diff options
262 files changed, 2680 insertions, 1358 deletions
diff --git a/Documentation/ABI/stable/sysfs-devices-system-xen_memory b/Documentation/ABI/stable/sysfs-devices-system-xen_memory index caa311d59ac1..6d83f95a8a8e 100644 --- a/Documentation/ABI/stable/sysfs-devices-system-xen_memory +++ b/Documentation/ABI/stable/sysfs-devices-system-xen_memory @@ -75,3 +75,12 @@ Contact: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Description: Amount (in KiB) of low (or normal) memory in the balloon. + +What: /sys/devices/system/xen_memory/xen_memory0/scrub_pages +Date: September 2018 +KernelVersion: 4.20 +Contact: xen-devel@lists.xenproject.org +Description: + Control scrubbing pages before returning them to Xen for others domains + use. Can be set with xen_scrub_pages cmdline + parameter. Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 64a3bf54b974..92eb1f42240d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5000,6 +5000,12 @@ Disables the PV optimizations forcing the HVM guest to run as generic HVM guest with no PV drivers. + xen_scrub_pages= [XEN] + Boolean option to control scrubbing pages before giving them back + to Xen, for use by other domains. Can be also changed at runtime + with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. + Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index 390c145f01d7..52a719b49afd 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -348,3 +348,7 @@ Version History 1.13.1 Fix deadlock caused by early md_stop_writes(). Also fix size an state races. 1.13.2 Fix raid redundancy validation and avoid keeping raid set frozen +1.14.0 Fix reshape race on small devices. Fix stripe adding reshape + deadlock/potential data corruption. Update superblock when + specific devices are requested via rebuild. Fix RAID leg + rebuild errors. diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 457d5ae16f23..3e17ac1d5d58 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -10,6 +10,7 @@ Required properties: Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on the Cadence GEM, or the generic form: "cdns,gem". Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs. + Use "atmel,sama5d3-macb" for the 10/100Mbit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs. Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 4b2084d0f1fb..a6c6a8af48a2 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -848,7 +848,7 @@ struct file_operations ---------------------- This describes how the VFS can manipulate an open file. As of kernel -4.1, the following members are defined: +4.18, the following members are defined: struct file_operations { struct module *owner; @@ -858,11 +858,11 @@ struct file_operations { ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iterate) (struct file *, struct dir_context *); + int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - int (*mremap)(struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -882,6 +882,10 @@ struct file_operations { #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif + ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); + int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); }; Again, all methods are called without any locks being held, unless @@ -899,6 +903,9 @@ otherwise noted. iterate: called when the VFS needs to read the directory contents + iterate_shared: called when the VFS needs to read the directory contents + when filesystem supports concurrent dir iterators + poll: called by the VFS when a process wants to check if there is activity on this file and (optionally) go to sleep until there is activity. Called by the select(2) and poll(2) system calls @@ -951,6 +958,16 @@ otherwise noted. fallocate: called by the VFS to preallocate blocks or punch a hole. + copy_file_range: called by the copy_file_range(2) system call. + + clone_file_range: called by the ioctl(2) system call for FICLONERANGE and + FICLONE commands. + + dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE + command. + + fadvise: possibly called by the fadvise64() system call. + Note that the file operations are implemented by the specific filesystem in which the inode resides. When opening a device node (character or block special) most filesystems will call special diff --git a/Documentation/process/code-of-conduct.rst b/Documentation/process/code-of-conduct.rst new file mode 100644 index 000000000000..ab7c24b5478c --- /dev/null +++ b/Documentation/process/code-of-conduct.rst @@ -0,0 +1,81 @@ +Contributor Covenant Code of Conduct +++++++++++++++++++++++++++++++++++++ + +Our Pledge +========== + +In the interest of fostering an open and welcoming environment, we as +contributors and maintainers pledge to making participation in our project and +our community a harassment-free experience for everyone, regardless of age, body +size, disability, ethnicity, sex characteristics, gender identity and +expression, level of experience, education, socio-economic status, nationality, +personal appearance, race, religion, or sexual identity and orientation. + +Our Standards +============= + +Examples of behavior that contributes to creating a positive environment +include: + +* Using welcoming and inclusive language +* Being respectful of differing viewpoints and experiences +* Gracefully accepting constructive criticism +* Focusing on what is best for the community +* Showing empathy towards other community members + + +Examples of unacceptable behavior by participants include: + +* The use of sexualized language or imagery and unwelcome sexual attention or + advances +* Trolling, insulting/derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others’ private information, such as a physical or electronic + address, without explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + + +Our Responsibilities +==================== + +Maintainers are responsible for clarifying the standards of acceptable behavior +and are expected to take appropriate and fair corrective action in response to +any instances of unacceptable behavior. + +Maintainers have the right and responsibility to remove, edit, or reject +comments, commits, code, wiki edits, issues, and other contributions that are +not aligned to this Code of Conduct, or to ban temporarily or permanently any +contributor for other behaviors that they deem inappropriate, threatening, +offensive, or harmful. + +Scope +===== + +This Code of Conduct applies both within project spaces and in public spaces +when an individual is representing the project or its community. Examples of +representing a project or community include using an official project e-mail +address, posting via an official social media account, or acting as an appointed +representative at an online or offline event. Representation of a project may be +further defined and clarified by project maintainers. + +Enforcement +=========== + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported by contacting the Technical Advisory Board (TAB) at +<tab@lists.linux-foundation.org>. All complaints will be reviewed and +investigated and will result in a response that is deemed necessary and +appropriate to the circumstances. The TAB is obligated to maintain +confidentiality with regard to the reporter of an incident. Further details of +specific enforcement policies may be posted separately. + +Maintainers who do not follow or enforce the Code of Conduct in good faith may +face temporary or permanent repercussions as determined by other members of the +project’s leadership. + +Attribution +=========== + +This Code of Conduct is adapted from the Contributor Covenant, version 1.4, +available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html diff --git a/Documentation/process/code-of-conflict.rst b/Documentation/process/code-of-conflict.rst deleted file mode 100644 index 47b6de763203..000000000000 --- a/Documentation/process/code-of-conflict.rst +++ /dev/null @@ -1,28 +0,0 @@ -Code of Conflict ----------------- - -The Linux kernel development effort is a very personal process compared -to "traditional" ways of developing software. Your code and ideas -behind it will be carefully reviewed, often resulting in critique and -criticism. The review will almost always require improvements to the -code before it can be included in the kernel. Know that this happens -because everyone involved wants to see the best possible solution for -the overall success of Linux. This development process has been proven -to create the most robust operating system kernel ever, and we do not -want to do anything to cause the quality of submission and eventual -result to ever decrease. - -If however, anyone feels personally abused, threatened, or otherwise -uncomfortable due to this process, that is not acceptable. If so, -please contact the Linux Foundation's Technical Advisory Board at -<tab@lists.linux-foundation.org>, or the individual members, and they -will work to resolve the issue to the best of their ability. For more -information on who is on the Technical Advisory Board and what their -role is, please see: - - - http://www.linuxfoundation.org/projects/linux/tab - -As a reviewer of code, please strive to keep things civil and focused on -the technical issues involved. We are all humans, and frustrations can -be high on both sides of the process. Try to keep in mind the immortal -words of Bill and Ted, "Be excellent to each other." diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index 37bd0628b6ee..9ae3e317bddf 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -20,7 +20,7 @@ Below are the essential guides that every developer should read. :maxdepth: 1 howto - code-of-conflict + code-of-conduct development-process submitting-patches coding-style diff --git a/Documentation/x86/earlyprintk.txt b/Documentation/x86/earlyprintk.txt index 688e3eeed21d..46933e06c972 100644 --- a/Documentation/x86/earlyprintk.txt +++ b/Documentation/x86/earlyprintk.txt @@ -35,25 +35,25 @@ and two USB cables, connected like this: ( If your system does not list a debug port capability then you probably won't be able to use the USB debug key. ) - b.) You also need a Netchip USB debug cable/key: + b.) You also need a NetChip USB debug cable/key: http://www.plxtech.com/products/NET2000/NET20DC/default.asp - This is a small blue plastic connector with two USB connections, + This is a small blue plastic connector with two USB connections; it draws power from its USB connections. c.) You need a second client/console system with a high speed USB 2.0 port. - d.) The Netchip device must be plugged directly into the physical + d.) The NetChip device must be plugged directly into the physical debug port on the "host/target" system. You cannot use a USB hub in between the physical debug port and the "host/target" system. The EHCI debug controller is bound to a specific physical USB - port and the Netchip device will only work as an early printk + port and the NetChip device will only work as an early printk device in this port. The EHCI host controllers are electrically wired such that the EHCI debug controller is hooked up to the - first physical and there is no way to change this via software. + first physical port and there is no way to change this via software. You can find the physical port through experimentation by trying each physical port on the system and rebooting. Or you can try and use lsusb or look at the kernel info messages emitted by the @@ -65,9 +65,9 @@ and two USB cables, connected like this: to the hardware vendor, because there is no reason not to wire this port into one of the physically accessible ports. - e.) It is also important to note, that many versions of the Netchip + e.) It is also important to note, that many versions of the NetChip device require the "client/console" system to be plugged into the - right and side of the device (with the product logo facing up and + right hand side of the device (with the product logo facing up and readable left to right). The reason being is that the 5 volt power supply is taken from only one side of the device and it must be the side that does not get rebooted. @@ -81,13 +81,18 @@ and two USB cables, connected like this: CONFIG_EARLY_PRINTK_DBGP=y And you need to add the boot command line: "earlyprintk=dbgp". + (If you are using Grub, append it to the 'kernel' line in - /etc/grub.conf) + /etc/grub.conf. If you are using Grub2 on a BIOS firmware system, + append it to the 'linux' line in /boot/grub2/grub.cfg. If you are + using Grub2 on an EFI firmware system, append it to the 'linux' + or 'linuxefi' line in /boot/grub2/grub.cfg or + /boot/efi/EFI/<distro>/grub.cfg.) On systems with more than one EHCI debug controller you must specify the correct EHCI debug controller number. The ordering comes from the PCI bus enumeration of the EHCI controllers. The - default with no number argument is "0" the first EHCI debug + default with no number argument is "0" or the first EHCI debug controller. To use the second EHCI debug controller, you would use the command line: "earlyprintk=dbgp1" @@ -111,7 +116,7 @@ and two USB cables, connected like this: see the raw output. c.) On Nvidia Southbridge based systems: the kernel will try to probe - and find out which port has debug device connected. + and find out which port has a debug device connected. 3. Testing that it works fine: diff --git a/MAINTAINERS b/MAINTAINERS index 4327777dce57..285bf51637d7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5625,6 +5625,8 @@ F: lib/fault-inject.c FBTFT Framebuffer drivers M: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> +L: dri-devel@lists.freedesktop.org +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/staging/fbtft/ @@ -6060,7 +6062,7 @@ F: Documentation/gcc-plugins.txt GASKET DRIVER FRAMEWORK M: Rob Springer <rspringer@google.com> -M: John Joseph <jnjoseph@google.com> +M: Todd Poynor <toddpoynor@google.com> M: Ben Chan <benchan@chromium.org> S: Maintained F: drivers/staging/gasket/ @@ -7016,6 +7018,20 @@ F: drivers/crypto/vmx/aes* F: drivers/crypto/vmx/ghash* F: drivers/crypto/vmx/ppc-xlate.pl +IBM Power PCI Hotplug Driver for RPA-compliant PPC64 platform +M: Tyrel Datwyler <tyreld@linux.vnet.ibm.com> +L: linux-pci@vger.kernel.org +L: linuxppc-dev@lists.ozlabs.org +S: Supported +F: drivers/pci/hotplug/rpaphp* + +IBM Power IO DLPAR Driver for RPA-compliant PPC64 platform +M: Tyrel Datwyler <tyreld@linux.vnet.ibm.com> +L: linux-pci@vger.kernel.org +L: linuxppc-dev@lists.ozlabs.org +S: Supported +F: drivers/pci/hotplug/rpadlpar* + IBM ServeRAID RAID DRIVER S: Orphan F: drivers/scsi/ips.* @@ -8309,7 +8325,7 @@ F: include/linux/libata.h F: Documentation/devicetree/bindings/ata/ LIBLOCKDEP -M: Sasha Levin <alexander.levin@verizon.com> +M: Sasha Levin <alexander.levin@microsoft.com> S: Maintained F: tools/lib/lockdep/ @@ -11163,7 +11179,7 @@ F: drivers/pci/controller/dwc/pci-exynos.c PCI DRIVER FOR SYNOPSYS DESIGNWARE M: Jingoo Han <jingoohan1@gmail.com> -M: Joao Pinto <Joao.Pinto@synopsys.com> +M: Gustavo Pimentel <gustavo.pimentel@synopsys.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/designware-pcie.txt @@ -11355,10 +11371,10 @@ S: Maintained F: drivers/platform/x86/peaq-wmi.c PER-CPU MEMORY ALLOCATOR +M: Dennis Zhou <dennis@kernel.org> M: Tejun Heo <tj@kernel.org> M: Christoph Lameter <cl@linux.com> -M: Dennis Zhou <dennisszhou@gmail.com> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu.git S: Maintained F: include/linux/percpu*.h F: mm/percpu*.c @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Merciless Moray # *DOCUMENTATION* @@ -299,19 +299,7 @@ KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null) KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(SUBLEVEL)))$(EXTRAVERSION) export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION -# SUBARCH tells the usermode build what the underlying arch is. That is set -# first, and if a usermode build is happening, the "ARCH=um" on the command -# line overrides the setting of ARCH below. If a native build is happening, -# then ARCH is assigned, getting whatever value it gets normally, and -# SUBARCH is subsequently ignored. - -SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ - -e s/sun4u/sparc64/ \ - -e s/arm.*/arm/ -e s/sa110/arm/ \ - -e s/s390x/s390/ -e s/parisc64/parisc/ \ - -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ - -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ - -e s/riscv.*/riscv/) +include scripts/subarch.include # Cross compiling and selecting different set of gcc/bin-utils # --------------------------------------------------------------------------- @@ -616,6 +604,11 @@ CFLAGS_GCOV := -fprofile-arcs -ftest-coverage \ $(call cc-disable-warning,maybe-uninitialized,) export CFLAGS_GCOV +# The arch Makefiles can override CC_FLAGS_FTRACE. We may also append it later. +ifdef CONFIG_FUNCTION_TRACER + CC_FLAGS_FTRACE := -pg +endif + # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default # values of the respective KBUILD_* variables ARCH_CPPFLAGS := @@ -755,9 +748,6 @@ KBUILD_CFLAGS += $(call cc-option, -femit-struct-debug-baseonly) \ endif ifdef CONFIG_FUNCTION_TRACER -ifndef CC_FLAGS_FTRACE -CC_FLAGS_FTRACE := -pg -endif ifdef CONFIG_FTRACE_MCOUNT_RECORD # gcc 5 supports generating the mcount tables directly ifeq ($(call cc-option-yn,-mrecord-mcount),y) diff --git a/arch/arm/boot/dts/sama5d3_emac.dtsi b/arch/arm/boot/dts/sama5d3_emac.dtsi index 7cb235ef0fb6..6e9e1c2f9def 100644 --- a/arch/arm/boot/dts/sama5d3_emac.dtsi +++ b/arch/arm/boot/dts/sama5d3_emac.dtsi @@ -41,7 +41,7 @@ }; macb1: ethernet@f802c000 { - compatible = "cdns,at91sam9260-macb", "cdns,macb"; + compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb"; reg = <0xf802c000 0x100>; interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>; pinctrl-names = "default"; diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 1b5e0e843c3a..7e2b3e360086 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -28,7 +28,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm goto("1: nop\n\t" + asm_volatile_goto("1: nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" @@ -42,7 +42,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm goto("1: b %l[l_yes]\n\t" + asm_volatile_goto("1: b %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 95ac7374d723..4c8b13bede80 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +arm64-obj-$(CONFIG_CRASH_CORE) += crash_core.o arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c new file mode 100644 index 000000000000..ca4c3e12d8c5 --- /dev/null +++ b/arch/arm64/kernel/crash_core.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + */ + +#include <linux/crash_core.h> +#include <asm/memory.h> + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(VA_BITS); + /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ + vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", + kimage_voffset); + vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", + PHYS_OFFSET); + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); +} diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index f6a5c6bc1434..922add8adb74 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -358,14 +358,3 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) } } #endif /* CONFIG_HIBERNATION */ - -void arch_crash_save_vmcoreinfo(void) -{ - VMCOREINFO_NUMBER(VA_BITS); - /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ - vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", - kimage_voffset); - vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", - PHYS_OFFSET); - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); -} diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 5e4a59b3ec1b..2691a1857d20 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -211,7 +211,7 @@ static inline long ffz(int x) * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline long fls(int x) +static inline int fls(int x) { int r; @@ -232,7 +232,7 @@ static inline long fls(int x) * the libc and compiler builtin ffs routines, therefore * differs in spirit from the above ffz (man ffs). */ -static inline long ffs(int x) +static inline int ffs(int x) { int r; diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index 77459df34e2e..7ebe7ad19d15 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -60,7 +60,7 @@ static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size, panic("Can't create %s() memory pool!", __func__); else gen_pool_add(coherent_pool, - pfn_to_virt(max_low_pfn), + (unsigned long)pfn_to_virt(max_low_pfn), hexagon_coherent_pool_size, -1); } diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 80b27294c1de..ab9a0ebecc19 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -208,7 +208,7 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, walk->dst.virt.addr, walk->src.virt.addr, n); if (k) ret = blkcipher_walk_done(desc, walk, nbytes - k); - if (n < k) { + if (k < n) { if (__cbc_paes_set_key(ctx) != 0) return blkcipher_walk_done(desc, walk, -EIO); memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f3e006bed9a7..c88ed39582a1 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void) x86_pmu.lbr_sel_mask = LBR_SEL_MASK; x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + /* Knights Landing does have MISPREDICT bit */ + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP) + x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS; } diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 24c6cf5f16b7..60d0f9015317 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -19,9 +19,6 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd); -#endif *pmdp = pmd; } @@ -61,9 +58,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #ifdef CONFIG_SMP static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0)); -#endif return __pmd(xchg((pmdval_t *)xp, 0)); } #else @@ -73,9 +67,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #ifdef CONFIG_SMP static inline pud_t native_pudp_get_and_clear(pud_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0)); -#endif return __pud(xchg((pudval_t *)xp, 0)); } #else diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ec00d1ff5098..f7151cd03cb0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp) return 0; } +#ifdef CONFIG_PROC_FS static int proc_apm_show(struct seq_file *m, void *v) { unsigned short bx; @@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v) units); return 0; } +#endif static int apm(void *unused) { diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index f260e452e4f8..e8c8c5d78dbd 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -7,11 +7,17 @@ #include <linux/eisa.h> #include <linux/io.h> +#include <xen/xen.h> + static __init int eisa_bus_probe(void) { - void __iomem *p = ioremap(0x0FFFD9, 4); + void __iomem *p; + + if (xen_pv_domain() && !xen_initial_domain()) + return 0; - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + p = ioremap(0x0FFFD9, 4); + if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24)) EISA_bus = 1; iounmap(p); return 0; diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 12cbe2b88c0f..738bf42b0218 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -111,8 +111,10 @@ int arch_register_cpu(int num) /* * Currently CPU0 is only hotpluggable on Intel platforms. Other * vendors can add hotplug support later. + * Xen PV guests don't support CPU0 hotplug at all. */ - if (c->x86_vendor != X86_VENDOR_INTEL) + if (c->x86_vendor != X86_VENDOR_INTEL || + boot_cpu_has(X86_FEATURE_XENPV)) cpu0_hotpluggable = 0; /* diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 05ca14222463..9959657127f4 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -85,10 +85,9 @@ pgd_t * __init efi_call_phys_prolog(void) void __init efi_call_phys_epilog(pgd_t *save_pgd) { + load_fixmap_gdt(0); load_cr3(save_pgd); __flush_tlb_all(); - - load_fixmap_gdt(0); } void __init efi_runtime_update_mappings(void) diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 04d038f3b6fa..b9ad83a0ee5d 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -4,6 +4,7 @@ config ZONE_DMA config XTENSA def_bool y + select ARCH_HAS_SG_CHAIN select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_NO_COHERENT_DMA_MMAP if !MMU diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile index 295c120ed099..d67e30faff9c 100644 --- a/arch/xtensa/Makefile +++ b/arch/xtensa/Makefile @@ -64,11 +64,7 @@ endif vardirs := $(patsubst %,arch/xtensa/variants/%/,$(variant-y)) plfdirs := $(patsubst %,arch/xtensa/platforms/%/,$(platform-y)) -ifeq ($(KBUILD_SRC),) -KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(vardirs) $(plfdirs)) -else KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(vardirs) $(plfdirs)) -endif KBUILD_DEFCONFIG := iss_defconfig diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index f4bbb28026f8..58709e89a8ed 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -78,23 +78,28 @@ static struct notifier_block iss_panic_block = { void __init platform_setup(char **p_cmdline) { + static void *argv[COMMAND_LINE_SIZE / sizeof(void *)] __initdata; + static char cmdline[COMMAND_LINE_SIZE] __initdata; int argc = simc_argc(); int argv_size = simc_argv_size(); if (argc > 1) { - void **argv = alloc_bootmem(argv_size); - char *cmdline = alloc_bootmem(argv_size); - int i; + if (argv_size > sizeof(argv)) { + pr_err("%s: command line too long: argv_size = %d\n", + __func__, argv_size); + } else { + int i; - cmdline[0] = 0; - simc_argv((void *)argv); + cmdline[0] = 0; + simc_argv((void *)argv); - for (i = 1; i < argc; ++i) { - if (i > 1) - strcat(cmdline, " "); - strcat(cmdline, argv[i]); + for (i = 1; i < argc; ++i) { + if (i > 1) + strcat(cmdline, " "); + strcat(cmdline, argv[i]); + } + *p_cmdline = cmdline; } - *p_cmdline = cmdline; } atomic_notifier_chain_register(&panic_notifier_list, &iss_panic_block); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c19f9078da1e..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1510,8 +1510,10 @@ int blkcg_policy_register(struct blkcg_policy *pol) for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; - if (i >= BLKCG_MAX_POLS) + if (i >= BLKCG_MAX_POLS) { + pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; + } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 3f3b7b253445..64fd96eada31 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -332,6 +332,35 @@ err_no_vma: return vma ? -ENOMEM : -ESRCH; } + +static inline void binder_alloc_set_vma(struct binder_alloc *alloc, + struct vm_area_struct *vma) +{ + if (vma) + alloc->vma_vm_mm = vma->vm_mm; + /* + * If we see alloc->vma is not NULL, buffer data structures set up + * completely. Look at smp_rmb side binder_alloc_get_vma. + * We also want to guarantee new alloc->vma_vm_mm is always visible + * if alloc->vma is set. + */ + smp_wmb(); + alloc->vma = vma; +} + +static inline struct vm_area_struct *binder_alloc_get_vma( + struct binder_alloc *alloc) +{ + struct vm_area_struct *vma = NULL; + + if (alloc->vma) { + /* Look at description in binder_alloc_set_vma */ + smp_rmb(); + vma = alloc->vma; + } + return vma; +} + static struct binder_buffer *binder_alloc_new_buf_locked( struct binder_alloc *alloc, size_t data_size, @@ -348,7 +377,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret; - if (alloc->vma == NULL) { + if (!binder_alloc_get_vma(alloc)) { binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); @@ -723,9 +752,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; - barrier(); - alloc->vma = vma; - alloc->vma_vm_mm = vma->vm_mm; + binder_alloc_set_vma(alloc, vma); mmgrab(alloc->vma_vm_mm); return 0; @@ -754,10 +781,10 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) int buffers, page_count; struct binder_buffer *buffer; - BUG_ON(alloc->vma); - buffers = 0; mutex_lock(&alloc->mutex); + BUG_ON(alloc->vma); + while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -900,7 +927,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - WRITE_ONCE(alloc->vma, NULL); + binder_alloc_set_vma(alloc, NULL); } /** @@ -935,7 +962,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; - vma = alloc->vma; + vma = binder_alloc_get_vma(alloc); if (vma) { if (!mmget_not_zero(alloc->vma_vm_mm)) goto err_mmget; diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 0943e7065e0e..b3c0498ee433 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -209,21 +209,24 @@ static struct fw_priv *__lookup_fw_priv(const char *fw_name) static int alloc_lookup_fw_priv(const char *fw_name, struct firmware_cache *fwc, struct fw_priv **fw_priv, void *dbuf, - size_t size) + size_t size, enum fw_opt opt_flags) { struct fw_priv *tmp; spin_lock(&fwc->lock); - tmp = __lookup_fw_priv(fw_name); - if (tmp) { - kref_get(&tmp->ref); - spin_unlock(&fwc->lock); - *fw_priv = tmp; - pr_debug("batched request - sharing the same struct fw_priv and lookup for multiple requests\n"); - return 1; + if (!(opt_flags & FW_OPT_NOCACHE)) { + tmp = __lookup_fw_priv(fw_name); + if (tmp) { + kref_get(&tmp->ref); + spin_unlock(&fwc->lock); + *fw_priv = tmp; + pr_debug("batched request - sharing the same struct fw_priv and lookup for multiple requests\n"); + return 1; + } } + tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size); - if (tmp) + if (tmp && !(opt_flags & FW_OPT_NOCACHE)) list_add(&tmp->list, &fwc->head); spin_unlock(&fwc->lock); @@ -493,7 +496,8 @@ int assign_fw(struct firmware *fw, struct device *device, */ static int _request_firmware_prepare(struct firmware **firmware_p, const char *name, - struct device *device, void *dbuf, size_t size) + struct device *device, void *dbuf, size_t size, + enum fw_opt opt_flags) { struct firmware *firmware; struct fw_priv *fw_priv; @@ -511,7 +515,8 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name, return 0; /* assigned */ } - ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size); + ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size, + opt_flags); /* * bind with 'priv' now to avoid warning in failure path @@ -571,7 +576,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name, goto out; } - ret = _request_firmware_prepare(&fw, name, device, buf, size); + ret = _request_firmware_prepare(&fw, name, device, buf, size, + opt_flags); if (ret <= 0) /* error or already assigned */ goto out; diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index d81781f22dba..34e0030f0592 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -87,10 +87,10 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd); -void null_zone_write(struct nullb_cmd *cmd); -void null_zone_reset(struct nullb_cmd *cmd); +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio); +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors); +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector); #else static inline int null_zone_init(struct nullb_device *dev) { @@ -98,11 +98,14 @@ static inline int null_zone_init(struct nullb_device *dev) } static inline void null_zone_exit(struct nullb_device *dev) {} static inline blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) + struct bio *bio) { return BLK_STS_NOTSUPP; } -static inline void null_zone_write(struct nullb_cmd *cmd) {} -static inline void null_zone_reset(struct nullb_cmd *cmd) {} +static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) +{ +} +static inline void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) {} #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* __NULL_BLK_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 6127e3ff7b4b..093b614d6524 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1157,16 +1157,33 @@ static void null_restart_queue_async(struct nullb *nullb) } } +static bool cmd_report_zone(struct nullb *nullb, struct nullb_cmd *cmd) +{ + struct nullb_device *dev = cmd->nq->dev; + + if (dev->queue_mode == NULL_Q_BIO) { + if (bio_op(cmd->bio) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->bio); + return true; + } + } else { + if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->rq->bio); + return true; + } + } + + return false; +} + static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; int err = 0; - if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd); + if (cmd_report_zone(nullb, cmd)) goto out; - } if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) { struct request *rq = cmd->rq; @@ -1234,10 +1251,24 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) cmd->error = errno_to_blk_status(err); if (!cmd->error && dev->zoned) { - if (req_op(cmd->rq) == REQ_OP_WRITE) - null_zone_write(cmd); - else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET) - null_zone_reset(cmd); + sector_t sector; + unsigned int nr_sectors; + int op; + + if (dev->queue_mode == NULL_Q_BIO) { + op = bio_op(cmd->bio); + sector = cmd->bio->bi_iter.bi_sector; + nr_sectors = cmd->bio->bi_iter.bi_size >> 9; + } else { + op = req_op(cmd->rq); + sector = blk_rq_pos(cmd->rq); + nr_sectors = blk_rq_sectors(cmd->rq); + } + + if (op == REQ_OP_WRITE) + null_zone_write(cmd, sector, nr_sectors); + else if (op == REQ_OP_ZONE_RESET) + null_zone_reset(cmd, sector); } out: /* Complete IO by inline, softirq or timer */ diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index a979ca00d7be..7c6b86d98700 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -48,8 +48,8 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, - unsigned int zno, unsigned int nr_zones) +static void null_zone_fill_bio(struct nullb_device *dev, struct bio *bio, + unsigned int zno, unsigned int nr_zones) { struct blk_zone_report_hdr *hdr = NULL; struct bio_vec bvec; @@ -57,7 +57,7 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, void *addr; unsigned int zones_to_cpy; - bio_for_each_segment(bvec, rq->bio, iter) { + bio_for_each_segment(bvec, bio, iter) { addr = kmap_atomic(bvec.bv_page); zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone); @@ -84,29 +84,24 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, } } -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio) { struct nullb_device *dev = nullb->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, bio->bi_iter.bi_sector); unsigned int nr_zones = dev->nr_zones - zno; - unsigned int max_zones = (blk_rq_bytes(rq) / - sizeof(struct blk_zone)) - 1; + unsigned int max_zones; + max_zones = (bio->bi_iter.bi_size / sizeof(struct blk_zone)) - 1; nr_zones = min_t(unsigned int, nr_zones, max_zones); - - null_zone_fill_rq(nullb->dev, rq, zno, nr_zones); + null_zone_fill_bio(nullb->dev, bio, zno, nr_zones); return BLK_STS_OK; } -void null_zone_write(struct nullb_cmd *cmd) +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - sector_t sector = blk_rq_pos(rq); - unsigned int rq_sectors = blk_rq_sectors(rq); unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; @@ -118,7 +113,7 @@ void null_zone_write(struct nullb_cmd *cmd) case BLK_ZONE_COND_EMPTY: case BLK_ZONE_COND_IMP_OPEN: /* Writes must be at the write pointer position */ - if (blk_rq_pos(rq) != zone->wp) { + if (sector != zone->wp) { cmd->error = BLK_STS_IOERR; break; } @@ -126,7 +121,7 @@ void null_zone_write(struct nullb_cmd *cmd) if (zone->cond == BLK_ZONE_COND_EMPTY) zone->cond = BLK_ZONE_COND_IMP_OPEN; - zone->wp += rq_sectors; + zone->wp += nr_sectors; if (zone->wp == zone->start + zone->len) zone->cond = BLK_ZONE_COND_FULL; break; @@ -137,11 +132,10 @@ void null_zone_write(struct nullb_cmd *cmd) } } -void null_zone_reset(struct nullb_cmd *cmd) +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; zone->cond = BLK_ZONE_COND_EMPTY; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 963bb0309e25..ea6238ed5c0e 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -543,6 +543,8 @@ static void hci_uart_tty_close(struct tty_struct *tty) } clear_bit(HCI_UART_PROTO_SET, &hu->flags); + percpu_free_rwsem(&hu->proto_lock); + kfree(hu); } diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c index a3397664f800..97d6856c9c0f 100644 --- a/drivers/char/ipmi/ipmi_bt_sm.c +++ b/drivers/char/ipmi/ipmi_bt_sm.c @@ -59,8 +59,6 @@ enum bt_states { BT_STATE_RESET3, BT_STATE_RESTART, BT_STATE_PRINTME, - BT_STATE_CAPABILITIES_BEGIN, - BT_STATE_CAPABILITIES_END, BT_STATE_LONG_BUSY /* BT doesn't get hosed :-) */ }; @@ -86,7 +84,6 @@ struct si_sm_data { int error_retries; /* end of "common" fields */ int nonzero_status; /* hung BMCs stay all 0 */ enum bt_states complete; /* to divert the state machine */ - int BT_CAP_outreqs; long BT_CAP_req2rsp; int BT_CAP_retries; /* Recommended retries */ }; @@ -137,8 +134,6 @@ static char *state2txt(unsigned char state) case BT_STATE_RESET3: return("RESET3"); case BT_STATE_RESTART: return("RESTART"); case BT_STATE_LONG_BUSY: return("LONG_BUSY"); - case BT_STATE_CAPABILITIES_BEGIN: return("CAP_BEGIN"); - case BT_STATE_CAPABILITIES_END: return("CAP_END"); } return("BAD STATE"); } @@ -185,7 +180,6 @@ static unsigned int bt_init_data(struct si_sm_data *bt, struct si_sm_io *io) bt->complete = BT_STATE_IDLE; /* end here */ bt->BT_CAP_req2rsp = BT_NORMAL_TIMEOUT * USEC_PER_SEC; bt->BT_CAP_retries = BT_NORMAL_RETRY_LIMIT; - /* BT_CAP_outreqs == zero is a flag to read BT Capabilities */ return 3; /* We claim 3 bytes of space; ought to check SPMI table */ } @@ -451,7 +445,7 @@ static enum si_sm_result error_recovery(struct si_sm_data *bt, static enum si_sm_result bt_event(struct si_sm_data *bt, long time) { - unsigned char status, BT_CAP[8]; + unsigned char status; static enum bt_states last_printed = BT_STATE_PRINTME; int i; @@ -504,12 +498,6 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) if (status & BT_H_BUSY) /* clear a leftover H_BUSY */ BT_CONTROL(BT_H_BUSY); - bt->timeout = bt->BT_CAP_req2rsp; - - /* Read BT capabilities if it hasn't been done yet */ - if (!bt->BT_CAP_outreqs) - BT_STATE_CHANGE(BT_STATE_CAPABILITIES_BEGIN, - SI_SM_CALL_WITHOUT_DELAY); BT_SI_SM_RETURN(SI_SM_IDLE); case BT_STATE_XACTION_START: @@ -614,37 +602,6 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) BT_STATE_CHANGE(BT_STATE_XACTION_START, SI_SM_CALL_WITH_DELAY); - /* - * Get BT Capabilities, using timing of upper level state machine. - * Set outreqs to prevent infinite loop on timeout. - */ - case BT_STATE_CAPABILITIES_BEGIN: - bt->BT_CAP_outreqs = 1; - { - unsigned char GetBT_CAP[] = { 0x18, 0x36 }; - bt->state = BT_STATE_IDLE; - bt_start_transaction(bt, GetBT_CAP, sizeof(GetBT_CAP)); - } - bt->complete = BT_STATE_CAPABILITIES_END; - BT_STATE_CHANGE(BT_STATE_XACTION_START, - SI_SM_CALL_WITH_DELAY); - - case BT_STATE_CAPABILITIES_END: - i = bt_get_result(bt, BT_CAP, sizeof(BT_CAP)); - bt_init_data(bt, bt->io); - if ((i == 8) && !BT_CAP[2]) { - bt->BT_CAP_outreqs = BT_CAP[3]; - bt->BT_CAP_req2rsp = BT_CAP[6] * USEC_PER_SEC; - bt->BT_CAP_retries = BT_CAP[7]; - } else - printk(KERN_WARNING "IPMI BT: using default values\n"); - if (!bt->BT_CAP_outreqs) - bt->BT_CAP_outreqs = 1; - printk(KERN_WARNING "IPMI BT: req2rsp=%ld secs retries=%d\n", - bt->BT_CAP_req2rsp / USEC_PER_SEC, bt->BT_CAP_retries); - bt->timeout = bt->BT_CAP_req2rsp; - return SI_SM_CALL_WITHOUT_DELAY; - default: /* should never occur */ return error_recovery(bt, status, @@ -655,6 +612,11 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) static int bt_detect(struct si_sm_data *bt) { + unsigned char GetBT_CAP[] = { 0x18, 0x36 }; + unsigned char BT_CAP[8]; + enum si_sm_result smi_result; + int rv; + /* * It's impossible for the BT status and interrupt registers to be * all 1's, (assuming a properly functioning, self-initialized BMC) @@ -665,6 +627,48 @@ static int bt_detect(struct si_sm_data *bt) if ((BT_STATUS == 0xFF) && (BT_INTMASK_R == 0xFF)) return 1; reset_flags(bt); + + /* + * Try getting the BT capabilities here. + */ + rv = bt_start_transaction(bt, GetBT_CAP, sizeof(GetBT_CAP)); + if (rv) { + dev_warn(bt->io->dev, + "Can't start capabilities transaction: %d\n", rv); + goto out_no_bt_cap; + } + + smi_result = SI_SM_CALL_WITHOUT_DELAY; + for (;;) { + if (smi_result == SI_SM_CALL_WITH_DELAY || + smi_result == SI_SM_CALL_WITH_TICK_DELAY) { + schedule_timeout_uninterruptible(1); + smi_result = bt_event(bt, jiffies_to_usecs(1)); + } else if (smi_result == SI_SM_CALL_WITHOUT_DELAY) { + smi_result = bt_event(bt, 0); + } else + break; + } + + rv = bt_get_result(bt, BT_CAP, sizeof(BT_CAP)); + bt_init_data(bt, bt->io); + if (rv < 8) { + dev_warn(bt->io->dev, "bt cap response too short: %d\n", rv); + goto out_no_bt_cap; + } + + if (BT_CAP[2]) { + dev_warn(bt->io->dev, "Error fetching bt cap: %x\n", BT_CAP[2]); +out_no_bt_cap: + dev_warn(bt->io->dev, "using default values\n"); + } else { + bt->BT_CAP_req2rsp = BT_CAP[6] * USEC_PER_SEC; + bt->BT_CAP_retries = BT_CAP[7]; + } + + dev_info(bt->io->dev, "req2rsp=%ld secs retries=%d\n", + bt->BT_CAP_req2rsp / USEC_PER_SEC, bt->BT_CAP_retries); + return 0; } diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 51832b8a2c62..7fc9612070a1 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3381,39 +3381,45 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, rv = handlers->start_processing(send_info, intf); if (rv) - goto out; + goto out_err; rv = __bmc_get_device_id(intf, NULL, &id, NULL, NULL, i); if (rv) { dev_err(si_dev, "Unable to get the device id: %d\n", rv); - goto out; + goto out_err_started; } mutex_lock(&intf->bmc_reg_mutex); rv = __scan_channels(intf, &id); mutex_unlock(&intf->bmc_reg_mutex); + if (rv) + goto out_err_bmc_reg; - out: - if (rv) { - ipmi_bmc_unregister(intf); - list_del_rcu(&intf->link); - mutex_unlock(&ipmi_interfaces_mutex); - synchronize_srcu(&ipmi_interfaces_srcu); - cleanup_srcu_struct(&intf->users_srcu); - kref_put(&intf->refcount, intf_free); - } else { - /* - * Keep memory order straight for RCU readers. Make - * sure everything else is committed to memory before - * setting intf_num to mark the interface valid. - */ - smp_wmb(); - intf->intf_num = i; - mutex_unlock(&ipmi_interfaces_mutex); + /* + * Keep memory order straight for RCU readers. Make + * sure everything else is committed to memory before + * setting intf_num to mark the interface valid. + */ + smp_wmb(); + intf->intf_num = i; + mutex_unlock(&ipmi_interfaces_mutex); - /* After this point the interface is legal to use. */ - call_smi_watchers(i, intf->si_dev); - } + /* After this point the interface is legal to use. */ + call_smi_watchers(i, intf->si_dev); + + return 0; + + out_err_bmc_reg: + ipmi_bmc_unregister(intf); + out_err_started: + if (intf->handlers->shutdown) + intf->handlers->shutdown(intf->send_info); + out_err: + list_del_rcu(&intf->link); + mutex_unlock(&ipmi_interfaces_mutex); + synchronize_srcu(&ipmi_interfaces_srcu); + cleanup_srcu_struct(&intf->users_srcu); + kref_put(&intf->refcount, intf_free); return rv; } @@ -3504,7 +3510,8 @@ void ipmi_unregister_smi(struct ipmi_smi *intf) } srcu_read_unlock(&intf->users_srcu, index); - intf->handlers->shutdown(intf->send_info); + if (intf->handlers->shutdown) + intf->handlers->shutdown(intf->send_info); cleanup_smi_msgs(intf); diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 90ec010bffbd..5faa917df1b6 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2083,18 +2083,9 @@ static int try_smi_init(struct smi_info *new_smi) si_to_str[new_smi->io.si_type]); WARN_ON(new_smi->io.dev->init_name != NULL); - kfree(init_name); - - return 0; - -out_err: - if (new_smi->intf) { - ipmi_unregister_smi(new_smi->intf); - new_smi->intf = NULL; - } + out_err: kfree(init_name); - return rv; } @@ -2227,6 +2218,8 @@ static void shutdown_smi(void *send_info) kfree(smi_info->si_sm); smi_info->si_sm = NULL; + + smi_info->intf = NULL; } /* @@ -2240,10 +2233,8 @@ static void cleanup_one_si(struct smi_info *smi_info) list_del(&smi_info->link); - if (smi_info->intf) { + if (smi_info->intf) ipmi_unregister_smi(smi_info->intf); - smi_info->intf = NULL; - } if (smi_info->pdev) { if (smi_info->pdev_registered) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 18e4650c233b..29e67a80fb20 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -181,6 +181,8 @@ struct ssif_addr_info { struct device *dev; struct i2c_client *client; + struct i2c_client *added_client; + struct mutex clients_mutex; struct list_head clients; @@ -1214,18 +1216,11 @@ static void shutdown_ssif(void *send_info) complete(&ssif_info->wake_thread); kthread_stop(ssif_info->thread); } - - /* - * No message can be outstanding now, we have removed the - * upper layer and it permitted us to do so. - */ - kfree(ssif_info); } static int ssif_remove(struct i2c_client *client) { struct ssif_info *ssif_info = i2c_get_clientdata(client); - struct ipmi_smi *intf; struct ssif_addr_info *addr_info; if (!ssif_info) @@ -1235,9 +1230,7 @@ static int ssif_remove(struct i2c_client *client) * After this point, we won't deliver anything asychronously * to the message handler. We can unregister ourself. */ - intf = ssif_info->intf; - ssif_info->intf = NULL; - ipmi_unregister_smi(intf); + ipmi_unregister_smi(ssif_info->intf); list_for_each_entry(addr_info, &ssif_infos, link) { if (addr_info->client == client) { @@ -1246,6 +1239,8 @@ static int ssif_remove(struct i2c_client *client) } } + kfree(ssif_info); + return 0; } @@ -1648,15 +1643,9 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id) out: if (rv) { - /* - * Note that if addr_info->client is assigned, we - * leave it. The i2c client hangs around even if we - * return a failure here, and the failure here is not - * propagated back to the i2c code. This seems to be - * design intent, strange as it may be. But if we - * don't leave it, ssif_platform_remove will not remove - * the client like it should. - */ + if (addr_info) + addr_info->client = NULL; + dev_err(&client->dev, "Unable to start IPMI SSIF: %d\n", rv); kfree(ssif_info); } @@ -1676,7 +1665,8 @@ static int ssif_adapter_handler(struct device *adev, void *opaque) if (adev->type != &i2c_adapter_type) return 0; - i2c_new_device(to_i2c_adapter(adev), &addr_info->binfo); + addr_info->added_client = i2c_new_device(to_i2c_adapter(adev), + &addr_info->binfo); if (!addr_info->adapter_name) return 1; /* Only try the first I2C adapter by default. */ @@ -1849,7 +1839,7 @@ static int ssif_platform_remove(struct platform_device *dev) return 0; mutex_lock(&ssif_infos_mutex); - i2c_unregister_device(addr_info->client); + i2c_unregister_device(addr_info->added_client); list_del(&addr_info->link); kfree(addr_info); diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c index bb882ab161fe..e6124bd548df 100644 --- a/drivers/char/ipmi/kcs_bmc.c +++ b/drivers/char/ipmi/kcs_bmc.c @@ -16,6 +16,8 @@ #include "kcs_bmc.h" +#define DEVICE_NAME "ipmi-kcs" + #define KCS_MSG_BUFSIZ 1000 #define KCS_ZERO_DATA 0 @@ -429,8 +431,6 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) if (!kcs_bmc) return NULL; - dev_set_name(dev, "ipmi-kcs%u", channel); - spin_lock_init(&kcs_bmc->lock); kcs_bmc->channel = channel; @@ -444,7 +444,8 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) return NULL; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; - kcs_bmc->miscdev.name = dev_name(dev); + kcs_bmc->miscdev.name = devm_kasprintf(dev, GFP_KERNEL, "%s%u", + DEVICE_NAME, channel); kcs_bmc->miscdev.fops = &kcs_bmc_fops; return kcs_bmc; diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c index 08ef69945ffb..d977193842df 100644 --- a/drivers/clk/x86/clk-pmc-atom.c +++ b/drivers/clk/x86/clk-pmc-atom.c @@ -55,6 +55,7 @@ struct clk_plt_data { u8 nparents; struct clk_plt *clks[PMC_CLK_NUM]; struct clk_lookup *mclk_lookup; + struct clk_lookup *ether_clk_lookup; }; /* Return an index in parent table */ @@ -186,13 +187,6 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; spin_lock_init(&pclk->lock); - /* - * If the clock was already enabled by the firmware mark it as critical - * to avoid it being gated by the clock framework if no driver owns it. - */ - if (plt_clk_is_enabled(&pclk->hw)) - init.flags |= CLK_IS_CRITICAL; - ret = devm_clk_hw_register(&pdev->dev, &pclk->hw); if (ret) { pclk = ERR_PTR(ret); @@ -351,11 +345,20 @@ static int plt_clk_probe(struct platform_device *pdev) goto err_unreg_clk_plt; } + data->ether_clk_lookup = clkdev_hw_create(&data->clks[4]->hw, + "ether_clk", NULL); + if (!data->ether_clk_lookup) { + err = -ENOMEM; + goto err_drop_mclk; + } + plt_clk_free_parent_names_loop(parent_names, data->nparents); platform_set_drvdata(pdev, data); return 0; +err_drop_mclk: + clkdev_drop(data->mclk_lookup); err_unreg_clk_plt: plt_clk_unregister_loop(data, i); plt_clk_unregister_parents(data); @@ -369,6 +372,7 @@ static int plt_clk_remove(struct platform_device *pdev) data = platform_get_drvdata(pdev); + clkdev_drop(data->ether_clk_lookup); clkdev_drop(data->mclk_lookup); plt_clk_unregister_loop(data, PMC_CLK_NUM); plt_clk_unregister_parents(data); diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c index b76cb17d879c..adfd316db1a8 100644 --- a/drivers/dma/mic_x100_dma.c +++ b/drivers/dma/mic_x100_dma.c @@ -639,7 +639,7 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev, int ret; struct device *dev = &mbdev->dev; - mic_dma_dev = kzalloc(sizeof(*mic_dma_dev), GFP_KERNEL); + mic_dma_dev = devm_kzalloc(dev, sizeof(*mic_dma_dev), GFP_KERNEL); if (!mic_dma_dev) { ret = -ENOMEM; goto alloc_error; @@ -664,7 +664,6 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev, reg_error: mic_dma_uninit(mic_dma_dev); init_error: - kfree(mic_dma_dev); mic_dma_dev = NULL; alloc_error: dev_err(dev, "Error at %s %d ret=%d\n", __func__, __LINE__, ret); @@ -674,7 +673,6 @@ alloc_error: static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev) { mic_dma_uninit(mic_dma_dev); - kfree(mic_dma_dev); } /* DEBUGFS CODE */ diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c index fc9fd2d0482f..0b840531ef33 100644 --- a/drivers/fpga/dfl-fme-pr.c +++ b/drivers/fpga/dfl-fme-pr.c @@ -420,7 +420,7 @@ static int pr_mgmt_init(struct platform_device *pdev, /* Create region for each port */ fme_region = dfl_fme_create_region(pdata, mgr, fme_br->br, i); - if (!fme_region) { + if (IS_ERR(fme_region)) { ret = PTR_ERR(fme_region); goto destroy_region; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index b6e9df11115d..b31d121a876b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -39,6 +39,7 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, { struct drm_gem_object *gobj; unsigned long size; + int r; gobj = drm_gem_object_lookup(p->filp, data->handle); if (gobj == NULL) @@ -50,20 +51,26 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, p->uf_entry.tv.shared = true; p->uf_entry.user_pages = NULL; - size = amdgpu_bo_size(p->uf_entry.robj); - if (size != PAGE_SIZE || (data->offset + 8) > size) - return -EINVAL; - - *offset = data->offset; - drm_gem_object_put_unlocked(gobj); + size = amdgpu_bo_size(p->uf_entry.robj); + if (size != PAGE_SIZE || (data->offset + 8) > size) { + r = -EINVAL; + goto error_unref; + } + if (amdgpu_ttm_tt_get_usermm(p->uf_entry.robj->tbo.ttm)) { - amdgpu_bo_unref(&p->uf_entry.robj); - return -EINVAL; + r = -EINVAL; + goto error_unref; } + *offset = data->offset; + return 0; + +error_unref: + amdgpu_bo_unref(&p->uf_entry.robj); + return r; } static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p, @@ -1262,10 +1269,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, error_abort: dma_fence_put(&job->base.s_fence->finished); job->base.s_fence = NULL; + amdgpu_mn_unlock(p->mn); error_unlock: amdgpu_job_free(job); - amdgpu_mn_unlock(p->mn); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8ab5ccbc14ac..39bf2ce548c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2063,6 +2063,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev) static enum amd_ip_block_type ip_order[] = { AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_COMMON, + AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_IH, }; @@ -2093,7 +2094,6 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev) static enum amd_ip_block_type ip_order[] = { AMD_IP_BLOCK_TYPE_SMC, - AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_DCE, AMD_IP_BLOCK_TYPE_GFX, AMD_IP_BLOCK_TYPE_SDMA, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index e7ca4623cfb9..7c3b634d8d5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -70,6 +70,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4[] = { SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0100, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831f07), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CLK_CTRL, 0xffffffff, 0x3f000100), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GFX_IB_CNTL, 0x800f0100, 0x00000100), @@ -81,7 +82,8 @@ static const struct soc15_reg_golden golden_settings_sdma_4[] = { SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC0_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_IB_CNTL, 0x800f0100, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0) + SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; static const struct soc15_reg_golden golden_settings_sdma_vg10[] = { @@ -109,7 +111,8 @@ static const struct soc15_reg_golden golden_settings_sdma_4_1[] = SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0) + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; static const struct soc15_reg_golden golden_settings_sdma_4_2[] = diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index a45f46d8537f..c7afee37b2b8 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -32,6 +32,7 @@ #include <linux/device.h> #include <linux/mm.h> #include <linux/mmu_context.h> +#include <linux/sched/mm.h> #include <linux/types.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -1792,16 +1793,21 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa, info = (struct kvmgt_guest_info *)handle; kvm = info->kvm; - if (kthread) + if (kthread) { + if (!mmget_not_zero(kvm->mm)) + return -EFAULT; use_mm(kvm->mm); + } idx = srcu_read_lock(&kvm->srcu); ret = write ? kvm_write_guest(kvm, gpa, buf, len) : kvm_read_guest(kvm, gpa, buf, len); srcu_read_unlock(&kvm->srcu, idx); - if (kthread) + if (kthread) { unuse_mm(kvm->mm); + mmput(kvm->mm); + } return ret; } diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index fa75a2eead90..b0d3a43ccd03 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -42,8 +42,6 @@ #define DEVICE_TYPE_EFP3 0x20 #define DEVICE_TYPE_EFP4 0x10 -#define DEV_SIZE 38 - struct opregion_header { u8 signature[16]; u32 size; @@ -63,6 +61,10 @@ struct bdb_data_header { u16 size; /* data size */ } __packed; +/* For supporting windows guest with opregion, here hardcode the emulated + * bdb header version as '186', and the corresponding child_device_config + * length should be '33' but not '38'. + */ struct efp_child_device_config { u16 handle; u16 device_type; @@ -109,12 +111,6 @@ struct efp_child_device_config { u8 mipi_bridge_type; /* 171 */ u16 device_class_ext; u8 dvo_function; - u8 dp_usb_type_c:1; /* 195 */ - u8 skip6:7; - u8 dp_usb_type_c_2x_gpio_index; /* 195 */ - u16 dp_usb_type_c_2x_gpio_pin; /* 195 */ - u8 iboost_dp:4; /* 196 */ - u8 iboost_hdmi:4; /* 196 */ } __packed; struct vbt { @@ -155,7 +151,7 @@ static void virt_vbt_generation(struct vbt *v) v->header.bdb_offset = offsetof(struct vbt, bdb_header); strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK"); - v->bdb_header.version = 186; /* child_dev_size = 38 */ + v->bdb_header.version = 186; /* child_dev_size = 33 */ v->bdb_header.header_size = sizeof(v->bdb_header); v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header) @@ -169,11 +165,13 @@ static void virt_vbt_generation(struct vbt *v) /* child device */ num_child = 4; /* each port has one child */ + v->general_definitions.child_dev_size = + sizeof(struct efp_child_device_config); v->general_definitions_header.id = BDB_GENERAL_DEFINITIONS; /* size will include child devices */ v->general_definitions_header.size = - sizeof(struct bdb_general_definitions) + num_child * DEV_SIZE; - v->general_definitions.child_dev_size = DEV_SIZE; + sizeof(struct bdb_general_definitions) + + num_child * v->general_definitions.child_dev_size; /* portA */ v->child0.handle = DEVICE_TYPE_EFP1; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 4a3c8ee9a973..d2951096bca0 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -5079,10 +5079,14 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state) mutex_lock(&dev_priv->pcu_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0)); mutex_unlock(&dev_priv->pcu_lock); - /* wait for pcode to finish disabling IPS, which may take up to 42ms */ + /* + * Wait for PCODE to finish disabling IPS. The BSpec specified + * 42ms timeout value leads to occasional timeouts so use 100ms + * instead. + */ if (intel_wait_for_register(dev_priv, IPS_CTL, IPS_ENABLE, 0, - 42)) + 100)) DRM_ERROR("Timed out waiting for IPS disable\n"); } else { I915_WRITE(IPS_CTL, 0); diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index c2f10d899329..443dfaefd7a6 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -181,8 +181,9 @@ struct intel_overlay { u32 brightness, contrast, saturation; u32 old_xscale, old_yscale; /* register access */ - u32 flip_addr; struct drm_i915_gem_object *reg_bo; + struct overlay_registers __iomem *regs; + u32 flip_addr; /* flip handling */ struct i915_gem_active last_flip; }; @@ -210,29 +211,6 @@ static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv, PCI_DEVFN(0, 0), I830_CLOCK_GATE, val); } -static struct overlay_registers __iomem * -intel_overlay_map_regs(struct intel_overlay *overlay) -{ - struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) - regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_handle->vaddr; - else - regs = io_mapping_map_wc(&dev_priv->ggtt.iomap, - overlay->flip_addr, - PAGE_SIZE); - - return regs; -} - -static void intel_overlay_unmap_regs(struct intel_overlay *overlay, - struct overlay_registers __iomem *regs) -{ - if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) - io_mapping_unmap(regs); -} - static void intel_overlay_submit_request(struct intel_overlay *overlay, struct i915_request *rq, i915_gem_retire_fn retire) @@ -784,13 +762,13 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, struct drm_i915_gem_object *new_bo, struct put_image_params *params) { - int ret, tmp_width; - struct overlay_registers __iomem *regs; - bool scale_changed = false; + struct overlay_registers __iomem *regs = overlay->regs; struct drm_i915_private *dev_priv = overlay->i915; u32 swidth, swidthsw, sheight, ostride; enum pipe pipe = overlay->crtc->pipe; + bool scale_changed = false; struct i915_vma *vma; + int ret, tmp_width; lockdep_assert_held(&dev_priv->drm.struct_mutex); WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex)); @@ -815,30 +793,19 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, if (!overlay->active) { u32 oconfig; - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unpin; - } + oconfig = OCONF_CC_OUT_8BIT; if (IS_GEN4(dev_priv)) oconfig |= OCONF_CSC_MODE_BT709; oconfig |= pipe == 0 ? OCONF_PIPE_A : OCONF_PIPE_B; iowrite32(oconfig, ®s->OCONFIG); - intel_overlay_unmap_regs(overlay, regs); ret = intel_overlay_on(overlay); if (ret != 0) goto out_unpin; } - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unpin; - } - iowrite32((params->dst_y << 16) | params->dst_x, ®s->DWINPOS); iowrite32((params->dst_h << 16) | params->dst_w, ®s->DWINSZ); @@ -882,8 +849,6 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, iowrite32(overlay_cmd_reg(params), ®s->OCMD); - intel_overlay_unmap_regs(overlay, regs); - ret = intel_overlay_continue(overlay, vma, scale_changed); if (ret) goto out_unpin; @@ -901,7 +866,6 @@ out_pin_section: int intel_overlay_switch_off(struct intel_overlay *overlay) { struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; int ret; lockdep_assert_held(&dev_priv->drm.struct_mutex); @@ -918,9 +882,7 @@ int intel_overlay_switch_off(struct intel_overlay *overlay) if (ret != 0) return ret; - regs = intel_overlay_map_regs(overlay); - iowrite32(0, ®s->OCMD); - intel_overlay_unmap_regs(overlay, regs); + iowrite32(0, &overlay->regs->OCMD); return intel_overlay_off(overlay); } @@ -1305,7 +1267,6 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, struct drm_intel_overlay_attrs *attrs = data; struct drm_i915_private *dev_priv = to_i915(dev); struct intel_overlay *overlay; - struct overlay_registers __iomem *regs; int ret; overlay = dev_priv->overlay; @@ -1345,15 +1306,7 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, overlay->contrast = attrs->contrast; overlay->saturation = attrs->saturation; - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unlock; - } - - update_reg_attrs(overlay, regs); - - intel_overlay_unmap_regs(overlay, regs); + update_reg_attrs(overlay, overlay->regs); if (attrs->flags & I915_OVERLAY_UPDATE_GAMMA) { if (IS_GEN2(dev_priv)) @@ -1386,12 +1339,47 @@ out_unlock: return ret; } +static int get_registers(struct intel_overlay *overlay, bool use_phys) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int err; + + obj = i915_gem_object_create_stolen(overlay->i915, PAGE_SIZE); + if (obj == NULL) + obj = i915_gem_object_create_internal(overlay->i915, PAGE_SIZE); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto err_put_bo; + } + + if (use_phys) + overlay->flip_addr = sg_dma_address(obj->mm.pages->sgl); + else + overlay->flip_addr = i915_ggtt_offset(vma); + overlay->regs = i915_vma_pin_iomap(vma); + i915_vma_unpin(vma); + + if (IS_ERR(overlay->regs)) { + err = PTR_ERR(overlay->regs); + goto err_put_bo; + } + + overlay->reg_bo = obj; + return 0; + +err_put_bo: + i915_gem_object_put(obj); + return err; +} + void intel_setup_overlay(struct drm_i915_private *dev_priv) { struct intel_overlay *overlay; - struct drm_i915_gem_object *reg_bo; - struct overlay_registers __iomem *regs; - struct i915_vma *vma = NULL; int ret; if (!HAS_OVERLAY(dev_priv)) @@ -1401,46 +1389,8 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv) if (!overlay) return; - mutex_lock(&dev_priv->drm.struct_mutex); - if (WARN_ON(dev_priv->overlay)) - goto out_free; - overlay->i915 = dev_priv; - reg_bo = NULL; - if (!OVERLAY_NEEDS_PHYSICAL(dev_priv)) - reg_bo = i915_gem_object_create_stolen(dev_priv, PAGE_SIZE); - if (reg_bo == NULL) - reg_bo = i915_gem_object_create(dev_priv, PAGE_SIZE); - if (IS_ERR(reg_bo)) - goto out_free; - overlay->reg_bo = reg_bo; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) { - ret = i915_gem_object_attach_phys(reg_bo, PAGE_SIZE); - if (ret) { - DRM_ERROR("failed to attach phys overlay regs\n"); - goto out_free_bo; - } - overlay->flip_addr = reg_bo->phys_handle->busaddr; - } else { - vma = i915_gem_object_ggtt_pin(reg_bo, NULL, - 0, PAGE_SIZE, PIN_MAPPABLE); - if (IS_ERR(vma)) { - DRM_ERROR("failed to pin overlay register bo\n"); - ret = PTR_ERR(vma); - goto out_free_bo; - } - overlay->flip_addr = i915_ggtt_offset(vma); - - ret = i915_gem_object_set_to_gtt_domain(reg_bo, true); - if (ret) { - DRM_ERROR("failed to move overlay register bo into the GTT\n"); - goto out_unpin_bo; - } - } - - /* init all values */ overlay->color_key = 0x0101fe; overlay->color_key_enabled = true; overlay->brightness = -19; @@ -1449,44 +1399,51 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv) init_request_active(&overlay->last_flip, NULL); - regs = intel_overlay_map_regs(overlay); - if (!regs) - goto out_unpin_bo; + mutex_lock(&dev_priv->drm.struct_mutex); + + ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv)); + if (ret) + goto out_free; + + ret = i915_gem_object_set_to_gtt_domain(overlay->reg_bo, true); + if (ret) + goto out_reg_bo; - memset_io(regs, 0, sizeof(struct overlay_registers)); - update_polyphase_filter(regs); - update_reg_attrs(overlay, regs); + mutex_unlock(&dev_priv->drm.struct_mutex); - intel_overlay_unmap_regs(overlay, regs); + memset_io(overlay->regs, 0, sizeof(struct overlay_registers)); + update_polyphase_filter(overlay->regs); + update_reg_attrs(overlay, overlay->regs); dev_priv->overlay = overlay; - mutex_unlock(&dev_priv->drm.struct_mutex); - DRM_INFO("initialized overlay support\n"); + DRM_INFO("Initialized overlay support.\n"); return; -out_unpin_bo: - if (vma) - i915_vma_unpin(vma); -out_free_bo: - i915_gem_object_put(reg_bo); +out_reg_bo: + i915_gem_object_put(overlay->reg_bo); out_free: mutex_unlock(&dev_priv->drm.struct_mutex); kfree(overlay); - return; } void intel_cleanup_overlay(struct drm_i915_private *dev_priv) { - if (!dev_priv->overlay) + struct intel_overlay *overlay; + + overlay = fetch_and_zero(&dev_priv->overlay); + if (!overlay) return; - /* The bo's should be free'd by the generic code already. + /* + * The bo's should be free'd by the generic code already. * Furthermore modesetting teardown happens beforehand so the - * hardware should be off already */ - WARN_ON(dev_priv->overlay->active); + * hardware should be off already. + */ + WARN_ON(overlay->active); + + i915_gem_object_put(overlay->reg_bo); - i915_gem_object_put(dev_priv->overlay->reg_bo); - kfree(dev_priv->overlay); + kfree(overlay); } #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) @@ -1498,37 +1455,11 @@ struct intel_overlay_error_state { u32 isr; }; -static struct overlay_registers __iomem * -intel_overlay_map_regs_atomic(struct intel_overlay *overlay) -{ - struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) - /* Cast to make sparse happy, but it's wc memory anyway, so - * equivalent to the wc io mapping on X86. */ - regs = (struct overlay_registers __iomem *) - overlay->reg_bo->phys_handle->vaddr; - else - regs = io_mapping_map_atomic_wc(&dev_priv->ggtt.iomap, - overlay->flip_addr); - - return regs; -} - -static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay, - struct overlay_registers __iomem *regs) -{ - if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) - io_mapping_unmap_atomic(regs); -} - struct intel_overlay_error_state * intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) { struct intel_overlay *overlay = dev_priv->overlay; struct intel_overlay_error_state *error; - struct overlay_registers __iomem *regs; if (!overlay || !overlay->active) return NULL; @@ -1541,18 +1472,9 @@ intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) error->isr = I915_READ(ISR); error->base = overlay->flip_addr; - regs = intel_overlay_map_regs_atomic(overlay); - if (!regs) - goto err; - - memcpy_fromio(&error->regs, regs, sizeof(struct overlay_registers)); - intel_overlay_unmap_regs_atomic(overlay, regs); + memcpy_fromio(&error->regs, overlay->regs, sizeof(error->regs)); return error; - -err: - kfree(error); - return NULL; } void diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c index d65959ef0564..17235e940ca9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c @@ -86,10 +86,8 @@ pmu_load(struct nv50_devinit *init, u8 type, bool post, struct nvkm_bios *bios = subdev->device->bios; struct nvbios_pmuR pmu; - if (!nvbios_pmuRm(bios, type, &pmu)) { - nvkm_error(subdev, "VBIOS PMU fuc %02x not found\n", type); + if (!nvbios_pmuRm(bios, type, &pmu)) return -EINVAL; - } if (!post) return 0; @@ -124,29 +122,30 @@ gm200_devinit_post(struct nvkm_devinit *base, bool post) return -EINVAL; } + /* Upload DEVINIT application from VBIOS onto PMU. */ ret = pmu_load(init, 0x04, post, &exec, &args); - if (ret) + if (ret) { + nvkm_error(subdev, "VBIOS PMU/DEVINIT not found\n"); return ret; + } - /* upload first chunk of init data */ + /* Upload tables required by opcodes in boot scripts. */ if (post) { - // devinit tables u32 pmu = pmu_args(init, args + 0x08, 0x08); u32 img = nvbios_rd16(bios, bit_I.offset + 0x14); u32 len = nvbios_rd16(bios, bit_I.offset + 0x16); pmu_data(init, pmu, img, len); } - /* upload second chunk of init data */ + /* Upload boot scripts. */ if (post) { - // devinit boot scripts u32 pmu = pmu_args(init, args + 0x08, 0x10); u32 img = nvbios_rd16(bios, bit_I.offset + 0x18); u32 len = nvbios_rd16(bios, bit_I.offset + 0x1a); pmu_data(init, pmu, img, len); } - /* execute init tables */ + /* Execute DEVINIT. */ if (post) { nvkm_wr32(device, 0x10a040, 0x00005000); pmu_exec(init, exec); @@ -157,7 +156,9 @@ gm200_devinit_post(struct nvkm_devinit *base, bool post) return -ETIMEDOUT; } - /* load and execute some other ucode image (bios therm?) */ + /* Optional: Execute PRE_OS application on PMU, which should at + * least take care of fans until a full PMU has been loaded. + */ pmu_load(init, 0x01, post, NULL, NULL); return 0; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b1b548a21f91..c71cc857b649 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1291,6 +1291,9 @@ static ssize_t vmbus_chan_attr_show(struct kobject *kobj, if (!attribute->show) return -EIO; + if (chan->state != CHANNEL_OPENED_STATE) + return -EINVAL; + return attribute->show(chan, buf); } diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index 7589f2ad1dae..631360b14ca7 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -187,12 +187,15 @@ static int st_lsm6dsx_set_fifo_odr(struct st_lsm6dsx_sensor *sensor, int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark) { - u16 fifo_watermark = ~0, cur_watermark, sip = 0, fifo_th_mask; + u16 fifo_watermark = ~0, cur_watermark, fifo_th_mask; struct st_lsm6dsx_hw *hw = sensor->hw; struct st_lsm6dsx_sensor *cur_sensor; int i, err, data; __le16 wdata; + if (!hw->sip) + return 0; + for (i = 0; i < ST_LSM6DSX_ID_MAX; i++) { cur_sensor = iio_priv(hw->iio_devs[i]); @@ -203,14 +206,10 @@ int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark) : cur_sensor->watermark; fifo_watermark = min_t(u16, fifo_watermark, cur_watermark); - sip += cur_sensor->sip; } - if (!sip) - return 0; - - fifo_watermark = max_t(u16, fifo_watermark, sip); - fifo_watermark = (fifo_watermark / sip) * sip; + fifo_watermark = max_t(u16, fifo_watermark, hw->sip); + fifo_watermark = (fifo_watermark / hw->sip) * hw->sip; fifo_watermark = fifo_watermark * hw->settings->fifo_ops.th_wl; err = regmap_read(hw->regmap, hw->settings->fifo_ops.fifo_th.addr + 1, diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c index 54e383231d1e..c31b9633f32d 100644 --- a/drivers/iio/temperature/maxim_thermocouple.c +++ b/drivers/iio/temperature/maxim_thermocouple.c @@ -258,7 +258,6 @@ static int maxim_thermocouple_remove(struct spi_device *spi) static const struct spi_device_id maxim_thermocouple_id[] = { {"max6675", MAX6675}, {"max31855", MAX31855}, - {"max31856", MAX31855}, {}, }; MODULE_DEVICE_TABLE(spi, maxim_thermocouple_id); diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index eec83757d55f..6c967dde58e7 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -893,14 +893,11 @@ static int trigger_sbr(struct hfi1_devdata *dd) } /* - * A secondary bus reset (SBR) issues a hot reset to our device. - * The following routine does a 1s wait after the reset is dropped - * per PCI Trhfa (recovery time). PCIe 3.0 section 6.6.1 - - * Conventional Reset, paragraph 3, line 35 also says that a 1s - * delay after a reset is required. Per spec requirements, - * the link is either working or not after that point. + * This is an end around to do an SBR during probe time. A new API needs + * to be implemented to have cleaner interface but this fixes the + * current brokenness */ - return pci_reset_bus(dev); + return pci_bridge_secondary_bus_reset(dev->bus->self); } /* diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f266c81f396f..0481223b1deb 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -332,7 +332,7 @@ static int crypt_iv_essiv_init(struct crypt_config *cc) int err; desc->tfm = essiv->hash_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; err = crypto_shash_digest(desc, cc->key, cc->key_size, essiv->salt); shash_desc_zero(desc); @@ -606,7 +606,7 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, int i, r; desc->tfm = lmk->hash_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (r) @@ -768,7 +768,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc, /* calculate crc32 for every 32bit part and xor it */ desc->tfm = tcw->crc32_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; for (i = 0; i < 4; i++) { r = crypto_shash_init(desc); if (r) @@ -1251,7 +1251,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc, * requests if driver request queue is full. */ skcipher_request_set_callback(ctx->r.req, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req)); } @@ -1268,7 +1268,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc, * requests if driver request queue is full. */ aead_request_set_callback(ctx->r.req_aead, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead)); } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 378878599466..89ccb64342de 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -532,7 +532,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result unsigned j, size; desc->tfm = ic->journal_mac; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (unlikely(r)) { @@ -676,7 +676,7 @@ static void complete_journal_encrypt(struct crypto_async_request *req, int err) static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_completion *comp) { int r; - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, complete_journal_encrypt, comp); if (likely(encrypt)) r = crypto_skcipher_encrypt(req); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index cae689de75fd..5ba067fa0c72 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2010-2011 Neil Brown - * Copyright (C) 2010-2017 Red Hat, Inc. All rights reserved. + * Copyright (C) 2010-2018 Red Hat, Inc. All rights reserved. * * This file is released under the GPL. */ @@ -29,9 +29,6 @@ */ #define MIN_RAID456_JOURNAL_SPACE (4*2048) -/* Global list of all raid sets */ -static LIST_HEAD(raid_sets); - static bool devices_handle_discard_safely = false; /* @@ -227,7 +224,6 @@ struct rs_layout { struct raid_set { struct dm_target *ti; - struct list_head list; uint32_t stripe_cache_entries; unsigned long ctr_flags; @@ -273,19 +269,6 @@ static void rs_config_restore(struct raid_set *rs, struct rs_layout *l) mddev->new_chunk_sectors = l->new_chunk_sectors; } -/* Find any raid_set in active slot for @rs on global list */ -static struct raid_set *rs_find_active(struct raid_set *rs) -{ - struct raid_set *r; - struct mapped_device *md = dm_table_get_md(rs->ti->table); - - list_for_each_entry(r, &raid_sets, list) - if (r != rs && dm_table_get_md(r->ti->table) == md) - return r; - - return NULL; -} - /* raid10 algorithms (i.e. formats) */ #define ALGORITHM_RAID10_DEFAULT 0 #define ALGORITHM_RAID10_NEAR 1 @@ -764,7 +747,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r mddev_init(&rs->md); - INIT_LIST_HEAD(&rs->list); rs->raid_disks = raid_devs; rs->delta_disks = 0; @@ -782,9 +764,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r for (i = 0; i < raid_devs; i++) md_rdev_init(&rs->dev[i].rdev); - /* Add @rs to global list. */ - list_add(&rs->list, &raid_sets); - /* * Remaining items to be initialized by further RAID params: * rs->md.persistent @@ -797,7 +776,7 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r return rs; } -/* Free all @rs allocations and remove it from global list. */ +/* Free all @rs allocations */ static void raid_set_free(struct raid_set *rs) { int i; @@ -815,8 +794,6 @@ static void raid_set_free(struct raid_set *rs) dm_put_device(rs->ti, rs->dev[i].data_dev); } - list_del(&rs->list); - kfree(rs); } @@ -2649,7 +2626,7 @@ static int rs_adjust_data_offsets(struct raid_set *rs) return 0; } - /* HM FIXME: get InSync raid_dev? */ + /* HM FIXME: get In_Sync raid_dev? */ rdev = &rs->dev[0].rdev; if (rs->delta_disks < 0) { @@ -3149,6 +3126,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); rs_set_new(rs); } else if (rs_is_recovering(rs)) { + /* Rebuild particular devices */ + if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { + set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); + rs_setup_recovery(rs, MaxSector); + } /* A recovering raid set may be resized */ ; /* skip setup rs */ } else if (rs_is_reshaping(rs)) { @@ -3242,6 +3224,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* Start raid set read-only and assumed clean to change in raid_resume() */ rs->md.ro = 1; rs->md.in_sync = 1; + + /* Keep array frozen */ set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery); /* Has to be held on running the array */ @@ -3265,7 +3249,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) rs->callbacks.congested_fn = raid_is_congested; dm_table_add_target_callbacks(ti->table, &rs->callbacks); - /* If raid4/5/6 journal mode explictely requested (only possible with journal dev) -> set it */ + /* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */ if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) { r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode); if (r) { @@ -3350,32 +3334,53 @@ static int raid_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } -/* Return string describing the current sync action of @mddev */ -static const char *decipher_sync_action(struct mddev *mddev, unsigned long recovery) +/* Return sync state string for @state */ +enum sync_state { st_frozen, st_reshape, st_resync, st_check, st_repair, st_recover, st_idle }; +static const char *sync_str(enum sync_state state) +{ + /* Has to be in above sync_state order! */ + static const char *sync_strs[] = { + "frozen", + "reshape", + "resync", + "check", + "repair", + "recover", + "idle" + }; + + return __within_range(state, 0, ARRAY_SIZE(sync_strs) - 1) ? sync_strs[state] : "undef"; +}; + +/* Return enum sync_state for @mddev derived from @recovery flags */ +static const enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery) { if (test_bit(MD_RECOVERY_FROZEN, &recovery)) - return "frozen"; + return st_frozen; - /* The MD sync thread can be done with io but still be running */ + /* The MD sync thread can be done with io or be interrupted but still be running */ if (!test_bit(MD_RECOVERY_DONE, &recovery) && (test_bit(MD_RECOVERY_RUNNING, &recovery) || (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery)))) { if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) - return "reshape"; + return st_reshape; if (test_bit(MD_RECOVERY_SYNC, &recovery)) { if (!test_bit(MD_RECOVERY_REQUESTED, &recovery)) - return "resync"; - else if (test_bit(MD_RECOVERY_CHECK, &recovery)) - return "check"; - return "repair"; + return st_resync; + if (test_bit(MD_RECOVERY_CHECK, &recovery)) + return st_check; + return st_repair; } if (test_bit(MD_RECOVERY_RECOVER, &recovery)) - return "recover"; + return st_recover; + + if (mddev->reshape_position != MaxSector) + return st_reshape; } - return "idle"; + return st_idle; } /* @@ -3409,6 +3414,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, sector_t resync_max_sectors) { sector_t r; + enum sync_state state; struct mddev *mddev = &rs->md; clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); @@ -3419,20 +3425,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags) && - !test_bit(MD_RECOVERY_INTR, &recovery) && - (test_bit(MD_RECOVERY_NEEDED, &recovery) || - test_bit(MD_RECOVERY_RESHAPE, &recovery) || - test_bit(MD_RECOVERY_RUNNING, &recovery))) - r = mddev->curr_resync_completed; - else + state = decipher_sync_action(mddev, recovery); + + if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery)) r = mddev->recovery_cp; + else + r = mddev->curr_resync_completed; - if (r >= resync_max_sectors && - (!test_bit(MD_RECOVERY_REQUESTED, &recovery) || - (!test_bit(MD_RECOVERY_FROZEN, &recovery) && - !test_bit(MD_RECOVERY_NEEDED, &recovery) && - !test_bit(MD_RECOVERY_RUNNING, &recovery)))) { + if (state == st_idle && r >= resync_max_sectors) { /* * Sync complete. */ @@ -3440,24 +3440,20 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, if (test_bit(MD_RECOVERY_RECOVER, &recovery)) set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - } else if (test_bit(MD_RECOVERY_RECOVER, &recovery)) { + } else if (state == st_recover) /* * In case we are recovering, the array is not in sync * and health chars should show the recovering legs. */ ; - - } else if (test_bit(MD_RECOVERY_SYNC, &recovery) && - !test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_resync) /* * If "resync" is occurring, the raid set * is or may be out of sync hence the health * characters shall be 'a'. */ set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - - } else if (test_bit(MD_RECOVERY_RESHAPE, &recovery) && - !test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_reshape) /* * If "reshape" is occurring, the raid set * is or may be out of sync hence the health @@ -3465,7 +3461,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - } else if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_check || state == st_repair) /* * If "check" or "repair" is occurring, the raid set has * undergone an initial sync and the health characters @@ -3473,12 +3469,12 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - } else { + else { struct md_rdev *rdev; /* * We are idle and recovery is needed, prevent 'A' chars race - * caused by components still set to in-sync by constrcuctor. + * caused by components still set to in-sync by constructor. */ if (test_bit(MD_RECOVERY_NEEDED, &recovery)) set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); @@ -3542,7 +3538,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, progress = rs_get_progress(rs, recovery, resync_max_sectors); resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ? atomic64_read(&mddev->resync_mismatches) : 0; - sync_action = decipher_sync_action(&rs->md, recovery); + sync_action = sync_str(decipher_sync_action(&rs->md, recovery)); /* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */ for (i = 0; i < rs->raid_disks; i++) @@ -3892,14 +3888,13 @@ static int rs_start_reshape(struct raid_set *rs) struct mddev *mddev = &rs->md; struct md_personality *pers = mddev->pers; + /* Don't allow the sync thread to work until the table gets reloaded. */ + set_bit(MD_RECOVERY_WAIT, &mddev->recovery); + r = rs_setup_reshape(rs); if (r) return r; - /* Need to be resumed to be able to start reshape, recovery is frozen until raid_resume() though */ - if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) - mddev_resume(mddev); - /* * Check any reshape constraints enforced by the personalility * @@ -3923,10 +3918,6 @@ static int rs_start_reshape(struct raid_set *rs) } } - /* Suspend because a resume will happen in raid_resume() */ - set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags); - mddev_suspend(mddev); - /* * Now reshape got set up, update superblocks to * reflect the fact so that a table reload will @@ -3947,29 +3938,6 @@ static int raid_preresume(struct dm_target *ti) if (test_and_set_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags)) return 0; - if (!test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { - struct raid_set *rs_active = rs_find_active(rs); - - if (rs_active) { - /* - * In case no rebuilds have been requested - * and an active table slot exists, copy - * current resynchonization completed and - * reshape position pointers across from - * suspended raid set in the active slot. - * - * This resumes the new mapping at current - * offsets to continue recover/reshape without - * necessarily redoing a raid set partially or - * causing data corruption in case of a reshape. - */ - if (rs_active->md.curr_resync_completed != MaxSector) - mddev->curr_resync_completed = rs_active->md.curr_resync_completed; - if (rs_active->md.reshape_position != MaxSector) - mddev->reshape_position = rs_active->md.reshape_position; - } - } - /* * The superblocks need to be updated on disk if the * array is new or new devices got added (thus zeroed @@ -4046,7 +4014,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 13, 2}, + .version = {1, 14, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 72142021b5c9..74f6770c70b1 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -189,6 +189,12 @@ struct dm_pool_metadata { sector_t data_block_size; /* + * We reserve a section of the metadata for commit overhead. + * All reported space does *not* include this. + */ + dm_block_t metadata_reserve; + + /* * Set if a transaction has to be aborted but the attempt to roll back * to the previous (good) transaction failed. The only pool metadata * operation possible in this state is the closing of the device. @@ -816,6 +822,22 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) return dm_tm_commit(pmd->tm, sblock); } +static void __set_metadata_reserve(struct dm_pool_metadata *pmd) +{ + int r; + dm_block_t total; + dm_block_t max_blocks = 4096; /* 16M */ + + r = dm_sm_get_nr_blocks(pmd->metadata_sm, &total); + if (r) { + DMERR("could not get size of metadata device"); + pmd->metadata_reserve = max_blocks; + } else { + sector_div(total, 10); + pmd->metadata_reserve = min(max_blocks, total); + } +} + struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, sector_t data_block_size, bool format_device) @@ -849,6 +871,8 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, return ERR_PTR(r); } + __set_metadata_reserve(pmd); + return pmd; } @@ -1820,6 +1844,13 @@ int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd, down_read(&pmd->root_lock); if (!pmd->fail_io) r = dm_sm_get_nr_free(pmd->metadata_sm, result); + + if (!r) { + if (*result < pmd->metadata_reserve) + *result = 0; + else + *result -= pmd->metadata_reserve; + } up_read(&pmd->root_lock); return r; @@ -1932,8 +1963,11 @@ int dm_pool_resize_metadata_dev(struct dm_pool_metadata *pmd, dm_block_t new_cou int r = -EINVAL; down_write(&pmd->root_lock); - if (!pmd->fail_io) + if (!pmd->fail_io) { r = __resize_space_map(pmd->metadata_sm, new_count); + if (!r) + __set_metadata_reserve(pmd); + } up_write(&pmd->root_lock); return r; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 7bd60a150f8f..aaf1ad481ee8 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -200,7 +200,13 @@ struct dm_thin_new_mapping; enum pool_mode { PM_WRITE, /* metadata may be changed */ PM_OUT_OF_DATA_SPACE, /* metadata may be changed, though data may not be allocated */ + + /* + * Like READ_ONLY, except may switch back to WRITE on metadata resize. Reported as READ_ONLY. + */ + PM_OUT_OF_METADATA_SPACE, PM_READ_ONLY, /* metadata may not be changed */ + PM_FAIL, /* all I/O fails */ }; @@ -1371,7 +1377,35 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); static void requeue_bios(struct pool *pool); -static void check_for_space(struct pool *pool) +static bool is_read_only_pool_mode(enum pool_mode mode) +{ + return (mode == PM_OUT_OF_METADATA_SPACE || mode == PM_READ_ONLY); +} + +static bool is_read_only(struct pool *pool) +{ + return is_read_only_pool_mode(get_pool_mode(pool)); +} + +static void check_for_metadata_space(struct pool *pool) +{ + int r; + const char *ooms_reason = NULL; + dm_block_t nr_free; + + r = dm_pool_get_free_metadata_block_count(pool->pmd, &nr_free); + if (r) + ooms_reason = "Could not get free metadata blocks"; + else if (!nr_free) + ooms_reason = "No free metadata blocks"; + + if (ooms_reason && !is_read_only(pool)) { + DMERR("%s", ooms_reason); + set_pool_mode(pool, PM_OUT_OF_METADATA_SPACE); + } +} + +static void check_for_data_space(struct pool *pool) { int r; dm_block_t nr_free; @@ -1397,14 +1431,16 @@ static int commit(struct pool *pool) { int r; - if (get_pool_mode(pool) >= PM_READ_ONLY) + if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) return -EINVAL; r = dm_pool_commit_metadata(pool->pmd); if (r) metadata_operation_failed(pool, "dm_pool_commit_metadata", r); - else - check_for_space(pool); + else { + check_for_metadata_space(pool); + check_for_data_space(pool); + } return r; } @@ -1470,6 +1506,19 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result) return r; } + r = dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks); + if (r) { + metadata_operation_failed(pool, "dm_pool_get_free_metadata_block_count", r); + return r; + } + + if (!free_blocks) { + /* Let's commit before we use up the metadata reserve. */ + r = commit(pool); + if (r) + return r; + } + return 0; } @@ -1501,6 +1550,7 @@ static blk_status_t should_error_unserviceable_bio(struct pool *pool) case PM_OUT_OF_DATA_SPACE: return pool->pf.error_if_no_space ? BLK_STS_NOSPC : 0; + case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: case PM_FAIL: return BLK_STS_IOERR; @@ -2464,8 +2514,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) error_retry_list(pool); break; + case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: - if (old_mode != new_mode) + if (!is_read_only_pool_mode(old_mode)) notify_of_pool_mode_change(pool, "read-only"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_read_only; @@ -3403,6 +3454,10 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit) DMINFO("%s: growing the metadata device from %llu to %llu blocks", dm_device_name(pool->pool_md), sb_metadata_dev_size, metadata_dev_size); + + if (get_pool_mode(pool) == PM_OUT_OF_METADATA_SPACE) + set_pool_mode(pool, PM_WRITE); + r = dm_pool_resize_metadata_dev(pool->pmd, metadata_dev_size); if (r) { metadata_operation_failed(pool, "dm_pool_resize_metadata_dev", r); @@ -3707,7 +3762,7 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv, struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - if (get_pool_mode(pool) >= PM_READ_ONLY) { + if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) { DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode", dm_device_name(pool->pool_md)); return -EOPNOTSUPP; @@ -3781,6 +3836,7 @@ static void pool_status(struct dm_target *ti, status_type_t type, dm_block_t nr_blocks_data; dm_block_t nr_blocks_metadata; dm_block_t held_root; + enum pool_mode mode; char buf[BDEVNAME_SIZE]; char buf2[BDEVNAME_SIZE]; struct pool_c *pt = ti->private; @@ -3851,9 +3907,10 @@ static void pool_status(struct dm_target *ti, status_type_t type, else DMEMIT("- "); - if (pool->pf.mode == PM_OUT_OF_DATA_SPACE) + mode = get_pool_mode(pool); + if (mode == PM_OUT_OF_DATA_SPACE) DMEMIT("out_of_data_space "); - else if (pool->pf.mode == PM_READ_ONLY) + else if (is_read_only_pool_mode(mode)) DMEMIT("ro "); else DMEMIT("rw "); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 12decdbd722d..fc65f0dedf7f 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -99,10 +99,26 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req, { struct scatterlist sg; - sg_init_one(&sg, data, len); - ahash_request_set_crypt(req, &sg, NULL, len); - - return crypto_wait_req(crypto_ahash_update(req), wait); + if (likely(!is_vmalloc_addr(data))) { + sg_init_one(&sg, data, len); + ahash_request_set_crypt(req, &sg, NULL, len); + return crypto_wait_req(crypto_ahash_update(req), wait); + } else { + do { + int r; + size_t this_step = min_t(size_t, len, PAGE_SIZE - offset_in_page(data)); + flush_kernel_vmap_range((void *)data, this_step); + sg_init_table(&sg, 1); + sg_set_page(&sg, vmalloc_to_page(data), this_step, offset_in_page(data)); + ahash_request_set_crypt(req, &sg, NULL, this_step); + r = crypto_wait_req(crypto_ahash_update(req), wait); + if (unlikely(r)) + return r; + data += this_step; + len -= this_step; + } while (len); + return 0; + } } /* diff --git a/drivers/misc/hmc6352.c b/drivers/misc/hmc6352.c index eeb7eef62174..38f90e179927 100644 --- a/drivers/misc/hmc6352.c +++ b/drivers/misc/hmc6352.c @@ -27,6 +27,7 @@ #include <linux/err.h> #include <linux/delay.h> #include <linux/sysfs.h> +#include <linux/nospec.h> static DEFINE_MUTEX(compass_mutex); @@ -50,6 +51,7 @@ static int compass_store(struct device *dev, const char *buf, size_t count, return ret; if (val >= strlen(map)) return -EINVAL; + val = array_index_nospec(val, strlen(map)); mutex_lock(&compass_mutex); ret = compass_command(c, map[val]); mutex_unlock(&compass_mutex); diff --git a/drivers/misc/ibmvmc.c b/drivers/misc/ibmvmc.c index 8f82bb9d11e2..b8aaa684c397 100644 --- a/drivers/misc/ibmvmc.c +++ b/drivers/misc/ibmvmc.c @@ -2131,7 +2131,7 @@ static int ibmvmc_init_crq_queue(struct crq_server_adapter *adapter) retrc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address, queue->msg_token, PAGE_SIZE); - retrc = rc; + rc = retrc; if (rc == H_RESOURCE) rc = ibmvmc_reset_crq_queue(adapter); diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 7bba62a72921..fc3872fe7b25 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -521,17 +521,15 @@ int mei_cldev_enable(struct mei_cl_device *cldev) cl = cldev->cl; + mutex_lock(&bus->device_lock); if (cl->state == MEI_FILE_UNINITIALIZED) { - mutex_lock(&bus->device_lock); ret = mei_cl_link(cl); - mutex_unlock(&bus->device_lock); if (ret) - return ret; + goto out; /* update pointers */ cl->cldev = cldev; } - mutex_lock(&bus->device_lock); if (mei_cl_is_connected(cl)) { ret = 0; goto out; @@ -616,9 +614,8 @@ int mei_cldev_disable(struct mei_cl_device *cldev) if (err < 0) dev_err(bus->dev, "Could not disconnect from the ME client\n"); -out: mei_cl_bus_module_put(cldev); - +out: /* Flush queues and remove any pending read */ mei_cl_flush_queues(cl, NULL); mei_cl_unlink(cl); @@ -876,12 +873,13 @@ static void mei_cl_bus_dev_release(struct device *dev) mei_me_cl_put(cldev->me_cl); mei_dev_bus_put(cldev->bus); + mei_cl_unlink(cldev->cl); kfree(cldev->cl); kfree(cldev); } static const struct device_type mei_cl_device_type = { - .release = mei_cl_bus_dev_release, + .release = mei_cl_bus_dev_release, }; /** diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 4ab6251d418e..ebdcf0b450e2 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -1767,7 +1767,7 @@ out: } } - rets = buf->size; + rets = len; err: cl_dbg(dev, cl, "rpm: autosuspend\n"); pm_runtime_mark_last_busy(dev->dev); diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 09e233d4c0de..e56f3e72d57a 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -1161,15 +1161,18 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) props_res = (struct hbm_props_response *)mei_msg; - if (props_res->status) { + if (props_res->status == MEI_HBMS_CLIENT_NOT_FOUND) { + dev_dbg(dev->dev, "hbm: properties response: %d CLIENT_NOT_FOUND\n", + props_res->me_addr); + } else if (props_res->status) { dev_err(dev->dev, "hbm: properties response: wrong status = %d %s\n", props_res->status, mei_hbm_status_str(props_res->status)); return -EPROTO; + } else { + mei_hbm_me_cl_add(dev, props_res); } - mei_hbm_me_cl_add(dev, props_res); - /* request property for the next client */ if (mei_hbm_prop_req(dev, props_res->me_addr + 1)) return -EIO; diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c index 09cb89645d06..2cfec33178c1 100644 --- a/drivers/mmc/host/meson-mx-sdio.c +++ b/drivers/mmc/host/meson-mx-sdio.c @@ -517,19 +517,23 @@ static struct mmc_host_ops meson_mx_mmc_ops = { static struct platform_device *meson_mx_mmc_slot_pdev(struct device *parent) { struct device_node *slot_node; + struct platform_device *pdev; /* * TODO: the MMC core framework currently does not support * controllers with multiple slots properly. So we only register * the first slot for now */ - slot_node = of_find_compatible_node(parent->of_node, NULL, "mmc-slot"); + slot_node = of_get_compatible_child(parent->of_node, "mmc-slot"); if (!slot_node) { dev_warn(parent, "no 'mmc-slot' sub-node found\n"); return ERR_PTR(-ENOENT); } - return of_platform_device_create(slot_node, NULL, parent); + pdev = of_platform_device_create(slot_node, NULL, parent); + of_node_put(slot_node); + + return pdev; } static int meson_mx_mmc_add_host(struct meson_mx_mmc_host *host) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 071693ebfe18..68760d4a5d3d 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -2177,6 +2177,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev) dma_release_channel(host->tx_chan); dma_release_channel(host->rx_chan); + dev_pm_clear_wake_irq(host->dev); pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index 9375cef22420..3d27616d9c85 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -283,8 +283,12 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCFINDIPDDPRT: spin_lock_bh(&ipddp_route_lock); rp = __ipddp_find_route(&rcp); - if (rp) - memcpy(&rcp2, rp, sizeof(rcp2)); + if (rp) { + memset(&rcp2, 0, sizeof(rcp2)); + rcp2.ip = rp->ip; + rcp2.at = rp->at; + rcp2.flags = rp->flags; + } spin_unlock_bh(&ipddp_route_lock); if (rp) { diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 7c791c1da4b9..bef01331266f 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -128,7 +128,7 @@ #define MV88E6XXX_G1_ATU_OP_GET_CLR_VIOLATION 0x7000 #define MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION BIT(7) #define MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION BIT(6) -#define MV88E6XXX_G1_ATU_OP_MISS_VIOLTATION BIT(5) +#define MV88E6XXX_G1_ATU_OP_MISS_VIOLATION BIT(5) #define MV88E6XXX_G1_ATU_OP_FULL_VIOLATION BIT(4) /* Offset 0x0C: ATU Data Register */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 307410898fc9..5200e4bdce93 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -349,7 +349,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) chip->ports[entry.portvec].atu_member_violation++; } - if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { + if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU miss violation for %pM portvec %x\n", entry.mac, entry.portvec); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index cecbb1d1f587..177587f9c3f1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -8027,7 +8027,7 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p) if (ether_addr_equal(addr->sa_data, dev->dev_addr)) return 0; - rc = bnxt_approve_mac(bp, addr->sa_data); + rc = bnxt_approve_mac(bp, addr->sa_data, true); if (rc) return rc; @@ -8827,14 +8827,19 @@ static int bnxt_init_mac_addr(struct bnxt *bp) } else { #ifdef CONFIG_BNXT_SRIOV struct bnxt_vf_info *vf = &bp->vf; + bool strict_approval = true; if (is_valid_ether_addr(vf->mac_addr)) { /* overwrite netdev dev_addr with admin VF MAC */ memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN); + /* Older PF driver or firmware may not approve this + * correctly. + */ + strict_approval = false; } else { eth_hw_addr_random(bp->dev); } - rc = bnxt_approve_mac(bp, bp->dev->dev_addr); + rc = bnxt_approve_mac(bp, bp->dev->dev_addr, strict_approval); #endif } return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index fcd085a9853a..3962f6fd543c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1104,7 +1104,7 @@ update_vf_mac_exit: mutex_unlock(&bp->hwrm_cmd_lock); } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { struct hwrm_func_vf_cfg_input req = {0}; int rc = 0; @@ -1122,12 +1122,13 @@ int bnxt_approve_mac(struct bnxt *bp, u8 *mac) memcpy(req.dflt_mac_addr, mac, ETH_ALEN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); mac_done: - if (rc) { + if (rc && strict) { rc = -EADDRNOTAVAIL; netdev_warn(bp->dev, "VF MAC address %pM not approved by the PF\n", mac); + return rc; } - return rc; + return 0; } #else @@ -1144,7 +1145,7 @@ void bnxt_update_vf_mac(struct bnxt *bp) { } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index e9b20cd19881..2eed9eda1195 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -39,5 +39,5 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); -int bnxt_approve_mac(struct bnxt *, u8 *); +int bnxt_approve_mac(struct bnxt *, u8 *, bool); #endif diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 96ae8c992810..7fddf76e6ead 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3836,6 +3836,13 @@ static const struct macb_config at91sam9260_config = { .init = macb_init, }; +static const struct macb_config sama5d3macb_config = { + .caps = MACB_CAPS_SG_DISABLED + | MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII, + .clk_init = macb_clk_init, + .init = macb_init, +}; + static const struct macb_config pc302gem_config = { .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE, .dma_burst_length = 16, @@ -3903,6 +3910,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "cdns,gem", .data = &pc302gem_config }, { .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config }, { .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config }, + { .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config }, { .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config }, { .compatible = "cdns,at91rm9200-emac", .data = &emac_config }, { .compatible = "cdns,emac", .data = &emac_config }, diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index c8c7ad2eff77..9b5a68b65432 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -2634,7 +2634,7 @@ static int hp100_login_to_vg_hub(struct net_device *dev, u_short force_relogin) /* Wait for link to drop */ time = jiffies + (HZ / 10); do { - if (~(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) + if (!(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) break; if (!in_interrupt()) schedule_timeout_interruptible(1); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 28500417843e..702fec82d806 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -58,6 +58,8 @@ static struct { */ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, const struct phylink_link_state *state); +static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, + phy_interface_t interface, struct phy_device *phy); /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 @@ -3142,6 +3144,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port) mvpp22_mode_reconfigure(port); if (port->phylink) { + netif_carrier_off(port->dev); phylink_start(port->phylink); } else { /* Phylink isn't used as of now for ACPI, so the MAC has to be @@ -3150,9 +3153,10 @@ static void mvpp2_start_dev(struct mvpp2_port *port) */ struct phylink_link_state state = { .interface = port->phy_interface, - .link = 1, }; mvpp2_mac_config(port->dev, MLO_AN_INBAND, &state); + mvpp2_mac_link_up(port->dev, MLO_AN_INBAND, port->phy_interface, + NULL); } netif_tx_start_all_queues(port->dev); @@ -4495,10 +4499,6 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, return; } - netif_tx_stop_all_queues(port->dev); - if (!port->has_phy) - netif_carrier_off(port->dev); - /* Make sure the port is disabled when reconfiguring the mode */ mvpp2_port_disable(port); @@ -4523,16 +4523,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK) mvpp2_port_loopback_set(port, state); - /* If the port already was up, make sure it's still in the same state */ - if (state->link || !port->has_phy) { - mvpp2_port_enable(port); - - mvpp2_egress_enable(port); - mvpp2_ingress_enable(port); - if (!port->has_phy) - netif_carrier_on(dev); - netif_tx_wake_all_queues(dev); - } + mvpp2_port_enable(port); } static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index b1a0e657febf..867cddba840f 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2847,7 +2847,7 @@ static void lan743x_pcidev_shutdown(struct pci_dev *pdev) lan743x_hardware_cleanup(adapter); } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static u16 lan743x_pm_wakeframe_crc16(const u8 *buf, int len) { return bitrev16(crc16(0xFFFF, buf, len)); @@ -3013,7 +3013,7 @@ static int lan743x_pm_resume(struct device *dev) static const struct dev_pm_ops lan743x_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume) }; -#endif /*CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ static const struct pci_device_id lan743x_pcidev_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) }, @@ -3025,7 +3025,7 @@ static struct pci_driver lan743x_pcidev_driver = { .id_table = lan743x_pcidev_tbl, .probe = lan743x_pcidev_probe, .remove = lan743x_pcidev_remove, -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .driver.pm = &lan743x_pm_ops, #endif .shutdown = lan743x_pcidev_shutdown, diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 1d8631303b53..bb529ff2ca81 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -13,6 +13,7 @@ #include <linux/pci.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/clk.h> #include <linux/delay.h> #include <linux/ethtool.h> #include <linux/phy.h> @@ -665,6 +666,7 @@ struct rtl8169_private { u16 event_slow; const struct rtl_coalesce_info *coalesce_info; + struct clk *clk; struct mdio_ops { void (*write)(struct rtl8169_private *, int, int); @@ -4775,12 +4777,14 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) { if (enable) { - RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); } else { RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); } + + udelay(10); } static void rtl_hw_start_8168bb(struct rtl8169_private *tp) @@ -5625,6 +5629,8 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) static void rtl_hw_start_8106(struct rtl8169_private *tp) { + rtl_hw_aspm_clkreq_enable(tp, false); + /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); @@ -5633,6 +5639,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); rtl_pcie_state_l2l3_enable(tp, false); + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8101(struct rtl8169_private *tp) @@ -7257,6 +7264,11 @@ static int rtl_jumbo_max(struct rtl8169_private *tp) } } +static void rtl_disable_clk(void *data) +{ + clk_disable_unprepare(data); +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data; @@ -7277,6 +7289,32 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT); tp->supports_gmii = cfg->has_gmii; + /* Get the *optional* external "ether_clk" used on some boards */ + tp->clk = devm_clk_get(&pdev->dev, "ether_clk"); + if (IS_ERR(tp->clk)) { + rc = PTR_ERR(tp->clk); + if (rc == -ENOENT) { + /* clk-core allows NULL (for suspend / resume) */ + tp->clk = NULL; + } else if (rc == -EPROBE_DEFER) { + return rc; + } else { + dev_err(&pdev->dev, "failed to get clk: %d\n", rc); + return rc; + } + } else { + rc = clk_prepare_enable(tp->clk); + if (rc) { + dev_err(&pdev->dev, "failed to enable clk: %d\n", rc); + return rc; + } + + rc = devm_add_action_or_reset(&pdev->dev, rtl_disable_clk, + tp->clk); + if (rc) + return rc; + } + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3609c7b696c7..2b800ce1d5bf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -67,7 +67,7 @@ static int dwmac1000_validate_mcast_bins(int mcast_bins) * Description: * This function validates the number of Unicast address entries supported * by a particular Synopsys 10/100/1000 controller. The Synopsys controller - * supports 1, 32, 64, or 128 Unicast filter entries for it's Unicast filter + * supports 1..32, 64, or 128 Unicast filter entries for it's Unicast filter * logic. This function validates a valid, supported configuration is * selected, and defaults to 1 Unicast address if an unsupported * configuration is selected. @@ -77,8 +77,7 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) int x = ucast_entries; switch (x) { - case 1: - case 32: + case 1 ... 32: case 64: case 128: break; diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 9263d638bd6d..f932923f7d56 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -41,6 +41,7 @@ config TI_DAVINCI_MDIO config TI_DAVINCI_CPDMA tristate "TI DaVinci CPDMA Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST + select GENERIC_ALLOCATOR ---help--- This driver supports TI's DaVinci CPDMA dma engine. diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 31c3d77b4733..fe01e141c8f8 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1203,6 +1203,9 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + netdev_info(ndev, "VF slot %u %s\n", + net_device_ctx->vf_serial, + net_device_ctx->vf_alloc ? "added" : "removed"); } static void netvsc_receive_inband(struct net_device *ndev, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 70921bbe0e28..3af6d8d15233 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1894,20 +1894,6 @@ out_unlock: rtnl_unlock(); } -static struct net_device *get_netvsc_bymac(const u8 *mac) -{ - struct net_device_context *ndev_ctx; - - list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { - struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx); - - if (ether_addr_equal(mac, dev->perm_addr)) - return dev; - } - - return NULL; -} - static struct net_device *get_netvsc_byref(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2036,26 +2022,48 @@ static void netvsc_vf_setup(struct work_struct *w) rtnl_unlock(); } +/* Find netvsc by VMBus serial number. + * The PCI hyperv controller records the serial number as the slot. + */ +static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) +{ + struct device *parent = vf_netdev->dev.parent; + struct net_device_context *ndev_ctx; + struct pci_dev *pdev; + + if (!parent || !dev_is_pci(parent)) + return NULL; /* not a PCI device */ + + pdev = to_pci_dev(parent); + if (!pdev->slot) { + netdev_notice(vf_netdev, "no PCI slot information\n"); + return NULL; + } + + list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { + if (!ndev_ctx->vf_alloc) + continue; + + if (ndev_ctx->vf_serial == pdev->slot->number) + return hv_get_drvdata(ndev_ctx->device_ctx); + } + + netdev_notice(vf_netdev, + "no netdev found for slot %u\n", pdev->slot->number); + return NULL; +} + static int netvsc_register_vf(struct net_device *vf_netdev) { - struct net_device *ndev; struct net_device_context *net_device_ctx; - struct device *pdev = vf_netdev->dev.parent; struct netvsc_device *netvsc_dev; + struct net_device *ndev; int ret; if (vf_netdev->addr_len != ETH_ALEN) return NOTIFY_DONE; - if (!pdev || !dev_is_pci(pdev) || dev_is_pf(pdev)) - return NOTIFY_DONE; - - /* - * We will use the MAC address to locate the synthetic interface to - * associate with the VF interface. If we don't find a matching - * synthetic interface, move on. - */ - ndev = get_netvsc_bymac(vf_netdev->perm_addr); + ndev = get_netvsc_byslot(vf_netdev); if (!ndev) return NOTIFY_DONE; @@ -2272,17 +2280,15 @@ static int netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); - rcu_read_lock(); - nvdev = rcu_dereference(ndev_ctx->nvdev); - - if (nvdev) + rtnl_lock(); + nvdev = rtnl_dereference(ndev_ctx->nvdev); + if (nvdev) cancel_work_sync(&nvdev->subchan_work); /* * Call to the vsc driver to let it know that the device is being * removed. Also blocks mtu and channel changes. */ - rtnl_lock(); vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); if (vf_netdev) netvsc_unregister_vf(vf_netdev); @@ -2294,7 +2300,6 @@ static int netvsc_remove(struct hv_device *dev) list_del(&ndev_ctx->list); rtnl_unlock(); - rcu_read_unlock(); hv_set_drvdata(dev, NULL); diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index ce61231e96ea..62dc564b251d 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -429,6 +429,9 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) goto out; + if (skb_mac_header_len(skb) < ETH_HLEN) + goto drop; + if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto drop; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index e3270deecec2..533b6fb8d923 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1213,13 +1213,13 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9063, 8)}, /* Sierra Wireless EM7305 */ {QMI_FIXED_INTF(0x1199, 0x9063, 10)}, /* Sierra Wireless EM7305 */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 10)},/* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/net/veth.c b/drivers/net/veth.c index bc8faf13a731..8fc64b67f01e 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -478,6 +478,8 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, int mac_len, delta, off; struct xdp_buff xdp; + skb_orphan(skb); + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (unlikely(!xdp_prog)) { @@ -523,8 +525,6 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, skb_copy_header(nskb, skb); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); - if (skb->sk) - skb_set_owner_w(nskb, skb->sk); consume_skb(skb); skb = nskb; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 9407acbd19a9..f17f602e6171 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -908,7 +908,11 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, BUG_ON(pull_to <= skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } - BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); + if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { + queue->rx.rsp_cons = ++cons; + kfree_skb(nskb); + return ~0U; + } skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(nfrag), @@ -1045,6 +1049,8 @@ err: skb->len += rx->status; i = xennet_fill_frags(queue, skb, &tmpq); + if (unlikely(i == ~0U)) + goto err; if (rx->flags & XEN_NETRXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 3533e918ea37..bfc4da660bb4 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -66,6 +66,7 @@ struct nvmet_rdma_rsp { struct nvmet_req req; + bool allocated; u8 n_rdma; u32 flags; u32 invalidate_rkey; @@ -174,11 +175,19 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue) unsigned long flags; spin_lock_irqsave(&queue->rsps_lock, flags); - rsp = list_first_entry(&queue->free_rsps, + rsp = list_first_entry_or_null(&queue->free_rsps, struct nvmet_rdma_rsp, free_list); - list_del(&rsp->free_list); + if (likely(rsp)) + list_del(&rsp->free_list); spin_unlock_irqrestore(&queue->rsps_lock, flags); + if (unlikely(!rsp)) { + rsp = kmalloc(sizeof(*rsp), GFP_KERNEL); + if (unlikely(!rsp)) + return NULL; + rsp->allocated = true; + } + return rsp; } @@ -187,6 +196,11 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp) { unsigned long flags; + if (rsp->allocated) { + kfree(rsp); + return; + } + spin_lock_irqsave(&rsp->queue->rsps_lock, flags); list_add_tail(&rsp->free_list, &rsp->queue->free_rsps); spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags); @@ -776,6 +790,15 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) cmd->queue = queue; rsp = nvmet_rdma_get_rsp(queue); + if (unlikely(!rsp)) { + /* + * we get here only under memory pressure, + * silently drop and have the host retry + * as we can't even fail it. + */ + nvmet_rdma_post_recv(queue->dev, cmd); + return; + } rsp->queue = queue; rsp->cmd = cmd; rsp->flags = 0; diff --git a/drivers/of/base.c b/drivers/of/base.c index 9095b8290150..74eaedd5b860 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -140,6 +140,9 @@ void of_populate_phandle_cache(void) if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL) phandles++; + if (!phandles) + goto out; + cache_entries = roundup_pow_of_two(phandles); phandle_cache_mask = cache_entries - 1; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index c00f82cc54aa..ee80e79db21a 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -89,6 +89,9 @@ static enum pci_protocol_version_t pci_protocol_version; #define STATUS_REVISION_MISMATCH 0xC0000059 +/* space for 32bit serial number as string */ +#define SLOT_NAME_SIZE 11 + /* * Message Types */ @@ -494,6 +497,7 @@ struct hv_pci_dev { struct list_head list_entry; refcount_t refs; enum hv_pcichild_state state; + struct pci_slot *pci_slot; struct pci_function_description desc; bool reported_missing; struct hv_pcibus_device *hbus; @@ -1457,6 +1461,34 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) spin_unlock_irqrestore(&hbus->device_list_lock, flags); } +/* + * Assign entries in sysfs pci slot directory. + * + * Note that this function does not need to lock the children list + * because it is called from pci_devices_present_work which + * is serialized with hv_eject_device_work because they are on the + * same ordered workqueue. Therefore hbus->children list will not change + * even when pci_create_slot sleeps. + */ +static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + char name[SLOT_NAME_SIZE]; + int slot_nr; + + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (hpdev->pci_slot) + continue; + + slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot)); + snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser); + hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr, + name, NULL); + if (!hpdev->pci_slot) + pr_warn("pci_create slot %s failed\n", name); + } +} + /** * create_root_hv_pci_bus() - Expose a new root PCI bus * @hbus: Root PCI bus, as understood by this driver @@ -1480,6 +1512,7 @@ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus) pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); pci_bus_assign_resources(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_bus_add_devices(hbus->pci_bus); pci_unlock_rescan_remove(); hbus->state = hv_pcibus_installed; @@ -1742,6 +1775,7 @@ static void pci_devices_present_work(struct work_struct *work) */ pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_unlock_rescan_remove(); break; @@ -1858,6 +1892,9 @@ static void hv_eject_device_work(struct work_struct *work) list_del(&hpdev->list_entry); spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags); + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + memset(&ctxt, 0, sizeof(ctxt)); ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE; diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 7136e3430925..a938abdb41ce 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -496,7 +496,7 @@ int pciehp_power_on_slot(struct slot *slot) u16 slot_status; int retval; - /* Clear sticky power-fault bit from previous power failures */ + /* Clear power-fault bit from previous power failures */ pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); if (slot_status & PCI_EXP_SLTSTA_PFD) pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, @@ -646,6 +646,14 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) pciehp_handle_button_press(slot); } + /* Check Power Fault Detected */ + if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { + ctrl->power_fault_detected = 1; + ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot)); + pciehp_set_attention_status(slot, 1); + pciehp_green_led_off(slot); + } + /* * Disable requests have higher priority than Presence Detect Changed * or Data Link Layer State Changed events. @@ -657,14 +665,6 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) pciehp_handle_presence_or_link_change(slot, events); up_read(&ctrl->reset_lock); - /* Check Power Fault Detected */ - if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { - ctrl->power_fault_detected = 1; - ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot)); - pciehp_set_attention_status(slot, 1); - pciehp_green_led_off(slot); - } - pci_config_pm_runtime_put(pdev); wake_up(&ctrl->requester); return IRQ_HANDLED; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 29ff9619b5fa..1835f3a7aa8d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4547,6 +4547,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); } +EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { @@ -5200,7 +5201,7 @@ static int __pci_reset_bus(struct pci_bus *bus) */ int pci_reset_bus(struct pci_dev *pdev) { - return pci_probe_reset_slot(pdev->slot) ? + return (!pci_probe_reset_slot(pdev->slot)) ? __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus); } EXPORT_SYMBOL_GPL(pci_reset_bus); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ec784009a36b..201f9e5ff55c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2074,6 +2074,7 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev) { #ifdef CONFIG_PCI_PASID struct pci_dev *bridge; + int pcie_type; u32 cap; if (!pci_is_pcie(dev)) @@ -2083,7 +2084,9 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev) if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX)) return; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + pcie_type = pci_pcie_type(dev); + if (pcie_type == PCI_EXP_TYPE_ROOT_PORT || + pcie_type == PCI_EXP_TYPE_RC_END) dev->eetlp_prefix_path = 1; else { bridge = pci_upstream_bridge(dev); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index ef7143a274e0..6bc27b7fd452 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4355,11 +4355,6 @@ static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags) * * 0x9d10-0x9d1b PCI Express Root port #{1-12} * - * The 300 series chipset suffers from the same bug so include those root - * ports here as well. - * - * 0xa32c-0xa343 PCI Express Root port #{0-24} - * * [1] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-datasheet-vol-2.html * [2] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-datasheet-vol-1.html * [3] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-spec-update.html @@ -4377,7 +4372,6 @@ static bool pci_quirk_intel_spt_pch_acs_match(struct pci_dev *dev) case 0xa110 ... 0xa11f: case 0xa167 ... 0xa16a: /* Sunrise Point */ case 0xa290 ... 0xa29f: case 0xa2e7 ... 0xa2ee: /* Union Point */ case 0x9d10 ... 0x9d1b: /* 7th & 8th Gen Mobile */ - case 0xa32c ... 0xa343: /* 300 series */ return true; } diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 9940cc70f38b..54a8b30dda38 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -14,6 +14,8 @@ #include <linux/poll.h> #include <linux/wait.h> +#include <linux/nospec.h> + MODULE_DESCRIPTION("Microsemi Switchtec(tm) PCIe Management Driver"); MODULE_VERSION("0.1"); MODULE_LICENSE("GPL"); @@ -909,6 +911,8 @@ static int ioctl_port_to_pff(struct switchtec_dev *stdev, default: if (p.port > ARRAY_SIZE(pcfg->dsp_pff_inst_id)) return -EINVAL; + p.port = array_index_nospec(p.port, + ARRAY_SIZE(pcfg->dsp_pff_inst_id) + 1); p.pff = ioread32(&pcfg->dsp_pff_inst_id[p.port - 1]); break; } diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c index ece41fb2848f..c4f4d904e4a6 100644 --- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c +++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c @@ -1040,7 +1040,7 @@ static int madera_pin_probe(struct platform_device *pdev) } /* if the configuration is provided through pdata, apply it */ - if (pdata) { + if (pdata && pdata->gpio_configs) { ret = pinctrl_register_mappings(pdata->gpio_configs, pdata->n_gpio_configs); if (ret) { diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index 6a1b6058b991..628817c40e3b 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -793,7 +793,7 @@ static int ingenic_pinctrl_probe(struct platform_device *pdev) err = pinctrl_generic_add_group(jzpc->pctl, group->name, group->pins, group->num_pins, group->data); - if (err) { + if (err < 0) { dev_err(dev, "Failed to register group %s\n", group->name); return err; @@ -806,7 +806,7 @@ static int ingenic_pinctrl_probe(struct platform_device *pdev) err = pinmux_generic_add_function(jzpc->pctl, func->name, func->group_names, func->num_group_names, func->data); - if (err) { + if (err < 0) { dev_err(dev, "Failed to register function %s\n", func->name); return err; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 2155a30c282b..5d72ffad32c2 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -634,6 +634,29 @@ static void msm_gpio_irq_mask(struct irq_data *d) raw_spin_lock_irqsave(&pctrl->lock, flags); val = readl(pctrl->regs + g->intr_cfg_reg); + /* + * There are two bits that control interrupt forwarding to the CPU. The + * RAW_STATUS_EN bit causes the level or edge sensed on the line to be + * latched into the interrupt status register when the hardware detects + * an irq that it's configured for (either edge for edge type or level + * for level type irq). The 'non-raw' status enable bit causes the + * hardware to assert the summary interrupt to the CPU if the latched + * status bit is set. There's a bug though, the edge detection logic + * seems to have a problem where toggling the RAW_STATUS_EN bit may + * cause the status bit to latch spuriously when there isn't any edge + * so we can't touch that bit for edge type irqs and we have to keep + * the bit set anyway so that edges are latched while the line is masked. + * + * To make matters more complicated, leaving the RAW_STATUS_EN bit + * enabled all the time causes level interrupts to re-latch into the + * status register because the level is still present on the line after + * we ack it. We clear the raw status enable bit during mask here and + * set the bit on unmask so the interrupt can't latch into the hardware + * while it's masked. + */ + if (irqd_get_trigger_type(d) & IRQ_TYPE_LEVEL_MASK) + val &= ~BIT(g->intr_raw_status_bit); + val &= ~BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); @@ -655,6 +678,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d) raw_spin_lock_irqsave(&pctrl->lock, flags); val = readl(pctrl->regs + g->intr_cfg_reg); + val |= BIT(g->intr_raw_status_bit); val |= BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ec891bc7d10a..f039266b275d 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -872,8 +872,6 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits) if (bits & 0x07) return -EINVAL; - memset(bitmap, 0, bits / 8); - if (str[0] == '0' && str[1] == 'x') str++; if (*str == 'x') @@ -895,25 +893,23 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits) } /* - * str2clrsetmasks() - parse bitmask argument and set the clear and - * the set bitmap mask. A concatenation (done with ',') of these terms - * is recognized: + * modify_bitmap() - parse bitmask argument and modify an existing + * bit mask accordingly. A concatenation (done with ',') of these + * terms is recognized: * +<bitnr>[-<bitnr>] or -<bitnr>[-<bitnr>] * <bitnr> may be any valid number (hex, decimal or octal) in the range * 0...bits-1; the leading + or - is required. Here are some examples: * +0-15,+32,-128,-0xFF * -0-255,+1-16,+0x128 * +1,+2,+3,+4,-5,-7-10 - * Returns a clear and a set bitmask. Every positive value in the string - * results in a bit set in the set mask and every negative value in the - * string results in a bit SET in the clear mask. As a bit may be touched - * more than once, the last 'operation' wins: +0-255,-128 = all but bit - * 128 set in the set mask, only bit 128 set in the clear mask. + * Returns the new bitmap after all changes have been applied. Every + * positive value in the string will set a bit and every negative value + * in the string will clear a bit. As a bit may be touched more than once, + * the last 'operation' wins: + * +0-255,-128 = first bits 0-255 will be set, then bit 128 will be + * cleared again. All other bits are unmodified. */ -static int str2clrsetmasks(const char *str, - unsigned long *clrmap, - unsigned long *setmap, - int bits) +static int modify_bitmap(const char *str, unsigned long *bitmap, int bits) { int a, i, z; char *np, sign; @@ -922,9 +918,6 @@ static int str2clrsetmasks(const char *str, if (bits & 0x07) return -EINVAL; - memset(clrmap, 0, bits / 8); - memset(setmap, 0, bits / 8); - while (*str) { sign = *str++; if (sign != '+' && sign != '-') @@ -940,13 +933,10 @@ static int str2clrsetmasks(const char *str, str = np; } for (i = a; i <= z; i++) - if (sign == '+') { - set_bit_inv(i, setmap); - clear_bit_inv(i, clrmap); - } else { - clear_bit_inv(i, setmap); - set_bit_inv(i, clrmap); - } + if (sign == '+') + set_bit_inv(i, bitmap); + else + clear_bit_inv(i, bitmap); while (*str == ',' || *str == '\n') str++; } @@ -970,44 +960,34 @@ static int process_mask_arg(const char *str, unsigned long *bitmap, int bits, struct mutex *lock) { - int i; + unsigned long *newmap, size; + int rc; /* bits needs to be a multiple of 8 */ if (bits & 0x07) return -EINVAL; + size = BITS_TO_LONGS(bits)*sizeof(unsigned long); + newmap = kmalloc(size, GFP_KERNEL); + if (!newmap) + return -ENOMEM; + if (mutex_lock_interruptible(lock)) { + kfree(newmap); + return -ERESTARTSYS; + } + if (*str == '+' || *str == '-') { - DECLARE_BITMAP(clrm, bits); - DECLARE_BITMAP(setm, bits); - - i = str2clrsetmasks(str, clrm, setm, bits); - if (i) - return i; - if (mutex_lock_interruptible(lock)) - return -ERESTARTSYS; - for (i = 0; i < bits; i++) { - if (test_bit_inv(i, clrm)) - clear_bit_inv(i, bitmap); - if (test_bit_inv(i, setm)) - set_bit_inv(i, bitmap); - } + memcpy(newmap, bitmap, size); + rc = modify_bitmap(str, newmap, bits); } else { - DECLARE_BITMAP(setm, bits); - - i = hex2bitmap(str, setm, bits); - if (i) - return i; - if (mutex_lock_interruptible(lock)) - return -ERESTARTSYS; - for (i = 0; i < bits; i++) - if (test_bit_inv(i, setm)) - set_bit_inv(i, bitmap); - else - clear_bit_inv(i, bitmap); + memset(newmap, 0, size); + rc = hex2bitmap(str, newmap, bits); } + if (rc == 0) + memcpy(bitmap, newmap, size); mutex_unlock(lock); - - return 0; + kfree(newmap); + return rc; } /* diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 7cb3ab0a35a0..3082e72e4f6c 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -30,7 +30,11 @@ #define DRIVER_NAME "fsl-dspi" +#ifdef CONFIG_M5441x +#define DSPI_FIFO_SIZE 16 +#else #define DSPI_FIFO_SIZE 4 +#endif #define DSPI_DMA_BUFSIZE (DSPI_FIFO_SIZE * 1024) #define SPI_MCR 0x00 @@ -623,9 +627,11 @@ static void dspi_tcfq_read(struct fsl_dspi *dspi) static void dspi_eoq_write(struct fsl_dspi *dspi) { int fifo_size = DSPI_FIFO_SIZE; + u16 xfer_cmd = dspi->tx_cmd; /* Fill TX FIFO with as many transfers as possible */ while (dspi->len && fifo_size--) { + dspi->tx_cmd = xfer_cmd; /* Request EOQF for last transfer in FIFO */ if (dspi->len == dspi->bytes_per_word || fifo_size == 0) dspi->tx_cmd |= SPI_PUSHR_CMD_EOQ; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ec395a6baf9c..9da0bc5a036c 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2143,8 +2143,17 @@ int spi_register_controller(struct spi_controller *ctlr) */ if (ctlr->num_chipselect == 0) return -EINVAL; - /* allocate dynamic bus number using Linux idr */ - if ((ctlr->bus_num < 0) && ctlr->dev.of_node) { + if (ctlr->bus_num >= 0) { + /* devices with a fixed bus num must check-in with the num */ + mutex_lock(&board_lock); + id = idr_alloc(&spi_master_idr, ctlr, ctlr->bus_num, + ctlr->bus_num + 1, GFP_KERNEL); + mutex_unlock(&board_lock); + if (WARN(id < 0, "couldn't get idr")) + return id == -ENOSPC ? -EBUSY : id; + ctlr->bus_num = id; + } else if (ctlr->dev.of_node) { + /* allocate dynamic bus number using Linux idr */ id = of_alias_get_id(ctlr->dev.of_node, "spi"); if (id >= 0) { ctlr->bus_num = id; diff --git a/drivers/staging/erofs/Kconfig b/drivers/staging/erofs/Kconfig index 96f614934df1..663b755bf2fb 100644 --- a/drivers/staging/erofs/Kconfig +++ b/drivers/staging/erofs/Kconfig @@ -2,7 +2,7 @@ config EROFS_FS tristate "EROFS filesystem support" - depends on BROKEN + depends on BLOCK help EROFS(Enhanced Read-Only File System) is a lightweight read-only file system with modern designs (eg. page-sized diff --git a/drivers/staging/erofs/super.c b/drivers/staging/erofs/super.c index 1aec509c805f..2df9768edac9 100644 --- a/drivers/staging/erofs/super.c +++ b/drivers/staging/erofs/super.c @@ -340,7 +340,7 @@ static int erofs_read_super(struct super_block *sb, goto err_sbread; sb->s_magic = EROFS_SUPER_MAGIC; - sb->s_flags |= MS_RDONLY | MS_NOATIME; + sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_time_gran = 1; @@ -627,7 +627,7 @@ static int erofs_remount(struct super_block *sb, int *flags, char *data) { BUG_ON(!sb_rdonly(sb)); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } diff --git a/drivers/staging/fbtft/TODO b/drivers/staging/fbtft/TODO index 7e64c7e438f0..a9f4802bb6be 100644 --- a/drivers/staging/fbtft/TODO +++ b/drivers/staging/fbtft/TODO @@ -2,3 +2,7 @@ GPIO descriptor API in <linux/gpio/consumer.h> and look up GPIO lines from device tree, ACPI or board files, board files should use <linux/gpio/machine.h> + +* convert all these over to drm_simple_display_pipe and submit for inclusion + into the DRM subsystem under drivers/gpu/drm - fbdev doesn't take any new + drivers anymore. diff --git a/drivers/staging/gasket/TODO b/drivers/staging/gasket/TODO index 6ff8e01b04cc..5b1865f8af2d 100644 --- a/drivers/staging/gasket/TODO +++ b/drivers/staging/gasket/TODO @@ -1,9 +1,22 @@ This is a list of things that need to be done to get this driver out of the staging directory. + +- Implement the gasket framework's functionality through UIO instead of + introducing a new user-space drivers framework that is quite similar. + + UIO provides the necessary bits to implement user-space drivers. Meanwhile + the gasket APIs adds some extra conveniences like PCI BAR mapping, and + MSI interrupts. Add these features to the UIO subsystem, then re-implement + the Apex driver as a basic UIO driver instead (include/linux/uio_driver.h) + - Document sysfs files with Documentation/ABI/ entries. + - Use misc interface instead of major number for driver version description. + - Add descriptions of module_param's + - apex_get_status() should actually check status. + - "drivers" should never be dealing with "raw" sysfs calls or mess around with kobjects at all. The driver core should handle all of this for you automaically. There should not be a need for raw attribute macros. diff --git a/drivers/staging/vboxvideo/vbox_drv.c b/drivers/staging/vboxvideo/vbox_drv.c index da92c493f157..69cc508af1bc 100644 --- a/drivers/staging/vboxvideo/vbox_drv.c +++ b/drivers/staging/vboxvideo/vbox_drv.c @@ -59,6 +59,11 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ret = PTR_ERR(dev); goto err_drv_alloc; } + + ret = pci_enable_device(pdev); + if (ret) + goto err_pci_enable; + dev->pdev = pdev; pci_set_drvdata(pdev, dev); @@ -75,6 +80,8 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_drv_dev_register: vbox_driver_unload(dev); err_vbox_driver_load: + pci_disable_device(pdev); + err_pci_enable: drm_dev_put(dev); err_drv_alloc: return ret; diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c index a83eac8668d0..79836c8fb909 100644 --- a/drivers/staging/vboxvideo/vbox_mode.c +++ b/drivers/staging/vboxvideo/vbox_mode.c @@ -323,6 +323,11 @@ static int vbox_crtc_page_flip(struct drm_crtc *crtc, if (rc) return rc; + mutex_lock(&vbox->hw_mutex); + vbox_set_view(crtc); + vbox_do_modeset(crtc, &crtc->mode); + mutex_unlock(&vbox->hw_mutex); + spin_lock_irqsave(&drm->event_lock, flags); if (event) diff --git a/drivers/staging/wilc1000/Makefile b/drivers/staging/wilc1000/Makefile index f7b07c0b5ce2..ee7e26b886a5 100644 --- a/drivers/staging/wilc1000/Makefile +++ b/drivers/staging/wilc1000/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_WILC1000) += wilc1000.o ccflags-y += -DFIRMWARE_1002=\"atmel/wilc1002_firmware.bin\" \ -DFIRMWARE_1003=\"atmel/wilc1003_firmware.bin\" @@ -11,9 +12,7 @@ wilc1000-objs := wilc_wfi_cfgoperations.o linux_wlan.o linux_mon.o \ wilc_wlan.o obj-$(CONFIG_WILC1000_SDIO) += wilc1000-sdio.o -wilc1000-sdio-objs += $(wilc1000-objs) wilc1000-sdio-objs += wilc_sdio.o obj-$(CONFIG_WILC1000_SPI) += wilc1000-spi.o -wilc1000-spi-objs += $(wilc1000-objs) wilc1000-spi-objs += wilc_spi.o diff --git a/drivers/staging/wilc1000/linux_wlan.c b/drivers/staging/wilc1000/linux_wlan.c index 01cf4bd2e192..3b8d237decbf 100644 --- a/drivers/staging/wilc1000/linux_wlan.c +++ b/drivers/staging/wilc1000/linux_wlan.c @@ -1038,8 +1038,8 @@ void wilc_netdev_cleanup(struct wilc *wilc) } kfree(wilc); - wilc_debugfs_remove(); } +EXPORT_SYMBOL_GPL(wilc_netdev_cleanup); static const struct net_device_ops wilc_netdev_ops = { .ndo_init = mac_init_fn, @@ -1062,7 +1062,6 @@ int wilc_netdev_init(struct wilc **wilc, struct device *dev, int io_type, if (!wl) return -ENOMEM; - wilc_debugfs_init(); *wilc = wl; wl->io_type = io_type; wl->hif_func = ops; @@ -1124,3 +1123,6 @@ int wilc_netdev_init(struct wilc **wilc, struct device *dev, int io_type, return 0; } +EXPORT_SYMBOL_GPL(wilc_netdev_init); + +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/wilc1000/wilc_debugfs.c b/drivers/staging/wilc1000/wilc_debugfs.c index edc72876458d..8001df66b8c2 100644 --- a/drivers/staging/wilc1000/wilc_debugfs.c +++ b/drivers/staging/wilc1000/wilc_debugfs.c @@ -19,6 +19,7 @@ static struct dentry *wilc_dir; #define DBG_LEVEL_ALL (DEBUG | INFO | WRN | ERR) static atomic_t WILC_DEBUG_LEVEL = ATOMIC_INIT(ERR); +EXPORT_SYMBOL_GPL(WILC_DEBUG_LEVEL); static ssize_t wilc_debug_level_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -87,7 +88,7 @@ static struct wilc_debugfs_info_t debugfs_info[] = { }, }; -int wilc_debugfs_init(void) +static int __init wilc_debugfs_init(void) { int i; struct wilc_debugfs_info_t *info; @@ -103,10 +104,12 @@ int wilc_debugfs_init(void) } return 0; } +module_init(wilc_debugfs_init); -void wilc_debugfs_remove(void) +static void __exit wilc_debugfs_remove(void) { debugfs_remove_recursive(wilc_dir); } +module_exit(wilc_debugfs_remove); #endif diff --git a/drivers/staging/wilc1000/wilc_wlan.c b/drivers/staging/wilc1000/wilc_wlan.c index 6787b6e9f124..8b184aa30d25 100644 --- a/drivers/staging/wilc1000/wilc_wlan.c +++ b/drivers/staging/wilc1000/wilc_wlan.c @@ -417,6 +417,7 @@ void chip_allow_sleep(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0xf0, reg & ~BIT(0)); wilc->hif_func->hif_write_reg(wilc, 0xfa, 0); } +EXPORT_SYMBOL_GPL(chip_allow_sleep); void chip_wakeup(struct wilc *wilc) { @@ -471,6 +472,7 @@ void chip_wakeup(struct wilc *wilc) } chip_ps_state = CHIP_WAKEDUP; } +EXPORT_SYMBOL_GPL(chip_wakeup); void wilc_chip_sleep_manually(struct wilc *wilc) { @@ -484,6 +486,7 @@ void wilc_chip_sleep_manually(struct wilc *wilc) chip_ps_state = CHIP_SLEEPING_MANUAL; release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(wilc_chip_sleep_manually); void host_wakeup_notify(struct wilc *wilc) { @@ -491,6 +494,7 @@ void host_wakeup_notify(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0x10b0, 1); release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(host_wakeup_notify); void host_sleep_notify(struct wilc *wilc) { @@ -498,6 +502,7 @@ void host_sleep_notify(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0x10ac, 1); release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(host_sleep_notify); int wilc_wlan_handle_txq(struct net_device *dev, u32 *txq_count) { @@ -871,6 +876,7 @@ void wilc_handle_isr(struct wilc *wilc) release_bus(wilc, RELEASE_ALLOW_SLEEP); } +EXPORT_SYMBOL_GPL(wilc_handle_isr); int wilc_wlan_firmware_download(struct wilc *wilc, const u8 *buffer, u32 buffer_size) diff --git a/drivers/staging/wilc1000/wilc_wlan_if.h b/drivers/staging/wilc1000/wilc_wlan_if.h index 00d13b153f80..b81a73b9bd67 100644 --- a/drivers/staging/wilc1000/wilc_wlan_if.h +++ b/drivers/staging/wilc1000/wilc_wlan_if.h @@ -831,6 +831,4 @@ struct wilc; int wilc_wlan_init(struct net_device *dev); u32 wilc_get_chipid(struct wilc *wilc, bool update); -int wilc_debugfs_init(void); -void wilc_debugfs_remove(void); #endif diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index 5414c4a87bea..27284a2dcd2b 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -522,6 +522,8 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count return -EIO; while (count > 0) { + int ret = 0; + spin_lock_irqsave(&hp->lock, flags); rsize = hp->outbuf_size - hp->n_outbuf; @@ -537,10 +539,13 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count } if (hp->n_outbuf > 0) - hvc_push(hp); + ret = hvc_push(hp); spin_unlock_irqrestore(&hp->lock, flags); + if (!ret) + break; + if (count) { if (hp->n_outbuf > 0) hvc_flush(hp); @@ -623,6 +628,15 @@ static int hvc_chars_in_buffer(struct tty_struct *tty) #define MAX_TIMEOUT (2000) static u32 timeout = MIN_TIMEOUT; +/* + * Maximum number of bytes to get from the console driver if hvc_poll is + * called from driver (and can't sleep). Any more than this and we break + * and start polling with khvcd. This value was derived from from an OpenBMC + * console with the OPAL driver that results in about 0.25ms interrupts off + * latency. + */ +#define HVC_ATOMIC_READ_MAX 128 + #define HVC_POLL_READ 0x00000001 #define HVC_POLL_WRITE 0x00000002 @@ -669,8 +683,8 @@ static int __hvc_poll(struct hvc_struct *hp, bool may_sleep) if (!hp->irq_requested) poll_mask |= HVC_POLL_READ; + read_again: /* Read data if any */ - count = tty_buffer_request_room(&hp->port, N_INBUF); /* If flip is full, just reschedule a later read */ @@ -717,9 +731,23 @@ static int __hvc_poll(struct hvc_struct *hp, bool may_sleep) #endif /* CONFIG_MAGIC_SYSRQ */ tty_insert_flip_char(&hp->port, buf[i], 0); } - if (n == count) - poll_mask |= HVC_POLL_READ; - read_total = n; + read_total += n; + + if (may_sleep) { + /* Keep going until the flip is full */ + spin_unlock_irqrestore(&hp->lock, flags); + cond_resched(); + spin_lock_irqsave(&hp->lock, flags); + goto read_again; + } else if (read_total < HVC_ATOMIC_READ_MAX) { + /* Break and defer if it's a large read in atomic */ + goto read_again; + } + + /* + * Latency break, schedule another poll immediately. + */ + poll_mask |= HVC_POLL_READ; out: /* Wakeup write queue if necessary */ diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 27346d69f393..f9b40a9dc4d3 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -780,20 +780,9 @@ static int acm_tty_write(struct tty_struct *tty, } if (acm->susp_count) { - if (acm->putbuffer) { - /* now to preserve order */ - usb_anchor_urb(acm->putbuffer->urb, &acm->delayed); - acm->putbuffer = NULL; - } usb_anchor_urb(wb->urb, &acm->delayed); spin_unlock_irqrestore(&acm->write_lock, flags); return count; - } else { - if (acm->putbuffer) { - /* at this point there is no good way to handle errors */ - acm_start_wb(acm, acm->putbuffer); - acm->putbuffer = NULL; - } } stat = acm_start_wb(acm, wb); @@ -804,66 +793,6 @@ static int acm_tty_write(struct tty_struct *tty, return count; } -static void acm_tty_flush_chars(struct tty_struct *tty) -{ - struct acm *acm = tty->driver_data; - struct acm_wb *cur; - int err; - unsigned long flags; - - spin_lock_irqsave(&acm->write_lock, flags); - - cur = acm->putbuffer; - if (!cur) /* nothing to do */ - goto out; - - acm->putbuffer = NULL; - err = usb_autopm_get_interface_async(acm->control); - if (err < 0) { - cur->use = 0; - acm->putbuffer = cur; - goto out; - } - - if (acm->susp_count) - usb_anchor_urb(cur->urb, &acm->delayed); - else - acm_start_wb(acm, cur); -out: - spin_unlock_irqrestore(&acm->write_lock, flags); - return; -} - -static int acm_tty_put_char(struct tty_struct *tty, unsigned char ch) -{ - struct acm *acm = tty->driver_data; - struct acm_wb *cur; - int wbn; - unsigned long flags; - -overflow: - cur = acm->putbuffer; - if (!cur) { - spin_lock_irqsave(&acm->write_lock, flags); - wbn = acm_wb_alloc(acm); - if (wbn >= 0) { - cur = &acm->wb[wbn]; - acm->putbuffer = cur; - } - spin_unlock_irqrestore(&acm->write_lock, flags); - if (!cur) - return 0; - } - - if (cur->len == acm->writesize) { - acm_tty_flush_chars(tty); - goto overflow; - } - - cur->buf[cur->len++] = ch; - return 1; -} - static int acm_tty_write_room(struct tty_struct *tty) { struct acm *acm = tty->driver_data; @@ -1987,8 +1916,6 @@ static const struct tty_operations acm_ops = { .cleanup = acm_tty_cleanup, .hangup = acm_tty_hangup, .write = acm_tty_write, - .put_char = acm_tty_put_char, - .flush_chars = acm_tty_flush_chars, .write_room = acm_tty_write_room, .ioctl = acm_tty_ioctl, .throttle = acm_tty_throttle, diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index eacc116e83da..ca06b20d7af9 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -96,7 +96,6 @@ struct acm { unsigned long read_urbs_free; struct urb *read_urbs[ACM_NR]; struct acm_rb read_buffers[ACM_NR]; - struct acm_wb *putbuffer; /* for acm_tty_put_char() */ int rx_buflimit; spinlock_t read_lock; u8 *notification_buffer; /* to reassemble fragmented notifications */ diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index bec581fb7c63..656d247819c9 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -460,7 +460,7 @@ static int service_outstanding_interrupt(struct wdm_device *desc) set_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irq(&desc->iuspin); - rv = usb_submit_urb(desc->response, GFP_KERNEL); + rv = usb_submit_urb(desc->response, GFP_ATOMIC); spin_lock_irq(&desc->iuspin); if (rv) { dev_err(&desc->intf->dev, diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index 50a2362ed3ea..48277bbc15e4 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -246,6 +246,31 @@ int of_usb_update_otg_caps(struct device_node *np, } EXPORT_SYMBOL_GPL(of_usb_update_otg_caps); +/** + * usb_of_get_companion_dev - Find the companion device + * @dev: the device pointer to find a companion + * + * Find the companion device from platform bus. + * + * Takes a reference to the returned struct device which needs to be dropped + * after use. + * + * Return: On success, a pointer to the companion device, %NULL on failure. + */ +struct device *usb_of_get_companion_dev(struct device *dev) +{ + struct device_node *node; + struct platform_device *pdev = NULL; + + node = of_parse_phandle(dev->of_node, "companion", 0); + if (node) + pdev = of_find_device_by_node(node); + + of_node_put(node); + + return pdev ? &pdev->dev : NULL; +} +EXPORT_SYMBOL_GPL(usb_of_get_companion_dev); #endif MODULE_LICENSE("GPL"); diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 66fe1b78d952..03432467b05f 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -515,8 +515,6 @@ static int resume_common(struct device *dev, int event) event == PM_EVENT_RESTORE); if (retval) { dev_err(dev, "PCI post-resume error %d!\n", retval); - if (hcd->shared_hcd) - usb_hc_died(hcd->shared_hcd); usb_hc_died(hcd); } } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 228672f2c4a1..bfa5eda0cc26 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1341,6 +1341,11 @@ void usb_enable_interface(struct usb_device *dev, * is submitted that needs that bandwidth. Some other operating systems * allocate bandwidth early, when a configuration is chosen. * + * xHCI reserves bandwidth and configures the alternate setting in + * usb_hcd_alloc_bandwidth(). If it fails the original interface altsetting + * may be disabled. Drivers cannot rely on any particular alternate + * setting being in effect after a failure. + * * This call is synchronous, and may not be used in an interrupt context. * Also, drivers must not change altsettings while urbs are scheduled for * endpoints in that interface; all such urbs must first be completed @@ -1376,6 +1381,12 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate) alternate); return -EINVAL; } + /* + * usb3 hosts configure the interface in usb_hcd_alloc_bandwidth, + * including freeing dropped endpoint ring buffers. + * Make sure the interface endpoints are flushed before that + */ + usb_disable_interface(dev, iface, false); /* Make sure we have enough bandwidth for this alternate interface. * Remove the current alt setting and add the new alt setting. diff --git a/drivers/usb/core/of.c b/drivers/usb/core/of.c index fd77442c2d12..651708d8c908 100644 --- a/drivers/usb/core/of.c +++ b/drivers/usb/core/of.c @@ -105,29 +105,3 @@ usb_of_get_interface_node(struct usb_device *udev, u8 config, u8 ifnum) return NULL; } EXPORT_SYMBOL_GPL(usb_of_get_interface_node); - -/** - * usb_of_get_companion_dev - Find the companion device - * @dev: the device pointer to find a companion - * - * Find the companion device from platform bus. - * - * Takes a reference to the returned struct device which needs to be dropped - * after use. - * - * Return: On success, a pointer to the companion device, %NULL on failure. - */ -struct device *usb_of_get_companion_dev(struct device *dev) -{ - struct device_node *node; - struct platform_device *pdev = NULL; - - node = of_parse_phandle(dev->of_node, "companion", 0); - if (node) - pdev = of_find_device_by_node(node); - - of_node_put(node); - - return pdev ? &pdev->dev : NULL; -} -EXPORT_SYMBOL_GPL(usb_of_get_companion_dev); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 097057d2eacf..e77dfe5ed5ec 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -178,6 +178,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* CBM - Flash disk */ { USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME }, + /* WORLDE Controller KS49 or Prodipe MIDI 49C USB controller */ + { USB_DEVICE(0x0218, 0x0201), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* WORLDE easy key (easykey.25) MIDI controller */ { USB_DEVICE(0x0218, 0x0401), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -406,6 +410,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2040, 0x7200), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* DJI CineSSD */ + { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 9a53a58e676e..577642895b57 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -412,8 +412,6 @@ static int dwc2_driver_probe(struct platform_device *dev) dev_dbg(&dev->dev, "mapped PA %08lx to VA %p\n", (unsigned long)res->start, hsotg->regs); - hsotg->needs_byte_swap = dwc2_check_core_endianness(hsotg); - retval = dwc2_lowlevel_hw_init(hsotg); if (retval) return retval; @@ -438,6 +436,8 @@ static int dwc2_driver_probe(struct platform_device *dev) if (retval) return retval; + hsotg->needs_byte_swap = dwc2_check_core_endianness(hsotg); + retval = dwc2_get_dr_mode(hsotg); if (retval) goto error; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 40bf9e0bbc59..4c2771c5e727 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -180,8 +180,7 @@ static int dwc3_of_simple_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM -static int dwc3_of_simple_runtime_suspend(struct device *dev) +static int __maybe_unused dwc3_of_simple_runtime_suspend(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); int i; @@ -192,7 +191,7 @@ static int dwc3_of_simple_runtime_suspend(struct device *dev) return 0; } -static int dwc3_of_simple_runtime_resume(struct device *dev) +static int __maybe_unused dwc3_of_simple_runtime_resume(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); int ret; @@ -210,7 +209,7 @@ static int dwc3_of_simple_runtime_resume(struct device *dev) return 0; } -static int dwc3_of_simple_suspend(struct device *dev) +static int __maybe_unused dwc3_of_simple_suspend(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); @@ -220,7 +219,7 @@ static int dwc3_of_simple_suspend(struct device *dev) return 0; } -static int dwc3_of_simple_resume(struct device *dev) +static int __maybe_unused dwc3_of_simple_resume(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); @@ -229,7 +228,6 @@ static int dwc3_of_simple_resume(struct device *dev) return 0; } -#endif static const struct dev_pm_ops dwc3_of_simple_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(dwc3_of_simple_suspend, dwc3_of_simple_resume) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 5edd79470368..1286076a8890 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -85,8 +85,8 @@ static int dwc3_byt_enable_ulpi_refclock(struct pci_dev *pci) u32 value; reg = pcim_iomap(pci, GP_RWBAR, 0); - if (IS_ERR(reg)) - return PTR_ERR(reg); + if (!reg) + return -ENOMEM; value = readl(reg + GP_RWREG1); if (!(value & GP_RWREG1_ULPI_REFCLK_DISABLE)) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 032ea7d709ba..2b53194081ba 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -473,7 +473,6 @@ static int dwc3_gadget_set_xfer_resource(struct dwc3_ep *dep) /** * dwc3_gadget_start_config - configure ep resources - * @dwc: pointer to our controller context structure * @dep: endpoint that is being enabled * * Issue a %DWC3_DEPCMD_DEPSTARTCFG command to @dep. After the command's diff --git a/drivers/usb/gadget/udc/fotg210-udc.c b/drivers/usb/gadget/udc/fotg210-udc.c index 53a48f561458..587c5037ff07 100644 --- a/drivers/usb/gadget/udc/fotg210-udc.c +++ b/drivers/usb/gadget/udc/fotg210-udc.c @@ -1063,12 +1063,15 @@ static const struct usb_gadget_ops fotg210_gadget_ops = { static int fotg210_udc_remove(struct platform_device *pdev) { struct fotg210_udc *fotg210 = platform_get_drvdata(pdev); + int i; usb_del_gadget_udc(&fotg210->gadget); iounmap(fotg210->reg); free_irq(platform_get_irq(pdev, 0), fotg210); fotg210_ep_free_request(&fotg210->ep[0]->ep, fotg210->ep0_req); + for (i = 0; i < FOTG210_MAX_NUM_EP; i++) + kfree(fotg210->ep[i]); kfree(fotg210); return 0; @@ -1099,7 +1102,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) /* initialize udc */ fotg210 = kzalloc(sizeof(struct fotg210_udc), GFP_KERNEL); if (fotg210 == NULL) - goto err_alloc; + goto err; for (i = 0; i < FOTG210_MAX_NUM_EP; i++) { _ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL); @@ -1111,7 +1114,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) fotg210->reg = ioremap(res->start, resource_size(res)); if (fotg210->reg == NULL) { pr_err("ioremap error.\n"); - goto err_map; + goto err_alloc; } spin_lock_init(&fotg210->lock); @@ -1159,7 +1162,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) fotg210->ep0_req = fotg210_ep_alloc_request(&fotg210->ep[0]->ep, GFP_KERNEL); if (fotg210->ep0_req == NULL) - goto err_req; + goto err_map; fotg210_init(fotg210); @@ -1187,12 +1190,14 @@ err_req: fotg210_ep_free_request(&fotg210->ep[0]->ep, fotg210->ep0_req); err_map: - if (fotg210->reg) - iounmap(fotg210->reg); + iounmap(fotg210->reg); err_alloc: + for (i = 0; i < FOTG210_MAX_NUM_EP; i++) + kfree(fotg210->ep[i]); kfree(fotg210); +err: return ret; } diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index 318246d8b2e2..b02ab2a8d927 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -1545,11 +1545,14 @@ static int net2280_pullup(struct usb_gadget *_gadget, int is_on) writel(tmp | BIT(USB_DETECT_ENABLE), &dev->usb->usbctl); } else { writel(tmp & ~BIT(USB_DETECT_ENABLE), &dev->usb->usbctl); - stop_activity(dev, dev->driver); + stop_activity(dev, NULL); } spin_unlock_irqrestore(&dev->lock, flags); + if (!is_on && dev->driver) + dev->driver->disconnect(&dev->gadget); + return 0; } @@ -2466,8 +2469,11 @@ static void stop_activity(struct net2280 *dev, struct usb_gadget_driver *driver) nuke(&dev->ep[i]); /* report disconnect; the driver is already quiesced */ - if (driver) + if (driver) { + spin_unlock(&dev->lock); driver->disconnect(&dev->gadget); + spin_lock(&dev->lock); + } usb_reinit(dev); } @@ -3341,6 +3347,8 @@ next_endpoints: BIT(PCI_RETRY_ABORT_INTERRUPT)) static void handle_stat1_irqs(struct net2280 *dev, u32 stat) +__releases(dev->lock) +__acquires(dev->lock) { struct net2280_ep *ep; u32 tmp, num, mask, scratch; @@ -3381,12 +3389,14 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) if (disconnect || reset) { stop_activity(dev, dev->driver); ep0_start(dev); + spin_unlock(&dev->lock); if (reset) usb_gadget_udc_reset (&dev->gadget, dev->driver); else (dev->driver->disconnect) (&dev->gadget); + spin_lock(&dev->lock); return; } } @@ -3405,6 +3415,7 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) tmp = BIT(SUSPEND_REQUEST_CHANGE_INTERRUPT); if (stat & tmp) { writel(tmp, &dev->regs->irqstat1); + spin_unlock(&dev->lock); if (stat & BIT(SUSPEND_REQUEST_INTERRUPT)) { if (dev->driver->suspend) dev->driver->suspend(&dev->gadget); @@ -3415,6 +3426,7 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) dev->driver->resume(&dev->gadget); /* at high speed, note erratum 0133 */ } + spin_lock(&dev->lock); stat &= ~tmp; } diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 1f879b3f2c96..e1656f361e08 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -812,12 +812,15 @@ static void usb3_irq_epc_int_1_speed(struct renesas_usb3 *usb3) switch (speed) { case USB_STA_SPEED_SS: usb3->gadget.speed = USB_SPEED_SUPER; + usb3->gadget.ep0->maxpacket = USB3_EP0_SS_MAX_PACKET_SIZE; break; case USB_STA_SPEED_HS: usb3->gadget.speed = USB_SPEED_HIGH; + usb3->gadget.ep0->maxpacket = USB3_EP0_HSFS_MAX_PACKET_SIZE; break; case USB_STA_SPEED_FS: usb3->gadget.speed = USB_SPEED_FULL; + usb3->gadget.ep0->maxpacket = USB3_EP0_HSFS_MAX_PACKET_SIZE; break; default: usb3->gadget.speed = USB_SPEED_UNKNOWN; @@ -2513,7 +2516,7 @@ static int renesas_usb3_init_ep(struct renesas_usb3 *usb3, struct device *dev, /* for control pipe */ usb3->gadget.ep0 = &usb3_ep->ep; usb_ep_set_maxpacket_limit(&usb3_ep->ep, - USB3_EP0_HSFS_MAX_PACKET_SIZE); + USB3_EP0_SS_MAX_PACKET_SIZE); usb3_ep->ep.caps.type_control = true; usb3_ep->ep.caps.dir_in = true; usb3_ep->ep.caps.dir_out = true; diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index 072bd5d5738e..5b8a3d9530c4 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -2555,7 +2555,7 @@ static int u132_get_frame(struct usb_hcd *hcd) } else { int frame = 0; dev_err(&u132->platform_dev->dev, "TODO: u132_get_frame\n"); - msleep(100); + mdelay(100); return frame; } } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index ef350c33dc4a..b1f27aa38b10 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1613,6 +1613,10 @@ void xhci_endpoint_copy(struct xhci_hcd *xhci, in_ep_ctx->ep_info2 = out_ep_ctx->ep_info2; in_ep_ctx->deq = out_ep_ctx->deq; in_ep_ctx->tx_info = out_ep_ctx->tx_info; + if (xhci->quirks & XHCI_MTK_HOST) { + in_ep_ctx->reserved[0] = out_ep_ctx->reserved[0]; + in_ep_ctx->reserved[1] = out_ep_ctx->reserved[1]; + } } /* Copy output xhci_slot_ctx to the input xhci_slot_ctx. diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 8dc77e34a859..94e939249b2b 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -153,7 +153,7 @@ static int xhci_plat_probe(struct platform_device *pdev) { const struct xhci_plat_priv *priv_match; const struct hc_driver *driver; - struct device *sysdev; + struct device *sysdev, *tmpdev; struct xhci_hcd *xhci; struct resource *res; struct usb_hcd *hcd; @@ -273,19 +273,24 @@ static int xhci_plat_probe(struct platform_device *pdev) goto disable_clk; } - if (device_property_read_bool(sysdev, "usb2-lpm-disable")) - xhci->quirks |= XHCI_HW_LPM_DISABLE; + /* imod_interval is the interrupt moderation value in nanoseconds. */ + xhci->imod_interval = 40000; - if (device_property_read_bool(sysdev, "usb3-lpm-capable")) - xhci->quirks |= XHCI_LPM_SUPPORT; + /* Iterate over all parent nodes for finding quirks */ + for (tmpdev = &pdev->dev; tmpdev; tmpdev = tmpdev->parent) { - if (device_property_read_bool(&pdev->dev, "quirk-broken-port-ped")) - xhci->quirks |= XHCI_BROKEN_PORT_PED; + if (device_property_read_bool(tmpdev, "usb2-lpm-disable")) + xhci->quirks |= XHCI_HW_LPM_DISABLE; - /* imod_interval is the interrupt moderation value in nanoseconds. */ - xhci->imod_interval = 40000; - device_property_read_u32(sysdev, "imod-interval-ns", - &xhci->imod_interval); + if (device_property_read_bool(tmpdev, "usb3-lpm-capable")) + xhci->quirks |= XHCI_LPM_SUPPORT; + + if (device_property_read_bool(tmpdev, "quirk-broken-port-ped")) + xhci->quirks |= XHCI_BROKEN_PORT_PED; + + device_property_read_u32(tmpdev, "imod-interval-ns", + &xhci->imod_interval); + } hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0); if (IS_ERR(hcd->usb_phy)) { diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 61f48b17e57b..0420eefa647a 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -37,6 +37,21 @@ static unsigned long long quirks; module_param(quirks, ullong, S_IRUGO); MODULE_PARM_DESC(quirks, "Bit flags for quirks to be enabled as default"); +static bool td_on_ring(struct xhci_td *td, struct xhci_ring *ring) +{ + struct xhci_segment *seg = ring->first_seg; + + if (!td || !td->start_seg) + return false; + do { + if (seg == td->start_seg) + return true; + seg = seg->next; + } while (seg && seg != ring->first_seg); + + return false; +} + /* TODO: copied from ehci-hcd.c - can this be refactored? */ /* * xhci_handshake - spin reading hc until handshake completes or fails @@ -1571,6 +1586,21 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) goto done; } + /* + * check ring is not re-allocated since URB was enqueued. If it is, then + * make sure none of the ring related pointers in this URB private data + * are touched, such as td_list, otherwise we overwrite freed data + */ + if (!td_on_ring(&urb_priv->td[0], ep_ring)) { + xhci_err(xhci, "Canceled URB td not found on endpoint ring"); + for (i = urb_priv->num_tds_done; i < urb_priv->num_tds; i++) { + td = &urb_priv->td[i]; + if (!list_empty(&td->cancelled_td_list)) + list_del_init(&td->cancelled_td_list); + } + goto err_giveback; + } + if (xhci->xhc_state & XHCI_STATE_HALTED) { xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "HC halted, freeing TD manually."); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index 82f220631bd7..b5d661644263 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -369,7 +369,7 @@ static unsigned char parport_uss720_frob_control(struct parport *pp, unsigned ch mask &= 0x0f; val &= 0x0f; d = (priv->reg[1] & (~mask)) ^ val; - if (set_1284_register(pp, 2, d, GFP_KERNEL)) + if (set_1284_register(pp, 2, d, GFP_ATOMIC)) return 0; priv->reg[1] = d; return d & 0xf; @@ -379,7 +379,7 @@ static unsigned char parport_uss720_read_status(struct parport *pp) { unsigned char ret; - if (get_1284_register(pp, 1, &ret, GFP_KERNEL)) + if (get_1284_register(pp, 1, &ret, GFP_ATOMIC)) return 0; return ret & 0xf8; } diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 3be40eaa1ac9..6d9fd5f64903 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -413,6 +413,9 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count, spin_unlock_irqrestore(&dev->lock, flags); mutex_unlock(&dev->io_mutex); + if (WARN_ON_ONCE(len >= sizeof(in_buffer))) + return -EIO; + return simple_read_from_buffer(buffer, count, ppos, in_buffer, len); } @@ -421,13 +424,13 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer, { struct usb_yurex *dev; int i, set = 0, retval = 0; - char buffer[16]; + char buffer[16 + 1]; char *data = buffer; unsigned long long c, c2 = 0; signed long timeout = 0; DEFINE_WAIT(wait); - count = min(sizeof(buffer), count); + count = min(sizeof(buffer) - 1, count); dev = file->private_data; /* verify that we actually have some data to write */ @@ -446,6 +449,7 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer, retval = -EFAULT; goto error; } + buffer[count] = 0; memset(dev->cntl_buffer, CMD_PADDING, YUREX_BUF_SIZE); switch (buffer[0]) { diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c index eecfd0671362..d045d8458f81 100644 --- a/drivers/usb/mtu3/mtu3_core.c +++ b/drivers/usb/mtu3/mtu3_core.c @@ -107,8 +107,12 @@ static int mtu3_device_enable(struct mtu3 *mtu) (SSUSB_U2_PORT_DIS | SSUSB_U2_PORT_PDN | SSUSB_U2_PORT_HOST_SEL)); - if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) + if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) { mtu3_setbits(ibase, SSUSB_U2_CTRL(0), SSUSB_U2_PORT_OTG_SEL); + if (mtu->is_u3_ip) + mtu3_setbits(ibase, SSUSB_U3_CTRL(0), + SSUSB_U3_PORT_DUAL_MODE); + } return ssusb_check_clocks(mtu->ssusb, check_clk); } diff --git a/drivers/usb/mtu3/mtu3_hw_regs.h b/drivers/usb/mtu3/mtu3_hw_regs.h index 6ee371478d89..a45bb253939f 100644 --- a/drivers/usb/mtu3/mtu3_hw_regs.h +++ b/drivers/usb/mtu3/mtu3_hw_regs.h @@ -459,6 +459,7 @@ /* U3D_SSUSB_U3_CTRL_0P */ #define SSUSB_U3_PORT_SSP_SPEED BIT(9) +#define SSUSB_U3_PORT_DUAL_MODE BIT(7) #define SSUSB_U3_PORT_HOST_SEL BIT(2) #define SSUSB_U3_PORT_PDN BIT(1) #define SSUSB_U3_PORT_DIS BIT(0) diff --git a/drivers/usb/serial/io_ti.h b/drivers/usb/serial/io_ti.h index e53c68261017..9bbcee37524e 100644 --- a/drivers/usb/serial/io_ti.h +++ b/drivers/usb/serial/io_ti.h @@ -173,7 +173,7 @@ struct ump_interrupt { } __attribute__((packed)); -#define TIUMP_GET_PORT_FROM_CODE(c) (((c) >> 4) - 3) +#define TIUMP_GET_PORT_FROM_CODE(c) (((c) >> 6) & 0x01) #define TIUMP_GET_FUNC_FROM_CODE(c) ((c) & 0x0f) #define TIUMP_INTERRUPT_CODE_LSR 0x03 #define TIUMP_INTERRUPT_CODE_MSR 0x04 diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index 3010878f7f8e..e3c5832337e0 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -1119,7 +1119,7 @@ static void ti_break(struct tty_struct *tty, int break_state) static int ti_get_port_from_code(unsigned char code) { - return (code >> 4) - 3; + return (code >> 6) & 0x01; } static int ti_get_func_from_code(unsigned char code) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index c267f2812a04..e227bb5b794f 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -376,6 +376,15 @@ static int queuecommand_lck(struct scsi_cmnd *srb, return 0; } + if ((us->fflags & US_FL_NO_ATA_1X) && + (srb->cmnd[0] == ATA_12 || srb->cmnd[0] == ATA_16)) { + memcpy(srb->sense_buffer, usb_stor_sense_invalidCDB, + sizeof(usb_stor_sense_invalidCDB)); + srb->result = SAM_STAT_CHECK_CONDITION; + done(srb); + return 0; + } + /* enqueue the command and wake up the control thread */ srb->scsi_done = done; us->srb = srb; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 9e9de5452860..1f7b401c4d04 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -842,6 +842,27 @@ static int uas_slave_configure(struct scsi_device *sdev) sdev->skip_ms_page_8 = 1; sdev->wce_default_on = 1; } + + /* + * Some disks return the total number of blocks in response + * to READ CAPACITY rather than the highest block number. + * If this device makes that mistake, tell the sd driver. + */ + if (devinfo->flags & US_FL_FIX_CAPACITY) + sdev->fix_capacity = 1; + + /* + * Some devices don't like MODE SENSE with page=0x3f, + * which is the command used for checking if a device + * is write-protected. Now that we tell the sd driver + * to do a 192-byte transfer with this command the + * majority of devices work fine, but a few still can't + * handle it. The sd driver will simply assume those + * devices are write-enabled. + */ + if (devinfo->flags & US_FL_NO_WP_DETECT) + sdev->skip_ms_page_3f = 1; + scsi_change_queue_depth(sdev, devinfo->qdepth - 2); return 0; } diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 22fcfccf453a..f7f83b21dc74 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2288,6 +2288,13 @@ UNUSUAL_DEV( 0x2735, 0x100b, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_GO_SLOW ), +/* Reported-by: Tim Anderson <tsa@biglakesoftware.com> */ +UNUSUAL_DEV( 0x2ca3, 0x0031, 0x0000, 0x9999, + "DJI", + "CineSSD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_ATA_1X), + /* * Reported by Frederic Marchal <frederic.marchal@wowcompany.com> * Mio Moov 330 diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 95a2b10127db..76299b6ff06d 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -255,12 +255,13 @@ EXPORT_SYMBOL_GPL(typec_altmode_unregister_driver); /* API for the port drivers */ /** - * typec_match_altmode - Match SVID to an array of alternate modes + * typec_match_altmode - Match SVID and mode to an array of alternate modes * @altmodes: Array of alternate modes - * @n: Number of elements in the array, or -1 for NULL termiated arrays + * @n: Number of elements in the array, or -1 for NULL terminated arrays * @svid: Standard or Vendor ID to match with + * @mode: Mode to match with * - * Return pointer to an alternate mode with SVID mathing @svid, or NULL when no + * Return pointer to an alternate mode with SVID matching @svid, or NULL when no * match is found. */ struct typec_altmode *typec_match_altmode(struct typec_altmode **altmodes, diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index c202975f8097..e61dffb27a0c 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1484,7 +1484,6 @@ EXPORT_SYMBOL_GPL(typec_set_mode); * typec_port_register_altmode - Register USB Type-C Port Alternate Mode * @port: USB Type-C Port that supports the alternate mode * @desc: Description of the alternate mode - * @drvdata: Private pointer to driver specific info * * This routine is used to register an alternate mode that @port is capable of * supporting. diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index b459edfacff3..90d387b50ab7 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -79,15 +79,19 @@ config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT This value is used to allocate enough space in internal tables needed for physical memory administration. -config XEN_SCRUB_PAGES - bool "Scrub pages before returning them to system" +config XEN_SCRUB_PAGES_DEFAULT + bool "Scrub pages before returning them to system by default" depends on XEN_BALLOON default y help Scrub pages before returning them to the system for reuse by other domains. This makes sure that any confidential data is not accidentally visible to other domains. Is it more - secure, but slightly less efficient. + secure, but slightly less efficient. This can be controlled with + xen_scrub_pages=0 parameter and + /sys/devices/system/xen_memory/xen_memory0/scrub_pages. + This option only sets the default value. + If in doubt, say yes. config XEN_DEV_EVTCHN diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index d4265c8ebb22..b1357aa4bc55 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -19,15 +19,16 @@ static void enable_hotplug_cpu(int cpu) static void disable_hotplug_cpu(int cpu) { - if (cpu_online(cpu)) { - lock_device_hotplug(); + if (!cpu_is_hotpluggable(cpu)) + return; + lock_device_hotplug(); + if (cpu_online(cpu)) device_offline(get_cpu_device(cpu)); - unlock_device_hotplug(); - } - if (cpu_present(cpu)) + if (!cpu_online(cpu) && cpu_present(cpu)) { xen_arch_unregister_cpu(cpu); - - set_cpu_present(cpu, false); + set_cpu_present(cpu, false); + } + unlock_device_hotplug(); } static int vcpu_online(unsigned int cpu) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 08e4af04d6f2..e6c1934734b7 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -138,7 +138,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq) clear_evtchn_to_irq_row(row); } - evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)] = irq; + evtchn_to_irq[row][col] = irq; return 0; } diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 57390c7666e5..b0b02a501167 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -492,12 +492,19 @@ static bool in_range(struct gntdev_grant_map *map, return true; } -static void unmap_if_in_range(struct gntdev_grant_map *map, - unsigned long start, unsigned long end) +static int unmap_if_in_range(struct gntdev_grant_map *map, + unsigned long start, unsigned long end, + bool blockable) { unsigned long mstart, mend; int err; + if (!in_range(map, start, end)) + return 0; + + if (!blockable) + return -EAGAIN; + mstart = max(start, map->vma->vm_start); mend = min(end, map->vma->vm_end); pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n", @@ -508,6 +515,8 @@ static void unmap_if_in_range(struct gntdev_grant_map *map, (mstart - map->vma->vm_start) >> PAGE_SHIFT, (mend - mstart) >> PAGE_SHIFT); WARN_ON(err); + + return 0; } static int mn_invl_range_start(struct mmu_notifier *mn, @@ -519,25 +528,20 @@ static int mn_invl_range_start(struct mmu_notifier *mn, struct gntdev_grant_map *map; int ret = 0; - /* TODO do we really need a mutex here? */ if (blockable) mutex_lock(&priv->lock); else if (!mutex_trylock(&priv->lock)) return -EAGAIN; list_for_each_entry(map, &priv->maps, next) { - if (in_range(map, start, end)) { - ret = -EAGAIN; + ret = unmap_if_in_range(map, start, end, blockable); + if (ret) goto out_unlock; - } - unmap_if_in_range(map, start, end); } list_for_each_entry(map, &priv->freeable_maps, next) { - if (in_range(map, start, end)) { - ret = -EAGAIN; + ret = unmap_if_in_range(map, start, end, blockable); + if (ret) goto out_unlock; - } - unmap_if_in_range(map, start, end); } out_unlock: diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index c93d8ef8df34..5bb01a62f214 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -280,9 +280,11 @@ static void sysrq_handler(struct xenbus_watch *watch, const char *path, /* * The Xenstore watch fires directly after registering it and * after a suspend/resume cycle. So ENOENT is no error but - * might happen in those cases. + * might happen in those cases. ERANGE is observed when we get + * an empty value (''), this happens when we acknowledge the + * request by writing '\0' below. */ - if (err != -ENOENT) + if (err != -ENOENT && err != -ERANGE) pr_err("Error %d reading sysrq code in control/sysrq\n", err); xenbus_transaction_end(xbt, 1); diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c index 084799c6180e..3782cf070338 100644 --- a/drivers/xen/mem-reservation.c +++ b/drivers/xen/mem-reservation.c @@ -14,6 +14,10 @@ #include <xen/interface/memory.h> #include <xen/mem-reservation.h> +#include <linux/moduleparam.h> + +bool __read_mostly xen_scrub_pages = IS_ENABLED(CONFIG_XEN_SCRUB_PAGES_DEFAULT); +core_param(xen_scrub_pages, xen_scrub_pages, bool, 0); /* * Use one extent per PAGE_SIZE to avoid to break down the page into diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index 294f35ce9e46..63c1494a8d73 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -44,6 +44,7 @@ #include <xen/xenbus.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/mem-reservation.h> #define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10)) @@ -137,6 +138,7 @@ static DEVICE_ULONG_ATTR(schedule_delay, 0444, balloon_stats.schedule_delay); static DEVICE_ULONG_ATTR(max_schedule_delay, 0644, balloon_stats.max_schedule_delay); static DEVICE_ULONG_ATTR(retry_count, 0444, balloon_stats.retry_count); static DEVICE_ULONG_ATTR(max_retry_count, 0644, balloon_stats.max_retry_count); +static DEVICE_BOOL_ATTR(scrub_pages, 0644, xen_scrub_pages); static ssize_t show_target_kb(struct device *dev, struct device_attribute *attr, char *buf) @@ -203,6 +205,7 @@ static struct attribute *balloon_attrs[] = { &dev_attr_max_schedule_delay.attr.attr, &dev_attr_retry_count.attr.attr, &dev_attr_max_retry_count.attr.attr, + &dev_attr_scrub_pages.attr.attr, NULL }; diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 35c83fe7dba0..abcd78e332fe 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -6,6 +6,7 @@ config CIFS select CRYPTO_MD4 select CRYPTO_MD5 select CRYPTO_SHA256 + select CRYPTO_SHA512 select CRYPTO_CMAC select CRYPTO_HMAC select CRYPTO_ARC4 diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index dc2f4cf08fe9..5657b79dbc99 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -601,10 +601,15 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) } count = 0; + /* + * We know that all the name entries in the protocols array + * are short (< 16 bytes anyway) and are NUL terminated. + */ for (i = 0; i < CIFS_NUM_PROT; i++) { - strncpy(pSMB->DialectsArray+count, protocols[i].name, 16); - count += strlen(protocols[i].name) + 1; - /* null at end of source and target buffers anyway */ + size_t len = strlen(protocols[i].name) + 1; + + memcpy(pSMB->DialectsArray+count, protocols[i].name, len); + count += len; } inc_rfc1001_len(pSMB, count); pSMB->ByteCount = cpu_to_le16(count); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index dacb2c05674c..6926685e513c 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -402,9 +402,17 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) (struct smb_com_transaction_change_notify_rsp *)buf; struct file_notify_information *pnotify; __u32 data_offset = 0; + size_t len = srv->total_read - sizeof(pSMBr->hdr.smb_buf_length); + if (get_bcc(buf) > sizeof(struct file_notify_information)) { data_offset = le32_to_cpu(pSMBr->DataOffset); + if (data_offset > + len - sizeof(struct file_notify_information)) { + cifs_dbg(FYI, "invalid data_offset %u\n", + data_offset); + return true; + } pnotify = (struct file_notify_information *) ((char *)&pSMBr->hdr.Protocol + data_offset); cifs_dbg(FYI, "dnotify on %s Action: 0x%x\n", diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index eeab81c9452f..e169e1a5fd35 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -376,8 +376,15 @@ static char *nxt_dir_entry(char *old_entry, char *end_of_smb, int level) new_entry = old_entry + sizeof(FIND_FILE_STANDARD_INFO) + pfData->FileNameLength; - } else - new_entry = old_entry + le32_to_cpu(pDirInfo->NextEntryOffset); + } else { + u32 next_offset = le32_to_cpu(pDirInfo->NextEntryOffset); + + if (old_entry + next_offset < old_entry) { + cifs_dbg(VFS, "invalid offset %u\n", next_offset); + return NULL; + } + new_entry = old_entry + next_offset; + } cifs_dbg(FYI, "new entry %p old entry %p\n", new_entry, old_entry); /* validate that new_entry is not past end of SMB */ if (new_entry >= end_of_smb) { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index c08acfc77abc..f54d07bda067 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2459,14 +2459,14 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, /* We check for obvious errors in the output buffer length and offset */ if (*plen == 0) goto ioctl_exit; /* server returned no data */ - else if (*plen > 0xFF00) { + else if (*plen > rsp_iov.iov_len || *plen > 0xFF00) { cifs_dbg(VFS, "srv returned invalid ioctl length: %d\n", *plen); *plen = 0; rc = -EIO; goto ioctl_exit; } - if (rsp_iov.iov_len < le32_to_cpu(rsp->OutputOffset) + *plen) { + if (rsp_iov.iov_len - *plen < le32_to_cpu(rsp->OutputOffset)) { cifs_dbg(VFS, "Malformed ioctl resp: len %d offset %d\n", *plen, le32_to_cpu(rsp->OutputOffset)); *plen = 0; @@ -3577,33 +3577,38 @@ num_entries(char *bufstart, char *end_of_buf, char **lastentry, size_t size) int len; unsigned int entrycount = 0; unsigned int next_offset = 0; - FILE_DIRECTORY_INFO *entryptr; + char *entryptr; + FILE_DIRECTORY_INFO *dir_info; if (bufstart == NULL) return 0; - entryptr = (FILE_DIRECTORY_INFO *)bufstart; + entryptr = bufstart; while (1) { - entryptr = (FILE_DIRECTORY_INFO *) - ((char *)entryptr + next_offset); - - if ((char *)entryptr + size > end_of_buf) { + if (entryptr + next_offset < entryptr || + entryptr + next_offset > end_of_buf || + entryptr + next_offset + size > end_of_buf) { cifs_dbg(VFS, "malformed search entry would overflow\n"); break; } - len = le32_to_cpu(entryptr->FileNameLength); - if ((char *)entryptr + len + size > end_of_buf) { + entryptr = entryptr + next_offset; + dir_info = (FILE_DIRECTORY_INFO *)entryptr; + + len = le32_to_cpu(dir_info->FileNameLength); + if (entryptr + len < entryptr || + entryptr + len > end_of_buf || + entryptr + len + size > end_of_buf) { cifs_dbg(VFS, "directory entry name would overflow frame end of buf %p\n", end_of_buf); break; } - *lastentry = (char *)entryptr; + *lastentry = entryptr; entrycount++; - next_offset = le32_to_cpu(entryptr->NextEntryOffset); + next_offset = le32_to_cpu(dir_info->NextEntryOffset); if (!next_offset) break; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index e2902d394f1b..f93f9881ec18 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -76,7 +76,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; else if (unlikely(((char *) de - buf) + rlen > size)) - error_msg = "directory entry across range"; + error_msg = "directory entry overrun"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; @@ -85,18 +85,16 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, - "bad entry in directory: %s - offset=%u(%u), " - "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % size), - offset, le32_to_cpu(de->inode), - rlen, de->name_len); + "bad entry in directory: %s - offset=%u, " + "inode=%u, rec_len=%d, name_len=%d, size=%d", + error_msg, offset, le32_to_cpu(de->inode), + rlen, de->name_len, size); else ext4_error_inode(dir, function, line, bh->b_blocknr, - "bad entry in directory: %s - offset=%u(%u), " - "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % size), - offset, le32_to_cpu(de->inode), - rlen, de->name_len); + "bad entry in directory: %s - offset=%u, " + "inode=%u, rec_len=%d, name_len=%d, size=%d", + error_msg, offset, le32_to_cpu(de->inode), + rlen, de->name_len, size); return 1; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0f0edd1cd0cd..caff935fbeb8 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -43,6 +43,17 @@ #define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION) #include <linux/fscrypt.h> +#include <linux/compiler.h> + +/* Until this gets included into linux/compiler-gcc.h */ +#ifndef __nonstring +#if defined(GCC_VERSION) && (GCC_VERSION >= 80000) +#define __nonstring __attribute__((nonstring)) +#else +#define __nonstring +#endif +#endif + /* * The fourth extended filesystem constants/structures */ @@ -675,6 +686,9 @@ enum { /* Max physical block we can address w/o extents */ #define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF +/* Max logical block we can support */ +#define EXT4_MAX_LOGICAL_BLOCK 0xFFFFFFFF + /* * Structure of an inode on the disk */ @@ -1226,7 +1240,7 @@ struct ext4_super_block { __le32 s_feature_ro_compat; /* readonly-compatible feature set */ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ /*78*/ char s_volume_name[16]; /* volume name */ -/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ /* * Performance hints. Directory preallocation should only @@ -1277,13 +1291,13 @@ struct ext4_super_block { __le32 s_first_error_time; /* first time an error happened */ __le32 s_first_error_ino; /* inode involved in first error */ __le64 s_first_error_block; /* block involved of first error */ - __u8 s_first_error_func[32]; /* function where the error happened */ + __u8 s_first_error_func[32] __nonstring; /* function where the error happened */ __le32 s_first_error_line; /* line number where error happened */ __le32 s_last_error_time; /* most recent time of an error */ __le32 s_last_error_ino; /* inode involved in last error */ __le32 s_last_error_line; /* line number where error happened */ __le64 s_last_error_block; /* block involved of last error */ - __u8 s_last_error_func[32]; /* function where the error happened */ + __u8 s_last_error_func[32] __nonstring; /* function where the error happened */ #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts) __u8 s_mount_opts[64]; __le32 s_usr_quota_inum; /* inode for tracking user quota */ diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 3543fe80a3c4..7b4736022761 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1753,6 +1753,7 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) { int err, inline_size; struct ext4_iloc iloc; + size_t inline_len; void *inline_pos; unsigned int offset; struct ext4_dir_entry_2 *de; @@ -1780,8 +1781,9 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) goto out; } + inline_len = ext4_get_inline_size(dir); offset = EXT4_INLINE_DOTDOT_SIZE; - while (offset < dir->i_size) { + while (offset < inline_len) { de = ext4_get_inline_entry(dir, &iloc, offset, &inline_pos, &inline_size); if (ext4_check_dir_entry(dir, NULL, de, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d0dd585add6a..d767e993591d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3413,12 +3413,16 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int blkbits = inode->i_blkbits; - unsigned long first_block = offset >> blkbits; - unsigned long last_block = (offset + length - 1) >> blkbits; + unsigned long first_block, last_block; struct ext4_map_blocks map; bool delalloc = false; int ret; + if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) + return -EINVAL; + first_block = offset >> blkbits; + last_block = min_t(loff_t, (offset + length - 1) >> blkbits, + EXT4_MAX_LOGICAL_BLOCK); if (flags & IOMAP_REPORT) { if (ext4_has_inline_data(inode)) { @@ -3948,6 +3952,7 @@ static const struct address_space_operations ext4_dax_aops = { .writepages = ext4_dax_writepages, .direct_IO = noop_direct_IO, .set_page_dirty = noop_set_page_dirty, + .bmap = ext4_bmap, .invalidatepage = noop_invalidatepage, }; @@ -4192,9 +4197,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, return 0; } -static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock) +static void ext4_wait_dax_page(struct ext4_inode_info *ei) { - *did_unlock = true; up_write(&ei->i_mmap_sem); schedule(); down_write(&ei->i_mmap_sem); @@ -4204,14 +4208,12 @@ int ext4_break_layouts(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct page *page; - bool retry; int error; if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem))) return -EINVAL; do { - retry = false; page = dax_layout_busy_page(inode->i_mapping); if (!page) return 0; @@ -4219,8 +4221,8 @@ int ext4_break_layouts(struct inode *inode) error = ___wait_var_event(&page->_refcount, atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE, 0, 0, - ext4_wait_dax_page(ei, &retry)); - } while (error == 0 && retry); + ext4_wait_dax_page(ei)); + } while (error == 0); return error; } @@ -4895,6 +4897,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); + ext4_set_inode_flags(inode); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); if (ext4_has_feature_64bit(sb)) @@ -5041,7 +5044,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) goto bad_inode; } brelse(iloc.bh); - ext4_set_inode_flags(inode); unlock_new_inode(inode); return inode; diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 39b07c2d3384..2305b4374fd3 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -49,7 +49,6 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) */ sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); - mark_buffer_dirty(bh); lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 116ff68c5bd4..377d516c475f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3478,6 +3478,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, int credits; u8 old_file_type; + if (new.inode && new.inode->i_nlink == 0) { + EXT4_ERROR_INODE(new.inode, + "target of rename is already freed"); + return -EFSCORRUPTED; + } + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) && (!projid_eq(EXT4_I(new_dir)->i_projid, EXT4_I(old_dentry->d_inode)->i_projid))) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e5fb38451a73..ebbc663d0798 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -19,6 +19,7 @@ int ext4_resize_begin(struct super_block *sb) { + struct ext4_sb_info *sbi = EXT4_SB(sb); int ret = 0; if (!capable(CAP_SYS_RESOURCE)) @@ -29,7 +30,7 @@ int ext4_resize_begin(struct super_block *sb) * because the user tools have no way of handling this. Probably a * bad time to do it anyways. */ - if (EXT4_SB(sb)->s_sbh->b_blocknr != + if (EXT4_B2C(sbi, sbi->s_sbh->b_blocknr) != le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { ext4_warning(sb, "won't resize using backup superblock at %llu", (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); @@ -1986,6 +1987,26 @@ retry: } } + /* + * Make sure the last group has enough space so that it's + * guaranteed to have enough space for all metadata blocks + * that it might need to hold. (We might not need to store + * the inode table blocks in the last block group, but there + * will be cases where this might be needed.) + */ + if ((ext4_group_first_block_no(sb, n_group) + + ext4_group_overhead_blocks(sb, n_group) + 2 + + sbi->s_itb_per_group + sbi->s_cluster_ratio) >= n_blocks_count) { + n_blocks_count = ext4_group_first_block_no(sb, n_group); + n_group--; + n_blocks_count_retry = 0; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + goto retry; + } + /* extend the last group */ if (n_group == o_group) add = n_blocks_count - o_blocks_count; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5863fd22e90b..1145109968ef 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2145,6 +2145,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); + if (DUMMY_ENCRYPTION_ENABLED(sbi)) + SEQ_OPTS_PUTS("test_dummy_encryption"); ext4_show_quota_options(seq, sb); return 0; @@ -4378,11 +4380,13 @@ no_journal: block = ext4_count_free_clusters(sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); + ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); + ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 34830f6457ea..8220a168282e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1637,6 +1637,14 @@ static void nfs_state_set_delegation(struct nfs4_state *state, write_sequnlock(&state->seqlock); } +static void nfs_state_clear_delegation(struct nfs4_state *state) +{ + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + clear_bit(NFS_DELEGATED_STATE, &state->flags); + write_sequnlock(&state->seqlock); +} + static int update_open_stateid(struct nfs4_state *state, const nfs4_stateid *open_stateid, const nfs4_stateid *delegation, @@ -2145,10 +2153,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_delegation(state); switch (type & (FMODE_READ|FMODE_WRITE)) { case FMODE_READ|FMODE_WRITE: case FMODE_WRITE: @@ -2601,10 +2606,7 @@ static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state, const nfs4_stateid *stateid) { nfs_remove_bad_delegation(state->inode, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_delegation(state); } static void nfs40_clear_delegation_stateid(struct nfs4_state *state) @@ -2672,15 +2674,20 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) delegation = rcu_dereference(NFS_I(state->inode)->delegation); if (delegation == NULL) { rcu_read_unlock(); + nfs_state_clear_delegation(state); return; } nfs4_stateid_copy(&stateid, &delegation->stateid); - if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) || - !test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, - &delegation->flags)) { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + rcu_read_unlock(); + nfs_state_clear_delegation(state); + return; + } + + if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, + &delegation->flags)) { rcu_read_unlock(); - nfs_finish_clear_delegation_stateid(state, &stateid); return; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3df0eb52da1c..40a08cd483f0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1390,6 +1390,8 @@ int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_ if (!nfs4_state_mark_reclaim_nograce(clp, state)) return -EBADF; + nfs_inode_find_delegation_state_and_recover(state->inode, + &state->stateid); dprintk("%s: scheduling stateid recovery for server %s\n", __func__, clp->cl_hostname); nfs4_schedule_state_manager(clp); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index a275fba93170..b1483b303e0b 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -1137,7 +1137,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, TP_fast_assign( __entry->error = error; __entry->fhandle = nfs_fhandle_hash(fhandle); - if (inode != NULL) { + if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; } else { @@ -1194,7 +1194,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, TP_fast_assign( __entry->error = error; __entry->fhandle = nfs_fhandle_hash(fhandle); - if (inode != NULL) { + if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; } else { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index e8f232de484f..7d9a51e6b847 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1740,16 +1740,16 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, return ret; } -static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) +static int pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) { /* * send layoutcommit as it can hold up layoutreturn due to lseg * reference */ pnfs_layoutcommit_inode(lo->plh_inode, false); - return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, + return wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, nfs_wait_bit_killable, - TASK_UNINTERRUPTIBLE); + TASK_KILLABLE); } static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo) @@ -1830,7 +1830,9 @@ pnfs_update_layout(struct inode *ino, } lookup_again: - nfs4_client_recover_expired_lease(clp); + lseg = ERR_PTR(nfs4_client_recover_expired_lease(clp)); + if (IS_ERR(lseg)) + goto out; first = false; spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); @@ -1863,9 +1865,9 @@ lookup_again: if (list_empty(&lo->plh_segs) && atomic_read(&lo->plh_outstanding) != 0) { spin_unlock(&ino->i_lock); - if (wait_var_event_killable(&lo->plh_outstanding, - atomic_read(&lo->plh_outstanding) == 0 - || !list_empty(&lo->plh_segs))) + lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding, + atomic_read(&lo->plh_outstanding))); + if (IS_ERR(lseg) || !list_empty(&lo->plh_segs)) goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); goto lookup_again; @@ -1898,8 +1900,11 @@ lookup_again: if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags)) { spin_unlock(&ino->i_lock); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET, - TASK_UNINTERRUPTIBLE); + lseg = ERR_PTR(wait_on_bit(&lo->plh_flags, + NFS_LAYOUT_FIRST_LAYOUTGET, + TASK_KILLABLE)); + if (IS_ERR(lseg)) + goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); dprintk("%s retrying\n", __func__); goto lookup_again; @@ -1925,7 +1930,8 @@ lookup_again: if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { spin_unlock(&ino->i_lock); dprintk("%s wait for layoutreturn\n", __func__); - if (pnfs_prepare_to_retry_layoutget(lo)) { + lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); + if (!IS_ERR(lseg)) { if (first) pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 32e9282893c9..aeaefd2a551b 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -131,9 +131,6 @@ static int ovl_open(struct inode *inode, struct file *file) if (IS_ERR(realfile)) return PTR_ERR(realfile); - /* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */ - file->f_mapping = realfile->f_mapping; - file->private_data = realfile; return 0; @@ -334,6 +331,25 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len return ret; } +static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + struct fd real; + const struct cred *old_cred; + int ret; + + ret = ovl_real_fdget(file, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(file)->i_sb); + ret = vfs_fadvise(real.file, offset, len, advice); + revert_creds(old_cred); + + fdput(real); + + return ret; +} + static long ovl_real_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -502,6 +518,7 @@ const struct file_operations ovl_file_operations = { .fsync = ovl_fsync, .mmap = ovl_mmap, .fallocate = ovl_fallocate, + .fadvise = ovl_fadvise, .unlocked_ioctl = ovl_ioctl, .compat_ioctl = ovl_compat_ioctl, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index e0bb217c01e2..b6ac545b5a32 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -467,6 +467,10 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return -EOPNOTSUPP; old_cred = ovl_override_creds(inode->i_sb); + + if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(realinode->i_mapping); + err = realinode->i_op->fiemap(realinode, fieinfo, start, len); revert_creds(old_cred); @@ -500,6 +504,11 @@ static const struct inode_operations ovl_special_inode_operations = { .update_time = ovl_update_time, }; +const struct address_space_operations ovl_aops = { + /* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */ + .direct_IO = noop_direct_IO, +}; + /* * It is possible to stack overlayfs instance on top of another * overlayfs instance as lower layer. We need to annonate the @@ -571,6 +580,7 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, case S_IFREG: inode->i_op = &ovl_file_inode_operations; inode->i_fop = &ovl_file_operations; + inode->i_mapping->a_ops = &ovl_aops; break; case S_IFDIR: diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2e0fc93c2c06..30adc9d408a0 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -982,16 +982,6 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) if (err) goto out; - err = -EBUSY; - if (ovl_inuse_trylock(upperpath->dentry)) { - ofs->upperdir_locked = true; - } else if (ofs->config.index) { - pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); - goto out; - } else { - pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); - } - upper_mnt = clone_private_mount(upperpath); err = PTR_ERR(upper_mnt); if (IS_ERR(upper_mnt)) { @@ -1002,6 +992,17 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) /* Don't inherit atime flags */ upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME); ofs->upper_mnt = upper_mnt; + + err = -EBUSY; + if (ovl_inuse_trylock(ofs->upper_mnt->mnt_root)) { + ofs->upperdir_locked = true; + } else if (ofs->config.index) { + pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); + goto out; + } else { + pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); + } + err = 0; out: return err; @@ -1101,8 +1102,10 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) goto out; } + ofs->workbasedir = dget(workpath.dentry); + err = -EBUSY; - if (ovl_inuse_trylock(workpath.dentry)) { + if (ovl_inuse_trylock(ofs->workbasedir)) { ofs->workdir_locked = true; } else if (ofs->config.index) { pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n"); @@ -1111,7 +1114,6 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } - ofs->workbasedir = dget(workpath.dentry); err = ovl_make_workdir(ofs, &workpath); if (err) goto out; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 951a14edcf51..0792595ebcfb 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -429,7 +429,12 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size, vaddr = vmap(pages, page_count, VM_MAP, prot); kfree(pages); - return vaddr; + /* + * Since vmap() uses page granularity, we must add the offset + * into the page here, to get the byte granularity address + * into the mapping to represent the actual "start" location. + */ + return vaddr + offset_in_page(start); } static void *persistent_ram_iomap(phys_addr_t start, size_t size, @@ -448,6 +453,11 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size, else va = ioremap_wc(start, size); + /* + * Since request_mem_region() and ioremap() are byte-granularity + * there is no need handle anything special like we do when the + * vmap() case in persistent_ram_vmap() above. + */ return va; } @@ -468,7 +478,7 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, return -ENOMEM; } - prz->buffer = prz->vaddr + offset_in_page(start); + prz->buffer = prz->vaddr; prz->buffer_size = size - sizeof(struct persistent_ram_buffer); return 0; @@ -515,7 +525,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz) if (prz->vaddr) { if (pfn_valid(prz->paddr >> PAGE_SHIFT)) { - vunmap(prz->vaddr); + /* We must vunmap() at page-granularity. */ + vunmap(prz->vaddr - offset_in_page(prz->paddr)); } else { iounmap(prz->vaddr); release_mem_region(prz->paddr, prz->size); diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 66d1d45fa2e1..d356f802945a 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1026,7 +1026,8 @@ static inline void __iomem *ioremap_wt(phys_addr_t offset, size_t size) #define ioport_map ioport_map static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) { - return PCI_IOBASE + (port & MMIO_UPPER_LIMIT); + port &= IO_SPACE_LIMIT; + return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..6c0b4a1c22ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1763,6 +1763,7 @@ struct file_operations { u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { @@ -3459,4 +3460,8 @@ static inline bool dir_relax_shared(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + #endif /* _LINUX_FS_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cd2bc939efd0..5ed8f6292a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5fe87687664c..d7016dcb245e 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -32,7 +32,7 @@ #define VMACACHE_MASK (VMACACHE_SIZE - 1) struct vmacache { - u32 seqnum; + u64 seqnum; struct vm_area_struct *vmas[VMACACHE_SIZE]; }; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1298a7daa57d..01797cb4587e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -754,6 +754,7 @@ struct tb_service_id { * struct typec_device_id - USB Type-C alternate mode identifiers * @svid: Standard or Vendor ID * @mode: Mode index + * @driver_data: Driver specific data */ struct typec_device_id { __u16 svid; diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..6925828f9f25 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1235,6 +1235,9 @@ void pci_bus_remove_resources(struct pci_bus *bus); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); +/* Temporary until new and working PCI SBR API in place */ +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); + #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5c7f010676a7..47a3441cf4c4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,7 +105,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_DEBUG_VM_VMACACHE VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, - VMACACHE_FULL_FLUSHES, #endif #ifdef CONFIG_SWAP SWAP_RA, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index 3e9a963edd6a..6fce268a4588 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -10,7 +10,6 @@ static inline void vmacache_flush(struct task_struct *tsk) memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } -extern void vmacache_flush_all(struct mm_struct *mm); extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); @@ -24,10 +23,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; - - /* deal with overflows */ - if (unlikely(mm->vmacache_seqnum == 0)) - vmacache_flush_all(mm); } #endif /* __LINUX_VMACACHE_H */ diff --git a/include/net/tls.h b/include/net/tls.h index 8630d28bd951..9f3c4ea9ad6f 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -173,15 +173,14 @@ struct cipher_context { char *rec_seq; }; +union tls_crypto_context { + struct tls_crypto_info info; + struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; +}; + struct tls_context { - union { - struct tls_crypto_info crypto_send; - struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128; - }; - union { - struct tls_crypto_info crypto_recv; - struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128; - }; + union tls_crypto_context crypto_send; + union tls_crypto_context crypto_recv; struct list_head list; struct net_device *netdev; @@ -369,8 +368,8 @@ static inline void tls_fill_prepend(struct tls_context *ctx, * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ buf[0] = record_type; - buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version); - buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version); + buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version); + buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version); /* we can use IV for nonce explicit according to spec */ buf[3] = pkt_len >> 8; buf[4] = pkt_len & 0xFF; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index eeb787b1c53c..f35eb72739c0 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -144,7 +144,7 @@ enum perf_event_sample_format { PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; /* diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h index 80b52b4945e9..a2ab516fcd2c 100644 --- a/include/xen/mem-reservation.h +++ b/include/xen/mem-reservation.h @@ -17,11 +17,12 @@ #include <xen/page.h> +extern bool xen_scrub_pages; + static inline void xenmem_reservation_scrub_page(struct page *page) { -#ifdef CONFIG_XEN_SCRUB_PAGES - clear_highpage(page); -#endif + if (xen_scrub_pages) + clear_highpage(page); } #ifdef CONFIG_XEN_HAVE_PVMMU diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2590700237c1..138f0302692e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1844,7 +1844,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env) hdr = &btf->hdr; cur = btf->nohdr_data + hdr->type_off; - end = btf->nohdr_data + hdr->type_len; + end = cur + hdr->type_len; env->log_type_id = 1; while (cur < end) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f4ff0c569e54..8cd4f5306c3c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3078,7 +3078,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * an arbitrary scalar. Disallow all math except * pointer subtraction */ - if (opcode == BPF_SUB){ + if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 2a62b96600ad..c80549bf82c6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp, _perf_event_disable(bp); err = modify_user_hw_breakpoint_check(bp, attr, true); - if (err) { - if (!bp->attr.disabled) - _perf_event_enable(bp); - return err; - } - - if (!attr->disabled) + if (!bp->attr.disabled) _perf_event_enable(bp); - return 0; + + return err; } static int perf_event_modify_attr(struct perf_event *event, @@ -5948,6 +5943,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, unsigned long sp; unsigned int rem; u64 dyn_size; + mm_segment_t fs; /* * We dump: @@ -5965,7 +5961,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, /* Data. */ sp = perf_user_stack_pointer(regs); + fs = get_fs(); + set_fs(USER_DS); rem = __output_copy_user(handle, (void *) sp, dump_size); + set_fs(fs); dyn_size = dump_size - rem; perf_output_skip(handle, rem); diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index b3814fce5ecb..d6b56180827c 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a */ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { + int err; + /* * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it * will not be possible to raise IPIs that invoke __perf_event_disable. @@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att else perf_event_disable(bp); - if (!attr->disabled) { - int err = modify_user_hw_breakpoint_check(bp, attr, false); + err = modify_user_hw_breakpoint_check(bp, attr, false); - if (err) - return err; + if (!bp->attr.disabled) perf_event_enable(bp); - bp->attr.disabled = 0; - } - return 0; + + return err; } EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 01ebdf1f9f40..2e62503bea0d 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -678,7 +678,7 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { - WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n"); + WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e406c5fdb41e..dd13f865ad40 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -55,7 +55,6 @@ #include "lockdep_internals.h" -#include <trace/events/preemptirq.h> #define CREATE_TRACE_POINTS #include <trace/events/lock.h> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 1a81a1257b3f..3f8a35104285 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -389,7 +389,7 @@ static bool __ww_mutex_wound(struct mutex *lock, /* * wake_up_process() paired with set_current_state() * inserts sufficient barriers to make sure @owner either sees - * it's wounded in __ww_mutex_lock_check_stamp() or has a + * it's wounded in __ww_mutex_check_kill() or has a * wakeup pending to re-read the wounded state. */ if (owner != current) @@ -946,7 +946,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } debug_mutex_lock_common(lock, &waiter); - debug_mutex_add_waiter(lock, &waiter, current); lock_contended(&lock->dep_map, ip); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 5b915b370d5a..0be047dbd897 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -324,7 +324,7 @@ static int __test_cycle(unsigned int nthreads) if (!cycle->result) continue; - pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n", + pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n", n, nthreads, cycle->result); ret = -EINVAL; break; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fd6f8ed28e01..9bf5404397e0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -351,7 +351,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; */ enum log_flags { - LOG_NOCONS = 1, /* suppress print, do not print to console */ LOG_NEWLINE = 2, /* text ended with a newline */ LOG_PREFIX = 4, /* text started with a prefix */ LOG_CONT = 8, /* text is a fragment of a continuation line */ @@ -1881,9 +1880,6 @@ int vprintk_store(int facility, int level, if (dict) lflags |= LOG_PREFIX|LOG_NEWLINE; - if (suppress_message_printing(level)) - lflags |= LOG_NOCONS; - return log_output(facility, level, lflags, dict, dictlen, text, text_len); } @@ -2032,6 +2028,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) {} static size_t msg_print_text(const struct printk_log *msg, bool syslog, char *buf, size_t size) { return 0; } +static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ @@ -2368,10 +2365,11 @@ skip: break; msg = log_from_idx(console_idx); - if (msg->flags & LOG_NOCONS) { + if (suppress_message_printing(msg->level)) { /* - * Skip record if !ignore_loglevel, and - * record has level above the console loglevel. + * Skip record we have buffered and already printed + * directly to the console when we received it, and + * record that has level above the console loglevel. */ console_idx = log_next(console_idx); console_seq++; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 60caf1fb94e0..6383aa6a60ca 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -89,12 +89,12 @@ struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { static void sched_feat_disable(int i) { - static_key_disable(&sched_feat_keys[i]); + static_key_disable_cpuslocked(&sched_feat_keys[i]); } static void sched_feat_enable(int i) { - static_key_enable(&sched_feat_keys[i]); + static_key_enable_cpuslocked(&sched_feat_keys[i]); } #else static void sched_feat_disable(int i) { }; @@ -146,9 +146,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf, /* Ensure the static_key remains in a consistent state */ inode = file_inode(filp); + cpus_read_lock(); inode_lock(inode); ret = sched_feat_set(cmp); inode_unlock(inode); + cpus_read_unlock(); if (ret < 0) return ret; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b39fb596f6c1..f808ddf2a868 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3362,6 +3362,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) * attach_entity_load_avg - attach this entity to its cfs_rq load avg * @cfs_rq: cfs_rq to attach to * @se: sched_entity to attach + * @flags: migration hints * * Must call update_cfs_rq_load_avg() before this, since we rely on * cfs_rq->avg.last_update_time being current. @@ -7263,6 +7264,7 @@ static void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); struct cfs_rq *cfs_rq, *pos; + const struct sched_class *curr_class; struct rq_flags rf; bool done = true; @@ -7299,8 +7301,10 @@ static void update_blocked_averages(int cpu) if (cfs_rq_has_blocked(cfs_rq)) done = false; } - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); /* Don't need periodic decay once load/util_avg are null */ if (others_have_blocked(rq)) @@ -7365,13 +7369,16 @@ static inline void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); struct cfs_rq *cfs_rq = &rq->cfs; + const struct sched_class *curr_class; struct rq_flags rf; rq_lock_irqsave(rq, &rf); update_rq_clock(rq); update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; @@ -7482,10 +7489,10 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long scale_rt_capacity(int cpu) +static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + unsigned long max = arch_scale_cpu_capacity(sd, cpu); unsigned long used, free; unsigned long irq; @@ -7507,7 +7514,7 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity = scale_rt_capacity(cpu); + unsigned long capacity = scale_rt_capacity(sd, cpu); struct sched_group *sdg = sd->groups; cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); @@ -8269,7 +8276,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) force_balance: /* Looks like there is an imbalance. Compute it */ calculate_imbalance(env, &sds); - return sds.busiest; + return env->imbalance ? sds.busiest : NULL; out_balanced: env->imbalance = 0; @@ -9638,7 +9645,8 @@ static inline bool vruntime_normalized(struct task_struct *p) * - A task which has been woken up by try_to_wake_up() and * waiting for actually being woken up by sched_ttwu_pending(). */ - if (!se->sum_exec_runtime || p->state == TASK_WAKING) + if (!se->sum_exec_runtime || + (p->state == TASK_WAKING && p->sched_remote_wakeup)) return true; return false; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 56a0fed30c0a..505a41c42b96 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1295,7 +1295,7 @@ static void init_numa_topology_type(void) n = sched_max_numa_distance; - if (sched_domains_numa_levels <= 1) { + if (sched_domains_numa_levels <= 2) { sched_numa_topology_type = NUMA_DIRECT; return; } @@ -1380,9 +1380,6 @@ void sched_init_numa(void) break; } - if (!level) - return; - /* * 'level' contains the number of unique distances * diff --git a/mm/Makefile b/mm/Makefile index 8716bdabe1e6..26ef77a3883b 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -32,7 +32,7 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH mmu-$(CONFIG_MMU) += process_vm_access.o endif -obj-y := filemap.o mempool.o oom_kill.o \ +obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ @@ -49,7 +49,6 @@ else obj-y += bootmem.o endif -obj-$(CONFIG_ADVISE_SYSCALLS) += fadvise.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o endif diff --git a/mm/debug.c b/mm/debug.c index 38c926520c97..bd10aad8539a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" #ifdef CONFIG_MMU "get_unmapped_area %px\n" #endif @@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm) "tlb_flush_pending %d\n" "def_flags: %#lx(%pGv)\n", - mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, + mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, #ifdef CONFIG_MMU mm->get_unmapped_area, #endif diff --git a/mm/fadvise.c b/mm/fadvise.c index 2d8376e3c640..467bcd032037 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -27,9 +27,9 @@ * deactivate the pages and clear PG_Referenced. */ -int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +static int generic_fadvise(struct file *file, loff_t offset, loff_t len, + int advice) { - struct fd f = fdget(fd); struct inode *inode; struct address_space *mapping; struct backing_dev_info *bdi; @@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) pgoff_t start_index; pgoff_t end_index; unsigned long nrpages; - int ret = 0; - - if (!f.file) - return -EBADF; - inode = file_inode(f.file); - if (S_ISFIFO(inode->i_mode)) { - ret = -ESPIPE; - goto out; - } + inode = file_inode(file); + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; - mapping = f.file->f_mapping; - if (!mapping || len < 0) { - ret = -EINVAL; - goto out; - } + mapping = file->f_mapping; + if (!mapping || len < 0) + return -EINVAL; bdi = inode_to_bdi(mapping->host); @@ -67,9 +59,9 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) /* no bad return value, but ignore advice */ break; default: - ret = -EINVAL; + return -EINVAL; } - goto out; + return 0; } /* @@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) switch (advice) { case POSIX_FADV_NORMAL: - f.file->f_ra.ra_pages = bdi->ra_pages; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_RANDOM: - spin_lock(&f.file->f_lock); - f.file->f_mode |= FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + spin_lock(&file->f_lock); + file->f_mode |= FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_SEQUENTIAL: - f.file->f_ra.ra_pages = bdi->ra_pages * 2; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: /* First and last PARTIAL page! */ @@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) * Ignore return value because fadvise() shall return * success even if filesystem can't retrieve a hint, */ - force_page_cache_readahead(mapping, f.file, start_index, - nrpages); + force_page_cache_readahead(mapping, file, start_index, nrpages); break; case POSIX_FADV_NOREUSE: break; @@ -183,9 +174,32 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) } break; default: - ret = -EINVAL; + return -EINVAL; } -out: + return 0; +} + +int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + if (file->f_op->fadvise) + return file->f_op->fadvise(file, offset, len, advice); + + return generic_fadvise(file, offset, len, advice); +} +EXPORT_SYMBOL(vfs_fadvise); + +#ifdef CONFIG_ADVISE_SYSCALLS + +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +{ + struct fd f = fdget(fd); + int ret; + + if (!f.file) + return -EBADF; + + ret = vfs_fadvise(f.file, offset, len, advice); + fdput(f); return ret; } @@ -203,3 +217,4 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice) } #endif +#endif diff --git a/mm/readahead.c b/mm/readahead.c index a59ea70527b9..4e630143a0ba 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -20,6 +20,7 @@ #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> +#include <linux/fadvise.h> #include "internal.h" @@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping, } EXPORT_SYMBOL_GPL(page_cache_async_readahead); -static ssize_t -do_readahead(struct address_space *mapping, struct file *filp, - pgoff_t index, unsigned long nr) -{ - if (!mapping || !mapping->a_ops) - return -EINVAL; - - /* - * Readahead doesn't make sense for DAX inodes, but we don't want it - * to report a failure either. Instead, we just return success and - * don't do any work. - */ - if (dax_mapping(mapping)) - return 0; - - return force_page_cache_readahead(mapping, filp, index, nr); -} - ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; @@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) ret = -EBADF; f = fdget(fd); - if (f.file) { - if (f.file->f_mode & FMODE_READ) { - struct address_space *mapping = f.file->f_mapping; - pgoff_t start = offset >> PAGE_SHIFT; - pgoff_t end = (offset + count - 1) >> PAGE_SHIFT; - unsigned long len = end - start + 1; - ret = do_readahead(mapping, f.file, start, len); - } - fdput(f); - } + if (!f.file || !(f.file->f_mode & FMODE_READ)) + goto out; + + /* + * The readahead() syscall is intended to run only on files + * that can execute readahead. If readahead is not possible + * on this file, then we must return -EINVAL. + */ + ret = -EINVAL; + if (!f.file->f_mapping || !f.file->f_mapping->a_ops || + !S_ISREG(file_inode(f.file)->i_mode)) + goto out; + + ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); +out: + fdput(f); return ret; } diff --git a/mm/vmacache.c b/mm/vmacache.c index ea517bef7dc5..cdc32a3b02fa 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -20,44 +20,6 @@ #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) /* - * Flush vma caches for threads that share a given mm. - * - * The operation is safe because the caller holds the mmap_sem - * exclusively and other threads accessing the vma cache will - * have mmap_sem held at least for read, so no extra locking - * is required to maintain the vma cache. - */ -void vmacache_flush_all(struct mm_struct *mm) -{ - struct task_struct *g, *p; - - count_vm_vmacache_event(VMACACHE_FULL_FLUSHES); - - /* - * Single threaded tasks need not iterate the entire - * list of process. We can avoid the flushing as well - * since the mm's seqnum was increased and don't have - * to worry about other threads' seqnum. Current's - * flush will occur upon the next lookup. - */ - if (atomic_read(&mm->mm_users) == 1) - return; - - rcu_read_lock(); - for_each_process_thread(g, p) { - /* - * Only flush the vmacache pointers as the - * mm seqnum is already set and curr's will - * be set upon invalidation when the next - * lookup is done. - */ - if (mm == p->mm) - vmacache_flush(p); - } - rcu_read_unlock(); -} - -/* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this * task's vmacache pertains to a different mm (ie, its own). There is diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ae91e2d40056..3a7b0773536b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -83,6 +83,7 @@ enum { struct smp_dev { /* Secure Connections OOB data */ + bool local_oob; u8 local_pk[64]; u8 local_rand[16]; bool debug_key; @@ -599,6 +600,8 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) memcpy(rand, smp->local_rand, 16); + smp->local_oob = true; + return 0; } @@ -1785,7 +1788,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (req->oob_flag == SMP_OOB_PRESENT) + if (req->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); /* SMP over BR/EDR requires special treatment */ @@ -1967,7 +1970,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (rsp->oob_flag == SMP_OOB_PRESENT) + if (rsp->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); smp->prsp[0] = SMP_CMD_PAIRING_RSP; @@ -2697,7 +2700,13 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) * key was set/generated. */ if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) { - struct smp_dev *smp_dev = chan->data; + struct l2cap_chan *hchan = hdev->smp_data; + struct smp_dev *smp_dev; + + if (!hchan || !hchan->data) + return SMP_UNSPECIFIED; + + smp_dev = hchan->data; tfm_ecdh = smp_dev->tfm_ecdh; } else { @@ -3230,6 +3239,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_ecdh); } + smp->local_oob = false; smp->tfm_aes = tfm_aes; smp->tfm_cmac = tfm_cmac; smp->tfm_ecdh = tfm_ecdh; diff --git a/net/core/filter.c b/net/core/filter.c index d301134bca3a..0b40f95da21b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2344,7 +2344,8 @@ BPF_CALL_4(bpf_msg_pull_data, if (unlikely(bytes_sg_total > copy)) return -EINVAL; - page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy)); + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, + get_order(copy)); if (unlikely(!page)) return -ENOMEM; p = page_address(page); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index aa19d86937af..91592fceeaad 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1180,6 +1180,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, lladdr = neigh->ha; } + /* Update confirmed timestamp for neighbour entry after we + * received ARP packet even if it doesn't change IP to MAC binding. + */ + if (new & NUD_CONNECTED) + neigh->confirmed = jiffies; + /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ @@ -1201,15 +1207,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } } - /* Update timestamps only once we know we will make a change to the + /* Update timestamp only once we know we will make a change to the * neighbour entry. Otherwise we risk to move the locktime window with * noop updates and ignore relevant ARP updates. */ - if (new != old || lladdr != neigh->ha) { - if (new & NUD_CONNECTED) - neigh->confirmed = jiffies; + if (new != old || lladdr != neigh->ha) neigh->updated = jiffies; - } if (new != old) { neigh_del_timer(neigh); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e4ae0319e189..80a7e18c65fb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2819,7 +2819,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { - __dev_notify_flags(dev, old_flags, 0U); + __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags)); } else { dev->rtnl_link_state = RTNL_LINK_INITIALIZED; __dev_notify_flags(dev, old_flags, ~0U); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f4e35b2ff8b8..7d69dd6fa7e8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2124,6 +2124,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, inet_compute_pseudo); } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + inet_compute_pseudo); + + ret = udp_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + /* * All we need to do is get the socket, and then do a checksum. */ @@ -2170,14 +2192,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp_sk_rx_dst_set(sk, dst); - ret = udp_queue_rcv_skb(sk, skb); + ret = udp_unicast_rcv_skb(sk, skb, uh); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; + return ret; } if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) @@ -2185,22 +2202,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk) { - int ret; - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - inet_compute_pseudo); - - ret = udp_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; - } + if (sk) + return udp_unicast_rcv_skb(sk, skb, uh); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 9a8934ac053b..89e0d5118afe 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -ENOBUFS; } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; - /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically, - * it is safe to call in our context (socket lock not held) - */ - skb_set_owner_w(skb, (struct sock *)sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b3268eaa394b..21a919e74fbf 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -946,8 +946,6 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort) static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) { - rt->dst.flags |= fib6_info_dst_flags(ort); - if (ort->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, ort); return; @@ -4641,20 +4639,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - struct rtmsg *rtm; + struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6key *rt6_dst, *rt6_src; + u32 *pmetrics, table, rt6_flags; struct nlmsghdr *nlh; + struct rtmsg *rtm; long expires = 0; - u32 *pmetrics; - u32 table; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; + if (rt6) { + rt6_dst = &rt6->rt6i_dst; + rt6_src = &rt6->rt6i_src; + rt6_flags = rt6->rt6i_flags; + } else { + rt6_dst = &rt->fib6_dst; + rt6_src = &rt->fib6_src; + rt6_flags = rt->fib6_flags; + } + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; - rtm->rtm_dst_len = rt->fib6_dst.plen; - rtm->rtm_src_len = rt->fib6_src.plen; + rtm->rtm_dst_len = rt6_dst->plen; + rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; @@ -4669,7 +4678,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; - if (rt->fib6_flags & RTF_CACHE) + if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { @@ -4677,7 +4686,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { @@ -4685,12 +4694,12 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE - if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) { + if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) @@ -4725,7 +4734,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ - if (rt->fib6_nsiblings) { + if (rt6) { + if (rt6_flags & RTF_GATEWAY && + nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) + goto nla_put_failure; + + if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) + goto nla_put_failure; + } else if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; struct nlattr *mp; @@ -4748,7 +4764,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } - if (rt->fib6_flags & RTF_EXPIRES) { + if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } @@ -4756,7 +4772,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; - if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags))) + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 83f4c77c79d8..28c4aa5078fc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -752,6 +752,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) } } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_compute_pseudo); + + ret = udpv6_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { @@ -803,13 +825,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp6_sk_rx_dst_set(sk, dst); - ret = udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + goto report_csum_error; + } - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - return 0; + ret = udp6_unicast_rcv_skb(sk, skb, uh); + sock_put(sk); + return ret; } /* @@ -822,30 +845,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - int ret; - - if (!uh->check && !udp_sk(sk)->no_check6_rx) { - udp6_csum_zero_error(skb); - goto csum_error; - } - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - ip6_compute_pseudo); - - ret = udpv6_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - - return 0; + if (!uh->check && !udp_sk(sk)->no_check6_rx) + goto report_csum_error; + return udp6_unicast_rcv_skb(sk, skb, uh); } - if (!uh->check) { - udp6_csum_zero_error(skb); - goto csum_error; - } + if (!uh->check) + goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; @@ -866,6 +872,9 @@ short_packet: ulen, skb->len, daddr, ntohs(uh->dest)); goto discard; + +report_csum_error: + udp6_csum_zero_error(skb); csum_error: __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 83a133375d6d..1a0c682fd734 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_sample_ops, bind, false); + &act_sample_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 1a67af8a6e8c..0a75cb2e5e7b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1902,6 +1902,8 @@ replay: RTM_NEWCHAIN, false); break; case RTM_DELCHAIN: + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER); /* Flush the chain first as the user requested chain removal. */ tcf_chain_flush(chain); /* In case the chain was successfully deleted, put a reference diff --git a/net/socket.c b/net/socket.c index e6945e318f02..01f3f8f32d6f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,7 +941,8 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg, + unsigned int ifreq_size) { int err; void __user *argp = (void __user *)arg; @@ -967,11 +968,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (copy_from_user(&ifr, argp, ifreq_size)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (copy_to_user(argp, &ifr, ifreq_size)) return -EFAULT; } return err; @@ -1070,7 +1071,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg); + err = sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct ifreq)); break; } return err; @@ -2750,7 +2752,8 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2766,7 +2769,8 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -3072,7 +3076,8 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, + sizeof(struct compat_ifreq)); set_fs(old_fs); out: @@ -3185,7 +3190,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg); + return sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct compat_ifreq)); } return -ENOIOCTLCMD; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 292742e50bfa..961b07d4d41c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -686,7 +686,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) goto free_marker_record; } - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; @@ -780,7 +780,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, - &ctx->crypto_send, + &ctx->crypto_send.info, tcp_sk(sk)->write_seq); if (rc) goto release_netdev; @@ -862,7 +862,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, - &ctx->crypto_recv, + &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); if (rc) { pr_err_ratelimited("%s: The netdev has refused to offload this socket\n", diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 6102169239d1..450a6dbc5a88 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -320,7 +320,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, goto free_req; iv = buf; - memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt, + memcpy(iv, tls_ctx->crypto_send.aes_gcm_128.salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 180b6640e531..523622dc74f8 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -241,6 +241,16 @@ static void tls_write_space(struct sock *sk) ctx->sk_write_space(sk); } +static void tls_ctx_free(struct tls_context *ctx) +{ + if (!ctx) + return; + + memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); + memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + kfree(ctx); +} + static void tls_sk_proto_close(struct sock *sk, long timeout) { struct tls_context *ctx = tls_get_ctx(sk); @@ -294,7 +304,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #else { #endif - kfree(ctx); + tls_ctx_free(ctx); ctx = NULL; } @@ -305,7 +315,7 @@ skip_tx_cleanup: * for sk->sk_prot->unhash [tls_hw_unhash] */ if (free_ctx) - kfree(ctx); + tls_ctx_free(ctx); } static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, @@ -330,7 +340,7 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -417,9 +427,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } if (tx) - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; else - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; /* Currently we don't support set crypto info more than one time */ if (TLS_CRYPTO_INFO_READY(crypto_info)) { @@ -499,7 +509,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, goto out; err_crypto_info: - memset(crypto_info, 0, sizeof(*crypto_info)); + memzero_explicit(crypto_info, sizeof(union tls_crypto_context)); out: return rc; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index f4aa7cdb01ca..5ff51bac8b46 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1109,6 +1109,13 @@ pick_next_record: } else { break; } + } else { + /* MSG_PEEK right now cannot look beyond current skb + * from strparser, meaning we cannot advance skb here + * and thus unpause strparser since we'd loose original + * one. + */ + break; } /* If we have a new message from strparser, continue now. */ @@ -1250,8 +1257,8 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) { + if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || + header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { ret = -EINVAL; goto read_failure; } @@ -1331,7 +1338,6 @@ void tls_sw_free_resources_rx(struct sock *sk) int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { - char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; @@ -1376,12 +1382,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (tx) { crypto_init_wait(&sw_ctx_tx->async_wait); - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; } else { crypto_init_wait(&sw_ctx_rx->async_wait); - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; aead = &sw_ctx_rx->aead_recv; } @@ -1460,9 +1466,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); - - rc = crypto_aead_setkey(*aead, keyval, + rc = crypto_aead_setkey(*aead, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); if (rc) goto free_aead; diff --git a/scripts/subarch.include b/scripts/subarch.include new file mode 100644 index 000000000000..650682821126 --- /dev/null +++ b/scripts/subarch.include @@ -0,0 +1,13 @@ +# SUBARCH tells the usermode build what the underlying arch is. That is set +# first, and if a usermode build is happening, the "ARCH=um" on the command +# line overrides the setting of ARCH below. If a native build is happening, +# then ARCH is assigned, getting whatever value it gets normally, and +# SUBARCH is subsequently ignored. + +SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ + -e s/sun4u/sparc64/ \ + -e s/arm.*/arm/ -e s/sa110/arm/ \ + -e s/s390x/s390/ -e s/parisc64/parisc/ \ + -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ + -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ + -e s/riscv.*/riscv/) diff --git a/security/Kconfig b/security/Kconfig index 27d8b2688f75..d9aa521b5206 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -57,7 +57,7 @@ config SECURITY_NETWORK config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" default y - depends on X86 && !UML + depends on (X86_64 || X86_PAE) && !UML help This feature reduces the number of hardware side channels by ensuring that the majority of kernel addresses are not mapped diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 16e006f708ca..4602464ebdfb 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -27,6 +27,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -125,6 +126,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 4e76630dd655..97c3478ee6e7 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -39,6 +39,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -154,6 +155,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 4cdaa55fabfe..9a50f02b9894 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -4,7 +4,7 @@ /* * KVM s390 specific structures and definitions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -225,6 +225,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) #define KVM_SYNC_BPBC (1UL << 10) +#define KVM_SYNC_ETOKEN (1UL << 11) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -258,6 +259,8 @@ struct kvm_sync_regs { struct { __u64 reserved1[2]; __u64 gscb[4]; + __u64 etoken; + __u64 etoken_extension; }; }; }; diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index c535c2fdea13..86299efa804a 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -378,4 +378,41 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + +#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_SMM_VMXON 0x00000002 + +struct kvm_vmx_nested_state { + __u64 vmxon_pa; + __u64 vmcs_pa; + + struct { + __u16 flags; + } smm; +}; + +/* for KVM_CAP_NESTED_STATE */ +struct kvm_nested_state { + /* KVM_STATE_* flags */ + __u16 flags; + + /* 0 for VMX, 1 for SVM. */ + __u16 format; + + /* 128 for SVM, 128 + VMCS size for VMX. */ + __u32 size; + + union { + /* VMXON, VMCS */ + struct kvm_vmx_nested_state vmx; + + /* Pad the header to 128 bytes. */ + __u8 pad[120]; + }; + + __u8 data[0]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index dbf6e8bd98ba..bbb2a8ef367c 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -286,7 +286,7 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size) * Found a match; just move the remaining * entries up. */ - if (i == num_records) { + if (i == (num_records - 1)) { kvp_file_info[pool].num_records--; kvp_update_file(pool); return 0; diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h index 6b0c36a58fcb..e56997288f2b 100644 --- a/tools/include/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -30,9 +30,12 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; gfp_t lockdep_reclaim_gfp; int pid; + int state; char comm[17]; }; +#define TASK_RUNNING 0 + extern struct task_struct *__curr(void); #define current (__curr()) diff --git a/tools/include/linux/nmi.h b/tools/include/linux/nmi.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/linux/nmi.h diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 42990676a55e..df4bedb9b01c 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free, sys_pkey_free) __SYSCALL(__NR_statx, sys_statx) #define __NR_io_pgetevents 292 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) +#define __NR_rseq 293 +__SYSCALL(__NR_rseq, sys_rseq) #undef __NR_syscalls -#define __NR_syscalls 293 +#define __NR_syscalls 294 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 9c660e1688ab..300f336633f2 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -687,6 +687,15 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_ASPECT_RATIO 4 +/** + * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS + * + * If set to 1, the DRM core will expose special connectors to be used for + * writing back to memory the scene setup in the commit. Depends on client + * also supporting DRM_CLIENT_CAP_ATOMIC + */ +#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 + /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 141cbfdc5865..58faab897201 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -165,6 +165,8 @@ enum { IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, __IFLA_MAX }; @@ -335,6 +337,7 @@ enum { IFLA_BRPORT_GROUP_FWD_MASK, IFLA_BRPORT_NEIGH_SUPPRESS, IFLA_BRPORT_ISOLATED, + IFLA_BRPORT_BACKUP_PORT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -460,6 +463,16 @@ enum { #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + enum macsec_validation_type { MACSEC_VALIDATE_DISABLED = 0, MACSEC_VALIDATE_CHECK = 1, @@ -922,6 +935,7 @@ enum { XDP_ATTACHED_DRV, XDP_ATTACHED_SKB, XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, }; enum { @@ -930,6 +944,9 @@ enum { IFLA_XDP_ATTACHED, IFLA_XDP_FLAGS, IFLA_XDP_PROG_ID, + IFLA_XDP_DRV_PROG_ID, + IFLA_XDP_SKB_PROG_ID, + IFLA_XDP_HW_PROG_ID, __IFLA_XDP_MAX, }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b6270a3b38e9..07548de5c988 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -949,6 +949,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GET_MSR_FEATURES 153 #define KVM_CAP_HYPERV_EVENTFD 154 #define KVM_CAP_HYPERV_TLBFLUSH 155 +#define KVM_CAP_S390_HPAGE_1M 156 +#define KVM_CAP_NESTED_STATE 157 +#define KVM_CAP_ARM_INJECT_SERROR_ESR 158 #ifdef KVM_CAP_IRQ_ROUTING @@ -1391,6 +1394,9 @@ struct kvm_enc_region { /* Available with KVM_CAP_HYPERV_EVENTFD */ #define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd) +/* Available with KVM_CAP_NESTED_STATE */ +#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) +#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) /* Secure Encrypted Virtualization command */ enum sev_cmd_id { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index eeb787b1c53c..f35eb72739c0 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -144,7 +144,7 @@ enum perf_event_sample_format { PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; /* diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c51f8e5cc608..84c3de89696a 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -65,6 +65,7 @@ struct vhost_iotlb_msg { }; #define VHOST_IOTLB_MSG 0x1 +#define VHOST_IOTLB_MSG_V2 0x2 struct vhost_msg { int type; @@ -74,6 +75,15 @@ struct vhost_msg { }; }; +struct vhost_msg_v2 { + __u32 type; + __u32 reserved; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + struct vhost_memory_region { __u64 guest_phys_addr; __u64 memory_size; /* bytes */ @@ -160,6 +170,14 @@ struct vhost_memory { #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \ struct vhost_vring_state) +/* Set or get vhost backend capability */ + +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 + +#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) +#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) + /* VHOST_NET specific defines */ /* Attach virtio net ring to a raw socket, or tap device. diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index b3d1b12a5081..5224ade3d5af 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -777,14 +777,12 @@ endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifndef NO_LIBBPF - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, include/bpf) \ - $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' - $(call QUIET_INSTALL, examples/bpf) \ - $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-headers) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ + $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-examples) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \ + $(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index f013b115dc86..dbef716a1913 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 out := $(OUTPUT)arch/arm64/include/generated/asm header := $(out)/syscalls.c -sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ systbl := $(sysprf)/mksyscalltbl @@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@ + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ clean:: $(call QUIET_CLEAN, arm64) $(RM) $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl index 52e197317d3e..2dbb8cade048 100755 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -11,7 +11,8 @@ gcc=$1 hostcc=$2 -input=$3 +incpath=$3 +input=$4 if ! test -r $input; then echo "Could not read input file" >&2 @@ -28,7 +29,6 @@ create_table_from_c() cat <<-_EoHEADER #include <stdio.h> - #define __ARCH_WANT_RENAMEAT #include "$input" int main(int argc, char *argv[]) { @@ -42,7 +42,7 @@ create_table_from_c() printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" printf "}\n" - } | $hostcc -o $create_table_exe -x c - + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - $create_table_exe diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 20e7d74d86cd..10a44e946f77 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) #endif -#if !defined(_CALL_ELF) || _CALL_ELF != 2 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { char *sym = syma->name; +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Skip over any initial dot */ if (*sym == '.') sym++; +#endif /* Avoid "SyS" kernel syscall aliases */ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3)) @@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma, return SYMBOL_A; } +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Allow matching against dot variants */ int arch__compare_symbol_names(const char *namea, const char *nameb) { diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c1bd979b957b..613709cfbbd0 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -9,6 +9,7 @@ struct test; int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__bp_modify(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 8e2c5a38c3b9..586849ff83a0 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ libperf-y += arch-tests.o libperf-y += rdpmc.o libperf-y += perf-time-to-tsc.o libperf-$(CONFIG_AUXTRACE) += insn-x86.o +libperf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index cc1802ff5410..d47d3f8e3c8e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -24,6 +24,12 @@ struct test arch_tests[] = { .func = test__insn_x86, }, #endif +#if defined(__x86_64__) + { + .desc = "x86 bp modify", + .func = test__bp_modify, + }, +#endif { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c new file mode 100644 index 000000000000..f53e4406709f --- /dev/null +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/user.h> +#include <syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ptrace.h> +#include <asm/ptrace.h> +#include <errno.h> +#include "debug.h" +#include "tests/tests.h" +#include "arch-tests.h" + +static noinline int bp_1(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static noinline int bp_2(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static int spawn_child(void) +{ + int child = fork(); + + if (child == 0) { + /* + * The child sets itself for as tracee and + * waits in signal for parent to trace it, + * then it calls bp_1 and quits. + */ + int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL); + + if (err) { + pr_debug("failed to PTRACE_TRACEME\n"); + exit(1); + } + + raise(SIGCONT); + bp_1(); + exit(0); + } + + return child; +} + +/* + * This tests creates HW breakpoint, tries to + * change it and checks it was properly changed. + */ +static int bp_modify1(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_2 function + * - changes that breakponit to bp_1 function + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_2)) { + pr_debug("failed to set breakpoint, 1st time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint, 2nd time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +/* + * This tests creates HW breakpoint, tries to + * change it to bogus value and checks the original + * breakpoint is hit. + */ +static int bp_modify2(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_1 function + * - tries to change that breakpoint to (-1) address + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (!ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) { + pr_debug("failed, breakpoint set to bogus address\n"); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +int test__bp_modify(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); + TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2()); + + return 0; +} diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 20061cf42288..28cd6a17491b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -246,8 +246,14 @@ find_target: indirect_call: tok = strchr(endptr, '*'); - if (tok != NULL) - ops->target.addr = strtoull(tok + 1, NULL, 16); + if (tok != NULL) { + endptr++; + + /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx). + * Do not parse such instruction. */ + if (strstr(endptr, "(%r") == NULL) + ops->target.addr = strtoull(endptr, NULL, 16); + } goto find_target; } @@ -276,7 +282,19 @@ bool ins__is_call(const struct ins *ins) return ins->ops == &call_ops || ins->ops == &s390_call_ops; } -static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms) +/* + * Prevents from matching commas in the comment section, e.g.: + * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast + */ +static inline const char *validate_comma(const char *c, struct ins_operands *ops) +{ + if (ops->raw_comment && c > ops->raw_comment) + return NULL; + + return c; +} + +static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { struct map *map = ms->map; struct symbol *sym = ms->sym; @@ -285,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op }; const char *c = strchr(ops->raw, ','); u64 start, end; + + ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); + c = validate_comma(c, ops); + /* * Examples of lines to parse for the _cpp_lex_token@@Base * function: @@ -304,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); + c = validate_comma(c, ops); if (c++ != NULL) ops->target.addr = strtoull(c, NULL, 16); } @@ -361,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name); c = strchr(ops->raw, ','); + c = validate_comma(c, ops); + if (c != NULL) { const char *c2 = strchr(c + 1, ','); + c2 = validate_comma(c2, ops); /* check for 3-op insn */ if (c2 != NULL) c = c2; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 005a5fe8a8c6..5399ba2321bb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -22,6 +22,7 @@ struct ins { struct ins_operands { char *raw; + char *raw_comment; struct { char *raw; char *name; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c980bbff6353..1a61628a1c12 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(perf_evsel__object.size); - if (evsel != NULL) - perf_evsel__init(evsel, attr, idx); + if (!evsel) + return NULL; + perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 36d0763311ef..6a6929f208b4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -576,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg, return NULL; } +static bool map__contains_symbol(struct map *map, struct symbol *sym) +{ + u64 ip = map->unmap_ip(map, sym->start); + + return ip >= map->start && ip < map->end; +} + struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { @@ -591,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, if (sym == NULL) continue; + if (!map__contains_symbol(pos, sym)) { + sym = NULL; + continue; + } if (mapp != NULL) *mapp = pos; goto out; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index c85d0d1a65ed..7b0ca7cbb7de 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -377,7 +377,7 @@ out: static int record_saved_cmdline(void) { - unsigned int size; + unsigned long long size; char *path; struct stat st; int ret, err = 0; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 920b1d58a068..e76214f8d596 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *pevent, void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { - char *comm; + char comm[17]; /* Max comm length in the kernel is 16. */ char *line; char *next = NULL; int pid; line = strtok_r(file, "\n", &next); while (line) { - sscanf(line, "%d %ms", &pid, &comm); - tep_register_comm(pevent, comm, pid); - free(comm); + if (sscanf(line, "%d %16s", &pid, comm) == 2) + tep_register_comm(pevent, comm, pid); line = strtok_r(NULL, "\n", &next); } } diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index 72c25a3cb658..d9a725478375 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -6,7 +6,7 @@ TEST_PROGS := run.sh include ../lib.mk -all: +all: khdr @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ diff --git a/tools/testing/selftests/android/ion/config b/tools/testing/selftests/android/config index b4ad748a9dd9..b4ad748a9dd9 100644 --- a/tools/testing/selftests/android/ion/config +++ b/tools/testing/selftests/android/config diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile index e03695287f76..88cfe88e466f 100644 --- a/tools/testing/selftests/android/ion/Makefile +++ b/tools/testing/selftests/android/ion/Makefile @@ -10,6 +10,8 @@ $(TEST_GEN_FILES): ipcsocket.c ionutils.c TEST_PROGS := ion_test.sh +KSFT_KHDR_INSTALL := 1 +top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index 95eb3a53c381..adacda50a4b2 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -1 +1,2 @@ test_memcontrol +test_core diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 1c5d2b2a583b..14c9fe284806 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -89,17 +89,28 @@ int cg_read(const char *cgroup, const char *control, char *buf, size_t len) int cg_read_strcmp(const char *cgroup, const char *control, const char *expected) { - size_t size = strlen(expected) + 1; + size_t size; char *buf; + int ret; + + /* Handle the case of comparing against empty string */ + if (!expected) + size = 32; + else + size = strlen(expected) + 1; buf = malloc(size); if (!buf) return -1; - if (cg_read(cgroup, control, buf, size)) + if (cg_read(cgroup, control, buf, size)) { + free(buf); return -1; + } - return strcmp(expected, buf); + ret = strcmp(expected, buf); + free(buf); + return ret; } int cg_read_strstr(const char *cgroup, const char *control, const char *needle) @@ -337,3 +348,24 @@ int is_swap_enabled(void) return cnt > 1; } + +int set_oom_adj_score(int pid, int score) +{ + char path[PATH_MAX]; + int fd, len; + + sprintf(path, "/proc/%d/oom_score_adj", pid); + + fd = open(path, O_WRONLY | O_APPEND); + if (fd < 0) + return fd; + + len = dprintf(fd, "%d", score); + if (len < 0) { + close(fd); + return len; + } + + close(fd); + return 0; +} diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 1ff6f9f1abdc..9ac8b7958f83 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -40,3 +40,4 @@ extern int get_temp_fd(void); extern int alloc_pagecache(int fd, size_t size); extern int alloc_anon(const char *cgroup, void *arg); extern int is_swap_enabled(void); +extern int set_oom_adj_score(int pid, int score); diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index cf0bddc9d271..28d321ba311b 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -2,6 +2,7 @@ #define _GNU_SOURCE #include <linux/limits.h> +#include <linux/oom.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -202,6 +203,36 @@ static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg) return 0; } +static int alloc_anon_noexit(const char *cgroup, void *arg) +{ + int ppid = getppid(); + + if (alloc_anon(cgroup, arg)) + return -1; + + while (getppid() == ppid) + sleep(1); + + return 0; +} + +/* + * Wait until processes are killed asynchronously by the OOM killer + * If we exceed a timeout, fail. + */ +static int cg_test_proc_killed(const char *cgroup) +{ + int limit; + + for (limit = 10; limit > 0; limit--) { + if (cg_read_strcmp(cgroup, "cgroup.procs", "") == 0) + return 0; + + usleep(100000); + } + return -1; +} + /* * First, this test creates the following hierarchy: * A memory.min = 50M, memory.max = 200M @@ -964,6 +995,177 @@ cleanup: return ret; } +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the leaf (but not the parent) were killed. + */ +static int test_memcg_oom_group_leaf_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "cgroup.subtree_control", "+memory")) + goto cleanup; + + if (cg_write(child, "memory.max", "50M")) + goto cleanup; + + if (cg_write(child, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(child, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + + if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0) + goto cleanup; + + if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the parent and leaf were killed. + */ +static int test_memcg_oom_group_parent_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "memory.max", "80M")) + goto cleanup; + + if (cg_write(parent, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(parent, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + if (cg_test_proc_killed(parent)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes were killed except those set with OOM_SCORE_ADJ_MIN + */ +static int test_memcg_oom_group_score_events(const char *root) +{ + int ret = KSFT_FAIL; + char *memcg; + int safe_pid; + + memcg = cg_name(root, "memcg_test_0"); + + if (!memcg) + goto cleanup; + + if (cg_create(memcg)) + goto cleanup; + + if (cg_write(memcg, "memory.max", "50M")) + goto cleanup; + + if (cg_write(memcg, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(memcg, "memory.oom.group", "1")) + goto cleanup; + + safe_pid = cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (set_oom_adj_score(safe_pid, OOM_SCORE_ADJ_MIN)) + goto cleanup; + + cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(memcg, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3) + goto cleanup; + + if (kill(safe_pid, SIGKILL)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (memcg) + cg_destroy(memcg); + free(memcg); + + return ret; +} + + #define T(x) { x, #x } struct memcg_test { int (*fn)(const char *root); @@ -978,6 +1180,9 @@ struct memcg_test { T(test_memcg_oom_events), T(test_memcg_swap_max), T(test_memcg_sock), + T(test_memcg_oom_group_leaf_events), + T(test_memcg_oom_group_parent_events), + T(test_memcg_oom_group_score_events), }; #undef T diff --git a/tools/testing/selftests/efivarfs/config b/tools/testing/selftests/efivarfs/config new file mode 100644 index 000000000000..4e151f1005b2 --- /dev/null +++ b/tools/testing/selftests/efivarfs/config @@ -0,0 +1 @@ +CONFIG_EFIVAR_FS=y diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index ff8feca49746..ad1eeb14fda7 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES := \ TEST_PROGS := run.sh +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 1bbb47565c55..4665cdbf1a8d 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -21,11 +21,8 @@ endef CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ LDLIBS += -lmount -I/usr/include/libmount -$(BINARIES): ../../../gpio/gpio-utils.o ../../../../usr/include/linux/gpio.h +$(BINARIES):| khdr +$(BINARIES): ../../../gpio/gpio-utils.o ../../../gpio/gpio-utils.o: make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio - -../../../../usr/include/linux/gpio.h: - make -C ../../../.. headers_install INSTALL_HDR_PATH=$(shell pwd)/../../../../usr/ - diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 15e6b75fc3a5..a3edb2c8e43d 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -19,7 +19,6 @@ #define KSFT_FAIL 1 #define KSFT_XFAIL 2 #define KSFT_XPASS 3 -/* Treat skip as pass */ #define KSFT_SKIP 4 /* counters */ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 03b0f551bedf..87d1a8488af8 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -37,9 +37,6 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ -$(LINUX_HDR_PATH): - make -C $(top_srcdir) headers_install - -all: $(STATIC_LIBS) $(LINUX_HDR_PATH) +all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) -$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH) +$(STATIC_LIBS):| khdr diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 17ab36605a8e..0a8e75886224 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -16,8 +16,20 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) +top_srcdir ?= ../../../.. +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) + all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +.PHONY: khdr +khdr: + make ARCH=$(ARCH) -C $(top_srcdir) headers_install + +ifdef KSFT_KHDR_INSTALL +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr +endif + .ONESHELL: define RUN_TEST_PRINT_RESULT TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST"; \ diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index 2fde30191a47..a7e8cd5bb265 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -2,3 +2,4 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m +CONFIG_MEMORY_HOTREMOVE=y diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index cccdb2295567..256d82d5fa87 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls +KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 96fc6fe70293..11d54c36ae49 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -502,6 +502,55 @@ TEST_F(tls, recv_peek_multiple) EXPECT_EQ(memcmp(test_str, buf, send_len), 0); } +TEST_F(tls, recv_peek_multiple_records) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + /* MSG_PEEK can only peek into the current record. */ + len = strlen(test_str_first) + 1; + EXPECT_EQ(memcmp(test_str_first, buf, len), 0); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, 0), -1); + + /* Non-MSG_PEEK will advance strparser (and therefore record) + * however. + */ + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); + + /* MSG_MORE will hold current record open, so later MSG_PEEK + * will see everything. + */ + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, MSG_MORE), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + TEST_F(tls, recv_peek_large_buf_mult_recs) { char const *test_str = "test_read_peek_mult_recs"; @@ -524,6 +573,7 @@ TEST_F(tls, recv_peek_large_buf_mult_recs) EXPECT_EQ(memcmp(test_str, buf, len), 0); } + TEST_F(tls, pollin) { char const *test_str = "test_poll"; diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index a728040edbe1..14cfcf006936 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -5,6 +5,7 @@ TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp all: $(TEST_PROGS) +top_srcdir = ../../../../.. include ../../lib.mk clean: diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9881876d2aa0..e94b7b14bcb2 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -26,10 +26,6 @@ TEST_PROGS := run_vmtests include ../lib.mk -$(OUTPUT)/userfaultfd: ../../../../usr/include/linux/kernel.h $(OUTPUT)/userfaultfd: LDLIBS += -lpthread $(OUTPUT)/mlock-random-test: LDLIBS += -lcap - -../../../../usr/include/linux/kernel.h: - make -C ../../../.. headers_install |