /dev/null +++ b/Documentation/driver-api/cxl/access-coordinates.rst @@ -0,0 +1,91 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: <isonum.txt> + +================================== +CXL Access Coordinates Computation +================================== + +Shared Upstream Link Calculation +================================ +For certain CXL region construction with endpoints behind CXL switches (SW) or +Root Ports (RP), there is the possibility of the total bandwidth for all +the endpoints behind a switch being more than the switch upstream link. +A similar situation can occur within the host, upstream of the root ports. +The CXL driver performs an additional pass after all the targets have +arrived for a region in order to recalculate the bandwidths with possible +upstream link being a limiting factor in mind. + +The algorithm assumes the configuration is a symmetric topology as that +maximizes performance. When asymmetric topology is detected, the calculation +is aborted. An asymmetric topology is detected during topology walk where the +number of RPs detected as a grandparent is not equal to the number of devices +iterated in the same iteration loop. The assumption is made that subtle +asymmetry in properties does not happen and all paths to EPs are equal. + +There can be multiple switches under an RP. There can be multiple RPs under +a CXL Host Bridge (HB). There can be multiple HBs under a CXL Fixed Memory +Window Structure (CFMWS). + +An example hierarchy: + +> CFMWS 0 +> | +> _________|_________ +> | | +> ACPI0017-0 ACPI0017-1 +> GP0/HB0/ACPI0016-0 GP1/HB1/ACPI0016-1 +> | | | | +> RP0 RP1 RP2 RP3 +> | | | | +> SW 0 SW 1 SW 2 SW 3 +> | | | | | | | | +> EP0 EP1 EP2 EP3 EP4 EP5 EP6 EP7 + +Computation for the example hierarchy: + +Min (GP0 to CPU BW, + Min(SW 0 Upstream Link to RP0 BW, + Min(SW0SSLBIS for SW0DSP0 (EP0), EP0 DSLBIS, EP0 Upstream Link) + + Min(SW0SSLBIS for SW0DSP1 (EP1), EP1 DSLBIS, EP1 Upstream link)) + + Min(SW 1 Upstream Link to RP1 BW, + Min(SW1SSLBIS for SW1DSP0 (EP2), EP2 DSLBIS, EP2 Upstream Link) + + Min(SW1SSLBIS for SW1DSP1 (EP3), EP3 DSLBIS, EP3 Upstream link))) + +Min (GP1 to CPU BW, + Min(SW 2 Upstream Link to RP2 BW, + Min(SW2SSLBIS for SW2DSP0 (EP4), EP4 DSLBIS, EP4 Upstream Link) + + Min(SW2SSLBIS for SW2DSP1 (EP5), EP5 DSLBIS, EP5 Upstream link)) + + Min(SW 3 Upstream Link to RP3 BW, + Min(SW3SSLBIS for SW3DSP0 (EP6), EP6 DSLBIS, EP6 Upstream Link) + + Min(SW3SSLBIS for SW3DSP1 (EP7), EP7 DSLBIS, EP7 Upstream link)))) + +The calculation starts at cxl_region_shared_upstream_perf_update(). A xarray +is created to collect all the endpoint bandwidths via the +cxl_endpoint_gather_bandwidth() function. The min() of bandwidth from the +endpoint CDAT and the upstream link bandwidth is calculated. If the endpoint +has a CXL switch as a parent, then min() of calculated bandwidth and the +bandwidth from the SSLBIS for the switch downstream port that is associated +with the endpoint is calculated. The final bandwidth is stored in a +'struct cxl_perf_ctx' in the xarray indexed by a device pointer. If the +endpoint is direct attached to a root port (RP), the device pointer would be an +RP device. If the endpoint is behind a switch, the device pointer would be the +upstream device of the parent switch. + +At the next stage, the code walks through one or more switches if they exist +in the topology. For endpoints directly attached to RPs, this step is skipped. +If there is another switch upstream, the code takes the min() of the current +gathered bandwidth and the upstream link bandwidth. If there's a switch +upstream, then the SSLBIS of the upstream switch. + +Once the topology walk reaches the RP, whether it's direct attached endpoints +or walking through the switch(es), cxl_rp_gather_bandwidth() is called. At +this point all the bandwidths are aggregated per each host bridge, which is +also the index for the resulting xarray. + +The next step is to take the min() of the per host bridge bandwidth and the +bandwidth from the Generic Port (GP). The bandwidths for the GP is retrieved +via ACPI tables SRAT/HMAT. The min bandwidth are aggregated under the same +ACPI0017 device to form a new xarray. + +Finally, the cxl_region_update_bandwidth() is called and the aggregated +bandwidth from all the members of the last xarray is updated for the +access coordinates residing in the cxl region (cxlr) context. diff --git a/Documentation/driver-api/cxl/index.rst b/Documentation/driver-api/cxl/index.rst index 12b82725d322..965ba90e8fb7 100644 --- a/Documentation/driver-api/cxl/index.rst +++ b/Documentation/driver-api/cxl/index.rst @@ -8,6 +8,7 @@ Compute Express Link :maxdepth: 1 memory-devices + access-coordinates maturity-map diff --git a/Documentation/translations/zh_CN/arch/loongarch/irq-chip-model.rst b/Documentation/translations/zh_CN/arch/loongarch/irq-chip-model.rst index f1e9ab18206c..472761938682 100644 --- a/Documentation/translations/zh_CN/arch/loongarch/irq-chip-model.rst +++ b/Documentation/translations/zh_CN/arch/loongarch/irq-chip-model.rst @@ -87,6 +87,38 @@ PCH-LPC/PCH-MSI，然后被EIOINTC统一收集，再直接到达CPUINTC:: | Devices | +---------+ +高级扩展IRQ模型 +=============== + +在这种模型里面，IPI（Inter-Processor Interrupt）和CPU本地时钟中断直接发送到CPUINTC， +CPU串口（UARTs）中断发送到LIOINTC，PCH-MSI中断发送到AVECINTC，而后通过AVECINTC直接 +送达CPUINTC，而其他所有设备的中断则分别发送到所连接的PCH-PIC/PCH-LPC，然后由EIOINTC +统一收集，再直接到达CPUINTC:: + + +-----+ +-----------------------+ +-------+ + | IPI | --> | CPUINTC | <-- | Timer | + +-----+ +-----------------------+ +-------+ + ^ ^ ^ + | | | + +---------+ +----------+ +---------+ +-------+ + | EIOINTC | | AVECINTC | | LIOINTC | <-- | UARTs | + +---------+ +----------+ +---------+ +-------+ + ^ ^ + | | + +---------+ +---------+ + | PCH-PIC | | PCH-MSI | + +---------+ +---------+ + ^ ^ ^ + | | | + +---------+ +---------+ +---------+ + | Devices | | PCH-LPC | | Devices | + +---------+ +---------+ +---------+ + ^ + | + +---------+ + | Devices | + +---------+ + ACPI相关的定义 ============== diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index b3be87489108..e32471977d0a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4214,7 +4214,9 @@ whether or not KVM_CAP_X86_USER_SPACE_MSR's KVM_MSR_EXIT_REASON_FILTER is enabled. If KVM_MSR_EXIT_REASON_FILTER is enabled, KVM will exit to userspace on denied accesses, i.e. userspace effectively intercepts the MSR access. If KVM_MSR_EXIT_REASON_FILTER is not enabled, KVM will inject a #GP into the guest -on denied accesses. +on denied accesses. Note, if an MSR access is denied during emulation of MSR +load/stores during VMX transitions, KVM ignores KVM_MSR_EXIT_REASON_FILTER. +See the below warning for full details. If an MSR access is allowed by userspace, KVM will emulate and/or virtualize the access in accordance with the vCPU model. Note, KVM may still ultimately @@ -4229,9 +4231,22 @@ filtering. In that mode, ``KVM_MSR_FILTER_DEFAULT_DENY`` is invalid and causes an error. .. warning:: - MSR accesses as part of nested VM-Enter/VM-Exit are not filtered. - This includes both writes to individual VMCS fields and reads/writes - through the MSR lists pointed to by the VMCS. + MSR accesses that are side effects of instruction execution (emulated or + native) are not filtered as hardware does not honor MSR bitmaps outside of + RDMSR and WRMSR, and KVM mimics that behavior when emulating instructions + to avoid pointless divergence from hardware. E.g. RDPID reads MSR_TSC_AUX, + SYSENTER reads the SYSENTER MSRs, etc. + + MSRs that are loaded/stored via dedicated VMCS fields are not filtered as + part of VM-Enter/VM-Exit emulation. + + MSRs that are loaded/store via VMX's load/store lists _are_ filtered as part + of VM-Enter/VM-Exit emulation. If an MSR access is denied on VM-Enter, KVM + synthesizes a consistency check VM-Exit(EXIT_REASON_MSR_LOAD_FAIL). If an + MSR access is denied on VM-Exit, KVM synthesizes a VM-Abort. In short, KVM + extends Intel's architectural list of MSRs that cannot be loaded/saved via + the VM-Enter/VM-Exit MSR list. It is platform owner's responsibility to + to communicate any such restrictions to their end users. x2APIC MSR accesses cannot be filtered (KVM silently ignores filters that cover any x2APIC MSRs). @@ -8082,6 +8097,14 @@ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if guest CPUID on writes to MISC_ENABLE if KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is disabled. + +KVM_X86_QUIRK_SLOT_ZAP_ALL By default, KVM invalidates all SPTEs in + fast way for memslot deletion when VM type + is KVM_X86_DEFAULT_VM. + When this quirk is disabled or when VM type + is other than KVM_X86_DEFAULT_VM, KVM zaps + only leaf SPTEs that are within the range of + the memslot being deleted. =================================== ============================================ 7.32 KVM_CAP_MAX_VCPU_ID diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 02880d5552d5..20a9a37d1cdd 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -11,6 +11,8 @@ The acquisition orders for mutexes are as follows: - cpus_read_lock() is taken outside kvm_lock +- kvm_usage_lock is taken outside cpus_read_lock() + - kvm->lock is taken outside vcpu->mutex - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock @@ -24,6 +26,13 @@ The acquisition orders for mutexes are as follows: are taken on the waiting side when modifying memslots, so MMU notifiers must not take either kvm->slots_lock or kvm->slots_arch_lock. +cpus_read_lock() vs kvm_lock: + +- Taking cpus_read_lock() outside of kvm_lock is problematic, despite that + being the official ordering, as it is quite easy to unknowingly trigger + cpus_read_lock() while holding kvm_lock. Use caution when walking vm_list, + e.g. avoid complex operations when possible. + For SRCU: - ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections @@ -227,10 +236,16 @@ time it will be set using the Dirty tracking mechanism described above. :Type: mutex :Arch: any :Protects: - vm_list - - kvm_usage_count + +``kvm_usage_lock`` +^^^^^^^^^^^^^^^^^^ + +:Type: mutex +:Arch: any +:Protects: - kvm_usage_count - hardware virtualization enable/disable -:Comment: KVM also disables CPU hotplug via cpus_read_lock() during - enable/disable. +:Comment: Exists to allow taking cpus_read_lock() while kvm_usage_count is + protected, which simplifies the virtualization enabling logic. ``kvm->mn_invalidate_lock`` ^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -290,11 +305,12 @@ time it will be set using the Dirty tracking mechanism described above. wakeup. ``vendor_module_lock`` -^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +^^^^^^^^^^^^^^^^^^^^^^ :Type: mutex :Arch: x86 :Protects: loading a vendor module (kvm_amd or kvm_intel) -:Comment: Exists because using kvm_lock leads to deadlock. cpu_hotplug_lock is - taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and - many operations need to take cpu_hotplug_lock when loading a vendor module, - e.g. updating static calls. +:Comment: Exists because using kvm_lock leads to deadlock. kvm_lock is taken + in notifiers, e.g. __kvmclock_cpufreq_notifier(), that may be invoked while + cpu_hotplug_lock is held, e.g. from cpufreq_boost_trigger_state(), and many + operations need to take cpu_hotplug_lock when loading a vendor module, e.g. + updating static calls. diff --git a/Documentation/virt/uml/user_mode_linux_howto_v2.rst b/Documentation/virt/uml/user_mode_linux_howto_v2.rst index 27942446f406..584000b743f3 100644 --- a/Documentation/virt/uml/user_mode_linux_howto_v2.rst +++ b/Documentation/virt/uml/user_mode_linux_howto_v2.rst @@ -217,6 +217,8 @@ remote UML and other VM instances. +-----------+--------+------------------------------------+------------+ | fd | vector | dependent on fd type | varies | +-----------+--------+------------------------------------+------------+ +| vde | vector | dep. on VDE VPN: Virt.Net Locator | varies | ++-----------+--------+------------------------------------+------------+ | tuntap | legacy | none | ~ 500Mbit | +-----------+--------+------------------------------------+------------+ | daemon | legacy | none | ~ 450Mbit | @@ -573,6 +575,41 @@ https://github.com/NetSys/bess/wiki/Built-In-Modules-and-Ports BESS transport does not require any special privileges. +VDE vector transport +-------------------- + +Virtual Distributed Ethernet (VDE) is a project whose main goal is to provide a +highly flexible support for virtual networking. + +http://wiki.virtualsquare.org/#/tutorials/vdebasics + +Common usages of VDE include fast prototyping and teaching. + +Examples: + + ``vecX:transport=vde,vnl=tap://tap0`` + +use tap0 + + ``vecX:transport=vde,vnl=slirp://`` + +use slirp + + ``vec0:transport=vde,vnl=vde:///tmp/switch`` + +connect to a vde switch + + ``vecX:transport=\"vde,vnl=cmd://ssh remote.host //tmp/sshlirp\"`` + +connect to a remote slirp (instant VPN: convert ssh to VPN, it uses sshlirp) +https://github.com/virtualsquare/sshlirp + + ``vec0:transport=vde,vnl=vxvde://234.0.0.1`` + +connect to a local area cloud (all the UML nodes using the same +multicast address running on hosts in the same multicast domain (LAN) +will be automagically connected together to a virtual LAN. + Configuring Legacy transports ============================= diff --git a/Documentation/watchdog/convert_drivers_to_kernel_api.rst b/Documentation/watchdog/convert_drivers_to_kernel_api.rst index a1c3f038ce0e..e83609a5d007 100644 --- a/Documentation/watchdog/convert_drivers_to_kernel_api.rst +++ b/Documentation/watchdog/convert_drivers_to_kernel_api.rst @@ -75,7 +75,6 @@ Example conversion:: -static const struct file_operations s3c2410wdt_fops = { - .owner = THIS_MODULE, - - .llseek = no_llseek, - .write = s3c2410wdt_write, - .unlocked_ioctl = s3c2410wdt_ioctl, - .open = s3c2410wdt_open, diff --git a/MAINTAINERS b/MAINTAINERS index 00716c1faff6..c27f3190737f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5728,8 +5728,7 @@ L: linux-cxl@vger.kernel.org S: Maintained F: Documentation/driver-api/cxl F: drivers/cxl/ -F: include/linux/einj-cxl.h -F: include/linux/cxl-event.h +F: include/cxl/ F: include/uapi/linux/cxl_mem.h F: tools/testing/cxl/ @@ -15679,6 +15678,9 @@ F: include/dt-bindings/clock/mobileye,eyeq5-clk.h MODULE SUPPORT M: Luis Chamberlain <mcgrof@kernel.org> +R: Petr Pavlu <petr.pavlu@suse.com> +R: Sami Tolvanen <samitolvanen@google.com> +R: Daniel Gomez <da.gomez@samsung.com> L: linux-modules@vger.kernel.org L: linux-kernel@vger.kernel.org S: Maintained @@ -19345,10 +19347,7 @@ F: drivers/char/random.c F: include/linux/random.h F: include/uapi/linux/random.h F: drivers/virt/vmgenid.c -F: include/vdso/getrandom.h -F: lib/vdso/getrandom.c -F: arch/x86/entry/vdso/vgetrandom* -F: arch/x86/include/asm/vdso/getrandom* +N: ^.*/vdso/[^/]*getrandom[^/]+$ RAPIDIO SUBSYSTEM M: Matt Porter <mporter@kernel.crashing.org> diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index fe0764173cd0..a0d01c46e408 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2164,7 +2164,7 @@ static void cpu_hyp_uninit(void *discard) } } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { /* * Most calls to this function are made with migration @@ -2184,7 +2184,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_timer_cpu_down(); kvm_vgic_cpu_down(); @@ -2380,7 +2380,7 @@ static int __init do_pkvm_init(u32 hyp_va_bits) /* * The stub hypercalls are now disabled, so set our local flag to - * prevent a later re-init attempt in kvm_arch_hardware_enable(). + * prevent a later re-init attempt in kvm_arch_enable_virtualization_cpu(). */ __this_cpu_write(kvm_hyp_initialized, 1); preempt_enable(); diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 0eb0436ad4ce..bb35c34f86d2 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -25,6 +25,8 @@ config LOONGARCH select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL + select ARCH_HAS_SET_MEMORY + select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_INLINE_READ_LOCK if !PREEMPTION select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION @@ -82,6 +84,7 @@ config LOONGARCH select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_DEVICES + select GENERIC_CPU_VULNERABILITIES select GENERIC_ENTRY select GENERIC_GETTIMEOFDAY select GENERIC_IOREMAP if !ARCH_IOREMAP @@ -147,7 +150,7 @@ config LOONGARCH select HAVE_LIVEPATCH select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI - select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB && !CC_IS_CLANG + select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB select HAVE_PCI select HAVE_PERF_EVENTS select HAVE_PERF_REGS @@ -267,7 +270,7 @@ config AS_HAS_FCSR_CLASS def_bool $(as-instr,movfcsr2gr \$t0$(comma)\$fcsr0) config AS_HAS_THIN_ADD_SUB - def_bool $(cc-option,-Wa$(comma)-mthin-add-sub) + def_bool $(cc-option,-Wa$(comma)-mthin-add-sub) || AS_IS_LLVM config AS_HAS_LSX_EXTENSION def_bool $(as-instr,vld \$vr0$(comma)\$a0$(comma)0) diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h index 99af8b3160a8..c86f0ab922ec 100644 --- a/arch/loongarch/include/asm/atomic.h +++ b/arch/loongarch/include/asm/atomic.h @@ -15,6 +15,7 @@ #define __LL "ll.w " #define __SC "sc.w " #define __AMADD "amadd.w " +#define __AMOR "amor.w " #define __AMAND_DB "amand_db.w " #define __AMOR_DB "amor_db.w " #define __AMXOR_DB "amxor_db.w " @@ -22,6 +23,7 @@ #define __LL "ll.d " #define __SC "sc.d " #define __AMADD "amadd.d " +#define __AMOR "amor.d " #define __AMAND_DB "amand_db.d " #define __AMOR_DB "amor_db.d " #define __AMXOR_DB "amxor_db.d " diff --git a/arch/loongarch/include/asm/cpu-features.h b/arch/loongarch/include/asm/cpu-features.h index 16a716f88a5c..fc83bb32f9f0 100644 --- a/arch/loongarch/include/asm/cpu-features.h +++ b/arch/loongarch/include/asm/cpu-features.h @@ -51,6 +51,7 @@ #define cpu_has_lbt_mips cpu_opt(LOONGARCH_CPU_LBT_MIPS) #define cpu_has_lbt (cpu_has_lbt_x86|cpu_has_lbt_arm|cpu_has_lbt_mips) #define cpu_has_csr cpu_opt(LOONGARCH_CPU_CSR) +#define cpu_has_iocsr cpu_opt(LOONGARCH_CPU_IOCSR) #define cpu_has_tlb cpu_opt(LOONGARCH_CPU_TLB) #define cpu_has_watch cpu_opt(LOONGARCH_CPU_WATCH) #define cpu_has_vint cpu_opt(LOONGARCH_CPU_VINT) @@ -65,6 +66,7 @@ #define cpu_has_guestid cpu_opt(LOONGARCH_CPU_GUESTID) #define cpu_has_hypervisor cpu_opt(LOONGARCH_CPU_HYPERVISOR) #define cpu_has_ptw cpu_opt(LOONGARCH_CPU_PTW) +#define cpu_has_lspw cpu_opt(LOONGARCH_CPU_LSPW) #define cpu_has_avecint cpu_opt(LOONGARCH_CPU_AVECINT) #endif /* __ASM_CPU_FEATURES_H */ diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index 843f9c4ec980..98cf4d7b4b0a 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -87,19 +87,21 @@ enum cpu_type_enum { #define CPU_FEATURE_LBT_MIPS 12 /* CPU has MIPS Binary Translation */ #define CPU_FEATURE_TLB 13 /* CPU has TLB */ #define CPU_FEATURE_CSR 14 /* CPU has CSR */ -#define CPU_FEATURE_WATCH 15 /* CPU has watchpoint registers */ -#define CPU_FEATURE_VINT 16 /* CPU has vectored interrupts */ -#define CPU_FEATURE_CSRIPI 17 /* CPU has CSR-IPI */ -#define CPU_FEATURE_EXTIOI 18 /* CPU has EXT-IOI */ -#define CPU_FEATURE_PREFETCH 19 /* CPU has prefetch instructions */ -#define CPU_FEATURE_PMP 20 /* CPU has perfermance counter */ -#define CPU_FEATURE_SCALEFREQ 21 /* CPU supports cpufreq scaling */ -#define CPU_FEATURE_FLATMODE 22 /* CPU has flat mode */ -#define CPU_FEATURE_EIODECODE 23 /* CPU has EXTIOI interrupt pin decode mode */ -#define CPU_FEATURE_GUESTID 24 /* CPU has GuestID feature */ -#define CPU_FEATURE_HYPERVISOR 25 /* CPU has hypervisor (running in VM) */ -#define CPU_FEATURE_PTW 26 /* CPU has hardware page table walker */ -#define CPU_FEATURE_AVECINT 27 /* CPU has avec interrupt */ +#define CPU_FEATURE_IOCSR 15 /* CPU has IOCSR */ +#define CPU_FEATURE_WATCH 16 /* CPU has watchpoint registers */ +#define CPU_FEATURE_VINT 17 /* CPU has vectored interrupts */ +#define CPU_FEATURE_CSRIPI 18 /* CPU has CSR-IPI */ +#define CPU_FEATURE_EXTIOI 19 /* CPU has EXT-IOI */ +#define CPU_FEATURE_PREFETCH 20 /* CPU has prefetch instructions */ +#define CPU_FEATURE_PMP 21 /* CPU has perfermance counter */ +#define CPU_FEATURE_SCALEFREQ 22 /* CPU supports cpufreq scaling */ +#define CPU_FEATURE_FLATMODE 23 /* CPU has flat mode */ +#define CPU_FEATURE_EIODECODE 24 /* CPU has EXTIOI interrupt pin decode mode */ +#define CPU_FEATURE_GUESTID 25 /* CPU has GuestID feature */ +#define CPU_FEATURE_HYPERVISOR 26 /* CPU has hypervisor (running in VM) */ +#define CPU_FEATURE_PTW 27 /* CPU has hardware page table walker */ +#define CPU_FEATURE_LSPW 28 /* CPU has LSPW (lddir/ldpte instructions) */ +#define CPU_FEATURE_AVECINT 29 /* CPU has AVEC interrupt */ #define LOONGARCH_CPU_CPUCFG BIT_ULL(CPU_FEATURE_CPUCFG) #define LOONGARCH_CPU_LAM BIT_ULL(CPU_FEATURE_LAM) @@ -115,6 +117,7 @@ enum cpu_type_enum { #define LOONGARCH_CPU_LBT_ARM BIT_ULL(CPU_FEATURE_LBT_ARM) #define LOONGARCH_CPU_LBT_MIPS BIT_ULL(CPU_FEATURE_LBT_MIPS) #define LOONGARCH_CPU_TLB BIT_ULL(CPU_FEATURE_TLB) +#define LOONGARCH_CPU_IOCSR BIT_ULL(CPU_FEATURE_IOCSR) #define LOONGARCH_CPU_CSR BIT_ULL(CPU_FEATURE_CSR) #define LOONGARCH_CPU_WATCH BIT_ULL(CPU_FEATURE_WATCH) #define LOONGARCH_CPU_VINT BIT_ULL(CPU_FEATURE_VINT) @@ -128,6 +131,7 @@ enum cpu_type_enum { #define LOONGARCH_CPU_GUESTID BIT_ULL(CPU_FEATURE_GUESTID) #define LOONGARCH_CPU_HYPERVISOR BIT_ULL(CPU_FEATURE_HYPERVISOR) #define LOONGARCH_CPU_PTW BIT_ULL(CPU_FEATURE_PTW) +#define LOONGARCH_CPU_LSPW BIT_ULL(CPU_FEATURE_LSPW) #define LOONGARCH_CPU_AVECINT BIT_ULL(CPU_FEATURE_AVECINT) #endif /* _ASM_CPU_H */ diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 04bf1a7f903a..26542413a5b0 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -62,6 +62,7 @@ #define LOONGARCH_CPUCFG1 0x1 #define CPUCFG1_ISGR32 BIT(0) #define CPUCFG1_ISGR64 BIT(1) +#define CPUCFG1_ISA GENMASK(1, 0) #define CPUCFG1_PAGING BIT(2) #define CPUCFG1_IOCSR BIT(3) #define CPUCFG1_PABITS GENMASK(11, 4) diff --git a/arch/loongarch/include/asm/mmu_context.h b/arch/loongarch/include/asm/mmu_context.h index 9f97c3453b9c..304363bd3935 100644 --- a/arch/loongarch/include/asm/mmu_context.h +++ b/arch/loongarch/include/asm/mmu_context.h @@ -49,12 +49,12 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) /* Normal, classic get_new_mmu_context */ static inline void -get_new_mmu_context(struct mm_struct *mm, unsigned long cpu) +get_new_mmu_context(struct mm_struct *mm, unsigned long cpu, bool *need_flush) { u64 asid = asid_cache(cpu); if (!((++asid) & cpu_asid_mask(&cpu_data[cpu]))) - local_flush_tlb_user(); /* start new asid cycle */ + *need_flush = true; /* start new asid cycle */ cpu_context(cpu, mm) = asid_cache(cpu) = asid; } @@ -74,21 +74,34 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm) return 0; } +static inline void atomic_update_pgd_asid(unsigned long asid, unsigned long pgdl) +{ + __asm__ __volatile__( + "csrwr %[pgdl_val], %[pgdl_reg] \n\t" + "csrwr %[asid_val], %[asid_reg] \n\t" + : [asid_val] "+r" (asid), [pgdl_val] "+r" (pgdl) + : [asid_reg] "i" (LOONGARCH_CSR_ASID), [pgdl_reg] "i" (LOONGARCH_CSR_PGDL) + : "memory" + ); +} + static inline void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { + bool need_flush = false; unsigned int cpu = smp_processor_id(); /* Check if our ASID is of an older version and thus invalid */ if (!asid_valid(next, cpu)) - get_new_mmu_context(next, cpu); - - write_csr_asid(cpu_asid(cpu, next)); + get_new_mmu_context(next, cpu, &need_flush); if (next != &init_mm) - csr_write64((unsigned long)next->pgd, LOONGARCH_CSR_PGDL); + atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)next->pgd); else - csr_write64((unsigned long)invalid_pg_dir, LOONGARCH_CSR_PGDL); + atomic_update_pgd_asid(cpu_asid(cpu, next), (unsigned long)invalid_pg_dir); + + if (need_flush) + local_flush_tlb_user(); /* Flush tlb after update ASID */ /* * Mark current->active_mm as not "active" anymore. @@ -135,9 +148,15 @@ drop_mmu_context(struct mm_struct *mm, unsigned int cpu) asid = read_csr_asid() & cpu_asid_mask(¤t_cpu_data); if (asid == cpu_asid(cpu, mm)) { + bool need_flush = false; + if (!current->mm || (current->mm == mm)) { - get_new_mmu_context(mm, cpu); + get_new_mmu_context(mm, cpu, &need_flush); + write_csr_asid(cpu_asid(cpu, mm)); + if (need_flush) + local_flush_tlb_user(); /* Flush tlb after update ASID */ + goto out; } } diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index 8f290e5546cf..87be9b14e9da 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -68,75 +68,6 @@ PERCPU_OP(and, and, &) PERCPU_OP(or, or, |) #undef PERCPU_OP -static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size) -{ - unsigned long ret; - - switch (size) { - case 1: - __asm__ __volatile__ ("ldx.b %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - case 2: - __asm__ __volatile__ ("ldx.h %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - case 4: - __asm__ __volatile__ ("ldx.w %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - case 8: - __asm__ __volatile__ ("ldx.d %[ret], $r21, %[ptr] \n" - : [ret] "=&r"(ret) - : [ptr] "r"(ptr) - : "memory"); - break; - default: - ret = 0; - BUILD_BUG(); - } - - return ret; -} - -static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size) -{ - switch (size) { - case 1: - __asm__ __volatile__("stx.b %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - case 2: - __asm__ __volatile__("stx.h %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - case 4: - __asm__ __volatile__("stx.w %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - case 8: - __asm__ __volatile__("stx.d %[val], $r21, %[ptr] \n" - : - : [val] "r" (val), [ptr] "r" (ptr) - : "memory"); - break; - default: - BUILD_BUG(); - } -} - static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size) { switch (size) { @@ -157,6 +88,33 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, return 0; } +#define __pcpu_op_1(op) op ".b " +#define __pcpu_op_2(op) op ".h " +#define __pcpu_op_4(op) op ".w " +#define __pcpu_op_8(op) op ".d " + +#define _percpu_read(size, _pcp) \ +({ \ + typeof(_pcp) __pcp_ret; \ + \ + __asm__ __volatile__( \ + __pcpu_op_##size("ldx") "%[ret], $r21, %[ptr] \n" \ + : [ret] "=&r"(__pcp_ret) \ + : [ptr] "r"(&(_pcp)) \ + : "memory"); \ + \ + __pcp_ret; \ +}) + +#define _percpu_write(size, _pcp, _val) \ +do { \ + __asm__ __volatile__( \ + __pcpu_op_##size("stx") "%[val], $r21, %[ptr] \n" \ + : \ + : [val] "r"(_val), [ptr] "r"(&(_pcp)) \ + : "memory"); \ +} while (0) + /* this_cpu_cmpxchg */ #define _protect_cmpxchg_local(pcp, o, n) \ ({ \ @@ -167,18 +125,6 @@ static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, __ret; \ }) -#define _percpu_read(pcp) \ -({ \ - typeof(pcp) __retval; \ - __retval = (typeof(pcp))__percpu_read(&(pcp), sizeof(pcp)); \ - __retval; \ -}) - -#define _percpu_write(pcp, val) \ -do { \ - __percpu_write(&(pcp), (unsigned long)(val), sizeof(pcp)); \ -} while (0) \ - #define _pcp_protect(operation, pcp, val) \ ({ \ typeof(pcp) __retval; \ @@ -215,15 +161,15 @@ do { \ #define this_cpu_or_4(pcp, val) _percpu_or(pcp, val) #define this_cpu_or_8(pcp, val) _percpu_or(pcp, val) -#define this_cpu_read_1(pcp) _percpu_read(pcp) -#define this_cpu_read_2(pcp) _percpu_read(pcp) -#define this_cpu_read_4(pcp) _percpu_read(pcp) -#define this_cpu_read_8(pcp) _percpu_read(pcp) +#define this_cpu_read_1(pcp) _percpu_read(1, pcp) +#define this_cpu_read_2(pcp) _percpu_read(2, pcp) +#define this_cpu_read_4(pcp) _percpu_read(4, pcp) +#define this_cpu_read_8(pcp) _percpu_read(8, pcp) -#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val) +#define this_cpu_write_1(pcp, val) _percpu_write(1, pcp, val) +#define this_cpu_write_2(pcp, val) _percpu_write(2, pcp, val) +#define this_cpu_write_4(pcp, val) _percpu_write(4, pcp, val) +#define this_cpu_write_8(pcp, val) _percpu_write(8, pcp, val) #define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val) #define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 85431f20a14d..9965f52ef65b 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -331,29 +331,23 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) * Make sure the buddy is global too (if it's !none, * it better already be global) */ + if (pte_none(ptep_get(buddy))) { #ifdef CONFIG_SMP - /* - * For SMP, multiple CPUs can race, so we need to do - * this atomically. - */ - unsigned long page_global = _PAGE_GLOBAL; - unsigned long tmp; - - __asm__ __volatile__ ( - "1:" __LL "%[tmp], %[buddy] \n" - " bnez %[tmp], 2f \n" - " or %[tmp], %[tmp], %[global] \n" - __SC "%[tmp], %[buddy] \n" - " beqz %[tmp], 1b \n" - " nop \n" - "2: \n" - __WEAK_LLSC_MB - : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) - : [global] "r" (page_global)); + /* + * For SMP, multiple CPUs can race, so we need + * to do this atomically. + */ + __asm__ __volatile__( + __AMOR "$zero, %[global], %[buddy] \n" + : [buddy] "+ZB" (buddy->pte) + : [global] "r" (_PAGE_GLOBAL) + : "memory"); + + DBAR(0b11000); /* o_wrw = 0b11000 */ #else /* !CONFIG_SMP */ - if (pte_none(ptep_get(buddy))) WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL)); #endif /* CONFIG_SMP */ + } } } diff --git a/arch/loongarch/include/asm/set_memory.h b/arch/loongarch/include/asm/set_memory.h new file mode 100644 index 000000000000..d70505b6676c --- /dev/null +++ b/arch/loongarch/include/asm/set_memory.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#ifndef _ASM_LOONGARCH_SET_MEMORY_H +#define _ASM_LOONGARCH_SET_MEMORY_H + +/* + * Functions to change memory attributes. + */ +int set_memory_x(unsigned long addr, int numpages); +int set_memory_nx(unsigned long addr, int numpages); +int set_memory_ro(unsigned long addr, int numpages); +int set_memory_rw(unsigned long addr, int numpages); + +bool kernel_page_present(struct page *page); +int set_direct_map_default_noflush(struct page *page); +int set_direct_map_invalid_noflush(struct page *page); + +#endif /* _ASM_LOONGARCH_SET_MEMORY_H */ diff --git a/arch/loongarch/include/uapi/asm/hwcap.h b/arch/loongarch/include/uapi/asm/hwcap.h index 6955a7cb2c65..2b34e56cfa9e 100644 --- a/arch/loongarch/include/uapi/asm/hwcap.h +++ b/arch/loongarch/include/uapi/asm/hwcap.h @@ -17,5 +17,6 @@ #define HWCAP_LOONGARCH_LBT_ARM (1 << 11) #define HWCAP_LOONGARCH_LBT_MIPS (1 << 12) #define HWCAP_LOONGARCH_PTW (1 << 13) +#define HWCAP_LOONGARCH_LSPW (1 << 14) #endif /* _UAPI_ASM_HWCAP_H */ diff --git a/arch/loongarch/include/uapi/asm/sigcontext.h b/arch/loongarch/include/uapi/asm/sigcontext.h index 6c22f616b8f1..5cd121275bac 100644 --- a/arch/loongarch/include/uapi/asm/sigcontext.h +++ b/arch/loongarch/include/uapi/asm/sigcontext.h @@ -9,7 +9,6 @@ #define _UAPI_ASM_SIGCONTEXT_H #include <linux/types.h> -#include <linux/posix_types.h> /* FP context was used */ #define SC_USED_FP (1 << 0) diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 929a497c987e..f1a74b80f22c 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -9,6 +9,7 @@ #include <linux/init.h> #include <linux/acpi.h> +#include <linux/efi-bgrt.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/memblock.h> @@ -212,6 +213,9 @@ void __init acpi_boot_table_init(void) /* Do not enable ACPI SPCR console by default */ acpi_parse_spcr(earlycon_acpi_spcr_enable, false); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); + return; fdt_earlycon: diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 14f0449f5452..cbce099037b2 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -91,12 +91,30 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) unsigned int config; unsigned long asid_mask; - c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | - LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH; + c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | LOONGARCH_CPU_VINT; elf_hwcap = HWCAP_LOONGARCH_CPUCFG; config = read_cpucfg(LOONGARCH_CPUCFG1); + + switch (config & CPUCFG1_ISA) { + case 0: + set_isa(c, LOONGARCH_CPU_ISA_LA32R); + break; + case 1: + set_isa(c, LOONGARCH_CPU_ISA_LA32S); + break; + case 2: + set_isa(c, LOONGARCH_CPU_ISA_LA64); + break; + default: + pr_warn("Warning: unknown ISA level\n"); + } + + if (config & CPUCFG1_PAGING) + c->options |= LOONGARCH_CPU_TLB; + if (config & CPUCFG1_IOCSR) + c->options |= LOONGARCH_CPU_IOCSR; if (config & CPUCFG1_UAL) { c->options |= LOONGARCH_CPU_UAL; elf_hwcap |= HWCAP_LOONGARCH_UAL; @@ -139,6 +157,10 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options |= LOONGARCH_CPU_PTW; elf_hwcap |= HWCAP_LOONGARCH_PTW; } + if (config & CPUCFG2_LSPW) { + c->options |= LOONGARCH_CPU_LSPW; + elf_hwcap |= HWCAP_LOONGARCH_LSPW; + } if (config & CPUCFG2_LVZP) { c->options |= LOONGARCH_CPU_LVZ; elf_hwcap |= HWCAP_LOONGARCH_LVZ; @@ -162,22 +184,6 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) if (config & CPUCFG6_PMP) c->options |= LOONGARCH_CPU_PMP; - config = iocsr_read32(LOONGARCH_IOCSR_FEATURES); - if (config & IOCSRF_CSRIPI) - c->options |= LOONGARCH_CPU_CSRIPI; - if (config & IOCSRF_EXTIOI) - c->options |= LOONGARCH_CPU_EXTIOI; - if (config & IOCSRF_FREQSCALE) - c->options |= LOONGARCH_CPU_SCALEFREQ; - if (config & IOCSRF_FLATMODE) - c->options |= LOONGARCH_CPU_FLATMODE; - if (config & IOCSRF_EIODECODE) - c->options |= LOONGARCH_CPU_EIODECODE; - if (config & IOCSRF_AVEC) - c->options |= LOONGARCH_CPU_AVECINT; - if (config & IOCSRF_VM) - c->options |= LOONGARCH_CPU_HYPERVISOR; - config = csr_read32(LOONGARCH_CSR_ASID); config = (config & CSR_ASID_BIT) >> CSR_ASID_BIT_SHIFT; asid_mask = GENMASK(config - 1, 0); @@ -210,6 +216,9 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) default: pr_warn("Warning: unknown TLB type\n"); } + + if (get_num_brps() + get_num_wrps()) + c->options |= LOONGARCH_CPU_WATCH; } #define MAX_NAME_LEN 32 @@ -220,52 +229,67 @@ static char cpu_full_name[MAX_NAME_LEN] = " - "; static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int cpu) { + uint32_t config; uint64_t *vendor = (void *)(&cpu_full_name[VENDOR_OFFSET]); uint64_t *cpuname = (void *)(&cpu_full_name[CPUNAME_OFFSET]); + const char *core_name = "Unknown"; - if (!__cpu_full_name[cpu]) - __cpu_full_name[cpu] = cpu_full_name; - - *vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR); - *cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME); - - switch (c->processor_id & PRID_SERIES_MASK) { - case PRID_SERIES_LA132: + switch (BIT(fls(c->isa_level) - 1)) { + case LOONGARCH_CPU_ISA_LA32R: + case LOONGARCH_CPU_ISA_LA32S: c->cputype = CPU_LOONGSON32; - set_isa(c, LOONGARCH_CPU_ISA_LA32S); __cpu_family[cpu] = "Loongson-32bit"; - pr_info("32-bit Loongson Processor probed (LA132 Core)\n"); break; - case PRID_SERIES_LA264: + case LOONGARCH_CPU_ISA_LA64: c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA264 Core)\n"); + break; + } + + switch (c->processor_id & PRID_SERIES_MASK) { + case PRID_SERIES_LA132: + core_name = "LA132"; + break; + case PRID_SERIES_LA264: + core_name = "LA264"; break; case PRID_SERIES_LA364: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA364 Core)\n"); + core_name = "LA364"; break; case PRID_SERIES_LA464: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA464 Core)\n"); + core_name = "LA464"; break; case PRID_SERIES_LA664: - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (LA664 Core)\n"); + core_name = "LA664"; break; - default: /* Default to 64 bit */ - c->cputype = CPU_LOONGSON64; - set_isa(c, LOONGARCH_CPU_ISA_LA64); - __cpu_family[cpu] = "Loongson-64bit"; - pr_info("64-bit Loongson Processor probed (Unknown Core)\n"); } + + pr_info("%s Processor probed (%s Core)\n", __cpu_family[cpu], core_name); + + if (!cpu_has_iocsr) + return; + + if (!__cpu_full_name[cpu]) + __cpu_full_name[cpu] = cpu_full_name; + + *vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR); + *cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME); + + config = iocsr_read32(LOONGARCH_IOCSR_FEATURES); + if (config & IOCSRF_CSRIPI) + c->options |= LOONGARCH_CPU_CSRIPI; + if (config & IOCSRF_EXTIOI) + c->options |= LOONGARCH_CPU_EXTIOI; + if (config & IOCSRF_FREQSCALE) + c->options |= LOONGARCH_CPU_SCALEFREQ; + if (config & IOCSRF_FLATMODE) + c->options |= LOONGARCH_CPU_FLATMODE; + if (config & IOCSRF_EIODECODE) + c->options |= LOONGARCH_CPU_EIODECODE; + if (config & IOCSRF_AVEC) + c->options |= LOONGARCH_CPU_AVECINT; + if (config & IOCSRF_VM) + c->options |= LOONGARCH_CPU_HYPERVISOR; } #ifdef CONFIG_64BIT diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c index 0d33cbc47e51..6ce46d92f1f1 100644 --- a/arch/loongarch/kernel/proc.c +++ b/arch/loongarch/kernel/proc.c @@ -31,6 +31,7 @@ int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v) static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; + unsigned int isa = cpu_data[n].isa_level; unsigned int version = cpu_data[n].processor_id & 0xff; unsigned int fp_version = cpu_data[n].fpu_vers; struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args; @@ -64,9 +65,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) cpu_pabits + 1, cpu_vabits + 1); seq_printf(m, "ISA\t\t\t:"); - if (cpu_has_loongarch32) - seq_printf(m, " loongarch32"); - if (cpu_has_loongarch64) + if (isa & LOONGARCH_CPU_ISA_LA32R) + seq_printf(m, " loongarch32r"); + if (isa & LOONGARCH_CPU_ISA_LA32S) + seq_printf(m, " loongarch32s"); + if (isa & LOONGARCH_CPU_ISA_LA64) seq_printf(m, " loongarch64"); seq_printf(m, "\n"); @@ -81,6 +84,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_complex) seq_printf(m, " complex"); if (cpu_has_crypto) seq_printf(m, " crypto"); if (cpu_has_ptw) seq_printf(m, " ptw"); + if (cpu_has_lspw) seq_printf(m, " lspw"); if (cpu_has_lvz) seq_printf(m, " lvz"); if (cpu_has_lbt_x86) seq_printf(m, " lbt_x86"); if (cpu_has_lbt_arm) seq_printf(m, " lbt_arm"); diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c index ba5d0930a74f..168bd97540f8 100644 --- a/arch/loongarch/kernel/syscall.c +++ b/arch/loongarch/kernel/syscall.c @@ -79,7 +79,3 @@ void noinstr __no_stack_protector do_syscall(struct pt_regs *regs) syscall_exit_to_user_mode(regs); } - -#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET -STACK_FRAME_NON_STANDARD(do_syscall); -#endif diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index 844736b99d38..27e9b94c0a0b 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -261,7 +261,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -ENOIOCTLCMD; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { unsigned long env, gcfg = 0; @@ -300,7 +300,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { write_csr_gcfg(0); write_csr_gstat(0); diff --git a/arch/loongarch/mm/Makefile b/arch/loongarch/mm/Makefile index e4d1e581dbae..278be2c8fc36 100644 --- a/arch/loongarch/mm/Makefile +++ b/arch/loongarch/mm/Makefile @@ -4,7 +4,8 @@ # obj-y += init.o cache.o tlb.o tlbex.o extable.o \ - fault.o ioremap.o maccess.o mmap.o pgtable.o page.o + fault.o ioremap.o maccess.o mmap.o pgtable.o \ + page.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_KASAN) += kasan_init.o diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 97b40defde06..deefd9617d00 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -31,11 +31,52 @@ int show_unhandled_signals = 1; +static int __kprobes spurious_fault(unsigned long write, unsigned long address) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if (!(address & __UA_LIMIT)) + return 0; + + pgd = pgd_offset_k(address); + if (!pgd_present(pgdp_get(pgd))) + return 0; + + p4d = p4d_offset(pgd, address); + if (!p4d_present(p4dp_get(p4d))) + return 0; + + pud = pud_offset(p4d, address); + if (!pud_present(pudp_get(pud))) + return 0; + + pmd = pmd_offset(pud, address); + if (!pmd_present(pmdp_get(pmd))) + return 0; + + if (pmd_leaf(*pmd)) { + return write ? pmd_write(pmdp_get(pmd)) : 1; + } else { + pte = pte_offset_kernel(pmd, address); + if (!pte_present(ptep_get(pte))) + return 0; + + return write ? pte_write(ptep_get(pte)) : 1; + } +} + static void __kprobes no_context(struct pt_regs *regs, unsigned long write, unsigned long address) { const int field = sizeof(unsigned long) * 2; + if (spurious_fault(write, address)) + return; + /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) return; diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c new file mode 100644 index 000000000000..ffd8d76021d4 --- /dev/null +++ b/arch/loongarch/mm/pageattr.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Loongson Technology Corporation Limited + */ + +#include <linux/pagewalk.h> +#include <linux/pgtable.h> +#include <asm/set_memory.h> +#include <asm/tlbflush.h> + +struct pageattr_masks { + pgprot_t set_mask; + pgprot_t clear_mask; +}; + +static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk) +{ + unsigned long new_val = val; + struct pageattr_masks *masks = walk->private; + + new_val &= ~(pgprot_val(masks->clear_mask)); + new_val |= (pgprot_val(masks->set_mask)); + + return new_val; +} + +static int pageattr_pgd_entry(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pgd_t val = pgdp_get(pgd); + + if (pgd_leaf(val)) { + val = __pgd(set_pageattr_masks(pgd_val(val), walk)); + set_pgd(pgd, val); + } + + return 0; +} + +static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + p4d_t val = p4dp_get(p4d); + + if (p4d_leaf(val)) { + val = __p4d(set_pageattr_masks(p4d_val(val), walk)); + set_p4d(p4d, val); + } + + return 0; +} + +static int pageattr_pud_entry(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pud_t val = pudp_get(pud); + + if (pud_leaf(val)) { + val = __pud(set_pageattr_masks(pud_val(val), walk)); + set_pud(pud, val); + } + + return 0; +} + +static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pmd_t val = pmdp_get(pmd); + + if (pmd_leaf(val)) { + val = __pmd(set_pageattr_masks(pmd_val(val), walk)); + set_pmd(pmd, val); + } + + return 0; +} + +static int pageattr_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t val = ptep_get(pte); + + val = __pte(set_pageattr_masks(pte_val(val), walk)); + set_pte(pte, val); + + return 0; +} + +static int pageattr_pte_hole(unsigned long addr, unsigned long next, + int depth, struct mm_walk *walk) +{ + return 0; +} + +static const struct mm_walk_ops pageattr_ops = { + .pgd_entry = pageattr_pgd_entry, + .p4d_entry = pageattr_p4d_entry, + .pud_entry = pageattr_pud_entry, + .pmd_entry = pageattr_pmd_entry, + .pte_entry = pageattr_pte_entry, + .pte_hole = pageattr_pte_hole, + .walk_lock = PGWALK_RDLOCK, +}; + +static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, pgprot_t clear_mask) +{ + int ret; + unsigned long start = addr; + unsigned long end = start + PAGE_SIZE * numpages; + struct pageattr_masks masks = { + .set_mask = set_mask, + .clear_mask = clear_mask + }; + + if (!numpages) + return 0; + + mmap_write_lock(&init_mm); + ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, &masks); + mmap_write_unlock(&init_mm); + + flush_tlb_kernel_range(start, end); + + return ret; +} + +int set_memory_x(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_NO_EXEC)); +} + +int set_memory_nx(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(_PAGE_NO_EXEC), __pgprot(0)); +} + +int set_memory_ro(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_WRITE | _PAGE_DIRTY)); +} + +int set_memory_rw(unsigned long addr, int numpages) +{ + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, numpages, __pgprot(_PAGE_WRITE | _PAGE_DIRTY), __pgprot(0)); +} + +bool kernel_page_present(struct page *page) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long addr = (unsigned long)page_address(page); + + if (addr < vm_map_base) + return true; + + pgd = pgd_offset_k(addr); + if (pgd_none(pgdp_get(pgd))) + return false; + if (pgd_leaf(pgdp_get(pgd))) + return true; + + p4d = p4d_offset(pgd, addr); + if (p4d_none(p4dp_get(p4d))) + return false; + if (p4d_leaf(p4dp_get(p4d))) + return true; + + pud = pud_offset(p4d, addr); + if (pud_none(pudp_get(pud))) + return false; + if (pud_leaf(pudp_get(pud))) + return true; + + pmd = pmd_offset(pud, addr); + if (pmd_none(pmdp_get(pmd))) + return false; + if (pmd_leaf(pmdp_get(pmd))) + return true; + + pte = pte_offset_kernel(pmd, addr); + return pte_present(ptep_get(pte)); +} + +int set_direct_map_default_noflush(struct page *page) +{ + unsigned long addr = (unsigned long)page_address(page); + + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, 1, PAGE_KERNEL, __pgprot(0)); +} + +int set_direct_map_invalid_noflush(struct page *page) +{ + unsigned long addr = (unsigned long)page_address(page); + + if (addr < vm_map_base) + return 0; + + return __set_memory(addr, 1, __pgprot(0), __pgprot(_PAGE_PRESENT | _PAGE_VALID)); +} diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c index 365f7de771cb..1da4dc46df43 100644 --- a/arch/loongarch/pci/acpi.c +++ b/arch/loongarch/pci/acpi.c @@ -225,6 +225,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) if (bus) { memcpy(bus->sysdata, info->cfg, sizeof(struct pci_config_window)); kfree(info); + kfree(root_ops); } else { struct pci_bus *child; diff --git a/arch/loongarch/vdso/vgetrandom-chacha.S b/arch/loongarch/vdso/vgetrandom-chacha.S index 7e86a50f6e85..c2733e6c3a8d 100644 --- a/arch/loongarch/vdso/vgetrandom-chacha.S +++ b/arch/loongarch/vdso/vgetrandom-chacha.S @@ -9,23 +9,11 @@ .text -/* Salsa20 quarter-round */ -.macro QR a b c d - add.w \a, \a, \b - xor \d, \d, \a - rotri.w \d, \d, 16 - - add.w \c, \c, \d - xor \b, \b, \c - rotri.w \b, \b, 20 - - add.w \a, \a, \b - xor \d, \d, \a - rotri.w \d, \d, 24 - - add.w \c, \c, \d - xor \b, \b, \c - rotri.w \b, \b, 25 +.macro OP_4REG op d0 d1 d2 d3 s0 s1 s2 s3 + \op \d0, \d0, \s0 + \op \d1, \d1, \s1 + \op \d2, \d2, \s2 + \op \d3, \d3, \s3 .endm /* @@ -74,6 +62,23 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) /* Reuse i as copy3 */ #define copy3 i +/* Packs to be used with OP_4REG */ +#define line0 state0, state1, state2, state3 +#define line1 state4, state5, state6, state7 +#define line2 state8, state9, state10, state11 +#define line3 state12, state13, state14, state15 + +#define line1_perm state5, state6, state7, state4 +#define line2_perm state10, state11, state8, state9 +#define line3_perm state15, state12, state13, state14 + +#define copy copy0, copy1, copy2, copy3 + +#define _16 16, 16, 16, 16 +#define _20 20, 20, 20, 20 +#define _24 24, 24, 24, 24 +#define _25 25, 25, 25, 25 + /* * The ABI requires s0-s9 saved, and sp aligned to 16-byte. * This does not violate the stack-less requirement: no sensitive data @@ -126,16 +131,38 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) li.w i, 10 .Lpermute: /* odd round */ - QR state0, state4, state8, state12 - QR state1, state5, state9, state13 - QR state2, state6, state10, state14 - QR state3, state7, state11, state15 + OP_4REG add.w line0, line1 + OP_4REG xor line3, line0 + OP_4REG rotri.w line3, _16 + + OP_4REG add.w line2, line3 + OP_4REG xor line1, line2 + OP_4REG rotri.w line1, _20 + + OP_4REG add.w line0, line1 + OP_4REG xor line3, line0 + OP_4REG rotri.w line3, _24 + + OP_4REG add.w line2, line3 + OP_4REG xor line1, line2 + OP_4REG rotri.w line1, _25 /* even round */ - QR state0, state5, state10, state15 - QR state1, state6, state11, state12 - QR state2, state7, state8, state13 - QR state3, state4, state9, state14 + OP_4REG add.w line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG rotri.w line3_perm, _16 + + OP_4REG add.w line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG rotri.w line1_perm, _20 + + OP_4REG add.w line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG rotri.w line3_perm, _24 + + OP_4REG add.w line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG rotri.w line1_perm, _25 addi.w i, i, -1 bnez i, .Lpermute @@ -147,10 +174,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) li.w copy3, 0x6b206574 /* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */ - add.w state0, state0, copy0 - add.w state1, state1, copy1 - add.w state2, state2, copy2 - add.w state3, state3, copy3 + OP_4REG add.w line0, copy st.w state0, output, 0 st.w state1, output, 4 st.w state2, output, 8 @@ -165,10 +189,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) ld.w state3, key, 12 /* output[4,5,6,7] = state[0,1,2,3] + state[4,5,6,7] */ - add.w state4, state4, state0 - add.w state5, state5, state1 - add.w state6, state6, state2 - add.w state7, state7, state3 + OP_4REG add.w line1, line0 st.w state4, output, 16 st.w state5, output, 20 st.w state6, output, 24 @@ -181,10 +202,7 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) ld.w state3, key, 28 /* output[8,9,10,11] = state[0,1,2,3] + state[8,9,10,11] */ - add.w state8, state8, state0 - add.w state9, state9, state1 - add.w state10, state10, state2 - add.w state11, state11, state3 + OP_4REG add.w line2, line0 st.w state8, output, 32 st.w state9, output, 36 st.w state10, output, 40 diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6743a57c1ab4..f7222eb594ea 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -728,8 +728,8 @@ struct kvm_mips_callbacks { int (*handle_fpe)(struct kvm_vcpu *vcpu); int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); int (*handle_guest_exit)(struct kvm_vcpu *vcpu); - int (*hardware_enable)(void); - void (*hardware_disable)(void); + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); int (*check_extension)(struct kvm *kvm, long ext); int (*vcpu_init)(struct kvm_vcpu *vcpu); void (*vcpu_uninit)(struct kvm_vcpu *vcpu); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b5de770b092e..60b43ea85c12 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -125,14 +125,14 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return 1; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { - return kvm_mips_callbacks->hardware_enable(); + return kvm_mips_callbacks->enable_virtualization_cpu(); } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { - kvm_mips_callbacks->hardware_disable(); + kvm_mips_callbacks->disable_virtualization_cpu(); } int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index 99d5a71e4300..ccab4d76b126 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -2869,7 +2869,7 @@ static unsigned int kvm_vz_resize_guest_vtlb(unsigned int size) return ret + 1; } -static int kvm_vz_hardware_enable(void) +static int kvm_vz_enable_virtualization_cpu(void) { unsigned int mmu_size, guest_mmu_size, ftlb_size; u64 guest_cvmctl, cvmvmconfig; @@ -2983,7 +2983,7 @@ static int kvm_vz_hardware_enable(void) return 0; } -static void kvm_vz_hardware_disable(void) +static void kvm_vz_disable_virtualization_cpu(void) { u64 cvmvmconfig; unsigned int mmu_size; @@ -3280,8 +3280,8 @@ static struct kvm_mips_callbacks kvm_vz_callbacks = { .handle_msa_disabled = kvm_trap_vz_handle_msa_disabled, .handle_guest_exit = kvm_trap_vz_handle_guest_exit, - .hardware_enable = kvm_vz_hardware_enable, - .hardware_disable = kvm_vz_hardware_disable, + .enable_virtualization_cpu = kvm_vz_enable_virtualization_cpu, + .disable_virtualization_cpu = kvm_vz_disable_virtualization_cpu, .check_extension = kvm_vz_check_extension, .vcpu_init = kvm_vz_vcpu_init, .vcpu_uninit = kvm_vz_vcpu_uninit, diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c index b0f0816879df..5e8e37a722ef 100644 --- a/arch/parisc/kernel/perf.c +++ b/arch/parisc/kernel/perf.c @@ -466,7 +466,6 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } static const struct file_operations perf_fops = { - .llseek = no_llseek, .read = perf_read, .write = perf_write, .unlocked_ioctl = perf_ioctl, diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index bab2ec34cd87..f3427f6de608 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -20,7 +20,7 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_hardware_enable(void) +int kvm_arch_enable_virtualization_cpu(void) { csr_write(CSR_HEDELEG, KVM_HEDELEG_DEFAULT); csr_write(CSR_HIDELEG, KVM_HIDELEG_DEFAULT); @@ -35,7 +35,7 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { kvm_riscv_aia_disable(); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 7ec1b8cd0de9..9b57add02cd5 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -59,6 +59,7 @@ CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_S390_HYPFS_FS=y CONFIG_KVM=m +CONFIG_KVM_S390_UCONTROL=y CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m CONFIG_S390_MODULES_SANITY_TEST=m diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 0e855c5e91c5..5d9effb0867c 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -76,7 +76,6 @@ static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations dbfs_ops = { .read = dbfs_read, - .llseek = no_llseek, .unlocked_ioctl = dbfs_ioctl, }; diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 858beaf4a8cb..d428635abf08 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -443,7 +443,6 @@ static const struct file_operations hypfs_file_ops = { .release = hypfs_release, .read_iter = hypfs_read_iter, .write_iter = hypfs_write_iter, - .llseek = no_llseek, }; static struct file_system_type hypfs_type = { diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index bce50ca75ea7..e62bea9ab21e 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -163,7 +163,6 @@ static const struct file_operations debug_file_ops = { .write = debug_input, .open = debug_open, .release = debug_close, - .llseek = no_llseek, }; static struct dentry *debug_debugfs_root_entry; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 18b0d025f3a2..e2e0aa463fbd 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -1698,7 +1698,6 @@ static const struct file_operations cfset_fops = { .release = cfset_release, .unlocked_ioctl = cfset_ioctl, .compat_ioctl = cfset_ioctl, - .llseek = no_llseek }; static struct miscdevice cfset_dev = { diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index 2be30a96696a..88055f58fbda 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -498,7 +498,6 @@ static const struct file_operations stsi_##fc##_##s1##_##s2##_fs_ops = { \ .open = stsi_open_##fc##_##s1##_##s2, \ .release = stsi_release, \ .read = stsi_read, \ - .llseek = no_llseek, \ }; static int stsi_release(struct inode *inode, struct file *file) diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index e26e68675c08..aa06c85bcbd3 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -13,10 +13,7 @@ * for details. */ .macro vdso_func func - .globl __kernel_\func - .type __kernel_\func,@function - __ALIGN -__kernel_\func: +SYM_FUNC_START(__kernel_\func) CFI_STARTPROC aghi %r15,-STACK_FRAME_VDSO_OVERHEAD CFI_DEF_CFA_OFFSET (STACK_FRAME_USER_OVERHEAD + STACK_FRAME_VDSO_OVERHEAD) @@ -32,7 +29,7 @@ __kernel_\func: CFI_RESTORE 15 br %r14 CFI_ENDPROC - .size __kernel_\func,.-__kernel_\func +SYM_FUNC_END(__kernel_\func) .endm vdso_func gettimeofday @@ -41,16 +38,13 @@ vdso_func clock_gettime vdso_func getcpu .macro vdso_syscall func,syscall - .globl __kernel_\func - .type __kernel_\func,@function - __ALIGN -__kernel_\func: +SYM_FUNC_START(__kernel_\func) CFI_STARTPROC svc \syscall /* Make sure we notice when a syscall returns, which shouldn't happen */ .word 0 CFI_ENDPROC - .size __kernel_\func,.-__kernel_\func +SYM_FUNC_END(__kernel_\func) .endm vdso_syscall restart_syscall,__NR_restart_syscall diff --git a/arch/s390/kernel/vdso64/vgetrandom-chacha.S b/arch/s390/kernel/vdso64/vgetrandom-chacha.S index d802b0a96f41..09c034c2f853 100644 --- a/arch/s390/kernel/vdso64/vgetrandom-chacha.S +++ b/arch/s390/kernel/vdso64/vgetrandom-chacha.S @@ -1,7 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/stringify.h> #include <linux/linkage.h> #include <asm/alternative.h> +#include <asm/dwarf.h> #include <asm/fpu-insn.h> #define STATE0 %v0 @@ -12,9 +14,6 @@ #define COPY1 %v5 #define COPY2 %v6 #define COPY3 %v7 -#define PERM4 %v16 -#define PERM8 %v17 -#define PERM12 %v18 #define BEPERM %v19 #define TMP0 %v20 #define TMP1 %v21 @@ -23,13 +22,11 @@ .section .rodata - .balign 128 -.Lconstants: + .balign 32 +SYM_DATA_START_LOCAL(chacha20_constants) .long 0x61707865,0x3320646e,0x79622d32,0x6b206574 # endian-neutral - .long 0x04050607,0x08090a0b,0x0c0d0e0f,0x00010203 # rotl 4 bytes - .long 0x08090a0b,0x0c0d0e0f,0x00010203,0x04050607 # rotl 8 bytes - .long 0x0c0d0e0f,0x00010203,0x04050607,0x08090a0b # rotl 12 bytes .long 0x03020100,0x07060504,0x0b0a0908,0x0f0e0d0c # byte swap +SYM_DATA_END(chacha20_constants) .text /* @@ -43,13 +40,14 @@ * size_t nblocks) */ SYM_FUNC_START(__arch_chacha20_blocks_nostack) - larl %r1,.Lconstants + CFI_STARTPROC + larl %r1,chacha20_constants /* COPY0 = "expand 32-byte k" */ VL COPY0,0,,%r1 - /* PERM4-PERM12,BEPERM = byte selectors for VPERM */ - VLM PERM4,BEPERM,16,%r1 + /* BEPERM = byte selectors for VPERM */ + ALTERNATIVE __stringify(VL BEPERM,16,,%r1), "brcl 0,0", ALT_FACILITY(148) /* COPY1,COPY2 = key */ VLM COPY1,COPY2,0,%r3 @@ -89,11 +87,11 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) VERLLF STATE1,STATE1,7 /* STATE1[0,1,2,3] = STATE1[1,2,3,0] */ - VPERM STATE1,STATE1,STATE1,PERM4 + VSLDB STATE1,STATE1,STATE1,4 /* STATE2[0,1,2,3] = STATE2[2,3,0,1] */ - VPERM STATE2,STATE2,STATE2,PERM8 + VSLDB STATE2,STATE2,STATE2,8 /* STATE3[0,1,2,3] = STATE3[3,0,1,2] */ - VPERM STATE3,STATE3,STATE3,PERM12 + VSLDB STATE3,STATE3,STATE3,12 /* STATE0 += STATE1, STATE3 = rotl32(STATE3 ^ STATE0, 16) */ VAF STATE0,STATE0,STATE1 @@ -116,32 +114,38 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) VERLLF STATE1,STATE1,7 /* STATE1[0,1,2,3] = STATE1[3,0,1,2] */ - VPERM STATE1,STATE1,STATE1,PERM12 + VSLDB STATE1,STATE1,STATE1,12 /* STATE2[0,1,2,3] = STATE2[2,3,0,1] */ - VPERM STATE2,STATE2,STATE2,PERM8 + VSLDB STATE2,STATE2,STATE2,8 /* STATE3[0,1,2,3] = STATE3[1,2,3,0] */ - VPERM STATE3,STATE3,STATE3,PERM4 + VSLDB STATE3,STATE3,STATE3,4 brctg %r0,.Ldoubleround - /* OUTPUT0 = STATE0 + STATE0 */ + /* OUTPUT0 = STATE0 + COPY0 */ VAF STATE0,STATE0,COPY0 - /* OUTPUT1 = STATE1 + STATE1 */ + /* OUTPUT1 = STATE1 + COPY1 */ VAF STATE1,STATE1,COPY1 - /* OUTPUT2 = STATE2 + STATE2 */ + /* OUTPUT2 = STATE2 + COPY2 */ VAF STATE2,STATE2,COPY2 - /* OUTPUT2 = STATE3 + STATE3 */ + /* OUTPUT3 = STATE3 + COPY3 */ VAF STATE3,STATE3,COPY3 - /* - * 32 bit wise little endian store to OUTPUT. If the vector - * enhancement facility 2 is not installed use the slow path. - */ - ALTERNATIVE "brc 0xf,.Lstoreslow", "nop", ALT_FACILITY(148) - VSTBRF STATE0,0,,%r2 - VSTBRF STATE1,16,,%r2 - VSTBRF STATE2,32,,%r2 - VSTBRF STATE3,48,,%r2 -.Lstoredone: + ALTERNATIVE \ + __stringify( \ + /* Convert STATE to little endian and store to OUTPUT */\ + VPERM TMP0,STATE0,STATE0,BEPERM; \ + VPERM TMP1,STATE1,STATE1,BEPERM; \ + VPERM TMP2,STATE2,STATE2,BEPERM; \ + VPERM TMP3,STATE3,STATE3,BEPERM; \ + VSTM TMP0,TMP3,0,%r2), \ + __stringify( \ + /* 32 bit wise little endian store to OUTPUT */ \ + VSTBRF STATE0,0,,%r2; \ + VSTBRF STATE1,16,,%r2; \ + VSTBRF STATE2,32,,%r2; \ + VSTBRF STATE3,48,,%r2; \ + brcl 0,0), \ + ALT_FACILITY(148) /* ++COPY3.COUNTER */ /* alsih %r3,1 */ @@ -173,13 +177,5 @@ SYM_FUNC_START(__arch_chacha20_blocks_nostack) VZERO TMP3 br %r14 - -.Lstoreslow: - /* Convert STATE to little endian format and store to OUTPUT */ - VPERM TMP0,STATE0,STATE0,BEPERM - VPERM TMP1,STATE1,STATE1,BEPERM - VPERM TMP2,STATE2,STATE2,BEPERM - VPERM TMP3,STATE3,STATE3,BEPERM - VSTM TMP0,TMP3,0,%r2 - j .Lstoredone + CFI_ENDPROC SYM_FUNC_END(__arch_chacha20_blocks_nostack) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 0fd96860fc45..bb7134faaebf 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -348,20 +348,29 @@ static inline int plo_test_bit(unsigned char nr) return cc == 0; } -static __always_inline void __insn32_query(unsigned int opcode, u8 *query) +static __always_inline void __sortl_query(u8 (*query)[32]) { asm volatile( " lghi 0,0\n" - " lgr 1,%[query]\n" + " la 1,%[query]\n" /* Parameter registers are ignored */ - " .insn rrf,%[opc] << 16,2,4,6,0\n" + " .insn rre,0xb9380000,2,4\n" + : [query] "=R" (*query) : - : [query] "d" ((unsigned long)query), [opc] "i" (opcode) - : "cc", "memory", "0", "1"); + : "cc", "0", "1"); } -#define INSN_SORTL 0xb938 -#define INSN_DFLTCC 0xb939 +static __always_inline void __dfltcc_query(u8 (*query)[32]) +{ + asm volatile( + " lghi 0,0\n" + " la 1,%[query]\n" + /* Parameter registers are ignored */ + " .insn rrf,0xb9390000,2,4,6,0\n" + : [query] "=R" (*query) + : + : "cc", "0", "1"); +} static void __init kvm_s390_cpu_feat_init(void) { @@ -415,10 +424,10 @@ static void __init kvm_s390_cpu_feat_init(void) kvm_s390_available_subfunc.kdsa); if (test_facility(150)) /* SORTL */ - __insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl); + __sortl_query(&kvm_s390_available_subfunc.sortl); if (test_facility(151)) /* DFLTCC */ - __insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc); + __dfltcc_query(&kvm_s390_available_subfunc.dfltcc); if (MACHINE_HAS_ESOP) allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP); diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index ee90a91ed888..6f55a59a0871 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -657,7 +657,6 @@ static const struct file_operations clp_misc_fops = { .release = clp_misc_release, .unlocked_ioctl = clp_misc_ioctl, .compat_ioctl = clp_misc_ioctl, - .llseek = no_llseek, }; static struct miscdevice clp_misc_device = { diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h index 0f384b1f45ca..53fc18a3d4c2 100644 --- a/arch/sh/include/asm/irq.h +++ b/arch/sh/include/asm/irq.h @@ -14,12 +14,6 @@ #define NO_IRQ_IGNORE ((unsigned int)-1) /* - * Simple Mask Register Support - */ -extern void make_maskreg_irq(unsigned int irq); -extern unsigned short *irq_mask_register; - -/* * PINT IRQs */ void make_imask_irq(unsigned int irq); diff --git a/arch/um/Kconfig b/arch/um/Kconfig index dca84fd6d00a..c89575d05021 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -11,7 +11,6 @@ config UML select ARCH_HAS_KCOV select ARCH_HAS_STRNCPY_FROM_USER select ARCH_HAS_STRNLEN_USER - select ARCH_NO_PREEMPT_DYNAMIC select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_KASAN if X86_64 select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index 99a7144b229f..819aabb4ecdc 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -164,7 +164,6 @@ static const struct file_operations harddog_fops = { .compat_ioctl = compat_ptr_ioctl, .open = harddog_open, .release = harddog_release, - .llseek = no_llseek, }; static struct miscdevice harddog_miscdev = { diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c index c42b793bce65..9d228878cea2 100644 --- a/arch/um/drivers/hostaudio_kern.c +++ b/arch/um/drivers/hostaudio_kern.c @@ -291,7 +291,6 @@ static int hostmixer_release(struct inode *inode, struct file *file) static const struct file_operations hostaudio_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = hostaudio_read, .write = hostaudio_write, .poll = hostaudio_poll, @@ -304,7 +303,6 @@ static const struct file_operations hostaudio_fops = { static const struct file_operations hostmixer_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = hostmixer_ioctl_mixdev, .open = hostmixer_open_mixdev, .release = hostmixer_release, diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 2d473282ab51..c992da83268d 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -22,6 +22,7 @@ #include <linux/interrupt.h> #include <linux/firmware.h> #include <linux/fs.h> +#include <asm/atomic.h> #include <uapi/linux/filter.h> #include <init.h> #include <irq_kern.h> @@ -102,18 +103,33 @@ static const struct { static void vector_reset_stats(struct vector_private *vp) { + /* We reuse the existing queue locks for stats */ + + /* RX stats are modified with RX head_lock held + * in vector_poll. + */ + + spin_lock(&vp->rx_queue->head_lock); vp->estats.rx_queue_max = 0; vp->estats.rx_queue_running_average = 0; - vp->estats.tx_queue_max = 0; - vp->estats.tx_queue_running_average = 0; vp->estats.rx_encaps_errors = 0; + vp->estats.sg_ok = 0; + vp->estats.sg_linearized = 0; + spin_unlock(&vp->rx_queue->head_lock); + + /* TX stats are modified with TX head_lock held + * in vector_send. + */ + + spin_lock(&vp->tx_queue->head_lock); vp->estats.tx_timeout_count = 0; vp->estats.tx_restart_queue = 0; vp->estats.tx_kicks = 0; vp->estats.tx_flow_control_xon = 0; vp->estats.tx_flow_control_xoff = 0; - vp->estats.sg_ok = 0; - vp->estats.sg_linearized = 0; + vp->estats.tx_queue_max = 0; + vp->estats.tx_queue_running_average = 0; + spin_unlock(&vp->tx_queue->head_lock); } static int get_mtu(struct arglist *def) @@ -232,12 +248,6 @@ static int get_transport_options(struct arglist *def) static char *drop_buffer; -/* Array backed queues optimized for bulk enqueue/dequeue and - * 1:N (small values of N) or 1:1 enqueuer/dequeuer ratios. - * For more details and full design rationale see - * http://foswiki.cambridgegreys.com/Main/EatYourTailAndEnjoyIt - */ - /* * Advance the mmsg queue head by n = advance. Resets the queue to @@ -247,27 +257,13 @@ static char *drop_buffer; static int vector_advancehead(struct vector_queue *qi, int advance) { - int queue_depth; - qi->head = (qi->head + advance) % qi->max_depth; - spin_lock(&qi->tail_lock); - qi->queue_depth -= advance; - - /* we are at 0, use this to - * reset head and tail so we can use max size vectors - */ - - if (qi->queue_depth == 0) { - qi->head = 0; - qi->tail = 0; - } - queue_depth = qi->queue_depth; - spin_unlock(&qi->tail_lock); - return queue_depth; + atomic_sub(advance, &qi->queue_depth); + return atomic_read(&qi->queue_depth); } /* Advance the queue tail by n = advance. @@ -277,16 +273,11 @@ static int vector_advancehead(struct vector_queue *qi, int advance) static int vector_advancetail(struct vector_queue *qi, int advance) { - int queue_depth; - qi->tail = (qi->tail + advance) % qi->max_depth; - spin_lock(&qi->head_lock); - qi->queue_depth += advance; - queue_depth = qi->queue_depth; - spin_unlock(&qi->head_lock); - return queue_depth; + atomic_add(advance, &qi->queue_depth); + return atomic_read(&qi->queue_depth); } static int prep_msg(struct vector_private *vp, @@ -339,9 +330,7 @@ static int vector_enqueue(struct vector_queue *qi, struct sk_buff *skb) int iov_count; spin_lock(&qi->tail_lock); - spin_lock(&qi->head_lock); - queue_depth = qi->queue_depth; - spin_unlock(&qi->head_lock); + queue_depth = atomic_read(&qi->queue_depth); if (skb) packet_len = skb->len; @@ -360,6 +349,7 @@ static int vector_enqueue(struct vector_queue *qi, struct sk_buff *skb) mmsg_vector->msg_hdr.msg_iovlen = iov_count; mmsg_vector->msg_hdr.msg_name = vp->fds->remote_addr; mmsg_vector->msg_hdr.msg_namelen = vp->fds->remote_addr_size; + wmb(); /* Make the packet visible to the NAPI poll thread */ queue_depth = vector_advancetail(qi, 1); } else goto drop; @@ -398,7 +388,7 @@ static int consume_vector_skbs(struct vector_queue *qi, int count) } /* - * Generic vector deque via sendmmsg with support for forming headers + * Generic vector dequeue via sendmmsg with support for forming headers * using transport specific callback. Allows GRE, L2TPv3, RAW and * other transports to use a common dequeue procedure in vector mode */ @@ -408,69 +398,64 @@ static int vector_send(struct vector_queue *qi) { struct vector_private *vp = netdev_priv(qi->dev); struct mmsghdr *send_from; - int result = 0, send_len, queue_depth = qi->max_depth; + int result = 0, send_len; if (spin_trylock(&qi->head_lock)) { - if (spin_trylock(&qi->tail_lock)) { - /* update queue_depth to current value */ - queue_depth = qi->queue_depth; - spin_unlock(&qi->tail_lock); - while (queue_depth > 0) { - /* Calculate the start of the vector */ - send_len = queue_depth; - send_from = qi->mmsg_vector; - send_from += qi->head; - /* Adjust vector size if wraparound */ - if (send_len + qi->head > qi->max_depth) - send_len = qi->max_depth - qi->head; - /* Try to TX as many packets as possible */ - if (send_len > 0) { - result = uml_vector_sendmmsg( - vp->fds->tx_fd, - send_from, - send_len, - 0 - ); - vp->in_write_poll = - (result != send_len); - } - /* For some of the sendmmsg error scenarios - * we may end being unsure in the TX success - * for all packets. It is safer to declare - * them all TX-ed and blame the network. - */ - if (result < 0) { - if (net_ratelimit()) - netdev_err(vp->dev, "sendmmsg err=%i\n", - result); - vp->in_error = true; - result = send_len; - } - if (result > 0) { - queue_depth = - consume_vector_skbs(qi, result); - /* This is equivalent to an TX IRQ. - * Restart the upper layers to feed us - * more packets. - */ - if (result > vp->estats.tx_queue_max) - vp->estats.tx_queue_max = result; - vp->estats.tx_queue_running_average = - (vp->estats.tx_queue_running_average + result) >> 1; - } - netif_wake_queue(qi->dev); - /* if TX is busy, break out of the send loop, - * poll write IRQ will reschedule xmit for us + /* update queue_depth to current value */ + while (atomic_read(&qi->queue_depth) > 0) { + /* Calculate the start of the vector */ + send_len = atomic_read(&qi->queue_depth); + send_from = qi->mmsg_vector; + send_from += qi->head; + /* Adjust vector size if wraparound */ + if (send_len + qi->head > qi->max_depth) + send_len = qi->max_depth - qi->head; + /* Try to TX as many packets as possible */ + if (send_len > 0) { + result = uml_vector_sendmmsg( + vp->fds->tx_fd, + send_from, + send_len, + 0 + ); + vp->in_write_poll = + (result != send_len); + } + /* For some of the sendmmsg error scenarios + * we may end being unsure in the TX success + * for all packets. It is safer to declare + * them all TX-ed and blame the network. + */ + if (result < 0) { + if (net_ratelimit()) + netdev_err(vp->dev, "sendmmsg err=%i\n", + result); + vp->in_error = true; + result = send_len; + } + if (result > 0) { + consume_vector_skbs(qi, result); + /* This is equivalent to an TX IRQ. + * Restart the upper layers to feed us + * more packets. */ - if (result != send_len) { - vp->estats.tx_restart_queue++; - break; - } + if (result > vp->estats.tx_queue_max) + vp->estats.tx_queue_max = result; + vp->estats.tx_queue_running_average = + (vp->estats.tx_queue_running_average + result) >> 1; + } + netif_wake_queue(qi->dev); + /* if TX is busy, break out of the send loop, + * poll write IRQ will reschedule xmit for us. + */ + if (result != send_len) { + vp->estats.tx_restart_queue++; + break; } } spin_unlock(&qi->head_lock); } - return queue_depth; + return atomic_read(&qi->queue_depth); } /* Queue destructor. Deliberately stateless so we can use @@ -589,7 +574,7 @@ static struct vector_queue *create_queue( } spin_lock_init(&result->head_lock); spin_lock_init(&result->tail_lock); - result->queue_depth = 0; + atomic_set(&result->queue_depth, 0); result->head = 0; result->tail = 0; return result; @@ -668,18 +653,27 @@ done: } -/* Prepare queue for recvmmsg one-shot rx - fill with fresh sk_buffs*/ +/* Prepare queue for recvmmsg one-shot rx - fill with fresh sk_buffs */ static void prep_queue_for_rx(struct vector_queue *qi) { struct vector_private *vp = netdev_priv(qi->dev); struct mmsghdr *mmsg_vector = qi->mmsg_vector; void **skbuff_vector = qi->skbuff_vector; - int i; + int i, queue_depth; + + queue_depth = atomic_read(&qi->queue_depth); - if (qi->queue_depth == 0) + if (queue_depth == 0) return; - for (i = 0; i < qi->queue_depth; i++) { + + /* RX is always emptied 100% during each cycle, so we do not + * have to do the tail wraparound math for it. + */ + + qi->head = qi->tail = 0; + + for (i = 0; i < queue_depth; i++) { /* it is OK if allocation fails - recvmmsg with NULL data in * iov argument still performs an RX, just drops the packet * This allows us stop faffing around with a "drop buffer" @@ -689,7 +683,7 @@ static void prep_queue_for_rx(struct vector_queue *qi) skbuff_vector++; mmsg_vector++; } - qi->queue_depth = 0; + atomic_set(&qi->queue_depth, 0); } static struct vector_device *find_device(int n) @@ -972,7 +966,7 @@ static int vector_mmsg_rx(struct vector_private *vp, int budget) budget = qi->max_depth; packet_count = uml_vector_recvmmsg( - vp->fds->rx_fd, qi->mmsg_vector, qi->max_depth, 0); + vp->fds->rx_fd, qi->mmsg_vector, budget, 0); if (packet_count < 0) vp->in_error = true; @@ -985,7 +979,7 @@ static int vector_mmsg_rx(struct vector_private *vp, int budget) * many do we need to prep the next time prep_queue_for_rx() is called. */ - qi->queue_depth = packet_count; + atomic_add(packet_count, &qi->queue_depth); for (i = 0; i < packet_count; i++) { skb = (*skbuff_vector); @@ -1172,6 +1166,7 @@ static int vector_poll(struct napi_struct *napi, int budget) if ((vp->options & VECTOR_TX) != 0) tx_enqueued = (vector_send(vp->tx_queue) > 0); + spin_lock(&vp->rx_queue->head_lock); if ((vp->options & VECTOR_RX) > 0) err = vector_mmsg_rx(vp, budget); else { @@ -1179,12 +1174,13 @@ static int vector_poll(struct napi_struct *napi, int budget) if (err > 0) err = 1; } + spin_unlock(&vp->rx_queue->head_lock); if (err > 0) work_done += err; if (tx_enqueued || err > 0) napi_schedule(napi); - if (work_done < budget) + if (work_done <= budget) napi_complete_done(napi, work_done); return work_done; } @@ -1225,7 +1221,7 @@ static int vector_net_open(struct net_device *dev) vp->rx_header_size, MAX_IOV_SIZE ); - vp->rx_queue->queue_depth = get_depth(vp->parsed); + atomic_set(&vp->rx_queue->queue_depth, get_depth(vp->parsed)); } else { vp->header_rxbuffer = kmalloc( vp->rx_header_size, @@ -1467,7 +1463,17 @@ static void vector_get_ethtool_stats(struct net_device *dev, { struct vector_private *vp = netdev_priv(dev); + /* Stats are modified in the dequeue portions of + * rx/tx which are protected by the head locks + * grabbing these locks here ensures they are up + * to date. + */ + + spin_lock(&vp->tx_queue->head_lock); + spin_lock(&vp->rx_queue->head_lock); memcpy(tmp_stats, &vp->estats, sizeof(struct vector_estats)); + spin_unlock(&vp->rx_queue->head_lock); + spin_unlock(&vp->tx_queue->head_lock); } static int vector_get_coalesce(struct net_device *netdev, diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h index 806df551be0b..417834793658 100644 --- a/arch/um/drivers/vector_kern.h +++ b/arch/um/drivers/vector_kern.h @@ -14,6 +14,7 @@ #include <linux/ctype.h> #include <linux/workqueue.h> #include <linux/interrupt.h> +#include <asm/atomic.h> #include "vector_user.h" @@ -44,7 +45,8 @@ struct vector_queue { struct net_device *dev; spinlock_t head_lock; spinlock_t tail_lock; - int queue_depth, head, tail, max_depth, max_iov_frags; + atomic_t queue_depth; + int head, tail, max_depth, max_iov_frags; short options; }; diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c index b16a5e5619d3..2ea67e6fd067 100644 --- a/arch/um/drivers/vector_user.c +++ b/arch/um/drivers/vector_user.c @@ -46,6 +46,9 @@ #define TRANS_FD "fd" #define TRANS_FD_LEN strlen(TRANS_FD) +#define TRANS_VDE "vde" +#define TRANS_VDE_LEN strlen(TRANS_VDE) + #define VNET_HDR_FAIL "could not enable vnet headers on fd %d" #define TUN_GET_F_FAIL "tapraw: TUNGETFEATURES failed: %s" #define L2TPV3_BIND_FAIL "l2tpv3_open : could not bind socket err=%i" @@ -434,6 +437,84 @@ fd_cleanup: return NULL; } +/* enough char to store an int type */ +#define ENOUGH(type) ((CHAR_BIT * sizeof(type) - 1) / 3 + 2) +#define ENOUGH_OCTAL(type) ((CHAR_BIT * sizeof(type) + 2) / 3) +/* vde_plug --descr xx --port2 xx --mod2 xx --group2 xx seqpacket://NN vnl (NULL) */ +#define VDE_MAX_ARGC 12 +#define VDE_SEQPACKET_HEAD "seqpacket://" +#define VDE_SEQPACKET_HEAD_LEN (sizeof(VDE_SEQPACKET_HEAD) - 1) +#define VDE_DEFAULT_DESCRIPTION "UML" + +static struct vector_fds *user_init_vde_fds(struct arglist *ifspec) +{ + char seqpacketvnl[VDE_SEQPACKET_HEAD_LEN + ENOUGH(int) + 1]; + char *argv[VDE_MAX_ARGC] = {"vde_plug"}; + int argc = 1; + int rv; + int sv[2]; + struct vector_fds *result = NULL; + + char *vnl = uml_vector_fetch_arg(ifspec,"vnl"); + char *descr = uml_vector_fetch_arg(ifspec,"descr"); + char *port = uml_vector_fetch_arg(ifspec,"port"); + char *mode = uml_vector_fetch_arg(ifspec,"mode"); + char *group = uml_vector_fetch_arg(ifspec,"group"); + if (descr == NULL) descr = VDE_DEFAULT_DESCRIPTION; + + argv[argc++] = "--descr"; + argv[argc++] = descr; + if (port != NULL) { + argv[argc++] = "--port2"; + argv[argc++] = port; + } + if (mode != NULL) { + argv[argc++] = "--mod2"; + argv[argc++] = mode; + } + if (group != NULL) { + argv[argc++] = "--group2"; + argv[argc++] = group; + } + argv[argc++] = seqpacketvnl; + argv[argc++] = vnl; + argv[argc++] = NULL; + + rv = socketpair(AF_UNIX, SOCK_SEQPACKET, 0, sv); + if (rv < 0) { + printk(UM_KERN_ERR "vde: seqpacket socketpair err %d", -errno); + return NULL; + } + rv = os_set_exec_close(sv[0]); + if (rv < 0) { + printk(UM_KERN_ERR "vde: seqpacket socketpair cloexec err %d", -errno); + goto vde_cleanup_sv; + } + snprintf(seqpacketvnl, sizeof(seqpacketvnl), VDE_SEQPACKET_HEAD "%d", sv[1]); + + run_helper(NULL, NULL, argv); + + close(sv[1]); + + result = uml_kmalloc(sizeof(struct vector_fds), UM_GFP_KERNEL); + if (result == NULL) { + printk(UM_KERN_ERR "fd open: allocation failed"); + goto vde_cleanup; + } + + result->rx_fd = sv[0]; + result->tx_fd = sv[0]; + result->remote_addr_size = 0; + result->remote_addr = NULL; + return result; + +vde_cleanup_sv: + close(sv[1]); +vde_cleanup: + close(sv[0]); + return NULL; +} + static struct vector_fds *user_init_raw_fds(struct arglist *ifspec) { int rxfd = -1, txfd = -1; @@ -673,6 +754,8 @@ struct vector_fds *uml_vector_user_open( return user_init_unix_fds(parsed, ID_BESS); if (strncmp(transport, TRANS_FD, TRANS_FD_LEN) == 0) return user_init_fd_fds(parsed); + if (strncmp(transport, TRANS_VDE, TRANS_VDE_LEN) == 0) + return user_init_vde_fds(parsed); return NULL; } diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 5bb397b65efb..83373c9963e7 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -359,11 +359,4 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } -/* Clear a kernel PTE and flush it from the TLB */ -#define kpte_clear_flush(ptep, vaddr) \ -do { \ - pte_clear(&init_mm, (vaddr), (ptep)); \ - __flush_tlb_one((vaddr)); \ -} while (0) - #endif diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index 5a7c05275aa7..bce4595798da 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -28,20 +28,10 @@ struct thread_struct { struct arch_thread arch; jmp_buf switch_buf; struct { - int op; - union { - struct { - int pid; - } fork, exec; - struct { - int (*proc)(void *); - void *arg; - } thread; - struct { - void (*proc)(void *); - void *arg; - } cb; - } u; + struct { + int (*proc)(void *); + void *arg; + } thread; } request; }; @@ -51,7 +41,7 @@ struct thread_struct { .fault_addr = NULL, \ .prev_sched = NULL, \ .arch = INIT_ARCH_THREAD, \ - .request = { 0 } \ + .request = { } \ } /* diff --git a/arch/um/include/asm/sysrq.h b/arch/um/include/asm/sysrq.h deleted file mode 100644 index 8fc8c65cd357..000000000000 --- a/arch/um/include/asm/sysrq.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_SYSRQ_H -#define __UM_SYSRQ_H - -struct task_struct; -extern void show_trace(struct task_struct* task, unsigned long *stack); - -#endif diff --git a/arch/um/include/shared/skas/mm_id.h b/arch/um/include/shared/skas/mm_id.h index 1e76ba40feba..140388c282f6 100644 --- a/arch/um/include/shared/skas/mm_id.h +++ b/arch/um/include/shared/skas/mm_id.h @@ -7,10 +7,7 @@ #define __MM_ID_H struct mm_id { - union { - int mm_fd; - int pid; - } u; + int pid; unsigned long stack; int syscall_data_len; }; diff --git a/arch/um/include/shared/skas/skas.h b/arch/um/include/shared/skas/skas.h index ebaa116de30b..85c50122ab98 100644 --- a/arch/um/include/shared/skas/skas.h +++ b/arch/um/include/shared/skas/skas.h @@ -10,10 +10,8 @@ extern int userspace_pid[]; -extern int user_thread(unsigned long stack, int flags); extern void new_thread_handler(void); extern void handle_syscall(struct uml_pt_regs *regs); -extern long execute_syscall_skas(void *r); extern unsigned long current_stub_stack(void); extern struct mm_id *current_mm_id(void); extern void current_mm_sync(void); diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index 2c15bb2c104c..cb8b5cd9285c 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -35,8 +35,5 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) PT_REGS_IP(regs) = eip; PT_REGS_SP(regs) = esp; clear_thread_flag(TIF_SINGLESTEP); -#ifdef SUBARCH_EXECVE1 - SUBARCH_EXECVE1(regs->regs); -#endif } EXPORT_SYMBOL(start_thread); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index f36b63f53bab..be2856af6d4c 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -109,8 +109,8 @@ void new_thread_handler(void) schedule_tail(current->thread.prev_sched); current->thread.prev_sched = NULL; - fn = current->thread.request.u.thread.proc; - arg = current->thread.request.u.thread.arg; + fn = current->thread.request.thread.proc; + arg = current->thread.request.thread.arg; /* * callback returns only if the kernel thread execs a process @@ -158,8 +158,8 @@ int copy_thread(struct task_struct * p, const struct kernel_clone_args *args) arch_copy_thread(¤t->thread.arch, &p->thread.arch); } else { get_safe_registers(p->thread.regs.regs.gp, p->thread.regs.regs.fp); - p->thread.request.u.thread.proc = args->fn; - p->thread.request.u.thread.arg = args->fn_arg; + p->thread.request.thread.proc = args->fn; + p->thread.request.thread.arg = args->fn_arg; handler = new_thread_handler; } diff --git a/arch/um/kernel/reboot.c b/arch/um/kernel/reboot.c index 3736bca626ba..680bce4bd8fa 100644 --- a/arch/um/kernel/reboot.c +++ b/arch/um/kernel/reboot.c @@ -29,7 +29,7 @@ static void kill_off_processes(void) t = find_lock_task_mm(p); if (!t) continue; - pid = t->mm->context.id.u.pid; + pid = t->mm->context.id.pid; task_unlock(t); os_kill_ptraced_process(pid, 1); } diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c index 47f98d87ea3c..886ed5e65674 100644 --- a/arch/um/kernel/skas/mmu.c +++ b/arch/um/kernel/skas/mmu.c @@ -32,11 +32,11 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm) new_id->stack = stack; block_signals_trace(); - new_id->u.pid = start_userspace(stack); + new_id->pid = start_userspace(stack); unblock_signals_trace(); - if (new_id->u.pid < 0) { - ret = new_id->u.pid; + if (new_id->pid < 0) { + ret = new_id->pid; goto out_free; } @@ -83,12 +83,12 @@ void destroy_context(struct mm_struct *mm) * whole UML suddenly dying. Also, cover negative and * 1 cases, since they shouldn't happen either. */ - if (mmu->id.u.pid < 2) { + if (mmu->id.pid < 2) { printk(KERN_ERR "corrupt mm_context - pid = %d\n", - mmu->id.u.pid); + mmu->id.pid); return; } - os_kill_ptraced_process(mmu->id.u.pid, 1); + os_kill_ptraced_process(mmu->id.pid, 1); free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES)); } diff --git a/arch/um/kernel/skas/process.c b/arch/um/kernel/skas/process.c index 5f9c1c5f36e2..68657988c8d1 100644 --- a/arch/um/kernel/skas/process.c +++ b/arch/um/kernel/skas/process.c @@ -39,8 +39,8 @@ int __init start_uml(void) init_new_thread_signals(); - init_task.thread.request.u.thread.proc = start_kernel_proc; - init_task.thread.request.u.thread.arg = NULL; + init_task.thread.request.thread.proc = start_kernel_proc; + init_task.thread.request.thread.arg = NULL; return start_idle_thread(task_stack_page(&init_task), &init_task.thread.switch_buf); } diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c index 9ee19e566da3..b09e85279d2b 100644 --- a/arch/um/kernel/skas/syscall.c +++ b/arch/um/kernel/skas/syscall.c @@ -12,23 +12,13 @@ #include <sysdep/syscalls.h> #include <linux/time-internal.h> #include <asm/unistd.h> +#include <asm/delay.h> void handle_syscall(struct uml_pt_regs *r) { struct pt_regs *regs = container_of(r, struct pt_regs, regs); int syscall; - /* - * If we have infinite CPU resources, then make every syscall also a - * preemption point, since we don't have any other preemption in this - * case, and kernel threads would basically never run until userspace - * went to sleep, even if said userspace interacts with the kernel in - * various ways. - */ - if (time_travel_mode == TT_MODE_INFCPU || - time_travel_mode == TT_MODE_EXTERNAL) - schedule(); - /* Initialize the syscall number and default return value. */ UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp); PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS); @@ -41,9 +31,25 @@ void handle_syscall(struct uml_pt_regs *r) goto out; syscall = UPT_SYSCALL_NR(r); - if (syscall >= 0 && syscall < __NR_syscalls) - PT_REGS_SET_SYSCALL_RETURN(regs, - EXECUTE_SYSCALL(syscall, regs)); + if (syscall >= 0 && syscall < __NR_syscalls) { + unsigned long ret = EXECUTE_SYSCALL(syscall, regs); + + PT_REGS_SET_SYSCALL_RETURN(regs, ret); + + /* + * An error value here can be some form of -ERESTARTSYS + * and then we'd just loop. Make any error syscalls take + * some time, so that it won't just loop if something is + * not ready, and hopefully other things will make some + * progress. + */ + if (IS_ERR_VALUE(ret) && + (time_travel_mode == TT_MODE_INFCPU || + time_travel_mode == TT_MODE_EXTERNAL)) { + um_udelay(1); + schedule(); + } + } out: syscall_trace_leave(regs); diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c index 746715379f12..4bb8622dc512 100644 --- a/arch/um/kernel/sysrq.c +++ b/arch/um/kernel/sysrq.c @@ -11,7 +11,6 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> -#include <asm/sysrq.h> #include <asm/stacktrace.h> #include <os.h> diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 47b9f5e63566..29b27b90581f 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -839,7 +839,7 @@ static irqreturn_t um_timer(int irq, void *dev) if (get_current()->mm != NULL) { /* userspace - relay signal, results in correct userspace timers */ - os_alarm_process(get_current()->mm->context.id.u.pid); + os_alarm_process(get_current()->mm->context.id.pid); } (*timer_clockevent.event_handler)(&timer_clockevent); diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 44c6fc697f3a..548af31d4111 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -82,16 +82,12 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr, (x ? UM_PROT_EXEC : 0)); if (pte_newpage(*pte)) { if (pte_present(*pte)) { - if (pte_newpage(*pte)) { - __u64 offset; - unsigned long phys = - pte_val(*pte) & PAGE_MASK; - int fd = phys_mapping(phys, &offset); - - ret = ops->mmap(ops->mm_idp, addr, - PAGE_SIZE, prot, fd, - offset); - } + __u64 offset; + unsigned long phys = pte_val(*pte) & PAGE_MASK; + int fd = phys_mapping(phys, &offset); + + ret = ops->mmap(ops->mm_idp, addr, PAGE_SIZE, + prot, fd, offset); } else ret = ops->unmap(ops->mm_idp, addr, PAGE_SIZE); } else if (pte_newprot(*pte)) diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index 5adf8f630049..f1d03cf3957f 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -528,7 +528,8 @@ int os_shutdown_socket(int fd, int r, int w) ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, void *data, size_t data_len) { - char buf[CMSG_SPACE(sizeof(*fds) * n_fds)]; +#define MAX_RCV_FDS 2 + char buf[CMSG_SPACE(sizeof(*fds) * MAX_RCV_FDS)]; struct cmsghdr *cmsg; struct iovec iov = { .iov_base = data, @@ -538,10 +539,13 @@ ssize_t os_rcv_fd_msg(int fd, int *fds, unsigned int n_fds, .msg_iov = &iov, .msg_iovlen = 1, .msg_control = buf, - .msg_controllen = sizeof(buf), + .msg_controllen = CMSG_SPACE(sizeof(*fds) * n_fds), }; int n; + if (n_fds > MAX_RCV_FDS) + return -EINVAL; + n = recvmsg(fd, &msg, 0); if (n < 0) return -errno; diff --git a/arch/um/os-Linux/skas/mem.c b/arch/um/os-Linux/skas/mem.c index c55430775efd..9a13ac23c606 100644 --- a/arch/um/os-Linux/skas/mem.c +++ b/arch/um/os-Linux/skas/mem.c @@ -78,7 +78,7 @@ static inline long do_syscall_stub(struct mm_id *mm_idp) { struct stub_data *proc_data = (void *)mm_idp->stack; int n, i; - int err, pid = mm_idp->u.pid; + int err, pid = mm_idp->pid; n = ptrace_setregs(pid, syscall_regs); if (n < 0) { diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index f7088345b3fc..b6f656bcffb1 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -588,5 +588,5 @@ void reboot_skas(void) void __switch_mm(struct mm_id *mm_idp) { - userspace_pid[0] = mm_idp->u.pid; + userspace_pid[0] = mm_idp->pid; } diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index da8b66dce0da..327c45c5013f 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -16,6 +16,7 @@ #include <asm/insn-eval.h> #include <asm/pgtable.h> #include <asm/set_memory.h> +#include <asm/traps.h> /* MMIO direction */ #define EPT_READ 0 @@ -433,6 +434,11 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; } + if (!fault_in_kernel_space(ve->gla)) { + WARN_ONCE(1, "Access to userspace address is not supported"); + return -EINVAL; + } + /* * Reject EPT violation #VEs that split pages. * diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 8db2ec4d6cda..1f650b4dde50 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -163,20 +163,18 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) } #define arch_atomic64_dec_return arch_atomic64_dec_return -static __always_inline s64 arch_atomic64_add(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) { __alternative_atomic64(add, add_return, ASM_OUTPUT2("+A" (i), "+c" (v)), ASM_NO_INPUT_CLOBBER("memory")); - return i; } -static __always_inline s64 arch_atomic64_sub(s64 i, atomic64_t *v) +static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v) { __alternative_atomic64(sub, sub_return, ASM_OUTPUT2("+A" (i), "+c" (v)), ASM_NO_INPUT_CLOBBER("memory")); - return i; } static __always_inline void arch_atomic64_inc(atomic64_t *v) diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 80cc6386d7b1..ca4243318aad 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -179,6 +179,7 @@ static __always_inline bool cpuid_function_is_indexed(u32 function) case 0x1d: case 0x1e: case 0x1f: + case 0x24: case 0x8000001d: return true; } diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 44949f972826..1a42f829667a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -135,6 +135,8 @@ #define INTEL_LUNARLAKE_M IFM(6, 0xBD) +#define INTEL_PANTHERLAKE_L IFM(6, 0xCC) + /* "Small Core" Processors (Atom/E-Core) */ #define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */ @@ -178,4 +180,7 @@ #define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */ #define INTEL_QUARK_X1000 IFM(5, 0x09) /* Quark X1000 SoC */ +/* Family 19 */ +#define INTEL_PANTHERCOVE_X IFM(19, 0x01) /* Diamond Rapids */ + #endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 68ad4f923664..861d080ed4c6 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -14,8 +14,8 @@ BUILD_BUG_ON(1) * be __static_call_return0. */ KVM_X86_OP(check_processor_compatibility) -KVM_X86_OP(hardware_enable) -KVM_X86_OP(hardware_disable) +KVM_X86_OP(enable_virtualization_cpu) +KVM_X86_OP(disable_virtualization_cpu) KVM_X86_OP(hardware_unsetup) KVM_X86_OP(has_emulated_msr) KVM_X86_OP(vcpu_after_set_cpuid) @@ -125,7 +125,7 @@ KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) -KVM_X86_OP(get_msr_feature) +KVM_X86_OP(get_feature_msr) KVM_X86_OP(check_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4a68cb3eba78..6d9f763a7bb9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -36,6 +36,7 @@ #include <asm/kvm_page_track.h> #include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> +#include <asm/reboot.h> #define __KVM_HAVE_ARCH_VCPU_DEBUGFS @@ -211,6 +212,7 @@ enum exit_fastpath_completion { EXIT_FASTPATH_NONE, EXIT_FASTPATH_REENTER_GUEST, EXIT_FASTPATH_EXIT_HANDLED, + EXIT_FASTPATH_EXIT_USERSPACE, }; typedef enum exit_fastpath_completion fastpath_t; @@ -280,10 +282,6 @@ enum x86_intercept_stage; #define PFERR_PRIVATE_ACCESS BIT_ULL(49) #define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) -#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ - PFERR_WRITE_MASK | \ - PFERR_PRESENT_MASK) - /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -1629,8 +1627,10 @@ struct kvm_x86_ops { int (*check_processor_compatibility)(void); - int (*hardware_enable)(void); - void (*hardware_disable)(void); + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); + cpu_emergency_virt_cb *emergency_disable_virtualization_cpu; + void (*hardware_unsetup)(void); bool (*has_emulated_msr)(struct kvm *kvm, u32 index); void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); @@ -1727,6 +1727,8 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); + + const bool x2apic_icr_is_split; const unsigned long required_apicv_inhibits; bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); @@ -1806,7 +1808,7 @@ struct kvm_x86_ops { int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); void (*guest_memory_reclaimed)(struct kvm *kvm); - int (*get_msr_feature)(struct kvm_msr_entry *entry); + int (*get_feature_msr)(u32 msr, u64 *data); int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len); @@ -2060,6 +2062,8 @@ void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); +int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data); +int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data); int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data); @@ -2136,7 +2140,15 @@ int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry); + +static inline bool kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa) +{ + return __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, false); +} + void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); @@ -2254,6 +2266,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); +int kvm_cpu_get_extint(struct kvm_vcpu *v); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); @@ -2345,7 +2358,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_OUT_7E_INC_RIP | \ KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \ KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \ - KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) + KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \ + KVM_X86_QUIRK_SLOT_ZAP_ALL) /* * KVM previously used a u32 field in kvm_run to indicate the hypercall was diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a7c06a46fb76..3ae84c3b8e6d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,6 +36,20 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) +/* + * Architectural memory types that are common to MTRRs, PAT, VMX MSRs, etc. + * Most MSRs support/allow only a subset of memory types, but the values + * themselves are common across all relevant MSRs. + */ +#define X86_MEMTYPE_UC 0ull /* Uncacheable, a.k.a. Strong Uncacheable */ +#define X86_MEMTYPE_WC 1ull /* Write Combining */ +/* RESERVED 2 */ +/* RESERVED 3 */ +#define X86_MEMTYPE_WT 4ull /* Write Through */ +#define X86_MEMTYPE_WP 5ull /* Write Protected */ +#define X86_MEMTYPE_WB 6ull /* Write Back */ +#define X86_MEMTYPE_UC_MINUS 7ull /* Weak Uncacheabled (PAT only) */ + /* FRED MSRs */ #define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ #define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ @@ -365,6 +379,12 @@ #define MSR_IA32_CR_PAT 0x00000277 +#define PAT_VALUE(p0, p1, p2, p3, p4, p5, p6, p7) \ + ((X86_MEMTYPE_ ## p0) | (X86_MEMTYPE_ ## p1 << 8) | \ + (X86_MEMTYPE_ ## p2 << 16) | (X86_MEMTYPE_ ## p3 << 24) | \ + (X86_MEMTYPE_ ## p4 << 32) | (X86_MEMTYPE_ ## p5 << 40) | \ + (X86_MEMTYPE_ ## p6 << 48) | (X86_MEMTYPE_ ## p7 << 56)) + #define MSR_IA32_DEBUGCTLMSR 0x000001d9 #define MSR_IA32_LASTBRANCHFROMIP 0x000001db #define MSR_IA32_LASTBRANCHTOIP 0x000001dc @@ -1159,15 +1179,6 @@ #define MSR_IA32_VMX_VMFUNC 0x00000491 #define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 -/* VMX_BASIC bits and bitmasks */ -#define VMX_BASIC_VMCS_SIZE_SHIFT 32 -#define VMX_BASIC_TRUE_CTLS (1ULL << 55) -#define VMX_BASIC_64 0x0001000000000000LLU -#define VMX_BASIC_MEM_TYPE_SHIFT 50 -#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU -#define VMX_BASIC_MEM_TYPE_WB 6LLU -#define VMX_BASIC_INOUT 0x0040000000000000LLU - /* Resctrl MSRs: */ /* - Intel: */ #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -1185,11 +1196,6 @@ #define MSR_IA32_SMBA_BW_BASE 0xc0000280 #define MSR_IA32_EVT_CFG_BASE 0xc0000400 -/* MSR_IA32_VMX_MISC bits */ -#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) -#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) -#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F - /* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 #define MSR_VM_IGNNE 0xc0010115 diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e9db77231ac..d1426b64c1b9 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -270,5 +270,26 @@ static inline bool gup_fast_permitted(unsigned long start, unsigned long end) #include <asm/pgtable-invert.h> -#endif /* !__ASSEMBLY__ */ +#else /* __ASSEMBLY__ */ + +#define l4_index(x) (((x) >> 39) & 511) +#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) +L4_START_KERNEL = l4_index(__START_KERNEL_map) + +L3_START_KERNEL = pud_index(__START_KERNEL_map) + +#define SYM_DATA_START_PAGE_ALIGNED(name) \ + SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) + +/* Automate the creation of 1 to 1 mapping pmd entries */ +#define PMDS(START, PERM, COUNT) \ + i = 0 ; \ + .rept (COUNT) ; \ + .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ + i = i + 1 ; \ + .endr + +#endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 6536873f8fc0..d0ef2a678d66 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,8 +25,8 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 -#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) typedef void (cpu_emergency_virt_cb)(void); +#if IS_ENABLED(CONFIG_KVM_INTEL) || IS_ENABLED(CONFIG_KVM_AMD) void cpu_emergency_register_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_unregister_virt_callback(cpu_emergency_virt_cb *callback); void cpu_emergency_disable_virtualization(void); diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f0dea3750ca9..2b59b9951c90 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -516,6 +516,20 @@ struct ghcb { u32 ghcb_usage; } __packed; +struct vmcb { + struct vmcb_control_area control; + union { + struct vmcb_save_area save; + + /* + * For SEV-ES VMs, the save area in the VMCB is used only to + * save/load host state. Guest state resides in a separate + * page, the aptly named VM Save Area (VMSA), that is encrypted + * with the guest's private key. + */ + struct sev_es_save_area host_sev_es_save; + }; +} __packed; #define EXPECTED_VMCB_SAVE_AREA_SIZE 744 #define EXPECTED_GHCB_SAVE_AREA_SIZE 1032 @@ -532,6 +546,7 @@ static inline void __unused_size_checks(void) BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(offsetof(struct vmcb, save) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); /* Check offsets of reserved fields */ @@ -568,11 +583,6 @@ static inline void __unused_size_checks(void) BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0); } -struct vmcb { - struct vmcb_control_area control; - struct vmcb_save_area save; -} __packed; - #define SVM_CPUID_FUNC 0x8000000a #define SVM_SELECTOR_S_SHIFT 4 diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index d77a31039f24..f7fd4369b821 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -122,19 +122,17 @@ #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff -#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f -#define VMX_MISC_SAVE_EFER_LMA 0x00000020 -#define VMX_MISC_ACTIVITY_HLT 0x00000040 -#define VMX_MISC_ACTIVITY_WAIT_SIPI 0x00000100 -#define VMX_MISC_ZERO_LEN_INS 0x40000000 -#define VMX_MISC_MSR_LIST_MULTIPLIER 512 - /* VMFUNC functions */ #define VMFUNC_CONTROL_BIT(x) BIT((VMX_FEATURE_##x & 0x1f) - 28) #define VMX_VMFUNC_EPTP_SWITCHING VMFUNC_CONTROL_BIT(EPTP_SWITCHING) #define VMFUNC_EPTP_ENTRIES 512 +#define VMX_BASIC_32BIT_PHYS_ADDR_ONLY BIT_ULL(48) +#define VMX_BASIC_DUAL_MONITOR_TREATMENT BIT_ULL(49) +#define VMX_BASIC_INOUT BIT_ULL(54) +#define VMX_BASIC_TRUE_CTLS BIT_ULL(55) + static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic) { return vmx_basic & GENMASK_ULL(30, 0); @@ -145,9 +143,30 @@ static inline u32 vmx_basic_vmcs_size(u64 vmx_basic) return (vmx_basic & GENMASK_ULL(44, 32)) >> 32; } +static inline u32 vmx_basic_vmcs_mem_type(u64 vmx_basic) +{ + return (vmx_basic & GENMASK_ULL(53, 50)) >> 50; +} + +static inline u64 vmx_basic_encode_vmcs_info(u32 revision, u16 size, u8 memtype) +{ + return revision | ((u64)size << 32) | ((u64)memtype << 50); +} + +#define VMX_MISC_SAVE_EFER_LMA BIT_ULL(5) +#define VMX_MISC_ACTIVITY_HLT BIT_ULL(6) +#define VMX_MISC_ACTIVITY_SHUTDOWN BIT_ULL(7) +#define VMX_MISC_ACTIVITY_WAIT_SIPI BIT_ULL(8) +#define VMX_MISC_INTEL_PT BIT_ULL(14) +#define VMX_MISC_RDMSR_IN_SMM BIT_ULL(15) +#define VMX_MISC_VMXOFF_BLOCK_SMI BIT_ULL(28) +#define VMX_MISC_VMWRITE_SHADOW_RO_FIELDS BIT_ULL(29) +#define VMX_MISC_ZERO_LEN_INS BIT_ULL(30) +#define VMX_MISC_MSR_LIST_MULTIPLIER 512 + static inline int vmx_misc_preemption_timer_rate(u64 vmx_misc) { - return vmx_misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + return vmx_misc & GENMASK_ULL(4, 0); } static inline int vmx_misc_cr3_count(u64 vmx_misc) @@ -508,9 +527,10 @@ enum vmcs_field { #define VMX_EPTP_PWL_4 0x18ull #define VMX_EPTP_PWL_5 0x20ull #define VMX_EPTP_AD_ENABLE_BIT (1ull << 6) +/* The EPTP memtype is encoded in bits 2:0, i.e. doesn't need to be shifted. */ #define VMX_EPTP_MT_MASK 0x7ull -#define VMX_EPTP_MT_WB 0x6ull -#define VMX_EPTP_MT_UC 0x0ull +#define VMX_EPTP_MT_WB X86_MEMTYPE_WB +#define VMX_EPTP_MT_UC X86_MEMTYPE_UC #define VMX_EPT_READABLE_MASK 0x1ull #define VMX_EPT_WRITABLE_MASK 0x2ull #define VMX_EPT_EXECUTABLE_MASK 0x4ull diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index bf57a824f722..a8debbf2f702 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -439,6 +439,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) +#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index a3aa0199222e..af44fd5dbd7c 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -331,7 +331,6 @@ static const struct file_operations mce_chrdev_ops = { .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct miscdevice mce_chrdev_device = { diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 2a2fc14955cd..989d368be04f 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -55,6 +55,12 @@ #include "mtrr.h" +static_assert(X86_MEMTYPE_UC == MTRR_TYPE_UNCACHABLE); +static_assert(X86_MEMTYPE_WC == MTRR_TYPE_WRCOMB); +static_assert(X86_MEMTYPE_WT == MTRR_TYPE_WRTHROUGH); +static_assert(X86_MEMTYPE_WP == MTRR_TYPE_WRPROT); +static_assert(X86_MEMTYPE_WB == MTRR_TYPE_WRBACK); + /* arch_phys_wc_add returns an MTRR register index plus this offset. */ #define MTRR_TO_PHYS_WC_OFFSET 1000 diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index e69489d48625..972e6b6b0481 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -1567,7 +1567,6 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) static const struct file_operations pseudo_lock_dev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = NULL, .write = NULL, .open = pseudo_lock_dev_open, diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 330922b328bf..16752b8dfa89 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -32,13 +32,6 @@ * We are not able to switch in one step to the final KERNEL ADDRESS SPACE * because we need identity-mapped pages. */ -#define l4_index(x) (((x) >> 39) & 511) -#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) - -L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) -L4_START_KERNEL = l4_index(__START_KERNEL_map) - -L3_START_KERNEL = pud_index(__START_KERNEL_map) __HEAD .code64 @@ -577,9 +570,6 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb) SYM_CODE_END(vc_no_ghcb) #endif -#define SYM_DATA_START_PAGE_ALIGNED(name) \ - SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) - #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Each PGD needs to be 8k long and 8k aligned. We do not @@ -601,14 +591,6 @@ SYM_CODE_END(vc_no_ghcb) #define PTI_USER_PGD_FILL 0 #endif -/* Automate the creation of 1 to 1 mapping pmd entries */ -#define PMDS(START, PERM, COUNT) \ - i = 0 ; \ - .rept (COUNT) ; \ - .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ - i = i + 1 ; \ - .endr - __INITDATA .balign 4 @@ -708,8 +690,6 @@ SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt) .endr SYM_DATA_END(level1_fixmap_pgt) -#undef PMDS - .data .align 16 diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2617be544480..41786b834b16 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -705,7 +705,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) | - F(AMX_COMPLEX) + F(AMX_COMPLEX) | F(AVX10) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, @@ -721,6 +721,10 @@ void kvm_set_cpu_caps(void) SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) ); + kvm_cpu_cap_init_kvm_defined(CPUID_24_0_EBX, + F(AVX10_128) | F(AVX10_256) | F(AVX10_512) + ); + kvm_cpu_cap_mask(CPUID_8000_0001_ECX, F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | @@ -949,7 +953,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) switch (function) { case 0: /* Limited to the highest leaf implemented in KVM. */ - entry->eax = min(entry->eax, 0x1fU); + entry->eax = min(entry->eax, 0x24U); break; case 1: cpuid_entry_override(entry, CPUID_1_EDX); @@ -1174,6 +1178,28 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; } break; + case 0x24: { + u8 avx10_version; + + if (!kvm_cpu_cap_has(X86_FEATURE_AVX10)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + + /* + * The AVX10 version is encoded in EBX[7:0]. Note, the version + * is guaranteed to be >=1 if AVX10 is supported. Note #2, the + * version needs to be captured before overriding EBX features! + */ + avx10_version = min_t(u8, entry->ebx & 0xff, 1); + cpuid_entry_override(entry, CPUID_24_0_EBX); + entry->ebx |= avx10_version; + + entry->eax = 0; + entry->ecx = 0; + entry->edx = 0; + break; + } case KVM_CPUID_SIGNATURE: { const u32 *sigptr = (const u32 *)KVM_SIGNATURE; entry->eax = KVM_CPUID_FEATURES; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 3d7eb11d0e45..63f66c51975a 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -108,7 +108,7 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); * Read pending interrupt(from non-APIC source) * vector and intack. */ -static int kvm_cpu_get_extint(struct kvm_vcpu *v) +int kvm_cpu_get_extint(struct kvm_vcpu *v) { if (!kvm_cpu_has_extint(v)) { WARN_ON(!lapic_in_kernel(v)); @@ -131,6 +131,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) } else return kvm_pic_read_irq(v->kvm); /* PIC */ } +EXPORT_SYMBOL_GPL(kvm_cpu_get_extint); /* * Read pending interrupt vector and intack. @@ -141,9 +142,12 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) if (vector != -1) return vector; /* PIC */ - return kvm_get_apic_interrupt(v); /* APIC */ + vector = kvm_apic_has_interrupt(v); /* APIC */ + if (vector != -1) + kvm_apic_ack_interrupt(v, vector); + + return vector; } -EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5bb481aefcbc..2098dc689088 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1944,7 +1944,7 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; - unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; + u32 this_tsc_khz = vcpu->arch.virtual_tsc_khz; unsigned long flags; ktime_t now; @@ -2453,6 +2453,43 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); +#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13)) + +int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) +{ + if (data & X2APIC_ICR_RESERVED_BITS) + return 1; + + /* + * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but + * only AMD requires it to be zero, Intel essentially just ignores the + * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled, + * the CPU performs the reserved bits checks, i.e. the underlying CPU + * behavior will "win". Arbitrarily clear the BUSY bit, as there is no + * sane way to provide consistent behavior with respect to hardware. + */ + data &= ~APIC_ICR_BUSY; + + kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); + if (kvm_x86_ops.x2apic_icr_is_split) { + kvm_lapic_set_reg(apic, APIC_ICR, data); + kvm_lapic_set_reg(apic, APIC_ICR2, data >> 32); + } else { + kvm_lapic_set_reg64(apic, APIC_ICR, data); + } + trace_kvm_apic_write(APIC_ICR, data); + return 0; +} + +static u64 kvm_x2apic_icr_read(struct kvm_lapic *apic) +{ + if (kvm_x86_ops.x2apic_icr_is_split) + return (u64)kvm_lapic_get_reg(apic, APIC_ICR) | + (u64)kvm_lapic_get_reg(apic, APIC_ICR2) << 32; + + return kvm_lapic_get_reg64(apic, APIC_ICR); +} + /* emulate APIC access in a trap manner */ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { @@ -2470,7 +2507,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) * maybe-unecessary write, and both are in the noise anyways. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) - kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_x2apic_icr_read(apic))); else kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } @@ -2922,14 +2959,13 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) } } -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) +void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector) { - int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (vector == -1) - return -1; + if (WARN_ON_ONCE(vector < 0 || !apic)) + return; /* * We get here even with APIC virtualization enabled, if doing @@ -2957,8 +2993,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) __apic_update_ppr(apic, &ppr); } - return vector; } +EXPORT_SYMBOL_GPL(kvm_apic_ack_interrupt); static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s, bool set) @@ -2990,18 +3026,22 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, /* * In x2APIC mode, the LDR is fixed and based on the id. And - * ICR is internally a single 64-bit register, but needs to be - * split to ICR+ICR2 in userspace for backwards compatibility. + * if the ICR is _not_ split, ICR is internally a single 64-bit + * register, but needs to be split to ICR+ICR2 in userspace for + * backwards compatibility. */ - if (set) { + if (set) *ldr = kvm_apic_calc_x2apic_ldr(x2apic_id); - icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | - (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; - __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr); - } else { - icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); - __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); + if (!kvm_x86_ops.x2apic_icr_is_split) { + if (set) { + icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | + (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; + __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr); + } else { + icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); + __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); + } } } @@ -3194,22 +3234,12 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) return 0; } -int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) -{ - data &= ~APIC_ICR_BUSY; - - kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); - kvm_lapic_set_reg64(apic, APIC_ICR, data); - trace_kvm_apic_write(APIC_ICR, data); - return 0; -} - static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) { u32 low; if (reg == APIC_ICR) { - *data = kvm_lapic_get_reg64(apic, APIC_ICR); + *data = kvm_x2apic_icr_read(apic); return 0; } diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 7ef8ae73e82d..1b8ef9856422 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -88,15 +88,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); +void kvm_apic_ack_interrupt(struct kvm_vcpu *vcpu, int vector); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_events(struct kvm_vcpu *vcpu); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); -u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_recalculate_apic_map(struct kvm *kvm); void kvm_apic_set_version(struct kvm_vcpu *vcpu); void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 4341e0e28571..9dc5dd43ae7f 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -223,8 +223,6 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, bool kvm_mmu_may_ignore_guest_pat(void); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); - int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7813d28b082f..e52f990548df 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -614,32 +614,6 @@ static u64 mmu_spte_get_lockless(u64 *sptep) return __get_spte_lockless(sptep); } -/* Returns the Accessed status of the PTE and resets it at the same time. */ -static bool mmu_spte_age(u64 *sptep) -{ - u64 spte = mmu_spte_get_lockless(sptep); - - if (!is_accessed_spte(spte)) - return false; - - if (spte_ad_enabled(spte)) { - clear_bit((ffs(shadow_accessed_mask) - 1), - (unsigned long *)sptep); - } else { - /* - * Capture the dirty status of the page, so that it doesn't get - * lost when the SPTE is marked for access tracking. - */ - if (is_writable_pte(spte)) - kvm_set_pfn_dirty(spte_to_pfn(spte)); - - spte = mark_spte_for_access_track(spte); - mmu_spte_update_no_track(sptep, spte); - } - - return true; -} - static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) { return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; @@ -938,6 +912,7 @@ static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct * pte_list_desc containing more mappings. */ +#define KVM_RMAP_MANY BIT(0) /* * Returns the number of pointers in the rmap chain, not counting the new one. @@ -950,16 +925,16 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, if (!rmap_head->val) { rmap_head->val = (unsigned long)spte; - } else if (!(rmap_head->val & 1)) { + } else if (!(rmap_head->val & KVM_RMAP_MANY)) { desc = kvm_mmu_memory_cache_alloc(cache); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; desc->spte_count = 2; desc->tail_count = 0; - rmap_head->val = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY; ++count; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); count = desc->tail_count + desc->spte_count; /* @@ -968,10 +943,10 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, */ if (desc->spte_count == PTE_LIST_EXT) { desc = kvm_mmu_memory_cache_alloc(cache); - desc->more = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc->more = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); desc->spte_count = 0; desc->tail_count = count; - rmap_head->val = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | KVM_RMAP_MANY; } desc->sptes[desc->spte_count++] = spte; } @@ -982,7 +957,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct pte_list_desc *desc, int i) { - struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); int j = head_desc->spte_count - 1; /* @@ -1011,7 +986,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, if (!head_desc->more) rmap_head->val = 0; else - rmap_head->val = (unsigned long)head_desc->more | 1; + rmap_head->val = (unsigned long)head_desc->more | KVM_RMAP_MANY; mmu_free_pte_list_desc(head_desc); } @@ -1024,13 +999,13 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte, if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_head->val, kvm)) return; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { if (KVM_BUG_ON_DATA_CORRUPTION((u64 *)rmap_head->val != spte, kvm)) return; rmap_head->val = 0; } else { - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { @@ -1063,12 +1038,12 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm, if (!rmap_head->val) return false; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { mmu_spte_clear_track_bits(kvm, (u64 *)rmap_head->val); goto out; } - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); for (; desc; desc = next) { for (i = 0; i < desc->spte_count; i++) @@ -1088,10 +1063,10 @@ unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) if (!rmap_head->val) return 0; - else if (!(rmap_head->val & 1)) + else if (!(rmap_head->val & KVM_RMAP_MANY)) return 1; - desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); return desc->tail_count + desc->spte_count; } @@ -1153,13 +1128,13 @@ static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, if (!rmap_head->val) return NULL; - if (!(rmap_head->val & 1)) { + if (!(rmap_head->val & KVM_RMAP_MANY)) { iter->desc = NULL; sptep = (u64 *)rmap_head->val; goto out; } - iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + iter->desc = (struct pte_list_desc *)(rmap_head->val & ~KVM_RMAP_MANY); iter->pos = 0; sptep = iter->desc->sptes[iter->pos]; out: @@ -1307,15 +1282,6 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, return flush; } -/** - * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages - * @kvm: kvm instance - * @slot: slot to protect - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should protect - * - * Used when we do not need to care about huge page mappings. - */ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1339,16 +1305,6 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, } } -/** - * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write - * protect the page if the D-bit isn't supported. - * @kvm: kvm instance - * @slot: slot to clear D-bit - * @gfn_offset: start of the BITS_PER_LONG pages we care about - * @mask: indicates which pages we should clear D-bit - * - * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap. - */ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) @@ -1372,24 +1328,16 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, } } -/** - * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected - * PT level pages. - * - * It calls kvm_mmu_write_protect_pt_masked to write protect selected pages to - * enable dirty logging for them. - * - * We need to care about huge page mappings: e.g. during dirty logging we may - * have such mappings. - */ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { /* - * Huge pages are NOT write protected when we start dirty logging in - * initially-all-set mode; must write protect them here so that they - * are split to 4K on the first write. + * If the slot was assumed to be "initially all dirty", write-protect + * huge pages to ensure they are split to 4KiB on the first write (KVM + * dirty logs at 4KiB granularity). If eager page splitting is enabled, + * immediately try to split huge pages, e.g. so that vCPUs don't get + * saddled with the cost of splitting. * * The gfn_offset is guaranteed to be aligned to 64, but the base_gfn * of memslot has no such restriction, so the range can cross two large @@ -1411,7 +1359,16 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, PG_LEVEL_2M); } - /* Now handle 4K PTEs. */ + /* + * (Re)Enable dirty logging for all 4KiB SPTEs that map the GFNs in + * mask. If PML is enabled and the GFN doesn't need to be write- + * protected for other reasons, e.g. shadow paging, clear the Dirty bit. + * Otherwise clear the Writable bit. + * + * Note that kvm_mmu_clear_dirty_pt_masked() is called whenever PML is + * enabled but it chooses between clearing the Dirty bit and Writeable + * bit based on the context. + */ if (kvm_x86_ops.cpu_dirty_log_size) kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else @@ -1453,16 +1410,10 @@ static bool kvm_vcpu_write_protect_gfn(struct kvm_vcpu *vcpu, u64 gfn) return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn, PG_LEVEL_4K); } -static bool __kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot) -{ - return kvm_zap_all_rmap_sptes(kvm, rmap_head); -} - static bool kvm_zap_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) + const struct kvm_memory_slot *slot) { - return __kvm_zap_rmap(kvm, rmap_head, slot); + return kvm_zap_all_rmap_sptes(kvm, rmap_head); } struct slot_rmap_walk_iterator { @@ -1513,7 +1464,7 @@ static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) { while (++iterator->rmap <= iterator->end_rmap) { - iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level)); + iterator->gfn += KVM_PAGES_PER_HPAGE(iterator->level); if (iterator->rmap->val) return; @@ -1534,23 +1485,71 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) slot_rmap_walk_okay(_iter_); \ slot_rmap_walk_next(_iter_)) -typedef bool (*rmap_handler_t)(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, - int level); +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_rmaps_handler) (struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + const struct kvm_memory_slot *slot); -static __always_inline bool kvm_handle_gfn_range(struct kvm *kvm, - struct kvm_gfn_range *range, - rmap_handler_t handler) +static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, + bool can_yield, bool flush_on_yield, + bool flush) { struct slot_rmap_walk_iterator iterator; - bool ret = false; - for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - range->start, range->end - 1, &iterator) - ret |= handler(kvm, iterator.rmap, range->slot, iterator.gfn, - iterator.level); + lockdep_assert_held_write(&kvm->mmu_lock); - return ret; + for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap, slot); + + if (!can_yield) + continue; + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { + if (flush && flush_on_yield) { + kvm_flush_remote_tlbs_range(kvm, start_gfn, + iterator.gfn - start_gfn + 1); + flush = false; + } + cond_resched_rwlock_write(&kvm->mmu_lock); + } + } + + return flush; +} + +static __always_inline bool walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + bool flush_on_yield) +{ + return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, + slot->base_gfn, slot->base_gfn + slot->npages - 1, + true, flush_on_yield, false); +} + +static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + bool flush_on_yield) +{ + return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); +} + +static bool __kvm_rmap_zap_gfn_range(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t start, gfn_t end, bool can_yield, + bool flush) +{ + return __walk_slot_rmaps(kvm, slot, kvm_zap_rmap, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + start, end - 1, can_yield, true, flush); } bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1558,7 +1557,9 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) bool flush = false; if (kvm_memslots_have_rmaps(kvm)) - flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap); + flush = __kvm_rmap_zap_gfn_range(kvm, range->slot, + range->start, range->end, + range->may_block, flush); if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); @@ -1570,31 +1571,6 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) return flush; } -static bool kvm_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) -{ - u64 *sptep; - struct rmap_iterator iter; - int young = 0; - - for_each_rmap_spte(rmap_head, &iter, sptep) - young |= mmu_spte_age(sptep); - - return young; -} - -static bool kvm_test_age_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, gfn_t gfn, int level) -{ - u64 *sptep; - struct rmap_iterator iter; - - for_each_rmap_spte(rmap_head, &iter, sptep) - if (is_accessed_spte(*sptep)) - return true; - return false; -} - #define RMAP_RECYCLE_THRESHOLD 1000 static void __rmap_add(struct kvm *kvm, @@ -1629,12 +1605,52 @@ static void rmap_add(struct kvm_vcpu *vcpu, const struct kvm_memory_slot *slot, __rmap_add(vcpu->kvm, cache, slot, spte, gfn, access); } +static bool kvm_rmap_age_gfn_range(struct kvm *kvm, + struct kvm_gfn_range *range, bool test_only) +{ + struct slot_rmap_walk_iterator iterator; + struct rmap_iterator iter; + bool young = false; + u64 *sptep; + + for_each_slot_rmap_range(range->slot, PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + range->start, range->end - 1, &iterator) { + for_each_rmap_spte(iterator.rmap, &iter, sptep) { + u64 spte = *sptep; + + if (!is_accessed_spte(spte)) + continue; + + if (test_only) + return true; + + if (spte_ad_enabled(spte)) { + clear_bit((ffs(shadow_accessed_mask) - 1), + (unsigned long *)sptep); + } else { + /* + * Capture the dirty status of the page, so that + * it doesn't get lost when the SPTE is marked + * for access tracking. + */ + if (is_writable_pte(spte)) + kvm_set_pfn_dirty(spte_to_pfn(spte)); + + spte = mark_spte_for_access_track(spte); + mmu_spte_update_no_track(sptep, spte); + } + young = true; + } + } + return young; +} + bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { bool young = false; if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap); + young = kvm_rmap_age_gfn_range(kvm, range, false); if (tdp_mmu_enabled) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); @@ -1647,7 +1663,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool young = false; if (kvm_memslots_have_rmaps(kvm)) - young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap); + young = kvm_rmap_age_gfn_range(kvm, range, true); if (tdp_mmu_enabled) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); @@ -2713,36 +2729,49 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) write_unlock(&kvm->mmu_lock); } -int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +bool __kvm_mmu_unprotect_gfn_and_retry(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + bool always_retry) { - struct kvm_mmu_page *sp; + struct kvm *kvm = vcpu->kvm; LIST_HEAD(invalid_list); - int r; + struct kvm_mmu_page *sp; + gpa_t gpa = cr2_or_gpa; + bool r = false; + + /* + * Bail early if there aren't any write-protected shadow pages to avoid + * unnecessarily taking mmu_lock lock, e.g. if the gfn is write-tracked + * by a third party. Reading indirect_shadow_pages without holding + * mmu_lock is safe, as this is purely an optimization, i.e. a false + * positive is benign, and a false negative will simply result in KVM + * skipping the unprotect+retry path, which is also an optimization. + */ + if (!READ_ONCE(kvm->arch.indirect_shadow_pages)) + goto out; + + if (!vcpu->arch.mmu->root_role.direct) { + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); + if (gpa == INVALID_GPA) + goto out; + } - r = 0; write_lock(&kvm->mmu_lock); - for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) { - r = 1; + for_each_gfn_valid_sp_with_gptes(kvm, sp, gpa_to_gfn(gpa)) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - } + + /* + * Snapshot the result before zapping, as zapping will remove all list + * entries, i.e. checking the list later would yield a false negative. + */ + r = !list_empty(&invalid_list); kvm_mmu_commit_zap_page(kvm, &invalid_list); write_unlock(&kvm->mmu_lock); - return r; -} - -static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa; - int r; - - if (vcpu->arch.mmu->root_role.direct) - return 0; - - gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - +out: + if (r || always_retry) { + vcpu->arch.last_retry_eip = kvm_rip_read(vcpu); + vcpu->arch.last_retry_addr = cr2_or_gpa; + } return r; } @@ -2914,10 +2943,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, trace_kvm_mmu_set_spte(level, gfn, sptep); } - if (wrprot) { - if (write_fault) - ret = RET_PF_EMULATE; - } + if (wrprot && write_fault) + ret = RET_PF_WRITE_PROTECTED; if (flush) kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); @@ -4549,7 +4576,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_RETRY; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4618,8 +4645,6 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, if (!flags) { trace_kvm_page_fault(vcpu, fault_address, error_code); - if (kvm_event_needs_reinjection(vcpu)) - kvm_mmu_unprotect_page_virt(vcpu, fault_address); r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn, insn_len); } else if (flags & KVM_PV_REASON_PAGE_NOT_PRESENT) { @@ -4642,7 +4667,7 @@ static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, int r; if (page_fault_handle_page_track(vcpu, fault)) - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; r = fast_page_fault(vcpu, fault); if (r != RET_PF_INVALID) @@ -4719,6 +4744,7 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, switch (r) { case RET_PF_FIXED: case RET_PF_SPURIOUS: + case RET_PF_WRITE_PROTECTED: return 0; case RET_PF_EMULATE: @@ -5963,6 +5989,106 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, write_unlock(&vcpu->kvm->mmu_lock); } +static bool is_write_to_guest_page_table(u64 error_code) +{ + const u64 mask = PFERR_GUEST_PAGE_MASK | PFERR_WRITE_MASK | PFERR_PRESENT_MASK; + + return (error_code & mask) == mask; +} + +static int kvm_mmu_write_protect_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, + u64 error_code, int *emulation_type) +{ + bool direct = vcpu->arch.mmu->root_role.direct; + + /* + * Do not try to unprotect and retry if the vCPU re-faulted on the same + * RIP with the same address that was previously unprotected, as doing + * so will likely put the vCPU into an infinite. E.g. if the vCPU uses + * a non-page-table modifying instruction on the PDE that points to the + * instruction, then unprotecting the gfn will unmap the instruction's + * code, i.e. make it impossible for the instruction to ever complete. + */ + if (vcpu->arch.last_retry_eip == kvm_rip_read(vcpu) && + vcpu->arch.last_retry_addr == cr2_or_gpa) + return RET_PF_EMULATE; + + /* + * Reset the unprotect+retry values that guard against infinite loops. + * The values will be refreshed if KVM explicitly unprotects a gfn and + * retries, in all other cases it's safe to retry in the future even if + * the next page fault happens on the same RIP+address. + */ + vcpu->arch.last_retry_eip = 0; + vcpu->arch.last_retry_addr = 0; + + /* + * It should be impossible to reach this point with an MMIO cache hit, + * as RET_PF_WRITE_PROTECTED is returned if and only if there's a valid, + * writable memslot, and creating a memslot should invalidate the MMIO + * cache by way of changing the memslot generation. WARN and disallow + * retry if MMIO is detected, as retrying MMIO emulation is pointless + * and could put the vCPU into an infinite loop because the processor + * will keep faulting on the non-existent MMIO address. + */ + if (WARN_ON_ONCE(mmio_info_in_cache(vcpu, cr2_or_gpa, direct))) + return RET_PF_EMULATE; + + /* + * Before emulating the instruction, check to see if the access was due + * to a read-only violation while the CPU was walking non-nested NPT + * page tables, i.e. for a direct MMU, for _guest_ page tables in L1. + * If L1 is sharing (a subset of) its page tables with L2, e.g. by + * having nCR3 share lower level page tables with hCR3, then when KVM + * (L0) write-protects the nested NPTs, i.e. npt12 entries, KVM is also + * unknowingly write-protecting L1's guest page tables, which KVM isn't + * shadowing. + * + * Because the CPU (by default) walks NPT page tables using a write + * access (to ensure the CPU can do A/D updates), page walks in L1 can + * trigger write faults for the above case even when L1 isn't modifying + * PTEs. As a result, KVM will unnecessarily emulate (or at least, try + * to emulate) an excessive number of L1 instructions; because L1's MMU + * isn't shadowed by KVM, there is no need to write-protect L1's gPTEs + * and thus no need to emulate in order to guarantee forward progress. + * + * Try to unprotect the gfn, i.e. zap any shadow pages, so that L1 can + * proceed without triggering emulation. If one or more shadow pages + * was zapped, skip emulation and resume L1 to let it natively execute + * the instruction. If no shadow pages were zapped, then the write- + * fault is due to something else entirely, i.e. KVM needs to emulate, + * as resuming the guest will put it into an infinite loop. + * + * Note, this code also applies to Intel CPUs, even though it is *very* + * unlikely that an L1 will share its page tables (IA32/PAE/paging64 + * format) with L2's page tables (EPT format). + * + * For indirect MMUs, i.e. if KVM is shadowing the current MMU, try to + * unprotect the gfn and retry if an event is awaiting reinjection. If + * KVM emulates multiple instructions before completing event injection, + * the event could be delayed beyond what is architecturally allowed, + * e.g. KVM could inject an IRQ after the TPR has been raised. + */ + if (((direct && is_write_to_guest_page_table(error_code)) || + (!direct && kvm_event_needs_reinjection(vcpu))) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) + return RET_PF_RETRY; + + /* + * The gfn is write-protected, but if KVM detects its emulating an + * instruction that is unlikely to be used to modify page tables, or if + * emulation fails, KVM can try to unprotect the gfn and let the CPU + * re-execute the instruction that caused the page fault. Do not allow + * retrying an instruction from a nested guest as KVM is only explicitly + * shadowing L1's page tables, i.e. unprotecting something for L1 isn't + * going to magically fix whatever issue caused L2 to fail. + */ + if (!is_guest_mode(vcpu)) + *emulation_type |= EMULTYPE_ALLOW_RETRY_PF; + + return RET_PF_EMULATE; +} + int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { @@ -6008,6 +6134,10 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r < 0) return r; + if (r == RET_PF_WRITE_PROTECTED) + r = kvm_mmu_write_protect_fault(vcpu, cr2_or_gpa, error_code, + &emulation_type); + if (r == RET_PF_FIXED) vcpu->stat.pf_fixed++; else if (r == RET_PF_EMULATE) @@ -6018,32 +6148,6 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r != RET_PF_EMULATE) return 1; - /* - * Before emulating the instruction, check if the error code - * was due to a RO violation while translating the guest page. - * This can occur when using nested virtualization with nested - * paging in both guests. If true, we simply unprotect the page - * and resume the guest. - */ - if (vcpu->arch.mmu->root_role.direct && - (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) { - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa)); - return 1; - } - - /* - * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still - * optimistically try to just unprotect the page and let the processor - * re-execute the instruction that caused the page fault. Do not allow - * retrying MMIO emulation, as it's not only pointless but could also - * cause us to enter an infinite loop because the processor will keep - * faulting on the non-existent MMIO address. Retrying an instruction - * from a nested guest is also pointless and dangerous as we are only - * explicitly shadowing L1's page tables, i.e. unprotecting something - * for L1 isn't going to magically fix whatever issue cause L2 to fail. - */ - if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu)) - emulation_type |= EMULTYPE_ALLOW_RETRY_PF; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); @@ -6202,59 +6306,6 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, } EXPORT_SYMBOL_GPL(kvm_configure_mmu); -/* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_rmaps_handler) (struct kvm *kvm, - struct kvm_rmap_head *rmap_head, - const struct kvm_memory_slot *slot); - -static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, - bool flush_on_yield, bool flush) -{ - struct slot_rmap_walk_iterator iterator; - - lockdep_assert_held_write(&kvm->mmu_lock); - - for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, - end_gfn, &iterator) { - if (iterator.rmap) - flush |= fn(kvm, iterator.rmap, slot); - - if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - if (flush && flush_on_yield) { - kvm_flush_remote_tlbs_range(kvm, start_gfn, - iterator.gfn - start_gfn + 1); - flush = false; - } - cond_resched_rwlock_write(&kvm->mmu_lock); - } - } - - return flush; -} - -static __always_inline bool walk_slot_rmaps(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - int start_level, int end_level, - bool flush_on_yield) -{ - return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, - slot->base_gfn, slot->base_gfn + slot->npages - 1, - flush_on_yield, false); -} - -static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, - const struct kvm_memory_slot *slot, - slot_rmaps_handler fn, - bool flush_on_yield) -{ - return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); -} - static void free_mmu_pages(struct kvm_mmu *mmu) { if (!tdp_enabled && mmu->pae_root) @@ -6528,9 +6579,8 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (WARN_ON_ONCE(start >= end)) continue; - flush = __walk_slot_rmaps(kvm, memslot, __kvm_zap_rmap, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = __kvm_rmap_zap_gfn_range(kvm, memslot, start, + end, true, flush); } } @@ -6818,7 +6868,7 @@ static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm, */ for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) __walk_slot_rmaps(kvm, slot, shadow_mmu_try_split_huge_pages, - level, level, start, end - 1, true, false); + level, level, start, end - 1, true, true, false); } /* Must be called with the mmu_lock held in write-mode. */ @@ -6997,10 +7047,42 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) kvm_mmu_zap_all(kvm); } +/* + * Zapping leaf SPTEs with memslot range when a memslot is moved/deleted. + * + * Zapping non-leaf SPTEs, a.k.a. not-last SPTEs, isn't required, worst + * case scenario we'll have unused shadow pages lying around until they + * are recycled due to age or when the VM is destroyed. + */ +static void kvm_mmu_zap_memslot_leafs(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + struct kvm_gfn_range range = { + .slot = slot, + .start = slot->base_gfn, + .end = slot->base_gfn + slot->npages, + .may_block = true, + }; + + write_lock(&kvm->mmu_lock); + if (kvm_unmap_gfn_range(kvm, &range)) + kvm_flush_remote_tlbs_memslot(kvm, slot); + + write_unlock(&kvm->mmu_lock); +} + +static inline bool kvm_memslot_flush_zap_all(struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_DEFAULT_VM && + kvm_check_has_quirk(kvm, KVM_X86_QUIRK_SLOT_ZAP_ALL); +} + void kvm_arch_flush_shadow_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { - kvm_mmu_zap_all_fast(kvm); + if (kvm_memslot_flush_zap_all(kvm)) + kvm_mmu_zap_all_fast(kvm); + else + kvm_mmu_zap_memslot_leafs(kvm, slot); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 1721d97743e9..c98827840e07 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -258,6 +258,8 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); * RET_PF_CONTINUE: So far, so good, keep handling the page fault. * RET_PF_RETRY: let CPU fault again on the address. * RET_PF_EMULATE: mmio page fault, emulate the instruction directly. + * RET_PF_WRITE_PROTECTED: the gfn is write-protected, either unprotected the + * gfn and retry, or emulate the instruction directly. * RET_PF_INVALID: the spte is invalid, let the real page fault path update it. * RET_PF_FIXED: The faulting entry has been fixed. * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU. @@ -274,6 +276,7 @@ enum { RET_PF_CONTINUE = 0, RET_PF_RETRY, RET_PF_EMULATE, + RET_PF_WRITE_PROTECTED, RET_PF_INVALID, RET_PF_FIXED, RET_PF_SPURIOUS, @@ -349,8 +352,6 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level); -void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); - void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index 195d98bc8de8..f35a830ce469 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -57,6 +57,7 @@ TRACE_DEFINE_ENUM(RET_PF_CONTINUE); TRACE_DEFINE_ENUM(RET_PF_RETRY); TRACE_DEFINE_ENUM(RET_PF_EMULATE); +TRACE_DEFINE_ENUM(RET_PF_WRITE_PROTECTED); TRACE_DEFINE_ENUM(RET_PF_INVALID); TRACE_DEFINE_ENUM(RET_PF_FIXED); TRACE_DEFINE_ENUM(RET_PF_SPURIOUS); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 69941cebb3a8..ae7d39ff2d07 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -646,10 +646,10 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, * really care if it changes underneath us after this point). */ if (FNAME(gpte_changed)(vcpu, gw, top_level)) - goto out_gpte_changed; + return RET_PF_RETRY; if (WARN_ON_ONCE(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) - goto out_gpte_changed; + return RET_PF_RETRY; /* * Load a new root and retry the faulting instruction in the extremely @@ -659,7 +659,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, */ if (unlikely(kvm_mmu_is_dummy_root(vcpu->arch.mmu->root.hpa))) { kvm_make_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu); - goto out_gpte_changed; + return RET_PF_RETRY; } for_each_shadow_entry(vcpu, fault->addr, it) { @@ -674,34 +674,38 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, sp = kvm_mmu_get_child_sp(vcpu, it.sptep, table_gfn, false, access); - if (sp != ERR_PTR(-EEXIST)) { - /* - * We must synchronize the pagetable before linking it - * because the guest doesn't need to flush tlb when - * the gpte is changed from non-present to present. - * Otherwise, the guest may use the wrong mapping. - * - * For PG_LEVEL_4K, kvm_mmu_get_page() has already - * synchronized it transiently via kvm_sync_page(). - * - * For higher level pagetable, we synchronize it via - * the slower mmu_sync_children(). If it needs to - * break, some progress has been made; return - * RET_PF_RETRY and retry on the next #PF. - * KVM_REQ_MMU_SYNC is not necessary but it - * expedites the process. - */ - if (sp->unsync_children && - mmu_sync_children(vcpu, sp, false)) - return RET_PF_RETRY; - } + /* + * Synchronize the new page before linking it, as the CPU (KVM) + * is architecturally disallowed from inserting non-present + * entries into the TLB, i.e. the guest isn't required to flush + * the TLB when changing the gPTE from non-present to present. + * + * For PG_LEVEL_4K, kvm_mmu_find_shadow_page() has already + * synchronized the page via kvm_sync_page(). + * + * For higher level pages, which cannot be unsync themselves + * but can have unsync children, synchronize via the slower + * mmu_sync_children(). If KVM needs to drop mmu_lock due to + * contention or to reschedule, instruct the caller to retry + * the #PF (mmu_sync_children() ensures forward progress will + * be made). + */ + if (sp != ERR_PTR(-EEXIST) && sp->unsync_children && + mmu_sync_children(vcpu, sp, false)) + return RET_PF_RETRY; /* - * Verify that the gpte in the page we've just write - * protected is still there. + * Verify that the gpte in the page, which is now either + * write-protected or unsync, wasn't modified between the fault + * and acquiring mmu_lock. This needs to be done even when + * reusing an existing shadow page to ensure the information + * gathered by the walker matches the information stored in the + * shadow page (which could have been modified by a different + * vCPU even if the page was already linked). Holding mmu_lock + * prevents the shadow page from changing after this point. */ if (FNAME(gpte_changed)(vcpu, gw, it.level - 1)) - goto out_gpte_changed; + return RET_PF_RETRY; if (sp != ERR_PTR(-EEXIST)) link_shadow_page(vcpu, it.sptep, sp); @@ -755,9 +759,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, FNAME(pte_prefetch)(vcpu, gw, it.sptep); return ret; - -out_gpte_changed: - return RET_PF_RETRY; } /* @@ -805,7 +806,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (page_fault_handle_page_track(vcpu, fault)) { shadow_page_table_clear_flood(vcpu, fault->addr); - return RET_PF_EMULATE; + return RET_PF_WRITE_PROTECTED; } r = mmu_topup_memory_caches(vcpu, true); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 3c55955bcaf8..3b996c1fdaab 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1046,10 +1046,8 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, * protected, emulation is needed. If the emulation was skipped, * the vCPU would have the same fault again. */ - if (wrprot) { - if (fault->write) - ret = RET_PF_EMULATE; - } + if (wrprot && fault->write) + ret = RET_PF_WRITE_PROTECTED; /* If a MMIO SPTE is installed, the MMIO will need to be emulated. */ if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) { diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 2f4e155080ba..0d17d6b70639 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -17,6 +17,7 @@ enum kvm_only_cpuid_leafs { CPUID_8000_0007_EDX, CPUID_8000_0022_EAX, CPUID_7_2_EDX, + CPUID_24_0_EBX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -46,6 +47,7 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) #define X86_FEATURE_AMX_COMPLEX KVM_X86_FEATURE(CPUID_7_1_EDX, 8) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +#define X86_FEATURE_AVX10 KVM_X86_FEATURE(CPUID_7_1_EDX, 19) /* Intel-defined sub-features, CPUID level 0x00000007:2 (EDX) */ #define X86_FEATURE_INTEL_PSFD KVM_X86_FEATURE(CPUID_7_2_EDX, 0) @@ -55,6 +57,11 @@ enum kvm_only_cpuid_leafs { #define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) #define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) +/* Intel-defined sub-features, CPUID level 0x00000024:0 (EBX) */ +#define X86_FEATURE_AVX10_128 KVM_X86_FEATURE(CPUID_24_0_EBX, 16) +#define X86_FEATURE_AVX10_256 KVM_X86_FEATURE(CPUID_24_0_EBX, 17) +#define X86_FEATURE_AVX10_512 KVM_X86_FEATURE(CPUID_24_0_EBX, 18) + /* CPUID level 0x80000007 (EDX). */ #define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) @@ -90,6 +97,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX}, [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, + [CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX}, }; /* diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 00e3c27d2a87..85241c0c7f56 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -624,17 +624,31 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) #endif /* - * Give leave_smm() a chance to make ISA-specific changes to the vCPU - * state (e.g. enter guest mode) before loading state from the SMM - * state-save area. + * FIXME: When resuming L2 (a.k.a. guest mode), the transition to guest + * mode should happen _after_ loading state from SMRAM. However, KVM + * piggybacks the nested VM-Enter flows (which is wrong for many other + * reasons), and so nSVM/nVMX would clobber state that is loaded from + * SMRAM and from the VMCS/VMCB. */ if (kvm_x86_call(leave_smm)(vcpu, &smram)) return X86EMUL_UNHANDLEABLE; #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - return rsm_load_state_64(ctxt, &smram.smram64); + ret = rsm_load_state_64(ctxt, &smram.smram64); else #endif - return rsm_load_state_32(ctxt, &smram.smram32); + ret = rsm_load_state_32(ctxt, &smram.smram32); + + /* + * If RSM fails and triggers shutdown, architecturally the shutdown + * occurs *before* the transition to guest mode. But due to KVM's + * flawed handling of RSM to L2 (see above), the vCPU may already be + * in_guest_mode(). Force the vCPU out of guest mode before delivering + * the shutdown, so that L1 enters shutdown instead of seeing a VM-Exit + * that architecturally shouldn't be possible. + */ + if (ret != X86EMUL_CONTINUE && is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + return ret; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 6f704c1037e5..d5314cb7dff4 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1693,8 +1693,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; ret = -ENOMEM; - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL_ACCOUNT); - save = kzalloc(sizeof(*save), GFP_KERNEL_ACCOUNT); + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + save = kzalloc(sizeof(*save), GFP_KERNEL); if (!ctl || !save) goto out_free; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5ab2c92c7331..9df3e1e5ae81 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -573,7 +573,7 @@ static void __svm_write_tsc_multiplier(u64 multiplier) static __always_inline struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) { - return page_address(sd->save_area) + 0x400; + return &sd->save_area->host_sev_es_save; } static inline void kvm_cpu_svm_disable(void) @@ -592,14 +592,14 @@ static inline void kvm_cpu_svm_disable(void) } } -static void svm_emergency_disable(void) +static void svm_emergency_disable_virtualization_cpu(void) { kvm_rebooting = true; kvm_cpu_svm_disable(); } -static void svm_hardware_disable(void) +static void svm_disable_virtualization_cpu(void) { /* Make sure we clean up behind us */ if (tsc_scaling) @@ -610,7 +610,7 @@ static void svm_hardware_disable(void) amd_pmu_disable_virt(); } -static int svm_hardware_enable(void) +static int svm_enable_virtualization_cpu(void) { struct svm_cpu_data *sd; @@ -696,7 +696,7 @@ static void svm_cpu_uninit(int cpu) return; kfree(sd->sev_vmcbs); - __free_page(sd->save_area); + __free_page(__sme_pa_to_page(sd->save_area_pa)); sd->save_area_pa = 0; sd->save_area = NULL; } @@ -704,23 +704,24 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); + struct page *save_area_page; int ret = -ENOMEM; memset(sd, 0, sizeof(struct svm_cpu_data)); - sd->save_area = snp_safe_alloc_page_node(cpu_to_node(cpu), GFP_KERNEL); - if (!sd->save_area) + save_area_page = snp_safe_alloc_page_node(cpu_to_node(cpu), GFP_KERNEL); + if (!save_area_page) return ret; ret = sev_cpu_init(sd); if (ret) goto free_save_area; - sd->save_area_pa = __sme_page_pa(sd->save_area); + sd->save_area = page_address(save_area_page); + sd->save_area_pa = __sme_page_pa(save_area_page); return 0; free_save_area: - __free_page(sd->save_area); - sd->save_area = NULL; + __free_page(save_area_page); return ret; } @@ -1124,8 +1125,7 @@ static void svm_hardware_unsetup(void) for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), - get_order(IOPM_SIZE)); + __free_pages(__sme_pa_to_page(iopm_base), get_order(IOPM_SIZE)); iopm_base = 0; } @@ -1301,7 +1301,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu) if (!kvm_hlt_in_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_HLT); - control->iopm_base_pa = __sme_set(iopm_base); + control->iopm_base_pa = iopm_base; control->msrpm_base_pa = __sme_set(__pa(svm->msrpm)); control->int_ctl = V_INTR_MASKING_MASK; @@ -1503,7 +1503,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) sev_free_vcpu(vcpu); - __free_page(pfn_to_page(__sme_clr(svm->vmcb01.pa) >> PAGE_SHIFT)); + __free_page(__sme_pa_to_page(svm->vmcb01.pa)); __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } @@ -1533,7 +1533,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * TSC_AUX is always virtualized for SEV-ES guests when the feature is * available. The user return MSR support is not required in this case * because TSC_AUX is restored on #VMEXIT from the host save area - * (which has been initialized in svm_hardware_enable()). + * (which has been initialized in svm_enable_virtualization_cpu()). */ if (likely(tsc_aux_uret_slot >= 0) && (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) @@ -2825,17 +2825,17 @@ static int efer_trap(struct kvm_vcpu *vcpu) return kvm_complete_insn_gp(vcpu, ret); } -static int svm_get_msr_feature(struct kvm_msr_entry *msr) +static int svm_get_feature_msr(u32 msr, u64 *data) { - msr->data = 0; + *data = 0; - switch (msr->index) { + switch (msr) { case MSR_AMD64_DE_CFG: if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) - msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; + *data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; @@ -3144,7 +3144,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * feature is available. The user return MSR support is not * required in this case because TSC_AUX is restored on #VMEXIT * from the host save area (which has been initialized in - * svm_hardware_enable()). + * svm_enable_virtualization_cpu()). */ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) break; @@ -3191,18 +3191,21 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; case MSR_AMD64_DE_CFG: { - struct kvm_msr_entry msr_entry; + u64 supported_de_cfg; - msr_entry.index = msr->index; - if (svm_get_msr_feature(&msr_entry)) + if (svm_get_feature_msr(ecx, &supported_de_cfg)) return 1; - /* Check the supported bits */ - if (data & ~msr_entry.data) + if (data & ~supported_de_cfg) return 1; - /* Don't allow the guest to change a bit, #GP */ - if (!msr->host_initiated && (data ^ msr_entry.data)) + /* + * Don't let the guest change the host-programmed value. The + * MSR is very model specific, i.e. contains multiple bits that + * are completely unknown to KVM, and the one bit known to KVM + * is simply a reflection of hardware capabilities. + */ + if (!msr->host_initiated && data != svm->msr_decfg) return 1; svm->msr_decfg = data; @@ -4156,12 +4159,21 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; - if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && - to_svm(vcpu)->vmcb->control.exit_info_1) + switch (svm->vmcb->control.exit_code) { + case SVM_EXIT_MSR: + if (!svm->vmcb->control.exit_info_1) + break; return handle_fastpath_set_msr_irqoff(vcpu); + case SVM_EXIT_HLT: + return handle_fastpath_hlt(vcpu); + default: + break; + } return EXIT_FASTPATH_NONE; } @@ -4992,8 +5004,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_processor_compatibility = svm_check_processor_compat, .hardware_unsetup = svm_hardware_unsetup, - .hardware_enable = svm_hardware_enable, - .hardware_disable = svm_hardware_disable, + .enable_virtualization_cpu = svm_enable_virtualization_cpu, + .disable_virtualization_cpu = svm_disable_virtualization_cpu, + .emergency_disable_virtualization_cpu = svm_emergency_disable_virtualization_cpu, .has_emulated_msr = svm_has_emulated_msr, .vcpu_create = svm_vcpu_create, @@ -5011,7 +5024,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_unblocking = avic_vcpu_unblocking, .update_exception_bitmap = svm_update_exception_bitmap, - .get_msr_feature = svm_get_msr_feature, + .get_feature_msr = svm_get_feature_msr, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, @@ -5062,6 +5075,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_nmi_window = svm_enable_nmi_window, .enable_irq_window = svm_enable_irq_window, .update_cr8_intercept = svm_update_cr8_intercept, + + .x2apic_icr_is_split = true, .set_virtual_apic_mode = avic_refresh_virtual_apic_mode, .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, .apicv_post_state_restore = avic_apicv_post_state_restore, @@ -5266,7 +5281,7 @@ static __init int svm_hardware_setup(void) iopm_va = page_address(iopm_pages); memset(iopm_va, 0xff, PAGE_SIZE * (1 << order)); - iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + iopm_base = __sme_page_pa(iopm_pages); init_msrpm_offsets(); @@ -5425,8 +5440,6 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static void __svm_exit(void) { kvm_x86_vendor_exit(); - - cpu_emergency_unregister_virt_callback(svm_emergency_disable); } static int __init svm_init(void) @@ -5442,8 +5455,6 @@ static int __init svm_init(void) if (r) return r; - cpu_emergency_register_virt_callback(svm_emergency_disable); - /* * Common KVM initialization _must_ come last, after this, /dev/kvm is * exposed to userspace! diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 76107c7d0595..43fa6a16eb19 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -25,7 +25,21 @@ #include "cpuid.h" #include "kvm_cache_regs.h" -#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) +/* + * Helpers to convert to/from physical addresses for pages whose address is + * consumed directly by hardware. Even though it's a physical address, SVM + * often restricts the address to the natural width, hence 'unsigned long' + * instead of 'hpa_t'. + */ +static inline unsigned long __sme_page_pa(struct page *page) +{ + return __sme_set(page_to_pfn(page) << PAGE_SHIFT); +} + +static inline struct page *__sme_pa_to_page(unsigned long pa) +{ + return pfn_to_page(__sme_clr(pa) >> PAGE_SHIFT); +} #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 @@ -321,7 +335,7 @@ struct svm_cpu_data { u32 next_asid; u32 min_asid; - struct page *save_area; + struct vmcb *save_area; unsigned long save_area_pa; struct vmcb *current_vmcb; diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index a0c8eb37d3e1..2ed80aea3bb1 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -209,10 +209,8 @@ SYM_FUNC_START(__svm_vcpu_run) 7: vmload %_ASM_AX 8: -#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT /* Clobbers RAX, RCX, RDX. */ RESTORE_HOST_SPEC_CTRL @@ -348,10 +346,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) 2: cli -#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE -#endif + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 41a4533f9989..cb6588238f46 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -54,9 +54,7 @@ struct nested_vmx_msrs { }; struct vmcs_config { - int size; - u32 basic_cap; - u32 revision_id; + u64 basic; u32 pin_based_exec_ctrl; u32 cpu_based_exec_ctrl; u32 cpu_based_2nd_exec_ctrl; @@ -76,7 +74,7 @@ extern struct vmx_capability vmx_capability __ro_after_init; static inline bool cpu_has_vmx_basic_inout(void) { - return (((u64)vmcs_config.basic_cap << 32) & VMX_BASIC_INOUT); + return vmcs_config.basic & VMX_BASIC_INOUT; } static inline bool cpu_has_virtual_nmis(void) @@ -225,7 +223,7 @@ static inline bool cpu_has_vmx_vmfunc(void) static inline bool cpu_has_vmx_shadow_vmcs(void) { /* check if the cpu supports writing r/o exit information fields */ - if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) + if (!(vmcs_config.misc & VMX_MISC_VMWRITE_SHADOW_RO_FIELDS)) return false; return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -367,7 +365,7 @@ static inline bool cpu_has_vmx_invvpid_global(void) static inline bool cpu_has_vmx_intel_pt(void) { - return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) && + return (vmcs_config.misc & VMX_MISC_INTEL_PT) && (vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) && (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL); } diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 0bf35ebe8a1b..7668e2fb8043 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -23,8 +23,10 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .hardware_unsetup = vmx_hardware_unsetup, - .hardware_enable = vmx_hardware_enable, - .hardware_disable = vmx_hardware_disable, + .enable_virtualization_cpu = vmx_enable_virtualization_cpu, + .disable_virtualization_cpu = vmx_disable_virtualization_cpu, + .emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu, + .has_emulated_msr = vmx_has_emulated_msr, .vm_size = sizeof(struct kvm_vmx), @@ -41,7 +43,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vcpu_put = vmx_vcpu_put, .update_exception_bitmap = vmx_update_exception_bitmap, - .get_msr_feature = vmx_get_msr_feature, + .get_feature_msr = vmx_get_feature_msr, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, @@ -89,6 +91,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .enable_nmi_window = vmx_enable_nmi_window, .enable_irq_window = vmx_enable_irq_window, .update_cr8_intercept = vmx_update_cr8_intercept, + + .x2apic_icr_is_split = false, .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 2392a7ef254d..a8e7bc04d9bf 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -981,7 +981,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); goto fail; } - if (kvm_set_msr(vcpu, e.index, e.value)) { + if (kvm_set_msr_with_filter(vcpu, e.index, e.value)) { pr_debug_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", __func__, i, e.index, e.value); @@ -1017,7 +1017,7 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu, } } - if (kvm_get_msr(vcpu, msr_index, data)) { + if (kvm_get_msr_with_filter(vcpu, msr_index, data)) { pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__, msr_index); return false; @@ -1112,9 +1112,9 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu, /* * Emulated VMEntry does not fail here. Instead a less * accurate value will be returned by - * nested_vmx_get_vmexit_msr_value() using kvm_get_msr() - * instead of reading the value from the vmcs02 VMExit - * MSR-store area. + * nested_vmx_get_vmexit_msr_value() by reading KVM's + * internal MSR state instead of reading the value from + * the vmcs02 VMExit MSR-store area. */ pr_warn_ratelimited( "Not enough msr entries in msr_autostore. Can't add msr %x\n", @@ -1251,21 +1251,32 @@ static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask) static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved = - /* feature (except bit 48; see below) */ - BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) | - /* reserved */ - BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56); + const u64 feature_bits = VMX_BASIC_DUAL_MONITOR_TREATMENT | + VMX_BASIC_INOUT | + VMX_BASIC_TRUE_CTLS; + + const u64 reserved_bits = GENMASK_ULL(63, 56) | + GENMASK_ULL(47, 45) | + BIT_ULL(31); + u64 vmx_basic = vmcs_config.nested.basic; - if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * Except for 32BIT_PHYS_ADDR_ONLY, which is an anti-feature bit (has + * inverted polarity), the incoming value must not set feature bits or + * reserved bits that aren't allowed/supported by KVM. Fields, i.e. + * multi-bit values, are explicitly checked below. + */ + if (!is_bitwise_subset(vmx_basic, data, feature_bits | reserved_bits)) return -EINVAL; /* * KVM does not emulate a version of VMX that constrains physical * addresses of VMX structures (e.g. VMCS) to 32-bits. */ - if (data & BIT_ULL(48)) + if (data & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EINVAL; if (vmx_basic_vmcs_revision_id(vmx_basic) != @@ -1334,16 +1345,29 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data) static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data) { - const u64 feature_and_reserved_bits = - /* feature */ - BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) | - BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) | - /* reserved */ - GENMASK_ULL(13, 9) | BIT_ULL(31); + const u64 feature_bits = VMX_MISC_SAVE_EFER_LMA | + VMX_MISC_ACTIVITY_HLT | + VMX_MISC_ACTIVITY_SHUTDOWN | + VMX_MISC_ACTIVITY_WAIT_SIPI | + VMX_MISC_INTEL_PT | + VMX_MISC_RDMSR_IN_SMM | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMXOFF_BLOCK_SMI | + VMX_MISC_ZERO_LEN_INS; + + const u64 reserved_bits = BIT_ULL(31) | GENMASK_ULL(13, 9); + u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low, vmcs_config.nested.misc_high); - if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits)) + BUILD_BUG_ON(feature_bits & reserved_bits); + + /* + * The incoming value must not set feature bits or reserved bits that + * aren't allowed/supported by KVM. Fields, i.e. multi-bit values, are + * explicitly checked below. + */ + if (!is_bitwise_subset(vmx_misc, data, feature_bits | reserved_bits)) return -EINVAL; if ((vmx->nested.msrs.pinbased_ctls_high & @@ -2317,10 +2341,12 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 /* Posted interrupts setting is only taken from vmcs12. */ vmx->nested.pi_pending = false; - if (nested_cpu_has_posted_intr(vmcs12)) + if (nested_cpu_has_posted_intr(vmcs12)) { vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; - else + } else { + vmx->nested.posted_intr_nv = -1; exec_control &= ~PIN_BASED_POSTED_INTR; + } pin_controls_set(vmx, exec_control); /* @@ -2470,6 +2496,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { + 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); @@ -2507,7 +2534,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base); vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base); - vmx->segment_cache.bitmask = 0; + vmx_segment_cache_clear(vmx); } if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & @@ -4284,11 +4311,52 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) } if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { + int irq; + if (block_nested_events) return -EBUSY; if (!nested_exit_on_intr(vcpu)) goto no_vmexit; - nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + + if (!nested_exit_intr_ack_set(vcpu)) { + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); + return 0; + } + + irq = kvm_cpu_get_extint(vcpu); + if (irq != -1) { + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + return 0; + } + + irq = kvm_apic_has_interrupt(vcpu); + if (WARN_ON_ONCE(irq < 0)) + goto no_vmexit; + + /* + * If the IRQ is L2's PI notification vector, process posted + * interrupts for L2 instead of injecting VM-Exit, as the + * detection/morphing architecturally occurs when the IRQ is + * delivered to the CPU. Note, only interrupts that are routed + * through the local APIC trigger posted interrupt processing, + * and enabling posted interrupts requires ACK-on-exit. + */ + if (irq == vmx->nested.posted_intr_nv) { + vmx->nested.pi_pending = true; + kvm_apic_clear_irr(vcpu, irq); + goto no_vmexit; + } + + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); + + /* + * ACK the interrupt _after_ emulating VM-Exit, as the IRQ must + * be marked as in-service in vmcs01.GUEST_INTERRUPT_STATUS.SVI + * if APICv is active. + */ + kvm_apic_ack_interrupt(vcpu, irq); return 0; } @@ -4806,7 +4874,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) goto vmabort; } - if (kvm_set_msr(vcpu, h.index, h.value)) { + if (kvm_set_msr_with_filter(vcpu, h.index, h.value)) { pr_debug_ratelimited( "%s WRMSR failed (%u, 0x%x, 0x%llx)\n", __func__, j, h.index, h.value); @@ -4969,14 +5037,6 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; if (likely(!vmx->fail)) { - if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT && - nested_exit_intr_ack_set(vcpu)) { - int irq = kvm_cpu_get_interrupt(vcpu); - WARN_ON(irq < 0); - vmcs12->vm_exit_intr_info = irq | - INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; - } - if (vm_exit_reason != -1) trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, @@ -7051,7 +7111,7 @@ static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, { msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE | VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; @@ -7066,12 +7126,10 @@ static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) * guest, and the VMCS structure we give it - not about the * VMX support of the underlying hardware. */ - msrs->basic = - VMCS12_REVISION | - VMX_BASIC_TRUE_CTLS | - ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) | - (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT); + msrs->basic = vmx_basic_encode_vmcs_info(VMCS12_REVISION, VMCS12_SIZE, + X86_MEMTYPE_WB); + msrs->basic |= VMX_BASIC_TRUE_CTLS; if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; } diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index cce4e2aa30fb..2c296b6abb8c 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -39,11 +39,17 @@ bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port, static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_vmcs12; } static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu) { + lockdep_assert_once(lockdep_is_held(&vcpu->mutex) || + !refcount_read(&vcpu->kvm->users_count)); + return to_vmx(vcpu)->nested.cached_shadow_vmcs12; } @@ -109,7 +115,7 @@ static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu) static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) { return to_vmx(vcpu)->nested.msrs.misc_low & - MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 6fef01e0536e..a3c3d2a51f47 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -274,7 +274,7 @@ static int handle_encls_ecreate(struct kvm_vcpu *vcpu) * simultaneously set SGX_ATTR_PROVISIONKEY to bypass the check to * enforce restriction of access to the PROVISIONKEY. */ - contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL_ACCOUNT); + contents = (struct sgx_secs *)__get_free_page(GFP_KERNEL); if (!contents) return -ENOMEM; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 733a0c45d1a6..1a4438358c5e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -525,10 +525,6 @@ static const struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; -static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) -{ - vmx->segment_cache.bitmask = 0; -} static unsigned long host_idt_base; @@ -755,7 +751,7 @@ fault: return -EIO; } -static void vmx_emergency_disable(void) +void vmx_emergency_disable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); struct loaded_vmcs *v; @@ -1998,15 +1994,15 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, return !(msr->data & ~valid_bits); } -int vmx_get_msr_feature(struct kvm_msr_entry *msr) +int vmx_get_feature_msr(u32 msr, u64 *data) { - switch (msr->index) { + switch (msr) { case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; - return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); + return vmx_get_vmx_msr(&vmcs_config.nested, msr, data); default: - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } } @@ -2605,13 +2601,13 @@ static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) static int setup_vmcs_config(struct vmcs_config *vmcs_conf, struct vmx_capability *vmx_cap) { - u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; u32 _cpu_based_exec_control = 0; u32 _cpu_based_2nd_exec_control = 0; u64 _cpu_based_3rd_exec_control = 0; u32 _vmexit_control = 0; u32 _vmentry_control = 0; + u64 basic_msr; u64 misc_msr; int i; @@ -2734,29 +2730,29 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf, _vmexit_control &= ~x_ctrl; } - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); + rdmsrl(MSR_IA32_VMX_BASIC, basic_msr); /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) + if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE) return -EIO; #ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) + /* + * KVM expects to be able to shove all legal physical addresses into + * VMCS fields for 64-bit kernels, and per the SDM, "This bit is always + * 0 for processors that support Intel 64 architecture". + */ + if (basic_msr & VMX_BASIC_32BIT_PHYS_ADDR_ONLY) return -EIO; #endif /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) + if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB) return -EIO; rdmsrl(MSR_IA32_VMX_MISC, misc_msr); - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; - - vmcs_conf->revision_id = vmx_msr_low; - + vmcs_conf->basic = basic_msr; vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; vmcs_conf->cpu_based_2nd_exec_ctrl = _cpu_based_2nd_exec_control; @@ -2844,7 +2840,7 @@ fault: return -EFAULT; } -int vmx_hardware_enable(void) +int vmx_enable_virtualization_cpu(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2881,7 +2877,7 @@ static void vmclear_local_loaded_vmcss(void) __loaded_vmcs_clear(v); } -void vmx_hardware_disable(void) +void vmx_disable_virtualization_cpu(void) { vmclear_local_loaded_vmcss(); @@ -2903,13 +2899,13 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) if (!pages) return NULL; vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); + memset(vmcs, 0, vmx_basic_vmcs_size(vmcs_config.basic)); /* KVM supports Enlightened VMCS v1 only */ if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); if (shadow) vmcs->hdr.shadow_vmcs = 1; @@ -3002,7 +2998,7 @@ static __init int alloc_kvm_area(void) * physical CPU. */ if (kvm_is_using_evmcs()) - vmcs->hdr.revision_id = vmcs_config.revision_id; + vmcs->hdr.revision_id = vmx_basic_vmcs_revision_id(vmcs_config.basic); per_cpu(vmxarea, cpu) = vmcs; } @@ -4219,6 +4215,13 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * DO NOT query the vCPU's vmcs12, as vmcs12 is dynamically allocated + * and freed, and must not be accessed outside of vcpu->mutex. The + * vCPU's cached PI NV is valid if and only if posted interrupts + * enabled in its vmcs12, i.e. checking the vector also checks that + * L1 has enabled posted interrupts for L2. + */ if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* @@ -5804,8 +5807,9 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) error_code |= (exit_qualification & EPT_VIOLATION_RWX_MASK) ? PFERR_PRESENT_MASK : 0; - error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? - PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; + if (error_code & EPT_VIOLATION_GVA_IS_VALID) + error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ? + PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; /* * Check that the GPA doesn't exceed physical memory limits, as that is @@ -7265,6 +7269,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); + case EXIT_REASON_HLT: + return handle_fastpath_hlt(vcpu); default: return EXIT_FASTPATH_NONE; } @@ -7965,6 +7971,7 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_clear(X86_FEATURE_SGX_LC); kvm_cpu_cap_clear(X86_FEATURE_SGX1); kvm_cpu_cap_clear(X86_FEATURE_SGX2); + kvm_cpu_cap_clear(X86_FEATURE_SGX_EDECCSSA); } if (vmx_umip_emulated()) @@ -8515,7 +8522,7 @@ __init int vmx_hardware_setup(void) u64 use_timer_freq = 5000ULL * 1000 * 1000; cpu_preemption_timer_multi = - vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK; + vmx_misc_preemption_timer_rate(vmcs_config.misc); if (tsc_khz) use_timer_freq = (u64)tsc_khz * 1000; @@ -8582,8 +8589,6 @@ static void __vmx_exit(void) { allow_smaller_maxphyaddr = false; - cpu_emergency_unregister_virt_callback(vmx_emergency_disable); - vmx_cleanup_l1d_flush(); } @@ -8630,8 +8635,6 @@ static int __init vmx_init(void) pi_init_cpu(cpu); } - cpu_emergency_register_virt_callback(vmx_emergency_disable); - vmx_check_vmcs12_offsets(); /* diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 42498fa63abb..2325f773a20b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -17,10 +17,6 @@ #include "run_flags.h" #include "../mmu.h" -#define MSR_TYPE_R 1 -#define MSR_TYPE_W 2 -#define MSR_TYPE_RW 3 - #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4)) #ifdef CONFIG_X86_64 @@ -756,4 +752,9 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } +static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) +{ + vmx->segment_cache.bitmask = 0; +} + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h index eb48153bfd73..bba24ed99ee6 100644 --- a/arch/x86/kvm/vmx/vmx_onhyperv.h +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -104,6 +104,14 @@ static inline void evmcs_load(u64 phys_addr) struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(smp_processor_id()); + /* + * When enabling eVMCS, KVM verifies that every CPU has a valid hv_vp_assist_page() + * and aborts enabling the feature otherwise. CPU onlining path is also checked in + * vmx_hardware_enable(). + */ + if (KVM_BUG_ON(!vp_ap, kvm_get_running_vcpu()->kvm)) + return; + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) vp_ap->nested_control.features.directhypercall = 1; vp_ap->current_nested_vmcs = phys_addr; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 8060e5fc6dbd..93e020dc88f6 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -47,7 +47,7 @@ static __always_inline void vmcs_check16(unsigned long field) BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, "16-bit accessor invalid for 64-bit high field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, - "16-bit accessor invalid for 32-bit high field"); + "16-bit accessor invalid for 32-bit field"); BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, "16-bit accessor invalid for natural width field"); } diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index ce3221cd1d01..a55981c5216e 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -13,8 +13,9 @@ extern struct kvm_x86_init_ops vt_init_ops __initdata; void vmx_hardware_unsetup(void); int vmx_check_processor_compat(void); -int vmx_hardware_enable(void); -void vmx_hardware_disable(void); +int vmx_enable_virtualization_cpu(void); +void vmx_disable_virtualization_cpu(void); +void vmx_emergency_disable_virtualization_cpu(void); int vmx_vm_init(struct kvm *kvm); void vmx_vm_destroy(struct kvm *kvm); int vmx_vcpu_precreate(struct kvm *kvm); @@ -56,7 +57,7 @@ bool vmx_has_emulated_msr(struct kvm *kvm, u32 index); void vmx_msr_filter_changed(struct kvm_vcpu *vcpu); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); -int vmx_get_msr_feature(struct kvm_msr_entry *msr); +int vmx_get_feature_msr(u32 msr, u64 *data); int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg); void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c983c8e434b8..83fe0a78146f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -305,24 +305,237 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { static struct kmem_cache *x86_emulator_cache; /* - * When called, it means the previous get/set msr reached an invalid msr. - * Return true if we want to ignore/silent this failed msr access. + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track + * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, + * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that + * require host support, i.e. should be probed via RDMSR. emulated_msrs holds + * MSRs that KVM emulates without strictly requiring host support. + * msr_based_features holds MSRs that enumerate features, i.e. are effectively + * CPUID leafs. Note, msr_based_features isn't mutually exclusive with + * msrs_to_save and emulated_msrs. */ -static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) + +static const u32 msrs_to_save_base[] = { + MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_STAR, +#ifdef CONFIG_X86_64 + MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, +#endif + MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, + MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, + MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, + MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, + MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, + MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, + MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, + MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, + MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, + MSR_IA32_UMWAIT_CONTROL, + + MSR_IA32_XFD, MSR_IA32_XFD_ERR, +}; + +static const u32 msrs_to_save_pmu[] = { + MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, + MSR_ARCH_PERFMON_FIXED_CTR0 + 2, + MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, + MSR_CORE_PERF_GLOBAL_CTRL, + MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, + + /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ + MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, + MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, + MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, + MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, + MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, + MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, + MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, + MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, + + MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, + MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, + + /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ + MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, + MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, + MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, + MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, + + MSR_AMD64_PERF_CNTR_GLOBAL_CTL, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, + MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, +}; + +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; +static unsigned num_msrs_to_save; + +static const u32 emulated_msrs_all[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, + HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, + HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, + HV_X64_MSR_RESET, + HV_X64_MSR_VP_INDEX, + HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_SCONTROL, + HV_X64_MSR_STIMER0_CONFIG, + HV_X64_MSR_VP_ASSIST_PAGE, + HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, + HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, + HV_X64_MSR_SYNDBG_OPTIONS, + HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, + HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, + HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif + + MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, + + MSR_IA32_TSC_ADJUST, + MSR_IA32_TSC_DEADLINE, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, + MSR_IA32_MISC_ENABLE, + MSR_IA32_MCG_STATUS, + MSR_IA32_MCG_CTL, + MSR_IA32_MCG_EXT_CTL, + MSR_IA32_SMBASE, + MSR_SMI_COUNT, + MSR_PLATFORM_INFO, + MSR_MISC_FEATURES_ENABLES, + MSR_AMD64_VIRT_SPEC_CTRL, + MSR_AMD64_TSC_RATIO, + MSR_IA32_POWER_CTL, + MSR_IA32_UCODE_REV, + + /* + * KVM always supports the "true" VMX control MSRs, even if the host + * does not. The VMX MSRs as a whole are considered "emulated" as KVM + * doesn't strictly require them to exist in the host (ignoring that + * KVM would refuse to load in the first place if the core set of MSRs + * aren't supported). + */ + MSR_IA32_VMX_BASIC, + MSR_IA32_VMX_TRUE_PINBASED_CTLS, + MSR_IA32_VMX_TRUE_PROCBASED_CTLS, + MSR_IA32_VMX_TRUE_EXIT_CTLS, + MSR_IA32_VMX_TRUE_ENTRY_CTLS, + MSR_IA32_VMX_MISC, + MSR_IA32_VMX_CR0_FIXED0, + MSR_IA32_VMX_CR4_FIXED0, + MSR_IA32_VMX_VMCS_ENUM, + MSR_IA32_VMX_PROCBASED_CTLS2, + MSR_IA32_VMX_EPT_VPID_CAP, + MSR_IA32_VMX_VMFUNC, + + MSR_K7_HWCR, + MSR_KVM_POLL_CONTROL, +}; + +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; +static unsigned num_emulated_msrs; + +/* + * List of MSRs that control the existence of MSR-based features, i.e. MSRs + * that are effectively CPUID leafs. VMX MSRs are also included in the set of + * feature MSRs, but are handled separately to allow expedited lookups. + */ +static const u32 msr_based_features_all_except_vmx[] = { + MSR_AMD64_DE_CFG, + MSR_IA32_UCODE_REV, + MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_PERF_CAPABILITIES, +}; + +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; +static unsigned int num_msr_based_features; + +/* + * All feature MSRs except uCode revID, which tracks the currently loaded uCode + * patch, are immutable once the vCPU model is defined. + */ +static bool kvm_is_immutable_feature_msr(u32 msr) { - const char *op = write ? "wrmsr" : "rdmsr"; + int i; - if (ignore_msrs) { - if (report_ignored_msrs) - kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", - op, msr, data); - /* Mask the error */ + if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) return true; - } else { + + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { + if (msr == msr_based_features_all_except_vmx[i]) + return msr != MSR_IA32_UCODE_REV; + } + + return false; +} + +static bool kvm_is_advertised_msr(u32 msr_index) +{ + unsigned int i; + + for (i = 0; i < num_msrs_to_save; i++) { + if (msrs_to_save[i] == msr_index) + return true; + } + + for (i = 0; i < num_emulated_msrs; i++) { + if (emulated_msrs[i] == msr_index) + return true; + } + + return false; +} + +typedef int (*msr_access_t)(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated); + +static __always_inline int kvm_do_msr_access(struct kvm_vcpu *vcpu, u32 msr, + u64 *data, bool host_initiated, + enum kvm_msr_access rw, + msr_access_t msr_access_fn) +{ + const char *op = rw == MSR_TYPE_W ? "wrmsr" : "rdmsr"; + int ret; + + BUILD_BUG_ON(rw != MSR_TYPE_R && rw != MSR_TYPE_W); + + /* + * Zero the data on read failures to avoid leaking stack data to the + * guest and/or userspace, e.g. if the failure is ignored below. + */ + ret = msr_access_fn(vcpu, msr, data, host_initiated); + if (ret && rw == MSR_TYPE_R) + *data = 0; + + if (ret != KVM_MSR_RET_UNSUPPORTED) + return ret; + + /* + * Userspace is allowed to read MSRs, and write '0' to MSRs, that KVM + * advertises to userspace, even if an MSR isn't fully supported. + * Simply check that @data is '0', which covers both the write '0' case + * and all reads (in which case @data is zeroed on failure; see above). + */ + if (host_initiated && !*data && kvm_is_advertised_msr(msr)) + return 0; + + if (!ignore_msrs) { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", - op, msr, data); - return false; + op, msr, *data); + return ret; } + + if (report_ignored_msrs) + kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, *data); + + return 0; } static struct kmem_cache *kvm_alloc_emulator_cache(void) @@ -355,7 +568,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn) /* * Disabling irqs at this point since the following code could be - * interrupted and executed through kvm_arch_hardware_disable() + * interrupted and executed through kvm_arch_disable_virtualization_cpu() */ local_irq_save(flags); if (msrs->registered) { @@ -413,8 +626,7 @@ EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { - unsigned int cpu = smp_processor_id(); - struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu); + struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs); u64 value; int i; @@ -621,12 +833,6 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } -/* Forcibly leave the nested mode in cases like a vCPU reset */ -static void kvm_leave_nested(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops.nested_ops->leave_nested(vcpu); -} - static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -1412,178 +1618,6 @@ int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); /* - * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) track - * the set of MSRs that KVM exposes to userspace through KVM_GET_MSRS, - * KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. msrs_to_save holds MSRs that - * require host support, i.e. should be probed via RDMSR. emulated_msrs holds - * MSRs that KVM emulates without strictly requiring host support. - * msr_based_features holds MSRs that enumerate features, i.e. are effectively - * CPUID leafs. Note, msr_based_features isn't mutually exclusive with - * msrs_to_save and emulated_msrs. - */ - -static const u32 msrs_to_save_base[] = { - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_STAR, -#ifdef CONFIG_X86_64 - MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, -#endif - MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, - MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, - MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, - MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, - MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B, - MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B, - MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, - MSR_IA32_UMWAIT_CONTROL, - - MSR_IA32_XFD, MSR_IA32_XFD_ERR, -}; - -static const u32 msrs_to_save_pmu[] = { - MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, - MSR_ARCH_PERFMON_FIXED_CTR0 + 2, - MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, - MSR_CORE_PERF_GLOBAL_CTRL, - MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG, - - /* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */ - MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1, - MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3, - MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5, - MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7, - MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, - MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, - MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, - MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7, - - MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3, - MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3, - - /* This part of MSRs should match KVM_MAX_NR_AMD_GP_COUNTERS. */ - MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2, - MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, - MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, - MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, - - MSR_AMD64_PERF_CNTR_GLOBAL_CTL, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, - MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, -}; - -static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + - ARRAY_SIZE(msrs_to_save_pmu)]; -static unsigned num_msrs_to_save; - -static const u32 emulated_msrs_all[] = { - MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, - -#ifdef CONFIG_KVM_HYPERV - HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, - HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, - HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, - HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, - HV_X64_MSR_RESET, - HV_X64_MSR_VP_INDEX, - HV_X64_MSR_VP_RUNTIME, - HV_X64_MSR_SCONTROL, - HV_X64_MSR_STIMER0_CONFIG, - HV_X64_MSR_VP_ASSIST_PAGE, - HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, - HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, - HV_X64_MSR_SYNDBG_OPTIONS, - HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, - HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, - HV_X64_MSR_SYNDBG_PENDING_BUFFER, -#endif - - MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, - - MSR_IA32_TSC_ADJUST, - MSR_IA32_TSC_DEADLINE, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, - MSR_IA32_MISC_ENABLE, - MSR_IA32_MCG_STATUS, - MSR_IA32_MCG_CTL, - MSR_IA32_MCG_EXT_CTL, - MSR_IA32_SMBASE, - MSR_SMI_COUNT, - MSR_PLATFORM_INFO, - MSR_MISC_FEATURES_ENABLES, - MSR_AMD64_VIRT_SPEC_CTRL, - MSR_AMD64_TSC_RATIO, - MSR_IA32_POWER_CTL, - MSR_IA32_UCODE_REV, - - /* - * KVM always supports the "true" VMX control MSRs, even if the host - * does not. The VMX MSRs as a whole are considered "emulated" as KVM - * doesn't strictly require them to exist in the host (ignoring that - * KVM would refuse to load in the first place if the core set of MSRs - * aren't supported). - */ - MSR_IA32_VMX_BASIC, - MSR_IA32_VMX_TRUE_PINBASED_CTLS, - MSR_IA32_VMX_TRUE_PROCBASED_CTLS, - MSR_IA32_VMX_TRUE_EXIT_CTLS, - MSR_IA32_VMX_TRUE_ENTRY_CTLS, - MSR_IA32_VMX_MISC, - MSR_IA32_VMX_CR0_FIXED0, - MSR_IA32_VMX_CR4_FIXED0, - MSR_IA32_VMX_VMCS_ENUM, - MSR_IA32_VMX_PROCBASED_CTLS2, - MSR_IA32_VMX_EPT_VPID_CAP, - MSR_IA32_VMX_VMFUNC, - - MSR_K7_HWCR, - MSR_KVM_POLL_CONTROL, -}; - -static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; -static unsigned num_emulated_msrs; - -/* - * List of MSRs that control the existence of MSR-based features, i.e. MSRs - * that are effectively CPUID leafs. VMX MSRs are also included in the set of - * feature MSRs, but are handled separately to allow expedited lookups. - */ -static const u32 msr_based_features_all_except_vmx[] = { - MSR_AMD64_DE_CFG, - MSR_IA32_UCODE_REV, - MSR_IA32_ARCH_CAPABILITIES, - MSR_IA32_PERF_CAPABILITIES, -}; - -static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + - (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; -static unsigned int num_msr_based_features; - -/* - * All feature MSRs except uCode revID, which tracks the currently loaded uCode - * patch, are immutable once the vCPU model is defined. - */ -static bool kvm_is_immutable_feature_msr(u32 msr) -{ - int i; - - if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) - return true; - - for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { - if (msr == msr_based_features_all_except_vmx[i]) - return msr != MSR_IA32_UCODE_REV; - } - - return false; -} - -/* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM * does not yet virtualize. These include: * 10 - MISC_PACKAGE_CTRLS @@ -1660,40 +1694,31 @@ static u64 kvm_get_arch_capabilities(void) return data; } -static int kvm_get_msr_feature(struct kvm_msr_entry *msr) +static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) { - switch (msr->index) { + WARN_ON_ONCE(!host_initiated); + + switch (index) { case MSR_IA32_ARCH_CAPABILITIES: - msr->data = kvm_get_arch_capabilities(); + *data = kvm_get_arch_capabilities(); break; case MSR_IA32_PERF_CAPABILITIES: - msr->data = kvm_caps.supported_perf_cap; + *data = kvm_caps.supported_perf_cap; break; case MSR_IA32_UCODE_REV: - rdmsrl_safe(msr->index, &msr->data); + rdmsrl_safe(index, data); break; default: - return kvm_x86_call(get_msr_feature)(msr); + return kvm_x86_call(get_feature_msr)(index, data); } return 0; } -static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +static int do_get_feature_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { - struct kvm_msr_entry msr; - int r; - - /* Unconditionally clear the output for simplicity */ - msr.data = 0; - msr.index = index; - r = kvm_get_msr_feature(&msr); - - if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false)) - r = 0; - - *data = msr.data; - - return r; + return kvm_do_msr_access(vcpu, index, data, true, MSR_TYPE_R, + kvm_get_feature_msr); } static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) @@ -1880,16 +1905,17 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, return kvm_x86_call(set_msr)(vcpu, &msr); } +static int _kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, + bool host_initiated) +{ + return __kvm_set_msr(vcpu, index, *data, host_initiated); +} + static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 data, bool host_initiated) { - int ret = __kvm_set_msr(vcpu, index, data, host_initiated); - - if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(index, data, true)) - ret = 0; - - return ret; + return kvm_do_msr_access(vcpu, index, &data, host_initiated, MSR_TYPE_W, + _kvm_set_msr); } /* @@ -1928,31 +1954,25 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated) { - int ret = __kvm_get_msr(vcpu, index, data, host_initiated); - - if (ret == KVM_MSR_RET_INVALID) { - /* Unconditionally clear *data for simplicity */ - *data = 0; - if (kvm_msr_ignored_check(index, 0, false)) - ret = 0; - } - - return ret; + return kvm_do_msr_access(vcpu, index, data, host_initiated, MSR_TYPE_R, + __kvm_get_msr); } -static int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) +int kvm_get_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 *data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; return kvm_get_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_GPL(kvm_get_msr_with_filter); -static int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) +int kvm_set_msr_with_filter(struct kvm_vcpu *vcpu, u32 index, u64 data) { if (!kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) return KVM_MSR_RET_FILTERED; return kvm_set_msr_ignored_check(vcpu, index, data, false); } +EXPORT_SYMBOL_GPL(kvm_set_msr_with_filter); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) { @@ -1999,7 +2019,7 @@ static int complete_fast_rdmsr(struct kvm_vcpu *vcpu) static u64 kvm_msr_reason(int r) { switch (r) { - case KVM_MSR_RET_INVALID: + case KVM_MSR_RET_UNSUPPORTED: return KVM_MSR_EXIT_REASON_UNKNOWN; case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; @@ -2162,31 +2182,34 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) { u32 msr = kvm_rcx_read(vcpu); u64 data; - fastpath_t ret = EXIT_FASTPATH_NONE; + fastpath_t ret; + bool handled; kvm_vcpu_srcu_read_lock(vcpu); switch (msr) { case APIC_BASE_MSR + (APIC_ICR >> 4): data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_x2apic_icr_irqoff(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_EXIT_HANDLED; - } + handled = !handle_fastpath_set_x2apic_icr_irqoff(vcpu, data); break; case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); - if (!handle_fastpath_set_tscdeadline(vcpu, data)) { - kvm_skip_emulated_instruction(vcpu); - ret = EXIT_FASTPATH_REENTER_GUEST; - } + handled = !handle_fastpath_set_tscdeadline(vcpu, data); break; default: + handled = false; break; } - if (ret != EXIT_FASTPATH_NONE) + if (handled) { + if (!kvm_skip_emulated_instruction(vcpu)) + ret = EXIT_FASTPATH_EXIT_USERSPACE; + else + ret = EXIT_FASTPATH_REENTER_GUEST; trace_kvm_msr_write(msr, data); + } else { + ret = EXIT_FASTPATH_NONE; + } kvm_vcpu_srcu_read_unlock(vcpu); @@ -3746,18 +3769,6 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } -static bool kvm_is_msr_to_save(u32 msr_index) -{ - unsigned int i; - - for (i = 0; i < num_msrs_to_save; i++) { - if (msrs_to_save[i] == msr_index) - return true; - } - - return false; -} - int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { u32 msr = msr_info->index; @@ -4139,15 +4150,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - /* - * Userspace is allowed to write '0' to MSRs that KVM reports - * as to-be-saved, even if an MSRs isn't fully supported. - */ - if (msr_info->host_initiated && !data && - kvm_is_msr_to_save(msr)) - break; - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } @@ -4498,17 +4501,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); - /* - * Userspace is allowed to read MSRs that KVM reports as - * to-be-saved, even if an MSR isn't fully supported. - */ - if (msr_info->host_initiated && - kvm_is_msr_to_save(msr_info->index)) { - msr_info->data = 0; - break; - } - - return KVM_MSR_RET_INVALID; + return KVM_MSR_RET_UNSUPPORTED; } return 0; } @@ -4946,7 +4939,7 @@ long kvm_arch_dev_ioctl(struct file *filp, break; } case KVM_GET_MSRS: - r = msr_io(NULL, argp, do_get_msr_feature, 1); + r = msr_io(NULL, argp, do_get_feature_msr, 1); break; #ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: @@ -7383,11 +7376,9 @@ out: static void kvm_probe_feature_msr(u32 msr_index) { - struct kvm_msr_entry msr = { - .index = msr_index, - }; + u64 data; - if (kvm_get_msr_feature(&msr)) + if (kvm_get_feature_msr(NULL, msr_index, &data, true)) return; msr_based_features[num_msr_based_features++] = msr_index; @@ -8865,60 +8856,13 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) return 1; } -static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - int emulation_type) +static bool kvm_unprotect_and_retry_on_failure(struct kvm_vcpu *vcpu, + gpa_t cr2_or_gpa, + int emulation_type) { - gpa_t gpa = cr2_or_gpa; - kvm_pfn_t pfn; - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) return false; - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (!vcpu->arch.mmu->root_role.direct) { - /* - * Write permission should be allowed since only - * write access need to be emulated. - */ - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - /* - * If the mapping is invalid in guest, let cpu retry - * it to generate fault. - */ - if (gpa == INVALID_GPA) - return true; - } - - /* - * Do not retry the unhandleable instruction if it faults on the - * readonly host memory, otherwise it will goto a infinite loop: - * retry instruction -> write #PF -> emulation fail -> retry - * instruction -> ... - */ - pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa)); - - /* - * If the instruction failed on the error pfn, it can not be fixed, - * report the error to userspace. - */ - if (is_error_noslot_pfn(pfn)) - return false; - - kvm_release_pfn_clean(pfn); - - /* - * If emulation may have been triggered by a write to a shadowed page - * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the - * guest to let the CPU re-execute the instruction in the hope that the - * CPU can cleanly execute the instruction that KVM failed to emulate. - */ - if (vcpu->kvm->arch.indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - /* * If the failed instruction faulted on an access to page tables that * are used to translate any part of the instruction, KVM can't resolve @@ -8929,54 +8873,24 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * then zap the SPTE to unprotect the gfn, and then do it all over * again. Report the error to userspace. */ - return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); -} - -static bool retry_instruction(struct x86_emulate_ctxt *ctxt, - gpa_t cr2_or_gpa, int emulation_type) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa; - - last_retry_eip = vcpu->arch.last_retry_eip; - last_retry_addr = vcpu->arch.last_retry_addr; + if (emulation_type & EMULTYPE_WRITE_PF_TO_SP) + return false; /* - * If the emulation is caused by #PF and it is non-page_table - * writing instruction, it means the VM-EXIT is caused by shadow - * page protected, we can zap the shadow page and retry this - * instruction directly. - * - * Note: if the guest uses a non-page-table modifying instruction - * on the PDE that points to the instruction, then we will unmap - * the instruction and go to an infinite loop. So, we cache the - * last retried eip and the last fault address, if we meet the eip - * and the address again, we can break out of the potential infinite - * loop. + * If emulation may have been triggered by a write to a shadowed page + * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the + * guest to let the CPU re-execute the instruction in the hope that the + * CPU can cleanly execute the instruction that KVM failed to emulate. */ - vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - - if (!(emulation_type & EMULTYPE_ALLOW_RETRY_PF)) - return false; - - if (WARN_ON_ONCE(is_guest_mode(vcpu)) || - WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF))) - return false; - - if (x86_page_table_writing_insn(ctxt)) - return false; - - if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa) - return false; - - vcpu->arch.last_retry_eip = ctxt->eip; - vcpu->arch.last_retry_addr = cr2_or_gpa; - - if (!vcpu->arch.mmu->root_role.direct) - gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL); - - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + __kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa, true); + /* + * Retry even if _this_ vCPU didn't unprotect the gfn, as it's possible + * all SPTEs were already zapped by a different task. The alternative + * is to report the error to userspace and likely terminate the guest, + * and the last_retry_{eip,addr} checks will prevent retrying the page + * fault indefinitely, i.e. there's nothing to lose by retrying. + */ return true; } @@ -9176,6 +9090,11 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + (WARN_ON_ONCE(is_guest_mode(vcpu)) || + WARN_ON_ONCE(!(emulation_type & EMULTYPE_PF)))) + emulation_type &= ~EMULTYPE_ALLOW_RETRY_PF; + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); if (r != X86EMUL_CONTINUE) { if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) @@ -9206,8 +9125,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - if (reexecute_instruction(vcpu, cr2_or_gpa, - emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; if (ctxt->have_exception && @@ -9254,7 +9173,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return 1; } - if (retry_instruction(ctxt, cr2_or_gpa, emulation_type)) + /* + * If emulation was caused by a write-protection #PF on a non-page_table + * writing instruction, try to unprotect the gfn, i.e. zap shadow pages, + * and retry the instruction, as the vCPU is likely no longer using the + * gfn as a page table. + */ + if ((emulation_type & EMULTYPE_ALLOW_RETRY_PF) && + !x86_page_table_writing_insn(ctxt) && + kvm_mmu_unprotect_gfn_and_retry(vcpu, cr2_or_gpa)) return 1; /* this is needed for vmware backdoor interface to work since it @@ -9285,7 +9212,8 @@ restart: return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); @@ -9753,7 +9681,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) guard(mutex)(&vendor_module_lock); - if (kvm_x86_ops.hardware_enable) { + if (kvm_x86_ops.enable_virtualization_cpu) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } @@ -9880,7 +9808,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) return 0; out_unwind_ops: - kvm_x86_ops.hardware_enable = NULL; + kvm_x86_ops.enable_virtualization_cpu = NULL; kvm_x86_call(hardware_unsetup)(); out_mmu_exit: kvm_mmu_vendor_module_exit(); @@ -9921,56 +9849,11 @@ void kvm_x86_vendor_exit(void) WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif mutex_lock(&vendor_module_lock); - kvm_x86_ops.hardware_enable = NULL; + kvm_x86_ops.enable_virtualization_cpu = NULL; mutex_unlock(&vendor_module_lock); } EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); -static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) -{ - /* - * The vCPU has halted, e.g. executed HLT. Update the run state if the - * local APIC is in-kernel, the run loop will detect the non-runnable - * state and halt the vCPU. Exit to userspace if the local APIC is - * managed by userspace, in which case userspace is responsible for - * handling wake events. - */ - ++vcpu->stat.halt_exits; - if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = state; - return 1; - } else { - vcpu->run->exit_reason = reason; - return 0; - } -} - -int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) -{ - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); - -int kvm_emulate_halt(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - /* - * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ - return kvm_emulate_halt_noskip(vcpu) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt); - -int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) -{ - int ret = kvm_skip_emulated_instruction(vcpu); - - return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, - KVM_EXIT_AP_RESET_HOLD) && ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); - #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -11207,6 +11090,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); + if (unlikely(exit_fastpath == EXIT_FASTPATH_EXIT_USERSPACE)) + return 0; + r = kvm_x86_call(handle_exit)(vcpu, exit_fastpath); return r; @@ -11220,6 +11106,67 @@ out: return r; } +static bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + +static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_pending_init_or_sipi(vcpu) && + kvm_apic_init_sipi_allowed(vcpu)) + return true; + + if (vcpu->arch.pv.pv_unhalted) + return true; + + if (kvm_is_exception_pending(vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + (vcpu->arch.nmi_pending && + kvm_x86_call(nmi_allowed)(vcpu, false))) + return true; + +#ifdef CONFIG_KVM_SMM + if (kvm_test_request(KVM_REQ_SMI, vcpu) || + (vcpu->arch.smi_pending && + kvm_x86_call(smi_allowed)(vcpu, false))) + return true; +#endif + + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + + if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) + return true; + + if (kvm_hv_has_stimer_pending(vcpu)) + return true; + + if (is_guest_mode(vcpu) && + kvm_x86_ops.nested_ops->has_events && + kvm_x86_ops.nested_ops->has_events(vcpu, false)) + return true; + + if (kvm_xen_has_pending_events(vcpu)) + return true; + + return false; +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); +} + /* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm_vcpu *vcpu) { @@ -11291,12 +11238,6 @@ static inline int vcpu_block(struct kvm_vcpu *vcpu) return 1; } -static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) -{ - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted); -} - /* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { @@ -11348,6 +11289,98 @@ static int vcpu_run(struct kvm_vcpu *vcpu) return r; } +static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) +{ + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ + ++vcpu->stat.halt_exits; + if (lapic_in_kernel(vcpu)) { + if (kvm_vcpu_has_events(vcpu)) + vcpu->arch.pv.pv_unhalted = false; + else + vcpu->arch.mp_state = state; + return 1; + } else { + vcpu->run->exit_reason = reason; + return 0; + } +} + +int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu) +{ + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt_noskip); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + /* + * TODO: we might be squashing a GUESTDBG_SINGLESTEP-triggered + * KVM_EXIT_DEBUG here. + */ + return kvm_emulate_halt_noskip(vcpu) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_halt); + +fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu) +{ + int ret; + + kvm_vcpu_srcu_read_lock(vcpu); + ret = kvm_emulate_halt(vcpu); + kvm_vcpu_srcu_read_unlock(vcpu); + + if (!ret) + return EXIT_FASTPATH_EXIT_USERSPACE; + + if (kvm_vcpu_running(vcpu)) + return EXIT_FASTPATH_REENTER_GUEST; + + return EXIT_FASTPATH_EXIT_HANDLED; +} +EXPORT_SYMBOL_GPL(handle_fastpath_hlt); + +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_emulate_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, + KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + +bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_apicv_active(vcpu) && + kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); +} + +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.preempted_in_kernel; +} + +bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) +{ + if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) + return true; + + if (kvm_test_request(KVM_REQ_NMI, vcpu) || +#ifdef CONFIG_KVM_SMM + kvm_test_request(KVM_REQ_SMI, vcpu) || +#endif + kvm_test_request(KVM_REQ_EVENT, vcpu)) + return true; + + return kvm_arch_dy_has_pending_interrupt(vcpu); +} + static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { return kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); @@ -12264,8 +12297,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); - vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; - kvm_async_pf_hash_reset(vcpu); vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; @@ -12431,6 +12462,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) if (!init_event) { vcpu->arch.smbase = 0x30000; + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + vcpu->arch.msr_misc_features_enables = 0; vcpu->arch.ia32_misc_enable_msr = MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | MSR_IA32_MISC_ENABLE_BTS_UNAVAIL; @@ -12516,7 +12549,17 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) } EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); -int kvm_arch_hardware_enable(void) +void kvm_arch_enable_virtualization(void) +{ + cpu_emergency_register_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} + +void kvm_arch_disable_virtualization(void) +{ + cpu_emergency_unregister_virt_callback(kvm_x86_ops.emergency_disable_virtualization_cpu); +} + +int kvm_arch_enable_virtualization_cpu(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; @@ -12532,7 +12575,7 @@ int kvm_arch_hardware_enable(void) if (ret) return ret; - ret = kvm_x86_call(hardware_enable)(); + ret = kvm_x86_call(enable_virtualization_cpu)(); if (ret != 0) return ret; @@ -12612,9 +12655,9 @@ int kvm_arch_hardware_enable(void) return 0; } -void kvm_arch_hardware_disable(void) +void kvm_arch_disable_virtualization_cpu(void) { - kvm_x86_call(hardware_disable)(); + kvm_x86_call(disable_virtualization_cpu)(); drop_user_return_notifiers(); } @@ -13162,87 +13205,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_arch_free_memslot(kvm, old); } -static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) -{ - if (!list_empty_careful(&vcpu->async_pf.done)) - return true; - - if (kvm_apic_has_pending_init_or_sipi(vcpu) && - kvm_apic_init_sipi_allowed(vcpu)) - return true; - - if (vcpu->arch.pv.pv_unhalted) - return true; - - if (kvm_is_exception_pending(vcpu)) - return true; - - if (kvm_test_request(KVM_REQ_NMI, vcpu) || - (vcpu->arch.nmi_pending && - kvm_x86_call(nmi_allowed)(vcpu, false))) - return true; - -#ifdef CONFIG_KVM_SMM - if (kvm_test_request(KVM_REQ_SMI, vcpu) || - (vcpu->arch.smi_pending && - kvm_x86_call(smi_allowed)(vcpu, false))) - return true; -#endif - - if (kvm_test_request(KVM_REQ_PMI, vcpu)) - return true; - - if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu)) - return true; - - if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)) - return true; - - if (kvm_hv_has_stimer_pending(vcpu)) - return true; - - if (is_guest_mode(vcpu) && - kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu, false)) - return true; - - if (kvm_xen_has_pending_events(vcpu)) - return true; - - return false; -} - -int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); -} - -bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - return kvm_vcpu_apicv_active(vcpu) && - kvm_x86_call(dy_apicv_has_pending_interrupt)(vcpu); -} - -bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.preempted_in_kernel; -} - -bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) -{ - if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) - return true; - - if (kvm_test_request(KVM_REQ_NMI, vcpu) || -#ifdef CONFIG_KVM_SMM - kvm_test_request(KVM_REQ_SMI, vcpu) || -#endif - kvm_test_request(KVM_REQ_EVENT, vcpu)) - return true; - - return kvm_arch_dy_has_pending_interrupt(vcpu); -} - bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) { if (vcpu->arch.guest_state_protected) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 50596f6f8320..a84c48ef5278 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -103,11 +103,18 @@ static inline unsigned int __shrink_ple_window(unsigned int val, return max(val, min); } -#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL +#define MSR_IA32_CR_PAT_DEFAULT \ + PAT_VALUE(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC) void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static inline void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu) { return vcpu->arch.last_vmentry_cpu != -1; @@ -334,6 +341,7 @@ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len); fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); +fastpath_t handle_fastpath_hlt(struct kvm_vcpu *vcpu); extern struct kvm_caps kvm_caps; extern struct kvm_host_values kvm_host; @@ -504,13 +512,26 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); +enum kvm_msr_access { + MSR_TYPE_R = BIT(0), + MSR_TYPE_W = BIT(1), + MSR_TYPE_RW = MSR_TYPE_R | MSR_TYPE_W, +}; + /* * Internal error codes that are used to indicate that MSR emulation encountered - * an error that should result in #GP in the guest, unless userspace - * handles it. + * an error that should result in #GP in the guest, unless userspace handles it. + * Note, '1', '0', and negative numbers are off limits, as they are used by KVM + * as part of KVM's lightly documented internal KVM_RUN return codes. + * + * UNSUPPORTED - The MSR isn't supported, either because it is completely + * unknown to KVM, or because the MSR should not exist according + * to the vCPU model. + * + * FILTERED - Access to the MSR is denied by a userspace MSR filter. */ -#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */ -#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */ +#define KVM_MSR_RET_UNSUPPORTED 2 +#define KVM_MSR_RET_FILTERED 3 #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 90afb488b396..b2eff07d65e4 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -16,6 +16,11 @@ cmpxchg8b (\reg) .endm +.macro read64_nonatomic reg + movl (\reg), %eax + movl 4(\reg), %edx +.endm + SYM_FUNC_START(atomic64_read_cx8) read64 %ecx RET @@ -51,7 +56,7 @@ SYM_FUNC_START(atomic64_\func\()_return_cx8) movl %edx, %edi movl %ecx, %ebp - read64 %ecx + read64_nonatomic %ecx 1: movl %eax, %ebx movl %edx, %ecx @@ -79,7 +84,7 @@ addsub_return sub sub sbb SYM_FUNC_START(atomic64_\func\()_return_cx8) pushl %ebx - read64 %esi + read64_nonatomic %esi 1: movl %eax, %ebx movl %edx, %ecx diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index f73b5ce270b3..feb8cc6a12bf 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -176,15 +176,6 @@ static inline void set_page_memtype(struct page *pg, } #endif -enum { - PAT_UC = 0, /* uncached */ - PAT_WC = 1, /* Write combining */ - PAT_WT = 4, /* Write Through */ - PAT_WP = 5, /* Write Protected */ - PAT_WB = 6, /* Write Back (default) */ - PAT_UC_MINUS = 7, /* UC, but can be overridden by MTRR */ -}; - #define CM(c) (_PAGE_CACHE_MODE_ ## c) static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, @@ -194,13 +185,13 @@ static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, char *cache_mode; switch (pat_val) { - case PAT_UC: cache = CM(UC); cache_mode = "UC "; break; - case PAT_WC: cache = CM(WC); cache_mode = "WC "; break; - case PAT_WT: cache = CM(WT); cache_mode = "WT "; break; - case PAT_WP: cache = CM(WP); cache_mode = "WP "; break; - case PAT_WB: cache = CM(WB); cache_mode = "WB "; break; - case PAT_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break; - default: cache = CM(WB); cache_mode = "WB "; break; + case X86_MEMTYPE_UC: cache = CM(UC); cache_mode = "UC "; break; + case X86_MEMTYPE_WC: cache = CM(WC); cache_mode = "WC "; break; + case X86_MEMTYPE_WT: cache = CM(WT); cache_mode = "WT "; break; + case X86_MEMTYPE_WP: cache = CM(WP); cache_mode = "WP "; break; + case X86_MEMTYPE_WB: cache = CM(WB); cache_mode = "WB "; break; + case X86_MEMTYPE_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break; + default: cache = CM(WB); cache_mode = "WB "; break; } memcpy(msg, cache_mode, 4); @@ -257,12 +248,6 @@ void pat_cpu_init(void) void __init pat_bp_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; -#define PAT(p0, p1, p2, p3, p4, p5, p6, p7) \ - (((u64)PAT_ ## p0) | ((u64)PAT_ ## p1 << 8) | \ - ((u64)PAT_ ## p2 << 16) | ((u64)PAT_ ## p3 << 24) | \ - ((u64)PAT_ ## p4 << 32) | ((u64)PAT_ ## p5 << 40) | \ - ((u64)PAT_ ## p6 << 48) | ((u64)PAT_ ## p7 << 56)) - if (!IS_ENABLED(CONFIG_X86_PAT)) pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); @@ -293,7 +278,7 @@ void __init pat_bp_init(void) * NOTE: When WC or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat_msr_val = PAT(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); + pat_msr_val = PAT_VALUE(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); } /* @@ -328,7 +313,7 @@ void __init pat_bp_init(void) * NOTE: When WT or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); + pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); } else { /* * Full PAT support. We put WT in slot 7 to improve @@ -356,13 +341,12 @@ void __init pat_bp_init(void) * The reserved slots are unused, but mapped to their * corresponding types in the presence of PAT errata. */ - pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); + pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); } memory_caching_control |= CACHE_PAT; init_cache_modes(pat_msr_val); -#undef PAT } static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */ diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index f7235ef87bc3..64fca49cd88f 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -7,6 +7,7 @@ .code32 .text #define _pa(x) ((x) - __START_KERNEL_map) +#define rva(x) ((x) - pvh_start_xen) #include <linux/elfnote.h> #include <linux/init.h> @@ -15,6 +16,7 @@ #include <asm/segment.h> #include <asm/asm.h> #include <asm/boot.h> +#include <asm/pgtable.h> #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/nospec-branch.h> @@ -54,7 +56,25 @@ SYM_CODE_START_LOCAL(pvh_start_xen) UNWIND_HINT_END_OF_STACK cld - lgdt (_pa(gdt)) + /* + * See the comment for startup_32 for more details. We need to + * execute a call to get the execution address to be position + * independent, but we don't have a stack. Save and restore the + * magic field of start_info in ebx, and use that as the stack. + */ + mov (%ebx), %eax + leal 4(%ebx), %esp + ANNOTATE_INTRA_FUNCTION_CALL + call 1f +1: popl %ebp + mov %eax, (%ebx) + subl $rva(1b), %ebp + movl $0, %esp + + leal rva(gdt)(%ebp), %eax + leal rva(gdt_start)(%ebp), %ecx + movl %ecx, 2(%eax) + lgdt (%eax) mov $PVH_DS_SEL,%eax mov %eax,%ds @@ -62,14 +82,14 @@ SYM_CODE_START_LOCAL(pvh_start_xen) mov %eax,%ss /* Stash hvm_start_info. */ - mov $_pa(pvh_start_info), %edi + leal rva(pvh_start_info)(%ebp), %edi mov %ebx, %esi - mov _pa(pvh_start_info_sz), %ecx + movl rva(pvh_start_info_sz)(%ebp), %ecx shr $2,%ecx rep movsl - mov $_pa(early_stack_end), %esp + leal rva(early_stack_end)(%ebp), %esp /* Enable PAE mode. */ mov %cr4, %eax @@ -83,31 +103,86 @@ SYM_CODE_START_LOCAL(pvh_start_xen) btsl $_EFER_LME, %eax wrmsr + mov %ebp, %ebx + subl $_pa(pvh_start_xen), %ebx /* offset */ + jz .Lpagetable_done + + /* Fixup page-tables for relocation. */ + leal rva(pvh_init_top_pgt)(%ebp), %edi + movl $PTRS_PER_PGD, %ecx +2: + testl $_PAGE_PRESENT, 0x00(%edi) + jz 1f + addl %ebx, 0x00(%edi) +1: + addl $8, %edi + decl %ecx + jnz 2b + + /* L3 ident has a single entry. */ + leal rva(pvh_level3_ident_pgt)(%ebp), %edi + addl %ebx, 0x00(%edi) + + leal rva(pvh_level3_kernel_pgt)(%ebp), %edi + addl %ebx, (PAGE_SIZE - 16)(%edi) + addl %ebx, (PAGE_SIZE - 8)(%edi) + + /* pvh_level2_ident_pgt is fine - large pages */ + + /* pvh_level2_kernel_pgt needs adjustment - large pages */ + leal rva(pvh_level2_kernel_pgt)(%ebp), %edi + movl $PTRS_PER_PMD, %ecx +2: + testl $_PAGE_PRESENT, 0x00(%edi) + jz 1f + addl %ebx, 0x00(%edi) +1: + addl $8, %edi + decl %ecx + jnz 2b + +.Lpagetable_done: /* Enable pre-constructed page tables. */ - mov $_pa(init_top_pgt), %eax + leal rva(pvh_init_top_pgt)(%ebp), %eax mov %eax, %cr3 mov $(X86_CR0_PG | X86_CR0_PE), %eax mov %eax, %cr0 /* Jump to 64-bit mode. */ - ljmp $PVH_CS_SEL, $_pa(1f) + pushl $PVH_CS_SEL + leal rva(1f)(%ebp), %eax + pushl %eax + lretl /* 64-bit entry point. */ .code64 1: + UNWIND_HINT_END_OF_STACK + /* Set base address in stack canary descriptor. */ mov $MSR_GS_BASE,%ecx - mov $_pa(canary), %eax + leal canary(%rip), %eax xor %edx, %edx wrmsr + /* + * Calculate load offset and store in phys_base. __pa() needs + * phys_base set to calculate the hypercall page in xen_pvh_init(). + */ + movq %rbp, %rbx + subq $_pa(pvh_start_xen), %rbx + movq %rbx, phys_base(%rip) call xen_prepare_pvh + /* + * Clear phys_base. __startup_64 will *add* to its value, + * so reset to 0. + */ + xor %rbx, %rbx + movq %rbx, phys_base(%rip) /* startup_64 expects boot_params in %rsi. */ - mov $_pa(pvh_bootparams), %rsi - mov $_pa(startup_64), %rax - ANNOTATE_RETPOLINE_SAFE - jmp *%rax + lea pvh_bootparams(%rip), %rsi + jmp startup_64 #else /* CONFIG_X86_64 */ @@ -143,7 +218,7 @@ SYM_CODE_END(pvh_start_xen) .balign 8 SYM_DATA_START_LOCAL(gdt) .word gdt_end - gdt_start - .long _pa(gdt_start) + .long _pa(gdt_start) /* x86-64 will overwrite if relocated. */ .word 0 SYM_DATA_END(gdt) SYM_DATA_START_LOCAL(gdt_start) @@ -163,5 +238,67 @@ SYM_DATA_START_LOCAL(early_stack) .fill BOOT_STACK_SIZE, 1, 0 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end) +#ifdef CONFIG_X86_64 +/* + * Xen PVH needs a set of identity mapped and kernel high mapping + * page tables. pvh_start_xen starts running on the identity mapped + * page tables, but xen_prepare_pvh calls into the high mapping. + * These page tables need to be relocatable and are only used until + * startup_64 transitions to init_top_pgt. + */ +SYM_DATA_START_PAGE_ALIGNED(pvh_init_top_pgt) + .quad pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .org pvh_init_top_pgt + L4_PAGE_OFFSET * 8, 0 + .quad pvh_level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .org pvh_init_top_pgt + L4_START_KERNEL * 8, 0 + /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ + .quad pvh_level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC +SYM_DATA_END(pvh_init_top_pgt) + +SYM_DATA_START_PAGE_ALIGNED(pvh_level3_ident_pgt) + .quad pvh_level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .fill 511, 8, 0 +SYM_DATA_END(pvh_level3_ident_pgt) +SYM_DATA_START_PAGE_ALIGNED(pvh_level2_ident_pgt) + /* + * Since I easily can, map the first 1G. + * Don't set NX because code runs from these pages. + * + * Note: This sets _PAGE_GLOBAL despite whether + * the CPU supports it or it is enabled. But, + * the CPU should ignore the bit. + */ + PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) +SYM_DATA_END(pvh_level2_ident_pgt) +SYM_DATA_START_PAGE_ALIGNED(pvh_level3_kernel_pgt) + .fill L3_START_KERNEL, 8, 0 + /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ + .quad pvh_level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC + .quad 0 /* no fixmap */ +SYM_DATA_END(pvh_level3_kernel_pgt) + +SYM_DATA_START_PAGE_ALIGNED(pvh_level2_kernel_pgt) + /* + * Kernel high mapping. + * + * The kernel code+data+bss must be located below KERNEL_IMAGE_SIZE in + * virtual address space, which is 1 GiB if RANDOMIZE_BASE is enabled, + * 512 MiB otherwise. + * + * (NOTE: after that starts the module area, see MODULES_VADDR.) + * + * This table is eventually used by the kernel during normal runtime. + * Care must be taken to clear out undesired bits later, like _PAGE_RW + * or _PAGE_GLOBAL in some cases. + */ + PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE / PMD_SIZE) +SYM_DATA_END(pvh_level2_kernel_pgt) + + ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_RELOC, + .long CONFIG_PHYSICAL_ALIGN; + .long LOAD_PHYSICAL_ADDR; + .long KERNEL_IMAGE_SIZE - 1) +#endif + ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY, _ASM_PTR (pvh_start_xen - __START_KERNEL_map)) diff --git a/arch/x86/um/sysrq_32.c b/arch/x86/um/sysrq_32.c index f2383484840d..a1ee415c008d 100644 --- a/arch/x86/um/sysrq_32.c +++ b/arch/x86/um/sysrq_32.c @@ -9,7 +9,6 @@ #include <linux/sched/debug.h> #include <linux/kallsyms.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> /* This is declared by <linux/sched.h> */ void show_regs(struct pt_regs *regs) diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c index 0bf6de40abff..340d8a243c8a 100644 --- a/arch/x86/um/sysrq_64.c +++ b/arch/x86/um/sysrq_64.c @@ -12,7 +12,6 @@ #include <linux/utsname.h> #include <asm/current.h> #include <asm/ptrace.h> -#include <asm/sysrq.h> void show_regs(struct pt_regs *regs) { diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 728a4366ca85..bf68c329fc01 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -4,6 +4,7 @@ #include <linux/mm.h> #include <xen/hvc-console.h> +#include <xen/acpi.h> #include <asm/bootparam.h> #include <asm/io_apic.h> @@ -28,6 +29,28 @@ bool __ro_after_init xen_pvh; EXPORT_SYMBOL_GPL(xen_pvh); +#ifdef CONFIG_XEN_DOM0 +int xen_pvh_setup_gsi(int gsi, int trigger, int polarity) +{ + int ret; + struct physdev_setup_gsi setup_gsi; + + setup_gsi.gsi = gsi; + setup_gsi.triggering = (trigger == ACPI_EDGE_SENSITIVE ? 0 : 1); + setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1); + + ret = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi); + if (ret == -EEXIST) { + xen_raw_printk("Already setup the GSI :%d\n", gsi); + ret = 0; + } else if (ret) + xen_raw_printk("Fail to setup GSI (%d)!\n", gsi); + + return ret; +} +EXPORT_SYMBOL_GPL(xen_pvh_setup_gsi); +#endif + /* * Reserve e820 UNUSABLE regions to inflate the memory balloon. * diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index e3a7c2aedd5f..d67f63d93b2a 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -451,7 +451,7 @@ config ACPI_HED config ACPI_BGRT bool "Boottime Graphics Resource Table support" - depends on EFI && (X86 || ARM64) + depends on EFI && (X86 || ARM64 || LOONGARCH) help This driver adds support for exposing the ACPI Boottime Graphics Resource Table, which allows the operating system to obtain diff --git a/drivers/acpi/apei/einj-cxl.c b/drivers/acpi/apei/einj-cxl.c index 8b8be0c90709..4f81a119ec08 100644 --- a/drivers/acpi/apei/einj-cxl.c +++ b/drivers/acpi/apei/einj-cxl.c @@ -7,9 +7,9 @@ * * Author: Ben Cheatham <benjamin.cheatham@amd.com> */ -#include <linux/einj-cxl.h> #include <linux/seq_file.h> #include <linux/pci.h> +#include <cxl/einj.h> #include "apei-internal.h" diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c index 8bc71cdc2270..246076341e8c 100644 --- a/drivers/acpi/apei/erst-dbg.c +++ b/drivers/acpi/apei/erst-dbg.c @@ -199,7 +199,6 @@ static const struct file_operations erst_dbg_ops = { .read = erst_dbg_read, .write = erst_dbg_write, .unlocked_ioctl = erst_dbg_ioctl, - .llseek = no_llseek, }; static struct miscdevice erst_dbg_dev = { diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 623cc0cb4a65..ada93cfde9ba 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -27,7 +27,6 @@ #include <linux/timer.h> #include <linux/cper.h> #include <linux/cleanup.h> -#include <linux/cxl-event.h> #include <linux/platform_device.h> #include <linux/mutex.h> #include <linux/ratelimit.h> @@ -50,6 +49,7 @@ #include <acpi/apei.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> +#include <cxl/event.h> #include <ras/ras_event.h> #include "apei-internal.h" diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index ff30ceca2203..630fe0a34bc6 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -288,7 +288,7 @@ static int acpi_reroute_boot_interrupt(struct pci_dev *dev, } #endif /* CONFIG_X86_IO_APIC */ -static struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin) +struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin) { struct acpi_prt_entry *entry = NULL; struct pci_dev *bridge; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 3328a6febc13..a4aedf7e1775 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2256,10 +2256,15 @@ static inline u16 ata_xlat_cdl_limit(u8 *buf) static unsigned int ata_msense_control_spgt2(struct ata_device *dev, u8 *buf, u8 spg) { - u8 *b, *cdl = dev->cdl->desc_log_buf, *desc; + u8 *b, *cdl, *desc; u32 policy; int i; + if (!(dev->flags & ATA_DFLAG_CDL) || !dev->cdl) + return 0; + + cdl = dev->cdl->desc_log_buf; + /* * Fill the subpage. The first four bytes of the T2A/T2B mode pages * are a header. The PAGE LENGTH field is the size of the page @@ -2356,7 +2361,7 @@ static unsigned int ata_msense_control(struct ata_device *dev, u8 *buf, case ALL_SUB_MPAGES: n = ata_msense_control_spg0(dev, buf, changeable); n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE); - n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE); + n += ata_msense_control_spgt2(dev, buf + n, CDL_T2B_SUB_MPAGE); n += ata_msense_control_ata_feature(dev, buf + n); return n; default: diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index bb9463814454..19b619376d48 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -526,7 +526,6 @@ static const struct file_operations charlcd_fops = { .write = charlcd_write, .open = charlcd_open, .release = charlcd_release, - .llseek = no_llseek, }; static struct miscdevice charlcd_dev = { diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c index 01ef796c2055..b6f941a6ab69 100644 --- a/drivers/base/attribute_container.c +++ b/drivers/base/attribute_container.c @@ -346,8 +346,7 @@ attribute_container_device_trigger_safe(struct device *dev, * @fn: the function to execute for each classdev. * * This function is for executing a trigger when you need to know both - * the container and the classdev. If you only care about the - * container, then use attribute_container_trigger() instead. + * the container and the classdev. */ void attribute_container_device_trigger(struct device *dev, @@ -379,33 +378,6 @@ attribute_container_device_trigger(struct device *dev, } /** - * attribute_container_trigger - trigger a function for each matching container - * - * @dev: The generic device to activate the trigger for - * @fn: the function to trigger - * - * This routine triggers a function that only needs to know the - * matching containers (not the classdev) associated with a device. - * It is more lightweight than attribute_container_device_trigger, so - * should be used in preference unless the triggering function - * actually needs to know the classdev. - */ -void -attribute_container_trigger(struct device *dev, - int (*fn)(struct attribute_container *, - struct device *)) -{ - struct attribute_container *cont; - - mutex_lock(&attribute_container_mutex); - list_for_each_entry(cont, &attribute_container_list, node) { - if (cont->match(cont, dev)) - fn(cont, dev); - } - mutex_unlock(&attribute_container_mutex); -} - -/** * attribute_container_add_attrs - add attributes * * @classdev: The class device @@ -459,24 +431,6 @@ attribute_container_add_class_device(struct device *classdev) } /** - * attribute_container_add_class_device_adapter - simple adapter for triggers - * - * @cont: the container to register. - * @dev: the generic device to activate the trigger for - * @classdev: the class device to add - * - * This function is identical to attribute_container_add_class_device except - * that it is designed to be called from the triggers - */ -int -attribute_container_add_class_device_adapter(struct attribute_container *cont, - struct device *dev, - struct device *classdev) -{ - return attribute_container_add_class_device(classdev); -} - -/** * attribute_container_remove_attrs - remove any attribute files * * @classdev: The class device to remove the files from diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index 54b92839e05c..7823888af4f6 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -352,7 +352,7 @@ EXPORT_SYMBOL_GPL(__auxiliary_device_add); */ struct auxiliary_device *auxiliary_find_device(struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)) + device_match_t match) { struct device *dev; diff --git a/drivers/base/base.h b/drivers/base/base.h index 0b53593372d7..8cf04a557bdb 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -145,7 +145,7 @@ void auxiliary_bus_init(void); static inline void auxiliary_bus_init(void) { } #endif -struct kobject *virtual_device_parent(struct device *dev); +struct kobject *virtual_device_parent(void); int bus_add_device(struct device *dev); void bus_probe_device(struct device *dev); diff --git a/drivers/base/bus.c b/drivers/base/bus.c index ffea0728b8b2..657c93c38b0d 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -152,7 +152,8 @@ static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr, { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); - ssize_t ret = 0; + /* return -EIO for reading a bus attribute without show() */ + ssize_t ret = -EIO; if (bus_attr->show) ret = bus_attr->show(subsys_priv->bus, buf); @@ -164,7 +165,8 @@ static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); - ssize_t ret = 0; + /* return -EIO for writing a bus attribute without store() */ + ssize_t ret = -EIO; if (bus_attr->store) ret = bus_attr->store(subsys_priv->bus, buf, count); @@ -389,7 +391,7 @@ EXPORT_SYMBOL_GPL(bus_for_each_dev); */ struct device *bus_find_device(const struct bus_type *bus, struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)) + device_match_t match) { struct subsys_private *sp = bus_to_subsys(bus); struct klist_iter i; @@ -920,6 +922,8 @@ bus_devices_fail: bus_remove_file(bus, &bus_attr_uevent); bus_uevent_fail: kset_unregister(&priv->subsys); + /* Above kset_unregister() will kfree @priv */ + priv = NULL; out: kfree(priv); return retval; @@ -1294,7 +1298,7 @@ int subsys_virtual_register(const struct bus_type *subsys, { struct kobject *virtual_dir; - virtual_dir = virtual_device_parent(NULL); + virtual_dir = virtual_device_parent(); if (!virtual_dir) return -ENOMEM; @@ -1385,8 +1389,13 @@ int __init buses_init(void) return -ENOMEM; system_kset = kset_create_and_add("system", NULL, &devices_kset->kobj); - if (!system_kset) + if (!system_kset) { + /* Do error handling here as devices_init() do */ + kset_unregister(bus_kset); + bus_kset = NULL; + pr_err("%s: failed to create and add kset 'bus'\n", __func__); return -ENOMEM; + } return 0; } diff --git a/drivers/base/class.c b/drivers/base/class.c index 7b38fdf8e1d7..cb5359235c70 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -183,6 +183,17 @@ int class_register(const struct class *cls) pr_debug("device class '%s': registering\n", cls->name); + if (cls->ns_type && !cls->namespace) { + pr_err("%s: class '%s' does not have namespace\n", + __func__, cls->name); + return -EINVAL; + } + if (!cls->ns_type && cls->namespace) { + pr_err("%s: class '%s' does not have ns_type\n", + __func__, cls->name); + return -EINVAL; + } + cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) return -ENOMEM; @@ -433,8 +444,7 @@ EXPORT_SYMBOL_GPL(class_for_each_device); * code. There's no locking restriction. */ struct device *class_find_device(const struct class *class, const struct device *start, - const void *data, - int (*match)(struct device *, const void *)) + const void *data, device_match_t match) { struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; diff --git a/drivers/base/core.c b/drivers/base/core.c index 8c0733d3aad8..a4c853411a6b 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -9,29 +9,30 @@ */ #include <linux/acpi.h> +#include <linux/blkdev.h> +#include <linux/cleanup.h> #include <linux/cpufreq.h> #include <linux/device.h> +#include <linux/dma-map-ops.h> /* for dma_default_coherent */ #include <linux/err.h> #include <linux/fwnode.h> #include <linux/init.h> +#include <linux/kdev_t.h> #include <linux/kstrtox.h> #include <linux/module.h> -#include <linux/slab.h> -#include <linux/kdev_t.h> +#include <linux/mutex.h> +#include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/blkdev.h> -#include <linux/mutex.h> #include <linux/pm_runtime.h> -#include <linux/netdevice.h> #include <linux/rcupdate.h> -#include <linux/sched/signal.h> #include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> #include <linux/string_helpers.h> #include <linux/swiotlb.h> #include <linux/sysfs.h> -#include <linux/dma-map-ops.h> /* for dma_default_coherent */ #include "base.h" #include "physical_location.h" @@ -97,12 +98,9 @@ static int __fwnode_link_add(struct fwnode_handle *con, int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup, u8 flags) { - int ret; + guard(mutex)(&fwnode_link_lock); - mutex_lock(&fwnode_link_lock); - ret = __fwnode_link_add(con, sup, flags); - mutex_unlock(&fwnode_link_lock); - return ret; + return __fwnode_link_add(con, sup, flags); } /** @@ -143,10 +141,10 @@ static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode) { struct fwnode_link *link, *tmp; - mutex_lock(&fwnode_link_lock); + guard(mutex)(&fwnode_link_lock); + list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) __fwnode_link_del(link); - mutex_unlock(&fwnode_link_lock); } /** @@ -159,10 +157,10 @@ static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode) { struct fwnode_link *link, *tmp; - mutex_lock(&fwnode_link_lock); + guard(mutex)(&fwnode_link_lock); + list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) __fwnode_link_del(link); - mutex_unlock(&fwnode_link_lock); } /** @@ -563,20 +561,11 @@ static struct class devlink_class = { static int devlink_add_symlinks(struct device *dev) { + char *buf_con __free(kfree) = NULL, *buf_sup __free(kfree) = NULL; int ret; - size_t len; struct device_link *link = to_devlink(dev); struct device *sup = link->supplier; struct device *con = link->consumer; - char *buf; - - len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), - strlen(dev_bus_name(con)) + strlen(dev_name(con))); - len += strlen(":"); - len += strlen("supplier:") + 1; - buf = kzalloc(len, GFP_KERNEL); - if (!buf) - return -ENOMEM; ret = sysfs_create_link(&link->link_dev.kobj, &sup->kobj, "supplier"); if (ret) @@ -586,58 +575,64 @@ static int devlink_add_symlinks(struct device *dev) if (ret) goto err_con; - snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); - ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf); + buf_con = kasprintf(GFP_KERNEL, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); + if (!buf_con) { + ret = -ENOMEM; + goto err_con_dev; + } + + ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf_con); if (ret) goto err_con_dev; - snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); - ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf); + buf_sup = kasprintf(GFP_KERNEL, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); + if (!buf_sup) { + ret = -ENOMEM; + goto err_sup_dev; + } + + ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf_sup); if (ret) goto err_sup_dev; goto out; err_sup_dev: - snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); - sysfs_remove_link(&sup->kobj, buf); + sysfs_remove_link(&sup->kobj, buf_con); err_con_dev: sysfs_remove_link(&link->link_dev.kobj, "consumer"); err_con: sysfs_remove_link(&link->link_dev.kobj, "supplier"); out: - kfree(buf); return ret; } static void devlink_remove_symlinks(struct device *dev) { + char *buf_con __free(kfree) = NULL, *buf_sup __free(kfree) = NULL; struct device_link *link = to_devlink(dev); - size_t len; struct device *sup = link->supplier; struct device *con = link->consumer; - char *buf; sysfs_remove_link(&link->link_dev.kobj, "consumer"); sysfs_remove_link(&link->link_dev.kobj, "supplier"); - len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), - strlen(dev_bus_name(con)) + strlen(dev_name(con))); - len += strlen(":"); - len += strlen("supplier:") + 1; - buf = kzalloc(len, GFP_KERNEL); - if (!buf) { - WARN(1, "Unable to properly free device link symlinks!\n"); - return; - } - if (device_is_registered(con)) { - snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); - sysfs_remove_link(&con->kobj, buf); + buf_sup = kasprintf(GFP_KERNEL, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); + if (!buf_sup) + goto out; + sysfs_remove_link(&con->kobj, buf_sup); } - snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); - sysfs_remove_link(&sup->kobj, buf); - kfree(buf); + + buf_con = kasprintf(GFP_KERNEL, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); + if (!buf_con) + goto out; + sysfs_remove_link(&sup->kobj, buf_con); + + return; + +out: + WARN(1, "Unable to properly free device link symlinks!\n"); } static struct class_interface devlink_class_intf = { @@ -678,6 +673,9 @@ postcore_initcall(devlink_class_init); * @supplier: Supplier end of the link. * @flags: Link flags. * + * Return: On success, a device_link struct will be returned. + * On error or invalid flag settings, NULL will be returned. + * * The caller is responsible for the proper synchronization of the link creation * with runtime PM. First, setting the DL_FLAG_PM_RUNTIME flag will cause the * runtime PM framework to take the link into account. Second, if the @@ -1061,20 +1059,16 @@ int device_links_check_suppliers(struct device *dev) * Device waiting for supplier to become available is not allowed to * probe. */ - mutex_lock(&fwnode_link_lock); - sup_fw = fwnode_links_check_suppliers(dev->fwnode); - if (sup_fw) { - if (!dev_is_best_effort(dev)) { - fwnode_ret = -EPROBE_DEFER; - dev_err_probe(dev, -EPROBE_DEFER, - "wait for supplier %pfwf\n", sup_fw); - } else { - fwnode_ret = -EAGAIN; + scoped_guard(mutex, &fwnode_link_lock) { + sup_fw = fwnode_links_check_suppliers(dev->fwnode); + if (sup_fw) { + if (dev_is_best_effort(dev)) + fwnode_ret = -EAGAIN; + else + return dev_err_probe(dev, -EPROBE_DEFER, + "wait for supplier %pfwf\n", sup_fw); } } - mutex_unlock(&fwnode_link_lock); - if (fwnode_ret == -EPROBE_DEFER) - return fwnode_ret; device_links_write_lock(); @@ -1093,10 +1087,8 @@ int device_links_check_suppliers(struct device *dev) } device_links_missing_supplier(dev); - dev_err_probe(dev, -EPROBE_DEFER, - "supplier %s not ready\n", - dev_name(link->supplier)); - ret = -EPROBE_DEFER; + ret = dev_err_probe(dev, -EPROBE_DEFER, + "supplier %s not ready\n", dev_name(link->supplier)); break; } WRITE_ONCE(link->status, DL_STATE_CONSUMER_PROBE); @@ -1249,9 +1241,8 @@ static ssize_t waiting_for_supplier_show(struct device *dev, bool val; device_lock(dev); - mutex_lock(&fwnode_link_lock); - val = !!fwnode_links_check_suppliers(dev->fwnode); - mutex_unlock(&fwnode_link_lock); + scoped_guard(mutex, &fwnode_link_lock) + val = !!fwnode_links_check_suppliers(dev->fwnode); device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } @@ -1324,13 +1315,15 @@ void device_links_driver_bound(struct device *dev) */ if (dev->fwnode && dev->fwnode->dev == dev) { struct fwnode_handle *child; + fwnode_links_purge_suppliers(dev->fwnode); - mutex_lock(&fwnode_link_lock); + + guard(mutex)(&fwnode_link_lock); + fwnode_for_each_available_child_node(dev->fwnode, child) __fw_devlink_pickup_dangling_consumers(child, dev->fwnode); __fw_devlink_link_to_consumers(dev); - mutex_unlock(&fwnode_link_lock); } device_remove_file(dev, &dev_attr_waiting_for_supplier); @@ -2339,10 +2332,10 @@ static void fw_devlink_link_device(struct device *dev) fw_devlink_parse_fwtree(fwnode); - mutex_lock(&fwnode_link_lock); + guard(mutex)(&fwnode_link_lock); + __fw_devlink_link_to_consumers(dev); __fw_devlink_link_to_suppliers(dev, fwnode); - mutex_unlock(&fwnode_link_lock); } /* Device links support end. */ @@ -2591,7 +2584,7 @@ static const void *device_namespace(const struct kobject *kobj) const struct device *dev = kobj_to_dev(kobj); const void *ns = NULL; - if (dev->class && dev->class->ns_type) + if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; @@ -3170,7 +3163,7 @@ void device_initialize(struct device *dev) } EXPORT_SYMBOL_GPL(device_initialize); -struct kobject *virtual_device_parent(struct device *dev) +struct kobject *virtual_device_parent(void) { static struct kobject *virtual_dir = NULL; @@ -3248,7 +3241,7 @@ static struct kobject *get_device_parent(struct device *dev, * in a "glue" directory to prevent namespace collisions. */ if (parent == NULL) - parent_kobj = virtual_device_parent(dev); + parent_kobj = virtual_device_parent(); else if (parent->class && !dev->class->ns_type) { subsys_put(sp); return &parent->kobj; @@ -4003,7 +3996,7 @@ int device_for_each_child(struct device *parent, void *data, struct device *child; int error = 0; - if (!parent->p) + if (!parent || !parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); @@ -4033,7 +4026,7 @@ int device_for_each_child_reverse(struct device *parent, void *data, struct device *child; int error = 0; - if (!parent->p) + if (!parent || !parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); @@ -4067,7 +4060,7 @@ struct device *device_find_child(struct device *parent, void *data, struct klist_iter i; struct device *child; - if (!parent) + if (!parent || !parent->p) return NULL; klist_iter_init(&parent->p->klist_children, &i); @@ -4515,9 +4508,11 @@ EXPORT_SYMBOL_GPL(device_destroy); */ int device_rename(struct device *dev, const char *new_name) { + struct subsys_private *sp = NULL; struct kobject *kobj = &dev->kobj; char *old_device_name = NULL; int error; + bool is_link_renamed = false; dev = get_device(dev); if (!dev) @@ -4532,7 +4527,7 @@ int device_rename(struct device *dev, const char *new_name) } if (dev->class) { - struct subsys_private *sp = class_to_subsys(dev->class); + sp = class_to_subsys(dev->class); if (!sp) { error = -EINVAL; @@ -4541,16 +4536,19 @@ int device_rename(struct device *dev, const char *new_name) error = sysfs_rename_link_ns(&sp->subsys.kobj, kobj, old_device_name, new_name, kobject_namespace(kobj)); - subsys_put(sp); if (error) goto out; + + is_link_renamed = true; } error = kobject_rename(kobj, new_name); - if (error) - goto out; - out: + if (error && is_link_renamed) + sysfs_rename_link_ns(&sp->subsys.kobj, kobj, new_name, + old_device_name, kobject_namespace(kobj)); + subsys_put(sp); + put_device(dev); kfree(old_device_name); @@ -4872,7 +4870,7 @@ set_dev_info(const struct device *dev, struct dev_printk_info *dev_info) else return; - strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem)); + strscpy(dev_info->subsystem, subsys); /* * Add device identifier DEVICE=: diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 964111361497..f0e4b4aba885 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -248,7 +248,7 @@ static int deferred_devs_show(struct seq_file *s, void *data) list_for_each_entry(curr, &deferred_probe_pending_list, deferred_probe) seq_printf(s, "%s\t%s", dev_name(curr->device), - curr->device->p->deferred_probe_reason ?: "\n"); + curr->deferred_probe_reason ?: "\n"); mutex_unlock(&deferred_probe_mutex); diff --git a/drivers/base/devres.c b/drivers/base/devres.c index a2ce0ead06a6..2152eec0c135 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -1231,6 +1231,6 @@ void devm_free_percpu(struct device *dev, void __percpu *pdata) * devm_free_pages() does. */ WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match, - (__force void *)pdata)); + (void *)(__force unsigned long)pdata)); } EXPORT_SYMBOL_GPL(devm_free_percpu); diff --git a/drivers/base/driver.c b/drivers/base/driver.c index 88c6fd1f1992..b4eb5b89c4ee 100644 --- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -150,7 +150,7 @@ EXPORT_SYMBOL_GPL(driver_for_each_device); */ struct device *driver_find_device(const struct device_driver *drv, struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)) + device_match_t match) { struct klist_iter i; struct device *dev; diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index a03ee4b11134..324a9a3c087a 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -849,6 +849,26 @@ static void fw_log_firmware_info(const struct firmware *fw, const char *name, {} #endif +/* + * Reject firmware file names with ".." path components. + * There are drivers that construct firmware file names from device-supplied + * strings, and we don't want some device to be able to tell us "I would like to + * be sent my firmware from ../../../etc/shadow, please". + * + * Search for ".." surrounded by either '/' or start/end of string. + * + * This intentionally only looks at the firmware name, not at the firmware base + * directory or at symlink contents. + */ +static bool name_contains_dotdot(const char *name) +{ + size_t name_len = strlen(name); + + return strcmp(name, "..") == 0 || strncmp(name, "../", 3) == 0 || + strstr(name, "/../") != NULL || + (name_len >= 3 && strcmp(name+name_len-3, "/..") == 0); +} + /* called from request_firmware() and request_firmware_work_func() */ static int _request_firmware(const struct firmware **firmware_p, const char *name, @@ -869,6 +889,14 @@ _request_firmware(const struct firmware **firmware_p, const char *name, goto out; } + if (name_contains_dotdot(name)) { + dev_warn(device, + "Firmware load for '%s' refused, path contains '..' component\n", + name); + ret = -EINVAL; + goto out; + } + ret = _request_firmware_prepare(&fw, name, device, buf, size, offset, opt_flags); if (ret <= 0) /* error or already assigned */ @@ -946,6 +974,8 @@ out: * @name will be used as $FIRMWARE in the uevent environment and * should be distinctive enough not to be confused with any other * firmware image for this or any other device. + * It must not contain any ".." path components - "foo/bar..bin" is + * allowed, but "foo/../bar.bin" is not. * * Caller must hold the reference count of @device. * diff --git a/drivers/base/module.c b/drivers/base/module.c index f742ad2a21da..c4eaa1158d54 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -66,27 +66,31 @@ int module_add_driver(struct module *mod, const struct device_driver *drv) driver_name = make_driver_name(drv); if (!driver_name) { ret = -ENOMEM; - goto out; + goto out_remove_kobj; } module_create_drivers_dir(mk); if (!mk->drivers_dir) { ret = -EINVAL; - goto out; + goto out_free_driver_name; } ret = sysfs_create_link(mk->drivers_dir, &drv->p->kobj, driver_name); if (ret) - goto out; + goto out_remove_drivers_dir; kfree(driver_name); return 0; -out: - sysfs_remove_link(&drv->p->kobj, "module"); + +out_remove_drivers_dir: sysfs_remove_link(mk->drivers_dir, driver_name); + +out_free_driver_name: kfree(driver_name); +out_remove_kobj: + sysfs_remove_link(&drv->p->kobj, "module"); return ret; } diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 4c3ee6521ba5..6f2a33722c52 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1474,7 +1474,7 @@ static const struct dev_pm_ops platform_dev_pm_ops = { USE_PLATFORM_PM_SLEEP_OPS }; -struct bus_type platform_bus_type = { +const struct bus_type platform_bus_type = { .name = "platform", .dev_groups = platform_dev_groups, .match = platform_match, diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 11901f2812ad..223faa9d5ffd 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2259,14 +2259,12 @@ static const struct file_operations mtip_regs_fops = { .owner = THIS_MODULE, .open = simple_open, .read = mtip_hw_read_registers, - .llseek = no_llseek, }; static const struct file_operations mtip_flags_fops = { .owner = THIS_MODULE, .open = simple_open, .read = mtip_hw_read_flags, - .llseek = no_llseek, }; static void mtip_hw_debugfs_init(struct driver_data *dd) diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 3edb37a41312..499c110465e3 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2835,7 +2835,6 @@ static const struct file_operations pkt_ctl_fops = { .compat_ioctl = pkt_ctl_compat_ioctl, #endif .owner = THIS_MODULE, - .llseek = no_llseek, }; static struct miscdevice pkt_misc = { diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index bca06bfb4bc3..a6c8e5cc6051 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1983,7 +1983,6 @@ static const struct file_operations ublk_ch_fops = { .owner = THIS_MODULE, .open = ublk_ch_open, .release = ublk_ch_release, - .llseek = no_llseek, .read_iter = ublk_ch_read_iter, .write_iter = ublk_ch_write_iter, .uring_cmd = ublk_ch_uring_cmd, diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index c3d245617083..ad9c9bc3ccfc 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2115,8 +2115,10 @@ static void zram_destroy_comps(struct zram *zram) zram->num_active_comps--; } - for (prio = ZRAM_SECONDARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { - kfree(zram->comp_algs[prio]); + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { + /* Do not free statically defined compression algorithms */ + if (zram->comp_algs[prio] != default_compressor) + kfree(zram->comp_algs[prio]); zram->comp_algs[prio] = NULL; } diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 43e9ac5a3324..aa6af351d02d 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -679,7 +679,6 @@ static const struct file_operations vhci_fops = { .poll = vhci_poll, .open = vhci_open, .release = vhci_release, - .llseek = no_llseek, }; static struct miscdevice vhci_miscdev = { diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index dd68b8191a0a..930d8a3ba722 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -309,7 +309,7 @@ static struct attribute *fsl_mc_bus_attrs[] = { ATTRIBUTE_GROUPS(fsl_mc_bus); -struct bus_type fsl_mc_bus_type = { +const struct bus_type fsl_mc_bus_type = { .name = "fsl-mc", .match = fsl_mc_bus_match, .uevent = fsl_mc_bus_uevent, diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index 8412406c4f1d..6276551d7968 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -484,7 +484,6 @@ static const struct file_operations input_fops = { .owner = THIS_MODULE, .open = moxtet_debug_open, .read = input_read, - .llseek = no_llseek, }; static ssize_t output_read(struct file *file, char __user *buf, size_t len, @@ -549,7 +548,6 @@ static const struct file_operations output_fops = { .open = moxtet_debug_open, .read = output_read, .write = output_write, - .llseek = no_llseek, }; static int moxtet_register_debugfs(struct moxtet *moxtet) diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c index 69314532f38c..9fed9706d9cd 100644 --- a/drivers/char/applicom.c +++ b/drivers/char/applicom.c @@ -111,7 +111,6 @@ static irqreturn_t ac_interrupt(int, void *); static const struct file_operations ac_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = ac_read, .write = ac_write, .unlocked_ioctl = ac_ioctl, diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c index a4f4291b4492..44a1cdbd4bfb 100644 --- a/drivers/char/ds1620.c +++ b/drivers/char/ds1620.c @@ -353,7 +353,6 @@ static const struct file_operations ds1620_fops = { .open = ds1620_open, .read = ds1620_read, .unlocked_ioctl = ds1620_unlocked_ioctl, - .llseek = no_llseek, }; static struct miscdevice ds1620_miscdev = { diff --git a/drivers/char/dtlk.c b/drivers/char/dtlk.c index 5a1a73310e97..27f5f9d19531 100644 --- a/drivers/char/dtlk.c +++ b/drivers/char/dtlk.c @@ -107,7 +107,6 @@ static const struct file_operations dtlk_fops = .unlocked_ioctl = dtlk_ioctl, .open = dtlk_open, .release = dtlk_release, - .llseek = no_llseek, }; /* local prototypes */ diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 3dadc4accee3..e904e476e49a 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -700,7 +700,6 @@ hpet_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations hpet_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = hpet_read, .poll = hpet_poll, .unlocked_ioctl = hpet_ioctl, diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 9a459257489f..335eea80054e 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -903,7 +903,6 @@ static const struct file_operations ipmi_wdog_fops = { .open = ipmi_open, .release = ipmi_close, .fasync = ipmi_fasync, - .llseek = no_llseek, }; static struct miscdevice ipmi_wdog_miscdev = { diff --git a/drivers/char/pc8736x_gpio.c b/drivers/char/pc8736x_gpio.c index c39a836ebd15..5f4696813cea 100644 --- a/drivers/char/pc8736x_gpio.c +++ b/drivers/char/pc8736x_gpio.c @@ -235,7 +235,6 @@ static const struct file_operations pc8736x_gpio_fileops = { .open = pc8736x_gpio_open, .write = nsc_gpio_write, .read = nsc_gpio_read, - .llseek = no_llseek, }; static void __init pc8736x_init_shadow(void) diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index eaff98dbaa8c..d1dfbd8d4d42 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -786,7 +786,6 @@ static const struct class ppdev_class = { static const struct file_operations pp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = pp_read, .write = pp_write, .poll = pp_poll, diff --git a/drivers/char/scx200_gpio.c b/drivers/char/scx200_gpio.c index 9f701dcba95c..700e6affea6f 100644 --- a/drivers/char/scx200_gpio.c +++ b/drivers/char/scx200_gpio.c @@ -68,7 +68,6 @@ static const struct file_operations scx200_gpio_fileops = { .read = nsc_gpio_read, .open = scx200_gpio_open, .release = scx200_gpio_release, - .llseek = no_llseek, }; static struct cdev scx200_gpio_cdev; /* use 1 cdev for all pins */ diff --git a/drivers/char/sonypi.c b/drivers/char/sonypi.c index bb5115b1736a..0f8185e541ed 100644 --- a/drivers/char/sonypi.c +++ b/drivers/char/sonypi.c @@ -1054,7 +1054,6 @@ static const struct file_operations sonypi_misc_fops = { .release = sonypi_misc_release, .fasync = sonypi_misc_fasync, .unlocked_ioctl = sonypi_misc_ioctl, - .llseek = no_llseek, }; static struct miscdevice sonypi_misc_device = { diff --git a/drivers/char/tpm/tpm-dev.c b/drivers/char/tpm/tpm-dev.c index e2c0baa69fef..97c94b5e9340 100644 --- a/drivers/char/tpm/tpm-dev.c +++ b/drivers/char/tpm/tpm-dev.c @@ -59,7 +59,6 @@ static int tpm_release(struct inode *inode, struct file *file) const struct file_operations tpm_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = tpm_open, .read = tpm_common_read, .write = tpm_common_write, diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 11c502039faf..8fe4a01eea12 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -243,7 +243,6 @@ static int vtpm_proxy_fops_release(struct inode *inode, struct file *filp) static const struct file_operations vtpm_proxy_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = vtpm_proxy_fops_read, .write = vtpm_proxy_fops_write, .poll = vtpm_proxy_fops_poll, diff --git a/drivers/char/tpm/tpmrm-dev.c b/drivers/char/tpm/tpmrm-dev.c index eef0fb06ea83..c25df7ea064e 100644 --- a/drivers/char/tpm/tpmrm-dev.c +++ b/drivers/char/tpm/tpmrm-dev.c @@ -46,7 +46,6 @@ static int tpmrm_release(struct inode *inode, struct file *file) const struct file_operations tpmrm_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = tpmrm_open, .read = tpm_common_read, .write = tpm_common_write, diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index de7d720d99fa..99a7f2441e70 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1093,7 +1093,6 @@ static const struct file_operations port_fops = { .poll = port_fops_poll, .release = port_fops_release, .fasync = port_fops_fasync, - .llseek = no_llseek, }; /* diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c index afc94d0062b1..3ee75e1a78cd 100644 --- a/drivers/counter/counter-chrdev.c +++ b/drivers/counter/counter-chrdev.c @@ -454,7 +454,6 @@ out_unlock: static const struct file_operations counter_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = counter_chrdev_read, .poll = counter_chrdev_poll, .unlocked_ioctl = counter_chrdev_ioctl, diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c index bb83867d9fec..ef1621d40f05 100644 --- a/drivers/cxl/core/cdat.c +++ b/drivers/cxl/core/cdat.c @@ -9,13 +9,12 @@ #include "cxlmem.h" #include "core.h" #include "cxl.h" -#include "core.h" struct dsmas_entry { struct range dpa_range; u8 handle; struct access_coordinate coord[ACCESS_COORDINATE_MAX]; - + struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX]; int entries; int qos_class; }; @@ -163,7 +162,7 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base), dslbis->data_type); - cxl_access_coordinate_set(dent->coord, dslbis->data_type, val); + cxl_access_coordinate_set(dent->cdat_coord, dslbis->data_type, val); return 0; } @@ -220,7 +219,7 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, xa_for_each(dsmas_xa, index, dent) { int qos_class; - cxl_coordinates_combine(dent->coord, dent->coord, ep_c); + cxl_coordinates_combine(dent->coord, dent->cdat_coord, ep_c); dent->entries = 1; rc = cxl_root->ops->qos_class(cxl_root, &dent->coord[ACCESS_COORDINATE_CPU], @@ -241,8 +240,10 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, static void update_perf_entry(struct device *dev, struct dsmas_entry *dent, struct cxl_dpa_perf *dpa_perf) { - for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { dpa_perf->coord[i] = dent->coord[i]; + dpa_perf->cdat_coord[i] = dent->cdat_coord[i]; + } dpa_perf->dpa_range = dent->dpa_range; dpa_perf->qos_class = dent->qos_class; dev_dbg(dev, @@ -546,19 +547,37 @@ void cxl_coordinates_combine(struct access_coordinate *out, MODULE_IMPORT_NS(CXL); -void cxl_region_perf_data_calculate(struct cxl_region *cxlr, - struct cxl_endpoint_decoder *cxled) +static void cxl_bandwidth_add(struct access_coordinate *coord, + struct access_coordinate *c1, + struct access_coordinate *c2) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + coord[i].read_bandwidth = c1[i].read_bandwidth + + c2[i].read_bandwidth; + coord[i].write_bandwidth = c1[i].write_bandwidth + + c2[i].write_bandwidth; + } +} + +static bool dpa_perf_contains(struct cxl_dpa_perf *perf, + struct resource *dpa_res) { - struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); - struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); struct range dpa = { - .start = cxled->dpa_res->start, - .end = cxled->dpa_res->end, + .start = dpa_res->start, + .end = dpa_res->end, }; + + return range_contains(&perf->dpa_range, &dpa); +} + +static struct cxl_dpa_perf *cxled_get_dpa_perf(struct cxl_endpoint_decoder *cxled, + enum cxl_decoder_mode mode) +{ + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); struct cxl_dpa_perf *perf; - switch (cxlr->mode) { + switch (mode) { case CXL_DECODER_RAM: perf = &mds->ram_perf; break; @@ -566,12 +585,473 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr, perf = &mds->pmem_perf; break; default: + return ERR_PTR(-EINVAL); + } + + if (!dpa_perf_contains(perf, cxled->dpa_res)) + return ERR_PTR(-EINVAL); + + return perf; +} + +/* + * Transient context for containing the current calculation of bandwidth when + * doing walking the port hierarchy to deal with shared upstream link. + */ +struct cxl_perf_ctx { + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct cxl_port *port; +}; + +/** + * cxl_endpoint_gather_bandwidth - collect all the endpoint bandwidth in an xarray + * @cxlr: CXL region for the bandwidth calculation + * @cxled: endpoint decoder to start on + * @usp_xa: (output) the xarray that collects all the bandwidth coordinates + * indexed by the upstream device with data of 'struct cxl_perf_ctx'. + * @gp_is_root: (output) bool of whether the grandparent is cxl root. + * + * Return: 0 for success or -errno + * + * Collects aggregated endpoint bandwidth and store the bandwidth in + * an xarray indexed by the upstream device of the switch or the RP + * device. Each endpoint consists the minimum of the bandwidth from DSLBIS + * from the endpoint CDAT, the endpoint upstream link bandwidth, and the + * bandwidth from the SSLBIS of the switch CDAT for the switch upstream port to + * the downstream port that's associated with the endpoint. If the + * device is directly connected to a RP, then no SSLBIS is involved. + */ +static int cxl_endpoint_gather_bandwidth(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, + struct xarray *usp_xa, + bool *gp_is_root) +{ + struct cxl_port *endpoint = to_cxl_port(cxled->cxld.dev.parent); + struct cxl_port *parent_port = to_cxl_port(endpoint->dev.parent); + struct cxl_port *gp_port = to_cxl_port(parent_port->dev.parent); + struct access_coordinate pci_coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate sw_coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate ep_coord[ACCESS_COORDINATE_MAX]; + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + struct cxl_perf_ctx *perf_ctx; + struct cxl_dpa_perf *perf; + unsigned long index; + void *ptr; + int rc; + + if (cxlds->rcd) + return -ENODEV; + + perf = cxled_get_dpa_perf(cxled, cxlr->mode); + if (IS_ERR(perf)) + return PTR_ERR(perf); + + gp_port = to_cxl_port(parent_port->dev.parent); + *gp_is_root = is_cxl_root(gp_port); + + /* + * If the grandparent is cxl root, then index is the root port, + * otherwise it's the parent switch upstream device. + */ + if (*gp_is_root) + index = (unsigned long)endpoint->parent_dport->dport_dev; + else + index = (unsigned long)parent_port->uport_dev; + + perf_ctx = xa_load(usp_xa, index); + if (!perf_ctx) { + struct cxl_perf_ctx *c __free(kfree) = + kzalloc(sizeof(*perf_ctx), GFP_KERNEL); + + if (!c) + return -ENOMEM; + ptr = xa_store(usp_xa, index, c, GFP_KERNEL); + if (xa_is_err(ptr)) + return xa_err(ptr); + perf_ctx = no_free_ptr(c); + perf_ctx->port = parent_port; + } + + /* Direct upstream link from EP bandwidth */ + rc = cxl_pci_get_bandwidth(pdev, pci_coord); + if (rc < 0) + return rc; + + /* + * Min of upstream link bandwidth and Endpoint CDAT bandwidth from + * DSLBIS. + */ + cxl_coordinates_combine(ep_coord, pci_coord, perf->cdat_coord); + + /* + * If grandparent port is root, then there's no switch involved and + * the endpoint is connected to a root port. + */ + if (!*gp_is_root) { + /* + * Retrieve the switch SSLBIS for switch downstream port + * associated with the endpoint bandwidth. + */ + rc = cxl_port_get_switch_dport_bandwidth(endpoint, sw_coord); + if (rc) + return rc; + + /* + * Min of the earlier coordinates with the switch SSLBIS + * bandwidth + */ + cxl_coordinates_combine(ep_coord, ep_coord, sw_coord); + } + + /* + * Aggregate the computed bandwidth with the current aggregated bandwidth + * of the endpoints with the same switch upstream device or RP. + */ + cxl_bandwidth_add(perf_ctx->coord, perf_ctx->coord, ep_coord); + + return 0; +} + +static void free_perf_xa(struct xarray *xa) +{ + struct cxl_perf_ctx *ctx; + unsigned long index; + + if (!xa) return; + + xa_for_each(xa, index, ctx) + kfree(ctx); + xa_destroy(xa); + kfree(xa); +} +DEFINE_FREE(free_perf_xa, struct xarray *, if (_T) free_perf_xa(_T)) + +/** + * cxl_switch_gather_bandwidth - collect all the bandwidth at switch level in an xarray + * @cxlr: The region being operated on + * @input_xa: xarray indexed by upstream device of a switch with data of 'struct + * cxl_perf_ctx' + * @gp_is_root: (output) bool of whether the grandparent is cxl root. + * + * Return: a xarray of resulting cxl_perf_ctx per parent switch or root port + * or ERR_PTR(-errno) + * + * Iterate through the xarray. Take the minimum of the downstream calculated + * bandwidth, the upstream link bandwidth, and the SSLBIS of the upstream + * switch if exists. Sum the resulting bandwidth under the switch upstream + * device or a RP device. The function can be iterated over multiple switches + * if the switches are present. + */ +static struct xarray *cxl_switch_gather_bandwidth(struct cxl_region *cxlr, + struct xarray *input_xa, + bool *gp_is_root) +{ + struct xarray *res_xa __free(free_perf_xa) = + kzalloc(sizeof(*res_xa), GFP_KERNEL); + struct access_coordinate coords[ACCESS_COORDINATE_MAX]; + struct cxl_perf_ctx *ctx, *us_ctx; + unsigned long index, us_index; + int dev_count = 0; + int gp_count = 0; + void *ptr; + int rc; + + if (!res_xa) + return ERR_PTR(-ENOMEM); + xa_init(res_xa); + + xa_for_each(input_xa, index, ctx) { + struct device *dev = (struct device *)index; + struct cxl_port *port = ctx->port; + struct cxl_port *parent_port = to_cxl_port(port->dev.parent); + struct cxl_port *gp_port = to_cxl_port(parent_port->dev.parent); + struct cxl_dport *dport = port->parent_dport; + bool is_root = false; + + dev_count++; + if (is_cxl_root(gp_port)) { + is_root = true; + gp_count++; + } + + /* + * If the grandparent is cxl root, then index is the root port, + * otherwise it's the parent switch upstream device. + */ + if (is_root) + us_index = (unsigned long)port->parent_dport->dport_dev; + else + us_index = (unsigned long)parent_port->uport_dev; + + us_ctx = xa_load(res_xa, us_index); + if (!us_ctx) { + struct cxl_perf_ctx *n __free(kfree) = + kzalloc(sizeof(*n), GFP_KERNEL); + + if (!n) + return ERR_PTR(-ENOMEM); + + ptr = xa_store(res_xa, us_index, n, GFP_KERNEL); + if (xa_is_err(ptr)) + return ERR_PTR(xa_err(ptr)); + us_ctx = no_free_ptr(n); + us_ctx->port = parent_port; + } + + /* + * If the device isn't an upstream PCIe port, there's something + * wrong with the topology. + */ + if (!dev_is_pci(dev)) + return ERR_PTR(-EINVAL); + + /* Retrieve the upstream link bandwidth */ + rc = cxl_pci_get_bandwidth(to_pci_dev(dev), coords); + if (rc) + return ERR_PTR(-ENXIO); + + /* + * Take the min of downstream bandwidth and the upstream link + * bandwidth. + */ + cxl_coordinates_combine(coords, coords, ctx->coord); + + /* + * Take the min of the calculated bandwdith and the upstream + * switch SSLBIS bandwidth if there's a parent switch + */ + if (!is_root) + cxl_coordinates_combine(coords, coords, dport->coord); + + /* + * Aggregate the calculated bandwidth common to an upstream + * switch. + */ + cxl_bandwidth_add(us_ctx->coord, us_ctx->coord, coords); } + /* Asymmetric topology detected. */ + if (gp_count) { + if (gp_count != dev_count) { + dev_dbg(&cxlr->dev, + "Asymmetric hierarchy detected, bandwidth not updated\n"); + return ERR_PTR(-EOPNOTSUPP); + } + *gp_is_root = true; + } + + return no_free_ptr(res_xa); +} + +/** + * cxl_rp_gather_bandwidth - handle the root port level bandwidth collection + * @xa: the xarray that holds the cxl_perf_ctx that has the bandwidth calculated + * below each root port device. + * + * Return: xarray that holds cxl_perf_ctx per host bridge or ERR_PTR(-errno) + */ +static struct xarray *cxl_rp_gather_bandwidth(struct xarray *xa) +{ + struct xarray *hb_xa __free(free_perf_xa) = + kzalloc(sizeof(*hb_xa), GFP_KERNEL); + struct cxl_perf_ctx *ctx; + unsigned long index; + + if (!hb_xa) + return ERR_PTR(-ENOMEM); + xa_init(hb_xa); + + xa_for_each(xa, index, ctx) { + struct cxl_port *port = ctx->port; + unsigned long hb_index = (unsigned long)port->uport_dev; + struct cxl_perf_ctx *hb_ctx; + void *ptr; + + hb_ctx = xa_load(hb_xa, hb_index); + if (!hb_ctx) { + struct cxl_perf_ctx *n __free(kfree) = + kzalloc(sizeof(*n), GFP_KERNEL); + + if (!n) + return ERR_PTR(-ENOMEM); + ptr = xa_store(hb_xa, hb_index, n, GFP_KERNEL); + if (xa_is_err(ptr)) + return ERR_PTR(xa_err(ptr)); + hb_ctx = no_free_ptr(n); + hb_ctx->port = port; + } + + cxl_bandwidth_add(hb_ctx->coord, hb_ctx->coord, ctx->coord); + } + + return no_free_ptr(hb_xa); +} + +/** + * cxl_hb_gather_bandwidth - handle the host bridge level bandwidth collection + * @xa: the xarray that holds the cxl_perf_ctx that has the bandwidth calculated + * below each host bridge. + * + * Return: xarray that holds cxl_perf_ctx per ACPI0017 device or ERR_PTR(-errno) + */ +static struct xarray *cxl_hb_gather_bandwidth(struct xarray *xa) +{ + struct xarray *mw_xa __free(free_perf_xa) = + kzalloc(sizeof(*mw_xa), GFP_KERNEL); + struct cxl_perf_ctx *ctx; + unsigned long index; + + if (!mw_xa) + return ERR_PTR(-ENOMEM); + xa_init(mw_xa); + + xa_for_each(xa, index, ctx) { + struct cxl_port *port = ctx->port; + struct cxl_port *parent_port; + struct cxl_perf_ctx *mw_ctx; + struct cxl_dport *dport; + unsigned long mw_index; + void *ptr; + + parent_port = to_cxl_port(port->dev.parent); + mw_index = (unsigned long)parent_port->uport_dev; + + mw_ctx = xa_load(mw_xa, mw_index); + if (!mw_ctx) { + struct cxl_perf_ctx *n __free(kfree) = + kzalloc(sizeof(*n), GFP_KERNEL); + + if (!n) + return ERR_PTR(-ENOMEM); + ptr = xa_store(mw_xa, mw_index, n, GFP_KERNEL); + if (xa_is_err(ptr)) + return ERR_PTR(xa_err(ptr)); + mw_ctx = no_free_ptr(n); + } + + dport = port->parent_dport; + cxl_coordinates_combine(ctx->coord, ctx->coord, dport->coord); + cxl_bandwidth_add(mw_ctx->coord, mw_ctx->coord, ctx->coord); + } + + return no_free_ptr(mw_xa); +} + +/** + * cxl_region_update_bandwidth - Update the bandwidth access coordinates of a region + * @cxlr: The region being operated on + * @input_xa: xarray holds cxl_perf_ctx wht calculated bandwidth per ACPI0017 instance + */ +static void cxl_region_update_bandwidth(struct cxl_region *cxlr, + struct xarray *input_xa) +{ + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct cxl_perf_ctx *ctx; + unsigned long index; + + memset(coord, 0, sizeof(coord)); + xa_for_each(input_xa, index, ctx) + cxl_bandwidth_add(coord, coord, ctx->coord); + + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + cxlr->coord[i].read_bandwidth = coord[i].read_bandwidth; + cxlr->coord[i].write_bandwidth = coord[i].write_bandwidth; + } +} + +/** + * cxl_region_shared_upstream_bandwidth_update - Recalculate the bandwidth for + * the region + * @cxlr: the cxl region to recalculate + * + * The function walks the topology from bottom up and calculates the bandwidth. It + * starts at the endpoints, processes at the switches if any, processes at the rootport + * level, at the host bridge level, and finally aggregates at the region. + */ +void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr) +{ + struct xarray *working_xa; + int root_count = 0; + bool is_root; + int rc; + + lockdep_assert_held(&cxl_dpa_rwsem); + + struct xarray *usp_xa __free(free_perf_xa) = + kzalloc(sizeof(*usp_xa), GFP_KERNEL); + + if (!usp_xa) + return; + + xa_init(usp_xa); + + /* Collect bandwidth data from all the endpoints. */ + for (int i = 0; i < cxlr->params.nr_targets; i++) { + struct cxl_endpoint_decoder *cxled = cxlr->params.targets[i]; + + is_root = false; + rc = cxl_endpoint_gather_bandwidth(cxlr, cxled, usp_xa, &is_root); + if (rc) + return; + root_count += is_root; + } + + /* Detect asymmetric hierarchy with some direct attached endpoints. */ + if (root_count && root_count != cxlr->params.nr_targets) { + dev_dbg(&cxlr->dev, + "Asymmetric hierarchy detected, bandwidth not updated\n"); + return; + } + + /* + * Walk up one or more switches to deal with the bandwidth of the + * switches if they exist. Endpoints directly attached to RPs skip + * over this part. + */ + if (!root_count) { + do { + working_xa = cxl_switch_gather_bandwidth(cxlr, usp_xa, + &is_root); + if (IS_ERR(working_xa)) + return; + free_perf_xa(usp_xa); + usp_xa = working_xa; + } while (!is_root); + } + + /* Handle the bandwidth at the root port of the hierarchy */ + working_xa = cxl_rp_gather_bandwidth(usp_xa); + if (IS_ERR(working_xa)) + return; + free_perf_xa(usp_xa); + usp_xa = working_xa; + + /* Handle the bandwidth at the host bridge of the hierarchy */ + working_xa = cxl_hb_gather_bandwidth(usp_xa); + if (IS_ERR(working_xa)) + return; + free_perf_xa(usp_xa); + usp_xa = working_xa; + + /* + * Aggregate all the bandwidth collected per CFMWS (ACPI0017) and + * update the region bandwidth with the final calculated values. + */ + cxl_region_update_bandwidth(cxlr, usp_xa); +} + +void cxl_region_perf_data_calculate(struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled) +{ + struct cxl_dpa_perf *perf; + lockdep_assert_held(&cxl_dpa_rwsem); - if (!range_contains(&perf->dpa_range, &dpa)) + perf = cxled_get_dpa_perf(cxled, cxlr->mode); + if (IS_ERR(perf)) return; for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 72a506c9dbd0..0c62b4069ba0 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -103,9 +103,11 @@ enum cxl_poison_trace_type { }; long cxl_pci_get_latency(struct pci_dev *pdev); - +int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c); int cxl_update_hmat_access_coordinates(int nid, struct cxl_region *cxlr, enum access_coordinate_class access); bool cxl_need_node_perf_attrs_update(int nid); +int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port, + struct access_coordinate *c); #endif /* __CXL_CORE_H__ */ diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index e5cdeafdf76e..946f8e44455f 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -225,7 +225,7 @@ static const char *cxl_mem_opcode_to_name(u16 opcode) /** * cxl_internal_send_cmd() - Kernel internal interface to send a mailbox command - * @mds: The driver data for the operation + * @cxl_mbox: CXL mailbox context * @mbox_cmd: initialized command to execute * * Context: Any context. @@ -241,19 +241,19 @@ static const char *cxl_mem_opcode_to_name(u16 opcode) * error. While this distinction can be useful for commands from userspace, the * kernel will only be able to use results when both are successful. */ -int cxl_internal_send_cmd(struct cxl_memdev_state *mds, +int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *mbox_cmd) { size_t out_size, min_out; int rc; - if (mbox_cmd->size_in > mds->payload_size || - mbox_cmd->size_out > mds->payload_size) + if (mbox_cmd->size_in > cxl_mbox->payload_size || + mbox_cmd->size_out > cxl_mbox->payload_size) return -E2BIG; out_size = mbox_cmd->size_out; min_out = mbox_cmd->min_out; - rc = mds->mbox_send(mds, mbox_cmd); + rc = cxl_mbox->mbox_send(cxl_mbox, mbox_cmd); /* * EIO is reserved for a payload size mismatch and mbox_send() * may not return this error. @@ -353,6 +353,7 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox, struct cxl_memdev_state *mds, u16 opcode, size_t in_size, size_t out_size, u64 in_payload) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; *mbox = (struct cxl_mbox_cmd) { .opcode = opcode, .size_in = in_size, @@ -374,7 +375,7 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox, /* Prepare to handle a full payload for variable sized output */ if (out_size == CXL_VARIABLE_PAYLOAD) - mbox->size_out = mds->payload_size; + mbox->size_out = cxl_mbox->payload_size; else mbox->size_out = out_size; @@ -398,6 +399,8 @@ static int cxl_to_mem_cmd_raw(struct cxl_mem_command *mem_cmd, const struct cxl_send_command *send_cmd, struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; + if (send_cmd->raw.rsvd) return -EINVAL; @@ -406,7 +409,7 @@ static int cxl_to_mem_cmd_raw(struct cxl_mem_command *mem_cmd, * gets passed along without further checking, so it must be * validated here. */ - if (send_cmd->out.size > mds->payload_size) + if (send_cmd->out.size > cxl_mbox->payload_size) return -EINVAL; if (!cxl_mem_raw_command_allowed(send_cmd->raw.opcode)) @@ -494,6 +497,7 @@ static int cxl_validate_cmd_from_user(struct cxl_mbox_cmd *mbox_cmd, struct cxl_memdev_state *mds, const struct cxl_send_command *send_cmd) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mem_command mem_cmd; int rc; @@ -505,7 +509,7 @@ static int cxl_validate_cmd_from_user(struct cxl_mbox_cmd *mbox_cmd, * supports, but output can be arbitrarily large (simply write out as * much data as the hardware provides). */ - if (send_cmd->in.size > mds->payload_size) + if (send_cmd->in.size > cxl_mbox->payload_size) return -EINVAL; /* Sanitize and construct a cxl_mem_command */ @@ -542,7 +546,7 @@ int cxl_query_cmd(struct cxl_memdev *cxlmd, return put_user(ARRAY_SIZE(cxl_mem_commands), &q->n_commands); /* - * otherwise, return max(n_commands, total commands) cxl_command_info + * otherwise, return min(n_commands, total commands) cxl_command_info * structures. */ cxl_for_each_cmd(cmd) { @@ -591,6 +595,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_memdev_state *mds, u64 out_payload, s32 *size_out, u32 *retval) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct device *dev = mds->cxlds.dev; int rc; @@ -601,7 +606,7 @@ static int handle_mailbox_cmd_from_user(struct cxl_memdev_state *mds, cxl_mem_opcode_to_name(mbox_cmd->opcode), mbox_cmd->opcode, mbox_cmd->size_in); - rc = mds->mbox_send(mds, mbox_cmd); + rc = cxl_mbox->mbox_send(cxl_mbox, mbox_cmd); if (rc) goto out; @@ -659,11 +664,12 @@ int cxl_send_cmd(struct cxl_memdev *cxlmd, struct cxl_send_command __user *s) static int cxl_xfer_log(struct cxl_memdev_state *mds, uuid_t *uuid, u32 *size, u8 *out) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; u32 remaining = *size; u32 offset = 0; while (remaining) { - u32 xfer_size = min_t(u32, remaining, mds->payload_size); + u32 xfer_size = min_t(u32, remaining, cxl_mbox->payload_size); struct cxl_mbox_cmd mbox_cmd; struct cxl_mbox_get_log log; int rc; @@ -682,7 +688,7 @@ static int cxl_xfer_log(struct cxl_memdev_state *mds, uuid_t *uuid, .payload_out = out, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); /* * The output payload length that indicates the number @@ -752,22 +758,23 @@ static void cxl_walk_cel(struct cxl_memdev_state *mds, size_t size, u8 *cel) static struct cxl_mbox_get_supported_logs *cxl_get_gsl(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_supported_logs *ret; struct cxl_mbox_cmd mbox_cmd; int rc; - ret = kvmalloc(mds->payload_size, GFP_KERNEL); + ret = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); mbox_cmd = (struct cxl_mbox_cmd) { .opcode = CXL_MBOX_OP_GET_SUPPORTED_LOGS, - .size_out = mds->payload_size, + .size_out = cxl_mbox->payload_size, .payload_out = ret, /* At least the record number field must be valid */ .min_out = 2, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { kvfree(ret); return ERR_PTR(rc); @@ -910,6 +917,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, enum cxl_event_log_type log, struct cxl_get_event_payload *get_pl) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_clear_event_payload *payload; u16 total = le16_to_cpu(get_pl->record_count); u8 max_handles = CXL_CLEAR_EVENT_MAX_HANDLES; @@ -920,8 +928,8 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, int i; /* Payload size may limit the max handles */ - if (pl_size > mds->payload_size) { - max_handles = (mds->payload_size - sizeof(*payload)) / + if (pl_size > cxl_mbox->payload_size) { + max_handles = (cxl_mbox->payload_size - sizeof(*payload)) / sizeof(__le16); pl_size = struct_size(payload, handles, max_handles); } @@ -955,7 +963,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, if (i == max_handles) { payload->nr_recs = i; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto free_pl; i = 0; @@ -966,7 +974,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, if (i) { payload->nr_recs = i; mbox_cmd.size_in = struct_size(payload, handles, i); - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto free_pl; } @@ -979,6 +987,7 @@ free_pl: static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, enum cxl_event_log_type type) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; struct device *dev = mds->cxlds.dev; struct cxl_get_event_payload *payload; @@ -995,11 +1004,11 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, .payload_in = &log_type, .size_in = sizeof(log_type), .payload_out = payload, - .size_out = mds->payload_size, + .size_out = cxl_mbox->payload_size, .min_out = struct_size(payload, records, 0), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) { dev_err_ratelimited(dev, "Event log '%d': Failed to query event records : %d", @@ -1070,6 +1079,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_get_event_records, CXL); */ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_partition_info pi; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -1079,7 +1089,7 @@ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds) .size_out = sizeof(pi), .payload_out = &pi, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) return rc; @@ -1106,6 +1116,7 @@ static int cxl_mem_get_partition_info(struct cxl_memdev_state *mds) */ int cxl_dev_state_identify(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ struct cxl_mbox_identify id; struct cxl_mbox_cmd mbox_cmd; @@ -1120,7 +1131,7 @@ int cxl_dev_state_identify(struct cxl_memdev_state *mds) .size_out = sizeof(id), .payload_out = &id, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; @@ -1148,6 +1159,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL); static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; int rc; u32 sec_out = 0; struct cxl_get_security_output { @@ -1159,14 +1171,13 @@ static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) .size_out = sizeof(out), }; struct cxl_mbox_cmd mbox_cmd = { .opcode = cmd }; - struct cxl_dev_state *cxlds = &mds->cxlds; if (cmd != CXL_MBOX_OP_SANITIZE && cmd != CXL_MBOX_OP_SECURE_ERASE) return -EINVAL; - rc = cxl_internal_send_cmd(mds, &sec_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &sec_cmd); if (rc < 0) { - dev_err(cxlds->dev, "Failed to get security state : %d", rc); + dev_err(cxl_mbox->host, "Failed to get security state : %d", rc); return rc; } @@ -1183,9 +1194,9 @@ static int __cxl_mem_sanitize(struct cxl_memdev_state *mds, u16 cmd) sec_out & CXL_PMEM_SEC_STATE_LOCKED) return -EINVAL; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { - dev_err(cxlds->dev, "Failed to sanitize device : %d", rc); + dev_err(cxl_mbox->host, "Failed to sanitize device : %d", rc); return rc; } @@ -1214,7 +1225,7 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) int rc; /* synchronize with cxl_mem_probe() and decoder write operations */ - device_lock(&cxlmd->dev); + guard(device)(&cxlmd->dev); endpoint = cxlmd->endpoint; down_read(&cxl_region_rwsem); /* @@ -1226,7 +1237,6 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd) else rc = -EBUSY; up_read(&cxl_region_rwsem); - device_unlock(&cxlmd->dev); return rc; } @@ -1300,6 +1310,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_mem_create_range_info, CXL); int cxl_set_timestamp(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_cmd mbox_cmd; struct cxl_mbox_set_timestamp_in pi; int rc; @@ -1311,7 +1322,7 @@ int cxl_set_timestamp(struct cxl_memdev_state *mds) .payload_in = &pi, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); /* * Command is optional. Devices may have another way of providing * a timestamp, or may return all 0s in timestamp fields. @@ -1328,6 +1339,7 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_region *cxlr) { struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_poison_out *po; struct cxl_mbox_poison_in pi; int nr_records = 0; @@ -1346,12 +1358,12 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, .opcode = CXL_MBOX_OP_GET_POISON, .size_in = sizeof(pi), .payload_in = &pi, - .size_out = mds->payload_size, + .size_out = cxl_mbox->payload_size, .payload_out = po, .min_out = struct_size(po, record, 0), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) break; @@ -1382,7 +1394,9 @@ static void free_poison_buf(void *buf) /* Get Poison List output buffer is protected by mds->poison.lock */ static int cxl_poison_alloc_buf(struct cxl_memdev_state *mds) { - mds->poison.list_out = kvmalloc(mds->payload_size, GFP_KERNEL); + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; + + mds->poison.list_out = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL); if (!mds->poison.list_out) return -ENOMEM; @@ -1408,6 +1422,19 @@ int cxl_poison_state_init(struct cxl_memdev_state *mds) } EXPORT_SYMBOL_NS_GPL(cxl_poison_state_init, CXL); +int cxl_mailbox_init(struct cxl_mailbox *cxl_mbox, struct device *host) +{ + if (!cxl_mbox || !host) + return -EINVAL; + + cxl_mbox->host = host; + mutex_init(&cxl_mbox->mbox_mutex); + rcuwait_init(&cxl_mbox->mbox_wait); + + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_mailbox_init, CXL); + struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev) { struct cxl_memdev_state *mds; @@ -1418,7 +1445,6 @@ struct cxl_memdev_state *cxl_memdev_state_create(struct device *dev) return ERR_PTR(-ENOMEM); } - mutex_init(&mds->mbox_mutex); mutex_init(&mds->event.log_lock); mds->cxlds.dev = dev; mds->cxlds.reg_map.host = dev; diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 0277726afd04..84fefb76dafa 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -58,7 +58,7 @@ static ssize_t payload_max_show(struct device *dev, if (!mds) return sysfs_emit(buf, "\n"); - return sysfs_emit(buf, "%zu\n", mds->payload_size); + return sysfs_emit(buf, "%zu\n", cxlds->cxl_mbox.payload_size); } static DEVICE_ATTR_RO(payload_max); @@ -124,15 +124,16 @@ static ssize_t security_state_show(struct device *dev, { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); unsigned long state = mds->security.state; int rc = 0; /* sync with latest submission state */ - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (mds->security.sanitize_active) rc = sysfs_emit(buf, "sanitize\n"); - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); if (rc) return rc; @@ -277,7 +278,7 @@ static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa) int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) { - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_inject_poison inject; struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; @@ -307,13 +308,13 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) .size_in = sizeof(inject), .payload_in = &inject, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto out; cxlr = cxl_dpa_to_region(cxlmd, dpa); if (cxlr) - dev_warn_once(mds->cxlds.dev, + dev_warn_once(cxl_mbox->host, "poison inject dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); @@ -332,7 +333,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL); int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) { - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_clear_poison clear; struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; @@ -371,13 +372,13 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) .payload_in = &clear, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc) goto out; cxlr = cxl_dpa_to_region(cxlmd, dpa); if (cxlr) - dev_warn_once(mds->cxlds.dev, + dev_warn_once(cxl_mbox->host, "poison clear dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); @@ -714,6 +715,7 @@ static int cxl_memdev_release_file(struct inode *inode, struct file *file) */ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_fw_info info; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -724,7 +726,7 @@ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds) .payload_out = &info, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; @@ -748,6 +750,7 @@ static int cxl_mem_get_fw_info(struct cxl_memdev_state *mds) */ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_activate_fw activate; struct cxl_mbox_cmd mbox_cmd; @@ -764,7 +767,7 @@ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot) activate.action = CXL_FW_ACTIVATE_OFFLINE; activate.slot = slot; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } /** @@ -779,6 +782,7 @@ static int cxl_mem_activate_fw(struct cxl_memdev_state *mds, int slot) */ static int cxl_mem_abort_fw_xfer(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_transfer_fw *transfer; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -798,7 +802,7 @@ static int cxl_mem_abort_fw_xfer(struct cxl_memdev_state *mds) transfer->action = CXL_FW_TRANSFER_ACTION_ABORT; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); kfree(transfer); return rc; } @@ -829,12 +833,13 @@ static enum fw_upload_err cxl_fw_prepare(struct fw_upload *fwl, const u8 *data, { struct cxl_memdev_state *mds = fwl->dd_handle; struct cxl_mbox_transfer_fw *transfer; + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; if (!size) return FW_UPLOAD_ERR_INVALID_SIZE; mds->fw.oneshot = struct_size(transfer, data, size) < - mds->payload_size; + cxl_mbox->payload_size; if (cxl_mem_get_fw_info(mds)) return FW_UPLOAD_ERR_HW_ERROR; @@ -854,6 +859,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data, { struct cxl_memdev_state *mds = fwl->dd_handle; struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; struct cxl_memdev *cxlmd = cxlds->cxlmd; struct cxl_mbox_transfer_fw *transfer; struct cxl_mbox_cmd mbox_cmd; @@ -877,7 +883,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data, * sizeof(*transfer) is 128. These constraints imply that @cur_size * will always be 128b aligned. */ - cur_size = min_t(size_t, size, mds->payload_size - sizeof(*transfer)); + cur_size = min_t(size_t, size, cxl_mbox->payload_size - sizeof(*transfer)); remaining = size - cur_size; size_in = struct_size(transfer, data, cur_size); @@ -921,7 +927,7 @@ static enum fw_upload_err cxl_fw_write(struct fw_upload *fwl, const u8 *data, .poll_count = 30, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { rc = FW_UPLOAD_ERR_RW_ERROR; goto out_free; @@ -1059,16 +1065,17 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_add_memdev, CXL); static void sanitize_teardown_notifier(void *data) { struct cxl_memdev_state *mds = data; + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct kernfs_node *state; /* * Prevent new irq triggered invocations of the workqueue and * flush inflight invocations. */ - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); state = mds->security.sanitize_node; mds->security.sanitize_node = NULL; - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); cancel_delayed_work_sync(&mds->security.poll_dwork); sysfs_put(state); diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 51132a575b27..5b46bc46aaa9 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -211,37 +211,6 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, CXL); -static int wait_for_valid(struct pci_dev *pdev, int d) -{ - u32 val; - int rc; - - /* - * Memory_Info_Valid: When set, indicates that the CXL Range 1 Size high - * and Size Low registers are valid. Must be set within 1 second of - * deassertion of reset to CXL device. Likely it is already set by the - * time this runs, but otherwise give a 1.5 second timeout in case of - * clock skew. - */ - rc = pci_read_config_dword(pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &val); - if (rc) - return rc; - - if (val & CXL_DVSEC_MEM_INFO_VALID) - return 0; - - msleep(1500); - - rc = pci_read_config_dword(pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &val); - if (rc) - return rc; - - if (val & CXL_DVSEC_MEM_INFO_VALID) - return 0; - - return -ETIMEDOUT; -} - static int cxl_set_mem_enable(struct cxl_dev_state *cxlds, u16 val) { struct pci_dev *pdev = to_pci_dev(cxlds->dev); @@ -322,11 +291,13 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) return devm_add_action_or_reset(host, disable_hdm, cxlhdm); } -int cxl_dvsec_rr_decode(struct device *dev, int d, +int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, struct cxl_endpoint_dvsec_info *info) { struct pci_dev *pdev = to_pci_dev(dev); + struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); int hdm_count, rc, i, ranges = 0; + int d = cxlds->cxl_dvsec; u16 cap, ctrl; if (!d) { @@ -353,12 +324,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, if (!hdm_count || hdm_count > 2) return -EINVAL; - rc = wait_for_valid(pdev, d); - if (rc) { - dev_dbg(dev, "Failure awaiting MEM_INFO_VALID (%d)\n", rc); - return rc; - } - /* * The current DVSEC values are moot if the memory capability is * disabled, and they will remain moot after the HDM Decoder @@ -376,6 +341,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, u64 base, size; u32 temp; + rc = cxl_dvsec_mem_range_valid(cxlds, i); + if (rc) + return rc; + rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_SIZE_HIGH(i), &temp); if (rc) @@ -390,10 +359,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK; if (!size) { - info->dvsec_range[i] = (struct range) { - .start = 0, - .end = CXL_RESOURCE_NONE, - }; continue; } @@ -411,12 +376,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d, base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK; - info->dvsec_range[i] = (struct range) { + info->dvsec_range[ranges++] = (struct range) { .start = base, .end = base + size - 1 }; - - ranges++; } info->ranges = ranges; @@ -463,7 +426,15 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, return -ENODEV; } - for (i = 0, allowed = 0; info->mem_enabled && i < info->ranges; i++) { + if (!info->mem_enabled) { + rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); + if (rc) + return rc; + + return devm_cxl_enable_mem(&port->dev, cxlds); + } + + for (i = 0, allowed = 0; i < info->ranges; i++) { struct device *cxld_dev; cxld_dev = device_find_child(&root->dev, &info->dvsec_range[i], @@ -477,7 +448,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, allowed++; } - if (!allowed && info->mem_enabled) { + if (!allowed) { dev_err(dev, "Range register decodes outside platform defined CXL ranges.\n"); return -ENXIO; } @@ -491,14 +462,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, * match. If at least one DVSEC range is enabled and allowed, skip HDM * Decoder Capability Enable. */ - if (info->mem_enabled) - return 0; - - rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); - if (rc) - return rc; - - return devm_cxl_enable_mem(&port->dev, cxlds); + return 0; } EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL); @@ -772,22 +736,20 @@ static bool cxl_handle_endpoint_ras(struct cxl_dev_state *cxlds) static void cxl_dport_map_rch_aer(struct cxl_dport *dport) { - struct cxl_rcrb_info *ri = &dport->rcrb; - void __iomem *dport_aer = NULL; resource_size_t aer_phys; struct device *host; + u16 aer_cap; - if (dport->rch && ri->aer_cap) { + aer_cap = cxl_rcrb_to_aer(dport->dport_dev, dport->rcrb.base); + if (aer_cap) { host = dport->reg_map.host; - aer_phys = ri->aer_cap + ri->base; - dport_aer = devm_cxl_iomap_block(host, aer_phys, - sizeof(struct aer_capability_regs)); + aer_phys = aer_cap + dport->rcrb.base; + dport->regs.dport_aer = devm_cxl_iomap_block(host, aer_phys, + sizeof(struct aer_capability_regs)); } - - dport->regs.dport_aer = dport_aer; } -static void cxl_dport_map_regs(struct cxl_dport *dport) +static void cxl_dport_map_ras(struct cxl_dport *dport) { struct cxl_register_map *map = &dport->reg_map; struct device *dev = dport->dport_dev; @@ -797,22 +759,16 @@ static void cxl_dport_map_regs(struct cxl_dport *dport) else if (cxl_map_component_regs(map, &dport->regs.component, BIT(CXL_CM_CAP_CAP_ID_RAS))) dev_dbg(dev, "Failed to map RAS capability.\n"); - - if (dport->rch) - cxl_dport_map_rch_aer(dport); } static void cxl_disable_rch_root_ints(struct cxl_dport *dport) { void __iomem *aer_base = dport->regs.dport_aer; - struct pci_host_bridge *bridge; u32 aer_cmd_mask, aer_cmd; if (!aer_base) return; - bridge = to_pci_host_bridge(dport->dport_dev); - /* * Disable RCH root port command interrupts. * CXL 3.0 12.2.1.1 - RCH Downstream Port-detected Errors @@ -821,34 +777,35 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport) * the root cmd register's interrupts is required. But, PCI spec * shows these are disabled by default on reset. */ - if (bridge->native_aer) { - aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN | - PCI_ERR_ROOT_CMD_NONFATAL_EN | - PCI_ERR_ROOT_CMD_FATAL_EN); - aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND); - aer_cmd &= ~aer_cmd_mask; - writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND); - } + aer_cmd_mask = (PCI_ERR_ROOT_CMD_COR_EN | + PCI_ERR_ROOT_CMD_NONFATAL_EN | + PCI_ERR_ROOT_CMD_FATAL_EN); + aer_cmd = readl(aer_base + PCI_ERR_ROOT_COMMAND); + aer_cmd &= ~aer_cmd_mask; + writel(aer_cmd, aer_base + PCI_ERR_ROOT_COMMAND); } -void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport) +/** + * cxl_dport_init_ras_reporting - Setup CXL RAS report on this dport + * @dport: the cxl_dport that needs to be initialized + * @host: host device for devm operations + */ +void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host) { - struct device *dport_dev = dport->dport_dev; + dport->reg_map.host = host; + cxl_dport_map_ras(dport); if (dport->rch) { - struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport_dev); - - if (host_bridge->native_aer) - dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base); - } + struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport->dport_dev); - dport->reg_map.host = host; - cxl_dport_map_regs(dport); + if (!host_bridge->native_aer) + return; - if (dport->rch) + cxl_dport_map_rch_aer(dport); cxl_disable_rch_root_ints(dport); + } } -EXPORT_SYMBOL_NS_GPL(cxl_setup_parent_dport, CXL); +EXPORT_SYMBOL_NS_GPL(cxl_dport_init_ras_reporting, CXL); static void cxl_handle_rdport_cor_ras(struct cxl_dev_state *cxlds, struct cxl_dport *dport) @@ -915,15 +872,13 @@ static void cxl_handle_rdport_errors(struct cxl_dev_state *cxlds) struct pci_dev *pdev = to_pci_dev(cxlds->dev); struct aer_capability_regs aer_regs; struct cxl_dport *dport; - struct cxl_port *port; int severity; - port = cxl_pci_find_port(pdev, &dport); + struct cxl_port *port __free(put_cxl_port) = + cxl_pci_find_port(pdev, &dport); if (!port) return; - put_device(&port->dev); - if (!cxl_rch_get_aer_info(dport->regs.dport_aer, &aer_regs)) return; @@ -1076,3 +1031,26 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port) __cxl_endpoint_decoder_reset_detected); } EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_reset_detected, CXL); + +int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c) +{ + int speed, bw; + u16 lnksta; + u32 width; + + speed = pcie_link_speed_mbps(pdev); + if (speed < 0) + return speed; + speed /= BITS_PER_BYTE; + + pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnksta); + width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta); + bw = speed * width; + + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].read_bandwidth = bw; + c[i].write_bandwidth = bw; + } + + return 0; +} diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 1d5007e3795a..e666ec6a9085 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -3,7 +3,6 @@ #include <linux/platform_device.h> #include <linux/memregion.h> #include <linux/workqueue.h> -#include <linux/einj-cxl.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/module.h> @@ -11,6 +10,7 @@ #include <linux/slab.h> #include <linux/idr.h> #include <linux/node.h> +#include <cxl/einj.h> #include <cxlmem.h> #include <cxlpci.h> #include <cxl.h> @@ -828,27 +828,20 @@ static void cxl_debugfs_create_dport_dir(struct cxl_dport *dport) &cxl_einj_inject_fops); } -static struct cxl_port *__devm_cxl_add_port(struct device *host, - struct device *uport_dev, - resource_size_t component_reg_phys, - struct cxl_dport *parent_dport) +static int cxl_port_add(struct cxl_port *port, + resource_size_t component_reg_phys, + struct cxl_dport *parent_dport) { - struct cxl_port *port; - struct device *dev; + struct device *dev __free(put_device) = &port->dev; int rc; - port = cxl_port_alloc(uport_dev, parent_dport); - if (IS_ERR(port)) - return port; - - dev = &port->dev; - if (is_cxl_memdev(uport_dev)) { - struct cxl_memdev *cxlmd = to_cxl_memdev(uport_dev); + if (is_cxl_memdev(port->uport_dev)) { + struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev); struct cxl_dev_state *cxlds = cxlmd->cxlds; rc = dev_set_name(dev, "endpoint%d", port->id); if (rc) - goto err; + return rc; /* * The endpoint driver already enumerated the component and RAS @@ -861,19 +854,41 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host, } else if (parent_dport) { rc = dev_set_name(dev, "port%d", port->id); if (rc) - goto err; + return rc; rc = cxl_port_setup_regs(port, component_reg_phys); if (rc) - goto err; - } else + return rc; + } else { rc = dev_set_name(dev, "root%d", port->id); - if (rc) - goto err; + if (rc) + return rc; + } rc = device_add(dev); if (rc) - goto err; + return rc; + + /* Inhibit the cleanup function invoked */ + dev = NULL; + return 0; +} + +static struct cxl_port *__devm_cxl_add_port(struct device *host, + struct device *uport_dev, + resource_size_t component_reg_phys, + struct cxl_dport *parent_dport) +{ + struct cxl_port *port; + int rc; + + port = cxl_port_alloc(uport_dev, parent_dport); + if (IS_ERR(port)) + return port; + + rc = cxl_port_add(port, component_reg_phys, parent_dport); + if (rc) + return ERR_PTR(rc); rc = devm_add_action_or_reset(host, unregister_port, port); if (rc) @@ -891,10 +906,6 @@ static struct cxl_port *__devm_cxl_add_port(struct device *host, port->pci_latency = cxl_pci_get_latency(to_pci_dev(uport_dev)); return port; - -err: - put_device(dev); - return ERR_PTR(rc); } /** @@ -941,7 +952,7 @@ struct cxl_root *devm_cxl_add_root(struct device *host, port = devm_cxl_add_port(host, host, CXL_RESOURCE_NONE, NULL); if (IS_ERR(port)) - return (struct cxl_root *)port; + return ERR_CAST(port); cxl_root = to_cxl_root(port); cxl_root->ops = ops; @@ -1258,18 +1269,13 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_add_rch_dport, CXL); static int add_ep(struct cxl_ep *new) { struct cxl_port *port = new->dport->port; - int rc; - device_lock(&port->dev); - if (port->dead) { - device_unlock(&port->dev); + guard(device)(&port->dev); + if (port->dead) return -ENXIO; - } - rc = xa_insert(&port->endpoints, (unsigned long)new->ep, new, - GFP_KERNEL); - device_unlock(&port->dev); - return rc; + return xa_insert(&port->endpoints, (unsigned long)new->ep, + new, GFP_KERNEL); } /** @@ -1393,14 +1399,14 @@ static void delete_endpoint(void *data) struct cxl_port *endpoint = cxlmd->endpoint; struct device *host = endpoint_host(endpoint); - device_lock(host); - if (host->driver && !endpoint->dead) { - devm_release_action(host, cxl_unlink_parent_dport, endpoint); - devm_release_action(host, cxl_unlink_uport, endpoint); - devm_release_action(host, unregister_port, endpoint); + scoped_guard(device, host) { + if (host->driver && !endpoint->dead) { + devm_release_action(host, cxl_unlink_parent_dport, endpoint); + devm_release_action(host, cxl_unlink_uport, endpoint); + devm_release_action(host, unregister_port, endpoint); + } + cxlmd->endpoint = NULL; } - cxlmd->endpoint = NULL; - device_unlock(host); put_device(&endpoint->dev); put_device(host); } @@ -1477,12 +1483,11 @@ static void cxl_detach_ep(void *data) .cxlmd = cxlmd, .depth = i, }; - struct device *dev; struct cxl_ep *ep; bool died = false; - dev = bus_find_device(&cxl_bus_type, NULL, &ctx, - port_has_memdev); + struct device *dev __free(put_device) = + bus_find_device(&cxl_bus_type, NULL, &ctx, port_has_memdev); if (!dev) continue; port = to_cxl_port(dev); @@ -1512,7 +1517,6 @@ static void cxl_detach_ep(void *data) dev_name(&port->dev)); delete_switch_port(port); } - put_device(&port->dev); device_unlock(&parent_port->dev); } } @@ -1540,7 +1544,6 @@ static int add_port_attach_ep(struct cxl_memdev *cxlmd, struct device *dport_dev) { struct device *dparent = grandparent(dport_dev); - struct cxl_port *port, *parent_port = NULL; struct cxl_dport *dport, *parent_dport; resource_size_t component_reg_phys; int rc; @@ -1556,50 +1559,52 @@ static int add_port_attach_ep(struct cxl_memdev *cxlmd, return -ENXIO; } - parent_port = find_cxl_port(dparent, &parent_dport); + struct cxl_port *parent_port __free(put_cxl_port) = + find_cxl_port(dparent, &parent_dport); if (!parent_port) { /* iterate to create this parent_port */ return -EAGAIN; } - device_lock(&parent_port->dev); - if (!parent_port->dev.driver) { - dev_warn(&cxlmd->dev, - "port %s:%s disabled, failed to enumerate CXL.mem\n", - dev_name(&parent_port->dev), dev_name(uport_dev)); - port = ERR_PTR(-ENXIO); - goto out; - } + /* + * Definition with __free() here to keep the sequence of + * dereferencing the device of the port before the parent_port releasing. + */ + struct cxl_port *port __free(put_cxl_port) = NULL; + scoped_guard(device, &parent_port->dev) { + if (!parent_port->dev.driver) { + dev_warn(&cxlmd->dev, + "port %s:%s disabled, failed to enumerate CXL.mem\n", + dev_name(&parent_port->dev), dev_name(uport_dev)); + return -ENXIO; + } - port = find_cxl_port_at(parent_port, dport_dev, &dport); - if (!port) { - component_reg_phys = find_component_registers(uport_dev); - port = devm_cxl_add_port(&parent_port->dev, uport_dev, - component_reg_phys, parent_dport); - /* retry find to pick up the new dport information */ - if (!IS_ERR(port)) + port = find_cxl_port_at(parent_port, dport_dev, &dport); + if (!port) { + component_reg_phys = find_component_registers(uport_dev); + port = devm_cxl_add_port(&parent_port->dev, uport_dev, + component_reg_phys, parent_dport); + if (IS_ERR(port)) + return PTR_ERR(port); + + /* retry find to pick up the new dport information */ port = find_cxl_port_at(parent_port, dport_dev, &dport); + if (!port) + return -ENXIO; + } } -out: - device_unlock(&parent_port->dev); - if (IS_ERR(port)) - rc = PTR_ERR(port); - else { - dev_dbg(&cxlmd->dev, "add to new port %s:%s\n", - dev_name(&port->dev), dev_name(port->uport_dev)); - rc = cxl_add_ep(dport, &cxlmd->dev); - if (rc == -EBUSY) { - /* - * "can't" happen, but this error code means - * something to the caller, so translate it. - */ - rc = -ENXIO; - } - put_device(&port->dev); + dev_dbg(&cxlmd->dev, "add to new port %s:%s\n", + dev_name(&port->dev), dev_name(port->uport_dev)); + rc = cxl_add_ep(dport, &cxlmd->dev); + if (rc == -EBUSY) { + /* + * "can't" happen, but this error code means + * something to the caller, so translate it. + */ + rc = -ENXIO; } - put_device(&parent_port->dev); return rc; } @@ -1630,7 +1635,6 @@ retry: struct device *dport_dev = grandparent(iter); struct device *uport_dev; struct cxl_dport *dport; - struct cxl_port *port; /* * The terminal "grandparent" in PCI is NULL and @platform_bus @@ -1649,7 +1653,8 @@ retry: dev_dbg(dev, "scan: iter: %s dport_dev: %s parent: %s\n", dev_name(iter), dev_name(dport_dev), dev_name(uport_dev)); - port = find_cxl_port(dport_dev, &dport); + struct cxl_port *port __free(put_cxl_port) = + find_cxl_port(dport_dev, &dport); if (port) { dev_dbg(&cxlmd->dev, "found already registered port %s:%s\n", @@ -1664,18 +1669,13 @@ retry: * the parent_port lock as the current port may be being * reaped. */ - if (rc && rc != -EBUSY) { - put_device(&port->dev); + if (rc && rc != -EBUSY) return rc; - } /* Any more ports to add between this one and the root? */ - if (!dev_is_cxl_root_child(&port->dev)) { - put_device(&port->dev); + if (!dev_is_cxl_root_child(&port->dev)) continue; - } - put_device(&port->dev); return 0; } @@ -1983,7 +1983,6 @@ EXPORT_SYMBOL_NS_GPL(cxl_decoder_add_locked, CXL); int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map) { struct cxl_port *port; - int rc; if (WARN_ON_ONCE(!cxld)) return -EINVAL; @@ -1993,11 +1992,8 @@ int cxl_decoder_add(struct cxl_decoder *cxld, int *target_map) port = to_cxl_port(cxld->dev.parent); - device_lock(&port->dev); - rc = cxl_decoder_add_locked(cxld, target_map); - device_unlock(&port->dev); - - return rc; + guard(device)(&port->dev); + return cxl_decoder_add_locked(cxld, target_map); } EXPORT_SYMBOL_NS_GPL(cxl_decoder_add, CXL); @@ -2241,6 +2237,26 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, } EXPORT_SYMBOL_NS_GPL(cxl_endpoint_get_perf_coordinates, CXL); +int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port, + struct access_coordinate *c) +{ + struct cxl_dport *dport = port->parent_dport; + + /* Check this port is connected to a switch DSP and not an RP */ + if (parent_port_is_cxl_root(to_cxl_port(port->dev.parent))) + return -ENODEV; + + if (!coordinates_valid(dport->coord)) + return -EINVAL; + + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].read_bandwidth = dport->coord[i].read_bandwidth; + c[i].write_bandwidth = dport->coord[i].write_bandwidth; + } + + return 0; +} + /* for user tooling to ensure port disable work has completed */ static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count) { diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 21ad5f242875..e701e4b04032 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1983,6 +1983,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, * then the region is already committed. */ p->state = CXL_CONFIG_COMMIT; + cxl_region_shared_upstream_bandwidth_update(cxlr); return 0; } @@ -2004,6 +2005,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (rc) return rc; p->state = CXL_CONFIG_ACTIVE; + cxl_region_shared_upstream_bandwidth_update(cxlr); } cxled->cxld.interleave_ways = p->interleave_ways; @@ -2313,8 +2315,6 @@ static void unregister_region(void *_cxlr) struct cxl_region_params *p = &cxlr->params; int i; - unregister_memory_notifier(&cxlr->memory_notifier); - unregister_mt_adistance_algorithm(&cxlr->adist_notifier); device_del(&cxlr->dev); /* @@ -2391,18 +2391,6 @@ static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid) return true; } -static int cxl_region_nid(struct cxl_region *cxlr) -{ - struct cxl_region_params *p = &cxlr->params; - struct resource *res; - - guard(rwsem_read)(&cxl_region_rwsem); - res = p->res; - if (!res) - return NUMA_NO_NODE; - return phys_to_target_node(res->start); -} - static int cxl_region_perf_attrs_callback(struct notifier_block *nb, unsigned long action, void *arg) { @@ -2415,7 +2403,11 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb, if (nid == NUMA_NO_NODE || action != MEM_ONLINE) return NOTIFY_DONE; - region_nid = cxl_region_nid(cxlr); + /* + * No need to hold cxl_region_rwsem; region parameters are stable + * within the cxl_region driver. + */ + region_nid = phys_to_target_node(cxlr->params.res->start); if (nid != region_nid) return NOTIFY_DONE; @@ -2434,7 +2426,11 @@ static int cxl_region_calculate_adistance(struct notifier_block *nb, int *adist = data; int region_nid; - region_nid = cxl_region_nid(cxlr); + /* + * No need to hold cxl_region_rwsem; region parameters are stable + * within the cxl_region driver. + */ + region_nid = phys_to_target_node(cxlr->params.res->start); if (nid != region_nid) return NOTIFY_OK; @@ -2484,14 +2480,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd, if (rc) goto err; - cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback; - cxlr->memory_notifier.priority = CXL_CALLBACK_PRI; - register_memory_notifier(&cxlr->memory_notifier); - - cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance; - cxlr->adist_notifier.priority = 100; - register_mt_adistance_algorithm(&cxlr->adist_notifier); - rc = devm_add_action_or_reset(port->uport_dev, unregister_region, cxlr); if (rc) return ERR_PTR(rc); @@ -3094,11 +3082,11 @@ static void cxlr_release_nvdimm(void *_cxlr) struct cxl_region *cxlr = _cxlr; struct cxl_nvdimm_bridge *cxl_nvb = cxlr->cxl_nvb; - device_lock(&cxl_nvb->dev); - if (cxlr->cxlr_pmem) - devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister, - cxlr->cxlr_pmem); - device_unlock(&cxl_nvb->dev); + scoped_guard(device, &cxl_nvb->dev) { + if (cxlr->cxlr_pmem) + devm_release_action(&cxl_nvb->dev, cxlr_pmem_unregister, + cxlr->cxlr_pmem); + } cxlr->cxl_nvb = NULL; put_device(&cxl_nvb->dev); } @@ -3134,13 +3122,14 @@ static int devm_cxl_add_pmem_region(struct cxl_region *cxlr) dev_dbg(&cxlr->dev, "%s: register %s\n", dev_name(dev->parent), dev_name(dev)); - device_lock(&cxl_nvb->dev); - if (cxl_nvb->dev.driver) - rc = devm_add_action_or_reset(&cxl_nvb->dev, - cxlr_pmem_unregister, cxlr_pmem); - else - rc = -ENXIO; - device_unlock(&cxl_nvb->dev); + scoped_guard(device, &cxl_nvb->dev) { + if (cxl_nvb->dev.driver) + rc = devm_add_action_or_reset(&cxl_nvb->dev, + cxlr_pmem_unregister, + cxlr_pmem); + else + rc = -ENXIO; + } if (rc) goto err_bridge; @@ -3386,6 +3375,14 @@ static int is_system_ram(struct resource *res, void *arg) return 1; } +static void shutdown_notifiers(void *_cxlr) +{ + struct cxl_region *cxlr = _cxlr; + + unregister_memory_notifier(&cxlr->memory_notifier); + unregister_mt_adistance_algorithm(&cxlr->adist_notifier); +} + static int cxl_region_probe(struct device *dev) { struct cxl_region *cxlr = to_cxl_region(dev); @@ -3421,6 +3418,18 @@ out: if (rc) return rc; + cxlr->memory_notifier.notifier_call = cxl_region_perf_attrs_callback; + cxlr->memory_notifier.priority = CXL_CALLBACK_PRI; + register_memory_notifier(&cxlr->memory_notifier); + + cxlr->adist_notifier.notifier_call = cxl_region_calculate_adistance; + cxlr->adist_notifier.priority = 100; + register_mt_adistance_algorithm(&cxlr->adist_notifier); + + rc = devm_add_action_or_reset(&cxlr->dev, shutdown_notifiers, cxlr); + if (rc) + return rc; + switch (cxlr->mode) { case CXL_DECODER_PMEM: return devm_cxl_add_pmem_region(cxlr); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 9afb407d438f..0d8b810a51f0 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -744,6 +744,7 @@ struct cxl_root *find_cxl_root(struct cxl_port *port); void put_cxl_root(struct cxl_root *cxl_root); DEFINE_FREE(put_cxl_root, struct cxl_root *, if (_T) put_cxl_root(_T)) +DEFINE_FREE(put_cxl_port, struct cxl_port *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev)) int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd); void cxl_bus_rescan(void); void cxl_bus_drain(void); @@ -762,9 +763,10 @@ struct cxl_dport *devm_cxl_add_rch_dport(struct cxl_port *port, #ifdef CONFIG_PCIEAER_CXL void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport); +void cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host); #else -static inline void cxl_setup_parent_dport(struct device *host, - struct cxl_dport *dport) { } +static inline void cxl_dport_init_ras_reporting(struct cxl_dport *dport, + struct device *host) { } #endif struct cxl_decoder *to_cxl_decoder(struct device *dev); @@ -809,7 +811,7 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info); int devm_cxl_add_passthrough_decoder(struct cxl_port *port); -int cxl_dvsec_rr_decode(struct device *dev, int dvsec, +int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); bool is_cxl_region(struct device *dev); @@ -889,6 +891,7 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct access_coordinate *coord); void cxl_region_perf_data_calculate(struct cxl_region *cxlr, struct cxl_endpoint_decoder *cxled); +void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr); void cxl_memdev_update_perf(struct cxl_memdev *cxlmd); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index afb53d058d62..2a25d1957ddb 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -3,11 +3,12 @@ #ifndef __CXL_MEM_H__ #define __CXL_MEM_H__ #include <uapi/linux/cxl_mem.h> +#include <linux/pci.h> #include <linux/cdev.h> #include <linux/uuid.h> -#include <linux/rcuwait.h> -#include <linux/cxl-event.h> #include <linux/node.h> +#include <cxl/event.h> +#include <cxl/mailbox.h> #include "cxl.h" /* CXL 2.0 8.2.8.5.1.1 Memory Device Status Register */ @@ -397,11 +398,13 @@ enum cxl_devtype { * struct cxl_dpa_perf - DPA performance property entry * @dpa_range: range for DPA address * @coord: QoS performance data (i.e. latency, bandwidth) + * @cdat_coord: raw QoS performance data from CDAT * @qos_class: QoS Class cookies */ struct cxl_dpa_perf { struct range dpa_range; struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate cdat_coord[ACCESS_COORDINATE_MAX]; int qos_class; }; @@ -424,6 +427,7 @@ struct cxl_dpa_perf { * @ram_res: Active Volatile memory capacity configuration * @serial: PCIe Device Serial Number * @type: Generic Memory Class device or Vendor Specific Memory device + * @cxl_mbox: CXL mailbox context */ struct cxl_dev_state { struct device *dev; @@ -438,8 +442,14 @@ struct cxl_dev_state { struct resource ram_res; u64 serial; enum cxl_devtype type; + struct cxl_mailbox cxl_mbox; }; +static inline struct cxl_dev_state *mbox_to_cxlds(struct cxl_mailbox *cxl_mbox) +{ + return dev_get_drvdata(cxl_mbox->host); +} + /** * struct cxl_memdev_state - Generic Type-3 Memory Device Class driver data * @@ -448,11 +458,8 @@ struct cxl_dev_state { * the functionality related to that like Identify Memory Device and Get * Partition Info * @cxlds: Core driver state common across Type-2 and Type-3 devices - * @payload_size: Size of space for payload - * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @lsa_size: Size of Label Storage Area * (CXL 2.0 8.2.9.5.1.1 Identify Memory Device) - * @mbox_mutex: Mutex to synchronize mailbox access. * @firmware_version: Firmware version for the memory device. * @enabled_cmds: Hardware commands found enabled in CEL. * @exclusive_cmds: Commands that are kernel-internal only @@ -470,17 +477,13 @@ struct cxl_dev_state { * @poison: poison driver state info * @security: security driver state info * @fw: firmware upload / activation state - * @mbox_wait: RCU wait for mbox send completely - * @mbox_send: @dev specific transport for transmitting mailbox commands * * See CXL 3.0 8.2.9.8.2 Capacity Configuration and Label Storage for * details on capacity parameters. */ struct cxl_memdev_state { struct cxl_dev_state cxlds; - size_t payload_size; size_t lsa_size; - struct mutex mbox_mutex; /* Protects device mailbox and firmware */ char firmware_version[0x10]; DECLARE_BITMAP(enabled_cmds, CXL_MEM_COMMAND_ID_MAX); DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); @@ -500,10 +503,6 @@ struct cxl_memdev_state { struct cxl_poison_state poison; struct cxl_security_state security; struct cxl_fw_state fw; - - struct rcuwait mbox_wait; - int (*mbox_send)(struct cxl_memdev_state *mds, - struct cxl_mbox_cmd *cmd); }; static inline struct cxl_memdev_state * @@ -814,7 +813,7 @@ enum { CXL_PMEM_SEC_PASS_USER, }; -int cxl_internal_send_cmd(struct cxl_memdev_state *mds, +int cxl_internal_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd); int cxl_dev_state_identify(struct cxl_memdev_state *mds); int cxl_await_media_ready(struct cxl_dev_state *cxlds); diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 7de232eaeb17..a9fd5cd5a0d2 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -109,7 +109,6 @@ static int cxl_mem_probe(struct device *dev) struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); struct cxl_dev_state *cxlds = cxlmd->cxlds; struct device *endpoint_parent; - struct cxl_port *parent_port; struct cxl_dport *dport; struct dentry *dentry; int rc; @@ -146,7 +145,8 @@ static int cxl_mem_probe(struct device *dev) if (rc) return rc; - parent_port = cxl_mem_find_port(cxlmd, &dport); + struct cxl_port *parent_port __free(put_cxl_port) = + cxl_mem_find_port(cxlmd, &dport); if (!parent_port) { dev_err(dev, "CXL port topology not found\n"); return -ENXIO; @@ -166,22 +166,19 @@ static int cxl_mem_probe(struct device *dev) else endpoint_parent = &parent_port->dev; - cxl_setup_parent_dport(dev, dport); + cxl_dport_init_ras_reporting(dport, dev); - device_lock(endpoint_parent); - if (!endpoint_parent->driver) { - dev_err(dev, "CXL port topology %s not enabled\n", - dev_name(endpoint_parent)); - rc = -ENXIO; - goto unlock; - } + scoped_guard(device, endpoint_parent) { + if (!endpoint_parent->driver) { + dev_err(dev, "CXL port topology %s not enabled\n", + dev_name(endpoint_parent)); + return -ENXIO; + } - rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport); -unlock: - device_unlock(endpoint_parent); - put_device(&parent_port->dev); - if (rc) - return rc; + rc = devm_cxl_add_endpoint(endpoint_parent, cxlmd, dport); + if (rc) + return rc; + } /* * The kernel may be operating out of CXL memory on this device, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 4be35dc22202..37164174b5fb 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/aer.h> #include <linux/io.h> +#include <cxl/mailbox.h> #include "cxlmem.h" #include "cxlpci.h" #include "cxl.h" @@ -124,6 +125,7 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id) u16 opcode; struct cxl_dev_id *dev_id = id; struct cxl_dev_state *cxlds = dev_id->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); if (!cxl_mbox_background_complete(cxlds)) @@ -132,13 +134,13 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id) reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_BG_CMD_STATUS_OFFSET); opcode = FIELD_GET(CXLDEV_MBOX_BG_CMD_COMMAND_OPCODE_MASK, reg); if (opcode == CXL_MBOX_OP_SANITIZE) { - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (mds->security.sanitize_node) mod_delayed_work(system_wq, &mds->security.poll_dwork, 0); - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); } else { /* short-circuit the wait in __cxl_pci_mbox_send_cmd() */ - rcuwait_wake_up(&mds->mbox_wait); + rcuwait_wake_up(&cxl_mbox->mbox_wait); } return IRQ_HANDLED; @@ -152,8 +154,9 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) struct cxl_memdev_state *mds = container_of(work, typeof(*mds), security.poll_dwork.work); struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (cxl_mbox_background_complete(cxlds)) { mds->security.poll_tmo_secs = 0; if (mds->security.sanitize_node) @@ -167,12 +170,12 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) mds->security.poll_tmo_secs = min(15 * 60, timeout); schedule_delayed_work(&mds->security.poll_dwork, timeout * HZ); } - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); } /** * __cxl_pci_mbox_send_cmd() - Execute a mailbox command - * @mds: The memory device driver data + * @cxl_mbox: CXL mailbox context * @mbox_cmd: Command to send to the memory device. * * Context: Any context. Expects mbox_mutex to be held. @@ -192,17 +195,18 @@ static void cxl_mbox_sanitize_work(struct work_struct *work) * not need to coordinate with each other. The driver only uses the primary * mailbox. */ -static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds, +static int __cxl_pci_mbox_send_cmd(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *mbox_cmd) { - struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_dev_state *cxlds = mbox_to_cxlds(cxl_mbox); + struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); void __iomem *payload = cxlds->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET; struct device *dev = cxlds->dev; u64 cmd_reg, status_reg; size_t out_len; int rc; - lockdep_assert_held(&mds->mbox_mutex); + lockdep_assert_held(&cxl_mbox->mbox_mutex); /* * Here are the steps from 8.2.8.4 of the CXL 2.0 spec. @@ -315,10 +319,10 @@ static int __cxl_pci_mbox_send_cmd(struct cxl_memdev_state *mds, timeout = mbox_cmd->poll_interval_ms; for (i = 0; i < mbox_cmd->poll_count; i++) { - if (rcuwait_wait_event_timeout(&mds->mbox_wait, - cxl_mbox_background_complete(cxlds), - TASK_UNINTERRUPTIBLE, - msecs_to_jiffies(timeout)) > 0) + if (rcuwait_wait_event_timeout(&cxl_mbox->mbox_wait, + cxl_mbox_background_complete(cxlds), + TASK_UNINTERRUPTIBLE, + msecs_to_jiffies(timeout)) > 0) break; } @@ -360,7 +364,7 @@ success: */ size_t n; - n = min3(mbox_cmd->size_out, mds->payload_size, out_len); + n = min3(mbox_cmd->size_out, cxl_mbox->payload_size, out_len); memcpy_fromio(mbox_cmd->payload_out, payload, n); mbox_cmd->size_out = n; } else { @@ -370,14 +374,14 @@ success: return 0; } -static int cxl_pci_mbox_send(struct cxl_memdev_state *mds, +static int cxl_pci_mbox_send(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd) { int rc; - mutex_lock_io(&mds->mbox_mutex); - rc = __cxl_pci_mbox_send_cmd(mds, cmd); - mutex_unlock(&mds->mbox_mutex); + mutex_lock_io(&cxl_mbox->mbox_mutex); + rc = __cxl_pci_mbox_send_cmd(cxl_mbox, cmd); + mutex_unlock(&cxl_mbox->mbox_mutex); return rc; } @@ -385,6 +389,7 @@ static int cxl_pci_mbox_send(struct cxl_memdev_state *mds, static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail) { struct cxl_dev_state *cxlds = &mds->cxlds; + struct cxl_mailbox *cxl_mbox = &cxlds->cxl_mbox; const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET); struct device *dev = cxlds->dev; unsigned long timeout; @@ -417,8 +422,8 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail) return -ETIMEDOUT; } - mds->mbox_send = cxl_pci_mbox_send; - mds->payload_size = + cxl_mbox->mbox_send = cxl_pci_mbox_send; + cxl_mbox->payload_size = 1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap); /* @@ -428,16 +433,15 @@ static int cxl_pci_setup_mailbox(struct cxl_memdev_state *mds, bool irq_avail) * there's no point in going forward. If the size is too large, there's * no harm is soft limiting it. */ - mds->payload_size = min_t(size_t, mds->payload_size, SZ_1M); - if (mds->payload_size < 256) { + cxl_mbox->payload_size = min_t(size_t, cxl_mbox->payload_size, SZ_1M); + if (cxl_mbox->payload_size < 256) { dev_err(dev, "Mailbox is too small (%zub)", - mds->payload_size); + cxl_mbox->payload_size); return -ENXIO; } - dev_dbg(dev, "Mailbox payload sized %zu", mds->payload_size); + dev_dbg(dev, "Mailbox payload sized %zu", cxl_mbox->payload_size); - rcuwait_init(&mds->mbox_wait); INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mbox_sanitize_work); /* background command interrupts are optional */ @@ -473,7 +477,6 @@ static bool is_cxl_restricted(struct pci_dev *pdev) static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev, struct cxl_register_map *map) { - struct cxl_port *port; struct cxl_dport *dport; resource_size_t component_reg_phys; @@ -482,14 +485,12 @@ static int cxl_rcrb_get_comp_regs(struct pci_dev *pdev, .resource = CXL_RESOURCE_NONE, }; - port = cxl_pci_find_port(pdev, &dport); + struct cxl_port *port __free(put_cxl_port) = + cxl_pci_find_port(pdev, &dport); if (!port) return -EPROBE_DEFER; component_reg_phys = cxl_rcd_component_reg_phys(&pdev->dev, dport); - - put_device(&port->dev); - if (component_reg_phys == CXL_RESOURCE_NONE) return -ENXIO; @@ -578,9 +579,10 @@ static void free_event_buf(void *buf) */ static int cxl_mem_alloc_event_buf(struct cxl_memdev_state *mds) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_get_event_payload *buf; - buf = kvmalloc(mds->payload_size, GFP_KERNEL); + buf = kvmalloc(cxl_mbox->payload_size, GFP_KERNEL); if (!buf) return -ENOMEM; mds->event.buf = buf; @@ -653,6 +655,7 @@ static int cxl_event_req_irq(struct cxl_dev_state *cxlds, u8 setting) static int cxl_event_get_int_policy(struct cxl_memdev_state *mds, struct cxl_event_interrupt_policy *policy) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_cmd mbox_cmd = { .opcode = CXL_MBOX_OP_GET_EVT_INT_POLICY, .payload_out = policy, @@ -660,7 +663,7 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds, }; int rc; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) dev_err(mds->cxlds.dev, "Failed to get event interrupt policy : %d", rc); @@ -671,6 +674,7 @@ static int cxl_event_get_int_policy(struct cxl_memdev_state *mds, static int cxl_event_config_msgnums(struct cxl_memdev_state *mds, struct cxl_event_interrupt_policy *policy) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -687,7 +691,7 @@ static int cxl_event_config_msgnums(struct cxl_memdev_state *mds, .size_in = sizeof(*policy), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) { dev_err(mds->cxlds.dev, "Failed to set event interrupt policy : %d", rc); @@ -786,6 +790,23 @@ static int cxl_event_config(struct pci_host_bridge *host_bridge, return 0; } +static int cxl_pci_type3_init_mailbox(struct cxl_dev_state *cxlds) +{ + int rc; + + /* + * Fail the init if there's no mailbox. For a type3 this is out of spec. + */ + if (!cxlds->reg_map.device_map.mbox.valid) + return -ENODEV; + + rc = cxl_mailbox_init(&cxlds->cxl_mbox, cxlds->dev); + if (rc) + return rc; + + return 0; +} + static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus); @@ -846,6 +867,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) dev_dbg(&pdev->dev, "Failed to map RAS capability.\n"); + rc = cxl_pci_type3_init_mailbox(cxlds); + if (rc) + return rc; + rc = cxl_await_media_ready(cxlds); if (rc == 0) cxlds->media_ready = true; diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 4ef93da22335..a6538a5f5c9f 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -102,13 +102,15 @@ static int cxl_pmem_get_config_size(struct cxl_memdev_state *mds, struct nd_cmd_get_config_size *cmd, unsigned int buf_len) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; + if (sizeof(*cmd) > buf_len) return -EINVAL; *cmd = (struct nd_cmd_get_config_size){ .config_size = mds->lsa_size, .max_xfer = - mds->payload_size - sizeof(struct cxl_mbox_set_lsa), + cxl_mbox->payload_size - sizeof(struct cxl_mbox_set_lsa), }; return 0; @@ -118,6 +120,7 @@ static int cxl_pmem_get_config_data(struct cxl_memdev_state *mds, struct nd_cmd_get_config_data_hdr *cmd, unsigned int buf_len) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_lsa get_lsa; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -139,7 +142,7 @@ static int cxl_pmem_get_config_data(struct cxl_memdev_state *mds, .payload_out = cmd->out_buf, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); cmd->status = 0; return rc; @@ -149,6 +152,7 @@ static int cxl_pmem_set_config_data(struct cxl_memdev_state *mds, struct nd_cmd_set_config_hdr *cmd, unsigned int buf_len) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_set_lsa *set_lsa; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -175,7 +179,7 @@ static int cxl_pmem_set_config_data(struct cxl_memdev_state *mds, .size_in = struct_size(set_lsa, data, cmd->in_length), }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); /* * Set "firmware" status (4-packed bytes at the end of the input @@ -233,15 +237,13 @@ static int detach_nvdimm(struct device *dev, void *data) if (!is_cxl_nvdimm(dev)) return 0; - device_lock(dev); - if (!dev->driver) - goto out; - - cxl_nvd = to_cxl_nvdimm(dev); - if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) - release = true; -out: - device_unlock(dev); + scoped_guard(device, dev) { + if (dev->driver) { + cxl_nvd = to_cxl_nvdimm(dev); + if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) + release = true; + } + } if (release) device_release_driver(dev); return 0; diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index d7d5d982ce69..861dde65768f 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -98,7 +98,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) struct cxl_port *root; int rc; - rc = cxl_dvsec_rr_decode(cxlds->dev, cxlds->cxl_dvsec, &info); + rc = cxl_dvsec_rr_decode(cxlds->dev, port, &info); if (rc < 0) return rc; diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index 21856a3f408e..452d1a9b9148 100644 --- a/drivers/cxl/security.c +++ b/drivers/cxl/security.c @@ -14,6 +14,7 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); unsigned long security_flags = 0; struct cxl_get_security_output { @@ -29,7 +30,7 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm, .payload_out = &out, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return 0; @@ -70,7 +71,7 @@ static int cxl_pmem_security_change_key(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_cmd mbox_cmd; struct cxl_set_pass set_pass; @@ -87,7 +88,7 @@ static int cxl_pmem_security_change_key(struct nvdimm *nvdimm, .payload_in = &set_pass, }; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } static int __cxl_pmem_security_disable(struct nvdimm *nvdimm, @@ -96,7 +97,7 @@ static int __cxl_pmem_security_disable(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_disable_pass dis_pass; struct cxl_mbox_cmd mbox_cmd; @@ -112,7 +113,7 @@ static int __cxl_pmem_security_disable(struct nvdimm *nvdimm, .payload_in = &dis_pass, }; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } static int cxl_pmem_security_disable(struct nvdimm *nvdimm, @@ -131,12 +132,12 @@ static int cxl_pmem_security_freeze(struct nvdimm *nvdimm) { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_cmd mbox_cmd = { .opcode = CXL_MBOX_OP_FREEZE_SECURITY, }; - return cxl_internal_send_cmd(mds, &mbox_cmd); + return cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); } static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, @@ -144,7 +145,7 @@ static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; u8 pass[NVDIMM_PASSPHRASE_LEN]; struct cxl_mbox_cmd mbox_cmd; int rc; @@ -156,7 +157,7 @@ static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, .payload_in = pass, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; @@ -169,7 +170,7 @@ static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm, { struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; - struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); + struct cxl_mailbox *cxl_mbox = &cxlmd->cxlds->cxl_mbox; struct cxl_mbox_cmd mbox_cmd; struct cxl_pass_erase erase; int rc; @@ -185,7 +186,7 @@ static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm, .payload_in = &erase, }; - rc = cxl_internal_send_cmd(mds, &mbox_cmd); + rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd); if (rc < 0) return rc; diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 518eaa073b2b..b360dca2c69e 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1911,7 +1911,6 @@ static __poll_t fw_device_op_poll(struct file *file, poll_table * pt) const struct file_operations fw_device_ops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = fw_device_op_open, .read = fw_device_op_read, .unlocked_ioctl = fw_device_op_ioctl, diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 69c15135371c..88c5c4ff4bb6 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2886,7 +2886,6 @@ static ssize_t reset_all_on_write(struct file *filp, const char __user *buf, static const struct file_operations fops_reset_counts = { .owner = THIS_MODULE, .open = simple_open, - .llseek = no_llseek, .write = reset_all_on_write, }; diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index 130d13e9cd6b..9e89a6a763da 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -950,7 +950,6 @@ static const struct file_operations scmi_dbg_raw_mode_reset_fops = { .open = scmi_dbg_raw_mode_open, .release = scmi_dbg_raw_mode_release, .write = scmi_dbg_raw_mode_reset_write, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -960,7 +959,6 @@ static const struct file_operations scmi_dbg_raw_mode_message_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_write, .poll = scmi_dbg_raw_mode_message_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -977,7 +975,6 @@ static const struct file_operations scmi_dbg_raw_mode_message_async_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_async_write, .poll = scmi_dbg_raw_mode_message_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1001,7 +998,6 @@ static const struct file_operations scmi_dbg_raw_mode_notification_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_notif_read, .poll = scmi_test_dbg_raw_mode_notif_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1025,7 +1021,6 @@ static const struct file_operations scmi_dbg_raw_mode_errors_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_errors_read, .poll = scmi_test_dbg_raw_mode_errors_poll, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 97bafb5f7038..0c17bdd388e1 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -309,7 +309,6 @@ static const struct file_operations efi_capsule_fops = { .open = efi_capsule_open, .write = efi_capsule_write, .release = efi_capsule_release, - .llseek = no_llseek, }; static struct miscdevice efi_capsule_misc = { diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c index 47d67bb0a516..9e2628728aad 100644 --- a/drivers/firmware/efi/test/efi_test.c +++ b/drivers/firmware/efi/test/efi_test.c @@ -750,7 +750,6 @@ static const struct file_operations efi_test_fops = { .unlocked_ioctl = efi_test_ioctl, .open = efi_test_open, .release = efi_test_close, - .llseek = no_llseek, }; static struct miscdevice efi_test_dev = { diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index 525ebdc7ded5..f3bc0d427825 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -386,7 +386,6 @@ static const struct file_operations do_sign_fops = { .open = rwtm_debug_open, .read = do_sign_read, .write = do_sign_write, - .llseek = no_llseek, }; static void rwtm_debugfs_release(void *root) diff --git a/drivers/gnss/core.c b/drivers/gnss/core.c index 48f2ee0f78c4..883ef86ad3fc 100644 --- a/drivers/gnss/core.c +++ b/drivers/gnss/core.c @@ -206,7 +206,6 @@ static const struct file_operations gnss_fops = { .read = gnss_read, .write = gnss_write, .poll = gnss_poll, - .llseek = no_llseek, }; static struct class *gnss_class; diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index 455eecf6380e..d39c6618bade 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -347,7 +347,6 @@ static const struct file_operations gpio_mockup_debugfs_ops = { .open = gpio_mockup_debugfs_open, .read = gpio_mockup_debugfs_read, .write = gpio_mockup_debugfs_write, - .llseek = no_llseek, .release = single_release, }; diff --git a/drivers/gpio/gpio-sloppy-logic-analyzer.c b/drivers/gpio/gpio-sloppy-logic-analyzer.c index aed6d1f6cfc3..07e0d7180579 100644 --- a/drivers/gpio/gpio-sloppy-logic-analyzer.c +++ b/drivers/gpio/gpio-sloppy-logic-analyzer.c @@ -217,7 +217,6 @@ static const struct file_operations fops_trigger = { .owner = THIS_MODULE, .open = trigger_open, .write = trigger_write, - .llseek = no_llseek, .release = single_release, }; diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 5aac59de0d76..78c9d9ed3d68 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2842,7 +2842,6 @@ static const struct file_operations gpio_fileops = { .poll = lineinfo_watch_poll, .read = lineinfo_watch_read, .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = gpio_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = gpio_ioctl_compat, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dcd59040c449..9b1e0ede05a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1083,10 +1083,6 @@ struct amdgpu_device { struct amdgpu_virt virt; - /* link all shadow bo */ - struct list_head shadow_list; - struct mutex shadow_list_lock; - /* record hw reset is performed */ bool has_hw_reset; u8 reset_magic[AMDGPU_RESET_MAGIC_NUM]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c index 57bda66e85ef..2ca127173135 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c @@ -511,7 +511,7 @@ static int __aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *h return -EINVAL; } - /* udpate aca bank to aca source error_cache first */ + /* update aca bank to aca source error_cache first */ ret = aca_banks_update(adev, smu_type, handler_aca_log_bank_error, qctx, NULL); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index 1254a43ec96b..3bc0cbf45bc5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -950,28 +950,30 @@ static void unlock_spi_csq_mutexes(struct amdgpu_device *adev) * @inst: xcc's instance number on a multi-XCC setup */ static void get_wave_count(struct amdgpu_device *adev, int queue_idx, - int *wave_cnt, int *vmid, uint32_t inst) + struct kfd_cu_occupancy *queue_cnt, uint32_t inst) { int pipe_idx; int queue_slot; unsigned int reg_val; - + unsigned int wave_cnt; /* * Program GRBM with appropriate MEID, PIPEID, QUEUEID and VMID * parameters to read out waves in flight. Get VMID if there are * non-zero waves in flight. */ - *vmid = 0xFF; - *wave_cnt = 0; pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe; queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe; - soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0, inst); - reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, inst, mmSPI_CSQ_WF_ACTIVE_COUNT_0) + - queue_slot); - *wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; - if (*wave_cnt != 0) - *vmid = (RREG32_SOC15(GC, inst, mmCP_HQD_VMID) & - CP_HQD_VMID__VMID_MASK) >> CP_HQD_VMID__VMID__SHIFT; + soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0, GET_INST(GC, inst)); + reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, GET_INST(GC, inst), + mmSPI_CSQ_WF_ACTIVE_COUNT_0) + queue_slot); + wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; + if (wave_cnt != 0) { + queue_cnt->wave_cnt += wave_cnt; + queue_cnt->doorbell_off = + (RREG32_SOC15(GC, GET_INST(GC, inst), mmCP_HQD_PQ_DOORBELL_CONTROL) & + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET_MASK) >> + CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_OFFSET__SHIFT; + } } /** @@ -981,9 +983,8 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx, * or more queues running and submitting waves to compute units. * * @adev: Handle of device from which to get number of waves in flight - * @pasid: Identifies the process for which this query call is invoked - * @pasid_wave_cnt: Output parameter updated with number of waves in flight that - * belong to process with given pasid + * @cu_occupancy: Array that gets filled with wave_cnt and doorbell offset + * for comparison later. * @max_waves_per_cu: Output parameter updated with maximum number of waves * possible per Compute Unit * @inst: xcc's instance number on a multi-XCC setup @@ -1011,34 +1012,28 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx, * number of waves that are in flight for the queue at specified index. The * index ranges from 0 to 7. * - * If non-zero waves are in flight, read CP_HQD_VMID register to obtain VMID - * of the wave(s). + * If non-zero waves are in flight, store the corresponding doorbell offset + * of the queue, along with the wave count. * - * Determine if VMID from above step maps to pasid provided as parameter. If - * it matches agrregate the wave count. That the VMID will not match pasid is - * a normal condition i.e. a device is expected to support multiple queues - * from multiple proceses. + * Determine if the queue belongs to the process by comparing the doorbell + * offset against the process's queues. If it matches, aggregate the wave + * count for the process. * * Reading registers referenced above involves programming GRBM appropriately */ -void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid, - int *pasid_wave_cnt, int *max_waves_per_cu, uint32_t inst) +void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst) { int qidx; - int vmid; int se_idx; - int sh_idx; int se_cnt; - int sh_cnt; - int wave_cnt; int queue_map; - int pasid_tmp; int max_queue_cnt; - int vmid_wave_cnt = 0; DECLARE_BITMAP(cp_queue_bitmap, AMDGPU_MAX_QUEUES); lock_spi_csq_mutexes(adev); - soc15_grbm_select(adev, 1, 0, 0, 0, inst); + soc15_grbm_select(adev, 1, 0, 0, 0, GET_INST(GC, inst)); /* * Iterate through the shader engines and arrays of the device @@ -1048,51 +1043,38 @@ void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid, AMDGPU_MAX_QUEUES); max_queue_cnt = adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - sh_cnt = adev->gfx.config.max_sh_per_se; se_cnt = adev->gfx.config.max_shader_engines; for (se_idx = 0; se_idx < se_cnt; se_idx++) { - for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) { + amdgpu_gfx_select_se_sh(adev, se_idx, 0, 0xffffffff, inst); + queue_map = RREG32_SOC15(GC, GET_INST(GC, inst), mmSPI_CSQ_WF_ACTIVE_STATUS); + + /* + * Assumption: queue map encodes following schema: four + * pipes per each micro-engine, with each pipe mapping + * eight queues. This schema is true for GFX9 devices + * and must be verified for newer device families + */ + for (qidx = 0; qidx < max_queue_cnt; qidx++) { + /* Skip qeueus that are not associated with + * compute functions + */ + if (!test_bit(qidx, cp_queue_bitmap)) + continue; - amdgpu_gfx_select_se_sh(adev, se_idx, sh_idx, 0xffffffff, inst); - queue_map = RREG32_SOC15(GC, inst, mmSPI_CSQ_WF_ACTIVE_STATUS); + if (!(queue_map & (1 << qidx))) + continue; - /* - * Assumption: queue map encodes following schema: four - * pipes per each micro-engine, with each pipe mapping - * eight queues. This schema is true for GFX9 devices - * and must be verified for newer device families - */ - for (qidx = 0; qidx < max_queue_cnt; qidx++) { - - /* Skip qeueus that are not associated with - * compute functions - */ - if (!test_bit(qidx, cp_queue_bitmap)) - continue; - - if (!(queue_map & (1 << qidx))) - continue; - - /* Get number of waves in flight and aggregate them */ - get_wave_count(adev, qidx, &wave_cnt, &vmid, - inst); - if (wave_cnt != 0) { - pasid_tmp = - RREG32(SOC15_REG_OFFSET(OSSSYS, inst, - mmIH_VMID_0_LUT) + vmid); - if (pasid_tmp == pasid) - vmid_wave_cnt += wave_cnt; - } - } + /* Get number of waves in flight and aggregate them */ + get_wave_count(adev, qidx, &cu_occupancy[qidx], + inst); } } amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, inst); - soc15_grbm_select(adev, 0, 0, 0, 0, inst); + soc15_grbm_select(adev, 0, 0, 0, 0, GET_INST(GC, inst)); unlock_spi_csq_mutexes(adev); /* Update the output parameters and return */ - *pasid_wave_cnt = vmid_wave_cnt; *max_waves_per_cu = adev->gfx.cu_info.simd_per_cu * adev->gfx.cu_info.max_waves_per_simd; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h index 988c50ac3be0..b6a91a552aa4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h @@ -52,8 +52,9 @@ bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct amdgpu_device *adev, uint8_t vmid, uint16_t *p_pasid); void kgd_gfx_v9_set_vm_context_page_table_base(struct amdgpu_device *adev, uint32_t vmid, uint64_t page_table_base); -void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid, - int *pasid_wave_cnt, int *max_waves_per_cu, uint32_t inst); +void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst); void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev, uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr, uint32_t inst); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 4afef5b46c7d..ce5ca304dba9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1499,7 +1499,7 @@ static int amdgpu_amdkfd_gpuvm_pin_bo(struct amdgpu_bo *bo, u32 domain) } } - ret = amdgpu_bo_pin_restricted(bo, domain, 0, 0); + ret = amdgpu_bo_pin(bo, domain); if (ret) pr_err("Error in Pinning BO to domain: %d\n", domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 42e64bce661e..45affc02548c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -87,8 +87,9 @@ static bool check_atom_bios(uint8_t *bios, size_t size) * part of the system bios. On boot, the system bios puts a * copy of the igp rom at the start of vram if a discrete card is * present. + * For SR-IOV, the vbios image is also put in VRAM in the VF. */ -static bool igp_read_bios_from_vram(struct amdgpu_device *adev) +static bool amdgpu_read_bios_from_vram(struct amdgpu_device *adev) { uint8_t __iomem *bios; resource_size_t vram_base; @@ -284,10 +285,6 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) acpi_status status; bool found = false; - /* ATRM is for the discrete card only */ - if (adev->flags & AMD_IS_APU) - return false; - /* ATRM is for on-platform devices only */ if (dev_is_removable(&adev->pdev->dev)) return false; @@ -343,11 +340,8 @@ static inline bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) static bool amdgpu_read_disabled_bios(struct amdgpu_device *adev) { - if (adev->flags & AMD_IS_APU) - return igp_read_bios_from_vram(adev); - else - return (!adev->asic_funcs || !adev->asic_funcs->read_disabled_bios) ? - false : amdgpu_asic_read_disabled_bios(adev); + return (!adev->asic_funcs || !adev->asic_funcs->read_disabled_bios) ? + false : amdgpu_asic_read_disabled_bios(adev); } #ifdef CONFIG_ACPI @@ -414,7 +408,36 @@ static inline bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev) } #endif -bool amdgpu_get_bios(struct amdgpu_device *adev) +static bool amdgpu_get_bios_apu(struct amdgpu_device *adev) +{ + if (amdgpu_acpi_vfct_bios(adev)) { + dev_info(adev->dev, "Fetched VBIOS from VFCT\n"); + goto success; + } + + if (amdgpu_read_bios_from_vram(adev)) { + dev_info(adev->dev, "Fetched VBIOS from VRAM BAR\n"); + goto success; + } + + if (amdgpu_read_bios(adev)) { + dev_info(adev->dev, "Fetched VBIOS from ROM BAR\n"); + goto success; + } + + if (amdgpu_read_platform_bios(adev)) { + dev_info(adev->dev, "Fetched VBIOS from platform\n"); + goto success; + } + + dev_err(adev->dev, "Unable to locate a BIOS ROM\n"); + return false; + +success: + return true; +} + +static bool amdgpu_get_bios_dgpu(struct amdgpu_device *adev) { if (amdgpu_atrm_get_bios(adev)) { dev_info(adev->dev, "Fetched VBIOS from ATRM\n"); @@ -426,7 +449,8 @@ bool amdgpu_get_bios(struct amdgpu_device *adev) goto success; } - if (igp_read_bios_from_vram(adev)) { + /* this is required for SR-IOV */ + if (amdgpu_read_bios_from_vram(adev)) { dev_info(adev->dev, "Fetched VBIOS from VRAM BAR\n"); goto success; } @@ -455,10 +479,24 @@ bool amdgpu_get_bios(struct amdgpu_device *adev) return false; success: - adev->is_atom_fw = adev->asic_type >= CHIP_VEGA10; return true; } +bool amdgpu_get_bios(struct amdgpu_device *adev) +{ + bool found; + + if (adev->flags & AMD_IS_APU) + found = amdgpu_get_bios_apu(adev); + else + found = amdgpu_get_bios_dgpu(adev); + + if (found) + adev->is_atom_fw = adev->asic_type >= CHIP_VEGA10; + + return found; +} + /* helper function for soc15 and onwards to read bios from rom */ bool amdgpu_soc15_read_bios_from_rom(struct amdgpu_device *adev, u8 *bios, u32 length_bytes) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f4628412dac4..c2394c8b4d6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4107,9 +4107,6 @@ int amdgpu_device_init(struct amdgpu_device *adev, spin_lock_init(&adev->mm_stats.lock); spin_lock_init(&adev->wb.lock); - INIT_LIST_HEAD(&adev->shadow_list); - mutex_init(&adev->shadow_list_lock); - INIT_LIST_HEAD(&adev->reset_list); INIT_LIST_HEAD(&adev->ras_list); @@ -5030,80 +5027,6 @@ static int amdgpu_device_ip_post_soft_reset(struct amdgpu_device *adev) } /** - * amdgpu_device_recover_vram - Recover some VRAM contents - * - * @adev: amdgpu_device pointer - * - * Restores the contents of VRAM buffers from the shadows in GTT. Used to - * restore things like GPUVM page tables after a GPU reset where - * the contents of VRAM might be lost. - * - * Returns: - * 0 on success, negative error code on failure. - */ -static int amdgpu_device_recover_vram(struct amdgpu_device *adev) -{ - struct dma_fence *fence = NULL, *next = NULL; - struct amdgpu_bo *shadow; - struct amdgpu_bo_vm *vmbo; - long r = 1, tmo; - - if (amdgpu_sriov_runtime(adev)) - tmo = msecs_to_jiffies(8000); - else - tmo = msecs_to_jiffies(100); - - dev_info(adev->dev, "recover vram bo from shadow start\n"); - mutex_lock(&adev->shadow_list_lock); - list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { - /* If vm is compute context or adev is APU, shadow will be NULL */ - if (!vmbo->shadow) - continue; - shadow = vmbo->shadow; - - /* No need to recover an evicted BO */ - if (!shadow->tbo.resource || - shadow->tbo.resource->mem_type != TTM_PL_TT || - shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || - shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) - continue; - - r = amdgpu_bo_restore_shadow(shadow, &next); - if (r) - break; - - if (fence) { - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - fence = next; - if (tmo == 0) { - r = -ETIMEDOUT; - break; - } else if (tmo < 0) { - r = tmo; - break; - } - } else { - fence = next; - } - } - mutex_unlock(&adev->shadow_list_lock); - - if (fence) - tmo = dma_fence_wait_timeout(fence, false, tmo); - dma_fence_put(fence); - - if (r < 0 || tmo <= 0) { - dev_err(adev->dev, "recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo); - return -EIO; - } - - dev_info(adev->dev, "recover vram bo from shadow done\n"); - return 0; -} - - -/** * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf * * @adev: amdgpu_device pointer @@ -5165,12 +5088,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, if (r) return r; - if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { + if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) amdgpu_inc_vram_lost(adev); - r = amdgpu_device_recover_vram(adev); - } - if (r) - return r; /* need to be called during full access so we can't do it later like * bare-metal does. @@ -5569,9 +5488,7 @@ out: } } - if (!r) - r = amdgpu_device_recover_vram(tmp_adev); - else + if (r) tmp_adev->asic_reset_res = r; } @@ -6189,7 +6106,7 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev, p2p_addressable = !(adev->gmc.aper_base & address_mask || aper_limit & address_mask); } - return is_large_bar && p2p_access && p2p_addressable; + return pcie_p2p && is_large_bar && p2p_access && p2p_addressable; #else return false; #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 092ec11258cd..b119d27271c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -233,6 +233,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, } if (!adev->enable_virtual_display) { + new_abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev, new_abo->flags)); if (unlikely(r != 0)) { @@ -1474,7 +1475,7 @@ bool amdgpu_display_crtc_scaling_mode_fixup(struct drm_crtc *crtc, if ((!(mode->flags & DRM_MODE_FLAG_INTERLACE)) && ((amdgpu_encoder->underscan_type == UNDERSCAN_ON) || ((amdgpu_encoder->underscan_type == UNDERSCAN_AUTO) && - connector->display_info.is_hdmi && + connector && connector->display_info.is_hdmi && amdgpu_display_is_hdtv_mode(mode)))) { if (amdgpu_encoder->underscan_hborder != 0) amdgpu_crtc->h_border = amdgpu_encoder->underscan_hborder; @@ -1759,6 +1760,7 @@ int amdgpu_display_resume_helper(struct amdgpu_device *adev) r = amdgpu_bo_reserve(aobj, true); if (r == 0) { + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); if (r != 0) dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f57411ed2dc2..81d9877c8735 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -117,9 +117,10 @@ * - 3.56.0 - Update IB start address and size alignment for decode and encode * - 3.57.0 - Compute tunneling on GFX10+ * - 3.58.0 - Add GFX12 DCC support + * - 3.59.0 - Cleared VRAM */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 58 +#define KMS_DRIVER_MINOR 59 #define KMS_DRIVER_PATCHLEVEL 0 /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 0e617dff8765..1a5df8b94661 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -43,8 +43,6 @@ #include "amdgpu_hmm.h" #include "amdgpu_xgmi.h" -static const struct drm_gem_object_funcs amdgpu_gem_object_funcs; - static vm_fault_t amdgpu_gem_fault(struct vm_fault *vmf) { struct ttm_buffer_object *bo = vmf->vma->vm_private_data; @@ -87,11 +85,11 @@ static const struct vm_operations_struct amdgpu_gem_vm_ops = { static void amdgpu_gem_object_free(struct drm_gem_object *gobj) { - struct amdgpu_bo *robj = gem_to_amdgpu_bo(gobj); + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(gobj); - if (robj) { - amdgpu_hmm_unregister(robj); - amdgpu_bo_unref(&robj); + if (aobj) { + amdgpu_hmm_unregister(aobj); + ttm_bo_put(&aobj->tbo); } } @@ -126,7 +124,6 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, bo = &ubo->bo; *obj = &bo->tbo.base; - (*obj)->funcs = &amdgpu_gem_object_funcs; return 0; } @@ -295,7 +292,7 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str return drm_gem_ttm_mmap(obj, vma); } -static const struct drm_gem_object_funcs amdgpu_gem_object_funcs = { +const struct drm_gem_object_funcs amdgpu_gem_object_funcs = { .free = amdgpu_gem_object_free, .open = amdgpu_gem_object_open, .close = amdgpu_gem_object_close, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h index f30264782ba2..3a8f57900a3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h @@ -33,6 +33,8 @@ #define AMDGPU_GEM_DOMAIN_MAX 0x3 #define gem_to_amdgpu_bo(gobj) container_of((gobj), struct amdgpu_bo, tbo.base) +extern const struct drm_gem_object_funcs amdgpu_gem_object_funcs; + unsigned long amdgpu_gem_timeout(uint64_t timeout_ns); /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index ad6bf5d4e0a9..16f2605ac50b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -107,8 +107,11 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) /* * Do the coredump immediately after a job timeout to get a very * close dump/snapshot/representation of GPU's current error status + * Skip it for SRIOV, since VF FLR will be triggered by host driver + * before job timeout */ - amdgpu_job_core_dump(adev, job); + if (!amdgpu_sriov_vf(adev)) + amdgpu_job_core_dump(adev, job); if (amdgpu_gpu_recovery && amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e32161f6b67a..44819cdba7fb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -77,24 +77,6 @@ static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo) amdgpu_bo_destroy(tbo); } -static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); - struct amdgpu_bo *shadow_bo = ttm_to_amdgpu_bo(tbo), *bo; - struct amdgpu_bo_vm *vmbo; - - bo = shadow_bo->parent; - vmbo = to_amdgpu_bo_vm(bo); - /* in case amdgpu_device_recover_vram got NULL of bo->parent */ - if (!list_empty(&vmbo->shadow_list)) { - mutex_lock(&adev->shadow_list_lock); - list_del_init(&vmbo->shadow_list); - mutex_unlock(&adev->shadow_list_lock); - } - - amdgpu_bo_destroy(tbo); -} - /** * amdgpu_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo * @bo: buffer object to be checked @@ -108,8 +90,7 @@ static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo) { if (bo->destroy == &amdgpu_bo_destroy || - bo->destroy == &amdgpu_bo_user_destroy || - bo->destroy == &amdgpu_bo_vm_destroy) + bo->destroy == &amdgpu_bo_user_destroy) return true; return false; @@ -583,6 +564,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (bo == NULL) return -ENOMEM; drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size); + bo->tbo.base.funcs = &amdgpu_gem_object_funcs; bo->vm_bo = NULL; bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain : bp->domain; @@ -723,52 +705,6 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev, } /** - * amdgpu_bo_add_to_shadow_list - add a BO to the shadow list - * - * @vmbo: BO that will be inserted into the shadow list - * - * Insert a BO to the shadow list. - */ -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(vmbo->bo.tbo.bdev); - - mutex_lock(&adev->shadow_list_lock); - list_add_tail(&vmbo->shadow_list, &adev->shadow_list); - vmbo->shadow->parent = amdgpu_bo_ref(&vmbo->bo); - vmbo->shadow->tbo.destroy = &amdgpu_bo_vm_destroy; - mutex_unlock(&adev->shadow_list_lock); -} - -/** - * amdgpu_bo_restore_shadow - restore an &amdgpu_bo shadow - * - * @shadow: &amdgpu_bo shadow to be restored - * @fence: dma_fence associated with the operation - * - * Copies a buffer object's shadow content back to the object. - * This is used for recovering a buffer from its shadow in case of a gpu - * reset where vram context may be lost. - * - * Returns: - * 0 for success or a negative error code on failure. - */ -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence) - -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(shadow->tbo.bdev); - struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring; - uint64_t shadow_addr, parent_addr; - - shadow_addr = amdgpu_bo_gpu_offset(shadow); - parent_addr = amdgpu_bo_gpu_offset(shadow->parent); - - return amdgpu_copy_buffer(ring, shadow_addr, parent_addr, - amdgpu_bo_size(shadow), NULL, fence, - true, false, 0); -} - -/** * amdgpu_bo_kmap - map an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be mapped * @ptr: kernel virtual address to be returned @@ -851,7 +787,7 @@ struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo) if (bo == NULL) return NULL; - ttm_bo_get(&bo->tbo); + drm_gem_object_get(&bo->tbo.base); return bo; } @@ -863,40 +799,30 @@ struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo) */ void amdgpu_bo_unref(struct amdgpu_bo **bo) { - struct ttm_buffer_object *tbo; - if ((*bo) == NULL) return; - tbo = &((*bo)->tbo); - ttm_bo_put(tbo); + drm_gem_object_put(&(*bo)->tbo.base); *bo = NULL; } /** - * amdgpu_bo_pin_restricted - pin an &amdgpu_bo buffer object + * amdgpu_bo_pin - pin an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be pinned * @domain: domain to be pinned to - * @min_offset: the start of requested address range - * @max_offset: the end of requested address range * - * Pins the buffer object according to requested domain and address range. If - * the memory is unbound gart memory, binds the pages into gart table. Adjusts - * pin_count and pin_size accordingly. + * Pins the buffer object according to requested domain. If the memory is + * unbound gart memory, binds the pages into gart table. Adjusts pin_count and + * pin_size accordingly. * * Pinning means to lock pages in memory along with keeping them at a fixed * offset. It is required when a buffer can not be moved, for example, when * a display buffer is being scanned out. * - * Compared with amdgpu_bo_pin(), this function gives more flexibility on - * where to pin a buffer if there are specific restrictions on where a buffer - * must be located. - * * Returns: * 0 for success or a negative error code on failure. */ -int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, - u64 min_offset, u64 max_offset) +int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct ttm_operation_ctx ctx = { false, false }; @@ -905,9 +831,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) return -EPERM; - if (WARN_ON_ONCE(min_offset > max_offset)) - return -EINVAL; - /* Check domain to be pinned to against preferred domains */ if (bo->preferred_domains & domain) domain = bo->preferred_domains & domain; @@ -933,14 +856,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return -EINVAL; ttm_bo_pin(&bo->tbo); - - if (max_offset != 0) { - u64 domain_start = amdgpu_ttm_domain_start(adev, - mem_type); - WARN_ON_ONCE(max_offset < - (amdgpu_bo_gpu_offset(bo) - domain_start)); - } - return 0; } @@ -957,17 +872,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; amdgpu_bo_placement_from_domain(bo, domain); for (i = 0; i < bo->placement.num_placement; i++) { - unsigned int fpfn, lpfn; - - fpfn = min_offset >> PAGE_SHIFT; - lpfn = max_offset >> PAGE_SHIFT; - - if (fpfn > bo->placements[i].fpfn) - bo->placements[i].fpfn = fpfn; - if (!bo->placements[i].lpfn || - (lpfn && lpfn < bo->placements[i].lpfn)) - bo->placements[i].lpfn = lpfn; - if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && bo->placements[i].mem_type == TTM_PL_VRAM) bo->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; @@ -994,24 +898,6 @@ error: } /** - * amdgpu_bo_pin - pin an &amdgpu_bo buffer object - * @bo: &amdgpu_bo buffer object to be pinned - * @domain: domain to be pinned to - * - * A simple wrapper to amdgpu_bo_pin_restricted(). - * Provides a simpler API for buffers that do not have any strict restrictions - * on where a buffer must be located. - * - * Returns: - * 0 for success or a negative error code on failure. - */ -int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain) -{ - bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - return amdgpu_bo_pin_restricted(bo, domain, 0, 0); -} - -/** * amdgpu_bo_unpin - unpin an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be unpinned * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index d7e27957013f..717e47b46167 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -136,8 +136,6 @@ struct amdgpu_bo_user { struct amdgpu_bo_vm { struct amdgpu_bo bo; - struct amdgpu_bo *shadow; - struct list_head shadow_list; struct amdgpu_vm_bo_base entries[]; }; @@ -275,22 +273,6 @@ static inline bool amdgpu_bo_encrypted(struct amdgpu_bo *bo) return bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED; } -/** - * amdgpu_bo_shadowed - check if the BO is shadowed - * - * @bo: BO to be tested. - * - * Returns: - * NULL if not shadowed or else return a BO pointer. - */ -static inline struct amdgpu_bo *amdgpu_bo_shadowed(struct amdgpu_bo *bo) -{ - if (bo->tbo.type == ttm_bo_type_kernel) - return to_amdgpu_bo_vm(bo)->shadow; - - return NULL; -} - bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain); @@ -322,8 +304,6 @@ void amdgpu_bo_kunmap(struct amdgpu_bo *bo); struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo); void amdgpu_bo_unref(struct amdgpu_bo **bo); int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain); -int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, - u64 min_offset, u64 max_offset); void amdgpu_bo_unpin(struct amdgpu_bo *bo); int amdgpu_bo_init(struct amdgpu_device *adev); void amdgpu_bo_fini(struct amdgpu_device *adev); @@ -349,9 +329,6 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo); u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats); -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo); -int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, - struct dma_fence **fence); uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, uint32_t domain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 189574d53ebd..0b28b2cf1517 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2853,7 +2853,7 @@ static int psp_load_non_psp_fw(struct psp_context *psp) if (ret) return ret; - /* Start rlc autoload after psp recieved all the gfx firmware */ + /* Start rlc autoload after psp received all the gfx firmware */ if (psp->autoload_supported && ucode->ucode_id == (amdgpu_sriov_vf(adev) ? adev->virt.autoload_ucode_id : AMDGPU_UCODE_ID_RLC_G)) { ret = psp_rlc_autoload_start(psp); @@ -3425,9 +3425,11 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name) const struct psp_firmware_header_v1_2 *sos_hdr_v1_2; const struct psp_firmware_header_v1_3 *sos_hdr_v1_3; const struct psp_firmware_header_v2_0 *sos_hdr_v2_0; - int err = 0; + const struct psp_firmware_header_v2_1 *sos_hdr_v2_1; + int fw_index, fw_bin_count, start_index = 0; + const struct psp_fw_bin_desc *fw_bin; uint8_t *ucode_array_start_addr; - int fw_index = 0; + int err = 0; err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, "amdgpu/%s_sos.bin", chip_name); if (err) @@ -3478,15 +3480,30 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name) case 2: sos_hdr_v2_0 = (const struct psp_firmware_header_v2_0 *)adev->psp.sos_fw->data; - if (le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count) >= UCODE_MAX_PSP_PACKAGING) { + fw_bin_count = le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count); + + if (fw_bin_count >= UCODE_MAX_PSP_PACKAGING) { dev_err(adev->dev, "packed SOS count exceeds maximum limit\n"); err = -EINVAL; goto out; } - for (fw_index = 0; fw_index < le32_to_cpu(sos_hdr_v2_0->psp_fw_bin_count); fw_index++) { - err = parse_sos_bin_descriptor(psp, - &sos_hdr_v2_0->psp_fw_bin[fw_index], + if (sos_hdr_v2_0->header.header_version_minor == 1) { + sos_hdr_v2_1 = (const struct psp_firmware_header_v2_1 *)adev->psp.sos_fw->data; + + fw_bin = sos_hdr_v2_1->psp_fw_bin; + + if (psp_is_aux_sos_load_required(psp)) + start_index = le32_to_cpu(sos_hdr_v2_1->psp_aux_fw_bin_index); + else + fw_bin_count -= le32_to_cpu(sos_hdr_v2_1->psp_aux_fw_bin_index); + + } else { + fw_bin = sos_hdr_v2_0->psp_fw_bin; + } + + for (fw_index = start_index; fw_index < fw_bin_count; fw_index++) { + err = parse_sos_bin_descriptor(psp, fw_bin + fw_index, sos_hdr_v2_0); if (err) goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 74a96516c913..e8abbbcb4326 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -138,6 +138,7 @@ struct psp_funcs { int (*vbflash_stat)(struct psp_context *psp); int (*fatal_error_recovery_quirk)(struct psp_context *psp); bool (*get_ras_capability)(struct psp_context *psp); + bool (*is_aux_sos_load_required)(struct psp_context *psp); }; struct ta_funcs { @@ -464,6 +465,9 @@ struct amdgpu_psp_funcs { ((psp)->funcs->fatal_error_recovery_quirk ? \ (psp)->funcs->fatal_error_recovery_quirk((psp)) : 0) +#define psp_is_aux_sos_load_required(psp) \ + ((psp)->funcs->is_aux_sos_load_required ? (psp)->funcs->is_aux_sos_load_required((psp)) : 0) + extern const struct amd_ip_funcs psp_ip_funcs; extern const struct amdgpu_ip_block_version psp_v3_1_ip_block; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 61a2f386d9fb..1a1395c5fff1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -882,7 +882,7 @@ int amdgpu_ras_feature_enable_on_boot(struct amdgpu_device *adev, if (ret) return ret; - /* gfx block ras dsiable cmd must send to ras-ta */ + /* gfx block ras disable cmd must send to ras-ta */ if (head->block == AMDGPU_RAS_BLOCK__GFX) con->features |= BIT(head->block); @@ -3468,6 +3468,11 @@ init_ras_enabled_flag: /* aca is disabled by default */ adev->aca.is_enabled = false; + + /* bad page feature is not applicable to specific app platform */ + if (adev->gmc.is_app_apu && + amdgpu_ip_version(adev, UMC_HWIP, 0) == IP_VERSION(12, 0, 0)) + amdgpu_bad_page_threshold = 0; } static void amdgpu_ras_counte_dw(struct work_struct *work) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index aab8077e5098..f28f6b4ba765 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -58,7 +58,7 @@ #define EEPROM_I2C_MADDR_4 0x40000 /* - * The 2 macros bellow represent the actual size in bytes that + * The 2 macros below represent the actual size in bytes that * those entities occupy in the EEPROM memory. * RAS_TABLE_RECORD_SIZE is different than sizeof(eeprom_table_record) which * uses uint64 to store 6b fields such as retired_page. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index bdf1ef825d89..c586ab4c911b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -260,6 +260,36 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, return 0; } +/** + * amdgpu_sync_kfd - sync to KFD fences + * + * @sync: sync object to add KFD fences to + * @resv: reservation object with KFD fences + * + * Extract all KFD fences and add them to the sync object. + */ +int amdgpu_sync_kfd(struct amdgpu_sync *sync, struct dma_resv *resv) +{ + struct dma_resv_iter cursor; + struct dma_fence *f; + int r = 0; + + dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP); + dma_resv_for_each_fence_unlocked(&cursor, f) { + void *fence_owner = amdgpu_sync_get_owner(f); + + if (fence_owner != AMDGPU_FENCE_OWNER_KFD) + continue; + + r = amdgpu_sync_fence(sync, f); + if (r) + break; + } + dma_resv_iter_end(&cursor); + + return r; +} + /* Free the entry back to the slab */ static void amdgpu_sync_entry_free(struct amdgpu_sync_entry *e) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h index cf1e9e858efd..e3272dce798d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h @@ -51,6 +51,7 @@ int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f); int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, struct dma_resv *resv, enum amdgpu_sync_mode mode, void *owner); +int amdgpu_sync_kfd(struct amdgpu_sync *sync, struct dma_resv *resv); struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync, struct amdgpu_ring *ring); struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b8bc7fa8c375..74adb983ab03 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1970,7 +1970,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) DRM_INFO("amdgpu: %uM of GTT memory ready.\n", (unsigned int)(gtt_size / (1024 * 1024))); - /* Initiailize doorbell pool on PCI BAR */ + /* Initialize doorbell pool on PCI BAR */ r = amdgpu_ttm_init_on_chip(adev, AMDGPU_PL_DOORBELL, adev->doorbell.size / PAGE_SIZE); if (r) { DRM_ERROR("Failed initializing doorbell heap.\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 5bc37acd3981..4e23419b92d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -136,6 +136,14 @@ struct psp_firmware_header_v2_0 { struct psp_fw_bin_desc psp_fw_bin[]; }; +/* version_major=2, version_minor=1 */ +struct psp_firmware_header_v2_1 { + struct common_firmware_header header; + uint32_t psp_fw_bin_count; + uint32_t psp_aux_fw_bin_index; + struct psp_fw_bin_desc psp_fw_bin[]; +}; + /* version_major=1, version_minor=0 */ struct ta_firmware_header_v1_0 { struct common_firmware_header header; @@ -426,6 +434,7 @@ union amdgpu_firmware_header { struct psp_firmware_header_v1_1 psp_v1_1; struct psp_firmware_header_v1_3 psp_v1_3; struct psp_firmware_header_v2_0 psp_v2_0; + struct psp_firmware_header_v2_0 psp_v2_1; struct ta_firmware_header_v1_0 ta; struct ta_firmware_header_v2_0 ta_v2_0; struct gfx_firmware_header_v1_0 gfx; @@ -447,7 +456,7 @@ union amdgpu_firmware_header { uint8_t raw[0x100]; }; -#define UCODE_MAX_PSP_PACKAGING ((sizeof(union amdgpu_firmware_header) - sizeof(struct common_firmware_header) - 4) / sizeof(struct psp_fw_bin_desc)) +#define UCODE_MAX_PSP_PACKAGING (((sizeof(union amdgpu_firmware_header) - sizeof(struct common_firmware_header) - 4) / sizeof(struct psp_fw_bin_desc)) * 2) /* * fw loading support diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index e5f508d34ed8..d4c2afafbb73 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -338,6 +338,7 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane, else domain = AMDGPU_GEM_DOMAIN_VRAM; + rbo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(rbo, domain); if (unlikely(r != 0)) { if (r != -ERESTARTSYS) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 2452dfa6314f..6005280f5f38 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -465,7 +465,6 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, { uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm); struct amdgpu_vm_bo_base *bo_base; - struct amdgpu_bo *shadow; struct amdgpu_bo *bo; int r; @@ -486,16 +485,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, spin_unlock(&vm->status_lock); bo = bo_base->bo; - shadow = amdgpu_bo_shadowed(bo); r = validate(param, bo); if (r) return r; - if (shadow) { - r = validate(param, shadow); - if (r) - return r; - } if (bo->tbo.type != ttm_bo_type_kernel) { amdgpu_vm_bo_moved(bo_base); @@ -1176,6 +1169,12 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, AMDGPU_SYNC_EQ_OWNER, vm); if (r) goto error_free; + if (bo) { + r = amdgpu_sync_kfd(&sync, bo->tbo.base.resv); + if (r) + goto error_free; + } + } else { struct drm_gem_object *obj = &bo->tbo.base; @@ -2149,10 +2148,6 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, { struct amdgpu_vm_bo_base *bo_base; - /* shadow bo doesn't have bo base, its validation needs its parent */ - if (bo->parent && (amdgpu_bo_shadowed(bo->parent) == bo)) - bo = bo->parent; - for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; @@ -2482,7 +2477,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, root_bo = amdgpu_bo_ref(&root->bo); r = amdgpu_bo_reserve(root_bo, true); if (r) { - amdgpu_bo_unref(&root->shadow); amdgpu_bo_unref(&root_bo); goto error_free_delayed; } @@ -2575,11 +2569,6 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm) vm->last_update = dma_fence_get_stub(); vm->is_compute_context = true; - /* Free the shadow bo for compute VM */ - amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow); - - goto unreserve_bo; - unreserve_bo: amdgpu_bo_unreserve(vm->root.bo); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index a076f43097e4..f78a0434a48f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -383,14 +383,6 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) return r; - if (vmbo->shadow) { - struct amdgpu_bo *shadow = vmbo->shadow; - - r = ttm_bo_validate(&shadow->tbo, &shadow->placement, &ctx); - if (r) - return r; - } - if (!drm_dev_enter(adev_to_drm(adev), &idx)) return -ENODEV; @@ -448,10 +440,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id) { struct amdgpu_bo_param bp; - struct amdgpu_bo *bo; - struct dma_resv *resv; unsigned int num_entries; - int r; memset(&bp, 0, sizeof(bp)); @@ -484,42 +473,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (vm->root.bo) bp.resv = vm->root.bo->tbo.base.resv; - r = amdgpu_bo_create_vm(adev, &bp, vmbo); - if (r) - return r; - - bo = &(*vmbo)->bo; - if (vm->is_compute_context || (adev->flags & AMD_IS_APU)) { - (*vmbo)->shadow = NULL; - return 0; - } - - if (!bp.resv) - WARN_ON(dma_resv_lock(bo->tbo.base.resv, - NULL)); - resv = bp.resv; - memset(&bp, 0, sizeof(bp)); - bp.size = amdgpu_vm_pt_size(adev, level); - bp.domain = AMDGPU_GEM_DOMAIN_GTT; - bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC; - bp.type = ttm_bo_type_kernel; - bp.resv = bo->tbo.base.resv; - bp.bo_ptr_size = sizeof(struct amdgpu_bo); - bp.xcp_id_plus1 = xcp_id + 1; - - r = amdgpu_bo_create(adev, &bp, &(*vmbo)->shadow); - - if (!resv) - dma_resv_unlock(bo->tbo.base.resv); - - if (r) { - amdgpu_bo_unref(&bo); - return r; - } - - amdgpu_bo_add_to_shadow_list(*vmbo); - - return 0; + return amdgpu_bo_create_vm(adev, &bp, vmbo); } /** @@ -569,7 +523,6 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, return 0; error_free_pt: - amdgpu_bo_unref(&pt->shadow); amdgpu_bo_unref(&pt_bo); return r; } @@ -581,17 +534,10 @@ error_free_pt: */ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) { - struct amdgpu_bo *shadow; - if (!entry->bo) return; entry->bo->vm_bo = NULL; - shadow = amdgpu_bo_shadowed(entry->bo); - if (shadow) { - ttm_bo_set_bulk_move(&shadow->tbo, NULL); - amdgpu_bo_unref(&shadow); - } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); spin_lock(&entry->vm->status_lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 4772fba33285..46d9fb433ab2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -35,16 +35,7 @@ */ static int amdgpu_vm_sdma_map_table(struct amdgpu_bo_vm *table) { - int r; - - r = amdgpu_ttm_alloc_gart(&table->bo.tbo); - if (r) - return r; - - if (table->shadow) - r = amdgpu_ttm_alloc_gart(&table->shadow->tbo); - - return r; + return amdgpu_ttm_alloc_gart(&table->bo.tbo); } /* Allocate a new job for @count PTE updates */ @@ -265,17 +256,13 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, if (!p->pages_addr) { /* set page commands needed */ - if (vmbo->shadow) - amdgpu_vm_sdma_set_ptes(p, vmbo->shadow, pe, addr, - count, incr, flags); amdgpu_vm_sdma_set_ptes(p, bo, pe, addr, count, incr, flags); return 0; } /* copy commands needed */ - ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw * - (vmbo->shadow ? 2 : 1); + ndw -= p->adev->vm_manager.vm_pte_funcs->copy_pte_num_dw; /* for padding */ ndw -= 7; @@ -290,8 +277,6 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, pte[i] |= flags; } - if (vmbo->shadow) - amdgpu_vm_sdma_copy_ptes(p, vmbo->shadow, pe, nptes); amdgpu_vm_sdma_copy_ptes(p, bo, pe, nptes); pe += nptes * 8; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h index 90138bc5f03d..32775260556f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h @@ -180,6 +180,6 @@ amdgpu_get_next_xcp(struct amdgpu_xcp_mgr *xcp_mgr, int *from) #define for_each_xcp(xcp_mgr, xcp, i) \ for (i = 0, xcp = amdgpu_get_next_xcp(xcp_mgr, &i); xcp; \ - xcp = amdgpu_get_next_xcp(xcp_mgr, &i)) + ++i, xcp = amdgpu_get_next_xcp(xcp_mgr, &i)) #endif diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index 26e2188101e7..5e8833e4fed2 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -94,8 +94,6 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, case AMDGPU_RING_TYPE_VCN_ENC: case AMDGPU_RING_TYPE_VCN_JPEG: ip_blk = AMDGPU_XCP_VCN; - if (aqua_vanjaram_xcp_vcn_shared(adev)) - inst_mask = 1 << (inst_idx * 2); break; default: DRM_ERROR("Not support ring type %d!", ring->funcs->type); @@ -105,6 +103,8 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, for (xcp_id = 0; xcp_id < adev->xcp_mgr->num_xcps; xcp_id++) { if (adev->xcp_mgr->xcp[xcp_id].ip[ip_blk].inst_mask & inst_mask) { ring->xcp_id = xcp_id; + dev_dbg(adev->dev, "ring:%s xcp_id :%u", ring->name, + ring->xcp_id); if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) adev->gfx.enforce_isolation[xcp_id].xcp_id = xcp_id; break; @@ -394,38 +394,31 @@ static int __aqua_vanjaram_get_xcp_ip_info(struct amdgpu_xcp_mgr *xcp_mgr, int x struct amdgpu_xcp_ip *ip) { struct amdgpu_device *adev = xcp_mgr->adev; + int num_sdma, num_vcn, num_shared_vcn, num_xcp; int num_xcc_xcp, num_sdma_xcp, num_vcn_xcp; - int num_sdma, num_vcn; num_sdma = adev->sdma.num_instances; num_vcn = adev->vcn.num_vcn_inst; + num_shared_vcn = 1; + + num_xcc_xcp = adev->gfx.num_xcc_per_xcp; + num_xcp = NUM_XCC(adev->gfx.xcc_mask) / num_xcc_xcp; switch (xcp_mgr->mode) { case AMDGPU_SPX_PARTITION_MODE: - num_sdma_xcp = num_sdma; - num_vcn_xcp = num_vcn; - break; case AMDGPU_DPX_PARTITION_MODE: - num_sdma_xcp = num_sdma / 2; - num_vcn_xcp = num_vcn / 2; - break; case AMDGPU_TPX_PARTITION_MODE: - num_sdma_xcp = num_sdma / 3; - num_vcn_xcp = num_vcn / 3; - break; case AMDGPU_QPX_PARTITION_MODE: - num_sdma_xcp = num_sdma / 4; - num_vcn_xcp = num_vcn / 4; - break; case AMDGPU_CPX_PARTITION_MODE: - num_sdma_xcp = 2; - num_vcn_xcp = num_vcn ? 1 : 0; + num_sdma_xcp = DIV_ROUND_UP(num_sdma, num_xcp); + num_vcn_xcp = DIV_ROUND_UP(num_vcn, num_xcp); break; default: return -EINVAL; } - num_xcc_xcp = adev->gfx.num_xcc_per_xcp; + if (num_vcn && num_xcp > num_vcn) + num_shared_vcn = num_xcp / num_vcn; switch (ip_id) { case AMDGPU_XCP_GFXHUB: @@ -441,7 +434,8 @@ static int __aqua_vanjaram_get_xcp_ip_info(struct amdgpu_xcp_mgr *xcp_mgr, int x ip->ip_funcs = &sdma_v4_4_2_xcp_funcs; break; case AMDGPU_XCP_VCN: - ip->inst_mask = XCP_INST_MASK(num_vcn_xcp, xcp_id); + ip->inst_mask = + XCP_INST_MASK(num_vcn_xcp, xcp_id / num_shared_vcn); /* TODO : Assign IP funcs */ break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 742adbc460c9..70c1399f738d 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -1881,6 +1881,7 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2401,6 +2402,7 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 8d46ebadfa46..f154c24499c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -1931,6 +1931,7 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2485,6 +2486,7 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index f08dc6a3886f..a7fcb135827f 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -1861,6 +1861,7 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2321,6 +2322,7 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index a6a3adf2ae13..77ac3f114d24 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1828,6 +1828,7 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc, return r; if (!atomic) { + abo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM); if (unlikely(r != 0)) { amdgpu_bo_unreserve(abo); @@ -2320,6 +2321,7 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc, return ret; } + aobj->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); amdgpu_bo_unreserve(aobj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index d1357c01eb39..47b47d21f464 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -202,12 +202,16 @@ static const struct amdgpu_hwip_reg_entry gc_gfx_queue_reg_list_12[] = { SOC15_REG_ENTRY_STR(GC, 0, regCP_IB1_BUFSZ) }; -static const struct soc15_reg_golden golden_settings_gc_12_0[] = { +static const struct soc15_reg_golden golden_settings_gc_12_0_rev0[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_MEM_CONFIG, 0x0000000f, 0x0000000f), SOC15_REG_GOLDEN_VALUE(GC, 0, regCB_HW_CONTROL_1, 0x03000000, 0x03000000), SOC15_REG_GOLDEN_VALUE(GC, 0, regGL2C_CTRL5, 0x00000070, 0x00000020) }; +static const struct soc15_reg_golden golden_settings_gc_12_0[] = { + SOC15_REG_GOLDEN_VALUE(GC, 0, regDB_MEM_CONFIG, 0x00008000, 0x00008000), +}; + #define DEFAULT_SH_MEM_CONFIG \ ((SH_MEM_ADDRESS_MODE_64 << SH_MEM_CONFIG__ADDRESS_MODE__SHIFT) | \ (SH_MEM_ALIGNMENT_MODE_UNALIGNED << SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | \ @@ -3495,10 +3499,14 @@ static void gfx_v12_0_init_golden_registers(struct amdgpu_device *adev) switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): + soc15_program_register_sequence(adev, + golden_settings_gc_12_0, + (const u32)ARRAY_SIZE(golden_settings_gc_12_0)); + if (adev->rev_id == 0) soc15_program_register_sequence(adev, - golden_settings_gc_12_0, - (const u32)ARRAY_SIZE(golden_settings_gc_12_0)); + golden_settings_gc_12_0_rev0, + (const u32)ARRAY_SIZE(golden_settings_gc_12_0_rev0)); break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 408e5600bb61..c100845409f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -1701,7 +1701,15 @@ static void gfx_v9_4_3_xcc_cp_compute_enable(struct amdgpu_device *adev, WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_MEC_CNTL, 0); } else { WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_MEC_CNTL, - (CP_MEC_CNTL__MEC_ME1_HALT_MASK | CP_MEC_CNTL__MEC_ME2_HALT_MASK)); + (CP_MEC_CNTL__MEC_INVALIDATE_ICACHE_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE0_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE1_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE2_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_PIPE3_RESET_MASK | + CP_MEC_CNTL__MEC_ME2_PIPE0_RESET_MASK | + CP_MEC_CNTL__MEC_ME2_PIPE1_RESET_MASK | + CP_MEC_CNTL__MEC_ME1_HALT_MASK | + CP_MEC_CNTL__MEC_ME2_HALT_MASK)); adev->gfx.kiq[xcc_id].ring.sched.ready = false; } udelay(50); @@ -2240,6 +2248,8 @@ static int gfx_v9_4_3_xcc_cp_resume(struct amdgpu_device *adev, int xcc_id) r = gfx_v9_4_3_xcc_cp_compute_load_microcode(adev, xcc_id); if (r) return r; + } else { + gfx_v9_4_3_xcc_cp_compute_enable(adev, false, xcc_id); } r = gfx_v9_4_3_xcc_kiq_resume(adev, xcc_id); @@ -2299,12 +2309,6 @@ static int gfx_v9_4_3_cp_resume(struct amdgpu_device *adev) return 0; } -static void gfx_v9_4_3_xcc_cp_enable(struct amdgpu_device *adev, bool enable, - int xcc_id) -{ - gfx_v9_4_3_xcc_cp_compute_enable(adev, enable, xcc_id); -} - static void gfx_v9_4_3_xcc_fini(struct amdgpu_device *adev, int xcc_id) { if (amdgpu_gfx_disable_kcq(adev, xcc_id)) @@ -2336,7 +2340,7 @@ static void gfx_v9_4_3_xcc_fini(struct amdgpu_device *adev, int xcc_id) } gfx_v9_4_3_xcc_kcq_fini_register(adev, xcc_id); - gfx_v9_4_3_xcc_cp_enable(adev, false, xcc_id); + gfx_v9_4_3_xcc_cp_compute_enable(adev, false, xcc_id); } static int gfx_v9_4_3_hw_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 6c1891889c4d..d4f72e47ae9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -153,7 +153,7 @@ static void imu_v11_0_setup(struct amdgpu_device *adev) WREG32_SOC15(GC, 0, regGFX_IMU_C2PMSG_16, imu_reg_val); } - //disble imu Rtavfs, SmsRepair, DfllBTC, and ClkB + //disable imu Rtavfs, SmsRepair, DfllBTC, and ClkB imu_reg_val = RREG32_SOC15(GC, 0, regGFX_IMU_SCRATCH_10); imu_reg_val |= 0x10007; WREG32_SOC15(GC, 0, regGFX_IMU_SCRATCH_10, imu_reg_val); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index ee91ff9e52a2..231a3d490ea8 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -161,7 +161,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, int api_status_off) { union MESAPI__QUERY_MES_STATUS mes_status_pkt; - signed long timeout = 3000000; /* 3000 ms */ + signed long timeout = 2100000; /* 2100 ms */ struct amdgpu_device *adev = mes->adev; struct amdgpu_ring *ring = &mes->ring[0]; struct MES_API_STATUS *api_status; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index e499b2857a01..8d27421689c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -146,7 +146,7 @@ static int mes_v12_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, int api_status_off) { union MESAPI__QUERY_MES_STATUS mes_status_pkt; - signed long timeout = 3000000; /* 3000 ms */ + signed long timeout = 2100000; /* 2100 ms */ struct amdgpu_device *adev = mes->adev; struct amdgpu_ring *ring = &mes->ring[pipe]; spinlock_t *ring_lock = &mes->ring_lock[pipe]; @@ -479,6 +479,11 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, union MESAPI__MISC misc_pkt; int pipe; + if (mes->adev->enable_uni_mes) + pipe = AMDGPU_MES_KIQ_PIPE; + else + pipe = AMDGPU_MES_SCHED_PIPE; + memset(&misc_pkt, 0, sizeof(misc_pkt)); misc_pkt.header.type = MES_API_TYPE_SCHEDULER; @@ -513,6 +518,7 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, misc_pkt.wait_reg_mem.reg_offset2 = input->wrm_reg.reg1; break; case MES_MISC_OP_SET_SHADER_DEBUGGER: + pipe = AMDGPU_MES_SCHED_PIPE; misc_pkt.opcode = MESAPI_MISC__SET_SHADER_DEBUGGER; misc_pkt.set_shader_debugger.process_context_addr = input->set_shader_debugger.process_context_addr; @@ -530,11 +536,6 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes, return -EINVAL; } - if (mes->adev->enable_uni_mes) - pipe = AMDGPU_MES_KIQ_PIPE; - else - pipe = AMDGPU_MES_SCHED_PIPE; - return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &misc_pkt, sizeof(misc_pkt), offsetof(union MESAPI__MISC, api_status)); @@ -608,6 +609,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) mes_set_hw_res_pkt.disable_mes_log = 1; mes_set_hw_res_pkt.use_different_vmid_compute = 1; mes_set_hw_res_pkt.enable_reg_active_poll = 1; + mes_set_hw_res_pkt.enable_level_process_quantum_check = 1; /* * Keep oversubscribe timer for sdma . When we have unmapped doorbell diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index fa479dfa1ec1..739fce4fa8fd 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -365,7 +365,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, data &= ~PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK; } else { - /* Disbale ASPM L1 */ + /* Disable ASPM L1 */ data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK; /* Disable ASPM TxL0s */ data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 1251ee38a676..51e470e8d67d 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -81,6 +81,8 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_4_ta.bin"); /* memory training timeout define */ #define MEM_TRAIN_SEND_MSG_TIMEOUT_US 3000000 +#define regMP1_PUB_SCRATCH0 0x3b10090 + static int psp_v13_0_init_microcode(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; @@ -807,6 +809,20 @@ static bool psp_v13_0_get_ras_capability(struct psp_context *psp) } } +static bool psp_v13_0_is_aux_sos_load_required(struct psp_context *psp) +{ + struct amdgpu_device *adev = psp->adev; + u32 pmfw_ver; + + if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6)) + return false; + + /* load 4e version of sos if pmfw version less than 85.115.0 */ + pmfw_ver = RREG32(regMP1_PUB_SCRATCH0 / 4); + + return (pmfw_ver < 0x557300); +} + static const struct psp_funcs psp_v13_0_funcs = { .init_microcode = psp_v13_0_init_microcode, .wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state, @@ -830,6 +846,7 @@ static const struct psp_funcs psp_v13_0_funcs = { .vbflash_stat = psp_v13_0_vbflash_status, .fatal_error_recovery_quirk = psp_v13_0_fatal_error_recovery_quirk, .get_ras_capability = psp_v13_0_get_ras_capability, + .is_aux_sos_load_required = psp_v13_0_is_aux_sos_load_required, }; void psp_v13_0_set_psp_funcs(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index aa637541da58..e65194fe94af 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -710,7 +710,7 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev) upper_32_bits(wptr_gpu_addr)); wptr_poll_cntl = RREG32(mmSDMA0_GFX_RB_WPTR_POLL_CNTL + sdma_offsets[i]); if (ring->use_pollmem) { - /*wptr polling is not enogh fast, directly clean the wptr register */ + /*wptr polling is not enough fast, directly clean the wptr register */ WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0); wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index cfd8e183ad50..a8763496aed3 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1080,13 +1080,16 @@ static void sdma_v7_0_vm_copy_pte(struct amdgpu_ib *ib, unsigned bytes = count * 8; ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_COPY) | - SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR); + SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) | + SDMA_PKT_COPY_LINEAR_HEADER_CPV(1); + ib->ptr[ib->length_dw++] = bytes - 1; ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */ ib->ptr[ib->length_dw++] = lower_32_bits(src); ib->ptr[ib->length_dw++] = upper_32_bits(src); ib->ptr[ib->length_dw++] = lower_32_bits(pe); ib->ptr[ib->length_dw++] = upper_32_bits(pe); + ib->ptr[ib->length_dw++] = 0; } @@ -1744,7 +1747,7 @@ static void sdma_v7_0_set_buffer_funcs(struct amdgpu_device *adev) } static const struct amdgpu_vm_pte_funcs sdma_v7_0_vm_pte_funcs = { - .copy_pte_num_dw = 7, + .copy_pte_num_dw = 8, .copy_pte = sdma_v7_0_vm_copy_pte, .write_pte = sdma_v7_0_vm_write_pte, .set_pte_pde = sdma_v7_0_vm_set_pte_pde, diff --git a/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c b/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c index e4e30b9d481b..c04fdd2d5b38 100644 --- a/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/smuio_v9_0.c @@ -60,7 +60,7 @@ static void smuio_v9_0_get_clock_gating_state(struct amdgpu_device *adev, u64 *f { u32 data; - /* CGTT_ROM_CLK_CTRL0 is not availabe for APUs */ + /* CGTT_ROM_CLK_CTRL0 is not available for APUs */ if (adev->flags & AMD_IS_APU) return; diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c index b0c3678cfb31..fd4c3d4f8387 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc24.c +++ b/drivers/gpu/drm/amd/amdgpu/soc24.c @@ -250,13 +250,6 @@ static void soc24_program_aspm(struct amdgpu_device *adev) adev->nbio.funcs->program_aspm(adev); } -static void soc24_enable_doorbell_aperture(struct amdgpu_device *adev, - bool enable) -{ - adev->nbio.funcs->enable_doorbell_aperture(adev, enable); - adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable); -} - const struct amdgpu_ip_block_version soc24_common_ip_block = { .type = AMD_IP_BLOCK_TYPE_COMMON, .major = 1, @@ -454,6 +447,11 @@ static int soc24_common_late_init(void *handle) if (amdgpu_sriov_vf(adev)) xgpu_nv_mailbox_get_irq(adev); + /* Enable selfring doorbell aperture late because doorbell BAR + * aperture will change if resize BAR successfully in gmc sw_init. + */ + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true); + return 0; } @@ -491,7 +489,7 @@ static int soc24_common_hw_init(void *handle) adev->df.funcs->hw_init(adev); /* enable the doorbell aperture */ - soc24_enable_doorbell_aperture(adev, true); + adev->nbio.funcs->enable_doorbell_aperture(adev, true); return 0; } @@ -500,8 +498,13 @@ static int soc24_common_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* disable the doorbell aperture */ - soc24_enable_doorbell_aperture(adev, false); + /* Disable the doorbell aperture and selfring doorbell aperture + * separately in hw_fini because soc21_enable_doorbell_aperture + * has been removed and there is no need to delay disabling + * selfring doorbell. + */ + adev->nbio.funcs->enable_doorbell_aperture(adev, false); + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false); if (amdgpu_sriov_vf(adev)) xgpu_nv_mailbox_put_irq(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index b1fd226b7efb..9d4f5352a62c 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -1395,170 +1395,6 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring) } } -static int vcn_v4_0_5_limit_sched(struct amdgpu_cs_parser *p, - struct amdgpu_job *job) -{ - struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; - - /* if VCN0 is harvested, we can't support AV1 */ - if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) - return -EINVAL; - - scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] - [AMDGPU_RING_PRIO_0].sched; - drm_sched_entity_modify_sched(job->base.entity, scheds, 1); - return 0; -} - -static int vcn_v4_0_5_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job, - uint64_t addr) -{ - struct ttm_operation_ctx ctx = { false, false }; - struct amdgpu_bo_va_mapping *map; - uint32_t *msg, num_buffers; - struct amdgpu_bo *bo; - uint64_t start, end; - unsigned int i; - void *ptr; - int r; - - addr &= AMDGPU_GMC_HOLE_MASK; - r = amdgpu_cs_find_mapping(p, addr, &bo, &map); - if (r) { - DRM_ERROR("Can't find BO for addr 0x%08llx\n", addr); - return r; - } - - start = map->start * AMDGPU_GPU_PAGE_SIZE; - end = (map->last + 1) * AMDGPU_GPU_PAGE_SIZE; - if (addr & 0x7) { - DRM_ERROR("VCN messages must be 8 byte aligned!\n"); - return -EINVAL; - } - - bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - amdgpu_bo_placement_from_domain(bo, bo->allowed_domains); - r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - if (r) { - DRM_ERROR("Failed validating the VCN message BO (%d)!\n", r); - return r; - } - - r = amdgpu_bo_kmap(bo, &ptr); - if (r) { - DRM_ERROR("Failed mapping the VCN message (%d)!\n", r); - return r; - } - - msg = ptr + addr - start; - - /* Check length */ - if (msg[1] > end - addr) { - r = -EINVAL; - goto out; - } - - if (msg[3] != RDECODE_MSG_CREATE) - goto out; - - num_buffers = msg[2]; - for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) { - uint32_t offset, size, *create; - - if (msg[0] != RDECODE_MESSAGE_CREATE) - continue; - - offset = msg[1]; - size = msg[2]; - - if (offset + size > end) { - r = -EINVAL; - goto out; - } - - create = ptr + addr + offset - start; - - /* H264, HEVC and VP9 can run on any instance */ - if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11) - continue; - - r = vcn_v4_0_5_limit_sched(p, job); - if (r) - goto out; - } - -out: - amdgpu_bo_kunmap(bo); - return r; -} - -#define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) -#define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - -#define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - -#define RENCODE_ENCODE_STANDARD_AV1 2 -#define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 - -/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_5_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) -{ - int i; - - for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { - if (ib->ptr[i + 1] == id) - return i; - } - return -1; -} - -static int vcn_v4_0_5_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, - struct amdgpu_job *job, - struct amdgpu_ib *ib) -{ - struct amdgpu_ring *ring = amdgpu_job_ring(job); - struct amdgpu_vcn_decode_buffer *decode_buffer; - uint64_t addr; - uint32_t val; - int idx; - - /* The first instance can decode anything */ - if (!ring->me) - return 0; - - /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_5_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; - - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_5_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_5_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_5_limit_sched(p, job); - } - return 0; -} - static const struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_ENC, .align_mask = 0x3f, @@ -1566,7 +1402,6 @@ static const struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = { .get_rptr = vcn_v4_0_5_unified_ring_get_rptr, .get_wptr = vcn_v4_0_5_unified_ring_get_wptr, .set_wptr = vcn_v4_0_5_unified_ring_set_wptr, - .patch_cs_in_place = vcn_v4_0_5_ring_patch_cs_in_place, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 + diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 71b465f8d83e..648f40091aa3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -3540,6 +3540,30 @@ int debug_refresh_runlist(struct device_queue_manager *dqm) return debug_map_and_unlock(dqm); } +bool kfd_dqm_is_queue_in_process(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + int doorbell_off, u32 *queue_format) +{ + struct queue *q; + bool r = false; + + if (!queue_format) + return r; + + dqm_lock(dqm); + + list_for_each_entry(q, &qpd->queues_list, list) { + if (q->properties.doorbell_off == doorbell_off) { + *queue_format = q->properties.format; + r = true; + goto out; + } + } + +out: + dqm_unlock(dqm); + return r; +} #if defined(CONFIG_DEBUG_FS) static void seq_reg_dump(struct seq_file *m, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 08b40826ad1e..09ab36f8e8c6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -324,6 +324,9 @@ void set_queue_snapshot_entry(struct queue *q, int debug_lock_and_unmap(struct device_queue_manager *dqm); int debug_map_and_unlock(struct device_queue_manager *dqm); int debug_refresh_runlist(struct device_queue_manager *dqm); +bool kfd_dqm_is_queue_in_process(struct device_queue_manager *dqm, + struct qcm_process_device *qpd, + int doorbell_off, u32 *queue_format); static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c index bb8cbfc39b90..37b69fe0ede3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c @@ -306,23 +306,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, client_id == SOC15_IH_CLIENTID_UTCL2) { struct kfd_vm_fault_info info = {0}; uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry); - uint32_t node_id = SOC15_NODEID_FROM_IH_ENTRY(ih_ring_entry); - uint32_t vmid_type = SOC15_VMID_TYPE_FROM_IH_ENTRY(ih_ring_entry); - int hub_inst = 0; struct kfd_hsa_memory_exception_data exception_data; - /* gfxhub */ - if (!vmid_type && dev->adev->gfx.funcs->ih_node_to_logical_xcc) { - hub_inst = dev->adev->gfx.funcs->ih_node_to_logical_xcc(dev->adev, - node_id); - if (hub_inst < 0) - hub_inst = 0; - } - - /* mmhub */ - if (vmid_type && client_id == SOC15_IH_CLIENTID_VMC) - hub_inst = node_id / 4; - info.vmid = vmid; info.mc_id = client_id; info.page_addr = ih_ring_entry[4] | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c index d163d92a692f..2b72d5b4949b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c @@ -341,6 +341,10 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, m->sdmax_rlcx_doorbell_offset = q->doorbell_off << SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT; + m->sdmax_rlcx_sched_cntl = (amdgpu_sdma_phase_quantum + << SDMA0_QUEUE0_SCHEDULE_CNTL__CONTEXT_QUANTUM__SHIFT) + & SDMA0_QUEUE0_SCHEDULE_CNTL__CONTEXT_QUANTUM_MASK; + m->sdma_engine_id = q->sdma_engine_id; m->sdma_queue_id = q->sdma_queue_id; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index a902950cc060..d07acf1b2f93 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -270,6 +270,11 @@ static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer) struct kfd_node *dev = NULL; struct kfd_process *proc = NULL; struct kfd_process_device *pdd = NULL; + int i; + struct kfd_cu_occupancy cu_occupancy[AMDGPU_MAX_QUEUES]; + u32 queue_format; + + memset(cu_occupancy, 0x0, sizeof(cu_occupancy)); pdd = container_of(attr, struct kfd_process_device, attr_cu_occupancy); dev = pdd->dev; @@ -287,8 +292,29 @@ static int kfd_get_cu_occupancy(struct attribute *attr, char *buffer) /* Collect wave count from device if it supports */ wave_cnt = 0; max_waves_per_cu = 0; - dev->kfd2kgd->get_cu_occupancy(dev->adev, proc->pasid, &wave_cnt, - &max_waves_per_cu, 0); + + /* + * For GFX 9.4.3, fetch the CU occupancy from the first XCC in the partition. + * For AQL queues, because of cooperative dispatch we multiply the wave count + * by number of XCCs in the partition to get the total wave counts across all + * XCCs in the partition. + * For PM4 queues, there is no cooperative dispatch so wave_cnt stay as it is. + */ + dev->kfd2kgd->get_cu_occupancy(dev->adev, cu_occupancy, + &max_waves_per_cu, ffs(dev->xcc_mask) - 1); + + for (i = 0; i < AMDGPU_MAX_QUEUES; i++) { + if (cu_occupancy[i].wave_cnt != 0 && + kfd_dqm_is_queue_in_process(dev->dqm, &pdd->qpd, + cu_occupancy[i].doorbell_off, + &queue_format)) { + if (unlikely(queue_format == KFD_QUEUE_FORMAT_PM4)) + wave_cnt += cu_occupancy[i].wave_cnt; + else + wave_cnt += (NUM_XCC(dev->xcc_mask) * + cu_occupancy[i].wave_cnt); + } + } /* Translate wave count to number of compute units */ cu_cnt = (wave_cnt + (max_waves_per_cu - 1)) / max_waves_per_cu; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index b439d4d0bd84..01b960b15274 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -517,7 +517,6 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) if (retval) goto err_destroy_queue; - kfd_procfs_del_queue(pqn->q); dqm = pqn->q->device->dqm; retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q); if (retval) { @@ -527,6 +526,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid) if (retval != -ETIME) goto err_destroy_queue; } + kfd_procfs_del_queue(pqn->q); kfd_queue_release_buffers(pdd, &pqn->q->properties); pqm_clean_queue_resource(pqm, pqn); uninit_queue(pqn->q); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0cff66735cfe..6e79028c5d78 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -808,6 +808,20 @@ static void dmub_hpd_callback(struct amdgpu_device *adev, } /** + * dmub_hpd_sense_callback - DMUB HPD sense processing callback. + * @adev: amdgpu_device pointer + * @notify: dmub notification structure + * + * HPD sense changes can occur during low power states and need to be + * notified from firmware to driver. + */ +static void dmub_hpd_sense_callback(struct amdgpu_device *adev, + struct dmub_notification *notify) +{ + DRM_DEBUG_DRIVER("DMUB HPD SENSE callback.\n"); +} + +/** * register_dmub_notify_callback - Sets callback for DMUB notify * @adev: amdgpu_device pointer * @type: Type of dmub notification @@ -1757,25 +1771,41 @@ static struct dml2_soc_bb *dm_dmub_get_vbios_bounding_box(struct amdgpu_device * static enum dmub_ips_disable_type dm_get_default_ips_mode( struct amdgpu_device *adev) { - /* - * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to - * cause a hard hang. A fix exists for newer PMFW. - * - * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest - * IPS state in all cases, except for s0ix and all displays off (DPMS), - * where IPS2 is allowed. - * - * When checking pmfw version, use the major and minor only. - */ - if (amdgpu_ip_version(adev, DCE_HWIP, 0) == IP_VERSION(3, 5, 0) && - (adev->pm.fw_version & 0x00FFFF00) < 0x005D6300) - return DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + enum dmub_ips_disable_type ret = DMUB_IPS_ENABLE; - if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 5, 0)) - return DMUB_IPS_ENABLE; + switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) { + case IP_VERSION(3, 5, 0): + /* + * On DCN35 systems with Z8 enabled, it's possible for IPS2 + Z8 to + * cause a hard hang. A fix exists for newer PMFW. + * + * As a workaround, for non-fixed PMFW, force IPS1+RCG as the deepest + * IPS state in all cases, except for s0ix and all displays off (DPMS), + * where IPS2 is allowed. + * + * When checking pmfw version, use the major and minor only. + */ + if ((adev->pm.fw_version & 0x00FFFF00) < 0x005D6300) + ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + else if (amdgpu_ip_version(adev, GC_HWIP, 0) > IP_VERSION(11, 5, 0)) + /* + * Other ASICs with DCN35 that have residency issues with + * IPS2 in idle. + * We want them to use IPS2 only in display off cases. + */ + ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + break; + case IP_VERSION(3, 5, 1): + ret = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; + break; + default: + /* ASICs older than DCN35 do not have IPSs */ + if (amdgpu_ip_version(adev, DCE_HWIP, 0) < IP_VERSION(3, 5, 0)) + ret = DMUB_IPS_DISABLE_ALL; + break; + } - /* ASICs older than DCN35 do not have IPSs */ - return DMUB_IPS_DISABLE_ALL; + return ret; } static int amdgpu_dm_init(struct amdgpu_device *adev) @@ -3808,6 +3838,12 @@ static int register_hpd_handlers(struct amdgpu_device *adev) DRM_ERROR("amdgpu: fail to register dmub hpd callback"); return -EINVAL; } + + if (!register_dmub_notify_callback(adev, DMUB_NOTIFICATION_HPD_SENSE_NOTIFY, + dmub_hpd_sense_callback, true)) { + DRM_ERROR("amdgpu: fail to register dmub hpd sense callback"); + return -EINVAL; + } } list_for_each_entry(connector, @@ -4449,6 +4485,7 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) #define AMDGPU_DM_DEFAULT_MIN_BACKLIGHT 12 #define AMDGPU_DM_DEFAULT_MAX_BACKLIGHT 255 +#define AMDGPU_DM_MIN_SPREAD ((AMDGPU_DM_DEFAULT_MAX_BACKLIGHT - AMDGPU_DM_DEFAULT_MIN_BACKLIGHT) / 2) #define AUX_BL_DEFAULT_TRANSITION_TIME_MS 50 static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, @@ -4463,6 +4500,21 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, return; amdgpu_acpi_get_backlight_caps(&caps); + + /* validate the firmware value is sane */ + if (caps.caps_valid) { + int spread = caps.max_input_signal - caps.min_input_signal; + + if (caps.max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + caps.min_input_signal < 0 || + spread > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + spread < AMDGPU_DM_MIN_SPREAD) { + DRM_DEBUG_KMS("DM: Invalid backlight caps: min=%d, max=%d\n", + caps.min_input_signal, caps.max_input_signal); + caps.caps_valid = false; + } + } + if (caps.caps_valid) { dm->backlight_caps[bl_idx].caps_valid = true; if (caps.aux_support) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 2d7755e2b6c3..15d4690c74d6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -50,7 +50,7 @@ #define AMDGPU_DM_MAX_NUM_EDP 2 -#define AMDGPU_DMUB_NOTIFICATION_MAX 6 +#define AMDGPU_DMUB_NOTIFICATION_MAX 7 #define HDMI_AMD_VENDOR_SPECIFIC_DATA_BLOCK_IEEE_REGISTRATION_ID 0x00001A #define AMD_VSDB_VERSION_3_FEATURECAP_REPLAYMODE 0x40 diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index c0c61c03984c..83a31b97e96b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1147,7 +1147,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, params[count].num_slices_v = aconnector->dsc_settings.dsc_num_slices_v; params[count].bpp_overwrite = aconnector->dsc_settings.dsc_bits_per_pixel; params[count].compression_possible = stream->sink->dsc_caps.dsc_dec_caps.is_dsc_supported; - dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy); + dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link)); if (!dc_dsc_compute_bandwidth_range( stream->sink->ctx->dc->res_pool->dscs[0], stream->sink->ctx->dc->debug.dsc_min_slice_height_override, @@ -1681,7 +1681,7 @@ static bool is_dsc_common_config_possible(struct dc_stream_state *stream, { struct dc_dsc_policy dsc_policy = {0}; - dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy); + dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link)); dc_dsc_compute_bandwidth_range(stream->sink->ctx->dc->res_pool->dscs[0], stream->sink->ctx->dc->debug.dsc_min_slice_height_override, dsc_policy.min_target_bpp * 16, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index 25f63b2e7a8e..495e3cd70426 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -961,6 +961,7 @@ static int amdgpu_dm_plane_helper_prepare_fb(struct drm_plane *plane, else domain = AMDGPU_GEM_DOMAIN_VRAM; + rbo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(rbo, domain); if (unlikely(r != 0)) { if (r != -ERESTARTSYS) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c index 08c494a7a21b..0d5fefb0f591 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c @@ -114,6 +114,7 @@ static int amdgpu_dm_wb_prepare_job(struct drm_writeback_connector *wb_connector domain = amdgpu_display_supported_domains(adev, rbo->flags); + rbo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; r = amdgpu_bo_pin(rbo, domain); if (unlikely(r != 0)) { if (r != -ERESTARTSYS) diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c index e47e9db062f4..681799468487 100644 --- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c @@ -569,7 +569,7 @@ static void calculate_bandwidth( break; } data->lb_partitions[i] = bw_floor2(bw_div(data->lb_size_per_component[i], data->lb_line_pitch), bw_int_to_fixed(1)); - /*clamp the partitions to the maxium number supported by the lb*/ + /* clamp the partitions to the maximum number supported by the lb */ if ((surface_type[i] != bw_def_graphics || dceip->graphics_lb_nodownscaling_multi_line_prefetching == 1)) { data->lb_partitions_max[i] = bw_int_to_fixed(10); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index f770828df149..0e243f4344d0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -59,6 +59,7 @@ int clk_mgr_helper_get_active_display_cnt( display_count = 0; for (i = 0; i < context->stream_count; i++) { const struct dc_stream_state *stream = context->streams[i]; + const struct dc_stream_status *stream_status = &context->stream_status[i]; /* Don't count SubVP phantom pipes as part of active * display count @@ -66,13 +67,7 @@ int clk_mgr_helper_get_active_display_cnt( if (dc_state_get_stream_subvp_type(context, stream) == SUBVP_PHANTOM) continue; - /* - * Only notify active stream or virtual stream. - * Need to notify virtual stream to work around - * headless case. HPD does not fire when system is in - * S0i2. - */ - if (!stream->dpms_off || stream->signal == SIGNAL_TYPE_VIRTUAL) + if (!stream->dpms_off || (stream_status && stream_status->plane_count)) display_count++; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 97164b5585a8..b46a3afe48ca 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -1222,6 +1222,12 @@ void dcn35_clk_mgr_construct( ctx->dc->debug.disable_dpp_power_gate = false; ctx->dc->debug.disable_hubp_power_gate = false; ctx->dc->debug.disable_dsc_power_gate = false; + + /* Disable dynamic IPS2 in older PMFW (93.12) for Z8 interop. */ + if (ctx->dc->config.disable_ips == DMUB_IPS_ENABLE && + ctx->dce_version == DCN_VERSION_3_5 && + ((clk_mgr->base.smu_ver & 0x00FFFFFF) <= 0x005d0c00)) + ctx->dc->config.disable_ips = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF; } else { /*let's reset the config control flag*/ ctx->dc->config.disable_ips = DMUB_IPS_DISABLE_ALL; /*pmfw not support it, disable it all*/ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index ae788154896c..5c39390ecbd5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1767,7 +1767,7 @@ bool dc_validate_boot_timing(const struct dc *dc, if (crtc_timing->pix_clk_100hz != pix_clk_100hz) return false; - if (!se->funcs->dp_get_pixel_format) + if (!se || !se->funcs->dp_get_pixel_format) return false; if (!se->funcs->dp_get_pixel_format( @@ -2376,7 +2376,7 @@ static bool is_surface_in_context( return false; } -static enum surface_update_type get_plane_info_update_type(const struct dc_surface_update *u) +static enum surface_update_type get_plane_info_update_type(const struct dc *dc, const struct dc_surface_update *u) { union surface_update_flags *update_flags = &u->surface->update_flags; enum surface_update_type update_type = UPDATE_TYPE_FAST; @@ -2455,7 +2455,7 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa /* todo: below are HW dependent, we should add a hook to * DCE/N resource and validated there. */ - if (u->plane_info->tiling_info.gfx9.swizzle != DC_SW_LINEAR) { + if (!dc->debug.skip_full_updated_if_possible) { /* swizzled mode requires RQ to be setup properly, * thus need to run DML to calculate RQ settings */ @@ -2547,7 +2547,7 @@ static enum surface_update_type det_surface_update(const struct dc *dc, update_flags->raw = 0; // Reset all flags - type = get_plane_info_update_type(u); + type = get_plane_info_update_type(dc, u); elevate_update_type(&overall_type, type); type = get_scaling_info_update_type(dc, u); @@ -2596,6 +2596,12 @@ static enum surface_update_type det_surface_update(const struct dc *dc, elevate_update_type(&overall_type, UPDATE_TYPE_MED); } + if (u->sdr_white_level_nits) + if (u->sdr_white_level_nits != u->surface->sdr_white_level_nits) { + update_flags->bits.sdr_white_level_nits = 1; + elevate_update_type(&overall_type, UPDATE_TYPE_FULL); + } + if (u->cm2_params) { if ((u->cm2_params->component_settings.shaper_3dlut_setting != u->surface->mcm_shaper_3dlut_setting) @@ -2876,6 +2882,10 @@ static void copy_surface_update_to_plane( surface->hdr_mult = srf_update->hdr_mult; + if (srf_update->sdr_white_level_nits) + surface->sdr_white_level_nits = + srf_update->sdr_white_level_nits; + if (srf_update->blend_tf) memcpy(&surface->blend_tf, srf_update->blend_tf, sizeof(surface->blend_tf)); @@ -4679,6 +4689,8 @@ static bool full_update_required(struct dc *dc, srf_updates[i].scaling_info || (srf_updates[i].hdr_mult.value && srf_updates[i].hdr_mult.value != srf_updates->surface->hdr_mult.value) || + (srf_updates[i].sdr_white_level_nits && + srf_updates[i].sdr_white_level_nits != srf_updates->surface->sdr_white_level_nits) || srf_updates[i].in_transfer_func || srf_updates[i].func_shaper || srf_updates[i].lut3d_func || @@ -5744,6 +5756,27 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, } /** + * dc_process_dmub_dpia_set_tps_notification - Submits tps notification + * + * @dc: [in] dc structure + * @link_index: [in] link index + * @tps: [in] request tps + * + * Submits set_tps_notification command to dmub via inbox message + */ +void dc_process_dmub_dpia_set_tps_notification(const struct dc *dc, uint32_t link_index, uint8_t tps) +{ + union dmub_rb_cmd cmd = {0}; + + cmd.set_tps_notification.header.type = DMUB_CMD__DPIA; + cmd.set_tps_notification.header.sub_type = DMUB_CMD__DPIA_SET_TPS_NOTIFICATION; + cmd.set_tps_notification.tps_notification.instance = dc->links[link_index]->ddc_hw_inst; + cmd.set_tps_notification.tps_notification.tps = tps; + + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); +} + +/** * dc_process_dmub_dpia_hpd_int_enable - Submits DPIA DPD interruption * * @dc: [in] dc structure diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4c94dd38be4b..3992ad73165b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -55,7 +55,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.299" +#define DC_VER "3.2.301" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -462,6 +462,7 @@ struct dc_config { bool support_edp0_on_dp1; unsigned int enable_fpo_flicker_detection; bool disable_hbr_audio_dp2; + bool consolidated_dpia_dp_lt; }; enum visual_confirm { @@ -762,7 +763,8 @@ union dpia_debug_options { uint32_t disable_mst_dsc_work_around:1; /* bit 3 */ uint32_t enable_force_tbt3_work_around:1; /* bit 4 */ uint32_t disable_usb4_pm_support:1; /* bit 5 */ - uint32_t reserved:26; + uint32_t enable_consolidated_dpia_dp_lt:1; /* bit 6 */ + uint32_t reserved:25; } bits; uint32_t raw; }; @@ -1056,6 +1058,9 @@ struct dc_debug_options { unsigned int force_lls; bool notify_dpia_hr_bw; bool enable_ips_visual_confirm; + unsigned int sharpen_policy; + unsigned int scale_to_sharpness_policy; + bool skip_full_updated_if_possible; }; @@ -1269,6 +1274,7 @@ union surface_update_flags { uint32_t tmz_changed:1; uint32_t mcm_transfer_function_enable_change:1; /* disable or enable MCM transfer func */ uint32_t full_update:1; + uint32_t sdr_white_level_nits:1; } bits; uint32_t raw; @@ -1351,6 +1357,7 @@ struct dc_plane_state { bool adaptive_sharpness_en; int sharpness_level; enum linear_light_scaling linear_light_scaling; + unsigned int sdr_white_level_nits; }; struct dc_plane_info { @@ -1508,6 +1515,7 @@ struct dc_surface_update { */ struct dc_cm2_parameters *cm2_params; const struct dc_csc_transform *cursor_csc_color_matrix; + unsigned int sdr_white_level_nits; }; /* @@ -2520,6 +2528,8 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, uint8_t mst_alloc_slots, uint8_t *mst_slots_in_use); +void dc_process_dmub_dpia_set_tps_notification(const struct dc *dc, uint32_t link_index, uint8_t tps); + void dc_process_dmub_dpia_hpd_int_enable(const struct dc *dc, uint32_t hpd_int_enable); diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h index 519c3df78ee5..41bd95e9177a 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h @@ -969,6 +969,14 @@ union dp_sink_video_fallback_formats { uint8_t raw; }; +union dpcd_max_uncompressed_pixel_rate_cap { + struct { + uint16_t max_uncompressed_pixel_rate_cap :15; + uint16_t valid :1; + } bits; + uint8_t raw[2]; +}; + union dp_fec_capability1 { struct { uint8_t AGGREGATED_ERROR_COUNTERS_CAPABLE :1; @@ -1170,6 +1178,7 @@ struct dpcd_caps { struct dc_lttpr_caps lttpr_caps; struct adaptive_sync_caps adaptive_sync_caps; struct dpcd_usb4_dp_tunneling_info usb4_dp_tun_info; + union dpcd_max_uncompressed_pixel_rate_cap max_uncompressed_pixel_rate_cap; union dp_128b_132b_supported_link_rates dp_128b_132b_supported_link_rates; union dp_main_line_channel_coding_cap channel_coding_cap; @@ -1340,6 +1349,9 @@ struct dp_trace { #ifndef DP_CABLE_ATTRIBUTES_UPDATED_BY_DPTX #define DP_CABLE_ATTRIBUTES_UPDATED_BY_DPTX 0x110 #endif +#ifndef DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP +#define DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP 0x221c +#endif #ifndef DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #endif diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h index fe3078b8789e..9014c2409817 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h @@ -59,6 +59,7 @@ struct dc_dsc_config_options { uint32_t max_target_bpp_limit_override_x16; uint32_t slice_height_granularity; uint32_t dsc_force_odm_hslice_override; + bool force_dsc_when_not_needed; }; bool dc_dsc_parse_dsc_dpcd(const struct dc *dc, @@ -100,7 +101,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps( */ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, uint32_t max_target_bpp_limit_override_x16, - struct dc_dsc_policy *policy); + struct dc_dsc_policy *policy, + const enum dc_link_encoding_format link_encoding); void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit); diff --git a/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c b/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c index cd6de93eb91c..603552dbd771 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c +++ b/drivers/gpu/drm/amd/display/dc/dc_spl_translate.c @@ -186,19 +186,17 @@ void translate_SPL_in_params_from_pipe_ctx(struct pipe_ctx *pipe_ctx, struct spl spl_in->h_active = pipe_ctx->plane_res.scl_data.h_active; spl_in->v_active = pipe_ctx->plane_res.scl_data.v_active; + + spl_in->debug.sharpen_policy = (enum sharpen_policy)pipe_ctx->stream->ctx->dc->debug.sharpen_policy; + spl_in->debug.scale_to_sharpness_policy = + (enum scale_to_sharpness_policy)pipe_ctx->stream->ctx->dc->debug.scale_to_sharpness_policy; + /* Check if it is stream is in fullscreen and if its HDR. * Use this to determine sharpness levels */ spl_in->is_fullscreen = dm_helpers_is_fullscreen(pipe_ctx->stream->ctx, pipe_ctx->stream); spl_in->is_hdr_on = dm_helpers_is_hdr_on(pipe_ctx->stream->ctx, pipe_ctx->stream); - spl_in->hdr_multx100 = 0; - if (spl_in->is_hdr_on) { - spl_in->hdr_multx100 = (uint32_t)dc_fixpt_floor(dc_fixpt_mul(plane_state->hdr_mult, - dc_fixpt_from_int(100))); - /* Disable sharpness for HDR Mult > 6.0 */ - if (spl_in->hdr_multx100 > 600) - spl_in->adaptive_sharpness.enable = false; - } + spl_in->sdr_white_level_nits = plane_state->sdr_white_level_nits; } /// @brief Translate SPL output parameters to pipe context diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c index e7019c95ba79..4fce64a030b6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c @@ -313,9 +313,6 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, if (swath_height_c > 0) log2_swath_height_c = dml_log2(swath_height_c); - - if (req128_c && log2_swath_height_c > 0) - log2_swath_height_c -= 1; } rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index ae5251041728..3fa9a5da02f6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -313,9 +313,6 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib, if (swath_height_c > 0) log2_swath_height_c = dml_log2(swath_height_c); - - if (req128_c && log2_swath_height_c > 0) - log2_swath_height_c -= 1; } rq_param->dlg.rq_l.swath_height = 1 << log2_swath_height_l; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index 0b132ce1d2cd..2b275e680379 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -1924,15 +1924,6 @@ static unsigned int CalculateVMAndRowBytes( *PixelPTEReqWidth = 32768.0 / BytePerPixel; *PTERequestSize = 64; FractionOfPTEReturnDrop = 0; - } else if (MacroTileSizeBytes == 4096) { - PixelPTEReqHeightPTEs = 1; - *PixelPTEReqHeight = MacroTileHeight; - *PixelPTEReqWidth = 8 * *MacroTileWidth; - *PTERequestSize = 64; - if (ScanDirection != dm_vert) - FractionOfPTEReturnDrop = 0; - else - FractionOfPTEReturnDrop = 7.0 / 8; } else if (GPUVMMinPageSize == 4 && MacroTileSizeBytes > 4096) { PixelPTEReqHeightPTEs = 16; *PixelPTEReqHeight = 16 * BlockHeight256Bytes; diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c index 547dfcc80fde..d851c081e376 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c @@ -8926,7 +8926,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc // The prefetch scheduling should only be calculated once as per AllowForPStateChangeOrStutterInVBlank requirement // If the AllowForPStateChangeOrStutterInVBlank requirement is not strict (i.e. only try those power saving feature - // if possible, then will try to program for the best power saving features in order of diffculty (dram, fclk, stutter) + // if possible, then will try to program for the best power saving features in order of difficulty (dram, fclk, stutter) s->iteration = 0; s->MaxTotalRDBandwidth = 0; s->AllPrefetchModeTested = false; @@ -9977,7 +9977,7 @@ void dml_core_get_row_heights( dml_print("DML_DLG: %s: GPUVMMinPageSizeKBytes = %u\n", __func__, GPUVMMinPageSizeKBytes); #endif - // just suppluy with enough parameters to calculate meta and dte + // just supply with enough parameters to calculate meta and dte CalculateVMAndRowBytes( 0, // dml_bool_t ViewportStationary, 1, // dml_bool_t DCCEnable, @@ -10110,7 +10110,7 @@ dml_bool_t dml_mode_support( /// Note: In this function, it is assumed that DCFCLK, SOCCLK freq are the state values, and mode_program will just use the DML calculated DPPCLK and DISPCLK /// @param mode_lib mode_lib data struct that house all the input/output/bbox and calculation values. /// @param state_idx Power state idx chosen -/// @param display_cfg Display Congiuration +/// @param display_cfg Display Configuration /// @param call_standalone Calling mode_programming without calling mode support. Some of the "support" struct member will be pre-calculated before doing mode programming /// TODO: Add clk_cfg input, could be useful for standalone mode dml_bool_t dml_mode_programming( diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c index b0d9aed0f265..8697eac1e1f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c @@ -858,7 +858,9 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm plane->immediate_flip = plane_state->flip_immediate; - plane->composition.rect_out_height_spans_vactive = plane_state->dst_rect.height >= stream->timing.v_addressable; + plane->composition.rect_out_height_spans_vactive = + plane_state->dst_rect.height >= stream->timing.v_addressable && + stream->dst.height >= stream->timing.v_addressable; } //TODO : Could be possibly moved to a common helper layer. diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c index d63558ee3135..1cf9015e854a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c @@ -940,9 +940,11 @@ static void build_synchronized_timing_groups( /* find synchronizable timing groups */ for (j = i + 1; j < display_config->display_config.num_streams; j++) { if (memcmp(master_timing, - &display_config->display_config.stream_descriptors[j].timing, - sizeof(struct dml2_timing_cfg)) == 0 && - display_config->display_config.stream_descriptors[i].output.output_encoder == display_config->display_config.stream_descriptors[j].output.output_encoder) { + &display_config->display_config.stream_descriptors[j].timing, + sizeof(struct dml2_timing_cfg)) == 0 && + display_config->display_config.stream_descriptors[i].output.output_encoder == display_config->display_config.stream_descriptors[j].output.output_encoder && + (display_config->display_config.stream_descriptors[i].output.output_encoder != dml2_hdmi || //hdmi requires formats match + display_config->display_config.stream_descriptors[i].output.output_format == display_config->display_config.stream_descriptors[j].output.output_format)) { set_bit_in_bitfield(&pmo->scratch.pmo_dcn4.synchronized_timing_group_masks[timing_group_idx], j); set_bit_in_bitfield(&stream_mapped_mask, j); } diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index a1727e5bf024..ebd5df1a36e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -668,6 +668,7 @@ static bool decide_dsc_bandwidth_range( */ static bool decide_dsc_target_bpp_x16( const struct dc_dsc_policy *policy, + const struct dc_dsc_config_options *options, const struct dsc_enc_caps *dsc_common_caps, const int target_bandwidth_kbps, const struct dc_crtc_timing *timing, @@ -682,7 +683,7 @@ static bool decide_dsc_target_bpp_x16( if (decide_dsc_bandwidth_range(policy->min_target_bpp * 16, policy->max_target_bpp * 16, num_slices_h, dsc_common_caps, timing, link_encoding, &range)) { if (target_bandwidth_kbps >= range.stream_kbps) { - if (policy->enable_dsc_when_not_needed) + if (policy->enable_dsc_when_not_needed || options->force_dsc_when_not_needed) /* enable max bpp even dsc is not needed */ *target_bpp_x16 = range.max_target_bpp_x16; } else if (target_bandwidth_kbps >= range.max_kbps) { @@ -882,7 +883,7 @@ static bool setup_dsc_config( memset(dsc_cfg, 0, sizeof(struct dc_dsc_config)); - dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy); + dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy, link_encoding); pic_width = timing->h_addressable + timing->h_border_left + timing->h_border_right; pic_height = timing->v_addressable + timing->v_border_top + timing->v_border_bottom; @@ -1080,6 +1081,7 @@ static bool setup_dsc_config( if (target_bandwidth_kbps > 0) { is_dsc_possible = decide_dsc_target_bpp_x16( &policy, + options, &dsc_common_caps, target_bandwidth_kbps, timing, @@ -1171,7 +1173,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps( void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, uint32_t max_target_bpp_limit_override_x16, - struct dc_dsc_policy *policy) + struct dc_dsc_policy *policy, + const enum dc_link_encoding_format link_encoding) { uint32_t bpc = 0; @@ -1235,10 +1238,7 @@ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, policy->max_target_bpp = max_target_bpp_limit_override_x16 / 16; /* enable DSC when not needed, default false */ - if (dsc_policy_enable_dsc_when_not_needed) - policy->enable_dsc_when_not_needed = dsc_policy_enable_dsc_when_not_needed; - else - policy->enable_dsc_when_not_needed = false; + policy->enable_dsc_when_not_needed = dsc_policy_enable_dsc_when_not_needed; } void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit) @@ -1267,4 +1267,5 @@ void dc_dsc_get_default_config_option(const struct dc *dc, struct dc_dsc_config_ options->dsc_force_odm_hslice_override = dc->debug.force_odm_combine; options->max_target_bpp_limit_override_x16 = 0; options->slice_height_granularity = 1; + options->force_dsc_when_not_needed = false; } diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c index 6293173ba2b9..5eb3da8d5206 100644 --- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c @@ -545,6 +545,7 @@ static void hubbub35_init(struct hubbub *hubbub) DCHUBBUB_ARB_MAX_REQ_OUTSTAND, 256, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 256); + memset(&hubbub2->watermarks.a.cstate_pstate, 0, sizeof(hubbub2->watermarks.a.cstate_pstate)); } /*static void hubbub35_set_request_limit(struct hubbub *hubbub, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index d52ce58c6a98..4fbed0298adf 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -57,6 +57,7 @@ #include "panel_cntl.h" #include "dc_state_priv.h" #include "dpcd_defs.h" +#include "dsc.h" /* include DCE11 register header files */ #include "dce/dce_11_0_d.h" #include "dce/dce_11_0_sh_mask.h" @@ -1823,6 +1824,48 @@ static void get_edp_links_with_sink( } } +static void clean_up_dsc_blocks(struct dc *dc) +{ + struct display_stream_compressor *dsc = NULL; + struct timing_generator *tg = NULL; + struct stream_encoder *se = NULL; + struct dccg *dccg = dc->res_pool->dccg; + struct pg_cntl *pg_cntl = dc->res_pool->pg_cntl; + int i; + + if (dc->ctx->dce_version != DCN_VERSION_3_5 && + dc->ctx->dce_version != DCN_VERSION_3_51) + return; + + for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) { + struct dcn_dsc_state s = {0}; + + dsc = dc->res_pool->dscs[i]; + dsc->funcs->dsc_read_state(dsc, &s); + if (s.dsc_fw_en) { + /* disable DSC in OPTC */ + if (i < dc->res_pool->timing_generator_count) { + tg = dc->res_pool->timing_generators[i]; + tg->funcs->set_dsc_config(tg, OPTC_DSC_DISABLED, 0, 0); + } + /* disable DSC in stream encoder */ + if (i < dc->res_pool->stream_enc_count) { + se = dc->res_pool->stream_enc[i]; + se->funcs->dp_set_dsc_config(se, OPTC_DSC_DISABLED, 0, 0); + se->funcs->dp_set_dsc_pps_info_packet(se, false, NULL, true); + } + /* disable DSC block */ + if (dccg->funcs->set_ref_dscclk) + dccg->funcs->set_ref_dscclk(dccg, dsc->inst); + dsc->funcs->dsc_disable(dsc); + + /* power down DSC */ + if (pg_cntl != NULL) + pg_cntl->funcs->dsc_pg_control(pg_cntl, dsc->inst, false); + } + } +} + /* * When ASIC goes from VBIOS/VGA mode to driver/accelerated mode we need: * 1. Power down all DC HW blocks @@ -1927,6 +1970,13 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context) clk_mgr_exit_optimized_pwr_state(dc, dc->clk_mgr); power_down_all_hw_blocks(dc); + + /* DSC could be enabled on eDP during VBIOS post. + * To clean up dsc blocks if eDP is in link but not active. + */ + if (edp_link_with_sink && (edp_stream_num == 0)) + clean_up_dsc_blocks(dc); + disable_vga_and_power_gate_all_controllers(dc); if (edp_link_with_sink && !keep_edp_vdd_on) dc->hwss.edp_power_control(edp_link_with_sink, false); @@ -2046,13 +2096,20 @@ static void set_drr(struct pipe_ctx **pipe_ctx, * as well. */ for (i = 0; i < num_pipes; i++) { - pipe_ctx[i]->stream_res.tg->funcs->set_drr( - pipe_ctx[i]->stream_res.tg, ¶ms); - - if (adjust.v_total_max != 0 && adjust.v_total_min != 0) - pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control( - pipe_ctx[i]->stream_res.tg, - event_triggers, num_frames); + /* dc_state_destruct() might null the stream resources, so fetch tg + * here first to avoid a race condition. The lifetime of the pointee + * itself (the timing_generator object) is not a problem here. + */ + struct timing_generator *tg = pipe_ctx[i]->stream_res.tg; + + if ((tg != NULL) && tg->funcs) { + if (tg->funcs->set_drr) + tg->funcs->set_drr(tg, ¶ms); + if (adjust.v_total_max != 0 && adjust.v_total_min != 0) + if (tg->funcs->set_static_screen_control) + tg->funcs->set_static_screen_control( + tg, event_triggers, num_frames); + } } } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index 42c52284a868..bded33575493 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -455,7 +455,7 @@ bool dcn30_mmhubbub_warmup( struct mcif_wb *mcif_wb; struct mcif_warmup_params warmup_params = {0}; unsigned int i, i_buf; - /*make sure there is no active DWB eanbled */ + /* make sure there is no active DWB enabled */ for (i = 0; i < num_dwb; i++) { dwb = dc->res_pool->dwbc[wb_info[i].dwb_pipe_inst]; if (dwb->dwb_is_efc_transition || dwb->dwb_is_drc) { diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index a36e11606f90..2e8c9f738259 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -1032,6 +1032,20 @@ void dcn32_update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) struct dsc_config dsc_cfg; struct dsc_optc_config dsc_optc_cfg = {0}; enum optc_dsc_mode optc_dsc_mode; + struct dcn_dsc_state dsc_state = {0}; + + if (!dsc) { + DC_LOG_DSC("DSC is NULL for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + + if (dsc->funcs->dsc_read_state) { + dsc->funcs->dsc_read_state(dsc, &dsc_state); + if (!dsc_state.dsc_fw_en) { + DC_LOG_DSC("DSC has been disabled for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + } /* Enable DSC hw block */ dsc_cfg.pic_width = (stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index 479fd3e89e5a..bd309dbdf7b2 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -334,7 +334,20 @@ static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) struct dsc_config dsc_cfg; struct dsc_optc_config dsc_optc_cfg = {0}; enum optc_dsc_mode optc_dsc_mode; + struct dcn_dsc_state dsc_state = {0}; + if (!dsc) { + DC_LOG_DSC("DSC is NULL for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + + if (dsc->funcs->dsc_read_state) { + dsc->funcs->dsc_read_state(dsc, &dsc_state); + if (!dsc_state.dsc_fw_en) { + DC_LOG_DSC("DSC has been disabled for tg instance %d:", pipe_ctx->stream_res.tg->inst); + return; + } + } /* Enable DSC hw block */ dsc_cfg.pic_width = (stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt; dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom; diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c index 46fb3649bc86..6499807af72a 100644 --- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dpia.c @@ -50,8 +50,31 @@ static void update_dpia_stream_allocation_table(struct dc_link *link, DC_LOG_MST("dpia : status[%d]: alloc_slots[%d]: used_slots[%d]\n", status, mst_alloc_slots, prev_mst_slots_in_use); - ASSERT(link_enc); - link_enc->funcs->update_mst_stream_allocation_table(link_enc, table); + if (link_enc) + link_enc->funcs->update_mst_stream_allocation_table(link_enc, table); +} + +static void set_dio_dpia_link_test_pattern(struct dc_link *link, + const struct link_resource *link_res, + struct encoder_set_dp_phy_pattern_param *tp_params) +{ + if (tp_params->dp_phy_pattern != DP_TEST_PATTERN_VIDEO_MODE) + return; + + struct link_encoder *link_enc = link_enc_cfg_get_link_enc(link); + + if (!link_enc) + return; + + link_enc->funcs->dp_set_phy_pattern(link_enc, tp_params); + link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_SET_SOURCE_PATTERN); +} + +static void set_dio_dpia_lane_settings(struct dc_link *link, + const struct link_resource *link_res, + const struct dc_link_settings *link_settings, + const struct dc_lane_settings lane_settings[LANE_COUNT_DP_MAX]) +{ } static const struct link_hwss dpia_link_hwss = { @@ -65,8 +88,8 @@ static const struct link_hwss dpia_link_hwss = { .ext = { .set_throttled_vcp_size = set_dio_throttled_vcp_size, .enable_dp_link_output = enable_dio_dp_link_output, - .set_dp_link_test_pattern = set_dio_dp_link_test_pattern, - .set_dp_lane_settings = set_dio_dp_lane_settings, + .set_dp_link_test_pattern = set_dio_dpia_link_test_pattern, + .set_dp_lane_settings = set_dio_dpia_lane_settings, .update_stream_allocation_table = update_dpia_stream_allocation_table, }, }; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index 1aed55b0ab6a..60f15a9ba7a5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -287,6 +287,13 @@ static bool dp_validate_mode_timing( req_bw = dc_bandwidth_in_kbps_from_timing(timing, dc_link_get_highest_encoding_format(link)); max_bw = dp_link_bandwidth_kbps(link, link_setting); + bool is_max_uncompressed_pixel_rate_exceeded = link->dpcd_caps.max_uncompressed_pixel_rate_cap.bits.valid && + timing->pix_clk_100hz > link->dpcd_caps.max_uncompressed_pixel_rate_cap.bits.max_uncompressed_pixel_rate_cap * 10000; + + if (is_max_uncompressed_pixel_rate_exceeded && !timing->flags.DSC) { + return false; + } + if (req_bw <= max_bw) { /* remember the biggest mode here, during * initial link training (to get diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index 34a618a7278b..d78c8ec4de79 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -1942,6 +1942,11 @@ static bool retrieve_link_cap(struct dc_link *link) DC_LOG_DP2("\tFEC aggregated error counters are supported"); } + core_link_read_dpcd(link, + DPCD_MAX_UNCOMPRESSED_PIXEL_RATE_CAP, + link->dpcd_caps.max_uncompressed_pixel_rate_cap.raw, + sizeof(link->dpcd_caps.max_uncompressed_pixel_rate_cap.raw)); + retrieve_cable_id(link); dpcd_write_cable_id_to_dprx(link); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 988999c44475..27b881f947e8 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -515,6 +515,41 @@ bool dp_is_interlane_aligned(union lane_align_status_updated align_status) return align_status.bits.INTERLANE_ALIGN_DONE == 1; } +bool dp_check_interlane_aligned(union lane_align_status_updated align_status, + struct dc_link *link, + uint8_t retries) +{ + /* Take into consideration corner case for DP 1.4a LL Compliance CTS as USB4 + * has to share encoders unlike DP and USBC + */ + return (dp_is_interlane_aligned(align_status) || + (link->skip_fallback_on_link_loss && retries)); +} + +uint32_t dp_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t offset, + uint8_t retries) +{ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (offset == 0 && retries == 1 && lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT) + return max(lt_settings->eq_pattern_time, (uint32_t) DPIA_CLK_SYNC_DELAY); + else + return dpia_get_eq_aux_rd_interval(link, lt_settings, offset); + } else if (is_repeater(lt_settings, offset)) + return dp_translate_training_aux_read_interval( + link->dpcd_caps.lttpr_caps.aux_rd_interval[offset - 1]); + else + return lt_settings->eq_pattern_time; +} + +bool dp_check_dpcd_reqeust_status(const struct dc_link *link, + enum dc_status status) +{ + return (status != DC_OK && link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA); +} + enum link_training_result dp_check_link_loss_status( struct dc_link *link, const struct link_training_settings *link_training_setting) @@ -973,13 +1008,17 @@ void repeater_training_done(struct dc_link *link, uint32_t offset) dpcd_pattern.v1_4.TRAINING_PATTERN_SET); } -static void dpcd_exit_training_mode(struct dc_link *link, enum dp_link_encoding encoding) +static enum link_training_result dpcd_exit_training_mode(struct dc_link *link, enum dp_link_encoding encoding) { + enum dc_status status; uint8_t sink_status = 0; uint8_t i; /* clear training pattern set */ - dpcd_set_training_pattern(link, DP_TRAINING_PATTERN_VIDEOIDLE); + status = dpcd_set_training_pattern(link, DP_TRAINING_PATTERN_VIDEOIDLE); + + if (dp_check_dpcd_reqeust_status(link, status)) + return LINK_TRAINING_ABORT; if (encoding == DP_128b_132b_ENCODING) { /* poll for intra-hop disable */ @@ -990,6 +1029,8 @@ static void dpcd_exit_training_mode(struct dc_link *link, enum dp_link_encoding fsleep(1000); } } + + return LINK_TRAINING_SUCCESS; } enum dc_status dpcd_configure_channel_coding(struct dc_link *link, @@ -1013,17 +1054,18 @@ enum dc_status dpcd_configure_channel_coding(struct dc_link *link, return status; } -void dpcd_set_training_pattern( +enum dc_status dpcd_set_training_pattern( struct dc_link *link, enum dc_dp_training_pattern training_pattern) { + enum dc_status status; union dpcd_training_pattern dpcd_pattern = {0}; dpcd_pattern.v1_4.TRAINING_PATTERN_SET = dp_training_pattern_to_dpcd_training_pattern( link, training_pattern); - core_link_write_dpcd( + status = core_link_write_dpcd( link, DP_TRAINING_PATTERN_SET, &dpcd_pattern.raw, @@ -1033,6 +1075,8 @@ void dpcd_set_training_pattern( __func__, DP_TRAINING_PATTERN_SET, dpcd_pattern.v1_4.TRAINING_PATTERN_SET); + + return status; } enum dc_status dpcd_set_link_settings( @@ -1185,6 +1229,13 @@ void dpcd_set_lt_pattern_and_lane_settings( dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - DP_TRAINING_PATTERN_SET] = dpcd_pattern.raw; + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + dpia_set_tps_notification( + link, + lt_settings, + dpcd_pattern.v1_4.TRAINING_PATTERN_SET, + offset); + if (is_repeater(lt_settings, offset)) { DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n 0x%X pattern = %x\n", __func__, @@ -1455,7 +1506,8 @@ static enum link_training_result dp_transition_to_video_idle( */ if (link->connector_signal != SIGNAL_TYPE_EDP && status == LINK_TRAINING_SUCCESS) { msleep(5); - status = dp_check_link_loss_status(link, lt_settings); + if (!link->skip_fallback_on_link_loss) + status = dp_check_link_loss_status(link, lt_settings); } return status; } @@ -1521,7 +1573,9 @@ enum link_training_result dp_perform_link_training( ASSERT(0); /* exit training mode */ - dpcd_exit_training_mode(link, encoding); + if ((dpcd_exit_training_mode(link, encoding) != LINK_TRAINING_SUCCESS || status == LINK_TRAINING_ABORT) && + link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + dpia_training_abort(link, <_settings, 0); /* switch to video idle */ if ((status == LINK_TRAINING_SUCCESS) || !skip_video_pattern) @@ -1599,8 +1653,7 @@ bool perform_link_training_with_retries( dp_perform_link_training_skip_aux(link, &pipe_ctx->link_res, &cur_link_settings); return true; } else { - /** @todo Consolidate USB4 DP and DPx.x training. */ - if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { + if (!link->dc->config.consolidated_dpia_dp_lt && link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { status = dpia_perform_link_training( link, &pipe_ctx->link_res, @@ -1629,8 +1682,17 @@ bool perform_link_training_with_retries( dp_trace_lt_total_count_increment(link, false); dp_trace_lt_result_update(link, status, false); dp_trace_set_lt_end_timestamp(link, false); - if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) + if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) { + // Update verified link settings to current one + // Because DPIA LT might fallback to lower link setting. + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { + link->verified_link_cap.link_rate = link->cur_link_settings.link_rate; + link->verified_link_cap.lane_count = link->cur_link_settings.lane_count; + dm_helpers_dp_mst_update_branch_bandwidth(link->ctx, link); + } return true; + } } fail_count++; diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h index 851bd17317a0..0b18aa35c33c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.h @@ -55,7 +55,7 @@ void dp_set_hw_test_pattern( uint8_t *custom_pattern, uint32_t custom_pattern_size); -void dpcd_set_training_pattern( +enum dc_status dpcd_set_training_pattern( struct dc_link *link, enum dc_dp_training_pattern training_pattern); @@ -182,4 +182,18 @@ uint32_t dp_translate_training_aux_read_interval( uint8_t dp_get_nibble_at_index(const uint8_t *buf, uint32_t index); + +bool dp_check_interlane_aligned(union lane_align_status_updated align_status, + struct dc_link *link, + uint8_t retries); + +uint32_t dp_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t offset, + uint8_t retries); + +bool dp_check_dpcd_reqeust_status(const struct dc_link *link, + enum dc_status status); + #endif /* __DC_LINK_DP_TRAINING_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c index 2b4c15b0b407..3bdce32a85e3 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_8b_10b.c @@ -157,6 +157,7 @@ enum link_training_result perform_8b_10b_clock_recovery_sequence( struct link_training_settings *lt_settings, uint32_t offset) { + enum dc_status status; uint32_t retries_cr; uint32_t retry_count; uint32_t wait_time_microsec; @@ -216,7 +217,7 @@ enum link_training_result perform_8b_10b_clock_recovery_sequence( /* 4. Read lane status and requested drive * settings as set by the sink */ - dp_get_lane_status_and_lane_adjust( + status = dp_get_lane_status_and_lane_adjust( link, lt_settings, dpcd_lane_status, @@ -224,6 +225,9 @@ enum link_training_result perform_8b_10b_clock_recovery_sequence( dpcd_lane_adjust, offset); + if (dp_check_dpcd_reqeust_status(link, status)) + return LINK_TRAINING_ABORT; + /* 5. check CR done*/ if (dp_is_cr_done(lane_count, dpcd_lane_status)) { DC_LOG_HW_LINK_TRAINING("%s: Clock recovery OK\n", __func__); @@ -273,6 +277,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( struct link_training_settings *lt_settings, uint32_t offset) { + enum dc_status status; enum dc_dp_training_pattern tr_pattern; uint32_t retries_ch_eq; uint32_t wait_time_microsec; @@ -308,12 +313,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( dpcd_set_lane_settings(link, lt_settings, offset); /* 3. wait for receiver to lock-on*/ - wait_time_microsec = lt_settings->eq_pattern_time; - - if (is_repeater(lt_settings, offset)) - wait_time_microsec = - dp_translate_training_aux_read_interval( - link->dpcd_caps.lttpr_caps.aux_rd_interval[offset - 1]); + wait_time_microsec = dp_get_eq_aux_rd_interval(link, lt_settings, offset, retries_ch_eq); dp_wait_for_training_aux_rd_interval( link, @@ -322,7 +322,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( /* 4. Read lane status and requested * drive settings as set by the sink*/ - dp_get_lane_status_and_lane_adjust( + status = dp_get_lane_status_and_lane_adjust( link, lt_settings, dpcd_lane_status, @@ -330,6 +330,9 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( dpcd_lane_adjust, offset); + if (dp_check_dpcd_reqeust_status(link, status)) + return LINK_TRAINING_ABORT; + /* 5. check CR done*/ if (!dp_is_cr_done(lane_count, dpcd_lane_status)) return dpcd_lane_status[0].bits.CR_DONE_0 ? @@ -339,7 +342,7 @@ enum link_training_result perform_8b_10b_channel_equalization_sequence( /* 6. check CHEQ done*/ if (dp_is_ch_eq_done(lane_count, dpcd_lane_status) && dp_is_symbol_locked(lane_count, dpcd_lane_status) && - dp_is_interlane_aligned(dpcd_lane_status_updated)) + dp_check_interlane_aligned(dpcd_lane_status_updated, link, retries_ch_eq)) return LINK_TRAINING_SUCCESS; /* 7. update VS/PE/PC2 in lt_settings*/ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c index cd1975c03f38..39e4b7dc9588 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.c @@ -43,9 +43,6 @@ #define DC_LOGGER \ link->ctx->logger -/* The approximate time (us) it takes to transmit 9 USB4 DP clock sync packets. */ -#define DPIA_CLK_SYNC_DELAY 16000 - /* Extend interval between training status checks for manual testing. */ #define DPIA_DEBUG_EXTENDED_AUX_RD_INTERVAL_US 60000000 @@ -566,28 +563,6 @@ static enum link_training_result dpia_training_cr_phase( return result; } -/* Return status read interval during equalization phase. */ -static uint32_t dpia_get_eq_aux_rd_interval( - const struct dc_link *link, - const struct link_training_settings *lt_settings, - uint32_t hop) -{ - uint32_t wait_time_microsec; - - if (hop == DPRX) - wait_time_microsec = lt_settings->eq_pattern_time; - else - wait_time_microsec = - dp_translate_training_aux_read_interval( - link->dpcd_caps.lttpr_caps.aux_rd_interval[hop - 1]); - - /* Check debug option for extending aux read interval. */ - if (link->dc->debug.dpia_debug.bits.extend_aux_rd_interval) - wait_time_microsec = DPIA_DEBUG_EXTENDED_AUX_RD_INTERVAL_US; - - return wait_time_microsec; -} - /* Execute equalization phase of link training for specified hop in display * path in non-transparent mode: * - driver issues both DPCD and SET_CONFIG transactions. @@ -936,6 +911,22 @@ static enum link_training_result dpia_training_end( return result; } +/* Return status read interval during equalization phase. */ +uint32_t dpia_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t hop) +{ + /* Check debug option for extending aux read interval. */ + if (link->dc->debug.dpia_debug.bits.extend_aux_rd_interval) + return DPIA_DEBUG_EXTENDED_AUX_RD_INTERVAL_US; + else if (hop == DPRX) + return lt_settings->eq_pattern_time; + else + return dp_translate_training_aux_read_interval( + link->dpcd_caps.lttpr_caps.aux_rd_interval[hop - 1]); +} + /* When aborting training of specified hop in display path, clean up by: * - Attempting to clear DPCD TRAINING_PATTERN_SET, LINK_BW_SET and LANE_COUNT_SET. * - Sending SET_CONFIG(SET_LINK) with lane count and link rate set to 0. @@ -943,7 +934,7 @@ static enum link_training_result dpia_training_end( * @param link DPIA link being trained. * @param hop Hop in display path. DPRX = 0. */ -static void dpia_training_abort( +void dpia_training_abort( struct dc_link *link, struct link_training_settings *lt_settings, uint32_t hop) @@ -968,7 +959,26 @@ static void dpia_training_abort( core_link_write_dpcd(link, dpcd_tps_offset, &data, 1); core_link_write_dpcd(link, DP_LINK_BW_SET, &data, 1); core_link_write_dpcd(link, DP_LANE_COUNT_SET, &data, 1); - core_link_send_set_config(link, DPIA_SET_CFG_SET_LINK, data); + + if (!link->dc->config.consolidated_dpia_dp_lt) + core_link_send_set_config(link, DPIA_SET_CFG_SET_LINK, data); +} + +void dpia_set_tps_notification( + struct dc_link *link, + const struct link_training_settings *lt_settings, + uint8_t pattern, + uint32_t hop) +{ + uint8_t repeater_cnt = 0; /* Number of hops/repeaters in display path. */ + + if (lt_settings->lttpr_mode != LTTPR_MODE_NON_TRANSPARENT || pattern == DPCD_TRAINING_PATTERN_VIDEOIDLE) + return; + + repeater_cnt = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt); + + if (hop != repeater_cnt) + dc_process_dmub_dpia_set_tps_notification(link->ctx->dc, link->link_index, pattern); } enum link_training_result dpia_perform_link_training( diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h index b39fb9faf1c2..9f4eceb494c2 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_dpia.h @@ -28,6 +28,9 @@ #define __DC_LINK_DP_TRAINING_DPIA_H__ #include "link_dp_training.h" +/* The approximate time (us) it takes to transmit 9 USB4 DP clock sync packets. */ +#define DPIA_CLK_SYNC_DELAY 16000 + /* Train DP tunneling link for USB4 DPIA display endpoint. * DPIA equivalent of dc_link_dp_perfrorm_link_training. * Aborts link training upon detection of sink unplug. @@ -38,4 +41,20 @@ enum link_training_result dpia_perform_link_training( const struct dc_link_settings *link_setting, bool skip_video_pattern); +void dpia_training_abort( + struct dc_link *link, + struct link_training_settings *lt_settings, + uint32_t hop); + +uint32_t dpia_get_eq_aux_rd_interval( + const struct dc_link *link, + const struct link_training_settings *lt_settings, + uint32_t hop); + +void dpia_set_tps_notification( + struct dc_link *link, + const struct link_training_settings *lt_settings, + uint8_t pattern, + uint32_t offset); + #endif /* __DC_LINK_DP_TRAINING_DPIA_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c index 46ad684fe192..893a9d9ee870 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c @@ -2155,6 +2155,7 @@ static bool dcn35_resource_construct( dc->dml2_options.max_segments_per_hubp = 24; dc->dml2_options.det_segment_size = DCN3_2_DET_SEG_SIZE;/*todo*/ + dc->dml2_options.override_det_buffer_size_kbytes = true; if (dc->config.sdpif_request_limit_words_per_umc == 0) dc->config.sdpif_request_limit_words_per_umc = 16;/*todo*/ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c index 4c5e722baa3a..da9101b83e8c 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c @@ -736,7 +736,7 @@ static const struct dc_debug_options debug_defaults_drv = { .hdmichar = true, .dpstream = true, .symclk32_se = true, - .symclk32_le = true, + .symclk32_le = false, .symclk_fe = true, .physymclk = false, .dpiasymclk = true, @@ -2133,6 +2133,7 @@ static bool dcn351_resource_construct( dc->dml2_options.max_segments_per_hubp = 24; dc->dml2_options.det_segment_size = DCN3_2_DET_SEG_SIZE;/*todo*/ + dc->dml2_options.override_det_buffer_size_kbytes = true; if (dc->config.sdpif_request_limit_words_per_umc == 0) dc->config.sdpif_request_limit_words_per_umc = 16;/*todo*/ diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c index 15f7eda903e6..014e8a296f0c 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c @@ -813,6 +813,14 @@ static bool enable_easf(struct spl_in *spl_in, struct spl_scratch *spl_scratch) return skip_easf; } +/* Check if video is in fullscreen mode */ +static bool spl_is_video_fullscreen(struct spl_in *spl_in) +{ + if (spl_is_yuv420(spl_in->basic_in.format) && spl_in->is_fullscreen) + return true; + return false; +} + static bool spl_get_isharp_en(struct spl_in *spl_in, struct spl_scratch *spl_scratch) { @@ -820,6 +828,7 @@ static bool spl_get_isharp_en(struct spl_in *spl_in, int vratio = 0; int hratio = 0; struct spl_taps taps = spl_scratch->scl_data.taps; + bool fullscreen = spl_is_video_fullscreen(spl_in); /* Return if adaptive sharpness is disabled */ if (spl_in->adaptive_sharpness.enable == false) @@ -835,9 +844,18 @@ static bool spl_get_isharp_en(struct spl_in *spl_in, // Scaling is up to 1:1 (no scaling) or upscaling /* - * Apply sharpness to all RGB surfaces and to - * NV12/P010 surfaces + * Apply sharpness to RGB and YUV (NV12/P010) + * surfaces based on policy setting */ + if (!spl_is_yuv420(spl_in->basic_in.format) && + (spl_in->debug.sharpen_policy == SHARPEN_YUV)) + return enable_isharp; + else if ((spl_is_yuv420(spl_in->basic_in.format) && !fullscreen) && + (spl_in->debug.sharpen_policy == SHARPEN_RGB_FULLSCREEN_YUV)) + return enable_isharp; + else if (!spl_in->is_fullscreen && + spl_in->debug.sharpen_policy == SHARPEN_FULLSCREEN_ALL) + return enable_isharp; /* * Apply sharpness if supports horizontal taps 4,6 AND @@ -1155,14 +1173,19 @@ static void spl_set_dscl_prog_data(struct spl_in *spl_in, struct spl_scratch *sp } /* Calculate C0-C3 coefficients based on HDR_mult */ -static void spl_calculate_c0_c3_hdr(struct dscl_prog_data *dscl_prog_data, uint32_t hdr_multx100) +static void spl_calculate_c0_c3_hdr(struct dscl_prog_data *dscl_prog_data, uint32_t sdr_white_level_nits) { struct spl_fixed31_32 hdr_mult, c0_mult, c1_mult, c2_mult; struct spl_fixed31_32 c0_calc, c1_calc, c2_calc; struct spl_custom_float_format fmt; + uint32_t hdr_multx100_int; - SPL_ASSERT(hdr_multx100); - hdr_mult = spl_fixpt_from_fraction((long long)hdr_multx100, 100LL); + if ((sdr_white_level_nits >= 80) && (sdr_white_level_nits <= 480)) + hdr_multx100_int = sdr_white_level_nits * 100 / 80; + else + hdr_multx100_int = 100; /* default for 80 nits otherwise */ + + hdr_mult = spl_fixpt_from_fraction((long long)hdr_multx100_int, 100LL); c0_mult = spl_fixpt_from_fraction(2126LL, 10000LL); c1_mult = spl_fixpt_from_fraction(7152LL, 10000LL); c2_mult = spl_fixpt_from_fraction(722LL, 10000LL); @@ -1191,7 +1214,7 @@ static void spl_calculate_c0_c3_hdr(struct dscl_prog_data *dscl_prog_data, uint3 static void spl_set_easf_data(struct spl_scratch *spl_scratch, struct spl_out *spl_out, bool enable_easf_v, bool enable_easf_h, enum linear_light_scaling lls_pref, enum spl_pixel_format format, enum system_setup setup, - uint32_t hdr_multx100) + uint32_t sdr_white_level_nits) { struct dscl_prog_data *dscl_prog_data = spl_out->dscl_prog_data; if (enable_easf_v) { @@ -1499,7 +1522,7 @@ static void spl_set_easf_data(struct spl_scratch *spl_scratch, struct spl_out *s dscl_prog_data->easf_ltonl_en = 1; // Linear input if ((setup == HDR_L) && (spl_is_rgb8(format))) { /* Calculate C0-C3 coefficients based on HDR multiplier */ - spl_calculate_c0_c3_hdr(dscl_prog_data, hdr_multx100); + spl_calculate_c0_c3_hdr(dscl_prog_data, sdr_white_level_nits); } else { // HDR_L ( DWM ) and SDR_L dscl_prog_data->easf_matrix_c0 = 0x4EF7; // fp1.5.10, C0 coefficient (LN_rec709: 0.2126 * (2^14)/125 = 27.86590720) @@ -1557,7 +1580,7 @@ static void spl_set_isharp_data(struct dscl_prog_data *dscl_prog_data, struct adaptive_sharpness adp_sharpness, bool enable_isharp, enum linear_light_scaling lls_pref, enum spl_pixel_format format, const struct spl_scaler_data *data, struct spl_fixed31_32 ratio, - enum system_setup setup) + enum system_setup setup, enum scale_to_sharpness_policy scale_to_sharpness_policy) { /* Turn off sharpener if not required */ if (!enable_isharp) { @@ -1565,6 +1588,11 @@ static void spl_set_isharp_data(struct dscl_prog_data *dscl_prog_data, return; } + spl_build_isharp_1dlut_from_reference_curve(ratio, setup, adp_sharpness, + scale_to_sharpness_policy); + dscl_prog_data->isharp_delta = spl_get_pregen_filter_isharp_1D_lut(setup); + dscl_prog_data->sharpness_level = adp_sharpness.sharpness_level; + dscl_prog_data->isharp_en = 1; // ISHARP_EN // Set ISHARP_NOISEDET_MODE if htaps = 6-tap if (data->taps.h_taps == 6) { @@ -1662,11 +1690,6 @@ static void spl_set_isharp_data(struct dscl_prog_data *dscl_prog_data, dscl_prog_data->isharp_lba.base_seg[5] = 0; // ISHARP LBA PWL for Seg 5. BASE value in U0.6 format } - - spl_build_isharp_1dlut_from_reference_curve(ratio, setup, adp_sharpness); - dscl_prog_data->isharp_delta = spl_get_pregen_filter_isharp_1D_lut(setup); - dscl_prog_data->sharpness_level = adp_sharpness.sharpness_level; - // Program the nldelta soft clip values if (lls_pref == LLS_PREF_YES) { dscl_prog_data->isharp_nldelta_sclip.enable_p = 0; /* ISHARP_NLDELTA_SCLIP_EN_P */ @@ -1750,7 +1773,7 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) // Set EASF spl_set_easf_data(&spl_scratch, spl_out, enable_easf_v, enable_easf_h, spl_in->lls_pref, - spl_in->basic_in.format, setup, spl_in->hdr_multx100); + spl_in->basic_in.format, setup, spl_in->sdr_white_level_nits); // Set iSHARP vratio = spl_fixpt_ceil(spl_scratch.scl_data.ratios.vert); @@ -1761,7 +1784,8 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out) isharp_scale_ratio = spl_scratch.scl_data.recip_ratios.horz; spl_set_isharp_data(spl_out->dscl_prog_data, spl_in->adaptive_sharpness, enable_isharp, - spl_in->lls_pref, spl_in->basic_in.format, data, isharp_scale_ratio, setup); + spl_in->lls_pref, spl_in->basic_in.format, data, isharp_scale_ratio, setup, + spl_in->debug.scale_to_sharpness_policy); return res; } diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c index 33712f50d303..e0572252c640 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.c @@ -500,6 +500,15 @@ struct isharp_1D_lut_pregen filter_isharp_1D_lut_pregen[NUM_SHARPNESS_SETUPS] = }, }; +struct scale_ratio_to_sharpness_level_adj sharpness_level_adj[NUM_SHARPNESS_ADJ_LEVELS] = { + {1125, 1000, 0}, + {11, 10, 1}, + {1075, 1000, 2}, + {105, 100, 3}, + {1025, 1000, 4}, + {1, 1, 5}, +}; + const uint32_t *spl_get_filter_isharp_1D_lut_0(void) { return filter_isharp_1D_lut_0; @@ -541,19 +550,72 @@ uint16_t *spl_get_filter_isharp_bs_3tap_64p(void) return filter_isharp_bs_3tap_64p_s1_12; } -static unsigned int spl_calculate_sharpness_level(int discrete_sharpness_level, enum system_setup setup, - struct spl_sharpness_range sharpness_range) +static unsigned int spl_calculate_sharpness_level_adj(struct spl_fixed31_32 ratio) +{ + int j; + struct spl_fixed31_32 ratio_level; + struct scale_ratio_to_sharpness_level_adj *lookup_ptr; + unsigned int sharpness_level_down_adj; + + /* + * Adjust sharpness level based on current scaling ratio + * + * We have 5 discrete scaling ratios which we will use to adjust the + * sharpness level down by 1 as we pass each ratio. The ratios + * are + * + * 1.125 upscale and higher - no adj + * 1.100 - under 1.125 - adj level down 1 + * 1.075 - under 1.100 - adj level down 2 + * 1.050 - under 1.075 - adj level down 3 + * 1.025 - under 1.050 - adj level down 4 + * 1.000 - under 1.025 - adj level down 5 + * + */ + j = 0; + sharpness_level_down_adj = 0; + lookup_ptr = sharpness_level_adj; + while (j < NUM_SHARPNESS_ADJ_LEVELS) { + ratio_level = spl_fixpt_from_fraction(lookup_ptr->ratio_numer, + lookup_ptr->ratio_denom); + if (ratio.value >= ratio_level.value) { + sharpness_level_down_adj = lookup_ptr->level_down_adj; + break; + } + lookup_ptr++; + j++; + } + return sharpness_level_down_adj; +} + +static unsigned int spl_calculate_sharpness_level(struct spl_fixed31_32 ratio, + int discrete_sharpness_level, enum system_setup setup, + struct spl_sharpness_range sharpness_range, + enum scale_to_sharpness_policy scale_to_sharpness_policy) { unsigned int sharpness_level = 0; + unsigned int sharpness_level_down_adj = 0; int min_sharpness, max_sharpness, mid_sharpness; + /* + * Adjust sharpness level if policy requires we adjust it based on + * scale ratio. Based on scale ratio, we may adjust the sharpness + * level down by a certain number of steps. We will not select + * a sharpness value of 0 so the lowest sharpness level will be + * 0 or 1 depending on what the min_sharpness is + * + * If the policy is no required, this code maybe removed at a later + * date + */ switch (setup) { case HDR_L: min_sharpness = sharpness_range.hdr_rgb_min; max_sharpness = sharpness_range.hdr_rgb_max; mid_sharpness = sharpness_range.hdr_rgb_mid; + if (scale_to_sharpness_policy == SCALE_TO_SHARPNESS_ADJ_ALL) + sharpness_level_down_adj = spl_calculate_sharpness_level_adj(ratio); break; case HDR_NL: /* currently no use case, use Non-linear SDR values for now */ @@ -561,15 +623,26 @@ static unsigned int spl_calculate_sharpness_level(int discrete_sharpness_level, min_sharpness = sharpness_range.sdr_yuv_min; max_sharpness = sharpness_range.sdr_yuv_max; mid_sharpness = sharpness_range.sdr_yuv_mid; + if (scale_to_sharpness_policy >= SCALE_TO_SHARPNESS_ADJ_YUV) + sharpness_level_down_adj = spl_calculate_sharpness_level_adj(ratio); break; case SDR_L: default: min_sharpness = sharpness_range.sdr_rgb_min; max_sharpness = sharpness_range.sdr_rgb_max; mid_sharpness = sharpness_range.sdr_rgb_mid; + if (scale_to_sharpness_policy == SCALE_TO_SHARPNESS_ADJ_ALL) + sharpness_level_down_adj = spl_calculate_sharpness_level_adj(ratio); break; } + if ((min_sharpness == 0) && (sharpness_level_down_adj >= discrete_sharpness_level)) + discrete_sharpness_level = 1; + else if (sharpness_level_down_adj >= discrete_sharpness_level) + discrete_sharpness_level = 0; + else + discrete_sharpness_level -= sharpness_level_down_adj; + int lower_half_step_size = (mid_sharpness - min_sharpness) / 5; int upper_half_step_size = (max_sharpness - mid_sharpness) / 5; @@ -584,7 +657,7 @@ static unsigned int spl_calculate_sharpness_level(int discrete_sharpness_level, } void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, enum system_setup setup, - struct adaptive_sharpness sharpness) + struct adaptive_sharpness sharpness, enum scale_to_sharpness_policy scale_to_sharpness_policy) { uint8_t *byte_ptr_1dlut_src, *byte_ptr_1dlut_dst; struct spl_fixed31_32 sharp_base, sharp_calc, sharp_level; @@ -594,8 +667,9 @@ void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, en uint32_t filter_pregen_store[ISHARP_LUT_TABLE_SIZE]; /* Custom sharpnessX1000 value */ - unsigned int sharpnessX1000 = spl_calculate_sharpness_level(sharpness.sharpness_level, - setup, sharpness.sharpness_range); + unsigned int sharpnessX1000 = spl_calculate_sharpness_level(ratio, + sharpness.sharpness_level, setup, + sharpness.sharpness_range, scale_to_sharpness_policy); sharp_level = spl_fixpt_from_fraction(sharpnessX1000, 1000); /* @@ -606,7 +680,6 @@ void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, en (filter_isharp_1D_lut_pregen[setup].sharpness_denom == 1000)) return; - /* * Calculate LUT_128_gained with this equation: * diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h index fe0b12571f2c..afcc66206ca2 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_isharp_filters.h @@ -20,11 +20,11 @@ uint16_t *spl_get_filter_isharp_bs_3tap_64p(void); const uint16_t *spl_get_filter_isharp_wide_6tap_64p(void); uint16_t *spl_dscl_get_blur_scale_coeffs_64p(int taps); -struct scale_ratio_to_sharpness_level_lookup { +#define NUM_SHARPNESS_ADJ_LEVELS 6 +struct scale_ratio_to_sharpness_level_adj { unsigned int ratio_numer; unsigned int ratio_denom; - unsigned int sharpness_numer; - unsigned int sharpness_denom; + unsigned int level_down_adj; /* adjust sharpness level down */ }; struct isharp_1D_lut_pregen { @@ -45,6 +45,7 @@ void spl_init_blur_scale_coeffs(void); void spl_set_blur_scale_data(struct dscl_prog_data *dscl_prog_data, const struct spl_scaler_data *data); -void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, enum system_setup setup, struct adaptive_sharpness sharpness); +void spl_build_isharp_1dlut_from_reference_curve(struct spl_fixed31_32 ratio, enum system_setup setup, + struct adaptive_sharpness sharpness, enum scale_to_sharpness_policy scale_to_sharpness_policy); uint32_t *spl_get_pregen_filter_isharp_1D_lut(enum system_setup setup); #endif /* __DC_SPL_ISHARP_FILTERS_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h index 85b19ebe2c57..2a74ff5fdfdb 100644 --- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h +++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl_types.h @@ -487,6 +487,17 @@ enum linear_light_scaling { // convert it in translation logic LLS_PREF_YES, LLS_PREF_NO }; +enum sharpen_policy { + SHARPEN_ALWAYS = 0, + SHARPEN_YUV = 1, + SHARPEN_RGB_FULLSCREEN_YUV = 2, + SHARPEN_FULLSCREEN_ALL = 3 +}; +enum scale_to_sharpness_policy { + NO_SCALE_TO_SHARPNESS_ADJ = 0, + SCALE_TO_SHARPNESS_ADJ_YUV = 1, + SCALE_TO_SHARPNESS_ADJ_ALL = 2 +}; struct spl_funcs { void (*spl_calc_lb_num_partitions) (bool alpha_en, @@ -499,6 +510,8 @@ struct spl_funcs { struct spl_debug { int visual_confirm_base_offset; int visual_confirm_dpp_offset; + enum sharpen_policy sharpen_policy; + enum scale_to_sharpness_policy scale_to_sharpness_policy; }; struct spl_in { @@ -518,7 +531,7 @@ struct spl_in { bool is_hdr_on; int h_active; int v_active; - int hdr_multx100; + int sdr_white_level_nits; }; // end of SPL inputs diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index cd70453aeae0..fe5b6f7a3eb1 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -300,6 +300,7 @@ struct dmub_srv_hw_params { enum dmub_ips_disable_type disable_ips; bool disallow_phy_access; bool disable_sldo_opt; + bool enable_non_transparent_setconfig; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index e20c220aa8b4..ebcf68bfae2b 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -682,7 +682,7 @@ union dmub_fw_boot_options { uint32_t gpint_scratch8: 1; /* 1 if GPINT is in scratch8*/ uint32_t usb4_cm_version: 1; /**< 1 CM support */ uint32_t dpia_hpd_int_enable_supported: 1; /* 1 if dpia hpd int enable supported */ - uint32_t reserved0: 1; + uint32_t enable_non_transparent_setconfig: 1; /* 1 if dpia use conventional dp lt flow*/ uint32_t disable_clk_ds: 1; /* 1 if disallow dispclk_ds and dppclk_ds*/ uint32_t disable_timeout_recovery : 1; /* 1 if timeout recovery should be disabled */ uint32_t ips_pg_disable: 1; /* 1 to disable ONO domains power gating*/ @@ -1308,6 +1308,7 @@ enum dmub_cmd_dpia_type { DMUB_CMD__DPIA_DIG1_DPIA_CONTROL = 0, DMUB_CMD__DPIA_SET_CONFIG_ACCESS = 1, DMUB_CMD__DPIA_MST_ALLOC_SLOTS = 2, + DMUB_CMD__DPIA_SET_TPS_NOTIFICATION = 3, }; /* DMUB_OUT_CMD__DPIA_NOTIFICATION command types. */ @@ -2139,6 +2140,24 @@ struct dmub_rb_cmd_set_mst_alloc_slots { }; /** + * Data passed from driver to FW in a DMUB_CMD__SET_TPS_NOTIFICATION command. + */ +struct dmub_cmd_tps_notification_data { + uint8_t instance; /* DPIA instance */ + uint8_t tps; /* requested training pattern */ + uint8_t reserved1; + uint8_t reserved2; +}; + +/** + * DMUB command structure for SET_TPS_NOTIFICATION command. + */ +struct dmub_rb_cmd_set_tps_notification { + struct dmub_cmd_header header; /* header */ + struct dmub_cmd_tps_notification_data tps_notification; /* set tps_notification data */ +}; + +/** * DMUB command structure for DPIA HPD int enable control. */ struct dmub_rb_cmd_dpia_hpd_int_enable { @@ -5305,6 +5324,10 @@ union dmub_rb_cmd { */ struct dmub_rb_cmd_set_mst_alloc_slots set_mst_alloc_slots; /** + * Definition of a DMUB_CMD__DPIA_SET_TPS_NOTIFICATION command. + */ + struct dmub_rb_cmd_set_tps_notification set_tps_notification; + /** * Definition of a DMUB_CMD__EDID_CEA command. */ struct dmub_rb_cmd_edid_cea edid_cea; diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c index 746696b6f09a..2ccad79053c5 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c @@ -425,6 +425,7 @@ void dmub_dcn35_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu boot_options.bits.ips_disable = params->disable_ips; boot_options.bits.ips_sequential_ono = params->ips_sequential_ono; boot_options.bits.disable_sldo_opt = params->disable_sldo_opt; + boot_options.bits.enable_non_transparent_setconfig = params->enable_non_transparent_setconfig; REG_WRITE(DMCUB_SCRATCH14, boot_options.all); } diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index a40e6590215a..bbd259cea4f4 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -134,7 +134,7 @@ unsigned int mod_freesync_calc_v_total_from_refresh( v_total = div64_u64(div64_u64(((unsigned long long)( frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)), - stream->timing.h_total), 1000000); + stream->timing.h_total) + 500000, 1000000); /* v_total cannot be less than nominal */ if (v_total < stream->timing.v_total) { diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 745fd052840d..3f91926a50e9 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -85,7 +85,7 @@ enum amd_apu_flags { * @AMD_IP_BLOCK_TYPE_MES: Micro-Engine Scheduler * @AMD_IP_BLOCK_TYPE_JPEG: JPEG Engine * @AMD_IP_BLOCK_TYPE_VPE: Video Processing Engine -* @AMD_IP_BLOCK_TYPE_UMSCH_MM: User Mode Schduler for Multimedia +* @AMD_IP_BLOCK_TYPE_UMSCH_MM: User Mode Scheduler for Multimedia * @AMD_IP_BLOCK_TYPE_ISP: Image Signal Processor * @AMD_IP_BLOCK_TYPE_NUM: Total number of IP block types */ diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index 7744ca3ef4b1..e3e635a31b8a 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -71,6 +71,11 @@ enum kgd_memory_pool { KGD_POOL_FRAMEBUFFER = 3, }; +struct kfd_cu_occupancy { + u32 wave_cnt; + u32 doorbell_off; +}; + /** * enum kfd_sched_policy * @@ -313,8 +318,9 @@ struct kfd2kgd_calls { uint32_t grace_period, uint32_t *reg_offset, uint32_t *reg_data); - void (*get_cu_occupancy)(struct amdgpu_device *adev, int pasid, - int *wave_cnt, int *max_waves_per_cu, uint32_t inst); + void (*get_cu_occupancy)(struct amdgpu_device *adev, + struct kfd_cu_occupancy *cu_occupancy, + int *max_waves_per_cu, uint32_t inst); void (*program_trap_handler_settings)(struct amdgpu_device *adev, uint32_t vmid, uint64_t tba_addr, uint64_t tma_addr, uint32_t inst); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h index 0b3c2f54a343..822c6425d90e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h @@ -123,7 +123,7 @@ typedef enum { VOLTAGE_GUARDBAND_COUNT } GFX_GUARDBAND_e; -#define SMU_METRICS_TABLE_VERSION 0xC +#define SMU_METRICS_TABLE_VERSION 0xD typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; @@ -227,6 +227,10 @@ typedef struct __attribute__((packed, aligned(4))) { // PCIE LINK Speed and width uint32_t PCIeLinkSpeed; uint32_t PCIeLinkWidth; + + // PER XCD ACTIVITY + uint32_t GfxBusy[8]; + uint64_t GfxBusyAcc[8]; } MetricsTableX_t; typedef struct __attribute__((packed, aligned(4))) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index a887ab945dfa..1d024b122b0c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2569,10 +2569,14 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, } } - return smu_cmn_send_smc_msg_with_param(smu, + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask, workload_mask, NULL); + if (!ret) + smu->workload_mask = workload_mask; + + return ret; } static bool smu_v13_0_0_is_mode1_reset_supported(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 9974c9f8135e..55ed6247eb61 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -2107,8 +2107,12 @@ static int smu_v13_0_6_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_v13_0_6_request_i2c_xfer(smu, req); - if (r) - goto fail; + if (r) { + /* Retry once, in case of an i2c collision */ + r = smu_v13_0_6_request_i2c_xfer(smu, req); + if (r) + goto fail; + } for (c = i = 0; i < num_msgs; i++) { if (!(msg[i].flags & I2C_M_RD)) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 7bc95c404377..b891a5e0a396 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2501,8 +2501,11 @@ static int smu_v13_0_7_set_power_profile_mode(struct smu_context *smu, long *inp return -EINVAL; ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask, 1 << workload_type, NULL); + if (ret) dev_err(smu->adev->dev, "[%s] Failed to set work load mask!", __func__); + else + smu->workload_mask = (1 << workload_type); return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 43820d7d2c54..5899d01fa73d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1861,10 +1861,14 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu, if (workload_type < 0) return -EINVAL; - return smu_cmn_send_smc_msg_with_param(smu, + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask, 1 << workload_type, NULL); + if (!ret) + smu->workload_mask = 1 << workload_type; + + return ret; } static int smu_v14_0_2_baco_enter(struct smu_context *smu) diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 07e493d14d0c..ad1dc638c83b 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -103,7 +103,6 @@ bool drm_dev_needs_global_mutex(struct drm_device *dev) * .compat_ioctl = drm_compat_ioctl, // NULL if CONFIG_COMPAT=n * .poll = drm_poll, * .read = drm_read, - * .llseek = no_llseek, * .mmap = drm_gem_mmap, * }; * diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 00fbe9f8c03a..b1c294236cc8 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -916,7 +916,7 @@ intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port, * instead of a specific AUX_IO_<port> reference without powering up any * extra wells. */ - if (intel_encoder_can_psr(&dig_port->base)) + if (intel_psr_needs_aux_io_power(&dig_port->base, crtc_state)) return intel_display_power_aux_io_domain(i915, dig_port->aux_ch); else if (DISPLAY_VER(i915) < 14 && (intel_crtc_has_dp_encoder(crtc_state) || diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index a1fcedfd404b..90fa73575feb 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -531,6 +531,10 @@ static void intel_dp_set_source_rates(struct intel_dp *intel_dp) { /* The values must be in increasing order */ + static const int bmg_rates[] = { + 162000, 216000, 243000, 270000, 324000, 432000, 540000, 675000, + 810000, 1000000, 1350000, + }; static const int mtl_rates[] = { 162000, 216000, 243000, 270000, 324000, 432000, 540000, 675000, 810000, 1000000, 2000000, @@ -561,8 +565,13 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp) intel_dp->source_rates || intel_dp->num_source_rates); if (DISPLAY_VER(dev_priv) >= 14) { - source_rates = mtl_rates; - size = ARRAY_SIZE(mtl_rates); + if (IS_BATTLEMAGE(dev_priv)) { + source_rates = bmg_rates; + size = ARRAY_SIZE(bmg_rates); + } else { + source_rates = mtl_rates; + size = ARRAY_SIZE(mtl_rates); + } max_rate = mtl_max_source_rate(intel_dp); } else if (DISPLAY_VER(dev_priv) >= 11) { source_rates = icl_rates; @@ -4058,6 +4067,9 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector drm_dp_is_branch(intel_dp->dpcd)); intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + intel_dp->colorimetry_support = + intel_dp_get_colorimetry_status(intel_dp); + /* * Read the eDP display control registers. * @@ -4171,6 +4183,9 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident); + intel_dp->colorimetry_support = + intel_dp_get_colorimetry_status(intel_dp); + intel_dp_update_sink_caps(intel_dp); } @@ -6922,9 +6937,6 @@ intel_dp_init_connector(struct intel_digital_port *dig_port, "HDCP init failed, skipping.\n"); } - intel_dp->colorimetry_support = - intel_dp_get_colorimetry_status(intel_dp); - intel_dp->frl.is_trained = false; intel_dp->frl.trained_rate_gbps = 0; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 1f83b3b67ea6..136a0d6ca970 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -203,6 +203,25 @@ bool intel_encoder_can_psr(struct intel_encoder *encoder) return false; } +bool intel_psr_needs_aux_io_power(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + /* + * For PSR/PR modes only eDP requires the AUX IO power to be enabled whenever + * the output is enabled. For non-eDP outputs the main link is always + * on, hence it doesn't require the HW initiated AUX wake-up signaling used + * for eDP. + * + * TODO: + * - Consider leaving AUX IO disabled for eDP / PR as well, in case + * the ALPM with main-link off mode is not enabled. + * - Leave AUX IO enabled for DP / PR, once support for ALPM with + * main-link off mode is added for it and this mode gets enabled. + */ + return intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP) && + intel_encoder_can_psr(encoder); +} + static bool psr_global_enabled(struct intel_dp *intel_dp) { struct intel_display *display = to_intel_display(intel_dp); @@ -2784,13 +2803,6 @@ static int _psr1_ready_for_pipe_update_locked(struct intel_dp *intel_dp) EDP_PSR_STATUS_STATE_MASK, 50); } -static int _panel_replay_ready_for_pipe_update_locked(struct intel_dp *intel_dp) -{ - return intel_dp_is_edp(intel_dp) ? - _psr2_ready_for_pipe_update_locked(intel_dp) : - _psr1_ready_for_pipe_update_locked(intel_dp); -} - /** * intel_psr_wait_for_idle_locked - wait for PSR be ready for a pipe update * @new_crtc_state: new CRTC state @@ -2813,12 +2825,10 @@ void intel_psr_wait_for_idle_locked(const struct intel_crtc_state *new_crtc_stat lockdep_assert_held(&intel_dp->psr.lock); - if (!intel_dp->psr.enabled) + if (!intel_dp->psr.enabled || intel_dp->psr.panel_replay_enabled) continue; - if (intel_dp->psr.panel_replay_enabled) - ret = _panel_replay_ready_for_pipe_update_locked(intel_dp); - else if (intel_dp->psr.sel_update_enabled) + if (intel_dp->psr.sel_update_enabled) ret = _psr2_ready_for_pipe_update_locked(intel_dp); else ret = _psr1_ready_for_pipe_update_locked(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h index 4e09c10908e4..6eb5f15f674f 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.h +++ b/drivers/gpu/drm/i915/display/intel_psr.h @@ -25,6 +25,8 @@ struct intel_plane_state; (intel_dp)->psr.source_panel_replay_support) bool intel_encoder_can_psr(struct intel_encoder *encoder); +bool intel_psr_needs_aux_io_power(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); void intel_psr_init_dpcd(struct intel_dp *intel_dp); void intel_psr_enable_sink(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 025a79fe5920..2406cda75b7b 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -3751,7 +3751,6 @@ static int i915_perf_release(struct inode *inode, struct file *file) static const struct file_operations fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .release = i915_perf_release, .poll = i915_perf_poll, .read = i915_perf_read, diff --git a/drivers/gpu/drm/msm/msm_perf.c b/drivers/gpu/drm/msm/msm_perf.c index 3d3da79fec2a..d3c7889aaf26 100644 --- a/drivers/gpu/drm/msm/msm_perf.c +++ b/drivers/gpu/drm/msm/msm_perf.c @@ -192,7 +192,6 @@ static const struct file_operations perf_debugfs_fops = { .owner = THIS_MODULE, .open = perf_open, .read = perf_read, - .llseek = no_llseek, .release = perf_release, }; diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c index ca44fd291c5b..39138e190cb9 100644 --- a/drivers/gpu/drm/msm/msm_rd.c +++ b/drivers/gpu/drm/msm/msm_rd.c @@ -227,7 +227,6 @@ static const struct file_operations rd_debugfs_fops = { .owner = THIS_MODULE, .open = rd_open, .read = rd_read, - .llseek = no_llseek, .release = rd_release, }; diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c index a13e0b3a169e..ef777dbdf4ec 100644 --- a/drivers/gpu/drm/xe/xe_bb.c +++ b/drivers/gpu/drm/xe/xe_bb.c @@ -65,7 +65,8 @@ __xe_bb_create_job(struct xe_exec_queue *q, struct xe_bb *bb, u64 *addr) { u32 size = drm_suballoc_size(bb->bo); - bb->cs[bb->len++] = MI_BATCH_BUFFER_END; + if (bb->len == 0 || bb->cs[bb->len - 1] != MI_BATCH_BUFFER_END) + bb->cs[bb->len++] = MI_BATCH_BUFFER_END; xe_gt_assert(q->gt, bb->len * 4 + bb_prefetch(q->gt) <= size); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 06911e9a3bf5..f379df3a12bf 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -2320,6 +2320,20 @@ void xe_bo_put_commit(struct llist_head *deferred) drm_gem_object_free(&bo->ttm.base.refcount); } +void xe_bo_put(struct xe_bo *bo) +{ + might_sleep(); + if (bo) { +#ifdef CONFIG_PROC_FS + if (bo->client) + might_lock(&bo->client->bos_lock); +#endif + if (bo->ggtt_node && bo->ggtt_node->ggtt) + might_lock(&bo->ggtt_node->ggtt->lock); + drm_gem_object_put(&bo->ttm.base); + } +} + /** * xe_bo_dumb_create - Create a dumb bo as backing for a fb * @file_priv: ... diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index dbfb3209615d..6e4be52306df 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -126,11 +126,7 @@ static inline struct xe_bo *xe_bo_get(struct xe_bo *bo) return bo; } -static inline void xe_bo_put(struct xe_bo *bo) -{ - if (bo) - drm_gem_object_put(&bo->ttm.base); -} +void xe_bo_put(struct xe_bo *bo); static inline void __xe_bo_unset_bulk_move(struct xe_bo *bo) { diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 95a05c5bc897..c4add8b38bbd 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -168,15 +168,10 @@ static void bo_meminfo(struct xe_bo *bo, struct drm_memory_stats stats[TTM_NUM_MEM_TYPES]) { u64 sz = bo->size; - u32 mem_type; + u32 mem_type = bo->ttm.resource->mem_type; xe_bo_assert_held(bo); - if (bo->placement.placement) - mem_type = bo->placement.placement->mem_type; - else - mem_type = XE_PL_TT; - if (drm_gem_object_is_shared_for_memory_stats(&bo->ttm.base)) stats[mem_type].shared += sz; else diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 730eec07795e..00af059a8971 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -212,6 +212,12 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf) * TODO: Change to read lock? Using write lock for simplicity. */ down_write(&vm->lock); + + if (xe_vm_is_closed(vm)) { + err = -ENOENT; + goto unlock_vm; + } + vma = lookup_vma(vm, pf->page_addr); if (!vma) { err = -EINVAL; diff --git a/drivers/gpu/drm/xe/xe_guc.h b/drivers/gpu/drm/xe/xe_guc.h index c3e6b51f7a09..42116b167c98 100644 --- a/drivers/gpu/drm/xe/xe_guc.h +++ b/drivers/gpu/drm/xe/xe_guc.h @@ -18,8 +18,10 @@ */ #define MAKE_GUC_VER(maj, min, pat) (((maj) << 16) | ((min) << 8) | (pat)) #define MAKE_GUC_VER_STRUCT(ver) MAKE_GUC_VER((ver).major, (ver).minor, (ver).patch) -#define GUC_SUBMIT_VER(guc) MAKE_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY]) -#define GUC_FIRMWARE_VER(guc) MAKE_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_RELEASE]) +#define GUC_SUBMIT_VER(guc) \ + MAKE_GUC_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_COMPATIBILITY]) +#define GUC_FIRMWARE_VER(guc) \ + MAKE_GUC_VER_STRUCT((guc)->fw.versions.found[XE_UC_FW_VER_RELEASE]) struct drm_printer; diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 0369cc016f6a..eae38a49ee8e 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -1263,7 +1263,6 @@ static int xe_oa_mmap(struct file *file, struct vm_area_struct *vma) static const struct file_operations xe_oa_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .release = xe_oa_release, .poll = xe_oa_poll, .read = xe_oa_read, diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c index 5bcd59190353..80ba2fc78837 100644 --- a/drivers/gpu/drm/xe/xe_vram.c +++ b/drivers/gpu/drm/xe/xe_vram.c @@ -182,6 +182,7 @@ static inline u64 get_flat_ccs_offset(struct xe_gt *gt, u64 tile_size) offset = offset_hi << 32; /* HW view bits 39:32 */ offset |= offset_lo << 6; /* HW view bits 31:6 */ offset *= num_enabled; /* convert to SW view */ + offset = round_up(offset, SZ_128K); /* SW must round up to nearest 128K */ /* We don't expect any holes */ xe_assert_msg(xe, offset == (xe_mmio_read64_2x32(gt, GSMBASE) - ccs_size), diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c index a54c7995b9be..21a70420151e 100644 --- a/drivers/hid/uhid.c +++ b/drivers/hid/uhid.c @@ -803,7 +803,6 @@ static const struct file_operations uhid_fops = { .read = uhid_char_read, .write = uhid_char_write, .poll = uhid_char_poll, - .llseek = no_llseek, }; static struct miscdevice uhid_misc = { diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c index 3751c1e3eddd..1dc7e24fe4c5 100644 --- a/drivers/hwmon/asus_atk0110.c +++ b/drivers/hwmon/asus_atk0110.c @@ -783,7 +783,6 @@ static const struct file_operations atk_debugfs_ggrp_fops = { .read = atk_debugfs_ggrp_read, .open = atk_debugfs_ggrp_open, .release = atk_debugfs_ggrp_release, - .llseek = no_llseek, }; static void atk_debugfs_init(struct atk_data *data) diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c index 1811f84d835e..a303959879ef 100644 --- a/drivers/hwmon/fschmd.c +++ b/drivers/hwmon/fschmd.c @@ -948,7 +948,6 @@ static long watchdog_ioctl(struct file *filp, unsigned int cmd, static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = watchdog_open, .release = watchdog_release, .write = watchdog_write, diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c index 0acf6bd0227f..67728f60333f 100644 --- a/drivers/hwmon/w83793.c +++ b/drivers/hwmon/w83793.c @@ -1451,7 +1451,6 @@ static long watchdog_ioctl(struct file *filp, unsigned int cmd, static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = watchdog_open, .release = watchdog_close, .write = watchdog_write, diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 7edd3f1d0d46..aea9ac9c4bd0 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -652,7 +652,6 @@ static const struct file_operations etb_fops = { .open = etb_open, .read = etb_read, .release = etb_release, - .llseek = no_llseek, }; static struct attribute *coresight_etb_mgmt_attrs[] = { diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c index b54562f392f3..3a482fd2cb22 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-core.c +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -220,7 +220,6 @@ static const struct file_operations tmc_fops = { .open = tmc_open, .read = tmc_read, .release = tmc_release, - .llseek = no_llseek, }; static enum tmc_mem_intf_width tmc_get_memwidth(u32 devid) diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c index f9ebf20c91e6..ef7f560f0ffa 100644 --- a/drivers/hwtracing/coresight/ultrasoc-smb.c +++ b/drivers/hwtracing/coresight/ultrasoc-smb.c @@ -163,7 +163,6 @@ static const struct file_operations smb_fops = { .open = smb_open, .read = smb_read, .release = smb_release, - .llseek = no_llseek, }; static ssize_t buf_size_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index be63d5b8f193..66123d684ac9 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -1677,7 +1677,6 @@ static const struct file_operations intel_th_msc_fops = { .release = intel_th_msc_release, .read = intel_th_msc_read, .mmap = intel_th_msc_mmap, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index ccf39a80dc4f..cdba4e875b28 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -839,7 +839,6 @@ static const struct file_operations stm_fops = { .mmap = stm_char_mmap, .unlocked_ioctl = stm_char_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static void stm_device_release(struct device *dev) diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index f4fb212b7f39..61f7c4003d2f 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -637,7 +637,6 @@ static int i2cdev_release(struct inode *inode, struct file *file) static const struct file_operations i2cdev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = i2cdev_read, .write = i2cdev_write, .unlocked_ioctl = i2cdev_ioctl, diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 9457e34b9e32..67aebfe0fed6 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -121,6 +121,12 @@ static unsigned int mwait_substates __initdata; #define CPUIDLE_FLAG_INIT_XSTATE BIT(17) /* + * Ignore the sub-state when matching mwait hints between the ACPI _CST and + * custom tables. + */ +#define CPUIDLE_FLAG_PARTIAL_HINT_MATCH BIT(18) + +/* * MWAIT takes an 8-bit "hint" in EAX "suggesting" * the C-state (top nibble) and sub-state (bottom nibble) * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc. @@ -1043,7 +1049,8 @@ static struct cpuidle_state gnr_cstates[] __initdata = { .name = "C6", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED | - CPUIDLE_FLAG_INIT_XSTATE, + CPUIDLE_FLAG_INIT_XSTATE | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 170, .target_residency = 650, .enter = &intel_idle, @@ -1052,7 +1059,8 @@ static struct cpuidle_state gnr_cstates[] __initdata = { .name = "C6P", .desc = "MWAIT 0x21", .flags = MWAIT2flg(0x21) | CPUIDLE_FLAG_TLB_FLUSHED | - CPUIDLE_FLAG_INIT_XSTATE, + CPUIDLE_FLAG_INIT_XSTATE | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 210, .target_residency = 1000, .enter = &intel_idle, @@ -1354,7 +1362,8 @@ static struct cpuidle_state srf_cstates[] __initdata = { { .name = "C6S", .desc = "MWAIT 0x22", - .flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x22) | CPUIDLE_FLAG_TLB_FLUSHED | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 270, .target_residency = 700, .enter = &intel_idle, @@ -1362,7 +1371,8 @@ static struct cpuidle_state srf_cstates[] __initdata = { { .name = "C6SP", .desc = "MWAIT 0x23", - .flags = MWAIT2flg(0x23) | CPUIDLE_FLAG_TLB_FLUSHED, + .flags = MWAIT2flg(0x23) | CPUIDLE_FLAG_TLB_FLUSHED | + CPUIDLE_FLAG_PARTIAL_HINT_MATCH, .exit_latency = 310, .target_residency = 900, .enter = &intel_idle, @@ -1744,7 +1754,7 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) } } -static bool __init intel_idle_off_by_default(u32 mwait_hint) +static bool __init intel_idle_off_by_default(unsigned int flags, u32 mwait_hint) { int cstate, limit; @@ -1761,7 +1771,15 @@ static bool __init intel_idle_off_by_default(u32 mwait_hint) * the interesting states are ACPI_CSTATE_FFH. */ for (cstate = 1; cstate < limit; cstate++) { - if (acpi_state_table.states[cstate].address == mwait_hint) + u32 acpi_hint = acpi_state_table.states[cstate].address; + u32 table_hint = mwait_hint; + + if (flags & CPUIDLE_FLAG_PARTIAL_HINT_MATCH) { + acpi_hint &= ~MWAIT_SUBSTATE_MASK; + table_hint &= ~MWAIT_SUBSTATE_MASK; + } + + if (acpi_hint == table_hint) return false; } return true; @@ -1771,7 +1789,10 @@ static bool __init intel_idle_off_by_default(u32 mwait_hint) static inline bool intel_idle_acpi_cst_extract(void) { return false; } static inline void intel_idle_init_cstates_acpi(struct cpuidle_driver *drv) { } -static inline bool intel_idle_off_by_default(u32 mwait_hint) { return false; } +static inline bool intel_idle_off_by_default(unsigned int flags, u32 mwait_hint) +{ + return false; +} #endif /* !CONFIG_ACPI_PROCESSOR_CSTATE */ /** @@ -2098,7 +2119,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && - intel_idle_off_by_default(mwait_hint) && + intel_idle_off_by_default(state->flags, mwait_hint) && !(state->flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) state->flags |= CPUIDLE_FLAG_OFF; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index dc57d07a1f45..5dbb248e9625 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1817,7 +1817,6 @@ static const struct file_operations ucma_fops = { .release = ucma_close, .write = ucma_write, .poll = ucma_poll, - .llseek = no_llseek, }; static struct miscdevice ucma_misc = { diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index f760dfffa188..fd67fc9fe85a 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -1082,7 +1082,6 @@ static const struct file_operations umad_fops = { #endif .open = ib_umad_open, .release = ib_umad_close, - .llseek = no_llseek, }; static int ib_umad_sm_open(struct inode *inode, struct file *filp) @@ -1150,7 +1149,6 @@ static const struct file_operations umad_sm_fops = { .owner = THIS_MODULE, .open = ib_umad_sm_open, .release = ib_umad_sm_close, - .llseek = no_llseek, }; static struct ib_umad_port *get_port(struct ib_device *ibdev, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index bc099287de9a..94454186ed81 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -353,7 +353,6 @@ const struct file_operations uverbs_event_fops = { .poll = ib_uverbs_comp_event_poll, .release = uverbs_uobject_fd_release, .fasync = ib_uverbs_comp_event_fasync, - .llseek = no_llseek, }; const struct file_operations uverbs_async_event_fops = { @@ -362,7 +361,6 @@ const struct file_operations uverbs_async_event_fops = { .poll = ib_uverbs_async_event_poll, .release = uverbs_async_event_release, .fasync = ib_uverbs_async_event_fasync, - .llseek = no_llseek, }; void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) @@ -991,7 +989,6 @@ static const struct file_operations uverbs_fops = { .write = ib_uverbs_write, .open = ib_uverbs_open, .release = ib_uverbs_close, - .llseek = no_llseek, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; @@ -1002,7 +999,6 @@ static const struct file_operations uverbs_mmap_fops = { .mmap = ib_uverbs_mmap, .open = ib_uverbs_open, .release = ib_uverbs_close, - .llseek = no_llseek, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/infiniband/hw/hfi1/fault.c b/drivers/infiniband/hw/hfi1/fault.c index 35d2382ee618..ec9ee59fcf0c 100644 --- a/drivers/infiniband/hw/hfi1/fault.c +++ b/drivers/infiniband/hw/hfi1/fault.c @@ -203,7 +203,6 @@ static const struct file_operations __fault_opcodes_fops = { .open = fault_opcodes_open, .read = fault_opcodes_read, .write = fault_opcodes_write, - .llseek = no_llseek }; void hfi1_fault_exit_debugfs(struct hfi1_ibdev *ibd) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 253fea374a72..69999d8d24f3 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2673,7 +2673,6 @@ static const struct file_operations devx_async_cmd_event_fops = { .read = devx_async_cmd_event_read, .poll = devx_async_cmd_event_poll, .release = uverbs_uobject_fd_release, - .llseek = no_llseek, }; static ssize_t devx_async_event_read(struct file *filp, char __user *buf, @@ -2788,7 +2787,6 @@ static const struct file_operations devx_async_event_fops = { .read = devx_async_event_read, .poll = devx_async_event_poll, .release = uverbs_uobject_fd_release, - .llseek = no_llseek, }; static void devx_async_cmd_event_destroy_uobj(struct ib_uobject *uobj, diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index eb4906552ac8..b5cbb57ee5f6 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -1299,7 +1299,6 @@ static const struct file_operations evdev_fops = { .compat_ioctl = evdev_ioctl_compat, #endif .fasync = evdev_fasync, - .llseek = no_llseek, }; /* diff --git a/drivers/input/joydev.c b/drivers/input/joydev.c index 5824bca02e5a..ba2b17288bcd 100644 --- a/drivers/input/joydev.c +++ b/drivers/input/joydev.c @@ -718,7 +718,6 @@ static const struct file_operations joydev_fops = { .compat_ioctl = joydev_compat_ioctl, #endif .fasync = joydev_fasync, - .llseek = no_llseek, }; /* diff --git a/drivers/input/keyboard/applespi.c b/drivers/input/keyboard/applespi.c index cf25177b4830..707c5a8ae736 100644 --- a/drivers/input/keyboard/applespi.c +++ b/drivers/input/keyboard/applespi.c @@ -1007,7 +1007,6 @@ static const struct file_operations applespi_tp_dim_fops = { .owner = THIS_MODULE, .open = applespi_tp_dim_open, .read = applespi_tp_dim_read, - .llseek = no_llseek, }; static void report_finger_data(struct input_dev *input, int slot, diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 445856c9127a..2c51ea9d01d7 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -1132,7 +1132,6 @@ static const struct file_operations uinput_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = uinput_compat_ioctl, #endif - .llseek = no_llseek, }; static struct miscdevice uinput_misc = { diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c index a88e2eee55c3..1ab12b247f98 100644 --- a/drivers/input/serio/userio.c +++ b/drivers/input/serio/userio.c @@ -267,7 +267,6 @@ static const struct file_operations userio_fops = { .read = userio_char_read, .write = userio_char_write, .poll = userio_char_poll, - .llseek = no_llseek, }; static struct miscdevice userio_misc = { diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index 8c8226f0dffd..e590973ce5cf 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -360,7 +360,6 @@ static const struct file_operations iommufd_fault_fops = { .write = iommufd_fault_fops_write, .poll = iommufd_fault_fops_poll, .release = iommufd_fault_fops_release, - .llseek = no_llseek, }; int iommufd_fault_alloc(struct iommufd_ucmd *ucmd) diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index 3ed257334562..70dee9ad4bae 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -1024,7 +1024,6 @@ static int capi_release(struct inode *inode, struct file *file) static const struct file_operations capi_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = capi_read, .write = capi_write, .poll = capi_poll, diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index 83d6b484d3c6..7cfa8c61dba0 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -266,7 +266,6 @@ static const struct file_operations mISDN_fops = { .unlocked_ioctl = mISDN_ioctl, .open = mISDN_open, .release = mISDN_close, - .llseek = no_llseek, }; static struct miscdevice mISDNtimer = { diff --git a/drivers/leds/uleds.c b/drivers/leds/uleds.c index 3d361c920030..374a841f18c3 100644 --- a/drivers/leds/uleds.c +++ b/drivers/leds/uleds.c @@ -200,7 +200,6 @@ static const struct file_operations uleds_fops = { .read = uleds_read, .write = uleds_write, .poll = uleds_poll, - .llseek = no_llseek, }; static struct miscdevice uleds_misc = { diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index b0407c5fadb2..88adee42ba82 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -842,7 +842,6 @@ out: static const struct file_operations adb_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = adb_read, .write = adb_write, .open = adb_open, diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index b2b78a53e532..a01bc5090cdf 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -1314,7 +1314,6 @@ static int smu_release(struct inode *inode, struct file *file) static const struct file_operations smu_device_fops = { - .llseek = no_llseek, .read = smu_read, .write = smu_write, .poll = smu_fpoll, diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 098bf526136c..d478aafa02c9 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -529,9 +529,6 @@ static struct dm_buffer *list_to_buffer(struct list_head *l) { struct lru_entry *le = list_entry(l, struct lru_entry, list); - if (!le) - return NULL; - return le_to_buffer(le); } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 17f0fab1e254..aaeeabfab09b 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1368,7 +1368,7 @@ static void mg_copy(struct work_struct *ws) */ bool rb = bio_detain_shared(mg->cache, mg->op->oblock, mg->overwrite_bio); - BUG_ON(rb); /* An exclussive lock must _not_ be held for this block */ + BUG_ON(rb); /* An exclusive lock must _not_ be held for this block */ mg->overwrite_bio = NULL; inc_io_migrations(mg->cache); mg_full_copy(ws); @@ -3200,8 +3200,6 @@ static int parse_cblock_range(struct cache *cache, const char *str, * Try and parse form (ii) first. */ r = sscanf(str, "%llu-%llu%c", &b, &e, &dummy); - if (r < 0) - return r; if (r == 2) { result->begin = to_cblock(b); @@ -3213,8 +3211,6 @@ static int parse_cblock_range(struct cache *cache, const char *str, * That didn't work, try form (i). */ r = sscanf(str, "%llu%c", &b, &dummy); - if (r < 0) - return r; if (r == 1) { result->begin = to_cblock(b); diff --git a/drivers/md/dm-clone-metadata.c b/drivers/md/dm-clone-metadata.c index 2db84cd2202b..14c5c28d938b 100644 --- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -530,10 +530,7 @@ static int __load_bitset_in_core(struct dm_clone_metadata *cmd) return r; for (i = 0; ; i++) { - if (dm_bitset_cursor_get_value(&c)) - __set_bit(i, cmd->region_map); - else - __clear_bit(i, cmd->region_map); + __assign_bit(i, cmd->region_map, dm_bitset_cursor_get_value(&c)); if (i >= (cmd->nr_regions - 1)) break; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 348b4b26c272..5228b03b6fe0 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -147,6 +147,7 @@ enum cipher_flags { CRYPT_MODE_INTEGRITY_AEAD, /* Use authenticated mode for cipher */ CRYPT_IV_LARGE_SECTORS, /* Calculate IV from sector_size, not 512B sectors */ CRYPT_ENCRYPT_PREPROCESS, /* Must preprocess data for encryption (elephant) */ + CRYPT_KEY_MAC_SIZE_SET, /* The integrity_key_size option was used */ }; /* @@ -2613,35 +2614,31 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string key = request_key(type, key_desc + 1, NULL); if (IS_ERR(key)) { - kfree_sensitive(new_key_string); - return PTR_ERR(key); + ret = PTR_ERR(key); + goto free_new_key_string; } down_read(&key->sem); - ret = set_key(cc, key); - if (ret < 0) { - up_read(&key->sem); - key_put(key); - kfree_sensitive(new_key_string); - return ret; - } - up_read(&key->sem); key_put(key); + if (ret < 0) + goto free_new_key_string; /* clear the flag since following operations may invalidate previously valid key */ clear_bit(DM_CRYPT_KEY_VALID, &cc->flags); ret = crypt_setkey(cc); + if (ret) + goto free_new_key_string; - if (!ret) { - set_bit(DM_CRYPT_KEY_VALID, &cc->flags); - kfree_sensitive(cc->key_string); - cc->key_string = new_key_string; - } else - kfree_sensitive(new_key_string); + set_bit(DM_CRYPT_KEY_VALID, &cc->flags); + kfree_sensitive(cc->key_string); + cc->key_string = new_key_string; + return 0; +free_new_key_string: + kfree_sensitive(new_key_string); return ret; } @@ -2937,7 +2934,8 @@ static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api) if (IS_ERR(mac)) return PTR_ERR(mac); - cc->key_mac_size = crypto_ahash_digestsize(mac); + if (!test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags)) + cc->key_mac_size = crypto_ahash_digestsize(mac); crypto_free_ahash(mac); cc->authenc_key = kmalloc(crypt_authenckey_size(cc), GFP_KERNEL); @@ -3219,6 +3217,13 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar cc->cipher_auth = kstrdup(sval, GFP_KERNEL); if (!cc->cipher_auth) return -ENOMEM; + } else if (sscanf(opt_string, "integrity_key_size:%u%c", &val, &dummy) == 1) { + if (!val) { + ti->error = "Invalid integrity_key_size argument"; + return -EINVAL; + } + cc->key_mac_size = val; + set_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags); } else if (sscanf(opt_string, "sector_size:%hu%c", &cc->sector_size, &dummy) == 1) { if (cc->sector_size < (1 << SECTOR_SHIFT) || cc->sector_size > 4096 || @@ -3607,10 +3612,10 @@ static void crypt_status(struct dm_target *ti, status_type_t type, num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags); num_feature_args += test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags); num_feature_args += test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags); + num_feature_args += !!cc->used_tag_size; num_feature_args += cc->sector_size != (1 << SECTOR_SHIFT); num_feature_args += test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags); - if (cc->used_tag_size) - num_feature_args++; + num_feature_args += test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags); if (num_feature_args) { DMEMIT(" %d", num_feature_args); if (ti->num_discard_bios) @@ -3631,6 +3636,8 @@ static void crypt_status(struct dm_target *ti, status_type_t type, DMEMIT(" sector_size:%d", cc->sector_size); if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags)) DMEMIT(" iv_large_sectors"); + if (test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags)) + DMEMIT(" integrity_key_size:%u", cc->key_mac_size); } break; @@ -3758,7 +3765,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type crypt_target = { .name = "crypt", - .version = {1, 27, 0}, + .version = {1, 28, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index acff2f64f251..ee9f7cecd78e 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -284,6 +284,7 @@ struct dm_integrity_c { mempool_t recheck_pool; struct bio_set recheck_bios; + struct bio_set recalc_bios; struct notifier_block reboot_notifier; }; @@ -321,7 +322,9 @@ struct dm_integrity_io { struct dm_bio_details bio_details; char *integrity_payload; + unsigned payload_len; bool integrity_payload_from_mempool; + bool integrity_range_locked; }; struct journal_completion { @@ -359,7 +362,7 @@ static struct kmem_cache *journal_io_cache; #endif static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map); -static int dm_integrity_map_inline(struct dm_integrity_io *dio); +static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map); static void integrity_bio_wait(struct work_struct *w); static void dm_integrity_dtr(struct dm_target *ti); @@ -491,7 +494,8 @@ static int sb_mac(struct dm_integrity_c *ic, bool wr) __u8 *sb = (__u8 *)ic->sb; __u8 *mac = sb + (1 << SECTOR_SHIFT) - mac_size; - if (sizeof(struct superblock) + mac_size > 1 << SECTOR_SHIFT) { + if (sizeof(struct superblock) + mac_size > 1 << SECTOR_SHIFT || + mac_size > HASH_MAX_DIGESTSIZE) { dm_integrity_io_error(ic, "digest is too long", -EINVAL); return -EINVAL; } @@ -1500,15 +1504,15 @@ static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_dat if (!ic->meta_dev) flush_data = false; if (flush_data) { - fr.io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC, - fr.io_req.mem.type = DM_IO_KMEM, - fr.io_req.mem.ptr.addr = NULL, - fr.io_req.notify.fn = flush_notify, + fr.io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC; + fr.io_req.mem.type = DM_IO_KMEM; + fr.io_req.mem.ptr.addr = NULL; + fr.io_req.notify.fn = flush_notify; fr.io_req.notify.context = &fr; - fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio), - fr.io_reg.bdev = ic->dev->bdev, - fr.io_reg.sector = 0, - fr.io_reg.count = 0, + fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio); + fr.io_reg.bdev = ic->dev->bdev; + fr.io_reg.sector = 0; + fr.io_reg.count = 0; fr.ic = ic; init_completion(&fr.comp); r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL, IOPRIO_DEFAULT); @@ -1946,8 +1950,13 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio) dio->bi_status = 0; dio->op = bio_op(bio); - if (ic->mode == 'I') - return dm_integrity_map_inline(dio); + if (ic->mode == 'I') { + bio->bi_iter.bi_sector = dm_target_offset(ic->ti, bio->bi_iter.bi_sector); + dio->integrity_payload = NULL; + dio->integrity_payload_from_mempool = false; + dio->integrity_range_locked = false; + return dm_integrity_map_inline(dio, true); + } if (unlikely(dio->op == REQ_OP_DISCARD)) { if (ti->max_io_len) { @@ -2397,15 +2406,13 @@ journal_read_write: do_endio_flush(ic, dio); } -static int dm_integrity_map_inline(struct dm_integrity_io *dio) +static int dm_integrity_map_inline(struct dm_integrity_io *dio, bool from_map) { struct dm_integrity_c *ic = dio->ic; struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); struct bio_integrity_payload *bip; - unsigned payload_len, digest_size, extra_size, ret; - - dio->integrity_payload = NULL; - dio->integrity_payload_from_mempool = false; + unsigned ret; + sector_t recalc_sector; if (unlikely(bio_integrity(bio))) { bio->bi_status = BLK_STS_NOTSUPP; @@ -2418,28 +2425,67 @@ static int dm_integrity_map_inline(struct dm_integrity_io *dio) return DM_MAPIO_REMAPPED; retry: - payload_len = ic->tuple_size * (bio_sectors(bio) >> ic->sb->log2_sectors_per_block); - digest_size = crypto_shash_digestsize(ic->internal_hash); - extra_size = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0; - payload_len += extra_size; - dio->integrity_payload = kmalloc(payload_len, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); - if (unlikely(!dio->integrity_payload)) { - const unsigned x_size = PAGE_SIZE << 1; - if (payload_len > x_size) { - unsigned sectors = ((x_size - extra_size) / ic->tuple_size) << ic->sb->log2_sectors_per_block; - if (WARN_ON(!sectors || sectors >= bio_sectors(bio))) { - bio->bi_status = BLK_STS_NOTSUPP; - bio_endio(bio); - return DM_MAPIO_SUBMITTED; + if (!dio->integrity_payload) { + unsigned digest_size, extra_size; + dio->payload_len = ic->tuple_size * (bio_sectors(bio) >> ic->sb->log2_sectors_per_block); + digest_size = crypto_shash_digestsize(ic->internal_hash); + extra_size = unlikely(digest_size > ic->tag_size) ? digest_size - ic->tag_size : 0; + dio->payload_len += extra_size; + dio->integrity_payload = kmalloc(dio->payload_len, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (unlikely(!dio->integrity_payload)) { + const unsigned x_size = PAGE_SIZE << 1; + if (dio->payload_len > x_size) { + unsigned sectors = ((x_size - extra_size) / ic->tuple_size) << ic->sb->log2_sectors_per_block; + if (WARN_ON(!sectors || sectors >= bio_sectors(bio))) { + bio->bi_status = BLK_STS_NOTSUPP; + bio_endio(bio); + return DM_MAPIO_SUBMITTED; + } + dm_accept_partial_bio(bio, sectors); + goto retry; } - dm_accept_partial_bio(bio, sectors); - goto retry; } + } + + dio->range.logical_sector = bio->bi_iter.bi_sector; + dio->range.n_sectors = bio_sectors(bio); + + if (!(ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING))) + goto skip_spinlock; +#ifdef CONFIG_64BIT + /* + * On 64-bit CPUs we can optimize the lock away (so that it won't cause + * cache line bouncing) and use acquire/release barriers instead. + * + * Paired with smp_store_release in integrity_recalc_inline. + */ + recalc_sector = le64_to_cpu(smp_load_acquire(&ic->sb->recalc_sector)); + if (likely(dio->range.logical_sector + dio->range.n_sectors <= recalc_sector)) + goto skip_spinlock; +#endif + spin_lock_irq(&ic->endio_wait.lock); + recalc_sector = le64_to_cpu(ic->sb->recalc_sector); + if (dio->range.logical_sector + dio->range.n_sectors <= recalc_sector) + goto skip_unlock; + if (unlikely(!add_new_range(ic, &dio->range, true))) { + if (from_map) { + spin_unlock_irq(&ic->endio_wait.lock); + INIT_WORK(&dio->work, integrity_bio_wait); + queue_work(ic->wait_wq, &dio->work); + return DM_MAPIO_SUBMITTED; + } + wait_and_add_new_range(ic, &dio->range); + } + dio->integrity_range_locked = true; +skip_unlock: + spin_unlock_irq(&ic->endio_wait.lock); +skip_spinlock: + + if (unlikely(!dio->integrity_payload)) { dio->integrity_payload = page_to_virt((struct page *)mempool_alloc(&ic->recheck_pool, GFP_NOIO)); dio->integrity_payload_from_mempool = true; } - bio->bi_iter.bi_sector = dm_target_offset(ic->ti, bio->bi_iter.bi_sector); dio->bio_details.bi_iter = bio->bi_iter; if (unlikely(!dm_integrity_check_limits(ic, bio->bi_iter.bi_sector, bio))) { @@ -2449,7 +2495,7 @@ retry: bio->bi_iter.bi_sector += ic->start + SB_SECTORS; bip = bio_integrity_alloc(bio, GFP_NOIO, 1); - if (unlikely(IS_ERR(bip))) { + if (IS_ERR(bip)) { bio->bi_status = errno_to_blk_status(PTR_ERR(bip)); bio_endio(bio); return DM_MAPIO_SUBMITTED; @@ -2470,8 +2516,8 @@ retry: } ret = bio_integrity_add_page(bio, virt_to_page(dio->integrity_payload), - payload_len, offset_in_page(dio->integrity_payload)); - if (unlikely(ret != payload_len)) { + dio->payload_len, offset_in_page(dio->integrity_payload)); + if (unlikely(ret != dio->payload_len)) { bio->bi_status = BLK_STS_RESOURCE; bio_endio(bio); return DM_MAPIO_SUBMITTED; @@ -2522,7 +2568,7 @@ static void dm_integrity_inline_recheck(struct work_struct *w) } bip = bio_integrity_alloc(outgoing_bio, GFP_NOIO, 1); - if (unlikely(IS_ERR(bip))) { + if (IS_ERR(bip)) { bio_put(outgoing_bio); bio->bi_status = errno_to_blk_status(PTR_ERR(bip)); bio_endio(bio); @@ -2579,6 +2625,9 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status struct dm_integrity_io *dio = dm_per_bio_data(bio, sizeof(struct dm_integrity_io)); if (dio->op == REQ_OP_READ && likely(*status == BLK_STS_OK)) { unsigned pos = 0; + if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) && + unlikely(dio->integrity_range_locked)) + goto skip_check; while (dio->bio_details.bi_iter.bi_size) { char digest[HASH_MAX_DIGESTSIZE]; struct bio_vec bv = bio_iter_iovec(bio, dio->bio_details.bi_iter); @@ -2598,9 +2647,10 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status bio_advance_iter_single(bio, &dio->bio_details.bi_iter, ic->sectors_per_block << SECTOR_SHIFT); } } - if (likely(dio->op == REQ_OP_READ) || likely(dio->op == REQ_OP_WRITE)) { - dm_integrity_free_payload(dio); - } +skip_check: + dm_integrity_free_payload(dio); + if (unlikely(dio->integrity_range_locked)) + remove_range(ic, &dio->range); } return DM_ENDIO_DONE; } @@ -2608,8 +2658,26 @@ static int dm_integrity_end_io(struct dm_target *ti, struct bio *bio, blk_status static void integrity_bio_wait(struct work_struct *w) { struct dm_integrity_io *dio = container_of(w, struct dm_integrity_io, work); + struct dm_integrity_c *ic = dio->ic; - dm_integrity_map_continue(dio, false); + if (ic->mode == 'I') { + struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io)); + int r = dm_integrity_map_inline(dio, false); + switch (r) { + case DM_MAPIO_KILL: + bio->bi_status = BLK_STS_IOERR; + fallthrough; + case DM_MAPIO_REMAPPED: + submit_bio_noacct(bio); + fallthrough; + case DM_MAPIO_SUBMITTED: + return; + default: + BUG(); + } + } else { + dm_integrity_map_continue(dio, false); + } } static void pad_uncommitted(struct dm_integrity_c *ic) @@ -3081,6 +3149,133 @@ free_ret: kvfree(recalc_tags); } +static void integrity_recalc_inline(struct work_struct *w) +{ + struct dm_integrity_c *ic = container_of(w, struct dm_integrity_c, recalc_work); + size_t recalc_tags_size; + u8 *recalc_buffer = NULL; + u8 *recalc_tags = NULL; + struct dm_integrity_range range; + struct bio *bio; + struct bio_integrity_payload *bip; + __u8 *t; + unsigned int i; + int r; + unsigned ret; + unsigned int super_counter = 0; + unsigned recalc_sectors = RECALC_SECTORS; + +retry: + recalc_buffer = kmalloc(recalc_sectors << SECTOR_SHIFT, GFP_NOIO | __GFP_NOWARN); + if (!recalc_buffer) { +oom: + recalc_sectors >>= 1; + if (recalc_sectors >= 1U << ic->sb->log2_sectors_per_block) + goto retry; + DMCRIT("out of memory for recalculate buffer - recalculation disabled"); + goto free_ret; + } + + recalc_tags_size = (recalc_sectors >> ic->sb->log2_sectors_per_block) * ic->tuple_size; + if (crypto_shash_digestsize(ic->internal_hash) > ic->tuple_size) + recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tuple_size; + recalc_tags = kmalloc(recalc_tags_size, GFP_NOIO | __GFP_NOWARN); + if (!recalc_tags) { + kfree(recalc_buffer); + recalc_buffer = NULL; + goto oom; + } + + spin_lock_irq(&ic->endio_wait.lock); + +next_chunk: + if (unlikely(dm_post_suspending(ic->ti))) + goto unlock_ret; + + range.logical_sector = le64_to_cpu(ic->sb->recalc_sector); + if (unlikely(range.logical_sector >= ic->provided_data_sectors)) + goto unlock_ret; + range.n_sectors = min((sector_t)recalc_sectors, ic->provided_data_sectors - range.logical_sector); + + add_new_range_and_wait(ic, &range); + spin_unlock_irq(&ic->endio_wait.lock); + + if (unlikely(++super_counter == RECALC_WRITE_SUPER)) { + recalc_write_super(ic); + super_counter = 0; + } + + if (unlikely(dm_integrity_failed(ic))) + goto err; + + DEBUG_print("recalculating: %llx - %llx\n", range.logical_sector, range.n_sectors); + + bio = bio_alloc_bioset(ic->dev->bdev, 1, REQ_OP_READ, GFP_NOIO, &ic->recalc_bios); + bio->bi_iter.bi_sector = ic->start + SB_SECTORS + range.logical_sector; + __bio_add_page(bio, virt_to_page(recalc_buffer), range.n_sectors << SECTOR_SHIFT, offset_in_page(recalc_buffer)); + r = submit_bio_wait(bio); + bio_put(bio); + if (unlikely(r)) { + dm_integrity_io_error(ic, "reading data", r); + goto err; + } + + t = recalc_tags; + for (i = 0; i < range.n_sectors; i += ic->sectors_per_block) { + memset(t, 0, ic->tuple_size); + integrity_sector_checksum(ic, range.logical_sector + i, recalc_buffer + (i << SECTOR_SHIFT), t); + t += ic->tuple_size; + } + + bio = bio_alloc_bioset(ic->dev->bdev, 1, REQ_OP_WRITE, GFP_NOIO, &ic->recalc_bios); + bio->bi_iter.bi_sector = ic->start + SB_SECTORS + range.logical_sector; + __bio_add_page(bio, virt_to_page(recalc_buffer), range.n_sectors << SECTOR_SHIFT, offset_in_page(recalc_buffer)); + + bip = bio_integrity_alloc(bio, GFP_NOIO, 1); + if (unlikely(IS_ERR(bip))) { + bio_put(bio); + DMCRIT("out of memory for bio integrity payload - recalculation disabled"); + goto err; + } + ret = bio_integrity_add_page(bio, virt_to_page(recalc_tags), t - recalc_tags, offset_in_page(recalc_tags)); + if (unlikely(ret != t - recalc_tags)) { + bio_put(bio); + dm_integrity_io_error(ic, "attaching integrity tags", -ENOMEM); + goto err; + } + + r = submit_bio_wait(bio); + bio_put(bio); + if (unlikely(r)) { + dm_integrity_io_error(ic, "writing data", r); + goto err; + } + + cond_resched(); + spin_lock_irq(&ic->endio_wait.lock); + remove_range_unlocked(ic, &range); +#ifdef CONFIG_64BIT + /* Paired with smp_load_acquire in dm_integrity_map_inline. */ + smp_store_release(&ic->sb->recalc_sector, cpu_to_le64(range.logical_sector + range.n_sectors)); +#else + ic->sb->recalc_sector = cpu_to_le64(range.logical_sector + range.n_sectors); +#endif + goto next_chunk; + +err: + remove_range(ic, &range); + goto free_ret; + +unlock_ret: + spin_unlock_irq(&ic->endio_wait.lock); + + recalc_write_super(ic); + +free_ret: + kfree(recalc_buffer); + kfree(recalc_tags); +} + static void bitmap_block_work(struct work_struct *w) { struct bitmap_block_status *bbs = container_of(w, struct bitmap_block_status, work); @@ -4619,6 +4814,17 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv r = -ENOMEM; goto bad; } + r = bioset_init(&ic->recalc_bios, 1, 0, BIOSET_NEED_BVECS); + if (r) { + ti->error = "Cannot allocate bio set"; + goto bad; + } + r = bioset_integrity_create(&ic->recalc_bios, 1); + if (r) { + ti->error = "Cannot allocate bio integrity set"; + r = -ENOMEM; + goto bad; + } } ic->metadata_wq = alloc_workqueue("dm-integrity-metadata", @@ -4717,13 +4923,18 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv ti->error = "Block size doesn't match the information in superblock"; goto bad; } - if (!le32_to_cpu(ic->sb->journal_sections) != (ic->mode == 'I')) { - r = -EINVAL; - if (ic->mode != 'I') + if (ic->mode != 'I') { + if (!le32_to_cpu(ic->sb->journal_sections)) { + r = -EINVAL; ti->error = "Corrupted superblock, journal_sections is 0"; - else + goto bad; + } + } else { + if (le32_to_cpu(ic->sb->journal_sections)) { + r = -EINVAL; ti->error = "Corrupted superblock, journal_sections is not 0"; - goto bad; + goto bad; + } } /* make sure that ti->max_io_len doesn't overflow */ if (!ic->meta_dev) { @@ -4830,7 +5041,7 @@ try_smaller_buffer: r = -ENOMEM; goto bad; } - INIT_WORK(&ic->recalc_work, integrity_recalc); + INIT_WORK(&ic->recalc_work, ic->mode == 'I' ? integrity_recalc_inline : integrity_recalc); } else { if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) { ti->error = "Recalculate can only be specified with internal_hash"; @@ -4847,17 +5058,15 @@ try_smaller_buffer: goto bad; } - if (ic->mode != 'I') { - ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev, - 1U << (SECTOR_SHIFT + ic->log2_buffer_sectors), 1, 0, NULL, NULL, 0); - if (IS_ERR(ic->bufio)) { - r = PTR_ERR(ic->bufio); - ti->error = "Cannot initialize dm-bufio"; - ic->bufio = NULL; - goto bad; - } - dm_bufio_set_sector_offset(ic->bufio, ic->start + ic->initial_sectors); + ic->bufio = dm_bufio_client_create(ic->meta_dev ? ic->meta_dev->bdev : ic->dev->bdev, + 1U << (SECTOR_SHIFT + ic->log2_buffer_sectors), 1, 0, NULL, NULL, 0); + if (IS_ERR(ic->bufio)) { + r = PTR_ERR(ic->bufio); + ti->error = "Cannot initialize dm-bufio"; + ic->bufio = NULL; + goto bad; } + dm_bufio_set_sector_offset(ic->bufio, ic->start + ic->initial_sectors); if (ic->mode != 'R' && ic->mode != 'I') { r = create_journal(ic, &ti->error); @@ -4979,6 +5188,7 @@ static void dm_integrity_dtr(struct dm_target *ti) kvfree(ic->bbs); if (ic->bufio) dm_bufio_client_destroy(ic->bufio); + bioset_exit(&ic->recalc_bios); bioset_exit(&ic->recheck_bios); mempool_exit(&ic->recheck_pool); mempool_exit(&ic->journal_io_mempool); @@ -5033,7 +5243,7 @@ static void dm_integrity_dtr(struct dm_target *ti) static struct target_type integrity_target = { .name = "integrity", - .version = {1, 12, 0}, + .version = {1, 13, 0}, .module = THIS_MODULE, .features = DM_TARGET_SINGLETON | DM_TARGET_INTEGRITY, .ctr = dm_integrity_ctr, diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 63682d27fc8d..1e0d3b9b75d6 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2519,7 +2519,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) rdev->saved_raid_disk = rdev->raid_disk; } - /* Reshape support -> restore repective data offsets */ + /* Reshape support -> restore respective data offsets */ rdev->data_offset = le64_to_cpu(sb->data_offset); rdev->new_data_offset = le64_to_cpu(sb->new_data_offset); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index f7e9a3632eb3..499f8cc8a39f 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -496,8 +496,10 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, map = dm_get_live_table(md, &srcu_idx); if (unlikely(!map)) { + DMERR_LIMIT("%s: mapping table unavailable, erroring io", + dm_device_name(md)); dm_put_live_table(md, srcu_idx); - return BLK_STS_RESOURCE; + return BLK_STS_IOERR; } ti = dm_table_find_target(map, 0); dm_put_live_table(md, srcu_idx); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index a0c1620e90c8..89632ce97760 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2948,7 +2948,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, pmd = dm_pool_metadata_open(metadata_dev, block_size, format_device); if (IS_ERR(pmd)) { *error = "Error creating metadata object"; - return (struct pool *)pmd; + return ERR_CAST(pmd); } pool = kzalloc(sizeof(*pool), GFP_KERNEL); diff --git a/drivers/md/dm-vdo/data-vio.c b/drivers/md/dm-vdo/data-vio.c index ab3ea8337809..0d502f6a86ad 100644 --- a/drivers/md/dm-vdo/data-vio.c +++ b/drivers/md/dm-vdo/data-vio.c @@ -501,6 +501,7 @@ static void launch_data_vio(struct data_vio *data_vio, logical_block_number_t lb memset(&data_vio->record_name, 0, sizeof(data_vio->record_name)); memset(&data_vio->duplicate, 0, sizeof(data_vio->duplicate)); + vdo_reset_completion(&data_vio->decrement_completion); vdo_reset_completion(completion); completion->error_handler = handle_data_vio_error; set_data_vio_logical_callback(data_vio, attempt_logical_block_lock); @@ -1273,12 +1274,14 @@ static void clean_hash_lock(struct vdo_completion *completion) static void finish_cleanup(struct data_vio *data_vio) { struct vdo_completion *completion = &data_vio->vio.completion; + u32 discard_size = min_t(u32, data_vio->remaining_discard, + VDO_BLOCK_SIZE - data_vio->offset); VDO_ASSERT_LOG_ONLY(data_vio->allocation.lock == NULL, "complete data_vio has no allocation lock"); VDO_ASSERT_LOG_ONLY(data_vio->hash_lock == NULL, "complete data_vio has no hash lock"); - if ((data_vio->remaining_discard <= VDO_BLOCK_SIZE) || + if ((data_vio->remaining_discard <= discard_size) || (completion->result != VDO_SUCCESS)) { struct data_vio_pool *pool = completion->vdo->data_vio_pool; @@ -1287,12 +1290,12 @@ static void finish_cleanup(struct data_vio *data_vio) return; } - data_vio->remaining_discard -= min_t(u32, data_vio->remaining_discard, - VDO_BLOCK_SIZE - data_vio->offset); + data_vio->remaining_discard -= discard_size; data_vio->is_partial = (data_vio->remaining_discard < VDO_BLOCK_SIZE); data_vio->read = data_vio->is_partial; data_vio->offset = 0; completion->requeue = true; + data_vio->first_reference_operation_complete = false; launch_data_vio(data_vio, data_vio->logical.lbn + 1); } @@ -1965,7 +1968,8 @@ static void allocate_block(struct vdo_completion *completion) .state = VDO_MAPPING_STATE_UNCOMPRESSED, }; - if (data_vio->fua) { + if (data_vio->fua || + data_vio->remaining_discard > (u32) (VDO_BLOCK_SIZE - data_vio->offset)) { prepare_for_dedupe(data_vio); return; } @@ -2042,7 +2046,6 @@ void continue_data_vio_with_block_map_slot(struct vdo_completion *completion) return; } - /* * We don't need to write any data, so skip allocation and just update the block map and * reference counts (via the journal). @@ -2051,7 +2054,7 @@ void continue_data_vio_with_block_map_slot(struct vdo_completion *completion) if (data_vio->is_zero) data_vio->new_mapped.state = VDO_MAPPING_STATE_UNCOMPRESSED; - if (data_vio->remaining_discard > VDO_BLOCK_SIZE) { + if (data_vio->remaining_discard > (u32) (VDO_BLOCK_SIZE - data_vio->offset)) { /* This is not the final block of a discard so we can't acknowledge it yet. */ update_metadata_for_data_vio_write(data_vio, NULL); return; diff --git a/drivers/md/dm-vdo/dedupe.c b/drivers/md/dm-vdo/dedupe.c index 39ac68614419..80628ae93fba 100644 --- a/drivers/md/dm-vdo/dedupe.c +++ b/drivers/md/dm-vdo/dedupe.c @@ -729,6 +729,7 @@ static void process_update_result(struct data_vio *agent) !change_context_state(context, DEDUPE_CONTEXT_COMPLETE, DEDUPE_CONTEXT_IDLE)) return; + agent->dedupe_context = NULL; release_context(context); } @@ -1648,6 +1649,7 @@ static void process_query_result(struct data_vio *agent) if (change_context_state(context, DEDUPE_CONTEXT_COMPLETE, DEDUPE_CONTEXT_IDLE)) { agent->is_duplicate = decode_uds_advice(context); + agent->dedupe_context = NULL; release_context(context); } } @@ -2321,6 +2323,7 @@ static void timeout_index_operations_callback(struct vdo_completion *completion) * send its requestor on its way. */ list_del_init(&context->list_entry); + context->requestor->dedupe_context = NULL; continue_data_vio(context->requestor); timed_out++; } diff --git a/drivers/md/dm-vdo/dm-vdo-target.c b/drivers/md/dm-vdo/dm-vdo-target.c index dd05691e4097..0e04c2021682 100644 --- a/drivers/md/dm-vdo/dm-vdo-target.c +++ b/drivers/md/dm-vdo/dm-vdo-target.c @@ -1105,6 +1105,9 @@ static int vdo_message(struct dm_target *ti, unsigned int argc, char **argv, if ((argc == 1) && (strcasecmp(argv[0], "stats") == 0)) { vdo_write_stats(vdo, result_buffer, maxlen); result = 1; + } else if ((argc == 1) && (strcasecmp(argv[0], "config") == 0)) { + vdo_write_config(vdo, &result_buffer, &maxlen); + result = 1; } else { result = vdo_status_to_errno(process_vdo_message(vdo, argc, argv)); } @@ -2293,6 +2296,14 @@ static void handle_load_error(struct vdo_completion *completion) return; } + if ((completion->result == VDO_UNSUPPORTED_VERSION) && + (vdo->admin.phase == LOAD_PHASE_MAKE_DIRTY)) { + vdo_log_error("Aborting load due to unsupported version"); + vdo->admin.phase = LOAD_PHASE_FINISHED; + load_callback(completion); + return; + } + vdo_log_error_strerror(completion->result, "Entering read-only mode due to load error"); vdo->admin.phase = LOAD_PHASE_WAIT_FOR_READ_ONLY; @@ -2737,6 +2748,19 @@ static int vdo_preresume_registered(struct dm_target *ti, struct vdo *vdo) vdo_log_info("starting device '%s'", device_name); result = perform_admin_operation(vdo, LOAD_PHASE_START, load_callback, handle_load_error, "load"); + if (result == VDO_UNSUPPORTED_VERSION) { + /* + * A component version is not supported. This can happen when the + * recovery journal metadata is in an old version format. Abort the + * load without saving the state. + */ + vdo->suspend_type = VDO_ADMIN_STATE_SUSPENDING; + perform_admin_operation(vdo, SUSPEND_PHASE_START, + suspend_callback, suspend_callback, + "suspend"); + return result; + } + if ((result != VDO_SUCCESS) && (result != VDO_READ_ONLY)) { /* * Something has gone very wrong. Make sure everything has drained and @@ -2808,7 +2832,8 @@ static int vdo_preresume(struct dm_target *ti) vdo_register_thread_device_id(&instance_thread, &vdo->instance); result = vdo_preresume_registered(ti, vdo); - if ((result == VDO_PARAMETER_MISMATCH) || (result == VDO_INVALID_ADMIN_STATE)) + if ((result == VDO_PARAMETER_MISMATCH) || (result == VDO_INVALID_ADMIN_STATE) || + (result == VDO_UNSUPPORTED_VERSION)) result = -EINVAL; vdo_unregister_thread_device_id(); return vdo_status_to_errno(result); @@ -2832,7 +2857,7 @@ static void vdo_resume(struct dm_target *ti) static struct target_type vdo_target_bio = { .features = DM_TARGET_SINGLETON, .name = "vdo", - .version = { 9, 0, 0 }, + .version = { 9, 1, 0 }, .module = THIS_MODULE, .ctr = vdo_ctr, .dtr = vdo_dtr, diff --git a/drivers/md/dm-vdo/indexer/chapter-index.c b/drivers/md/dm-vdo/indexer/chapter-index.c index 7e32a25d3f2f..fb1db41c794b 100644 --- a/drivers/md/dm-vdo/indexer/chapter-index.c +++ b/drivers/md/dm-vdo/indexer/chapter-index.c @@ -177,7 +177,7 @@ int uds_pack_open_chapter_index_page(struct open_chapter_index *chapter_index, if (list_number < 0) return UDS_OVERFLOW; - next_list = first_list + list_number--, + next_list = first_list + list_number--; result = uds_start_delta_index_search(delta_index, next_list, 0, &entry); if (result != UDS_SUCCESS) diff --git a/drivers/md/dm-vdo/io-submitter.c b/drivers/md/dm-vdo/io-submitter.c index 9a3716bb3c05..ab62abe18827 100644 --- a/drivers/md/dm-vdo/io-submitter.c +++ b/drivers/md/dm-vdo/io-submitter.c @@ -346,7 +346,6 @@ void __submit_metadata_vio(struct vio *vio, physical_block_number_t physical, VDO_ASSERT_LOG_ONLY(!code->quiescent, "I/O not allowed in state %s", code->name); - VDO_ASSERT_LOG_ONLY(vio->bio->bi_next == NULL, "metadata bio has no next bio"); vdo_reset_completion(completion); completion->error_handler = error_handler; diff --git a/drivers/md/dm-vdo/message-stats.c b/drivers/md/dm-vdo/message-stats.c index 2802cf92922b..75dfcd7c5f63 100644 --- a/drivers/md/dm-vdo/message-stats.c +++ b/drivers/md/dm-vdo/message-stats.c @@ -4,6 +4,7 @@ */ #include "dedupe.h" +#include "indexer.h" #include "logger.h" #include "memory-alloc.h" #include "message-stats.h" @@ -430,3 +431,50 @@ int vdo_write_stats(struct vdo *vdo, char *buf, unsigned int maxlen) vdo_free(stats); return VDO_SUCCESS; } + +static void write_index_memory(u32 mem, char **buf, unsigned int *maxlen) +{ + char *prefix = "memorySize : "; + + /* Convert index memory to fractional value */ + if (mem == (u32)UDS_MEMORY_CONFIG_256MB) + write_string(prefix, "0.25, ", NULL, buf, maxlen); + else if (mem == (u32)UDS_MEMORY_CONFIG_512MB) + write_string(prefix, "0.50, ", NULL, buf, maxlen); + else if (mem == (u32)UDS_MEMORY_CONFIG_768MB) + write_string(prefix, "0.75, ", NULL, buf, maxlen); + else + write_u32(prefix, mem, ", ", buf, maxlen); +} + +static void write_index_config(struct index_config *config, char **buf, + unsigned int *maxlen) +{ + write_string("index : ", "{ ", NULL, buf, maxlen); + /* index mem size */ + write_index_memory(config->mem, buf, maxlen); + /* whether the index is sparse or not */ + write_bool("isSparse : ", config->sparse, ", ", buf, maxlen); + write_string(NULL, "}", ", ", buf, maxlen); +} + +int vdo_write_config(struct vdo *vdo, char **buf, unsigned int *maxlen) +{ + struct vdo_config *config = &vdo->states.vdo.config; + + write_string(NULL, "{ ", NULL, buf, maxlen); + /* version */ + write_u32("version : ", 1, ", ", buf, maxlen); + /* physical size */ + write_block_count_t("physicalSize : ", config->physical_blocks * VDO_BLOCK_SIZE, ", ", + buf, maxlen); + /* logical size */ + write_block_count_t("logicalSize : ", config->logical_blocks * VDO_BLOCK_SIZE, ", ", + buf, maxlen); + /* slab size */ + write_block_count_t("slabSize : ", config->slab_size, ", ", buf, maxlen); + /* index config */ + write_index_config(&vdo->geometry.index_config, buf, maxlen); + write_string(NULL, "}", NULL, buf, maxlen); + return VDO_SUCCESS; +} diff --git a/drivers/md/dm-vdo/message-stats.h b/drivers/md/dm-vdo/message-stats.h index f7fceca9acab..f9c95eff569d 100644 --- a/drivers/md/dm-vdo/message-stats.h +++ b/drivers/md/dm-vdo/message-stats.h @@ -8,6 +8,7 @@ #include "types.h" +int vdo_write_config(struct vdo *vdo, char **buf, unsigned int *maxlen); int vdo_write_stats(struct vdo *vdo, char *buf, unsigned int maxlen); #endif /* VDO_MESSAGE_STATS_H */ diff --git a/drivers/md/dm-vdo/repair.c b/drivers/md/dm-vdo/repair.c index 7e0009d2f67d..ffff2c999518 100644 --- a/drivers/md/dm-vdo/repair.c +++ b/drivers/md/dm-vdo/repair.c @@ -1202,17 +1202,14 @@ static bool __must_check is_valid_recovery_journal_block(const struct recovery_j * @journal: The journal to use. * @header: The unpacked block header to check. * @sequence: The expected sequence number. - * @type: The expected metadata type. * * Return: True if the block matches. */ static bool __must_check is_exact_recovery_journal_block(const struct recovery_journal *journal, const struct recovery_block_header *header, - sequence_number_t sequence, - enum vdo_metadata_type type) + sequence_number_t sequence) { - return ((header->metadata_type == type) && - (header->sequence_number == sequence) && + return ((header->sequence_number == sequence) && (is_valid_recovery_journal_block(journal, header, true))); } @@ -1371,7 +1368,8 @@ static void extract_entries_from_block(struct repair_completion *repair, get_recovery_journal_block_header(journal, repair->journal_data, sequence); - if (!is_exact_recovery_journal_block(journal, &header, sequence, format)) { + if (!is_exact_recovery_journal_block(journal, &header, sequence) || + (header.metadata_type != format)) { /* This block is invalid, so skip it. */ return; } @@ -1557,10 +1555,13 @@ static int parse_journal_for_recovery(struct repair_completion *repair) sequence_number_t i, head; bool found_entries = false; struct recovery_journal *journal = repair->completion.vdo->recovery_journal; + struct recovery_block_header header; + enum vdo_metadata_type expected_format; head = min(repair->block_map_head, repair->slab_journal_head); + header = get_recovery_journal_block_header(journal, repair->journal_data, head); + expected_format = header.metadata_type; for (i = head; i <= repair->highest_tail; i++) { - struct recovery_block_header header; journal_entry_count_t block_entries; u8 j; @@ -1572,19 +1573,15 @@ static int parse_journal_for_recovery(struct repair_completion *repair) }; header = get_recovery_journal_block_header(journal, repair->journal_data, i); - if (header.metadata_type == VDO_METADATA_RECOVERY_JOURNAL) { - /* This is an old format block, so we need to upgrade */ - vdo_log_error_strerror(VDO_UNSUPPORTED_VERSION, - "Recovery journal is in the old format, a read-only rebuild is required."); - vdo_enter_read_only_mode(repair->completion.vdo, - VDO_UNSUPPORTED_VERSION); - return VDO_UNSUPPORTED_VERSION; - } - - if (!is_exact_recovery_journal_block(journal, &header, i, - VDO_METADATA_RECOVERY_JOURNAL_2)) { + if (!is_exact_recovery_journal_block(journal, &header, i)) { /* A bad block header was found so this must be the end of the journal. */ break; + } else if (header.metadata_type != expected_format) { + /* There is a mix of old and new format blocks, so we need to rebuild. */ + vdo_log_error_strerror(VDO_CORRUPT_JOURNAL, + "Recovery journal is in an invalid format, a read-only rebuild is required."); + vdo_enter_read_only_mode(repair->completion.vdo, VDO_CORRUPT_JOURNAL); + return VDO_CORRUPT_JOURNAL; } block_entries = header.entry_count; @@ -1620,8 +1617,14 @@ static int parse_journal_for_recovery(struct repair_completion *repair) break; } - if (!found_entries) + if (!found_entries) { return validate_heads(repair); + } else if (expected_format == VDO_METADATA_RECOVERY_JOURNAL) { + /* All journal blocks have the old format, so we need to upgrade. */ + vdo_log_error_strerror(VDO_UNSUPPORTED_VERSION, + "Recovery journal is in the old format. Downgrade and complete recovery, then upgrade with a clean volume"); + return VDO_UNSUPPORTED_VERSION; + } /* Set the tail to the last valid tail block, if there is one. */ if (repair->tail_recovery_point.sector_count == 0) diff --git a/drivers/md/dm-vdo/status-codes.c b/drivers/md/dm-vdo/status-codes.c index d3493450b169..dd252d660b6d 100644 --- a/drivers/md/dm-vdo/status-codes.c +++ b/drivers/md/dm-vdo/status-codes.c @@ -28,7 +28,7 @@ const struct error_info vdo_status_list[] = { { "VDO_LOCK_ERROR", "A lock is held incorrectly" }, { "VDO_READ_ONLY", "The device is in read-only mode" }, { "VDO_SHUTTING_DOWN", "The device is shutting down" }, - { "VDO_CORRUPT_JOURNAL", "Recovery journal entries corrupted" }, + { "VDO_CORRUPT_JOURNAL", "Recovery journal corrupted" }, { "VDO_TOO_MANY_SLABS", "Exceeds maximum number of slabs supported" }, { "VDO_INVALID_FRAGMENT", "Compressed block fragment is invalid" }, { "VDO_RETRY_AFTER_REBUILD", "Retry operation after rebuilding finishes" }, diff --git a/drivers/md/dm-vdo/status-codes.h b/drivers/md/dm-vdo/status-codes.h index 72da04159f88..426dc8e2ca5d 100644 --- a/drivers/md/dm-vdo/status-codes.h +++ b/drivers/md/dm-vdo/status-codes.h @@ -52,7 +52,7 @@ enum vdo_status_codes { VDO_READ_ONLY, /* the VDO is shutting down */ VDO_SHUTTING_DOWN, - /* the recovery journal has corrupt entries */ + /* the recovery journal has corrupt entries or corrupt metadata */ VDO_CORRUPT_JOURNAL, /* exceeds maximum number of slabs supported */ VDO_TOO_MANY_SLABS, diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 24ba9a10444c..36e4ddfe2d15 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -273,8 +273,10 @@ out: if (v->mode == DM_VERITY_MODE_LOGGING) return 0; - if (v->mode == DM_VERITY_MODE_RESTART) - kernel_restart("dm-verity device corrupted"); + if (v->mode == DM_VERITY_MODE_RESTART) { + pr_emerg("dm-verity device corrupted\n"); + emergency_restart(); + } if (v->mode == DM_VERITY_MODE_PANIC) panic("dm-verity device corrupted"); @@ -597,6 +599,23 @@ static void verity_finish_io(struct dm_verity_io *io, blk_status_t status) if (!static_branch_unlikely(&use_bh_wq_enabled) || !io->in_bh) verity_fec_finish_io(io); + if (unlikely(status != BLK_STS_OK) && + unlikely(!(bio->bi_opf & REQ_RAHEAD)) && + !verity_is_system_shutting_down()) { + if (v->mode == DM_VERITY_MODE_RESTART || + v->mode == DM_VERITY_MODE_PANIC) + DMERR_LIMIT("%s has error: %s", v->data_dev->name, + blk_status_to_str(status)); + + if (v->mode == DM_VERITY_MODE_RESTART) { + pr_emerg("dm-verity device corrupted\n"); + emergency_restart(); + } + + if (v->mode == DM_VERITY_MODE_PANIC) + panic("dm-verity device corrupted"); + } + bio_endio(bio); } diff --git a/drivers/md/dm-verity-verify-sig.c b/drivers/md/dm-verity-verify-sig.c index d351d7d39c60..a9e2c6c0a33c 100644 --- a/drivers/md/dm-verity-verify-sig.c +++ b/drivers/md/dm-verity-verify-sig.c @@ -127,7 +127,7 @@ int verity_verify_root_hash(const void *root_hash, size_t root_hash_len, #endif VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); #ifdef CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG_PLATFORM_KEYRING - if (ret == -ENOKEY) + if (ret == -ENOKEY || ret == -EKEYREJECTED) ret = verify_pkcs7_signature(root_hash, root_hash_len, sig_data, sig_len, VERIFY_USE_PLATFORM_KEYRING, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 87bb90303435..ff4a6b570b76 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2030,10 +2030,15 @@ static void dm_submit_bio(struct bio *bio) struct dm_table *map; map = dm_get_live_table(md, &srcu_idx); + if (unlikely(!map)) { + DMERR_LIMIT("%s: mapping table unavailable, erroring io", + dm_device_name(md)); + bio_io_error(bio); + goto out; + } - /* If suspended, or map not yet available, queue this IO for later */ - if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) || - unlikely(!map)) { + /* If suspended, queue this IO for later */ + if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) { if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); else if (bio->bi_opf & REQ_RAHEAD) diff --git a/drivers/md/dm.h b/drivers/md/dm.h index cc466ad5cb1d..8ad782249af8 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -109,7 +109,6 @@ void dm_zone_endio(struct dm_io *io, struct bio *clone); int dm_blk_report_zones(struct gendisk *disk, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); bool dm_is_zone_write(struct mapped_device *md, struct bio *bio); -int dm_zone_map_bio(struct dm_target_io *io); int dm_zone_get_reset_bitmap(struct mapped_device *md, struct dm_table *t, sector_t sector, unsigned int nr_zones, unsigned long *need_reset); @@ -119,10 +118,6 @@ static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) { return false; } -static inline int dm_zone_map_bio(struct dm_target_io *tio) -{ - return DM_MAPIO_KILL; -} #endif /* diff --git a/drivers/media/cec/core/cec-api.c b/drivers/media/cec/core/cec-api.c index c75a4057f00e..c50299246fc4 100644 --- a/drivers/media/cec/core/cec-api.c +++ b/drivers/media/cec/core/cec-api.c @@ -698,5 +698,4 @@ const struct file_operations cec_devnode_fops = { .compat_ioctl = cec_ioctl, .release = cec_release, .poll = cec_poll, - .llseek = no_llseek, }; diff --git a/drivers/media/mc/mc-devnode.c b/drivers/media/mc/mc-devnode.c index 318e267e798e..56444edaf136 100644 --- a/drivers/media/mc/mc-devnode.c +++ b/drivers/media/mc/mc-devnode.c @@ -204,7 +204,6 @@ static const struct file_operations media_devnode_fops = { #endif /* CONFIG_COMPAT */ .release = media_release, .poll = media_poll, - .llseek = no_llseek, }; int __must_check media_devnode_register(struct media_device *mdev, diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index b8dfd530fab7..f042f3f14afa 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -706,7 +706,6 @@ static const struct file_operations lirc_fops = { .poll = lirc_poll, .open = lirc_open, .release = lirc_close, - .llseek = no_llseek, }; static void lirc_release_device(struct device *ld) diff --git a/drivers/media/usb/uvc/uvc_debugfs.c b/drivers/media/usb/uvc/uvc_debugfs.c index 1a1258d4ffca..14fa41cb8148 100644 --- a/drivers/media/usb/uvc/uvc_debugfs.c +++ b/drivers/media/usb/uvc/uvc_debugfs.c @@ -59,7 +59,6 @@ static int uvc_debugfs_stats_release(struct inode *inode, struct file *file) static const struct file_operations uvc_debugfs_stats_fops = { .owner = THIS_MODULE, .open = uvc_debugfs_stats_open, - .llseek = no_llseek, .read = uvc_debugfs_stats_read, .release = uvc_debugfs_stats_release, }; diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 570ba00e00b3..3d7711cc42bc 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -483,7 +483,6 @@ static const struct file_operations v4l2_fops = { #endif .release = v4l2_release, .poll = v4l2_poll, - .llseek = no_llseek, }; /** diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c index 9f3999750c23..77fa55df70d0 100644 --- a/drivers/message/fusion/mptctl.c +++ b/drivers/message/fusion/mptctl.c @@ -1609,7 +1609,7 @@ mptctl_eventreport (MPT_ADAPTER *ioc, unsigned long arg) maxEvents = numBytes/sizeof(MPT_IOCTL_EVENTS); - max = MPTCTL_EVENT_LOG_SIZE < maxEvents ? MPTCTL_EVENT_LOG_SIZE : maxEvents; + max = min(maxEvents, MPTCTL_EVENT_LOG_SIZE); /* If fewer than 1 event is requested, there must have * been some type of error. @@ -2691,7 +2691,6 @@ mptctl_hp_targetinfo(MPT_ADAPTER *ioc, unsigned long arg) static const struct file_operations mptctl_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .fasync = mptctl_fasync, .unlocked_ioctl = mptctl_ioctl, #ifdef CONFIG_COMPAT diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c index 1fc635a27568..4233dc4cc7d6 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d.c +++ b/drivers/misc/lis3lv02d/lis3lv02d.c @@ -669,7 +669,6 @@ static int lis3lv02d_misc_fasync(int fd, struct file *file, int on) static const struct file_operations lis3lv02d_misc_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = lis3lv02d_misc_read, .open = lis3lv02d_misc_open, .release = lis3lv02d_misc_release, diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 40c3fe26f76d..1f5aaf16e300 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -1176,7 +1176,6 @@ static const struct file_operations mei_fops = { .poll = mei_poll, .fsync = mei_fsync, .fasync = mei_fasync, - .llseek = no_llseek }; /** diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c index 3c2f743c58b0..4954553b7baa 100644 --- a/drivers/misc/ntsync.c +++ b/drivers/misc/ntsync.c @@ -126,7 +126,6 @@ static const struct file_operations ntsync_obj_fops = { .release = ntsync_obj_release, .unlocked_ioctl = ntsync_obj_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct ntsync_obj *ntsync_alloc_obj(struct ntsync_device *dev, @@ -233,7 +232,6 @@ static const struct file_operations ntsync_fops = { .release = ntsync_char_release, .unlocked_ioctl = ntsync_char_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct miscdevice ntsync_misc = { diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index 30bd7c39c261..701db2c5859b 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -279,7 +279,6 @@ static const struct file_operations phantom_file_ops = { .unlocked_ioctl = phantom_ioctl, .compat_ioctl = phantom_compat_ioctl, .poll = phantom_poll, - .llseek = no_llseek, }; static irqreturn_t phantom_isr(int irq, void *data) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index f58bea534004..ef06a4d5d65b 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2734,7 +2734,6 @@ static const struct file_operations mmc_rpmb_fileops = { .release = mmc_rpmb_chrdev_release, .open = mmc_rpmb_chrdev_open, .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = mmc_rpmb_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = mmc_rpmb_ioctl_compat, diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 0d8f04cf03c5..6bb80d7714bc 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -1095,7 +1095,6 @@ const struct file_operations ubi_vol_cdev_operations = { /* UBI character device operations */ const struct file_operations ubi_cdev_operations = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = ubi_cdev_ioctl, .compat_ioctl = compat_ptr_ioctl, }; @@ -1105,5 +1104,4 @@ const struct file_operations ubi_ctrl_cdev_operations = { .owner = THIS_MODULE, .unlocked_ioctl = ctrl_cdev_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index 9ec3b8b6a0aa..d2a53961d8e2 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -470,7 +470,6 @@ static const struct file_operations dfs_fops = { .read = dfs_file_read, .write = dfs_file_write, .open = simple_open, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index a1f91ff8ec56..41e80f78b316 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -1414,7 +1414,6 @@ out: static const struct file_operations nsim_nexthop_bucket_activity_fops = { .open = simple_open, .write = nsim_nexthop_bucket_activity_write, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 77574f7a3bd4..5aa41d5f7765 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1162,7 +1162,6 @@ static const struct file_operations tap_fops = { .read_iter = tap_read_iter, .write_iter = tap_write_iter, .poll = tap_poll, - .llseek = no_llseek, .unlocked_ioctl = tap_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 5f77faef0ff1..9a0f6eb32016 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3543,7 +3543,6 @@ static void tun_chr_show_fdinfo(struct seq_file *m, struct file *file) static const struct file_operations tun_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read_iter = tun_chr_read_iter, .write_iter = tun_chr_write_iter, .poll = tun_chr_poll, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index df53dd1d7e74..da72fd2d541f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -1184,7 +1184,6 @@ static ssize_t bus_reset_write(struct file *file, const char __user *user_buf, static const struct file_operations bus_reset_fops = { .open = simple_open, - .llseek = no_llseek, .write = bus_reset_write, }; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 99a541d442bb..49a6aff42376 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -3768,7 +3768,6 @@ static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file) } const struct file_operations iwl_dbgfs_d3_test_ops = { - .llseek = no_llseek, .open = iwl_mvm_d3_test_open, .read = iwl_mvm_d3_test_read, .release = iwl_mvm_d3_test_release, diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c index 4525ad1b59f4..839154c46e46 100644 --- a/drivers/platform/chrome/cros_ec_debugfs.c +++ b/drivers/platform/chrome/cros_ec_debugfs.c @@ -302,7 +302,6 @@ static const struct file_operations cros_ec_console_log_fops = { .owner = THIS_MODULE, .open = cros_ec_console_log_open, .read = cros_ec_console_log_read, - .llseek = no_llseek, .poll = cros_ec_console_log_poll, .release = cros_ec_console_log_release, }; diff --git a/drivers/platform/chrome/wilco_ec/debugfs.c b/drivers/platform/chrome/wilco_ec/debugfs.c index 983f2fa44ba5..99486086af6a 100644 --- a/drivers/platform/chrome/wilco_ec/debugfs.c +++ b/drivers/platform/chrome/wilco_ec/debugfs.c @@ -156,7 +156,6 @@ static const struct file_operations fops_raw = { .owner = THIS_MODULE, .read = raw_read, .write = raw_write, - .llseek = no_llseek, }; #define CMD_KB_CHROME 0x88 diff --git a/drivers/platform/chrome/wilco_ec/event.c b/drivers/platform/chrome/wilco_ec/event.c index bd1fb53ba028..196e46a1d489 100644 --- a/drivers/platform/chrome/wilco_ec/event.c +++ b/drivers/platform/chrome/wilco_ec/event.c @@ -403,7 +403,6 @@ static const struct file_operations event_fops = { .poll = event_poll, .read = event_read, .release = event_release, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/platform/chrome/wilco_ec/telemetry.c b/drivers/platform/chrome/wilco_ec/telemetry.c index 21d4cbbb009a..a87877e4300a 100644 --- a/drivers/platform/chrome/wilco_ec/telemetry.c +++ b/drivers/platform/chrome/wilco_ec/telemetry.c @@ -330,7 +330,6 @@ static const struct file_operations telem_fops = { .write = telem_write, .read = telem_read, .release = telem_release, - .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/platform/surface/surface_aggregator_cdev.c b/drivers/platform/surface/surface_aggregator_cdev.c index 07e065b9159f..165b1416230d 100644 --- a/drivers/platform/surface/surface_aggregator_cdev.c +++ b/drivers/platform/surface/surface_aggregator_cdev.c @@ -670,7 +670,6 @@ static const struct file_operations ssam_controller_fops = { .fasync = ssam_cdev_fasync, .unlocked_ioctl = ssam_cdev_device_ioctl, .compat_ioctl = ssam_cdev_device_ioctl, - .llseek = no_llseek, }; diff --git a/drivers/platform/surface/surface_dtx.c b/drivers/platform/surface/surface_dtx.c index 2de843b7ea70..89ca6b50e812 100644 --- a/drivers/platform/surface/surface_dtx.c +++ b/drivers/platform/surface/surface_dtx.c @@ -555,7 +555,6 @@ static const struct file_operations surface_dtx_fops = { .fasync = surface_dtx_fasync, .unlocked_ioctl = surface_dtx_ioctl, .compat_ioctl = surface_dtx_ioctl, - .llseek = no_llseek, }; diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 5d19baae6a38..25d47907db17 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -319,7 +319,6 @@ static int pps_cdev_release(struct inode *inode, struct file *file) static const struct file_operations pps_cdev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .poll = pps_cdev_poll, .fasync = pps_cdev_fasync, .compat_ioctl = pps_cdev_compat_ioctl, diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index 4aad9bb99868..c4a3ab53dcd4 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -523,7 +523,6 @@ static int rtc_dev_release(struct inode *inode, struct file *file) static const struct file_operations rtc_dev_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = rtc_dev_read, .poll = rtc_dev_poll, .unlocked_ioctl = rtc_dev_ioctl, diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index 0013bff0447d..1f58ae8b151e 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -850,7 +850,6 @@ static const struct file_operations wdt_fops = { .write = wdt_write, .open = wdt_open, .release = wdt_release, - .llseek = no_llseek, }; static struct miscdevice wdt_dev = { diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 61515781c5dd..cfe7efd5b5da 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -515,7 +515,6 @@ static const struct file_operations fs3270_fops = { .compat_ioctl = fs3270_ioctl, /* ioctl */ .open = fs3270_open, /* open */ .release = fs3270_close, /* release */ - .llseek = no_llseek, }; static void fs3270_create_cb(int minor) diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c index 248b5db3eaa8..dd6051602070 100644 --- a/drivers/s390/char/sclp_ctl.c +++ b/drivers/s390/char/sclp_ctl.c @@ -115,7 +115,6 @@ static const struct file_operations sclp_ctl_fops = { .open = nonseekable_open, .unlocked_ioctl = sclp_ctl_ioctl, .compat_ioctl = sclp_ctl_ioctl, - .llseek = no_llseek, }; /* diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c index cc8237afeffa..89778d922d9f 100644 --- a/drivers/s390/char/tape_char.c +++ b/drivers/s390/char/tape_char.c @@ -52,7 +52,6 @@ static const struct file_operations tape_fops = #endif .open = tapechar_open, .release = tapechar_release, - .llseek = no_llseek, }; static int tapechar_major = TAPECHAR_MAJOR; diff --git a/drivers/s390/char/uvdevice.c b/drivers/s390/char/uvdevice.c index 42c9f77f8da0..f598edc5f251 100644 --- a/drivers/s390/char/uvdevice.c +++ b/drivers/s390/char/uvdevice.c @@ -448,7 +448,6 @@ static long uvio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static const struct file_operations uvio_dev_fops = { .owner = THIS_MODULE, .unlocked_ioctl = uvio_ioctl, - .llseek = no_llseek, }; static struct miscdevice uvio_dev_miscdev = { diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c index eb0520a9d4af..c6d58335beb4 100644 --- a/drivers/s390/char/vmcp.c +++ b/drivers/s390/char/vmcp.c @@ -242,7 +242,6 @@ static const struct file_operations vmcp_fops = { .write = vmcp_write, .unlocked_ioctl = vmcp_ioctl, .compat_ioctl = vmcp_ioctl, - .llseek = no_llseek, }; static struct miscdevice vmcp_dev = { diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index c09e1e09fb66..bd5cecc44123 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -96,7 +96,6 @@ static const struct file_operations vmlogrdr_fops = { .open = vmlogrdr_open, .release = vmlogrdr_release, .read = vmlogrdr_read, - .llseek = no_llseek, }; diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index 0969fa01df58..33cebb91b933 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -165,7 +165,6 @@ static const struct file_operations zcore_reipl_fops = { .write = zcore_reipl_write, .open = zcore_reipl_open, .release = zcore_reipl_release, - .llseek = no_llseek, }; static ssize_t zcore_hsa_read(struct file *filp, char __user *buf, @@ -200,7 +199,6 @@ static const struct file_operations zcore_hsa_fops = { .write = zcore_hsa_write, .read = zcore_hsa_read, .open = nonseekable_open, - .llseek = no_llseek, }; static int __init check_sdias(void) diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index e6c800653f98..1e58ee3cc87d 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -924,7 +924,6 @@ static const struct file_operations chsc_fops = { .release = chsc_release, .unlocked_ioctl = chsc_ioctl, .compat_ioctl = chsc_ioctl, - .llseek = no_llseek, }; static struct miscdevice chsc_misc_device = { diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 53b68f8c32f3..7b59d20bf785 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -1332,7 +1332,6 @@ static ssize_t cio_settle_write(struct file *file, const char __user *buf, static const struct proc_ops cio_settle_proc_ops = { .proc_open = nonseekable_open, .proc_write = cio_settle_write, - .proc_lseek = no_llseek, }; static int __init cio_settle_init(void) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index c20251e00cf9..3a39e167bdbf 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -776,7 +776,6 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, static const struct file_operations pkey_fops = { .owner = THIS_MODULE, .open = nonseekable_open, - .llseek = no_llseek, .unlocked_ioctl = pkey_unlocked_ioctl, }; diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index 4aeb3e1213c7..67a807e2e75b 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -26,6 +26,18 @@ MODULE_LICENSE("GPL v2"); struct ap_matrix_dev *matrix_dev; debug_info_t *vfio_ap_dbf_info; +static ssize_t features_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "guest_matrix hotplug ap_config\n"); +} +static DEVICE_ATTR_RO(features); + +static struct attribute *matrix_dev_attrs[] = { + &dev_attr_features.attr, + NULL, +}; +ATTRIBUTE_GROUPS(matrix_dev); + /* Only type 10 adapters (CEX4 and later) are supported * by the AP matrix device driver */ @@ -68,6 +80,7 @@ static struct device_driver matrix_driver = { .name = "vfio_ap", .bus = &matrix_bus, .suppress_bind_attrs = true, + .dev_groups = matrix_dev_groups, }; static int vfio_ap_matrix_dev_create(void) diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index f9a47b54c51a..5020696f1379 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -1908,7 +1908,6 @@ static const struct file_operations zcrypt_fops = { #endif .open = zcrypt_open, .release = zcrypt_release, - .llseek = no_llseek, }; /* diff --git a/drivers/sbus/char/openprom.c b/drivers/sbus/char/openprom.c index cc178874c4a6..8643947fee8e 100644 --- a/drivers/sbus/char/openprom.c +++ b/drivers/sbus/char/openprom.c @@ -687,7 +687,6 @@ static int openprom_release(struct inode * inode, struct file * file) static const struct file_operations openprom_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = openprom_ioctl, .compat_ioctl = openprom_compat_ioctl, .open = openprom_open, diff --git a/drivers/sbus/char/uctrl.c b/drivers/sbus/char/uctrl.c index 3c88f29f4c47..8bbed7a7afb7 100644 --- a/drivers/sbus/char/uctrl.c +++ b/drivers/sbus/char/uctrl.c @@ -221,7 +221,6 @@ static irqreturn_t uctrl_interrupt(int irq, void *dev_id) static const struct file_operations uctrl_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = uctrl_ioctl, .open = uctrl_open, }; diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h index d92cf1dccc2f..0909b03e2497 100644 --- a/drivers/scsi/cxgbi/libcxgbi.h +++ b/drivers/scsi/cxgbi/libcxgbi.h @@ -485,7 +485,6 @@ struct cxgbi_device { unsigned char nmtus; unsigned char nports; struct pci_dev *pdev; - struct dentry *debugfs_root; struct iscsi_transport *itp; struct module *owner; @@ -499,7 +498,6 @@ struct cxgbi_device { unsigned int rxq_idx_cntr; struct cxgbi_ports_map pmap; - void (*dev_ddp_cleanup)(struct cxgbi_device *); struct cxgbi_ppm* (*cdev2ppm)(struct cxgbi_device *); int (*csk_ddp_set_map)(struct cxgbi_ppm *, struct cxgbi_sock *, struct cxgbi_task_tag_info *); @@ -512,7 +510,6 @@ struct cxgbi_device { unsigned int, int); void (*csk_release_offload_resources)(struct cxgbi_sock *); - int (*csk_rx_pdu_ready)(struct cxgbi_sock *, struct sk_buff *); u32 (*csk_send_rx_credits)(struct cxgbi_sock *, u32); int (*csk_push_tx_frames)(struct cxgbi_sock *, int); void (*csk_send_abort_req)(struct cxgbi_sock *); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index feda9b54b443..4cd3a3eab6f1 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2421,7 +2421,7 @@ out: spin_lock_irqsave(&device->done_lock, flags); if (test_bit(SAS_HA_FROZEN, &ha->state)) { spin_unlock_irqrestore(&device->done_lock, flags); - dev_info(dev, "slot complete: task(%pK) ignored\n ", + dev_info(dev, "slot complete: task(%pK) ignored\n", task); return; } diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index a3d1013c8307..e66c3ef74267 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -37,6 +37,7 @@ static unsigned int default_timeout = IBMVFC_DEFAULT_TIMEOUT; static u64 max_lun = IBMVFC_MAX_LUN; static unsigned int max_targets = IBMVFC_MAX_TARGETS; static unsigned int max_requests = IBMVFC_MAX_REQUESTS_DEFAULT; +static u16 max_sectors = IBMVFC_MAX_SECTORS; static u16 scsi_qdepth = IBMVFC_SCSI_QDEPTH; static unsigned int disc_threads = IBMVFC_MAX_DISC_THREADS; static unsigned int ibmvfc_debug = IBMVFC_DEBUG; @@ -83,6 +84,9 @@ MODULE_PARM_DESC(default_timeout, module_param_named(max_requests, max_requests, uint, S_IRUGO); MODULE_PARM_DESC(max_requests, "Maximum requests for this adapter. " "[Default=" __stringify(IBMVFC_MAX_REQUESTS_DEFAULT) "]"); +module_param_named(max_sectors, max_sectors, ushort, S_IRUGO); +MODULE_PARM_DESC(max_sectors, "Maximum sectors for this adapter. " + "[Default=" __stringify(IBMVFC_MAX_SECTORS) "]"); module_param_named(scsi_qdepth, scsi_qdepth, ushort, S_IRUGO); MODULE_PARM_DESC(scsi_qdepth, "Maximum scsi command depth per adapter queue. " "[Default=" __stringify(IBMVFC_SCSI_QDEPTH) "]"); @@ -1494,7 +1498,7 @@ static void ibmvfc_set_login_info(struct ibmvfc_host *vhost) memset(login_info, 0, sizeof(*login_info)); login_info->ostype = cpu_to_be32(IBMVFC_OS_LINUX); - login_info->max_dma_len = cpu_to_be64(IBMVFC_MAX_SECTORS << 9); + login_info->max_dma_len = cpu_to_be64(max_sectors << 9); login_info->max_payload = cpu_to_be32(sizeof(struct ibmvfc_fcp_cmd_iu)); login_info->max_response = cpu_to_be32(sizeof(struct ibmvfc_fcp_rsp)); login_info->partition_num = cpu_to_be32(vhost->partition_number); @@ -5230,7 +5234,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt) } vhost->logged_in = 1; - npiv_max_sectors = min((uint)(be64_to_cpu(rsp->max_dma_len) >> 9), IBMVFC_MAX_SECTORS); + npiv_max_sectors = min((uint)(be64_to_cpu(rsp->max_dma_len) >> 9), max_sectors); dev_info(vhost->dev, "Host partition: %s, device: %s %s %s max sectors %u\n", rsp->partition_name, rsp->device_name, rsp->port_loc_code, rsp->drc_name, npiv_max_sectors); @@ -6329,7 +6333,7 @@ static int ibmvfc_probe(struct vio_dev *vdev, const struct vio_device_id *id) shost->can_queue = scsi_qdepth; shost->max_lun = max_lun; shost->max_id = max_targets; - shost->max_sectors = IBMVFC_MAX_SECTORS; + shost->max_sectors = max_sectors; shost->max_cmd_len = IBMVFC_MAX_CDB_LEN; shost->unique_id = shost->host_no; shost->nr_hw_queues = mq_enabled ? min(max_scsi_queues, nr_scsi_hw_queues) : 1; @@ -6556,6 +6560,7 @@ static struct fc_function_template ibmvfc_transport_functions = { **/ static int __init ibmvfc_module_init(void) { + int min_max_sectors = PAGE_SIZE >> 9; int rc; if (!firmware_has_feature(FW_FEATURE_VIO)) @@ -6564,6 +6569,16 @@ static int __init ibmvfc_module_init(void) printk(KERN_INFO IBMVFC_NAME": IBM Virtual Fibre Channel Driver version: %s %s\n", IBMVFC_DRIVER_VERSION, IBMVFC_DRIVER_DATE); + /* + * Range check the max_sectors module parameter. The upper bounds is + * implicity checked since the parameter is a ushort. + */ + if (max_sectors < min_max_sectors) { + printk(KERN_ERR IBMVFC_NAME ": max_sectors must be at least %d.\n", + min_max_sectors); + max_sectors = min_max_sectors; + } + ibmvfc_transport_template = fc_attach_transport(&ibmvfc_transport_functions); if (!ibmvfc_transport_template) return -ENOMEM; diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h index 745ad5ac7251..c73ed2314ad0 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.h +++ b/drivers/scsi/ibmvscsi/ibmvfc.h @@ -32,7 +32,7 @@ #define IBMVFC_DEBUG 0 #define IBMVFC_MAX_TARGETS 1024 #define IBMVFC_MAX_LUN 0xffffffff -#define IBMVFC_MAX_SECTORS 0xffffu +#define IBMVFC_MAX_SECTORS 2048 #define IBMVFC_MAX_DISC_THREADS 4 #define IBMVFC_TGT_MEMPOOL_SZ 64 #define IBMVFC_MAX_CMDS_PER_LUN 64 diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c index 4756a3f82531..85059b83ea6b 100644 --- a/drivers/scsi/lpfc/lpfc_bsg.c +++ b/drivers/scsi/lpfc/lpfc_bsg.c @@ -3208,6 +3208,9 @@ lpfc_bsg_diag_loopback_run(struct bsg_job *job) cmdiocbq->num_bdes = num_bde; cmdiocbq->cmd_flag |= LPFC_IO_LIBDFC; cmdiocbq->cmd_flag |= LPFC_IO_LOOPBACK; + if (phba->cfg_vmid_app_header) + cmdiocbq->cmd_flag |= LPFC_IO_VMID; + cmdiocbq->vport = phba->pport; cmdiocbq->cmd_cmpl = NULL; cmdiocbq->bpl_dmabuf = txbmp; diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 2dedd1493e5b..134bc96dd134 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -1572,8 +1572,8 @@ lpfc_cmpl_ct_cmd_gft_id(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } } } else - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "3065 GFT_ID failed x%08x\n", ulp_status); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_DISCOVERY, + "3065 GFT_ID status x%08x\n", ulp_status); out: lpfc_ct_free_iocb(phba, cmdiocb); @@ -1647,6 +1647,18 @@ lpfc_cmpl_ct(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } out: + /* If the caller wanted a synchronous DA_ID completion, signal the + * wait obj and clear flag to reset the vport. + */ + if (ndlp->save_flags & NLP_WAIT_FOR_DA_ID) { + if (ndlp->da_id_waitq) + wake_up(ndlp->da_id_waitq); + } + + spin_lock_irq(&ndlp->lock); + ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID; + spin_unlock_irq(&ndlp->lock); + lpfc_ct_free_iocb(phba, cmdiocb); lpfc_nlp_put(ndlp); return; @@ -2246,7 +2258,7 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY, - "0229 FDMI cmd %04x failed, latt = %d " + "0229 FDMI cmd %04x latt = %d " "ulp_status: x%x, rid x%x\n", be16_to_cpu(fdmi_cmd), latt, ulp_status, ulp_word4); @@ -2263,9 +2275,9 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* Check for a CT LS_RJT response */ cmd = be16_to_cpu(fdmi_cmd); if (be16_to_cpu(fdmi_rsp) == SLI_CT_RESPONSE_FS_RJT) { - /* FDMI rsp failed */ + /* Log FDMI reject */ lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_ELS, - "0220 FDMI cmd failed FS_RJT Data: x%x", cmd); + "0220 FDMI cmd FS_RJT Data: x%x", cmd); /* Should we fallback to FDMI-2 / FDMI-1 ? */ switch (cmd) { diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h index f82615d87c4b..f5ae8cc15820 100644 --- a/drivers/scsi/lpfc/lpfc_disc.h +++ b/drivers/scsi/lpfc/lpfc_disc.h @@ -90,6 +90,8 @@ enum lpfc_nlp_save_flags { NLP_IN_RECOV_POST_DEV_LOSS = 0x1, /* wait for outstanding LOGO to cmpl */ NLP_WAIT_FOR_LOGO = 0x2, + /* wait for outstanding DA_ID to finish */ + NLP_WAIT_FOR_DA_ID = 0x4 }; struct lpfc_nodelist { @@ -159,7 +161,12 @@ struct lpfc_nodelist { uint32_t nvme_fb_size; /* NVME target's supported byte cnt */ #define NVME_FB_BIT_SHIFT 9 /* PRLI Rsp first burst in 512B units. */ uint32_t nlp_defer_did; + + /* These wait objects are NPIV specific. These IOs must complete + * synchronously. + */ wait_queue_head_t *logo_waitq; + wait_queue_head_t *da_id_waitq; }; struct lpfc_node_rrq { diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index de0ec945d2f1..d737b897ddd8 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -979,7 +979,7 @@ lpfc_cmpl_els_flogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, phba->fcoe_cvl_eventtag_attn = phba->fcoe_cvl_eventtag; lpfc_printf_log(phba, KERN_WARNING, LOG_FIP | LOG_ELS, - "2611 FLOGI failed on FCF (x%x), " + "2611 FLOGI FCF (x%x), " "status:x%x/x%x, tmo:x%x, perform " "roundrobin FCF failover\n", phba->fcf.current_rec.fcf_indx, @@ -997,11 +997,11 @@ stop_rr_fcf_flogi: if (!(ulp_status == IOSTAT_LOCAL_REJECT && ((ulp_word4 & IOERR_PARAM_MASK) == IOERR_LOOP_OPEN_FAILURE))) - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2858 FLOGI failure Status:x%x/x%x TMO" - ":x%x Data x%lx x%x\n", - ulp_status, ulp_word4, tmo, - phba->hba_flag, phba->fcf.fcf_flag); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2858 FLOGI Status:x%x/x%x TMO" + ":x%x Data x%lx x%x\n", + ulp_status, ulp_word4, tmo, + phba->hba_flag, phba->fcf.fcf_flag); /* Check for retry */ if (lpfc_els_retry(phba, cmdiocb, rspiocb)) { @@ -1023,7 +1023,7 @@ stop_rr_fcf_flogi: lpfc_nlp_put(ndlp); lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS, - "0150 FLOGI failure Status:x%x/x%x " + "0150 FLOGI Status:x%x/x%x " "xri x%x TMO:x%x refcnt %d\n", ulp_status, ulp_word4, cmdiocb->sli4_xritag, tmo, kref_read(&ndlp->kref)); @@ -1032,11 +1032,11 @@ stop_rr_fcf_flogi: if (!(ulp_status == IOSTAT_LOCAL_REJECT && ((ulp_word4 & IOERR_PARAM_MASK) == IOERR_LOOP_OPEN_FAILURE))) { - /* FLOGI failure */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "0100 FLOGI failure Status:x%x/x%x " - "TMO:x%x\n", - ulp_status, ulp_word4, tmo); + /* Warn FLOGI status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0100 FLOGI Status:x%x/x%x " + "TMO:x%x\n", + ulp_status, ulp_word4, tmo); goto flogifail; } @@ -1964,16 +1964,16 @@ lpfc_cmpl_els_rrq(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if (ulp_status) { /* Check for retry */ - /* RRQ failed Don't print the vport to vport rjts */ + /* Warn RRQ status Don't print the vport to vport rjts */ if (ulp_status != IOSTAT_LS_RJT || (((ulp_word4) >> 16 != LSRJT_INVALID_CMD) && ((ulp_word4) >> 16 != LSRJT_UNABLE_TPC)) || (phba)->pport->cfg_log_verbose & LOG_ELS) - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2881 RRQ failure DID:%06X Status:" - "x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2881 RRQ DID:%06X Status:" + "x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); } lpfc_clr_rrq_active(phba, rrq->xritag, rrq); @@ -2077,16 +2077,16 @@ lpfc_cmpl_els_plogi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } goto out; } - /* PLOGI failed Don't print the vport to vport rjts */ + /* Warn PLOGI status Don't print the vport to vport rjts */ if (ulp_status != IOSTAT_LS_RJT || (((ulp_word4) >> 16 != LSRJT_INVALID_CMD) && ((ulp_word4) >> 16 != LSRJT_UNABLE_TPC)) || (phba)->pport->cfg_log_verbose & LOG_ELS) - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2753 PLOGI failure DID:%06X " - "Status:x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2753 PLOGI DID:%06X " + "Status:x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); /* Do not call DSM for lpfc_els_abort'ed ELS cmds */ if (!lpfc_error_lost_link(vport, ulp_status, ulp_word4)) @@ -2323,7 +2323,6 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, struct lpfc_vport *vport = cmdiocb->vport; struct lpfc_nodelist *ndlp; char *mode; - u32 loglevel; u32 ulp_status; u32 ulp_word4; bool release_node = false; @@ -2372,17 +2371,14 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * could be expected. */ if (test_bit(FC_FABRIC, &vport->fc_flag) || - vport->cfg_enable_fc4_type != LPFC_ENABLE_BOTH) { - mode = KERN_ERR; - loglevel = LOG_TRACE_EVENT; - } else { + vport->cfg_enable_fc4_type != LPFC_ENABLE_BOTH) + mode = KERN_WARNING; + else mode = KERN_INFO; - loglevel = LOG_ELS; - } - /* PRLI failed */ - lpfc_printf_vlog(vport, mode, loglevel, - "2754 PRLI failure DID:%06X Status:x%x/x%x, " + /* Warn PRLI status */ + lpfc_printf_vlog(vport, mode, LOG_ELS, + "2754 PRLI DID:%06X Status:x%x/x%x, " "data: x%x x%x x%x\n", ndlp->nlp_DID, ulp_status, ulp_word4, ndlp->nlp_state, @@ -2854,11 +2850,11 @@ lpfc_cmpl_els_adisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, } goto out; } - /* ADISC failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2755 ADISC failure DID:%06X Status:x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + /* Warn ADISC status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2755 ADISC DID:%06X Status:x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); lpfc_disc_state_machine(vport, ndlp, cmdiocb, NLP_EVT_CMPL_ADISC); @@ -3045,12 +3041,12 @@ lpfc_cmpl_els_logo(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * discovery. The PLOGI will retry. */ if (ulp_status) { - /* LOGO failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "2756 LOGO failure, No Retry DID:%06X " - "Status:x%x/x%x\n", - ndlp->nlp_DID, ulp_status, - ulp_word4); + /* Warn LOGO status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "2756 LOGO, No Retry DID:%06X " + "Status:x%x/x%x\n", + ndlp->nlp_DID, ulp_status, + ulp_word4); if (lpfc_error_lost_link(vport, ulp_status, ulp_word4)) skip_recovery = 1; @@ -4837,11 +4833,10 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, if ((phba->sli3_options & LPFC_SLI3_NPIV_ENABLED) && (cmd == ELS_CMD_FDISC) && (stat.un.b.lsRjtRsnCodeExp == LSEXP_OUT_OF_RESOURCE)){ - lpfc_printf_vlog(vport, KERN_ERR, - LOG_TRACE_EVENT, - "0125 FDISC Failed (x%x). " - "Fabric out of resources\n", - stat.un.lsRjtError); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0125 FDISC (x%x). " + "Fabric out of resources\n", + stat.un.lsRjtError); lpfc_vport_set_state(vport, FC_VPORT_NO_FABRIC_RSCS); } @@ -4877,11 +4872,10 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, LSEXP_NOTHING_MORE) { vport->fc_sparam.cmn.bbRcvSizeMsb &= 0xf; retry = 1; - lpfc_printf_vlog(vport, KERN_ERR, - LOG_TRACE_EVENT, - "0820 FLOGI Failed (x%x). " - "BBCredit Not Supported\n", - stat.un.lsRjtError); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0820 FLOGI (x%x). " + "BBCredit Not Supported\n", + stat.un.lsRjtError); } break; @@ -4891,11 +4885,10 @@ lpfc_els_retry(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, ((stat.un.b.lsRjtRsnCodeExp == LSEXP_INVALID_PNAME) || (stat.un.b.lsRjtRsnCodeExp == LSEXP_INVALID_NPORT_ID)) ) { - lpfc_printf_vlog(vport, KERN_ERR, - LOG_TRACE_EVENT, - "0122 FDISC Failed (x%x). " - "Fabric Detected Bad WWN\n", - stat.un.lsRjtError); + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0122 FDISC (x%x). " + "Fabric Detected Bad WWN\n", + stat.un.lsRjtError); lpfc_vport_set_state(vport, FC_VPORT_FABRIC_REJ_WWN); } @@ -5355,8 +5348,8 @@ lpfc_cmpl_els_rsp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, u32 ulp_status, ulp_word4, tmo, did, iotag; if (!vport) { - lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "3177 ELS response failed\n"); + lpfc_printf_log(phba, KERN_WARNING, LOG_ELS, + "3177 null vport in ELS rsp\n"); goto out; } if (cmdiocb->context_un.mbox) @@ -9658,11 +9651,12 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport) if (piocb->cmd_flag & LPFC_DRIVER_ABORTED && !mbx_tmo_err) continue; - /* On the ELS ring we can have ELS_REQUESTs or - * GEN_REQUESTs waiting for a response. + /* On the ELS ring we can have ELS_REQUESTs, ELS_RSPs, + * or GEN_REQUESTs waiting for a CQE response. */ ulp_command = get_job_cmnd(phba, piocb); - if (ulp_command == CMD_ELS_REQUEST64_CR) { + if (ulp_command == CMD_ELS_REQUEST64_WQE || + ulp_command == CMD_XMIT_ELS_RSP64_WQE) { list_add_tail(&piocb->dlist, &abort_list); /* If the link is down when flushing ELS commands @@ -11327,10 +11321,10 @@ lpfc_cmpl_els_fdisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* Check for retry */ if (lpfc_els_retry(phba, cmdiocb, rspiocb)) goto out; - /* FDISC failed */ - lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, - "0126 FDISC failed. (x%x/x%x)\n", - ulp_status, ulp_word4); + /* Warn FDISC status */ + lpfc_vlog_msg(vport, KERN_WARNING, LOG_ELS, + "0126 FDISC cmpl status: x%x/x%x)\n", + ulp_status, ulp_word4); goto fdisc_failed; } diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 35c9181c6608..9241075f72fa 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -527,6 +527,9 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) * the following lpfc_nlp_put is necessary after fabric node is * recovered. */ + spin_lock_irqsave(&ndlp->lock, iflags); + ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; + spin_unlock_irqrestore(&ndlp->lock, iflags); if (recovering) { lpfc_printf_vlog(vport, KERN_INFO, LOG_DISCOVERY | LOG_NODE, @@ -539,6 +542,7 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) spin_lock_irqsave(&ndlp->lock, iflags); ndlp->save_flags |= NLP_IN_RECOV_POST_DEV_LOSS; spin_unlock_irqrestore(&ndlp->lock, iflags); + return fcf_inuse; } else if (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE) { /* Fabric node fully recovered before this dev_loss_tmo * queue work is processed. Thus, ignore the @@ -552,15 +556,9 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) ndlp->nlp_DID, kref_read(&ndlp->kref), ndlp, ndlp->nlp_flag, vport->port_state); - spin_lock_irqsave(&ndlp->lock, iflags); - ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; - spin_unlock_irqrestore(&ndlp->lock, iflags); return fcf_inuse; } - spin_lock_irqsave(&ndlp->lock, iflags); - ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; - spin_unlock_irqrestore(&ndlp->lock, iflags); lpfc_nlp_put(ndlp); return fcf_inuse; } diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index 2108b4cb7815..d5c15742f7f2 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -562,6 +562,27 @@ struct fc_vft_header { #include <uapi/scsi/fc/fc_els.h> /* + * Application Header + */ +struct fc_app_header { + uint32_t dst_app_id; + uint32_t src_app_id; +#define LOOPBACK_SRC_APPID 0x4321 + uint32_t word2; + uint32_t word3; +}; + +/* + * dfctl optional header definition + */ +enum lpfc_fc_dfctl { + LPFC_FC_NO_DEVICE_HEADER, + LPFC_FC_16B_DEVICE_HEADER, + LPFC_FC_32B_DEVICE_HEADER, + LPFC_FC_64B_DEVICE_HEADER, +}; + +/* * Extended Link Service LS_COMMAND codes (Payload Word 0) */ #ifdef __BIG_ENDIAN_BITFIELD diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h index 500253007b1d..26e1313ebb21 100644 --- a/drivers/scsi/lpfc/lpfc_hw4.h +++ b/drivers/scsi/lpfc/lpfc_hw4.h @@ -4847,6 +4847,7 @@ struct fcp_iwrite64_wqe { #define cmd_buff_len_SHIFT 16 #define cmd_buff_len_MASK 0x00000ffff #define cmd_buff_len_WORD word3 +/* Note: payload_offset_len field depends on ASIC support */ #define payload_offset_len_SHIFT 0 #define payload_offset_len_MASK 0x0000ffff #define payload_offset_len_WORD word3 @@ -4863,6 +4864,7 @@ struct fcp_iread64_wqe { #define cmd_buff_len_SHIFT 16 #define cmd_buff_len_MASK 0x00000ffff #define cmd_buff_len_WORD word3 +/* Note: payload_offset_len field depends on ASIC support */ #define payload_offset_len_SHIFT 0 #define payload_offset_len_MASK 0x0000ffff #define payload_offset_len_WORD word3 @@ -4879,6 +4881,7 @@ struct fcp_icmnd64_wqe { #define cmd_buff_len_SHIFT 16 #define cmd_buff_len_MASK 0x00000ffff #define cmd_buff_len_WORD word3 +/* Note: payload_offset_len field depends on ASIC support */ #define payload_offset_len_SHIFT 0 #define payload_offset_len_MASK 0x0000ffff #define payload_offset_len_WORD word3 diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 50620918becd..0dd451009b07 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -4699,6 +4699,7 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) uint64_t wwn; bool use_no_reset_hba = false; int rc; + u8 if_type; if (lpfc_no_hba_reset_cnt) { if (phba->sli_rev < LPFC_SLI_REV4 && @@ -4773,10 +4774,24 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev) shost->max_id = LPFC_MAX_TARGET; shost->max_lun = vport->cfg_max_luns; shost->this_id = -1; - if (phba->sli_rev == LPFC_SLI_REV4) - shost->max_cmd_len = LPFC_FCP_CDB_LEN_32; - else + + /* Set max_cmd_len applicable to ASIC support */ + if (phba->sli_rev == LPFC_SLI_REV4) { + if_type = bf_get(lpfc_sli_intf_if_type, + &phba->sli4_hba.sli_intf); + switch (if_type) { + case LPFC_SLI_INTF_IF_TYPE_2: + fallthrough; + case LPFC_SLI_INTF_IF_TYPE_6: + shost->max_cmd_len = LPFC_FCP_CDB_LEN_32; + break; + default: + shost->max_cmd_len = LPFC_FCP_CDB_LEN; + break; + } + } else { shost->max_cmd_len = LPFC_FCP_CDB_LEN; + } if (phba->sli_rev == LPFC_SLI_REV4) { if (!phba->cfg_fcp_mq_threshold || @@ -10436,6 +10451,7 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) struct lpfc_vector_map_info *cpup; struct lpfc_vector_map_info *eqcpup; struct lpfc_eq_intr_info *eqi; + u32 wqesize; /* * Create HBA Record arrays. @@ -10655,9 +10671,15 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba) * Create ELS Work Queues */ - /* Create slow-path ELS Work Queue */ + /* + * Create slow-path ELS Work Queue. + * Increase the ELS WQ size when WQEs contain an embedded cdb + */ + wqesize = (phba->fcp_embed_io) ? + LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize; + qdesc = lpfc_sli4_queue_alloc(phba, LPFC_DEFAULT_PAGE_SIZE, - phba->sli4_hba.wq_esize, + wqesize, phba->sli4_hba.wq_ecount, cpu); if (!qdesc) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 60cd60ebff38..0eaede8275da 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -4760,7 +4760,7 @@ static int lpfc_scsi_prep_cmnd_buf_s4(struct lpfc_vport *vport, /* Word 3 */ bf_set(payload_offset_len, &wqe->fcp_icmd, - sizeof(struct fcp_cmnd32) + sizeof(struct fcp_rsp)); + sizeof(struct fcp_cmnd) + sizeof(struct fcp_rsp)); /* Word 6 */ bf_set(wqe_ctxt_tag, &wqe->generic.wqe_com, diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 332b8d2348e9..2ec6e55771b4 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -1940,12 +1940,15 @@ lpfc_issue_cmf_sync_wqe(struct lpfc_hba *phba, u32 ms, u64 total) atot = atomic_xchg(&phba->cgn_sync_alarm_cnt, 0); wtot = atomic_xchg(&phba->cgn_sync_warn_cnt, 0); + spin_lock_irqsave(&phba->hbalock, iflags); + /* ONLY Managed mode will send the CMF_SYNC_WQE to the HBA */ if (phba->cmf_active_mode != LPFC_CFG_MANAGED || - phba->link_state == LPFC_LINK_DOWN) - return 0; + phba->link_state < LPFC_LINK_UP) { + ret_val = 0; + goto out_unlock; + } - spin_lock_irqsave(&phba->hbalock, iflags); sync_buf = __lpfc_sli_get_iocbq(phba); if (!sync_buf) { lpfc_printf_log(phba, KERN_ERR, LOG_CGN_MGMT, @@ -8818,7 +8821,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba) rc = lpfc_sli4_queue_setup(phba); if (unlikely(rc)) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "0381 Error %d during queue setup.\n ", rc); + "0381 Error %d during queue setup.\n", rc); goto out_stop_timers; } /* Initialize the driver internal SLI layer lists. */ @@ -11090,9 +11093,17 @@ __lpfc_sli_prep_xmit_seq64_s4(struct lpfc_iocbq *cmdiocbq, /* Word 9 */ bf_set(wqe_rcvoxid, &wqe->xmit_sequence.wqe_com, ox_id); - /* Word 12 */ - if (cmdiocbq->cmd_flag & (LPFC_IO_LIBDFC | LPFC_IO_LOOPBACK)) + if (cmdiocbq->cmd_flag & (LPFC_IO_LIBDFC | LPFC_IO_LOOPBACK)) { + /* Word 10 */ + if (cmdiocbq->cmd_flag & LPFC_IO_VMID) { + bf_set(wqe_appid, &wqe->xmit_sequence.wqe_com, 1); + bf_set(wqe_wqes, &wqe->xmit_sequence.wqe_com, 1); + wqe->words[31] = LOOPBACK_SRC_APPID; + } + + /* Word 12 */ wqe->xmit_sequence.xmit_len = full_size; + } else wqe->xmit_sequence.xmit_len = wqe->xmit_sequence.bde.tus.f.bdeSize; @@ -18431,6 +18442,7 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr) { /* make rctl_names static to save stack space */ struct fc_vft_header *fc_vft_hdr; + struct fc_app_header *fc_app_hdr; uint32_t *header = (uint32_t *) fc_hdr; #define FC_RCTL_MDS_DIAGS 0xF4 @@ -18486,6 +18498,32 @@ lpfc_fc_frame_check(struct lpfc_hba *phba, struct fc_frame_header *fc_hdr) goto drop; } + if (unlikely(phba->link_flag == LS_LOOPBACK_MODE && + phba->cfg_vmid_app_header)) { + /* Application header is 16B device header */ + if (fc_hdr->fh_df_ctl & LPFC_FC_16B_DEVICE_HEADER) { + fc_app_hdr = (struct fc_app_header *) (fc_hdr + 1); + if (be32_to_cpu(fc_app_hdr->src_app_id) != + LOOPBACK_SRC_APPID) { + lpfc_printf_log(phba, KERN_WARNING, + LOG_ELS | LOG_LIBDFC, + "1932 Loopback src app id " + "not matched, app_id:x%x\n", + be32_to_cpu(fc_app_hdr->src_app_id)); + + goto drop; + } + } else { + lpfc_printf_log(phba, KERN_WARNING, + LOG_ELS | LOG_LIBDFC, + "1933 Loopback df_ctl bit not set, " + "df_ctl:x%x\n", + fc_hdr->fh_df_ctl); + + goto drop; + } + } + lpfc_printf_log(phba, KERN_INFO, LOG_ELS, "2538 Received frame rctl:x%x, type:x%x, " "frame Data:%08x %08x %08x %08x %08x %08x %08x\n", @@ -21149,7 +21187,7 @@ lpfc_drain_txq(struct lpfc_hba *phba) if (!piocbq) { spin_unlock_irqrestore(&pring->ring_lock, iflags); lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "2823 txq empty and txq_cnt is %d\n ", + "2823 txq empty and txq_cnt is %d\n", txq_cnt); break; } diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index 2fe0386a1fee..e70f163fab90 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.4.0.4" +#define LPFC_DRIVER_VERSION "14.4.0.5" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 4439167a5188..7a4d4d8e2ad5 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -626,6 +626,7 @@ lpfc_vport_delete(struct fc_vport *fc_vport) struct Scsi_Host *shost = lpfc_shost_from_vport(vport); struct lpfc_hba *phba = vport->phba; int rc; + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq); if (vport->port_type == LPFC_PHYSICAL_PORT) { lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, @@ -679,21 +680,49 @@ lpfc_vport_delete(struct fc_vport *fc_vport) if (!ndlp) goto skip_logo; + /* Send the DA_ID and Fabric LOGO to cleanup the NPIV fabric entries. */ if (ndlp && ndlp->nlp_state == NLP_STE_UNMAPPED_NODE && phba->link_state >= LPFC_LINK_UP && phba->fc_topology != LPFC_TOPOLOGY_LOOP) { if (vport->cfg_enable_da_id) { - /* Send DA_ID and wait for a completion. */ + /* Send DA_ID and wait for a completion. This is best + * effort. If the DA_ID fails, likely the fabric will + * "leak" NportIDs but at least the driver issued the + * command. + */ + ndlp = lpfc_findnode_did(vport, NameServer_DID); + if (!ndlp) + goto issue_logo; + + spin_lock_irq(&ndlp->lock); + ndlp->da_id_waitq = &waitq; + ndlp->save_flags |= NLP_WAIT_FOR_DA_ID; + spin_unlock_irq(&ndlp->lock); + rc = lpfc_ns_cmd(vport, SLI_CTNS_DA_ID, 0, 0); - if (rc) { - lpfc_printf_log(vport->phba, KERN_WARNING, - LOG_VPORT, - "1829 CT command failed to " - "delete objects on fabric, " - "rc %d\n", rc); + if (!rc) { + wait_event_timeout(waitq, + !(ndlp->save_flags & NLP_WAIT_FOR_DA_ID), + msecs_to_jiffies(phba->fc_ratov * 2000)); } + + lpfc_printf_vlog(vport, KERN_INFO, LOG_VPORT | LOG_ELS, + "1829 DA_ID issue status %d. " + "SFlag x%x NState x%x, NFlag x%x " + "Rpi x%x\n", + rc, ndlp->save_flags, ndlp->nlp_state, + ndlp->nlp_flag, ndlp->nlp_rpi); + + /* Remove the waitq and save_flags. It no + * longer matters if the wake happened. + */ + spin_lock_irq(&ndlp->lock); + ndlp->da_id_waitq = NULL; + ndlp->save_flags &= ~NLP_WAIT_FOR_DA_ID; + spin_unlock_irq(&ndlp->lock); } +issue_logo: /* * If the vpi is not registered, then a valid FDISC doesn't * exist and there is no need for a ELS LOGO. Just cleanup diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 6c79c350a4d5..4ecf5284c0fc 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -6380,7 +6380,7 @@ static int megasas_init_fw(struct megasas_instance *instance) GFP_KERNEL); if (!fusion->stream_detect_by_ld[i]) { dev_err(&instance->pdev->dev, - "unable to allocate stream detect by LD\n "); + "unable to allocate stream detect by LD\n"); for (j = 0; j < i; ++j) kfree(fusion->stream_detect_by_ld[j]); kfree(fusion->stream_detect_by_ld); diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h b/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h index 4b7a8f6314a3..00cd18edfad6 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_cnfg.h @@ -67,6 +67,7 @@ #define MPI3_SECURITY_PGAD_SLOT_GROUP_MASK (0x0000ff00) #define MPI3_SECURITY_PGAD_SLOT_GROUP_SHIFT (8) #define MPI3_SECURITY_PGAD_SLOT_MASK (0x000000ff) +#define MPI3_INSTANCE_PGAD_INSTANCE_MASK (0x0000ffff) struct mpi3_config_request { __le16 host_tag; u8 ioc_use_only02; @@ -75,7 +76,8 @@ struct mpi3_config_request { u8 ioc_use_only06; u8 msg_flags; __le16 change_count; - __le16 reserved0a; + u8 proxy_ioc_number; + u8 reserved0b; u8 page_version; u8 page_number; u8 page_type; @@ -206,6 +208,9 @@ struct mpi3_config_page_header { #define MPI3_MFGPAGE_DEVID_SAS5116_MPI_MGMT (0x00b5) #define MPI3_MFGPAGE_DEVID_SAS5116_NVME_MGMT (0x00b6) #define MPI3_MFGPAGE_DEVID_SAS5116_PCIE_SWITCH (0x00b8) +#define MPI3_MFGPAGE_DEVID_SAS5248_MPI (0x00f0) +#define MPI3_MFGPAGE_DEVID_SAS5248_MPI_NS (0x00f1) +#define MPI3_MFGPAGE_DEVID_SAS5248_PCIE_SWITCH (0x00f2) struct mpi3_man_page0 { struct mpi3_config_page_header header; u8 chip_revision[8]; @@ -1074,6 +1079,8 @@ struct mpi3_io_unit_page8 { #define MPI3_IOUNIT8_SBSTATE_SVN_UPDATE_PENDING (0x04) #define MPI3_IOUNIT8_SBSTATE_KEY_UPDATE_PENDING (0x02) #define MPI3_IOUNIT8_SBSTATE_SECURE_BOOT_ENABLED (0x01) +#define MPI3_IOUNIT8_SBMODE_CURRENT_KEY_IOUNIT17 (0x10) +#define MPI3_IOUNIT8_SBMODE_HARD_SECURE_RECERTIFIED (0x08) struct mpi3_io_unit_page9 { struct mpi3_config_page_header header; __le32 flags; @@ -1089,6 +1096,8 @@ struct mpi3_io_unit_page9 { #define MPI3_IOUNIT9_FLAGS_UBM_ENCLOSURE_ORDER_BACKPLANE_TYPE (0x00000004) #define MPI3_IOUNIT9_FLAGS_VDFIRST_ENABLED (0x00000001) #define MPI3_IOUNIT9_FIRSTDEVICE_UNKNOWN (0xffff) +#define MPI3_IOUNIT9_FIRSTDEVICE_IN_DRIVER_PAGE_0 (0xfffe) + struct mpi3_io_unit_page10 { struct mpi3_config_page_header header; u8 flags; @@ -1224,6 +1233,19 @@ struct mpi3_io_unit_page15 { #define MPI3_IOUNIT15_FLAGS_EPRSUPPORT_WITHOUT_POWER_BRAKE_GPIO (0x01) #define MPI3_IOUNIT15_FLAGS_EPRSUPPORT_WITH_POWER_BRAKE_GPIO (0x02) #define MPI3_IOUNIT15_NUMPOWERBUDGETDATA_POWER_BUDGETING_DISABLED (0x00) + +struct mpi3_io_unit_page17 { + struct mpi3_config_page_header header; + u8 num_instances; + u8 instance; + __le16 reserved0a; + __le32 reserved0c[4]; + __le16 key_length; + u8 encryption_algorithm; + u8 reserved1f; + __le32 current_key[]; +}; +#define MPI3_IOUNIT17_PAGEVERSION (0x00) struct mpi3_ioc_page0 { struct mpi3_config_page_header header; __le32 reserved08; @@ -1311,7 +1333,7 @@ struct mpi3_driver_page0 { u8 tur_interval; u8 reserved10; u8 security_key_timeout; - __le16 reserved12; + __le16 first_device; __le32 reserved14; __le32 reserved18; }; @@ -1324,10 +1346,13 @@ struct mpi3_driver_page0 { #define MPI3_DRIVER0_BSDOPTS_REGISTRATION_IOC_AND_DEVS (0x00000000) #define MPI3_DRIVER0_BSDOPTS_REGISTRATION_IOC_ONLY (0x00000001) #define MPI3_DRIVER0_BSDOPTS_REGISTRATION_IOC_AND_INTERNAL_DEVS (0x00000002) +#define MPI3_DRIVER0_FIRSTDEVICE_IGNORE1 (0x0000) +#define MPI3_DRIVER0_FIRSTDEVICE_IGNORE2 (0xffff) struct mpi3_driver_page1 { struct mpi3_config_page_header header; __le32 flags; - __le32 reserved0c; + u8 time_stamp_update; + u8 reserved0d[3]; __le16 host_diag_trace_max_size; __le16 host_diag_trace_min_size; __le16 host_diag_trace_decrement_size; @@ -2347,6 +2372,10 @@ struct mpi3_device0_vd_format { #define MPI3_DEVICE0_VD_DEVICE_INFO_SAS (0x0001) #define MPI3_DEVICE0_VD_FLAGS_IO_THROTTLE_GROUP_QD_MASK (0xf000) #define MPI3_DEVICE0_VD_FLAGS_IO_THROTTLE_GROUP_QD_SHIFT (12) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_MASK (0x0003) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_HDD (0x0000) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_SSD (0x0001) +#define MPI3_DEVICE0_VD_FLAGS_OSEXPOSURE_NO_GUIDANCE (0x0002) union mpi3_device0_dev_spec_format { struct mpi3_device0_sas_sata_format sas_sata_format; struct mpi3_device0_pcie_format pcie_format; diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_image.h b/drivers/scsi/mpi3mr/mpi/mpi30_image.h index 7df242190135..2c6e548cbd0f 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_image.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_image.h @@ -205,13 +205,14 @@ struct mpi3_encrypted_hash_entry { u8 hash_image_type; u8 hash_algorithm; u8 encryption_algorithm; - u8 reserved03; + u8 flags; __le16 public_key_size; __le16 signature_size; __le32 public_key[MPI3_PUBLIC_KEY_MAX]; }; - -#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_SIGNATURE (0x03) +#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_HASH (0x03) +#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_HASH_1_OF_2 (0x04) +#define MPI3_HASH_IMAGE_TYPE_KEY_WITH_HASH_2_OF_2 (0x05) #define MPI3_HASH_ALGORITHM_VERSION_MASK (0xe0) #define MPI3_HASH_ALGORITHM_VERSION_NONE (0x00) #define MPI3_HASH_ALGORITHM_VERSION_SHA1 (0x20) @@ -230,6 +231,12 @@ struct mpi3_encrypted_hash_entry { #define MPI3_ENCRYPTION_ALGORITHM_RSA4096 (0x05) #define MPI3_ENCRYPTION_ALGORITHM_RSA3072 (0x06) +/* hierarchical signature system (hss) */ +#define MPI3_ENCRYPTION_ALGORITHM_ML_DSA_87 (0x0b) +#define MPI3_ENCRYPTION_ALGORITHM_ML_DSA_65 (0x0c) +#define MPI3_ENCRYPTION_ALGORITHM_ML_DSA_44 (0x0d) +#define MPI3_ENCRYPTED_HASH_ENTRY_FLAGS_PAIRED_KEY_MASK (0x0f) + #ifndef MPI3_ENCRYPTED_HASH_ENTRY_MAX #define MPI3_ENCRYPTED_HASH_ENTRY_MAX (1) #endif diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h index c9fa0d69b75f..c374867f9ba0 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_ioc.h @@ -39,6 +39,12 @@ struct mpi3_ioc_init_request { #define MPI3_WHOINIT_HOST_DRIVER (0x03) #define MPI3_WHOINIT_MANUFACTURER (0x04) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_MASK (0x00000003) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_NO_GUIDANCE (0x00000000) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_NO_SPECIAL (0x00000001) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_REPORT_AS_HDD (0x00000002) +#define MPI3_IOCINIT_DRIVERCAP_OSEXPOSURE_REPORT_AS_SSD (0x00000003) + struct mpi3_ioc_facts_request { __le16 host_tag; u8 ioc_use_only02; @@ -140,6 +146,8 @@ struct mpi3_ioc_facts_data { #define MPI3_IOCFACTS_EXCEPT_MANUFACT_CHECKSUM_FAIL (0x0020) #define MPI3_IOCFACTS_EXCEPT_FW_CHECKSUM_FAIL (0x0010) #define MPI3_IOCFACTS_EXCEPT_CONFIG_CHECKSUM_FAIL (0x0008) +#define MPI3_IOCFACTS_EXCEPT_BLOCKING_BOOT_EVENT (0x0004) +#define MPI3_IOCFACTS_EXCEPT_SECURITY_SELFTEST_FAILURE (0x0002) #define MPI3_IOCFACTS_EXCEPT_BOOTSTAT_MASK (0x0001) #define MPI3_IOCFACTS_EXCEPT_BOOTSTAT_PRIMARY (0x0000) #define MPI3_IOCFACTS_EXCEPT_BOOTSTAT_SECONDARY (0x0001) diff --git a/drivers/scsi/mpi3mr/mpi/mpi30_transport.h b/drivers/scsi/mpi3mr/mpi/mpi30_transport.h index fdc3d1968e43..b2ab25a1cfeb 100644 --- a/drivers/scsi/mpi3mr/mpi/mpi30_transport.h +++ b/drivers/scsi/mpi3mr/mpi/mpi30_transport.h @@ -18,7 +18,7 @@ union mpi3_version_union { #define MPI3_VERSION_MAJOR (3) #define MPI3_VERSION_MINOR (0) -#define MPI3_VERSION_UNIT (31) +#define MPI3_VERSION_UNIT (34) #define MPI3_VERSION_DEV (0) #define MPI3_DEVHANDLE_INVALID (0xffff) struct mpi3_sysif_oper_queue_indexes { @@ -158,6 +158,7 @@ struct mpi3_sysif_registers { #define MPI3_SYSIF_FAULT_CODE_SOFT_RESET_NEEDED (0x0000f004) #define MPI3_SYSIF_FAULT_CODE_POWER_CYCLE_REQUIRED (0x0000f005) #define MPI3_SYSIF_FAULT_CODE_TEMP_THRESHOLD_EXCEEDED (0x0000f006) +#define MPI3_SYSIF_FAULT_CODE_INSUFFICIENT_PCI_SLOT_POWER (0x0000f007) #define MPI3_SYSIF_FAULT_INFO0_OFFSET (0x00001c14) #define MPI3_SYSIF_FAULT_INFO1_OFFSET (0x00001c18) #define MPI3_SYSIF_FAULT_INFO2_OFFSET (0x00001c1c) @@ -410,6 +411,7 @@ struct mpi3_default_reply { #define MPI3_IOCSTATUS_INSUFFICIENT_RESOURCES (0x0006) #define MPI3_IOCSTATUS_INVALID_FIELD (0x0007) #define MPI3_IOCSTATUS_INVALID_STATE (0x0008) +#define MPI3_IOCSTATUS_SHUTDOWN_ACTIVE (0x0009) #define MPI3_IOCSTATUS_INSUFFICIENT_POWER (0x000a) #define MPI3_IOCSTATUS_INVALID_CHANGE_COUNT (0x000b) #define MPI3_IOCSTATUS_ALLOWED_CMD_BLOCK (0x000c) diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index 1dc640de3efc..fcb0fa31536b 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -57,8 +57,8 @@ extern struct list_head mrioc_list; extern int prot_mask; extern atomic64_t event_counter; -#define MPI3MR_DRIVER_VERSION "8.10.0.5.50" -#define MPI3MR_DRIVER_RELDATE "08-Aug-2024" +#define MPI3MR_DRIVER_VERSION "8.12.0.0.50" +#define MPI3MR_DRIVER_RELDATE "05-Sept-2024" #define MPI3MR_DRIVER_NAME "mpi3mr" #define MPI3MR_DRIVER_LICENSE "GPL" @@ -178,7 +178,7 @@ extern atomic64_t event_counter; #define MPI3MR_DEFAULT_SDEV_QD 32 /* Definitions for Threaded IRQ poll*/ -#define MPI3MR_IRQ_POLL_SLEEP 2 +#define MPI3MR_IRQ_POLL_SLEEP 20 #define MPI3MR_IRQ_POLL_TRIGGER_IOCOUNT 8 /* Definitions for the controller security status*/ @@ -1090,6 +1090,7 @@ struct scmd_priv { * @evtack_cmds_bitmap: Event Ack bitmap * @delayed_evtack_cmds_list: Delayed event acknowledgment list * @ts_update_counter: Timestamp update counter + * @ts_update_interval: Timestamp update interval * @reset_in_progress: Reset in progress flag * @unrecoverable: Controller unrecoverable flag * @prev_reset_result: Result of previous reset @@ -1277,7 +1278,8 @@ struct mpi3mr_ioc { unsigned long *evtack_cmds_bitmap; struct list_head delayed_evtack_cmds_list; - u32 ts_update_counter; + u16 ts_update_counter; + u16 ts_update_interval; u8 reset_in_progress; u8 unrecoverable; int prev_reset_result; diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 2e1a92d306b2..f1ab76351bd8 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -728,7 +728,7 @@ static irqreturn_t mpi3mr_isr_poll(int irq, void *privdata) mpi3mr_process_op_reply_q(mrioc, intr_info->op_reply_q); - usleep_range(MPI3MR_IRQ_POLL_SLEEP, 10 * MPI3MR_IRQ_POLL_SLEEP); + usleep_range(MPI3MR_IRQ_POLL_SLEEP, MPI3MR_IRQ_POLL_SLEEP + 1); } while (atomic_read(&intr_info->op_reply_q->pend_ios) && (num_op_reply < mrioc->max_host_ios)); @@ -1362,6 +1362,10 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) int retval = 0; enum mpi3mr_iocstate ioc_state; u64 base_info; + u8 retry = 0; + u64 start_time, elapsed_time_sec; + +retry_bring_ioc_ready: ioc_status = readl(&mrioc->sysif_regs->ioc_status); ioc_config = readl(&mrioc->sysif_regs->ioc_configuration); @@ -1380,26 +1384,23 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) ioc_info(mrioc, "controller is in %s state during detection\n", mpi3mr_iocstate_name(ioc_state)); - if (ioc_state == MRIOC_STATE_BECOMING_READY || - ioc_state == MRIOC_STATE_RESET_REQUESTED) { - timeout = mrioc->ready_timeout * 10; - do { - msleep(100); - } while (--timeout); + timeout = mrioc->ready_timeout * 10; + + do { + ioc_state = mpi3mr_get_iocstate(mrioc); + + if (ioc_state != MRIOC_STATE_BECOMING_READY && + ioc_state != MRIOC_STATE_RESET_REQUESTED) + break; if (!pci_device_is_present(mrioc->pdev)) { mrioc->unrecoverable = 1; - ioc_err(mrioc, - "controller is not present while waiting to reset\n"); - retval = -1; + ioc_err(mrioc, "controller is not present while waiting to reset\n"); goto out_device_not_present; } - ioc_state = mpi3mr_get_iocstate(mrioc); - ioc_info(mrioc, - "controller is in %s state after waiting to reset\n", - mpi3mr_iocstate_name(ioc_state)); - } + msleep(100); + } while (--timeout); if (ioc_state == MRIOC_STATE_READY) { ioc_info(mrioc, "issuing message unit reset (MUR) to bring to reset state\n"); @@ -1460,6 +1461,9 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) ioc_config |= MPI3_SYSIF_IOC_CONFIG_ENABLE_IOC; writel(ioc_config, &mrioc->sysif_regs->ioc_configuration); + if (retry == 0) + start_time = jiffies; + timeout = mrioc->ready_timeout * 10; do { ioc_state = mpi3mr_get_iocstate(mrioc); @@ -1469,6 +1473,12 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) mpi3mr_iocstate_name(ioc_state)); return 0; } + ioc_status = readl(&mrioc->sysif_regs->ioc_status); + if ((ioc_status & MPI3_SYSIF_IOC_STATUS_RESET_HISTORY) || + (ioc_status & MPI3_SYSIF_IOC_STATUS_FAULT)) { + mpi3mr_print_fault_info(mrioc); + goto out_failed; + } if (!pci_device_is_present(mrioc->pdev)) { mrioc->unrecoverable = 1; ioc_err(mrioc, @@ -1477,9 +1487,19 @@ static int mpi3mr_bring_ioc_ready(struct mpi3mr_ioc *mrioc) goto out_device_not_present; } msleep(100); - } while (--timeout); + elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000; + } while (elapsed_time_sec < mrioc->ready_timeout); out_failed: + elapsed_time_sec = jiffies_to_msecs(jiffies - start_time)/1000; + if ((retry < 2) && (elapsed_time_sec < (mrioc->ready_timeout - 60))) { + retry++; + + ioc_warn(mrioc, "retrying to bring IOC ready, retry_count:%d\n" + " elapsed time =%llu\n", retry, elapsed_time_sec); + + goto retry_bring_ioc_ready; + } ioc_state = mpi3mr_get_iocstate(mrioc); ioc_err(mrioc, "failed to bring to ready state, current state: %s\n", @@ -2671,7 +2691,7 @@ static void mpi3mr_watchdog_work(struct work_struct *work) return; } - if (mrioc->ts_update_counter++ >= MPI3MR_TSUPDATE_INTERVAL) { + if (mrioc->ts_update_counter++ >= mrioc->ts_update_interval) { mrioc->ts_update_counter = 0; mpi3mr_sync_timestamp(mrioc); } @@ -3845,6 +3865,29 @@ static int mpi3mr_repost_diag_bufs(struct mpi3mr_ioc *mrioc) } /** + * mpi3mr_read_tsu_interval - Update time stamp interval + * @mrioc: Adapter instance reference + * + * Update time stamp interval if its defined in driver page 1, + * otherwise use default value. + * + * Return: Nothing + */ +static void +mpi3mr_read_tsu_interval(struct mpi3mr_ioc *mrioc) +{ + struct mpi3_driver_page1 driver_pg1; + u16 pg_sz = sizeof(driver_pg1); + int retval = 0; + + mrioc->ts_update_interval = MPI3MR_TSUPDATE_INTERVAL; + + retval = mpi3mr_cfg_get_driver_pg1(mrioc, &driver_pg1, pg_sz); + if (!retval && driver_pg1.time_stamp_update) + mrioc->ts_update_interval = (driver_pg1.time_stamp_update * 60); +} + +/** * mpi3mr_print_ioc_info - Display controller information * @mrioc: Adapter instance reference * @@ -4140,6 +4183,7 @@ retry_init: goto out_failed_noretry; } + mpi3mr_read_tsu_interval(mrioc); mpi3mr_print_ioc_info(mrioc); if (!mrioc->cfg_page) { @@ -4321,6 +4365,7 @@ retry_init: goto out_failed_noretry; } + mpi3mr_read_tsu_interval(mrioc); mpi3mr_print_ioc_info(mrioc); if (is_resume) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 9a24f7776d64..ed5046593fda 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -8898,9 +8898,8 @@ _base_check_ioc_facts_changes(struct MPT3SAS_ADAPTER *ioc) ioc->device_remove_in_progress, pd_handles_sz, GFP_KERNEL); if (!device_remove_in_progress) { ioc_info(ioc, - "Unable to allocate the memory for " - "device_remove_in_progress of sz: %d\n " - , pd_handles_sz); + "Unable to allocate the memory for device_remove_in_progress of sz: %d\n", + pd_handles_sz); return -ENOMEM; } memset(device_remove_in_progress + diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index 1e63cb6cd8e3..33e1eba62ca1 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -100,10 +100,12 @@ static void pm8001_map_queues(struct Scsi_Host *shost) struct pm8001_hba_info *pm8001_ha = sha->lldd_ha; struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - if (pm8001_ha->number_of_intr > 1) + if (pm8001_ha->number_of_intr > 1) { blk_mq_pci_map_queues(qmap, pm8001_ha->pdev, 1); + return; + } - return blk_mq_map_queues(qmap); + blk_mq_map_queues(qmap); } /* diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 8fe886dc5e47..a9869cd8c4c0 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2037,7 +2037,7 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) atomic_dec(&pm8001_dev->running_req); break; } - pm8001_dbg(pm8001_ha, IO, "scsi_status = 0x%x\n ", + pm8001_dbg(pm8001_ha, IO, "scsi_status = 0x%x\n", psspPayload->ssp_resp_iu.status); spin_lock_irqsave(&t->task_state_lock, flags); t->task_state_flags &= ~SAS_TASK_STATE_PENDING; diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 72a4c6e3d0c8..4c5881917d76 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -1946,7 +1946,7 @@ static void pmcraid_soft_reset(struct pmcraid_cmd *cmd) } iowrite32(doorbell, pinstance->int_regs.host_ioa_interrupt_reg); - ioread32(pinstance->int_regs.host_ioa_interrupt_reg), + ioread32(pinstance->int_regs.host_ioa_interrupt_reg); int_reg = ioread32(pinstance->int_regs.ioa_host_interrupt_reg); pmcraid_info("Waiting for IOA to become operational %x:%x\n", diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index 054a51713d55..fcfc3bed02c6 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -310,7 +310,7 @@ struct qedf_ioreq *qedf_alloc_cmd(struct qedf_rport *fcport, u8 cmd_type) if (!free_sqes) { QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_IO, - "Returning NULL, free_sqes=%d.\n ", + "Returning NULL, free_sqes=%d.\n", free_sqes); goto out_failed; } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index a9d8a9c62663..d95f417e24c0 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -2760,7 +2760,6 @@ static int resp_mode_sense(struct scsi_cmnd *scp, else bd_len = 0; alloc_len = msense_6 ? cmd[4] : get_unaligned_be16(cmd + 7); - memset(arr, 0, SDEBUG_MAX_MSENSE_SZ); if (0x3 == pcontrol) { /* Saving values not supported */ mk_sense_buffer(scp, ILLEGAL_REQUEST, SAVING_PARAMS_UNSUP, 0); return check_condition_result; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 76f488ef6a7e..41e2dfa2d67d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -38,7 +38,6 @@ #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/bio-integrity.h> #include <linux/hdreg.h> #include <linux/errno.h> #include <linux/idr.h> @@ -3404,7 +3403,7 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp, rcu_read_lock(); vpd = rcu_dereference(sdkp->device->vpd_pgb1); - if (!vpd || vpd->len < 8) { + if (!vpd || vpd->len <= 8) { rcu_read_unlock(); return; } @@ -4093,9 +4092,38 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) { unsigned char cmd[6] = { START_STOP }; /* START_VALID */ struct scsi_sense_hdr sshdr; + struct scsi_failure failure_defs[] = { + { + /* Power on, reset, or bus device reset occurred */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 0, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + /* Power on occurred */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 1, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + /* SCSI bus reset */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 2, + .result = SAM_STAT_CHECK_CONDITION, + }, + {} + }; + struct scsi_failures failures = { + .total_allowed = 3, + .failure_definitions = failure_defs, + }; const struct scsi_exec_args exec_args = { .sshdr = &sshdr, .req_flags = BLK_MQ_REQ_PM, + .failures = &failures, }; struct scsi_device *sdp = sdkp->device; int res; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index baf870a03ecf..f86be197fedd 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1424,7 +1424,6 @@ static const struct file_operations sg_fops = { .mmap = sg_mmap, .release = sg_release, .fasync = sg_fasync, - .llseek = no_llseek, }; static const struct class sg_sysfs_class = { diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 0d8ce1a92168..d50bad3a2ce9 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -834,6 +834,9 @@ static int flush_buffer(struct scsi_tape *STp, int seek_next) int backspace, result; struct st_partstat *STps; + if (STp->ready != ST_READY) + return 0; + /* * If there was a bus reset, block further access * to this device. @@ -841,8 +844,6 @@ static int flush_buffer(struct scsi_tape *STp, int seek_next) if (STp->pos_unknown) return (-EIO); - if (STp->ready != ST_READY) - return 0; STps = &(STp->ps[STp->partition]); if (STps->rw == ST_WRITING) /* Writing */ return st_flush_write_buffer(STp); diff --git a/drivers/scsi/zalon.c b/drivers/scsi/zalon.c index 22d412cab91d..15602ec862e3 100644 --- a/drivers/scsi/zalon.c +++ b/drivers/scsi/zalon.c @@ -139,7 +139,7 @@ zalon_probe(struct parisc_device *dev) return -ENODEV; if (request_irq(dev->irq, ncr53c8xx_intr, IRQF_SHARED, "zalon", host)) { - dev_printk(KERN_ERR, &dev->dev, "irq problem with %d, detaching\n ", + dev_printk(KERN_ERR, &dev->dev, "irq problem with %d, detaching\n", dev->irq); goto fail; } diff --git a/drivers/sh/intc/userimask.c b/drivers/sh/intc/userimask.c index abe9091827cd..a363f77881d1 100644 --- a/drivers/sh/intc/userimask.c +++ b/drivers/sh/intc/userimask.c @@ -32,8 +32,11 @@ store_intc_userimask(struct device *dev, const char *buf, size_t count) { unsigned long level; + int ret; - level = simple_strtoul(buf, NULL, 10); + ret = kstrtoul(buf, 10, &level); + if (ret != 0) + return ret; /* * Minimal acceptable IRQ levels are in the 2 - 16 range, but diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 5539c5d139d4..653f82984216 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -685,7 +685,6 @@ static const struct file_operations spidev_fops = { .compat_ioctl = spidev_compat_ioctl, .open = spidev_open, .release = spidev_release, - .llseek = no_llseek, }; /*-------------------------------------------------------------------------*/ diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c index 4b4a4d63e61f..cb149bcdd7d5 100644 --- a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c +++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c @@ -564,7 +564,6 @@ static const struct file_operations acpi_thermal_rel_fops = { .open = acpi_thermal_rel_open, .release = acpi_thermal_rel_release, .unlocked_ioctl = acpi_thermal_rel_ioctl, - .llseek = no_llseek, }; static struct miscdevice acpi_thermal_rel_misc_device = { diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 6bd28a042dff..9771072da177 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -459,7 +459,6 @@ static void tty_show_fdinfo(struct seq_file *m, struct file *file) } static const struct file_operations tty_fops = { - .llseek = no_llseek, .read_iter = tty_read, .write_iter = tty_write, .splice_read = copy_splice_read, @@ -474,7 +473,6 @@ static const struct file_operations tty_fops = { }; static const struct file_operations console_fops = { - .llseek = no_llseek, .read_iter = tty_read, .write_iter = redirected_tty_write, .splice_read = copy_splice_read, @@ -488,7 +486,6 @@ static const struct file_operations console_fops = { }; static const struct file_operations hung_up_tty_fops = { - .llseek = no_llseek, .read_iter = hung_up_tty_read, .write_iter = hung_up_tty_write, .poll = hung_up_tty_poll, diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index c87fdc849c62..ecdfff2456e3 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -93,7 +93,7 @@ static const struct __ufs_qcom_bw_table { [MODE_HS_RB][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, [MODE_HS_RB][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, - [MODE_MAX][0][0] = { 7643136, 307200 }, + [MODE_MAX][0][0] = { 7643136, 819200 }, }; static void ufs_qcom_get_default_testbus_cfg(struct ufs_qcom_host *host); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 05b52e61a66f..c626bb73ea59 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -722,7 +722,6 @@ static __poll_t ffs_ep0_poll(struct file *file, poll_table *wait) } static const struct file_operations ffs_ep0_operations = { - .llseek = no_llseek, .open = ffs_ep0_open, .write = ffs_ep0_write, @@ -1830,7 +1829,6 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, } static const struct file_operations ffs_epfile_operations = { - .llseek = no_llseek, .open = ffs_epfile_open, .write_iter = ffs_epfile_write_iter, diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 03179b1880fd..9c7381661016 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -705,7 +705,6 @@ static const struct file_operations ep_io_operations = { .open = ep_open, .release = ep_release, - .llseek = no_llseek, .unlocked_ioctl = ep_ioctl, .read_iter = ep_read_iter, .write_iter = ep_write_iter, @@ -1939,7 +1938,6 @@ gadget_dev_open (struct inode *inode, struct file *fd) } static const struct file_operations ep0_operations = { - .llseek = no_llseek, .open = gadget_dev_open, .read = ep0_read, diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index 399fca32a8ac..112fd18d8c99 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -1364,7 +1364,6 @@ static const struct file_operations raw_fops = { .unlocked_ioctl = raw_ioctl, .compat_ioctl = raw_ioctl, .release = raw_release, - .llseek = no_llseek, }; static struct miscdevice raw_misc_device = { diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index b76885d78e8a..4928eba19327 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -187,7 +187,6 @@ static int regs_dbg_release(struct inode *inode, struct file *file) static const struct file_operations queue_dbg_fops = { .owner = THIS_MODULE, .open = queue_dbg_open, - .llseek = no_llseek, .read = queue_dbg_read, .release = queue_dbg_release, }; diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index 7cbef74dfc9a..f392d6f84df9 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -627,7 +627,6 @@ static const struct file_operations ld_usb_fops = { .open = ld_usb_open, .release = ld_usb_release, .poll = ld_usb_poll, - .llseek = no_llseek, }; /* diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index 4e30de4db1c0..afb71c18415d 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1289,7 +1289,6 @@ static int mon_bin_mmap(struct file *filp, struct vm_area_struct *vma) static const struct file_operations mon_fops_binary = { .owner = THIS_MODULE, .open = mon_bin_open, - .llseek = no_llseek, .read = mon_bin_read, /* .write = mon_text_write, */ .poll = mon_bin_poll, diff --git a/drivers/usb/mon/mon_stat.c b/drivers/usb/mon/mon_stat.c index 3c23805ab1a4..398e02af6a2b 100644 --- a/drivers/usb/mon/mon_stat.c +++ b/drivers/usb/mon/mon_stat.c @@ -62,7 +62,6 @@ static int mon_stat_release(struct inode *inode, struct file *file) const struct file_operations mon_fops_stat = { .owner = THIS_MODULE, .open = mon_stat_open, - .llseek = no_llseek, .read = mon_stat_read, /* .write = mon_stat_write, */ /* .poll = mon_stat_poll, */ diff --git a/drivers/usb/mon/mon_text.c b/drivers/usb/mon/mon_text.c index 2fe9b95bac1d..68b9b2b41189 100644 --- a/drivers/usb/mon/mon_text.c +++ b/drivers/usb/mon/mon_text.c @@ -685,7 +685,6 @@ static int mon_text_release(struct inode *inode, struct file *file) static const struct file_operations mon_fops_text_t = { .owner = THIS_MODULE, .open = mon_text_open, - .llseek = no_llseek, .read = mon_text_read_t, .release = mon_text_release, }; @@ -693,7 +692,6 @@ static const struct file_operations mon_fops_text_t = { static const struct file_operations mon_fops_text_u = { .owner = THIS_MODULE, .open = mon_text_open, - .llseek = no_llseek, .read = mon_text_read_u, .release = mon_text_release, }; diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index 9a3e97108ace..0d632ba5d2a3 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -723,7 +723,6 @@ static const struct file_operations hisi_acc_vf_resume_fops = { .owner = THIS_MODULE, .write = hisi_acc_vf_resume_write, .release = hisi_acc_vf_release_file, - .llseek = no_llseek, }; static struct hisi_acc_vf_migration_file * @@ -845,7 +844,6 @@ static const struct file_operations hisi_acc_vf_save_fops = { .unlocked_ioctl = hisi_acc_vf_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = hisi_acc_vf_release_file, - .llseek = no_llseek, }; static struct hisi_acc_vf_migration_file * diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 61d9b0f9146d..242c23eef452 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -587,7 +587,6 @@ static const struct file_operations mlx5vf_save_fops = { .unlocked_ioctl = mlx5vf_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = mlx5vf_release_file, - .llseek = no_llseek, }; static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev) @@ -1000,7 +999,6 @@ static const struct file_operations mlx5vf_resume_fops = { .owner = THIS_MODULE, .write = mlx5vf_resume_write, .release = mlx5vf_release_file, - .llseek = no_llseek, }; static struct mlx5_vf_migration_file * diff --git a/drivers/vfio/pci/pds/lm.c b/drivers/vfio/pci/pds/lm.c index 6b94cc0bf45b..f2673d395236 100644 --- a/drivers/vfio/pci/pds/lm.c +++ b/drivers/vfio/pci/pds/lm.c @@ -235,7 +235,6 @@ static const struct file_operations pds_vfio_save_fops = { .owner = THIS_MODULE, .read = pds_vfio_save_read, .release = pds_vfio_release_file, - .llseek = no_llseek, }; static int pds_vfio_get_save_file(struct pds_vfio_pci_device *pds_vfio) @@ -334,7 +333,6 @@ static const struct file_operations pds_vfio_restore_fops = { .owner = THIS_MODULE, .write = pds_vfio_restore_write, .release = pds_vfio_release_file, - .llseek = no_llseek, }; static int pds_vfio_get_restore_file(struct pds_vfio_pci_device *pds_vfio) diff --git a/drivers/vfio/pci/qat/main.c b/drivers/vfio/pci/qat/main.c index e36740a282e7..be3644ced17b 100644 --- a/drivers/vfio/pci/qat/main.c +++ b/drivers/vfio/pci/qat/main.c @@ -220,7 +220,6 @@ static const struct file_operations qat_vf_save_fops = { .unlocked_ioctl = qat_vf_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = qat_vf_release_file, - .llseek = no_llseek, }; static int qat_vf_save_state(struct qat_vf_core_device *qat_vdev, @@ -345,7 +344,6 @@ static const struct file_operations qat_vf_resume_fops = { .owner = THIS_MODULE, .write = qat_vf_resume_write, .release = qat_vf_release_file, - .llseek = no_llseek, }; static struct qat_vf_migration_file * diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 2e093535884b..e8b4e8c119b5 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -512,8 +512,10 @@ static int search_fb_in_map(int idx) int i, retval = 0; for (i = first_fb_vc; i <= last_fb_vc; i++) { - if (con2fb_map[i] == idx) + if (con2fb_map[i] == idx) { retval = 1; + break; + } } return retval; } @@ -523,8 +525,10 @@ static int search_for_mapped_con(void) int i, retval = 0; for (i = first_fb_vc; i <= last_fb_vc; i++) { - if (con2fb_map[i] != -1) + if (con2fb_map[i] != -1) { retval = 1; + break; + } } return retval; } @@ -861,6 +865,8 @@ static int set_con2fb_map(int unit, int newidx, int user) return err; fbcon_add_cursor_work(info); + } else if (vc) { + set_blitting_type(vc, info); } con2fb_map[unit] = newidx; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c index 4040e247e026..d5a43b3bf45e 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dss-of.c @@ -129,12 +129,9 @@ omapdss_of_find_source_for_first_ep(struct device_node *node) return ERR_PTR(-EINVAL); src_port = of_graph_get_remote_port(ep); - if (!src_port) { - of_node_put(ep); - return ERR_PTR(-EINVAL); - } - of_node_put(ep); + if (!src_port) + return ERR_PTR(-EINVAL); src = omap_dss_find_output_by_port_node(src_port); diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c index 009bf1d92644..75033e6be15a 100644 --- a/drivers/video/fbdev/sis/sis_main.c +++ b/drivers/video/fbdev/sis/sis_main.c @@ -183,7 +183,7 @@ static void sisfb_search_mode(char *name, bool quiet) { unsigned int j = 0, xres = 0, yres = 0, depth = 0, rate = 0; int i = 0; - char strbuf[16], strbuf1[20]; + char strbuf[24], strbuf1[20]; char *nameptr = name; /* We don't know the hardware specs yet and there is no ivideo */ diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index 2acba56ad42e..d7db6c824e13 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -285,7 +285,6 @@ static long tdx_guest_ioctl(struct file *file, unsigned int cmd, static const struct file_operations tdx_guest_fops = { .owner = THIS_MODULE, .unlocked_ioctl = tdx_guest_ioctl, - .llseek = no_llseek, }; static struct miscdevice tdx_misc_dev = { diff --git a/drivers/watchdog/acquirewdt.c b/drivers/watchdog/acquirewdt.c index 53b04abd55b0..08ca18e91124 100644 --- a/drivers/watchdog/acquirewdt.c +++ b/drivers/watchdog/acquirewdt.c @@ -218,7 +218,6 @@ static int acq_close(struct inode *inode, struct file *file) static const struct file_operations acq_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = acq_write, .unlocked_ioctl = acq_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/advantechwdt.c b/drivers/watchdog/advantechwdt.c index 7a0acbc3e4dd..e41cd3ba4e0e 100644 --- a/drivers/watchdog/advantechwdt.c +++ b/drivers/watchdog/advantechwdt.c @@ -217,7 +217,6 @@ static int advwdt_close(struct inode *inode, struct file *file) static const struct file_operations advwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = advwdt_write, .unlocked_ioctl = advwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/alim1535_wdt.c b/drivers/watchdog/alim1535_wdt.c index bfb9a91ca1df..1ecbd1ac5c3a 100644 --- a/drivers/watchdog/alim1535_wdt.c +++ b/drivers/watchdog/alim1535_wdt.c @@ -359,7 +359,6 @@ static int __init ali_find_watchdog(void) static const struct file_operations ali_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = ali_write, .unlocked_ioctl = ali_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/alim7101_wdt.c b/drivers/watchdog/alim7101_wdt.c index 4ff7f5afb7aa..9c7cf939ba3d 100644 --- a/drivers/watchdog/alim7101_wdt.c +++ b/drivers/watchdog/alim7101_wdt.c @@ -289,7 +289,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/at91rm9200_wdt.c b/drivers/watchdog/at91rm9200_wdt.c index 558015f08c7a..17382512a609 100644 --- a/drivers/watchdog/at91rm9200_wdt.c +++ b/drivers/watchdog/at91rm9200_wdt.c @@ -210,7 +210,6 @@ static ssize_t at91_wdt_write(struct file *file, const char *data, static const struct file_operations at91wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = at91_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = at91_wdt_open, diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c index e5cc30622b12..d16b2c583fa4 100644 --- a/drivers/watchdog/ath79_wdt.c +++ b/drivers/watchdog/ath79_wdt.c @@ -231,7 +231,6 @@ static long ath79_wdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations ath79_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = ath79_wdt_write, .unlocked_ioctl = ath79_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/cpu5wdt.c b/drivers/watchdog/cpu5wdt.c index 9f279c0e13a6..f94b84048612 100644 --- a/drivers/watchdog/cpu5wdt.c +++ b/drivers/watchdog/cpu5wdt.c @@ -185,7 +185,6 @@ static ssize_t cpu5wdt_write(struct file *file, const char __user *buf, static const struct file_operations cpu5wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = cpu5wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = cpu5wdt_open, diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index 901b94d456db..8ee81f018dda 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -507,7 +507,6 @@ static const struct file_operations cpwd_fops = { .write = cpwd_write, .read = cpwd_read, .release = cpwd_release, - .llseek = no_llseek, }; static int cpwd_probe(struct platform_device *op) diff --git a/drivers/watchdog/eurotechwdt.c b/drivers/watchdog/eurotechwdt.c index e26609ad4c17..10c647b1226a 100644 --- a/drivers/watchdog/eurotechwdt.c +++ b/drivers/watchdog/eurotechwdt.c @@ -368,7 +368,6 @@ static int eurwdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations eurwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = eurwdt_write, .unlocked_ioctl = eurwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c index 6a1db1c783fa..d854fcfbfa5b 100644 --- a/drivers/watchdog/gef_wdt.c +++ b/drivers/watchdog/gef_wdt.c @@ -245,7 +245,6 @@ static int gef_wdt_release(struct inode *inode, struct file *file) static const struct file_operations gef_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = gef_wdt_write, .unlocked_ioctl = gef_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/geodewdt.c b/drivers/watchdog/geodewdt.c index 5186c37ad451..4ed6d139320b 100644 --- a/drivers/watchdog/geodewdt.c +++ b/drivers/watchdog/geodewdt.c @@ -196,7 +196,6 @@ static long geodewdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations geodewdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = geodewdt_write, .unlocked_ioctl = geodewdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/ib700wdt.c b/drivers/watchdog/ib700wdt.c index 39ea97009abd..b041ad90a62c 100644 --- a/drivers/watchdog/ib700wdt.c +++ b/drivers/watchdog/ib700wdt.c @@ -256,7 +256,6 @@ static int ibwdt_close(struct inode *inode, struct file *file) static const struct file_operations ibwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = ibwdt_write, .unlocked_ioctl = ibwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/ibmasr.c b/drivers/watchdog/ibmasr.c index 6955c693b5fd..cf845f865945 100644 --- a/drivers/watchdog/ibmasr.c +++ b/drivers/watchdog/ibmasr.c @@ -340,7 +340,6 @@ static int asr_release(struct inode *inode, struct file *file) static const struct file_operations asr_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = asr_write, .unlocked_ioctl = asr_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/indydog.c b/drivers/watchdog/indydog.c index 9857bb74a723..d3092d261345 100644 --- a/drivers/watchdog/indydog.c +++ b/drivers/watchdog/indydog.c @@ -149,7 +149,6 @@ static int indydog_notify_sys(struct notifier_block *this, static const struct file_operations indydog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = indydog_write, .unlocked_ioctl = indydog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/it8712f_wdt.c b/drivers/watchdog/it8712f_wdt.c index 3ce6a58bd81e..b776e6766c9d 100644 --- a/drivers/watchdog/it8712f_wdt.c +++ b/drivers/watchdog/it8712f_wdt.c @@ -341,7 +341,6 @@ static int it8712f_wdt_release(struct inode *inode, struct file *file) static const struct file_operations it8712f_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = it8712f_wdt_write, .unlocked_ioctl = it8712f_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/m54xx_wdt.c b/drivers/watchdog/m54xx_wdt.c index 062ea3e6497e..26bd073bd375 100644 --- a/drivers/watchdog/m54xx_wdt.c +++ b/drivers/watchdog/m54xx_wdt.c @@ -179,7 +179,6 @@ static int m54xx_wdt_release(struct inode *inode, struct file *file) static const struct file_operations m54xx_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = m54xx_wdt_write, .unlocked_ioctl = m54xx_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/machzwd.c b/drivers/watchdog/machzwd.c index 73f2221f6222..73d641486909 100644 --- a/drivers/watchdog/machzwd.c +++ b/drivers/watchdog/machzwd.c @@ -359,7 +359,6 @@ static int zf_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations zf_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = zf_write, .unlocked_ioctl = zf_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/mixcomwd.c b/drivers/watchdog/mixcomwd.c index d387bad377c4..70d9cf84c342 100644 --- a/drivers/watchdog/mixcomwd.c +++ b/drivers/watchdog/mixcomwd.c @@ -224,7 +224,6 @@ static long mixcomwd_ioctl(struct file *file, static const struct file_operations mixcomwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = mixcomwd_write, .unlocked_ioctl = mixcomwd_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/mtx-1_wdt.c b/drivers/watchdog/mtx-1_wdt.c index 06756135033d..11f05024a181 100644 --- a/drivers/watchdog/mtx-1_wdt.c +++ b/drivers/watchdog/mtx-1_wdt.c @@ -177,7 +177,6 @@ static ssize_t mtx1_wdt_write(struct file *file, const char *buf, static const struct file_operations mtx1_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = mtx1_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = mtx1_wdt_open, diff --git a/drivers/watchdog/nv_tco.c b/drivers/watchdog/nv_tco.c index ac4a9c16341d..f8eb1f65a59e 100644 --- a/drivers/watchdog/nv_tco.c +++ b/drivers/watchdog/nv_tco.c @@ -264,7 +264,6 @@ static long nv_tco_ioctl(struct file *file, unsigned int cmd, static const struct file_operations nv_tco_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = nv_tco_write, .unlocked_ioctl = nv_tco_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/pc87413_wdt.c b/drivers/watchdog/pc87413_wdt.c index c7f745caf203..fbf835d112b8 100644 --- a/drivers/watchdog/pc87413_wdt.c +++ b/drivers/watchdog/pc87413_wdt.c @@ -470,7 +470,6 @@ static int pc87413_notify_sys(struct notifier_block *this, static const struct file_operations pc87413_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = pc87413_write, .unlocked_ioctl = pc87413_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/pcwd.c b/drivers/watchdog/pcwd.c index a793b03a785d..1a4282235aac 100644 --- a/drivers/watchdog/pcwd.c +++ b/drivers/watchdog/pcwd.c @@ -749,7 +749,6 @@ static int pcwd_temp_close(struct inode *inode, struct file *file) static const struct file_operations pcwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = pcwd_write, .unlocked_ioctl = pcwd_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -765,7 +764,6 @@ static struct miscdevice pcwd_miscdev = { static const struct file_operations pcwd_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = pcwd_temp_read, .open = pcwd_temp_open, .release = pcwd_temp_close, diff --git a/drivers/watchdog/pcwd_pci.c b/drivers/watchdog/pcwd_pci.c index 54d86fcb1837..a489b426f2ba 100644 --- a/drivers/watchdog/pcwd_pci.c +++ b/drivers/watchdog/pcwd_pci.c @@ -643,7 +643,6 @@ static int pcipcwd_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations pcipcwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = pcipcwd_write, .unlocked_ioctl = pcipcwd_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -659,7 +658,6 @@ static struct miscdevice pcipcwd_miscdev = { static const struct file_operations pcipcwd_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = pcipcwd_temp_read, .open = pcipcwd_temp_open, .release = pcipcwd_temp_release, diff --git a/drivers/watchdog/pcwd_usb.c b/drivers/watchdog/pcwd_usb.c index 8202f0a6b093..132699e2f247 100644 --- a/drivers/watchdog/pcwd_usb.c +++ b/drivers/watchdog/pcwd_usb.c @@ -549,7 +549,6 @@ static int usb_pcwd_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations usb_pcwd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = usb_pcwd_write, .unlocked_ioctl = usb_pcwd_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -565,7 +564,6 @@ static struct miscdevice usb_pcwd_miscdev = { static const struct file_operations usb_pcwd_temperature_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = usb_pcwd_temperature_read, .open = usb_pcwd_temperature_open, .release = usb_pcwd_temperature_release, diff --git a/drivers/watchdog/pika_wdt.c b/drivers/watchdog/pika_wdt.c index 782b8c23d99c..393aa4b1bc13 100644 --- a/drivers/watchdog/pika_wdt.c +++ b/drivers/watchdog/pika_wdt.c @@ -209,7 +209,6 @@ static long pikawdt_ioctl(struct file *file, static const struct file_operations pikawdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .open = pikawdt_open, .release = pikawdt_release, .write = pikawdt_write, diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c index 417f9b75679c..efadbb9d7ce7 100644 --- a/drivers/watchdog/rc32434_wdt.c +++ b/drivers/watchdog/rc32434_wdt.c @@ -242,7 +242,6 @@ static long rc32434_wdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations rc32434_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = rc32434_wdt_write, .unlocked_ioctl = rc32434_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/rdc321x_wdt.c b/drivers/watchdog/rdc321x_wdt.c index 6176f4343fc5..80490316a27f 100644 --- a/drivers/watchdog/rdc321x_wdt.c +++ b/drivers/watchdog/rdc321x_wdt.c @@ -197,7 +197,6 @@ static ssize_t rdc321x_wdt_write(struct file *file, const char __user *buf, static const struct file_operations rdc321x_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = rdc321x_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = rdc321x_wdt_open, diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c index b293792a292a..f47d90d01c19 100644 --- a/drivers/watchdog/riowd.c +++ b/drivers/watchdog/riowd.c @@ -160,7 +160,6 @@ static ssize_t riowd_write(struct file *file, const char __user *buf, static const struct file_operations riowd_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = riowd_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = riowd_open, diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c index 34a917221e31..6e91ee3fbfb5 100644 --- a/drivers/watchdog/sa1100_wdt.c +++ b/drivers/watchdog/sa1100_wdt.c @@ -164,7 +164,6 @@ static long sa1100dog_ioctl(struct file *file, unsigned int cmd, static const struct file_operations sa1100dog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sa1100dog_write, .unlocked_ioctl = sa1100dog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sb_wdog.c b/drivers/watchdog/sb_wdog.c index 504be461f992..eaa68b54cf56 100644 --- a/drivers/watchdog/sb_wdog.c +++ b/drivers/watchdog/sb_wdog.c @@ -234,7 +234,6 @@ static int sbwdog_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations sbwdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sbwdog_write, .unlocked_ioctl = sbwdog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sbc60xxwdt.c b/drivers/watchdog/sbc60xxwdt.c index 7b974802dfc7..e9bf12918ed8 100644 --- a/drivers/watchdog/sbc60xxwdt.c +++ b/drivers/watchdog/sbc60xxwdt.c @@ -275,7 +275,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/sbc7240_wdt.c b/drivers/watchdog/sbc7240_wdt.c index d640b26e18a6..21a1f0b32070 100644 --- a/drivers/watchdog/sbc7240_wdt.c +++ b/drivers/watchdog/sbc7240_wdt.c @@ -205,7 +205,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/sbc8360.c b/drivers/watchdog/sbc8360.c index 4f8b9912fc51..a9fd1615b4c3 100644 --- a/drivers/watchdog/sbc8360.c +++ b/drivers/watchdog/sbc8360.c @@ -301,7 +301,6 @@ static int sbc8360_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations sbc8360_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sbc8360_write, .open = sbc8360_open, .release = sbc8360_close, diff --git a/drivers/watchdog/sbc_epx_c3.c b/drivers/watchdog/sbc_epx_c3.c index 5e3a9ddb952e..1d291dc0a4a6 100644 --- a/drivers/watchdog/sbc_epx_c3.c +++ b/drivers/watchdog/sbc_epx_c3.c @@ -153,7 +153,6 @@ static int epx_c3_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations epx_c3_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = epx_c3_write, .unlocked_ioctl = epx_c3_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sbc_fitpc2_wdt.c b/drivers/watchdog/sbc_fitpc2_wdt.c index b8eb8d5ca1af..ff9e44825423 100644 --- a/drivers/watchdog/sbc_fitpc2_wdt.c +++ b/drivers/watchdog/sbc_fitpc2_wdt.c @@ -181,7 +181,6 @@ static int fitpc2_wdt_release(struct inode *inode, struct file *file) static const struct file_operations fitpc2_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fitpc2_wdt_write, .unlocked_ioctl = fitpc2_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sc1200wdt.c b/drivers/watchdog/sc1200wdt.c index f22ebe89fe13..76a58715f665 100644 --- a/drivers/watchdog/sc1200wdt.c +++ b/drivers/watchdog/sc1200wdt.c @@ -304,7 +304,6 @@ static struct notifier_block sc1200wdt_notifier = { static const struct file_operations sc1200wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sc1200wdt_write, .unlocked_ioctl = sc1200wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/sc520_wdt.c b/drivers/watchdog/sc520_wdt.c index ca65468f4b9c..e849e1af267b 100644 --- a/drivers/watchdog/sc520_wdt.c +++ b/drivers/watchdog/sc520_wdt.c @@ -331,7 +331,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c index 409d49880170..76053158d259 100644 --- a/drivers/watchdog/sch311x_wdt.c +++ b/drivers/watchdog/sch311x_wdt.c @@ -334,7 +334,6 @@ static int sch311x_wdt_close(struct inode *inode, struct file *file) static const struct file_operations sch311x_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sch311x_wdt_write, .unlocked_ioctl = sch311x_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/scx200_wdt.c b/drivers/watchdog/scx200_wdt.c index 7b5e18323f3f..4dd8549e3674 100644 --- a/drivers/watchdog/scx200_wdt.c +++ b/drivers/watchdog/scx200_wdt.c @@ -198,7 +198,6 @@ static long scx200_wdt_ioctl(struct file *file, unsigned int cmd, static const struct file_operations scx200_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = scx200_wdt_write, .unlocked_ioctl = scx200_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/smsc37b787_wdt.c b/drivers/watchdog/smsc37b787_wdt.c index 7463df479d11..97ca500ec8a8 100644 --- a/drivers/watchdog/smsc37b787_wdt.c +++ b/drivers/watchdog/smsc37b787_wdt.c @@ -502,7 +502,6 @@ static int wb_smsc_wdt_notify_sys(struct notifier_block *this, static const struct file_operations wb_smsc_wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wb_smsc_wdt_write, .unlocked_ioctl = wb_smsc_wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/w83877f_wdt.c b/drivers/watchdog/w83877f_wdt.c index f2650863fd02..1937084c182c 100644 --- a/drivers/watchdog/w83877f_wdt.c +++ b/drivers/watchdog/w83877f_wdt.c @@ -299,7 +299,6 @@ static long fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg) static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = fop_write, .open = fop_open, .release = fop_close, diff --git a/drivers/watchdog/w83977f_wdt.c b/drivers/watchdog/w83977f_wdt.c index 31bf21ceaf48..3776030fa7c6 100644 --- a/drivers/watchdog/w83977f_wdt.c +++ b/drivers/watchdog/w83977f_wdt.c @@ -443,7 +443,6 @@ static int wdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdt_write, .unlocked_ioctl = wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wafer5823wdt.c b/drivers/watchdog/wafer5823wdt.c index a8a1ed215e1e..291109349e73 100644 --- a/drivers/watchdog/wafer5823wdt.c +++ b/drivers/watchdog/wafer5823wdt.c @@ -227,7 +227,6 @@ static int wafwdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wafwdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wafwdt_write, .unlocked_ioctl = wafwdt_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wdrtas.c b/drivers/watchdog/wdrtas.c index c00627825de8..d4fe0bc82211 100644 --- a/drivers/watchdog/wdrtas.c +++ b/drivers/watchdog/wdrtas.c @@ -469,7 +469,6 @@ static int wdrtas_reboot(struct notifier_block *this, static const struct file_operations wdrtas_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdrtas_write, .unlocked_ioctl = wdrtas_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -485,7 +484,6 @@ static struct miscdevice wdrtas_miscdev = { static const struct file_operations wdrtas_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = wdrtas_temp_read, .open = wdrtas_temp_open, .release = wdrtas_temp_close, diff --git a/drivers/watchdog/wdt.c b/drivers/watchdog/wdt.c index 183876156243..3980d60bacd8 100644 --- a/drivers/watchdog/wdt.c +++ b/drivers/watchdog/wdt.c @@ -520,7 +520,6 @@ static int wdt_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdt_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdt_write, .unlocked_ioctl = wdt_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -536,7 +535,6 @@ static struct miscdevice wdt_miscdev = { static const struct file_operations wdt_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = wdt_temp_read, .open = wdt_temp_open, .release = wdt_temp_release, diff --git a/drivers/watchdog/wdt285.c b/drivers/watchdog/wdt285.c index 5b7be7a62d54..78681d9f7d53 100644 --- a/drivers/watchdog/wdt285.c +++ b/drivers/watchdog/wdt285.c @@ -178,7 +178,6 @@ static long watchdog_ioctl(struct file *file, unsigned int cmd, static const struct file_operations watchdog_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = watchdog_write, .unlocked_ioctl = watchdog_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wdt977.c b/drivers/watchdog/wdt977.c index c9b8e863f70f..4f449ac4dda4 100644 --- a/drivers/watchdog/wdt977.c +++ b/drivers/watchdog/wdt977.c @@ -419,7 +419,6 @@ static int wdt977_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdt977_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdt977_write, .unlocked_ioctl = wdt977_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/drivers/watchdog/wdt_pci.c b/drivers/watchdog/wdt_pci.c index d5e56b601351..dc5f29560e9b 100644 --- a/drivers/watchdog/wdt_pci.c +++ b/drivers/watchdog/wdt_pci.c @@ -563,7 +563,6 @@ static int wdtpci_notify_sys(struct notifier_block *this, unsigned long code, static const struct file_operations wdtpci_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = wdtpci_write, .unlocked_ioctl = wdtpci_ioctl, .compat_ioctl = compat_ptr_ioctl, @@ -579,7 +578,6 @@ static struct miscdevice wdtpci_miscdev = { static const struct file_operations wdtpci_temp_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = wdtpci_temp_read, .open = wdtpci_temp_open, .release = wdtpci_temp_release, diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index f7d6f47971fd..62035fe16bb8 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -261,6 +261,7 @@ config XEN_SCSI_BACKEND config XEN_PRIVCMD tristate "Xen hypercall passthrough driver" depends on XEN + imply CONFIG_XEN_PCIDEV_BACKEND default m help The hypercall passthrough driver allows privileged user programs to diff --git a/drivers/xen/acpi.c b/drivers/xen/acpi.c index 6893c79fd2a1..9e2096524fbc 100644 --- a/drivers/xen/acpi.c +++ b/drivers/xen/acpi.c @@ -30,6 +30,7 @@ * IN THE SOFTWARE. */ +#include <linux/pci.h> #include <xen/acpi.h> #include <xen/interface/platform.h> #include <asm/xen/hypercall.h> @@ -75,3 +76,52 @@ int xen_acpi_notify_hypervisor_extended_sleep(u8 sleep_state, return xen_acpi_notify_hypervisor_state(sleep_state, val_a, val_b, true); } + +struct acpi_prt_entry { + struct acpi_pci_id id; + u8 pin; + acpi_handle link; + u32 index; +}; + +int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out) +{ + int gsi; + u8 pin; + struct acpi_prt_entry *entry; + int trigger = ACPI_LEVEL_SENSITIVE; + int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ? + ACPI_ACTIVE_HIGH : ACPI_ACTIVE_LOW; + + if (!dev || !gsi_out || !trigger_out || !polarity_out) + return -EINVAL; + + pin = dev->pin; + if (!pin) + return -EINVAL; + + entry = acpi_pci_irq_lookup(dev, pin); + if (entry) { + if (entry->link) + gsi = acpi_pci_link_allocate_irq(entry->link, + entry->index, + &trigger, &polarity, + NULL); + else + gsi = entry->index; + } else + gsi = -1; + + if (gsi < 0) + return -EINVAL; + + *gsi_out = gsi; + *trigger_out = trigger; + *polarity_out = polarity; + + return 0; +} +EXPORT_SYMBOL_GPL(xen_acpi_get_gsi_info); diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 9b7fcc7dbb38..7e4a13e632dc 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -694,7 +694,6 @@ static const struct file_operations evtchn_fops = { .fasync = evtchn_fasync, .open = evtchn_open, .release = evtchn_release, - .llseek = no_llseek, }; static struct miscdevice evtchn_miscdev = { diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c index e9ac3b8c4167..4f65b641c054 100644 --- a/drivers/xen/mcelog.c +++ b/drivers/xen/mcelog.c @@ -182,7 +182,6 @@ static const struct file_operations xen_mce_chrdev_ops = { .read = xen_mce_chrdev_read, .poll = xen_mce_chrdev_poll, .unlocked_ioctl = xen_mce_chrdev_ioctl, - .llseek = no_llseek, }; static struct miscdevice xen_mce_chrdev_device = { diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index a2facd8f7e51..416f231809cb 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -173,6 +173,19 @@ static int xen_remove_device(struct device *dev) return r; } +int xen_reset_device(const struct pci_dev *dev) +{ + struct pci_device_reset device = { + .dev.seg = pci_domain_nr(dev->bus), + .dev.bus = dev->bus->number, + .dev.devfn = dev->devfn, + .flags = PCI_DEVICE_RESET_FLR, + }; + + return HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_reset, &device); +} +EXPORT_SYMBOL_GPL(xen_reset_device); + static int xen_pci_notifier(struct notifier_block *nb, unsigned long action, void *data) { diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 54e4f285c0f4..3273cb8c2a66 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -46,6 +46,9 @@ #include <xen/page.h> #include <xen/xen-ops.h> #include <xen/balloon.h> +#ifdef CONFIG_XEN_ACPI +#include <xen/acpi.h> +#endif #include "privcmd.h" @@ -844,6 +847,31 @@ out: return rc; } +static long privcmd_ioctl_pcidev_get_gsi(struct file *file, void __user *udata) +{ +#if defined(CONFIG_XEN_ACPI) + int rc = -EINVAL; + struct privcmd_pcidev_get_gsi kdata; + + if (copy_from_user(&kdata, udata, sizeof(kdata))) + return -EFAULT; + + if (IS_REACHABLE(CONFIG_XEN_PCIDEV_BACKEND)) + rc = pcistub_get_gsi_from_sbdf(kdata.sbdf); + + if (rc < 0) + return rc; + + kdata.gsi = rc; + if (copy_to_user(udata, &kdata, sizeof(kdata))) + return -EFAULT; + + return 0; +#else + return -EINVAL; +#endif +} + #ifdef CONFIG_XEN_PRIVCMD_EVENTFD /* Irqfd support */ static struct workqueue_struct *irqfd_cleanup_wq; @@ -1543,6 +1571,10 @@ static long privcmd_ioctl(struct file *file, ret = privcmd_ioctl_ioeventfd(file, udata); break; + case IOCTL_PRIVCMD_PCIDEV_GET_GSI: + ret = privcmd_ioctl_pcidev_get_gsi(file, udata); + break; + default: break; } diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c index 1948a9700c8f..cf568e899ee2 100644 --- a/drivers/xen/xen-pciback/conf_space_capability.c +++ b/drivers/xen/xen-pciback/conf_space_capability.c @@ -122,7 +122,7 @@ static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value, if (err) goto out; - new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK); + new_state = (__force pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK); new_value &= PM_OK_BITS; if ((old_value & PM_OK_BITS) != new_value) { diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 4faebbb84999..2f3da5ac62cd 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -21,6 +21,9 @@ #include <xen/events.h> #include <xen/pci.h> #include <xen/xen.h> +#ifdef CONFIG_XEN_ACPI +#include <xen/acpi.h> +#endif #include <asm/xen/hypervisor.h> #include <xen/interface/physdev.h> #include "pciback.h" @@ -53,6 +56,9 @@ struct pcistub_device { struct pci_dev *dev; struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */ +#ifdef CONFIG_XEN_ACPI + int gsi; +#endif }; /* Access to pcistub_devices & seized_devices lists and the initialize_devices @@ -85,10 +91,23 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev) kref_init(&psdev->kref); spin_lock_init(&psdev->lock); +#ifdef CONFIG_XEN_ACPI + psdev->gsi = -1; +#endif return psdev; } +static int pcistub_reset_device_state(struct pci_dev *dev) +{ + __pci_reset_function_locked(dev); + + if (!xen_pv_domain()) + return xen_reset_device(dev); + else + return 0; +} + /* Don't call this directly as it's called by pcistub_device_put */ static void pcistub_device_release(struct kref *kref) { @@ -107,7 +126,7 @@ static void pcistub_device_release(struct kref *kref) /* Call the reset function which does not take lock as this * is called from "unbind" which takes a device_lock mutex. */ - __pci_reset_function_locked(dev); + pcistub_reset_device_state(dev); if (dev_data && pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state)) dev_info(&dev->dev, "Could not reload PCI state\n"); @@ -207,6 +226,25 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev, return pci_dev; } +#ifdef CONFIG_XEN_ACPI +int pcistub_get_gsi_from_sbdf(unsigned int sbdf) +{ + struct pcistub_device *psdev; + int domain = (sbdf >> 16) & 0xffff; + int bus = PCI_BUS_NUM(sbdf); + int slot = PCI_SLOT(sbdf); + int func = PCI_FUNC(sbdf); + + psdev = pcistub_device_find(domain, bus, slot, func); + + if (!psdev) + return -ENODEV; + + return psdev->gsi; +} +EXPORT_SYMBOL_GPL(pcistub_get_gsi_from_sbdf); +#endif + struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev, int domain, int bus, int slot, int func) @@ -284,7 +322,7 @@ void pcistub_put_pci_dev(struct pci_dev *dev) * (so it's ready for the next domain) */ device_lock_assert(&dev->dev); - __pci_reset_function_locked(dev); + pcistub_reset_device_state(dev); dev_data = pci_get_drvdata(dev); ret = pci_load_saved_state(dev, dev_data->pci_saved_state); @@ -354,11 +392,20 @@ static int pcistub_match(struct pci_dev *dev) return found; } -static int pcistub_init_device(struct pci_dev *dev) +static int pcistub_init_device(struct pcistub_device *psdev) { struct xen_pcibk_dev_data *dev_data; + struct pci_dev *dev; +#ifdef CONFIG_XEN_ACPI + int gsi, trigger, polarity; +#endif int err = 0; + if (!psdev) + return -EINVAL; + + dev = psdev->dev; + dev_dbg(&dev->dev, "initializing...\n"); /* The PCI backend is not intended to be a module (or to work with @@ -420,9 +467,26 @@ static int pcistub_init_device(struct pci_dev *dev) dev_err(&dev->dev, "Could not store PCI conf saved state!\n"); else { dev_dbg(&dev->dev, "resetting (FLR, D3, etc) the device\n"); - __pci_reset_function_locked(dev); + err = pcistub_reset_device_state(dev); + if (err) + goto config_release; pci_restore_state(dev); } + +#ifdef CONFIG_XEN_ACPI + if (xen_initial_domain() && xen_pvh_domain()) { + err = xen_acpi_get_gsi_info(dev, &gsi, &trigger, &polarity); + if (err) { + dev_err(&dev->dev, "Fail to get gsi info!\n"); + goto config_release; + } + err = xen_pvh_setup_gsi(gsi, trigger, polarity); + if (err) + goto config_release; + psdev->gsi = gsi; + } +#endif + /* Now disable the device (this also ensures some private device * data is setup before we export) */ @@ -462,7 +526,7 @@ static int __init pcistub_init_devices_late(void) spin_unlock_irqrestore(&pcistub_devices_lock, flags); - err = pcistub_init_device(psdev->dev); + err = pcistub_init_device(psdev); if (err) { dev_err(&psdev->dev->dev, "error %d initializing device\n", err); @@ -532,7 +596,7 @@ static int pcistub_seize(struct pci_dev *dev, spin_unlock_irqrestore(&pcistub_devices_lock, flags); /* don't want irqs disabled when calling pcistub_init_device */ - err = pcistub_init_device(psdev->dev); + err = pcistub_init_device(psdev); spin_lock_irqsave(&pcistub_devices_lock, flags); @@ -757,7 +821,7 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev, } clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags); - res = (pci_ers_result_t)aer_op->err; + res = (__force pci_ers_result_t)aer_op->err; return res; } diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 6f56640092a9..46f8916597e5 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -700,7 +700,6 @@ const struct file_operations xen_xenbus_fops = { .open = xenbus_file_open, .release = xenbus_file_release, .poll = xenbus_file_poll, - .llseek = no_llseek, }; EXPORT_SYMBOL_GPL(xen_xenbus_fops); diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index e11989a57ca0..47455a85c909 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -501,7 +501,7 @@ found: prt_printf(&buf, "\n %s ", bch2_btree_id_str(o_btree)); bch2_bkey_val_to_text(&buf, c, extent2); - struct nonce nonce = extent_nonce(extent.k->version, p.crc); + struct nonce nonce = extent_nonce(extent.k->bversion, p.crc); struct bch_csum csum = bch2_checksum(c, p.crc.csum_type, nonce, data_buf, bytes); if (fsck_err_on(bch2_crc_cmp(csum, p.crc.csum), trans, dup_backpointer_to_bad_csum_extent, diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index c711d4c27a03..f4151ee51b03 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -594,6 +594,7 @@ struct bch_dev { #define BCH_FS_FLAGS() \ x(new_fs) \ x(started) \ + x(clean_recovery) \ x(btree_running) \ x(accounting_replay_done) \ x(may_go_rw) \ @@ -776,7 +777,7 @@ struct bch_fs { unsigned nsec_per_time_unit; u64 features; u64 compat; - unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)]; + unsigned long errors_silent[BITS_TO_LONGS(BCH_FSCK_ERR_MAX)]; u64 btrees_lost_data; } sb; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 8c4addddd07e..203ee627cab5 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -217,7 +217,7 @@ struct bkey { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ __u8 pad[1]; - struct bversion version; + struct bversion bversion; __u32 size; /* extent size, in sectors */ struct bpos p; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ @@ -328,8 +328,8 @@ enum bch_bkey_fields { bkey_format_field(OFFSET, p.offset), \ bkey_format_field(SNAPSHOT, p.snapshot), \ bkey_format_field(SIZE, size), \ - bkey_format_field(VERSION_HI, version.hi), \ - bkey_format_field(VERSION_LO, version.lo), \ + bkey_format_field(VERSION_HI, bversion.hi), \ + bkey_format_field(VERSION_LO, bversion.lo), \ }, \ }) diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h index e34cb2bf329c..41df24a53d97 100644 --- a/fs/bcachefs/bkey.h +++ b/fs/bcachefs/bkey.h @@ -214,9 +214,9 @@ static __always_inline int bversion_cmp(struct bversion l, struct bversion r) #define ZERO_VERSION ((struct bversion) { .hi = 0, .lo = 0 }) #define MAX_VERSION ((struct bversion) { .hi = ~0, .lo = ~0ULL }) -static __always_inline int bversion_zero(struct bversion v) +static __always_inline bool bversion_zero(struct bversion v) { - return !bversion_cmp(v, ZERO_VERSION); + return bversion_cmp(v, ZERO_VERSION) == 0; } #ifdef CONFIG_BCACHEFS_DEBUG @@ -554,8 +554,8 @@ static inline void bch2_bkey_pack_test(void) {} x(BKEY_FIELD_OFFSET, p.offset) \ x(BKEY_FIELD_SNAPSHOT, p.snapshot) \ x(BKEY_FIELD_SIZE, size) \ - x(BKEY_FIELD_VERSION_HI, version.hi) \ - x(BKEY_FIELD_VERSION_LO, version.lo) + x(BKEY_FIELD_VERSION_HI, bversion.hi) \ + x(BKEY_FIELD_VERSION_LO, bversion.lo) struct bkey_format_state { u64 field_min[BKEY_NR_FIELDS]; diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index 88d8958281e8..e7ac227ba7e8 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -289,7 +289,7 @@ void bch2_bkey_to_text(struct printbuf *out, const struct bkey *k) bch2_bpos_to_text(out, k->p); - prt_printf(out, " len %u ver %llu", k->size, k->version.lo); + prt_printf(out, " len %u ver %llu", k->size, k->bversion.lo); } else { prt_printf(out, "(null)"); } diff --git a/fs/bcachefs/bkey_methods.h b/fs/bcachefs/bkey_methods.h index 3df3dd2723a1..018fb72e32d3 100644 --- a/fs/bcachefs/bkey_methods.h +++ b/fs/bcachefs/bkey_methods.h @@ -70,7 +70,7 @@ bool bch2_bkey_normalize(struct bch_fs *, struct bkey_s); static inline bool bch2_bkey_maybe_mergable(const struct bkey *l, const struct bkey *r) { return l->type == r->type && - !bversion_cmp(l->version, r->version) && + !bversion_cmp(l->bversion, r->bversion) && bpos_eq(l->p, bkey_start_pos(r)); } diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index b5e0692f03c6..660d2fa02da2 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -513,6 +513,8 @@ int bch2_check_topology(struct bch_fs *c) struct bpos pulled_from_scan = POS_MIN; int ret = 0; + bch2_trans_srcu_unlock(trans); + for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) { struct btree_root *r = bch2_btree_id_root(c, i); bool reconstructed_root = false; @@ -599,15 +601,15 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, if (initial) { BUG_ON(bch2_journal_seq_verify && - k.k->version.lo > atomic64_read(&c->journal.seq)); + k.k->bversion.lo > atomic64_read(&c->journal.seq)); if (fsck_err_on(btree_id != BTREE_ID_accounting && - k.k->version.lo > atomic64_read(&c->key_version), + k.k->bversion.lo > atomic64_read(&c->key_version), trans, bkey_version_in_future, "key version number higher than recorded %llu\n %s", atomic64_read(&c->key_version), (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - atomic64_set(&c->key_version, k.k->version.lo); + atomic64_set(&c->key_version, k.k->bversion.lo); } if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, k), diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index cb48a9477514..1c1448b52207 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1195,6 +1195,10 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, set_btree_bset(b, b->set, &b->data->keys); b->nr = bch2_key_sort_fix_overlapping(c, &sorted->keys, iter); + memset((uint8_t *)(sorted + 1) + b->nr.live_u64s * sizeof(u64), 0, + btree_buf_bytes(b) - + sizeof(struct btree_node) - + b->nr.live_u64s * sizeof(u64)); u64s = le16_to_cpu(sorted->keys.u64s); *sorted = *b->data; @@ -1219,7 +1223,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, ret = bch2_bkey_val_validate(c, u.s_c, READ); if (ret == -BCH_ERR_fsck_delete_bkey || (bch2_inject_invalid_keys && - !bversion_cmp(u.k->version, MAX_VERSION))) { + !bversion_cmp(u.k->bversion, MAX_VERSION))) { btree_keys_account_key_drop(&b->nr, 0, k); i->u64s = cpu_to_le16(le16_to_cpu(i->u64s) - k->u64s); diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index b28c649c6838..1e694fedc5da 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -275,7 +275,7 @@ static int read_btree_nodes(struct find_btree_nodes *f) w->ca = ca; t = kthread_run(read_btree_nodes_worker, w, "read_btree_nodes/%s", ca->name); - ret = IS_ERR_OR_NULL(t); + ret = PTR_ERR_OR_ZERO(t); if (ret) { percpu_ref_put(&ca->io_ref); closure_put(&cl); diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index 91884da4e30a..1a74a1a252ee 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -684,10 +684,10 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, !(flags & BCH_TRANS_COMMIT_no_journal_res)) { if (bch2_journal_seq_verify) trans_for_each_update(trans, i) - i->k->k.version.lo = trans->journal_res.seq; + i->k->k.bversion.lo = trans->journal_res.seq; else if (bch2_inject_invalid_keys) trans_for_each_update(trans, i) - i->k->k.version = MAX_VERSION; + i->k->k.bversion = MAX_VERSION; } h = trans->hooks; @@ -700,27 +700,31 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, struct jset_entry *entry = trans->journal_entries; - if (likely(!(flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { - percpu_down_read(&c->mark_lock); + percpu_down_read(&c->mark_lock); + + for (entry = trans->journal_entries; + entry != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); + entry = vstruct_next(entry)) + if (entry->type == BCH_JSET_ENTRY_write_buffer_keys && + entry->start->k.type == KEY_TYPE_accounting) { + BUG_ON(!trans->journal_res.ref); + + struct bkey_i_accounting *a = bkey_i_to_accounting(entry->start); - for (entry = trans->journal_entries; - entry != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); - entry = vstruct_next(entry)) - if (jset_entry_is_key(entry) && entry->start->k.type == KEY_TYPE_accounting) { - struct bkey_i_accounting *a = bkey_i_to_accounting(entry->start); + a->k.bversion = journal_pos_to_bversion(&trans->journal_res, + (u64 *) entry - (u64 *) trans->journal_entries); + BUG_ON(bversion_zero(a->k.bversion)); - a->k.version = journal_pos_to_bversion(&trans->journal_res, - (u64 *) entry - (u64 *) trans->journal_entries); - BUG_ON(bversion_zero(a->k.version)); - ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), false, false); + if (likely(!(flags & BCH_TRANS_COMMIT_skip_accounting_apply))) { + ret = bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal); if (ret) goto revert_fs_usage; } - percpu_up_read(&c->mark_lock); + } + percpu_up_read(&c->mark_lock); - /* XXX: we only want to run this if deltas are nonzero */ - bch2_trans_account_disk_usage_change(trans); - } + /* XXX: we only want to run this if deltas are nonzero */ + bch2_trans_account_disk_usage_change(trans); trans_for_each_update(trans, i) if (btree_node_type_has_atomic_triggers(i->bkey_type)) { @@ -735,6 +739,40 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags, goto fatal_err; } + trans_for_each_update(trans, i) { + enum bch_validate_flags invalid_flags = 0; + + if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) + invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; + + ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), + i->bkey_type, invalid_flags); + if (unlikely(ret)){ + bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", + trans->fn, (void *) i->ip_allocated); + goto fatal_err; + } + btree_insert_entry_checks(trans, i); + } + + for (struct jset_entry *i = trans->journal_entries; + i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); + i = vstruct_next(i)) { + enum bch_validate_flags invalid_flags = 0; + + if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) + invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; + + ret = bch2_journal_entry_validate(c, NULL, i, + bcachefs_metadata_version_current, + CPU_BIG_ENDIAN, invalid_flags); + if (unlikely(ret)) { + bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", + trans->fn); + goto fatal_err; + } + } + if (likely(!(flags & BCH_TRANS_COMMIT_no_journal_res))) { struct journal *j = &c->journal; struct jset_entry *entry; @@ -798,7 +836,7 @@ revert_fs_usage: struct bkey_s_accounting a = bkey_i_to_s_accounting(entry2->start); bch2_accounting_neg(a); - bch2_accounting_mem_mod_locked(trans, a.c, false, false); + bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal); bch2_accounting_neg(a); } percpu_up_read(&c->mark_lock); @@ -1019,40 +1057,6 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) if (ret) goto out_reset; - trans_for_each_update(trans, i) { - enum bch_validate_flags invalid_flags = 0; - - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - - ret = bch2_bkey_validate(c, bkey_i_to_s_c(i->k), - i->bkey_type, invalid_flags); - if (unlikely(ret)){ - bch2_trans_inconsistent(trans, "invalid bkey on insert from %s -> %ps\n", - trans->fn, (void *) i->ip_allocated); - return ret; - } - btree_insert_entry_checks(trans, i); - } - - for (struct jset_entry *i = trans->journal_entries; - i != (void *) ((u64 *) trans->journal_entries + trans->journal_entries_u64s); - i = vstruct_next(i)) { - enum bch_validate_flags invalid_flags = 0; - - if (!(flags & BCH_TRANS_COMMIT_no_journal_res)) - invalid_flags |= BCH_VALIDATE_write|BCH_VALIDATE_commit; - - ret = bch2_journal_entry_validate(c, NULL, i, - bcachefs_metadata_version_current, - CPU_BIG_ENDIAN, invalid_flags); - if (unlikely(ret)) { - bch2_trans_inconsistent(trans, "invalid journal entry on insert from %s\n", - trans->fn); - return ret; - } - } - if (unlikely(!test_bit(BCH_FS_may_go_rw, &c->flags))) { ret = do_bch2_trans_commit_to_journal_replay(trans); goto out_reset; diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h index 60393e98084d..6a454f2fa005 100644 --- a/fs/bcachefs/btree_update.h +++ b/fs/bcachefs/btree_update.h @@ -220,7 +220,8 @@ static inline struct bkey_i *__bch2_bkey_make_mut_noupdate(struct btree_trans *t if (type && k.k->type != type) return ERR_PTR(-ENOENT); - mut = bch2_trans_kmalloc_nomemzero(trans, bytes); + /* extra padding for varint_decode_fast... */ + mut = bch2_trans_kmalloc_nomemzero(trans, bytes + 8); if (!IS_ERR(mut)) { bkey_reassemble(mut, k); diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index ef1f74866e23..cbfd88f98472 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -471,7 +471,6 @@ static ssize_t bch2_data_job_read(struct file *file, char __user *buf, static const struct file_operations bcachefs_data_ops = { .release = bch2_data_job_release, .read = bch2_data_job_read, - .llseek = no_llseek, }; static long bch2_ioctl_data(struct bch_fs *c, diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 757b9884ef55..462b1a2fe1ad 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -639,7 +639,7 @@ int bch2_data_update_init(struct btree_trans *trans, bch2_write_op_init(&m->op, c, io_opts); m->op.pos = bkey_start_pos(k.k); - m->op.version = k.k->version; + m->op.version = k.k->bversion; m->op.target = data_opts.target; m->op.write_point = wp; m->op.nr_replicas = 0; diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index e972e2bca546..9f3133e3e7e5 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -134,6 +134,10 @@ int bch2_accounting_validate(struct bch_fs *c, struct bkey_s_c k, void *end = &acc_k + 1; int ret = 0; + bkey_fsck_err_on(bversion_zero(k.k->bversion), + c, accounting_key_version_0, + "accounting key with version=0"); + switch (acc_k.type) { case BCH_DISK_ACCOUNTING_nr_inodes: end = field_end(acc_k, nr_inodes); @@ -291,7 +295,7 @@ static int __bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accoun struct accounting_mem_entry n = { .pos = a.k->p, - .version = a.k->version, + .bversion = a.k->bversion, .nr_counters = bch2_accounting_counters(a.k), .v[0] = __alloc_percpu_gfp(n.nr_counters * sizeof(u64), sizeof(u64), GFP_KERNEL), @@ -319,11 +323,13 @@ err: return -BCH_ERR_ENOMEM_disk_accounting; } -int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a, bool gc) +int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a, + enum bch_accounting_mode mode) { struct bch_replicas_padded r; - if (accounting_to_replicas(&r.e, a.k->p) && + if (mode != BCH_ACCOUNTING_read && + accounting_to_replicas(&r.e, a.k->p) && !bch2_replicas_marked_locked(c, &r.e)) return -BCH_ERR_btree_insert_need_mark_replicas; @@ -566,7 +572,9 @@ int bch2_gc_accounting_done(struct bch_fs *c) struct { __BKEY_PADDED(k, BCH_ACCOUNTING_MAX_COUNTERS); } k_i; accounting_key_init(&k_i.k, &acc_k, src_v, nr); - bch2_accounting_mem_mod_locked(trans, bkey_i_to_s_c_accounting(&k_i.k), false, false); + bch2_accounting_mem_mod_locked(trans, + bkey_i_to_s_c_accounting(&k_i.k), + BCH_ACCOUNTING_normal); preempt_disable(); struct bch_fs_usage_base *dst = this_cpu_ptr(c->usage); @@ -589,30 +597,14 @@ fsck_err: static int accounting_read_key(struct btree_trans *trans, struct bkey_s_c k) { struct bch_fs *c = trans->c; - struct printbuf buf = PRINTBUF; if (k.k->type != KEY_TYPE_accounting) return 0; percpu_down_read(&c->mark_lock); - int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k), false, true); + int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k), + BCH_ACCOUNTING_read); percpu_up_read(&c->mark_lock); - - if (bch2_accounting_key_is_zero(bkey_s_c_to_accounting(k)) && - ret == -BCH_ERR_btree_insert_need_mark_replicas) - ret = 0; - - struct disk_accounting_pos acc; - bpos_to_disk_accounting_pos(&acc, k.k->p); - - if (fsck_err_on(ret == -BCH_ERR_btree_insert_need_mark_replicas, - trans, accounting_replicas_not_marked, - "accounting not marked in superblock replicas\n %s", - (bch2_accounting_key_to_text(&buf, &acc), - buf.buf))) - ret = bch2_accounting_update_sb_one(c, k.k->p); -fsck_err: - printbuf_exit(&buf); return ret; } @@ -624,6 +616,7 @@ int bch2_accounting_read(struct bch_fs *c) { struct bch_accounting_mem *acc = &c->accounting; struct btree_trans *trans = bch2_trans_get(c); + struct printbuf buf = PRINTBUF; int ret = for_each_btree_key(trans, iter, BTREE_ID_accounting, POS_MIN, @@ -647,7 +640,7 @@ int bch2_accounting_read(struct bch_fs *c) accounting_pos_cmp, &k.k->p); bool applied = idx < acc->k.nr && - bversion_cmp(acc->k.data[idx].version, k.k->version) >= 0; + bversion_cmp(acc->k.data[idx].bversion, k.k->bversion) >= 0; if (applied) continue; @@ -655,7 +648,7 @@ int bch2_accounting_read(struct bch_fs *c) if (i + 1 < &darray_top(*keys) && i[1].k->k.type == KEY_TYPE_accounting && !journal_key_cmp(i, i + 1)) { - BUG_ON(bversion_cmp(i[0].k->k.version, i[1].k->k.version) >= 0); + WARN_ON(bversion_cmp(i[0].k->k.bversion, i[1].k->k.bversion) >= 0); i[1].journal_seq = i[0].journal_seq; @@ -674,6 +667,45 @@ int bch2_accounting_read(struct bch_fs *c) keys->gap = keys->nr = dst - keys->data; percpu_down_read(&c->mark_lock); + for (unsigned i = 0; i < acc->k.nr; i++) { + u64 v[BCH_ACCOUNTING_MAX_COUNTERS]; + bch2_accounting_mem_read_counters(acc, i, v, ARRAY_SIZE(v), false); + + if (bch2_is_zero(v, sizeof(v[0]) * acc->k.data[i].nr_counters)) + continue; + + struct bch_replicas_padded r; + if (!accounting_to_replicas(&r.e, acc->k.data[i].pos)) + continue; + + /* + * If the replicas entry is invalid it'll get cleaned up by + * check_allocations: + */ + if (bch2_replicas_entry_validate(&r.e, c, &buf)) + continue; + + struct disk_accounting_pos k; + bpos_to_disk_accounting_pos(&k, acc->k.data[i].pos); + + if (fsck_err_on(!bch2_replicas_marked_locked(c, &r.e), + trans, accounting_replicas_not_marked, + "accounting not marked in superblock replicas\n %s", + (printbuf_reset(&buf), + bch2_accounting_key_to_text(&buf, &k), + buf.buf))) { + /* + * We're not RW yet and still single threaded, dropping + * and retaking lock is ok: + */ + percpu_up_read(&c->mark_lock); + ret = bch2_mark_replicas(c, &r.e); + if (ret) + goto fsck_err; + percpu_down_read(&c->mark_lock); + } + } + preempt_disable(); struct bch_fs_usage_base *usage = this_cpu_ptr(c->usage); @@ -709,8 +741,10 @@ int bch2_accounting_read(struct bch_fs *c) } } preempt_enable(); +fsck_err: percpu_up_read(&c->mark_lock); err: + printbuf_exit(&buf); bch2_trans_put(trans); bch_err_fn(c, ret); return ret; diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index f29fd0dd9581..4ea6c8a092bc 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -36,8 +36,8 @@ static inline void bch2_accounting_accumulate(struct bkey_i_accounting *dst, for (unsigned i = 0; i < bch2_accounting_counters(&dst->k); i++) dst->v.d[i] += src.v->d[i]; - if (bversion_cmp(dst->k.version, src.k->version) < 0) - dst->k.version = src.k->version; + if (bversion_cmp(dst->k.bversion, src.k->bversion) < 0) + dst->k.bversion = src.k->bversion; } static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage, @@ -103,23 +103,35 @@ static inline int accounting_pos_cmp(const void *_l, const void *_r) return bpos_cmp(*l, *r); } -int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, bool); +enum bch_accounting_mode { + BCH_ACCOUNTING_normal, + BCH_ACCOUNTING_gc, + BCH_ACCOUNTING_read, +}; + +int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode); void bch2_accounting_mem_gc(struct bch_fs *); /* * Update in memory counters so they match the btree update we're doing; called * from transaction commit path */ -static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc, bool read) +static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, + struct bkey_s_c_accounting a, + enum bch_accounting_mode mode) { struct bch_fs *c = trans->c; + struct bch_accounting_mem *acc = &c->accounting; struct disk_accounting_pos acc_k; bpos_to_disk_accounting_pos(&acc_k, a.k->p); + bool gc = mode == BCH_ACCOUNTING_gc; + + EBUG_ON(gc && !acc->gc_running); if (acc_k.type == BCH_DISK_ACCOUNTING_inum) return 0; - if (!gc && !read) { + if (mode == BCH_ACCOUNTING_normal) { switch (acc_k.type) { case BCH_DISK_ACCOUNTING_persistent_reserved: trans->fs_usage_delta.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0]; @@ -140,14 +152,11 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, stru } } - struct bch_accounting_mem *acc = &c->accounting; unsigned idx; - EBUG_ON(gc && !acc->gc_running); - while ((idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), accounting_pos_cmp, &a.k->p)) >= acc->k.nr) { - int ret = bch2_accounting_mem_insert(c, a, gc); + int ret = bch2_accounting_mem_insert(c, a, mode); if (ret) return ret; } @@ -164,7 +173,7 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, stru static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc) { percpu_down_read(&trans->c->mark_lock); - int ret = bch2_accounting_mem_mod_locked(trans, a, gc, false); + int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal); percpu_up_read(&trans->c->mark_lock); return ret; } diff --git a/fs/bcachefs/disk_accounting_types.h b/fs/bcachefs/disk_accounting_types.h index 1687a45177a7..b1982131b206 100644 --- a/fs/bcachefs/disk_accounting_types.h +++ b/fs/bcachefs/disk_accounting_types.h @@ -6,7 +6,7 @@ struct accounting_mem_entry { struct bpos pos; - struct bversion version; + struct bversion bversion; unsigned nr_counters; u64 __percpu *v[2]; }; diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index 95afa7bf2020..3a16b535b6c3 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -239,7 +239,19 @@ int __bch2_fsck_err(struct bch_fs *c, if (!c) c = trans->c; - WARN_ON(!trans && bch2_current_has_btree_trans(c)); + /* + * Ugly: if there's a transaction in the current task it has to be + * passed in to unlock if we prompt for user input. + * + * But, plumbing a transaction and transaction restarts into + * bkey_validate() is problematic. + * + * So: + * - make all bkey errors AUTOFIX, they're simple anyways (we just + * delete the key) + * - and we don't need to warn if we're not prompting + */ + WARN_ON(!(flags & FSCK_AUTOFIX) && !trans && bch2_current_has_btree_trans(c)); if ((flags & FSCK_CAN_FIX) && test_bit(err, c->sb.errors_silent)) diff --git a/fs/bcachefs/error.h b/fs/bcachefs/error.h index 2f1b86978f36..21ee7211b03e 100644 --- a/fs/bcachefs/error.h +++ b/fs/bcachefs/error.h @@ -184,7 +184,7 @@ do { \ ret = -BCH_ERR_fsck_delete_bkey; \ goto fsck_err; \ } \ - int _ret = __bch2_bkey_fsck_err(c, k, FSCK_CAN_FIX, \ + int _ret = __bch2_bkey_fsck_err(c, k, FSCK_CAN_FIX|FSCK_AUTOFIX,\ BCH_FSCK_ERR_##_err_type, \ _err_msg, ##__VA_ARGS__); \ if (_ret != -BCH_ERR_fsck_fix && \ diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 9b3470a97546..0d8b782b63fb 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -21,6 +21,49 @@ #include <linux/bsearch.h> #include <linux/dcache.h> /* struct qstr */ +static bool inode_points_to_dirent(struct bch_inode_unpacked *inode, + struct bkey_s_c_dirent d) +{ + return inode->bi_dir == d.k->p.inode && + inode->bi_dir_offset == d.k->p.offset; +} + +static bool dirent_points_to_inode_nowarn(struct bkey_s_c_dirent d, + struct bch_inode_unpacked *inode) +{ + if (d.v->d_type == DT_SUBVOL + ? le32_to_cpu(d.v->d_child_subvol) == inode->bi_subvol + : le64_to_cpu(d.v->d_inum) == inode->bi_inum) + return 0; + return -BCH_ERR_ENOENT_dirent_doesnt_match_inode; +} + +static void dirent_inode_mismatch_msg(struct printbuf *out, + struct bch_fs *c, + struct bkey_s_c_dirent dirent, + struct bch_inode_unpacked *inode) +{ + prt_str(out, "inode points to dirent that does not point back:"); + prt_newline(out); + bch2_bkey_val_to_text(out, c, dirent.s_c); + prt_newline(out); + bch2_inode_unpacked_to_text(out, inode); +} + +static int dirent_points_to_inode(struct bch_fs *c, + struct bkey_s_c_dirent dirent, + struct bch_inode_unpacked *inode) +{ + int ret = dirent_points_to_inode_nowarn(dirent, inode); + if (ret) { + struct printbuf buf = PRINTBUF; + dirent_inode_mismatch_msg(&buf, c, dirent, inode); + bch_warn(c, "%s", buf.buf); + printbuf_exit(&buf); + } + return ret; +} + /* * XXX: this is handling transaction restarts without returning * -BCH_ERR_transaction_restart_nested, this is not how we do things anymore: @@ -346,14 +389,17 @@ static int reattach_inode(struct btree_trans *trans, static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { - struct btree_iter iter; - struct bkey_s_c_dirent d; - int ret; + if (!inode->bi_dir) + return 0; - d = bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_dirents, - POS(inode->bi_dir, inode->bi_dir_offset), 0, + struct bch_fs *c = trans->c; + struct btree_iter iter; + struct bkey_s_c_dirent d = + bch2_bkey_get_iter_typed(trans, &iter, BTREE_ID_dirents, + SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot), 0, dirent); - ret = bkey_err(d) ?: + int ret = bkey_err(d) ?: + dirent_points_to_inode(c, d, inode) ?: __remove_dirent(trans, d.k->p); bch2_trans_iter_exit(trans, &iter); return ret; @@ -371,7 +417,8 @@ static int reattach_subvol(struct btree_trans *trans, struct bkey_s_c_subvolume return ret; ret = remove_backpointer(trans, &inode); - bch_err_msg(c, ret, "removing dirent"); + if (!bch2_err_matches(ret, ENOENT)) + bch_err_msg(c, ret, "removing dirent"); if (ret) return ret; @@ -626,12 +673,12 @@ static int ref_visible2(struct bch_fs *c, struct inode_walker_entry { struct bch_inode_unpacked inode; u32 snapshot; - bool seen_this_pos; u64 count; }; struct inode_walker { bool first_this_inode; + bool have_inodes; bool recalculate_sums; struct bpos last_pos; @@ -669,6 +716,12 @@ static int get_inodes_all_snapshots(struct btree_trans *trans, struct bkey_s_c k; int ret; + /* + * We no longer have inodes for w->last_pos; clear this to avoid + * screwing up check_i_sectors/check_subdir_count if we take a + * transaction restart here: + */ + w->have_inodes = false; w->recalculate_sums = false; w->inodes.nr = 0; @@ -686,6 +739,7 @@ static int get_inodes_all_snapshots(struct btree_trans *trans, return ret; w->first_this_inode = true; + w->have_inodes = true; return 0; } @@ -740,9 +794,6 @@ static struct inode_walker_entry *walk_inode(struct btree_trans *trans, int ret = get_inodes_all_snapshots(trans, w, k.k->p.inode); if (ret) return ERR_PTR(ret); - } else if (bkey_cmp(w->last_pos, k.k->p)) { - darray_for_each(w->inodes, i) - i->seen_this_pos = false; } w->last_pos = k.k->p; @@ -896,21 +947,6 @@ static struct bkey_s_c_dirent inode_get_dirent(struct btree_trans *trans, return dirent_get_by_pos(trans, iter, SPOS(inode->bi_dir, inode->bi_dir_offset, *snapshot)); } -static bool inode_points_to_dirent(struct bch_inode_unpacked *inode, - struct bkey_s_c_dirent d) -{ - return inode->bi_dir == d.k->p.inode && - inode->bi_dir_offset == d.k->p.offset; -} - -static bool dirent_points_to_inode(struct bkey_s_c_dirent d, - struct bch_inode_unpacked *inode) -{ - return d.v->d_type == DT_SUBVOL - ? le32_to_cpu(d.v->d_child_subvol) == inode->bi_subvol - : le64_to_cpu(d.v->d_inum) == inode->bi_inum; -} - static int check_inode_deleted_list(struct btree_trans *trans, struct bpos p) { struct btree_iter iter; @@ -920,13 +956,14 @@ static int check_inode_deleted_list(struct btree_trans *trans, struct bpos p) return ret; } -static int check_inode_dirent_inode(struct btree_trans *trans, struct bkey_s_c inode_k, +static int check_inode_dirent_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode, - u32 inode_snapshot, bool *write_inode) + bool *write_inode) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + u32 inode_snapshot = inode->bi_snapshot; struct btree_iter dirent_iter = {}; struct bkey_s_c_dirent d = inode_get_dirent(trans, &dirent_iter, inode, &inode_snapshot); int ret = bkey_err(d); @@ -936,13 +973,13 @@ static int check_inode_dirent_inode(struct btree_trans *trans, struct bkey_s_c i if (fsck_err_on(ret, trans, inode_points_to_missing_dirent, "inode points to missing dirent\n%s", - (bch2_bkey_val_to_text(&buf, c, inode_k), buf.buf)) || - fsck_err_on(!ret && !dirent_points_to_inode(d, inode), + (bch2_inode_unpacked_to_text(&buf, inode), buf.buf)) || + fsck_err_on(!ret && dirent_points_to_inode_nowarn(d, inode), trans, inode_points_to_wrong_dirent, - "inode points to dirent that does not point back:\n%s", - (bch2_bkey_val_to_text(&buf, c, inode_k), - prt_newline(&buf), - bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) { + "%s", + (printbuf_reset(&buf), + dirent_inode_mismatch_msg(&buf, c, d, inode), + buf.buf))) { /* * We just clear the backpointer fields for now. If we find a * dirent that points to this inode in check_dirents(), we'll @@ -963,7 +1000,7 @@ fsck_err: return ret; } -static bool bch2_inode_open(struct bch_fs *c, struct bpos p) +static bool bch2_inode_is_open(struct bch_fs *c, struct bpos p) { subvol_inum inum = { .subvol = snapshot_t(c, p.snapshot)->subvol, @@ -972,7 +1009,7 @@ static bool bch2_inode_open(struct bch_fs *c, struct bpos p) /* snapshot tree corruption, can't safely delete */ if (!inum.subvol) { - bch_err_ratelimited(c, "%s(): snapshot %u has no subvol", __func__, p.snapshot); + bch_warn_ratelimited(c, "%s(): snapshot %u has no subvol, unlinked but can't safely delete", __func__, p.snapshot); return true; } @@ -1045,30 +1082,44 @@ static int check_inode(struct btree_trans *trans, } if (u.bi_flags & BCH_INODE_unlinked) { - ret = check_inode_deleted_list(trans, k.k->p); - if (ret < 0) - return ret; + if (!test_bit(BCH_FS_started, &c->flags)) { + /* + * If we're not in online fsck, don't delete unlinked + * inodes, just make sure they're on the deleted list. + * + * They might be referred to by a logged operation - + * i.e. we might have crashed in the middle of a + * truncate on an unlinked but open file - so we want to + * let the delete_dead_inodes kill it after resuming + * logged ops. + */ + ret = check_inode_deleted_list(trans, k.k->p); + if (ret < 0) + return ret; - fsck_err_on(!ret, - trans, unlinked_inode_not_on_deleted_list, - "inode %llu:%u unlinked, but not on deleted list", - u.bi_inum, k.k->p.snapshot); - ret = 0; - } + fsck_err_on(!ret, + trans, unlinked_inode_not_on_deleted_list, + "inode %llu:%u unlinked, but not on deleted list", + u.bi_inum, k.k->p.snapshot); - if (u.bi_flags & BCH_INODE_unlinked && - !bch2_inode_open(c, k.k->p) && - (!c->sb.clean || - fsck_err(trans, inode_unlinked_but_clean, - "filesystem marked clean, but inode %llu unlinked", - u.bi_inum))) { - ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); - bch_err_msg(c, ret, "in fsck deleting inode"); - return ret; + ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_deleted_inodes, k.k->p, 1); + if (ret) + goto err; + } else { + if (fsck_err_on(bch2_inode_is_open(c, k.k->p), + trans, inode_unlinked_and_not_open, + "inode %llu%u unlinked and not open", + u.bi_inum, u.bi_snapshot)) { + ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); + bch_err_msg(c, ret, "in fsck deleting inode"); + return ret; + } + } } + /* i_size_dirty is vestigal, since we now have logged ops for truncate * */ if (u.bi_flags & BCH_INODE_i_size_dirty && - (!c->sb.clean || + (!test_bit(BCH_FS_clean_recovery, &c->flags) || fsck_err(trans, inode_i_size_dirty_but_clean, "filesystem marked clean, but inode %llu has i_size dirty", u.bi_inum))) { @@ -1097,8 +1148,9 @@ static int check_inode(struct btree_trans *trans, do_update = true; } + /* i_sectors_dirty is vestigal, i_sectors is always updated transactionally */ if (u.bi_flags & BCH_INODE_i_sectors_dirty && - (!c->sb.clean || + (!test_bit(BCH_FS_clean_recovery, &c->flags) || fsck_err(trans, inode_i_sectors_dirty_but_clean, "filesystem marked clean, but inode %llu has i_sectors dirty", u.bi_inum))) { @@ -1126,7 +1178,7 @@ static int check_inode(struct btree_trans *trans, } if (u.bi_dir || u.bi_dir_offset) { - ret = check_inode_dirent_inode(trans, k, &u, k.k->p.snapshot, &do_update); + ret = check_inode_dirent_inode(trans, &u, &do_update); if (ret) goto err; } @@ -1555,10 +1607,10 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct inode_walker *inode, struct snapshots_seen *s, - struct extent_ends *extent_ends) + struct extent_ends *extent_ends, + struct disk_reservation *res) { struct bch_fs *c = trans->c; - struct inode_walker_entry *i; struct printbuf buf = PRINTBUF; int ret = 0; @@ -1568,7 +1620,7 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, goto out; } - if (inode->last_pos.inode != k.k->p.inode) { + if (inode->last_pos.inode != k.k->p.inode && inode->have_inodes) { ret = check_i_sectors(trans, inode); if (ret) goto err; @@ -1578,12 +1630,12 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; - i = walk_inode(trans, inode, k); - ret = PTR_ERR_OR_ZERO(i); + struct inode_walker_entry *extent_i = walk_inode(trans, inode, k); + ret = PTR_ERR_OR_ZERO(extent_i); if (ret) goto err; - ret = check_key_has_inode(trans, iter, inode, i, k); + ret = check_key_has_inode(trans, iter, inode, extent_i, k); if (ret) goto err; @@ -1592,24 +1644,19 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, &inode->recalculate_sums); if (ret) goto err; - } - /* - * Check inodes in reverse order, from oldest snapshots to newest, - * starting from the inode that matches this extent's snapshot. If we - * didn't have one, iterate over all inodes: - */ - if (!i) - i = &darray_last(inode->inodes); - - for (; - inode->inodes.data && i >= inode->inodes.data; - --i) { - if (i->snapshot > k.k->p.snapshot || - !key_visible_in_snapshot(c, s, i->snapshot, k.k->p.snapshot)) - continue; + /* + * Check inodes in reverse order, from oldest snapshots to + * newest, starting from the inode that matches this extent's + * snapshot. If we didn't have one, iterate over all inodes: + */ + for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); + inode->inodes.data && i >= inode->inodes.data; + --i) { + if (i->snapshot > k.k->p.snapshot || + !key_visible_in_snapshot(c, s, i->snapshot, k.k->p.snapshot)) + continue; - if (k.k->type != KEY_TYPE_whiteout) { if (fsck_err_on(!(i->inode.bi_flags & BCH_INODE_i_size_dirty) && k.k->p.offset > round_up(i->inode.bi_size, block_bytes(c)) >> 9 && !bkey_extent_is_reservation(k), @@ -1629,13 +1676,25 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, goto err; iter->k.type = KEY_TYPE_whiteout; + break; } - - if (bkey_extent_is_allocation(k.k)) - i->count += k.k->size; } + } - i->seen_this_pos = true; + ret = bch2_trans_commit(trans, res, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + if (bkey_extent_is_allocation(k.k)) { + for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); + inode->inodes.data && i >= inode->inodes.data; + --i) { + if (i->snapshot > k.k->p.snapshot || + !key_visible_in_snapshot(c, s, i->snapshot, k.k->p.snapshot)) + continue; + + i->count += k.k->size; + } } if (k.k->type != KEY_TYPE_whiteout) { @@ -1666,13 +1725,11 @@ int bch2_check_extents(struct bch_fs *c) extent_ends_init(&extent_ends); int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, BTREE_ID_extents, + for_each_btree_key(trans, iter, BTREE_ID_extents, POS(BCACHEFS_ROOT_INO, 0), - BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, - &res, NULL, - BCH_TRANS_COMMIT_no_enospc, ({ + BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, ({ bch2_disk_reservation_put(c, &res); - check_extent(trans, &iter, k, &w, &s, &extent_ends) ?: + check_extent(trans, &iter, k, &w, &s, &extent_ends, &res) ?: check_extent_overbig(trans, &iter, k); })) ?: check_i_sectors_notnested(trans, &w)); @@ -1758,6 +1815,7 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; + struct btree_iter bp_iter = { NULL }; int ret = 0; if (inode_points_to_dirent(target, d)) @@ -1770,7 +1828,7 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, prt_printf(&buf, "\n "), bch2_inode_unpacked_to_text(&buf, target), buf.buf))) - goto out_noiter; + goto err; if (!target->bi_dir && !target->bi_dir_offset) { @@ -1779,7 +1837,6 @@ static int check_dirent_inode_dirent(struct btree_trans *trans, return __bch2_fsck_write_inode(trans, target, target_snapshot); } - struct btree_iter bp_iter = { NULL }; struct bkey_s_c_dirent bp_dirent = dirent_get_by_pos(trans, &bp_iter, SPOS(target->bi_dir, target->bi_dir_offset, target_snapshot)); ret = bkey_err(bp_dirent); @@ -1840,7 +1897,6 @@ out: err: fsck_err: bch2_trans_iter_exit(trans, &bp_iter); -out_noiter: printbuf_exit(&buf); bch_err_fn(c, ret); return ret; @@ -2075,7 +2131,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (k.k->type == KEY_TYPE_whiteout) goto out; - if (dir->last_pos.inode != k.k->p.inode) { + if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) { ret = check_subdir_count(trans, dir); if (ret) goto err; @@ -2137,11 +2193,15 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; } - - if (d.v->d_type == DT_DIR) - for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) - i->count++; } + + ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + if (ret) + goto err; + + if (d.v->d_type == DT_DIR) + for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) + i->count++; out: err: fsck_err: @@ -2164,12 +2224,9 @@ int bch2_check_dirents(struct bch_fs *c) snapshots_seen_init(&s); int ret = bch2_trans_run(c, - for_each_btree_key_commit(trans, iter, BTREE_ID_dirents, + for_each_btree_key(trans, iter, BTREE_ID_dirents, POS(BCACHEFS_ROOT_INO, 0), - BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, - k, - NULL, NULL, - BCH_TRANS_COMMIT_no_enospc, + BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s)) ?: check_subdir_count_notnested(trans, &dir)); @@ -2314,22 +2371,6 @@ static bool darray_u32_has(darray_u32 *d, u32 v) return false; } -/* - * We've checked that inode backpointers point to valid dirents; here, it's - * sufficient to check that the subvolume root has a dirent: - */ -static int subvol_has_dirent(struct btree_trans *trans, struct bkey_s_c_subvolume s) -{ - struct bch_inode_unpacked inode; - int ret = bch2_inode_find_by_inum_trans(trans, - (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, - &inode); - if (ret) - return ret; - - return inode.bi_dir != 0; -} - static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; @@ -2348,14 +2389,24 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); - ret = subvol_has_dirent(trans, s); - if (ret < 0) + struct bch_inode_unpacked subvol_root; + ret = bch2_inode_find_by_inum_trans(trans, + (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, + &subvol_root); + if (ret) break; - if (fsck_err_on(!ret, + /* + * We've checked that inode backpointers point to valid dirents; + * here, it's sufficient to check that the subvolume root has a + * dirent: + */ + if (fsck_err_on(!subvol_root.bi_dir, trans, subvol_unreachable, "unreachable subvolume %s", (bch2_bkey_val_to_text(&buf, c, s.s_c), + prt_newline(&buf), + bch2_inode_unpacked_to_text(&buf, &subvol_root), buf.buf))) { ret = reattach_subvol(trans, s); break; @@ -2450,10 +2501,8 @@ static int check_path(struct btree_trans *trans, pathbuf *p, struct bkey_s_c ino if (ret && !bch2_err_matches(ret, ENOENT)) break; - if (!ret && !dirent_points_to_inode(d, &inode)) { + if (!ret && (ret = dirent_points_to_inode(c, d, &inode))) bch2_trans_iter_exit(trans, &dirent_iter); - ret = -BCH_ERR_ENOENT_dirent_doesnt_match_inode; - } if (bch2_err_matches(ret, ENOENT)) { ret = 0; diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index 6ac0ff7e074b..753c208896c3 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -320,9 +320,11 @@ static noinline int bch2_inode_unpack_slowpath(struct bkey_s_c k, int bch2_inode_unpack(struct bkey_s_c k, struct bch_inode_unpacked *unpacked) { - if (likely(k.k->type == KEY_TYPE_inode_v3)) - return bch2_inode_unpack_v3(k, unpacked); - return bch2_inode_unpack_slowpath(k, unpacked); + unpacked->bi_snapshot = k.k->p.snapshot; + + return likely(k.k->type == KEY_TYPE_inode_v3) + ? bch2_inode_unpack_v3(k, unpacked) + : bch2_inode_unpack_slowpath(k, unpacked); } int bch2_inode_peek_nowarn(struct btree_trans *trans, @@ -557,7 +559,7 @@ static void __bch2_inode_unpacked_to_text(struct printbuf *out, void bch2_inode_unpacked_to_text(struct printbuf *out, struct bch_inode_unpacked *inode) { - prt_printf(out, "inum: %llu ", inode->bi_inum); + prt_printf(out, "inum: %llu:%u ", inode->bi_inum, inode->bi_snapshot); __bch2_inode_unpacked_to_text(out, inode); } @@ -1111,7 +1113,7 @@ static int may_delete_deleted_inode(struct btree_trans *trans, pos.offset, pos.snapshot)) goto delete; - if (c->sb.clean && + if (test_bit(BCH_FS_clean_recovery, &c->flags) && !fsck_err(trans, deleted_inode_but_clean, "filesystem marked as clean but have deleted inode %llu:%u", pos.offset, pos.snapshot)) { diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index f1fcb4c58039..695abd707cb6 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -69,6 +69,7 @@ typedef u64 u96; struct bch_inode_unpacked { u64 bi_inum; + u32 bi_snapshot; u64 bi_journal_seq; __le64 bi_hash_seed; u64 bi_size; diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index b2f50e74bb76..e4fc17c548fd 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -517,7 +517,7 @@ static int __bch2_rbio_narrow_crcs(struct btree_trans *trans, if ((ret = bkey_err(k))) goto out; - if (bversion_cmp(k.k->version, rbio->version) || + if (bversion_cmp(k.k->bversion, rbio->version) || !bch2_bkey_matches_ptr(c, k, rbio->pick.ptr, data_offset)) goto out; @@ -1031,7 +1031,7 @@ get_bio: rbio->read_pos = read_pos; rbio->data_btree = data_btree; rbio->data_pos = data_pos; - rbio->version = k.k->version; + rbio->version = k.k->bversion; rbio->promote = promote; INIT_WORK(&rbio->work, NULL); diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index d3b5be7fd9bf..b5fe9e0dc155 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -697,7 +697,7 @@ static void init_append_extent(struct bch_write_op *op, e = bkey_extent_init(op->insert_keys.top); e->k.p = op->pos; e->k.size = crc.uncompressed_size; - e->k.version = version; + e->k.bversion = version; if (crc.csum_type || crc.compression_type || @@ -1544,7 +1544,7 @@ static void bch2_write_data_inline(struct bch_write_op *op, unsigned data_len) id = bkey_inline_data_init(op->insert_keys.top); id->k.p = op->pos; - id->k.version = op->version; + id->k.bversion = op->version; id->k.size = sectors; iter = bio->bi_iter; diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 30460bce04be..954f6a96e0f4 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -605,7 +605,7 @@ static int journal_entry_data_usage_validate(struct bch_fs *c, goto out; } - if (journal_entry_err_on(bch2_replicas_entry_validate(&u->r, c->disk_sb.sb, &err), + if (journal_entry_err_on(bch2_replicas_entry_validate(&u->r, c, &err), c, version, jset, entry, journal_entry_data_usage_bad_size, "invalid journal entry usage: %s", err.buf)) { diff --git a/fs/bcachefs/logged_ops.c b/fs/bcachefs/logged_ops.c index f49fdca1d07d..6f4a4e1083c9 100644 --- a/fs/bcachefs/logged_ops.c +++ b/fs/bcachefs/logged_ops.c @@ -37,6 +37,14 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter, const struct bch_logged_op_fn *fn = logged_op_fn(k.k->type); struct bkey_buf sk; u32 restart_count = trans->restart_count; + struct printbuf buf = PRINTBUF; + int ret = 0; + + fsck_err_on(test_bit(BCH_FS_clean_recovery, &c->flags), + trans, logged_op_but_clean, + "filesystem marked as clean but have logged op\n%s", + (bch2_bkey_val_to_text(&buf, c, k), + buf.buf)); if (!fn) return 0; @@ -47,8 +55,9 @@ static int resume_logged_op(struct btree_trans *trans, struct btree_iter *iter, fn->resume(trans, sk.k); bch2_bkey_buf_exit(&sk, c); - - return trans_was_restarted(trans, restart_count); +fsck_err: + printbuf_exit(&buf); + return ret ?: trans_was_restarted(trans, restart_count); } int bch2_resume_logged_ops(struct bch_fs *c) diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index be1e7ca4362f..6db72d3bad7d 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -151,7 +151,7 @@ static int bch2_journal_replay_accounting_key(struct btree_trans *trans, struct bkey_s_c old = bch2_btree_path_peek_slot(btree_iter_path(trans, &iter), &u); /* Has this delta already been applied to the btree? */ - if (bversion_cmp(old.k->version, k->k->k.version) >= 0) { + if (bversion_cmp(old.k->bversion, k->k->k.bversion) >= 0) { ret = 0; goto out; } @@ -717,6 +717,8 @@ int bch2_fs_recovery(struct bch_fs *c) if (c->opts.fsck) set_bit(BCH_FS_fsck_running, &c->flags); + if (c->sb.clean) + set_bit(BCH_FS_clean_recovery, &c->flags); ret = bch2_blacklist_table_initialize(c); if (ret) { @@ -862,6 +864,9 @@ use_clean: clear_bit(BCH_FS_fsck_running, &c->flags); + /* in case we don't run journal replay, i.e. norecovery mode */ + set_bit(BCH_FS_accounting_replay_done, &c->flags); + /* fsync if we fixed errors */ if (test_bit(BCH_FS_errors_fixed, &c->flags) && bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) { diff --git a/fs/bcachefs/recovery_passes_types.h b/fs/bcachefs/recovery_passes_types.h index 8c7dee5983d2..50406ce0e4ef 100644 --- a/fs/bcachefs/recovery_passes_types.h +++ b/fs/bcachefs/recovery_passes_types.h @@ -50,7 +50,7 @@ x(check_directory_structure, 30, PASS_ONLINE|PASS_FSCK) \ x(check_nlinks, 31, PASS_FSCK) \ x(resume_logged_ops, 23, PASS_ALWAYS) \ - x(delete_dead_inodes, 32, PASS_FSCK|PASS_UNCLEAN) \ + x(delete_dead_inodes, 32, PASS_ALWAYS) \ x(fix_reflink_p, 33, 0) \ x(set_fs_needs_rebalance, 34, 0) \ diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index e59c0abb4772..f457925fa362 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -367,7 +367,7 @@ static int bch2_make_extent_indirect(struct btree_trans *trans, r_v->k.type = bkey_type_to_indirect(&orig->k); r_v->k.p = reflink_iter.pos; bch2_key_resize(&r_v->k, orig->k.size); - r_v->k.version = orig->k.version; + r_v->k.bversion = orig->k.bversion; set_bkey_val_bytes(&r_v->k, sizeof(__le64) + bkey_val_bytes(&orig->k)); diff --git a/fs/bcachefs/replicas.c b/fs/bcachefs/replicas.c index 998c0bd06802..bcb3276747e0 100644 --- a/fs/bcachefs/replicas.c +++ b/fs/bcachefs/replicas.c @@ -66,9 +66,9 @@ void bch2_replicas_entry_to_text(struct printbuf *out, prt_printf(out, "]"); } -int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *r, - struct bch_sb *sb, - struct printbuf *err) +static int bch2_replicas_entry_validate_locked(struct bch_replicas_entry_v1 *r, + struct bch_sb *sb, + struct printbuf *err) { if (!r->nr_devs) { prt_printf(err, "no devices in entry "); @@ -94,6 +94,16 @@ bad: return -BCH_ERR_invalid_replicas_entry; } +int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *r, + struct bch_fs *c, + struct printbuf *err) +{ + mutex_lock(&c->sb_lock); + int ret = bch2_replicas_entry_validate_locked(r, c->disk_sb.sb, err); + mutex_unlock(&c->sb_lock); + return ret; +} + void bch2_cpu_replicas_to_text(struct printbuf *out, struct bch_replicas_cpu *r) { @@ -676,7 +686,7 @@ static int bch2_cpu_replicas_validate(struct bch_replicas_cpu *cpu_r, struct bch_replicas_entry_v1 *e = cpu_replicas_entry(cpu_r, i); - int ret = bch2_replicas_entry_validate(e, sb, err); + int ret = bch2_replicas_entry_validate_locked(e, sb, err); if (ret) return ret; diff --git a/fs/bcachefs/replicas.h b/fs/bcachefs/replicas.h index 622482559c3d..5aba2c1ce133 100644 --- a/fs/bcachefs/replicas.h +++ b/fs/bcachefs/replicas.h @@ -10,7 +10,7 @@ void bch2_replicas_entry_sort(struct bch_replicas_entry_v1 *); void bch2_replicas_entry_to_text(struct printbuf *, struct bch_replicas_entry_v1 *); int bch2_replicas_entry_validate(struct bch_replicas_entry_v1 *, - struct bch_sb *, struct printbuf *); + struct bch_fs *, struct printbuf *); void bch2_cpu_replicas_to_text(struct printbuf *, struct bch_replicas_cpu *); static inline struct bch_replicas_entry_v1 * diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index 025848a9c4c0..005275281804 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -167,6 +167,7 @@ struct bch_sb_field_clean *bch2_read_superblock_clean(struct bch_fs *c) ret = bch2_sb_clean_validate_late(c, clean, READ); if (ret) { + kfree(clean); mutex_unlock(&c->sb_lock); return ERR_PTR(ret); } diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index c7e4cdd3f6a5..5102059a0f1d 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -312,8 +312,7 @@ static void bch2_sb_downgrade_to_text(struct printbuf *out, struct bch_sb *sb, if (!first) prt_char(out, ','); first = false; - unsigned e = le16_to_cpu(i->errors[j]); - prt_str(out, e < BCH_SB_ERR_MAX ? bch2_sb_error_strs[e] : "(unknown)"); + bch2_sb_error_id_to_text(out, le16_to_cpu(i->errors[j])); } prt_newline(out); } @@ -353,7 +352,9 @@ int bch2_sb_downgrade_update(struct bch_fs *c) for (unsigned i = 0; i < src->nr_errors; i++) dst->errors[i] = cpu_to_le16(src->errors[i]); - downgrade_table_extra(c, &table); + ret = downgrade_table_extra(c, &table); + if (ret) + goto out; if (!dst->recovery_passes[0] && !dst->recovery_passes[1] && @@ -399,7 +400,7 @@ void bch2_sb_set_downgrade(struct bch_fs *c, unsigned new_minor, unsigned old_mi for (unsigned j = 0; j < le16_to_cpu(i->nr_errors); j++) { unsigned e = le16_to_cpu(i->errors[j]); - if (e < BCH_SB_ERR_MAX) + if (e < BCH_FSCK_ERR_MAX) __set_bit(e, c->sb.errors_silent); if (e < sizeof(ext->errors_silent) * 8) __set_bit_le64(e, ext->errors_silent); diff --git a/fs/bcachefs/sb-errors.c b/fs/bcachefs/sb-errors.c index c1270d790e43..013a96883b4e 100644 --- a/fs/bcachefs/sb-errors.c +++ b/fs/bcachefs/sb-errors.c @@ -7,12 +7,12 @@ const char * const bch2_sb_error_strs[] = { #define x(t, n, ...) [n] = #t, BCH_SB_ERRS() - NULL +#undef x }; -static void bch2_sb_error_id_to_text(struct printbuf *out, enum bch_sb_error_id id) +void bch2_sb_error_id_to_text(struct printbuf *out, enum bch_sb_error_id id) { - if (id < BCH_SB_ERR_MAX) + if (id < BCH_FSCK_ERR_MAX) prt_str(out, bch2_sb_error_strs[id]); else prt_printf(out, "(unknown error %u)", id); diff --git a/fs/bcachefs/sb-errors.h b/fs/bcachefs/sb-errors.h index 8889001e7db4..b2357b8e6107 100644 --- a/fs/bcachefs/sb-errors.h +++ b/fs/bcachefs/sb-errors.h @@ -6,6 +6,8 @@ extern const char * const bch2_sb_error_strs[]; +void bch2_sb_error_id_to_text(struct printbuf *, enum bch_sb_error_id); + extern const struct bch_sb_field_ops bch_sb_field_ops_errors; void bch2_sb_error_count(struct bch_fs *, enum bch_sb_error_id); diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index f0c14702f9e6..ed5dca5e1161 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -210,22 +210,23 @@ enum bch_fsck_flags { x(inode_snapshot_mismatch, 196, 0) \ x(inode_unlinked_but_clean, 197, 0) \ x(inode_unlinked_but_nlink_nonzero, 198, 0) \ + x(inode_unlinked_and_not_open, 281, 0) \ x(inode_checksum_type_invalid, 199, 0) \ x(inode_compression_type_invalid, 200, 0) \ x(inode_subvol_root_but_not_dir, 201, 0) \ - x(inode_i_size_dirty_but_clean, 202, 0) \ - x(inode_i_sectors_dirty_but_clean, 203, 0) \ - x(inode_i_sectors_wrong, 204, 0) \ - x(inode_dir_wrong_nlink, 205, 0) \ - x(inode_dir_multiple_links, 206, 0) \ - x(inode_multiple_links_but_nlink_0, 207, 0) \ - x(inode_wrong_backpointer, 208, 0) \ - x(inode_wrong_nlink, 209, 0) \ - x(inode_unreachable, 210, 0) \ - x(deleted_inode_but_clean, 211, 0) \ - x(deleted_inode_missing, 212, 0) \ - x(deleted_inode_is_dir, 213, 0) \ - x(deleted_inode_not_unlinked, 214, 0) \ + x(inode_i_size_dirty_but_clean, 202, FSCK_AUTOFIX) \ + x(inode_i_sectors_dirty_but_clean, 203, FSCK_AUTOFIX) \ + x(inode_i_sectors_wrong, 204, FSCK_AUTOFIX) \ + x(inode_dir_wrong_nlink, 205, FSCK_AUTOFIX) \ + x(inode_dir_multiple_links, 206, FSCK_AUTOFIX) \ + x(inode_multiple_links_but_nlink_0, 207, FSCK_AUTOFIX) \ + x(inode_wrong_backpointer, 208, FSCK_AUTOFIX) \ + x(inode_wrong_nlink, 209, FSCK_AUTOFIX) \ + x(inode_unreachable, 210, FSCK_AUTOFIX) \ + x(deleted_inode_but_clean, 211, FSCK_AUTOFIX) \ + x(deleted_inode_missing, 212, FSCK_AUTOFIX) \ + x(deleted_inode_is_dir, 213, FSCK_AUTOFIX) \ + x(deleted_inode_not_unlinked, 214, FSCK_AUTOFIX) \ x(extent_overlapping, 215, 0) \ x(key_in_missing_inode, 216, 0) \ x(key_in_wrong_inode_type, 217, 0) \ @@ -255,7 +256,7 @@ enum bch_fsck_flags { x(dir_loop, 241, 0) \ x(hash_table_key_duplicate, 242, 0) \ x(hash_table_key_wrong_offset, 243, 0) \ - x(unlinked_inode_not_on_deleted_list, 244, 0) \ + x(unlinked_inode_not_on_deleted_list, 244, FSCK_AUTOFIX) \ x(reflink_p_front_pad_bad, 245, 0) \ x(journal_entry_dup_same_device, 246, 0) \ x(inode_bi_subvol_missing, 247, 0) \ @@ -270,7 +271,7 @@ enum bch_fsck_flags { x(subvol_children_not_set, 256, 0) \ x(subvol_children_bad, 257, 0) \ x(subvol_loop, 258, 0) \ - x(subvol_unreachable, 259, 0) \ + x(subvol_unreachable, 259, FSCK_AUTOFIX) \ x(btree_node_bkey_bad_u64s, 260, 0) \ x(btree_node_topology_empty_interior_node, 261, 0) \ x(btree_ptr_v2_min_key_bad, 262, 0) \ @@ -282,8 +283,8 @@ enum bch_fsck_flags { x(btree_ptr_v2_written_0, 268, 0) \ x(subvol_snapshot_bad, 269, 0) \ x(subvol_inode_bad, 270, 0) \ - x(alloc_key_stripe_sectors_wrong, 271, 0) \ - x(accounting_mismatch, 272, 0) \ + x(alloc_key_stripe_sectors_wrong, 271, FSCK_AUTOFIX) \ + x(accounting_mismatch, 272, FSCK_AUTOFIX) \ x(accounting_replicas_not_marked, 273, 0) \ x(invalid_btree_id, 274, 0) \ x(alloc_key_io_time_bad, 275, 0) \ @@ -292,12 +293,14 @@ enum bch_fsck_flags { x(accounting_key_replicas_nr_devs_0, 278, FSCK_AUTOFIX) \ x(accounting_key_replicas_nr_required_bad, 279, FSCK_AUTOFIX) \ x(accounting_key_replicas_devs_unsorted, 280, FSCK_AUTOFIX) \ + x(accounting_key_version_0, 282, FSCK_AUTOFIX) \ + x(logged_op_but_clean, 283, FSCK_AUTOFIX) \ + x(MAX, 284, 0) enum bch_sb_error_id { #define x(t, n, ...) BCH_FSCK_ERR_##t = n, BCH_SB_ERRS() #undef x - BCH_SB_ERR_MAX }; struct bch_sb_field_errors { diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index 9cbd3c14c94f..617d07e53b20 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -169,11 +169,17 @@ static int __do_six_trylock(struct six_lock *lock, enum six_lock_type type, ret = -1 - SIX_LOCK_write; } } else if (type == SIX_LOCK_write && lock->readers) { - if (try) { + if (try) atomic_add(SIX_LOCK_HELD_write, &lock->state); - smp_mb__after_atomic(); - } + /* + * Make sure atomic_add happens before pcpu_read_count and + * six_set_bitmask in slow path happens before pcpu_read_count. + * + * Paired with the smp_mb() in read lock fast path (per-cpu mode) + * and the one before atomic_read in read unlock path. + */ + smp_mb(); ret = !pcpu_read_count(lock); if (try && !ret) { diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 8b18a9b483a4..1809442b00ee 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -469,6 +469,7 @@ static u32 bch2_snapshot_tree_oldest_subvol(struct bch_fs *c, u32 snapshot_root) u32 id = snapshot_root; u32 subvol = 0, s; + rcu_read_lock(); while (id) { s = snapshot_t(c, id)->subvol; @@ -477,6 +478,7 @@ static u32 bch2_snapshot_tree_oldest_subvol(struct bch_fs *c, u32 snapshot_root) id = bch2_snapshot_tree_next(c, id); } + rcu_read_unlock(); return subvol; } @@ -1782,6 +1784,7 @@ static int bch2_propagate_key_to_snapshot_leaf(struct btree_trans *trans, new->k.p.snapshot = leaf_id; ret = bch2_trans_update(trans, &iter, new, 0); out: + bch2_set_btree_iter_dontneed(&iter); bch2_trans_iter_exit(trans, &iter); return ret; } diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index dbe834cb349f..6845dde1b339 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -92,34 +92,32 @@ static int check_subvol(struct btree_trans *trans, } struct bch_inode_unpacked inode; - struct btree_iter inode_iter = {}; - ret = bch2_inode_peek_nowarn(trans, &inode_iter, &inode, + ret = bch2_inode_find_by_inum_nowarn_trans(trans, (subvol_inum) { k.k->p.offset, le64_to_cpu(subvol.v->inode) }, - 0); - bch2_trans_iter_exit(trans, &inode_iter); - - if (ret && !bch2_err_matches(ret, ENOENT)) - return ret; - - if (fsck_err_on(ret, - trans, subvol_to_missing_root, - "subvolume %llu points to missing subvolume root %llu:%u", - k.k->p.offset, le64_to_cpu(subvol.v->inode), - le32_to_cpu(subvol.v->snapshot))) { - ret = bch2_subvolume_delete(trans, iter->pos.offset); - bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset); - return ret ?: -BCH_ERR_transaction_restart_nested; - } - - if (fsck_err_on(inode.bi_subvol != subvol.k->p.offset, - trans, subvol_root_wrong_bi_subvol, - "subvol root %llu:%u has wrong bi_subvol field: got %u, should be %llu", - inode.bi_inum, inode_iter.k.p.snapshot, - inode.bi_subvol, subvol.k->p.offset)) { - inode.bi_subvol = subvol.k->p.offset; - ret = __bch2_fsck_write_inode(trans, &inode, le32_to_cpu(subvol.v->snapshot)); - if (ret) + &inode); + if (!ret) { + if (fsck_err_on(inode.bi_subvol != subvol.k->p.offset, + trans, subvol_root_wrong_bi_subvol, + "subvol root %llu:%u has wrong bi_subvol field: got %u, should be %llu", + inode.bi_inum, inode.bi_snapshot, + inode.bi_subvol, subvol.k->p.offset)) { + inode.bi_subvol = subvol.k->p.offset; + ret = __bch2_fsck_write_inode(trans, &inode, le32_to_cpu(subvol.v->snapshot)); + if (ret) + goto err; + } + } else if (bch2_err_matches(ret, ENOENT)) { + if (fsck_err(trans, subvol_to_missing_root, + "subvolume %llu points to missing subvolume root %llu:%u", + k.k->p.offset, le64_to_cpu(subvol.v->inode), + le32_to_cpu(subvol.v->snapshot))) { + ret = bch2_subvolume_delete(trans, iter->pos.offset); + bch_err_msg(c, ret, "deleting subvolume %llu", iter->pos.offset); + ret = ret ?: -BCH_ERR_transaction_restart_nested; goto err; + } + } else { + goto err; } if (!BCH_SUBVOLUME_SNAP(subvol.v)) { @@ -137,7 +135,7 @@ static int check_subvol(struct btree_trans *trans, "%s: snapshot tree %u not found", __func__, snapshot_tree); if (ret) - return ret; + goto err; if (fsck_err_on(le32_to_cpu(st.master_subvol) != subvol.k->p.offset, trans, subvol_not_master_and_not_snapshot, @@ -147,7 +145,7 @@ static int check_subvol(struct btree_trans *trans, bch2_bkey_make_mut_typed(trans, iter, &subvol.s_c, 0, subvolume); ret = PTR_ERR_OR_ZERO(s); if (ret) - return ret; + goto err; SET_BCH_SUBVOLUME_SNAP(&s->v, true); } diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index d86d5dae54c9..ce7410d72089 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -799,8 +799,10 @@ retry: i < layout.sb_offset + layout.nr_superblocks; i++) { offset = le64_to_cpu(*i); - if (offset == opt_get(*opts, sb)) + if (offset == opt_get(*opts, sb)) { + ret = -BCH_ERR_invalid; continue; + } ret = read_one_super(sb, offset, &err); if (!ret) @@ -1188,7 +1190,8 @@ static void bch2_sb_ext_to_text(struct printbuf *out, struct bch_sb *sb, le_bitvector_to_cpu(errors_silent, (void *) e->errors_silent, sizeof(e->errors_silent) * 8); prt_printf(out, "Errors to silently fix:\t"); - prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, sizeof(e->errors_silent) * 8); + prt_bitflags_vector(out, bch2_sb_error_strs, errors_silent, + min(BCH_FSCK_ERR_MAX, sizeof(e->errors_silent) * 8)); prt_newline(out); kfree(errors_silent); diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c index 01b768c9b767..b2f209743afe 100644 --- a/fs/bcachefs/tests.c +++ b/fs/bcachefs/tests.c @@ -394,7 +394,7 @@ static int insert_test_extent(struct bch_fs *c, k.k_i.k.p.offset = end; k.k_i.k.p.snapshot = U32_MAX; k.k_i.k.size = end - start; - k.k_i.k.version.lo = test_version++; + k.k_i.k.bversion.lo = test_version++; ret = bch2_btree_insert(c, BTREE_ID_extents, &k.k_i, NULL, 0, 0); bch_err_fn(c, ret); diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c index fb3442a7c67f..dea73bc1cb51 100644 --- a/fs/bcachefs/thread_with_file.c +++ b/fs/bcachefs/thread_with_file.c @@ -275,7 +275,6 @@ static long thread_with_stdio_ioctl(struct file *file, unsigned int cmd, unsigne } static const struct file_operations thread_with_stdio_fops = { - .llseek = no_llseek, .read = thread_with_stdio_read, .write = thread_with_stdio_write, .poll = thread_with_stdio_poll, @@ -285,7 +284,6 @@ static const struct file_operations thread_with_stdio_fops = { }; static const struct file_operations thread_with_stdout_fops = { - .llseek = no_llseek, .read = thread_with_stdio_read, .poll = thread_with_stdout_poll, .flush = thread_with_stdio_flush, diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 5d9ccda098cc..53fef258c2bc 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -96,7 +96,6 @@ static bool ceph_dirty_folio(struct address_space *mapping, struct folio *folio) /* dirty the head */ spin_lock(&ci->i_ceph_lock); - BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference if (__ceph_have_pending_cap_snap(ci)) { struct ceph_cap_snap *capsnap = list_last_entry(&ci->i_cap_snaps, diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 808c9c048276..bed34fc11c91 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -10,6 +10,7 @@ #include <linux/writeback.h> #include <linux/iversion.h> #include <linux/filelock.h> +#include <linux/jiffies.h> #include "super.h" #include "mds_client.h" @@ -4149,7 +4150,7 @@ retry: ceph_remove_cap(mdsc, cap, false); goto out_unlock; } else if (tsession) { - /* add placeholder for the export tagert */ + /* add placeholder for the export target */ int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0; tcap = new_cap; ceph_add_cap(inode, tsession, t_cap_id, issued, 0, @@ -4602,7 +4603,7 @@ flush_cap_releases: __ceph_queue_cap_release(session, cap); spin_unlock(&session->s_cap_lock); } - ceph_flush_cap_releases(mdsc, session); + ceph_flush_session_cap_releases(mdsc, session); goto done; bad: @@ -4659,7 +4660,7 @@ unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc) * slowness doesn't block mdsc delayed work, * preventing send_renew_caps() from running. */ - if (jiffies - loop_start >= 5 * HZ) + if (time_after_eq(jiffies, loop_start + 5 * HZ)) break; } spin_unlock(&mdsc->cap_delay_lock); @@ -4701,6 +4702,28 @@ void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc) ceph_mdsc_iterate_sessions(mdsc, flush_dirty_session_caps, true); } +/* + * Flush all cap releases to the mds + */ +static void flush_cap_releases(struct ceph_mds_session *s) +{ + struct ceph_mds_client *mdsc = s->s_mdsc; + struct ceph_client *cl = mdsc->fsc->client; + + doutc(cl, "begin\n"); + spin_lock(&s->s_cap_lock); + if (s->s_num_cap_releases) + ceph_flush_session_cap_releases(mdsc, s); + spin_unlock(&s->s_cap_lock); + doutc(cl, "done\n"); + +} + +void ceph_flush_cap_releases(struct ceph_mds_client *mdsc) +{ + ceph_mdsc_iterate_sessions(mdsc, flush_cap_releases, true); +} + void __ceph_touch_fmode(struct ceph_inode_info *ci, struct ceph_mds_client *mdsc, int fmode) { diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index ddec8c9244ee..952109292d69 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -2058,7 +2058,7 @@ static int ceph_d_delete(const struct dentry *dentry) return 0; if (ceph_snap(d_inode(dentry)) != CEPH_NOSNAP) return 0; - /* vaild lease? */ + /* valid lease? */ di = ceph_dentry(dentry); if (di) { if (__dentry_lease_is_valid(di)) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 4a8eec46254b..315ef02f9a3f 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1779,7 +1779,7 @@ retry_lookup: if (err < 0) goto done; } else if (rinfo->head->is_dentry && req->r_dentry) { - /* parent inode is not locked, be carefull */ + /* parent inode is not locked, be careful */ struct ceph_vino *ptvino = NULL; dvino.ino = le64_to_cpu(rinfo->diri.in->ino); dvino.snap = le64_to_cpu(rinfo->diri.in->snapid); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 276e34ab3e2c..c4a5fd94bbbb 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2266,7 +2266,7 @@ int ceph_trim_caps(struct ceph_mds_client *mdsc, trim_caps - remaining); } - ceph_flush_cap_releases(mdsc, session); + ceph_flush_session_cap_releases(mdsc, session); return 0; } @@ -2420,7 +2420,7 @@ static void ceph_cap_release_work(struct work_struct *work) ceph_put_mds_session(session); } -void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, +void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc, struct ceph_mds_session *session) { struct ceph_client *cl = mdsc->fsc->client; @@ -2447,7 +2447,7 @@ void __ceph_queue_cap_release(struct ceph_mds_session *session, session->s_num_cap_releases++; if (!(session->s_num_cap_releases % CEPH_CAPS_PER_RELEASE)) - ceph_flush_cap_releases(session->s_mdsc, session); + ceph_flush_session_cap_releases(session->s_mdsc, session); } static void ceph_cap_reclaim_work(struct work_struct *work) @@ -4340,7 +4340,7 @@ skip_cap_auths: /* flush cap releases */ spin_lock(&session->s_cap_lock); if (session->s_num_cap_releases) - ceph_flush_cap_releases(mdsc, session); + ceph_flush_session_cap_releases(mdsc, session); spin_unlock(&session->s_cap_lock); send_flushmsg_ack(mdsc, session, seq); @@ -4910,7 +4910,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, } else { recon_state.msg_version = 2; } - /* trsaverse this session's caps */ + /* traverse this session's caps */ err = ceph_iterate_session_caps(session, reconnect_caps_cb, &recon_state); spin_lock(&session->s_cap_lock); @@ -5446,7 +5446,7 @@ static void delayed_work(struct work_struct *work) } mutex_unlock(&mdsc->mutex); - ceph_flush_cap_releases(mdsc, s); + ceph_flush_session_cap_releases(mdsc, s); mutex_lock(&s->s_mutex); if (renew_caps) @@ -5877,6 +5877,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc) mutex_unlock(&mdsc->mutex); ceph_flush_dirty_caps(mdsc); + ceph_flush_cap_releases(mdsc); spin_lock(&mdsc->cap_dirty_lock); want_flush = mdsc->last_cap_flush_tid; if (!list_empty(&mdsc->cap_flush_list)) { @@ -6015,6 +6016,18 @@ static void ceph_mdsc_stop(struct ceph_mds_client *mdsc) ceph_mdsmap_destroy(mdsc->mdsmap); kfree(mdsc->sessions); ceph_caps_finalize(mdsc); + + if (mdsc->s_cap_auths) { + int i; + + for (i = 0; i < mdsc->s_cap_auths_num; i++) { + kfree(mdsc->s_cap_auths[i].match.gids); + kfree(mdsc->s_cap_auths[i].match.path); + kfree(mdsc->s_cap_auths[i].match.fs_name); + } + kfree(mdsc->s_cap_auths); + } + ceph_pool_perm_destroy(mdsc); } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 9bcc7f181bfe..3dd54587944a 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -559,9 +559,6 @@ extern struct ceph_mds_session * ceph_get_mds_session(struct ceph_mds_session *s); extern void ceph_put_mds_session(struct ceph_mds_session *s); -extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc, - struct ceph_msg *msg, int mds); - extern int ceph_mdsc_init(struct ceph_fs_client *fsc); extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc); extern void ceph_mdsc_force_umount(struct ceph_mds_client *mdsc); @@ -602,8 +599,8 @@ extern void ceph_mdsc_iterate_sessions(struct ceph_mds_client *mdsc, extern struct ceph_msg *ceph_create_session_msg(u32 op, u64 seq); extern void __ceph_queue_cap_release(struct ceph_mds_session *session, struct ceph_cap *cap); -extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session); +extern void ceph_flush_session_cap_releases(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session); extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc); extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr); extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 0cdf84cd1791..73f321b52895 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -126,6 +126,7 @@ static int ceph_sync_fs(struct super_block *sb, int wait) if (!wait) { doutc(cl, "(non-blocking)\n"); ceph_flush_dirty_caps(fsc->mdsc); + ceph_flush_cap_releases(fsc->mdsc); doutc(cl, "(non-blocking) done\n"); return 0; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6e817bf1337c..2508aa8950b7 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1056,8 +1056,6 @@ extern int ceph_fill_trace(struct super_block *sb, extern int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct ceph_mds_session *session); -extern int ceph_inode_holds_cap(struct inode *inode, int mask); - extern bool ceph_inode_set_size(struct inode *inode, loff_t size); extern void __ceph_do_pending_vmtruncate(struct inode *inode); @@ -1208,10 +1206,6 @@ static inline void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx) { } -static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode) -{ - return 0; -} static inline void ceph_forget_all_cached_acls(struct inode *inode) { @@ -1270,6 +1264,7 @@ extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags); extern unsigned long ceph_check_delayed_caps(struct ceph_mds_client *mdsc); extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc); +extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc); extern int ceph_drop_caps_for_unlink(struct inode *inode); extern int ceph_encode_inode_release(void **p, struct inode *inode, int mds, int drop, int unless, int force); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index c6f4a9a98b85..67299e8b734e 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -1218,7 +1218,6 @@ static const struct file_operations u32_array_fops = { .open = u32_array_open, .release = u32_array_release, .read = u32_array_read, - .llseek = no_llseek, }; /** diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 7112958c2e5b..700a0cbb2f14 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -733,7 +733,6 @@ out: static const struct file_operations dlm_rawmsg_fops = { .open = simple_open, .write = dlm_rawmsg_write, - .llseek = no_llseek, }; void *dlm_create_debug_comms_file(int nodeid, void *data) diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 7e9961639802..23c51d62f902 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -110,5 +110,4 @@ const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, - .llseek = no_llseek, }; diff --git a/fs/fsopen.c b/fs/fsopen.c index ee92ca58429e..6cef3deccded 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -78,7 +78,6 @@ static int fscontext_release(struct inode *inode, struct file *file) const struct file_operations fscontext_fops = { .read = fscontext_read, .release = fscontext_release, - .llseek = no_llseek, }; /* diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 97ac994ff78f..2a730d88cc3b 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -183,27 +183,23 @@ out: static const struct file_operations fuse_ctl_abort_ops = { .open = nonseekable_open, .write = fuse_conn_abort_write, - .llseek = no_llseek, }; static const struct file_operations fuse_ctl_waiting_ops = { .open = nonseekable_open, .read = fuse_conn_waiting_read, - .llseek = no_llseek, }; static const struct file_operations fuse_conn_max_background_ops = { .open = nonseekable_open, .read = fuse_conn_max_background_read, .write = fuse_conn_max_background_write, - .llseek = no_llseek, }; static const struct file_operations fuse_conn_congestion_threshold_ops = { .open = nonseekable_open, .read = fuse_conn_congestion_threshold_read, .write = fuse_conn_congestion_threshold_write, - .llseek = no_llseek, }; static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 46ed30a4e0fc..1f64ae6d7a69 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2456,7 +2456,6 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd, const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, .open = fuse_dev_open, - .llseek = no_llseek, .read_iter = fuse_dev_read, .splice_read = fuse_dev_splice_read, .write_iter = fuse_dev_write, diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index c9f0ed24cb7b..c562aec3b483 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -58,6 +58,7 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {} /* * misc.c */ +struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq); int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, bool needs_put); struct folio_queue *netfs_delete_buffer_head(struct netfs_io_request *wreq); diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 0ad0982ce0e2..63280791de3b 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -9,34 +9,66 @@ #include "internal.h" /* - * Append a folio to the rolling queue. + * Make sure there's space in the rolling queue. */ -int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, - bool needs_put) +struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq) { - struct folio_queue *tail = rreq->buffer_tail; - unsigned int slot, order = folio_order(folio); + struct folio_queue *tail = rreq->buffer_tail, *prev; + unsigned int prev_nr_slots = 0; if (WARN_ON_ONCE(!rreq->buffer && tail) || WARN_ON_ONCE(rreq->buffer && !tail)) - return -EIO; - - if (!tail || folioq_full(tail)) { - tail = kmalloc(sizeof(*tail), GFP_NOFS); - if (!tail) - return -ENOMEM; - netfs_stat(&netfs_n_folioq); - folioq_init(tail); - tail->prev = rreq->buffer_tail; - if (tail->prev) - tail->prev->next = tail; - rreq->buffer_tail = tail; - if (!rreq->buffer) { - rreq->buffer = tail; - iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); + return ERR_PTR(-EIO); + + prev = tail; + if (prev) { + if (!folioq_full(tail)) + return tail; + prev_nr_slots = folioq_nr_slots(tail); + } + + tail = kmalloc(sizeof(*tail), GFP_NOFS); + if (!tail) + return ERR_PTR(-ENOMEM); + netfs_stat(&netfs_n_folioq); + folioq_init(tail); + tail->prev = prev; + if (prev) + /* [!] NOTE: After we set prev->next, the consumer is entirely + * at liberty to delete prev. + */ + WRITE_ONCE(prev->next, tail); + + rreq->buffer_tail = tail; + if (!rreq->buffer) { + rreq->buffer = tail; + iov_iter_folio_queue(&rreq->io_iter, ITER_SOURCE, tail, 0, 0, 0); + } else { + /* Make sure we don't leave the master iterator pointing to a + * block that might get immediately consumed. + */ + if (rreq->io_iter.folioq == prev && + rreq->io_iter.folioq_slot == prev_nr_slots) { + rreq->io_iter.folioq = tail; + rreq->io_iter.folioq_slot = 0; } - rreq->buffer_tail_slot = 0; } + rreq->buffer_tail_slot = 0; + return tail; +} + +/* + * Append a folio to the rolling queue. + */ +int netfs_buffer_append_folio(struct netfs_io_request *rreq, struct folio *folio, + bool needs_put) +{ + struct folio_queue *tail; + unsigned int slot, order = folio_order(folio); + + tail = netfs_buffer_make_space(rreq); + if (IS_ERR(tail)) + return PTR_ERR(tail); rreq->io_iter.count += PAGE_SIZE << order; diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 04e66d587f77..0929d9fd4ce7 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -153,12 +153,22 @@ static void netfs_prepare_write(struct netfs_io_request *wreq, loff_t start) { struct netfs_io_subrequest *subreq; + struct iov_iter *wreq_iter = &wreq->io_iter; + + /* Make sure we don't point the iterator at a used-up folio_queue + * struct being used as a placeholder to prevent the queue from + * collapsing. In such a case, extend the queue. + */ + if (iov_iter_is_folioq(wreq_iter) && + wreq_iter->folioq_slot >= folioq_nr_slots(wreq_iter->folioq)) { + netfs_buffer_make_space(wreq); + } subreq = netfs_alloc_subrequest(wreq); subreq->source = stream->source; subreq->start = start; subreq->stream_nr = stream->stream_nr; - subreq->io_iter = wreq->io_iter; + subreq->io_iter = *wreq_iter; _enter("R=%x[%x]", wreq->debug_id, subreq->debug_index); diff --git a/fs/nsfs.c b/fs/nsfs.c index 67ee176b8824..c675fc40ce2d 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -22,7 +22,6 @@ static struct vfsmount *nsfs_mnt; static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); static const struct file_operations ns_file_operations = { - .llseek = no_llseek, .unlocked_ioctl = ns_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1fea43c33b6b..db72b3e924b3 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -156,9 +156,8 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock, err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count, &ext_flags); if (err) { - mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, " - "%llu, NULL)\n", err, inode, (unsigned long long)iblock, - (unsigned long long)p_blkno); + mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, " + "block: %llu\n", inode, (unsigned long long)iblock); goto bail; } diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 70a768b623cf..f7672472fa82 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -973,7 +973,13 @@ int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr, } while (done < nr) { - down_read(&OCFS2_I(inode)->ip_alloc_sem); + if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { + rc = -EAGAIN; + mlog(ML_ERROR, + "Inode #%llu ip_alloc_sem is temporarily unavailable\n", + (unsigned long long)OCFS2_I(inode)->ip_blkno); + break; + } rc = ocfs2_extent_map_get_blocks(inode, v_block + done, &p_block, &p_count, NULL); up_read(&OCFS2_I(inode)->ip_alloc_sem); diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 4f85508538fc..004393b13c0a 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -25,6 +25,7 @@ #include "namei.h" #include "ocfs2_trace.h" #include "file.h" +#include "symlink.h" #include <linux/bio.h> #include <linux/blkdev.h> @@ -4148,8 +4149,9 @@ static int __ocfs2_reflink(struct dentry *old_dentry, int ret; struct inode *inode = d_inode(old_dentry); struct buffer_head *new_bh = NULL; + struct ocfs2_inode_info *oi = OCFS2_I(inode); - if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) { + if (oi->ip_flags & OCFS2_INODE_SYSTEM_FILE) { ret = -EINVAL; mlog_errno(ret); goto out; @@ -4175,6 +4177,26 @@ static int __ocfs2_reflink(struct dentry *old_dentry, goto out_unlock; } + if ((oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) && + (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) { + /* + * Adjust extent record count to reserve space for extended attribute. + * Inline data count had been adjusted in ocfs2_duplicate_inline_data(). + */ + struct ocfs2_inode_info *new_oi = OCFS2_I(new_inode); + + if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) && + !(ocfs2_inode_is_fast_symlink(new_inode))) { + struct ocfs2_dinode *new_di = (struct ocfs2_dinode *)new_bh->b_data; + struct ocfs2_dinode *old_di = (struct ocfs2_dinode *)old_bh->b_data; + struct ocfs2_extent_list *el = &new_di->id2.i_list; + int inline_size = le16_to_cpu(old_di->i_xattr_inline_size); + + le16_add_cpu(&el->l_count, -(inline_size / + sizeof(struct ocfs2_extent_rec))); + } + } + ret = ocfs2_create_reflink_node(inode, old_bh, new_inode, new_bh, preserve); if (ret) { @@ -4182,7 +4204,7 @@ static int __ocfs2_reflink(struct dentry *old_dentry, goto inode_unlock; } - if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_XATTR_FL) { + if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) { ret = ocfs2_reflink_xattrs(inode, old_bh, new_inode, new_bh, preserve); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 0e58a5ce539e..dd0a05365e79 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -6511,16 +6511,7 @@ static int ocfs2_reflink_xattr_inline(struct ocfs2_xattr_reflink *args) } new_oi = OCFS2_I(args->new_inode); - /* - * Adjust extent record count to reserve space for extended attribute. - * Inline data count had been adjusted in ocfs2_duplicate_inline_data(). - */ - if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) && - !(ocfs2_inode_is_fast_symlink(args->new_inode))) { - struct ocfs2_extent_list *el = &new_di->id2.i_list; - le16_add_cpu(&el->l_count, -(inline_size / - sizeof(struct ocfs2_extent_rec))); - } + spin_lock(&new_oi->ip_lock); new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL; new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 2b7a5a3a7a2f..4504493b20be 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -117,7 +117,7 @@ static int ovl_real_fdget_meta(const struct file *file, struct fd *real, struct file *f = ovl_open_realfile(file, &realpath); if (IS_ERR(f)) return PTR_ERR(f); - real->word = (unsigned long)ovl_open_realfile(file, &realpath) | FDPUT_FPUT; + real->word = (unsigned long)f | FDPUT_FPUT; return 0; } diff --git a/fs/pipe.c b/fs/pipe.c index 4083ba492cb6..12b22c2723b7 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1231,7 +1231,6 @@ err: const struct file_operations pipefifo_fops = { .open = fifo_open, - .llseek = no_llseek, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 7481b21a0489..2d851f596a72 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -416,7 +416,7 @@ find_timestamp(struct cifs_ses *ses) } static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, - const struct nls_table *nls_cp) + const struct nls_table *nls_cp, struct shash_desc *hmacmd5) { int rc = 0; int len; @@ -425,34 +425,26 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, wchar_t *domain; wchar_t *server; - if (!ses->server->secmech.hmacmd5) { - cifs_dbg(VFS, "%s: can't generate ntlmv2 hash\n", __func__); - return -1; - } - /* calculate md4 hash of password */ E_md4hash(ses->password, nt_hash, nls_cp); - rc = crypto_shash_setkey(ses->server->secmech.hmacmd5->tfm, nt_hash, - CIFS_NTHASH_SIZE); + rc = crypto_shash_setkey(hmacmd5->tfm, nt_hash, CIFS_NTHASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not set NT Hash as a key\n", __func__); + cifs_dbg(VFS, "%s: Could not set NT hash as a key, rc=%d\n", __func__, rc); return rc; } - rc = crypto_shash_init(ses->server->secmech.hmacmd5); + rc = crypto_shash_init(hmacmd5); if (rc) { - cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init HMAC-MD5, rc=%d\n", __func__, rc); return rc; } /* convert ses->user_name to unicode */ len = ses->user_name ? strlen(ses->user_name) : 0; user = kmalloc(2 + (len * 2), GFP_KERNEL); - if (user == NULL) { - rc = -ENOMEM; - return rc; - } + if (user == NULL) + return -ENOMEM; if (len) { len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp); @@ -461,11 +453,10 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, *(u16 *)user = 0; } - rc = crypto_shash_update(ses->server->secmech.hmacmd5, - (char *)user, 2 * len); + rc = crypto_shash_update(hmacmd5, (char *)user, 2 * len); kfree(user); if (rc) { - cifs_dbg(VFS, "%s: Could not update with user\n", __func__); + cifs_dbg(VFS, "%s: Could not update with user, rc=%d\n", __func__, rc); return rc; } @@ -474,19 +465,15 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, len = strlen(ses->domainName); domain = kmalloc(2 + (len * 2), GFP_KERNEL); - if (domain == NULL) { - rc = -ENOMEM; - return rc; - } + if (domain == NULL) + return -ENOMEM; + len = cifs_strtoUTF16((__le16 *)domain, ses->domainName, len, nls_cp); - rc = - crypto_shash_update(ses->server->secmech.hmacmd5, - (char *)domain, 2 * len); + rc = crypto_shash_update(hmacmd5, (char *)domain, 2 * len); kfree(domain); if (rc) { - cifs_dbg(VFS, "%s: Could not update with domain\n", - __func__); + cifs_dbg(VFS, "%s: Could not update with domain, rc=%d\n", __func__, rc); return rc; } } else { @@ -494,33 +481,27 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, len = strlen(ses->ip_addr); server = kmalloc(2 + (len * 2), GFP_KERNEL); - if (server == NULL) { - rc = -ENOMEM; - return rc; - } - len = cifs_strtoUTF16((__le16 *)server, ses->ip_addr, len, - nls_cp); - rc = - crypto_shash_update(ses->server->secmech.hmacmd5, - (char *)server, 2 * len); + if (server == NULL) + return -ENOMEM; + + len = cifs_strtoUTF16((__le16 *)server, ses->ip_addr, len, nls_cp); + rc = crypto_shash_update(hmacmd5, (char *)server, 2 * len); kfree(server); if (rc) { - cifs_dbg(VFS, "%s: Could not update with server\n", - __func__); + cifs_dbg(VFS, "%s: Could not update with server, rc=%d\n", __func__, rc); return rc; } } - rc = crypto_shash_final(ses->server->secmech.hmacmd5, - ntlmv2_hash); + rc = crypto_shash_final(hmacmd5, ntlmv2_hash); if (rc) - cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__); + cifs_dbg(VFS, "%s: Could not generate MD5 hash, rc=%d\n", __func__, rc); return rc; } static int -CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) +CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash, struct shash_desc *hmacmd5) { int rc; struct ntlmv2_resp *ntlmv2 = (struct ntlmv2_resp *) @@ -531,43 +512,33 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) hash_len = ses->auth_key.len - (CIFS_SESS_KEY_SIZE + offsetof(struct ntlmv2_resp, challenge.key[0])); - if (!ses->server->secmech.hmacmd5) { - cifs_dbg(VFS, "%s: can't generate ntlmv2 hash\n", __func__); - return -1; - } - - rc = crypto_shash_setkey(ses->server->secmech.hmacmd5->tfm, - ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); + rc = crypto_shash_setkey(hmacmd5->tfm, ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not set NTLMV2 Hash as a key\n", - __func__); + cifs_dbg(VFS, "%s: Could not set NTLMv2 hash as a key, rc=%d\n", __func__, rc); return rc; } - rc = crypto_shash_init(ses->server->secmech.hmacmd5); + rc = crypto_shash_init(hmacmd5); if (rc) { - cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init HMAC-MD5, rc=%d\n", __func__, rc); return rc; } if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) - memcpy(ntlmv2->challenge.key, - ses->ntlmssp->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); + memcpy(ntlmv2->challenge.key, ses->ntlmssp->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); else - memcpy(ntlmv2->challenge.key, - ses->server->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); - rc = crypto_shash_update(ses->server->secmech.hmacmd5, - ntlmv2->challenge.key, hash_len); + memcpy(ntlmv2->challenge.key, ses->server->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); + + rc = crypto_shash_update(hmacmd5, ntlmv2->challenge.key, hash_len); if (rc) { - cifs_dbg(VFS, "%s: Could not update with response\n", __func__); + cifs_dbg(VFS, "%s: Could not update with response, rc=%d\n", __func__, rc); return rc; } /* Note that the MD5 digest over writes anon.challenge_key.key */ - rc = crypto_shash_final(ses->server->secmech.hmacmd5, - ntlmv2->ntlmv2_hash); + rc = crypto_shash_final(hmacmd5, ntlmv2->ntlmv2_hash); if (rc) - cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__); + cifs_dbg(VFS, "%s: Could not generate MD5 hash, rc=%d\n", __func__, rc); return rc; } @@ -575,6 +546,7 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash) int setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) { + struct shash_desc *hmacmd5 = NULL; int rc; int baselen; unsigned int tilen; @@ -640,55 +612,51 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) cifs_server_lock(ses->server); - rc = cifs_alloc_hash("hmac(md5)", &ses->server->secmech.hmacmd5); + rc = cifs_alloc_hash("hmac(md5)", &hmacmd5); if (rc) { + cifs_dbg(VFS, "Could not allocate HMAC-MD5, rc=%d\n", rc); goto unlock; } /* calculate ntlmv2_hash */ - rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp); + rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp, hmacmd5); if (rc) { - cifs_dbg(VFS, "Could not get v2 hash rc %d\n", rc); + cifs_dbg(VFS, "Could not get NTLMv2 hash, rc=%d\n", rc); goto unlock; } /* calculate first part of the client response (CR1) */ - rc = CalcNTLMv2_response(ses, ntlmv2_hash); + rc = CalcNTLMv2_response(ses, ntlmv2_hash, hmacmd5); if (rc) { - cifs_dbg(VFS, "Could not calculate CR1 rc: %d\n", rc); + cifs_dbg(VFS, "Could not calculate CR1, rc=%d\n", rc); goto unlock; } /* now calculate the session key for NTLMv2 */ - rc = crypto_shash_setkey(ses->server->secmech.hmacmd5->tfm, - ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); + rc = crypto_shash_setkey(hmacmd5->tfm, ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not set NTLMV2 Hash as a key\n", - __func__); + cifs_dbg(VFS, "%s: Could not set NTLMv2 hash as a key, rc=%d\n", __func__, rc); goto unlock; } - rc = crypto_shash_init(ses->server->secmech.hmacmd5); + rc = crypto_shash_init(hmacmd5); if (rc) { - cifs_dbg(VFS, "%s: Could not init hmacmd5\n", __func__); + cifs_dbg(VFS, "%s: Could not init HMAC-MD5, rc=%d\n", __func__, rc); goto unlock; } - rc = crypto_shash_update(ses->server->secmech.hmacmd5, - ntlmv2->ntlmv2_hash, - CIFS_HMAC_MD5_HASH_SIZE); + rc = crypto_shash_update(hmacmd5, ntlmv2->ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not update with response\n", __func__); + cifs_dbg(VFS, "%s: Could not update with response, rc=%d\n", __func__, rc); goto unlock; } - rc = crypto_shash_final(ses->server->secmech.hmacmd5, - ses->auth_key.response); + rc = crypto_shash_final(hmacmd5, ses->auth_key.response); if (rc) - cifs_dbg(VFS, "%s: Could not generate md5 hash\n", __func__); - + cifs_dbg(VFS, "%s: Could not generate MD5 hash, rc=%d\n", __func__, rc); unlock: cifs_server_unlock(ses->server); + cifs_free_hash(&hmacmd5); setup_ntlmv2_rsp_ret: kfree_sensitive(tiblob); @@ -732,16 +700,19 @@ cifs_crypto_secmech_release(struct TCP_Server_Info *server) cifs_free_hash(&server->secmech.aes_cmac); cifs_free_hash(&server->secmech.hmacsha256); cifs_free_hash(&server->secmech.md5); - cifs_free_hash(&server->secmech.sha512); - cifs_free_hash(&server->secmech.hmacmd5); - if (server->secmech.enc) { - crypto_free_aead(server->secmech.enc); - server->secmech.enc = NULL; - } + if (!SERVER_IS_CHAN(server)) { + if (server->secmech.enc) { + crypto_free_aead(server->secmech.enc); + server->secmech.enc = NULL; + } - if (server->secmech.dec) { - crypto_free_aead(server->secmech.dec); + if (server->secmech.dec) { + crypto_free_aead(server->secmech.dec); + server->secmech.dec = NULL; + } + } else { + server->secmech.enc = NULL; server->secmech.dec = NULL; } } diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 15571cf0ba63..315aac5dec05 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -178,10 +178,8 @@ struct session_key { /* crypto hashing related structure/fields, not specific to a sec mech */ struct cifs_secmech { - struct shash_desc *hmacmd5; /* hmacmd5 hash function, for NTLMv2/CR1 hashes */ struct shash_desc *md5; /* md5 hash function, for CIFS/SMB1 signatures */ struct shash_desc *hmacsha256; /* hmac-sha256 hash function, for SMB2 signatures */ - struct shash_desc *sha512; /* sha512 hash function, for SMB3.1.1 preauth hash */ struct shash_desc *aes_cmac; /* block-cipher based MAC function, for SMB3 signatures */ struct crypto_aead *enc; /* smb3 encryption AEAD TFM (AES-CCM and AES-GCM) */ diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 3216f786908f..03c0b484a4b5 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -624,7 +624,7 @@ cifs_ses_add_channel(struct cifs_ses *ses, * to sign packets before we generate the channel signing key * (we sign with the session key) */ - rc = smb311_crypto_shash_allocate(chan->server); + rc = smb3_crypto_shash_allocate(chan->server); if (rc) { cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__); mutex_unlock(&ses->session_mutex); diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index f3c4b70b77b9..bdeb12ff53e3 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -906,41 +906,41 @@ smb311_update_preauth_hash(struct cifs_ses *ses, struct TCP_Server_Info *server, || (hdr->Status != cpu_to_le32(NT_STATUS_MORE_PROCESSING_REQUIRED)))) return 0; - ok: - rc = smb311_crypto_shash_allocate(server); - if (rc) + rc = cifs_alloc_hash("sha512", &sha512); + if (rc) { + cifs_dbg(VFS, "%s: Could not allocate SHA512 shash, rc=%d\n", __func__, rc); return rc; + } - sha512 = server->secmech.sha512; rc = crypto_shash_init(sha512); if (rc) { - cifs_dbg(VFS, "%s: Could not init sha512 shash\n", __func__); - return rc; + cifs_dbg(VFS, "%s: Could not init SHA512 shash, rc=%d\n", __func__, rc); + goto err_free; } rc = crypto_shash_update(sha512, ses->preauth_sha_hash, SMB2_PREAUTH_HASH_SIZE); if (rc) { - cifs_dbg(VFS, "%s: Could not update sha512 shash\n", __func__); - return rc; + cifs_dbg(VFS, "%s: Could not update SHA512 shash, rc=%d\n", __func__, rc); + goto err_free; } for (i = 0; i < nvec; i++) { rc = crypto_shash_update(sha512, iov[i].iov_base, iov[i].iov_len); if (rc) { - cifs_dbg(VFS, "%s: Could not update sha512 shash\n", - __func__); - return rc; + cifs_dbg(VFS, "%s: Could not update SHA512 shash, rc=%d\n", __func__, rc); + goto err_free; } } rc = crypto_shash_final(sha512, ses->preauth_sha_hash); if (rc) { - cifs_dbg(VFS, "%s: Could not finalize sha512 shash\n", - __func__); - return rc; + cifs_dbg(VFS, "%s: Could not finalize SHA12 shash, rc=%d\n", __func__, rc); + goto err_free; } +err_free: + cifs_free_hash(&sha512); return 0; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1ee2dd4a1cae..177173072bfa 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4309,7 +4309,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) */ static int crypt_message(struct TCP_Server_Info *server, int num_rqst, - struct smb_rqst *rqst, int enc) + struct smb_rqst *rqst, int enc, struct crypto_aead *tfm) { struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)rqst[0].rq_iov[0].iov_base; @@ -4320,8 +4320,6 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; u8 *iv; - DECLARE_CRYPTO_WAIT(wait); - struct crypto_aead *tfm; unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize); void *creq; size_t sensitive_size; @@ -4333,14 +4331,6 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, return rc; } - rc = smb3_crypto_aead_allocate(server); - if (rc) { - cifs_server_dbg(VFS, "%s: crypto alloc failed\n", __func__); - return rc; - } - - tfm = enc ? server->secmech.enc : server->secmech.dec; - if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE); @@ -4380,11 +4370,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, aead_request_set_crypt(req, sg, sg, crypt_len, iv); aead_request_set_ad(req, assoc_data_len); - aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &wait); - - rc = crypto_wait_req(enc ? crypto_aead_encrypt(req) - : crypto_aead_decrypt(req), &wait); + rc = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req); if (!rc && enc) memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE); @@ -4526,7 +4512,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst, /* fill the 1st iov with a transform header */ fill_transform_hdr(tr_hdr, orig_len, old_rq, server->cipher_type); - rc = crypt_message(server, num_rqst, new_rq, 1); + rc = crypt_message(server, num_rqst, new_rq, 1, server->secmech.enc); cifs_dbg(FYI, "Encrypt message returned %d\n", rc); if (rc) goto err_free; @@ -4551,8 +4537,9 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, unsigned int buf_data_size, struct iov_iter *iter, bool is_offloaded) { - struct kvec iov[2]; + struct crypto_aead *tfm; struct smb_rqst rqst = {NULL}; + struct kvec iov[2]; size_t iter_size = 0; int rc; @@ -4568,9 +4555,31 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, iter_size = iov_iter_count(iter); } - rc = crypt_message(server, 1, &rqst, 0); + if (is_offloaded) { + if ((server->cipher_type == SMB2_ENCRYPTION_AES128_GCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) + tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + else + tfm = crypto_alloc_aead("ccm(aes)", 0, 0); + if (IS_ERR(tfm)) { + rc = PTR_ERR(tfm); + cifs_server_dbg(VFS, "%s: Failed alloc decrypt TFM, rc=%d\n", __func__, rc); + + return rc; + } + } else { + if (unlikely(!server->secmech.dec)) + return -EIO; + + tfm = server->secmech.dec; + } + + rc = crypt_message(server, 1, &rqst, 0, tfm); cifs_dbg(FYI, "Decrypt message returned %d\n", rc); + if (is_offloaded) + crypto_free_aead(tfm); + if (rc) return rc; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index bb225758448a..02828b9c3cb3 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1266,6 +1266,16 @@ SMB2_negotiate(const unsigned int xid, else cifs_server_dbg(VFS, "Missing expected negotiate contexts\n"); } + + if (server->cipher_type && !rc) { + if (!SERVER_IS_CHAN(server)) { + rc = smb3_crypto_aead_allocate(server); + } else { + /* For channels, just reuse the primary server crypto secmech. */ + server->secmech.enc = server->primary_server->secmech.enc; + server->secmech.dec = server->primary_server->secmech.dec; + } + } neg_exit: free_rsp_buf(resp_buftype, rsp); return rc; diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index c7e1b149877a..56a896ff7cd9 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -291,7 +291,7 @@ extern int smb2_validate_and_copy_iov(unsigned int offset, extern void smb2_copy_fs_info_to_kstatfs( struct smb2_fs_full_size_info *pfs_inf, struct kstatfs *kst); -extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server); +extern int smb3_crypto_shash_allocate(struct TCP_Server_Info *server); extern int smb311_update_preauth_hash(struct cifs_ses *ses, struct TCP_Server_Info *server, struct kvec *iov, int nvec); diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index e4636fca821d..f7e04c40d22e 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -26,8 +26,7 @@ #include "../common/smb2status.h" #include "smb2glob.h" -static int -smb3_crypto_shash_allocate(struct TCP_Server_Info *server) +int smb3_crypto_shash_allocate(struct TCP_Server_Info *server) { struct cifs_secmech *p = &server->secmech; int rc; @@ -46,33 +45,6 @@ err: return rc; } -int -smb311_crypto_shash_allocate(struct TCP_Server_Info *server) -{ - struct cifs_secmech *p = &server->secmech; - int rc = 0; - - rc = cifs_alloc_hash("hmac(sha256)", &p->hmacsha256); - if (rc) - return rc; - - rc = cifs_alloc_hash("cmac(aes)", &p->aes_cmac); - if (rc) - goto err; - - rc = cifs_alloc_hash("sha512", &p->sha512); - if (rc) - goto err; - - return 0; - -err: - cifs_free_hash(&p->aes_cmac); - cifs_free_hash(&p->hmacsha256); - return rc; -} - - static int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key) { @@ -242,7 +214,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, ses = smb2_find_smb_ses(server, le64_to_cpu(shdr->SessionId)); if (unlikely(!ses)) { - cifs_server_dbg(VFS, "%s: Could not find session\n", __func__); + cifs_server_dbg(FYI, "%s: Could not find session\n", __func__); return -ENOENT; } diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index c769f9dbc0b4..9f272cc8f566 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -6,7 +6,7 @@ * Note that, due to trying to use names similar to the protocol specifications, * there are many mixed case field names in the structures below. Although * this does not match typical Linux kernel style, it is necessary to be - * able to match against the protocol specfication. + * able to match against the protocol specification. * * SMB2 commands * Some commands have minimal (wct=0,bcc=0), or uninteresting, responses @@ -491,7 +491,7 @@ struct smb2_encryption_neg_context { __le16 ContextType; /* 2 */ __le16 DataLength; __le32 Reserved; - /* CipherCount usally 2, but can be 3 when AES256-GCM enabled */ + /* CipherCount usually 2, but can be 3 when AES256-GCM enabled */ __le16 CipherCount; /* AES128-GCM and AES128-CCM by default */ __le16 Ciphers[]; } __packed; @@ -1061,7 +1061,7 @@ struct smb2_server_client_notification { #define IL_IMPERSONATION cpu_to_le32(0x00000002) #define IL_DELEGATE cpu_to_le32(0x00000003) -/* File Attrubutes */ +/* File Attributes */ #define FILE_ATTRIBUTE_READONLY 0x00000001 #define FILE_ATTRIBUTE_HIDDEN 0x00000002 #define FILE_ATTRIBUTE_SYSTEM 0x00000004 diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index cac80e7bfefc..aa2a37a7ce84 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -25,7 +25,7 @@ DECLARE_RWSEM(conn_list_lock); /** * ksmbd_conn_free() - free resources of the connection instance * - * @conn: connection instance to be cleand up + * @conn: connection instance to be cleaned up * * During the thread termination, the corresponding conn instance * resources(sock/memory) are released and finally the conn object is freed. diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index f4e55199938d..38e6fd2da3b8 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -213,7 +213,7 @@ struct ksmbd_tree_connect_response { }; /* - * IPC Request struture to disconnect tree connection. + * IPC Request structure to disconnect tree connection. */ struct ksmbd_tree_disconnect_request { __u64 session_id; /* session id */ diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 246cde380dfb..4142c7ad5fa9 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -796,7 +796,7 @@ out: /** * smb2_lease_break_noti() - break lease when a new client request * write lease - * @opinfo: conains lease state information + * @opinfo: contains lease state information * * Return: 0 on success, otherwise error */ @@ -1484,7 +1484,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) } /** - * parse_lease_state() - parse lease context containted in file open request + * parse_lease_state() - parse lease context contained in file open request * @open_req: buffer containing smb2 file open(create) request * * Return: allocated lease context object on success, otherwise NULL diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index c402d4abe826..231d2d224656 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -279,7 +279,7 @@ static void handle_ksmbd_work(struct work_struct *wk) /** * queue_ksmbd_work() - queue a smb request to worker thread queue - * for proccessing smb command and sending response + * for processing smb command and sending response * @conn: connection instance * * read remaining data from socket create and submit work. diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index e6bdc1b20727..7460089c186f 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1335,8 +1335,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, return rc; sz = le16_to_cpu(rsp->SecurityBufferOffset); - chgblob = - (struct challenge_message *)((char *)&rsp->hdr.ProtocolId + sz); + chgblob = (struct challenge_message *)rsp->Buffer; memset(chgblob, 0, sizeof(struct challenge_message)); if (!work->conn->use_spnego) { @@ -1369,9 +1368,7 @@ static int ntlm_negotiate(struct ksmbd_work *work, goto out; } - sz = le16_to_cpu(rsp->SecurityBufferOffset); - unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len, - /* alloc is larger than blob, see smb2_allocate_rsp_buf() */); + memcpy(rsp->Buffer, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); out: @@ -1453,10 +1450,7 @@ static int ntlm_authenticate(struct ksmbd_work *work, if (rc) return -ENOMEM; - sz = le16_to_cpu(rsp->SecurityBufferOffset); - unsafe_memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, - spnego_blob_len, - /* alloc is larger than blob, see smb2_allocate_rsp_buf() */); + memcpy(rsp->Buffer, spnego_blob, spnego_blob_len); rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len); kfree(spnego_blob); } @@ -2058,18 +2052,20 @@ out_err1: * @access: file access flags * @disposition: file disposition flags * @may_flags: set with MAY_ flags - * @is_dir: is creating open flags for directory + * @coptions: file creation options + * @mode: file mode * * Return: file open flags */ static int smb2_create_open_flags(bool file_present, __le32 access, __le32 disposition, int *may_flags, - bool is_dir) + __le32 coptions, + umode_t mode) { int oflags = O_NONBLOCK | O_LARGEFILE; - if (is_dir) { + if (coptions & FILE_DIRECTORY_FILE_LE || S_ISDIR(mode)) { access &= ~FILE_WRITE_DESIRE_ACCESS_LE; ksmbd_debug(SMB, "Discard write access to a directory\n"); } @@ -2086,7 +2082,7 @@ static int smb2_create_open_flags(bool file_present, __le32 access, *may_flags = MAY_OPEN | MAY_READ; } - if (access == FILE_READ_ATTRIBUTES_LE) + if (access == FILE_READ_ATTRIBUTES_LE || S_ISBLK(mode) || S_ISCHR(mode)) oflags |= O_PATH; if (file_present) { @@ -3181,8 +3177,8 @@ int smb2_open(struct ksmbd_work *work) open_flags = smb2_create_open_flags(file_present, daccess, req->CreateDisposition, &may_flags, - req->CreateOptions & FILE_DIRECTORY_FILE_LE || - (file_present && S_ISDIR(d_inode(path.dentry)->i_mode))); + req->CreateOptions, + file_present ? d_inode(path.dentry)->i_mode : 0); if (!test_tree_conn_flag(tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { if (open_flags & (O_CREAT | O_TRUNC)) { @@ -3531,8 +3527,9 @@ int smb2_open(struct ksmbd_work *work) memcpy(fp->create_guid, dh_info.CreateGuid, SMB2_CREATE_GUID_SIZE); if (dh_info.timeout) - fp->durable_timeout = min(dh_info.timeout, - DURABLE_HANDLE_MAX_TIMEOUT); + fp->durable_timeout = + min_t(unsigned int, dh_info.timeout, + DURABLE_HANDLE_MAX_TIMEOUT); else fp->durable_timeout = 60; } @@ -4586,7 +4583,7 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, path = &fp->filp->f_path; /* single EA entry is requested with given user.* name */ if (req->InputBufferLength) { - if (le32_to_cpu(req->InputBufferLength) < + if (le32_to_cpu(req->InputBufferLength) <= sizeof(struct smb2_ea_info_req)) return -EINVAL; @@ -8090,7 +8087,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - if (in_buf_len < sizeof(struct copychunk_ioctl_req)) { + if (in_buf_len <= sizeof(struct copychunk_ioctl_req)) { ret = -EINVAL; goto out; } diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 3be7d5ae65a8..73aff20e22d0 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -194,7 +194,7 @@ struct copychunk_ioctl_req { __le64 ResumeKey[3]; __le32 ChunkCount; __le32 Reserved; - __u8 Chunks[1]; /* array of srv_copychunk */ + __u8 Chunks[]; /* array of srv_copychunk */ } __packed; struct srv_copychunk { @@ -370,7 +370,7 @@ struct smb2_file_attr_tag_info { struct smb2_ea_info_req { __le32 NextEntryOffset; __u8 EaNameLength; - char name[1]; + char name[]; } __packed; /* level 15 Query */ struct smb2_ea_info { diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index cc4bb2377cbd..5b8d75e78ffb 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -488,7 +488,7 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, * @shortname: destination short filename * * Return: shortname length or 0 when source long name is '.' or '..' - * TODO: Though this function comforms the restriction of 8.3 Filename spec, + * TODO: Though this function conforms the restriction of 8.3 Filename spec, * but the result is different with Windows 7's one. need to check. */ int ksmbd_extract_shortname(struct ksmbd_conn *conn, const char *longname, diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index b0f6d0f94cb8..5bbb179736c2 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -100,8 +100,8 @@ struct ksmbd_file { struct list_head blocked_works; struct list_head lock_list; - int durable_timeout; - int durable_scavenger_timeout; + unsigned int durable_timeout; + unsigned int durable_scavenger_timeout; /* if ls is happening on directory, below is valid*/ struct ksmbd_readdir_data readdir_data; diff --git a/fs/smb/server/xattr.h b/fs/smb/server/xattr.h index fa3e27d6971b..505101a8104c 100644 --- a/fs/smb/server/xattr.h +++ b/fs/smb/server/xattr.h @@ -99,7 +99,7 @@ struct xattr_ntacl { __u8 posix_acl_hash[XATTR_SD_HASH_SIZE]; /* 64bytes hash for posix acl */ }; -/* DOS ATTRIBUITE XATTR PREFIX */ +/* DOS ATTRIBUTE XATTR PREFIX */ #define DOS_ATTRIBUTE_PREFIX "DOSATTRIB" #define DOS_ATTRIBUTE_PREFIX_LEN (sizeof(DOS_ATTRIBUTE_PREFIX) - 1) #define XATTR_NAME_DOS_ATTRIBUTE (XATTR_USER_PREFIX DOS_ATTRIBUTE_PREFIX) diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index d91cec93d968..5cc69beaa62e 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2807,7 +2807,6 @@ static const struct file_operations dfs_fops = { .read = dfs_file_read, .write = dfs_file_write, .owner = THIS_MODULE, - .llseek = no_llseek, }; /** @@ -2952,7 +2951,6 @@ static const struct file_operations dfs_global_fops = { .read = dfs_global_file_read, .write = dfs_global_file_write, .owner = THIS_MODULE, - .llseek = no_llseek, }; /** diff --git a/include/linux/einj-cxl.h b/include/cxl/einj.h index 624ff6ff41f9..624ff6ff41f9 100644 --- a/include/linux/einj-cxl.h +++ b/include/cxl/einj.h diff --git a/include/linux/cxl-event.h b/include/cxl/event.h index 0bea1afbd747..0bea1afbd747 100644 --- a/include/linux/cxl-event.h +++ b/include/cxl/event.h diff --git a/include/cxl/mailbox.h b/include/cxl/mailbox.h new file mode 100644 index 000000000000..bacd111e75f1 --- /dev/null +++ b/include/cxl/mailbox.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2024 Intel Corporation. */ +#ifndef __CXL_MBOX_H__ +#define __CXL_MBOX_H__ +#include <linux/rcuwait.h> + +struct cxl_mbox_cmd; + +/** + * struct cxl_mailbox - context for CXL mailbox operations + * @host: device that hosts the mailbox + * @payload_size: Size of space for payload + * (CXL 3.1 8.2.8.4.3 Mailbox Capabilities Register) + * @mbox_mutex: mutex protects device mailbox and firmware + * @mbox_wait: rcuwait for mailbox + * @mbox_send: @dev specific transport for transmitting mailbox commands + */ +struct cxl_mailbox { + struct device *host; + size_t payload_size; + struct mutex mbox_mutex; /* lock to protect mailbox context */ + struct rcuwait mbox_wait; + int (*mbox_send)(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd); +}; + +int cxl_mailbox_init(struct cxl_mailbox *cxl_mbox, struct device *host); + +#endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1655c4c23a78..4d5ee84c468b 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -363,6 +363,7 @@ void acpi_unregister_gsi (u32 gsi); struct pci_dev; +struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin); int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h index e4004d1e6725..b3643de9931d 100644 --- a/include/linux/attribute_container.h +++ b/include/linux/attribute_container.h @@ -61,14 +61,8 @@ int attribute_container_device_trigger_safe(struct device *dev, int (*undo)(struct attribute_container *, struct device *, struct device *)); -void attribute_container_trigger(struct device *dev, - int (*fn)(struct attribute_container *, - struct device *)); int attribute_container_add_attrs(struct device *classdev); int attribute_container_add_class_device(struct device *classdev); -int attribute_container_add_class_device_adapter(struct attribute_container *cont, - struct device *dev, - struct device *classdev); void attribute_container_remove_attrs(struct device *classdev); void attribute_container_class_device_del(struct device *classdev); struct attribute_container *attribute_container_classdev_to_container(struct device *); diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index 662b8ae54b6a..31762324bcc9 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -271,6 +271,6 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); struct auxiliary_device *auxiliary_find_device(struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)); + device_match_t match); #endif /* _AUXILIARY_BUS_H_ */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index d3b66d77df7a..262b6596eca5 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -203,12 +203,12 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ -static inline unsigned long -bitmap_find_next_zero_area(unsigned long *map, - unsigned long size, - unsigned long start, - unsigned int nr, - unsigned long align_mask) +static __always_inline +unsigned long bitmap_find_next_zero_area(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned int nr, + unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); @@ -228,7 +228,7 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) -static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) +static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -238,7 +238,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) memset(dst, 0, len); } -static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) +static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -248,8 +248,8 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) memset(dst, 0xff, len); } -static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = bitmap_size(nbits); @@ -262,8 +262,8 @@ 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) +static __always_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) @@ -318,16 +318,18 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) #endif -static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_and(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } -static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; @@ -335,8 +337,9 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, __bitmap_or(dst, src1, src2, nbits); } -static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +void bitmap_xor(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; @@ -344,16 +347,17 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } -static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, - unsigned int nbits) +static __always_inline +void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); @@ -368,8 +372,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) -static inline bool bitmap_equal(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -388,10 +392,9 @@ static inline bool bitmap_equal(const unsigned long *src1, * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ -static inline bool bitmap_or_equal(const unsigned long *src1, - const unsigned long *src2, - const unsigned long *src3, - unsigned int nbits) +static __always_inline +bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, + const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); @@ -399,9 +402,8 @@ static inline bool bitmap_or_equal(const unsigned long *src1, return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } -static inline bool bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, - unsigned int nbits) +static __always_inline +bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -409,8 +411,8 @@ static inline bool bitmap_intersects(const unsigned long *src1, return __bitmap_intersects(src1, src2, nbits); } -static inline bool bitmap_subset(const unsigned long *src1, - const unsigned long *src2, unsigned int nbits) +static __always_inline +bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); @@ -418,7 +420,8 @@ static inline bool bitmap_subset(const unsigned long *src1, return __bitmap_subset(src1, src2, nbits); } -static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) +static __always_inline +bool bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -426,7 +429,8 @@ static inline bool bitmap_empty(const unsigned long *src, unsigned nbits) return find_first_bit(src, nbits) == nbits; } -static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) +static __always_inline +bool bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); @@ -460,8 +464,8 @@ unsigned long bitmap_weight_andnot(const unsigned long *src1, return __bitmap_weight_andnot(src1, src2, nbits); } -static __always_inline void bitmap_set(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); @@ -476,8 +480,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start, __bitmap_set(map, start, nbits); } -static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, - unsigned int nbits) +static __always_inline +void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); @@ -492,8 +496,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, __bitmap_clear(map, start, nbits); } -static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; @@ -501,8 +506,9 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s __bitmap_shift_right(dst, src, shift, nbits); } -static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, - unsigned int shift, unsigned int nbits) +static __always_inline +void bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); @@ -510,11 +516,12 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr __bitmap_shift_left(dst, src, shift, nbits); } -static inline void bitmap_replace(unsigned long *dst, - const unsigned long *old, - const unsigned long *new, - const unsigned long *mask, - unsigned int nbits) +static __always_inline +void bitmap_replace(unsigned long *dst, + const unsigned long *old, + const unsigned long *new, + const unsigned long *mask, + unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); @@ -557,8 +564,9 @@ static inline void bitmap_replace(unsigned long *dst, * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. * See bitmap_scatter() for details related to this relationship. */ -static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_scatter(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -611,8 +619,9 @@ static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, * bitmap_scatter(res, src, mask, n) and a call to * bitmap_scatter(res, result, mask, n) will lead to the same res value. */ -static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, - const unsigned long *mask, unsigned int nbits) +static __always_inline +void bitmap_gather(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) { unsigned int n = 0; unsigned int bit; @@ -623,9 +632,9 @@ static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, __assign_bit(n++, dst, test_bit(bit, src)); } -static inline void bitmap_next_set_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) +static __always_inline +void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, + unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); @@ -640,7 +649,8 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, * This is the complement to __bitmap_find_free_region() and releases * the found region (by clearing it in the bitmap). */ -static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order) { bitmap_clear(bitmap, pos, BIT(order)); } @@ -656,7 +666,8 @@ static inline void bitmap_release_region(unsigned long *bitmap, unsigned int pos * Returns: 0 on success, or %-EBUSY if specified region wasn't * free (not all bits were zero). */ -static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) +static __always_inline +int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order) { unsigned int len = BIT(order); @@ -680,7 +691,8 @@ static inline int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos * Returns: the bit offset in bitmap of the allocated region, * or -errno on failure. */ -static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) +static __always_inline +int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order) { unsigned int pos, end; /* scans bitmap by regions of size order */ @@ -734,7 +746,7 @@ static inline int bitmap_find_free_region(unsigned long *bitmap, unsigned int bi * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ -static inline void bitmap_from_u64(unsigned long *dst, u64 mask) +static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask) { bitmap_from_arr64(dst, &mask, 64); } @@ -749,9 +761,8 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return * value is undefined. */ -static inline unsigned long bitmap_read(const unsigned long *map, - unsigned long start, - unsigned long nbits) +static __always_inline +unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits) { size_t index = BIT_WORD(start); unsigned long offset = start % BITS_PER_LONG; @@ -784,8 +795,9 @@ static inline unsigned long bitmap_read(const unsigned long *map, * * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_write(unsigned long *map, unsigned long value, - unsigned long start, unsigned long nbits) +static __always_inline +void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) { size_t index; unsigned long offset; diff --git a/include/linux/bits.h b/include/linux/bits.h index 0eb24d21aac2..60044b608817 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -36,4 +36,19 @@ #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __GENMASK_U128() depends on _BIT128() which would not work + * in the asm code, as it shifts an 'unsigned __init128' data + * type instead of direct representation of 128 bit constants + * such as long and unsigned long. The fundamental problem is + * that a 128 bit constant will get silently truncated by the + * gcc compiler. + */ +#define GENMASK_U128(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l)) +#endif + #endif /* __LINUX_BITS_H */ diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f66f6aac74f6..d7941478158c 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -449,8 +449,6 @@ extern int ceph_osdc_init(struct ceph_osd_client *osdc, extern void ceph_osdc_stop(struct ceph_osd_client *osdc); extern void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc); -extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc, - struct ceph_msg *msg); extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg); void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb); diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index a3d3e888cf1f..038b2d523bf8 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -4,6 +4,142 @@ #include <linux/compiler.h> +/** + * DOC: scope-based cleanup helpers + * + * The "goto error" pattern is notorious for introducing subtle resource + * leaks. It is tedious and error prone to add new resource acquisition + * constraints into code paths that already have several unwind + * conditions. The "cleanup" helpers enable the compiler to help with + * this tedium and can aid in maintaining LIFO (last in first out) + * unwind ordering to avoid unintentional leaks. + * + * As drivers make up the majority of the kernel code base, here is an + * example of using these helpers to clean up PCI drivers. The target of + * the cleanups are occasions where a goto is used to unwind a device + * reference (pci_dev_put()), or unlock the device (pci_dev_unlock()) + * before returning. + * + * The DEFINE_FREE() macro can arrange for PCI device references to be + * dropped when the associated variable goes out of scope:: + * + * DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T)) + * ... + * struct pci_dev *dev __free(pci_dev_put) = + * pci_get_slot(parent, PCI_DEVFN(0, 0)); + * + * The above will automatically call pci_dev_put() if @dev is non-NULL + * when @dev goes out of scope (automatic variable scope). If a function + * wants to invoke pci_dev_put() on error, but return @dev (i.e. without + * freeing it) on success, it can do:: + * + * return no_free_ptr(dev); + * + * ...or:: + * + * return_ptr(dev); + * + * The DEFINE_GUARD() macro can arrange for the PCI device lock to be + * dropped when the scope where guard() is invoked ends:: + * + * DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T)) + * ... + * guard(pci_dev)(dev); + * + * The lifetime of the lock obtained by the guard() helper follows the + * scope of automatic variable declaration. Take the following example:: + * + * func(...) + * { + * if (...) { + * ... + * guard(pci_dev)(dev); // pci_dev_lock() invoked here + * ... + * } // <- implied pci_dev_unlock() triggered here + * } + * + * Observe the lock is held for the remainder of the "if ()" block not + * the remainder of "func()". + * + * Now, when a function uses both __free() and guard(), or multiple + * instances of __free(), the LIFO order of variable definition order + * matters. GCC documentation says: + * + * "When multiple variables in the same scope have cleanup attributes, + * at exit from the scope their associated cleanup functions are run in + * reverse order of definition (last defined, first cleanup)." + * + * When the unwind order matters it requires that variables be defined + * mid-function scope rather than at the top of the file. Take the + * following example and notice the bug highlighted by "!!":: + * + * LIST_HEAD(list); + * DEFINE_MUTEX(lock); + * + * struct object { + * struct list_head node; + * }; + * + * static struct object *alloc_add(void) + * { + * struct object *obj; + * + * lockdep_assert_held(&lock); + * obj = kzalloc(sizeof(*obj), GFP_KERNEL); + * if (obj) { + * LIST_HEAD_INIT(&obj->node); + * list_add(obj->node, &list): + * } + * return obj; + * } + * + * static void remove_free(struct object *obj) + * { + * lockdep_assert_held(&lock); + * list_del(&obj->node); + * kfree(obj); + * } + * + * DEFINE_FREE(remove_free, struct object *, if (_T) remove_free(_T)) + * static int init(void) + * { + * struct object *obj __free(remove_free) = NULL; + * int err; + * + * guard(mutex)(&lock); + * obj = alloc_add(); + * + * if (!obj) + * return -ENOMEM; + * + * err = other_init(obj); + * if (err) + * return err; // remove_free() called without the lock!! + * + * no_free_ptr(obj); + * return 0; + * } + * + * That bug is fixed by changing init() to call guard() and define + + * initialize @obj in this order:: + * + * guard(mutex)(&lock); + * struct object *obj __free(remove_free) = alloc_add(); + * + * Given that the "__free(...) = NULL" pattern for variables defined at + * the top of the function poses this potential interdependency problem + * the recommendation is to always define and assign variables in one + * statement and not group variable definitions at the top of the + * function when __free() is used. + * + * Lastly, given that the benefit of cleanup helpers is removal of + * "goto", and that the "goto" statement can jump between scopes, the + * expectation is that usage of "goto" and cleanup helpers is never + * mixed in the same function. I.e. for a given routine, convert all + * resources that need a "goto" cleanup to scope-based cleanup, or + * convert none of them. + */ + /* * DEFINE_FREE(name, type, free): * simple helper macro that defines the required wrapper for a __free() diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ec55bcce4146..4d4e23b6e3e7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -133,7 +133,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define annotate_unreachable() __annotate_unreachable(__COUNTER__) /* Annotate a C jump table to allow objtool to follow the code flow */ -#define __annotate_jump_table __section(".rodata..c_jump_table") +#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #") #else /* !CONFIG_OBJTOOL */ #define annotate_reachable() diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 53158de44b83..9278a50d514f 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -30,7 +30,7 @@ extern unsigned int nr_cpu_ids; #endif -static inline void set_nr_cpu_ids(unsigned int nr) +static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); @@ -149,7 +149,7 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu) * * Return: >= nr_cpu_ids if no cpus set. */ -static inline unsigned int cpumask_first(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -160,7 +160,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if all cpus are set. */ -static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -172,7 +172,7 @@ static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ -static inline +static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); @@ -186,7 +186,7 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask * * Return: >= nr_cpu_ids if no cpus set in all. */ -static inline +static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) @@ -201,7 +201,7 @@ unsigned int cpumask_first_and_and(const struct cpumask *srcp1, * * Return: >= nr_cpumask_bits if no CPUs set. */ -static inline unsigned int cpumask_last(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } @@ -213,7 +213,7 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus set. */ -static inline +static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ @@ -229,7 +229,8 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) * * Return: >= nr_cpu_ids if no further cpus unset. */ -static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) @@ -239,18 +240,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ -static inline unsigned int cpumask_local_spread(unsigned int i, int node) +static __always_inline +unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } -static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, + const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } -static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } @@ -269,9 +273,9 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp); * * Return: >= nr_cpu_ids if no further cpus set in both. */ -static inline +static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, - const struct cpumask *src2p) + const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) @@ -291,7 +295,7 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p, for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 -static inline +static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); @@ -394,7 +398,7 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ -static inline +static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; @@ -414,7 +418,7 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) * * Returns >= nr_cpu_ids if no cpus set. */ -static inline +static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) @@ -436,7 +440,8 @@ unsigned int cpumask_any_and_but(const struct cpumask *mask1, * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) +static __always_inline +unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } @@ -449,7 +454,7 @@ static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *s * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -465,7 +470,7 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ -static inline +static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -508,12 +513,14 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline +void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -557,7 +564,8 @@ static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, * * Return: true if @cpu is set in @cpumask, else returns false */ -static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline +bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -571,7 +579,8 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -585,7 +594,8 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ -static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline +bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -594,7 +604,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask * * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_setall(struct cpumask *dstp) +static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); @@ -607,7 +617,7 @@ static inline void cpumask_setall(struct cpumask *dstp) * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ -static inline void cpumask_clear(struct cpumask *dstp) +static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } @@ -620,9 +630,9 @@ static inline void cpumask_clear(struct cpumask *dstp) * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_and(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -634,8 +644,9 @@ static inline bool cpumask_and(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -647,9 +658,9 @@ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input */ -static inline void cpumask_xor(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -663,9 +674,9 @@ static inline void cpumask_xor(struct cpumask *dstp, * * Return: false if *@dstp is empty, else returns true */ -static inline bool cpumask_andnot(struct cpumask *dstp, - const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -678,8 +689,8 @@ static inline bool cpumask_andnot(struct cpumask *dstp, * * Return: true if the cpumasks are equal, false if not */ -static inline bool cpumask_equal(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -694,9 +705,9 @@ static inline bool cpumask_equal(const struct cpumask *src1p, * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ -static inline bool cpumask_or_equal(const struct cpumask *src1p, - const struct cpumask *src2p, - const struct cpumask *src3p) +static __always_inline +bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, + const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); @@ -710,8 +721,8 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p, * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ -static inline bool cpumask_intersects(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -724,8 +735,8 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, * * Return: true if *@src1p is a subset of *@src2p, else returns false */ -static inline bool cpumask_subset(const struct cpumask *src1p, - const struct cpumask *src2p) +static __always_inline +bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); @@ -737,7 +748,7 @@ static inline bool cpumask_subset(const struct cpumask *src1p, * * Return: true if srcp is empty (has no bits set), else false */ -static inline bool cpumask_empty(const struct cpumask *srcp) +static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } @@ -748,7 +759,7 @@ static inline bool cpumask_empty(const struct cpumask *srcp) * * Return: true if srcp is full (has all bits set), else false */ -static inline bool cpumask_full(const struct cpumask *srcp) +static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } @@ -759,7 +770,7 @@ static inline bool cpumask_full(const struct cpumask *srcp) * * Return: count of bits set in *srcp */ -static inline unsigned int cpumask_weight(const struct cpumask *srcp) +static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } @@ -771,8 +782,8 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp) * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -784,8 +795,9 @@ static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, * * Return: count of bits set in both *srcp1 and *srcp2 */ -static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, - const struct cpumask *srcp2) +static __always_inline +unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, + const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } @@ -796,8 +808,8 @@ static inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_right(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); @@ -809,8 +821,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp, * @srcp: the input to shift * @n: the number of bits to shift by */ -static inline void cpumask_shift_left(struct cpumask *dstp, - const struct cpumask *srcp, int n) +static __always_inline +void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); @@ -821,8 +833,8 @@ static inline void cpumask_shift_left(struct cpumask *dstp, * @dstp: the result * @srcp: the input cpumask */ -static inline void cpumask_copy(struct cpumask *dstp, - const struct cpumask *srcp) +static __always_inline +void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } @@ -858,8 +870,8 @@ static inline void cpumask_copy(struct cpumask *dstp, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } @@ -872,8 +884,8 @@ static inline int cpumask_parse_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parselist_user(const char __user *buf, int len, - struct cpumask *dstp) +static __always_inline +int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); @@ -886,7 +898,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, * * Return: -errno, or 0 for success. */ -static inline int cpumask_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } @@ -898,7 +910,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) * * Return: -errno, or 0 for success. */ -static inline int cpulist_parse(const char *buf, struct cpumask *dstp) +static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } @@ -908,7 +920,7 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) * * Return: size to allocate for a &struct cpumask in bytes */ -static inline unsigned int cpumask_size(void) +static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } @@ -920,7 +932,7 @@ static inline unsigned int cpumask_size(void) bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -static inline +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); @@ -938,13 +950,13 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) * * Return: %true if allocation succeeded, %false if not */ -static inline +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } -static inline +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); @@ -954,7 +966,7 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } @@ -964,43 +976,43 @@ static inline bool cpumask_available(cpumask_var_t mask) #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly -static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } -static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } -static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } -static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, +static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } -static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) +static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } -static inline void free_cpumask_var(cpumask_var_t mask) +static __always_inline void free_cpumask_var(cpumask_var_t mask) { } -static inline void free_bootmem_cpumask_var(cpumask_var_t mask) +static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } -static inline bool cpumask_available(cpumask_var_t mask) +static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } @@ -1058,7 +1070,7 @@ void set_cpu_online(unsigned int cpu, bool online); ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) -static inline int __check_is_bitmap(const unsigned long *bitmap) +static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } @@ -1073,7 +1085,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap) extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; -static inline const struct cpumask *get_cpu_mask(unsigned int cpu) +static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; @@ -1100,32 +1112,32 @@ static __always_inline unsigned int num_online_cpus(void) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } -static inline bool cpu_enabled(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } @@ -1138,32 +1150,32 @@ static inline bool cpu_dying(unsigned int cpu) #define num_present_cpus() 1U #define num_active_cpus() 1U -static inline bool cpu_online(unsigned int cpu) +static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_possible(unsigned int cpu) +static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_enabled(unsigned int cpu) +static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_present(unsigned int cpu) +static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_active(unsigned int cpu) +static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } -static inline bool cpu_dying(unsigned int cpu) +static __always_inline bool cpu_dying(unsigned int cpu) { return false; } @@ -1197,7 +1209,7 @@ static inline bool cpu_dying(unsigned int cpu) * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ -static inline ssize_t +static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), @@ -1220,9 +1232,9 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; @@ -1242,9 +1254,9 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ -static inline ssize_t -cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, - loff_t off, size_t count) +static __always_inline +ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, + loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index c9c65b132c0f..0928a6c8ae1e 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -57,7 +57,6 @@ static const struct file_operations __fops = { \ .release = simple_attr_release, \ .read = debugfs_attr_read, \ .write = (__is_signed) ? debugfs_attr_write_signed : debugfs_attr_write, \ - .llseek = no_llseek, \ } #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt) \ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 53ca3a913d06..8321f65897f3 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -524,7 +524,6 @@ int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors); void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone); -union map_info *dm_get_rq_mapinfo(struct request *rq); #ifdef CONFIG_BLK_DEV_ZONED struct dm_report_zones_args { diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 807831d6bf0f..cdc4757217f9 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -126,6 +126,9 @@ struct bus_attribute { int __must_check bus_create_file(const struct bus_type *bus, struct bus_attribute *attr); void bus_remove_file(const struct bus_type *bus, struct bus_attribute *attr); +/* Matching function type for drivers/base APIs to find a specific device */ +typedef int (*device_match_t)(struct device *dev, const void *data); + /* Generic device matching functions that all busses can use to match with */ int device_match_name(struct device *dev, const void *name); int device_match_of_node(struct device *dev, const void *np); @@ -139,8 +142,7 @@ int device_match_any(struct device *dev, const void *unused); int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data, int (*fn)(struct device *dev, void *data)); struct device *bus_find_device(const struct bus_type *bus, struct device *start, - const void *data, - int (*match)(struct device *dev, const void *data)); + const void *data, device_match_t match); /** * bus_find_device_by_name - device iterator for locating a particular device * of a specific name. diff --git a/include/linux/device/class.h b/include/linux/device/class.h index c576b49c55c2..518c9c83d64b 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -95,7 +95,7 @@ void class_dev_iter_exit(struct class_dev_iter *iter); int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *dev, void *data)); struct device *class_find_device(const struct class *class, const struct device *start, - const void *data, int (*match)(struct device *, const void *)); + const void *data, device_match_t match); /** * class_find_device_by_name - device iterator for locating a particular device diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 1fc8b68786de..5c04b8e3833b 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -157,7 +157,7 @@ int __must_check driver_for_each_device(struct device_driver *drv, struct device void *data, int (*fn)(struct device *dev, void *)); struct device *driver_find_device(const struct device_driver *drv, struct device *start, const void *data, - int (*match)(struct device *dev, const void *data)); + device_match_t match); /** * driver_find_device_by_name - device iterator for locating a particular device diff --git a/include/linux/find.h b/include/linux/find.h index 5dfca4225fef..68685714bc18 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -52,7 +52,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -81,7 +81,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -112,7 +112,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -142,7 +142,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -171,7 +171,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1, * Returns the bit number of the next zero bit * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -198,7 +198,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, * Returns the bit number of the first set bit. * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -224,7 +224,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) * Returns the bit number of the N'th set bit. * If no such, returns >= @size. */ -static inline +static __always_inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) { if (n >= size) @@ -249,7 +249,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -276,7 +276,7 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long * * Returns the bit number of the N'th set bit. * If no such, returns @size. */ -static inline +static __always_inline unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n) { @@ -332,7 +332,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, * Returns the bit number for the next set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size) @@ -357,7 +357,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1, * Returns the bit number for the first set bit * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, const unsigned long *addr3, @@ -381,7 +381,7 @@ unsigned long find_first_and_and_bit(const unsigned long *addr1, * Returns the bit number of the first cleared bit. * If no bits are zero, returns @size. */ -static inline +static __always_inline unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -402,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) * * Returns the bit number of the last set bit, or size. */ -static inline +static __always_inline unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -425,7 +425,7 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size) * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_and_bit_wrap(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) @@ -448,7 +448,7 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1, * Returns the bit number for the next set bit, or first set bit up to @offset * If no bits are set, returns @size. */ -static inline +static __always_inline unsigned long find_next_bit_wrap(const unsigned long *addr, unsigned long size, unsigned long offset) { @@ -465,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr, * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing * before using it alone. */ -static inline +static __always_inline unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size, unsigned long start, unsigned long n) { @@ -506,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump, #if defined(__LITTLE_ENDIAN) -static inline unsigned long find_next_zero_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_zero_bit(addr, size, offset); } -static inline unsigned long find_next_bit_le(const void *addr, - unsigned long size, unsigned long offset) +static __always_inline +unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return find_next_bit(addr, size, offset); } -static inline unsigned long find_first_zero_bit_le(const void *addr, - unsigned long size) +static __always_inline +unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { return find_first_zero_bit(addr, size); } @@ -527,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr, #elif defined(__BIG_ENDIAN) #ifndef find_next_zero_bit_le -static inline +static __always_inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { @@ -546,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned #endif #ifndef find_first_zero_bit_le -static inline +static __always_inline unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) { if (small_const_nbits(size)) { @@ -560,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size) #endif #ifndef find_next_bit_le -static inline +static __always_inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { diff --git a/include/linux/fs.h b/include/linux/fs.h index eae5b67e4a15..e3c603d01337 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3234,7 +3234,6 @@ extern ssize_t iter_file_splice_write(struct pipe_inode_info *, extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); -#define no_llseek NULL extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 083c860fd28e..c90ec889bfc2 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -436,7 +436,7 @@ void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, u16 if_id); -extern struct bus_type fsl_mc_bus_type; +extern const struct bus_type fsl_mc_bus_type; extern struct device_type fsl_mc_bus_dprc_type; extern struct device_type fsl_mc_bus_dpni_type; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 98c47c394b89..e4697539b665 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -692,6 +692,9 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); +struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask); + int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, @@ -1060,6 +1063,13 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, } static inline struct folio * +alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) +{ + return NULL; +} + +static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0d5125a3e31a..db567d26f7b9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1529,8 +1529,22 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING -int kvm_arch_hardware_enable(void); -void kvm_arch_hardware_disable(void); +/* + * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under + * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of + * kvm_usage_count, i.e. at the beginning of the generic hardware enabling + * sequence, and at the end of the generic hardware disabling sequence. + */ +void kvm_arch_enable_virtualization(void); +void kvm_arch_disable_virtualization(void); +/* + * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to + * do the actual twiddling of hardware bits. The hooks are called on all + * online CPUs when KVM enables/disabled virtualization, and on a single CPU + * when that CPU is onlined/offlined (including for Resume/Suspend). + */ +int kvm_arch_enable_virtualization_cpu(void); +void kvm_arch_disable_virtualization_cpu(void); #endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index b61438313a73..9fd7a0ce9c1a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -107,11 +107,11 @@ extern nodemask_t _unused_nodemask_arg_; */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) -static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) +static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } -static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) +static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } @@ -132,19 +132,19 @@ static __always_inline void __node_set(int node, volatile nodemask_t *dstp) } #define node_clear(node, dst) __node_clear((node), &(dst)) -static inline void __node_clear(int node, volatile nodemask_t *dstp) +static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) -static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) -static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) +static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } @@ -154,14 +154,14 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) -static inline bool __node_test_and_set(int node, nodemask_t *addr) +static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -169,7 +169,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -177,7 +177,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -185,7 +185,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) -static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, +static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); @@ -193,7 +193,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) -static inline void __nodes_complement(nodemask_t *dstp, +static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); @@ -201,7 +201,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_equal(const nodemask_t *src1p, +static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); @@ -209,7 +209,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_intersects(const nodemask_t *src1p, +static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); @@ -217,33 +217,33 @@ static inline bool __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) -static inline bool __nodes_subset(const nodemask_t *src1p, +static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) +static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) -static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) +static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_right(nodemask_t *dstp, +static __always_inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); @@ -251,7 +251,7 @@ static inline void __nodes_shift_right(nodemask_t *dstp, #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) -static inline void __nodes_shift_left(nodemask_t *dstp, +static __always_inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); @@ -261,13 +261,13 @@ static inline void __nodes_shift_left(nodemask_t *dstp, > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) -static inline unsigned int __first_node(const nodemask_t *srcp) +static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) -static inline unsigned int __next_node(int n, const nodemask_t *srcp) +static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } @@ -277,7 +277,7 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) +static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); @@ -286,7 +286,7 @@ static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) return ret; } -static inline void init_nodemask_of_node(nodemask_t *mask, int node) +static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); @@ -304,7 +304,7 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node) }) #define first_unset_node(mask) __first_unset_node(&(mask)) -static inline unsigned int __first_unset_node(const nodemask_t *maskp) +static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); @@ -338,21 +338,21 @@ static inline unsigned int __first_unset_node(const nodemask_t *maskp) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) -static inline int __nodemask_parse_user(const char __user *buf, int len, +static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) -static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) +static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) -static inline int __node_remap(int oldbit, +static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); @@ -360,7 +360,7 @@ static inline int __node_remap(int oldbit, #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) -static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, +static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); @@ -368,7 +368,7 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) -static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); @@ -376,7 +376,7 @@ static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) -static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, +static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); @@ -418,22 +418,22 @@ enum node_states { extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } @@ -443,11 +443,11 @@ static inline int num_node_state(enum node_states state) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) -static inline unsigned int next_online_node(int nid) +static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } -static inline unsigned int next_memory_node(int nid) +static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } @@ -455,13 +455,13 @@ static inline unsigned int next_memory_node(int nid) extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; -static inline void node_set_online(int nid) +static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } -static inline void node_set_offline(int nid) +static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); @@ -469,20 +469,20 @@ static inline void node_set_offline(int nid) #else -static inline int node_state(int node, enum node_states state) +static __always_inline int node_state(int node, enum node_states state) { return node == 0; } -static inline void node_set_state(int node, enum node_states state) +static __always_inline void node_set_state(int node, enum node_states state) { } -static inline void node_clear_state(int node, enum node_states state) +static __always_inline void node_clear_state(int node, enum node_states state) { } -static inline int num_node_state(enum node_states state) +static __always_inline int num_node_state(enum node_states state) { return 1; } @@ -502,7 +502,7 @@ static inline int num_node_state(enum node_states state) #endif -static inline int node_random(const nodemask_t *maskp) +static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int w, bit; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index d422db6eec63..7132623e4658 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -52,7 +52,7 @@ struct platform_device { extern int platform_device_register(struct platform_device *); extern void platform_device_unregister(struct platform_device *); -extern struct bus_type platform_bus_type; +extern const struct bus_type platform_bus_type; extern struct device platform_bus; extern struct resource *platform_get_resource(struct platform_device *, diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h index f57f05331d73..569f86a44aaa 100644 --- a/include/trace/events/dma.h +++ b/include/trace/events/dma.h @@ -176,9 +176,9 @@ TRACE_EVENT(dma_free, ); TRACE_EVENT(dma_map_sg, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, + TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, int ents, enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, sg, nents, ents, dir, attrs), + TP_ARGS(dev, sgl, nents, ents, dir, attrs), TP_STRUCT__entry( __string(device, dev_name(dev)) @@ -190,17 +190,17 @@ TRACE_EVENT(dma_map_sg, ), TP_fast_assign( + struct scatterlist *sg; int i; __assign_str(device); - for (i = 0; i < nents; i++) - ((u64 *)__get_dynamic_array(phys_addrs))[i] = - sg_phys(sg + i); - for (i = 0; i < ents; i++) { + for_each_sg(sgl, sg, nents, i) + ((u64 *)__get_dynamic_array(phys_addrs))[i] = sg_phys(sg); + for_each_sg(sgl, sg, ents, i) { ((u64 *)__get_dynamic_array(dma_addrs))[i] = - sg_dma_address(sg + i); + sg_dma_address(sg); ((unsigned int *)__get_dynamic_array(lengths))[i] = - sg_dma_len(sg + i); + sg_dma_len(sg); } __entry->dir = dir; __entry->attrs = attrs; @@ -222,9 +222,9 @@ TRACE_EVENT(dma_map_sg, ); TRACE_EVENT(dma_unmap_sg, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, + TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir, unsigned long attrs), - TP_ARGS(dev, sg, nents, dir, attrs), + TP_ARGS(dev, sgl, nents, dir, attrs), TP_STRUCT__entry( __string(device, dev_name(dev)) @@ -234,12 +234,12 @@ TRACE_EVENT(dma_unmap_sg, ), TP_fast_assign( + struct scatterlist *sg; int i; __assign_str(device); - for (i = 0; i < nents; i++) - ((u64 *)__get_dynamic_array(addrs))[i] = - sg_phys(sg + i); + for_each_sg(sgl, sg, nents, i) + ((u64 *)__get_dynamic_array(addrs))[i] = sg_phys(sg); __entry->dir = dir; __entry->attrs = attrs; ), @@ -290,9 +290,9 @@ DEFINE_EVENT(dma_sync_single, dma_sync_single_for_device, TP_ARGS(dev, dma_addr, size, dir)); DECLARE_EVENT_CLASS(dma_sync_sg, - TP_PROTO(struct device *dev, struct scatterlist *sg, int nents, + TP_PROTO(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction dir), - TP_ARGS(dev, sg, nents, dir), + TP_ARGS(dev, sgl, nents, dir), TP_STRUCT__entry( __string(device, dev_name(dev)) @@ -302,14 +302,15 @@ DECLARE_EVENT_CLASS(dma_sync_sg, ), TP_fast_assign( + struct scatterlist *sg; int i; __assign_str(device); - for (i = 0; i < nents; i++) { + for_each_sg(sgl, sg, nents, i) { ((u64 *)__get_dynamic_array(dma_addrs))[i] = - sg_dma_address(sg + i); + sg_dma_address(sg); ((unsigned int *)__get_dynamic_array(lengths))[i] = - sg_dma_len(sg + i); + sg_dma_len(sg); } __entry->dir = dir; ), diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h index 3c2a101986a3..5ee30f882736 100644 --- a/include/uapi/linux/bits.h +++ b/include/uapi/linux/bits.h @@ -12,4 +12,7 @@ (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) + #endif /* _UAPI_LINUX_BITS_H */ diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index a429381e7ca5..e16be0d37746 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __BIT128() would not work in the asm code, as it shifts an + * 'unsigned __init128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting asm code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) diff --git a/include/uapi/xen/privcmd.h b/include/uapi/xen/privcmd.h index 8b8c5d1420fe..8e2c8fd44764 100644 --- a/include/uapi/xen/privcmd.h +++ b/include/uapi/xen/privcmd.h @@ -126,6 +126,11 @@ struct privcmd_ioeventfd { __u8 pad[2]; }; +struct privcmd_pcidev_get_gsi { + __u32 sbdf; + __u32 gsi; +}; + /* * @cmd: IOCTL_PRIVCMD_HYPERCALL * @arg: &privcmd_hypercall_t @@ -157,5 +162,7 @@ struct privcmd_ioeventfd { _IOW('P', 8, struct privcmd_irqfd) #define IOCTL_PRIVCMD_IOEVENTFD \ _IOW('P', 9, struct privcmd_ioeventfd) +#define IOCTL_PRIVCMD_PCIDEV_GET_GSI \ + _IOC(_IOC_NONE, 'P', 10, sizeof(struct privcmd_pcidev_get_gsi)) #endif /* __LINUX_PUBLIC_PRIVCMD_H__ */ diff --git a/include/xen/acpi.h b/include/xen/acpi.h index b1e11863144d..daa96a22d257 100644 --- a/include/xen/acpi.h +++ b/include/xen/acpi.h @@ -67,10 +67,37 @@ static inline void xen_acpi_sleep_register(void) acpi_suspend_lowlevel = xen_acpi_suspend_lowlevel; } } +int xen_pvh_setup_gsi(int gsi, int trigger, int polarity); +int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out); #else static inline void xen_acpi_sleep_register(void) { } + +static inline int xen_pvh_setup_gsi(int gsi, int trigger, int polarity) +{ + return -1; +} + +static inline int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out) +{ + return -1; +} +#endif + +#ifdef CONFIG_XEN_PCI_STUB +int pcistub_get_gsi_from_sbdf(unsigned int sbdf); +#else +static inline int pcistub_get_gsi_from_sbdf(unsigned int sbdf) +{ + return -1; +} #endif #endif /* _XEN_ACPI_H */ diff --git a/include/xen/interface/elfnote.h b/include/xen/interface/elfnote.h index 38deb1214613..918f47d87d7a 100644 --- a/include/xen/interface/elfnote.h +++ b/include/xen/interface/elfnote.h @@ -11,7 +11,9 @@ #define __XEN_PUBLIC_ELFNOTE_H__ /* - * The notes should live in a SHT_NOTE segment and have "Xen" in the + * `incontents 200 elfnotes ELF notes + * + * The notes should live in a PT_NOTE segment and have "Xen" in the * name field. * * Numeric types are either 4 or 8 bytes depending on the content of @@ -22,6 +24,8 @@ * * String values (for non-legacy) are NULL terminated ASCII, also known * as ASCIZ type. + * + * Xen only uses ELF Notes contained in x86 binaries. */ /* @@ -52,7 +56,7 @@ #define XEN_ELFNOTE_VIRT_BASE 3 /* - * The offset of the ELF paddr field from the acutal required + * The offset of the ELF paddr field from the actual required * pseudo-physical address (numeric). * * This is used to maintain backwards compatibility with older kernels @@ -92,7 +96,12 @@ #define XEN_ELFNOTE_LOADER 8 /* - * The kernel supports PAE (x86/32 only, string = "yes" or "no"). + * The kernel supports PAE (x86/32 only, string = "yes", "no" or + * "bimodal"). + * + * For compatibility with Xen 3.0.3 and earlier the "bimodal" setting + * may be given as "yes,bimodal" which will cause older Xen to treat + * this kernel as PAE. * * LEGACY: PAE (n.b. The legacy interface included a provision to * indicate 'extended-cr3' support allowing L3 page tables to be @@ -149,7 +158,9 @@ * The (non-default) location the initial phys-to-machine map should be * placed at by the hypervisor (Dom0) or the tools (DomU). * The kernel must be prepared for this mapping to be established using - * large pages, despite such otherwise not being available to guests. + * large pages, despite such otherwise not being available to guests. Note + * that these large pages may be misaligned in PFN space (they'll obviously + * be aligned in MFN and virtual address spaces). * The kernel must also be able to handle the page table pages used for * this mapping not being accessible through the initial mapping. * (Only x86-64 supports this at present.) @@ -186,8 +197,80 @@ #define XEN_ELFNOTE_PHYS32_ENTRY 18 /* + * Physical loading constraints for PVH kernels + * + * The presence of this note indicates the kernel supports relocating itself. + * + * The note may include up to three 32bit values to place constraints on the + * guest physical loading addresses and alignment for a PVH kernel. Values + * are read in the following order: + * - a required start alignment (default 0x200000) + * - a minimum address for the start of the image (default 0; see below) + * - a maximum address for the last byte of the image (default 0xffffffff) + * + * When this note specifies an alignment value, it is used. Otherwise the + * maximum p_align value from loadable ELF Program Headers is used, if it is + * greater than or equal to 4k (0x1000). Otherwise, the default is used. + */ +#define XEN_ELFNOTE_PHYS32_RELOC 19 + +/* * The number of the highest elfnote defined. */ -#define XEN_ELFNOTE_MAX XEN_ELFNOTE_PHYS32_ENTRY +#define XEN_ELFNOTE_MAX XEN_ELFNOTE_PHYS32_RELOC + +/* + * System information exported through crash notes. + * + * The kexec / kdump code will create one XEN_ELFNOTE_CRASH_INFO + * note in case of a system crash. This note will contain various + * information about the system, see xen/include/xen/elfcore.h. + */ +#define XEN_ELFNOTE_CRASH_INFO 0x1000001 + +/* + * System registers exported through crash notes. + * + * The kexec / kdump code will create one XEN_ELFNOTE_CRASH_REGS + * note per cpu in case of a system crash. This note is architecture + * specific and will contain registers not saved in the "CORE" note. + * See xen/include/xen/elfcore.h for more information. + */ +#define XEN_ELFNOTE_CRASH_REGS 0x1000002 + + +/* + * xen dump-core none note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_NONE + * in its dump file to indicate that the file is xen dump-core + * file. This note doesn't have any other information. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_NONE 0x2000000 + +/* + * xen dump-core header note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_HEADER + * in its dump file. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_HEADER 0x2000001 + +/* + * xen dump-core xen version note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_XEN_VERSION + * in its dump file. It contains the xen version obtained via the + * XENVER hypercall. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_XEN_VERSION 0x2000002 + +/* + * xen dump-core format version note. + * xm dump-core code will create one XEN_ELFNOTE_DUMPCORE_FORMAT_VERSION + * in its dump file. It contains a format version identifier. + * See tools/libxc/xc_core.h for more information. + */ +#define XEN_ELFNOTE_DUMPCORE_FORMAT_VERSION 0x2000003 #endif /* __XEN_PUBLIC_ELFNOTE_H__ */ diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h index a237af867873..df74e65a884b 100644 --- a/include/xen/interface/physdev.h +++ b/include/xen/interface/physdev.h @@ -256,6 +256,13 @@ struct physdev_pci_device_add { */ #define PHYSDEVOP_prepare_msix 30 #define PHYSDEVOP_release_msix 31 +/* + * Notify the hypervisor that a PCI device has been reset, so that any + * internally cached state is regenerated. Should be called after any + * device reset performed by the hardware domain. + */ +#define PHYSDEVOP_pci_device_reset 32 + struct physdev_pci_device { /* IN */ uint16_t seg; @@ -263,6 +270,16 @@ struct physdev_pci_device { uint8_t devfn; }; +struct pci_device_reset { + struct physdev_pci_device dev; +#define PCI_DEVICE_RESET_COLD 0x0 +#define PCI_DEVICE_RESET_WARM 0x1 +#define PCI_DEVICE_RESET_HOT 0x2 +#define PCI_DEVICE_RESET_FLR 0x3 +#define PCI_DEVICE_RESET_MASK 0x3 + uint32_t flags; +}; + #define PHYSDEVOP_DBGP_RESET_PREPARE 1 #define PHYSDEVOP_DBGP_RESET_DONE 2 diff --git a/include/xen/pci.h b/include/xen/pci.h index b8337cf85fd1..424b8ea89ca8 100644 --- a/include/xen/pci.h +++ b/include/xen/pci.h @@ -4,10 +4,16 @@ #define __XEN_PCI_H__ #if defined(CONFIG_XEN_DOM0) +int xen_reset_device(const struct pci_dev *dev); int xen_find_device_domain_owner(struct pci_dev *dev); int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); int xen_unregister_device_domain_owner(struct pci_dev *dev); #else +static inline int xen_reset_device(const struct pci_dev *dev) +{ + return -1; +} + static inline int xen_find_device_domain_owner(struct pci_dev *dev) { return -1; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 112581cf97e7..106735145948 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -283,7 +283,6 @@ static int iter_release(struct inode *inode, struct file *file) const struct file_operations bpf_iter_fops = { .open = iter_open, - .llseek = no_llseek, .read = bpf_seq_read, .release = iter_release, }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 5a8071c45c80..e3589c4287cb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6821,7 +6821,6 @@ static int perf_fasync(int fd, struct file *filp, int on) } static const struct file_operations perf_fops = { - .llseek = no_llseek, .release = perf_release, .read = perf_read, .poll = perf_poll, diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 6dc76b590703..93a822d3c468 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -168,7 +168,7 @@ bool static_key_slow_inc_cpuslocked(struct static_key *key) jump_label_update(key); /* * Ensure that when static_key_fast_inc_not_disabled() or - * static_key_slow_try_dec() observe the positive value, + * static_key_dec_not_one() observe the positive value, * they must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); @@ -250,7 +250,7 @@ void static_key_disable(struct static_key *key) } EXPORT_SYMBOL_GPL(static_key_disable); -static bool static_key_slow_try_dec(struct static_key *key) +static bool static_key_dec_not_one(struct static_key *key) { int v; @@ -274,6 +274,14 @@ static bool static_key_slow_try_dec(struct static_key *key) * enabled. This suggests an ordering problem on the user side. */ WARN_ON_ONCE(v < 0); + + /* + * Warn about underflow, and lie about success in an attempt to + * not make things worse. + */ + if (WARN_ON_ONCE(v == 0)) + return true; + if (v <= 1) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1))); @@ -284,15 +292,27 @@ static bool static_key_slow_try_dec(struct static_key *key) static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); + int val; - if (static_key_slow_try_dec(key)) + if (static_key_dec_not_one(key)) return; guard(mutex)(&jump_label_mutex); - if (atomic_cmpxchg(&key->enabled, 1, 0) == 1) + val = atomic_read(&key->enabled); + /* + * It should be impossible to observe -1 with jump_label_mutex held, + * see static_key_slow_inc_cpuslocked(). + */ + if (WARN_ON_ONCE(val == -1)) + return; + /* + * Cannot already be 0, something went sideways. + */ + if (WARN_ON_ONCE(val == 0)) + return; + + if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); - else - WARN_ON_ONCE(!static_key_slow_try_dec(key)); } static void __static_key_slow_dec(struct static_key *key) @@ -329,7 +349,7 @@ void __static_key_slow_dec_deferred(struct static_key *key, { STATIC_KEY_CHECK_USE(key); - if (static_key_slow_try_dec(key)) + if (static_key_dec_not_one(key)) return; schedule_delayed_work(work, timeout); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 7963deac33c3..536bd471557f 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -788,7 +788,7 @@ static void lockdep_print_held_locks(struct task_struct *p) printk("no locks held by %s/%d.\n", p->comm, task_pid_nr(p)); else printk("%d lock%s held by %s/%d:\n", depth, - depth > 1 ? "s" : "", p->comm, task_pid_nr(p)); + str_plural(depth), p->comm, task_pid_nr(p)); /* * It's not reliable to print a task's held locks if it's not sleeping * and it's not the current task. @@ -2084,6 +2084,9 @@ static noinline void print_bfs_bug(int ret) /* * Breadth-first-search failed, graph got corrupted? */ + if (ret == BFS_EQUEUEFULL) + pr_warn("Increase LOCKDEP_CIRCULAR_QUEUE_BITS to avoid this warning:\n"); + WARN(1, "lockdep bfs error:%d\n", ret); } @@ -6263,25 +6266,27 @@ static struct pending_free *get_pending_free(void) static void free_zapped_rcu(struct rcu_head *cb); /* - * Schedule an RCU callback if no RCU callback is pending. Must be called with - * the graph lock held. - */ -static void call_rcu_zapped(struct pending_free *pf) +* See if we need to queue an RCU callback, must called with +* the lockdep lock held, returns false if either we don't have +* any pending free or the callback is already scheduled. +* Otherwise, a call_rcu() must follow this function call. +*/ +static bool prepare_call_rcu_zapped(struct pending_free *pf) { WARN_ON_ONCE(inside_selftest()); if (list_empty(&pf->zapped)) - return; + return false; if (delayed_free.scheduled) - return; + return false; delayed_free.scheduled = true; WARN_ON_ONCE(delayed_free.pf + delayed_free.index != pf); delayed_free.index ^= 1; - call_rcu(&delayed_free.rcu_head, free_zapped_rcu); + return true; } /* The caller must hold the graph lock. May be called from RCU context. */ @@ -6307,6 +6312,7 @@ static void free_zapped_rcu(struct rcu_head *ch) { struct pending_free *pf; unsigned long flags; + bool need_callback; if (WARN_ON_ONCE(ch != &delayed_free.rcu_head)) return; @@ -6318,14 +6324,18 @@ static void free_zapped_rcu(struct rcu_head *ch) pf = delayed_free.pf + (delayed_free.index ^ 1); __free_zapped_classes(pf); delayed_free.scheduled = false; + need_callback = + prepare_call_rcu_zapped(delayed_free.pf + delayed_free.index); + lockdep_unlock(); + raw_local_irq_restore(flags); /* - * If there's anything on the open list, close and start a new callback. - */ - call_rcu_zapped(delayed_free.pf + delayed_free.index); + * If there's pending free and its callback has not been scheduled, + * queue an RCU callback. + */ + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); - lockdep_unlock(); - raw_local_irq_restore(flags); } /* @@ -6365,6 +6375,7 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size) { struct pending_free *pf; unsigned long flags; + bool need_callback; init_data_structures_once(); @@ -6372,10 +6383,11 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size) lockdep_lock(); pf = get_pending_free(); __lockdep_free_key_range(pf, start, size); - call_rcu_zapped(pf); + need_callback = prepare_call_rcu_zapped(pf); lockdep_unlock(); raw_local_irq_restore(flags); - + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); /* * Wait for any possible iterators from look_up_lock_class() to pass * before continuing to free the memory they refer to. @@ -6469,6 +6481,7 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock) struct pending_free *pf; unsigned long flags; int locked; + bool need_callback = false; raw_local_irq_save(flags); locked = graph_lock(); @@ -6477,11 +6490,13 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock) pf = get_pending_free(); __lockdep_reset_lock(pf, lock); - call_rcu_zapped(pf); + need_callback = prepare_call_rcu_zapped(pf); graph_unlock(); out_irq: raw_local_irq_restore(flags); + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); } /* @@ -6525,6 +6540,7 @@ void lockdep_unregister_key(struct lock_class_key *key) struct pending_free *pf; unsigned long flags; bool found = false; + bool need_callback = false; might_sleep(); @@ -6545,11 +6561,14 @@ void lockdep_unregister_key(struct lock_class_key *key) if (found) { pf = get_pending_free(); __lockdep_free_key_range(pf, key, 1); - call_rcu_zapped(pf); + need_callback = prepare_call_rcu_zapped(pf); } lockdep_unlock(); raw_local_irq_restore(flags); + if (need_callback) + call_rcu(&delayed_free.rcu_head, free_zapped_rcu); + /* Wait until is_dynamic_key() has finished accessing k->hash_entry. */ synchronize_rcu(); } diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index e2bfb1db589d..6db0f43fc4df 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -424,7 +424,7 @@ static void seq_line(struct seq_file *m, char c, int offset, int length) for (i = 0; i < offset; i++) seq_puts(m, " "); for (i = 0; i < length; i++) - seq_printf(m, "%c", c); + seq_putc(m, c); seq_puts(m, "\n"); } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 5ded7dff46ef..2bbb6eca5144 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -181,12 +181,21 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem) __rwsem_set_reader_owned(sem, current); } +#ifdef CONFIG_DEBUG_RWSEMS +/* + * Return just the real task structure pointer of the owner + */ +static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem) +{ + return (struct task_struct *) + (atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK); +} + /* * Return true if the rwsem is owned by a reader. */ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) { -#ifdef CONFIG_DEBUG_RWSEMS /* * Check the count to see if it is write-locked. */ @@ -194,11 +203,9 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem) if (count & RWSEM_WRITER_MASK) return false; -#endif return rwsem_test_oflags(sem, RWSEM_READER_OWNED); } -#ifdef CONFIG_DEBUG_RWSEMS /* * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there * is a task pointer in owner of a reader-owned rwsem, it will be the @@ -266,15 +273,6 @@ static inline bool rwsem_write_trylock(struct rw_semaphore *sem) } /* - * Return just the real task structure pointer of the owner - */ -static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem) -{ - return (struct task_struct *) - (atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK); -} - -/* * Return the real task structure pointer of the owner and the embedded * flags in the owner. pflags must be non-NULL. */ diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 05a9a06a140c..7c6588148d42 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -229,7 +229,7 @@ comment "Do not forget to sign required modules with scripts/sign-file" depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL choice - prompt "Which hash algorithm should modules be signed with?" + prompt "Hash algorithm to sign modules" depends on MODULE_SIG || IMA_APPRAISE_MODSIG help This determines which sort of hashing algorithm will be used during @@ -239,31 +239,31 @@ choice the signature on that module. config MODULE_SIG_SHA1 - bool "Sign modules with SHA-1" + bool "SHA-1" select CRYPTO_SHA1 config MODULE_SIG_SHA256 - bool "Sign modules with SHA-256" + bool "SHA-256" select CRYPTO_SHA256 config MODULE_SIG_SHA384 - bool "Sign modules with SHA-384" + bool "SHA-384" select CRYPTO_SHA512 config MODULE_SIG_SHA512 - bool "Sign modules with SHA-512" + bool "SHA-512" select CRYPTO_SHA512 config MODULE_SIG_SHA3_256 - bool "Sign modules with SHA3-256" + bool "SHA3-256" select CRYPTO_SHA3 config MODULE_SIG_SHA3_384 - bool "Sign modules with SHA3-384" + bool "SHA3-384" select CRYPTO_SHA3 config MODULE_SIG_SHA3_512 - bool "Sign modules with SHA3-512" + bool "SHA3-512" select CRYPTO_SHA3 endchoice @@ -279,64 +279,65 @@ config MODULE_SIG_HASH default "sha3-384" if MODULE_SIG_SHA3_384 default "sha3-512" if MODULE_SIG_SHA3_512 -choice - prompt "Module compression mode" +config MODULE_COMPRESS + bool "Module compression" help - This option allows you to choose the algorithm which will be used to - compress modules when 'make modules_install' is run. (or, you can - choose to not compress modules at all.) - - External modules will also be compressed in the same way during the - installation. - - For modules inside an initrd or initramfs, it's more efficient to - compress the whole initrd or initramfs instead. - + Enable module compression to reduce on-disk size of module binaries. This is fully compatible with signed modules. - Please note that the tool used to load modules needs to support the - corresponding algorithm. module-init-tools MAY support gzip, and kmod - MAY support gzip, xz and zstd. + The tool used to work with modules needs to support the selected + compression type. kmod MAY support gzip, xz and zstd. Other tools + might have a limited selection of the supported types. - Your build system needs to provide the appropriate compression tool - to compress the modules. + Note that for modules inside an initrd or initramfs, it's more + efficient to compress the whole ramdisk instead. - If in doubt, select 'None'. + If unsure, say N. -config MODULE_COMPRESS_NONE - bool "None" +choice + prompt "Module compression type" + depends on MODULE_COMPRESS help - Do not compress modules. The installed modules are suffixed - with .ko. + Choose the supported algorithm for module compression. config MODULE_COMPRESS_GZIP bool "GZIP" help - Compress modules with GZIP. The installed modules are suffixed - with .ko.gz. + Support modules compressed with GZIP. The installed modules are + suffixed with .ko.gz. config MODULE_COMPRESS_XZ bool "XZ" help - Compress modules with XZ. The installed modules are suffixed - with .ko.xz. + Support modules compressed with XZ. The installed modules are + suffixed with .ko.xz. config MODULE_COMPRESS_ZSTD bool "ZSTD" help - Compress modules with ZSTD. The installed modules are suffixed - with .ko.zst. + Support modules compressed with ZSTD. The installed modules are + suffixed with .ko.zst. endchoice +config MODULE_COMPRESS_ALL + bool "Automatically compress all modules" + default y + depends on MODULE_COMPRESS + help + Compress all modules during 'make modules_install'. + + Your build system needs to provide the appropriate compression tool + for the selected compression type. External modules will also be + compressed in the same way during the installation. + config MODULE_DECOMPRESS bool "Support in-kernel module decompression" - depends on MODULE_COMPRESS_GZIP || MODULE_COMPRESS_XZ || MODULE_COMPRESS_ZSTD + depends on MODULE_COMPRESS select ZLIB_INFLATE if MODULE_COMPRESS_GZIP select XZ_DEC if MODULE_COMPRESS_XZ select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD help - Support for decompressing kernel modules by the kernel itself instead of relying on userspace to perform this task. Useful when load pinning security policy is enabled. diff --git a/kernel/module/debug_kmemleak.c b/kernel/module/debug_kmemleak.c index 12a569d361e8..b4cc03842d70 100644 --- a/kernel/module/debug_kmemleak.c +++ b/kernel/module/debug_kmemleak.c @@ -12,19 +12,9 @@ void kmemleak_load_module(const struct module *mod, const struct load_info *info) { - unsigned int i; - - /* only scan the sections containing data */ - kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); - - for (i = 1; i < info->hdr->e_shnum; i++) { - /* Scan all writable sections that's not executable */ - if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) || - !(info->sechdrs[i].sh_flags & SHF_WRITE) || - (info->sechdrs[i].sh_flags & SHF_EXECINSTR)) - continue; - - kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, - info->sechdrs[i].sh_size, GFP_KERNEL); + /* only scan writable, non-executable sections */ + for_each_mod_mem_type(type) { + if (type != MOD_DATA && type != MOD_INIT_DATA) + kmemleak_no_scan(mod->mem[type].base); } } diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c index 26efe1305c12..456358e1fdc4 100644 --- a/kernel/module/sysfs.c +++ b/kernel/module/sysfs.c @@ -69,12 +69,13 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs) kfree(sect_attrs); } -static void add_sect_attrs(struct module *mod, const struct load_info *info) +static int add_sect_attrs(struct module *mod, const struct load_info *info) { unsigned int nloaded = 0, i, size[2]; struct module_sect_attrs *sect_attrs; struct module_sect_attr *sattr; struct bin_attribute **gattr; + int ret; /* Count loaded sections and allocate structures */ for (i = 0; i < info->hdr->e_shnum; i++) @@ -85,7 +86,7 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]); sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); if (!sect_attrs) - return; + return -ENOMEM; /* Setup section attributes. */ sect_attrs->grp.name = "sections"; @@ -103,8 +104,10 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) sattr->address = sec->sh_addr; sattr->battr.attr.name = kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); - if (!sattr->battr.attr.name) + if (!sattr->battr.attr.name) { + ret = -ENOMEM; goto out; + } sect_attrs->nsections++; sattr->battr.read = module_sect_read; sattr->battr.size = MODULE_SECT_READ_SIZE; @@ -113,13 +116,15 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info) } *gattr = NULL; - if (sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp)) + ret = sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp); + if (ret) goto out; mod->sect_attrs = sect_attrs; - return; + return 0; out: free_sect_attrs(sect_attrs); + return ret; } static void remove_sect_attrs(struct module *mod) @@ -158,15 +163,12 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs, kfree(notes_attrs); } -static void add_notes_attrs(struct module *mod, const struct load_info *info) +static int add_notes_attrs(struct module *mod, const struct load_info *info) { unsigned int notes, loaded, i; struct module_notes_attrs *notes_attrs; struct bin_attribute *nattr; - - /* failed to create section attributes, so can't create notes */ - if (!mod->sect_attrs) - return; + int ret; /* Count notes sections and allocate structures. */ notes = 0; @@ -176,12 +178,12 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) ++notes; if (notes == 0) - return; + return 0; notes_attrs = kzalloc(struct_size(notes_attrs, attrs, notes), GFP_KERNEL); if (!notes_attrs) - return; + return -ENOMEM; notes_attrs->notes = notes; nattr = ¬es_attrs->attrs[0]; @@ -201,19 +203,23 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info) } notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); - if (!notes_attrs->dir) + if (!notes_attrs->dir) { + ret = -ENOMEM; goto out; + } - for (i = 0; i < notes; ++i) - if (sysfs_create_bin_file(notes_attrs->dir, - ¬es_attrs->attrs[i])) + for (i = 0; i < notes; ++i) { + ret = sysfs_create_bin_file(notes_attrs->dir, ¬es_attrs->attrs[i]); + if (ret) goto out; + } mod->notes_attrs = notes_attrs; - return; + return 0; out: free_notes_attrs(notes_attrs, i); + return ret; } static void remove_notes_attrs(struct module *mod) @@ -223,9 +229,15 @@ static void remove_notes_attrs(struct module *mod) } #else /* !CONFIG_KALLSYMS */ -static inline void add_sect_attrs(struct module *mod, const struct load_info *info) { } +static inline int add_sect_attrs(struct module *mod, const struct load_info *info) +{ + return 0; +} static inline void remove_sect_attrs(struct module *mod) { } -static inline void add_notes_attrs(struct module *mod, const struct load_info *info) { } +static inline int add_notes_attrs(struct module *mod, const struct load_info *info) +{ + return 0; +} static inline void remove_notes_attrs(struct module *mod) { } #endif /* CONFIG_KALLSYMS */ @@ -385,11 +397,20 @@ int mod_sysfs_setup(struct module *mod, if (err) goto out_unreg_modinfo_attrs; - add_sect_attrs(mod, info); - add_notes_attrs(mod, info); + err = add_sect_attrs(mod, info); + if (err) + goto out_del_usage_links; + + err = add_notes_attrs(mod, info); + if (err) + goto out_unreg_sect_attrs; return 0; +out_unreg_sect_attrs: + remove_sect_attrs(mod); +out_del_usage_links: + del_usage_links(mod); out_unreg_modinfo_attrs: module_remove_modinfo_attrs(mod, -1); out_unreg_param: diff --git a/kernel/power/user.c b/kernel/power/user.c index 3aa41ba22129..3f9e3efb9f6e 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -447,7 +447,6 @@ static const struct file_operations snapshot_fops = { .release = snapshot_release, .read = snapshot_read, .write = snapshot_write, - .llseek = no_llseek, .unlocked_ioctl = snapshot_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = snapshot_compat_ioctl, diff --git a/kernel/relay.c b/kernel/relay.c index a8e90e98bf2c..a8ae436dc77e 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1079,7 +1079,6 @@ const struct file_operations relay_file_operations = { .poll = relay_file_poll, .mmap = relay_file_mmap, .read = relay_file_read, - .llseek = no_llseek, .release = relay_file_release, }; EXPORT_SYMBOL_GPL(relay_file_operations); diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c index 639397b5491c..5259cda486d0 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -411,6 +411,17 @@ static void static_call_del_module(struct module *mod) for (site = start; site < stop; site++) { key = static_call_key(site); + + /* + * If the key was not updated due to a memory allocation + * failure in __static_call_init() then treating key::sites + * as key::mods in the code below would cause random memory + * access and #GP. In that case all subsequent sites have + * not been touched either, so stop iterating. + */ + if (!static_call_key_has_mods(key)) + break; + if (key == prev_key) continue; @@ -442,7 +453,7 @@ static int static_call_module_notify(struct notifier_block *nb, case MODULE_STATE_COMING: ret = static_call_add_module(mod); if (ret) { - WARN(1, "Failed to allocate memory for static calls"); + pr_warn("Failed to allocate memory for static calls\n"); static_call_del_module(mod); } break; diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 4782edcbe7b9..c2f3d0c490d5 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -168,7 +168,6 @@ static int posix_clock_release(struct inode *inode, struct file *fp) static const struct file_operations posix_clock_file_operations = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = posix_clock_read, .poll = posix_clock_poll, .unlocked_ioctl = posix_clock_ioctl, diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index df0745a42a3f..dc819aec43e8 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -306,7 +306,6 @@ static ssize_t monitor_enable_write_data(struct file *filp, const char __user *u static const struct file_operations interface_enable_fops = { .open = simple_open, - .llseek = no_llseek, .write = monitor_enable_write_data, .read = monitor_enable_read_data, }; @@ -329,7 +328,6 @@ static ssize_t monitor_desc_read_data(struct file *filp, char __user *user_buf, static const struct file_operations interface_desc_fops = { .open = simple_open, - .llseek = no_llseek, .read = monitor_desc_read_data, }; @@ -674,7 +672,6 @@ static ssize_t monitoring_on_write_data(struct file *filp, const char __user *us static const struct file_operations monitoring_on_fops = { .open = simple_open, - .llseek = no_llseek, .write = monitoring_on_write_data, .read = monitoring_on_read_data, }; diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index 6aae106695b6..7b49cbe388d4 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -426,7 +426,6 @@ static ssize_t reacting_on_write_data(struct file *filp, const char __user *user static const struct file_operations reacting_on_fops = { .open = simple_open, - .llseek = no_llseek, .write = reacting_on_write_data, .read = reacting_on_read_data, }; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index b4f348b4653f..c01375adc471 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7557,7 +7557,6 @@ static const struct file_operations tracing_pipe_fops = { .read = tracing_read_pipe, .splice_read = tracing_splice_read_pipe, .release = tracing_release_pipe, - .llseek = no_llseek, }; static const struct file_operations tracing_entries_fops = { @@ -7636,7 +7635,6 @@ static const struct file_operations snapshot_raw_fops = { .read = tracing_buffers_read, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, - .llseek = no_llseek, }; #endif /* CONFIG_TRACER_SNAPSHOT */ @@ -8466,7 +8464,6 @@ static const struct file_operations tracing_buffers_fops = { .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, - .llseek = no_llseek, .mmap = tracing_buffers_mmap, }; diff --git a/lib/list-test.c b/lib/list-test.c index 4f3dc75baec1..e207c4c98d70 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -408,13 +408,10 @@ static void list_test_list_cut_position(struct kunit *test) KUNIT_EXPECT_EQ(test, i, 2); - i = 0; list_for_each(cur, &list1) { KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } - - KUNIT_EXPECT_EQ(test, i, 1); } static void list_test_list_cut_before(struct kunit *test) @@ -439,13 +436,10 @@ static void list_test_list_cut_before(struct kunit *test) KUNIT_EXPECT_EQ(test, i, 1); - i = 0; list_for_each(cur, &list1) { KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } - - KUNIT_EXPECT_EQ(test, i, 2); } static void list_test_list_splice(struct kunit *test) diff --git a/lib/test_bits.c b/lib/test_bits.c index 01313980f175..c7b38d91e1f1 100644 --- a/lib/test_bits.c +++ b/lib/test_bits.c @@ -39,6 +39,36 @@ static void genmask_ull_test(struct kunit *test) #endif } +static void genmask_u128_test(struct kunit *test) +{ +#ifdef CONFIG_ARCH_SUPPORTS_INT128 + /* Below 64 bit masks */ + KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(0, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(1, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000006ull, GENMASK_U128(2, 1)); + KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(31, 0)); + KUNIT_EXPECT_EQ(test, 0x000000ffffe00000ull, GENMASK_U128(39, 21)); + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(63, 0)); + + /* Above 64 bit masks - only 64 bit portion can be validated once */ + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(64, 0) >> 1); + KUNIT_EXPECT_EQ(test, 0x00000000ffffffffull, GENMASK_U128(81, 50) >> 50); + KUNIT_EXPECT_EQ(test, 0x0000000000ffffffull, GENMASK_U128(87, 64) >> 64); + KUNIT_EXPECT_EQ(test, 0x0000000000ff0000ull, GENMASK_U128(87, 80) >> 64); + + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, GENMASK_U128(127, 0) >> 64); + KUNIT_EXPECT_EQ(test, 0xffffffffffffffffull, (u64)GENMASK_U128(127, 0)); + KUNIT_EXPECT_EQ(test, 0x0000000000000003ull, GENMASK_U128(127, 126) >> 126); + KUNIT_EXPECT_EQ(test, 0x0000000000000001ull, GENMASK_U128(127, 127) >> 127); +#ifdef TEST_GENMASK_FAILURES + /* these should fail compilation */ + GENMASK_U128(0, 1); + GENMASK_U128(0, 10); + GENMASK_U128(9, 10); +#endif /* TEST_GENMASK_FAILURES */ +#endif /* CONFIG_ARCH_SUPPORTS_INT128 */ +} + static void genmask_input_check_test(struct kunit *test) { unsigned int x, y; @@ -56,12 +86,16 @@ static void genmask_input_check_test(struct kunit *test) /* Valid input */ KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(1, 1)); KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(39, 21)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(100, 80)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(110, 65)); + KUNIT_EXPECT_EQ(test, 0, GENMASK_INPUT_CHECK(127, 0)); } static struct kunit_case bits_test_cases[] = { KUNIT_CASE(genmask_test), KUNIT_CASE(genmask_ull_test), + KUNIT_CASE(genmask_u128_test), KUNIT_CASE(genmask_input_check_test), {} }; diff --git a/mm/Kconfig b/mm/Kconfig index 09aebca1cae3..4c9f5ea13271 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -595,6 +595,7 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE config SPLIT_PTE_PTLOCKS def_bool y depends on MMU + depends on SMP depends on NR_CPUS >= 4 depends on !ARM || CPU_CACHE_VIPT depends on !PARISC || PA20 diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index fecb8172410c..35b72f88983a 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -9,7 +9,7 @@ config DAMON access frequency of each memory region. The information can be useful for performance-centric DRAM level memory management. - See https://damonitor.github.io/doc/html/latest-damon/index.html for + See https://www.kernel.org/doc/html/latest/mm/damon/index.html for more information. config DAMON_KUNIT_TEST diff --git a/mm/filemap.c b/mm/filemap.c index bbaed3dd5049..36d22968be9a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2196,6 +2196,10 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, if (xa_is_value(folio)) goto update_start; + /* If we landed in the middle of a THP, continue at its end. */ + if (xa_is_sibling(folio)) + goto update_start; + if (!folio_try_get(folio)) goto retry; @@ -3700,6 +3700,7 @@ long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, ret = PTR_ERR(folio); if (ret != -EEXIST) goto err; + folio = NULL; } } } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0580ac9e47b9..3ca89e0279a7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -4115,7 +4115,6 @@ out: static const struct file_operations split_huge_pages_fops = { .owner = THIS_MODULE, .write = split_huge_pages_write, - .llseek = no_llseek, }; static int __init split_huge_pages_debugfs(void) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index def84d8bcf2d..190fa05635f4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2390,6 +2390,23 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, return folio; } +struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, + nodemask_t *nmask, gfp_t gfp_mask) +{ + struct folio *folio; + + spin_lock_irq(&hugetlb_lock); + folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, + nmask); + if (folio) { + VM_BUG_ON(!h->resv_huge_pages); + h->resv_huge_pages--; + } + + spin_unlock_irq(&hugetlb_lock); + return folio; +} + /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 451991a3a8f2..6370c5207d1a 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -109,7 +109,7 @@ static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadat const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track; u64 ts_sec = track->ts_nsec; unsigned long rem_nsec = do_div(ts_sec, NSEC_PER_SEC); - u64 interval_nsec = local_clock() - meta->alloc_track.ts_nsec; + u64 interval_nsec = local_clock() - track->ts_nsec; unsigned long rem_interval_nsec = do_div(interval_nsec, NSEC_PER_SEC); /* Timestamp matches printk timestamp format. */ diff --git a/mm/memfd.c b/mm/memfd.c index e7b7c5294d59..c17c3ea701a1 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -79,23 +79,25 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) * alloc from. Also, the folio will be pinned for an indefinite * amount of time, so it is not expected to be migrated away. */ - gfp_mask = htlb_alloc_mask(hstate_file(memfd)); + struct hstate *h = hstate_file(memfd); + + gfp_mask = htlb_alloc_mask(h); gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE); + idx >>= huge_page_order(h); - folio = alloc_hugetlb_folio_nodemask(hstate_file(memfd), - numa_node_id(), - NULL, - gfp_mask, - false); - if (folio && folio_try_get(folio)) { + folio = alloc_hugetlb_folio_reserve(h, + numa_node_id(), + NULL, + gfp_mask); + if (folio) { err = hugetlb_add_to_page_cache(folio, memfd->f_mapping, idx); if (err) { folio_put(folio); - free_huge_folio(folio); return ERR_PTR(err); } + folio_unlock(folio); return folio; } return ERR_PTR(-ENOMEM); diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 9842acebd05e..fc14fe53e9b7 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -768,10 +768,10 @@ int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, pr_info( "memory-tiers: the performance of DRAM node %d mismatches that of the reference\n" "DRAM node %d.\n", nid, default_dram_perf_ref_nid); - pr_info(" performance of reference DRAM node %d:\n", - default_dram_perf_ref_nid); + pr_info(" performance of reference DRAM node %d from %s:\n", + default_dram_perf_ref_nid, default_dram_perf_ref_source); dump_hmem_attrs(&default_dram_perf, " "); - pr_info(" performance of DRAM node %d:\n", nid); + pr_info(" performance of DRAM node %d from %s:\n", nid, source); dump_hmem_attrs(perf, " "); pr_info( " disable default DRAM node performance based abstract distance algorithm.\n"); diff --git a/mm/migrate.c b/mm/migrate.c index dfdb3a136bf8..df91248755e4 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1196,7 +1196,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio, int rc = -EAGAIN; int old_page_state = 0; struct anon_vma *anon_vma = NULL; - bool is_lru = !__folio_test_movable(src); + bool is_lru = data_race(!__folio_test_movable(src)); bool locked = false; bool dst_locked = false; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3c8b78d9c4d1..d1b5705dc0c6 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1254,7 +1254,7 @@ static int ceph_dns_resolve_name(const char *name, size_t namelen, colon_p = memchr(name, ':', namelen); if (delim_p && colon_p) - end = delim_p < colon_p ? delim_p : colon_p; + end = min(delim_p, colon_p); else if (!delim_p && colon_p) end = colon_p; else { diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index 25b8a67a63a4..85149c774505 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -187,7 +187,6 @@ static const struct file_operations minstrel_ht_stat_fops = { .open = minstrel_ht_stats_open, .read = minstrel_stats_read, .release = minstrel_stats_release, - .llseek = no_llseek, }; static char * @@ -323,7 +322,6 @@ static const struct file_operations minstrel_ht_stat_csv_fops = { .open = minstrel_ht_stats_csv_open, .read = minstrel_stats_read, .release = minstrel_stats_release, - .llseek = no_llseek, }; void diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 13a5126bc36e..7d3e82e4c2fc 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1394,7 +1394,6 @@ static const struct file_operations rfkill_fops = { .release = rfkill_fop_release, .unlocked_ioctl = rfkill_fop_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; #define RFKILL_NAME "rfkill" diff --git a/net/socket.c b/net/socket.c index 7b046dd3e9a7..601ad74930ef 100644 --- a/net/socket.c +++ b/net/socket.c @@ -153,7 +153,6 @@ static void sock_show_fdinfo(struct seq_file *m, struct file *f) static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 4f31e73dc34d..1bd3e531b0e0 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1592,7 +1592,6 @@ static int cache_release_procfs(struct inode *inode, struct file *filp) } static const struct proc_ops cache_channel_proc_ops = { - .proc_lseek = no_llseek, .proc_read = cache_read_procfs, .proc_write = cache_write_procfs, .proc_poll = cache_poll_procfs, @@ -1658,7 +1657,6 @@ static const struct proc_ops cache_flush_proc_ops = { .proc_read = read_flush_procfs, .proc_write = write_flush_procfs, .proc_release = release_flush_procfs, - .proc_lseek = no_llseek, }; static void remove_cache_proc_entries(struct cache_detail *cd) @@ -1811,7 +1809,6 @@ static int cache_release_pipefs(struct inode *inode, struct file *filp) const struct file_operations cache_file_operations_pipefs = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = cache_read_pipefs, .write = cache_write_pipefs, .poll = cache_poll_pipefs, @@ -1877,7 +1874,6 @@ const struct file_operations cache_flush_operations_pipefs = { .read = read_flush_pipefs, .write = write_flush_pipefs, .release = release_flush_pipefs, - .llseek = no_llseek, }; int sunrpc_cache_register_pipefs(struct dentry *parent, diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 910a5d850d04..7ce3721c06ca 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -385,7 +385,6 @@ rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static const struct file_operations rpc_pipe_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = rpc_pipe_read, .write = rpc_pipe_write, .poll = rpc_pipe_poll, diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index b382c696c877..59eefe2fed10 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -927,7 +927,6 @@ static const struct file_operations mtty_save_fops = { .unlocked_ioctl = mtty_precopy_ioctl, .compat_ioctl = compat_ptr_ioctl, .release = mtty_release_migf, - .llseek = no_llseek, }; static void mtty_save_state(struct mdev_state *mdev_state) @@ -1082,7 +1081,6 @@ static const struct file_operations mtty_resume_fops = { .owner = THIS_MODULE, .write = mtty_resume_write, .release = mtty_release_migf, - .llseek = no_llseek, }; static struct mtty_migration_file * diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 4d81ed9af294..d97720943189 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -53,9 +53,11 @@ $(foreach x, % :, $(if $(findstring $x, $(dst)), \ $(error module installation path cannot contain '$x'))) suffix-y := +ifdef CONFIG_MODULE_COMPRESS_ALL suffix-$(CONFIG_MODULE_COMPRESS_GZIP) := .gz suffix-$(CONFIG_MODULE_COMPRESS_XZ) := .xz suffix-$(CONFIG_MODULE_COMPRESS_ZSTD) := .zst +endif modules := $(patsubst $(extmod_prefix)%.o, $(dst)/%.ko$(suffix-y), $(modules)) install-$(CONFIG_MODULES) += $(modules) diff --git a/scripts/coccinelle/api/stream_open.cocci b/scripts/coccinelle/api/stream_open.cocci index df00d6619b06..50ab60c81f13 100644 --- a/scripts/coccinelle/api/stream_open.cocci +++ b/scripts/coccinelle/api/stream_open.cocci @@ -131,7 +131,6 @@ identifier llseek_f; identifier fops0.fops; @@ struct file_operations fops = { - .llseek = no_llseek, }; @ has_noop_llseek @ diff --git a/scripts/coccinelle/api/string_choices.cocci b/scripts/coccinelle/api/string_choices.cocci index 5e729f187f22..375045086912 100644 --- a/scripts/coccinelle/api/string_choices.cocci +++ b/scripts/coccinelle/api/string_choices.cocci @@ -14,23 +14,18 @@ expression E; - ((E == 1) ? "" : "s") + str_plural(E) | -- ((E != 1) ? "s" : "") -+ str_plural(E) -| - ((E > 1) ? "s" : "") + str_plural(E) ) -@str_plural_r depends on !patch exists@ +@str_plural_r depends on !patch@ expression E; position P; @@ ( -* ((E@P == 1) ? "" : "s") -| -* ((E@P != 1) ? "s" : "") +* (E@P == 1) ? "" : "s" | -* ((E@P > 1) ? "s" : "") +* (E@P > 1) ? "s" : "" ) @script:python depends on report@ @@ -40,21 +35,17 @@ e << str_plural_r.E; coccilib.report.print_report(p[0], "opportunity for str_plural(%s)" % e) -@str_up_down depends on patch@ +@str_up_down depends on patch disable neg_if_exp@ expression E; @@ -( - ((E) ? "up" : "down") + str_up_down(E) -) -@str_up_down_r depends on !patch exists@ +@str_up_down_r depends on !patch disable neg_if_exp@ expression E; position P; @@ -( -* ((E@P) ? "up" : "down") -) +* E@P ? "up" : "down" @script:python depends on report@ p << str_up_down_r.P; @@ -63,21 +54,17 @@ e << str_up_down_r.E; coccilib.report.print_report(p[0], "opportunity for str_up_down(%s)" % e) -@str_down_up depends on patch@ +@str_down_up depends on patch disable neg_if_exp@ expression E; @@ -( - ((E) ? "down" : "up") + str_down_up(E) -) -@str_down_up_r depends on !patch exists@ +@str_down_up_r depends on !patch disable neg_if_exp@ expression E; position P; @@ -( -* ((E@P) ? "down" : "up") -) +* E@P ? "down" : "up" @script:python depends on report@ p << str_down_up_r.P; @@ -85,3 +72,231 @@ e << str_down_up_r.E; @@ coccilib.report.print_report(p[0], "opportunity for str_down_up(%s)" % e) + +@str_true_false depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "true" : "false") ++ str_true_false(E) + +@str_true_false_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "true" : "false" + +@script:python depends on report@ +p << str_true_false_r.P; +e << str_true_false_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_true_false(%s)" % e) + +@str_false_true depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "false" : "true") ++ str_false_true(E) + +@str_false_true_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "false" : "true" + +@script:python depends on report@ +p << str_false_true_r.P; +e << str_false_true_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_false_true(%s)" % e) + +@str_hi_lo depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "hi" : "lo") ++ str_hi_lo(E) + +@str_hi_lo_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "hi" : "lo" + +@script:python depends on report@ +p << str_hi_lo_r.P; +e << str_hi_lo_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_hi_lo(%s)" % e) + +@str_high_low depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "high" : "low") ++ str_high_low(E) + +@str_high_low_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "high" : "low" + +@script:python depends on report@ +p << str_high_low_r.P; +e << str_high_low_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_high_low(%s)" % e) + +@str_lo_hi depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "lo" : "hi") ++ str_lo_hi(E) + +@str_lo_hi_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "lo" : "hi" + +@script:python depends on report@ +p << str_lo_hi_r.P; +e << str_lo_hi_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_lo_hi(%s)" % e) + +@str_low_high depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "low" : "high") ++ str_low_high(E) + +@str_low_high_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "low" : "high" + +@script:python depends on report@ +p << str_low_high_r.P; +e << str_low_high_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_low_high(%s)" % e) + +@str_enable_disable depends on patch@ +expression E; +@@ +- ((E) ? "enable" : "disable") ++ str_enable_disable(E) + +@str_enable_disable_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "enable" : "disable" + +@script:python depends on report@ +p << str_enable_disable_r.P; +e << str_enable_disable_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_enable_disable(%s)" % e) + +@str_enabled_disabled depends on patch@ +expression E; +@@ +- ((E) ? "enabled" : "disabled") ++ str_enabled_disabled(E) + +@str_enabled_disabled_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "enabled" : "disabled" + +@script:python depends on report@ +p << str_enabled_disabled_r.P; +e << str_enabled_disabled_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_enabled_disabled(%s)" % e) + +@str_read_write depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "read" : "write") ++ str_read_write(E) + +@str_read_write_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "read" : "write" + +@script:python depends on report@ +p << str_read_write_r.P; +e << str_read_write_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_read_write(%s)" % e) + +@str_write_read depends on patch disable neg_if_exp@ +expression E; +@@ +- ((E) ? "write" : "read") ++ str_write_read(E) + +@str_write_read_r depends on !patch disable neg_if_exp@ +expression E; +position P; +@@ +* E@P ? "write" : "read" + +@script:python depends on report@ +p << str_write_read_r.P; +e << str_write_read_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_write_read(%s)" % e) + +@str_on_off depends on patch@ +expression E; +@@ +- ((E) ? "on" : "off") ++ str_on_off(E) + +@str_on_off_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "on" : "off" + +@script:python depends on report@ +p << str_on_off_r.P; +e << str_on_off_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_on_off(%s)" % e) + +@str_yes_no depends on patch@ +expression E; +@@ +- ((E) ? "yes" : "no") ++ str_yes_no(E) + +@str_yes_no_r depends on !patch@ +expression E; +position P; +@@ +* E@P ? "yes" : "no" + +@script:python depends on report@ +p << str_yes_no_r.P; +e << str_yes_no_r.E; +@@ + +coccilib.report.print_report(p[0], "opportunity for str_yes_no(%s)" % e) diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig index 1e0dd1a6d0b0..90eccc6cd464 100644 --- a/security/tomoyo/Kconfig +++ b/security/tomoyo/Kconfig @@ -13,6 +13,21 @@ config SECURITY_TOMOYO found at <https://tomoyo.sourceforge.net/>. If you are unsure how to answer this question, answer N. +config SECURITY_TOMOYO_LKM + bool "Cut out most of TOMOYO's code to a loadable kernel module" + default n + depends on SECURITY_TOMOYO + depends on MODULES + help + Say Y here if you want to include TOMOYO without bloating + vmlinux file. If you say Y, most of TOMOYO code is cut out to + a loadable kernel module named tomoyo.ko . This option will be + useful for kernels built by Linux distributors where TOMOYO is + included but TOMOYO is not enabled by default. Please be sure + to explicitly load tomoyo.ko if you want to activate TOMOYO + without calling userspace policy loader, for tomoyo.ko is + loaded immediately before calling userspace policy loader. + config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY int "Default maximal count for learning mode" default 2048 diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index 55c67b9846a9..287a7d16fa15 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -1,5 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o +tomoyo-objs := audit.o common.o condition.o domain.o environ.o file.o gc.o group.o memory.o mount.o network.o proxy.o realpath.o securityfs_if.o util.o +obj-y += init.o load_policy.o +ifdef CONFIG_SECURITY_TOMOYO_LKM +obj-m += tomoyo.o +else +obj-y += tomoyo.o +endif targets += builtin-policy.h diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 5c7b059a332a..c0ef014f8009 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -998,8 +998,13 @@ static bool tomoyo_select_domain(struct tomoyo_io_buffer *head, p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); - if (p) + if (p) { domain = tomoyo_task(p)->domain_info; +#ifdef CONFIG_SECURITY_TOMOYO_LKM + if (!domain) + domain = &tomoyo_kernel_domain; +#endif + } rcu_read_unlock(); } else if (!strncmp(data, "domain=", 7)) { if (tomoyo_domain_def(data + 7)) @@ -1710,8 +1715,13 @@ static void tomoyo_read_pid(struct tomoyo_io_buffer *head) p = find_task_by_pid_ns(pid, &init_pid_ns); else p = find_task_by_vpid(pid); - if (p) + if (p) { domain = tomoyo_task(p)->domain_info; +#ifdef CONFIG_SECURITY_TOMOYO_LKM + if (!domain) + domain = &tomoyo_kernel_domain; +#endif + } rcu_read_unlock(); if (!domain) return; diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h index 0e8e2e959aef..4f6c52a9f478 100644 --- a/security/tomoyo/common.h +++ b/security/tomoyo/common.h @@ -978,6 +978,7 @@ int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index); +int __init tomoyo_interface_init(void); int tomoyo_mkdev_perm(const u8 operation, const struct path *path, const unsigned int mode, unsigned int dev); int tomoyo_mount_permission(const char *dev_name, const struct path *path, @@ -1214,10 +1215,14 @@ static inline void tomoyo_put_group(struct tomoyo_group *group) * * Returns pointer to "struct tomoyo_task" for specified thread. */ +#ifdef CONFIG_SECURITY_TOMOYO_LKM +extern struct tomoyo_task *tomoyo_task(struct task_struct *task); +#else static inline struct tomoyo_task *tomoyo_task(struct task_struct *task) { return task->security + tomoyo_blob_sizes.lbs_task; } +#endif /** * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry. @@ -1284,4 +1289,71 @@ static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void) pos = srcu_dereference((head)->next, &tomoyo_ss); \ for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss)) +#ifdef CONFIG_SECURITY_TOMOYO_LKM + +#define LSM_HOOK(RET, DEFAULT, NAME, ...) typedef RET (NAME##_t)(__VA_ARGS__); +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK + +struct tomoyo_hooks { + cred_prepare_t *cred_prepare; + bprm_committed_creds_t *bprm_committed_creds; + task_alloc_t *task_alloc; + task_free_t *task_free; + bprm_check_security_t *bprm_check_security; + file_fcntl_t *file_fcntl; + file_open_t *file_open; + file_truncate_t *file_truncate; + path_truncate_t *path_truncate; + path_unlink_t *path_unlink; + path_mkdir_t *path_mkdir; + path_rmdir_t *path_rmdir; + path_symlink_t *path_symlink; + path_mknod_t *path_mknod; + path_link_t *path_link; + path_rename_t *path_rename; + inode_getattr_t *inode_getattr; + file_ioctl_t *file_ioctl; + file_ioctl_compat_t *file_ioctl_compat; + path_chmod_t *path_chmod; + path_chown_t *path_chown; + path_chroot_t *path_chroot; + sb_mount_t *sb_mount; + sb_umount_t *sb_umount; + sb_pivotroot_t *sb_pivotroot; + socket_bind_t *socket_bind; + socket_connect_t *socket_connect; + socket_listen_t *socket_listen; + socket_sendmsg_t *socket_sendmsg; +}; + +extern void tomoyo_register_hooks(const struct tomoyo_hooks *tomoyo_hooks); + +struct tomoyo_operations { + void (*check_profile)(void); + int enabled; +}; + +extern struct tomoyo_operations tomoyo_ops; + +/* + * Temporary hack: functions needed by tomoyo.ko . This will be removed + * after all functions are marked as EXPORT_STMBOL_GPL(). + */ +struct tomoyo_tmp_exports { + struct task_struct * (*find_task_by_vpid)(pid_t nr); + struct task_struct * (*find_task_by_pid_ns)(pid_t nr, struct pid_namespace *ns); + void (*put_filesystem)(struct file_system_type *fs); + struct file * (*get_mm_exe_file)(struct mm_struct *mm); + char * (*d_absolute_path)(const struct path *path, char *buf, int buflen); +}; +extern const struct tomoyo_tmp_exports tomoyo_tmp_exports; +#define find_task_by_vpid tomoyo_tmp_exports.find_task_by_vpid +#define find_task_by_pid_ns tomoyo_tmp_exports.find_task_by_pid_ns +#define put_filesystem tomoyo_tmp_exports.put_filesystem +#define get_mm_exe_file tomoyo_tmp_exports.get_mm_exe_file +#define d_absolute_path tomoyo_tmp_exports.d_absolute_path + +#endif /* defined(CONFIG_SECURITY_TOMOYO_LKM) */ + #endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */ diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 90b53500a236..aed9e3ef2c9e 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -723,10 +723,13 @@ int tomoyo_find_next_domain(struct linux_binprm *bprm) ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* Get symlink's pathname of program. */ - retval = -ENOENT; exename.name = tomoyo_realpath_nofollow(original_name); - if (!exename.name) - goto out; + if (!exename.name) { + /* Fallback to realpath if symlink's pathname does not exist. */ + exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); + if (!exename.name) + goto out; + } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ diff --git a/security/tomoyo/gc.c b/security/tomoyo/gc.c index 026e29ea3796..6eccca150839 100644 --- a/security/tomoyo/gc.c +++ b/security/tomoyo/gc.c @@ -9,6 +9,9 @@ #include <linux/kthread.h> #include <linux/slab.h> +/* Lock for GC. */ +DEFINE_SRCU(tomoyo_ss); + /** * tomoyo_memory_free - Free memory for elements. * diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/hooks.h index 04a92c3d65d4..58929bb71477 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/hooks.h @@ -1,12 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* - * security/tomoyo/tomoyo.c + * security/tomoyo/hooks.h * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ -#include <linux/lsm_hooks.h> -#include <uapi/linux/lsm.h> #include "common.h" /** @@ -18,10 +16,6 @@ struct tomoyo_domain_info *tomoyo_domain(void) { struct tomoyo_task *s = tomoyo_task(current); - if (s->old_domain_info && !current->in_execve) { - atomic_dec(&s->old_domain_info->users); - s->old_domain_info = NULL; - } return s->domain_info; } @@ -62,26 +56,6 @@ static void tomoyo_bprm_committed_creds(const struct linux_binprm *bprm) s->old_domain_info = NULL; } -#ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER -/** - * tomoyo_bprm_creds_for_exec - Target for security_bprm_creds_for_exec(). - * - * @bprm: Pointer to "struct linux_binprm". - * - * Returns 0. - */ -static int tomoyo_bprm_creds_for_exec(struct linux_binprm *bprm) -{ - /* - * Load policy if /sbin/tomoyo-init exists and /sbin/init is requested - * for the first time. - */ - if (!tomoyo_policy_loaded) - tomoyo_load_policy(bprm->filename); - return 0; -} -#endif - /** * tomoyo_bprm_check_security - Target for security_bprm_check(). * @@ -501,10 +475,6 @@ static int tomoyo_socket_sendmsg(struct socket *sock, struct msghdr *msg, return tomoyo_socket_sendmsg_permission(sock, msg, size); } -struct lsm_blob_sizes tomoyo_blob_sizes __ro_after_init = { - .lbs_task = sizeof(struct tomoyo_task), -}; - /** * tomoyo_task_alloc - Target for security_task_alloc(). * @@ -543,81 +513,3 @@ static void tomoyo_task_free(struct task_struct *task) s->old_domain_info = NULL; } } - -static const struct lsm_id tomoyo_lsmid = { - .name = "tomoyo", - .id = LSM_ID_TOMOYO, -}; - -/* - * tomoyo_security_ops is a "struct security_operations" which is used for - * registering TOMOYO. - */ -static struct security_hook_list tomoyo_hooks[] __ro_after_init = { - LSM_HOOK_INIT(cred_prepare, tomoyo_cred_prepare), - LSM_HOOK_INIT(bprm_committed_creds, tomoyo_bprm_committed_creds), - LSM_HOOK_INIT(task_alloc, tomoyo_task_alloc), - LSM_HOOK_INIT(task_free, tomoyo_task_free), -#ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER - LSM_HOOK_INIT(bprm_creds_for_exec, tomoyo_bprm_creds_for_exec), -#endif - LSM_HOOK_INIT(bprm_check_security, tomoyo_bprm_check_security), - LSM_HOOK_INIT(file_fcntl, tomoyo_file_fcntl), - LSM_HOOK_INIT(file_open, tomoyo_file_open), - LSM_HOOK_INIT(file_truncate, tomoyo_file_truncate), - LSM_HOOK_INIT(path_truncate, tomoyo_path_truncate), - LSM_HOOK_INIT(path_unlink, tomoyo_path_unlink), - LSM_HOOK_INIT(path_mkdir, tomoyo_path_mkdir), - LSM_HOOK_INIT(path_rmdir, tomoyo_path_rmdir), - LSM_HOOK_INIT(path_symlink, tomoyo_path_symlink), - LSM_HOOK_INIT(path_mknod, tomoyo_path_mknod), - LSM_HOOK_INIT(path_link, tomoyo_path_link), - LSM_HOOK_INIT(path_rename, tomoyo_path_rename), - LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr), - LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl), - LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl), - LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod), - LSM_HOOK_INIT(path_chown, tomoyo_path_chown), - LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot), - LSM_HOOK_INIT(sb_mount, tomoyo_sb_mount), - LSM_HOOK_INIT(sb_umount, tomoyo_sb_umount), - LSM_HOOK_INIT(sb_pivotroot, tomoyo_sb_pivotroot), - LSM_HOOK_INIT(socket_bind, tomoyo_socket_bind), - LSM_HOOK_INIT(socket_connect, tomoyo_socket_connect), - LSM_HOOK_INIT(socket_listen, tomoyo_socket_listen), - LSM_HOOK_INIT(socket_sendmsg, tomoyo_socket_sendmsg), -}; - -/* Lock for GC. */ -DEFINE_SRCU(tomoyo_ss); - -int tomoyo_enabled __ro_after_init = 1; - -/** - * tomoyo_init - Register TOMOYO Linux as a LSM module. - * - * Returns 0. - */ -static int __init tomoyo_init(void) -{ - struct tomoyo_task *s = tomoyo_task(current); - - /* register ourselves with the security framework */ - security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), - &tomoyo_lsmid); - pr_info("TOMOYO Linux initialized\n"); - s->domain_info = &tomoyo_kernel_domain; - atomic_inc(&tomoyo_kernel_domain.users); - s->old_domain_info = NULL; - tomoyo_mm_init(); - - return 0; -} - -DEFINE_LSM(tomoyo) = { - .name = "tomoyo", - .enabled = &tomoyo_enabled, - .flags = LSM_FLAG_LEGACY_MAJOR, - .blobs = &tomoyo_blob_sizes, - .init = tomoyo_init, -}; diff --git a/security/tomoyo/init.c b/security/tomoyo/init.c new file mode 100644 index 000000000000..034e7db22d4e --- /dev/null +++ b/security/tomoyo/init.c @@ -0,0 +1,366 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * security/tomoyo/init.c + * + * Copyright (C) 2005-2011 NTT DATA CORPORATION + */ + +#include <linux/lsm_hooks.h> +#include <uapi/linux/lsm.h> +#include "common.h" + +#ifndef CONFIG_SECURITY_TOMOYO_LKM + +#include "hooks.h" + +#else + +#define DEFINE_STATIC_CALL_PROXY(NAME) \ + static NAME##_t tomoyo_##NAME; \ + DEFINE_STATIC_CALL_RET0(tomoyo_##NAME, tomoyo_##NAME); +DEFINE_STATIC_CALL_PROXY(cred_prepare) +DEFINE_STATIC_CALL_PROXY(bprm_committed_creds) +DEFINE_STATIC_CALL_PROXY(bprm_check_security) +DEFINE_STATIC_CALL_PROXY(inode_getattr) +DEFINE_STATIC_CALL_PROXY(path_truncate) +DEFINE_STATIC_CALL_PROXY(file_truncate) +DEFINE_STATIC_CALL_PROXY(path_unlink) +DEFINE_STATIC_CALL_PROXY(path_mkdir) +DEFINE_STATIC_CALL_PROXY(path_rmdir) +DEFINE_STATIC_CALL_PROXY(path_symlink) +DEFINE_STATIC_CALL_PROXY(path_mknod) +DEFINE_STATIC_CALL_PROXY(path_link) +DEFINE_STATIC_CALL_PROXY(path_rename) +DEFINE_STATIC_CALL_PROXY(file_fcntl) +DEFINE_STATIC_CALL_PROXY(file_open) +DEFINE_STATIC_CALL_PROXY(file_ioctl) +DEFINE_STATIC_CALL_PROXY(path_chmod) +DEFINE_STATIC_CALL_PROXY(path_chown) +DEFINE_STATIC_CALL_PROXY(path_chroot) +DEFINE_STATIC_CALL_PROXY(sb_mount) +DEFINE_STATIC_CALL_PROXY(sb_umount) +DEFINE_STATIC_CALL_PROXY(sb_pivotroot) +DEFINE_STATIC_CALL_PROXY(socket_listen) +DEFINE_STATIC_CALL_PROXY(socket_connect) +DEFINE_STATIC_CALL_PROXY(socket_bind) +DEFINE_STATIC_CALL_PROXY(socket_sendmsg) +DEFINE_STATIC_CALL_PROXY(task_alloc) +DEFINE_STATIC_CALL_PROXY(task_free) +#undef DEFINE_STATIC_CALL_PROXY + +static int tomoyo_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) +{ + return static_call(tomoyo_cred_prepare)(new, old, gfp); +} + +static void tomoyo_bprm_committed_creds(const struct linux_binprm *bprm) +{ + static_call(tomoyo_bprm_committed_creds)(bprm); +} + +static int tomoyo_bprm_check_security(struct linux_binprm *bprm) +{ + return static_call(tomoyo_bprm_check_security)(bprm); +} + +static int tomoyo_inode_getattr(const struct path *path) +{ + return static_call(tomoyo_inode_getattr)(path); +} + +static int tomoyo_path_truncate(const struct path *path) +{ + return static_call(tomoyo_path_truncate)(path); +} + +static int tomoyo_file_truncate(struct file *file) +{ + return static_call(tomoyo_file_truncate)(file); +} + +static int tomoyo_path_unlink(const struct path *parent, struct dentry *dentry) +{ + return static_call(tomoyo_path_unlink)(parent, dentry); +} + +static int tomoyo_path_mkdir(const struct path *parent, struct dentry *dentry, umode_t mode) +{ + return static_call(tomoyo_path_mkdir)(parent, dentry, mode); +} + +static int tomoyo_path_rmdir(const struct path *parent, struct dentry *dentry) +{ + return static_call(tomoyo_path_rmdir)(parent, dentry); +} + +static int tomoyo_path_symlink(const struct path *parent, struct dentry *dentry, + const char *old_name) +{ + return static_call(tomoyo_path_symlink)(parent, dentry, old_name); +} + +static int tomoyo_path_mknod(const struct path *parent, struct dentry *dentry, + umode_t mode, unsigned int dev) +{ + return static_call(tomoyo_path_mknod)(parent, dentry, mode, dev); +} + +static int tomoyo_path_link(struct dentry *old_dentry, const struct path *new_dir, + struct dentry *new_dentry) +{ + return static_call(tomoyo_path_link)(old_dentry, new_dir, new_dentry); +} + +static int tomoyo_path_rename(const struct path *old_parent, struct dentry *old_dentry, + const struct path *new_parent, struct dentry *new_dentry, + const unsigned int flags) +{ + return static_call(tomoyo_path_rename)(old_parent, old_dentry, new_parent, new_dentry, flags); +} + +static int tomoyo_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return static_call(tomoyo_file_fcntl)(file, cmd, arg); +} + +static int tomoyo_file_open(struct file *f) +{ + return static_call(tomoyo_file_open)(f); +} + +static int tomoyo_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return static_call(tomoyo_file_ioctl)(file, cmd, arg); +} + +static int tomoyo_path_chmod(const struct path *path, umode_t mode) +{ + return static_call(tomoyo_path_chmod)(path, mode); +} + +static int tomoyo_path_chown(const struct path *path, kuid_t uid, kgid_t gid) +{ + return static_call(tomoyo_path_chown)(path, uid, gid); +} + +static int tomoyo_path_chroot(const struct path *path) +{ + return static_call(tomoyo_path_chroot)(path); +} + +static int tomoyo_sb_mount(const char *dev_name, const struct path *path, + const char *type, unsigned long flags, void *data) +{ + return static_call(tomoyo_sb_mount)(dev_name, path, type, flags, data); +} + +static int tomoyo_sb_umount(struct vfsmount *mnt, int flags) +{ + return static_call(tomoyo_sb_umount)(mnt, flags); +} + +static int tomoyo_sb_pivotroot(const struct path *old_path, const struct path *new_path) +{ + return static_call(tomoyo_sb_pivotroot)(old_path, new_path); +} + +static int tomoyo_socket_listen(struct socket *sock, int backlog) +{ + return static_call(tomoyo_socket_listen)(sock, backlog); +} + +static int tomoyo_socket_connect(struct socket *sock, struct sockaddr *addr, int addr_len) +{ + return static_call(tomoyo_socket_connect)(sock, addr, addr_len); +} + +static int tomoyo_socket_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +{ + return static_call(tomoyo_socket_bind)(sock, addr, addr_len); +} + +static int tomoyo_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) +{ + return static_call(tomoyo_socket_sendmsg)(sock, msg, size); +} + +static int tomoyo_task_alloc(struct task_struct *task, unsigned long clone_flags) +{ + return static_call(tomoyo_task_alloc)(task, clone_flags); +} + +static void tomoyo_task_free(struct task_struct *task) +{ + static_call(tomoyo_task_free)(task); +} + +void tomoyo_register_hooks(const struct tomoyo_hooks *tomoyo_hooks) +{ + static void *registered; + + if (cmpxchg(®istered, NULL, ®istered)) + panic("%s was called twice!\n", __func__); + static_call_update(tomoyo_task_free, tomoyo_hooks->task_free); + static_call_update(tomoyo_task_alloc, tomoyo_hooks->task_alloc); + static_call_update(tomoyo_cred_prepare, tomoyo_hooks->cred_prepare); + static_call_update(tomoyo_bprm_committed_creds, tomoyo_hooks->bprm_committed_creds); + static_call_update(tomoyo_bprm_check_security, tomoyo_hooks->bprm_check_security); + static_call_update(tomoyo_inode_getattr, tomoyo_hooks->inode_getattr); + static_call_update(tomoyo_path_truncate, tomoyo_hooks->path_truncate); + static_call_update(tomoyo_file_truncate, tomoyo_hooks->file_truncate); + static_call_update(tomoyo_path_unlink, tomoyo_hooks->path_unlink); + static_call_update(tomoyo_path_mkdir, tomoyo_hooks->path_mkdir); + static_call_update(tomoyo_path_rmdir, tomoyo_hooks->path_rmdir); + static_call_update(tomoyo_path_symlink, tomoyo_hooks->path_symlink); + static_call_update(tomoyo_path_mknod, tomoyo_hooks->path_mknod); + static_call_update(tomoyo_path_link, tomoyo_hooks->path_link); + static_call_update(tomoyo_path_rename, tomoyo_hooks->path_rename); + static_call_update(tomoyo_file_fcntl, tomoyo_hooks->file_fcntl); + static_call_update(tomoyo_file_open, tomoyo_hooks->file_open); + static_call_update(tomoyo_file_ioctl, tomoyo_hooks->file_ioctl); + static_call_update(tomoyo_path_chmod, tomoyo_hooks->path_chmod); + static_call_update(tomoyo_path_chown, tomoyo_hooks->path_chown); + static_call_update(tomoyo_path_chroot, tomoyo_hooks->path_chroot); + static_call_update(tomoyo_sb_mount, tomoyo_hooks->sb_mount); + static_call_update(tomoyo_sb_umount, tomoyo_hooks->sb_umount); + static_call_update(tomoyo_sb_pivotroot, tomoyo_hooks->sb_pivotroot); + static_call_update(tomoyo_socket_listen, tomoyo_hooks->socket_listen); + static_call_update(tomoyo_socket_connect, tomoyo_hooks->socket_connect); + static_call_update(tomoyo_socket_bind, tomoyo_hooks->socket_bind); + static_call_update(tomoyo_socket_sendmsg, tomoyo_hooks->socket_sendmsg); +} +EXPORT_SYMBOL_GPL(tomoyo_register_hooks); + +/* + * Temporary hack: functions needed by tomoyo.ko . This hack will be removed + * after all functions are marked as EXPORT_STMBOL_GPL(). + */ +#undef find_task_by_vpid +#undef find_task_by_pid_ns +#undef put_filesystem +#undef get_mm_exe_file +#undef d_absolute_path +const struct tomoyo_tmp_exports tomoyo_tmp_exports = { + .find_task_by_vpid = find_task_by_vpid, + .find_task_by_pid_ns = find_task_by_pid_ns, + .put_filesystem = put_filesystem, + .get_mm_exe_file = get_mm_exe_file, + .d_absolute_path = d_absolute_path, +}; +EXPORT_SYMBOL_GPL(tomoyo_tmp_exports); + +#endif + +#ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER +static int tomoyo_bprm_creds_for_exec(struct linux_binprm *bprm) +{ + /* + * Load policy if /sbin/tomoyo-init exists and /sbin/init is requested + * for the first time. + */ + if (!tomoyo_policy_loaded) + tomoyo_load_policy(bprm->filename); + return 0; +} +#endif + +struct lsm_blob_sizes tomoyo_blob_sizes __ro_after_init = { + .lbs_task = sizeof(struct tomoyo_task), +}; + +static const struct lsm_id tomoyo_lsmid = { + .name = "tomoyo", + .id = LSM_ID_TOMOYO, +}; + +/* tomoyo_hooks is used for registering TOMOYO. */ +static struct security_hook_list tomoyo_hooks[] __ro_after_init = { + LSM_HOOK_INIT(cred_prepare, tomoyo_cred_prepare), + LSM_HOOK_INIT(bprm_committed_creds, tomoyo_bprm_committed_creds), + LSM_HOOK_INIT(task_alloc, tomoyo_task_alloc), + LSM_HOOK_INIT(task_free, tomoyo_task_free), +#ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER + LSM_HOOK_INIT(bprm_creds_for_exec, tomoyo_bprm_creds_for_exec), +#endif + LSM_HOOK_INIT(bprm_check_security, tomoyo_bprm_check_security), + LSM_HOOK_INIT(file_fcntl, tomoyo_file_fcntl), + LSM_HOOK_INIT(file_open, tomoyo_file_open), + LSM_HOOK_INIT(file_truncate, tomoyo_file_truncate), + LSM_HOOK_INIT(path_truncate, tomoyo_path_truncate), + LSM_HOOK_INIT(path_unlink, tomoyo_path_unlink), + LSM_HOOK_INIT(path_mkdir, tomoyo_path_mkdir), + LSM_HOOK_INIT(path_rmdir, tomoyo_path_rmdir), + LSM_HOOK_INIT(path_symlink, tomoyo_path_symlink), + LSM_HOOK_INIT(path_mknod, tomoyo_path_mknod), + LSM_HOOK_INIT(path_link, tomoyo_path_link), + LSM_HOOK_INIT(path_rename, tomoyo_path_rename), + LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr), + LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl), + LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl), + LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod), + LSM_HOOK_INIT(path_chown, tomoyo_path_chown), + LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot), + LSM_HOOK_INIT(sb_mount, tomoyo_sb_mount), + LSM_HOOK_INIT(sb_umount, tomoyo_sb_umount), + LSM_HOOK_INIT(sb_pivotroot, tomoyo_sb_pivotroot), + LSM_HOOK_INIT(socket_bind, tomoyo_socket_bind), + LSM_HOOK_INIT(socket_connect, tomoyo_socket_connect), + LSM_HOOK_INIT(socket_listen, tomoyo_socket_listen), + LSM_HOOK_INIT(socket_sendmsg, tomoyo_socket_sendmsg), +}; + +int tomoyo_enabled __ro_after_init = 1; + +/* Has /sbin/init started? */ +bool tomoyo_policy_loaded; + +#ifdef CONFIG_SECURITY_TOMOYO_LKM +EXPORT_SYMBOL_GPL(tomoyo_blob_sizes); +EXPORT_SYMBOL_GPL(tomoyo_policy_loaded); + +struct tomoyo_operations tomoyo_ops; +EXPORT_SYMBOL_GPL(tomoyo_ops); + +/** + * tomoyo_init - Reserve hooks for TOMOYO Linux. + * + * Returns 0. + */ +static int __init tomoyo_init(void) +{ + /* register ourselves with the security framework */ + security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), &tomoyo_lsmid); + tomoyo_ops.enabled = tomoyo_enabled; + pr_info("Hooks for initializing TOMOYO Linux are ready\n"); + return 0; +} +#else +/** + * tomoyo_init - Register TOMOYO Linux as a LSM module. + * + * Returns 0. + */ +static int __init tomoyo_init(void) +{ + struct tomoyo_task *s = tomoyo_task(current); + + /* register ourselves with the security framework */ + security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks), + &tomoyo_lsmid); + pr_info("TOMOYO Linux initialized\n"); + s->domain_info = &tomoyo_kernel_domain; + atomic_inc(&tomoyo_kernel_domain.users); + s->old_domain_info = NULL; + tomoyo_mm_init(); + + return 0; +} +#endif + +DEFINE_LSM(tomoyo) = { + .name = "tomoyo", + .enabled = &tomoyo_enabled, + .flags = LSM_FLAG_LEGACY_MAJOR, + .blobs = &tomoyo_blob_sizes, + .init = tomoyo_init, +}; diff --git a/security/tomoyo/load_policy.c b/security/tomoyo/load_policy.c index 363b65be87ab..6a2a72354a64 100644 --- a/security/tomoyo/load_policy.c +++ b/security/tomoyo/load_policy.c @@ -97,6 +97,14 @@ void tomoyo_load_policy(const char *filename) if (!tomoyo_policy_loader_exists()) return; done = true; +#ifdef CONFIG_SECURITY_TOMOYO_LKM + /* Load tomoyo.ko if not yet loaded. */ + if (!tomoyo_ops.check_profile) + request_module("tomoyo"); + /* Check if tomoyo.ko was successfully loaded. */ + if (!tomoyo_ops.check_profile) + panic("Failed to load tomoyo module."); +#endif pr_info("Calling %s to load policy. Please wait.\n", tomoyo_loader); argv[0] = (char *) tomoyo_loader; argv[1] = NULL; @@ -104,7 +112,11 @@ void tomoyo_load_policy(const char *filename) envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC); +#ifdef CONFIG_SECURITY_TOMOYO_LKM + tomoyo_ops.check_profile(); +#else tomoyo_check_profile(); +#endif } #endif diff --git a/security/tomoyo/proxy.c b/security/tomoyo/proxy.c new file mode 100644 index 000000000000..1618cc0f2af8 --- /dev/null +++ b/security/tomoyo/proxy.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * security/tomoyo/proxy.c + * + * Copyright (C) 2005-2011 NTT DATA CORPORATION + */ + +#include <linux/security.h> +#include "common.h" + +#ifdef CONFIG_SECURITY_TOMOYO_LKM + +struct tomoyo_task *tomoyo_task(struct task_struct *task) +{ + struct tomoyo_task *s = task->security + tomoyo_blob_sizes.lbs_task; + + if (unlikely(!s->domain_info)) { + if (likely(task == current)) { + s->domain_info = &tomoyo_kernel_domain; + atomic_inc(&tomoyo_kernel_domain.users); + } else { + /* Caller handles s->domain_info == NULL case. */ + } + } + return s; +} + +#include "hooks.h" + +/** + * tomoyo_runtime_init - Register TOMOYO Linux as a loadable LSM module. + * + * Returns 0 if TOMOYO is enabled, -EINVAL otherwise. + */ +static int __init tomoyo_runtime_init(void) +{ + const struct tomoyo_hooks tomoyo_hooks = { + .cred_prepare = tomoyo_cred_prepare, + .bprm_committed_creds = tomoyo_bprm_committed_creds, + .task_alloc = tomoyo_task_alloc, + .task_free = tomoyo_task_free, + .bprm_check_security = tomoyo_bprm_check_security, + .file_fcntl = tomoyo_file_fcntl, + .file_open = tomoyo_file_open, + .file_truncate = tomoyo_file_truncate, + .path_truncate = tomoyo_path_truncate, + .path_unlink = tomoyo_path_unlink, + .path_mkdir = tomoyo_path_mkdir, + .path_rmdir = tomoyo_path_rmdir, + .path_symlink = tomoyo_path_symlink, + .path_mknod = tomoyo_path_mknod, + .path_link = tomoyo_path_link, + .path_rename = tomoyo_path_rename, + .inode_getattr = tomoyo_inode_getattr, + .file_ioctl = tomoyo_file_ioctl, + .file_ioctl_compat = tomoyo_file_ioctl, + .path_chmod = tomoyo_path_chmod, + .path_chown = tomoyo_path_chown, + .path_chroot = tomoyo_path_chroot, + .sb_mount = tomoyo_sb_mount, + .sb_umount = tomoyo_sb_umount, + .sb_pivotroot = tomoyo_sb_pivotroot, + .socket_bind = tomoyo_socket_bind, + .socket_connect = tomoyo_socket_connect, + .socket_listen = tomoyo_socket_listen, + .socket_sendmsg = tomoyo_socket_sendmsg, + }; + + if (!tomoyo_ops.enabled) + return -EINVAL; + tomoyo_ops.check_profile = tomoyo_check_profile; + pr_info("TOMOYO Linux initialized\n"); + tomoyo_task(current); + tomoyo_mm_init(); + tomoyo_interface_init(); + tomoyo_register_hooks(&tomoyo_hooks); + return 0; +} +module_init(tomoyo_runtime_init); +MODULE_LICENSE("GPL"); + +#endif diff --git a/security/tomoyo/securityfs_if.c b/security/tomoyo/securityfs_if.c index a2705798476f..a3b821b7f477 100644 --- a/security/tomoyo/securityfs_if.c +++ b/security/tomoyo/securityfs_if.c @@ -229,17 +229,19 @@ static void __init tomoyo_create_entry(const char *name, const umode_t mode, } /** - * tomoyo_initerface_init - Initialize /sys/kernel/security/tomoyo/ interface. + * tomoyo_interface_init - Initialize /sys/kernel/security/tomoyo/ interface. * * Returns 0. */ -static int __init tomoyo_initerface_init(void) +int __init tomoyo_interface_init(void) { struct tomoyo_domain_info *domain; struct dentry *tomoyo_dir; +#ifndef CONFIG_SECURITY_TOMOYO_LKM if (!tomoyo_enabled) return 0; +#endif domain = tomoyo_domain(); /* Don't create securityfs entries unless registered. */ if (domain != &tomoyo_kernel_domain) @@ -270,4 +272,6 @@ static int __init tomoyo_initerface_init(void) return 0; } -fs_initcall(tomoyo_initerface_init); +#ifndef CONFIG_SECURITY_TOMOYO_LKM +fs_initcall(tomoyo_interface_init); +#endif diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c index 6799b1122c9d..b851ff377382 100644 --- a/security/tomoyo/util.c +++ b/security/tomoyo/util.c @@ -13,9 +13,6 @@ /* Lock for protecting policy. */ DEFINE_MUTEX(tomoyo_policy_lock); -/* Has /sbin/init started? */ -bool tomoyo_policy_loaded; - /* * Mapping table from "enum tomoyo_mac_index" to * "enum tomoyo_mac_category_index". diff --git a/sound/core/control.c b/sound/core/control.c index 4f55f64c42e1..2f790a7b1e90 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -2267,7 +2267,6 @@ static const struct file_operations snd_ctl_f_ops = .read = snd_ctl_read, .open = snd_ctl_open, .release = snd_ctl_release, - .llseek = no_llseek, .poll = snd_ctl_poll, .unlocked_ioctl = snd_ctl_ioctl, .compat_ioctl = snd_ctl_ioctl_compat, diff --git a/sound/core/oss/mixer_oss.c b/sound/core/oss/mixer_oss.c index 33bf9a220ada..668604d0ec9d 100644 --- a/sound/core/oss/mixer_oss.c +++ b/sound/core/oss/mixer_oss.c @@ -412,7 +412,6 @@ static const struct file_operations snd_mixer_oss_f_ops = .owner = THIS_MODULE, .open = snd_mixer_oss_open, .release = snd_mixer_oss_release, - .llseek = no_llseek, .unlocked_ioctl = snd_mixer_oss_ioctl, .compat_ioctl = snd_mixer_oss_ioctl_compat, }; diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 7386982cf40e..4683b9139c56 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -3106,7 +3106,6 @@ static const struct file_operations snd_pcm_oss_f_reg = .write = snd_pcm_oss_write, .open = snd_pcm_oss_open, .release = snd_pcm_oss_release, - .llseek = no_llseek, .poll = snd_pcm_oss_poll, .unlocked_ioctl = snd_pcm_oss_ioctl, .compat_ioctl = snd_pcm_oss_ioctl_compat, diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 99e39b5359cc..5b9076829ade 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -4115,7 +4115,6 @@ const struct file_operations snd_pcm_f_ops[2] = { .write_iter = snd_pcm_writev, .open = snd_pcm_playback_open, .release = snd_pcm_release, - .llseek = no_llseek, .poll = snd_pcm_poll, .unlocked_ioctl = snd_pcm_ioctl, .compat_ioctl = snd_pcm_ioctl_compat, @@ -4129,7 +4128,6 @@ const struct file_operations snd_pcm_f_ops[2] = { .read_iter = snd_pcm_readv, .open = snd_pcm_capture_open, .release = snd_pcm_release, - .llseek = no_llseek, .poll = snd_pcm_poll, .unlocked_ioctl = snd_pcm_ioctl, .compat_ioctl = snd_pcm_ioctl_compat, diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 7accf9a1ddf4..03306be5fa02 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1784,7 +1784,6 @@ static const struct file_operations snd_rawmidi_f_ops = { .write = snd_rawmidi_write, .open = snd_rawmidi_open, .release = snd_rawmidi_release, - .llseek = no_llseek, .poll = snd_rawmidi_poll, .unlocked_ioctl = snd_rawmidi_ioctl, .compat_ioctl = snd_rawmidi_ioctl_compat, diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 6437193e42bf..3930e2f9082f 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -2722,7 +2722,6 @@ static const struct file_operations snd_seq_f_ops = .write = snd_seq_write, .open = snd_seq_open, .release = snd_seq_release, - .llseek = no_llseek, .poll = snd_seq_poll, .unlocked_ioctl = snd_seq_ioctl, .compat_ioctl = snd_seq_ioctl_compat, diff --git a/sound/core/timer.c b/sound/core/timer.c index 668c40bac318..fbada79380f9 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -2436,7 +2436,6 @@ static const struct file_operations snd_timer_f_ops = .read = snd_timer_user_read, .open = snd_timer_user_open, .release = snd_timer_user_release, - .llseek = no_llseek, .poll = snd_timer_user_poll, .unlocked_ioctl = snd_timer_user_ioctl, .compat_ioctl = snd_timer_user_ioctl_compat, diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 4b1baf4dd50e..dea2d9b18fc9 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -381,7 +381,6 @@ static long mixer_unlocked_ioctl(struct file *file, u_int cmd, u_long arg) static const struct file_operations mixer_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .unlocked_ioctl = mixer_unlocked_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = mixer_open, @@ -1155,7 +1154,6 @@ static long sq_unlocked_ioctl(struct file *file, u_int cmd, u_long arg) static const struct file_operations sq_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .write = sq_write, .poll = sq_poll, .unlocked_ioctl = sq_unlocked_ioctl, @@ -1351,7 +1349,6 @@ static ssize_t state_read(struct file *file, char __user *buf, size_t count, static const struct file_operations state_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = state_read, .open = state_open, .release = state_release, diff --git a/sound/soc/intel/avs/debugfs.c b/sound/soc/intel/avs/debugfs.c index 3fc2bbb63369..1767ded4d983 100644 --- a/sound/soc/intel/avs/debugfs.c +++ b/sound/soc/intel/avs/debugfs.c @@ -68,7 +68,6 @@ static ssize_t fw_regs_read(struct file *file, char __user *to, size_t count, lo static const struct file_operations fw_regs_fops = { .open = simple_open, .read = fw_regs_read, - .llseek = no_llseek, }; static ssize_t debug_window_read(struct file *file, char __user *to, size_t count, loff_t *ppos) @@ -93,7 +92,6 @@ static ssize_t debug_window_read(struct file *file, char __user *to, size_t coun static const struct file_operations debug_window_fops = { .open = simple_open, .read = debug_window_read, - .llseek = no_llseek, }; static ssize_t probe_points_read(struct file *file, char __user *to, size_t count, loff_t *ppos) @@ -170,7 +168,6 @@ static const struct file_operations probe_points_fops = { .open = simple_open, .read = probe_points_read, .write = probe_points_write, - .llseek = no_llseek, }; static ssize_t probe_points_disconnect_write(struct file *file, const char __user *from, diff --git a/tools/include/linux/linkage.h b/tools/include/linux/linkage.h index b7183576d8eb..7baaa5898ca2 100644 --- a/tools/include/linux/linkage.h +++ b/tools/include/linux/linkage.h @@ -4,7 +4,9 @@ #include <linux/export.h> #define SYM_FUNC_START(x) .globl x; x: - #define SYM_FUNC_END(x) +#define SYM_DATA_START(x) .globl x; x: +#define SYM_DATA_START_LOCAL(x) x: +#define SYM_DATA_END(x) #endif /* _TOOLS_INCLUDE_LINUX_LINKAGE_H */ diff --git a/tools/objtool/arch/loongarch/decode.c b/tools/objtool/arch/loongarch/decode.c index aee479d2191c..69b66994f2a1 100644 --- a/tools/objtool/arch/loongarch/decode.c +++ b/tools/objtool/arch/loongarch/decode.c @@ -122,7 +122,7 @@ static bool decode_insn_reg2i12_fomat(union loongarch_instruction inst, switch (inst.reg2i12_format.opcode) { case addid_op: if ((inst.reg2i12_format.rd == CFI_SP) || (inst.reg2i12_format.rj == CFI_SP)) { - /* addi.d sp,sp,si12 or addi.d fp,sp,si12 */ + /* addi.d sp,sp,si12 or addi.d fp,sp,si12 or addi.d sp,fp,si12 */ insn->immediate = sign_extend64(inst.reg2i12_format.immediate, 11); ADD_OP(op) { op->src.type = OP_SRC_ADD; @@ -132,6 +132,15 @@ static bool decode_insn_reg2i12_fomat(union loongarch_instruction inst, op->dest.reg = inst.reg2i12_format.rd; } } + if ((inst.reg2i12_format.rd == CFI_SP) && (inst.reg2i12_format.rj == CFI_FP)) { + /* addi.d sp,fp,si12 */ + struct symbol *func = find_func_containing(insn->sec, insn->offset); + + if (!func) + return false; + + func->frame_pointer = true; + } break; case ldd_op: if (inst.reg2i12_format.rj == CFI_SP) { diff --git a/tools/objtool/check.c b/tools/objtool/check.c index d086f207a3d3..6604f5d038aa 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3043,10 +3043,27 @@ static int update_cfi_state(struct instruction *insn, break; } - if (op->dest.reg == CFI_SP && op->src.reg == CFI_BP) { + if (op->dest.reg == CFI_BP && op->src.reg == CFI_SP && + insn->sym->frame_pointer) { + /* addi.d fp,sp,imm on LoongArch */ + if (cfa->base == CFI_SP && cfa->offset == op->src.offset) { + cfa->base = CFI_BP; + cfa->offset = 0; + } + break; + } - /* lea disp(%rbp), %rsp */ - cfi->stack_size = -(op->src.offset + regs[CFI_BP].offset); + if (op->dest.reg == CFI_SP && op->src.reg == CFI_BP) { + /* addi.d sp,fp,imm on LoongArch */ + if (cfa->base == CFI_BP && cfa->offset == 0) { + if (insn->sym->frame_pointer) { + cfa->base = CFI_SP; + cfa->offset = -op->src.offset; + } + } else { + /* lea disp(%rbp), %rsp */ + cfi->stack_size = -(op->src.offset + regs[CFI_BP].offset); + } break; } diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index 2b8a69de4db8..d7e815c2fd15 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -68,6 +68,7 @@ struct symbol { u8 warned : 1; u8 embedded_insn : 1; u8 local_label : 1; + u8 frame_pointer : 1; struct list_head pv_target; struct reloc *relocs; }; diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 3d1ca9e38b1f..b1256fee3567 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -14,7 +14,7 @@ ldflags-y += --wrap=cxl_dvsec_rr_decode ldflags-y += --wrap=devm_cxl_add_rch_dport ldflags-y += --wrap=cxl_rcd_component_reg_phys ldflags-y += --wrap=cxl_endpoint_parse_cdat -ldflags-y += --wrap=cxl_setup_parent_dport +ldflags-y += --wrap=cxl_dport_init_ras_reporting DRIVERS := ../../../drivers CXL_SRC := $(DRIVERS)/cxl diff --git a/tools/testing/cxl/mock_acpi.c b/tools/testing/cxl/mock_acpi.c index 55813de26d46..8da94378ccec 100644 --- a/tools/testing/cxl/mock_acpi.c +++ b/tools/testing/cxl/mock_acpi.c @@ -18,7 +18,7 @@ struct acpi_device *to_cxl_host_bridge(struct device *host, struct device *dev) goto out; } - if (dev->bus == &platform_bus_type) + if (dev_is_platform(dev)) goto out; adev = to_acpi_device(dev); diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 129f179b0ac5..ccdd6a504222 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -8,6 +8,7 @@ #include <linux/delay.h> #include <linux/sizes.h> #include <linux/bits.h> +#include <cxl/mailbox.h> #include <asm/unaligned.h> #include <crypto/sha2.h> #include <cxlmem.h> @@ -534,6 +535,7 @@ static int mock_gsl(struct cxl_mbox_cmd *cmd) static int mock_get_log(struct cxl_memdev_state *mds, struct cxl_mbox_cmd *cmd) { + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; struct cxl_mbox_get_log *gl = cmd->payload_in; u32 offset = le32_to_cpu(gl->offset); u32 length = le32_to_cpu(gl->length); @@ -542,7 +544,7 @@ static int mock_get_log(struct cxl_memdev_state *mds, struct cxl_mbox_cmd *cmd) if (cmd->size_in < sizeof(*gl)) return -EINVAL; - if (length > mds->payload_size) + if (length > cxl_mbox->payload_size) return -EINVAL; if (offset + length > sizeof(mock_cel)) return -EINVAL; @@ -617,12 +619,13 @@ void cxl_mockmem_sanitize_work(struct work_struct *work) { struct cxl_memdev_state *mds = container_of(work, typeof(*mds), security.poll_dwork.work); + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (mds->security.sanitize_node) sysfs_notify_dirent(mds->security.sanitize_node); mds->security.sanitize_active = false; - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); dev_dbg(mds->cxlds.dev, "sanitize complete\n"); } @@ -631,6 +634,7 @@ static int mock_sanitize(struct cxl_mockmem_data *mdata, struct cxl_mbox_cmd *cmd) { struct cxl_memdev_state *mds = mdata->mds; + struct cxl_mailbox *cxl_mbox = &mds->cxlds.cxl_mbox; int rc = 0; if (cmd->size_in != 0) @@ -648,14 +652,14 @@ static int mock_sanitize(struct cxl_mockmem_data *mdata, return -ENXIO; } - mutex_lock(&mds->mbox_mutex); + mutex_lock(&cxl_mbox->mbox_mutex); if (schedule_delayed_work(&mds->security.poll_dwork, msecs_to_jiffies(mdata->sanitize_timeout))) { mds->security.sanitize_active = true; dev_dbg(mds->cxlds.dev, "sanitize issued\n"); } else rc = -EBUSY; - mutex_unlock(&mds->mbox_mutex); + mutex_unlock(&cxl_mbox->mbox_mutex); return rc; } @@ -1333,12 +1337,13 @@ static int mock_activate_fw(struct cxl_mockmem_data *mdata, return -EINVAL; } -static int cxl_mock_mbox_send(struct cxl_memdev_state *mds, +static int cxl_mock_mbox_send(struct cxl_mailbox *cxl_mbox, struct cxl_mbox_cmd *cmd) { - struct cxl_dev_state *cxlds = &mds->cxlds; - struct device *dev = cxlds->dev; + struct device *dev = cxl_mbox->host; struct cxl_mockmem_data *mdata = dev_get_drvdata(dev); + struct cxl_memdev_state *mds = mdata->mds; + struct cxl_dev_state *cxlds = &mds->cxlds; int rc = -EIO; switch (cmd->opcode) { @@ -1453,6 +1458,17 @@ static ssize_t event_trigger_store(struct device *dev, } static DEVICE_ATTR_WO(event_trigger); +static int cxl_mock_mailbox_create(struct cxl_dev_state *cxlds) +{ + int rc; + + rc = cxl_mailbox_init(&cxlds->cxl_mbox, cxlds->dev); + if (rc) + return rc; + + return 0; +} + static int cxl_mock_mem_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1460,6 +1476,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) struct cxl_memdev_state *mds; struct cxl_dev_state *cxlds; struct cxl_mockmem_data *mdata; + struct cxl_mailbox *cxl_mbox; int rc; mdata = devm_kzalloc(dev, sizeof(*mdata), GFP_KERNEL); @@ -1487,13 +1504,18 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (IS_ERR(mds)) return PTR_ERR(mds); + cxlds = &mds->cxlds; + rc = cxl_mock_mailbox_create(cxlds); + if (rc) + return rc; + + cxl_mbox = &mds->cxlds.cxl_mbox; mdata->mds = mds; - mds->mbox_send = cxl_mock_mbox_send; - mds->payload_size = SZ_4K; + cxl_mbox->mbox_send = cxl_mock_mbox_send; + cxl_mbox->payload_size = SZ_4K; mds->event.buf = (struct cxl_get_event_payload *) mdata->event_buf; INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mockmem_sanitize_work); - cxlds = &mds->cxlds; cxlds->serial = pdev->id; if (is_rcd(pdev)) cxlds->rcd = true; diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index d619672faa49..f4ce96cc11d4 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -228,7 +228,7 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, CXL); -int __wrap_cxl_dvsec_rr_decode(struct device *dev, int dvsec, +int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; @@ -237,7 +237,7 @@ int __wrap_cxl_dvsec_rr_decode(struct device *dev, int dvsec, if (ops && ops->is_mock_dev(dev)) rc = 0; else - rc = cxl_dvsec_rr_decode(dev, dvsec, info); + rc = cxl_dvsec_rr_decode(dev, port, info); put_cxl_mock_ops(index); return rc; @@ -299,17 +299,17 @@ void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL); -void __wrap_cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport) +void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host) { int index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); if (!ops || !ops->is_mock_port(dport->dport_dev)) - cxl_setup_parent_dport(host, dport); + cxl_dport_init_ras_reporting(dport, host); put_cxl_mock_ops(index); } -EXPORT_SYMBOL_NS_GPL(__wrap_cxl_setup_parent_dport, CXL); +EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, CXL); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(ACPI); diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 6d9381d60172..7f57abf936e7 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -5,3 +5,7 @@ !*.h !*.S !*.sh +!.gitignore +!config +!settings +!Makefile diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0c4b254ab56b..960cf6a77198 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -130,6 +130,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test +TEST_GEN_PROGS_x86_64 += coalesced_io_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test @@ -167,6 +168,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access TEST_GEN_PROGS_aarch64 += aarch64/no-vgic-v3 TEST_GEN_PROGS_aarch64 += access_tracking_perf_test TEST_GEN_PROGS_aarch64 += arch_timer +TEST_GEN_PROGS_aarch64 += coalesced_io_test TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += dirty_log_perf_test @@ -188,6 +190,7 @@ TEST_GEN_PROGS_s390x += s390x/tprot TEST_GEN_PROGS_s390x += s390x/cmma_test TEST_GEN_PROGS_s390x += s390x/debug_test TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test +TEST_GEN_PROGS_s390x += s390x/ucontrol_test TEST_GEN_PROGS_s390x += demand_paging_test TEST_GEN_PROGS_s390x += dirty_log_test TEST_GEN_PROGS_s390x += guest_print_test @@ -200,6 +203,7 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test TEST_GEN_PROGS_riscv += riscv/ebreak_test TEST_GEN_PROGS_riscv += arch_timer +TEST_GEN_PROGS_riscv += coalesced_io_test TEST_GEN_PROGS_riscv += demand_paging_test TEST_GEN_PROGS_riscv += dirty_log_test TEST_GEN_PROGS_riscv += get-reg-list diff --git a/tools/testing/selftests/kvm/coalesced_io_test.c b/tools/testing/selftests/kvm/coalesced_io_test.c new file mode 100644 index 000000000000..60cb25454899 --- /dev/null +++ b/tools/testing/selftests/kvm/coalesced_io_test.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include <linux/sizes.h> + +#include <kvm_util.h> +#include <processor.h> + +#include "ucall_common.h" + +struct kvm_coalesced_io { + struct kvm_coalesced_mmio_ring *ring; + uint32_t ring_size; + uint64_t mmio_gpa; + uint64_t *mmio; + + /* + * x86-only, but define pio_port for all architectures to minimize the + * amount of #ifdeffery and complexity, without having to sacrifice + * verbose error messages. + */ + uint8_t pio_port; +}; + +static struct kvm_coalesced_io kvm_builtin_io_ring; + +#ifdef __x86_64__ +static const int has_pio = 1; +#else +static const int has_pio = 0; +#endif + +static void guest_code(struct kvm_coalesced_io *io) +{ + int i, j; + + for (;;) { + for (j = 0; j < 1 + has_pio; j++) { + /* + * KVM always leaves one free entry, i.e. exits to + * userspace before the last entry is filled. + */ + for (i = 0; i < io->ring_size - 1; i++) { +#ifdef __x86_64__ + if (i & 1) + outl(io->pio_port, io->pio_port + i); + else +#endif + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); + } +#ifdef __x86_64__ + if (j & 1) + outl(io->pio_port, io->pio_port + i); + else +#endif + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); + } + GUEST_SYNC(0); + + WRITE_ONCE(*io->mmio, io->mmio_gpa + i); +#ifdef __x86_64__ + outl(io->pio_port, io->pio_port + i); +#endif + } +} + +static void vcpu_run_and_verify_io_exit(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, + uint32_t ring_start, + uint32_t expected_exit) +{ + const bool want_pio = expected_exit == KVM_EXIT_IO; + struct kvm_coalesced_mmio_ring *ring = io->ring; + struct kvm_run *run = vcpu->run; + uint32_t pio_value; + + WRITE_ONCE(ring->first, ring_start); + WRITE_ONCE(ring->last, ring_start); + + vcpu_run(vcpu); + + /* + * Annoyingly, reading PIO data is safe only for PIO exits, otherwise + * data_offset is garbage, e.g. an MMIO gpa. + */ + if (run->exit_reason == KVM_EXIT_IO) + pio_value = *(uint32_t *)((void *)run + run->io.data_offset); + else + pio_value = 0; + + TEST_ASSERT((!want_pio && (run->exit_reason == KVM_EXIT_MMIO && run->mmio.is_write && + run->mmio.phys_addr == io->mmio_gpa && run->mmio.len == 8 && + *(uint64_t *)run->mmio.data == io->mmio_gpa + io->ring_size - 1)) || + (want_pio && (run->exit_reason == KVM_EXIT_IO && run->io.port == io->pio_port && + run->io.direction == KVM_EXIT_IO_OUT && run->io.count == 1 && + pio_value == io->pio_port + io->ring_size - 1)), + "For start = %u, expected exit on %u-byte %s write 0x%llx = %lx, got exit_reason = %u (%s)\n " + "(MMIO addr = 0x%llx, write = %u, len = %u, data = %lx)\n " + "(PIO port = 0x%x, write = %u, len = %u, count = %u, data = %x", + ring_start, want_pio ? 4 : 8, want_pio ? "PIO" : "MMIO", + want_pio ? (unsigned long long)io->pio_port : io->mmio_gpa, + (want_pio ? io->pio_port : io->mmio_gpa) + io->ring_size - 1, run->exit_reason, + run->exit_reason == KVM_EXIT_MMIO ? "MMIO" : run->exit_reason == KVM_EXIT_IO ? "PIO" : "other", + run->mmio.phys_addr, run->mmio.is_write, run->mmio.len, *(uint64_t *)run->mmio.data, + run->io.port, run->io.direction, run->io.size, run->io.count, pio_value); +} + +static void vcpu_run_and_verify_coalesced_io(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, + uint32_t ring_start, + uint32_t expected_exit) +{ + struct kvm_coalesced_mmio_ring *ring = io->ring; + int i; + + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, expected_exit); + + TEST_ASSERT((ring->last + 1) % io->ring_size == ring->first, + "Expected ring to be full (minus 1), first = %u, last = %u, max = %u, start = %u", + ring->first, ring->last, io->ring_size, ring_start); + + for (i = 0; i < io->ring_size - 1; i++) { + uint32_t idx = (ring->first + i) % io->ring_size; + struct kvm_coalesced_mmio *entry = &ring->coalesced_mmio[idx]; + +#ifdef __x86_64__ + if (i & 1) + TEST_ASSERT(entry->phys_addr == io->pio_port && + entry->len == 4 && entry->pio && + *(uint32_t *)entry->data == io->pio_port + i, + "Wanted 4-byte port I/O 0x%x = 0x%x in entry %u, got %u-byte %s 0x%llx = 0x%x", + io->pio_port, io->pio_port + i, i, + entry->len, entry->pio ? "PIO" : "MMIO", + entry->phys_addr, *(uint32_t *)entry->data); + else +#endif + TEST_ASSERT(entry->phys_addr == io->mmio_gpa && + entry->len == 8 && !entry->pio, + "Wanted 8-byte MMIO to 0x%lx = %lx in entry %u, got %u-byte %s 0x%llx = 0x%lx", + io->mmio_gpa, io->mmio_gpa + i, i, + entry->len, entry->pio ? "PIO" : "MMIO", + entry->phys_addr, *(uint64_t *)entry->data); + } +} + +static void test_coalesced_io(struct kvm_vcpu *vcpu, + struct kvm_coalesced_io *io, uint32_t ring_start) +{ + struct kvm_coalesced_mmio_ring *ring = io->ring; + + kvm_vm_register_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */); +#ifdef __x86_64__ + kvm_vm_register_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */); +#endif + + vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_MMIO); +#ifdef __x86_64__ + vcpu_run_and_verify_coalesced_io(vcpu, io, ring_start, KVM_EXIT_IO); +#endif + + /* + * Verify ucall, which may use non-coalesced MMIO or PIO, generates an + * immediate exit. + */ + WRITE_ONCE(ring->first, ring_start); + WRITE_ONCE(ring->last, ring_start); + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); + TEST_ASSERT_EQ(ring->first, ring_start); + TEST_ASSERT_EQ(ring->last, ring_start); + + /* Verify that non-coalesced MMIO/PIO generates an exit to userspace. */ + kvm_vm_unregister_coalesced_io(vcpu->vm, io->mmio_gpa, 8, false /* pio */); + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_MMIO); + +#ifdef __x86_64__ + kvm_vm_unregister_coalesced_io(vcpu->vm, io->pio_port, 8, true /* pio */); + vcpu_run_and_verify_io_exit(vcpu, io, ring_start, KVM_EXIT_IO); +#endif +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int i; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_MMIO)); + +#ifdef __x86_64__ + TEST_REQUIRE(kvm_has_cap(KVM_CAP_COALESCED_PIO)); +#endif + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + + kvm_builtin_io_ring = (struct kvm_coalesced_io) { + /* + * The I/O ring is a kernel-allocated page whose address is + * relative to each vCPU's run page, with the page offset + * provided by KVM in the return of KVM_CAP_COALESCED_MMIO. + */ + .ring = (void *)vcpu->run + + (kvm_check_cap(KVM_CAP_COALESCED_MMIO) * getpagesize()), + + /* + * The size of the I/O ring is fixed, but KVM defines the sized + * based on the kernel's PAGE_SIZE. Thus, userspace must query + * the host's page size at runtime to compute the ring size. + */ + .ring_size = (getpagesize() - sizeof(struct kvm_coalesced_mmio_ring)) / + sizeof(struct kvm_coalesced_mmio), + + /* + * Arbitrary address+port (MMIO mustn't overlap memslots), with + * the MMIO GPA identity mapped in the guest. + */ + .mmio_gpa = 4ull * SZ_1G, + .mmio = (uint64_t *)(4ull * SZ_1G), + .pio_port = 0x80, + }; + + virt_map(vm, (uint64_t)kvm_builtin_io_ring.mmio, kvm_builtin_io_ring.mmio_gpa, 1); + + sync_global_to_guest(vm, kvm_builtin_io_ring); + vcpu_args_set(vcpu, 1, &kvm_builtin_io_ring); + + for (i = 0; i < kvm_builtin_io_ring.ring_size; i++) + test_coalesced_io(vcpu, &kvm_builtin_io_ring, i); + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c index 8092c2d0f5d6..bcf582852db9 100644 --- a/tools/testing/selftests/kvm/guest_print_test.c +++ b/tools/testing/selftests/kvm/guest_print_test.c @@ -107,6 +107,21 @@ static void ucall_abort(const char *assert_msg, const char *expected_assert_msg) expected_assert_msg, &assert_msg[offset]); } +/* + * Open code vcpu_run(), sans the UCALL_ABORT handling, so that intentional + * guest asserts guest can be verified instead of being reported as failures. + */ +static void do_vcpu_run(struct kvm_vcpu *vcpu) +{ + int r; + + do { + r = __vcpu_run(vcpu); + } while (r == -1 && errno == EINTR); + + TEST_ASSERT(!r, KVM_IOCTL_ERROR(KVM_RUN, r)); +} + static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, const char *expected_assert) { @@ -114,7 +129,7 @@ static void run_test(struct kvm_vcpu *vcpu, const char *expected_printf, struct ucall uc; while (1) { - vcpu_run(vcpu); + do_vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, "Unexpected exit reason: %u (%s),", @@ -159,7 +174,7 @@ static void test_limits(void) vm = vm_create_with_one_vcpu(&vcpu, guest_code_limits); run = vcpu->run; - vcpu_run(vcpu); + do_vcpu_run(vcpu); TEST_ASSERT(run->exit_reason == UCALL_EXIT_REASON, "Unexpected exit reason: %u (%s),", diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 63c2aaae51f3..bc7c242480d6 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -428,8 +428,6 @@ const char *vm_guest_mode_string(uint32_t i); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp); void kvm_vm_release(struct kvm_vm *vmp); -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, - size_t len); void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); int kvm_memfd_alloc(size_t size, bool hugepages); @@ -460,6 +458,32 @@ static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); } +static inline void kvm_vm_register_coalesced_io(struct kvm_vm *vm, + uint64_t address, + uint64_t size, bool pio) +{ + struct kvm_coalesced_mmio_zone zone = { + .addr = address, + .size = size, + .pio = pio, + }; + + vm_ioctl(vm, KVM_REGISTER_COALESCED_MMIO, &zone); +} + +static inline void kvm_vm_unregister_coalesced_io(struct kvm_vm *vm, + uint64_t address, + uint64_t size, bool pio) +{ + struct kvm_coalesced_mmio_zone zone = { + .addr = address, + .size = size, + .pio = pio, + }; + + vm_ioctl(vm, KVM_UNREGISTER_COALESCED_MMIO, &zone); +} + static inline int vm_get_stats_fd(struct kvm_vm *vm) { int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390x/debug_print.h new file mode 100644 index 000000000000..1bf275631cc6 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/debug_print.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Definition for kernel virtual machines on s390x + * + * Copyright IBM Corp. 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + */ + +#ifndef SELFTEST_KVM_DEBUG_PRINT_H +#define SELFTEST_KVM_DEBUG_PRINT_H + +#include "asm/ptrace.h" +#include "kvm_util.h" +#include "sie.h" + +static inline void print_hex_bytes(const char *name, u64 addr, size_t len) +{ + u64 pos; + + pr_debug("%s (%p)\n", name, (void *)addr); + pr_debug(" 0/0x00---------|"); + if (len > 8) + pr_debug(" 8/0x08---------|"); + if (len > 16) + pr_debug(" 16/0x10--------|"); + if (len > 24) + pr_debug(" 24/0x18--------|"); + for (pos = 0; pos < len; pos += 8) { + if ((pos % 32) == 0) + pr_debug("\n %3lu 0x%.3lx ", pos, pos); + pr_debug(" %16lx", *((u64 *)(addr + pos))); + } + pr_debug("\n"); +} + +static inline void print_hex(const char *name, u64 addr) +{ + print_hex_bytes(name, addr, 512); +} + +static inline void print_psw(struct kvm_run *run, struct kvm_s390_sie_block *sie_block) +{ + pr_debug("flags:0x%x psw:0x%.16llx:0x%.16llx exit:%u %s\n", + run->flags, + run->psw_mask, run->psw_addr, + run->exit_reason, exit_reason_str(run->exit_reason)); + pr_debug("sie_block psw:0x%.16llx:0x%.16llx\n", + sie_block->psw_mask, sie_block->psw_addr); +} + +static inline void print_run(struct kvm_run *run, struct kvm_s390_sie_block *sie_block) +{ + print_hex_bytes("run", (u64)run, 0x150); + print_hex("sie_block", (u64)sie_block); + print_psw(run, sie_block); +} + +static inline void print_regs(struct kvm_run *run) +{ + struct kvm_sync_regs *sync_regs = &run->s.regs; + + print_hex_bytes("GPRS", (u64)sync_regs->gprs, 8 * NUM_GPRS); + print_hex_bytes("ACRS", (u64)sync_regs->acrs, 4 * NUM_ACRS); + print_hex_bytes("CRS", (u64)sync_regs->crs, 8 * NUM_CRS); +} + +#endif /* SELFTEST_KVM_DEBUG_PRINT_H */ diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h index 255c9b990f4c..481bd2fd6a32 100644 --- a/tools/testing/selftests/kvm/include/s390x/processor.h +++ b/tools/testing/selftests/kvm/include/s390x/processor.h @@ -21,6 +21,11 @@ #define PAGE_PROTECT 0x200 /* HW read-only bit */ #define PAGE_NOEXEC 0x100 /* HW no-execute bit */ +/* Page size definitions */ +#define PAGE_SHIFT 12 +#define PAGE_SIZE BIT_ULL(PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE - 1)) + /* Is there a portable way to do this? */ static inline void cpu_relax(void) { diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390x/sie.h new file mode 100644 index 000000000000..160acd4a1db9 --- /dev/null +++ b/tools/testing/selftests/kvm/include/s390x/sie.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Definition for kernel virtual machines on s390. + * + * Adapted copy of struct definition kvm_s390_sie_block from + * arch/s390/include/asm/kvm_host.h for use in userspace selftest programs. + * + * Copyright IBM Corp. 2008, 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + * Carsten Otte <cotte@de.ibm.com> + */ + +#ifndef SELFTEST_KVM_SIE_H +#define SELFTEST_KVM_SIE_H + +#include <linux/types.h> + +struct kvm_s390_sie_block { +#define CPUSTAT_STOPPED 0x80000000 +#define CPUSTAT_WAIT 0x10000000 +#define CPUSTAT_ECALL_PEND 0x08000000 +#define CPUSTAT_STOP_INT 0x04000000 +#define CPUSTAT_IO_INT 0x02000000 +#define CPUSTAT_EXT_INT 0x01000000 +#define CPUSTAT_RUNNING 0x00800000 +#define CPUSTAT_RETAINED 0x00400000 +#define CPUSTAT_TIMING_SUB 0x00020000 +#define CPUSTAT_SIE_SUB 0x00010000 +#define CPUSTAT_RRF 0x00008000 +#define CPUSTAT_SLSV 0x00004000 +#define CPUSTAT_SLSR 0x00002000 +#define CPUSTAT_ZARCH 0x00000800 +#define CPUSTAT_MCDS 0x00000100 +#define CPUSTAT_KSS 0x00000200 +#define CPUSTAT_SM 0x00000080 +#define CPUSTAT_IBS 0x00000040 +#define CPUSTAT_GED2 0x00000010 +#define CPUSTAT_G 0x00000008 +#define CPUSTAT_GED 0x00000004 +#define CPUSTAT_J 0x00000002 +#define CPUSTAT_P 0x00000001 + __u32 cpuflags; /* 0x0000 */ + __u32: 1; /* 0x0004 */ + __u32 prefix : 18; + __u32: 1; + __u32 ibc : 12; + __u8 reserved08[4]; /* 0x0008 */ +#define PROG_IN_SIE BIT(0) + __u32 prog0c; /* 0x000c */ + union { + __u8 reserved10[16]; /* 0x0010 */ + struct { + __u64 pv_handle_cpu; + __u64 pv_handle_config; + }; + }; +#define PROG_BLOCK_SIE BIT(0) +#define PROG_REQUEST BIT(1) + __u32 prog20; /* 0x0020 */ + __u8 reserved24[4]; /* 0x0024 */ + __u64 cputm; /* 0x0028 */ + __u64 ckc; /* 0x0030 */ + __u64 epoch; /* 0x0038 */ + __u32 svcc; /* 0x0040 */ +#define LCTL_CR0 0x8000 +#define LCTL_CR6 0x0200 +#define LCTL_CR9 0x0040 +#define LCTL_CR10 0x0020 +#define LCTL_CR11 0x0010 +#define LCTL_CR14 0x0002 + __u16 lctl; /* 0x0044 */ + __s16 icpua; /* 0x0046 */ +#define ICTL_OPEREXC 0x80000000 +#define ICTL_PINT 0x20000000 +#define ICTL_LPSW 0x00400000 +#define ICTL_STCTL 0x00040000 +#define ICTL_ISKE 0x00004000 +#define ICTL_SSKE 0x00002000 +#define ICTL_RRBE 0x00001000 +#define ICTL_TPROT 0x00000200 + __u32 ictl; /* 0x0048 */ +#define ECA_CEI 0x80000000 +#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_APIE 0x00000008 +#define ECA_SII 0x00000001 + __u32 eca; /* 0x004c */ +#define ICPT_INST 0x04 +#define ICPT_PROGI 0x08 +#define ICPT_INSTPROGI 0x0C +#define ICPT_EXTREQ 0x10 +#define ICPT_EXTINT 0x14 +#define ICPT_IOREQ 0x18 +#define ICPT_WAIT 0x1c +#define ICPT_VALIDITY 0x20 +#define ICPT_STOP 0x28 +#define ICPT_OPEREXC 0x2C +#define ICPT_PARTEXEC 0x38 +#define ICPT_IOINST 0x40 +#define ICPT_KSS 0x5c +#define ICPT_MCHKREQ 0x60 +#define ICPT_INT_ENABLE 0x64 +#define ICPT_PV_INSTR 0x68 +#define ICPT_PV_NOTIFY 0x6c +#define ICPT_PV_PREF 0x70 + __u8 icptcode; /* 0x0050 */ + __u8 icptstatus; /* 0x0051 */ + __u16 ihcpu; /* 0x0052 */ + __u8 reserved54; /* 0x0054 */ +#define IICTL_CODE_NONE 0x00 +#define IICTL_CODE_MCHK 0x01 +#define IICTL_CODE_EXT 0x02 +#define IICTL_CODE_IO 0x03 +#define IICTL_CODE_RESTART 0x04 +#define IICTL_CODE_SPECIFICATION 0x10 +#define IICTL_CODE_OPERAND 0x11 + __u8 iictl; /* 0x0055 */ + __u16 ipa; /* 0x0056 */ + __u32 ipb; /* 0x0058 */ + __u32 scaoh; /* 0x005c */ +#define FPF_BPBC 0x20 + __u8 fpf; /* 0x0060 */ +#define ECB_GS 0x40 +#define ECB_TE 0x10 +#define ECB_SPECI 0x08 +#define ECB_SRSI 0x04 +#define ECB_HOSTPROTINT 0x02 +#define ECB_PTF 0x01 + __u8 ecb; /* 0x0061 */ +#define ECB2_CMMA 0x80 +#define ECB2_IEP 0x20 +#define ECB2_PFMFI 0x08 +#define ECB2_ESCA 0x04 +#define ECB2_ZPCI_LSI 0x02 + __u8 ecb2; /* 0x0062 */ +#define ECB3_AISI 0x20 +#define ECB3_AISII 0x10 +#define ECB3_DEA 0x08 +#define ECB3_AES 0x04 +#define ECB3_RI 0x01 + __u8 ecb3; /* 0x0063 */ +#define ESCA_SCAOL_MASK ~0x3fU + __u32 scaol; /* 0x0064 */ + __u8 sdf; /* 0x0068 */ + __u8 epdx; /* 0x0069 */ + __u8 cpnc; /* 0x006a */ + __u8 reserved6b; /* 0x006b */ + __u32 todpr; /* 0x006c */ +#define GISA_FORMAT1 0x00000001 + __u32 gd; /* 0x0070 */ + __u8 reserved74[12]; /* 0x0074 */ + __u64 mso; /* 0x0080 */ + __u64 msl; /* 0x0088 */ + __u64 psw_mask; /* 0x0090 */ + __u64 psw_addr; /* 0x0098 */ + __u64 gg14; /* 0x00a0 */ + __u64 gg15; /* 0x00a8 */ + __u8 reservedb0[8]; /* 0x00b0 */ +#define HPID_KVM 0x4 +#define HPID_VSIE 0x5 + __u8 hpid; /* 0x00b8 */ + __u8 reservedb9[7]; /* 0x00b9 */ + union { + struct { + __u32 eiparams; /* 0x00c0 */ + __u16 extcpuaddr; /* 0x00c4 */ + __u16 eic; /* 0x00c6 */ + }; + __u64 mcic; /* 0x00c0 */ + } __packed; + __u32 reservedc8; /* 0x00c8 */ + union { + struct { + __u16 pgmilc; /* 0x00cc */ + __u16 iprcc; /* 0x00ce */ + }; + __u32 edc; /* 0x00cc */ + } __packed; + union { + struct { + __u32 dxc; /* 0x00d0 */ + __u16 mcn; /* 0x00d4 */ + __u8 perc; /* 0x00d6 */ + __u8 peratmid; /* 0x00d7 */ + }; + __u64 faddr; /* 0x00d0 */ + } __packed; + __u64 peraddr; /* 0x00d8 */ + __u8 eai; /* 0x00e0 */ + __u8 peraid; /* 0x00e1 */ + __u8 oai; /* 0x00e2 */ + __u8 armid; /* 0x00e3 */ + __u8 reservede4[4]; /* 0x00e4 */ + union { + __u64 tecmc; /* 0x00e8 */ + struct { + __u16 subchannel_id; /* 0x00e8 */ + __u16 subchannel_nr; /* 0x00ea */ + __u32 io_int_parm; /* 0x00ec */ + __u32 io_int_word; /* 0x00f0 */ + }; + } __packed; + __u8 reservedf4[8]; /* 0x00f4 */ +#define CRYCB_FORMAT_MASK 0x00000003 +#define CRYCB_FORMAT0 0x00000000 +#define CRYCB_FORMAT1 0x00000001 +#define CRYCB_FORMAT2 0x00000003 + __u32 crycbd; /* 0x00fc */ + __u64 gcr[16]; /* 0x0100 */ + union { + __u64 gbea; /* 0x0180 */ + __u64 sidad; + }; + __u8 reserved188[8]; /* 0x0188 */ + __u64 sdnxo; /* 0x0190 */ + __u8 reserved198[8]; /* 0x0198 */ + __u32 fac; /* 0x01a0 */ + __u8 reserved1a4[20]; /* 0x01a4 */ + __u64 cbrlo; /* 0x01b8 */ + __u8 reserved1c0[8]; /* 0x01c0 */ +#define ECD_HOSTREGMGMT 0x20000000 +#define ECD_MEF 0x08000000 +#define ECD_ETOKENF 0x02000000 +#define ECD_ECC 0x00200000 + __u32 ecd; /* 0x01c8 */ + __u8 reserved1cc[18]; /* 0x01cc */ + __u64 pp; /* 0x01de */ + __u8 reserved1e6[2]; /* 0x01e6 */ + __u64 itdba; /* 0x01e8 */ + __u64 riccbd; /* 0x01f0 */ + __u64 gvrd; /* 0x01f8 */ +} __packed __aligned(512); + +#endif /* SELFTEST_KVM_SIE_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h index 0f268b55fa06..51990094effd 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86_64/apic.h @@ -11,6 +11,7 @@ #include <stdint.h> #include "processor.h" +#include "ucall_common.h" #define APIC_DEFAULT_GPA 0xfee00000ULL @@ -93,9 +94,27 @@ static inline uint64_t x2apic_read_reg(unsigned int reg) return rdmsr(APIC_BASE_MSR + (reg >> 4)); } +static inline uint8_t x2apic_write_reg_safe(unsigned int reg, uint64_t value) +{ + return wrmsr_safe(APIC_BASE_MSR + (reg >> 4), value); +} + static inline void x2apic_write_reg(unsigned int reg, uint64_t value) { - wrmsr(APIC_BASE_MSR + (reg >> 4), value); + uint8_t fault = x2apic_write_reg_safe(reg, value); + + __GUEST_ASSERT(!fault, "Unexpected fault 0x%x on WRMSR(%x) = %lx\n", + fault, APIC_BASE_MSR + (reg >> 4), value); } +static inline void x2apic_write_reg_fault(unsigned int reg, uint64_t value) +{ + uint8_t fault = x2apic_write_reg_safe(reg, value); + + __GUEST_ASSERT(fault == GP_VECTOR, + "Wanted #GP on WRMSR(%x) = %lx, got 0x%x\n", + APIC_BASE_MSR + (reg >> 4), value, fault); +} + + #endif /* SELFTEST_KVM_APIC_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index fa65b908b13e..6849e2552f1b 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -186,6 +186,18 @@ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED \ KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14) +/* HYPERV_CPUID_NESTED_FEATURES.EAX */ +#define HV_X64_NESTED_DIRECT_FLUSH \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 17) +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 18) +#define HV_X64_NESTED_MSR_BITMAP \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EAX, 19) + +/* HYPERV_CPUID_NESTED_FEATURES.EBX */ +#define HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_NESTED_FEATURES, 0, EBX, 0) + /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ #define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING \ KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1) @@ -343,4 +355,10 @@ struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); + +bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature); + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index a0c1440017bb..e247f99e0473 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -25,6 +25,10 @@ extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; extern uint64_t guest_tsc_khz; +#ifndef MAX_NR_CPUID_ENTRIES +#define MAX_NR_CPUID_ENTRIES 100 +#endif + /* Forced emulation prefix, used to invoke the emulator unconditionally. */ #define KVM_FEP "ud2; .byte 'k', 'v', 'm';" @@ -908,8 +912,6 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs) const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, uint32_t function, uint32_t index); const struct kvm_cpuid2 *kvm_get_supported_cpuid(void); -const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); -const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu); static inline uint32_t kvm_cpu_fms(void) { @@ -1009,7 +1011,6 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries) } void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid); -void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu); static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function, diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 56b170b725b3..a2b7df5f1d39 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -712,16 +712,13 @@ void kvm_vm_release(struct kvm_vm *vmp) } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region, - bool unlink) + struct userspace_mem_region *region) { int ret; - if (unlink) { - rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); - rb_erase(®ion->hva_node, &vm->regions.hva_tree); - hash_del(®ion->slot_node); - } + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); region->region.memory_size = 0; vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); @@ -762,7 +759,7 @@ void kvm_vm_free(struct kvm_vm *vmp) /* Free userspace_mem_regions. */ hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) - __vm_mem_region_delete(vmp, region, false); + __vm_mem_region_delete(vmp, region); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -794,76 +791,6 @@ int kvm_memfd_alloc(size_t size, bool hugepages) return fd; } -/* - * Memory Compare, host virtual to guest virtual - * - * Input Args: - * hva - Starting host virtual address - * vm - Virtual Machine - * gva - Starting guest virtual address - * len - number of bytes to compare - * - * Output Args: None - * - * Input/Output Args: None - * - * Return: - * Returns 0 if the bytes starting at hva for a length of len - * are equal the guest virtual bytes starting at gva. Returns - * a value < 0, if bytes at hva are less than those at gva. - * Otherwise a value > 0 is returned. - * - * Compares the bytes starting at the host virtual address hva, for - * a length of len, to the guest bytes starting at the guest virtual - * address given by gva. - */ -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) -{ - size_t amt; - - /* - * Compare a batch of bytes until either a match is found - * or all the bytes have been compared. - */ - for (uintptr_t offset = 0; offset < len; offset += amt) { - uintptr_t ptr1 = (uintptr_t)hva + offset; - - /* - * Determine host address for guest virtual address - * at offset. - */ - uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset); - - /* - * Determine amount to compare on this pass. - * Don't allow the comparsion to cross a page boundary. - */ - amt = len - offset; - if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr1 % vm->page_size); - if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr2 % vm->page_size); - - assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift)); - assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift)); - - /* - * Perform the comparison. If there is a difference - * return that result to the caller, otherwise need - * to continue on looking for a mismatch. - */ - int ret = memcmp((void *)ptr1, (void *)ptr2, amt); - if (ret != 0) - return ret; - } - - /* - * No mismatch found. Let the caller know the two memory - * areas are equal. - */ - return 0; -} - static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, struct userspace_mem_region *region) { @@ -1270,7 +1197,7 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot), true); + __vm_mem_region_delete(vm, memslot2region(vm, slot)); } void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index 4ad4492eea1d..20cfe970e3e3 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -14,7 +14,7 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm) { vm_paddr_t paddr; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); if (vm->pgd_created) @@ -79,7 +79,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa) } /* Fill in page table entry */ - idx = (gva >> 12) & 0x0ffu; /* page index */ + idx = (gva >> PAGE_SHIFT) & 0x0ffu; /* page index */ if (!(entry[idx] & PAGE_INVALID)) fprintf(stderr, "WARNING: PTE for gpa=0x%"PRIx64" already set!\n", gpa); @@ -91,7 +91,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) int ri, idx; uint64_t *entry; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); entry = addr_gpa2hva(vm, vm->pgd); @@ -103,7 +103,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN); } - idx = (gva >> 12) & 0x0ffu; /* page index */ + idx = (gva >> PAGE_SHIFT) & 0x0ffu; /* page index */ TEST_ASSERT(!(entry[idx] & PAGE_INVALID), "No page mapping for vm virtual address 0x%lx", gva); @@ -168,7 +168,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) struct kvm_sregs sregs; struct kvm_vcpu *vcpu; - TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x", + TEST_ASSERT(vm->page_size == PAGE_SIZE, "Unsupported page size: 0x%x", vm->page_size); stack_vaddr = __vm_vaddr_alloc(vm, stack_size, diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c index efb7e7a1354d..15bc8cd583aa 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c +++ b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c @@ -8,6 +8,73 @@ #include "processor.h" #include "hyperv.h" +const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) +{ + static struct kvm_cpuid2 *cpuid; + int kvm_fd; + + if (cpuid) + return cpuid; + + cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); + kvm_fd = open_kvm_dev_path_or_exit(); + + kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + + close(kvm_fd); + return cpuid; +} + +void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu) +{ + static struct kvm_cpuid2 *cpuid_full; + const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; + int i, nent = 0; + + if (!cpuid_full) { + cpuid_sys = kvm_get_supported_cpuid(); + cpuid_hv = kvm_get_supported_hv_cpuid(); + + cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent); + if (!cpuid_full) { + perror("malloc"); + abort(); + } + + /* Need to skip KVM CPUID leaves 0x400000xx */ + for (i = 0; i < cpuid_sys->nent; i++) { + if (cpuid_sys->entries[i].function >= 0x40000000 && + cpuid_sys->entries[i].function < 0x40000100) + continue; + cpuid_full->entries[nent] = cpuid_sys->entries[i]; + nent++; + } + + memcpy(&cpuid_full->entries[nent], cpuid_hv->entries, + cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2)); + cpuid_full->nent = nent + cpuid_hv->nent; + } + + vcpu_init_cpuid(vcpu, cpuid_full); +} + +const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); + + vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid); + + return cpuid; +} + +bool kvm_hv_cpu_has(struct kvm_x86_cpu_feature feature) +{ + if (!kvm_has_cap(KVM_CAP_SYS_HYPERV_CPUID)) + return false; + + return kvm_cpuid_has(kvm_get_supported_hv_cpuid(), feature); +} + struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, vm_vaddr_t *p_hv_pages_gva) { diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 153739f2e201..974bcd2df6d7 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,8 +19,6 @@ #define KERNEL_DS 0x10 #define KERNEL_TSS 0x18 -#define MAX_NR_CPUID_ENTRIES 100 - vm_vaddr_t exception_handlers; bool host_cpu_is_amd; bool host_cpu_is_intel; @@ -566,10 +564,8 @@ void route_exception(struct ex_regs *regs) if (kvm_fixup_exception(regs)) return; - ucall_assert(UCALL_UNHANDLED, - "Unhandled exception in guest", __FILE__, __LINE__, - "Unhandled exception '0x%lx' at guest RIP '0x%lx'", - regs->vector, regs->rip); + GUEST_FAIL("Unhandled exception '0x%lx' at guest RIP '0x%lx'", + regs->vector, regs->rip); } static void vm_init_descriptor_tables(struct kvm_vm *vm) @@ -611,7 +607,7 @@ void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { struct ucall uc; - if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) + if (get_ucall(vcpu, &uc) == UCALL_ABORT) REPORT_GUEST_ASSERT(uc); } @@ -1195,65 +1191,6 @@ void xen_hypercall(uint64_t nr, uint64_t a0, void *a1) GUEST_ASSERT(!__xen_hypercall(nr, a0, a1)); } -const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void) -{ - static struct kvm_cpuid2 *cpuid; - int kvm_fd; - - if (cpuid) - return cpuid; - - cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); - kvm_fd = open_kvm_dev_path_or_exit(); - - kvm_ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid); - - close(kvm_fd); - return cpuid; -} - -void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu) -{ - static struct kvm_cpuid2 *cpuid_full; - const struct kvm_cpuid2 *cpuid_sys, *cpuid_hv; - int i, nent = 0; - - if (!cpuid_full) { - cpuid_sys = kvm_get_supported_cpuid(); - cpuid_hv = kvm_get_supported_hv_cpuid(); - - cpuid_full = allocate_kvm_cpuid2(cpuid_sys->nent + cpuid_hv->nent); - if (!cpuid_full) { - perror("malloc"); - abort(); - } - - /* Need to skip KVM CPUID leaves 0x400000xx */ - for (i = 0; i < cpuid_sys->nent; i++) { - if (cpuid_sys->entries[i].function >= 0x40000000 && - cpuid_sys->entries[i].function < 0x40000100) - continue; - cpuid_full->entries[nent] = cpuid_sys->entries[i]; - nent++; - } - - memcpy(&cpuid_full->entries[nent], cpuid_hv->entries, - cpuid_hv->nent * sizeof(struct kvm_cpuid_entry2)); - cpuid_full->nent = nent + cpuid_hv->nent; - } - - vcpu_init_cpuid(vcpu, cpuid_full); -} - -const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid2 *cpuid = allocate_kvm_cpuid2(MAX_NR_CPUID_ENTRIES); - - vcpu_ioctl(vcpu, KVM_GET_SUPPORTED_HV_CPUID, cpuid); - - return cpuid; -} - unsigned long vm_compute_max_gfn(struct kvm_vm *vm) { const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 49f162573126..e3343f0df9e1 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -79,6 +79,7 @@ struct test_params { useconds_t delay; uint64_t nr_iterations; bool partition_vcpu_memory_access; + bool disable_slot_zap_quirk; }; static void run_test(enum vm_guest_mode mode, void *arg) @@ -89,6 +90,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, VM_MEM_SRC_ANONYMOUS, p->partition_vcpu_memory_access); +#ifdef __x86_64__ + if (p->disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + + pr_info("Memslot zap quirk %s\n", p->disable_slot_zap_quirk ? + "disabled" : "enabled"); +#endif pr_info("Finished creating vCPUs\n"); @@ -107,11 +115,12 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m mode] [-d delay_usec]\n" + printf("usage: %s [-h] [-m mode] [-d delay_usec] [-q]\n" " [-b memory] [-v vcpus] [-o] [-i iterations]\n", name); guest_modes_help(); printf(" -d: add a delay between each iteration of adding and\n" " deleting a memslot in usec.\n"); + printf(" -q: Disable memslot zap quirk.\n"); printf(" -b: specify the size of the memory region which should be\n" " accessed by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); @@ -137,7 +146,7 @@ int main(int argc, char *argv[]) guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:d:b:v:oi:")) != -1) { + while ((opt = getopt(argc, argv, "hm:d:qb:v:oi:")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -160,6 +169,12 @@ int main(int argc, char *argv[]) case 'i': p.nr_iterations = atoi_positive("Number of iterations", optarg); break; + case 'q': + p.disable_slot_zap_quirk = true; + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & + KVM_X86_QUIRK_SLOT_ZAP_ALL); + break; case 'h': default: help(argv[0]); diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 579a64f97333..893366982f77 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -113,6 +113,7 @@ static_assert(ATOMIC_BOOL_LOCK_FREE == 2, "atomic bool is not lockless"); static sem_t vcpu_ready; static bool map_unmap_verify; +static bool disable_slot_zap_quirk; static bool verbose; #define pr_info_v(...) \ @@ -578,6 +579,9 @@ static bool test_memslot_move_prepare(struct vm_data *data, uint32_t guest_page_size = data->vm->page_size; uint64_t movesrcgpa, movetestgpa; + if (disable_slot_zap_quirk) + vm_enable_cap(data->vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + movesrcgpa = vm_slot2gpa(data, data->nslots - 1); if (isactive) { @@ -896,6 +900,7 @@ static void help(char *name, struct test_args *targs) pr_info(" -h: print this help screen.\n"); pr_info(" -v: enable verbose mode (not for benchmarking).\n"); pr_info(" -d: enable extra debug checks.\n"); + pr_info(" -q: Disable memslot zap quirk during memslot move.\n"); pr_info(" -s: specify memslot count cap (-1 means no cap; currently: %i)\n", targs->nslots); pr_info(" -f: specify the first test to run (currently: %i; max %zu)\n", @@ -954,7 +959,7 @@ static bool parse_args(int argc, char *argv[], uint32_t max_mem_slots; int opt; - while ((opt = getopt(argc, argv, "hvds:f:e:l:r:")) != -1) { + while ((opt = getopt(argc, argv, "hvdqs:f:e:l:r:")) != -1) { switch (opt) { case 'h': default: @@ -966,6 +971,11 @@ static bool parse_args(int argc, char *argv[], case 'd': map_unmap_verify = true; break; + case 'q': + disable_slot_zap_quirk = true; + TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & + KVM_X86_QUIRK_SLOT_ZAP_ALL); + break; case 's': targs->nslots = atoi_paranoid(optarg); if (targs->nslots <= 1 && targs->nslots != -1) { diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c index b39033844756..e32dd59703a0 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390x/cmma_test.c @@ -17,16 +17,17 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" #define MAIN_PAGE_COUNT 512 #define TEST_DATA_PAGE_COUNT 512 #define TEST_DATA_MEMSLOT 1 -#define TEST_DATA_START_GFN 4096 +#define TEST_DATA_START_GFN PAGE_SIZE #define TEST_DATA_TWO_PAGE_COUNT 256 #define TEST_DATA_TWO_MEMSLOT 2 -#define TEST_DATA_TWO_START_GFN 8192 +#define TEST_DATA_TWO_START_GFN (2 * PAGE_SIZE) static char cmma_value_buf[MAIN_PAGE_COUNT + TEST_DATA_PAGE_COUNT]; @@ -66,7 +67,7 @@ static void guest_dirty_test_data(void) " lghi 5,%[page_count]\n" /* r5 += r1 */ "2: agfr 5,1\n" - /* r2 = r1 << 12 */ + /* r2 = r1 << PAGE_SHIFT */ "1: sllg 2,1,12(0)\n" /* essa(r4, r2, SET_STABLE) */ " .insn rrf,0xb9ab0000,4,2,1,0\n" diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390x/config new file mode 100644 index 000000000000..23270f2d679f --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/config @@ -0,0 +1,2 @@ +CONFIG_KVM=y +CONFIG_KVM_S390_UCONTROL=y diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390x/debug_test.c index 84313fb27529..ad8095968601 100644 --- a/tools/testing/selftests/kvm/s390x/debug_test.c +++ b/tools/testing/selftests/kvm/s390x/debug_test.c @@ -2,12 +2,12 @@ /* Test KVM debugging features. */ #include "kvm_util.h" #include "test_util.h" +#include "sie.h" #include <linux/kvm.h> #define __LC_SVC_NEW_PSW 0x1c0 #define __LC_PGM_NEW_PSW 0x1d0 -#define ICPT_INSTRUCTION 0x04 #define IPA0_DIAG 0x8300 #define PGM_SPECIFICATION 0x06 @@ -85,7 +85,7 @@ static void test_step_pgm_diag(void) vm = test_step_int_1(&vcpu, test_step_pgm_diag_guest_code, __LC_PGM_NEW_PSW, new_psw); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_S390_SIEIC); - TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INSTRUCTION); + TEST_ASSERT_EQ(vcpu->run->s390_sieic.icptcode, ICPT_INST); TEST_ASSERT_EQ(vcpu->run->s390_sieic.ipa & 0xff00, IPA0_DIAG); vcpu_ioctl(vcpu, KVM_S390_IRQ, &irq); vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index f2df7416be84..4374b4cd2a80 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -16,6 +16,7 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" enum mop_target { LOGICAL, @@ -226,9 +227,6 @@ static void memop_ioctl(struct test_info info, struct kvm_s390_mem_op *ksmo, #define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); }) -#define PAGE_SHIFT 12 -#define PAGE_SIZE (1ULL << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c index 7a742a673b7c..12d5e1cb62e3 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -9,9 +9,8 @@ #include "kvm_util.h" #include "kselftest.h" #include "ucall_common.h" +#include "processor.h" -#define PAGE_SHIFT 12 -#define PAGE_SIZE (1 << PAGE_SHIFT) #define CR0_FETCH_PROTECTION_OVERRIDE (1UL << (63 - 38)) #define CR0_STORAGE_PROTECTION_OVERRIDE (1UL << (63 - 39)) @@ -151,7 +150,7 @@ static enum stage perform_next_stage(int *i, bool mapped_0) * instead. * In order to skip these tests we detect this inside the guest */ - skip = tests[*i].addr < (void *)4096 && + skip = tests[*i].addr < (void *)PAGE_SIZE && tests[*i].expected != TRANSL_UNAVAIL && !mapped_0; if (!skip) { diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c new file mode 100644 index 000000000000..f257beec1430 --- /dev/null +++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test code for the s390x kvm ucontrol interface + * + * Copyright IBM Corp. 2024 + * + * Authors: + * Christoph Schlameuss <schlameuss@linux.ibm.com> + */ +#include "debug_print.h" +#include "kselftest_harness.h" +#include "kvm_util.h" +#include "processor.h" +#include "sie.h" + +#include <linux/capability.h> +#include <linux/sizes.h> + +#define VM_MEM_SIZE (4 * SZ_1M) + +/* so directly declare capget to check caps without libcap */ +int capget(cap_user_header_t header, cap_user_data_t data); + +/** + * In order to create user controlled virtual machines on S390, + * check KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL + * as privileged user (SYS_ADMIN). + */ +void require_ucontrol_admin(void) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + int rc; + + rc = capget(&hdr, data); + TEST_ASSERT_EQ(0, rc); + TEST_REQUIRE((data->effective & CAP_TO_MASK(CAP_SYS_ADMIN)) > 0); + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_UCONTROL)); +} + +/* Test program setting some registers and looping */ +extern char test_gprs_asm[]; +asm("test_gprs_asm:\n" + "xgr %r0, %r0\n" + "lgfi %r1,1\n" + "lgfi %r2,2\n" + "lgfi %r3,3\n" + "lgfi %r4,4\n" + "lgfi %r5,5\n" + "lgfi %r6,6\n" + "lgfi %r7,7\n" + "0:\n" + " diag 0,0,0x44\n" + " ahi %r0,1\n" + " j 0b\n" +); + +FIXTURE(uc_kvm) +{ + struct kvm_s390_sie_block *sie_block; + struct kvm_run *run; + uintptr_t base_gpa; + uintptr_t code_gpa; + uintptr_t base_hva; + uintptr_t code_hva; + int kvm_run_size; + void *vm_mem; + int vcpu_fd; + int kvm_fd; + int vm_fd; +}; + +/** + * create VM with single vcpu, map kvm_run and SIE control block for easy access + */ +FIXTURE_SETUP(uc_kvm) +{ + struct kvm_s390_vm_cpu_processor info; + int rc; + + require_ucontrol_admin(); + + self->kvm_fd = open_kvm_dev_path_or_exit(); + self->vm_fd = ioctl(self->kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL); + ASSERT_GE(self->vm_fd, 0); + + kvm_device_attr_get(self->vm_fd, KVM_S390_VM_CPU_MODEL, + KVM_S390_VM_CPU_PROCESSOR, &info); + TH_LOG("create VM 0x%llx", info.cpuid); + + self->vcpu_fd = ioctl(self->vm_fd, KVM_CREATE_VCPU, 0); + ASSERT_GE(self->vcpu_fd, 0); + + self->kvm_run_size = ioctl(self->kvm_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); + ASSERT_GE(self->kvm_run_size, sizeof(struct kvm_run)) + TH_LOG(KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, self->kvm_run_size)); + self->run = (struct kvm_run *)mmap(NULL, self->kvm_run_size, + PROT_READ | PROT_WRITE, MAP_SHARED, self->vcpu_fd, 0); + ASSERT_NE(self->run, MAP_FAILED); + /** + * For virtual cpus that have been created with S390 user controlled + * virtual machines, the resulting vcpu fd can be memory mapped at page + * offset KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of + * the virtual cpu's hardware control block. + */ + self->sie_block = (struct kvm_s390_sie_block *)mmap(NULL, PAGE_SIZE, + PROT_READ | PROT_WRITE, MAP_SHARED, + self->vcpu_fd, KVM_S390_SIE_PAGE_OFFSET << PAGE_SHIFT); + ASSERT_NE(self->sie_block, MAP_FAILED); + + TH_LOG("VM created %p %p", self->run, self->sie_block); + + self->base_gpa = 0; + self->code_gpa = self->base_gpa + (3 * SZ_1M); + + self->vm_mem = aligned_alloc(SZ_1M, VM_MEM_SIZE); + ASSERT_NE(NULL, self->vm_mem) TH_LOG("malloc failed %u", errno); + self->base_hva = (uintptr_t)self->vm_mem; + self->code_hva = self->base_hva - self->base_gpa + self->code_gpa; + struct kvm_s390_ucas_mapping map = { + .user_addr = self->base_hva, + .vcpu_addr = self->base_gpa, + .length = VM_MEM_SIZE, + }; + TH_LOG("ucas map %p %p 0x%llx", + (void *)map.user_addr, (void *)map.vcpu_addr, map.length); + rc = ioctl(self->vcpu_fd, KVM_S390_UCAS_MAP, &map); + ASSERT_EQ(0, rc) TH_LOG("ucas map result %d not expected, %s", + rc, strerror(errno)); + + TH_LOG("page in %p", (void *)self->base_gpa); + rc = ioctl(self->vcpu_fd, KVM_S390_VCPU_FAULT, self->base_gpa); + ASSERT_EQ(0, rc) TH_LOG("vcpu fault (%p) result %d not expected, %s", + (void *)self->base_hva, rc, strerror(errno)); + + self->sie_block->cpuflags &= ~CPUSTAT_STOPPED; +} + +FIXTURE_TEARDOWN(uc_kvm) +{ + munmap(self->sie_block, PAGE_SIZE); + munmap(self->run, self->kvm_run_size); + close(self->vcpu_fd); + close(self->vm_fd); + close(self->kvm_fd); + free(self->vm_mem); +} + +TEST_F(uc_kvm, uc_sie_assertions) +{ + /* assert interception of Code 08 (Program Interruption) is set */ + EXPECT_EQ(0, self->sie_block->ecb & ECB_SPECI); +} + +TEST_F(uc_kvm, uc_attr_mem_limit) +{ + u64 limit; + struct kvm_device_attr attr = { + .group = KVM_S390_VM_MEM_CTRL, + .attr = KVM_S390_VM_MEM_LIMIT_SIZE, + .addr = (unsigned long)&limit, + }; + int rc; + + rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr); + EXPECT_EQ(0, rc); + EXPECT_EQ(~0UL, limit); + + /* assert set not supported */ + rc = ioctl(self->vm_fd, KVM_SET_DEVICE_ATTR, &attr); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +TEST_F(uc_kvm, uc_no_dirty_log) +{ + struct kvm_dirty_log dlog; + int rc; + + rc = ioctl(self->vm_fd, KVM_GET_DIRTY_LOG, &dlog); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +/** + * Assert HPAGE CAP cannot be enabled on UCONTROL VM + */ +TEST(uc_cap_hpage) +{ + int rc, kvm_fd, vm_fd, vcpu_fd; + struct kvm_enable_cap cap = { + .cap = KVM_CAP_S390_HPAGE_1M, + }; + + require_ucontrol_admin(); + + kvm_fd = open_kvm_dev_path_or_exit(); + vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, KVM_VM_S390_UCONTROL); + ASSERT_GE(vm_fd, 0); + + /* assert hpages are not supported on ucontrol vm */ + rc = ioctl(vm_fd, KVM_CHECK_EXTENSION, KVM_CAP_S390_HPAGE_1M); + EXPECT_EQ(0, rc); + + /* Test that KVM_CAP_S390_HPAGE_1M can't be enabled for a ucontrol vm */ + rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); + + /* assert HPAGE CAP is rejected after vCPU creation */ + vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0); + ASSERT_GE(vcpu_fd, 0); + rc = ioctl(vm_fd, KVM_ENABLE_CAP, cap); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EBUSY, errno); + + close(vcpu_fd); + close(vm_fd); + close(kvm_fd); +} + +/* verify SIEIC exit + * * fail on codes not expected in the test cases + */ +static bool uc_handle_sieic(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_s390_sie_block *sie_block = self->sie_block; + struct kvm_run *run = self->run; + + /* check SIE interception code */ + pr_info("sieic: 0x%.2x 0x%.4x 0x%.4x\n", + run->s390_sieic.icptcode, + run->s390_sieic.ipa, + run->s390_sieic.ipb); + switch (run->s390_sieic.icptcode) { + case ICPT_INST: + /* end execution in caller on intercepted instruction */ + pr_info("sie instruction interception\n"); + return false; + case ICPT_OPEREXC: + /* operation exception */ + TEST_FAIL("sie exception on %.4x%.8x", sie_block->ipa, sie_block->ipb); + default: + TEST_FAIL("UNEXPECTED SIEIC CODE %d", run->s390_sieic.icptcode); + } + return true; +} + +/* verify VM state on exit */ +static bool uc_handle_exit(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_run *run = self->run; + + switch (run->exit_reason) { + case KVM_EXIT_S390_SIEIC: + return uc_handle_sieic(self); + default: + pr_info("exit_reason %2d not handled\n", run->exit_reason); + } + return true; +} + +/* run the VM until interrupted */ +static int uc_run_once(FIXTURE_DATA(uc_kvm) * self) +{ + int rc; + + rc = ioctl(self->vcpu_fd, KVM_RUN, NULL); + print_run(self->run, self->sie_block); + print_regs(self->run); + pr_debug("run %d / %d %s\n", rc, errno, strerror(errno)); + return rc; +} + +static void uc_assert_diag44(FIXTURE_DATA(uc_kvm) * self) +{ + struct kvm_s390_sie_block *sie_block = self->sie_block; + + /* assert vm was interrupted by diag 0x0044 */ + TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason); + TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode); + TEST_ASSERT_EQ(0x8300, sie_block->ipa); + TEST_ASSERT_EQ(0x440000, sie_block->ipb); +} + +TEST_F(uc_kvm, uc_gprs) +{ + struct kvm_sync_regs *sync_regs = &self->run->s.regs; + struct kvm_run *run = self->run; + struct kvm_regs regs = {}; + + /* Set registers to values that are different from the ones that we expect below */ + for (int i = 0; i < 8; i++) + sync_regs->gprs[i] = 8; + run->kvm_dirty_regs |= KVM_SYNC_GPRS; + + /* copy test_gprs_asm to code_hva / code_gpa */ + TH_LOG("copy code %p to vm mapped memory %p / %p", + &test_gprs_asm, (void *)self->code_hva, (void *)self->code_gpa); + memcpy((void *)self->code_hva, &test_gprs_asm, PAGE_SIZE); + + /* DAT disabled + 64 bit mode */ + run->psw_mask = 0x0000000180000000ULL; + run->psw_addr = self->code_gpa; + + /* run and expect interception of diag 44 */ + ASSERT_EQ(0, uc_run_once(self)); + ASSERT_EQ(false, uc_handle_exit(self)); + uc_assert_diag44(self); + + /* Retrieve and check guest register values */ + ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, ®s)); + for (int i = 0; i < 8; i++) { + ASSERT_EQ(i, regs.gprs[i]); + ASSERT_EQ(i, sync_regs->gprs[i]); + } + + /* run and expect interception of diag 44 again */ + ASSERT_EQ(0, uc_run_once(self)); + ASSERT_EQ(false, uc_handle_exit(self)); + uc_assert_diag44(self); + + /* check continued increment of register 0 value */ + ASSERT_EQ(0, ioctl(self->vcpu_fd, KVM_GET_REGS, ®s)); + ASSERT_EQ(1, regs.gprs[0]); + ASSERT_EQ(1, sync_regs->gprs[0]); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index bb8002084f52..a8267628e9ed 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -175,7 +175,7 @@ static void guest_code_move_memory_region(void) GUEST_DONE(); } -static void test_move_memory_region(void) +static void test_move_memory_region(bool disable_slot_zap_quirk) { pthread_t vcpu_thread; struct kvm_vcpu *vcpu; @@ -184,6 +184,9 @@ static void test_move_memory_region(void) vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_move_memory_region); + if (disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + hva = addr_gpa2hva(vm, MEM_REGION_GPA); /* @@ -266,7 +269,7 @@ static void guest_code_delete_memory_region(void) GUEST_ASSERT(0); } -static void test_delete_memory_region(void) +static void test_delete_memory_region(bool disable_slot_zap_quirk) { pthread_t vcpu_thread; struct kvm_vcpu *vcpu; @@ -276,6 +279,9 @@ static void test_delete_memory_region(void) vm = spawn_vm(&vcpu, &vcpu_thread, guest_code_delete_memory_region); + if (disable_slot_zap_quirk) + vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_SLOT_ZAP_ALL); + /* Delete the memory region, the guest should not die. */ vm_mem_region_delete(vm, MEM_REGION_SLOT); wait_for_vcpu(); @@ -553,7 +559,10 @@ int main(int argc, char *argv[]) { #ifdef __x86_64__ int i, loops; + int j, disable_slot_zap_quirk = 0; + if (kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_SLOT_ZAP_ALL) + disable_slot_zap_quirk = 1; /* * FIXME: the zero-memslot test fails on aarch64 and s390x because * KVM_RUN fails with ENOEXEC or EFAULT. @@ -579,13 +588,17 @@ int main(int argc, char *argv[]) else loops = 10; - pr_info("Testing MOVE of in-use region, %d loops\n", loops); - for (i = 0; i < loops; i++) - test_move_memory_region(); + for (j = 0; j <= disable_slot_zap_quirk; j++) { + pr_info("Testing MOVE of in-use region, %d loops, slot zap quirk %s\n", + loops, j ? "disabled" : "enabled"); + for (i = 0; i < loops; i++) + test_move_memory_region(!!j); - pr_info("Testing DELETE of in-use region, %d loops\n", loops); - for (i = 0; i < loops; i++) - test_delete_memory_region(); + pr_info("Testing DELETE of in-use region, %d loops, slot zap quirk %s\n", + loops, j ? "disabled" : "enabled"); + for (i = 0; i < loops; i++) + test_delete_memory_region(!!j); + } #endif return 0; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index f6b295e0b2d2..76cc2df9238a 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -47,15 +47,18 @@ static void guest_code(void) /* * Single step test, covers 2 basic instructions and 2 emulated * - * Enable interrupts during the single stepping to see that - * pending interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ + * Enable interrupts during the single stepping to see that pending + * interrupt we raised is not handled due to KVM_GUESTDBG_BLOCKIRQ. + * + * Write MSR_IA32_TSC_DEADLINE to verify that KVM's fastpath handler + * exits to userspace due to single-step being enabled. */ asm volatile("ss_start: " "sti\n\t" "xor %%eax,%%eax\n\t" "cpuid\n\t" - "movl $0x1a0,%%ecx\n\t" - "rdmsr\n\t" + "movl $" __stringify(MSR_IA32_TSC_DEADLINE) ", %%ecx\n\t" + "wrmsr\n\t" "cli\n\t" : : : "eax", "ebx", "ecx", "edx"); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index e192720bfe14..74cf19661309 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -242,7 +242,7 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); + TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index b987a3d79715..0ddb63229bcb 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -157,7 +157,7 @@ int main(int argc, char *argv[]) int stage; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); - TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); + TEST_REQUIRE(kvm_hv_cpu_has(HV_X64_NESTED_DIRECT_FLUSH)); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c index 7c70c0da4fb7..2e9197eb1652 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c @@ -160,6 +160,36 @@ static void test_sev(void *guest_code, uint64_t policy) kvm_vm_free(vm); } +static void guest_shutdown_code(void) +{ + struct desc_ptr idt; + + /* Clobber the IDT so that #UD is guaranteed to trigger SHUTDOWN. */ + memset(&idt, 0, sizeof(idt)); + __asm__ __volatile__("lidt %0" :: "m"(idt)); + + __asm__ __volatile__("ud2"); +} + +static void test_sev_es_shutdown(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + uint32_t type = KVM_X86_SEV_ES_VM; + + vm = vm_sev_create_with_one_vcpu(type, guest_shutdown_code, &vcpu); + + vm_sev_launch(vm, SEV_POLICY_ES, NULL); + + vcpu_run(vcpu); + TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SHUTDOWN, + "Wanted SHUTDOWN, got %s", + exit_reason_str(vcpu->run->exit_reason)); + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); @@ -171,6 +201,8 @@ int main(int argc, char *argv[]) test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG); test_sev(guest_sev_es_code, SEV_POLICY_ES); + test_sev_es_shutdown(); + if (kvm_has_cap(KVM_CAP_XCRS) && (xgetbv(0) & XFEATURE_MASK_X87_AVX) == XFEATURE_MASK_X87_AVX) { test_sync_vmsa(0); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index 618cd2442390..88bcca188799 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -13,6 +13,7 @@ struct xapic_vcpu { struct kvm_vcpu *vcpu; bool is_x2apic; + bool has_xavic_errata; }; static void xapic_guest_code(void) @@ -31,6 +32,10 @@ static void xapic_guest_code(void) } } +#define X2APIC_RSVD_BITS_MASK (GENMASK_ULL(31, 20) | \ + GENMASK_ULL(17, 16) | \ + GENMASK_ULL(13, 13)) + static void x2apic_guest_code(void) { asm volatile("cli"); @@ -41,7 +46,12 @@ static void x2apic_guest_code(void) uint64_t val = x2apic_read_reg(APIC_IRR) | x2apic_read_reg(APIC_IRR + 0x10) << 32; - x2apic_write_reg(APIC_ICR, val); + if (val & X2APIC_RSVD_BITS_MASK) { + x2apic_write_reg_fault(APIC_ICR, val); + } else { + x2apic_write_reg(APIC_ICR, val); + GUEST_ASSERT_EQ(x2apic_read_reg(APIC_ICR), val); + } GUEST_SYNC(val); } while (1); } @@ -71,27 +81,28 @@ static void ____test_icr(struct xapic_vcpu *x, uint64_t val) icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) | (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32; if (!x->is_x2apic) { - val &= (-1u | (0xffull << (32 + 24))); - TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); - } else { - TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + if (!x->has_xavic_errata) + val &= (-1u | (0xffull << (32 + 24))); + } else if (val & X2APIC_RSVD_BITS_MASK) { + return; } -} -#define X2APIC_RSVED_BITS_MASK (GENMASK_ULL(31,20) | \ - GENMASK_ULL(17,16) | \ - GENMASK_ULL(13,13)) + if (x->has_xavic_errata) + TEST_ASSERT_EQ(icr & ~APIC_ICR_BUSY, val & ~APIC_ICR_BUSY); + else + TEST_ASSERT_EQ(icr, val & ~APIC_ICR_BUSY); +} static void __test_icr(struct xapic_vcpu *x, uint64_t val) { - if (x->is_x2apic) { - /* Hardware writing vICR register requires reserved bits 31:20, - * 17:16 and 13 kept as zero to avoid #GP exception. Data value - * written to vICR should mask out those bits above. - */ - val &= ~X2APIC_RSVED_BITS_MASK; - } - ____test_icr(x, val | APIC_ICR_BUSY); + /* + * The BUSY bit is reserved on both AMD and Intel, but only AMD treats + * it is as _must_ be zero. Intel simply ignores the bit. Don't test + * the BUSY bit for x2APIC, as there is no single correct behavior. + */ + if (!x->is_x2apic) + ____test_icr(x, val | APIC_ICR_BUSY); + ____test_icr(x, val & ~(u64)APIC_ICR_BUSY); } @@ -231,6 +242,15 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&x.vcpu, xapic_guest_code); x.is_x2apic = false; + /* + * AMD's AVIC implementation is buggy (fails to clear the ICR BUSY bit), + * and also diverges from KVM with respect to ICR2[23:0] (KVM and Intel + * drops writes, AMD does not). Account for the errata when checking + * that KVM reads back what was written. + */ + x.has_xavic_errata = host_cpu_is_amd && + get_kvm_amd_param_bool("avic"); + vcpu_clear_cpuid_feature(x.vcpu, X86_FEATURE_X2APIC); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c index e149d0574961..2585087cdf5c 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c @@ -10,6 +10,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "hyperv.h" #define HCALL_REGION_GPA 0xc0000000ULL #define HCALL_REGION_SLOT 10 diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index fc90af2a97b8..bcc73b4e805c 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -15,7 +15,7 @@ #include <sys/ioctl.h> #include <sys/stat.h> #include <math.h> -#include <asm-generic/unistd.h> +#include <asm/unistd.h> #include <pthread.h> #include <sys/resource.h> #include <assert.h> diff --git a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c index 27f6fdf11969..644915862af8 100644 --- a/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c +++ b/tools/testing/selftests/vDSO/vdso_standalone_test_x86.c @@ -131,6 +131,8 @@ asm ( "_start:\n\t" #ifdef __x86_64__ "mov %rsp,%rdi\n\t" + "and $-16,%rsp\n\t" + "sub $8,%rsp\n\t" "jmp c_main" #else "push %esp\n\t" diff --git a/tools/testing/shared/maple-shared.h b/tools/testing/shared/maple-shared.h index 3d847edd149d..dc4d30f3860b 100644 --- a/tools/testing/shared/maple-shared.h +++ b/tools/testing/shared/maple-shared.h @@ -1,4 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef __MAPLE_SHARED_H__ +#define __MAPLE_SHARED_H__ #define CONFIG_DEBUG_MAPLE_TREE #define CONFIG_MAPLE_SEARCH @@ -7,3 +9,5 @@ #include <stdlib.h> #include <time.h> #include "linux/init.h" + +#endif /* __MAPLE_SHARED_H__ */ diff --git a/tools/testing/shared/shared.h b/tools/testing/shared/shared.h index f08f683812ad..13fb4d39966b 100644 --- a/tools/testing/shared/shared.h +++ b/tools/testing/shared/shared.h @@ -1,4 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SHARED_H__ +#define __SHARED_H__ #include <linux/types.h> #include <linux/bug.h> @@ -31,3 +33,5 @@ #ifndef dump_stack #define dump_stack() assert(0) #endif + +#endif /* __SHARED_H__ */ diff --git a/tools/testing/shared/shared.mk b/tools/testing/shared/shared.mk index a05f0588513a..a6bc51d0b0bf 100644 --- a/tools/testing/shared/shared.mk +++ b/tools/testing/shared/shared.mk @@ -15,7 +15,9 @@ SHARED_DEPS = Makefile ../shared/shared.mk ../shared/*.h generated/map-shift.h \ ../../../include/linux/maple_tree.h \ ../../../include/linux/radix-tree.h \ ../../../lib/radix-tree.h \ - ../../../include/linux/idr.h + ../../../include/linux/idr.h \ + ../../../lib/maple_tree.c \ + ../../../lib/test_maple_tree.c ifndef SHIFT SHIFT=3 diff --git a/tools/testing/shared/xarray-shared.h b/tools/testing/shared/xarray-shared.h index ac2d16ff53ae..d50de7884803 100644 --- a/tools/testing/shared/xarray-shared.h +++ b/tools/testing/shared/xarray-shared.h @@ -1,4 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef __XARRAY_SHARED_H__ +#define __XARRAY_SHARED_H__ #define XA_DEBUG #include "shared.h" + +#endif /* __XARRAY_SHARED_H__ */ diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 1b90acb6e3fe..375d6285475e 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -40,27 +40,6 @@ static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, return 1; } -static int coalesced_mmio_has_room(struct kvm_coalesced_mmio_dev *dev, u32 last) -{ - struct kvm_coalesced_mmio_ring *ring; - unsigned avail; - - /* Are we able to batch it ? */ - - /* last is the first free entry - * check if we don't meet the first used entry - * there is always one unused entry in the buffer - */ - ring = dev->kvm->coalesced_mmio_ring; - avail = (ring->first - last - 1) % KVM_COALESCED_MMIO_MAX; - if (avail == 0) { - /* full */ - return 0; - } - - return 1; -} - static int coalesced_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val) @@ -74,9 +53,15 @@ static int coalesced_mmio_write(struct kvm_vcpu *vcpu, spin_lock(&dev->kvm->ring_lock); + /* + * last is the index of the entry to fill. Verify userspace hasn't + * set last to be out of range, and that there is room in the ring. + * Leave one entry free in the ring so that userspace can differentiate + * between an empty ring and a full ring. + */ insert = READ_ONCE(ring->last); - if (!coalesced_mmio_has_room(dev, insert) || - insert >= KVM_COALESCED_MMIO_MAX) { + if (insert >= KVM_COALESCED_MMIO_MAX || + (insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f416d5e3f9c0..05cbb2548d99 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -136,8 +136,8 @@ static int kvm_no_compat_open(struct inode *inode, struct file *file) #define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ .open = kvm_no_compat_open #endif -static int hardware_enable_all(void); -static void hardware_disable_all(void); +static int kvm_enable_virtualization(void); +static void kvm_disable_virtualization(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); @@ -1220,7 +1220,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) if (r) goto out_err_no_arch_destroy_vm; - r = hardware_enable_all(); + r = kvm_enable_virtualization(); if (r) goto out_err_no_disable; @@ -1263,7 +1263,7 @@ out_no_coalesced_mmio: mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); #endif out_err_no_mmu_notifier: - hardware_disable_all(); + kvm_disable_virtualization(); out_err_no_disable: kvm_arch_destroy_vm(kvm); out_err_no_arch_destroy_vm: @@ -1360,7 +1360,7 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); - hardware_disable_all(); + kvm_disable_virtualization(); mmdrop(mm); } @@ -3270,6 +3270,9 @@ static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3343,6 +3346,9 @@ static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3373,6 +3379,9 @@ static int __kvm_write_guest_page(struct kvm *kvm, int r; unsigned long addr; + if (WARN_ON_ONCE(offset + len > PAGE_SIZE)) + return -EFAULT; + addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; @@ -3576,7 +3585,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) int ret; while ((seg = next_segment(len, offset)) != 0) { - ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len); + ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, seg); if (ret < 0) return ret; offset = 0; @@ -5566,137 +5575,67 @@ static struct miscdevice kvm_dev = { }; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +static bool enable_virt_at_load = true; +module_param(enable_virt_at_load, bool, 0444); + __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); -static DEFINE_PER_CPU(bool, hardware_enabled); +static DEFINE_PER_CPU(bool, virtualization_enabled); +static DEFINE_MUTEX(kvm_usage_lock); static int kvm_usage_count; -static int __hardware_enable_nolock(void) +__weak void kvm_arch_enable_virtualization(void) +{ + +} + +__weak void kvm_arch_disable_virtualization(void) +{ + +} + +static int kvm_enable_virtualization_cpu(void) { - if (__this_cpu_read(hardware_enabled)) + if (__this_cpu_read(virtualization_enabled)) return 0; - if (kvm_arch_hardware_enable()) { + if (kvm_arch_enable_virtualization_cpu()) { pr_info("kvm: enabling virtualization on CPU%d failed\n", raw_smp_processor_id()); return -EIO; } - __this_cpu_write(hardware_enabled, true); + __this_cpu_write(virtualization_enabled, true); return 0; } -static void hardware_enable_nolock(void *failed) -{ - if (__hardware_enable_nolock()) - atomic_inc(failed); -} - static int kvm_online_cpu(unsigned int cpu) { - int ret = 0; - /* * Abort the CPU online process if hardware virtualization cannot * be enabled. Otherwise running VMs would encounter unrecoverable * errors when scheduled to this CPU. */ - mutex_lock(&kvm_lock); - if (kvm_usage_count) - ret = __hardware_enable_nolock(); - mutex_unlock(&kvm_lock); - return ret; + return kvm_enable_virtualization_cpu(); } -static void hardware_disable_nolock(void *junk) +static void kvm_disable_virtualization_cpu(void *ign) { - /* - * Note, hardware_disable_all_nolock() tells all online CPUs to disable - * hardware, not just CPUs that successfully enabled hardware! - */ - if (!__this_cpu_read(hardware_enabled)) + if (!__this_cpu_read(virtualization_enabled)) return; - kvm_arch_hardware_disable(); + kvm_arch_disable_virtualization_cpu(); - __this_cpu_write(hardware_enabled, false); + __this_cpu_write(virtualization_enabled, false); } static int kvm_offline_cpu(unsigned int cpu) { - mutex_lock(&kvm_lock); - if (kvm_usage_count) - hardware_disable_nolock(NULL); - mutex_unlock(&kvm_lock); + kvm_disable_virtualization_cpu(NULL); return 0; } -static void hardware_disable_all_nolock(void) -{ - BUG_ON(!kvm_usage_count); - - kvm_usage_count--; - if (!kvm_usage_count) - on_each_cpu(hardware_disable_nolock, NULL, 1); -} - -static void hardware_disable_all(void) -{ - cpus_read_lock(); - mutex_lock(&kvm_lock); - hardware_disable_all_nolock(); - mutex_unlock(&kvm_lock); - cpus_read_unlock(); -} - -static int hardware_enable_all(void) -{ - atomic_t failed = ATOMIC_INIT(0); - int r; - - /* - * Do not enable hardware virtualization if the system is going down. - * If userspace initiated a forced reboot, e.g. reboot -f, then it's - * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling - * after kvm_reboot() is called. Note, this relies on system_state - * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops - * hook instead of registering a dedicated reboot notifier (the latter - * runs before system_state is updated). - */ - if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || - system_state == SYSTEM_RESTART) - return -EBUSY; - - /* - * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() - * is called, and so on_each_cpu() between them includes the CPU that - * is being onlined. As a result, hardware_enable_nolock() may get - * invoked before kvm_online_cpu(), which also enables hardware if the - * usage count is non-zero. Disable CPU hotplug to avoid attempting to - * enable hardware multiple times. - */ - cpus_read_lock(); - mutex_lock(&kvm_lock); - - r = 0; - - kvm_usage_count++; - if (kvm_usage_count == 1) { - on_each_cpu(hardware_enable_nolock, &failed, 1); - - if (atomic_read(&failed)) { - hardware_disable_all_nolock(); - r = -EBUSY; - } - } - - mutex_unlock(&kvm_lock); - cpus_read_unlock(); - - return r; -} - static void kvm_shutdown(void) { /* @@ -5712,34 +5651,32 @@ static void kvm_shutdown(void) */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; - on_each_cpu(hardware_disable_nolock, NULL, 1); + on_each_cpu(kvm_disable_virtualization_cpu, NULL, 1); } static int kvm_suspend(void) { /* * Secondary CPUs and CPU hotplug are disabled across the suspend/resume - * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count - * is stable. Assert that kvm_lock is not held to ensure the system - * isn't suspended while KVM is enabling hardware. Hardware enabling - * can be preempted, but the task cannot be frozen until it has dropped - * all locks (userspace tasks are frozen via a fake signal). + * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage + * count is stable. Assert that kvm_usage_lock is not held to ensure + * the system isn't suspended while KVM is enabling hardware. Hardware + * enabling can be preempted, but the task cannot be frozen until it has + * dropped all locks (userspace tasks are frozen via a fake signal). */ - lockdep_assert_not_held(&kvm_lock); + lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); - if (kvm_usage_count) - hardware_disable_nolock(NULL); + kvm_disable_virtualization_cpu(NULL); return 0; } static void kvm_resume(void) { - lockdep_assert_not_held(&kvm_lock); + lockdep_assert_not_held(&kvm_usage_lock); lockdep_assert_irqs_disabled(); - if (kvm_usage_count) - WARN_ON_ONCE(__hardware_enable_nolock()); + WARN_ON_ONCE(kvm_enable_virtualization_cpu()); } static struct syscore_ops kvm_syscore_ops = { @@ -5747,13 +5684,95 @@ static struct syscore_ops kvm_syscore_ops = { .resume = kvm_resume, .shutdown = kvm_shutdown, }; + +static int kvm_enable_virtualization(void) +{ + int r; + + guard(mutex)(&kvm_usage_lock); + + if (kvm_usage_count++) + return 0; + + kvm_arch_enable_virtualization(); + + r = cpuhp_setup_state(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); + if (r) + goto err_cpuhp; + + register_syscore_ops(&kvm_syscore_ops); + + /* + * Undo virtualization enabling and bail if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight operation to enable virtualization after + * syscore_shutdown() is called, i.e. without kvm_shutdown() being + * invoked. Note, this relies on system_state being set _before_ + * kvm_shutdown(), e.g. to ensure either kvm_shutdown() is invoked + * or this CPU observes the impending shutdown. Which is why KVM uses + * a syscore ops hook instead of registering a dedicated reboot + * notifier (the latter runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) { + r = -EBUSY; + goto err_rebooting; + } + + return 0; + +err_rebooting: + unregister_syscore_ops(&kvm_syscore_ops); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); +err_cpuhp: + kvm_arch_disable_virtualization(); + --kvm_usage_count; + return r; +} + +static void kvm_disable_virtualization(void) +{ + guard(mutex)(&kvm_usage_lock); + + if (--kvm_usage_count) + return; + + unregister_syscore_ops(&kvm_syscore_ops); + cpuhp_remove_state(CPUHP_AP_KVM_ONLINE); + kvm_arch_disable_virtualization(); +} + +static int kvm_init_virtualization(void) +{ + if (enable_virt_at_load) + return kvm_enable_virtualization(); + + return 0; +} + +static void kvm_uninit_virtualization(void) +{ + if (enable_virt_at_load) + kvm_disable_virtualization(); +} #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ -static int hardware_enable_all(void) +static int kvm_enable_virtualization(void) +{ + return 0; +} + +static int kvm_init_virtualization(void) { return 0; } -static void hardware_disable_all(void) +static void kvm_disable_virtualization(void) +{ + +} + +static void kvm_uninit_virtualization(void) { } @@ -6186,7 +6205,6 @@ static const struct file_operations stat_fops_per_vm = { .release = kvm_debugfs_release, .read = simple_attr_read, .write = simple_attr_write, - .llseek = no_llseek, }; static int vm_stat_get(void *_offset, u64 *val) @@ -6455,15 +6473,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) int r; int cpu; -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", - kvm_online_cpu, kvm_offline_cpu); - if (r) - return r; - - register_syscore_ops(&kvm_syscore_ops); -#endif - /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); @@ -6474,10 +6483,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) offsetofend(struct kvm_vcpu, stats_id) - offsetof(struct kvm_vcpu, arch), NULL); - if (!kvm_vcpu_cache) { - r = -ENOMEM; - goto err_vcpu_cache; - } + if (!kvm_vcpu_cache) + return -ENOMEM; for_each_possible_cpu(cpu) { if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), @@ -6511,6 +6518,10 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kvm_gmem_init(module); + r = kvm_init_virtualization(); + if (r) + goto err_virt; + /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! @@ -6524,6 +6535,8 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) return 0; err_register: + kvm_uninit_virtualization(); +err_virt: kvm_vfio_ops_exit(); err_vfio: kvm_async_pf_deinit(); @@ -6534,11 +6547,6 @@ err_cpu_kick_mask: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); -err_vcpu_cache: -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - unregister_syscore_ops(&kvm_syscore_ops); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); -#endif return r; } EXPORT_SYMBOL_GPL(kvm_init); @@ -6554,16 +6562,14 @@ void kvm_exit(void) */ misc_deregister(&kvm_dev); + kvm_uninit_virtualization(); + debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_vfio_ops_exit(); kvm_async_pf_deinit(); -#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING - unregister_syscore_ops(&kvm_syscore_ops); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); -#endif kvm_irqfd_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); |