diff options
805 files changed, 8350 insertions, 4518 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 9871e649ffef..92eb1f42240d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3523,6 +3523,12 @@ ramdisk_size= [RAM] Sizes of RAM disks in kilobytes See Documentation/blockdev/ramdisk.txt. + random.trust_cpu={on,off} + [KNL] Enable or disable trusting the use of the + CPU's random number generator (if available) to + fully seed the kernel's CRNG. Default is controlled + by CONFIG_RANDOM_TRUST_CPU. + ras=option[,option,...] [KNL] RAS-specific options cec_disable [X86] @@ -4994,6 +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/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt index 00e4365d7206..091c8dfd3229 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt @@ -3,7 +3,6 @@ Required properties: - compatible : - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc - - "fsl,imx8dv-lpi2c" for LPI2C compatible with the one integrated on i.MX8DV soc - reg : address and length of the lpi2c master registers - interrupts : lpi2c interrupt - clocks : lpi2c clock specifier @@ -11,7 +10,7 @@ Required properties: Examples: lpi2c7: lpi2c7@40a50000 { - compatible = "fsl,imx8dv-lpi2c"; + compatible = "fsl,imx7ulp-lpi2c"; reg = <0x40A50000 0x10000>; interrupt-parent = <&intc>; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 41089369f891..b3acebe08eb0 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -19,6 +19,10 @@ Required properties: - slaves : Specifies number for slaves - active_slave : Specifies the slave to use for time stamping, ethtool and SIOCGMIIPHY +- cpsw-phy-sel : Specifies the phandle to the CPSW phy mode selection + device. See also cpsw-phy-sel.txt for it's binding. + Note that in legacy cases cpsw-phy-sel may be + a child device instead of a phandle. Optional properties: - ti,hwmods : Must be "cpgmac0" @@ -75,6 +79,7 @@ Examples: cpts_clock_mult = <0x80000000>; cpts_clock_shift = <29>; syscon = <&cm>; + cpsw-phy-sel = <&phy_sel>; cpsw_emac0: slave@0 { phy_id = <&davinci_mdio>, <0>; phy-mode = "rgmii-txid"; @@ -103,6 +108,7 @@ Examples: cpts_clock_mult = <0x80000000>; cpts_clock_shift = <29>; syscon = <&cm>; + cpsw-phy-sel = <&phy_sel>; cpsw_emac0: slave@0 { phy_id = <&davinci_mdio>, <0>; phy-mode = "rgmii-txid"; 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/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt index 76db9f13ad96..abc36274227c 100644 --- a/Documentation/devicetree/bindings/net/sh_eth.txt +++ b/Documentation/devicetree/bindings/net/sh_eth.txt @@ -16,6 +16,7 @@ Required properties: "renesas,ether-r8a7794" if the device is a part of R8A7794 SoC. "renesas,gether-r8a77980" if the device is a part of R8A77980 SoC. "renesas,ether-r7s72100" if the device is a part of R7S72100 SoC. + "renesas,ether-r7s9210" if the device is a part of R7S9210 SoC. "renesas,rcar-gen1-ether" for a generic R-Car Gen1 device. "renesas,rcar-gen2-ether" for a generic R-Car Gen2 or RZ/G1 device. 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/changes.rst b/Documentation/process/changes.rst index 61f918b10a0c..d1bf143b446f 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -86,7 +86,7 @@ pkg-config The build system, as of 4.18, requires pkg-config to check for installed kconfig tools and to determine flags settings for use in -'make {menu,n,g,x}config'. Previously pkg-config was being used but not +'make {g,x}config'. Previously pkg-config was being used but not verified or documented. Flex 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/scsi/scsi-parameters.txt b/Documentation/scsi/scsi-parameters.txt index 25a4b4cf04a6..92999d4e0cb8 100644 --- a/Documentation/scsi/scsi-parameters.txt +++ b/Documentation/scsi/scsi-parameters.txt @@ -97,6 +97,11 @@ parameters may be changed at runtime by the command allowing boot to proceed. none ignores them, expecting user space to do the scan. + scsi_mod.use_blk_mq= + [SCSI] use blk-mq I/O path by default + See SCSI_MQ_DEFAULT in drivers/scsi/Kconfig. + Format: <y/n> + sim710= [SCSI,HW] See header of drivers/scsi/sim710.c. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index c664064f76fb..647f94128a85 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4510,7 +4510,8 @@ Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits. Architectures: s390 Parameters: none Returns: 0 on success, -EINVAL if hpage module parameter was not set - or cmma is enabled + or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL + flag set With this capability the KVM support for memory backing with 1m pages through hugetlbfs can be enabled for a VM. After the capability is @@ -4521,6 +4522,15 @@ hpage module parameter is not set to 1, -EINVAL is returned. While it is generally possible to create a huge page backed VM without this capability, the VM will not be able to run. +7.14 KVM_CAP_MSR_PLATFORM_INFO + +Architectures: x86 +Parameters: args[0] whether feature should be enabled or not + +With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise, +a #GP would be raised when the guest tries to access. Currently, this +capability does not enable write permissions of this MSR for the guest. + 8. Other capabilities. ---------------------- 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 567e03759af9..0d039697fe2a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2311,6 +2311,7 @@ F: drivers/clocksource/cadence_ttc_timer.c F: drivers/i2c/busses/i2c-cadence.c F: drivers/mmc/host/sdhci-of-arasan.c F: drivers/edac/synopsys_edac.c +F: drivers/i2c/busses/i2c-xiic.c ARM64 PORT (AARCH64 ARCHITECTURE) M: Catalin Marinas <catalin.marinas@arm.com> @@ -5625,6 +5626,8 @@ 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 +6063,7 @@ 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 +7019,20 @@ 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.* @@ -8300,7 +8317,7 @@ 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/ @@ -11154,7 +11171,7 @@ 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 @@ -11346,10 +11363,10 @@ 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 @@ -12244,6 +12261,7 @@ F: Documentation/networking/rds.txt RDT - RESOURCE ALLOCATION M: Fenghua Yu <fenghua.yu@intel.com> +M: Reinette Chatre <reinette.chatre@intel.com> L: linux-kernel@vger.kernel.org S: Supported F: arch/x86/kernel/cpu/intel_rdt* @@ -13433,9 +13451,8 @@ F: drivers/i2c/busses/i2c-synquacer.c F: Documentation/devicetree/bindings/i2c/i2c-synquacer.txt SOCIONEXT UNIPHIER SOUND DRIVER -M: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Maintained +S: Orphan F: sound/soc/uniphier/ SOEKRIS NET48XX LED SUPPORT @@ -15905,6 +15922,7 @@ F: net/x25/ X86 ARCHITECTURE (32-BIT AND 64-BIT) M: Thomas Gleixner <tglx@linutronix.de> M: Ingo Molnar <mingo@redhat.com> +M: Borislav Petkov <bp@alien8.de> R: "H. Peter Anvin" <hpa@zytor.com> M: x86@kernel.org L: linux-kernel@vger.kernel.org @@ -15933,6 +15951,15 @@ M: Borislav Petkov <bp@alien8.de> S: Maintained F: arch/x86/kernel/cpu/microcode/* +X86 MM +M: Dave Hansen <dave.hansen@linux.intel.com> +M: Andy Lutomirski <luto@kernel.org> +M: Peter Zijlstra <peterz@infradead.org> +L: linux-kernel@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm +S: Maintained +F: arch/x86/mm/ + X86 PLATFORM DRIVERS M: Darren Hart <dvhart@infradead.org> M: Andy Shevchenko <andy@infradead.org> @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc5 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/arc/Kconfig b/arch/arc/Kconfig index 6d5eb8267e42..b4441b0764d7 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -9,6 +9,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SG_CHAIN @@ -28,8 +29,12 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK + select HAVE_DEBUG_STACKOVERFLOW select HAVE_FUTEX_CMPXCHG if FUTEX + select HAVE_GENERIC_DMA_COHERENT select HAVE_IOREMAP_PROT + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZMA select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_MEMBLOCK @@ -44,11 +49,6 @@ config ARC select OF_EARLY_FLATTREE select OF_RESERVED_MEM select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_GENERIC_DMA_COHERENT - select HAVE_KERNEL_GZIP - select HAVE_KERNEL_LZMA - select ARCH_HAS_PTE_SPECIAL config ARCH_HAS_CACHE_LINE_SIZE def_bool y diff --git a/arch/arc/Makefile b/arch/arc/Makefile index fb026196aaab..99cce77ab98f 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -43,10 +43,7 @@ ifdef CONFIG_ARC_CURR_IN_REG LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h endif -upto_gcc44 := $(call cc-ifversion, -le, 0404, y) -atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y) - -cflags-$(atleast_gcc44) += -fsection-anchors +cflags-y += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape @@ -82,11 +79,6 @@ cflags-$(disable_small_data) += -mno-sdata -fcall-used-gp cflags-$(CONFIG_CPU_BIG_ENDIAN) += -mbig-endian ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB -# STAR 9000518362: (fixed with binutils shipping with gcc 4.8) -# arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept -# --build-id w/o "-marclinux". Default arc-elf32-ld is OK -ldflags-$(upto_gcc44) += -marclinux - LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index dc91c663bcc0..d75d65ddf8e3 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -94,6 +94,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * The DW APB ICTL intc on MB is connected to CPU intc via a * DT "invisible" DW APB GPIO block, configured to simply pass thru * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c) diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 69ff4895f2ba..a05bb737ea63 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -101,6 +101,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * This INTC is actually connected to DW APB GPIO * which acts as a wire between MB INTC and CPU INTC. * GPIO INTC is configured in platform init code diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 47b74fbc403c..37bafd44e36d 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -9,6 +9,10 @@ */ / { + aliases { + ethernet = &gmac; + }; + axs10x_mb { compatible = "simple-bus"; #address-cells = <1>; @@ -68,7 +72,7 @@ }; }; - ethernet@0x18000 { + gmac: ethernet@0x18000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = < 0x18000 0x2000 >; @@ -81,6 +85,7 @@ max-speed = <100>; resets = <&creg_rst 5>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ }; ehci@0x40000 { diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 006aa3de5348..ef149f59929a 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -25,6 +25,10 @@ bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; }; + aliases { + ethernet = &gmac; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -163,7 +167,7 @@ #clock-cells = <0>; }; - ethernet@8000 { + gmac: ethernet@8000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; @@ -176,6 +180,8 @@ phy-handle = <&phy0>; resets = <&cgu_rst HSDK_ETH_RESET>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ + dma-coherent; mdio { #address-cells = <1>; @@ -194,12 +200,14 @@ compatible = "snps,hsdk-v1.0-ohci", "generic-ohci"; reg = <0x60000 0x100>; interrupts = <15>; + dma-coherent; }; ehci@40000 { compatible = "snps,hsdk-v1.0-ehci", "generic-ehci"; reg = <0x40000 0x100>; interrupts = <15>; + dma-coherent; }; mmc@a000 { @@ -212,6 +220,7 @@ clock-names = "biu", "ciu"; interrupts = <12>; bus-width = <4>; + dma-coherent; }; }; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index a635ea972304..41bc08be6a3b 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -63,7 +61,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index aa507e423075..1e1c4a8011b5 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -64,7 +62,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index eba07f468654..6b0c0cfd5c30 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -65,7 +63,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 098b19fbaa51..240dd2cd5148 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -57,7 +56,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 0104c404d897..14ae7e5acc7c 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -60,7 +59,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 6491be0ddbc9..1dec2b4bc5e6 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ_IDLE=y diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 7c9c706ae7f6..31ba224bbfb4 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -59,7 +59,6 @@ CONFIG_NETCONSOLE=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 99e05cf63fca..8e0b8b134cd9 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -44,7 +43,6 @@ CONFIG_LXT_PHY=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index 0dc4f9b737e7..739b90e5e893 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -45,7 +44,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index be3c30a15e54..b5895bdf3a93 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y @@ -44,7 +43,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 3a74b9b21772..f14eeff7d308 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -48,7 +47,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index ea2834b4dc1d..025298a48305 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -47,7 +46,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 80a5a1b4924b..df7b77b13b82 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -58,7 +57,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 2cc87f909747..a7f65313f84a 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -57,7 +57,6 @@ CONFIG_STMMAC_ETH=y # CONFIG_SERIO is not set # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index f629493929ea..db47c3541f15 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -53,7 +52,6 @@ CONFIG_NATIONAL_PHY=y CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 21f0ca26a05d..a8ac5e917d9a 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 4e0072730241..158af079838d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -84,7 +84,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ "1: llock %[orig], [%[ctr]] \n" \ " " #asm_op " %[val], %[orig], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ + " bnz 1b \n" \ : [val] "=&r" (val), \ [orig] "=&r" (orig) \ : [ctr] "r" (&v->counter), \ diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h new file mode 100644 index 000000000000..c946c0a83e76 --- /dev/null +++ b/arch/arc/include/asm/dma-mapping.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +// (C) 2018 Synopsys, Inc. (www.synopsys.com) + +#ifndef ASM_ARC_DMA_MAPPING_H +#define ASM_ARC_DMA_MAPPING_H + +#include <asm-generic/dma-mapping.h> + +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent); +#define arch_setup_dma_ops arch_setup_dma_ops + +#endif diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 783b20354f8b..e8d9fb452346 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -83,9 +83,6 @@ done: static void show_faulting_vma(unsigned long address, char *buf) { struct vm_area_struct *vma; - struct inode *inode; - unsigned long ino = 0; - dev_t dev = 0; char *nm = buf; struct mm_struct *active_mm = current->active_mm; @@ -99,12 +96,10 @@ static void show_faulting_vma(unsigned long address, char *buf) * if the container VMA is not found */ if (vma && (vma->vm_start <= address)) { - struct file *file = vma->vm_file; - if (file) { - nm = file_path(file, buf, PAGE_SIZE - 1); - inode = file_inode(vma->vm_file); - dev = inode->i_sb->s_dev; - ino = inode->i_ino; + if (vma->vm_file) { + nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1); + if (IS_ERR(nm)) + nm = "?"; } pr_info(" @off 0x%lx in [%s]\n" " VMA: 0x%08lx to 0x%08lx\n", diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 25c631942500..f2701c13a66b 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -65,7 +65,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n", perip_base, - IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency ")); + IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency (per-device) ")); return buf; } @@ -897,15 +897,6 @@ static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz) } /* - * DMA ops for systems with IOC - * IOC hardware snoops all DMA traffic keeping the caches consistent with - * memory - eliding need for any explicit cache maintenance of DMA buffers - */ -static void __dma_cache_wback_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_wback_ioc(phys_addr_t start, unsigned long sz) {} - -/* * Exported DMA API */ void dma_cache_wback_inv(phys_addr_t start, unsigned long sz) @@ -1153,6 +1144,19 @@ noinline void __init arc_ioc_setup(void) { unsigned int ioc_base, mem_sz; + /* + * As for today we don't support both IOC and ZONE_HIGHMEM enabled + * simultaneously. This happens because as of today IOC aperture covers + * only ZONE_NORMAL (low mem) and any dma transactions outside this + * region won't be HW coherent. + * If we want to use both IOC and ZONE_HIGHMEM we can use + * bounce_buffer to handle dma transactions to HIGHMEM. + * Also it is possible to modify dma_direct cache ops or increase IOC + * aperture size if we are planning to use HIGHMEM without PAE. + */ + if (IS_ENABLED(CONFIG_HIGHMEM)) + panic("IOC and HIGHMEM can't be used simultaneously"); + /* Flush + invalidate + disable L1 dcache */ __dc_disable(); @@ -1264,11 +1268,7 @@ void __init arc_cache_init_master(void) if (is_isa_arcv2() && ioc_enable) arc_ioc_setup(); - if (is_isa_arcv2() && ioc_enable) { - __dma_cache_wback_inv = __dma_cache_wback_inv_ioc; - __dma_cache_inv = __dma_cache_inv_ioc; - __dma_cache_wback = __dma_cache_wback_ioc; - } else if (is_isa_arcv2() && l2_line_sz && slc_enable) { + if (is_isa_arcv2() && l2_line_sz && slc_enable) { __dma_cache_wback_inv = __dma_cache_wback_inv_slc; __dma_cache_inv = __dma_cache_inv_slc; __dma_cache_wback = __dma_cache_wback_slc; @@ -1277,6 +1277,12 @@ void __init arc_cache_init_master(void) __dma_cache_inv = __dma_cache_inv_l1; __dma_cache_wback = __dma_cache_wback_l1; } + /* + * In case of IOC (say IOC+SLC case), pointers above could still be set + * but end up not being relevant as the first function in chain is not + * called at all for @dma_direct_ops + * arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*() + */ } void __ref arc_cache_init(void) diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index ec47e6079f5d..c75d5c3470e3 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -6,20 +6,17 @@ * published by the Free Software Foundation. */ -/* - * DMA Coherent API Notes - * - * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is - * implemented by accessing it using a kernel virtual address, with - * Cache bit off in the TLB entry. - * - * The default DMA address == Phy address which is 0x8000_0000 based. - */ - #include <linux/dma-noncoherent.h> #include <asm/cache.h> #include <asm/cacheflush.h> +/* + * ARCH specific callbacks for generic noncoherent DMA ops (dma/noncoherent.c) + * - hardware IOC not available (or "dma-coherent" not set for device in DT) + * - But still handle both coherent and non-coherent requests from caller + * + * For DMA coherent hardware (IOC) generic code suffices + */ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { @@ -27,42 +24,29 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, struct page *page; phys_addr_t paddr; void *kvaddr; - int need_coh = 1, need_kvaddr = 0; - - page = alloc_pages(gfp, order); - if (!page) - return NULL; + bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT); /* - * IOC relies on all data (even coherent DMA data) being in cache - * Thus allocate normal cached memory - * - * The gains with IOC are two pronged: - * -For streaming data, elides need for cache maintenance, saving - * cycles in flush code, and bus bandwidth as all the lines of a - * buffer need to be flushed out to memory - * -For coherent data, Read/Write to buffers terminate early in cache - * (vs. always going to memory - thus are faster) + * __GFP_HIGHMEM flag is cleared by upper layer functions + * (in include/linux/dma-mapping.h) so we should never get a + * __GFP_HIGHMEM here. */ - if ((is_isa_arcv2() && ioc_enable) || - (attrs & DMA_ATTR_NON_CONSISTENT)) - need_coh = 0; + BUG_ON(gfp & __GFP_HIGHMEM); - /* - * - A coherent buffer needs MMU mapping to enforce non-cachability - * - A highmem page needs a virtual handle (hence MMU mapping) - * independent of cachability - */ - if (PageHighMem(page) || need_coh) - need_kvaddr = 1; + page = alloc_pages(gfp, order); + if (!page) + return NULL; /* This is linear addr (0x8000_0000 based) */ paddr = page_to_phys(page); *dma_handle = paddr; - /* This is kernel Virtual address (0x7000_0000 based) */ - if (need_kvaddr) { + /* + * A coherent buffer needs MMU mapping to enforce non-cachability. + * kvaddr is kernel Virtual address (0x7000_0000 based). + */ + if (need_coh) { kvaddr = ioremap_nocache(paddr, size); if (kvaddr == NULL) { __free_pages(page, order); @@ -93,12 +77,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, { phys_addr_t paddr = dma_handle; struct page *page = virt_to_page(paddr); - int is_non_coh = 1; - - is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) || - (is_isa_arcv2() && ioc_enable); - if (PageHighMem(page) || !is_non_coh) + if (!(attrs & DMA_ATTR_NON_CONSISTENT)) iounmap((void __force __iomem *)vaddr); __free_pages(page, get_order(size)); @@ -185,3 +165,23 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, break; } } + +/* + * Plug in coherent or noncoherent dma ops + */ +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent) +{ + /* + * IOC hardware snoops all DMA traffic keeping the caches consistent + * with memory - eliding need for any explicit cache maintenance of + * DMA buffers - so we can use dma_direct cache ops. + */ + if (is_isa_arcv2() && ioc_enable && coherent) { + set_dma_ops(dev, &dma_direct_ops); + dev_info(dev, "use dma_direct_ops cache ops\n"); + } else { + set_dma_ops(dev, &dma_noncoherent_ops); + dev_info(dev, "use dma_noncoherent_ops cache ops\n"); + } +} 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/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 79906cecb091..3ad482d2f1eb 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -223,7 +223,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts index ceffc40810ee..48daec7f78ba 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts @@ -46,6 +46,7 @@ pinctrl-0 = <&mmc0_pins>; vmmc-supply = <®_cldo1>; cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; + bus-width = <4>; status = "okay"; }; @@ -56,6 +57,7 @@ vqmmc-supply = <®_bldo2>; non-removable; cap-mmc-hw-reset; + bus-width = <8>; status = "okay"; }; 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/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f26055f2306e..3d6d7336f871 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -61,8 +61,7 @@ struct kvm_arch { u64 vmid_gen; u32 vmid; - /* 1-level 2nd stage table and lock */ - spinlock_t pgd_lock; + /* 1-level 2nd stage table, protected by kvm->mmu_lock */ pgd_t *pgd; /* VTTBR value associated with above pgd and vmid */ @@ -357,7 +356,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); 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/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index d496ef579859..ca46153d7915 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -98,8 +98,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; val &= ~CPACR_EL1_ZEN; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val &= ~CPACR_EL1_FPEN; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cpacr_el1); @@ -114,8 +116,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) val = CPTR_EL2_DEFAULT; val |= CPTR_EL2_TTA | CPTR_EL2_TZ; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val |= CPTR_EL2_TFP; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cptr_el2); } @@ -129,7 +133,6 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); - __activate_traps_fpsimd32(vcpu); if (has_vhe()) activate_traps_vhe(vcpu); else diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 65f86271f02b..8080c9f489c3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -985,8 +985,9 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) pmd = READ_ONCE(*pmdp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pmd_present(pmd) || !pmd_table(pmd)) { + if (!pmd_present(pmd)) + return 1; + if (!pmd_table(pmd)) { VM_WARN_ON(!pmd_table(pmd)); return 1; } @@ -1007,8 +1008,9 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pud = READ_ONCE(*pudp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pud_present(pud) || !pud_table(pud)) { + if (!pud_present(pud)) + return 1; + if (!pud_table(pud)) { VM_WARN_ON(!pud_table(pud)); return 1; } 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/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 70dde040779b..f5453d944ff5 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -172,7 +172,7 @@ void __init cf_bootmem_alloc(void) high_memory = (void *)_ramend; /* Reserve kernel text/data/bss */ - memblock_reserve(memstart, memstart - _rambase); + memblock_reserve(_rambase, memstart - _rambase); m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index a9af1d2dcd69..2c1c53d12179 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -931,7 +931,6 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, bool write); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h index 4901833498f7..8441b2698e64 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h +++ b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h @@ -40,6 +40,7 @@ struct ltq_dma_channel { int desc; /* the current descriptor */ struct ltq_dma_desc *desc_base; /* the descriptor base */ int phys; /* physical addr */ + struct device *dev; }; enum { diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 019035d7225c..8f845f6e5f42 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/init.h> #include <linux/ioport.h> +#include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> @@ -20,6 +21,7 @@ #include <asm/abi.h> #include <asm/mips-cps.h> +#include <asm/page.h> #include <asm/vdso.h> /* Kernel-provided data used by the VDSO. */ @@ -128,12 +130,30 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) vvar_size = gic_size + PAGE_SIZE; size = vvar_size + image->size; + /* + * Find a region that's large enough for us to perform the + * colour-matching alignment below. + */ + if (cpu_has_dc_aliases) + size += shm_align_mask + 1; + base = get_unmapped_area(NULL, 0, size, 0, 0); if (IS_ERR_VALUE(base)) { ret = base; goto out; } + /* + * If we suffer from dcache aliasing, ensure that the VDSO data page + * mapping is coloured the same as the kernel's mapping of that memory. + * This ensures that when the kernel updates the VDSO data userland + * will observe it without requiring cache invalidations. + */ + if (cpu_has_dc_aliases) { + base = __ALIGN_MASK(base, shm_align_mask); + base += ((unsigned long)&vdso_data - gic_size) & shm_align_mask; + } + data_addr = base + gic_size; vdso_addr = data_addr + PAGE_SIZE; diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index ee64db032793..d8dcdb350405 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -512,16 +512,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - unsigned long end = hva + PAGE_SIZE; - - handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); - - kvm_mips_callbacks->flush_shadow_all(kvm); - return 0; -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c index 4b9fbb6744ad..664f2f7f55c1 100644 --- a/arch/mips/lantiq/xway/dma.c +++ b/arch/mips/lantiq/xway/dma.c @@ -130,7 +130,7 @@ ltq_dma_alloc(struct ltq_dma_channel *ch) unsigned long flags; ch->desc = 0; - ch->desc_base = dma_zalloc_coherent(NULL, + ch->desc_base = dma_zalloc_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, &ch->phys, GFP_ATOMIC); @@ -182,7 +182,7 @@ ltq_dma_free(struct ltq_dma_channel *ch) if (!ch->desc_base) return; ltq_dma_close(ch); - dma_free_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE, + dma_free_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, ch->desc_base, ch->phys); } EXPORT_SYMBOL_GPL(ltq_dma_free); diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 1d4248fa55e9..7068f341133d 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -40,6 +40,10 @@ config NDS32 select NO_IOPORT_MAP select RTC_LIB select THREAD_INFO_IN_TASK + select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE help Andes(nds32) Linux support. diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index 63f4f173e5f4..3509fac10491 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -5,6 +5,10 @@ KBUILD_DEFCONFIG := defconfig comma = , +ifdef CONFIG_FUNCTION_TRACER +arch-y += -malways-save-lp -mno-relax +endif + KBUILD_CFLAGS += $(call cc-option, -mno-sched-prolog-epilog) KBUILD_CFLAGS += -mcmodel=large diff --git a/arch/nds32/include/asm/elf.h b/arch/nds32/include/asm/elf.h index 56c479058802..f5f9cf7e0544 100644 --- a/arch/nds32/include/asm/elf.h +++ b/arch/nds32/include/asm/elf.h @@ -121,9 +121,9 @@ struct elf32_hdr; */ #define ELF_CLASS ELFCLASS32 #ifdef __NDS32_EB__ -#define ELF_DATA ELFDATA2MSB; +#define ELF_DATA ELFDATA2MSB #else -#define ELF_DATA ELFDATA2LSB; +#define ELF_DATA ELFDATA2LSB #endif #define ELF_ARCH EM_NDS32 #define USE_ELF_CORE_DUMP diff --git a/arch/nds32/include/asm/ftrace.h b/arch/nds32/include/asm/ftrace.h new file mode 100644 index 000000000000..2f96cc96aa35 --- /dev/null +++ b/arch/nds32/include/asm/ftrace.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_NDS32_FTRACE_H +#define __ASM_NDS32_FTRACE_H + +#ifdef CONFIG_FUNCTION_TRACER + +#define HAVE_FUNCTION_GRAPH_FP_TEST + +#define MCOUNT_ADDR ((unsigned long)(_mcount)) +/* mcount call is composed of three instructions: + * sethi + ori + jral + */ +#define MCOUNT_INSN_SIZE 12 + +extern void _mcount(unsigned long parent_ip); + +#ifdef CONFIG_DYNAMIC_FTRACE + +#define FTRACE_ADDR ((unsigned long)_ftrace_caller) + +#ifdef __NDS32_EL__ +#define INSN_NOP 0x09000040 +#define INSN_SIZE(insn) (((insn & 0x00000080) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0x000000fe) == 0x00000046) +#define ENDIAN_CONVERT(insn) be32_to_cpu(insn) +#else /* __NDS32_EB__ */ +#define INSN_NOP 0x40000009 +#define INSN_SIZE(insn) (((insn & 0x80000000) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0xfe000000) == 0x46000000) +#define ENDIAN_CONVERT(insn) (insn) +#endif + +extern void _ftrace_caller(unsigned long parent_ip); +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} +struct dyn_arch_ftrace { +}; + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif /* __ASM_NDS32_FTRACE_H */ diff --git a/arch/nds32/include/asm/nds32.h b/arch/nds32/include/asm/nds32.h index 19b19394a936..68c38151c3e4 100644 --- a/arch/nds32/include/asm/nds32.h +++ b/arch/nds32/include/asm/nds32.h @@ -17,6 +17,7 @@ #else #define FP_OFFSET (-2) #endif +#define LP_OFFSET (-1) extern void __init early_trap_init(void); static inline void GIE_ENABLE(void) diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h index 18a009f3804d..362a32d9bd16 100644 --- a/arch/nds32/include/asm/uaccess.h +++ b/arch/nds32/include/asm/uaccess.h @@ -38,7 +38,7 @@ struct exception_table_entry { extern int fixup_exception(struct pt_regs *regs); #define KERNEL_DS ((mm_segment_t) { ~0UL }) -#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) +#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) #define get_ds() (KERNEL_DS) #define get_fs() (current_thread_info()->addr_limit) @@ -49,11 +49,11 @@ static inline void set_fs(mm_segment_t fs) current_thread_info()->addr_limit = fs; } -#define segment_eq(a, b) ((a) == (b)) +#define segment_eq(a, b) ((a) == (b)) #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size)) -#define access_ok(type, addr, size) \ +#define access_ok(type, addr, size) \ __range_ok((unsigned long)addr, (unsigned long)size) /* * Single-value transfer routines. They automatically use the right @@ -75,70 +75,73 @@ static inline void set_fs(mm_segment_t fs) * versions are void (ie, don't return a value as such). */ -#define get_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_READ, p, sizeof(*p)))) { \ - __e = __get_user(x,p); \ - } else \ - x = 0; \ - __e; \ -}) -#define __get_user(x,ptr) \ +#define get_user __get_user \ + +#define __get_user(x, ptr) \ ({ \ long __gu_err = 0; \ - __get_user_err((x),(ptr),__gu_err); \ + __get_user_check((x), (ptr), __gu_err); \ __gu_err; \ }) -#define __get_user_error(x,ptr,err) \ +#define __get_user_error(x, ptr, err) \ ({ \ - __get_user_err((x),(ptr),err); \ - (void) 0; \ + __get_user_check((x), (ptr), (err)); \ + (void)0; \ }) -#define __get_user_err(x,ptr,err) \ +#define __get_user_check(x, ptr, err) \ +({ \ + const __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_READ, __p, sizeof(*__p))) { \ + __get_user_err((x), __p, (err)); \ + } else { \ + (x) = 0; (err) = -EFAULT; \ + } \ +}) + +#define __get_user_err(x, ptr, err) \ do { \ - unsigned long __gu_addr = (unsigned long)(ptr); \ unsigned long __gu_val; \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm("lbi",__gu_val,__gu_addr,err); \ + __get_user_asm("lbi", __gu_val, (ptr), (err)); \ break; \ case 2: \ - __get_user_asm("lhi",__gu_val,__gu_addr,err); \ + __get_user_asm("lhi", __gu_val, (ptr), (err)); \ break; \ case 4: \ - __get_user_asm("lwi",__gu_val,__gu_addr,err); \ + __get_user_asm("lwi", __gu_val, (ptr), (err)); \ break; \ case 8: \ - __get_user_asm_dword(__gu_val,__gu_addr,err); \ + __get_user_asm_dword(__gu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ break; \ } \ - (x) = (__typeof__(*(ptr)))__gu_val; \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) -#define __get_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " move %1, #0\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err), "=&r" (x) \ - : "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __get_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " move %1, #0\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err), "=&r" (x) \ + : "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __gu_reg_oper0 "%H1" @@ -149,61 +152,66 @@ do { \ #endif #define __get_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ - "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err), "=&r"(x) \ - : "r"(addr), "i"(-EFAULT) \ - : "cc") -#define put_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_WRITE, p, sizeof(*p)))) { \ - __e = __put_user(x,p); \ - } \ - __e; \ -}) -#define __put_user(x,ptr) \ + __asm__ __volatile__ ( \ + "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ + "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err), "=&r"(x) \ + : "r"(addr), "i"(-EFAULT) \ + : "cc") + +#define put_user __put_user \ + +#define __put_user(x, ptr) \ ({ \ long __pu_err = 0; \ - __put_user_err((x),(ptr),__pu_err); \ + __put_user_err((x), (ptr), __pu_err); \ __pu_err; \ }) -#define __put_user_error(x,ptr,err) \ +#define __put_user_error(x, ptr, err) \ +({ \ + __put_user_err((x), (ptr), (err)); \ + (void)0; \ +}) + +#define __put_user_check(x, ptr, err) \ ({ \ - __put_user_err((x),(ptr),err); \ - (void) 0; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) { \ + __put_user_err((x), __p, (err)); \ + } else { \ + (err) = -EFAULT; \ + } \ }) -#define __put_user_err(x,ptr,err) \ +#define __put_user_err(x, ptr, err) \ do { \ - unsigned long __pu_addr = (unsigned long)(ptr); \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __put_user_asm("sbi",__pu_val,__pu_addr,err); \ + __put_user_asm("sbi", __pu_val, (ptr), (err)); \ break; \ case 2: \ - __put_user_asm("shi",__pu_val,__pu_addr,err); \ + __put_user_asm("shi", __pu_val, (ptr), (err)); \ break; \ case 4: \ - __put_user_asm("swi",__pu_val,__pu_addr,err); \ + __put_user_asm("swi", __pu_val, (ptr), (err)); \ break; \ case 8: \ - __put_user_asm_dword(__pu_val,__pu_addr,err); \ + __put_user_asm_dword(__pu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ @@ -211,22 +219,22 @@ do { \ } \ } while (0) -#define __put_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err) \ - : "r" (x), "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __put_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err) \ + : "r" (x), "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __pu_reg_oper0 "%H2" @@ -237,23 +245,24 @@ do { \ #endif #define __put_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ - "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err) \ - : "r"(addr), "r"(x), "i"(-EFAULT) \ - : "cc") + __asm__ __volatile__ ( \ + "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ + "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err) \ + : "r"(addr), "r"(x), "i"(-EFAULT) \ + : "cc") + extern unsigned long __arch_clear_user(void __user * addr, unsigned long n); extern long strncpy_from_user(char *dest, const char __user * src, long count); extern __must_check long strlen_user(const char __user * str); diff --git a/arch/nds32/kernel/Makefile b/arch/nds32/kernel/Makefile index 42792743e8b9..27cded39fa66 100644 --- a/arch/nds32/kernel/Makefile +++ b/arch/nds32/kernel/Makefile @@ -21,3 +21,9 @@ extra-y := head.o vmlinux.lds obj-y += vdso/ + +obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +endif diff --git a/arch/nds32/kernel/atl2c.c b/arch/nds32/kernel/atl2c.c index 0c6d031a1c4a..0c5386e72098 100644 --- a/arch/nds32/kernel/atl2c.c +++ b/arch/nds32/kernel/atl2c.c @@ -9,7 +9,8 @@ void __iomem *atl2c_base; static const struct of_device_id atl2c_ids[] __initconst = { - {.compatible = "andestech,atl2c",} + {.compatible = "andestech,atl2c",}, + {} }; static int __init atl2c_of_init(void) diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S index b8ae4e9a6b93..21a144071566 100644 --- a/arch/nds32/kernel/ex-entry.S +++ b/arch/nds32/kernel/ex-entry.S @@ -118,7 +118,7 @@ common_exception_handler: /* interrupt */ 2: #ifdef CONFIG_TRACE_IRQFLAGS - jal trace_hardirqs_off + jal __trace_hardirqs_off #endif move $r0, $sp sethi $lp, hi20(ret_from_intr) diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S index 03e4f7788a18..f00af92f7e22 100644 --- a/arch/nds32/kernel/ex-exit.S +++ b/arch/nds32/kernel/ex-exit.S @@ -138,8 +138,8 @@ no_work_pending: #ifdef CONFIG_TRACE_IRQFLAGS lwi $p0, [$sp+(#IPSW_OFFSET)] andi $p0, $p0, #0x1 - la $r10, trace_hardirqs_off - la $r9, trace_hardirqs_on + la $r10, __trace_hardirqs_off + la $r9, __trace_hardirqs_on cmovz $r9, $p0, $r10 jral $r9 #endif diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c new file mode 100644 index 000000000000..a0a9679ad5de --- /dev/null +++ b/arch/nds32/kernel/ftrace.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/ftrace.h> +#include <linux/uaccess.h> +#include <asm/cacheflush.h> + +#ifndef CONFIG_DYNAMIC_FTRACE +extern void (*ftrace_trace_function)(unsigned long, unsigned long, + struct ftrace_ops*, struct pt_regs*); +extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace); +extern void ftrace_graph_caller(void); + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void _mcount(unsigned long parent_ip) +{ + /* save all state by the compiler prologue */ + + unsigned long ip = (unsigned long)__builtin_return_address(0); + + if (ftrace_trace_function != ftrace_stub) + ftrace_trace_function(ip - MCOUNT_INSN_SIZE, parent_ip, + NULL, NULL); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (ftrace_graph_return != (trace_func_graph_ret_t)ftrace_stub + || ftrace_graph_entry != ftrace_graph_entry_stub) + ftrace_graph_caller(); +#endif + + /* restore all state by the compiler epilogue */ +} +EXPORT_SYMBOL(_mcount); + +#else /* CONFIG_DYNAMIC_FTRACE */ + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void __naked _mcount(unsigned long parent_ip) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} +EXPORT_SYMBOL(_mcount); + +#define XSTR(s) STR(s) +#define STR(s) #s +void _ftrace_caller(unsigned long parent_ip) +{ + /* save all state needed by the compiler prologue */ + + /* + * prepare arguments for real tracing function + * first arg : __builtin_return_address(0) - MCOUNT_INSN_SIZE + * second arg : parent_ip + */ + __asm__ __volatile__ ( + "move $r1, %0 \n\t" + "addi $r0, %1, #-" XSTR(MCOUNT_INSN_SIZE) "\n\t" + : + : "r" (parent_ip), "r" (__builtin_return_address(0))); + + /* a placeholder for the call to a real tracing function */ + __asm__ __volatile__ ( + "ftrace_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* a placeholder for the call to ftrace_graph_caller */ + __asm__ __volatile__ ( + "ftrace_graph_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); +#endif + /* restore all state needed by the compiler epilogue */ +} + +int __init ftrace_dyn_arch_init(void) +{ + return 0; +} + +int ftrace_arch_code_modify_prepare(void) +{ + set_all_modules_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_all_modules_text_ro(); + return 0; +} + +static unsigned long gen_sethi_insn(unsigned long addr) +{ + unsigned long opcode = 0x46000000; + unsigned long imm = addr >> 12; + unsigned long rt_num = 0xf << 20; + + return ENDIAN_CONVERT(opcode | rt_num | imm); +} + +static unsigned long gen_ori_insn(unsigned long addr) +{ + unsigned long opcode = 0x58000000; + unsigned long imm = addr & 0x0000fff; + unsigned long rt_num = 0xf << 20; + unsigned long ra_num = 0xf << 15; + + return ENDIAN_CONVERT(opcode | rt_num | ra_num | imm); +} + +static unsigned long gen_jral_insn(unsigned long addr) +{ + unsigned long opcode = 0x4a000001; + unsigned long rt_num = 0x1e << 20; + unsigned long rb_num = 0xf << 10; + + return ENDIAN_CONVERT(opcode | rt_num | rb_num); +} + +static void ftrace_gen_call_insn(unsigned long *call_insns, + unsigned long addr) +{ + call_insns[0] = gen_sethi_insn(addr); /* sethi $r15, imm20u */ + call_insns[1] = gen_ori_insn(addr); /* ori $r15, $r15, imm15u */ + call_insns[2] = gen_jral_insn(addr); /* jral $lp, $r15 */ +} + +static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + unsigned long orig_insn[3]; + + if (validate) { + if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE)) + return -EFAULT; + if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE)) + return -EINVAL; + } + + if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} + +static int ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + int ret; + + ret = __ftrace_modify_code(pc, old_insn, new_insn, validate); + if (ret) + return ret; + + flush_icache_range(pc, pc + MCOUNT_INSN_SIZE); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long pc = (unsigned long)&ftrace_call; + unsigned long old_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long new_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + if (func != ftrace_stub) + ftrace_gen_call_insn(new_insn, (unsigned long)func); + + return ftrace_modify_code(pc, old_insn, new_insn, false); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, nop_insn, call_insn, true); +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + struct ftrace_graph_ent trace; + unsigned long old; + int err; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + return; + + err = ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer, NULL); + + if (err == -EBUSY) + return; + + *parent = return_hooker; +} + +noinline void ftrace_graph_caller(void) +{ + unsigned long *parent_ip = + (unsigned long *)(__builtin_frame_address(2) - 4); + + unsigned long selfpc = + (unsigned long)(__builtin_return_address(1) - MCOUNT_INSN_SIZE); + + unsigned long frame_pointer = + (unsigned long)__builtin_frame_address(3); + + prepare_ftrace_return(parent_ip, selfpc, frame_pointer); +} + +extern unsigned long ftrace_return_to_handler(unsigned long frame_pointer); +void __naked return_to_handler(void) +{ + __asm__ __volatile__ ( + /* save state needed by the ABI */ + "smw.adm $r0,[$sp],$r1,#0x0 \n\t" + + /* get original return address */ + "move $r0, $fp \n\t" + "bal ftrace_return_to_handler\n\t" + "move $lp, $r0 \n\t" + + /* restore state nedded by the ABI */ + "lmw.bim $r0,[$sp],$r1,#0x0 \n\t"); +} + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_graph_call; + +static int ftrace_modify_graph_caller(bool enable) +{ + unsigned long pc = (unsigned long)&ftrace_graph_call; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, (unsigned long)ftrace_graph_caller); + + if (enable) + return ftrace_modify_code(pc, nop_insn, call_insn, true); + else + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(false); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + +#ifdef CONFIG_TRACE_IRQFLAGS +noinline void __trace_hardirqs_off(void) +{ + trace_hardirqs_off(); +} +noinline void __trace_hardirqs_on(void) +{ + trace_hardirqs_on(); +} +#endif /* CONFIG_TRACE_IRQFLAGS */ diff --git a/arch/nds32/kernel/module.c b/arch/nds32/kernel/module.c index 4167283d8293..1e31829cbc2a 100644 --- a/arch/nds32/kernel/module.c +++ b/arch/nds32/kernel/module.c @@ -40,7 +40,7 @@ void do_reloc16(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { @@ -70,7 +70,7 @@ void do_reloc32(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { diff --git a/arch/nds32/kernel/stacktrace.c b/arch/nds32/kernel/stacktrace.c index 8b231e910ea6..d974c0c1c65f 100644 --- a/arch/nds32/kernel/stacktrace.c +++ b/arch/nds32/kernel/stacktrace.c @@ -4,6 +4,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <linux/ftrace.h> void save_stack_trace(struct stack_trace *trace) { @@ -16,6 +17,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) unsigned long *fpn; int skip = trace->skip; int savesched; + int graph_idx = 0; if (tsk == current) { __asm__ __volatile__("\tori\t%0, $fp, #0\n":"=r"(fpn)); @@ -29,10 +31,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) && (fpn >= (unsigned long *)TASK_SIZE)) { unsigned long lpp, fpp; - lpp = fpn[-1]; + lpp = fpn[LP_OFFSET]; fpp = fpn[FP_OFFSET]; if (!__kernel_text_address(lpp)) break; + else + lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL); if (savesched || !in_sched_functions(lpp)) { if (skip) { diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index a6205fd4db52..1496aab48998 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -8,6 +8,7 @@ #include <linux/kdebug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> +#include <linux/ftrace.h> #include <asm/proc-fns.h> #include <asm/unistd.h> @@ -94,28 +95,6 @@ static void dump_instr(struct pt_regs *regs) set_fs(fs); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -#include <linux/ftrace.h> -static void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ - if (*addr == (unsigned long)return_to_handler) { - int index = tsk->curr_ret_stack; - - if (tsk->ret_stack && index >= *graph) { - index -= *graph; - *addr = tsk->ret_stack[index].ret; - (*graph)++; - } - } -} -#else -static inline void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ -} -#endif - #define LOOP_TIMES (100) static void __dump(struct task_struct *tsk, unsigned long *base_reg) { @@ -126,7 +105,8 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) while (!kstack_end(base_reg)) { ret_addr = *base_reg++; if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -137,15 +117,12 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) !((unsigned long)base_reg & 0x3) && ((unsigned long)base_reg >= TASK_SIZE)) { unsigned long next_fp; -#if !defined(NDS32_ABI_2) - ret_addr = base_reg[0]; - next_fp = base_reg[1]; -#else - ret_addr = base_reg[-1]; + ret_addr = base_reg[LP_OFFSET]; next_fp = base_reg[FP_OFFSET]; -#endif if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -196,11 +173,10 @@ void die(const char *str, struct pt_regs *regs, int err) pr_emerg("CPU: %i\n", smp_processor_id()); show_regs(regs); pr_emerg("Process %s (pid: %d, stack limit = 0x%p)\n", - tsk->comm, tsk->pid, task_thread_info(tsk) + 1); + tsk->comm, tsk->pid, end_of_stack(tsk)); if (!user_mode(regs) || in_interrupt()) { - dump_mem("Stack: ", regs->sp, - THREAD_SIZE + (unsigned long)task_thread_info(tsk)); + dump_mem("Stack: ", regs->sp, (regs->sp + PAGE_SIZE) & PAGE_MASK); dump_instr(regs); dump_stack(); } diff --git a/arch/nds32/kernel/vmlinux.lds.S b/arch/nds32/kernel/vmlinux.lds.S index 288313b886ef..9e90f30a181d 100644 --- a/arch/nds32/kernel/vmlinux.lds.S +++ b/arch/nds32/kernel/vmlinux.lds.S @@ -13,14 +13,26 @@ OUTPUT_ARCH(nds32) ENTRY(_stext_lma) jiffies = jiffies_64; +#if defined(CONFIG_GCOV_KERNEL) +#define NDS32_EXIT_KEEP(x) x +#else +#define NDS32_EXIT_KEEP(x) +#endif + SECTIONS { _stext_lma = TEXTADDR - LOAD_OFFSET; . = TEXTADDR; __init_begin = .; HEAD_TEXT_SECTION + .exit.text : { + NDS32_EXIT_KEEP(EXIT_TEXT) + } INIT_TEXT_SECTION(PAGE_SIZE) INIT_DATA_SECTION(16) + .exit.data : { + NDS32_EXIT_KEEP(EXIT_DATA) + } PERCPU_SECTION(L1_CACHE_BYTES) __init_end = .; diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 13a688fc8cd0..2fdc865ca374 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1051,7 +1051,6 @@ static inline void vmemmap_remove_mapping(unsigned long start, return hash__vmemmap_remove_mapping(start, page_size); } #endif -struct page *realmode_pfn_to_page(unsigned long pfn); static inline pte_t pmd_pte(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index ab3a4fba38e3..3d4b88cb8599 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -220,8 +220,6 @@ extern void iommu_del_device(struct device *dev); extern int __init tce_iommu_bus_notifier_init(void); extern long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); -extern long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction); #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index b2f89b621b15..b694d6af1150 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -38,6 +38,7 @@ extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, unsigned long ua, unsigned int pageshift, unsigned long *hpa); +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua); extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem); extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem); #endif diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index af7a20dc6e09..19b4c628f3be 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1013,31 +1013,6 @@ long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry, } EXPORT_SYMBOL_GPL(iommu_tce_xchg); -#ifdef CONFIG_PPC_BOOK3S_64 -long iommu_tce_xchg_rm(struct iommu_table *tbl, unsigned long entry, - unsigned long *hpa, enum dma_data_direction *direction) -{ - long ret; - - ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - - if (!ret && ((*direction == DMA_FROM_DEVICE) || - (*direction == DMA_BIDIRECTIONAL))) { - struct page *pg = realmode_pfn_to_page(*hpa >> PAGE_SHIFT); - - if (likely(pg)) { - SetPageDirty(pg); - } else { - tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); - ret = -EFAULT; - } - } - - return ret; -} -EXPORT_SYMBOL_GPL(iommu_tce_xchg_rm); -#endif - int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 3c0e8fb2b773..68e14afecac8 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -358,7 +358,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long pp, key; unsigned long v, orig_v, gr; __be64 *hptep; - int index; + long int index; int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); if (kvm_is_radix(vcpu->kvm)) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 0af1c0aea1fe..933c574e1cf7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -525,8 +525,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned long ea, unsigned long dsisr) { struct kvm *kvm = vcpu->kvm; - unsigned long mmu_seq, pte_size; - unsigned long gpa, gfn, hva, pfn; + unsigned long mmu_seq; + unsigned long gpa, gfn, hva; struct kvm_memory_slot *memslot; struct page *page = NULL; long ret; @@ -623,9 +623,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, */ hva = gfn_to_hva_memslot(memslot, gfn); if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) { - pfn = page_to_pfn(page); upgrade_write = true; } else { + unsigned long pfn; + /* Call KVM generic code to do the slow-path check */ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL, writing, upgrade_p); @@ -639,63 +640,45 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, } } - /* See if we can insert a 1GB or 2MB large PTE here */ - level = 0; - if (page && PageCompound(page)) { - pte_size = PAGE_SIZE << compound_order(compound_head(page)); - if (pte_size >= PUD_SIZE && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1); - } else if (pte_size >= PMD_SIZE && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1); - } - } - /* - * Compute the PTE value that we need to insert. + * Read the PTE from the process' radix tree and use that + * so we get the shift and attribute bits. */ - if (page) { - pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE | - _PAGE_ACCESSED; - if (writing || upgrade_write) - pgflags |= _PAGE_WRITE | _PAGE_DIRTY; - pte = pfn_pte(pfn, __pgprot(pgflags)); + local_irq_disable(); + ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); + pte = *ptep; + local_irq_enable(); + + /* Get pte level from shift/size */ + if (shift == PUD_SHIFT && + (gpa & (PUD_SIZE - PAGE_SIZE)) == + (hva & (PUD_SIZE - PAGE_SIZE))) { + level = 2; + } else if (shift == PMD_SHIFT && + (gpa & (PMD_SIZE - PAGE_SIZE)) == + (hva & (PMD_SIZE - PAGE_SIZE))) { + level = 1; } else { - /* - * Read the PTE from the process' radix tree and use that - * so we get the attribute bits. - */ - local_irq_disable(); - ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift); - pte = *ptep; - local_irq_enable(); - if (shift == PUD_SHIFT && - (gpa & (PUD_SIZE - PAGE_SIZE)) == - (hva & (PUD_SIZE - PAGE_SIZE))) { - level = 2; - } else if (shift == PMD_SHIFT && - (gpa & (PMD_SIZE - PAGE_SIZE)) == - (hva & (PMD_SIZE - PAGE_SIZE))) { - level = 1; - } else if (shift && shift != PAGE_SHIFT) { - /* Adjust PFN */ - unsigned long mask = (1ul << shift) - PAGE_SIZE; - pte = __pte(pte_val(pte) | (hva & mask)); - } - pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); - if (writing || upgrade_write) { - if (pte_val(pte) & _PAGE_WRITE) - pte = __pte(pte_val(pte) | _PAGE_DIRTY); - } else { - pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + level = 0; + if (shift > PAGE_SHIFT) { + /* + * If the pte maps more than one page, bring over + * bits from the virtual address to get the real + * address of the specific single page we want. + */ + unsigned long rpnmask = (1ul << shift) - PAGE_SIZE; + pte = __pte(pte_val(pte) | (hva & rpnmask)); } } + pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED); + if (writing || upgrade_write) { + if (pte_val(pte) & _PAGE_WRITE) + pte = __pte(pte_val(pte) | _PAGE_DIRTY); + } else { + pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY)); + } + /* Allocate space in the tree and write the PTE */ ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq); @@ -725,10 +708,10 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, gpa, shift); kvmppc_radix_tlbie_page(kvm, gpa, shift); if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) { - unsigned long npages = 1; + unsigned long psize = PAGE_SIZE; if (shift) - npages = 1ul << (shift - PAGE_SHIFT); - kvmppc_update_dirty_map(memslot, gfn, npages); + psize = 1ul << shift; + kvmppc_update_dirty_map(memslot, gfn, psize); } } return 0; diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 506a4d400458..6821ead4b4eb 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -187,12 +187,35 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa, EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE -static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry) +static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl, + unsigned long entry, unsigned long *hpa, + enum dma_data_direction *direction) +{ + long ret; + + ret = tbl->it_ops->exchange_rm(tbl, entry, hpa, direction); + + if (!ret && ((*direction == DMA_FROM_DEVICE) || + (*direction == DMA_BIDIRECTIONAL))) { + __be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry); + /* + * kvmppc_rm_tce_iommu_do_map() updates the UA cache after + * calling this so we still get here a valid UA. + */ + if (pua && *pua) + mm_iommu_ua_mark_dirty_rm(mm, be64_to_cpu(*pua)); + } + + return ret; +} + +static void kvmppc_rm_clear_tce(struct kvm *kvm, struct iommu_table *tbl, + unsigned long entry) { unsigned long hpa = 0; enum dma_data_direction dir = DMA_NONE; - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); } static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm, @@ -224,7 +247,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, unsigned long hpa = 0; long ret; - if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir)) + if (iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir)) /* * real mode xchg can fail if struct page crosses * a page boundary @@ -236,7 +259,7 @@ static long kvmppc_rm_tce_iommu_do_unmap(struct kvm *kvm, ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry); if (ret) - iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); return ret; } @@ -282,7 +305,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl, if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem))) return H_CLOSED; - ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir); + ret = iommu_tce_xchg_rm(kvm->mm, tbl, entry, &hpa, &dir); if (ret) { mm_iommu_mapped_dec(mem); /* @@ -371,7 +394,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry, tce); @@ -520,7 +543,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu, goto unlock_exit; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } kvmppc_tce_put(stt, entry + i, tce); @@ -571,7 +594,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu, return ret; WARN_ON_ONCE_RM(1); - kvmppc_rm_clear_tce(stit->tbl, entry); + kvmppc_rm_clear_tce(vcpu->kvm, stit->tbl, entry); } } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 51ce091914f9..7a9886f98b0c 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -308,55 +308,6 @@ void register_page_bootmem_memmap(unsigned long section_nr, { } -/* - * We do not have access to the sparsemem vmemmap, so we fallback to - * walking the list of sparsemem blocks which we already maintain for - * the sake of crashdump. In the long run, we might want to maintain - * a tree if performance of that linear walk becomes a problem. - * - * realmode_pfn_to_page functions can fail due to: - * 1) As real sparsemem blocks do not lay in RAM continously (they - * are in virtual address space which is not available in the real mode), - * the requested page struct can be split between blocks so get_page/put_page - * may fail. - * 2) When huge pages are used, the get_page/put_page API will fail - * in real mode as the linked addresses in the page struct are virtual - * too. - */ -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct vmemmap_backing *vmem_back; - struct page *page; - unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; - unsigned long pg_va = (unsigned long) pfn_to_page(pfn); - - for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) { - if (pg_va < vmem_back->virt_addr) - continue; - - /* After vmemmap_list entry free is possible, need check all */ - if ((pg_va + sizeof(struct page)) <= - (vmem_back->virt_addr + page_size)) { - page = (struct page *) (vmem_back->phys + pg_va - - vmem_back->virt_addr); - return page; - } - } - - /* Probably that page struct is split between real pages */ - return NULL; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - -#else - -struct page *realmode_pfn_to_page(unsigned long pfn) -{ - struct page *page = pfn_to_page(pfn); - return page; -} -EXPORT_SYMBOL_GPL(realmode_pfn_to_page); - #endif /* CONFIG_SPARSEMEM_VMEMMAP */ #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index c9ee9e23845f..56c2234cc6ae 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -18,11 +18,15 @@ #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/swap.h> +#include <linux/sizes.h> #include <asm/mmu_context.h> #include <asm/pte-walk.h> static DEFINE_MUTEX(mem_list_mutex); +#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY 0x1 +#define MM_IOMMU_TABLE_GROUP_PAGE_MASK ~(SZ_4K - 1) + struct mm_iommu_table_group_mem_t { struct list_head next; struct rcu_head rcu; @@ -263,6 +267,9 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem) if (!page) continue; + if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY) + SetPageDirty(page); + put_page(page); mem->hpas[i] = 0; } @@ -360,7 +367,6 @@ struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm, return ret; } -EXPORT_SYMBOL_GPL(mm_iommu_lookup_rm); struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm, unsigned long ua, unsigned long entries) @@ -390,7 +396,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem, if (pageshift > mem->pageshift) return -EFAULT; - *hpa = *va | (ua & ~PAGE_MASK); + *hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } @@ -413,11 +419,31 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem, if (!pa) return -EFAULT; - *hpa = *pa | (ua & ~PAGE_MASK); + *hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK); return 0; } -EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa_rm); + +extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua) +{ + struct mm_iommu_table_group_mem_t *mem; + long entry; + void *va; + unsigned long *pa; + + mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE); + if (!mem) + return; + + entry = (ua - mem->ua) >> PAGE_SHIFT; + va = &mem->hpas[entry]; + + pa = (void *) vmalloc_to_phys(va); + if (!pa) + return; + + *pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY; +} long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem) { diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index db20dc630e7e..aee603123030 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -85,15 +85,8 @@ atomic_t hart_lottery; #ifdef CONFIG_BLK_DEV_INITRD static void __init setup_initrd(void) { - extern char __initramfs_start[]; - extern unsigned long __initramfs_size; unsigned long size; - if (__initramfs_size > 0) { - initrd_start = (unsigned long)(&__initramfs_start); - initrd_end = initrd_start + __initramfs_size; - } - if (initrd_start >= initrd_end) { printk(KERN_INFO "initrd not found or empty"); goto disable; 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/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index f31a15044c24..a8418e1379eb 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -16,7 +16,13 @@ typedef struct { unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; - /* The mmu context allocates 4K page tables. */ + /* + * The following bitfields need a down_write on the mm + * semaphore when they are written to. As they are only + * written once, they can be read without a lock. + * + * The mmu context allocates 4K page tables. + */ unsigned int alloc_pgste:1; /* The mmu context uses extended page tables. */ unsigned int has_pgste:1; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 91ad4a9425c0..ac5da6b0b862 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -481,7 +481,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_S390_HPAGE_1M: r = 0; - if (hpage) + if (hpage && !kvm_is_ucontrol(kvm)) r = 1; break; case KVM_CAP_S390_MEM_OP: @@ -691,11 +691,13 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) mutex_lock(&kvm->lock); if (kvm->created_vcpus) r = -EBUSY; - else if (!hpage || kvm->arch.use_cmma) + else if (!hpage || kvm->arch.use_cmma || kvm_is_ucontrol(kvm)) r = -EINVAL; else { r = 0; + down_write(&kvm->mm->mmap_sem); kvm->mm->context.allow_gmap_hpage_1m = 1; + up_write(&kvm->mm->mmap_sem); /* * We might have to create fake 4k page * tables. To avoid that the hardware works on diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index d68f10441a16..8679bd74d337 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -280,9 +280,11 @@ retry: goto retry; } } - if (rc) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; vcpu->run->s.regs.gprs[reg1] &= ~0xff; vcpu->run->s.regs.gprs[reg1] |= key; return 0; @@ -324,9 +326,11 @@ retry: goto retry; } } - if (rc < 0) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; kvm_s390_set_psw_cc(vcpu, rc); return 0; } @@ -390,12 +394,12 @@ static int handle_sske(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc < 0) + return rc; + start += PAGE_SIZE; } if (m3 & (SSKE_MC | SSKE_MR)) { @@ -1002,13 +1006,15 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc == -EAGAIN) + continue; + if (rc < 0) + return rc; } + start += PAGE_SIZE; } if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 63844b95c22c..a2b28cd1e3fe 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -173,7 +173,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return set_validity_icpt(scb_s, 0x0039U); /* copy only the wrapping keys */ - if (read_guest_real(vcpu, crycb_addr + 72, &vsie_page->crycb, 56)) + if (read_guest_real(vcpu, crycb_addr + 72, + vsie_page->crycb.dea_wrapping_key_mask, 56)) return set_validity_icpt(scb_s, 0x0035U); scb_s->ecb3 |= ecb3_flags; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index bb44990c8212..911c7ded35f1 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -708,11 +708,13 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to) vmaddr |= gaddr & ~PMD_MASK; /* Find vma in the parent mm */ vma = find_vma(gmap->mm, vmaddr); + if (!vma) + continue; /* * We do not discard pages that are backed by * hugetlbfs, so we don't have to refault them. */ - if (vma && is_vm_hugetlb_page(vma)) + if (is_vm_hugetlb_page(vma)) continue; size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK)); zap_page_range(vma, vmaddr, size); diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index 3641a294ed54..e4abe9b8f97a 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -9,6 +9,7 @@ #include <linux/irq.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <linux/dma-mapping.h> #include <asm/leon.h> #include <asm/leon_amba.h> @@ -381,6 +382,9 @@ static struct platform_device * __init scan_one_device(struct device_node *dp, else dev_set_name(&op->dev, "%08x", dp->phandle); + op->dev.coherent_dma_mask = DMA_BIT_MASK(32); + op->dev.dma_mask = &op->dev.coherent_dma_mask; + if (of_device_register(op)) { printk("%s: Could not register of device.\n", dp->full_name); diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 44e4d4435bed..6df6086968c6 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -2,6 +2,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/of.h> +#include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mod_devicetable.h> @@ -675,6 +676,8 @@ static struct platform_device * __init scan_one_device(struct device_node *dp, dev_set_name(&op->dev, "root"); else dev_set_name(&op->dev, "%08x", dp->phandle); + op->dev.coherent_dma_mask = DMA_BIT_MASK(32); + op->dev.dma_mask = &op->dev.coherent_dma_mask; if (of_device_register(op)) { printk("%s: Could not register of device.\n", diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c index acd11b3bf639..2a356b948720 100644 --- a/arch/x86/crypto/aegis128-aesni-glue.c +++ b/arch/x86/crypto/aegis128-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c index 2071c3d1ae07..dbe8bb980da1 100644 --- a/arch/x86/crypto/aegis128l-aesni-glue.c +++ b/arch/x86/crypto/aegis128l-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis128l_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c index b5f2a8fd5a71..8bebda2de92f 100644 --- a/arch/x86/crypto/aegis256-aesni-glue.c +++ b/arch/x86/crypto/aegis256-aesni-glue.c @@ -379,7 +379,6 @@ static int __init crypto_aegis256_aesni_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || !boot_cpu_has(X86_FEATURE_AES) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c index 95cf857d2cbb..f40244eaf14d 100644 --- a/arch/x86/crypto/morus1280-sse2-glue.c +++ b/arch/x86/crypto/morus1280-sse2-glue.c @@ -40,7 +40,6 @@ MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350); static int __init crypto_morus1280_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c index 615fb7bc9a32..9afaf8f8565a 100644 --- a/arch/x86/crypto/morus640-sse2-glue.c +++ b/arch/x86/crypto/morus640-sse2-glue.c @@ -40,7 +40,6 @@ MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400); static int __init crypto_morus640_sse2_module_init(void) { if (!boot_cpu_has(X86_FEATURE_XMM2) || - !boot_cpu_has(X86_FEATURE_OSXSAVE) || !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL)) return -ENODEV; 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/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5b0f613428c2..2c43e3055948 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -95,8 +95,8 @@ static void hv_apic_eoi_write(u32 reg, u32 val) */ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) { - struct ipi_arg_ex **arg; - struct ipi_arg_ex *ipi_arg; + struct hv_send_ipi_ex **arg; + struct hv_send_ipi_ex *ipi_arg; unsigned long flags; int nr_bank = 0; int ret = 1; @@ -105,7 +105,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) return false; local_irq_save(flags); - arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); + arg = (struct hv_send_ipi_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); ipi_arg = *arg; if (unlikely(!ipi_arg)) @@ -135,7 +135,7 @@ ipi_mask_ex_done: static bool __send_ipi_mask(const struct cpumask *mask, int vector) { int cur_cpu, vcpu; - struct ipi_arg_non_ex ipi_arg; + struct hv_send_ipi ipi_arg; int ret = 1; trace_hyperv_send_ipi_mask(mask, vector); diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index b143717b92b3..ce84388e540c 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,11 +80,11 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); } +#define arch_atomic_sub_and_test arch_atomic_sub_and_test /** * arch_atomic_inc - increment atomic variable @@ -92,12 +92,12 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); } +#define arch_atomic_inc arch_atomic_inc /** * arch_atomic_dec - decrement atomic variable @@ -105,12 +105,12 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); } +#define arch_atomic_dec arch_atomic_dec /** * arch_atomic_dec_and_test - decrement and test @@ -120,11 +120,11 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); } +#define arch_atomic_dec_and_test arch_atomic_dec_and_test /** * arch_atomic_inc_and_test - increment and test @@ -134,11 +134,11 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); } +#define arch_atomic_inc_and_test arch_atomic_inc_and_test /** * arch_atomic_add_negative - add and test if negative @@ -149,11 +149,11 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); } +#define arch_atomic_add_negative arch_atomic_add_negative /** * arch_atomic_add_return - add integer and return diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index ef959f02d070..6a5b0ec460da 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -205,12 +205,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -218,12 +218,12 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_add_unless - add unless the number is a given value @@ -245,7 +245,6 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } -#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -253,8 +252,8 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) "S" (v) : "ecx", "edx", "memory"); return r; } +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; @@ -262,6 +261,7 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) "S" (v) : "ecx", "memory"); return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #undef alternative_atomic64 #undef __alternative_atomic64 diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 4343d9b4f30e..5f851d92eecd 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,11 +71,11 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); } +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test /** * arch_atomic64_inc - increment atomic64 variable @@ -83,13 +83,13 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -97,13 +97,13 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_dec_and_test - decrement and test @@ -113,11 +113,11 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); } +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test /** * arch_atomic64_inc_and_test - increment and test @@ -127,11 +127,11 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); } +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test /** * arch_atomic64_add_negative - add and test if negative @@ -142,11 +142,11 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); } +#define arch_atomic64_add_negative arch_atomic64_add_negative /** * arch_atomic64_add_return - add and return diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index e203169931c7..6390bd8c141b 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -14,6 +14,16 @@ #ifndef _ASM_X86_FIXMAP_H #define _ASM_X86_FIXMAP_H +/* + * Exposed to assembly code for setting up initial page tables. Cannot be + * calculated in assembly code (fixmap entries are an enum), but is sanity + * checked in the actual fixmap C code to make sure that the fixmap is + * covered fully. + */ +#define FIXMAP_PMD_NUM 2 +/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */ +#define FIXMAP_PMD_TOP 507 + #ifndef __ASSEMBLY__ #include <linux/kernel.h> #include <asm/acpi.h> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index e977b6b3a538..00e01d215f74 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -726,19 +726,21 @@ struct hv_enlightened_vmcs { #define HV_STIMER_AUTOENABLE (1ULL << 3) #define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) -struct ipi_arg_non_ex { - u32 vector; - u32 reserved; - u64 cpu_mask; -}; - struct hv_vpset { u64 format; u64 valid_bank_mask; u64 bank_contents[]; }; -struct ipi_arg_ex { +/* HvCallSendSyntheticClusterIpi hypercall */ +struct hv_send_ipi { + u32 vector; + u32 reserved; + u64 cpu_mask; +}; + +/* HvCallSendSyntheticClusterIpiEx hypercall */ +struct hv_send_ipi_ex { u32 vector; u32 reserved; struct hv_vpset vp_set; diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 395c9631e000..75f1e35e7c15 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -22,10 +22,20 @@ enum die_val { DIE_NMIUNKNOWN, }; +enum show_regs_mode { + SHOW_REGS_SHORT, + /* + * For when userspace crashed, but we don't think it's our fault, and + * therefore don't print kernel registers. + */ + SHOW_REGS_USER, + SHOW_REGS_ALL +}; + extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); -extern void __show_regs(struct pt_regs *regs, int all); +extern void __show_regs(struct pt_regs *regs, enum show_regs_mode); extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 00ddb0c9e612..09b2e3e2cf1b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -869,6 +869,8 @@ struct kvm_arch { bool x2apic_format; bool x2apic_broadcast_quirk_disabled; + + bool guest_can_read_msr_platform_info; }; struct kvm_vm_stat { @@ -1022,6 +1024,7 @@ struct kvm_x86_ops { void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); + bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); @@ -1055,6 +1058,7 @@ struct kvm_x86_ops { bool (*umip_emulated)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); + void (*request_immediate_exit)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *kvm, int cpu); @@ -1237,19 +1241,12 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -#define EMULTYPE_RETRY (1 << 3) -#define EMULTYPE_NO_REEXECUTE (1 << 4) -#define EMULTYPE_NO_UD_ON_FAIL (1 << 5) -#define EMULTYPE_VMWARE (1 << 6) -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, - int emulation_type, void *insn, int insn_len); - -static inline int emulate_instruction(struct kvm_vcpu *vcpu, - int emulation_type) -{ - return x86_emulate_instruction(vcpu, 0, - emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0); -} +#define EMULTYPE_ALLOW_RETRY (1 << 3) +#define EMULTYPE_NO_UD_ON_FAIL (1 << 4) +#define EMULTYPE_VMWARE (1 << 5) +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -1450,7 +1447,6 @@ asmlinkage void kvm_spurious_fault(void); ____kvm_handle_fault_on_reboot(insn, "") #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); @@ -1463,7 +1459,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); u64 kvm_get_arch_capabilities(void); @@ -1490,6 +1486,7 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); int kvm_is_in_guest(void); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index c0643831706e..616f8e637bc3 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -48,10 +48,13 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); /* Architecture __weak replacement functions */ void __init mem_encrypt_init(void); +void __init mem_encrypt_free_decrypted_mem(void); bool sme_active(void); bool sev_active(void); +#define __bss_decrypted __attribute__((__section__(".bss..decrypted"))) + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define sme_me_mask 0ULL @@ -77,6 +80,8 @@ early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; static inline int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +#define __bss_decrypted + #endif /* CONFIG_AMD_MEM_ENCRYPT */ /* @@ -88,6 +93,8 @@ early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; #define __sme_pa(x) (__pa(x) | sme_me_mask) #define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) +extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; + #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ 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/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e4ffa565a69f..690c0307afed 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1195,7 +1195,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); return old; } } diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f773d5e6c8cc..9c85b54bf03c 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -14,6 +14,7 @@ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> +#include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; @@ -22,7 +23,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; -extern pte_t level1_fixmap_pgt[512]; +extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt @@ -55,15 +56,15 @@ struct mm_struct; void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); -static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) +static inline void native_set_pte(pte_t *ptep, pte_t pte) { - *ptep = native_make_pte(0); + WRITE_ONCE(*ptep, pte); } -static inline void native_set_pte(pte_t *ptep, pte_t pte) +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - *ptep = pte; + native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) @@ -73,7 +74,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) @@ -109,7 +110,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) static inline void native_set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) @@ -137,13 +138,13 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { - *p4dp = p4d; + WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); - *p4dp = native_make_p4d(native_pgd_val(pgd)); + WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) @@ -153,7 +154,7 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pti_set_user_pgtbl(pgdp, pgd); + WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 86299efa804a..fd23d5778ea1 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -377,6 +377,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..7654febd5102 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -413,7 +413,7 @@ static int activate_managed(struct irq_data *irqd) if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { /* Something in the core code broke! Survive gracefully */ pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); - return EINVAL; + return -EINVAL; } ret = assign_managed_vector(irqd, vector_searchmask); 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/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 4e588f36228f..285eb3ec4200 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -382,6 +382,11 @@ static inline bool is_mbm_event(int e) e <= QOS_L3_MBM_LOCAL_EVENT_ID); } +struct rdt_parse_data { + struct rdtgroup *rdtgrp; + char *buf; +}; + /** * struct rdt_resource - attributes of an RDT resource * @rid: The index of the resource @@ -423,16 +428,19 @@ struct rdt_resource { struct rdt_cache cache; struct rdt_membw membw; const char *format_str; - int (*parse_ctrlval) (void *data, struct rdt_resource *r, - struct rdt_domain *d); + int (*parse_ctrlval)(struct rdt_parse_data *data, + struct rdt_resource *r, + struct rdt_domain *d); struct list_head evt_list; int num_rmid; unsigned int mon_scale; unsigned long fflags; }; -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d); -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d); +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d); extern struct mutex rdtgroup_mutex; @@ -536,6 +544,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp); void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int update_domains(struct rdt_resource *r, int closid); +int closids_supported(void); void closid_free(int closid); int alloc_rmid(void); void free_rmid(u32 rmid); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index af358ca05160..0f53049719cd 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -64,19 +64,19 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return true; } -int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d) +int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - unsigned long data; - char *buf = _buf; + unsigned long bw_val; if (d->have_new_ctrl) { rdt_last_cmd_printf("duplicate domain %d\n", d->id); return -EINVAL; } - if (!bw_validate(buf, &data, r)) + if (!bw_validate(data->buf, &bw_val, r)) return -EINVAL; - d->new_ctrl = data; + d->new_ctrl = bw_val; d->have_new_ctrl = true; return 0; @@ -123,18 +123,13 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) return true; } -struct rdt_cbm_parse_data { - struct rdtgroup *rdtgrp; - char *buf; -}; - /* * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) +int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, + struct rdt_domain *d) { - struct rdt_cbm_parse_data *data = _data; struct rdtgroup *rdtgrp = data->rdtgrp; u32 cbm_val; @@ -195,11 +190,17 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d) static int parse_line(char *line, struct rdt_resource *r, struct rdtgroup *rdtgrp) { - struct rdt_cbm_parse_data data; + struct rdt_parse_data data; char *dom = NULL, *id; struct rdt_domain *d; unsigned long dom_id; + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && + r->rid == RDT_RESOURCE_MBA) { + rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); + return -EINVAL; + } + next: if (!line || line[0] == '\0') return 0; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index b799c00bef09..1b8e86a5d5e1 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -97,6 +97,12 @@ void rdt_last_cmd_printf(const char *fmt, ...) * limited as the number of resources grows. */ static int closid_free_map; +static int closid_free_map_len; + +int closids_supported(void) +{ + return closid_free_map_len; +} static void closid_init(void) { @@ -111,6 +117,7 @@ static void closid_init(void) /* CLOSID 0 is always reserved for the default group */ closid_free_map &= ~1; + closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) @@ -802,7 +809,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, sw_shareable = 0; exclusive = 0; seq_printf(seq, "%d=", dom->id); - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (!closid_allocated(i)) continue; mode = rdtgroup_mode_by_closid(i); @@ -989,7 +996,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { ctrl_b = (unsigned long *)ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && @@ -1024,16 +1031,27 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) { int closid = rdtgrp->closid; struct rdt_resource *r; + bool has_cache = false; struct rdt_domain *d; for_each_alloc_enabled_rdt_resource(r) { + if (r->rid == RDT_RESOURCE_MBA) + continue; + has_cache = true; list_for_each_entry(d, &r->domains, list) { if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid], - rdtgrp->closid, false)) + rdtgrp->closid, false)) { + rdt_last_cmd_puts("schemata overlaps\n"); return false; + } } } + if (!has_cache) { + rdt_last_cmd_puts("cannot be exclusive without CAT/CDP\n"); + return false; + } + return true; } @@ -1085,7 +1103,6 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, rdtgrp->mode = RDT_MODE_SHAREABLE; } else if (!strcmp(buf, "exclusive")) { if (!rdtgroup_mode_test_exclusive(rdtgrp)) { - rdt_last_cmd_printf("schemata overlaps\n"); ret = -EINVAL; goto out; } @@ -1155,8 +1172,8 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; - bool sep = false; - u32 cbm; + bool sep; + u32 ctrl; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -1174,6 +1191,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, } for_each_alloc_enabled_rdt_resource(r) { + sep = false; seq_printf(s, "%*s:", max_name_width, r->name); list_for_each_entry(d, &r->domains, list) { if (sep) @@ -1181,8 +1199,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) { size = 0; } else { - cbm = d->ctrl_val[rdtgrp->closid]; - size = rdtgroup_cbm_to_size(r, d, cbm); + ctrl = (!is_mba_sc(r) ? + d->ctrl_val[rdtgrp->closid] : + d->mbps_val[rdtgrp->closid]); + if (r->rid == RDT_RESOURCE_MBA) + size = ctrl; + else + size = rdtgroup_cbm_to_size(r, d, ctrl); } seq_printf(s, "%d=%u", d->id, size); sep = true; @@ -2336,12 +2359,18 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) u32 *ctrl; for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; list_for_each_entry(d, &r->domains, list) { d->have_new_ctrl = false; d->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; ctrl = d->ctrl_val; - for (i = 0; i < r->num_closid; i++, ctrl++) { + for (i = 0; i < closids_supported(); i++, ctrl++) { if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) @@ -2373,6 +2402,12 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) } for_each_alloc_enabled_rdt_resource(r) { + /* + * Only initialize default allocations for CBM cache + * resources + */ + if (r->rid == RDT_RESOURCE_MBA) + continue; ret = update_domains(r, rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("failed to initialize allocations\n"); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 0624957aa068..07b5fc00b188 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; + enum ucode_state ret; u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } if (__apply_microcode_amd(mc_amd)) { @@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu) cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + ret = UCODE_UPDATED; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); - return UCODE_UPDATED; +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; + + return ret; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 97ccf4c3b45b..16936a24795c 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; + enum ucode_state ret; static int prev_rev; u32 rev; @@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu) */ rev = intel_get_microcode_revision(); if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; - c->microcode = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } /* @@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } + ret = UCODE_UPDATED; + +out: uci->cpu_sig.rev = rev; - c->microcode = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f56895106ccf..2b5886401e5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -146,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, * they can be printed in the right context. */ if (!partial && on_stack(info, regs, sizeof(*regs))) { - __show_regs(regs, 0); + __show_regs(regs, SHOW_REGS_SHORT); } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET, IRET_FRAME_SIZE)) { @@ -344,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) oops_exit(); /* Executive summary in case the oops scrolled away */ - __show_regs(&exec_summary_regs, true); + __show_regs(&exec_summary_regs, SHOW_REGS_ALL); if (!signr) return; @@ -407,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err) void show_regs(struct pt_regs *regs) { - bool all = true; - show_regs_print_info(KERN_DEFAULT); - if (IS_ENABLED(CONFIG_X86_32)) - all = !user_mode(regs); - - __show_regs(regs, all); + __show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL); /* * When in-kernel, we also print out the stack at the time of the fault.. 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/head64.c b/arch/x86/kernel/head64.c index 8047379e575a..ddee1f0870c4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -35,6 +35,7 @@ #include <asm/bootparam_utils.h> #include <asm/microcode.h> #include <asm/kasan.h> +#include <asm/fixmap.h> /* * Manage page tables very early on. @@ -112,6 +113,7 @@ static bool __head check_la57_support(unsigned long physaddr) unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { + unsigned long vaddr, vaddr_end; unsigned long load_delta, *p; unsigned long pgtable_flags; pgdval_t *pgd; @@ -165,7 +167,8 @@ unsigned long __head __startup_64(unsigned long physaddr, pud[511] += load_delta; pmd = fixup_pointer(level2_fixmap_pgt, physaddr); - pmd[506] += load_delta; + for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) + pmd[i] += load_delta; /* * Set up the identity mapping for the switchover. These @@ -235,6 +238,21 @@ unsigned long __head __startup_64(unsigned long physaddr, sme_encrypt_kernel(bp); /* + * Clear the memory encryption mask from the .bss..decrypted section. + * The bss section will be memset to zero later in the initialization so + * there is no need to zero it after changing the memory encryption + * attribute. + */ + if (mem_encrypt_active()) { + vaddr = (unsigned long)__start_bss_decrypted; + vaddr_end = (unsigned long)__end_bss_decrypted; + for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { + i = pmd_index(vaddr); + pmd[i] -= sme_get_me_mask(); + } + } + + /* * Return the SME encryption mask (if SME is active) to be used as a * modifier for the initial pgdir entry programmed into CR3. */ diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 15ebc2fc166e..a3618cf04cf6 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -24,6 +24,7 @@ #include "../entry/calling.h" #include <asm/export.h> #include <asm/nospec-branch.h> +#include <asm/fixmap.h> #ifdef CONFIG_PARAVIRT #include <asm/asm-offsets.h> @@ -445,13 +446,20 @@ NEXT_PAGE(level2_kernel_pgt) KERNEL_IMAGE_SIZE/PMD_SIZE) NEXT_PAGE(level2_fixmap_pgt) - .fill 506,8,0 - .quad level1_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC - /* 8MB reserved for vsyscalls + a 2MB hole = 4 + 1 entries */ - .fill 5,8,0 + .fill (512 - 4 - FIXMAP_PMD_NUM),8,0 + pgtno = 0 + .rept (FIXMAP_PMD_NUM) + .quad level1_fixmap_pgt + (pgtno << PAGE_SHIFT) - __START_KERNEL_map \ + + _PAGE_TABLE_NOENC; + pgtno = pgtno + 1 + .endr + /* 6 MB reserved space + a 2MB hole */ + .fill 4,8,0 NEXT_PAGE(level1_fixmap_pgt) + .rept (FIXMAP_PMD_NUM) .fill 512,8,0 + .endr #undef PMDS diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1e6764648af3..013fe3d21dbb 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -28,6 +28,7 @@ #include <linux/sched/clock.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/set_memory.h> #include <asm/hypervisor.h> #include <asm/mem_encrypt.h> @@ -61,9 +62,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) static struct pvclock_vsyscall_time_info - hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE); -static struct pvclock_wall_clock wall_clock; + hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); +static struct pvclock_wall_clock wall_clock __bss_decrypted; static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +static struct pvclock_vsyscall_time_info *hvclock_mem; static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) { @@ -236,6 +238,45 @@ static void kvm_shutdown(void) native_machine_shutdown(); } +static void __init kvmclock_init_mem(void) +{ + unsigned long ncpus; + unsigned int order; + struct page *p; + int r; + + if (HVC_BOOT_ARRAY_SIZE >= num_possible_cpus()) + return; + + ncpus = num_possible_cpus() - HVC_BOOT_ARRAY_SIZE; + order = get_order(ncpus * sizeof(*hvclock_mem)); + + p = alloc_pages(GFP_KERNEL, order); + if (!p) { + pr_warn("%s: failed to alloc %d pages", __func__, (1U << order)); + return; + } + + hvclock_mem = page_address(p); + + /* + * hvclock is shared between the guest and the hypervisor, must + * be mapped decrypted. + */ + if (sev_active()) { + r = set_memory_decrypted((unsigned long) hvclock_mem, + 1UL << order); + if (r) { + __free_pages(p, order); + hvclock_mem = NULL; + pr_warn("kvmclock: set_memory_decrypted() failed. Disabling\n"); + return; + } + } + + memset(hvclock_mem, 0, PAGE_SIZE << order); +} + static int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 @@ -250,6 +291,9 @@ static int __init kvm_setup_vsyscall_timeinfo(void) kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; #endif + + kvmclock_init_mem(); + return 0; } early_initcall(kvm_setup_vsyscall_timeinfo); @@ -269,8 +313,10 @@ static int kvmclock_setup_percpu(unsigned int cpu) /* Use the static page for the first CPUs, allocate otherwise */ if (cpu < HVC_BOOT_ARRAY_SIZE) p = &hv_clock_boot[cpu]; + else if (hvclock_mem) + p = hvclock_mem + cpu - HVC_BOOT_ARRAY_SIZE; else - p = kzalloc(sizeof(*p), GFP_KERNEL); + return -ENOMEM; per_cpu(hv_clock_per_cpu, cpu) = p; return p ? 0 : -ENOMEM; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index afdb303285f8..8dc69d82567e 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -91,7 +91,7 @@ unsigned paravirt_patch_call(void *insnbuf, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect CALL in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } @@ -111,7 +111,7 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target, if (len < 5) { #ifdef CONFIG_RETPOLINE - WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr); + WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr); #endif return len; /* call too long for patch site */ } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2924fd447e61..5046a3c9dec2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -59,7 +59,7 @@ #include <asm/intel_rdt_sched.h> #include <asm/proto.h> -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; @@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n", (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags); - if (!all) + if (mode != SHOW_REGS_ALL) return; cr0 = read_cr0(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a451bc374b9b..ea5ea850348d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -62,7 +62,7 @@ __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -87,9 +87,17 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); - if (!all) + if (mode == SHOW_REGS_SHORT) return; + if (mode == SHOW_REGS_USER) { + rdmsrl(MSR_FS_BASE, fs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n", + fs, shadowgs); + return; + } + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); 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/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1463468ba9a0..6490f618e096 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1415,7 +1415,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early) static unsigned long __init get_loops_per_jiffy(void) { - unsigned long lpj = tsc_khz * KHZ; + u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 8bde0a419f86..5dd3317d761f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -65,6 +65,23 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE); #define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE); +/* + * This section contains data which will be mapped as decrypted. Memory + * encryption operates on a page basis. Make this section PMD-aligned + * to avoid splitting the pages while mapping the section early. + * + * Note: We use a separate section so that only this section gets + * decrypted to avoid exposing more than we wish. + */ +#define BSS_DECRYPTED \ + . = ALIGN(PMD_SIZE); \ + __start_bss_decrypted = .; \ + *(.bss..decrypted); \ + . = ALIGN(PAGE_SIZE); \ + __start_bss_decrypted_unused = .; \ + . = ALIGN(PMD_SIZE); \ + __end_bss_decrypted = .; \ + #else #define X86_ALIGN_RODATA_BEGIN @@ -74,6 +91,7 @@ jiffies_64 = jiffies; #define ALIGN_ENTRY_TEXT_BEGIN #define ALIGN_ENTRY_TEXT_END +#define BSS_DECRYPTED #endif @@ -355,6 +373,7 @@ SECTIONS __bss_start = .; *(.bss..page_aligned) *(.bss) + BSS_DECRYPTED . = ALIGN(PAGE_SIZE); __bss_stop = .; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0cefba28c864..fbb0e6df121b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -548,7 +548,7 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, } int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { int i; @@ -571,18 +571,31 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); + if (min > map->max_apic_id) + goto out; /* Bits above cluster_size are masked in the caller. */ - for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + for_each_set_bit(i, &ipi_bitmap_low, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } min += cluster_size; - for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + + if (min > map->max_apic_id) + goto out; + + for_each_set_bit(i, &ipi_bitmap_high, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } +out: rcu_read_unlock(); return count; } @@ -1331,9 +1344,8 @@ EXPORT_SYMBOL_GPL(kvm_lapic_reg_read); static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) { - return kvm_apic_hw_enabled(apic) && - addr >= apic->base_address && - addr < apic->base_address + LAPIC_MMIO_LENGTH; + return addr >= apic->base_address && + addr < apic->base_address + LAPIC_MMIO_LENGTH; } static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, @@ -1345,6 +1357,15 @@ static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + memset(data, 0xff, len); + return 0; + } + kvm_lapic_reg_read(apic, offset, len, data); return 0; @@ -1904,6 +1925,14 @@ static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; + if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { + if (!kvm_check_has_quirk(vcpu->kvm, + KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) + return -EOPNOTSUPP; + + return 0; + } + /* * APIC register must be aligned on 128-bits boundary. * 32/64/128 bits registers must be accessed thru 32 bits. diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a282321329b5..d7e9bce6ff61 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -899,7 +899,7 @@ static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { /* * Make sure the write to vcpu->mode is not reordered in front of - * reads to sptes. If it does, kvm_commit_zap_page() can see us + * reads to sptes. If it does, kvm_mmu_commit_zap_page() can see us * OUTSIDE_GUEST_MODE and proceed to free the shadow page table. */ smp_store_release(&vcpu->mode, OUTSIDE_GUEST_MODE); @@ -1853,11 +1853,6 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); @@ -5217,7 +5212,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, void *insn, int insn_len) { - int r, emulation_type = EMULTYPE_RETRY; + int r, emulation_type = 0; enum emulation_result er; bool direct = vcpu->arch.mmu.direct_map; @@ -5230,10 +5225,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2, direct); - if (r == RET_PF_EMULATE) { - emulation_type = 0; + if (r == RET_PF_EMULATE) goto emulate; - } } if (r == RET_PF_INVALID) { @@ -5260,8 +5253,19 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, return 1; } - if (mmio_info_in_cache(vcpu, cr2, direct)) - emulation_type = 0; + /* + * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still + * optimistically try to just unprotect the page and let the processor + * re-execute the instruction that caused the page fault. Do not allow + * retrying MMIO emulation, as it's not only pointless but could also + * cause us to enter an infinite loop because the processor will keep + * faulting on the non-existent MMIO address. Retrying an instruction + * from a nested guest is also pointless and dangerous as we are only + * explicitly shadowing L1's page tables, i.e. unprotecting something + * for L1 isn't going to magically fix whatever issue cause L2 to fail. + */ + if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* * On AMD platforms, under certain conditions insn_len may be zero on #NPF. @@ -5413,7 +5417,12 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) { MMU_WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); - kvm_init_mmu(vcpu, true); + /* + * kvm_mmu_setup() is called only on vCPU initialization. + * Therefore, no need to reset mmu roots as they are not yet + * initialized. + */ + kvm_init_mmu(vcpu, false); } static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6276140044d0..d96092b35936 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -776,7 +776,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } if (!svm->next_rip) { - if (emulate_instruction(vcpu, EMULTYPE_SKIP) != + if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -1226,8 +1226,7 @@ static __init int sev_hardware_setup(void) min_sev_asid = cpuid_edx(0x8000001F); /* Initialize SEV ASID bitmap */ - sev_asid_bitmap = kcalloc(BITS_TO_LONGS(max_sev_asid), - sizeof(unsigned long), GFP_KERNEL); + sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); if (!sev_asid_bitmap) return 1; @@ -1405,7 +1404,7 @@ static __exit void svm_hardware_unsetup(void) int cpu; if (svm_sev_enabled()) - kfree(sev_asid_bitmap); + bitmap_free(sev_asid_bitmap); for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); @@ -2715,7 +2714,7 @@ static int gp_interception(struct vcpu_svm *svm) WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -2819,7 +2818,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -3861,7 +3860,7 @@ static int iret_interception(struct vcpu_svm *svm) static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); return kvm_skip_emulated_instruction(&svm->vcpu); @@ -3869,13 +3868,13 @@ static int invlpg_interception(struct vcpu_svm *svm) static int emulate_on_interception(struct vcpu_svm *svm) { - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } static int rsm_interception(struct vcpu_svm *svm) { - return x86_emulate_instruction(&svm->vcpu, 0, 0, - rsm_ins_bytes, 2) == EMULATE_DONE; + return kvm_emulate_instruction_from_buffer(&svm->vcpu, + rsm_ins_bytes, 2) == EMULATE_DONE; } static int rdpmc_interception(struct vcpu_svm *svm) @@ -4700,7 +4699,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm) ret = avic_unaccel_trap_write(svm); } else { /* Handling Fault */ - ret = (emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); + ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); } return ret; @@ -6747,7 +6746,7 @@ e_free: static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) { unsigned long vaddr, vaddr_end, next_vaddr; - unsigned long dst_vaddr, dst_vaddr_end; + unsigned long dst_vaddr; struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; @@ -6763,7 +6762,6 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) size = debug.len; vaddr_end = vaddr + size; dst_vaddr = debug.dst_uaddr; - dst_vaddr_end = dst_vaddr + size; for (; vaddr < vaddr_end; vaddr = next_vaddr) { int len, s_off, d_off; @@ -7150,6 +7148,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .check_intercept = svm_check_intercept, .handle_external_intr = svm_handle_external_intr, + .request_immediate_exit = __kvm_request_immediate_exit, + .sched_in = svm_sched_in, .pmu_ops = &amd_pmu_ops, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1d26f3c4985b..06412ba46aa3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -397,6 +397,7 @@ struct loaded_vmcs { int cpu; bool launched; bool nmi_known_unmasked; + bool hv_timer_armed; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; ktime_t entry_time; @@ -1019,6 +1020,8 @@ struct vcpu_vmx { int ple_window; bool ple_window_dirty; + bool req_immediate_exit; + /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; @@ -2864,6 +2867,8 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i; + vmx->req_immediate_exit = false; + if (vmx->loaded_cpu_state) return; @@ -5393,9 +5398,10 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) * To use VMXON (and later other VMX instructions), a guest * must first be able to turn on cr4.VMXE (see handle_vmon()). * So basically the check on whether to allow nested VMX - * is here. + * is here. We operate under the default treatment of SMM, + * so VMX cannot be enabled under SMM. */ - if (!nested_vmx_allowed(vcpu)) + if (!nested_vmx_allowed(vcpu) || is_smm(vcpu)) return 1; } @@ -6183,6 +6189,27 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) nested_mark_vmcs12_pages_dirty(vcpu); } +static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + void *vapic_page; + u32 vppr; + int rvi; + + if (WARN_ON_ONCE(!is_guest_mode(vcpu)) || + !nested_cpu_has_vid(get_vmcs12(vcpu)) || + WARN_ON_ONCE(!vmx->nested.virtual_apic_page)) + return false; + + rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff; + + vapic_page = kmap(vmx->nested.virtual_apic_page); + vppr = *((u32 *)(vapic_page + APIC_PROCPRI)); + kunmap(vmx->nested.virtual_apic_page); + + return ((rvi & 0xf0) > (vppr & 0xf0)); +} + static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, bool nested) { @@ -6983,7 +7010,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { + if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_vcpu_halt(vcpu); @@ -7054,7 +7081,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -7157,7 +7184,7 @@ static int handle_io(struct kvm_vcpu *vcpu) ++vcpu->stat.io_exits; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -7231,7 +7258,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_cr(struct kvm_vcpu *vcpu) @@ -7480,7 +7507,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu) static int handle_invd(struct kvm_vcpu *vcpu) { - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_invlpg(struct kvm_vcpu *vcpu) @@ -7547,7 +7574,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } } - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) @@ -7704,8 +7731,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) return kvm_skip_emulated_instruction(vcpu); else - return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP, - NULL, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) == + EMULATE_DONE; } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -7748,7 +7775,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; - err = emulate_instruction(vcpu, 0); + err = kvm_emulate_instruction(vcpu, 0); if (err == EMULATE_USER_EXIT) { ++vcpu->stat.mmio_exits; @@ -7966,6 +7993,9 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + if (!cpu_has_vmx_preemption_timer()) + kvm_x86_ops->request_immediate_exit = __kvm_request_immediate_exit; + if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) { u64 vmx_msr; @@ -9208,7 +9238,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - kvm_lapic_expired_hv_timer(vcpu); + if (!to_vmx(vcpu)->req_immediate_exit) + kvm_lapic_expired_hv_timer(vcpu); return 1; } @@ -10595,24 +10626,43 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val) +{ + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val); + if (!vmx->loaded_vmcs->hv_timer_armed) + vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = true; +} + +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; - if (vmx->hv_deadline_tsc == -1) + if (vmx->req_immediate_exit) { + vmx_arm_hv_timer(vmx, 0); return; + } - tscl = rdtsc(); - if (vmx->hv_deadline_tsc > tscl) - /* sure to be 32 bit only because checked on set_hv_timer */ - delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> - cpu_preemption_timer_multi); - else - delta_tsc = 0; + if (vmx->hv_deadline_tsc != -1) { + tscl = rdtsc(); + if (vmx->hv_deadline_tsc > tscl) + /* set_hv_timer ensures the delta fits in 32-bits */ + delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >> + cpu_preemption_timer_multi); + else + delta_tsc = 0; + + vmx_arm_hv_timer(vmx, delta_tsc); + return; + } - vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc); + if (vmx->loaded_vmcs->hv_timer_armed) + vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, + PIN_BASED_VMX_PREEMPTION_TIMER); + vmx->loaded_vmcs->hv_timer_armed = false; } static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) @@ -10672,7 +10722,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) atomic_switch_perf_msrs(vmx); - vmx_arm_hv_timer(vcpu); + vmx_update_hv_timer(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -11427,16 +11477,18 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu) u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value; struct vcpu_vmx *vmx = to_vmx(vcpu); - if (vcpu->arch.virtual_tsc_khz == 0) - return; - - /* Make sure short timeouts reliably trigger an immediate vmexit. - * hrtimer_start does not guarantee this. */ - if (preemption_timeout <= 1) { + /* + * A timer value of zero is architecturally guaranteed to cause + * a VMExit prior to executing any instructions in the guest. + */ + if (preemption_timeout == 0) { vmx_preemption_timer_fn(&vmx->nested.preemption_timer); return; } + if (vcpu->arch.virtual_tsc_khz == 0) + return; + preemption_timeout <<= VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE; preemption_timeout *= 1000000; do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz); @@ -11646,11 +11698,15 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, * bits 15:8 should be zero in posted_intr_nv, * the descriptor address has been already checked * in nested_get_vmcs12_pages. + * + * bits 5:0 of posted_intr_desc_addr should be zero. */ if (nested_cpu_has_posted_intr(vmcs12) && (!nested_cpu_has_vid(vmcs12) || !nested_exit_intr_ack_set(vcpu) || - vmcs12->posted_intr_nv & 0xff00)) + (vmcs12->posted_intr_nv & 0xff00) || + (vmcs12->posted_intr_desc_addr & 0x3f) || + (!page_address_valid(vcpu, vmcs12->posted_intr_desc_addr)))) return -EINVAL; /* tpr shadow is needed by all apicv features. */ @@ -12076,11 +12132,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, exec_control = vmcs12->pin_based_vm_exec_control; - /* Preemption timer setting is only taken from vmcs01. */ - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + /* Preemption timer setting is computed directly in vmx_vcpu_run. */ exec_control |= vmcs_config.pin_based_exec_ctrl; - if (vmx->hv_deadline_tsc == -1) - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + vmx->loaded_vmcs->hv_timer_armed = false; /* Posted interrupts setting is only taken from vmcs12. */ if (nested_cpu_has_posted_intr(vmcs12)) { @@ -12318,6 +12373,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12)) return VMXERR_ENTRY_INVALID_CONTROL_FIELD; @@ -12537,8 +12595,11 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); bool from_vmentry = !!exit_qual; u32 dummy_exit_qual; + u32 vmcs01_cpu_exec_ctrl; int r = 0; + vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -12575,6 +12636,25 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) } /* + * If L1 had a pending IRQ/NMI until it executed + * VMLAUNCH/VMRESUME which wasn't delivered because it was + * disallowed (e.g. interrupts disabled), L0 needs to + * evaluate if this pending event should cause an exit from L2 + * to L1 or delivered directly to L2 (e.g. In case L1 don't + * intercept EXTERNAL_INTERRUPT). + * + * Usually this would be handled by L0 requesting a + * IRQ/NMI window by setting VMCS accordingly. However, + * this setting was done on VMCS01 and now VMCS02 is active + * instead. Thus, we force L0 to perform pending event + * evaluation by requesting a KVM_REQ_EVENT. + */ + if (vmcs01_cpu_exec_ctrl & + (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) { + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + + /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set @@ -12841,6 +12921,11 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } +static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + to_vmx(vcpu)->req_immediate_exit = true; +} + static u32 vmx_get_preemption_timer_value(struct kvm_vcpu *vcpu) { ktime_t remaining = @@ -13231,12 +13316,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (vmx->hv_deadline_tsc == -1) - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - else - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -13440,18 +13520,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) return -ERANGE; vmx->hv_deadline_tsc = tscl + delta_tsc; - vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); - return delta_tsc == 0; } static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx->hv_deadline_tsc = -1; - vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, - PIN_BASED_VMX_PREEMPTION_TIMER); + to_vmx(vcpu)->hv_deadline_tsc = -1; } #endif @@ -13932,6 +14006,14 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; + /* + * SMM temporarily disables VMX, so we cannot be in guest mode, + * nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags + * must be zero. + */ + if (is_smm(vcpu) ? kvm_state->flags : kvm_state->vmx.smm.flags) + return -EINVAL; + if ((kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) && !(kvm_state->vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON)) return -EINVAL; @@ -13988,9 +14070,6 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, check_vmentry_postreqs(vcpu, vmcs12, &exit_qual)) return -EINVAL; - if (kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING) - vmx->nested.nested_run_pending = 1; - vmx->nested.dirty_vmcs12 = true; ret = enter_vmx_non_root_mode(vcpu, NULL); if (ret) @@ -14078,6 +14157,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .apicv_post_state_restore = vmx_apicv_post_state_restore, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, + .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_posted_interrupt = vmx_deliver_posted_interrupt, @@ -14111,6 +14191,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .umip_emulated = vmx_umip_emulated, .check_nested_events = vmx_check_nested_events, + .request_immediate_exit = vmx_request_immediate_exit, .sched_in = vmx_sched_in, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 506bd2b4b8bb..edbf00ec56b3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -628,7 +628,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu) gfn_t gfn; int r; - if (is_long_mode(vcpu) || !is_pae(vcpu)) + if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu)) return false; if (!test_bit(VCPU_EXREG_PDPTR, @@ -2537,7 +2537,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_PLATFORM_INFO: if (!msr_info->host_initiated || - data & ~MSR_PLATFORM_INFO_CPUID_FAULT || (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) && cpuid_fault_enabled(vcpu))) return 1; @@ -2780,6 +2779,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.osvw.status; break; case MSR_PLATFORM_INFO: + if (!msr_info->host_initiated && + !vcpu->kvm->arch.guest_can_read_msr_platform_info) + return 1; msr_info->data = vcpu->arch.msr_platform_info; break; case MSR_MISC_FEATURES_ENABLES: @@ -2927,6 +2929,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_GET_MSR_FEATURES: + case KVM_CAP_MSR_PLATFORM_INFO: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -4007,19 +4010,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size)); + r = -EFAULT; if (get_user(user_data_size, &user_kvm_nested_state->size)) - return -EFAULT; + break; r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state, user_data_size); if (r < 0) - return r; + break; if (r > user_data_size) { if (put_user(r, &user_kvm_nested_state->size)) - return -EFAULT; - return -E2BIG; + r = -EFAULT; + else + r = -E2BIG; + break; } + r = 0; break; } @@ -4031,19 +4038,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (!kvm_x86_ops->set_nested_state) break; + r = -EFAULT; if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state))) - return -EFAULT; + break; + r = -EINVAL; if (kvm_state.size < sizeof(kvm_state)) - return -EINVAL; + break; if (kvm_state.flags & ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE)) - return -EINVAL; + break; /* nested_run_pending implies guest_mode. */ if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING) - return -EINVAL; + break; r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state); break; @@ -4350,6 +4359,10 @@ split_irqchip_unlock: kvm->arch.pause_in_guest = true; r = 0; break; + case KVM_CAP_MSR_PLATFORM_INFO: + kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; + r = 0; + break; default: r = -EINVAL; break; @@ -4987,7 +5000,7 @@ int handle_ud(struct kvm_vcpu *vcpu) emul_type = 0; } - er = emulate_instruction(vcpu, emul_type); + er = kvm_emulate_instruction(vcpu, emul_type); if (er == EMULATE_USER_EXIT) return 0; if (er != EMULATE_DONE) @@ -5870,7 +5883,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, gpa_t gpa = cr2; kvm_pfn_t pfn; - if (emulation_type & EMULTYPE_NO_REEXECUTE) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (!vcpu->arch.mmu.direct_map) { @@ -5958,7 +5974,10 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, */ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - if (!(emulation_type & EMULTYPE_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (x86_page_table_writing_insn(ctxt)) @@ -6276,7 +6295,19 @@ restart: return r; } -EXPORT_SYMBOL_GPL(x86_emulate_instruction); + +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) +{ + return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction); + +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len) +{ + return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) @@ -7343,6 +7374,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); +void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) +{ + smp_send_reschedule(vcpu->cpu); +} +EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); + /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7547,7 +7584,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - smp_send_reschedule(vcpu->cpu); + kvm_x86_ops->request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); @@ -7734,7 +7771,7 @@ static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { int r; vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); + r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r != EMULATE_DONE) return 0; @@ -7811,6 +7848,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) return 0; } +/* Swap (qemu) user FPU context for the guest FPU context. */ +static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); + preempt_enable(); + trace_kvm_fpu(1); +} + +/* When vcpu_run ends, restore user space FPU context. */ +static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); + copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); + preempt_enable(); + ++vcpu->stat.fpu_reload; + trace_kvm_fpu(0); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { int r; @@ -8159,7 +8219,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); - if (!is_long_mode(vcpu) && is_pae(vcpu)) { + if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) { load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); mmu_reset_needed = 1; } @@ -8388,29 +8448,6 @@ static void fx_init(struct kvm_vcpu *vcpu) vcpu->arch.cr0 |= X86_CR0_ET; } -/* Swap (qemu) user FPU context for the guest FPU context. */ -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.user_fpu); - /* PKRU is separately restored in kvm_x86_ops->run. */ - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, - ~XFEATURE_MASK_PKRU); - preempt_enable(); - trace_kvm_fpu(1); -} - -/* When vcpu_run ends, restore user space FPU context. */ -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); - copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state); - preempt_enable(); - ++vcpu->stat.fpu_reload; - trace_kvm_fpu(0); -} - void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; @@ -8834,6 +8871,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.kvmclock_offset = -ktime_get_boot_ns(); pvclock_update_vm_gtod_copy(kvm); + kvm->arch.guest_can_read_msr_platform_info = true; + INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn); INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn); @@ -9182,6 +9221,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_page_track_flush_slot(kvm, slot); } +static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) +{ + return (is_guest_mode(vcpu) && + kvm_x86_ops->guest_apic_has_interrupt && + kvm_x86_ops->guest_apic_has_interrupt(vcpu)); +} + static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) { if (!list_empty_careful(&vcpu->async_pf.done)) @@ -9206,7 +9252,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; if (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)) + (kvm_cpu_has_interrupt(vcpu) || + kvm_guest_apic_has_interrupt(vcpu))) return true; if (kvm_hv_has_stimer_pending(vcpu)) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 257f27620bc2..67b9568613f3 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -274,6 +274,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); +int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, + int emulation_type, void *insn, int insn_len); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 7a8fc26c1115..faca978ebf9d 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -815,10 +815,14 @@ void free_kernel_image_pages(void *begin, void *end) set_memory_np_noalias(begin_ul, len_pages); } +void __weak mem_encrypt_free_decrypted_mem(void) { } + void __ref free_initmem(void) { e820__reallocate_tables(); + mem_encrypt_free_decrypted_mem(); + free_kernel_image_pages(&__init_begin, &__init_end); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index b2de398d1fd3..006f373f54ab 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -348,6 +348,30 @@ bool sev_active(void) EXPORT_SYMBOL(sev_active); /* Architecture __weak replacement functions */ +void __init mem_encrypt_free_decrypted_mem(void) +{ + unsigned long vaddr, vaddr_end, npages; + int r; + + vaddr = (unsigned long)__start_bss_decrypted_unused; + vaddr_end = (unsigned long)__end_bss_decrypted; + npages = (vaddr_end - vaddr) >> PAGE_SHIFT; + + /* + * The unused memory range was mapped decrypted, change the encryption + * attribute from decrypted to encrypted before freeing it. + */ + if (mem_encrypt_active()) { + r = set_memory_encrypted(vaddr, npages); + if (r) { + pr_warn("failed to free unused decrypted pages\n"); + return; + } + } + + free_init_pages("unused decrypted", vaddr, vaddr_end); +} + void __init mem_encrypt_init(void) { if (!sme_me_mask) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index e848a4811785..089e78c4effd 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -269,7 +269,7 @@ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - *pgdp = native_make_pgd(0); + pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); @@ -494,7 +494,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(*ptep, entry); if (changed && dirty) - *ptep = entry; + set_pte(ptep, entry); return changed; } @@ -509,7 +509,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { - *pmdp = entry; + set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -529,7 +529,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { - *pudp = entry; + set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, @@ -637,6 +637,15 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); +#ifdef CONFIG_X86_64 + /* + * Ensure that the static initial page tables are covering the + * fixmap completely. + */ + BUILD_BUG_ON(__end_of_permanent_fixed_addresses > + (FIXMAP_PMD_NUM * PTRS_PER_PTE)); +#endif + if (idx >= __end_of_fixed_addresses) { BUG(); return; 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/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 2fe5c9b1816b..dd461c0167ef 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1907,7 +1907,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); - /* L3_k[511][506] -> level1_fixmap_pgt */ + /* L3_k[511][508-FIXMAP_PMD_NUM ... 507] -> level1_fixmap_pgt */ convert_pfn_mfn(level2_fixmap_pgt); /* We get [511][511] and have Xen's version of level2_kernel_pgt */ @@ -1952,7 +1952,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); + + for (i = 0; i < FIXMAP_PMD_NUM; i++) { + set_page_prot(level1_fixmap_pgt + i * PTRS_PER_PTE, + PAGE_KERNEL_RO); + } /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 7d00d4ad44d4..95997e6c0696 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -478,7 +478,7 @@ static void xen_convert_regs(const struct xen_pmu_regs *xen_regs, irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) { int err, ret = IRQ_NONE; - struct pt_regs regs; + struct pt_regs regs = {0}; const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); uint8_t xenpmu_flags = get_xenpmu_flags(); 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/bfq-cgroup.c b/block/bfq-cgroup.c index 58c6efa9f9a9..9fe5952d117d 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -275,9 +275,9 @@ static void bfqg_and_blkg_get(struct bfq_group *bfqg) void bfqg_and_blkg_put(struct bfq_group *bfqg) { - bfqg_put(bfqg); - blkg_put(bfqg_to_blkg(bfqg)); + + bfqg_put(bfqg); } /* @stats = 0 */ diff --git a/block/bio.c b/block/bio.c index b12966e415d3..0093bed81c0e 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1684,7 +1684,7 @@ void generic_end_io_acct(struct request_queue *q, int req_op, const int sgrp = op_stat_group(req_op); int cpu = part_stat_lock(); - part_stat_add(cpu, part, ticks[sgrp], duration); + part_stat_add(cpu, part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_round_stats(q, cpu, part); part_dec_in_flight(q, part, op_is_write(req_op)); @@ -2015,7 +2015,8 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) { if (unlikely(bio->bi_blkg)) return -EBUSY; - blkg_get(blkg); + if (!blkg_try_get(blkg)) + return -ENODEV; bio->bi_blkg = blkg; return 0; } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 694595b29b8f..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -310,28 +310,11 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, } } -static void blkg_pd_offline(struct blkcg_gq *blkg) -{ - int i; - - lockdep_assert_held(blkg->q->queue_lock); - lockdep_assert_held(&blkg->blkcg->lock); - - for (i = 0; i < BLKCG_MAX_POLS; i++) { - struct blkcg_policy *pol = blkcg_policy[i]; - - if (blkg->pd[i] && !blkg->pd[i]->offline && - pol->pd_offline_fn) { - pol->pd_offline_fn(blkg->pd[i]); - blkg->pd[i]->offline = true; - } - } -} - static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; struct blkcg_gq *parent = blkg->parent; + int i; lockdep_assert_held(blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); @@ -340,6 +323,13 @@ static void blkg_destroy(struct blkcg_gq *blkg) WARN_ON_ONCE(list_empty(&blkg->q_node)); WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node)); + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + + if (blkg->pd[i] && pol->pd_offline_fn) + pol->pd_offline_fn(blkg->pd[i]); + } + if (parent) { blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); @@ -382,7 +372,6 @@ static void blkg_destroy_all(struct request_queue *q) struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); - blkg_pd_offline(blkg); blkg_destroy(blkg); spin_unlock(&blkcg->lock); } @@ -1053,59 +1042,64 @@ static struct cftype blkcg_legacy_files[] = { { } /* terminate */ }; +/* + * blkcg destruction is a three-stage process. + * + * 1. Destruction starts. The blkcg_css_offline() callback is invoked + * which offlines writeback. Here we tie the next stage of blkg destruction + * to the completion of writeback associated with the blkcg. This lets us + * avoid punting potentially large amounts of outstanding writeback to root + * while maintaining any ongoing policies. The next stage is triggered when + * the nr_cgwbs count goes to zero. + * + * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called + * and handles the destruction of blkgs. Here the css reference held by + * the blkg is put back eventually allowing blkcg_css_free() to be called. + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. Any submitted ios that fail to get the blkg ref will be + * punted to the root_blkg. + * + * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. + * This finally frees the blkcg. + */ + /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * - * This function is called when @css is about to go away and responsible - * for offlining all blkgs pd and killing all wbs associated with @css. - * blkgs pd offline should be done while holding both q and blkcg locks. - * As blkcg lock is nested inside q lock, this function performs reverse - * double lock dancing. - * - * This is the blkcg counterpart of ioc_release_fn(). + * This function is called when @css is about to go away. Here the cgwbs are + * offlined first and only once writeback associated with the blkcg has + * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); - struct blkcg_gq *blkg; - - spin_lock_irq(&blkcg->lock); - - hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - struct request_queue *q = blkg->q; - - if (spin_trylock(q->queue_lock)) { - blkg_pd_offline(blkg); - spin_unlock(q->queue_lock); - } else { - spin_unlock_irq(&blkcg->lock); - cpu_relax(); - spin_lock_irq(&blkcg->lock); - } - } - - spin_unlock_irq(&blkcg->lock); + /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(blkcg); + + /* put the base cgwb reference allowing step 2 to be triggered */ + blkcg_cgwb_put(blkcg); } /** - * blkcg_destroy_all_blkgs - destroy all blkgs associated with a blkcg + * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * - * This function is called when blkcg css is about to free and responsible for - * destroying all blkgs associated with @blkcg. - * blkgs should be removed while holding both q and blkcg locks. As blkcg lock + * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. + * Destroying the blkgs releases the reference held on the blkcg's css allowing + * blkcg_css_free to eventually be called. + * + * This is the blkcg counterpart of ioc_release_fn(). */ -static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) +void blkcg_destroy_blkgs(struct blkcg *blkcg) { spin_lock_irq(&blkcg->lock); + while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, - struct blkcg_gq, - blkcg_node); + struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (spin_trylock(q->queue_lock)) { @@ -1117,6 +1111,7 @@ static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) spin_lock_irq(&blkcg->lock); } } + spin_unlock_irq(&blkcg->lock); } @@ -1125,8 +1120,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css) struct blkcg *blkcg = css_to_blkcg(css); int i; - blkcg_destroy_all_blkgs(blkcg); - mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); @@ -1189,6 +1182,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); + refcount_set(&blkcg->cgwb_refcnt, 1); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); @@ -1480,11 +1474,8 @@ void blkcg_deactivate_policy(struct request_queue *q, list_for_each_entry(blkg, &q->blkg_list, q_node) { if (blkg->pd[pol->plid]) { - if (!blkg->pd[pol->plid]->offline && - pol->pd_offline_fn) { + if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); - blkg->pd[pol->plid]->offline = true; - } pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } @@ -1519,8 +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/block/blk-core.c b/block/blk-core.c index dee56c282efb..cff0a60ee200 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2163,9 +2163,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) { const int op = bio_op(bio); - if (part->policy && (op_is_write(op) && !op_is_flush(op))) { + if (part->policy && op_is_write(op)) { char b[BDEVNAME_SIZE]; + if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) + return false; + WARN_ONCE(1, "generic_make_request: Trying to write " "to read-only block-device %s (partno %d)\n", @@ -2730,17 +2733,15 @@ void blk_account_io_done(struct request *req, u64 now) * containing request is enough. */ if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { - unsigned long duration; const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; int cpu; - duration = nsecs_to_jiffies(now - req->start_time_ns); cpu = part_stat_lock(); part = req->part; part_stat_inc(cpu, part, ios[sgrp]); - part_stat_add(cpu, part, ticks[sgrp], duration); + part_stat_add(cpu, part, nsecs[sgrp], now - req->start_time_ns); part_round_stats(req->q, cpu, part); part_dec_in_flight(req->q, part, rq_data_dir(req)); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a3eede00d302..01d0620a4e4a 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2129,8 +2129,9 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) { #ifdef CONFIG_BLK_DEV_THROTTLING_LOW - if (bio->bi_css) - bio_associate_blkg(bio, tg_to_blkg(tg)); + /* fallback to root_blkg if we fail to get a blkg ref */ + if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV)) + bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg); bio_issue_init(&bio->bi_issue, bio_sectors(bio)); #endif } diff --git a/block/genhd.c b/block/genhd.c index 8cc719a37b32..be5bab20b2ab 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1343,18 +1343,18 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, ios[STAT_READ]), part_stat_read(hd, merges[STAT_READ]), part_stat_read(hd, sectors[STAT_READ]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])), + (unsigned int)part_stat_read_msecs(hd, STAT_READ), part_stat_read(hd, ios[STAT_WRITE]), part_stat_read(hd, merges[STAT_WRITE]), part_stat_read(hd, sectors[STAT_WRITE]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])), + (unsigned int)part_stat_read_msecs(hd, STAT_WRITE), inflight[0], jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)), part_stat_read(hd, ios[STAT_DISCARD]), part_stat_read(hd, merges[STAT_DISCARD]), part_stat_read(hd, sectors[STAT_DISCARD]), - jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD])) + (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD) ); } disk_part_iter_exit(&piter); diff --git a/block/partition-generic.c b/block/partition-generic.c index 5a8975a1201c..d3d14e81fb12 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -136,18 +136,18 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, ios[STAT_READ]), part_stat_read(p, merges[STAT_READ]), (unsigned long long)part_stat_read(p, sectors[STAT_READ]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])), + (unsigned int)part_stat_read_msecs(p, STAT_READ), part_stat_read(p, ios[STAT_WRITE]), part_stat_read(p, merges[STAT_WRITE]), (unsigned long long)part_stat_read(p, sectors[STAT_WRITE]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])), + (unsigned int)part_stat_read_msecs(p, STAT_WRITE), inflight[0], jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue)), part_stat_read(p, ios[STAT_DISCARD]), part_stat_read(p, merges[STAT_DISCARD]), (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]), - jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD]))); + (unsigned int)part_stat_read_msecs(p, STAT_DISCARD)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 9706613eecf9..bf64cfa30feb 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -879,7 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev) #define LPSS_GPIODEF0_DMA_LLP BIT(13) static DEFINE_MUTEX(lpss_iosf_mutex); -static bool lpss_iosf_d3_entered; +static bool lpss_iosf_d3_entered = true; static void lpss_iosf_enter_d3_state(void) { diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 292088fcc624..d2e29a19890d 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -35,11 +35,11 @@ #include <linux/delay.h> #ifdef CONFIG_X86 #include <asm/mpspec.h> +#include <linux/dmi.h> #endif #include <linux/acpi_iort.h> #include <linux/pci.h> #include <acpi/apei.h> -#include <linux/dmi.h> #include <linux/suspend.h> #include "internal.h" @@ -82,10 +82,6 @@ static const struct dmi_system_id dsdt_dmi_table[] __initconst = { }, {} }; -#else -static const struct dmi_system_id dsdt_dmi_table[] __initconst = { - {} -}; #endif /* -------------------------------------------------------------------------- @@ -1033,11 +1029,16 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; +#ifdef CONFIG_X86 /* * If the machine falls into the DMI check table, - * DSDT will be copied to memory + * DSDT will be copied to memory. + * Note that calling dmi_check_system() here on other architectures + * would not be OK because only x86 initializes dmi early enough. + * Thankfully only x86 systems need such quirks for now. */ dmi_check_system(dsdt_dmi_table); +#endif status = acpi_reallocate_root_table(); if (ACPI_FAILURE(status)) { 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/ata/libata-core.c b/drivers/ata/libata-core.c index 172e32840256..a9dd4ea7467d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5359,10 +5359,20 @@ void ata_qc_complete(struct ata_queued_cmd *qc) */ int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active) { + u64 done_mask, ap_qc_active = ap->qc_active; int nr_done = 0; - u64 done_mask; - done_mask = ap->qc_active ^ qc_active; + /* + * If the internal tag is set on ap->qc_active, then we care about + * bit0 on the passed in qc_active mask. Move that bit up to match + * the internal tag. + */ + if (ap_qc_active & (1ULL << ATA_TAG_INTERNAL)) { + qc_active |= (qc_active & 0x01) << ATA_TAG_INTERNAL; + qc_active ^= qc_active & 0x01; + } + + done_mask = ap_qc_active ^ qc_active; if (unlikely(done_mask & qc_active)) { ata_port_err(ap, "illegal qc_active transition (%08llx->%08llx)\n", @@ -7394,4 +7404,4 @@ EXPORT_SYMBOL_GPL(ata_cable_unknown); EXPORT_SYMBOL_GPL(ata_cable_ignore); EXPORT_SYMBOL_GPL(ata_cable_sata); EXPORT_SYMBOL_GPL(ata_host_get); -EXPORT_SYMBOL_GPL(ata_host_put);
\ No newline at end of file +EXPORT_SYMBOL_GPL(ata_host_put); 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/base/memory.c b/drivers/base/memory.c index c8a1cb0b6136..817320c7c4c1 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -417,25 +417,23 @@ static ssize_t show_valid_zones(struct device *dev, int nid; /* - * The block contains more than one zone can not be offlined. - * This can happen e.g. for ZONE_DMA and ZONE_DMA32 - */ - if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn)) - return sprintf(buf, "none\n"); - - start_pfn = valid_start_pfn; - nr_pages = valid_end_pfn - start_pfn; - - /* * Check the existing zone. Make sure that we do that only on the * online nodes otherwise the page_zone is not reliable */ if (mem->state == MEM_ONLINE) { + /* + * The block contains more than one zone can not be offlined. + * This can happen e.g. for ZONE_DMA and ZONE_DMA32 + */ + if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, + &valid_start_pfn, &valid_end_pfn)) + return sprintf(buf, "none\n"); + start_pfn = valid_start_pfn; strcat(buf, page_zone(pfn_to_page(start_pfn))->name); goto out; } - nid = pfn_to_nid(start_pfn); + nid = mem->nid; default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages); strcat(buf, default_zone->name); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 48f622728ce6..f2b6f4da1034 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3467,6 +3467,9 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int (struct floppy_struct **)&outparam); if (ret) return ret; + memcpy(&inparam.g, outparam, + offsetof(struct floppy_struct, name)); + outparam = &inparam.g; break; case FDMSGON: UDP->flags |= FTD_MSG; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3863c00372bb..14a51254c3db 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1239,6 +1239,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, case NBD_SET_SOCK: return nbd_add_socket(nbd, arg, false); case NBD_SET_BLKSIZE: + if (!arg || !is_power_of_2(arg) || arg < 512 || + arg > PAGE_SIZE) + return -EINVAL; nbd_size_set(nbd, arg, div_s64(config->bytesize, arg)); return 0; 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/block/rbd.c b/drivers/block/rbd.c index 7915f3b03736..73ed5f3a862d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4207,11 +4207,13 @@ static ssize_t rbd_parent_show(struct device *dev, count += sprintf(&buf[count], "%s" "pool_id %llu\npool_name %s\n" + "pool_ns %s\n" "image_id %s\nimage_name %s\n" "snap_id %llu\nsnap_name %s\n" "overlap %llu\n", !count ? "" : "\n", /* first? */ spec->pool_id, spec->pool_name, + spec->pool_ns ?: "", spec->image_id, spec->image_name ?: "(unknown)", spec->snap_id, spec->snap_name, rbd_dev->parent_overlap); @@ -4584,47 +4586,177 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev) &rbd_dev->header.features); } +struct parent_image_info { + u64 pool_id; + const char *pool_ns; + const char *image_id; + u64 snap_id; + + bool has_overlap; + u64 overlap; +}; + +/* + * The caller is responsible for @pii. + */ +static int decode_parent_image_spec(void **p, void *end, + struct parent_image_info *pii) +{ + u8 struct_v; + u32 struct_len; + int ret; + + ret = ceph_start_decoding(p, end, 1, "ParentImageSpec", + &struct_v, &struct_len); + if (ret) + return ret; + + ceph_decode_64_safe(p, end, pii->pool_id, e_inval); + pii->pool_ns = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->pool_ns)) { + ret = PTR_ERR(pii->pool_ns); + pii->pool_ns = NULL; + return ret; + } + pii->image_id = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(p, end, pii->snap_id, e_inval); + return 0; + +e_inval: + return -EINVAL; +} + +static int __get_parent_info(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret == -EOPNOTSUPP ? 1 : ret; + + p = page_address(reply_page); + end = p + reply_len; + ret = decode_parent_image_spec(&p, end, pii); + if (ret) + return ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_overlap_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_8_safe(&p, end, pii->has_overlap, e_inval); + if (pii->has_overlap) + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +/* + * The caller is responsible for @pii. + */ +static int __get_parent_info_legacy(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "get_parent", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_64_safe(&p, end, pii->pool_id, e_inval); + pii->image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(&p, end, pii->snap_id, e_inval); + pii->has_overlap = true; + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +static int get_parent_info(struct rbd_device *rbd_dev, + struct parent_image_info *pii) +{ + struct page *req_page, *reply_page; + void *p; + int ret; + + req_page = alloc_page(GFP_KERNEL); + if (!req_page) + return -ENOMEM; + + reply_page = alloc_page(GFP_KERNEL); + if (!reply_page) { + __free_page(req_page); + return -ENOMEM; + } + + p = page_address(req_page); + ceph_encode_64(&p, rbd_dev->spec->snap_id); + ret = __get_parent_info(rbd_dev, req_page, reply_page, pii); + if (ret > 0) + ret = __get_parent_info_legacy(rbd_dev, req_page, reply_page, + pii); + + __free_page(req_page); + __free_page(reply_page); + return ret; +} + static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) { struct rbd_spec *parent_spec; - size_t size; - void *reply_buf = NULL; - __le64 snapid; - void *p; - void *end; - u64 pool_id; - char *image_id; - u64 snap_id; - u64 overlap; + struct parent_image_info pii = { 0 }; int ret; parent_spec = rbd_spec_alloc(); if (!parent_spec) return -ENOMEM; - size = sizeof (__le64) + /* pool_id */ - sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX + /* image_id */ - sizeof (__le64) + /* snap_id */ - sizeof (__le64); /* overlap */ - reply_buf = kmalloc(size, GFP_KERNEL); - if (!reply_buf) { - ret = -ENOMEM; + ret = get_parent_info(rbd_dev, &pii); + if (ret) goto out_err; - } - snapid = cpu_to_le64(rbd_dev->spec->snap_id); - ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, - &rbd_dev->header_oloc, "get_parent", - &snapid, sizeof(snapid), reply_buf, size); - dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret); - if (ret < 0) - goto out_err; + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id, + pii.has_overlap, pii.overlap); - p = reply_buf; - end = reply_buf + ret; - ret = -ERANGE; - ceph_decode_64_safe(&p, end, pool_id, out_err); - if (pool_id == CEPH_NOPOOL) { + if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) { /* * Either the parent never existed, or we have * record of it but the image got flattened so it no @@ -4633,6 +4765,10 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) * overlap to 0. The effect of this is that all new * requests will be treated as if the image had no * parent. + * + * If !pii.has_overlap, the parent image spec is not + * applicable. It's there to avoid duplication in each + * snapshot record. */ if (rbd_dev->parent_overlap) { rbd_dev->parent_overlap = 0; @@ -4647,51 +4783,36 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) /* The ceph file layout needs to fit pool id in 32 bits */ ret = -EIO; - if (pool_id > (u64)U32_MAX) { + if (pii.pool_id > (u64)U32_MAX) { rbd_warn(NULL, "parent pool id too large (%llu > %u)", - (unsigned long long)pool_id, U32_MAX); + (unsigned long long)pii.pool_id, U32_MAX); goto out_err; } - image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); - if (IS_ERR(image_id)) { - ret = PTR_ERR(image_id); - goto out_err; - } - ceph_decode_64_safe(&p, end, snap_id, out_err); - ceph_decode_64_safe(&p, end, overlap, out_err); - /* * The parent won't change (except when the clone is * flattened, already handled that). So we only need to * record the parent spec we have not already done so. */ if (!rbd_dev->parent_spec) { - parent_spec->pool_id = pool_id; - parent_spec->image_id = image_id; - parent_spec->snap_id = snap_id; - - /* TODO: support cloning across namespaces */ - if (rbd_dev->spec->pool_ns) { - parent_spec->pool_ns = kstrdup(rbd_dev->spec->pool_ns, - GFP_KERNEL); - if (!parent_spec->pool_ns) { - ret = -ENOMEM; - goto out_err; - } + parent_spec->pool_id = pii.pool_id; + if (pii.pool_ns && *pii.pool_ns) { + parent_spec->pool_ns = pii.pool_ns; + pii.pool_ns = NULL; } + parent_spec->image_id = pii.image_id; + pii.image_id = NULL; + parent_spec->snap_id = pii.snap_id; rbd_dev->parent_spec = parent_spec; parent_spec = NULL; /* rbd_dev now owns this */ - } else { - kfree(image_id); } /* * We always update the parent overlap. If it's zero we issue * a warning, as we will proceed as if there was no parent. */ - if (!overlap) { + if (!pii.overlap) { if (parent_spec) { /* refresh, careful to warn just once */ if (rbd_dev->parent_overlap) @@ -4702,14 +4823,14 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); } } - rbd_dev->parent_overlap = overlap; + rbd_dev->parent_overlap = pii.overlap; out: ret = 0; out_err: - kfree(reply_buf); + kfree(pii.pool_ns); + kfree(pii.image_id); rbd_spec_put(parent_spec); - return ret; } 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/Kconfig b/drivers/char/Kconfig index ce277ee0a28a..40728491f37b 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -566,5 +566,5 @@ config RANDOM_TRUST_CPU that CPU manufacturer (perhaps with the insistence or mandate of a Nation State's intelligence or law enforcement agencies) has not installed a hidden back door to compromise the CPU's - random number generation facilities. - + random number generation facilities. This can also be configured + at boot with "random.trust_cpu=on/off". 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/char/random.c b/drivers/char/random.c index bf5f99fc36f1..c75b6cdf0053 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -779,6 +779,13 @@ static struct crng_state **crng_node_pool __read_mostly; static void invalidate_batched_entropy(void); +static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); +static int __init parse_trust_cpu(char *arg) +{ + return kstrtobool(arg, &trust_cpu); +} +early_param("random.trust_cpu", parse_trust_cpu); + static void crng_initialize(struct crng_state *crng) { int i; @@ -799,12 +806,10 @@ static void crng_initialize(struct crng_state *crng) } crng->state[i] ^= rv; } -#ifdef CONFIG_RANDOM_TRUST_CPU - if (arch_init) { + if (trust_cpu && arch_init) { crng_init = 2; pr_notice("random: crng done (trusting CPU's manufacturer)\n"); } -#endif crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; } 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/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c index 218739b961fe..72790d88236d 100644 --- a/drivers/crypto/ccp/psp-dev.c +++ b/drivers/crypto/ccp/psp-dev.c @@ -38,6 +38,17 @@ static DEFINE_MUTEX(sev_cmd_mutex); static struct sev_misc_dev *misc_dev; static struct psp_device *psp_master; +static int psp_cmd_timeout = 100; +module_param(psp_cmd_timeout, int, 0644); +MODULE_PARM_DESC(psp_cmd_timeout, " default timeout value, in seconds, for PSP commands"); + +static int psp_probe_timeout = 5; +module_param(psp_probe_timeout, int, 0644); +MODULE_PARM_DESC(psp_probe_timeout, " default timeout value, in seconds, during PSP device probe"); + +static bool psp_dead; +static int psp_timeout; + static struct psp_device *psp_alloc_struct(struct sp_device *sp) { struct device *dev = sp->dev; @@ -82,10 +93,19 @@ done: return IRQ_HANDLED; } -static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg) +static int sev_wait_cmd_ioc(struct psp_device *psp, + unsigned int *reg, unsigned int timeout) { - wait_event(psp->sev_int_queue, psp->sev_int_rcvd); + int ret; + + ret = wait_event_timeout(psp->sev_int_queue, + psp->sev_int_rcvd, timeout * HZ); + if (!ret) + return -ETIMEDOUT; + *reg = ioread32(psp->io_regs + psp->vdata->cmdresp_reg); + + return 0; } static int sev_cmd_buffer_len(int cmd) @@ -133,12 +153,15 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) if (!psp) return -ENODEV; + if (psp_dead) + return -EBUSY; + /* Get the physical address of the command buffer */ phys_lsb = data ? lower_32_bits(__psp_pa(data)) : 0; phys_msb = data ? upper_32_bits(__psp_pa(data)) : 0; - dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x\n", - cmd, phys_msb, phys_lsb); + dev_dbg(psp->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n", + cmd, phys_msb, phys_lsb, psp_timeout); print_hex_dump_debug("(in): ", DUMP_PREFIX_OFFSET, 16, 2, data, sev_cmd_buffer_len(cmd), false); @@ -154,7 +177,18 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) iowrite32(reg, psp->io_regs + psp->vdata->cmdresp_reg); /* wait for command completion */ - sev_wait_cmd_ioc(psp, ®); + ret = sev_wait_cmd_ioc(psp, ®, psp_timeout); + if (ret) { + if (psp_ret) + *psp_ret = 0; + + dev_err(psp->dev, "sev command %#x timed out, disabling PSP \n", cmd); + psp_dead = true; + + return ret; + } + + psp_timeout = psp_cmd_timeout; if (psp_ret) *psp_ret = reg & PSP_CMDRESP_ERR_MASK; @@ -888,6 +922,8 @@ void psp_pci_init(void) psp_master = sp->psp_data; + psp_timeout = psp_probe_timeout; + if (sev_get_api_version()) goto err; diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 6fd46083e629..bbe4d72ca105 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -392,7 +392,8 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, { struct file *filp = vmf->vma->vm_file; unsigned long fault_size; - int rc, id; + vm_fault_t rc = VM_FAULT_SIGBUS; + int id; pfn_t pfn; struct dev_dax *dev_dax = filp->private_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/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 721e6c57beae..64342944d917 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -166,7 +166,13 @@ scmi_perf_domain_attributes_get(const struct scmi_handle *handle, u32 domain, le32_to_cpu(attr->sustained_freq_khz); dom_info->sustained_perf_level = le32_to_cpu(attr->sustained_perf_level); - dom_info->mult_factor = (dom_info->sustained_freq_khz * 1000) / + if (!dom_info->sustained_freq_khz || + !dom_info->sustained_perf_level) + /* CPUFreq converts to kHz, hence default 1000 */ + dom_info->mult_factor = 1000; + else + dom_info->mult_factor = + (dom_info->sustained_freq_khz * 1000) / dom_info->sustained_perf_level; memcpy(dom_info->name, attr->name, SCMI_MAX_STR_SIZE); } diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index d8e159feb573..89110dfc7127 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -90,14 +90,17 @@ config EFI_ARMSTUB config EFI_ARMSTUB_DTB_LOADER bool "Enable the DTB loader" depends on EFI_ARMSTUB + default y help Select this config option to add support for the dtb= command line parameter, allowing a device tree blob to be loaded into memory from the EFI System Partition by the stub. - The device tree is typically provided by the platform or by - the bootloader, so this option is mostly for development - purposes only. + If the device tree is provided by the platform or by + the bootloader this option may not be needed. + But, for various development reasons and to maintain existing + functionality for bootloaders that do not have such support + this option is necessary. config EFI_BOOTLOADER_CONTROL tristate "EFI Bootloader Control" 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/gpio/gpio-adp5588.c b/drivers/gpio/gpio-adp5588.c index 3530ccd17e04..da9781a2ef4a 100644 --- a/drivers/gpio/gpio-adp5588.c +++ b/drivers/gpio/gpio-adp5588.c @@ -41,6 +41,8 @@ struct adp5588_gpio { uint8_t int_en[3]; uint8_t irq_mask[3]; uint8_t irq_stat[3]; + uint8_t int_input_en[3]; + uint8_t int_lvl_cached[3]; }; static int adp5588_gpio_read(struct i2c_client *client, u8 reg) @@ -173,12 +175,28 @@ static void adp5588_irq_bus_sync_unlock(struct irq_data *d) struct adp5588_gpio *dev = irq_data_get_irq_chip_data(d); int i; - for (i = 0; i <= ADP5588_BANK(ADP5588_MAXGPIO); i++) + for (i = 0; i <= ADP5588_BANK(ADP5588_MAXGPIO); i++) { + if (dev->int_input_en[i]) { + mutex_lock(&dev->lock); + dev->dir[i] &= ~dev->int_input_en[i]; + dev->int_input_en[i] = 0; + adp5588_gpio_write(dev->client, GPIO_DIR1 + i, + dev->dir[i]); + mutex_unlock(&dev->lock); + } + + if (dev->int_lvl_cached[i] != dev->int_lvl[i]) { + dev->int_lvl_cached[i] = dev->int_lvl[i]; + adp5588_gpio_write(dev->client, GPIO_INT_LVL1 + i, + dev->int_lvl[i]); + } + if (dev->int_en[i] ^ dev->irq_mask[i]) { dev->int_en[i] = dev->irq_mask[i]; adp5588_gpio_write(dev->client, GPIO_INT_EN1 + i, dev->int_en[i]); } + } mutex_unlock(&dev->irq_lock); } @@ -221,9 +239,7 @@ static int adp5588_irq_set_type(struct irq_data *d, unsigned int type) else return -EINVAL; - adp5588_gpio_direction_input(&dev->gpio_chip, gpio); - adp5588_gpio_write(dev->client, GPIO_INT_LVL1 + bank, - dev->int_lvl[bank]); + dev->int_input_en[bank] |= bit; return 0; } diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 28da700f5f52..044888fd96a1 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -728,6 +728,7 @@ static int dwapb_gpio_probe(struct platform_device *pdev) out_unregister: dwapb_gpio_unregister(gpio); dwapb_irq_teardown(gpio); + clk_disable_unprepare(gpio->clk); return err; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index c48ed9d89ff5..8b9d7e42c600 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -25,7 +25,6 @@ struct acpi_gpio_event { struct list_head node; - struct list_head initial_sync_list; acpi_handle handle; unsigned int pin; unsigned int irq; @@ -49,10 +48,19 @@ struct acpi_gpio_chip { struct mutex conn_lock; struct gpio_chip *chip; struct list_head events; + struct list_head deferred_req_irqs_list_entry; }; -static LIST_HEAD(acpi_gpio_initial_sync_list); -static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock); +/* + * For gpiochips which call acpi_gpiochip_request_interrupts() before late_init + * (so builtin drivers) we register the ACPI GpioInt event handlers from a + * late_initcall_sync handler, so that other builtin drivers can register their + * OpRegions before the event handlers can run. This list contains gpiochips + * for which the acpi_gpiochip_request_interrupts() has been deferred. + */ +static DEFINE_MUTEX(acpi_gpio_deferred_req_irqs_lock); +static LIST_HEAD(acpi_gpio_deferred_req_irqs_list); +static bool acpi_gpio_deferred_req_irqs_done; static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) { @@ -89,21 +97,6 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) return gpiochip_get_desc(chip, pin); } -static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event) -{ - mutex_lock(&acpi_gpio_initial_sync_list_lock); - list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list); - mutex_unlock(&acpi_gpio_initial_sync_list_lock); -} - -static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event) -{ - mutex_lock(&acpi_gpio_initial_sync_list_lock); - if (!list_empty(&event->initial_sync_list)) - list_del_init(&event->initial_sync_list); - mutex_unlock(&acpi_gpio_initial_sync_list_lock); -} - static irqreturn_t acpi_gpio_irq_handler(int irq, void *data) { struct acpi_gpio_event *event = data; @@ -186,7 +179,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, gpiod_direction_input(desc); - value = gpiod_get_value(desc); + value = gpiod_get_value_cansleep(desc); ret = gpiochip_lock_as_irq(chip, pin); if (ret) { @@ -229,7 +222,6 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, event->irq = irq; event->pin = pin; event->desc = desc; - INIT_LIST_HEAD(&event->initial_sync_list); ret = request_threaded_irq(event->irq, NULL, handler, irqflags, "ACPI:Event", event); @@ -251,10 +243,9 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, * may refer to OperationRegions from other (builtin) drivers which * may be probed after us. */ - if (handler == acpi_gpio_irq_handler && - (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || - ((irqflags & IRQF_TRIGGER_FALLING) && value == 0))) - acpi_gpio_add_to_initial_sync_list(event); + if (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || + ((irqflags & IRQF_TRIGGER_FALLING) && value == 0)) + handler(event->irq, event); return AE_OK; @@ -283,6 +274,7 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) struct acpi_gpio_chip *acpi_gpio; acpi_handle handle; acpi_status status; + bool defer; if (!chip->parent || !chip->to_irq) return; @@ -295,6 +287,16 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + defer = !acpi_gpio_deferred_req_irqs_done; + if (defer) + list_add(&acpi_gpio->deferred_req_irqs_list_entry, + &acpi_gpio_deferred_req_irqs_list); + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); + + if (defer) + return; + acpi_walk_resources(handle, "_AEI", acpi_gpiochip_request_interrupt, acpi_gpio); } @@ -325,11 +327,14 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + if (!list_empty(&acpi_gpio->deferred_req_irqs_list_entry)) + list_del_init(&acpi_gpio->deferred_req_irqs_list_entry); + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); + list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) { struct gpio_desc *desc; - acpi_gpio_del_from_initial_sync_list(event); - if (irqd_is_wakeup_set(irq_get_irq_data(event->irq))) disable_irq_wake(event->irq); @@ -1052,6 +1057,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip) acpi_gpio->chip = chip; INIT_LIST_HEAD(&acpi_gpio->events); + INIT_LIST_HEAD(&acpi_gpio->deferred_req_irqs_list_entry); status = acpi_attach_data(handle, acpi_gpio_chip_dh, acpi_gpio); if (ACPI_FAILURE(status)) { @@ -1198,20 +1204,28 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) return con_id == NULL; } -/* Sync the initial state of handlers after all builtin drivers have probed */ -static int acpi_gpio_initial_sync(void) +/* Run deferred acpi_gpiochip_request_interrupts() */ +static int acpi_gpio_handle_deferred_request_interrupts(void) { - struct acpi_gpio_event *event, *ep; + struct acpi_gpio_chip *acpi_gpio, *tmp; + + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + list_for_each_entry_safe(acpi_gpio, tmp, + &acpi_gpio_deferred_req_irqs_list, + deferred_req_irqs_list_entry) { + acpi_handle handle; - mutex_lock(&acpi_gpio_initial_sync_list_lock); - list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list, - initial_sync_list) { - acpi_evaluate_object(event->handle, NULL, NULL, NULL); - list_del_init(&event->initial_sync_list); + handle = ACPI_HANDLE(acpi_gpio->chip->parent); + acpi_walk_resources(handle, "_AEI", + acpi_gpiochip_request_interrupt, acpi_gpio); + + list_del_init(&acpi_gpio->deferred_req_irqs_list_entry); } - mutex_unlock(&acpi_gpio_initial_sync_list_lock); + + acpi_gpio_deferred_req_irqs_done = true; + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); return 0; } /* We must use _sync so that this runs after the first deferred_probe run */ -late_initcall_sync(acpi_gpio_initial_sync); +late_initcall_sync(acpi_gpio_handle_deferred_request_interrupts); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index a4f1157d6aa0..d4e7a09598fa 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -31,6 +31,7 @@ static int of_gpiochip_match_node_and_xlate(struct gpio_chip *chip, void *data) struct of_phandle_args *gpiospec = data; return chip->gpiodev->dev.of_node == gpiospec->np && + chip->of_xlate && chip->of_xlate(chip, gpiospec, NULL) >= 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 5661c343a71d..0f9947edb12a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -250,7 +250,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd) int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, - void **cpu_ptr) + void **cpu_ptr, bool mqd_gfx9) { struct amdgpu_device *adev = (struct amdgpu_device *)kgd; struct amdgpu_bo *bo = NULL; @@ -265,6 +265,10 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC; bp.type = ttm_bo_type_kernel; bp.resv = NULL; + + if (mqd_gfx9) + bp.flags |= AMDGPU_GEM_CREATE_MQD_GFX9; + r = amdgpu_bo_create(adev, &bp, &bo); if (r) { dev_err(adev->dev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 41e7dfc3ced3..056fc6ef6c63 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -136,7 +136,7 @@ void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd); /* Shared API */ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, - void **cpu_ptr); + void **cpu_ptr, bool mqd_gfx9); void free_gtt_mem(struct kgd_dev *kgd, void *mem_obj); void get_local_mem_info(struct kgd_dev *kgd, struct kfd_local_mem_info *mem_info); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index 6f0b5267addb..b2e45c8e2e0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -686,7 +686,7 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd, while (true) { temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS); - if (temp & SDMA0_STATUS_REG__RB_CMD_IDLE__SHIFT) + if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK) break; if (time_after(jiffies, end_jiffies)) return -ETIME; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 693ec5ea4950..8816c697b205 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -367,12 +367,14 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, break; case CHIP_POLARIS10: if (type == CGS_UCODE_ID_SMU) { - if ((adev->pdev->device == 0x67df) && - ((adev->pdev->revision == 0xe0) || - (adev->pdev->revision == 0xe3) || - (adev->pdev->revision == 0xe4) || - (adev->pdev->revision == 0xe5) || - (adev->pdev->revision == 0xe7) || + if (((adev->pdev->device == 0x67df) && + ((adev->pdev->revision == 0xe0) || + (adev->pdev->revision == 0xe3) || + (adev->pdev->revision == 0xe4) || + (adev->pdev->revision == 0xe5) || + (adev->pdev->revision == 0xe7) || + (adev->pdev->revision == 0xef))) || + ((adev->pdev->device == 0x6fdf) && (adev->pdev->revision == 0xef))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/polaris10_k_smc.bin"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index b7ec2b0e5a9b..663043c8f0f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1262,10 +1262,10 @@ 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_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 53e038963936..723f0f7754bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -837,6 +837,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x67CA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, {0x1002, 0x67CC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, {0x1002, 0x67CF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, + {0x1002, 0x6FDF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS10}, /* Polaris12 */ {0x1002, 0x6980, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, {0x1002, 0x6981, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_POLARIS12}, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index b4d9e6b4f583..9b4e6ad4a7df 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -457,7 +457,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, if (kfd->kfd2kgd->init_gtt_mem_allocation( kfd->kgd, size, &kfd->gtt_mem, - &kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr)){ + &kfd->gtt_start_gpu_addr, &kfd->gtt_start_cpu_ptr, + false)) { dev_err(kfd_device, "Could not allocate %d bytes\n", size); goto out; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index 7a61f38c09e6..01494752c36a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -62,9 +62,20 @@ int kfd_iommu_device_init(struct kfd_dev *kfd) struct amd_iommu_device_info iommu_info; unsigned int pasid_limit; int err; + struct kfd_topology_device *top_dev; - if (!kfd->device_info->needs_iommu_device) + top_dev = kfd_topology_device_by_id(kfd->id); + + /* + * Overwrite ATS capability according to needs_iommu_device to fix + * potential missing corresponding bit in CRAT of BIOS. + */ + if (!kfd->device_info->needs_iommu_device) { + top_dev->node_props.capability &= ~HSA_CAP_ATS_PRESENT; return 0; + } + + top_dev->node_props.capability |= HSA_CAP_ATS_PRESENT; iommu_info.flags = 0; err = amd_iommu_device_info(kfd->pdev, &iommu_info); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c index f5fc3675f21e..0cedb37cf513 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c @@ -88,7 +88,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd, ALIGN(sizeof(struct v9_mqd), PAGE_SIZE), &((*mqd_mem_obj)->gtt_mem), &((*mqd_mem_obj)->gpu_addr), - (void *)&((*mqd_mem_obj)->cpu_ptr)); + (void *)&((*mqd_mem_obj)->cpu_ptr), true); } else retval = kfd_gtt_sa_allocate(mm->dev, sizeof(struct v9_mqd), mqd_mem_obj); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 05283c99d731..b0064b08aa11 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -782,6 +782,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu); int kfd_topology_remove_device(struct kfd_dev *gpu); struct kfd_topology_device *kfd_topology_device_by_proximity_domain( uint32_t proximity_domain); +struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id); struct kfd_dev *kfd_device_by_id(uint32_t gpu_id); struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev); int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 19ecc8233d66..0dff66be8d7a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -63,22 +63,33 @@ struct kfd_topology_device *kfd_topology_device_by_proximity_domain( return device; } -struct kfd_dev *kfd_device_by_id(uint32_t gpu_id) +struct kfd_topology_device *kfd_topology_device_by_id(uint32_t gpu_id) { - struct kfd_topology_device *top_dev; - struct kfd_dev *device = NULL; + struct kfd_topology_device *top_dev = NULL; + struct kfd_topology_device *ret = NULL; down_read(&topology_lock); list_for_each_entry(top_dev, &topology_device_list, list) if (top_dev->gpu_id == gpu_id) { - device = top_dev->gpu; + ret = top_dev; break; } up_read(&topology_lock); - return device; + return ret; +} + +struct kfd_dev *kfd_device_by_id(uint32_t gpu_id) +{ + struct kfd_topology_device *top_dev; + + top_dev = kfd_topology_device_by_id(gpu_id); + if (!top_dev) + return NULL; + + return top_dev->gpu; } struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev) diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index cb4deb28bb7f..f43ed96cfa6c 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -322,7 +322,7 @@ struct tile_config { struct kfd2kgd_calls { int (*init_gtt_mem_allocation)(struct kgd_dev *kgd, size_t size, void **mem_obj, uint64_t *gpu_addr, - void **cpu_ptr); + void **cpu_ptr, bool mqd_gfx9); void (*free_gtt_mem)(struct kgd_dev *kgd, void *mem_obj); diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 7ada75919756..2870ae205237 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1106,7 +1106,7 @@ static void __drm_state_dump(struct drm_device *dev, struct drm_printer *p, struct drm_connector *connector; struct drm_connector_list_iter conn_iter; - if (!drm_core_check_feature(dev, DRIVER_ATOMIC)) + if (!drm_drv_uses_atomic_modeset(dev)) return; list_for_each_entry(plane, &config->plane_list, head) { diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 6f28fe58f169..373bd4c2b698 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -151,7 +151,7 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id, return ret; } - if (drm_core_check_feature(dev, DRIVER_ATOMIC)) { + if (drm_drv_uses_atomic_modeset(dev)) { ret = drm_atomic_debugfs_init(minor); if (ret) { DRM_ERROR("Failed to create atomic debugfs files\n"); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 8e95d0f7c71d..66493178ffcf 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -2370,7 +2370,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, { int c, o; struct drm_connector *connector; - const struct drm_connector_helper_funcs *connector_funcs; int my_score, best_score, score; struct drm_fb_helper_crtc **crtcs, *crtc; struct drm_fb_helper_connector *fb_helper_conn; @@ -2399,8 +2398,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, if (drm_has_preferred_mode(fb_helper_conn, width, height)) my_score++; - connector_funcs = connector->helper_private; - /* * select a crtc for this connector and then attempt to configure * remaining connectors diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 6e3f56684f4e..51ed99a37803 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -170,20 +170,22 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev, unsigned int tiling_mode = 0; unsigned int stride = 0; - switch (info->drm_format_mod << 10) { - case PLANE_CTL_TILED_LINEAR: + switch (info->drm_format_mod) { + case DRM_FORMAT_MOD_LINEAR: tiling_mode = I915_TILING_NONE; break; - case PLANE_CTL_TILED_X: + case I915_FORMAT_MOD_X_TILED: tiling_mode = I915_TILING_X; stride = info->stride; break; - case PLANE_CTL_TILED_Y: + case I915_FORMAT_MOD_Y_TILED: + case I915_FORMAT_MOD_Yf_TILED: tiling_mode = I915_TILING_Y; stride = info->stride; break; default: - gvt_dbg_core("not supported tiling mode\n"); + gvt_dbg_core("invalid drm_format_mod %llx for tiling\n", + info->drm_format_mod); } obj->tiling_and_stride = tiling_mode | stride; } else { @@ -222,9 +224,26 @@ static int vgpu_get_plane_info(struct drm_device *dev, info->height = p.height; info->stride = p.stride; info->drm_format = p.drm_format; - info->drm_format_mod = p.tiled; + + switch (p.tiled) { + case PLANE_CTL_TILED_LINEAR: + info->drm_format_mod = DRM_FORMAT_MOD_LINEAR; + break; + case PLANE_CTL_TILED_X: + info->drm_format_mod = I915_FORMAT_MOD_X_TILED; + break; + case PLANE_CTL_TILED_Y: + info->drm_format_mod = I915_FORMAT_MOD_Y_TILED; + break; + case PLANE_CTL_TILED_YF: + info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED; + break; + default: + gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled); + } + info->size = (((p.stride * p.height * p.bpp) / 8) + - (PAGE_SIZE - 1)) >> PAGE_SHIFT; + (PAGE_SIZE - 1)) >> PAGE_SHIFT; } else if (plane_id == DRM_PLANE_TYPE_CURSOR) { ret = intel_vgpu_decode_cursor_plane(vgpu, &c); if (ret) diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index face664be3e8..481896fb712a 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -220,8 +220,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) { - plane->tiled = (val & PLANE_CTL_TILED_MASK) >> - _PLANE_CTL_TILED_SHIFT; + plane->tiled = val & PLANE_CTL_TILED_MASK; fmt = skl_format_to_drm( val & PLANE_CTL_FORMAT_MASK, val & PLANE_CTL_ORDER_RGBX, @@ -260,7 +259,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, return -EINVAL; } - plane->stride = intel_vgpu_get_stride(vgpu, pipe, (plane->tiled << 10), + plane->stride = intel_vgpu_get_stride(vgpu, pipe, plane->tiled, (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) ? diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.h b/drivers/gpu/drm/i915/gvt/fb_decoder.h index cb055f3c81a2..60c155085029 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.h +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.h @@ -101,7 +101,7 @@ struct intel_gvt; /* color space conversion and gamma correction are not included */ struct intel_vgpu_primary_plane_format { u8 enabled; /* plane is enabled */ - u8 tiled; /* X-tiled */ + u32 tiled; /* tiling mode: linear, X-tiled, Y tiled, etc */ u8 bpp; /* bits per pixel */ u32 hw_format; /* format field in the PRI_CTL register */ u32 drm_format; /* format in DRM definition */ diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index d26258786e3f..90f50f67909a 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1297,6 +1297,19 @@ static int power_well_ctl_mmio_write(struct intel_vgpu *vgpu, return 0; } +static int gen9_dbuf_ctl_mmio_write(struct intel_vgpu *vgpu, + unsigned int offset, void *p_data, unsigned int bytes) +{ + write_vreg(vgpu, offset, p_data, bytes); + + if (vgpu_vreg(vgpu, offset) & DBUF_POWER_REQUEST) + vgpu_vreg(vgpu, offset) |= DBUF_POWER_STATE; + else + vgpu_vreg(vgpu, offset) &= ~DBUF_POWER_STATE; + + return 0; +} + static int fpga_dbg_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { @@ -1526,9 +1539,15 @@ static int bxt_phy_ctl_family_write(struct intel_vgpu *vgpu, u32 v = *(u32 *)p_data; u32 data = v & COMMON_RESET_DIS ? BXT_PHY_LANE_ENABLED : 0; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data; + switch (offset) { + case _PHY_CTL_FAMILY_EDP: + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data; + break; + case _PHY_CTL_FAMILY_DDI: + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data; + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data; + break; + } vgpu_vreg(vgpu, offset) = v; @@ -2801,6 +2820,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_PWR_WELL_CTL1, D_SKL_PLUS); MMIO_DH(HSW_PWR_WELL_CTL2, D_SKL_PLUS, NULL, skl_power_well_ctl_write); + MMIO_DH(DBUF_CTL, D_SKL_PLUS, NULL, gen9_dbuf_ctl_mmio_write); + MMIO_D(_MMIO(0xa210), D_SKL_PLUS); MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS); MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS); @@ -2976,8 +2997,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) NULL, gen9_trtte_write); MMIO_DH(_MMIO(0x4dfc), D_SKL_PLUS, NULL, gen9_trtt_chicken_write); - MMIO_D(_MMIO(0x45008), D_SKL_PLUS); - MMIO_D(_MMIO(0x46430), D_SKL_PLUS); MMIO_D(_MMIO(0x46520), D_SKL_PLUS); @@ -3014,7 +3033,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(_MMIO(0x44500), D_SKL_PLUS); MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, - NULL, NULL); + NULL, NULL); + MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); MMIO_D(_MMIO(0x4ab8), D_KBL); MMIO_D(_MMIO(0x2248), D_KBL | D_SKL); @@ -3178,6 +3199,7 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(BXT_DSI_PLL_ENABLE, D_BXT); MMIO_D(GEN9_CLKGATE_DIS_0, D_BXT); + MMIO_D(GEN9_CLKGATE_DIS_4, D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_A), D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 71751be329e3..c1072143da1d 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; } @@ -1827,6 +1833,8 @@ static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn) { struct kvmgt_guest_info *info; struct kvm *kvm; + int idx; + bool ret; if (!handle_valid(handle)) return false; @@ -1834,8 +1842,11 @@ static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn) info = (struct kvmgt_guest_info *)handle; kvm = info->kvm; - return kvm_is_visible_gfn(kvm, gfn); + idx = srcu_read_lock(&kvm->srcu); + ret = kvm_is_visible_gfn(kvm, gfn); + srcu_read_unlock(&kvm->srcu, idx); + return ret; } struct intel_gvt_mpt kvmgt_mpt = { diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 4db817c21ed8..43f65848ecd6 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -245,6 +245,34 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu, bool dmlr) /* set the bit 0:2(Core C-State ) to C0 */ vgpu_vreg_t(vgpu, GEN6_GT_CORE_STATUS) = 0; + + if (IS_BROXTON(vgpu->gvt->dev_priv)) { + vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= + ~(BIT(0) | BIT(1)); + vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &= + ~PHY_POWER_GOOD; + vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) &= + ~PHY_POWER_GOOD; + vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY0)) &= + ~BIT(30); + vgpu_vreg_t(vgpu, BXT_PHY_CTL_FAMILY(DPIO_PHY1)) &= + ~BIT(30); + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_A)) &= + ~BXT_PHY_LANE_ENABLED; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_A)) |= + BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_B)) &= + ~BXT_PHY_LANE_ENABLED; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_B)) |= + BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_C)) &= + ~BXT_PHY_LANE_ENABLED; + vgpu_vreg_t(vgpu, BXT_PHY_CTL(PORT_C)) |= + BXT_PHY_CMNLANE_POWERDOWN_ACK | + BXT_PHY_LANE_POWERDOWN_ACK; + } } else { #define GVT_GEN8_MMIO_RESET_OFFSET (0x44200) /* only reset the engine related, so starting with 0x44200 diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 7e702c6a32af..10e63eea5492 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -549,11 +549,9 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre, * performace for batch mmio read/write, so we need * handle forcewake mannually. */ - intel_runtime_pm_get(dev_priv); intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); switch_mmio(pre, next, ring_id); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); - intel_runtime_pm_put(dev_priv); } /** diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 82586c8e434f..276db53f1bf1 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/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 09d7bb72b4ff..c32e7d5e8629 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -47,11 +47,15 @@ static bool vgpu_has_pending_workload(struct intel_vgpu *vgpu) return false; } +/* We give 2 seconds higher prio for vGPU during start */ +#define GVT_SCHED_VGPU_PRI_TIME 2 + struct vgpu_sched_data { struct list_head lru_list; struct intel_vgpu *vgpu; bool active; - + bool pri_sched; + ktime_t pri_time; ktime_t sched_in_time; ktime_t sched_time; ktime_t left_ts; @@ -183,6 +187,14 @@ static struct intel_vgpu *find_busy_vgpu(struct gvt_sched_data *sched_data) if (!vgpu_has_pending_workload(vgpu_data->vgpu)) continue; + if (vgpu_data->pri_sched) { + if (ktime_before(ktime_get(), vgpu_data->pri_time)) { + vgpu = vgpu_data->vgpu; + break; + } else + vgpu_data->pri_sched = false; + } + /* Return the vGPU only if it has time slice left */ if (vgpu_data->left_ts > 0) { vgpu = vgpu_data->vgpu; @@ -202,6 +214,7 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data) struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; struct vgpu_sched_data *vgpu_data; struct intel_vgpu *vgpu = NULL; + /* no active vgpu or has already had a target */ if (list_empty(&sched_data->lru_runq_head) || scheduler->next_vgpu) goto out; @@ -209,12 +222,13 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data) vgpu = find_busy_vgpu(sched_data); if (vgpu) { scheduler->next_vgpu = vgpu; - - /* Move the last used vGPU to the tail of lru_list */ vgpu_data = vgpu->sched_data; - list_del_init(&vgpu_data->lru_list); - list_add_tail(&vgpu_data->lru_list, - &sched_data->lru_runq_head); + if (!vgpu_data->pri_sched) { + /* Move the last used vGPU to the tail of lru_list */ + list_del_init(&vgpu_data->lru_list); + list_add_tail(&vgpu_data->lru_list, + &sched_data->lru_runq_head); + } } else { scheduler->next_vgpu = gvt->idle_vgpu; } @@ -328,11 +342,17 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu) { struct gvt_sched_data *sched_data = vgpu->gvt->scheduler.sched_data; struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + ktime_t now; if (!list_empty(&vgpu_data->lru_list)) return; - list_add_tail(&vgpu_data->lru_list, &sched_data->lru_runq_head); + now = ktime_get(); + vgpu_data->pri_time = ktime_add(now, + ktime_set(GVT_SCHED_VGPU_PRI_TIME, 0)); + vgpu_data->pri_sched = true; + + list_add(&vgpu_data->lru_list, &sched_data->lru_runq_head); if (!hrtimer_active(&sched_data->timer)) hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(), @@ -426,6 +446,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) &vgpu->gvt->scheduler; int ring_id; struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; if (!vgpu_data->active) return; @@ -444,6 +465,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) scheduler->current_vgpu = NULL; } + intel_runtime_pm_get(dev_priv); spin_lock_bh(&scheduler->mmio_context_lock); for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) { if (scheduler->engine_owner[ring_id] == vgpu) { @@ -452,5 +474,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) } } spin_unlock_bh(&scheduler->mmio_context_lock); + intel_runtime_pm_put(dev_priv); mutex_unlock(&vgpu->gvt->sched_lock); } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index a4e8e3cf74fd..c628be05fbfe 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -281,6 +281,7 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) intel_vgpu_clean_submission(vgpu); intel_vgpu_clean_display(vgpu); intel_vgpu_clean_opregion(vgpu); + intel_vgpu_reset_ggtt(vgpu, true); intel_vgpu_clean_gtt(vgpu); intel_gvt_hypervisor_detach_vgpu(vgpu); intel_vgpu_free_resource(vgpu); 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/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index a9bb656058e5..1dbd1dcdcf15 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1123,17 +1123,21 @@ nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state) int ret; if (dpcd >= 0x12) { - ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CTRL, &dpcd); + /* Even if we're enabling MST, start with disabling the + * branching unit to clear any sink-side MST topology state + * that wasn't set by us + */ + ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, 0); if (ret < 0) return ret; - dpcd &= ~DP_MST_EN; - if (state) - dpcd |= DP_MST_EN; - - ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, dpcd); - if (ret < 0) - return ret; + if (state) { + /* Now, start initializing */ + ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, + DP_MST_EN); + if (ret < 0) + return ret; + } } return nvif_mthd(disp, 0, &args, sizeof(args)); @@ -1142,31 +1146,58 @@ nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state) int nv50_mstm_detect(struct nv50_mstm *mstm, u8 dpcd[8], int allow) { - int ret, state = 0; + struct drm_dp_aux *aux; + int ret; + bool old_state, new_state; + u8 mstm_ctrl; if (!mstm) return 0; - if (dpcd[0] >= 0x12) { - ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CAP, &dpcd[1]); + mutex_lock(&mstm->mgr.lock); + + old_state = mstm->mgr.mst_state; + new_state = old_state; + aux = mstm->mgr.aux; + + if (old_state) { + /* Just check that the MST hub is still as we expect it */ + ret = drm_dp_dpcd_readb(aux, DP_MSTM_CTRL, &mstm_ctrl); + if (ret < 0 || !(mstm_ctrl & DP_MST_EN)) { + DRM_DEBUG_KMS("Hub gone, disabling MST topology\n"); + new_state = false; + } + } else if (dpcd[0] >= 0x12) { + ret = drm_dp_dpcd_readb(aux, DP_MSTM_CAP, &dpcd[1]); if (ret < 0) - return ret; + goto probe_error; if (!(dpcd[1] & DP_MST_CAP)) dpcd[0] = 0x11; else - state = allow; + new_state = allow; + } + + if (new_state == old_state) { + mutex_unlock(&mstm->mgr.lock); + return new_state; } - ret = nv50_mstm_enable(mstm, dpcd[0], state); + ret = nv50_mstm_enable(mstm, dpcd[0], new_state); if (ret) - return ret; + goto probe_error; + + mutex_unlock(&mstm->mgr.lock); - ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, state); + ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, new_state); if (ret) return nv50_mstm_enable(mstm, dpcd[0], 0); - return mstm->mgr.mst_state; + return new_state; + +probe_error: + mutex_unlock(&mstm->mgr.lock); + return ret; } static void @@ -2074,7 +2105,7 @@ nv50_disp_atomic_state_alloc(struct drm_device *dev) static const struct drm_mode_config_funcs nv50_disp_func = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, .atomic_check = nv50_disp_atomic_check, .atomic_commit = nv50_disp_atomic_commit, .atomic_state_alloc = nv50_disp_atomic_state_alloc, diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index eb4f766b5958..dde8724aa8f5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -411,59 +411,45 @@ static struct nouveau_encoder * nouveau_connector_ddc_detect(struct drm_connector *connector) { struct drm_device *dev = connector->dev; - struct nouveau_connector *nv_connector = nouveau_connector(connector); - struct nouveau_drm *drm = nouveau_drm(dev); - struct nvkm_gpio *gpio = nvxx_gpio(&drm->client.device); - struct nouveau_encoder *nv_encoder = NULL; + struct nouveau_encoder *nv_encoder = NULL, *found = NULL; struct drm_encoder *encoder; - int i, panel = -ENODEV; - - /* eDP panels need powering on by us (if the VBIOS doesn't default it - * to on) before doing any AUX channel transactions. LVDS panel power - * is handled by the SOR itself, and not required for LVDS DDC. - */ - if (nv_connector->type == DCB_CONNECTOR_eDP) { - panel = nvkm_gpio_get(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff); - if (panel == 0) { - nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 1); - msleep(300); - } - } + int i, ret; + bool switcheroo_ddc = false; drm_connector_for_each_possible_encoder(connector, encoder, i) { nv_encoder = nouveau_encoder(encoder); - if (nv_encoder->dcb->type == DCB_OUTPUT_DP) { - int ret = nouveau_dp_detect(nv_encoder); + switch (nv_encoder->dcb->type) { + case DCB_OUTPUT_DP: + ret = nouveau_dp_detect(nv_encoder); if (ret == NOUVEAU_DP_MST) return NULL; - if (ret == NOUVEAU_DP_SST) - break; - } else - if ((vga_switcheroo_handler_flags() & - VGA_SWITCHEROO_CAN_SWITCH_DDC) && - nv_encoder->dcb->type == DCB_OUTPUT_LVDS && - nv_encoder->i2c) { - int ret; - vga_switcheroo_lock_ddc(dev->pdev); - ret = nvkm_probe_i2c(nv_encoder->i2c, 0x50); - vga_switcheroo_unlock_ddc(dev->pdev); - if (ret) + else if (ret == NOUVEAU_DP_SST) + found = nv_encoder; + + break; + case DCB_OUTPUT_LVDS: + switcheroo_ddc = !!(vga_switcheroo_handler_flags() & + VGA_SWITCHEROO_CAN_SWITCH_DDC); + /* fall-through */ + default: + if (!nv_encoder->i2c) break; - } else - if (nv_encoder->i2c) { + + if (switcheroo_ddc) + vga_switcheroo_lock_ddc(dev->pdev); if (nvkm_probe_i2c(nv_encoder->i2c, 0x50)) - break; + found = nv_encoder; + if (switcheroo_ddc) + vga_switcheroo_unlock_ddc(dev->pdev); + + break; } + if (found) + break; } - /* eDP panel not detected, restore panel power GPIO to previous - * state to avoid confusing the SOR for other output types. - */ - if (!nv_encoder && panel == 0) - nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, panel); - - return nv_encoder; + return found; } static struct nouveau_encoder * @@ -557,12 +543,16 @@ nouveau_connector_detect(struct drm_connector *connector, bool force) nv_connector->edid = NULL; } - /* Outputs are only polled while runtime active, so acquiring a - * runtime PM ref here is unnecessary (and would deadlock upon - * runtime suspend because it waits for polling to finish). + /* Outputs are only polled while runtime active, so resuming the + * device here is unnecessary (and would deadlock upon runtime suspend + * because it waits for polling to finish). We do however, want to + * prevent the autosuspend timer from elapsing during this operation + * if possible. */ - if (!drm_kms_helper_is_poll_worker()) { - ret = pm_runtime_get_sync(connector->dev->dev); + if (drm_kms_helper_is_poll_worker()) { + pm_runtime_get_noresume(dev->dev); + } else { + ret = pm_runtime_get_sync(dev->dev); if (ret < 0 && ret != -EACCES) return conn_status; } @@ -641,10 +631,8 @@ detect_analog: out: - if (!drm_kms_helper_is_poll_worker()) { - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); - } + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); return conn_status; } @@ -1108,6 +1096,26 @@ nouveau_connector_hotplug(struct nvif_notify *notify) const struct nvif_notify_conn_rep_v0 *rep = notify->data; const char *name = connector->name; struct nouveau_encoder *nv_encoder; + int ret; + + ret = pm_runtime_get(drm->dev->dev); + if (ret == 0) { + /* We can't block here if there's a pending PM request + * running, as we'll deadlock nouveau_display_fini() when it + * calls nvif_put() on our nvif_notify struct. So, simply + * defer the hotplug event until the device finishes resuming + */ + NV_DEBUG(drm, "Deferring HPD on %s until runtime resume\n", + name); + schedule_work(&drm->hpd_work); + + pm_runtime_put_noidle(drm->dev->dev); + return NVIF_NOTIFY_KEEP; + } else if (ret != 1 && ret != -EACCES) { + NV_WARN(drm, "HPD on %s dropped due to RPM failure: %d\n", + name, ret); + return NVIF_NOTIFY_DROP; + } if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) { NV_DEBUG(drm, "service %s\n", name); @@ -1128,6 +1136,8 @@ nouveau_connector_hotplug(struct nvif_notify *notify) drm_helper_hpd_irq_event(connector->dev); } + pm_runtime_mark_last_busy(drm->dev->dev); + pm_runtime_put_autosuspend(drm->dev->dev); return NVIF_NOTIFY_KEEP; } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 139368b31916..540c0cbbfcee 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -293,7 +293,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev, static const struct drm_mode_config_funcs nouveau_mode_config_funcs = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, }; @@ -355,8 +355,6 @@ nouveau_display_hpd_work(struct work_struct *work) pm_runtime_get_sync(drm->dev->dev); drm_helper_hpd_irq_event(drm->dev); - /* enable polling for external displays */ - drm_kms_helper_poll_enable(drm->dev); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); @@ -379,15 +377,29 @@ nouveau_display_acpi_ntfy(struct notifier_block *nb, unsigned long val, { struct nouveau_drm *drm = container_of(nb, typeof(*drm), acpi_nb); struct acpi_bus_event *info = data; + int ret; if (!strcmp(info->device_class, ACPI_VIDEO_CLASS)) { if (info->type == ACPI_VIDEO_NOTIFY_PROBE) { - /* - * This may be the only indication we receive of a - * connector hotplug on a runtime suspended GPU, - * schedule hpd_work to check. - */ - schedule_work(&drm->hpd_work); + ret = pm_runtime_get(drm->dev->dev); + if (ret == 1 || ret == -EACCES) { + /* If the GPU is already awake, or in a state + * where we can't wake it up, it can handle + * it's own hotplug events. + */ + pm_runtime_put_autosuspend(drm->dev->dev); + } else if (ret == 0) { + /* This may be the only indication we receive + * of a connector hotplug on a runtime + * suspended GPU, schedule hpd_work to check. + */ + NV_DEBUG(drm, "ACPI requested connector reprobe\n"); + schedule_work(&drm->hpd_work); + pm_runtime_put_noidle(drm->dev->dev); + } else { + NV_WARN(drm, "Dropped ACPI reprobe event due to RPM error: %d\n", + ret); + } /* acpi-video should not generate keypresses for this */ return NOTIFY_BAD; @@ -411,6 +423,11 @@ nouveau_display_init(struct drm_device *dev) if (ret) return ret; + /* enable connector detection and polling for connectors without HPD + * support + */ + drm_kms_helper_poll_enable(dev); + /* enable hotplug interrupts */ drm_connector_list_iter_begin(dev, &conn_iter); nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { @@ -425,7 +442,7 @@ nouveau_display_init(struct drm_device *dev) } void -nouveau_display_fini(struct drm_device *dev, bool suspend) +nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime) { struct nouveau_display *disp = nouveau_display(dev); struct nouveau_drm *drm = nouveau_drm(dev); @@ -450,6 +467,9 @@ nouveau_display_fini(struct drm_device *dev, bool suspend) } drm_connector_list_iter_end(&conn_iter); + if (!runtime) + cancel_work_sync(&drm->hpd_work); + drm_kms_helper_poll_disable(dev); disp->fini(dev); } @@ -618,11 +638,11 @@ nouveau_display_suspend(struct drm_device *dev, bool runtime) } } - nouveau_display_fini(dev, true); + nouveau_display_fini(dev, true, runtime); return 0; } - nouveau_display_fini(dev, true); + nouveau_display_fini(dev, true, runtime); list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_framebuffer *nouveau_fb; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h index 54aa7c3fa42d..ff92b54ce448 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.h +++ b/drivers/gpu/drm/nouveau/nouveau_display.h @@ -62,7 +62,7 @@ nouveau_display(struct drm_device *dev) int nouveau_display_create(struct drm_device *dev); void nouveau_display_destroy(struct drm_device *dev); int nouveau_display_init(struct drm_device *dev); -void nouveau_display_fini(struct drm_device *dev, bool suspend); +void nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime); int nouveau_display_suspend(struct drm_device *dev, bool runtime); void nouveau_display_resume(struct drm_device *dev, bool runtime); int nouveau_display_vblank_enable(struct drm_device *, unsigned int); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index c7ec86d6c3c9..74d2283f2c28 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -230,7 +230,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, mutex_unlock(&drm->master.lock); } if (ret) { - NV_ERROR(drm, "Client allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "Client allocation failed: %d\n", ret); goto done; } @@ -240,37 +240,37 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, }, sizeof(struct nv_device_v0), &cli->device); if (ret) { - NV_ERROR(drm, "Device allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "Device allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->device.object, mmus); if (ret < 0) { - NV_ERROR(drm, "No supported MMU class\n"); + NV_PRINTK(err, cli, "No supported MMU class\n"); goto done; } ret = nvif_mmu_init(&cli->device.object, mmus[ret].oclass, &cli->mmu); if (ret) { - NV_ERROR(drm, "MMU allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "MMU allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->mmu.object, vmms); if (ret < 0) { - NV_ERROR(drm, "No supported VMM class\n"); + NV_PRINTK(err, cli, "No supported VMM class\n"); goto done; } ret = nouveau_vmm_init(cli, vmms[ret].oclass, &cli->vmm); if (ret) { - NV_ERROR(drm, "VMM allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "VMM allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->mmu.object, mems); if (ret < 0) { - NV_ERROR(drm, "No supported MEM class\n"); + NV_PRINTK(err, cli, "No supported MEM class\n"); goto done; } @@ -592,10 +592,8 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags) pm_runtime_allow(dev->dev); pm_runtime_mark_last_busy(dev->dev); pm_runtime_put(dev->dev); - } else { - /* enable polling for external displays */ - drm_kms_helper_poll_enable(dev); } + return 0; fail_dispinit: @@ -629,7 +627,7 @@ nouveau_drm_unload(struct drm_device *dev) nouveau_debugfs_fini(drm); if (dev->mode_config.num_crtc) - nouveau_display_fini(dev, false); + nouveau_display_fini(dev, false, false); nouveau_display_destroy(dev); nouveau_bios_takedown(dev); @@ -835,7 +833,6 @@ nouveau_pmops_runtime_suspend(struct device *dev) return -EBUSY; } - drm_kms_helper_poll_disable(drm_dev); nouveau_switcheroo_optimus_dsm(); ret = nouveau_do_suspend(drm_dev, true); pci_save_state(pdev); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 20a260887be3..032317c81bf0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -465,6 +465,7 @@ nouveau_fbcon_set_suspend_work(struct work_struct *work) console_unlock(); if (state == FBINFO_STATE_RUNNING) { + nouveau_fbcon_hotplug_resume(drm->fbcon); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); } @@ -486,6 +487,61 @@ nouveau_fbcon_set_suspend(struct drm_device *dev, int state) schedule_work(&drm->fbcon_work); } +void +nouveau_fbcon_output_poll_changed(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon = drm->fbcon; + int ret; + + if (!fbcon) + return; + + mutex_lock(&fbcon->hotplug_lock); + + ret = pm_runtime_get(dev->dev); + if (ret == 1 || ret == -EACCES) { + drm_fb_helper_hotplug_event(&fbcon->helper); + + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); + } else if (ret == 0) { + /* If the GPU was already in the process of suspending before + * this event happened, then we can't block here as we'll + * deadlock the runtime pmops since they wait for us to + * finish. So, just defer this event for when we runtime + * resume again. It will be handled by fbcon_work. + */ + NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n"); + fbcon->hotplug_waiting = true; + pm_runtime_put_noidle(drm->dev->dev); + } else { + DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n", + ret); + } + + mutex_unlock(&fbcon->hotplug_lock); +} + +void +nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon) +{ + struct nouveau_drm *drm; + + if (!fbcon) + return; + drm = nouveau_drm(fbcon->helper.dev); + + mutex_lock(&fbcon->hotplug_lock); + if (fbcon->hotplug_waiting) { + fbcon->hotplug_waiting = false; + + NV_DEBUG(drm, "Handling deferred fbcon HPD events\n"); + drm_fb_helper_hotplug_event(&fbcon->helper); + } + mutex_unlock(&fbcon->hotplug_lock); +} + int nouveau_fbcon_init(struct drm_device *dev) { @@ -504,6 +560,7 @@ nouveau_fbcon_init(struct drm_device *dev) drm->fbcon = fbcon; INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work); + mutex_init(&fbcon->hotplug_lock); drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.h b/drivers/gpu/drm/nouveau/nouveau_fbcon.h index a6f192ea3fa6..db9d52047ef8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.h +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.h @@ -41,6 +41,9 @@ struct nouveau_fbdev { struct nvif_object gdi; struct nvif_object blit; struct nvif_object twod; + + struct mutex hotplug_lock; + bool hotplug_waiting; }; void nouveau_fbcon_restore(void); @@ -68,6 +71,8 @@ void nouveau_fbcon_set_suspend(struct drm_device *dev, int state); void nouveau_fbcon_accel_save_disable(struct drm_device *dev); void nouveau_fbcon_accel_restore(struct drm_device *dev); +void nouveau_fbcon_output_poll_changed(struct drm_device *dev); +void nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon); extern int nouveau_nofbaccel; #endif /* __NV50_FBCON_H__ */ diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c index 3da5a4305aa4..8f1ce4833230 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vga.c +++ b/drivers/gpu/drm/nouveau/nouveau_vga.c @@ -46,12 +46,10 @@ nouveau_switcheroo_set_state(struct pci_dev *pdev, pr_err("VGA switcheroo: switched nouveau on\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; nouveau_pmops_resume(&pdev->dev); - drm_kms_helper_poll_enable(dev); dev->switch_power_state = DRM_SWITCH_POWER_ON; } else { pr_err("VGA switcheroo: switched nouveau off\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; - drm_kms_helper_poll_disable(dev); nouveau_switcheroo_optimus_dsm(); nouveau_pmops_suspend(&pdev->dev); dev->switch_power_state = DRM_SWITCH_POWER_OFF; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c index 32fa94a9773f..cbd33e87b799 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c @@ -275,6 +275,7 @@ nvkm_disp_oneinit(struct nvkm_engine *engine) struct nvkm_outp *outp, *outt, *pair; struct nvkm_conn *conn; struct nvkm_head *head; + struct nvkm_ior *ior; struct nvbios_connE connE; struct dcb_output dcbE; u8 hpd = 0, ver, hdr; @@ -399,6 +400,19 @@ nvkm_disp_oneinit(struct nvkm_engine *engine) return ret; } + /* Enforce identity-mapped SOR assignment for panels, which have + * certain bits (ie. backlight controls) wired to a specific SOR. + */ + list_for_each_entry(outp, &disp->outp, head) { + if (outp->conn->info.type == DCB_CONNECTOR_LVDS || + outp->conn->info.type == DCB_CONNECTOR_eDP) { + ior = nvkm_ior_find(disp, SOR, ffs(outp->info.or) - 1); + if (!WARN_ON(!ior)) + ior->identity = true; + outp->identity = true; + } + } + i = 0; list_for_each_entry(head, &disp->head, head) i = max(i, head->id + 1); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c index 7c5bed29ffef..5f301e632599 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c @@ -28,6 +28,7 @@ #include <subdev/bios.h> #include <subdev/bios/init.h> +#include <subdev/gpio.h> #include <subdev/i2c.h> #include <nvif/event.h> @@ -412,14 +413,10 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps) } static void -nvkm_dp_release(struct nvkm_outp *outp, struct nvkm_ior *ior) +nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior) { struct nvkm_dp *dp = nvkm_dp(outp); - /* Prevent link from being retrained if sink sends an IRQ. */ - atomic_set(&dp->lt.done, 0); - ior->dp.nr = 0; - /* Execute DisableLT script from DP Info Table. */ nvbios_init(&ior->disp->engine.subdev, dp->info.script[4], init.outp = &dp->outp.info; @@ -428,6 +425,16 @@ nvkm_dp_release(struct nvkm_outp *outp, struct nvkm_ior *ior) ); } +static void +nvkm_dp_release(struct nvkm_outp *outp) +{ + struct nvkm_dp *dp = nvkm_dp(outp); + + /* Prevent link from being retrained if sink sends an IRQ. */ + atomic_set(&dp->lt.done, 0); + dp->outp.ior->dp.nr = 0; +} + static int nvkm_dp_acquire(struct nvkm_outp *outp) { @@ -491,7 +498,7 @@ done: return ret; } -static void +static bool nvkm_dp_enable(struct nvkm_dp *dp, bool enable) { struct nvkm_i2c_aux *aux = dp->aux; @@ -505,7 +512,7 @@ nvkm_dp_enable(struct nvkm_dp *dp, bool enable) if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, dp->dpcd, sizeof(dp->dpcd))) - return; + return true; } if (dp->present) { @@ -515,6 +522,7 @@ nvkm_dp_enable(struct nvkm_dp *dp, bool enable) } atomic_set(&dp->lt.done, 0); + return false; } static int @@ -555,9 +563,38 @@ nvkm_dp_fini(struct nvkm_outp *outp) static void nvkm_dp_init(struct nvkm_outp *outp) { + struct nvkm_gpio *gpio = outp->disp->engine.subdev.device->gpio; struct nvkm_dp *dp = nvkm_dp(outp); + nvkm_notify_put(&dp->outp.conn->hpd); - nvkm_dp_enable(dp, true); + + /* eDP panels need powering on by us (if the VBIOS doesn't default it + * to on) before doing any AUX channel transactions. LVDS panel power + * is handled by the SOR itself, and not required for LVDS DDC. + */ + if (dp->outp.conn->info.type == DCB_CONNECTOR_eDP) { + int power = nvkm_gpio_get(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff); + if (power == 0) + nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 1); + + /* We delay here unconditionally, even if already powered, + * because some laptop panels having a significant resume + * delay before the panel begins responding. + * + * This is likely a bit of a hack, but no better idea for + * handling this at the moment. + */ + msleep(300); + + /* If the eDP panel can't be detected, we need to restore + * the panel power GPIO to avoid breaking another output. + */ + if (!nvkm_dp_enable(dp, true) && power == 0) + nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 0); + } else { + nvkm_dp_enable(dp, true); + } + nvkm_notify_get(&dp->hpd); } @@ -576,6 +613,7 @@ nvkm_dp_func = { .fini = nvkm_dp_fini, .acquire = nvkm_dp_acquire, .release = nvkm_dp_release, + .disable = nvkm_dp_disable, }; static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h index e0b4e0c5704e..19911211a12a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h @@ -16,6 +16,7 @@ struct nvkm_ior { char name[8]; struct list_head head; + bool identity; struct nvkm_ior_state { struct nvkm_outp *outp; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c index f89c7b977aa5..def005dd5fda 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c @@ -501,11 +501,11 @@ nv50_disp_super_2_0(struct nv50_disp *disp, struct nvkm_head *head) nv50_disp_super_ied_off(head, ior, 2); /* If we're shutting down the OR's only active head, execute - * the output path's release function. + * the output path's disable function. */ if (ior->arm.head == (1 << head->id)) { - if ((outp = ior->arm.outp) && outp->func->release) - outp->func->release(outp, ior); + if ((outp = ior->arm.outp) && outp->func->disable) + outp->func->disable(outp, ior); } } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c index be9e7f8c3b23..c62030c96fba 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c @@ -93,6 +93,8 @@ nvkm_outp_release(struct nvkm_outp *outp, u8 user) if (ior) { outp->acquired &= ~user; if (!outp->acquired) { + if (outp->func->release && outp->ior) + outp->func->release(outp); outp->ior->asy.outp = NULL; outp->ior = NULL; } @@ -127,17 +129,26 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user) if (proto == UNKNOWN) return -ENOSYS; + /* Deal with panels requiring identity-mapped SOR assignment. */ + if (outp->identity) { + ior = nvkm_ior_find(outp->disp, SOR, ffs(outp->info.or) - 1); + if (WARN_ON(!ior)) + return -ENOSPC; + return nvkm_outp_acquire_ior(outp, user, ior); + } + /* First preference is to reuse the OR that is currently armed * on HW, if any, in order to prevent unnecessary switching. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->arm.outp == outp) + if (!ior->identity && !ior->asy.outp && ior->arm.outp == outp) return nvkm_outp_acquire_ior(outp, user, ior); } /* Failing that, a completely unused OR is the next best thing. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->type == type && !ior->arm.outp && + if (!ior->identity && + !ior->asy.outp && ior->type == type && !ior->arm.outp && (ior->func->route.set || ior->id == __ffs(outp->info.or))) return nvkm_outp_acquire_ior(outp, user, ior); } @@ -146,7 +157,7 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user) * but will be released during the next modeset. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->type == type && + if (!ior->identity && !ior->asy.outp && ior->type == type && (ior->func->route.set || ior->id == __ffs(outp->info.or))) return nvkm_outp_acquire_ior(outp, user, ior); } @@ -245,7 +256,6 @@ nvkm_outp_ctor(const struct nvkm_outp_func *func, struct nvkm_disp *disp, outp->index = index; outp->info = *dcbE; outp->i2c = nvkm_i2c_bus_find(i2c, dcbE->i2c_index); - outp->or = ffs(outp->info.or) - 1; OUTP_DBG(outp, "type %02x loc %d or %d link %d con %x " "edid %x bus %d head %x", diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h index ea84d7d5741a..6c8aa5cfed9d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h @@ -13,10 +13,10 @@ struct nvkm_outp { struct dcb_output info; struct nvkm_i2c_bus *i2c; - int or; struct list_head head; struct nvkm_conn *conn; + bool identity; /* Assembly state. */ #define NVKM_OUTP_PRIV 1 @@ -41,7 +41,8 @@ struct nvkm_outp_func { void (*init)(struct nvkm_outp *); void (*fini)(struct nvkm_outp *); int (*acquire)(struct nvkm_outp *); - void (*release)(struct nvkm_outp *, struct nvkm_ior *); + void (*release)(struct nvkm_outp *); + void (*disable)(struct nvkm_outp *, struct nvkm_ior *); }; #define OUTP_MSG(o,l,f,a...) do { \ diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c index b80618e35491..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); @@ -157,8 +156,11 @@ gm200_devinit_post(struct nvkm_devinit *base, bool post) return -ETIMEDOUT; } - /* load and execute some other ucode image (bios therm?) */ - return pmu_load(init, 0x01, post, NULL, NULL); + /* 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; } static const struct nvkm_devinit_func diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index de269eb482dd..7459def78d50 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -1423,7 +1423,7 @@ nvkm_vmm_get(struct nvkm_vmm *vmm, u8 page, u64 size, struct nvkm_vma **pvma) void nvkm_vmm_part(struct nvkm_vmm *vmm, struct nvkm_memory *inst) { - if (vmm->func->part && inst) { + if (inst && vmm->func->part) { mutex_lock(&vmm->mutex); vmm->func->part(vmm, inst); mutex_unlock(&vmm->mutex); diff --git a/drivers/gpu/drm/pl111/pl111_vexpress.c b/drivers/gpu/drm/pl111/pl111_vexpress.c index a534b225e31b..5fa0441bb6df 100644 --- a/drivers/gpu/drm/pl111/pl111_vexpress.c +++ b/drivers/gpu/drm/pl111/pl111_vexpress.c @@ -111,7 +111,8 @@ static int vexpress_muxfpga_probe(struct platform_device *pdev) } static const struct of_device_id vexpress_muxfpga_match[] = { - { .compatible = "arm,vexpress-muxfpga", } + { .compatible = "arm,vexpress-muxfpga", }, + {} }; static struct platform_driver vexpress_muxfpga_driver = { diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 1e41c3f5fd6d..9027ddde4262 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -402,7 +402,6 @@ static const struct of_device_id sun4i_drv_of_table[] = { { .compatible = "allwinner,sun8i-a33-display-engine" }, { .compatible = "allwinner,sun8i-a83t-display-engine" }, { .compatible = "allwinner,sun8i-h3-display-engine" }, - { .compatible = "allwinner,sun8i-r40-display-engine" }, { .compatible = "allwinner,sun8i-v3s-display-engine" }, { .compatible = "allwinner,sun9i-a80-display-engine" }, { .compatible = "allwinner,sun50i-a64-display-engine" }, diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c index 856124806353..471993097ced 100644 --- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c +++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c @@ -398,7 +398,6 @@ static struct regmap_config sun8i_hdmi_phy_regmap_config = { static const struct sun8i_hdmi_phy_variant sun50i_a64_hdmi_phy = { .has_phy_clk = true, - .has_second_pll = true, .phy_init = &sun8i_hdmi_phy_init_h3, .phy_disable = &sun8i_hdmi_phy_disable_h3, .phy_config = &sun8i_hdmi_phy_config_h3, diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index 8b3d02b146b7..091f6cf40353 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -545,22 +545,6 @@ static const struct sun8i_mixer_cfg sun8i_h3_mixer0_cfg = { .vi_num = 1, }; -static const struct sun8i_mixer_cfg sun8i_r40_mixer0_cfg = { - .ccsc = 0, - .mod_rate = 297000000, - .scaler_mask = 0xf, - .ui_num = 3, - .vi_num = 1, -}; - -static const struct sun8i_mixer_cfg sun8i_r40_mixer1_cfg = { - .ccsc = 1, - .mod_rate = 297000000, - .scaler_mask = 0x3, - .ui_num = 1, - .vi_num = 1, -}; - static const struct sun8i_mixer_cfg sun8i_v3s_mixer_cfg = { .vi_num = 2, .ui_num = 1, @@ -599,14 +583,6 @@ static const struct of_device_id sun8i_mixer_of_table[] = { .data = &sun8i_h3_mixer0_cfg, }, { - .compatible = "allwinner,sun8i-r40-de2-mixer-0", - .data = &sun8i_r40_mixer0_cfg, - }, - { - .compatible = "allwinner,sun8i-r40-de2-mixer-1", - .data = &sun8i_r40_mixer1_cfg, - }, - { .compatible = "allwinner,sun8i-v3s-de2-mixer", .data = &sun8i_v3s_mixer_cfg, }, diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c index 3040a79f298f..9831a9fe2cf4 100644 --- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c +++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c @@ -252,7 +252,6 @@ static int sun8i_tcon_top_remove(struct platform_device *pdev) /* sun4i_drv uses this list to check if a device node is a TCON TOP */ const struct of_device_id sun8i_tcon_top_of_table[] = { - { .compatible = "allwinner,sun8i-r40-tcon-top" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sun8i_tcon_top_of_table); diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index dbb62f6eb48a..dd9ffded223b 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -432,9 +432,11 @@ static void udl_fbdev_destroy(struct drm_device *dev, { drm_fb_helper_unregister_fbi(&ufbdev->helper); drm_fb_helper_fini(&ufbdev->helper); - drm_framebuffer_unregister_private(&ufbdev->ufb.base); - drm_framebuffer_cleanup(&ufbdev->ufb.base); - drm_gem_object_put_unlocked(&ufbdev->ufb.obj->base); + if (ufbdev->ufb.obj) { + drm_framebuffer_unregister_private(&ufbdev->ufb.base); + drm_framebuffer_cleanup(&ufbdev->ufb.base); + drm_gem_object_put_unlocked(&ufbdev->ufb.obj->base); + } } int udl_fbdev_init(struct drm_device *dev) diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index f39ee212412d..9dc3fcbd290b 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -296,6 +296,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_state->y_scaling[0] = vc4_get_scaling_mode(vc4_state->src_h[0], vc4_state->crtc_h); + vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && + vc4_state->y_scaling[0] == VC4_SCALING_NONE); + if (num_planes > 1) { vc4_state->is_yuv = true; @@ -311,24 +314,17 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_get_scaling_mode(vc4_state->src_h[1], vc4_state->crtc_h); - /* YUV conversion requires that scaling be enabled, - * even on a plane that's otherwise 1:1. Choose TPZ - * for simplicity. + /* YUV conversion requires that horizontal scaling be enabled, + * even on a plane that's otherwise 1:1. Looks like only PPF + * works in that case, so let's pick that one. */ - if (vc4_state->x_scaling[0] == VC4_SCALING_NONE) - vc4_state->x_scaling[0] = VC4_SCALING_TPZ; - if (vc4_state->y_scaling[0] == VC4_SCALING_NONE) - vc4_state->y_scaling[0] = VC4_SCALING_TPZ; + if (vc4_state->is_unity) + vc4_state->x_scaling[0] = VC4_SCALING_PPF; } else { vc4_state->x_scaling[1] = VC4_SCALING_NONE; vc4_state->y_scaling[1] = VC4_SCALING_NONE; } - vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && - vc4_state->y_scaling[0] == VC4_SCALING_NONE && - vc4_state->x_scaling[1] == VC4_SCALING_NONE && - vc4_state->y_scaling[1] == VC4_SCALING_NONE); - /* No configuring scaling on the cursor plane, since it gets non-vblank-synced updates, and scaling requires requires LBM changes which have to be vblank-synced. @@ -671,7 +667,10 @@ static int vc4_plane_mode_set(struct drm_plane *plane, vc4_dlist_write(vc4_state, SCALER_CSC2_ITR_R_601_5); } - if (!vc4_state->is_unity) { + if (vc4_state->x_scaling[0] != VC4_SCALING_NONE || + vc4_state->x_scaling[1] != VC4_SCALING_NONE || + vc4_state->y_scaling[0] != VC4_SCALING_NONE || + vc4_state->y_scaling[1] != VC4_SCALING_NONE) { /* LBM Base Address. */ if (vc4_state->y_scaling[0] != VC4_SCALING_NONE || vc4_state->y_scaling[1] != VC4_SCALING_NONE) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 1f134570b759..f0ab6b2313bb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3729,7 +3729,7 @@ int vmw_validate_single_buffer(struct vmw_private *dev_priv, { struct vmw_buffer_object *vbo = container_of(bo, struct vmw_buffer_object, base); - struct ttm_operation_ctx ctx = { interruptible, true }; + struct ttm_operation_ctx ctx = { interruptible, false }; int ret; if (vbo->pin_count > 0) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 0c25bb8faf80..292e48feba83 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1510,21 +1510,19 @@ static int vmw_kms_check_display_memory(struct drm_device *dev, struct drm_rect *rects) { struct vmw_private *dev_priv = vmw_priv(dev); - struct drm_mode_config *mode_config = &dev->mode_config; struct drm_rect bounding_box = {0}; u64 total_pixels = 0, pixel_mem, bb_mem; int i; for (i = 0; i < num_rects; i++) { /* - * Currently this check is limiting the topology within max - * texture/screentarget size. This should change in future when - * user-space support multiple fb with topology. + * For STDU only individual screen (screen target) is limited by + * SCREENTARGET_MAX_WIDTH/HEIGHT registers. */ - if (rects[i].x1 < 0 || rects[i].y1 < 0 || - rects[i].x2 > mode_config->max_width || - rects[i].y2 > mode_config->max_height) { - DRM_ERROR("Invalid GUI layout.\n"); + if (dev_priv->active_display_unit == vmw_du_screen_target && + (drm_rect_width(&rects[i]) > dev_priv->stdu_max_width || + drm_rect_height(&rects[i]) > dev_priv->stdu_max_height)) { + DRM_ERROR("Screen size not supported.\n"); return -EINVAL; } @@ -1613,7 +1611,7 @@ static int vmw_kms_check_topology(struct drm_device *dev, struct drm_connector_state *conn_state; struct vmw_connector_state *vmw_conn_state; - if (!new_crtc_state->enable && old_crtc_state->enable) { + if (!new_crtc_state->enable) { rects[i].x1 = 0; rects[i].y1 = 0; rects[i].x2 = 0; @@ -2214,12 +2212,16 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector, if (dev_priv->assume_16bpp) assumed_bpp = 2; + max_width = min(max_width, dev_priv->texture_max_width); + max_height = min(max_height, dev_priv->texture_max_height); + + /* + * For STDU extra limit for a mode on SVGA_REG_SCREENTARGET_MAX_WIDTH/ + * HEIGHT registers. + */ if (dev_priv->active_display_unit == vmw_du_screen_target) { max_width = min(max_width, dev_priv->stdu_max_width); - max_width = min(max_width, dev_priv->texture_max_width); - max_height = min(max_height, dev_priv->stdu_max_height); - max_height = min(max_height, dev_priv->texture_max_height); } /* Add preferred mode */ @@ -2374,6 +2376,7 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct vmw_private *dev_priv = vmw_priv(dev); + struct drm_mode_config *mode_config = &dev->mode_config; struct drm_vmw_update_layout_arg *arg = (struct drm_vmw_update_layout_arg *)data; void __user *user_rects; @@ -2419,6 +2422,21 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, drm_rects[i].y1 = curr_rect.y; drm_rects[i].x2 = curr_rect.x + curr_rect.w; drm_rects[i].y2 = curr_rect.y + curr_rect.h; + + /* + * Currently this check is limiting the topology within + * mode_config->max (which actually is max texture size + * supported by virtual device). This limit is here to address + * window managers that create a big framebuffer for whole + * topology. + */ + if (drm_rects[i].x1 < 0 || drm_rects[i].y1 < 0 || + drm_rects[i].x2 > mode_config->max_width || + drm_rects[i].y2 > mode_config->max_height) { + DRM_ERROR("Invalid GUI layout.\n"); + ret = -EINVAL; + goto out_free; + } } ret = vmw_kms_check_display_memory(dev, arg->num_outputs, drm_rects); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 93f6b96ca7bb..f30e839f7bfd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -1600,31 +1600,6 @@ int vmw_kms_stdu_init_display(struct vmw_private *dev_priv) dev_priv->active_display_unit = vmw_du_screen_target; - if (dev_priv->capabilities & SVGA_CAP_3D) { - /* - * For 3D VMs, display (scanout) buffer size is the smaller of - * max texture and max STDU - */ - uint32_t max_width, max_height; - - max_width = min(dev_priv->texture_max_width, - dev_priv->stdu_max_width); - max_height = min(dev_priv->texture_max_height, - dev_priv->stdu_max_height); - - dev->mode_config.max_width = max_width; - dev->mode_config.max_height = max_height; - } else { - /* - * Given various display aspect ratios, there's no way to - * estimate these using prim_bb_mem. So just set these to - * something arbitrarily large and we will reject any layout - * that doesn't fit prim_bb_mem later - */ - dev->mode_config.max_width = 8192; - dev->mode_config.max_height = 8192; - } - vmw_kms_create_implicit_placement_property(dev_priv, false); for (i = 0; i < VMWGFX_NUM_DISPLAY_UNITS; ++i) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index e125233e074b..80a01cd4c051 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -1404,22 +1404,17 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, *srf_out = NULL; if (for_scanout) { - uint32_t max_width, max_height; - if (!svga3dsurface_is_screen_target_format(format)) { DRM_ERROR("Invalid Screen Target surface format."); return -EINVAL; } - max_width = min(dev_priv->texture_max_width, - dev_priv->stdu_max_width); - max_height = min(dev_priv->texture_max_height, - dev_priv->stdu_max_height); - - if (size.width > max_width || size.height > max_height) { + if (size.width > dev_priv->texture_max_width || + size.height > dev_priv->texture_max_height) { DRM_ERROR("%ux%u\n, exceeds max surface size %ux%u", size.width, size.height, - max_width, max_height); + dev_priv->texture_max_width, + dev_priv->texture_max_height); return -EINVAL; } } else { @@ -1495,8 +1490,17 @@ int vmw_surface_gb_priv_define(struct drm_device *dev, if (srf->flags & SVGA3D_SURFACE_BIND_STREAM_OUTPUT) srf->res.backup_size += sizeof(SVGA3dDXSOState); + /* + * Don't set SVGA3D_SURFACE_SCREENTARGET flag for a scanout surface with + * size greater than STDU max width/height. This is really a workaround + * to support creation of big framebuffer requested by some user-space + * for whole topology. That big framebuffer won't really be used for + * binding with screen target as during prepare_fb a separate surface is + * created so it's safe to ignore SVGA3D_SURFACE_SCREENTARGET flag. + */ if (dev_priv->active_display_unit == vmw_du_screen_target && - for_scanout) + for_scanout && size.width <= dev_priv->stdu_max_width && + size.height <= dev_priv->stdu_max_height) srf->flags |= SVGA3D_SURFACE_SCREENTARGET; /* diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index a96bf46bc483..cf2a18571d48 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -215,6 +215,8 @@ static void vga_switcheroo_enable(void) return; client->id = ret | ID_BIT_AUDIO; + if (client->ops->gpu_bound) + client->ops->gpu_bound(client->pdev, ret); } vga_switcheroo_debugfs_init(&vgasr_priv); diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 25b7bd56ae11..1cb41992aaa1 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -335,7 +335,8 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { - if (usage->hid == (HID_UP_CUSTOM | 0x0003)) { + if (usage->hid == (HID_UP_CUSTOM | 0x0003) || + usage->hid == (HID_UP_MSVENDOR | 0x0003)) { /* The fn key on Apple USB keyboards */ set_bit(EV_REP, hi->input->evbit); hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN); @@ -472,6 +473,12 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI), .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI), + .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ISO), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3da354af7a0a..44564f61e9cc 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1000,7 +1000,7 @@ int hid_open_report(struct hid_device *device) parser = vzalloc(sizeof(struct hid_parser)); if (!parser) { ret = -ENOMEM; - goto err; + goto alloc_err; } parser->device = device; @@ -1039,6 +1039,7 @@ int hid_open_report(struct hid_device *device) hid_err(device, "unbalanced delimiter at end of report description\n"); goto err; } + kfree(parser->collection_stack); vfree(parser); device->status |= HID_STAT_PARSED; return 0; @@ -1047,6 +1048,8 @@ int hid_open_report(struct hid_device *device) hid_err(device, "item fetching failed at offset %d\n", (int)(end - start)); err: + kfree(parser->collection_stack); +alloc_err: vfree(parser); hid_close_report(device); return ret; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 79bdf0c7e351..5146ee029db4 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -88,6 +88,7 @@ #define USB_DEVICE_ID_ANTON_TOUCH_PAD 0x3101 #define USB_VENDOR_ID_APPLE 0x05ac +#define BT_VENDOR_ID_APPLE 0x004c #define USB_DEVICE_ID_APPLE_MIGHTYMOUSE 0x0304 #define USB_DEVICE_ID_APPLE_MAGICMOUSE 0x030d #define USB_DEVICE_ID_APPLE_MAGICTRACKPAD 0x030e @@ -157,6 +158,7 @@ #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO 0x0256 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS 0x0257 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI 0x0267 +#define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI 0x026c #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292 @@ -528,9 +530,6 @@ #define I2C_VENDOR_ID_HANTICK 0x0911 #define I2C_PRODUCT_ID_HANTICK_5288 0x5288 -#define I2C_VENDOR_ID_RAYD 0x2386 -#define I2C_PRODUCT_ID_RAYD_3118 0x3118 - #define USB_VENDOR_ID_HANWANG 0x0b57 #define USB_DEVICE_ID_HANWANG_TABLET_FIRST 0x5000 #define USB_DEVICE_ID_HANWANG_TABLET_LAST 0x8fff @@ -950,6 +949,7 @@ #define USB_DEVICE_ID_SAITEK_RUMBLEPAD 0xff17 #define USB_DEVICE_ID_SAITEK_PS1000 0x0621 #define USB_DEVICE_ID_SAITEK_RAT7_OLD 0x0ccb +#define USB_DEVICE_ID_SAITEK_RAT7_CONTAGION 0x0ccd #define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7 #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 4e94ea3e280a..a481eaf39e88 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1582,6 +1582,7 @@ static struct hid_input *hidinput_allocate(struct hid_device *hid, input_dev->dev.parent = &hid->dev; hidinput->input = input_dev; + hidinput->application = application; list_add_tail(&hidinput->list, &hid->inputs); INIT_LIST_HEAD(&hidinput->reports); @@ -1677,8 +1678,7 @@ static struct hid_input *hidinput_match_application(struct hid_report *report) struct hid_input *hidinput; list_for_each_entry(hidinput, &hid->inputs, list) { - if (hidinput->report && - hidinput->report->application == report->application) + if (hidinput->application == report->application) return hidinput; } @@ -1815,6 +1815,7 @@ void hidinput_disconnect(struct hid_device *hid) input_unregister_device(hidinput->input); else input_free_device(hidinput->input); + kfree(hidinput->name); kfree(hidinput); } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 40fbb7c52723..da954f3f4da7 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1375,7 +1375,8 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, struct hid_usage *usage, enum latency_mode latency, bool surface_switch, - bool button_switch) + bool button_switch, + bool *inputmode_found) { struct mt_device *td = hid_get_drvdata(hdev); struct mt_class *cls = &td->mtclass; @@ -1387,6 +1388,14 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, switch (usage->hid) { case HID_DG_INPUTMODE: + /* + * Some elan panels wrongly declare 2 input mode features, + * and silently ignore when we set the value in the second + * field. Skip the second feature and hope for the best. + */ + if (*inputmode_found) + return false; + if (cls->quirks & MT_QUIRK_FORCE_GET_FEATURE) { report_len = hid_report_len(report); buf = hid_alloc_report_buf(report, GFP_KERNEL); @@ -1402,6 +1411,7 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, } field->value[index] = td->inputmode_value; + *inputmode_found = true; return true; case HID_DG_CONTACTMAX: @@ -1439,6 +1449,7 @@ static void mt_set_modes(struct hid_device *hdev, enum latency_mode latency, struct hid_usage *usage; int i, j; bool update_report; + bool inputmode_found = false; rep_enum = &hdev->report_enum[HID_FEATURE_REPORT]; list_for_each_entry(rep, &rep_enum->report_list, list) { @@ -1457,7 +1468,8 @@ static void mt_set_modes(struct hid_device *hdev, enum latency_mode latency, usage, latency, surface_switch, - button_switch)) + button_switch, + &inputmode_found)) update_report = true; } } @@ -1685,6 +1697,9 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) */ hdev->quirks |= HID_QUIRK_INPUT_PER_APP; + if (id->group != HID_GROUP_MULTITOUCH_WIN_8) + hdev->quirks |= HID_QUIRK_MULTI_INPUT; + timer_setup(&td->release_timer, mt_expired_timeout, 0); ret = hid_parse(hdev); diff --git a/drivers/hid/hid-saitek.c b/drivers/hid/hid-saitek.c index 39e642686ff0..683861f324e3 100644 --- a/drivers/hid/hid-saitek.c +++ b/drivers/hid/hid-saitek.c @@ -183,6 +183,8 @@ static const struct hid_device_id saitek_devices[] = { .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7), .driver_data = SAITEK_RELEASE_MODE_RAT7 }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7_CONTAGION), + .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT9), .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_RAT9), diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 50af72baa5ca..2b63487057c2 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -579,6 +579,28 @@ void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev) } EXPORT_SYMBOL_GPL(sensor_hub_device_close); +static __u8 *sensor_hub_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + /* + * Checks if the report descriptor of Thinkpad Helix 2 has a logical + * minimum for magnetic flux axis greater than the maximum. + */ + if (hdev->product == USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA && + *rsize == 2558 && rdesc[913] == 0x17 && rdesc[914] == 0x40 && + rdesc[915] == 0x81 && rdesc[916] == 0x08 && + rdesc[917] == 0x00 && rdesc[918] == 0x27 && + rdesc[921] == 0x07 && rdesc[922] == 0x00) { + /* Sets negative logical minimum for mag x, y and z */ + rdesc[914] = rdesc[935] = rdesc[956] = 0xc0; + rdesc[915] = rdesc[936] = rdesc[957] = 0x7e; + rdesc[916] = rdesc[937] = rdesc[958] = 0xf7; + rdesc[917] = rdesc[938] = rdesc[959] = 0xff; + } + + return rdesc; +} + static int sensor_hub_probe(struct hid_device *hdev, const struct hid_device_id *id) { @@ -743,6 +765,7 @@ static struct hid_driver sensor_hub_driver = { .probe = sensor_hub_probe, .remove = sensor_hub_remove, .raw_event = sensor_hub_raw_event, + .report_fixup = sensor_hub_report_fixup, #ifdef CONFIG_PM .suspend = sensor_hub_suspend, .resume = sensor_hub_resume, diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 2ce194a84868..f3076659361a 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -170,8 +170,6 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV }, { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, - { I2C_VENDOR_ID_RAYD, I2C_PRODUCT_ID_RAYD_3118, - I2C_HID_QUIRK_RESEND_REPORT_DESCR }, { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH, I2C_HID_QUIRK_RESEND_REPORT_DESCR }, { 0, 0 } @@ -1235,11 +1233,16 @@ static int i2c_hid_resume(struct device *dev) pm_runtime_enable(dev); enable_irq(client->irq); - ret = i2c_hid_hwreset(client); + + /* Instead of resetting device, simply powers the device on. This + * solves "incomplete reports" on Raydium devices 2386:3118 and + * 2386:4B33 + */ + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); if (ret) return ret; - /* RAYDIUM device (2386:3118) need to re-send report descr cmd + /* Some devices need to re-send report descr cmd * after resume, after this it will be back normal. * otherwise it issues too many incomplete reports. */ diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index 97869b7410eb..da133716bed0 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -29,6 +29,7 @@ #define CNL_Ax_DEVICE_ID 0x9DFC #define GLK_Ax_DEVICE_ID 0x31A2 #define CNL_H_DEVICE_ID 0xA37C +#define SPT_H_DEVICE_ID 0xA135 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 050f9872f5c0..a1125a5c7965 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -38,6 +38,7 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_Ax_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, GLK_Ax_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_H_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)}, {0, } }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); 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/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 944f5b63aecd..78603b78cf41 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -207,8 +207,6 @@ superio_exit(int ioreg) #define NUM_FAN 7 -#define TEMP_SOURCE_VIRTUAL 0x1f - /* Common and NCT6775 specific data */ /* Voltage min/max registers for nr=7..14 are in bank 5 */ @@ -299,8 +297,9 @@ static const u16 NCT6775_REG_PWM_READ[] = { static const u16 NCT6775_REG_FAN[] = { 0x630, 0x632, 0x634, 0x636, 0x638 }; static const u16 NCT6775_REG_FAN_MIN[] = { 0x3b, 0x3c, 0x3d }; -static const u16 NCT6775_REG_FAN_PULSES[] = { 0x641, 0x642, 0x643, 0x644, 0 }; -static const u16 NCT6775_FAN_PULSE_SHIFT[] = { 0, 0, 0, 0, 0, 0 }; +static const u16 NCT6775_REG_FAN_PULSES[NUM_FAN] = { + 0x641, 0x642, 0x643, 0x644 }; +static const u16 NCT6775_FAN_PULSE_SHIFT[NUM_FAN] = { }; static const u16 NCT6775_REG_TEMP[] = { 0x27, 0x150, 0x250, 0x62b, 0x62c, 0x62d }; @@ -373,6 +372,7 @@ static const char *const nct6775_temp_label[] = { }; #define NCT6775_TEMP_MASK 0x001ffffe +#define NCT6775_VIRT_TEMP_MASK 0x00000000 static const u16 NCT6775_REG_TEMP_ALTERNATE[32] = { [13] = 0x661, @@ -425,8 +425,8 @@ static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0 }; static const u16 NCT6776_REG_FAN_MIN[] = { 0x63a, 0x63c, 0x63e, 0x640, 0x642, 0x64a, 0x64c }; -static const u16 NCT6776_REG_FAN_PULSES[] = { - 0x644, 0x645, 0x646, 0x647, 0x648, 0x649, 0 }; +static const u16 NCT6776_REG_FAN_PULSES[NUM_FAN] = { + 0x644, 0x645, 0x646, 0x647, 0x648, 0x649 }; static const u16 NCT6776_REG_WEIGHT_DUTY_BASE[] = { 0x13e, 0x23e, 0x33e, 0x83e, 0x93e, 0xa3e }; @@ -461,6 +461,7 @@ static const char *const nct6776_temp_label[] = { }; #define NCT6776_TEMP_MASK 0x007ffffe +#define NCT6776_VIRT_TEMP_MASK 0x00000000 static const u16 NCT6776_REG_TEMP_ALTERNATE[32] = { [14] = 0x401, @@ -501,9 +502,9 @@ static const s8 NCT6779_BEEP_BITS[] = { 30, 31 }; /* intrusion0, intrusion1 */ static const u16 NCT6779_REG_FAN[] = { - 0x4b0, 0x4b2, 0x4b4, 0x4b6, 0x4b8, 0x4ba, 0x660 }; -static const u16 NCT6779_REG_FAN_PULSES[] = { - 0x644, 0x645, 0x646, 0x647, 0x648, 0x649, 0 }; + 0x4c0, 0x4c2, 0x4c4, 0x4c6, 0x4c8, 0x4ca, 0x4ce }; +static const u16 NCT6779_REG_FAN_PULSES[NUM_FAN] = { + 0x644, 0x645, 0x646, 0x647, 0x648, 0x649 }; static const u16 NCT6779_REG_CRITICAL_PWM_ENABLE[] = { 0x136, 0x236, 0x336, 0x836, 0x936, 0xa36, 0xb36 }; @@ -559,7 +560,9 @@ static const char *const nct6779_temp_label[] = { }; #define NCT6779_TEMP_MASK 0x07ffff7e +#define NCT6779_VIRT_TEMP_MASK 0x00000000 #define NCT6791_TEMP_MASK 0x87ffff7e +#define NCT6791_VIRT_TEMP_MASK 0x80000000 static const u16 NCT6779_REG_TEMP_ALTERNATE[32] = { 0x490, 0x491, 0x492, 0x493, 0x494, 0x495, 0, 0, @@ -638,6 +641,7 @@ static const char *const nct6792_temp_label[] = { }; #define NCT6792_TEMP_MASK 0x9fffff7e +#define NCT6792_VIRT_TEMP_MASK 0x80000000 static const char *const nct6793_temp_label[] = { "", @@ -675,6 +679,7 @@ static const char *const nct6793_temp_label[] = { }; #define NCT6793_TEMP_MASK 0xbfff037e +#define NCT6793_VIRT_TEMP_MASK 0x80000000 static const char *const nct6795_temp_label[] = { "", @@ -712,6 +717,7 @@ static const char *const nct6795_temp_label[] = { }; #define NCT6795_TEMP_MASK 0xbfffff7e +#define NCT6795_VIRT_TEMP_MASK 0x80000000 static const char *const nct6796_temp_label[] = { "", @@ -724,8 +730,8 @@ static const char *const nct6796_temp_label[] = { "AUXTIN4", "SMBUSMASTER 0", "SMBUSMASTER 1", - "", - "", + "Virtual_TEMP", + "Virtual_TEMP", "", "", "", @@ -748,7 +754,8 @@ static const char *const nct6796_temp_label[] = { "Virtual_TEMP" }; -#define NCT6796_TEMP_MASK 0xbfff03fe +#define NCT6796_TEMP_MASK 0xbfff0ffe +#define NCT6796_VIRT_TEMP_MASK 0x80000c00 /* NCT6102D/NCT6106D specific data */ @@ -779,8 +786,8 @@ static const u16 NCT6106_REG_TEMP_CONFIG[] = { static const u16 NCT6106_REG_FAN[] = { 0x20, 0x22, 0x24 }; static const u16 NCT6106_REG_FAN_MIN[] = { 0xe0, 0xe2, 0xe4 }; -static const u16 NCT6106_REG_FAN_PULSES[] = { 0xf6, 0xf6, 0xf6, 0, 0 }; -static const u16 NCT6106_FAN_PULSE_SHIFT[] = { 0, 2, 4, 0, 0 }; +static const u16 NCT6106_REG_FAN_PULSES[] = { 0xf6, 0xf6, 0xf6 }; +static const u16 NCT6106_FAN_PULSE_SHIFT[] = { 0, 2, 4 }; static const u8 NCT6106_REG_PWM_MODE[] = { 0xf3, 0xf3, 0xf3 }; static const u8 NCT6106_PWM_MODE_MASK[] = { 0x01, 0x02, 0x04 }; @@ -917,6 +924,11 @@ static unsigned int fan_from_reg16(u16 reg, unsigned int divreg) return 1350000U / (reg << divreg); } +static unsigned int fan_from_reg_rpm(u16 reg, unsigned int divreg) +{ + return reg; +} + static u16 fan_to_reg(u32 fan, unsigned int divreg) { if (!fan) @@ -969,6 +981,7 @@ struct nct6775_data { u16 reg_temp_config[NUM_TEMP]; const char * const *temp_label; u32 temp_mask; + u32 virt_temp_mask; u16 REG_CONFIG; u16 REG_VBAT; @@ -1276,11 +1289,11 @@ static bool is_word_sized(struct nct6775_data *data, u16 reg) case nct6795: case nct6796: return reg == 0x150 || reg == 0x153 || reg == 0x155 || - ((reg & 0xfff0) == 0x4b0 && (reg & 0x000f) < 0x0b) || + (reg & 0xfff0) == 0x4c0 || reg == 0x402 || reg == 0x63a || reg == 0x63c || reg == 0x63e || reg == 0x640 || reg == 0x642 || reg == 0x64a || - reg == 0x64c || reg == 0x660 || + reg == 0x64c || reg == 0x73 || reg == 0x75 || reg == 0x77 || reg == 0x79 || reg == 0x7b || reg == 0x7d; } @@ -1558,7 +1571,7 @@ static void nct6775_update_pwm(struct device *dev) reg = nct6775_read_value(data, data->REG_WEIGHT_TEMP_SEL[i]); data->pwm_weight_temp_sel[i] = reg & 0x1f; /* If weight is disabled, report weight source as 0 */ - if (j == 1 && !(reg & 0x80)) + if (!(reg & 0x80)) data->pwm_weight_temp_sel[i] = 0; /* Weight temp data */ @@ -1682,9 +1695,13 @@ static struct nct6775_data *nct6775_update_device(struct device *dev) if (data->has_fan_min & BIT(i)) data->fan_min[i] = nct6775_read_value(data, data->REG_FAN_MIN[i]); - data->fan_pulses[i] = - (nct6775_read_value(data, data->REG_FAN_PULSES[i]) - >> data->FAN_PULSE_SHIFT[i]) & 0x03; + + if (data->REG_FAN_PULSES[i]) { + data->fan_pulses[i] = + (nct6775_read_value(data, + data->REG_FAN_PULSES[i]) + >> data->FAN_PULSE_SHIFT[i]) & 0x03; + } nct6775_select_fan_div(dev, data, i, reg); } @@ -3639,6 +3656,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6776_temp_label; data->temp_mask = NCT6776_TEMP_MASK; + data->virt_temp_mask = NCT6776_VIRT_TEMP_MASK; data->REG_VBAT = NCT6106_REG_VBAT; data->REG_DIODE = NCT6106_REG_DIODE; @@ -3717,6 +3735,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6775_temp_label; data->temp_mask = NCT6775_TEMP_MASK; + data->virt_temp_mask = NCT6775_VIRT_TEMP_MASK; data->REG_CONFIG = NCT6775_REG_CONFIG; data->REG_VBAT = NCT6775_REG_VBAT; @@ -3789,6 +3808,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6776_temp_label; data->temp_mask = NCT6776_TEMP_MASK; + data->virt_temp_mask = NCT6776_VIRT_TEMP_MASK; data->REG_CONFIG = NCT6775_REG_CONFIG; data->REG_VBAT = NCT6775_REG_VBAT; @@ -3853,7 +3873,7 @@ static int nct6775_probe(struct platform_device *pdev) data->ALARM_BITS = NCT6779_ALARM_BITS; data->BEEP_BITS = NCT6779_BEEP_BITS; - data->fan_from_reg = fan_from_reg13; + data->fan_from_reg = fan_from_reg_rpm; data->fan_from_reg_min = fan_from_reg13; data->target_temp_mask = 0xff; data->tolerance_mask = 0x07; @@ -3861,6 +3881,7 @@ static int nct6775_probe(struct platform_device *pdev) data->temp_label = nct6779_temp_label; data->temp_mask = NCT6779_TEMP_MASK; + data->virt_temp_mask = NCT6779_VIRT_TEMP_MASK; data->REG_CONFIG = NCT6775_REG_CONFIG; data->REG_VBAT = NCT6775_REG_VBAT; @@ -3933,7 +3954,7 @@ static int nct6775_probe(struct platform_device *pdev) data->ALARM_BITS = NCT6791_ALARM_BITS; data->BEEP_BITS = NCT6779_BEEP_BITS; - data->fan_from_reg = fan_from_reg13; + data->fan_from_reg = fan_from_reg_rpm; data->fan_from_reg_min = fan_from_reg13; data->target_temp_mask = 0xff; data->tolerance_mask = 0x07; @@ -3944,22 +3965,27 @@ static int nct6775_probe(struct platform_device *pdev) case nct6791: data->temp_label = nct6779_temp_label; data->temp_mask = NCT6791_TEMP_MASK; + data->virt_temp_mask = NCT6791_VIRT_TEMP_MASK; break; case nct6792: data->temp_label = nct6792_temp_label; data->temp_mask = NCT6792_TEMP_MASK; + data->virt_temp_mask = NCT6792_VIRT_TEMP_MASK; break; case nct6793: data->temp_label = nct6793_temp_label; data->temp_mask = NCT6793_TEMP_MASK; + data->virt_temp_mask = NCT6793_VIRT_TEMP_MASK; break; case nct6795: data->temp_label = nct6795_temp_label; data->temp_mask = NCT6795_TEMP_MASK; + data->virt_temp_mask = NCT6795_VIRT_TEMP_MASK; break; case nct6796: data->temp_label = nct6796_temp_label; data->temp_mask = NCT6796_TEMP_MASK; + data->virt_temp_mask = NCT6796_VIRT_TEMP_MASK; break; } @@ -4143,7 +4169,7 @@ static int nct6775_probe(struct platform_device *pdev) * for each fan reflects a different temperature, and there * are no duplicates. */ - if (src != TEMP_SOURCE_VIRTUAL) { + if (!(data->virt_temp_mask & BIT(src))) { if (mask & BIT(src)) continue; mask |= BIT(src); diff --git a/drivers/hwmon/raspberrypi-hwmon.c b/drivers/hwmon/raspberrypi-hwmon.c index fb4e4a6bb1f6..be5ba4690895 100644 --- a/drivers/hwmon/raspberrypi-hwmon.c +++ b/drivers/hwmon/raspberrypi-hwmon.c @@ -164,3 +164,4 @@ module_platform_driver(rpi_hwmon_driver); MODULE_AUTHOR("Stefan Wahren <stefan.wahren@i2se.com>"); MODULE_DESCRIPTION("Raspberry Pi voltage sensor driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:raspberrypi-hwmon"); diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 04b60a349d7e..c91e145ef5a5 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -140,6 +140,7 @@ #define SBREG_BAR 0x10 #define SBREG_SMBCTRL 0xc6000c +#define SBREG_SMBCTRL_DNV 0xcf000c /* Host status bits for SMBPCISTS */ #define SMBPCISTS_INTS BIT(3) @@ -1399,7 +1400,11 @@ static void i801_add_tco(struct i801_priv *priv) spin_unlock(&p2sb_spinlock); res = &tco_res[ICH_RES_MEM_OFF]; - res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL; + if (pci_dev->device == PCI_DEVICE_ID_INTEL_DNV_SMBUS) + res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL_DNV; + else + res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL; + res->end = res->start + 3; res->flags = IORESOURCE_MEM; diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 6d975f5221ca..06c4c767af32 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -538,7 +538,6 @@ static const struct i2c_algorithm lpi2c_imx_algo = { static const struct of_device_id lpi2c_imx_of_match[] = { { .compatible = "fsl,imx7ulp-lpi2c" }, - { .compatible = "fsl,imx8dv-lpi2c" }, { }, }; MODULE_DEVICE_TABLE(of, lpi2c_imx_of_match); diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index 9918bdd81619..a403e8579b65 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -401,11 +401,8 @@ static int uniphier_fi2c_master_xfer(struct i2c_adapter *adap, return ret; for (msg = msgs; msg < emsg; msg++) { - /* If next message is read, skip the stop condition */ - bool stop = !(msg + 1 < emsg && msg[1].flags & I2C_M_RD); - /* but, force it if I2C_M_STOP is set */ - if (msg->flags & I2C_M_STOP) - stop = true; + /* Emit STOP if it is the last message or I2C_M_STOP is set. */ + bool stop = (msg + 1 == emsg) || (msg->flags & I2C_M_STOP); ret = uniphier_fi2c_master_xfer_one(adap, msg, stop); if (ret) diff --git a/drivers/i2c/busses/i2c-uniphier.c b/drivers/i2c/busses/i2c-uniphier.c index bb181b088291..454f914ae66d 100644 --- a/drivers/i2c/busses/i2c-uniphier.c +++ b/drivers/i2c/busses/i2c-uniphier.c @@ -248,11 +248,8 @@ static int uniphier_i2c_master_xfer(struct i2c_adapter *adap, return ret; for (msg = msgs; msg < emsg; msg++) { - /* If next message is read, skip the stop condition */ - bool stop = !(msg + 1 < emsg && msg[1].flags & I2C_M_RD); - /* but, force it if I2C_M_STOP is set */ - if (msg->flags & I2C_M_STOP) - stop = true; + /* Emit STOP if it is the last message or I2C_M_STOP is set. */ + bool stop = (msg + 1 == emsg) || (msg->flags & I2C_M_STOP); ret = uniphier_i2c_master_xfer_one(adap, msg, stop); if (ret) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 9a71e50d21f1..0c51c0ffdda9 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -532,6 +532,7 @@ static void xiic_start_recv(struct xiic_i2c *i2c) { u8 rx_watermark; struct i2c_msg *msg = i2c->rx_msg = i2c->tx_msg; + unsigned long flags; /* Clear and enable Rx full interrupt. */ xiic_irq_clr_en(i2c, XIIC_INTR_RX_FULL_MASK | XIIC_INTR_TX_ERROR_MASK); @@ -547,6 +548,7 @@ static void xiic_start_recv(struct xiic_i2c *i2c) rx_watermark = IIC_RX_FIFO_DEPTH; xiic_setreg8(i2c, XIIC_RFD_REG_OFFSET, rx_watermark - 1); + local_irq_save(flags); if (!(msg->flags & I2C_M_NOSTART)) /* write the address */ xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, @@ -556,6 +558,8 @@ static void xiic_start_recv(struct xiic_i2c *i2c) xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, msg->len | ((i2c->nmsgs == 1) ? XIIC_TX_DYN_STOP_MASK : 0)); + local_irq_restore(flags); + if (i2c->nmsgs == 1) /* very last, enable bus not busy as well */ xiic_irq_clr_en(i2c, XIIC_INTR_BNB_MASK); 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/core/cma.c b/drivers/infiniband/core/cma.c index f72677291b69..a36c94930c31 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -724,6 +724,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); + mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { if (!rdma_cap_af_ib(cur_dev->device, p)) @@ -750,18 +751,19 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; + goto found; } } } } - - if (!cma_dev) - return -ENODEV; + mutex_unlock(&lock); + return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); - addr = (struct sockaddr_ib *) cma_src_addr(id_priv); - memcpy(&addr->sib_addr, &sgid, sizeof sgid); + mutex_unlock(&lock); + addr = (struct sockaddr_ib *)cma_src_addr(id_priv); + memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 6eb64c6f0802..c4118bcd5103 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -882,6 +882,8 @@ static int __uverbs_cleanup_ufile(struct ib_uverbs_file *ufile, WARN_ON(uverbs_try_lock_object(obj, UVERBS_LOOKUP_WRITE)); if (!uverbs_destroy_uobject(obj, reason)) ret = 0; + else + atomic_set(&obj->usecnt, 0); } return ret; } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ec8fb289621f..5f437d1570fb 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -124,6 +124,8 @@ static DEFINE_MUTEX(mut); static DEFINE_IDR(ctx_idr); static DEFINE_IDR(multicast_idr); +static const struct file_operations ucma_fops; + static inline struct ucma_context *_ucma_find_context(int id, struct ucma_file *file) { @@ -1581,6 +1583,10 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file, f = fdget(cmd.fd); if (!f.file) return -ENOENT; + if (f.file->f_op != &ucma_fops) { + ret = -EINVAL; + goto file_put; + } /* Validate current fd and prevent destruction of id. */ ctx = ucma_get_ctx(f.file->private_data, cmd.id); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 823beca448e1..6d974e2363df 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -1050,7 +1050,7 @@ static void ib_uverbs_add_one(struct ib_device *device) uverbs_dev->num_comp_vectors = device->num_comp_vectors; if (ib_uverbs_create_uapi(device, uverbs_dev)) - goto err; + goto err_uapi; cdev_init(&uverbs_dev->cdev, NULL); uverbs_dev->cdev.owner = THIS_MODULE; @@ -1077,11 +1077,10 @@ static void ib_uverbs_add_one(struct ib_device *device) err_class: device_destroy(uverbs_class, uverbs_dev->cdev.dev); - err_cdev: cdev_del(&uverbs_dev->cdev); +err_uapi: clear_bit(devnum, dev_map); - err: if (atomic_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index bbfb86eb2d24..bc2b9e038439 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -833,6 +833,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) "Failed to destroy Shadow QP"); return rc; } + bnxt_qplib_free_qp_res(&rdev->qplib_res, + &rdev->qp1_sqp->qplib_qp); mutex_lock(&rdev->qp_lock); list_del(&rdev->qp1_sqp->list); atomic_dec(&rdev->qp_count); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e426b990c1dd..6ad0d46ab879 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -196,7 +196,7 @@ static int bnxt_qplib_alloc_qp_hdr_buf(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_q *rq = &qp->rq; - struct bnxt_qplib_q *sq = &qp->rq; + struct bnxt_qplib_q *sq = &qp->sq; int rc = 0; if (qp->sq_hdr_buf_size && sq->hwq.max_elements) { diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index b3203afa3b1d..347fe18b1a41 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1685,6 +1685,12 @@ static void flush_qp(struct c4iw_qp *qhp) schp = to_c4iw_cq(qhp->ibqp.send_cq); if (qhp->ibqp.uobject) { + + /* for user qps, qhp->wq.flushed is protected by qhp->mutex */ + if (qhp->wq.flushed) + return; + + qhp->wq.flushed = 1; t4_set_wq_in_error(&qhp->wq, 0); t4_set_cq_in_error(&rchp->cq); spin_lock_irqsave(&rchp->comp_handler_lock, flag); 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/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index ca0f1ee26091..0bbeaaae47e0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -517,9 +517,11 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->page_size_cap = dev->dev->caps.page_size_cap; props->max_qp = dev->dev->quotas.qp; props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE; - props->max_send_sge = dev->dev->caps.max_sq_sg; - props->max_recv_sge = dev->dev->caps.max_rq_sg; - props->max_sge_rd = MLX4_MAX_SGE_RD; + props->max_send_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_recv_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_sge_rd = MLX4_MAX_SGE_RD; props->max_cq = dev->dev->quotas.cq; props->max_cqe = dev->dev->caps.max_cqes; props->max_mr = dev->dev->quotas.mpt; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index ea01b8dd2be6..3d5424f335cb 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1027,12 +1027,14 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, skb_queue_head_init(&skqueue); + netif_tx_lock_bh(p->dev); spin_lock_irq(&priv->lock); set_bit(IPOIB_FLAG_OPER_UP, &p->flags); if (p->neigh) while ((skb = __skb_dequeue(&p->neigh->queue))) __skb_queue_tail(&skqueue, skb); spin_unlock_irq(&priv->lock); + netif_tx_unlock_bh(p->dev); while ((skb = __skb_dequeue(&skqueue))) { skb->dev = p->dev; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 316a57530f6d..c2df341ff6fa 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1439,6 +1439,7 @@ static struct irq_chip its_irq_chip = { * The consequence of the above is that allocation is cost is low, but * freeing is expensive. We assumes that freeing rarely occurs. */ +#define ITS_MAX_LPI_NRBITS 16 /* 64K LPIs */ static DEFINE_MUTEX(lpi_range_lock); static LIST_HEAD(lpi_range_list); @@ -1625,7 +1626,8 @@ static int __init its_alloc_lpi_tables(void) { phys_addr_t paddr; - lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer); + lpi_id_bits = min_t(u32, GICD_TYPER_ID_BITS(gic_rdists->gicd_typer), + ITS_MAX_LPI_NRBITS); gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT); if (!gic_rdists->prop_page) { pr_err("Failed to allocate PROPBASE\n"); 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/md/md-cluster.c b/drivers/md/md-cluster.c index 94329e03001e..0b2af6e74fc3 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1276,18 +1276,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi) static int resync_finish(struct mddev *mddev) { struct md_cluster_info *cinfo = mddev->cluster_info; + int ret = 0; clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery); - dlm_unlock_sync(cinfo->resync_lockres); /* * If resync thread is interrupted so we can't say resync is finished, * another node will launch resync thread to continue. */ - if (test_bit(MD_CLOSING, &mddev->flags)) - return 0; - else - return resync_info_update(mddev, 0, 0); + if (!test_bit(MD_CLOSING, &mddev->flags)) + ret = resync_info_update(mddev, 0, 0); + dlm_unlock_sync(cinfo->resync_lockres); + return ret; } static int area_resyncing(struct mddev *mddev, int direction, diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 981898049491..d6f7978b4449 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4529,11 +4529,12 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, allow_barrier(conf); } + raise_barrier(conf, 0); read_more: /* Now schedule reads for blocks from sector_nr to last */ r10_bio = raid10_alloc_init_r10buf(conf); r10_bio->state = 0; - raise_barrier(conf, sectors_done != 0); + raise_barrier(conf, 1); atomic_set(&r10_bio->remaining, 0); r10_bio->mddev = mddev; r10_bio->sector = sector_nr; @@ -4629,6 +4630,8 @@ read_more: if (sector_nr <= last) goto read_more; + lower_barrier(conf); + /* Now that we have done the whole section we can * update reshape_progress */ diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index a001808a2b77..bfb811407061 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -46,6 +46,11 @@ extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add); extern void ppl_quiesce(struct r5conf *conf, int quiesce); extern int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio); +static inline bool raid5_has_log(struct r5conf *conf) +{ + return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags); +} + static inline bool raid5_has_ppl(struct r5conf *conf) { return test_bit(MD_HAS_PPL, &conf->mddev->flags); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4ce0d7502fad..e4e98f47865d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -733,7 +733,7 @@ static bool stripe_can_batch(struct stripe_head *sh) { struct r5conf *conf = sh->raid_conf; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return false; return test_bit(STRIPE_BATCH_READY, &sh->state) && !test_bit(STRIPE_BITMAP_PENDING, &sh->state) && @@ -7737,7 +7737,7 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) sector_t newsize; struct r5conf *conf = mddev->private; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return -EINVAL; sectors &= ~((sector_t)conf->chunk_sectors - 1); newsize = raid5_size(mddev, sectors, mddev->raid_disks); @@ -7788,7 +7788,7 @@ static int check_reshape(struct mddev *mddev) { struct r5conf *conf = mddev->private; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return -EINVAL; if (mddev->delta_disks == 0 && mddev->new_layout == mddev->layout && diff --git a/drivers/memory/ti-aemif.c b/drivers/memory/ti-aemif.c index 31112f622b88..475e5b3790ed 100644 --- a/drivers/memory/ti-aemif.c +++ b/drivers/memory/ti-aemif.c @@ -411,7 +411,7 @@ static int aemif_probe(struct platform_device *pdev) if (ret < 0) goto error; } - } else { + } else if (pdata) { for (i = 0; i < pdata->num_sub_devices; i++) { pdata->sub_devices[i].dev.parent = dev; ret = platform_device_register(&pdata->sub_devices[i]); diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index e11ab12fbdf2..800986a79704 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -528,8 +528,8 @@ static int usbhs_omap_get_dt_pdata(struct device *dev, } static const struct of_device_id usbhs_child_match_table[] = { - { .compatible = "ti,omap-ehci", }, - { .compatible = "ti,omap-ohci", }, + { .compatible = "ti,ehci-omap", }, + { .compatible = "ti,ohci-omap3", }, { } }; @@ -855,6 +855,7 @@ static struct platform_driver usbhs_omap_driver = { .pm = &usbhsomap_dev_pm_ops, .of_match_table = usbhs_omap_dt_ids, }, + .probe = usbhs_omap_probe, .remove = usbhs_omap_remove, }; @@ -864,9 +865,9 @@ MODULE_ALIAS("platform:" USBHS_DRIVER_NAME); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("usb host common core driver for omap EHCI and OHCI"); -static int __init omap_usbhs_drvinit(void) +static int omap_usbhs_drvinit(void) { - return platform_driver_probe(&usbhs_omap_driver, usbhs_omap_probe); + return platform_driver_register(&usbhs_omap_driver); } /* @@ -878,7 +879,7 @@ static int __init omap_usbhs_drvinit(void) */ fs_initcall_sync(omap_usbhs_drvinit); -static void __exit omap_usbhs_drvexit(void) +static void omap_usbhs_drvexit(void) { platform_driver_unregister(&usbhs_omap_driver); } 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/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c index cbfafc453274..270d3c9580c5 100644 --- a/drivers/mtd/devices/m25p80.c +++ b/drivers/mtd/devices/m25p80.c @@ -39,13 +39,23 @@ static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len) struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(code, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_IN(len, val, 1)); + SPI_MEM_OP_DATA_IN(len, NULL, 1)); + void *scratchbuf; int ret; + scratchbuf = kmalloc(len, GFP_KERNEL); + if (!scratchbuf) + return -ENOMEM; + + op.data.buf.in = scratchbuf; ret = spi_mem_exec_op(flash->spimem, &op); if (ret < 0) dev_err(&flash->spimem->spi->dev, "error %d reading %x\n", ret, code); + else + memcpy(val, scratchbuf, len); + + kfree(scratchbuf); return ret; } @@ -56,9 +66,19 @@ static int m25p80_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len) struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(opcode, 1), SPI_MEM_OP_NO_ADDR, SPI_MEM_OP_NO_DUMMY, - SPI_MEM_OP_DATA_OUT(len, buf, 1)); + SPI_MEM_OP_DATA_OUT(len, NULL, 1)); + void *scratchbuf; + int ret; - return spi_mem_exec_op(flash->spimem, &op); + scratchbuf = kmemdup(buf, len, GFP_KERNEL); + if (!scratchbuf) + return -ENOMEM; + + op.data.buf.out = scratchbuf; + ret = spi_mem_exec_op(flash->spimem, &op); + kfree(scratchbuf); + + return ret; } static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len, diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 52e2cb35fc79..99c460facd5e 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -873,8 +873,11 @@ static int mtd_part_of_parse(struct mtd_info *master, int ret, err = 0; np = mtd_get_of_node(master); - if (!mtd_is_partition(master)) + if (mtd_is_partition(master)) + of_node_get(np); + else np = of_get_child_by_name(np, "partitions"); + of_property_for_each_string(np, "compatible", prop, compat) { parser = mtd_part_get_compatible_parser(compat); if (!parser) diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index 67b2065e7a19..b864b93dd289 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -596,6 +596,12 @@ static int denali_dma_xfer(struct denali_nand_info *denali, void *buf, } iowrite32(DMA_ENABLE__FLAG, denali->reg + DMA_ENABLE); + /* + * The ->setup_dma() hook kicks DMA by using the data/command + * interface, which belongs to a different AXI port from the + * register interface. Read back the register to avoid a race. + */ + ioread32(denali->reg + DMA_ENABLE); denali_reset_irq(denali); denali->setup_dma(denali, dma_addr, page, write); diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 7af4d6213ee5..bc2ef5209783 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -1547,7 +1547,7 @@ static void marvell_nfc_parse_instructions(struct nand_chip *chip, for (op_id = 0; op_id < subop->ninstrs; op_id++) { unsigned int offset, naddrs; const u8 *addrs; - int len = nand_subop_get_data_len(subop, op_id); + int len; instr = &subop->instrs[op_id]; @@ -1593,6 +1593,7 @@ static void marvell_nfc_parse_instructions(struct nand_chip *chip, nfc_op->ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW) | NDCB0_LEN_OVRD; + len = nand_subop_get_data_len(subop, op_id); nfc_op->ndcb[3] |= round_up(len, FIFO_DEPTH); } nfc_op->data_delay_ns = instr->delay_ns; @@ -1606,6 +1607,7 @@ static void marvell_nfc_parse_instructions(struct nand_chip *chip, nfc_op->ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW) | NDCB0_LEN_OVRD; + len = nand_subop_get_data_len(subop, op_id); nfc_op->ndcb[3] |= round_up(len, FIFO_DEPTH); } nfc_op->data_delay_ns = instr->delay_ns; 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/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 17f12c18d225..7635c38e77dd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -459,12 +459,12 @@ static void ena_com_handle_admin_completion(struct ena_com_admin_queue *admin_qu cqe = &admin_queue->cq.entries[head_masked]; /* Go over all the completions */ - while ((cqe->acq_common_descriptor.flags & + while ((READ_ONCE(cqe->acq_common_descriptor.flags) & ENA_ADMIN_ACQ_COMMON_DESC_PHASE_MASK) == phase) { /* Do not read the rest of the completion entry before the * phase bit was validated */ - rmb(); + dma_rmb(); ena_com_handle_single_admin_completion(admin_queue, cqe); head_masked++; @@ -627,17 +627,10 @@ static u32 ena_com_reg_bar_read32(struct ena_com_dev *ena_dev, u16 offset) mmio_read_reg |= mmio_read->seq_num & ENA_REGS_MMIO_REG_READ_REQ_ID_MASK; - /* make sure read_resp->req_id get updated before the hw can write - * there - */ - wmb(); - - writel_relaxed(mmio_read_reg, - ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF); + writel(mmio_read_reg, ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF); - mmiowb(); for (i = 0; i < timeout; i++) { - if (read_resp->req_id == mmio_read->seq_num) + if (READ_ONCE(read_resp->req_id) == mmio_read->seq_num) break; udelay(1); @@ -1796,8 +1789,13 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data) aenq_common = &aenq_e->aenq_common_desc; /* Go over all the events */ - while ((aenq_common->flags & ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == - phase) { + while ((READ_ONCE(aenq_common->flags) & + ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == phase) { + /* Make sure the phase bit (ownership) is as expected before + * reading the rest of the descriptor. + */ + dma_rmb(); + pr_debug("AENQ! Group[%x] Syndrom[%x] timestamp: [%llus]\n", aenq_common->group, aenq_common->syndrom, (u64)aenq_common->timestamp_low + diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index ea149c134e15..1c682b76190f 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -51,6 +51,11 @@ static inline struct ena_eth_io_rx_cdesc_base *ena_com_get_next_rx_cdesc( if (desc_phase != expected_phase) return NULL; + /* Make sure we read the rest of the descriptor after the phase bit + * has been read + */ + dma_rmb(); + return cdesc; } @@ -493,6 +498,7 @@ int ena_com_tx_comp_req_id_get(struct ena_com_io_cq *io_cq, u16 *req_id) if (cdesc_phase != expected_phase) return -EAGAIN; + dma_rmb(); if (unlikely(cdesc->req_id >= io_cq->q_depth)) { pr_err("Invalid req id %d\n", cdesc->req_id); return -EINVAL; diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h index 6fdc753d9483..2f7657227cfe 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h @@ -107,8 +107,7 @@ static inline int ena_com_sq_empty_space(struct ena_com_io_sq *io_sq) return io_sq->q_depth - 1 - cnt; } -static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq, - bool relaxed) +static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq) { u16 tail; @@ -117,10 +116,7 @@ static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq, pr_debug("write submission queue doorbell for queue: %d tail: %d\n", io_sq->qid, tail); - if (relaxed) - writel_relaxed(tail, io_sq->db_addr); - else - writel(tail, io_sq->db_addr); + writel(tail, io_sq->db_addr); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index c673ac2df65b..29b5774dd32d 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -76,7 +76,7 @@ MODULE_DEVICE_TABLE(pci, ena_pci_tbl); static int ena_rss_init_default(struct ena_adapter *adapter); static void check_for_admin_com_state(struct ena_adapter *adapter); -static void ena_destroy_device(struct ena_adapter *adapter); +static void ena_destroy_device(struct ena_adapter *adapter, bool graceful); static int ena_restore_device(struct ena_adapter *adapter); static void ena_tx_timeout(struct net_device *dev) @@ -461,7 +461,7 @@ static inline int ena_alloc_rx_page(struct ena_ring *rx_ring, return -ENOMEM; } - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, + dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(rx_ring->dev, dma))) { u64_stats_update_begin(&rx_ring->syncp); @@ -478,7 +478,7 @@ static inline int ena_alloc_rx_page(struct ena_ring *rx_ring, rx_info->page_offset = 0; ena_buf = &rx_info->ena_buf; ena_buf->paddr = dma; - ena_buf->len = PAGE_SIZE; + ena_buf->len = ENA_PAGE_SIZE; return 0; } @@ -495,7 +495,7 @@ static void ena_free_rx_page(struct ena_ring *rx_ring, return; } - dma_unmap_page(rx_ring->dev, ena_buf->paddr, PAGE_SIZE, + dma_unmap_page(rx_ring->dev, ena_buf->paddr, ENA_PAGE_SIZE, DMA_FROM_DEVICE); __free_page(page); @@ -551,14 +551,9 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) rx_ring->qid, i, num); } - if (likely(i)) { - /* Add memory barrier to make sure the desc were written before - * issue a doorbell - */ - wmb(); - ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq, true); - mmiowb(); - } + /* ena_com_write_sq_doorbell issues a wmb() */ + if (likely(i)) + ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq); rx_ring->next_to_use = next_to_use; @@ -916,10 +911,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, do { dma_unmap_page(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr), - PAGE_SIZE, DMA_FROM_DEVICE); + ENA_PAGE_SIZE, DMA_FROM_DEVICE); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, - rx_info->page_offset, len, PAGE_SIZE); + rx_info->page_offset, len, ENA_PAGE_SIZE); netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx skb updated. len %d. data_len %d\n", @@ -1900,7 +1895,7 @@ static int ena_close(struct net_device *netdev) "Destroy failure, restarting device\n"); ena_dump_stats_to_dmesg(adapter); /* rtnl lock already obtained in dev_ioctl() layer */ - ena_destroy_device(adapter); + ena_destroy_device(adapter, false); ena_restore_device(adapter); } @@ -2112,12 +2107,6 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_ring->next_to_use = ENA_TX_RING_IDX_NEXT(next_to_use, tx_ring->ring_size); - /* This WMB is aimed to: - * 1 - perform smp barrier before reading next_to_completion - * 2 - make sure the desc were written before trigger DB - */ - wmb(); - /* stop the queue when no more space available, the packet can have up * to sgl_size + 2. one for the meta descriptor and one for header * (if the header is larger than tx_max_header_size). @@ -2136,10 +2125,11 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) * stop the queue but meanwhile clean_tx_irq updates * next_to_completion and terminates. * The queue will remain stopped forever. - * To solve this issue this function perform rmb, check - * the wakeup condition and wake up the queue if needed. + * To solve this issue add a mb() to make sure that + * netif_tx_stop_queue() write is vissible before checking if + * there is additional space in the queue. */ - smp_rmb(); + smp_mb(); if (ena_com_sq_empty_space(tx_ring->ena_com_io_sq) > ENA_TX_WAKEUP_THRESH) { @@ -2151,8 +2141,10 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) } if (netif_xmit_stopped(txq) || !skb->xmit_more) { - /* trigger the dma engine */ - ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq, false); + /* trigger the dma engine. ena_com_write_sq_doorbell() + * has a mb + */ + ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq); u64_stats_update_begin(&tx_ring->syncp); tx_ring->tx_stats.doorbells++; u64_stats_update_end(&tx_ring->syncp); @@ -2550,12 +2542,15 @@ err_disable_msix: return rc; } -static void ena_destroy_device(struct ena_adapter *adapter) +static void ena_destroy_device(struct ena_adapter *adapter, bool graceful) { struct net_device *netdev = adapter->netdev; struct ena_com_dev *ena_dev = adapter->ena_dev; bool dev_up; + if (!test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) + return; + netif_carrier_off(netdev); del_timer_sync(&adapter->timer_service); @@ -2563,7 +2558,8 @@ static void ena_destroy_device(struct ena_adapter *adapter) dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags); adapter->dev_up_before_reset = dev_up; - ena_com_set_admin_running_state(ena_dev, false); + if (!graceful) + ena_com_set_admin_running_state(ena_dev, false); if (test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) ena_down(adapter); @@ -2591,6 +2587,7 @@ static void ena_destroy_device(struct ena_adapter *adapter) adapter->reset_reason = ENA_REGS_RESET_NORMAL; clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); } static int ena_restore_device(struct ena_adapter *adapter) @@ -2635,6 +2632,7 @@ static int ena_restore_device(struct ena_adapter *adapter) } } + set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); dev_err(&pdev->dev, "Device reset completed successfully\n"); @@ -2665,7 +2663,7 @@ static void ena_fw_reset_device(struct work_struct *work) return; } rtnl_lock(); - ena_destroy_device(adapter); + ena_destroy_device(adapter, false); ena_restore_device(adapter); rtnl_unlock(); } @@ -3409,30 +3407,24 @@ static void ena_remove(struct pci_dev *pdev) netdev->rx_cpu_rmap = NULL; } #endif /* CONFIG_RFS_ACCEL */ - - unregister_netdev(netdev); del_timer_sync(&adapter->timer_service); cancel_work_sync(&adapter->reset_task); - /* Reset the device only if the device is running. */ - if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) - ena_com_dev_reset(ena_dev, adapter->reset_reason); + unregister_netdev(netdev); - ena_free_mgmnt_irq(adapter); + /* If the device is running then we want to make sure the device will be + * reset to make sure no more events will be issued by the device. + */ + if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); - ena_disable_msix(adapter); + rtnl_lock(); + ena_destroy_device(adapter, true); + rtnl_unlock(); free_netdev(netdev); - ena_com_mmio_reg_read_request_destroy(ena_dev); - - ena_com_abort_admin_commands(ena_dev); - - ena_com_wait_for_abort_completion(ena_dev); - - ena_com_admin_destroy(ena_dev); - ena_com_rss_destroy(ena_dev); ena_com_delete_debug_area(ena_dev); @@ -3467,7 +3459,7 @@ static int ena_suspend(struct pci_dev *pdev, pm_message_t state) "ignoring device reset request as the device is being suspended\n"); clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); } - ena_destroy_device(adapter); + ena_destroy_device(adapter, true); rtnl_unlock(); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index f1972b5ab650..7c7ae56c52cf 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -355,4 +355,15 @@ void ena_dump_stats_to_buf(struct ena_adapter *adapter, u8 *buf); int ena_get_sset_count(struct net_device *netdev, int sset); +/* The ENA buffer length fields is 16 bit long. So when PAGE_SIZE == 64kB the + * driver passas 0. + * Since the max packet size the ENA handles is ~9kB limit the buffer length to + * 16kB. + */ +#if PAGE_SIZE > SZ_16K +#define ENA_PAGE_SIZE SZ_16K +#else +#define ENA_PAGE_SIZE PAGE_SIZE +#endif + #endif /* !(ENA_H) */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8bb1e38b1681..177587f9c3f1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5913,12 +5913,12 @@ unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp) return bp->hw_resc.max_cp_rings; } -void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max) +unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp) { - bp->hw_resc.max_cp_rings = max; + return bp->hw_resc.max_cp_rings - bnxt_get_ulp_msix_num(bp); } -unsigned int bnxt_get_max_func_irqs(struct bnxt *bp) +static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; @@ -6684,6 +6684,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) hw_resc->resv_rx_rings = 0; hw_resc->resv_hw_ring_grps = 0; hw_resc->resv_vnics = 0; + bp->tx_nr_rings = 0; + bp->rx_nr_rings = 0; } return rc; } @@ -8025,7 +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; @@ -8629,7 +8631,8 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, *max_tx = hw_resc->max_tx_rings; *max_rx = hw_resc->max_rx_rings; - *max_cp = min_t(int, hw_resc->max_irqs, hw_resc->max_cp_rings); + *max_cp = min_t(int, bnxt_get_max_func_cp_rings_for_en(bp), + hw_resc->max_irqs); *max_cp = min_t(int, *max_cp, hw_resc->max_stat_ctxs); max_ring_grps = hw_resc->max_hw_ring_grps; if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) { @@ -8769,20 +8772,25 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp) if (bp->tx_nr_rings) return 0; + bnxt_ulp_irq_stop(bp); + bnxt_clear_int_mode(bp); rc = bnxt_set_dflt_rings(bp, true); if (rc) { netdev_err(bp->dev, "Not enough rings available.\n"); - return rc; + goto init_dflt_ring_err; } rc = bnxt_init_int_mode(bp); if (rc) - return rc; + goto init_dflt_ring_err; + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; if (bnxt_rfs_supported(bp) && bnxt_rfs_capable(bp)) { bp->flags |= BNXT_FLAG_RFS; bp->dev->features |= NETIF_F_NTUPLE; } - return 0; +init_dflt_ring_err: + bnxt_ulp_irq_restart(bp, rc); + return rc; } int bnxt_restore_pf_fw_resources(struct bnxt *bp) @@ -8819,14 +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.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index fefa011320e0..bde384630a75 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1481,8 +1481,7 @@ int bnxt_hwrm_set_coal(struct bnxt *); unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp); void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max); unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp); -void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max); -unsigned int bnxt_get_max_func_irqs(struct bnxt *bp); +unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp); int bnxt_get_avail_msix(struct bnxt *bp, int num); int bnxt_reserve_rings(struct bnxt *bp); void bnxt_tx_disable(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 6d583bcd2a81..3962f6fd543c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -451,7 +451,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1); - vf_cp_rings = hw_resc->max_cp_rings - bp->cp_nr_rings; + vf_cp_rings = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings; vf_stat_ctx = hw_resc->max_stat_ctxs - bp->num_stat_ctxs; if (bp->flags & BNXT_FLAG_AGG_RINGS) vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2; @@ -549,7 +549,8 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) max_stat_ctxs = hw_resc->max_stat_ctxs; /* Remaining rings are distributed equally amongs VF's for now */ - vf_cp_rings = (hw_resc->max_cp_rings - bp->cp_nr_rings) / num_vfs; + vf_cp_rings = (bnxt_get_max_func_cp_rings_for_en(bp) - + bp->cp_nr_rings) / num_vfs; vf_stat_ctx = (max_stat_ctxs - bp->num_stat_ctxs) / num_vfs; if (bp->flags & BNXT_FLAG_AGG_RINGS) vf_rx_rings = (hw_resc->max_rx_rings - bp->rx_nr_rings * 2) / @@ -643,7 +644,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) */ vfs_supported = *num_vfs; - avail_cp = hw_resc->max_cp_rings - bp->cp_nr_rings; + avail_cp = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings; avail_stat = hw_resc->max_stat_ctxs - bp->num_stat_ctxs; avail_cp = min_t(int, avail_cp, avail_stat); @@ -1103,7 +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; @@ -1121,12 +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 @@ -1143,7 +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/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index c37b2842f972..beee61292d5e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, edev->ulp_tbl[ulp_id].msix_requested = avail_msix; } bnxt_fill_msix_vecs(bp, ent); - bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix); edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED; return avail_msix; } @@ -178,7 +177,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); - int max_cp_rings, msix_requested; ASSERT_RTNL(); if (ulp_id != BNXT_ROCE_ULP) @@ -187,9 +185,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id) if (!(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) return 0; - max_cp_rings = bnxt_get_max_func_cp_rings(bp); - msix_requested = edev->ulp_tbl[ulp_id].msix_requested; - bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested); edev->ulp_tbl[ulp_id].msix_requested = 0; edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; if (netif_running(dev)) { @@ -220,21 +215,6 @@ int bnxt_get_ulp_msix_base(struct bnxt *bp) return 0; } -void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id) -{ - ASSERT_RTNL(); - if (bnxt_ulp_registered(bp->edev, ulp_id)) { - struct bnxt_en_dev *edev = bp->edev; - unsigned int msix_req, max; - - msix_req = edev->ulp_tbl[ulp_id].msix_requested; - max = bnxt_get_max_func_cp_rings(bp); - bnxt_set_max_func_cp_rings(bp, max - msix_req); - max = bnxt_get_max_func_stat_ctxs(bp); - bnxt_set_max_func_stat_ctxs(bp, max - 1); - } -} - static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id, struct bnxt_fw_msg *fw_msg) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h index df48ac71729f..d9bea37cd211 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h @@ -90,7 +90,6 @@ static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id) int bnxt_get_ulp_msix_num(struct bnxt *bp); int bnxt_get_ulp_msix_base(struct bnxt *bp); -void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id); void bnxt_ulp_stop(struct bnxt *bp); void bnxt_ulp_start(struct bnxt *bp); void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index b773bc07edf7..14b49612aa86 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -186,6 +186,9 @@ struct bcmgenet_mib_counters { #define UMAC_MAC1 0x010 #define UMAC_MAX_FRAME_LEN 0x014 +#define UMAC_MODE 0x44 +#define MODE_LINK_STATUS (1 << 5) + #define UMAC_EEE_CTRL 0x064 #define EN_LPI_RX_PAUSE (1 << 0) #define EN_LPI_TX_PFC (1 << 1) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 5333274a283c..4241ae928d4a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -115,8 +115,14 @@ void bcmgenet_mii_setup(struct net_device *dev) static int bcmgenet_fixed_phy_link_update(struct net_device *dev, struct fixed_phy_status *status) { - if (dev && dev->phydev && status) - status->link = dev->phydev->link; + struct bcmgenet_priv *priv; + u32 reg; + + if (dev && dev->phydev && status) { + priv = netdev_priv(dev); + reg = bcmgenet_umac_readl(priv, UMAC_MODE); + status->link = !!(reg & MODE_LINK_STATUS); + } return 0; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index c6707ea2d751..f1a86b422617 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -649,7 +649,7 @@ static int macb_halt_tx(struct macb *bp) if (!(status & MACB_BIT(TGO))) return 0; - usleep_range(10, 250); + udelay(250); } while (time_before(halt_time, timeout)); return -ETIMEDOUT; @@ -3837,6 +3837,13 @@ 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, @@ -3904,6 +3911,7 @@ 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/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index ff92ab1daeb8..1e9d882c04ef 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -4500,7 +4500,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, port_res->max_vfs += le16_to_cpu(pcie->num_vfs); } } - return status; + goto err; } pcie = be_get_pcie_desc(resp->func_param, desc_count, diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index cad52bd331f7..08a750fb60c4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -486,6 +486,8 @@ struct hnae_ae_ops { u8 *auto_neg, u16 *speed, u8 *duplex); void (*toggle_ring_irq)(struct hnae_ring *ring, u32 val); void (*adjust_link)(struct hnae_handle *handle, int speed, int duplex); + bool (*need_adjust_link)(struct hnae_handle *handle, + int speed, int duplex); int (*set_loopback)(struct hnae_handle *handle, enum hnae_loop loop_mode, int en); void (*get_ring_bdnum_limit)(struct hnae_queue *queue, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index e6aad30e7e69..b52029e26d15 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -155,6 +155,41 @@ static void hns_ae_put_handle(struct hnae_handle *handle) hns_ae_get_ring_pair(handle->qs[i])->used_by_vf = 0; } +static int hns_ae_wait_flow_down(struct hnae_handle *handle) +{ + struct dsaf_device *dsaf_dev; + struct hns_ppe_cb *ppe_cb; + struct hnae_vf_cb *vf_cb; + int ret; + int i; + + for (i = 0; i < handle->q_num; i++) { + ret = hns_rcb_wait_tx_ring_clean(handle->qs[i]); + if (ret) + return ret; + } + + ppe_cb = hns_get_ppe_cb(handle); + ret = hns_ppe_wait_tx_fifo_clean(ppe_cb); + if (ret) + return ret; + + dsaf_dev = hns_ae_get_dsaf_dev(handle->dev); + if (!dsaf_dev) + return -EINVAL; + ret = hns_dsaf_wait_pkt_clean(dsaf_dev, handle->dport_id); + if (ret) + return ret; + + vf_cb = hns_ae_get_vf_cb(handle); + ret = hns_mac_wait_fifo_clean(vf_cb->mac_cb); + if (ret) + return ret; + + mdelay(10); + return 0; +} + static void hns_ae_ring_enable_all(struct hnae_handle *handle, int val) { int q_num = handle->q_num; @@ -399,12 +434,41 @@ static int hns_ae_get_mac_info(struct hnae_handle *handle, return hns_mac_get_port_info(mac_cb, auto_neg, speed, duplex); } +static bool hns_ae_need_adjust_link(struct hnae_handle *handle, int speed, + int duplex) +{ + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + return hns_mac_need_adjust_link(mac_cb, speed, duplex); +} + static void hns_ae_adjust_link(struct hnae_handle *handle, int speed, int duplex) { struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); - hns_mac_adjust_link(mac_cb, speed, duplex); + switch (mac_cb->dsaf_dev->dsaf_ver) { + case AE_VERSION_1: + hns_mac_adjust_link(mac_cb, speed, duplex); + break; + + case AE_VERSION_2: + /* chip need to clear all pkt inside */ + hns_mac_disable(mac_cb, MAC_COMM_MODE_RX); + if (hns_ae_wait_flow_down(handle)) { + hns_mac_enable(mac_cb, MAC_COMM_MODE_RX); + break; + } + + hns_mac_adjust_link(mac_cb, speed, duplex); + hns_mac_enable(mac_cb, MAC_COMM_MODE_RX); + break; + + default: + break; + } + + return; } static void hns_ae_get_ring_bdnum_limit(struct hnae_queue *queue, @@ -902,6 +966,7 @@ static struct hnae_ae_ops hns_dsaf_ops = { .get_status = hns_ae_get_link_status, .get_info = hns_ae_get_mac_info, .adjust_link = hns_ae_adjust_link, + .need_adjust_link = hns_ae_need_adjust_link, .set_loopback = hns_ae_config_loopback, .get_ring_bdnum_limit = hns_ae_get_ring_bdnum_limit, .get_pauseparam = hns_ae_get_pauseparam, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 5488c6e89f21..09e4061d1fa6 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -257,6 +257,16 @@ static void hns_gmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_pause_en, *tx_pause_en = dsaf_get_bit(pause_en, GMAC_PAUSE_EN_TX_FDFC_B); } +static bool hns_gmac_need_adjust_link(void *mac_drv, enum mac_speed speed, + int duplex) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct hns_mac_cb *mac_cb = drv->mac_cb; + + return (mac_cb->speed != speed) || + (mac_cb->half_duplex == duplex); +} + static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed, u32 full_duplex) { @@ -309,6 +319,30 @@ static void hns_gmac_set_promisc(void *mac_drv, u8 en) hns_gmac_set_uc_match(mac_drv, en); } +int hns_gmac_wait_fifo_clean(void *mac_drv) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + int wait_cnt; + u32 val; + + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + val = dsaf_read_dev(drv, GMAC_FIFO_STATE_REG); + /* bit5~bit0 is not send complete pkts */ + if ((val & 0x3f) == 0) + break; + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(drv->dev, + "hns ge %d fifo was not idle.\n", drv->mac_id); + return -EBUSY; + } + + return 0; +} + static void hns_gmac_init(void *mac_drv) { u32 port; @@ -690,6 +724,7 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) mac_drv->mac_disable = hns_gmac_disable; mac_drv->mac_free = hns_gmac_free; mac_drv->adjust_link = hns_gmac_adjust_link; + mac_drv->need_adjust_link = hns_gmac_need_adjust_link; mac_drv->set_tx_auto_pause_frames = hns_gmac_set_tx_auto_pause_frames; mac_drv->config_max_frame_length = hns_gmac_config_max_frame_length; mac_drv->mac_pausefrm_cfg = hns_gmac_pause_frm_cfg; @@ -717,6 +752,7 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) mac_drv->get_strings = hns_gmac_get_strings; mac_drv->update_stats = hns_gmac_update_stats; mac_drv->set_promiscuous = hns_gmac_set_promisc; + mac_drv->wait_fifo_clean = hns_gmac_wait_fifo_clean; return (void *)mac_drv; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 1c2326bd76e2..6ed6f142427e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -114,6 +114,26 @@ int hns_mac_get_port_info(struct hns_mac_cb *mac_cb, return 0; } +/** + *hns_mac_is_adjust_link - check is need change mac speed and duplex register + *@mac_cb: mac device + *@speed: phy device speed + *@duplex:phy device duplex + * + */ +bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex) +{ + struct mac_driver *mac_ctrl_drv; + + mac_ctrl_drv = (struct mac_driver *)(mac_cb->priv.mac); + + if (mac_ctrl_drv->need_adjust_link) + return mac_ctrl_drv->need_adjust_link(mac_ctrl_drv, + (enum mac_speed)speed, duplex); + else + return true; +} + void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex) { int ret; @@ -430,6 +450,16 @@ int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable) return 0; } +int hns_mac_wait_fifo_clean(struct hns_mac_cb *mac_cb) +{ + struct mac_driver *drv = hns_mac_get_drv(mac_cb); + + if (drv->wait_fifo_clean) + return drv->wait_fifo_clean(drv); + + return 0; +} + void hns_mac_reset(struct hns_mac_cb *mac_cb) { struct mac_driver *drv = hns_mac_get_drv(mac_cb); @@ -998,6 +1028,20 @@ static int hns_mac_get_max_port_num(struct dsaf_device *dsaf_dev) return DSAF_MAX_PORT_NUM; } +void hns_mac_enable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->mac_enable(mac_cb->priv.mac, mode); +} + +void hns_mac_disable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->mac_disable(mac_cb->priv.mac, mode); +} + /** * hns_mac_init - init mac * @dsaf_dev: dsa fabric device struct pointer diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h index bbc0a98e7ca3..fbc75341bef7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -356,6 +356,9 @@ struct mac_driver { /*adjust mac mode of port,include speed and duplex*/ int (*adjust_link)(void *mac_drv, enum mac_speed speed, u32 full_duplex); + /* need adjust link */ + bool (*need_adjust_link)(void *mac_drv, enum mac_speed speed, + int duplex); /* config autoegotaite mode of port*/ void (*set_an_mode)(void *mac_drv, u8 enable); /* config loopbank mode */ @@ -394,6 +397,7 @@ struct mac_driver { void (*get_info)(void *mac_drv, struct mac_info *mac_info); void (*update_stats)(void *mac_drv); + int (*wait_fifo_clean)(void *mac_drv); enum mac_mode mac_mode; u8 mac_id; @@ -427,6 +431,7 @@ void *hns_xgmac_config(struct hns_mac_cb *mac_cb, int hns_mac_init(struct dsaf_device *dsaf_dev); void mac_adjust_link(struct net_device *net_dev); +bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex); void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status); int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, char *addr); int hns_mac_set_multi(struct hns_mac_cb *mac_cb, @@ -463,5 +468,8 @@ int hns_mac_add_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id, int hns_mac_rm_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id, const unsigned char *addr); int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn); +void hns_mac_enable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode); +void hns_mac_disable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode); +int hns_mac_wait_fifo_clean(struct hns_mac_cb *mac_cb); #endif /* _HNS_DSAF_MAC_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index ca50c2553a9c..e557a4ef5996 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -2727,6 +2727,35 @@ void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev, soft_mac_entry->index = enable ? entry_index : DSAF_INVALID_ENTRY_IDX; } +int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port) +{ + u32 val, val_tmp; + int wait_cnt; + + if (port >= DSAF_SERVICE_NW_NUM) + return 0; + + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + val = dsaf_read_dev(dsaf_dev, DSAF_VOQ_IN_PKT_NUM_0_REG + + (port + DSAF_XGE_NUM) * 0x40); + val_tmp = dsaf_read_dev(dsaf_dev, DSAF_VOQ_OUT_PKT_NUM_0_REG + + (port + DSAF_XGE_NUM) * 0x40); + if (val == val_tmp) + break; + + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(dsaf_dev->dev, "hns dsaf clean wait timeout(%u - %u).\n", + val, val_tmp); + return -EBUSY; + } + + return 0; +} + /** * dsaf_probe - probo dsaf dev * @pdev: dasf platform device diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 4507e8222683..0e1cd99831a6 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -44,6 +44,8 @@ struct hns_mac_cb; #define DSAF_ROCE_CREDIT_CHN 8 #define DSAF_ROCE_CHAN_MODE 3 +#define HNS_MAX_WAIT_CNT 10000 + enum dsaf_roce_port_mode { DSAF_ROCE_6PORT_MODE, DSAF_ROCE_4PORT_MODE, @@ -463,5 +465,6 @@ int hns_dsaf_rm_mac_addr( int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id, u8 port_num); +int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port); #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index d160d8c9e45b..0942e4916d9d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -275,6 +275,29 @@ static void hns_ppe_exc_irq_en(struct hns_ppe_cb *ppe_cb, int en) dsaf_write_dev(ppe_cb, PPE_INTEN_REG, msk_vlue & vld_msk); } +int hns_ppe_wait_tx_fifo_clean(struct hns_ppe_cb *ppe_cb) +{ + int wait_cnt; + u32 val; + + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + val = dsaf_read_dev(ppe_cb, PPE_CURR_TX_FIFO0_REG) & 0x3ffU; + if (!val) + break; + + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(ppe_cb->dev, "hns ppe tx fifo clean wait timeout, still has %u pkt.\n", + val); + return -EBUSY; + } + + return 0; +} + /** * ppe_init_hw - init ppe * @ppe_cb: ppe device diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h index 9d8e643e8aa6..f670e63a5a01 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h @@ -100,6 +100,7 @@ struct ppe_common_cb { }; +int hns_ppe_wait_tx_fifo_clean(struct hns_ppe_cb *ppe_cb); int hns_ppe_init(struct dsaf_device *dsaf_dev); void hns_ppe_uninit(struct dsaf_device *dsaf_dev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 9d76e2e54f9d..5d64519b9b1d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -66,6 +66,29 @@ void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag) "queue(%d) wait fbd(%d) clean fail!!\n", i, fbd_num); } +int hns_rcb_wait_tx_ring_clean(struct hnae_queue *qs) +{ + u32 head, tail; + int wait_cnt; + + tail = dsaf_read_dev(&qs->tx_ring, RCB_REG_TAIL); + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + head = dsaf_read_dev(&qs->tx_ring, RCB_REG_HEAD); + if (tail == head) + break; + + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(qs->dev->dev, "rcb wait timeout, head not equal to tail.\n"); + return -EBUSY; + } + + return 0; +} + /** *hns_rcb_reset_ring_hw - ring reset *@q: ring struct pointer diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index 602816498c8d..2319b772a271 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -136,6 +136,7 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag); void hns_rcb_init_hw(struct ring_pair_cb *ring); void hns_rcb_reset_ring_hw(struct hnae_queue *q); void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag); +int hns_rcb_wait_tx_ring_clean(struct hnae_queue *qs); u32 hns_rcb_get_rx_coalesced_frames( struct rcb_common_cb *rcb_common, u32 port_idx); u32 hns_rcb_get_tx_coalesced_frames( diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index 886cbbf25761..74d935d82cbc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -464,6 +464,7 @@ #define RCB_RING_INTMSK_TX_OVERTIME_REG 0x000C4 #define RCB_RING_INTSTS_TX_OVERTIME_REG 0x000C8 +#define GMAC_FIFO_STATE_REG 0x0000UL #define GMAC_DUPLEX_TYPE_REG 0x0008UL #define GMAC_FD_FC_TYPE_REG 0x000CUL #define GMAC_TX_WATER_LINE_REG 0x0010UL diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 02a0ba20fad5..f56855e63c96 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1112,11 +1112,26 @@ static void hns_nic_adjust_link(struct net_device *ndev) struct hnae_handle *h = priv->ae_handle; int state = 1; + /* If there is no phy, do not need adjust link */ if (ndev->phydev) { - h->dev->ops->adjust_link(h, ndev->phydev->speed, - ndev->phydev->duplex); - state = ndev->phydev->link; + /* When phy link down, do nothing */ + if (ndev->phydev->link == 0) + return; + + if (h->dev->ops->need_adjust_link(h, ndev->phydev->speed, + ndev->phydev->duplex)) { + /* because Hi161X chip don't support to change gmac + * speed and duplex with traffic. Delay 200ms to + * make sure there is no more data in chip FIFO. + */ + netif_carrier_off(ndev); + msleep(200); + h->dev->ops->adjust_link(h, ndev->phydev->speed, + ndev->phydev->duplex); + netif_carrier_on(ndev); + } } + state = state && h->dev->ops->get_status(h); if (state != priv->link) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 08f3c4743f74..774beda040a1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -243,7 +243,9 @@ static int hns_nic_set_link_ksettings(struct net_device *net_dev, } if (h->dev->ops->adjust_link) { + netif_carrier_off(net_dev); h->dev->ops->adjust_link(h, (int)speed, cmd->base.duplex); + netif_carrier_on(net_dev); return 0; } 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/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 354c0982847b..372664686309 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -494,9 +494,6 @@ static u32 __emac_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_s case 16384: ret |= EMAC_MR1_RFS_16K; break; - case 8192: - ret |= EMAC4_MR1_RFS_8K; - break; case 4096: ret |= EMAC_MR1_RFS_4K; break; @@ -537,6 +534,9 @@ static u32 __emac4_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_ case 16384: ret |= EMAC4_MR1_RFS_16K; break; + case 8192: + ret |= EMAC4_MR1_RFS_8K; + break; case 4096: ret |= EMAC4_MR1_RFS_4K; break; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index dafdd4ade705..4f0daf67b18d 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1823,11 +1823,17 @@ static int do_reset(struct ibmvnic_adapter *adapter, adapter->map_id = 1; release_rx_pools(adapter); release_tx_pools(adapter); - init_rx_pools(netdev); - init_tx_pools(netdev); + rc = init_rx_pools(netdev); + if (rc) + return rc; + rc = init_tx_pools(netdev); + if (rc) + return rc; release_napi(adapter); - init_napi(adapter); + rc = init_napi(adapter); + if (rc) + return rc; } else { rc = reset_tx_pools(adapter); if (rc) diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 7a637b51c7d2..e08301d833e2 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -274,6 +274,7 @@ ltq_etop_hw_init(struct net_device *dev) struct ltq_etop_chan *ch = &priv->ch[i]; ch->idx = ch->dma.nr = i; + ch->dma.dev = &priv->pdev->dev; if (IS_TX(i)) { ltq_dma_alloc_tx(&ch->dma); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 32d785b616e1..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, @@ -4803,6 +4794,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->min_mtu = ETH_MIN_MTU; /* 9704 == 9728 - 20 and rounding to 8 */ dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE; + dev->dev.of_node = port_node; /* Phylink isn't used w/ ACPI as of now */ if (port_node) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index b994b80d5714..37ba7c78859d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -132,11 +132,11 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) delayed_event_start(priv); dev_ctx->context = intf->add(dev); - set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - if (intf->attach) - set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); - if (dev_ctx->context) { + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); + if (intf->attach) + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); + spin_lock_irq(&priv->ctx_lock); list_add_tail(&dev_ctx->list, &priv->ctx_list); @@ -211,12 +211,17 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv if (intf->attach) { if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) goto out; - intf->attach(dev, dev_ctx->context); + if (intf->attach(dev, dev_ctx->context)) + goto out; + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); } else { if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) goto out; dev_ctx->context = intf->add(dev); + if (!dev_ctx->context) + goto out; + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); } @@ -391,16 +396,17 @@ void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol) } } -static u16 mlx5_gen_pci_id(struct mlx5_core_dev *dev) +static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev) { - return (u16)((dev->pdev->bus->number << 8) | + return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | + (dev->pdev->bus->number << 8) | PCI_SLOT(dev->pdev->devfn)); } /* Must be called with intf_mutex held */ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev) { - u16 pci_id = mlx5_gen_pci_id(dev); + u32 pci_id = mlx5_gen_pci_id(dev); struct mlx5_core_dev *res = NULL; struct mlx5_core_dev *tmp_dev; struct mlx5_priv *priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 75bb981e00b7..41cde926cdab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -191,7 +191,7 @@ set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v, { if (psrc_m) { MLX5E_FTE_SET(headers_c, udp_sport, 0xffff); - MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_v)); + MLX5E_FTE_SET(headers_v, udp_sport, ntohs(psrc_v)); } if (pdst_m) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f72b5c9dcfe9..3028e8d90920 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -663,6 +663,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) if (err) goto miss_rule_err; + kvfree(flow_group_in); return 0; miss_rule_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f418541af7cf..37d114c668b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1578,6 +1578,33 @@ static u64 matched_fgs_get_version(struct list_head *match_head) return version; } +static struct fs_fte * +lookup_fte_locked(struct mlx5_flow_group *g, + u32 *match_value, + bool take_write) +{ + struct fs_fte *fte_tmp; + + if (take_write) + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + else + nested_down_read_ref_node(&g->node, FS_LOCK_PARENT); + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, + rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { + fte_tmp = NULL; + goto out; + } + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); +out: + if (take_write) + up_write_ref_node(&g->node); + else + up_read_ref_node(&g->node); + return fte_tmp; +} + static struct mlx5_flow_handle * try_add_to_existing_fg(struct mlx5_flow_table *ft, struct list_head *match_head, @@ -1600,10 +1627,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, if (IS_ERR(fte)) return ERR_PTR(-ENOMEM); - list_for_each_entry(iter, match_head, list) { - nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT); - } - search_again_locked: version = matched_fgs_get_version(match_head); /* Try to find a fg that already contains a matching fte */ @@ -1611,20 +1634,9 @@ search_again_locked: struct fs_fte *fte_tmp; g = iter->g; - fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, - rhash_fte); - if (!fte_tmp || !tree_get_node(&fte_tmp->node)) + fte_tmp = lookup_fte_locked(g, spec->match_value, take_write); + if (!fte_tmp) continue; - - nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); - if (!take_write) { - list_for_each_entry(iter, match_head, list) - up_read_ref_node(&iter->g->node); - } else { - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); - } - rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, fte_tmp); up_write_ref_node(&fte_tmp->node); @@ -1633,19 +1645,6 @@ search_again_locked: return rule; } - /* No group with matching fte found. Try to add a new fte to any - * matching fg. - */ - - if (!take_write) { - list_for_each_entry(iter, match_head, list) - up_read_ref_node(&iter->g->node); - list_for_each_entry(iter, match_head, list) - nested_down_write_ref_node(&iter->g->node, - FS_LOCK_PARENT); - take_write = true; - } - /* Check the ft version, for case that new flow group * was added while the fgs weren't locked */ @@ -1657,27 +1656,30 @@ search_again_locked: /* Check the fgs version, for case the new FTE with the * same values was added while the fgs weren't locked */ - if (version != matched_fgs_get_version(match_head)) + if (version != matched_fgs_get_version(match_head)) { + take_write = true; goto search_again_locked; + } list_for_each_entry(iter, match_head, list) { g = iter->g; if (!g->node.active) continue; + + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + err = insert_fte(g, fte); if (err) { + up_write_ref_node(&g->node); if (err == -ENOSPC) continue; - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); kmem_cache_free(steering->ftes_cache, fte); return ERR_PTR(err); } nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); + up_write_ref_node(&g->node); rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node); @@ -1686,8 +1688,6 @@ search_again_locked: } rule = ERR_PTR(-ENOENT); out: - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); kmem_cache_free(steering->ftes_cache, fte); return rule; } @@ -1726,6 +1726,8 @@ search_again_locked: if (err) { if (take_write) up_write_ref_node(&ft->node); + else + up_read_ref_node(&ft->node); return ERR_PTR(err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index d39b0b7011b2..9f39aeca863f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -331,9 +331,17 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) add_timer(&health->timer); } -void mlx5_stop_health_poll(struct mlx5_core_dev *dev) +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health) { struct mlx5_core_health *health = &dev->priv.health; + unsigned long flags; + + if (disable_health) { + spin_lock_irqsave(&health->wq_lock, flags); + set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock_irqrestore(&health->wq_lock, flags); + } del_timer_sync(&health->timer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index cf3e4a659052..b5e9f664fc66 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -878,8 +878,10 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) priv->numa_node = dev_to_node(&dev->pdev->dev); priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root); - if (!priv->dbg_root) + if (!priv->dbg_root) { + dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n"); return -ENOMEM; + } err = mlx5_pci_enable_device(dev); if (err) { @@ -928,7 +930,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv) pci_clear_master(dev->pdev); release_bar(dev->pdev); mlx5_pci_disable_device(dev); - debugfs_remove(priv->dbg_root); + debugfs_remove_recursive(priv->dbg_root); } static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) @@ -1286,7 +1288,7 @@ err_cleanup_once: mlx5_cleanup_once(dev); err_stop_poll: - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, boot); if (mlx5_cmd_teardown_hca(dev)) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); goto out_err; @@ -1346,7 +1348,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_free_irq_vectors(dev); if (cleanup) mlx5_cleanup_once(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, cleanup); err = mlx5_cmd_teardown_hca(dev); if (err) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); @@ -1608,7 +1610,7 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) * with the HCA, so the health polll is no longer needed. */ mlx5_drain_health_wq(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_force_teardown_hca(dev); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 86478a6b99c5..68e7f8df2a6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -39,9 +39,9 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) return (u32)wq->fbc.sz_m1 + 1; } -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) { - return (u32)wq->fbc.frag_sz_m1 + 1; + return wq->fbc.frag_sz_m1 + 1; } u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) @@ -138,15 +138,16 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { - u32 sq_strides_offset; + u16 sq_strides_offset; + u32 rq_pg_remainder; int err; mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, MLX5_GET(qpc, qpc, log_rq_size), &wq->rq.fbc); - sq_strides_offset = - ((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB; + rq_pg_remainder = mlx5_wq_cyc_get_byte_size(&wq->rq) % PAGE_SIZE; + sq_strides_offset = rq_pg_remainder / MLX5_SEND_WQE_BB; mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB), MLX5_GET(qpc, qpc, log_sq_size), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 2bd4c3184eba..3a1a170bb2d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,7 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 4327487553c5..3589432d1643 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -337,14 +337,14 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = { MLXSW_SP_SB_CM(1500, 9, 0), MLXSW_SP_SB_CM(1500, 9, 0), MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), MLXSW_SP_SB_CM(1, 0xff, 0), }; diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e7dce79ff2c9..001b5f714c1b 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2850,7 +2850,7 @@ 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)); @@ -3016,7 +3016,7 @@ 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) }, @@ -3028,7 +3028,7 @@ 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/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 9044496803e6..46ba0cf257c6 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -52,6 +52,7 @@ #define NFP_FL_TUNNEL_CSUM cpu_to_be16(0x01) #define NFP_FL_TUNNEL_KEY cpu_to_be16(0x04) #define NFP_FL_TUNNEL_GENEVE_OPT cpu_to_be16(0x0800) +#define NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS IP_TUNNEL_INFO_TX #define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS (NFP_FL_TUNNEL_CSUM | \ NFP_FL_TUNNEL_KEY | \ NFP_FL_TUNNEL_GENEVE_OPT) @@ -741,11 +742,16 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, nfp_fl_push_vlan(psh_v, a); *a_len += sizeof(struct nfp_fl_push_vlan); } else if (is_tcf_tunnel_set(a)) { + struct ip_tunnel_info *ip_tun = tcf_tunnel_info(a); struct nfp_repr *repr = netdev_priv(netdev); + *tun_type = nfp_fl_get_tun_from_act_l4_port(repr->app, a); if (*tun_type == NFP_FL_TUNNEL_NONE) return -EOPNOTSUPP; + if (ip_tun->mode & ~NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS) + return -EOPNOTSUPP; + /* Pre-tunnel action is required for tunnel encap. * This checks for next hop entries on NFP. * If none, the packet falls back before applying other actions. diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 85f8209bf007..81d941ab895c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -70,6 +70,7 @@ struct nfp_app; #define NFP_FL_FEATS_GENEVE BIT(0) #define NFP_FL_NBI_MTU_SETTING BIT(1) #define NFP_FL_FEATS_GENEVE_OPT BIT(2) +#define NFP_FL_FEATS_VLAN_PCP BIT(3) #define NFP_FL_FEATS_LAG BIT(31) struct nfp_fl_mask_id { diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index a0c72f277faa..17acb8cc6044 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -56,7 +56,7 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame, FLOW_DISSECTOR_KEY_VLAN, target); /* Populate the tci field. */ - if (flow_vlan->vlan_id) { + if (flow_vlan->vlan_id || flow_vlan->vlan_priority) { tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, flow_vlan->vlan_priority) | FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 2edab01c3beb..bd19624f10cf 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -192,6 +192,17 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, key_size += sizeof(struct nfp_flower_mac_mpls); } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *flow_vlan; + + flow_vlan = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_VLAN, + flow->mask); + if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_PCP) && + flow_vlan->vlan_priority) + return -EOPNOTSUPP; + } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index a8b9fbab5f73..253bdaef1505 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -229,29 +229,16 @@ done: spin_unlock_bh(&nn->reconfig_lock); } -/** - * nfp_net_reconfig() - Reconfigure the firmware - * @nn: NFP Net device to reconfigure - * @update: The value for the update field in the BAR config - * - * Write the update word to the BAR and ping the reconfig queue. The - * poll until the firmware has acknowledged the update by zeroing the - * update word. - * - * Return: Negative errno on error, 0 on success - */ -int nfp_net_reconfig(struct nfp_net *nn, u32 update) +static void nfp_net_reconfig_sync_enter(struct nfp_net *nn) { bool cancelled_timer = false; u32 pre_posted_requests; - int ret; spin_lock_bh(&nn->reconfig_lock); nn->reconfig_sync_present = true; if (nn->reconfig_timer_active) { - del_timer(&nn->reconfig_timer); nn->reconfig_timer_active = false; cancelled_timer = true; } @@ -260,14 +247,43 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update) spin_unlock_bh(&nn->reconfig_lock); - if (cancelled_timer) + if (cancelled_timer) { + del_timer_sync(&nn->reconfig_timer); nfp_net_reconfig_wait(nn, nn->reconfig_timer.expires); + } /* Run the posted reconfigs which were issued before we started */ if (pre_posted_requests) { nfp_net_reconfig_start(nn, pre_posted_requests); nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT); } +} + +static void nfp_net_reconfig_wait_posted(struct nfp_net *nn) +{ + nfp_net_reconfig_sync_enter(nn); + + spin_lock_bh(&nn->reconfig_lock); + nn->reconfig_sync_present = false; + spin_unlock_bh(&nn->reconfig_lock); +} + +/** + * nfp_net_reconfig() - Reconfigure the firmware + * @nn: NFP Net device to reconfigure + * @update: The value for the update field in the BAR config + * + * Write the update word to the BAR and ping the reconfig queue. The + * poll until the firmware has acknowledged the update by zeroing the + * update word. + * + * Return: Negative errno on error, 0 on success + */ +int nfp_net_reconfig(struct nfp_net *nn, u32 update) +{ + int ret; + + nfp_net_reconfig_sync_enter(nn); nfp_net_reconfig_start(nn, update); ret = nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT); @@ -3633,6 +3649,7 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev, */ void nfp_net_free(struct nfp_net *nn) { + WARN_ON(timer_pending(&nn->reconfig_timer) || nn->reconfig_posted); if (nn->dp.netdev) free_netdev(nn->dp.netdev); else @@ -3920,4 +3937,5 @@ void nfp_net_clean(struct nfp_net *nn) return; unregister_netdev(nn->dp.netdev); + nfp_net_reconfig_wait_posted(nn); } diff --git a/drivers/net/ethernet/qualcomm/qca_7k.c b/drivers/net/ethernet/qualcomm/qca_7k.c index ffe7a16bdfc8..6c8543fb90c0 100644 --- a/drivers/net/ethernet/qualcomm/qca_7k.c +++ b/drivers/net/ethernet/qualcomm/qca_7k.c @@ -45,34 +45,33 @@ qcaspi_read_register(struct qcaspi *qca, u16 reg, u16 *result) { __be16 rx_data; __be16 tx_data; - struct spi_transfer *transfer; - struct spi_message *msg; + struct spi_transfer transfer[2]; + struct spi_message msg; int ret; + memset(transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_INTERNAL | reg); + *result = 0; + + transfer[0].tx_buf = &tx_data; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].rx_buf = &rx_data; + transfer[1].len = QCASPI_CMD_LEN; + + spi_message_add_tail(&transfer[0], &msg); if (qca->legacy_mode) { - msg = &qca->spi_msg1; - transfer = &qca->spi_xfer1; - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - spi_sync(qca->spi_dev, msg); - } else { - msg = &qca->spi_msg2; - transfer = &qca->spi_xfer2[0]; - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; + spi_sync(qca->spi_dev, &msg); + spi_message_init(&msg); } - transfer->tx_buf = NULL; - transfer->rx_buf = &rx_data; - transfer->len = QCASPI_CMD_LEN; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); @@ -86,35 +85,32 @@ int qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value) { __be16 tx_data[2]; - struct spi_transfer *transfer; - struct spi_message *msg; + struct spi_transfer transfer[2]; + struct spi_message msg; int ret; + memset(&transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data[0] = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_INTERNAL | reg); tx_data[1] = cpu_to_be16(value); + transfer[0].tx_buf = &tx_data[0]; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].tx_buf = &tx_data[1]; + transfer[1].len = QCASPI_CMD_LEN; + + spi_message_add_tail(&transfer[0], &msg); if (qca->legacy_mode) { - msg = &qca->spi_msg1; - transfer = &qca->spi_xfer1; - transfer->tx_buf = &tx_data[0]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - spi_sync(qca->spi_dev, msg); - } else { - msg = &qca->spi_msg2; - transfer = &qca->spi_xfer2[0]; - transfer->tx_buf = &tx_data[0]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; + spi_sync(qca->spi_dev, &msg); + spi_message_init(&msg); } - transfer->tx_buf = &tx_data[1]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 206f0266463e..66b775d462fd 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -99,22 +99,24 @@ static u32 qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len) { __be16 cmd; - struct spi_message *msg = &qca->spi_msg2; - struct spi_transfer *transfer = &qca->spi_xfer2[0]; + struct spi_message msg; + struct spi_transfer transfer[2]; int ret; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + cmd = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_EXTERNAL); - transfer->tx_buf = &cmd; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; - transfer->tx_buf = src; - transfer->rx_buf = NULL; - transfer->len = len; + transfer[0].tx_buf = &cmd; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].tx_buf = src; + transfer[1].len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[0], &msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) { + if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) { qcaspi_spi_error(qca); return 0; } @@ -125,17 +127,20 @@ qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len) static u32 qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len) { - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; - transfer->tx_buf = src; - transfer->rx_buf = NULL; - transfer->len = len; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + + transfer.tx_buf = src; + transfer.len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer, &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != len)) { + if (ret || (msg.actual_length != len)) { qcaspi_spi_error(qca); return 0; } @@ -146,23 +151,25 @@ qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len) static u32 qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len) { - struct spi_message *msg = &qca->spi_msg2; + struct spi_message msg; __be16 cmd; - struct spi_transfer *transfer = &qca->spi_xfer2[0]; + struct spi_transfer transfer[2]; int ret; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + cmd = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_EXTERNAL); - transfer->tx_buf = &cmd; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; - transfer->tx_buf = NULL; - transfer->rx_buf = dst; - transfer->len = len; + transfer[0].tx_buf = &cmd; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].rx_buf = dst; + transfer[1].len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[0], &msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) { + if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) { qcaspi_spi_error(qca); return 0; } @@ -173,17 +180,20 @@ qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len) static u32 qcaspi_read_legacy(struct qcaspi *qca, u8 *dst, u32 len) { - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; - transfer->tx_buf = NULL; - transfer->rx_buf = dst; - transfer->len = len; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); - ret = spi_sync(qca->spi_dev, msg); + transfer.rx_buf = dst; + transfer.len = len; - if (ret || (msg->actual_length != len)) { + spi_message_add_tail(&transfer, &msg); + ret = spi_sync(qca->spi_dev, &msg); + + if (ret || (msg.actual_length != len)) { qcaspi_spi_error(qca); return 0; } @@ -195,19 +205,23 @@ static int qcaspi_tx_cmd(struct qcaspi *qca, u16 cmd) { __be16 tx_data; - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; + memset(&transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data = cpu_to_be16(cmd); - transfer->len = sizeof(tx_data); - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; + transfer.len = sizeof(cmd); + transfer.tx_buf = &tx_data; + spi_message_add_tail(&transfer, &msg); - ret = spi_sync(qca->spi_dev, msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); @@ -835,16 +849,6 @@ qcaspi_netdev_setup(struct net_device *dev) qca = netdev_priv(dev); memset(qca, 0, sizeof(struct qcaspi)); - memset(&qca->spi_xfer1, 0, sizeof(struct spi_transfer)); - memset(&qca->spi_xfer2, 0, sizeof(struct spi_transfer) * 2); - - spi_message_init(&qca->spi_msg1); - spi_message_add_tail(&qca->spi_xfer1, &qca->spi_msg1); - - spi_message_init(&qca->spi_msg2); - spi_message_add_tail(&qca->spi_xfer2[0], &qca->spi_msg2); - spi_message_add_tail(&qca->spi_xfer2[1], &qca->spi_msg2); - memset(&qca->txr, 0, sizeof(qca->txr)); qca->txr.count = TX_RING_MAX_LEN; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index fc4beb1b32d1..fc0e98726b36 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -83,11 +83,6 @@ struct qcaspi { struct tx_ring txr; struct qcaspi_stats stats; - struct spi_message spi_msg1; - struct spi_message spi_msg2; - struct spi_transfer spi_xfer1; - struct spi_transfer spi_xfer2[2]; - u8 *rx_buffer; u32 buffer_size; u8 sync; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 0efa977c422d..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> @@ -218,6 +219,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8161), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8167), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8168), 0, 0, RTL_CFG_1 }, + { PCI_DEVICE(PCI_VENDOR_ID_NCUBE, 0x8168), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8169), 0, 0, RTL_CFG_0 }, { PCI_VENDOR_ID_DLINK, 0x4300, PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0, RTL_CFG_1 }, @@ -630,7 +632,7 @@ struct rtl8169_tc_offsets { }; enum rtl_flag { - RTL_FLAG_TASK_ENABLED, + RTL_FLAG_TASK_ENABLED = 0, RTL_FLAG_TASK_SLOW_PENDING, RTL_FLAG_TASK_RESET_PENDING, RTL_FLAG_MAX @@ -664,6 +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); @@ -4522,7 +4525,7 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) rtl_hw_reset(tp); } -static void rtl_set_rx_tx_config_registers(struct rtl8169_private *tp) +static void rtl_set_tx_config_registers(struct rtl8169_private *tp) { /* Set DMA burst size and Interframe Gap Time */ RTL_W32(tp, TxConfig, (TX_DMA_BURST << TxDMAShift) | @@ -4633,12 +4636,14 @@ static void rtl_hw_start(struct rtl8169_private *tp) rtl_set_rx_max_size(tp); rtl_set_rx_tx_desc_registers(tp); - rtl_set_rx_tx_config_registers(tp); RTL_W8(tp, Cfg9346, Cfg9346_Lock); /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ RTL_R8(tp, IntrMask); RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); + rtl_init_rxcfg(tp); + rtl_set_tx_config_registers(tp); + rtl_set_rx_mode(tp->dev); /* no early-rx interrupts */ RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); @@ -4772,12 +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) @@ -5622,6 +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); @@ -5630,6 +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) @@ -6652,7 +6662,8 @@ static int rtl8169_close(struct net_device *dev) rtl8169_update_counters(tp); rtl_lock_work(tp); - clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags); + /* Clear all task flags */ + bitmap_zero(tp->wk.flags, RTL_FLAG_MAX); rtl8169_down(dev); rtl_unlock_work(tp); @@ -6835,7 +6846,9 @@ static void rtl8169_net_suspend(struct net_device *dev) rtl_lock_work(tp); napi_disable(&tp->napi); - clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags); + /* Clear all task flags */ + bitmap_zero(tp->wk.flags, RTL_FLAG_MAX); + rtl_unlock_work(tp); rtl_pll_power_down(tp); @@ -7251,6 +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; @@ -7271,6 +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/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index f3f7477043ce..bb0ebdfd4459 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Renesas device configuration # diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile index a05102a7df02..f21ab8c02af0 100644 --- a/drivers/net/ethernet/renesas/Makefile +++ b/drivers/net/ethernet/renesas/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the Renesas device drivers. # diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index eede70ec37f8..0721b5c35d91 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* PTP 1588 clock using the Renesas Ethernet AVB * * Copyright (C) 2013-2015 Renesas Electronics Corporation * Copyright (C) 2015 Renesas Solutions Corp. * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include "ravb.h" diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index ad4433d59237..f27a0dc8c563 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -798,6 +798,41 @@ static struct sh_eth_cpu_data r8a77980_data = { .magic = 1, .cexcr = 1, }; + +/* R7S9210 */ +static struct sh_eth_cpu_data r7s9210_data = { + .soft_reset = sh_eth_soft_reset, + + .set_duplex = sh_eth_set_duplex, + .set_rate = sh_eth_set_rate_rcar, + + .register_type = SH_ETH_REG_FAST_SH4, + + .edtrr_trns = EDTRR_TRNS_ETHER, + .ecsr_value = ECSR_ICD, + .ecsipr_value = ECSIPR_ICDIP, + .eesipr_value = EESIPR_TWBIP | EESIPR_TABTIP | EESIPR_RABTIP | + EESIPR_RFCOFIP | EESIPR_ECIIP | EESIPR_FTCIP | + EESIPR_TDEIP | EESIPR_TFUFIP | EESIPR_FRIP | + EESIPR_RDEIP | EESIPR_RFOFIP | EESIPR_CNDIP | + EESIPR_DLCIP | EESIPR_CDIP | EESIPR_TROIP | + EESIPR_RMAFIP | EESIPR_RRFIP | EESIPR_RTLFIP | + EESIPR_RTSFIP | EESIPR_PREIP | EESIPR_CERFIP, + + .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_TRO, + .eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE | + EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE, + + .fdr_value = 0x0000070f, + + .apr = 1, + .mpr = 1, + .tpauser = 1, + .hw_swap = 1, + .rpadir = 1, + .no_ade = 1, + .xdfar_rw = 1, +}; #endif /* CONFIG_OF */ static void sh_eth_set_rate_sh7724(struct net_device *ndev) @@ -3121,6 +3156,7 @@ static const struct of_device_id sh_eth_match_table[] = { { .compatible = "renesas,ether-r8a7794", .data = &rcar_gen2_data }, { .compatible = "renesas,gether-r8a77980", .data = &r8a77980_data }, { .compatible = "renesas,ether-r7s72100", .data = &r7s72100_data }, + { .compatible = "renesas,ether-r7s9210", .data = &r7s9210_data }, { .compatible = "renesas,rcar-gen1-ether", .data = &rcar_gen1_data }, { .compatible = "renesas,rcar-gen2-ether", .data = &rcar_gen2_data }, { } diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index bf4acebb6bcd..324049eebb9b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -110,7 +110,7 @@ config DWMAC_ROCKCHIP config DWMAC_SOCFPGA tristate "SOCFPGA dwmac support" - default ARCH_SOCFPGA + default (ARCH_SOCFPGA || ARCH_STRATIX10) depends on OF && (ARCH_SOCFPGA || ARCH_STRATIX10 || COMPILE_TEST) select MFD_SYSCON help diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 76649adf8fb0..c0a855b7ab3b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -112,7 +112,6 @@ struct stmmac_priv { u32 tx_count_frames; u32 tx_coal_frames; u32 tx_coal_timer; - bool tx_timer_armed; int tx_coalesce; int hwts_tx_en; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ff1ffb46198a..9f458bb16f2a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3147,16 +3147,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) * element in case of no SG. */ priv->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > priv->tx_count_frames) && - !priv->tx_timer_armed) { + if (likely(priv->tx_coal_frames > priv->tx_count_frames)) { mod_timer(&priv->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer)); - priv->tx_timer_armed = true; } else { priv->tx_count_frames = 0; stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; - priv->tx_timer_armed = false; } skb_tx_timestamp(skb); 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/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index 0c1adad7415d..396e1cd10667 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -170,10 +170,13 @@ void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave) struct device_node *node; struct cpsw_phy_sel_priv *priv; - node = of_get_child_by_name(dev->of_node, "cpsw-phy-sel"); + node = of_parse_phandle(dev->of_node, "cpsw-phy-sel", 0); if (!node) { - dev_err(dev, "Phy mode driver DT not found\n"); - return; + node = of_get_child_by_name(dev->of_node, "cpsw-phy-sel"); + if (!node) { + dev_err(dev, "Phy mode driver DT not found\n"); + return; + } } dev = bus_find_device(&platform_bus_type, NULL, node, match); 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 1121a1ec407c..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; @@ -2206,6 +2214,16 @@ static int netvsc_probe(struct hv_device *dev, memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); + /* We must get rtnl lock before scheduling nvdev->subchan_work, + * otherwise netvsc_subchan_work() can get rtnl lock first and wait + * all subchannels to show up, but that may not happen because + * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer() + * -> ... -> device_add() -> ... -> __device_attach() can't get + * the device lock, so all the subchannels can't be processed -- + * finally netvsc_subchan_work() hangs for ever. + */ + rtnl_lock(); + if (nvdev->num_chn > 1) schedule_work(&nvdev->subchan_work); @@ -2224,7 +2242,6 @@ static int netvsc_probe(struct hv_device *dev, else net->max_mtu = ETH_DATA_LEN; - rtnl_lock(); ret = register_netdevice(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); @@ -2263,17 +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); @@ -2285,7 +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/phy/sfp.c b/drivers/net/phy/sfp.c index 4637d980310e..52fffb98fde9 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -398,7 +398,6 @@ static umode_t sfp_hwmon_is_visible(const void *data, switch (type) { case hwmon_temp: switch (attr) { - case hwmon_temp_input: case hwmon_temp_min_alarm: case hwmon_temp_max_alarm: case hwmon_temp_lcrit_alarm: @@ -407,13 +406,16 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_temp_max: case hwmon_temp_lcrit: case hwmon_temp_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_temp_input: return 0444; default: return 0; } case hwmon_in: switch (attr) { - case hwmon_in_input: case hwmon_in_min_alarm: case hwmon_in_max_alarm: case hwmon_in_lcrit_alarm: @@ -422,13 +424,16 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_in_max: case hwmon_in_lcrit: case hwmon_in_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_in_input: return 0444; default: return 0; } case hwmon_curr: switch (attr) { - case hwmon_curr_input: case hwmon_curr_min_alarm: case hwmon_curr_max_alarm: case hwmon_curr_lcrit_alarm: @@ -437,6 +442,10 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_curr_max: case hwmon_curr_lcrit: case hwmon_curr_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_curr_input: return 0444; default: return 0; @@ -452,7 +461,6 @@ static umode_t sfp_hwmon_is_visible(const void *data, channel == 1) return 0; switch (attr) { - case hwmon_power_input: case hwmon_power_min_alarm: case hwmon_power_max_alarm: case hwmon_power_lcrit_alarm: @@ -461,6 +469,10 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_power_max: case hwmon_power_lcrit: case hwmon_power_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_power_input: return 0444; default: return 0; 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 cb0cc30c3d6a..533b6fb8d923 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -967,6 +967,13 @@ static const struct usb_device_id products[] = { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* Quectel EP06/EG06/EM06 */ + USB_DEVICE_AND_INTERFACE_INFO(0x2c7c, 0x0306, + USB_CLASS_VENDOR_SPEC, + USB_SUBCLASS_VENDOR_SPEC, + 0xff), + .driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr, + }, /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ @@ -1206,13 +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 */ @@ -1255,7 +1262,6 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ - {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ @@ -1331,6 +1337,19 @@ static bool quectel_ec20_detected(struct usb_interface *intf) return false; } +static bool quectel_ep06_diag_detected(struct usb_interface *intf) +{ + struct usb_device *dev = interface_to_usbdev(intf); + struct usb_interface_descriptor intf_desc = intf->cur_altsetting->desc; + + if (le16_to_cpu(dev->descriptor.idVendor) == 0x2c7c && + le16_to_cpu(dev->descriptor.idProduct) == 0x0306 && + intf_desc.bNumEndpoints == 2) + return true; + + return false; +} + static int qmi_wwan_probe(struct usb_interface *intf, const struct usb_device_id *prod) { @@ -1365,6 +1384,15 @@ static int qmi_wwan_probe(struct usb_interface *intf, return -ENODEV; } + /* Quectel EP06/EM06/EG06 supports dynamic interface configuration, so + * we need to match on class/subclass/protocol. These values are + * identical for the diagnostic- and QMI-interface, but bNumEndpoints is + * different. Ignore the current interface if the number of endpoints + * the number for the diag interface (two). + */ + if (quectel_ep06_diag_detected(intf)) + return -ENODEV; + return usbnet_probe(intf, id); } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 8d679c8b7f25..41a00cd76955 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -463,6 +463,8 @@ 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)) { @@ -508,8 +510,6 @@ 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/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index b4c3a957c102..73969dbeb5c5 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -985,15 +985,12 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, const u8 *nvm_chan = cfg->nvm_type == IWL_NVM_EXT ? iwl_ext_nvm_channels : iwl_nvm_channels; struct ieee80211_regdomain *regd, *copy_rd; - int size_of_regd, regd_to_copy, wmms_to_copy; - int size_of_wmms = 0; + int size_of_regd, regd_to_copy; struct ieee80211_reg_rule *rule; - struct ieee80211_wmm_rule *wmm_rule, *d_wmm, *s_wmm; struct regdb_ptrs *regdb_ptrs; enum nl80211_band band; int center_freq, prev_center_freq = 0; - int valid_rules = 0, n_wmms = 0; - int i; + int valid_rules = 0; bool new_rule; int max_num_ch = cfg->nvm_type == IWL_NVM_EXT ? IWL_NVM_NUM_CHANNELS_EXT : IWL_NVM_NUM_CHANNELS; @@ -1012,11 +1009,7 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, sizeof(struct ieee80211_regdomain) + num_of_ch * sizeof(struct ieee80211_reg_rule); - if (geo_info & GEO_WMM_ETSI_5GHZ_INFO) - size_of_wmms = - num_of_ch * sizeof(struct ieee80211_wmm_rule); - - regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL); + regd = kzalloc(size_of_regd, GFP_KERNEL); if (!regd) return ERR_PTR(-ENOMEM); @@ -1030,8 +1023,6 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, regd->alpha2[0] = fw_mcc >> 8; regd->alpha2[1] = fw_mcc & 0xff; - wmm_rule = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd); - for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) { ch_flags = (u16)__le32_to_cpup(channels + ch_idx); band = (ch_idx < NUM_2GHZ_CHANNELS) ? @@ -1085,26 +1076,10 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, band == NL80211_BAND_2GHZ) continue; - if (!reg_query_regdb_wmm(regd->alpha2, center_freq, - ®db_ptrs[n_wmms].token, wmm_rule)) { - /* Add only new rules */ - for (i = 0; i < n_wmms; i++) { - if (regdb_ptrs[i].token == - regdb_ptrs[n_wmms].token) { - rule->wmm_rule = regdb_ptrs[i].rule; - break; - } - } - if (i == n_wmms) { - rule->wmm_rule = wmm_rule; - regdb_ptrs[n_wmms++].rule = wmm_rule; - wmm_rule++; - } - } + reg_query_regdb_wmm(regd->alpha2, center_freq, rule); } regd->n_reg_rules = valid_rules; - regd->n_wmm_rules = n_wmms; /* * Narrow down regdom for unused regulatory rules to prevent hole @@ -1113,28 +1088,13 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, regd_to_copy = sizeof(struct ieee80211_regdomain) + valid_rules * sizeof(struct ieee80211_reg_rule); - wmms_to_copy = sizeof(struct ieee80211_wmm_rule) * n_wmms; - - copy_rd = kzalloc(regd_to_copy + wmms_to_copy, GFP_KERNEL); + copy_rd = kzalloc(regd_to_copy, GFP_KERNEL); if (!copy_rd) { copy_rd = ERR_PTR(-ENOMEM); goto out; } memcpy(copy_rd, regd, regd_to_copy); - memcpy((u8 *)copy_rd + regd_to_copy, (u8 *)regd + size_of_regd, - wmms_to_copy); - - d_wmm = (struct ieee80211_wmm_rule *)((u8 *)copy_rd + regd_to_copy); - s_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd); - - for (i = 0; i < regd->n_reg_rules; i++) { - if (!regd->reg_rules[i].wmm_rule) - continue; - - copy_rd->reg_rules[i].wmm_rule = d_wmm + - (regd->reg_rules[i].wmm_rule - s_wmm); - } out: kfree(regdb_ptrs); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 998dfac0fcff..1068757ec42e 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -34,6 +34,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/rhashtable.h> +#include <linux/nospec.h> #include "mac80211_hwsim.h" #define WARN_QUEUE 100 @@ -2820,9 +2821,6 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_SHORT_GI_160 | IEEE80211_VHT_CAP_TXSTBC | - IEEE80211_VHT_CAP_RXSTBC_1 | - IEEE80211_VHT_CAP_RXSTBC_2 | - IEEE80211_VHT_CAP_RXSTBC_3 | IEEE80211_VHT_CAP_RXSTBC_4 | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; sband->vht_cap.vht_mcs.rx_mcs_map = @@ -3317,6 +3315,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_CHANNELS]) param.channels = nla_get_u32(info->attrs[HWSIM_ATTR_CHANNELS]); + if (param.channels < 1) { + GENL_SET_ERR_MSG(info, "must have at least one channel"); + return -EINVAL; + } + if (param.channels > CFG80211_MAX_NUM_DIFFERENT_CHANNELS) { GENL_SET_ERR_MSG(info, "too many channels specified"); return -EINVAL; @@ -3350,6 +3353,9 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) kfree(hwname); return -EINVAL; } + + idx = array_index_nospec(idx, + ARRAY_SIZE(hwsim_world_regdom_custom)); param.regd = hwsim_world_regdom_custom[idx]; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 73f596a90c69..f17f602e6171 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -87,8 +87,7 @@ struct netfront_cb { /* IRQ name is queue name with "-tx" or "-rx" appended */ #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) -static DECLARE_WAIT_QUEUE_HEAD(module_load_q); -static DECLARE_WAIT_QUEUE_HEAD(module_unload_q); +static DECLARE_WAIT_QUEUE_HEAD(module_wq); struct netfront_stats { u64 packets; @@ -909,7 +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), @@ -1046,6 +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; @@ -1332,11 +1337,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); xenbus_switch_state(dev, XenbusStateInitialising); - wait_event(module_load_q, - xenbus_read_driver_state(dev->otherend) != - XenbusStateClosed && - xenbus_read_driver_state(dev->otherend) != - XenbusStateUnknown); + wait_event(module_wq, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown); return netdev; exit: @@ -2010,15 +2015,14 @@ static void netback_changed(struct xenbus_device *dev, dev_dbg(&dev->dev, "%s\n", xenbus_strstate(backend_state)); + wake_up_all(&module_wq); + switch (backend_state) { case XenbusStateInitialising: case XenbusStateInitialised: case XenbusStateReconfiguring: case XenbusStateReconfigured: - break; - case XenbusStateUnknown: - wake_up_all(&module_unload_q); break; case XenbusStateInitWait: @@ -2034,12 +2038,10 @@ static void netback_changed(struct xenbus_device *dev, break; case XenbusStateClosed: - wake_up_all(&module_unload_q); if (dev->state == XenbusStateClosed) break; /* Missed the backend's CLOSING state -- fallthrough */ case XenbusStateClosing: - wake_up_all(&module_unload_q); xenbus_frontend_closed(dev); break; } @@ -2147,14 +2149,14 @@ static int xennet_remove(struct xenbus_device *dev) if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) { xenbus_switch_state(dev, XenbusStateClosing); - wait_event(module_unload_q, + wait_event(module_wq, xenbus_read_driver_state(dev->otherend) == XenbusStateClosing || xenbus_read_driver_state(dev->otherend) == XenbusStateUnknown); xenbus_switch_state(dev, XenbusStateClosed); - wait_event(module_unload_q, + wait_event(module_wq, xenbus_read_driver_state(dev->otherend) == XenbusStateClosed || xenbus_read_driver_state(dev->otherend) == diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index a21caea1e080..2008fa62a373 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -245,6 +245,10 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req) offset += len; ngrps++; } + for ( ; grpid <= NVMET_MAX_ANAGRPS; grpid++) { + if (nvmet_ana_group_enabled[grpid]) + ngrps++; + } hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt); hdr.ngrps = cpu_to_le16(ngrps); 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/of/platform.c b/drivers/of/platform.c index 7ba90c290a42..6c59673933e9 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -241,6 +241,10 @@ static struct amba_device *of_amba_device_create(struct device_node *node, if (!dev) goto err_clear_flag; + /* AMBA devices only support a single DMA mask */ + dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + dev->dev.dma_mask = &dev->dev.coherent_dma_mask; + /* setup generic device info */ dev->dev.of_node = of_node_get(node); dev->dev.fwnode = &node->fwnode; 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/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c index fb1afe55bf53..8d48371caaa2 100644 --- a/drivers/pinctrl/intel/pinctrl-cannonlake.c +++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c @@ -379,7 +379,7 @@ static const struct intel_padgroup cnlh_community1_gpps[] = { static const struct intel_padgroup cnlh_community3_gpps[] = { CNL_GPP(0, 155, 178, 192), /* GPP_K */ CNL_GPP(1, 179, 202, 224), /* GPP_H */ - CNL_GPP(2, 203, 215, 258), /* GPP_E */ + CNL_GPP(2, 203, 215, 256), /* GPP_E */ CNL_GPP(3, 216, 239, 288), /* GPP_F */ CNL_GPP(4, 240, 248, CNL_NO_GPIO), /* SPI */ }; diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 62b009b27eda..ec8dafc94694 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -747,13 +747,63 @@ static const struct pinctrl_desc intel_pinctrl_desc = { .owner = THIS_MODULE, }; +/** + * intel_gpio_to_pin() - Translate from GPIO offset to pin number + * @pctrl: Pinctrl structure + * @offset: GPIO offset from gpiolib + * @commmunity: Community is filled here if not %NULL + * @padgrp: Pad group is filled here if not %NULL + * + * When coming through gpiolib irqchip, the GPIO offset is not + * automatically translated to pinctrl pin number. This function can be + * used to find out the corresponding pinctrl pin. + */ +static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset, + const struct intel_community **community, + const struct intel_padgroup **padgrp) +{ + int i; + + for (i = 0; i < pctrl->ncommunities; i++) { + const struct intel_community *comm = &pctrl->communities[i]; + int j; + + for (j = 0; j < comm->ngpps; j++) { + const struct intel_padgroup *pgrp = &comm->gpps[j]; + + if (pgrp->gpio_base < 0) + continue; + + if (offset >= pgrp->gpio_base && + offset < pgrp->gpio_base + pgrp->size) { + int pin; + + pin = pgrp->base + offset - pgrp->gpio_base; + if (community) + *community = comm; + if (padgrp) + *padgrp = pgrp; + + return pin; + } + } + } + + return -EINVAL; +} + static int intel_gpio_get(struct gpio_chip *chip, unsigned offset) { struct intel_pinctrl *pctrl = gpiochip_get_data(chip); void __iomem *reg; u32 padcfg0; + int pin; + + pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL); + if (pin < 0) + return -EINVAL; - reg = intel_get_padcfg(pctrl, offset, PADCFG0); + reg = intel_get_padcfg(pctrl, pin, PADCFG0); if (!reg) return -EINVAL; @@ -770,8 +820,13 @@ static void intel_gpio_set(struct gpio_chip *chip, unsigned offset, int value) unsigned long flags; void __iomem *reg; u32 padcfg0; + int pin; + + pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL); + if (pin < 0) + return; - reg = intel_get_padcfg(pctrl, offset, PADCFG0); + reg = intel_get_padcfg(pctrl, pin, PADCFG0); if (!reg) return; @@ -790,8 +845,13 @@ static int intel_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) struct intel_pinctrl *pctrl = gpiochip_get_data(chip); void __iomem *reg; u32 padcfg0; + int pin; - reg = intel_get_padcfg(pctrl, offset, PADCFG0); + pin = intel_gpio_to_pin(pctrl, offset, NULL, NULL); + if (pin < 0) + return -EINVAL; + + reg = intel_get_padcfg(pctrl, pin, PADCFG0); if (!reg) return -EINVAL; @@ -827,51 +887,6 @@ static const struct gpio_chip intel_gpio_chip = { .set_config = gpiochip_generic_config, }; -/** - * intel_gpio_to_pin() - Translate from GPIO offset to pin number - * @pctrl: Pinctrl structure - * @offset: GPIO offset from gpiolib - * @commmunity: Community is filled here if not %NULL - * @padgrp: Pad group is filled here if not %NULL - * - * When coming through gpiolib irqchip, the GPIO offset is not - * automatically translated to pinctrl pin number. This function can be - * used to find out the corresponding pinctrl pin. - */ -static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset, - const struct intel_community **community, - const struct intel_padgroup **padgrp) -{ - int i; - - for (i = 0; i < pctrl->ncommunities; i++) { - const struct intel_community *comm = &pctrl->communities[i]; - int j; - - for (j = 0; j < comm->ngpps; j++) { - const struct intel_padgroup *pgrp = &comm->gpps[j]; - - if (pgrp->gpio_base < 0) - continue; - - if (offset >= pgrp->gpio_base && - offset < pgrp->gpio_base + pgrp->size) { - int pin; - - pin = pgrp->base + offset - pgrp->gpio_base; - if (community) - *community = comm; - if (padgrp) - *padgrp = pgrp; - - return pin; - } - } - } - - return -EINVAL; -} - static int intel_gpio_irq_reqres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); 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/platform/x86/alienware-wmi.c b/drivers/platform/x86/alienware-wmi.c index d975462a4c57..f10af5c383c5 100644 --- a/drivers/platform/x86/alienware-wmi.c +++ b/drivers/platform/x86/alienware-wmi.c @@ -536,6 +536,7 @@ static acpi_status alienware_wmax_command(struct wmax_basic_args *in_args, if (obj && obj->type == ACPI_TYPE_INTEGER) *out_data = (u32) obj->integer.value; } + kfree(output.pointer); return status; } diff --git a/drivers/platform/x86/dell-smbios-wmi.c b/drivers/platform/x86/dell-smbios-wmi.c index 88afe5651d24..cf2229ece9ff 100644 --- a/drivers/platform/x86/dell-smbios-wmi.c +++ b/drivers/platform/x86/dell-smbios-wmi.c @@ -78,6 +78,7 @@ static int run_smbios_call(struct wmi_device *wdev) dev_dbg(&wdev->dev, "result: [%08x,%08x,%08x,%08x]\n", priv->buf->std.output[0], priv->buf->std.output[1], priv->buf->std.output[2], priv->buf->std.output[3]); + kfree(output.pointer); return 0; } 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/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 49f64eb3eab0..de8282420f96 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -25,6 +25,7 @@ #include <linux/netdevice.h> #include <linux/netdev_features.h> #include <linux/skbuff.h> +#include <linux/vmalloc.h> #include <net/iucv/af_iucv.h> #include <net/dsfield.h> @@ -4699,7 +4700,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) priv.buffer_len = oat_data.buffer_len; priv.response_len = 0; - priv.buffer = kzalloc(oat_data.buffer_len, GFP_KERNEL); + priv.buffer = vzalloc(oat_data.buffer_len); if (!priv.buffer) { rc = -ENOMEM; goto out; @@ -4740,7 +4741,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) rc = -EFAULT; out_free: - kfree(priv.buffer); + vfree(priv.buffer); out: return rc; } @@ -5706,6 +5707,8 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->hw_features |= NETIF_F_SG; dev->vlan_features |= NETIF_F_SG; + if (IS_IQD(card)) + dev->features |= NETIF_F_SG; } return dev; @@ -5768,8 +5771,10 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) qeth_update_from_chp_desc(card); card->dev = qeth_alloc_netdev(card); - if (!card->dev) + if (!card->dev) { + rc = -ENOMEM; goto err_card; + } qeth_determine_capabilities(card); enforced_disc = qeth_enforce_discipline(card); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 710fa74892ae..b5e38531733f 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -423,7 +423,7 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, default: dev_kfree_skb_any(skb); QETH_CARD_TEXT(card, 3, "inbunkno"); - QETH_DBF_HEX(CTRL, 3, hdr, QETH_DBF_CTRL_LEN); + QETH_DBF_HEX(CTRL, 3, hdr, sizeof(*hdr)); continue; } work_done++; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 7175086677fb..ada258c01a08 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1390,7 +1390,7 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card, default: dev_kfree_skb_any(skb); QETH_CARD_TEXT(card, 3, "inbunkno"); - QETH_DBF_HEX(CTRL, 3, hdr, QETH_DBF_CTRL_LEN); + QETH_DBF_HEX(CTRL, 3, hdr, sizeof(*hdr)); continue; } work_done++; diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8fc851a9e116..7c097006c54d 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -52,12 +52,12 @@ config SCSI_MQ_DEFAULT default y depends on SCSI ---help--- - This option enables the new blk-mq based I/O path for SCSI - devices by default. With the option the scsi_mod.use_blk_mq - module/boot option defaults to Y, without it to N, but it can - still be overridden either way. + This option enables the blk-mq based I/O path for SCSI devices by + default. With this option the scsi_mod.use_blk_mq module/boot + option defaults to Y, without it to N, but it can still be + overridden either way. - If unsure say N. + If unsure say Y. config SCSI_PROC_FS bool "legacy /proc/scsi/ support" diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 29bf1e60f542..39eb415987fc 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1346,7 +1346,7 @@ struct fib { struct aac_hba_map_info { __le32 rmw_nexus; /* nexus for native HBA devices */ u8 devtype; /* device type */ - u8 reset_state; /* 0 - no reset, 1..x - */ + s8 reset_state; /* 0 - no reset, 1..x - */ /* after xth TM LUN reset */ u16 qd_limit; u32 scan_counter; diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index 23d07e9f87d0..e51923886475 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -1602,6 +1602,46 @@ fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16) } /** + * fwcaps32_to_caps16 - convert 32-bit Port Capabilities to 16-bits + * @caps32: a 32-bit Port Capabilities value + * + * Returns the equivalent 16-bit Port Capabilities value. Note that + * not all 32-bit Port Capabilities can be represented in the 16-bit + * Port Capabilities and some fields/values may not make it. + */ +fw_port_cap16_t fwcaps32_to_caps16(fw_port_cap32_t caps32) +{ + fw_port_cap16_t caps16 = 0; + + #define CAP32_TO_CAP16(__cap) \ + do { \ + if (caps32 & FW_PORT_CAP32_##__cap) \ + caps16 |= FW_PORT_CAP_##__cap; \ + } while (0) + + CAP32_TO_CAP16(SPEED_100M); + CAP32_TO_CAP16(SPEED_1G); + CAP32_TO_CAP16(SPEED_10G); + CAP32_TO_CAP16(SPEED_25G); + CAP32_TO_CAP16(SPEED_40G); + CAP32_TO_CAP16(SPEED_100G); + CAP32_TO_CAP16(FC_RX); + CAP32_TO_CAP16(FC_TX); + CAP32_TO_CAP16(802_3_PAUSE); + CAP32_TO_CAP16(802_3_ASM_DIR); + CAP32_TO_CAP16(ANEG); + CAP32_TO_CAP16(FORCE_PAUSE); + CAP32_TO_CAP16(MDIAUTO); + CAP32_TO_CAP16(MDISTRAIGHT); + CAP32_TO_CAP16(FEC_RS); + CAP32_TO_CAP16(FEC_BASER_RS); + + #undef CAP32_TO_CAP16 + + return caps16; +} + +/** * lstatus_to_fwcap - translate old lstatus to 32-bit Port Capabilities * @lstatus: old FW_PORT_ACTION_GET_PORT_INFO lstatus value * @@ -1759,7 +1799,7 @@ csio_enable_ports(struct csio_hw *hw) val = 1; csio_mb_params(hw, mbp, CSIO_MB_DEFAULT_TMO, - hw->pfn, 0, 1, ¶m, &val, false, + hw->pfn, 0, 1, ¶m, &val, true, NULL); if (csio_mb_issue(hw, mbp)) { @@ -1769,16 +1809,9 @@ csio_enable_ports(struct csio_hw *hw) return -EINVAL; } - csio_mb_process_read_params_rsp(hw, mbp, &retval, 1, - &val); - if (retval != FW_SUCCESS) { - csio_err(hw, "FW_PARAMS_CMD(r) port:%d failed: 0x%x\n", - portid, retval); - mempool_free(mbp, hw->mb_mempool); - return -EINVAL; - } - - fw_caps = val; + csio_mb_process_read_params_rsp(hw, mbp, &retval, + 0, NULL); + fw_caps = retval ? FW_CAPS16 : FW_CAPS32; } /* Read PORT information */ @@ -2364,8 +2397,8 @@ bye: } /* - * Returns -EINVAL if attempts to flash the firmware failed - * else returns 0, + * Returns -EINVAL if attempts to flash the firmware failed, + * -ENOMEM if memory allocation failed else returns 0, * if flashing was not attempted because the card had the * latest firmware ECANCELED is returned */ @@ -2393,6 +2426,13 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset) return -EINVAL; } + /* allocate memory to read the header of the firmware on the + * card + */ + card_fw = kmalloc(sizeof(*card_fw), GFP_KERNEL); + if (!card_fw) + return -ENOMEM; + if (csio_is_t5(pci_dev->device & CSIO_HW_CHIP_MASK)) fw_bin_file = FW_FNAME_T5; else @@ -2406,11 +2446,6 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset) fw_size = fw->size; } - /* allocate memory to read the header of the firmware on the - * card - */ - card_fw = kmalloc(sizeof(*card_fw), GFP_KERNEL); - /* upgrade FW logic */ ret = csio_hw_prep_fw(hw, fw_info, fw_data, fw_size, card_fw, hw->fw_state, reset); diff --git a/drivers/scsi/csiostor/csio_hw.h b/drivers/scsi/csiostor/csio_hw.h index 9e73ef771eb7..e351af6e7c81 100644 --- a/drivers/scsi/csiostor/csio_hw.h +++ b/drivers/scsi/csiostor/csio_hw.h @@ -639,6 +639,7 @@ int csio_handle_intr_status(struct csio_hw *, unsigned int, fw_port_cap32_t fwcap_to_fwspeed(fw_port_cap32_t acaps); fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16); +fw_port_cap16_t fwcaps32_to_caps16(fw_port_cap32_t caps32); fw_port_cap32_t lstatus_to_fwcap(u32 lstatus); int csio_hw_start(struct csio_hw *); diff --git a/drivers/scsi/csiostor/csio_mb.c b/drivers/scsi/csiostor/csio_mb.c index c026417269c3..6f13673d6aa0 100644 --- a/drivers/scsi/csiostor/csio_mb.c +++ b/drivers/scsi/csiostor/csio_mb.c @@ -368,7 +368,7 @@ csio_mb_port(struct csio_hw *hw, struct csio_mb *mbp, uint32_t tmo, FW_CMD_LEN16_V(sizeof(*cmdp) / 16)); if (fw_caps == FW_CAPS16) - cmdp->u.l1cfg.rcap = cpu_to_be32(fc); + cmdp->u.l1cfg.rcap = cpu_to_be32(fwcaps32_to_caps16(fc)); else cmdp->u.l1cfg32.rcap32 = cpu_to_be32(fc); } @@ -395,8 +395,8 @@ csio_mb_process_read_port_rsp(struct csio_hw *hw, struct csio_mb *mbp, *pcaps = fwcaps16_to_caps32(ntohs(rsp->u.info.pcap)); *acaps = fwcaps16_to_caps32(ntohs(rsp->u.info.acap)); } else { - *pcaps = ntohs(rsp->u.info32.pcaps32); - *acaps = ntohs(rsp->u.info32.acaps32); + *pcaps = be32_to_cpu(rsp->u.info32.pcaps32); + *acaps = be32_to_cpu(rsp->u.info32.acaps32); } } } diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index f02dcc875a09..ea4b0bb0c1cd 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -563,35 +563,13 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) } EXPORT_SYMBOL(scsi_host_get); -struct scsi_host_mq_in_flight { - int cnt; -}; - -static void scsi_host_check_in_flight(struct request *rq, void *data, - bool reserved) -{ - struct scsi_host_mq_in_flight *in_flight = data; - - if (blk_mq_request_started(rq)) - in_flight->cnt++; -} - /** * scsi_host_busy - Return the host busy counter * @shost: Pointer to Scsi_Host to inc. **/ int scsi_host_busy(struct Scsi_Host *shost) { - struct scsi_host_mq_in_flight in_flight = { - .cnt = 0, - }; - - if (!shost->use_blk_mq) - return atomic_read(&shost->host_busy); - - blk_mq_tagset_busy_iter(&shost->tag_set, scsi_host_check_in_flight, - &in_flight); - return in_flight.cnt; + return atomic_read(&shost->host_busy); } EXPORT_SYMBOL(scsi_host_busy); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 58bb70b886d7..c120929d4ffe 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -976,7 +976,7 @@ static struct scsi_host_template hpsa_driver_template = { #endif .sdev_attrs = hpsa_sdev_attrs, .shost_attrs = hpsa_shost_attrs, - .max_sectors = 1024, + .max_sectors = 2048, .no_write_same = 1, }; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index e0d0da5f43d6..43732e8d1347 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -672,7 +672,7 @@ struct lpfc_hba { #define LS_NPIV_FAB_SUPPORTED 0x2 /* Fabric supports NPIV */ #define LS_IGNORE_ERATT 0x4 /* intr handler should ignore ERATT */ #define LS_MDS_LINK_DOWN 0x8 /* MDS Diagnostics Link Down */ -#define LS_MDS_LOOPBACK 0x16 /* MDS Diagnostics Link Up (Loopback) */ +#define LS_MDS_LOOPBACK 0x10 /* MDS Diagnostics Link Up (Loopback) */ uint32_t hba_flag; /* hba generic flags */ #define HBA_ERATT_HANDLED 0x1 /* This flag is set when eratt handled */ diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 5a25553415f8..057a60abe664 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -5122,16 +5122,16 @@ LPFC_ATTR_R(enable_SmartSAN, 0, 0, 1, "Enable SmartSAN functionality"); /* # lpfc_fdmi_on: Controls FDMI support. -# 0 No FDMI support (default) -# 1 Traditional FDMI support +# 0 No FDMI support +# 1 Traditional FDMI support (default) # Traditional FDMI support means the driver will assume FDMI-2 support; # however, if that fails, it will fallback to FDMI-1. # If lpfc_enable_SmartSAN is set to 1, the driver ignores lpfc_fdmi_on. # If lpfc_enable_SmartSAN is set 0, the driver uses the current value of # lpfc_fdmi_on. -# Value range [0,1]. Default value is 0. +# Value range [0,1]. Default value is 1. */ -LPFC_ATTR_R(fdmi_on, 0, 0, 1, "Enable FDMI support"); +LPFC_ATTR_R(fdmi_on, 1, 0, 1, "Enable FDMI support"); /* # Specifies the maximum number of ELS cmds we can have outstanding (for diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h index fc3babc15fa3..a6f96b35e971 100644 --- a/drivers/scsi/qedi/qedi.h +++ b/drivers/scsi/qedi/qedi.h @@ -77,6 +77,11 @@ enum qedi_nvm_tgts { QEDI_NVM_TGT_SEC, }; +struct qedi_nvm_iscsi_image { + struct nvm_iscsi_cfg iscsi_cfg; + u32 crc; +}; + struct qedi_uio_ctrl { /* meta data */ u32 uio_hsi_version; @@ -294,7 +299,7 @@ struct qedi_ctx { void *bdq_pbl_list; dma_addr_t bdq_pbl_list_dma; u8 bdq_pbl_list_num_entries; - struct nvm_iscsi_cfg *iscsi_cfg; + struct qedi_nvm_iscsi_image *iscsi_image; dma_addr_t nvm_buf_dma; void __iomem *bdq_primary_prod; void __iomem *bdq_secondary_prod; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index aa96bccb5a96..cc8e64dc65ad 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1346,23 +1346,26 @@ exit_setup_int: static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - if (qedi->iscsi_cfg) + if (qedi->iscsi_image) dma_free_coherent(&qedi->pdev->dev, - sizeof(struct nvm_iscsi_cfg), - qedi->iscsi_cfg, qedi->nvm_buf_dma); + sizeof(struct qedi_nvm_iscsi_image), + qedi->iscsi_image, qedi->nvm_buf_dma); } static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - qedi->iscsi_cfg = dma_zalloc_coherent(&qedi->pdev->dev, - sizeof(struct nvm_iscsi_cfg), - &qedi->nvm_buf_dma, GFP_KERNEL); - if (!qedi->iscsi_cfg) { + struct qedi_nvm_iscsi_image nvm_image; + + qedi->iscsi_image = dma_zalloc_coherent(&qedi->pdev->dev, + sizeof(nvm_image), + &qedi->nvm_buf_dma, + GFP_KERNEL); + if (!qedi->iscsi_image) { QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); return -ENOMEM; } QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, - "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_cfg, + "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_image, qedi->nvm_buf_dma); return 0; @@ -1905,7 +1908,7 @@ qedi_get_nvram_block(struct qedi_ctx *qedi) struct nvm_iscsi_block *block; pf = qedi->dev_info.common.abs_pf_id; - block = &qedi->iscsi_cfg->block[0]; + block = &qedi->iscsi_image->iscsi_cfg.block[0]; for (i = 0; i < NUM_OF_ISCSI_PF_SUPPORTED; i++, block++) { flags = ((block->id) & NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK) >> NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET; @@ -2194,15 +2197,14 @@ static void qedi_boot_release(void *data) static int qedi_get_boot_info(struct qedi_ctx *qedi) { int ret = 1; - u16 len; - - len = sizeof(struct nvm_iscsi_cfg); + struct qedi_nvm_iscsi_image nvm_image; QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Get NVM iSCSI CFG image\n"); ret = qedi_ops->common->nvm_get_image(qedi->cdev, QED_NVM_IMAGE_ISCSI_CFG, - (char *)qedi->iscsi_cfg, len); + (char *)qedi->iscsi_image, + sizeof(nvm_image)); if (ret) QEDI_ERR(&qedi->dbg_ctx, "Could not get NVM image. ret = %d\n", ret); diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index fecf96f0225c..199d3ba1916d 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -374,8 +374,8 @@ struct atio_from_isp { static inline int fcpcmd_is_corrupted(struct atio *atio) { if (atio->entry_type == ATIO_TYPE7 && - (le16_to_cpu(atio->attr_n_length & FCP_CMD_LENGTH_MASK) < - FCP_CMD_LENGTH_MIN)) + ((le16_to_cpu(atio->attr_n_length) & FCP_CMD_LENGTH_MASK) < + FCP_CMD_LENGTH_MIN)) return 1; else return 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0adfb3bce0fd..eb97d2dd3651 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -345,8 +345,7 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost) unsigned long flags; rcu_read_lock(); - if (!shost->use_blk_mq) - atomic_dec(&shost->host_busy); + atomic_dec(&shost->host_busy); if (unlikely(scsi_host_in_recovery(shost))) { spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) @@ -445,12 +444,7 @@ static inline bool scsi_target_is_busy(struct scsi_target *starget) static inline bool scsi_host_is_busy(struct Scsi_Host *shost) { - /* - * blk-mq can handle host queue busy efficiently via host-wide driver - * tag allocation - */ - - if (!shost->use_blk_mq && shost->can_queue > 0 && + if (shost->can_queue > 0 && atomic_read(&shost->host_busy) >= shost->can_queue) return true; if (atomic_read(&shost->host_blocked) > 0) @@ -1606,10 +1600,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q, if (scsi_host_in_recovery(shost)) return 0; - if (!shost->use_blk_mq) - busy = atomic_inc_return(&shost->host_busy) - 1; - else - busy = 0; + busy = atomic_inc_return(&shost->host_busy) - 1; if (atomic_read(&shost->host_blocked) > 0) { if (busy) goto starved; @@ -1625,7 +1616,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q, "unblocking host at zero depth\n")); } - if (!shost->use_blk_mq && shost->can_queue > 0 && busy >= shost->can_queue) + if (shost->can_queue > 0 && busy >= shost->can_queue) goto starved; if (shost->host_self_blocked) goto starved; @@ -1711,9 +1702,7 @@ static void scsi_kill_request(struct request *req, struct request_queue *q) * with the locks as normal issue path does. */ atomic_inc(&sdev->device_busy); - - if (!shost->use_blk_mq) - atomic_inc(&shost->host_busy); + atomic_inc(&shost->host_busy); if (starget->can_queue > 0) atomic_inc(&starget->target_busy); 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/target/iscsi/cxgbit/cxgbit_ddp.c b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c index 768cce0ccb80..76a262674c8d 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c @@ -207,8 +207,8 @@ cxgbit_ddp_reserve(struct cxgbit_sock *csk, struct cxgbi_task_tag_info *ttinfo, ret = dma_map_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE); sgl->offset = sg_offset; if (!ret) { - pr_info("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", - __func__, 0, xferlen, sgcnt); + pr_debug("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", + __func__, 0, xferlen, sgcnt); goto rel_ppods; } @@ -250,8 +250,8 @@ cxgbit_get_r2t_ttt(struct iscsi_conn *conn, struct iscsi_cmd *cmd, ret = cxgbit_ddp_reserve(csk, ttinfo, cmd->se_cmd.data_length); if (ret < 0) { - pr_info("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n", - csk, cmd, cmd->se_cmd.data_length, ttinfo->nents); + pr_debug("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n", + csk, cmd, cmd->se_cmd.data_length, ttinfo->nents); ttinfo->sgl = NULL; ttinfo->nents = 0; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 94bad43c41ff..cc756a123fd8 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1416,7 +1416,8 @@ static void iscsit_do_crypto_hash_buf(struct ahash_request *hash, sg_init_table(sg, ARRAY_SIZE(sg)); sg_set_buf(sg, buf, payload_length); - sg_set_buf(sg + 1, pad_bytes, padding); + if (padding) + sg_set_buf(sg + 1, pad_bytes, padding); ahash_request_set_crypt(hash, sg, data_crc, payload_length + padding); @@ -3910,10 +3911,14 @@ static bool iscsi_target_check_conn_state(struct iscsi_conn *conn) static void iscsit_get_rx_pdu(struct iscsi_conn *conn) { int ret; - u8 buffer[ISCSI_HDR_LEN], opcode; + u8 *buffer, opcode; u32 checksum = 0, digest = 0; struct kvec iov; + buffer = kcalloc(ISCSI_HDR_LEN, sizeof(*buffer), GFP_KERNEL); + if (!buffer) + return; + while (!kthread_should_stop()) { /* * Ensure that both TX and RX per connection kthreads @@ -3921,7 +3926,6 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) */ iscsit_thread_check_cpumask(conn, current, 0); - memset(buffer, 0, ISCSI_HDR_LEN); memset(&iov, 0, sizeof(struct kvec)); iov.iov_base = buffer; @@ -3930,7 +3934,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) ret = rx_data(conn, &iov, 1, ISCSI_HDR_LEN); if (ret != ISCSI_HDR_LEN) { iscsit_rx_thread_wait_for_tcp(conn); - return; + break; } if (conn->conn_ops->HeaderDigest) { @@ -3940,7 +3944,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) ret = rx_data(conn, &iov, 1, ISCSI_CRC_LEN); if (ret != ISCSI_CRC_LEN) { iscsit_rx_thread_wait_for_tcp(conn); - return; + break; } iscsit_do_crypto_hash_buf(conn->conn_rx_hash, buffer, @@ -3964,7 +3968,7 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) } if (conn->conn_state == TARG_CONN_STATE_IN_LOGOUT) - return; + break; opcode = buffer[0] & ISCSI_OPCODE_MASK; @@ -3975,13 +3979,15 @@ static void iscsit_get_rx_pdu(struct iscsi_conn *conn) " while in Discovery Session, rejecting.\n", opcode); iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, buffer); - return; + break; } ret = iscsi_target_rx_opcode(conn, buffer); if (ret < 0) - return; + break; } + + kfree(buffer); } int iscsi_target_rx_thread(void *arg) @@ -4208,22 +4214,15 @@ int iscsit_close_connection( crypto_free_ahash(tfm); } - free_cpumask_var(conn->conn_cpumask); - - kfree(conn->conn_ops); - conn->conn_ops = NULL; - if (conn->sock) sock_release(conn->sock); if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); - iscsit_put_transport(conn->conn_transport); - pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); conn->conn_state = TARG_CONN_STATE_FREE; - kfree(conn); + iscsit_free_conn(conn); spin_lock_bh(&sess->conn_lock); atomic_dec(&sess->nconn); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 9e74f8bc2963..bb90c80ff388 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -67,45 +67,10 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsi_conn *conn) goto out_req_buf; } - conn->conn_ops = kzalloc(sizeof(struct iscsi_conn_ops), GFP_KERNEL); - if (!conn->conn_ops) { - pr_err("Unable to allocate memory for" - " struct iscsi_conn_ops.\n"); - goto out_rsp_buf; - } - - init_waitqueue_head(&conn->queues_wq); - INIT_LIST_HEAD(&conn->conn_list); - INIT_LIST_HEAD(&conn->conn_cmd_list); - INIT_LIST_HEAD(&conn->immed_queue_list); - INIT_LIST_HEAD(&conn->response_queue_list); - init_completion(&conn->conn_post_wait_comp); - init_completion(&conn->conn_wait_comp); - init_completion(&conn->conn_wait_rcfr_comp); - init_completion(&conn->conn_waiting_on_uc_comp); - init_completion(&conn->conn_logout_comp); - init_completion(&conn->rx_half_close_comp); - init_completion(&conn->tx_half_close_comp); - init_completion(&conn->rx_login_comp); - spin_lock_init(&conn->cmd_lock); - spin_lock_init(&conn->conn_usage_lock); - spin_lock_init(&conn->immed_queue_lock); - spin_lock_init(&conn->nopin_timer_lock); - spin_lock_init(&conn->response_queue_lock); - spin_lock_init(&conn->state_lock); - - if (!zalloc_cpumask_var(&conn->conn_cpumask, GFP_KERNEL)) { - pr_err("Unable to allocate conn->conn_cpumask\n"); - goto out_conn_ops; - } conn->conn_login = login; return login; -out_conn_ops: - kfree(conn->conn_ops); -out_rsp_buf: - kfree(login->rsp_buf); out_req_buf: kfree(login->req_buf); out_login: @@ -310,11 +275,9 @@ static int iscsi_login_zero_tsih_s1( return -ENOMEM; } - ret = iscsi_login_set_conn_values(sess, conn, pdu->cid); - if (unlikely(ret)) { - kfree(sess); - return ret; - } + if (iscsi_login_set_conn_values(sess, conn, pdu->cid)) + goto free_sess; + sess->init_task_tag = pdu->itt; memcpy(&sess->isid, pdu->isid, 6); sess->exp_cmd_sn = be32_to_cpu(pdu->cmdsn); @@ -1149,6 +1112,75 @@ iscsit_conn_set_transport(struct iscsi_conn *conn, struct iscsit_transport *t) return 0; } +static struct iscsi_conn *iscsit_alloc_conn(struct iscsi_np *np) +{ + struct iscsi_conn *conn; + + conn = kzalloc(sizeof(struct iscsi_conn), GFP_KERNEL); + if (!conn) { + pr_err("Could not allocate memory for new connection\n"); + return NULL; + } + pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); + conn->conn_state = TARG_CONN_STATE_FREE; + + init_waitqueue_head(&conn->queues_wq); + INIT_LIST_HEAD(&conn->conn_list); + INIT_LIST_HEAD(&conn->conn_cmd_list); + INIT_LIST_HEAD(&conn->immed_queue_list); + INIT_LIST_HEAD(&conn->response_queue_list); + init_completion(&conn->conn_post_wait_comp); + init_completion(&conn->conn_wait_comp); + init_completion(&conn->conn_wait_rcfr_comp); + init_completion(&conn->conn_waiting_on_uc_comp); + init_completion(&conn->conn_logout_comp); + init_completion(&conn->rx_half_close_comp); + init_completion(&conn->tx_half_close_comp); + init_completion(&conn->rx_login_comp); + spin_lock_init(&conn->cmd_lock); + spin_lock_init(&conn->conn_usage_lock); + spin_lock_init(&conn->immed_queue_lock); + spin_lock_init(&conn->nopin_timer_lock); + spin_lock_init(&conn->response_queue_lock); + spin_lock_init(&conn->state_lock); + + timer_setup(&conn->nopin_response_timer, + iscsit_handle_nopin_response_timeout, 0); + timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); + + if (iscsit_conn_set_transport(conn, np->np_transport) < 0) + goto free_conn; + + conn->conn_ops = kzalloc(sizeof(struct iscsi_conn_ops), GFP_KERNEL); + if (!conn->conn_ops) { + pr_err("Unable to allocate memory for struct iscsi_conn_ops.\n"); + goto put_transport; + } + + if (!zalloc_cpumask_var(&conn->conn_cpumask, GFP_KERNEL)) { + pr_err("Unable to allocate conn->conn_cpumask\n"); + goto free_mask; + } + + return conn; + +free_mask: + free_cpumask_var(conn->conn_cpumask); +put_transport: + iscsit_put_transport(conn->conn_transport); +free_conn: + kfree(conn); + return NULL; +} + +void iscsit_free_conn(struct iscsi_conn *conn) +{ + free_cpumask_var(conn->conn_cpumask); + kfree(conn->conn_ops); + iscsit_put_transport(conn->conn_transport); + kfree(conn); +} + void iscsi_target_login_sess_out(struct iscsi_conn *conn, struct iscsi_np *np, bool zero_tsih, bool new_sess) { @@ -1198,10 +1230,6 @@ old_sess_out: crypto_free_ahash(tfm); } - free_cpumask_var(conn->conn_cpumask); - - kfree(conn->conn_ops); - if (conn->param_list) { iscsi_release_param_list(conn->param_list); conn->param_list = NULL; @@ -1219,8 +1247,7 @@ old_sess_out: if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); - iscsit_put_transport(conn->conn_transport); - kfree(conn); + iscsit_free_conn(conn); } static int __iscsi_target_login_thread(struct iscsi_np *np) @@ -1250,31 +1277,16 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) } spin_unlock_bh(&np->np_thread_lock); - conn = kzalloc(sizeof(struct iscsi_conn), GFP_KERNEL); + conn = iscsit_alloc_conn(np); if (!conn) { - pr_err("Could not allocate memory for" - " new connection\n"); /* Get another socket */ return 1; } - pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); - conn->conn_state = TARG_CONN_STATE_FREE; - - timer_setup(&conn->nopin_response_timer, - iscsit_handle_nopin_response_timeout, 0); - timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); - - if (iscsit_conn_set_transport(conn, np->np_transport) < 0) { - kfree(conn); - return 1; - } rc = np->np_transport->iscsit_accept_np(np, conn); if (rc == -ENOSYS) { complete(&np->np_restart_comp); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; + iscsit_free_conn(conn); goto exit; } else if (rc < 0) { spin_lock_bh(&np->np_thread_lock); @@ -1282,17 +1294,13 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; + iscsit_free_conn(conn); /* Get another socket */ return 1; } spin_unlock_bh(&np->np_thread_lock); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; - goto out; + iscsit_free_conn(conn); + return 1; } /* * Perform the remaining iSCSI connection initialization items.. @@ -1442,7 +1450,6 @@ old_sess_out: tpg_np = NULL; } -out: return 1; exit: diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index 74ac3abc44a0..3b8e3639ff5d 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -19,7 +19,7 @@ extern int iscsi_target_setup_login_socket(struct iscsi_np *, extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *); extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *); extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); -extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *); +extern void iscsit_free_conn(struct iscsi_conn *); extern int iscsit_start_kthreads(struct iscsi_conn *); extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *, 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/grant-table.c b/drivers/xen/grant-table.c index 7bafa703a992..84575baceebc 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -1040,18 +1040,33 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, return ret; for (i = 0; i < count; i++) { - /* Retry eagain maps */ - if (map_ops[i].status == GNTST_eagain) - gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i, - &map_ops[i].status, __func__); - - if (map_ops[i].status == GNTST_okay) { + switch (map_ops[i].status) { + case GNTST_okay: + { struct xen_page_foreign *foreign; SetPageForeign(pages[i]); foreign = xen_page_foreign(pages[i]); foreign->domid = map_ops[i].dom; foreign->gref = map_ops[i].ref; + break; + } + + case GNTST_no_device_space: + pr_warn_ratelimited("maptrack limit reached, can't map all guest pages\n"); + break; + + case GNTST_eagain: + /* Retry eagain maps */ + gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, + map_ops + i, + &map_ops[i].status, __func__); + /* Test status in next loop iteration. */ + i--; + break; + + default: + break; } } 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/afs/proc.c b/fs/afs/proc.c index 0c3285c8db95..476dcbb79713 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -98,13 +98,13 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) goto inval; args = strchr(name, ' '); - if (!args) - goto inval; - do { - *args++ = 0; - } while(*args == ' '); - if (!*args) - goto inval; + if (args) { + do { + *args++ = 0; + } while(*args == ' '); + if (!*args) + goto inval; + } /* determine command to perform */ _debug("cmd=%s name=%s args=%s", buf, name, args); @@ -120,7 +120,6 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) if (test_and_set_bit(AFS_CELL_FL_NO_GC, &cell->flags)) afs_put_cell(net, cell); - printk("kAFS: Added new cell '%s'\n", name); } else { goto inval; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 53af9f5253f4..2cddfe7806a4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1280,6 +1280,7 @@ struct btrfs_root { int send_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshotted; + atomic_t snapshot_force_cow; /* For qgroup metadata reserved space */ spinlock_t qgroup_meta_rsv_lock; @@ -3390,9 +3391,9 @@ do { \ #define btrfs_debug(fs_info, fmt, args...) \ btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_in_rcu(fs_info, fmt, args...) \ - btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) + btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \ - btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) + btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_rl(fs_info, fmt, args...) \ btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) #endif @@ -3404,6 +3405,13 @@ do { \ rcu_read_unlock(); \ } while (0) +#define btrfs_no_printk_in_rcu(fs_info, fmt, args...) \ +do { \ + rcu_read_lock(); \ + btrfs_no_printk(fs_info, fmt, ##args); \ + rcu_read_unlock(); \ +} while (0) + #define btrfs_printk_ratelimited(fs_info, fmt, args...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5124c15705ce..05dc3c17cb62 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1187,6 +1187,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, atomic_set(&root->log_batch, 0); refcount_set(&root->refs, 1); atomic_set(&root->will_be_snapshotted, 0); + atomic_set(&root->snapshot_force_cow, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index de6f75f5547b..2d9074295d7f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5800,7 +5800,7 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) * root: the root of the parent directory * rsv: block reservation * items: the number of items that we need do reservation - * qgroup_reserved: used to return the reserved size in qgroup + * use_global_rsv: allow fallback to the global block reservation * * This function is used to reserve the space for snapshot/subvolume * creation and deletion. Those operations are different with the @@ -5810,10 +5810,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) * the space reservation mechanism in start_transaction(). */ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, - struct btrfs_block_rsv *rsv, - int items, + struct btrfs_block_rsv *rsv, int items, bool use_global_rsv) { + u64 qgroup_num_bytes = 0; u64 num_bytes; int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -5821,12 +5821,11 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { /* One for parent inode, two for dir entries */ - num_bytes = 3 * fs_info->nodesize; - ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true); + qgroup_num_bytes = 3 * fs_info->nodesize; + ret = btrfs_qgroup_reserve_meta_prealloc(root, + qgroup_num_bytes, true); if (ret) return ret; - } else { - num_bytes = 0; } num_bytes = btrfs_calc_trans_metadata_size(fs_info, items); @@ -5838,8 +5837,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (ret == -ENOSPC && use_global_rsv) ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1); - if (ret && num_bytes) - btrfs_qgroup_free_meta_prealloc(root, num_bytes); + if (ret && qgroup_num_bytes) + btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9357a19d2bff..3ea5339603cf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1271,7 +1271,7 @@ static noinline int run_delalloc_nocow(struct inode *inode, u64 disk_num_bytes; u64 ram_bytes; int extent_type; - int ret, err; + int ret; int type; int nocow; int check_prev = 1; @@ -1403,11 +1403,8 @@ next_slot: * if there are pending snapshots for this root, * we fall into common COW way. */ - if (!nolock) { - err = btrfs_start_write_no_snapshotting(root); - if (!err) - goto out_check; - } + if (!nolock && atomic_read(&root->snapshot_force_cow)) + goto out_check; /* * force cow if csum exists in the range. * this ensure that csum for a given extent are @@ -1416,9 +1413,6 @@ next_slot: ret = csum_exist_in_range(fs_info, disk_bytenr, num_bytes); if (ret) { - if (!nolock) - btrfs_end_write_no_snapshotting(root); - /* * ret could be -EIO if the above fails to read * metadata. @@ -1431,11 +1425,8 @@ next_slot: WARN_ON_ONCE(nolock); goto out_check; } - if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) { - if (!nolock) - btrfs_end_write_no_snapshotting(root); + if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) goto out_check; - } nocow = 1; } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = found_key.offset + @@ -1448,8 +1439,6 @@ next_slot: out_check: if (extent_end <= start) { path->slots[0]++; - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); goto next_slot; @@ -1471,8 +1460,6 @@ out_check: end, page_started, nr_written, 1, NULL); if (ret) { - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1492,8 +1479,6 @@ out_check: ram_bytes, BTRFS_COMPRESS_NONE, BTRFS_ORDERED_PREALLOC); if (IS_ERR(em)) { - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1532,8 +1517,6 @@ out_check: EXTENT_CLEAR_DATA_RESV, PAGE_UNLOCK | PAGE_SET_PRIVATE2); - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); cur_offset = extent_end; /* @@ -6639,6 +6622,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, drop_inode = 1; } else { struct dentry *parent = dentry->d_parent; + int ret; + err = btrfs_update_inode(trans, root, inode); if (err) goto fail; @@ -6652,7 +6637,12 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, goto fail; } d_instantiate(dentry, inode); - btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent); + ret = btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent, + true, NULL); + if (ret == BTRFS_NEED_TRANS_COMMIT) { + err = btrfs_commit_transaction(trans); + trans = NULL; + } } fail: @@ -9388,14 +9378,21 @@ static int btrfs_rename_exchange(struct inode *old_dir, u64 new_idx = 0; u64 root_objectid; int ret; - int ret2; bool root_log_pinned = false; bool dest_log_pinned = false; + struct btrfs_log_ctx ctx_root; + struct btrfs_log_ctx ctx_dest; + bool sync_log_root = false; + bool sync_log_dest = false; + bool commit_transaction = false; /* we only allow rename subvolume link between subvolumes */ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) return -EXDEV; + btrfs_init_log_ctx(&ctx_root, old_inode); + btrfs_init_log_ctx(&ctx_dest, new_inode); + /* close the race window with snapshot create/destroy ioctl */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) down_read(&fs_info->subvol_sem); @@ -9542,15 +9539,29 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (root_log_pinned) { parent = new_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), - parent); + ret = btrfs_log_new_name(trans, BTRFS_I(old_inode), + BTRFS_I(old_dir), parent, + false, &ctx_root); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log_root = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; btrfs_end_log_trans(root); root_log_pinned = false; } if (dest_log_pinned) { - parent = old_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir), - parent); + if (!commit_transaction) { + parent = old_dentry->d_parent; + ret = btrfs_log_new_name(trans, BTRFS_I(new_inode), + BTRFS_I(new_dir), parent, + false, &ctx_dest); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log_dest = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; + } btrfs_end_log_trans(dest); dest_log_pinned = false; } @@ -9583,8 +9594,26 @@ out_fail: dest_log_pinned = false; } } - ret2 = btrfs_end_transaction(trans); - ret = ret ? ret : ret2; + if (!ret && sync_log_root && !commit_transaction) { + ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, + &ctx_root); + if (ret) + commit_transaction = true; + } + if (!ret && sync_log_dest && !commit_transaction) { + ret = btrfs_sync_log(trans, BTRFS_I(new_inode)->root, + &ctx_dest); + if (ret) + commit_transaction = true; + } + if (commit_transaction) { + ret = btrfs_commit_transaction(trans); + } else { + int ret2; + + ret2 = btrfs_end_transaction(trans); + ret = ret ? ret : ret2; + } out_notrans: if (new_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); @@ -9661,6 +9690,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, int ret; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); bool log_pinned = false; + struct btrfs_log_ctx ctx; + bool sync_log = false; + bool commit_transaction = false; if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9818,8 +9850,15 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (log_pinned) { struct dentry *parent = new_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), - parent); + btrfs_init_log_ctx(&ctx, old_inode); + ret = btrfs_log_new_name(trans, BTRFS_I(old_inode), + BTRFS_I(old_dir), parent, + false, &ctx); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; btrfs_end_log_trans(root); log_pinned = false; } @@ -9856,7 +9895,19 @@ out_fail: btrfs_end_log_trans(root); log_pinned = false; } - btrfs_end_transaction(trans); + if (!ret && sync_log) { + ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, &ctx); + if (ret) + commit_transaction = true; + } + if (commit_transaction) { + ret = btrfs_commit_transaction(trans); + } else { + int ret2; + + ret2 = btrfs_end_transaction(trans); + ret = ret ? ret : ret2; + } out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 63600dc2ac4c..d60b6caf09e8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -747,6 +747,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct btrfs_pending_snapshot *pending_snapshot; struct btrfs_trans_handle *trans; int ret; + bool snapshot_force_cow = false; if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state)) return -EINVAL; @@ -763,6 +764,11 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } + /* + * Force new buffered writes to reserve space even when NOCOW is + * possible. This is to avoid later writeback (running dealloc) to + * fallback to COW mode and unexpectedly fail with ENOSPC. + */ atomic_inc(&root->will_be_snapshotted); smp_mb__after_atomic(); /* wait for no snapshot writes */ @@ -773,6 +779,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) goto dec_and_free; + /* + * All previous writes have started writeback in NOCOW mode, so now + * we force future writes to fallback to COW mode during snapshot + * creation. + */ + atomic_inc(&root->snapshot_force_cow); + snapshot_force_cow = true; + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); btrfs_init_block_rsv(&pending_snapshot->block_rsv, @@ -837,6 +851,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, fail: btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); dec_and_free: + if (snapshot_force_cow) + atomic_dec(&root->snapshot_force_cow); if (atomic_dec_and_test(&root->will_be_snapshotted)) wake_up_var(&root->will_be_snapshotted); free_pending: @@ -3453,6 +3469,25 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, same_lock_start = min_t(u64, loff, dst_loff); same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start; + } else { + /* + * If the source and destination inodes are different, the + * source's range end offset matches the source's i_size, that + * i_size is not a multiple of the sector size, and the + * destination range does not go past the destination's i_size, + * we must round down the length to the nearest sector size + * multiple. If we don't do this adjustment we end replacing + * with zeroes the bytes in the range that starts at the + * deduplication range's end offset and ends at the next sector + * size multiple. + */ + if (loff + olen == i_size_read(src) && + dst_loff + len < i_size_read(dst)) { + const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize; + + len = round_down(i_size_read(src), sz) - loff; + olen = len; + } } again: diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 4353bb69bb86..d4917c0cddf5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1019,10 +1019,9 @@ out_add_root: spin_unlock(&fs_info->qgroup_lock); ret = btrfs_commit_transaction(trans); - if (ret) { - trans = NULL; + trans = NULL; + if (ret) goto out_free_path; - } ret = qgroup_rescan_init(fs_info, 0, 1); if (!ret) { diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 1650dc44a5e3..3c2ae0e4f25a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6025,14 +6025,25 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, * Call this after adding a new name for a file and it will properly * update the log to reflect the new name. * - * It will return zero if all goes well, and it will return 1 if a - * full transaction commit is required. + * @ctx can not be NULL when @sync_log is false, and should be NULL when it's + * true (because it's not used). + * + * Return value depends on whether @sync_log is true or false. + * When true: returns BTRFS_NEED_TRANS_COMMIT if the transaction needs to be + * committed by the caller, and BTRFS_DONT_NEED_TRANS_COMMIT + * otherwise. + * When false: returns BTRFS_DONT_NEED_LOG_SYNC if the caller does not need to + * to sync the log, BTRFS_NEED_LOG_SYNC if it needs to sync the log, + * or BTRFS_NEED_TRANS_COMMIT if the transaction needs to be + * committed (without attempting to sync the log). */ int btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_inode *old_dir, - struct dentry *parent) + struct dentry *parent, + bool sync_log, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = trans->fs_info; + int ret; /* * this will force the logging code to walk the dentry chain @@ -6047,9 +6058,34 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans, */ if (inode->logged_trans <= fs_info->last_trans_committed && (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed)) - return 0; + return sync_log ? BTRFS_DONT_NEED_TRANS_COMMIT : + BTRFS_DONT_NEED_LOG_SYNC; + + if (sync_log) { + struct btrfs_log_ctx ctx2; + + btrfs_init_log_ctx(&ctx2, &inode->vfs_inode); + ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, + LOG_INODE_EXISTS, &ctx2); + if (ret == BTRFS_NO_LOG_SYNC) + return BTRFS_DONT_NEED_TRANS_COMMIT; + else if (ret) + return BTRFS_NEED_TRANS_COMMIT; + + ret = btrfs_sync_log(trans, inode->root, &ctx2); + if (ret) + return BTRFS_NEED_TRANS_COMMIT; + return BTRFS_DONT_NEED_TRANS_COMMIT; + } + + ASSERT(ctx); + ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, + LOG_INODE_EXISTS, ctx); + if (ret == BTRFS_NO_LOG_SYNC) + return BTRFS_DONT_NEED_LOG_SYNC; + else if (ret) + return BTRFS_NEED_TRANS_COMMIT; - return btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, - LOG_INODE_EXISTS, NULL); + return BTRFS_NEED_LOG_SYNC; } diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index 122e68b89a5a..7ab9bb88a639 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -71,8 +71,16 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, int for_rename); void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir); +/* Return values for btrfs_log_new_name() */ +enum { + BTRFS_DONT_NEED_TRANS_COMMIT, + BTRFS_NEED_TRANS_COMMIT, + BTRFS_DONT_NEED_LOG_SYNC, + BTRFS_NEED_LOG_SYNC, +}; int btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_inode *old_dir, - struct dentry *parent); + struct dentry *parent, + bool sync_log, struct btrfs_log_ctx *ctx); #endif diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index da86706123ff..f4405e430da6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4491,7 +4491,12 @@ again: /* Now btrfs_update_device() will change the on-disk size. */ ret = btrfs_update_device(trans, device); - btrfs_end_transaction(trans); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + } else { + ret = btrfs_commit_transaction(trans); + } done: btrfs_free_path(path); if (ret) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 43ca3b763875..eab1359d0553 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -602,6 +602,8 @@ static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg) /* * create a new fs client + * + * Success or not, this function consumes @fsopt and @opt. */ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_options *opt) @@ -609,17 +611,20 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_fs_client *fsc; int page_count; size_t size; - int err = -ENOMEM; + int err; fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); - if (!fsc) - return ERR_PTR(-ENOMEM); + if (!fsc) { + err = -ENOMEM; + goto fail; + } fsc->client = ceph_create_client(opt, fsc); if (IS_ERR(fsc->client)) { err = PTR_ERR(fsc->client); goto fail; } + opt = NULL; /* fsc->client now owns this */ fsc->client->extra_mon_dispatch = extra_mon_dispatch; fsc->client->osdc.abort_on_full = true; @@ -677,6 +682,9 @@ fail_client: ceph_destroy_client(fsc->client); fail: kfree(fsc); + if (opt) + ceph_destroy_options(opt); + destroy_mount_options(fsopt); return ERR_PTR(err); } @@ -1042,8 +1050,6 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, fsc = create_fs_client(fsopt, opt); if (IS_ERR(fsc)) { res = ERR_CAST(fsc); - destroy_mount_options(fsopt); - ceph_destroy_options(opt); goto out_final; } 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/cifs_unicode.c b/fs/cifs/cifs_unicode.c index b380e0871372..a2b2355e7f01 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -105,9 +105,6 @@ convert_sfm_char(const __u16 src_char, char *target) case SFM_LESSTHAN: *target = '<'; break; - case SFM_SLASH: - *target = '\\'; - break; case SFM_SPACE: *target = ' '; break; 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/connect.c b/fs/cifs/connect.c index c832a8a1970a..7aa08dba4719 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2547,7 +2547,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb_vol *volume_info) if (tcon == NULL) return -ENOMEM; - snprintf(unc, sizeof(unc), "\\\\%s\\IPC$", ses->serverName); + snprintf(unc, sizeof(unc), "\\\\%s\\IPC$", ses->server->hostname); /* cannot fail */ nls_codepage = load_nls_default(); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index d32eaa4b2437..6e8765f44508 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -467,6 +467,8 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path, oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_READ; oparms.create_options = CREATE_NOT_DIR; + if (backup_cred(cifs_sb)) + oparms.create_options |= CREATE_OPEN_BACKUP_INTENT; oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; 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/smb2misc.c b/fs/cifs/smb2misc.c index db0453660ff6..6a9c47541c53 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -248,16 +248,20 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) * MacOS server pads after SMB2.1 write response with 3 bytes * of junk. Other servers match RFC1001 len to actual * SMB2/SMB3 frame length (header + smb2 response specific data) - * Some windows servers do too when compounding is used. - * Log the server error (once), but allow it and continue + * Some windows servers also pad up to 8 bytes when compounding. + * If pad is longer than eight bytes, log the server behavior + * (once), since may indicate a problem but allow it and continue * since the frame is parseable. */ if (clc_len < len) { - printk_once(KERN_WARNING - "SMB2 server sent bad RFC1001 len %d not %d\n", - len, clc_len); + pr_warn_once( + "srv rsp padded more than expected. Length %d not %d for cmd:%d mid:%llu\n", + len, clc_len, command, mid); return 0; } + pr_warn_once( + "srv rsp too short, len %d not %d. cmd:%d mid:%llu\n", + len, clc_len, command, mid); return 1; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 247a98e6c856..d954ce36b473 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -630,7 +630,10 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -779,7 +782,10 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_EA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -858,7 +864,10 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_WRITE_EA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -1453,7 +1462,10 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = fid; oparms.reconnect = false; @@ -1857,7 +1869,10 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -3639,7 +3654,7 @@ struct smb_version_values smb21_values = { struct smb_version_values smb3any_values = { .version_string = SMB3ANY_VERSION_STRING, .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3660,7 +3675,7 @@ struct smb_version_values smb3any_values = { struct smb_version_values smbdefault_values = { .version_string = SMBDEFAULT_VERSION_STRING, .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3681,7 +3696,7 @@ struct smb_version_values smbdefault_values = { struct smb_version_values smb30_values = { .version_string = SMB30_VERSION_STRING, .protocol_id = SMB30_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3702,7 +3717,7 @@ struct smb_version_values smb30_values = { struct smb_version_values smb302_values = { .version_string = SMB302_VERSION_STRING, .protocol_id = SMB302_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3723,7 +3738,7 @@ struct smb_version_values smb302_values = { struct smb_version_values smb311_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5740aa809be6..f54d07bda067 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2178,6 +2178,9 @@ SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock, if (!(server->capabilities & SMB2_GLOBAL_CAP_LEASING) || *oplock == SMB2_OPLOCK_LEVEL_NONE) req->RequestedOplockLevel = *oplock; + else if (!(server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) && + (oparms->create_options & CREATE_NOT_FILE)) + req->RequestedOplockLevel = *oplock; /* no srv lease support */ else { rc = add_lease_context(server, iov, &n_iov, oparms->fid->lease_key, oplock); @@ -2456,14 +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; @@ -3574,33 +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/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 03b8ba933eb2..235b959fc2b3 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * alloc.c - NILFS dat/inode allocator * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Koji Sato. * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 05149e606a78..0303c3968cee 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * alloc.h - persistent object (dat entry/disk inode) allocator/deallocator * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Koji Sato. * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 01fb1831ca25..fb5a9a8a13cf 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * bmap.c - NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h index 2b6ffbe5997a..2c63858e81c9 100644 --- a/fs/nilfs2/bmap.h +++ b/fs/nilfs2/bmap.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * bmap.h - NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index dec98cab729d..ebb24a314f43 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * btnode.c - NILFS B-tree node cache * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Seiji Kihara. * Fully revised by Ryusuke Konishi for stabilization and simplification. * diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 4e8aaa1aeb65..0f88dbc9bcb3 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * btnode.h - NILFS B-tree node cache * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Seiji Kihara. * Revised by Ryusuke Konishi. */ diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 16a7a67a11c9..23e043eca237 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * btree.c - NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h index 2184e47fa4bf..d1421b646ce4 100644 --- a/fs/nilfs2/btree.h +++ b/fs/nilfs2/btree.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * btree.h - NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index a15a1601e931..8d41311b5db4 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * cpfile.c - NILFS checkpoint file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h index 6eca972f9673..6336222df24a 100644 --- a/fs/nilfs2/cpfile.h +++ b/fs/nilfs2/cpfile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * cpfile.h - NILFS checkpoint file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index dffedb2f8817..6f4066636be9 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * dat.c - NILFS disk address translation. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dat.h b/fs/nilfs2/dat.h index 57dc6cf466d0..b17ee34580ae 100644 --- a/fs/nilfs2/dat.h +++ b/fs/nilfs2/dat.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * dat.h - NILFS disk address translation. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 582831ab3eb9..81394e22d0a0 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * dir.c - NILFS directory entry operations * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Modified for NILFS by Amagai Yoshiji. */ /* diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 96e3ed0d9652..533e24ea3a88 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * direct.c - NILFS direct block pointer. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/direct.h b/fs/nilfs2/direct.h index cfe85e848bba..ec9a23c77994 100644 --- a/fs/nilfs2/direct.h +++ b/fs/nilfs2/direct.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * direct.h - NILFS direct block pointer. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 7da0fac71dc2..64bc81363c6c 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * file.c - NILFS regular file handling primitives including fsync(). * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji and Ryusuke Konishi. */ diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 853a831dcde0..aa3c328ee189 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * gcinode.c - dummy inodes to buffer blocks for garbage collection * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Seiji Kihara, Amagai Yoshiji, and Ryusuke Konishi. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index b8fa45c20c63..4140d232cadc 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * ifile.c - NILFS inode file * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h index 188b94fe0ec5..a1e1e5711a05 100644 --- a/fs/nilfs2/ifile.h +++ b/fs/nilfs2/ifile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * ifile.h - NILFS inode file * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6a612d832e7d..671085512e0f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * inode.c - NILFS inode operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 1d2c3d7711fe..9b96d79eea6c 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * ioctl.c - NILFS ioctl operations. * * Copyright (C) 2007, 2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index c6bc1033e7d2..700870a92bc4 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * mdt.c - meta data file for NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index 3f67f3932097..e77aea4bb921 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * mdt.h - NILFS meta data file prototype and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index dd52d3f82e8d..9fe6d4ab74f0 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * namei.c - NILFS pathname lookup operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Modified for NILFS by Amagai Yoshiji and Ryusuke Konishi. */ /* diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 33f8c8fc96e8..a2f247b6a209 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * nilfs.h - NILFS local header file. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato and Ryusuke Konishi. */ diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 4cb850a6f1c2..329a056b73b1 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * page.c - buffer/page management specific to NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi and Seiji Kihara. */ diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index f3687c958fa8..62b9bb469e92 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * page.h - buffer/page management specific to NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi and Seiji Kihara. */ diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 5139efed1888..140b663e91c7 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * recovery.c - NILFS recovery logic * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 68cb9e4740b4..20c479b5e41b 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * segbuf.c - NILFS segment buffer * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segbuf.h b/fs/nilfs2/segbuf.h index 10e16935fff6..9bea1bd59041 100644 --- a/fs/nilfs2/segbuf.h +++ b/fs/nilfs2/segbuf.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * segbuf.h - NILFS Segment buffer prototypes and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0953635e7d48..445eef41bfaf 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * segment.c - NILFS segment constructor. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 04634e3e3d58..f5cf5308f3fc 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * segment.h - NILFS Segment constructor prototypes and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index c7fa139d50e8..bf3f8f05c89b 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * sufile.c - NILFS segment usage file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. * Revised by Ryusuke Konishi. */ diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index 673a891350f4..c4e2c7a7add1 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * sufile.h - NILFS segment usage file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1b9067cf4511..26290aa1023f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * super.c - NILFS module and super block management. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ /* diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 4b25837e7724..e60be7bb55b0 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1,19 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * sysfs.c - sysfs support implementation. * * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation. * Copyright (C) 2014 HGST, Inc., a Western Digital Company. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com> */ diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h index 648cedf9c06e..d001eb862dae 100644 --- a/fs/nilfs2/sysfs.h +++ b/fs/nilfs2/sysfs.h @@ -1,19 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * sysfs.h - sysfs support declarations. * * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation. * Copyright (C) 2014 HGST, Inc., a Western Digital Company. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com> */ diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 1a85317e83f0..484785cdf96e 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * the_nilfs.c - the_nilfs shared structure. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 36da1779f976..380a543c5b19 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * the_nilfs.h - the_nilfs shared structure. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index f174397b63a0..ababdbfab537 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -351,16 +351,9 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); - if ((mask & FS_MODIFY) || - (test_mask & to_tell->i_fsnotify_mask)) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = - fsnotify_first_mark(&to_tell->i_fsnotify_marks); - } - - if (mnt && ((mask & FS_MODIFY) || - (test_mask & mnt->mnt_fsnotify_mask))) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = - fsnotify_first_mark(&to_tell->i_fsnotify_marks); + iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = + fsnotify_first_mark(&to_tell->i_fsnotify_marks); + if (mnt) { iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index d9ebe11c8990..1d098c3c00e0 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -342,6 +342,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, * for this bh as it's not marked locally * uptodate. */ status = -EIO; + clear_buffer_needs_validate(bh); put_bh(bh); bhs[i] = NULL; continue; 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/proc/kcore.c b/fs/proc/kcore.c index ad72261ee3fe..d297fe4472a9 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -464,6 +464,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) ret = -EFAULT; goto out; } + m = NULL; /* skip the list anchor */ } else if (m->type == KCORE_VMALLOC) { vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ 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/fs/ubifs/super.c b/fs/ubifs/super.c index 23e7042666a7..bf000c8aeffb 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1912,7 +1912,9 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) mutex_unlock(&c->bu_mutex); } - ubifs_assert(c, c->lst.taken_empty_lebs > 0); + if (!c->need_recovery) + ubifs_assert(c, c->lst.taken_empty_lebs > 0); + return 0; } @@ -1954,6 +1956,9 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode) int dev, vol; char *endptr; + if (!name || !*name) + return ERR_PTR(-EINVAL); + /* First, try to open using the device node path method */ ubi = ubi_open_volume_path(name, mode); if (!IS_ERR(ubi)) diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 61afdfee4b28..f5ad1ede7990 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -152,12 +152,6 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, ui->data_len = size; mutex_lock(&host_ui->ui_mutex); - - if (!host->i_nlink) { - err = -ENOENT; - goto out_noent; - } - host->i_ctime = current_time(host); host_ui->xattr_cnt += 1; host_ui->xattr_size += CALC_DENT_SIZE(fname_len(nm)); @@ -190,7 +184,6 @@ out_cancel: host_ui->xattr_size -= CALC_XATTR_BYTES(size); host_ui->xattr_names -= fname_len(nm); host_ui->flags &= ~UBIFS_CRYPT_FL; -out_noent: mutex_unlock(&host_ui->ui_mutex); out_free: make_bad_inode(inode); @@ -242,12 +235,6 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, mutex_unlock(&ui->ui_mutex); mutex_lock(&host_ui->ui_mutex); - - if (!host->i_nlink) { - err = -ENOENT; - goto out_noent; - } - host->i_ctime = current_time(host); host_ui->xattr_size -= CALC_XATTR_BYTES(old_size); host_ui->xattr_size += CALC_XATTR_BYTES(size); @@ -269,7 +256,6 @@ static int change_xattr(struct ubifs_info *c, struct inode *host, out_cancel: host_ui->xattr_size -= CALC_XATTR_BYTES(size); host_ui->xattr_size += CALC_XATTR_BYTES(old_size); -out_noent: mutex_unlock(&host_ui->ui_mutex); make_bad_inode(inode); out_free: @@ -496,12 +482,6 @@ static int remove_xattr(struct ubifs_info *c, struct inode *host, return err; mutex_lock(&host_ui->ui_mutex); - - if (!host->i_nlink) { - err = -ENOENT; - goto out_noent; - } - host->i_ctime = current_time(host); host_ui->xattr_cnt -= 1; host_ui->xattr_size -= CALC_DENT_SIZE(fname_len(nm)); @@ -521,7 +501,6 @@ out_cancel: host_ui->xattr_size += CALC_DENT_SIZE(fname_len(nm)); host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len); host_ui->xattr_names += fname_len(nm); -out_noent: mutex_unlock(&host_ui->ui_mutex); ubifs_release_budget(c, &req); make_bad_inode(inode); @@ -561,9 +540,6 @@ static int ubifs_xattr_remove(struct inode *host, const char *name) ubifs_assert(c, inode_is_locked(host)); - if (!host->i_nlink) - return -ENOENT; - if (fname_len(&nm) > UBIFS_MAX_NLEN) return -ENAMETOOLONG; 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/drm/drm_drv.h b/include/drm/drm_drv.h index 8830e3de3a86..3199ef70c007 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -674,7 +674,7 @@ static inline bool drm_core_check_feature(struct drm_device *dev, u32 feature) static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev) { return drm_core_check_feature(dev, DRIVER_ATOMIC) || - dev->mode_config.funcs->atomic_commit != NULL; + (dev->mode_config.funcs && dev->mode_config.funcs->atomic_commit != NULL); } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 34aec30e06c7..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -56,6 +56,7 @@ struct blkcg { struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; + refcount_t cgwb_refcnt; #endif }; @@ -89,7 +90,6 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; - bool offline; }; /* @@ -387,6 +387,49 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) return cpd ? cpd->blkcg : NULL; } +extern void blkcg_destroy_blkgs(struct blkcg *blkcg); + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * blkcg_cgwb_get - get a reference for blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + */ +static inline void blkcg_cgwb_get(struct blkcg *blkcg) +{ + refcount_inc(&blkcg->cgwb_refcnt); +} + +/** + * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + * When this count goes to zero, all active wb has finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. + */ +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + if (refcount_dec_and_test(&blkcg->cgwb_refcnt)) + blkcg_destroy_blkgs(blkcg); +} + +#else + +static inline void blkcg_cgwb_get(struct blkcg *blkcg) { } + +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + /* wb isn't being accounted, so trigger destruction right away */ + blkcg_destroy_blkgs(blkcg); +} + +#endif + /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest 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/compiler-gcc.h b/include/linux/compiler-gcc.h index 763bbad1e258..4d36b27214fd 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -79,20 +79,6 @@ #define __noretpoline __attribute__((indirect_branch("keep"))) #endif -/* - * it doesn't make sense on ARM (currently the only user of __naked) - * to trace naked functions because then mcount is called without - * stack and frame pointer being set up and there is no chance to - * restore the lr register to the value before mcount was called. - * - * The asm() bodies of naked functions often depend on standard calling - * conventions, therefore they must be noinline and noclone. - * - * GCC 4.[56] currently fail to enforce this, so we must do so ourselves. - * See GCC PR44290. - */ -#define __naked __attribute__((naked)) noinline __noclone notrace - #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) #define __optimize(level) __attribute__((__optimize__(level))) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3525c179698c..db192becfec4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -226,6 +226,14 @@ struct ftrace_likely_data { #define notrace __attribute__((no_instrument_function)) #endif +/* + * it doesn't make sense on ARM (currently the only user of __naked) + * to trace naked functions because then mcount is called without + * stack and frame pointer being set up and there is no chance to + * restore the lr register to the value before mcount was called. + */ +#define __naked __attribute__((naked)) notrace + #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) /* 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/genhd.h b/include/linux/genhd.h index 57864422a2c8..25c08c6c7f99 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -83,10 +83,10 @@ struct partition { } __attribute__((packed)); struct disk_stats { + u64 nsecs[NR_STAT_GROUPS]; unsigned long sectors[NR_STAT_GROUPS]; unsigned long ios[NR_STAT_GROUPS]; unsigned long merges[NR_STAT_GROUPS]; - unsigned long ticks[NR_STAT_GROUPS]; unsigned long io_ticks; unsigned long time_in_queue; }; @@ -354,6 +354,9 @@ static inline void free_part_stats(struct hd_struct *part) #endif /* CONFIG_SMP */ +#define part_stat_read_msecs(part, which) \ + div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC) + #define part_stat_read_accum(part, field) \ (part_stat_read(part, field[STAT_READ]) + \ part_stat_read(part, field[STAT_WRITE]) + \ diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..d44a78362942 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,6 +526,7 @@ struct hid_input { const char *name; bool registered; struct list_head reports; /* the list of reports */ + unsigned int application; /* application usage for this input */ }; enum hid_type { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0205aee44ded..c926698040e0 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -733,8 +733,6 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); diff --git a/include/linux/mfd/da9063/pdata.h b/include/linux/mfd/da9063/pdata.h index 8a125701ef7b..50bed4f89c1a 100644 --- a/include/linux/mfd/da9063/pdata.h +++ b/include/linux/mfd/da9063/pdata.h @@ -21,7 +21,7 @@ /* * Regulator configuration */ -/* DA9063 regulator IDs */ +/* DA9063 and DA9063L regulator IDs */ enum { /* BUCKs */ DA9063_ID_BCORE1, @@ -37,18 +37,20 @@ enum { DA9063_ID_BMEM_BIO_MERGED, /* When two BUCKs are merged, they cannot be reused separately */ - /* LDOs */ + /* LDOs on both DA9063 and DA9063L */ + DA9063_ID_LDO3, + DA9063_ID_LDO7, + DA9063_ID_LDO8, + DA9063_ID_LDO9, + DA9063_ID_LDO11, + + /* DA9063-only LDOs */ DA9063_ID_LDO1, DA9063_ID_LDO2, - DA9063_ID_LDO3, DA9063_ID_LDO4, DA9063_ID_LDO5, DA9063_ID_LDO6, - DA9063_ID_LDO7, - DA9063_ID_LDO8, - DA9063_ID_LDO9, DA9063_ID_LDO10, - DA9063_ID_LDO11, }; /* Regulators platform data */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..66d94b4557cf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -362,8 +362,8 @@ struct mlx5_frag_buf { struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; - u32 frag_sz_m1; - u32 strides_offset; + u16 frag_sz_m1; + u16 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -995,7 +995,7 @@ static inline u32 mlx5_base_mkey(const u32 key) } static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, - u32 strides_offset, + u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; @@ -1052,7 +1052,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -void mlx5_stop_health_poll(struct mlx5_core_dev *dev); +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); 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/pci_ids.h b/include/linux/pci_ids.h index 99d366cb0e9f..d157983b84cf 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3084,4 +3084,6 @@ #define PCI_VENDOR_ID_OCZ 0x1b85 +#define PCI_VENDOR_ID_NCUBE 0x10ff + #endif /* _LINUX_PCI_IDS_H */ diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..a5a3cfc3c2fa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -258,8 +258,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, - struct timespec64 *boot_offset); +void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 7f2e16e76ac4..041f7e56a289 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -158,8 +158,10 @@ extern void syscall_unregfunc(void); * For rcuidle callers, use srcu since sched-rcu \ * doesn't work from the idle path. \ */ \ - if (rcuidle) \ + if (rcuidle) { \ idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + rcu_irq_enter_irqson(); \ + } \ \ it_func_ptr = rcu_dereference_raw((tp)->funcs); \ \ @@ -171,8 +173,10 @@ extern void syscall_unregfunc(void); } while ((++it_func_ptr)->func); \ } \ \ - if (rcuidle) \ + if (rcuidle) { \ + rcu_irq_exit_irqson(); \ srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + } \ \ preempt_enable_notrace(); \ } while (0) diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index a34539b7f750..7e6ac0114d55 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -133,15 +133,18 @@ struct vga_switcheroo_handler { * @can_switch: check if the device is in a position to switch now. * Mandatory. The client should return false if a user space process * has one of its device files open + * @gpu_bound: notify the client id to audio client when the GPU is bound. * * Client callbacks. A client can be either a GPU or an audio device on a GPU. * The @set_gpu_state and @can_switch methods are mandatory, @reprobe may be * set to NULL. For audio clients, the @reprobe member is bogus. + * OTOH, @gpu_bound is only for audio clients, and not used for GPU clients. */ struct vga_switcheroo_client_ops { void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state); void (*reprobe)(struct pci_dev *dev); bool (*can_switch)(struct pci_dev *dev); + void (*gpu_bound)(struct pci_dev *dev, enum vga_switcheroo_client_id); }; #if defined(CONFIG_VGA_SWITCHEROO) 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/cfg80211.h b/include/net/cfg80211.h index 9a850973e09a..8ebabc9873d1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4865,8 +4865,8 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); * * Return: 0 on success. -ENODATA. */ -int reg_query_regdb_wmm(char *alpha2, int freq, u32 *ptr, - struct ieee80211_wmm_rule *rule); +int reg_query_regdb_wmm(char *alpha2, int freq, + struct ieee80211_reg_rule *rule); /* * callbacks for asynchronous cfg80211 methods, notification diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index d5f62cc6c2ae..3394d75e1c80 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -30,7 +30,7 @@ struct nf_conn_timeout { }; static inline unsigned int * -nf_ct_timeout_data(struct nf_conn_timeout *t) +nf_ct_timeout_data(const struct nf_conn_timeout *t) { struct nf_ct_timeout *timeout; diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 60f8cc86a447..3469750df0f4 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -217,15 +217,15 @@ struct ieee80211_wmm_rule { struct ieee80211_reg_rule { struct ieee80211_freq_range freq_range; struct ieee80211_power_rule power_rule; - struct ieee80211_wmm_rule *wmm_rule; + struct ieee80211_wmm_rule wmm_rule; u32 flags; u32 dfs_cac_ms; + bool has_wmm; }; struct ieee80211_regdomain { struct rcu_head rcu_head; u32 n_reg_rules; - u32 n_wmm_rules; char alpha2[3]; enum nl80211_dfs_regions dfs_region; struct ieee80211_reg_rule reg_rules[]; diff --git a/include/net/tls.h b/include/net/tls.h index d5c683e8bb22..0a769cf2f5f3 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -171,15 +171,14 @@ 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; @@ -367,8 +366,8 @@ 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/sound/hdaudio.h b/include/sound/hdaudio.h index 6f1e1f3b3063..cd1773d0e08f 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -412,6 +412,7 @@ void snd_hdac_bus_init_cmd_io(struct hdac_bus *bus); void snd_hdac_bus_stop_cmd_io(struct hdac_bus *bus); void snd_hdac_bus_enter_link_reset(struct hdac_bus *bus); void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus); +int snd_hdac_bus_reset_link(struct hdac_bus *bus, bool full_reset); void snd_hdac_bus_update_rirb(struct hdac_bus *bus); int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index af9ef16cc34d..fdaaafdc7a00 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -407,6 +407,7 @@ int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm, int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card); void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card); int snd_soc_dapm_new_pcm(struct snd_soc_card *card, + struct snd_soc_pcm_runtime *rtd, const struct snd_soc_pcm_stream *params, unsigned int num_params, struct snd_soc_dapm_widget *source, diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index 7b8c9e19bad1..910cc4334b21 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -65,7 +65,7 @@ /* keyctl structures */ struct keyctl_dh_params { - __s32 private; + __s32 dh_private; __s32 prime; __s32 base; }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 07548de5c988..251be353f950 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -952,6 +952,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_HPAGE_1M 156 #define KVM_CAP_NESTED_STATE 157 #define KVM_CAP_ARM_INJECT_SERROR_ESR 158 +#define KVM_CAP_MSR_PLATFORM_INFO 159 #ifdef KVM_CAP_IRQ_ROUTING 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/uapi/linux/rds.h b/include/uapi/linux/rds.h index dc520e1a4123..8b73cb603c5f 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -37,6 +37,7 @@ #include <linux/types.h> #include <linux/socket.h> /* For __kernel_sockaddr_storage. */ +#include <linux/in6.h> /* For struct in6_addr. */ #define RDS_IB_ABI_VERSION 0x301 diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index b1e22c40c4b6..84c3de89696a 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -176,7 +176,7 @@ struct vhost_memory { #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) -#define VHOST_GET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x26, __u64) +#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) /* VHOST_NET specific defines */ diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index f58cafa42f18..f39352cef382 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -10,6 +10,8 @@ #ifndef __HDA_TPLG_INTERFACE_H__ #define __HDA_TPLG_INTERFACE_H__ +#include <linux/types.h> + /* * Default types range from 0~12. type can range from 0 to 0xff * SST types start at higher to avoid any overlapping in future @@ -143,10 +145,10 @@ enum skl_module_param_type { }; struct skl_dfw_algo_data { - u32 set_params:2; - u32 rsvd:30; - u32 param_id; - u32 max; + __u32 set_params:2; + __u32 rsvd:30; + __u32 param_id; + __u32 max; char params[0]; } __packed; @@ -163,68 +165,68 @@ enum skl_tuple_type { /* v4 configuration data */ struct skl_dfw_v4_module_pin { - u16 module_id; - u16 instance_id; + __u16 module_id; + __u16 instance_id; } __packed; struct skl_dfw_v4_module_fmt { - u32 channels; - u32 freq; - u32 bit_depth; - u32 valid_bit_depth; - u32 ch_cfg; - u32 interleaving_style; - u32 sample_type; - u32 ch_map; + __u32 channels; + __u32 freq; + __u32 bit_depth; + __u32 valid_bit_depth; + __u32 ch_cfg; + __u32 interleaving_style; + __u32 sample_type; + __u32 ch_map; } __packed; struct skl_dfw_v4_module_caps { - u32 set_params:2; - u32 rsvd:30; - u32 param_id; - u32 caps_size; - u32 caps[HDA_SST_CFG_MAX]; + __u32 set_params:2; + __u32 rsvd:30; + __u32 param_id; + __u32 caps_size; + __u32 caps[HDA_SST_CFG_MAX]; } __packed; struct skl_dfw_v4_pipe { - u8 pipe_id; - u8 pipe_priority; - u16 conn_type:4; - u16 rsvd:4; - u16 memory_pages:8; + __u8 pipe_id; + __u8 pipe_priority; + __u16 conn_type:4; + __u16 rsvd:4; + __u16 memory_pages:8; } __packed; struct skl_dfw_v4_module { char uuid[SKL_UUID_STR_SZ]; - u16 module_id; - u16 instance_id; - u32 max_mcps; - u32 mem_pages; - u32 obs; - u32 ibs; - u32 vbus_id; - - u32 max_in_queue:8; - u32 max_out_queue:8; - u32 time_slot:8; - u32 core_id:4; - u32 rsvd1:4; - - u32 module_type:8; - u32 conn_type:4; - u32 dev_type:4; - u32 hw_conn_type:4; - u32 rsvd2:12; - - u32 params_fixup:8; - u32 converter:8; - u32 input_pin_type:1; - u32 output_pin_type:1; - u32 is_dynamic_in_pin:1; - u32 is_dynamic_out_pin:1; - u32 is_loadable:1; - u32 rsvd3:11; + __u16 module_id; + __u16 instance_id; + __u32 max_mcps; + __u32 mem_pages; + __u32 obs; + __u32 ibs; + __u32 vbus_id; + + __u32 max_in_queue:8; + __u32 max_out_queue:8; + __u32 time_slot:8; + __u32 core_id:4; + __u32 rsvd1:4; + + __u32 module_type:8; + __u32 conn_type:4; + __u32 dev_type:4; + __u32 hw_conn_type:4; + __u32 rsvd2:12; + + __u32 params_fixup:8; + __u32 converter:8; + __u32 input_pin_type:1; + __u32 output_pin_type:1; + __u32 is_dynamic_in_pin:1; + __u32 is_dynamic_out_pin:1; + __u32 is_loadable:1; + __u32 rsvd3:11; struct skl_dfw_v4_pipe pipe; struct skl_dfw_v4_module_fmt in_fmt[MAX_IN_QUEUE]; 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/ipc/shm.c b/ipc/shm.c index b0eb3757ab89..4cd402e4cfeb 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -199,6 +199,7 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) } ipc_unlock_object(ipcp); + ipcp = ERR_PTR(-EIDRM); err: rcu_read_unlock(); /* 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/sockmap.c b/kernel/bpf/sockmap.c index cf5195c7c331..488ef9663c01 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -236,7 +236,7 @@ static int bpf_tcp_init(struct sock *sk) } static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md); +static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge); static void bpf_tcp_release(struct sock *sk) { @@ -248,7 +248,7 @@ static void bpf_tcp_release(struct sock *sk) goto out; if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); psock->cork = NULL; } @@ -330,14 +330,14 @@ static void bpf_tcp_close(struct sock *sk, long timeout) close_fun = psock->save_close; if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); psock->cork = NULL; } list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { list_del(&md->list); - free_start_sg(psock->sock, md); + free_start_sg(psock->sock, md, true); kfree(md); } @@ -369,7 +369,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout) /* If another thread deleted this object skip deletion. * The refcnt on psock may or may not be zero. */ - if (l) { + if (l && l == link) { hlist_del_rcu(&link->hash_node); smap_release_sock(psock, link->sk); free_htab_elem(htab, link); @@ -570,14 +570,16 @@ static void free_bytes_sg(struct sock *sk, int bytes, md->sg_start = i; } -static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) +static int free_sg(struct sock *sk, int start, + struct sk_msg_buff *md, bool charge) { struct scatterlist *sg = md->sg_data; int i = start, free = 0; while (sg[i].length) { free += sg[i].length; - sk_mem_uncharge(sk, sg[i].length); + if (charge) + sk_mem_uncharge(sk, sg[i].length); if (!md->skb) put_page(sg_page(&sg[i])); sg[i].length = 0; @@ -594,9 +596,9 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) return free; } -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md) +static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge) { - int free = free_sg(sk, md->sg_start, md); + int free = free_sg(sk, md->sg_start, md, charge); md->sg_start = md->sg_end; return free; @@ -604,7 +606,7 @@ static int free_start_sg(struct sock *sk, struct sk_msg_buff *md) static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) { - return free_sg(sk, md->sg_curr, md); + return free_sg(sk, md->sg_curr, md, true); } static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) @@ -718,7 +720,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes, list_add_tail(&r->list, &psock->ingress); sk->sk_data_ready(sk); } else { - free_start_sg(sk, r); + free_start_sg(sk, r, true); kfree(r); } @@ -752,14 +754,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send, release_sock(sk); } smap_release_sock(psock, sk); - if (unlikely(err)) - goto out; - return 0; + return err; out_rcu: rcu_read_unlock(); -out: - free_bytes_sg(NULL, send, md, false); - return err; + return 0; } static inline void bpf_md_init(struct smap_psock *psock) @@ -822,7 +820,7 @@ more_data: case __SK_PASS: err = bpf_tcp_push(sk, send, m, flags, true); if (unlikely(err)) { - *copied -= free_start_sg(sk, m); + *copied -= free_start_sg(sk, m, true); break; } @@ -845,16 +843,17 @@ more_data: lock_sock(sk); if (unlikely(err < 0)) { - free_start_sg(sk, m); + int free = free_start_sg(sk, m, false); + psock->sg_size = 0; if (!cork) - *copied -= send; + *copied -= free; } else { psock->sg_size -= send; } if (cork) { - free_start_sg(sk, m); + free_start_sg(sk, m, true); psock->sg_size = 0; kfree(m); m = NULL; @@ -912,6 +911,8 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); rcu_read_lock(); psock = smap_psock_sk(sk); @@ -922,9 +923,6 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto out; rcu_read_unlock(); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); bytes_ready: while (copied != len) { @@ -1122,7 +1120,7 @@ wait_for_memory: err = sk_stream_wait_memory(sk, &timeo); if (err) { if (m && m != psock->cork) - free_start_sg(sk, m); + free_start_sg(sk, m, true); goto out_err; } } @@ -1464,10 +1462,16 @@ static void smap_destroy_psock(struct rcu_head *rcu) schedule_work(&psock->gc_work); } +static bool psock_is_smap_sk(struct sock *sk) +{ + return inet_csk(sk)->icsk_ulp_ops == &bpf_tcp_ulp_ops; +} + static void smap_release_sock(struct smap_psock *psock, struct sock *sock) { if (refcount_dec_and_test(&psock->refcnt)) { - tcp_cleanup_ulp(sock); + if (psock_is_smap_sk(sock)) + tcp_cleanup_ulp(sock); write_lock_bh(&sock->sk_callback_lock); smap_stop_sock(psock, sock); write_unlock_bh(&sock->sk_callback_lock); @@ -1581,13 +1585,13 @@ static void smap_gc_work(struct work_struct *w) bpf_prog_put(psock->bpf_tx_msg); if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); } list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { list_del(&md->list); - free_start_sg(psock->sock, md); + free_start_sg(psock->sock, md, true); kfree(md); } @@ -1894,6 +1898,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, * doesn't update user data. */ if (psock) { + if (!psock_is_smap_sk(sock)) { + err = -EBUSY; + goto out_progs; + } if (READ_ONCE(psock->bpf_parse) && parse) { err = -EBUSY; goto out_progs; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 92246117d2b0..bb07e74b34a2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3163,7 +3163,7 @@ 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/cpu.c b/kernel/cpu.c index aa7fe85ad62e..0097acec1c71 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -607,15 +607,15 @@ static void cpuhp_thread_fun(unsigned int cpu) bool bringup = st->bringup; enum cpuhp_state state; + if (WARN_ON_ONCE(!st->should_run)) + return; + /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (WARN_ON_ONCE(!st->should_run)) - return; - cpuhp_lock_acquire(bringup); if (st->single) { @@ -916,7 +916,8 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); if (ret) { st->target = prev_state; - undo_cpu_down(cpu, st); + if (st->state < prev_state) + undo_cpu_down(cpu, st); break; } } @@ -969,7 +970,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); - if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { + if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) { cpuhp_reset_state(st, prev_state); __cpuhp_kick_ap(st); } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 1c35b7b945d0..de87b0282e74 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -168,7 +168,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, int dma_direct_supported(struct device *dev, u64 mask) { #ifdef CONFIG_ZONE_DMA - if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + if (mask < phys_to_dma(dev, DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))) return 0; #else /* @@ -177,7 +177,7 @@ int dma_direct_supported(struct device *dev, u64 mask) * memory, or by providing a ZONE_DMA32. If neither is the case, the * architecture needs to use an IOMMU instead of the direct mapping. */ - if (mask < DMA_BIT_MASK(32)) + if (mask < phys_to_dma(dev, DMA_BIT_MASK(32))) return 0; #endif /* 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/fork.c b/kernel/fork.c index d896e9ca38b0..f0b58479534f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -550,8 +550,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; } /* a new mm has just been created */ - arch_dup_mmap(oldmm, mm); - retval = 0; + retval = arch_dup_mmap(oldmm, mm); out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); 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/pid.c b/kernel/pid.c index de1cfc4f75a2..cdf63e53a014 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -195,7 +195,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) idr_preload_end(); if (nr < 0) { - retval = nr; + retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } 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/printk/printk_safe.c b/kernel/printk/printk_safe.c index a0a74c533e4b..0913b4d385de 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -306,12 +306,12 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) return printk_safe_log_store(s, fmt, args); } -void printk_nmi_enter(void) +void notrace printk_nmi_enter(void) { this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); } -void printk_nmi_exit(void) +void notrace printk_nmi_exit(void) { this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK); } 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/kernel/sys.c b/kernel/sys.c index cf5c67533ff1..123bd73046ec 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -71,9 +71,6 @@ #include <asm/io.h> #include <asm/unistd.h> -/* Hardening for Spectre-v1 */ -#include <linux/nospec.h> - #include "uid16.h" #ifndef SET_UNALIGN_CTL diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f74fb00d8064..0e6e97a01942 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -133,19 +133,40 @@ static void inline clocksource_watchdog_unlock(unsigned long *flags) spin_unlock_irqrestore(&watchdog_lock, *flags); } +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); + /* * Interval: 0.5sec Threshold: 0.0625s */ #define WATCHDOG_INTERVAL (HZ >> 1) #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) +static void clocksource_watchdog_work(struct work_struct *work) +{ + /* + * We cannot directly run clocksource_watchdog_kthread() here, because + * clocksource_select() calls timekeeping_notify() which uses + * stop_machine(). One cannot use stop_machine() from a workqueue() due + * lock inversions wrt CPU hotplug. + * + * Also, we only ever run this work once or twice during the lifetime + * of the kernel, so there is no point in creating a more permanent + * kthread for this. + * + * If kthread_run fails the next watchdog scan over the + * watchdog_list will find the unstable clock again. + */ + kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); +} + static void __clocksource_unstable(struct clocksource *cs) { cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; /* - * If the clocksource is registered clocksource_watchdog_work() will + * If the clocksource is registered clocksource_watchdog_kthread() will * re-rate and re-select. */ if (list_empty(&cs->list)) { @@ -156,7 +177,7 @@ static void __clocksource_unstable(struct clocksource *cs) if (cs->mark_unstable) cs->mark_unstable(cs); - /* kick clocksource_watchdog_work() */ + /* kick clocksource_watchdog_kthread() */ if (finished_booting) schedule_work(&watchdog_work); } @@ -166,7 +187,7 @@ static void __clocksource_unstable(struct clocksource *cs) * @cs: clocksource to be marked unstable * * This function is called by the x86 TSC code to mark clocksources as unstable; - * it defers demotion and re-selection to a work. + * it defers demotion and re-selection to a kthread. */ void clocksource_mark_unstable(struct clocksource *cs) { @@ -391,9 +412,7 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs) } } -static void __clocksource_change_rating(struct clocksource *cs, int rating); - -static int __clocksource_watchdog_work(void) +static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; @@ -418,12 +437,13 @@ static int __clocksource_watchdog_work(void) return select; } -static void clocksource_watchdog_work(struct work_struct *work) +static int clocksource_watchdog_kthread(void *data) { mutex_lock(&clocksource_mutex); - if (__clocksource_watchdog_work()) + if (__clocksource_watchdog_kthread()) clocksource_select(); mutex_unlock(&clocksource_mutex); + return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) @@ -442,7 +462,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_select_watchdog(bool fallback) { } static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } -static inline int __clocksource_watchdog_work(void) { return 0; } +static inline int __clocksource_watchdog_kthread(void) { return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } void clocksource_mark_unstable(struct clocksource *cs) { } @@ -810,7 +830,7 @@ static int __init clocksource_done_booting(void) /* * Run the watchdog first to eliminate unstable clock sources */ - __clocksource_watchdog_work(); + __clocksource_watchdog_kthread(); clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 1d92d4a982fd..65bd4616220d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1546,6 +1546,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) tmp_iter_page = first_page; do { + cond_resched(); + to_remove_page = tmp_iter_page; rb_inc_page(cpu_buffer, &tmp_iter_page); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 613316724c6a..4966c4fbe7f7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1277,13 +1277,13 @@ config WARN_ALL_UNSEEDED_RANDOM time. This is really bad from a security perspective, and so architecture maintainers really need to do what they can to get the CRNG seeded sooner after the system is booted. - However, since users can not do anything actionble to + However, since users cannot do anything actionable to address this, by default the kernel will issue only a single warning for the first use of unseeded randomness. Say Y here if you want to receive warnings for all uses of unseeded randomness. This will be of use primarily for - those developers interersted in improving the security of + those developers interested in improving the security of Linux kernels running on their architecture (or subarchitecture). diff --git a/mm/Kconfig b/mm/Kconfig index a550635ea5c3..de64ea658716 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -637,6 +637,7 @@ config DEFERRED_STRUCT_PAGE_INIT depends on NO_BOOTMEM depends on SPARSEMEM depends on !NEED_PER_CPU_KM + depends on 64BIT help Ordinarily all struct pages are initialised during early boot in a single thread. On very large machines this can take a considerable 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/backing-dev.c b/mm/backing-dev.c index f5981e9d6ae2..8a8bb8796c6c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -491,6 +491,7 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); + struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); @@ -499,6 +500,9 @@ static void cgwb_release_workfn(struct work_struct *work) css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); + /* triggers blkg destruction if cgwb_refcnt becomes zero */ + blkcg_cgwb_put(blkcg); + fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); wb_exit(wb); @@ -597,6 +601,7 @@ static int cgwb_create(struct backing_dev_info *bdi, list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); + blkcg_cgwb_get(blkcg); css_get(memcg_css); css_get(blkcg_css); } 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/huge_memory.c b/mm/huge_memory.c index c3bc7e9c9a2a..533f9b00147d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -821,11 +821,11 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - BUG_ON(!pfn_t_devmap(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 9a085d525bbc..17dd883198ae 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2097,6 +2097,11 @@ static int __init kmemleak_late_init(void) kmemleak_initialized = 1; + dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, + &kmemleak_fops); + if (!dentry) + pr_warn("Failed to create the debugfs kmemleak file\n"); + if (kmemleak_error) { /* * Some error occurred and kmemleak was disabled. There is a @@ -2108,10 +2113,6 @@ static int __init kmemleak_late_init(void) return -ENOMEM; } - dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, - &kmemleak_fops); - if (!dentry) - pr_warn("Failed to create the debugfs kmemleak file\n"); mutex_lock(&scan_mutex); start_scan_thread(); mutex_unlock(&scan_mutex); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4ead5a4817de..e79cb59552d9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1701,8 +1701,6 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int if (mem_cgroup_out_of_memory(memcg, mask, order)) return OOM_SUCCESS; - WARN(1,"Memory cgroup charge failed because of no reclaimable memory! " - "This looks like a misconfiguration or a kernel bug."); return OOM_FAILED; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9eea6e809a4e..38d94b703e9d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1333,7 +1333,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) if (__PageMovable(page)) return pfn; if (PageHuge(page)) { - if (page_huge_active(page)) + if (hugepage_migration_supported(page_hstate(page)) && + page_huge_active(page)) return pfn; else pfn = round_up(pfn + 1, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b5b25e4dcbbb..f10aa5360616 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -522,6 +522,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm) tlb_gather_mmu(&tlb, mm, start, end); if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) { + tlb_finish_mmu(&tlb, start, end); ret = false; continue; } @@ -1103,10 +1104,17 @@ bool out_of_memory(struct oom_control *oc) } select_bad_process(oc); - /* Found nothing?!?! Either we hang forever, or we panic. */ - if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) { + /* Found nothing?!?! */ + if (!oc->chosen) { dump_header(oc, NULL); - panic("Out of memory and no killable processes...\n"); + pr_warn("Out of memory and no killable processes...\n"); + /* + * If we got here due to an actual allocation at the + * system level, we cannot survive this and will enter + * an endless loop in the allocator. Bail out now. + */ + if (!is_sysrq_oom(oc) && !is_memcg_oom(oc)) + panic("System is deadlocked on memory\n"); } if (oc->chosen && oc->chosen != (void *)-1UL) oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 05e983f42316..89d2a2ab3fe6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7708,6 +7708,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * handle each tail page individually in migration. */ if (PageHuge(page)) { + + if (!hugepage_migration_supported(page_hstate(page))) + goto unmovable; + iter = round_up(iter + 1, 1<<compound_order(page)) - 1; continue; } 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/shmem.c b/mm/shmem.c index 0376c124b043..446942677cd4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2227,6 +2227,8 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode mpol_shared_policy_init(&info->policy, NULL); break; } + + lockdep_annotate_inode_mutex_key(inode); } else shmem_free_inode(sb); return inode; diff --git a/mm/util.c b/mm/util.c index d2890a407332..9e3ebd2ef65f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -435,11 +435,14 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) EXPORT_SYMBOL(kvmalloc_node); /** - * kvfree - free memory allocated with kvmalloc - * @addr: pointer returned by kvmalloc + * kvfree() - Free memory. + * @addr: Pointer to allocated memory. * - * If the memory is allocated from vmalloc area it is freed with vfree(). - * Otherwise kfree() is used. + * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). + * It is slightly more efficient to use kfree() or vfree() if you are certain + * that you know which one to use. + * + * Context: Any context except NMI. */ void kvfree(const void *addr) { 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/mm/vmscan.c b/mm/vmscan.c index 7e7d25504651..c7ce2c161225 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -476,6 +476,17 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); + + /* + * Make sure we apply some minimal pressure on default priority + * even on small cgroups. Stale objects are not only consuming memory + * by themselves, but can also hold a reference to a dying cgroup, + * preventing it from being reclaimed. A dying cgroup with all + * corresponding structures like per-cpu stats and kmem caches + * can be really big, so it may lead to a significant waste of memory. + */ + delta = max_t(unsigned long long, delta, min(freeable, batch_size)); + total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", 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 c25eb36f1320..5e00f2b85a56 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2282,14 +2282,21 @@ static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .arg2_type = ARG_ANYTHING, }; +#define sk_msg_iter_var(var) \ + do { \ + var++; \ + if (var == MAX_SKB_FRAGS) \ + var = 0; \ + } while (0) + BPF_CALL_4(bpf_msg_pull_data, struct sk_msg_buff *, msg, u32, start, u32, end, u64, flags) { - unsigned int len = 0, offset = 0, copy = 0; + unsigned int len = 0, offset = 0, copy = 0, poffset = 0; + int bytes = end - start, bytes_sg_total; struct scatterlist *sg = msg->sg_data; int first_sg, last_sg, i, shift; unsigned char *p, *to, *from; - int bytes = end - start; struct page *page; if (unlikely(flags || end <= start)) @@ -2299,21 +2306,22 @@ BPF_CALL_4(bpf_msg_pull_data, i = msg->sg_start; do { len = sg[i].length; - offset += len; if (start < offset + len) break; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + offset += len; + sk_msg_iter_var(i); } while (i != msg->sg_end); if (unlikely(start >= offset + len)) return -EINVAL; - if (!msg->sg_copy[i] && bytes <= len) - goto out; - first_sg = i; + /* The start may point into the sg element so we need to also + * account for the headroom. + */ + bytes_sg_total = start - offset + bytes; + if (!msg->sg_copy[i] && bytes_sg_total <= len) + goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to @@ -2327,37 +2335,33 @@ BPF_CALL_4(bpf_msg_pull_data, */ do { copy += sg[i].length; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - if (bytes < copy) + sk_msg_iter_var(i); + if (bytes_sg_total <= copy) break; } while (i != msg->sg_end); last_sg = i; - if (unlikely(copy < end - start)) + 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); - offset = 0; i = first_sg; do { from = sg_virt(&sg[i]); len = sg[i].length; - to = p + offset; + to = p + poffset; memcpy(to, from, len); - offset += len; + poffset += len; sg[i].length = 0; put_page(sg_page(&sg[i])); - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + sk_msg_iter_var(i); } while (i != last_sg); sg[first_sg].length = copy; @@ -2367,11 +2371,15 @@ BPF_CALL_4(bpf_msg_pull_data, * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ - shift = last_sg - first_sg - 1; + WARN_ON_ONCE(last_sg == first_sg); + shift = last_sg > first_sg ? + last_sg - first_sg - 1 : + MAX_SKB_FRAGS - first_sg + last_sg - 1; if (!shift) goto out; - i = first_sg + 1; + i = first_sg; + sk_msg_iter_var(i); do { int move_from; @@ -2388,15 +2396,13 @@ BPF_CALL_4(bpf_msg_pull_data, sg[move_from].page_link = 0; sg[move_from].offset = 0; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + sk_msg_iter_var(i); } while (1); msg->sg_end -= shift; if (msg->sg_end < 0) msg->sg_end += MAX_SKB_FRAGS; out: - msg->data = sg_virt(&sg[i]) + start - offset; + msg->data = sg_virt(&sg[first_sg]) + start - offset; msg->data_end = msg->data + bytes; return 0; @@ -7281,7 +7287,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_reuseport_md, ip_protocol): - BUILD_BUG_ON(hweight_long(SK_FL_PROTO_MASK) != BITS_PER_BYTE); + BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset, BPF_W, 0); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); 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 24431e578310..63ce2283a456 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -324,6 +324,10 @@ void rtnl_unregister_all(int protocol) rtnl_lock(); tab = rtnl_msg_handlers[protocol]; + if (!tab) { + rtnl_unlock(); + return; + } RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL); for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) { link = tab[msgindex]; @@ -2806,7 +2810,7 @@ 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/core/skbuff.c b/net/core/skbuff.c index c996c09d095f..b2c807f67aba 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -939,9 +939,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) WARN_ON_ONCE(!in_task()); - if (!sock_flag(sk, SOCK_ZEROCOPY)) - return NULL; - skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index e63c554e0623..9f3209ff7ffd 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -19,12 +19,10 @@ #include <linux/of_mdio.h> #include <linux/of_platform.h> #include <linux/of_net.h> -#include <linux/of_gpio.h> #include <linux/netdevice.h> #include <linux/sysfs.h> #include <linux/phy_fixed.h> #include <linux/ptp_classify.h> -#include <linux/gpio/consumer.h> #include <linux/etherdevice.h> #include "dsa_priv.h" diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 20fda8fb8ffd..1fbe2f815474 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1377,6 +1377,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; + skb_reset_mac_len(skb); } while ((skb = skb->next)); out: diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index cf75f8944b05..4da39446da2d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -820,10 +820,9 @@ static void igmp_timer_expire(struct timer_list *t) spin_lock(&im->lock); im->tm_running = 0; - if (im->unsolicit_count) { - im->unsolicit_count--; + if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); - } + im->reporter = 1; spin_unlock(&im->lock); @@ -1308,6 +1307,8 @@ static void igmp_group_added(struct ip_mc_list *im) if (in_dev->dead) return; + + im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); @@ -1391,9 +1392,6 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode) { struct ip_mc_list *im; -#ifdef CONFIG_IP_MULTICAST - struct net *net = dev_net(in_dev->dev); -#endif ASSERT_RTNL(); @@ -1420,7 +1418,6 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); - im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; #endif im->next_rcu = in_dev->mc_list; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 88281fbce88c..e7227128df2c 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -599,6 +599,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, nextp = &fp->next; fp->prev = NULL; memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; head->data_len += fp->len; head->len += fp->len; if (head->ip_summed != fp->ip_summed) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 51a5d06085ac..8cce0e9ea08c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -178,6 +178,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info, if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); + else if (tpi->proto == htons(ETH_P_ERSPAN) || + tpi->proto == htons(ETH_P_ERSPAN2)) + itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); @@ -328,6 +331,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } + return PACKET_REJECT; + drop: kfree_skb(skb); return PACKET_RCVD; @@ -1508,11 +1513,14 @@ nla_put_failure: static void erspan_setup(struct net_device *dev) { + struct ip_tunnel *t = netdev_priv(dev); + ether_setup(dev); dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); + t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index d9504adc47b3..184bf2e0a1ed 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -106,6 +106,10 @@ config NF_NAT_IPV4 if NF_NAT_IPV4 +config NF_NAT_MASQUERADE_IPV4 + bool + +if NF_TABLES config NFT_CHAIN_NAT_IPV4 depends on NF_TABLES_IPV4 tristate "IPv4 nf_tables nat chain support" @@ -115,9 +119,6 @@ config NFT_CHAIN_NAT_IPV4 packet transformations such as the source, destination address and source and destination ports. -config NF_NAT_MASQUERADE_IPV4 - bool - config NFT_MASQ_IPV4 tristate "IPv4 masquerading support for nf_tables" depends on NF_TABLES_IPV4 @@ -135,6 +136,7 @@ config NFT_REDIR_IPV4 help This is the expression that provides IPv4 redirect support for nf_tables. +endif # NF_TABLES config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b8af2fec5ad5..10c6246396cc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1185,7 +1185,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; - if (flags & MSG_ZEROCOPY && size) { + if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { if (sk->sk_state != TCP_ESTABLISHED) { err = -EINVAL; goto out_err; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4c2dd9f863f7..4cf2f7bb2802 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6367,8 +6367,8 @@ static bool tcp_syn_flood_action(const struct sock *sk, if (!queue->synflood_warned && net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) - pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); + net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); return want_cookie; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 75ef332a7caf..12affb7864d9 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -184,8 +184,9 @@ kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; } + } else { + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); } - inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; 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/af_inet6.c b/net/ipv6/af_inet6.c index 673bba31eb18..9a4261e50272 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -938,14 +938,14 @@ static int __init inet6_init(void) err = proto_register(&pingv6_prot, 1); if (err) - goto out_unregister_ping_proto; + goto out_unregister_raw_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ err = rawv6_init(); if (err) - goto out_unregister_raw_proto; + goto out_unregister_ping_proto; /* Register the family here so that the init calls below will * be able to create sockets. (?? is this dangerous ??) @@ -1113,11 +1113,11 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: - ip6_mr_cleanup(); + icmpv6_cleanup(); icmp_fail: - unregister_pernet_subsys(&inet6_net_ops); + ip6_mr_cleanup(); ipmr_fail: - icmpv6_cleanup(); + unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index c861a6d4671d..5516f55e214b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -989,7 +989,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_clean_expires(iter); else fib6_set_expires(iter, rt->expires); - fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); + + if (rt->fib6_pmtu) + fib6_metric_set(iter, RTAX_MTU, + rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 18a3794b0f52..e493b041d4ac 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1778,6 +1778,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; + parms->erspan_ver = 1; if (data[IFLA_GRE_ERSPAN_VER]) parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 37ff4805b20c..c7e495f12011 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -115,6 +115,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, payload_len = skb->len - nhoff - sizeof(*ipv6h); ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; + skb_reset_mac_len(skb); if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 16f200f06500..f9f8f554d141 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/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5df2a58d945c..419960b0ba16 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1188,7 +1188,15 @@ route_lookup: init_tel_txopt(&opt, encap_limit); ipv6_push_frag_opts(skb, &opt.ops, &proto); } - hop_limit = hop_limit ? : ip6_dst_hoplimit(dst); + + if (hop_limit == 0) { + if (skb->protocol == htons(ETH_P_IP)) + hop_limit = ip_hdr(skb)->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + hop_limit = ipv6_hdr(skb)->hop_limit; + else + hop_limit = ip6_dst_hoplimit(dst); + } /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 5095367c7204..eeaf7455d51e 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -481,7 +481,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (!skb->ignore_df && skb->len > mtu) { + if (skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2a14d8b65924..8f68a518d9db 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -445,6 +445,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; + fp->sk = NULL; } sub_frag_mem_limit(fq->q.net, head->truesize); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c4ea13e8360b..480a79f47c52 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; @@ -996,7 +994,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) rt->rt6i_src = ort->fib6_src; #endif rt->rt6i_prefsrc = ort->fib6_prefsrc; - rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, @@ -4671,20 +4668,31 @@ 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; @@ -4699,7 +4707,7 @@ 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) { @@ -4707,7 +4715,7 @@ 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) { @@ -4715,12 +4723,12 @@ 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) @@ -4755,7 +4763,14 @@ 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; @@ -4778,7 +4793,7 @@ 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; } @@ -4786,7 +4801,7 @@ 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/iucv/af_iucv.c b/net/iucv/af_iucv.c index a21d8ed0a325..e2f16a0173a9 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -351,20 +351,28 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, memcpy(&phs_hdr->iucv_hdr, imsg, sizeof(struct iucv_message)); skb->dev = iucv->hs_dev; - if (!skb->dev) - return -ENODEV; - if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) - return -ENETDOWN; + if (!skb->dev) { + err = -ENODEV; + goto err_free; + } + if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) { + err = -ENETDOWN; + goto err_free; + } if (skb->len > skb->dev->mtu) { - if (sock->sk_type == SOCK_SEQPACKET) - return -EMSGSIZE; - else - skb_trim(skb, skb->dev->mtu); + if (sock->sk_type == SOCK_SEQPACKET) { + err = -EMSGSIZE; + goto err_free; + } + skb_trim(skb, skb->dev->mtu); } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) - return -ENOMEM; + if (!nskb) { + err = -ENOMEM; + goto err_free; + } + skb_queue_tail(&iucv->send_skb_q, nskb); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { @@ -375,6 +383,10 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, WARN_ON(atomic_read(&iucv->msg_recv) < 0); } return net_xmit_eval(err); + +err_free: + kfree_skb(skb); + return err; } static struct sock *__iucv_get_sock_by_name(char *nm) @@ -1167,7 +1179,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, err = afiucv_hs_send(&txmsg, sk, skb, 0); if (err) { atomic_dec(&iucv->msg_sent); - goto fail; + goto out; } } else { /* Classic VM IUCV transport */ skb_queue_tail(&iucv->send_skb_q, skb); @@ -2155,8 +2167,8 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, struct sock *sk; struct iucv_sock *iucv; struct af_iucv_trans_hdr *trans_hdr; + int err = NET_RX_SUCCESS; char nullstring[8]; - int err = 0; if (skb->len < (ETH_HLEN + sizeof(struct af_iucv_trans_hdr))) { WARN_ONCE(1, "AF_IUCV too short skb, len=%d, min=%d", @@ -2254,7 +2266,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, err = afiucv_hs_callback_rx(sk, skb); break; default: - ; + kfree_skb(skb); } return err; diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 8f7ef167c45a..eb502c6290c2 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1874,7 +1874,7 @@ static void iucv_pm_complete(struct device *dev) * Returns 0 if there are still iucv pathes defined * 1 if there are no iucv pathes defined */ -int iucv_path_table_empty(void) +static int iucv_path_table_empty(void) { int i; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 6449a1c2283b..f0f5fedb8caa 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -947,8 +947,8 @@ static void ieee80211_rx_mgmt_deauth_ibss(struct ieee80211_sub_if_data *sdata, if (len < IEEE80211_DEAUTH_FRAME_LEN) return; - ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM BSSID=%pM (reason: %d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, reason); + ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (reason: %d)\n", mgmt->bssid, reason); sta_info_destroy_addr(sdata, mgmt->sa); } @@ -966,9 +966,9 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg); auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction); - ibss_dbg(sdata, - "RX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=%d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, auth_transaction); + ibss_dbg(sdata, "RX Auth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (auth_transaction=%d)\n", + mgmt->bssid, auth_transaction); if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1) return; @@ -1175,10 +1175,10 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, rx_timestamp = drv_get_tsf(local, sdata); } - ibss_dbg(sdata, - "RX beacon SA=%pM BSSID=%pM TSF=0x%llx BCN=0x%llx diff=%lld @%lu\n", + ibss_dbg(sdata, "RX beacon SA=%pM BSSID=%pM TSF=0x%llx\n", mgmt->sa, mgmt->bssid, - (unsigned long long)rx_timestamp, + (unsigned long long)rx_timestamp); + ibss_dbg(sdata, "\tBCN=0x%llx diff=%lld @%lu\n", (unsigned long long)beacon_timestamp, (unsigned long long)(rx_timestamp - beacon_timestamp), jiffies); @@ -1537,9 +1537,9 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, tx_last_beacon = drv_tx_last_beacon(local); - ibss_dbg(sdata, - "RX ProbeReq SA=%pM DA=%pM BSSID=%pM (tx_last_beacon=%d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, tx_last_beacon); + ibss_dbg(sdata, "RX ProbeReq SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (tx_last_beacon=%d)\n", + mgmt->bssid, tx_last_beacon); if (!tx_last_beacon && is_multicast_ether_addr(mgmt->da)) return; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4fb2709cb527..513627896204 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -256,8 +256,27 @@ static void ieee80211_restart_work(struct work_struct *work) flush_work(&local->radar_detected_work); rtnl_lock(); - list_for_each_entry(sdata, &local->interfaces, list) + list_for_each_entry(sdata, &local->interfaces, list) { + /* + * XXX: there may be more work for other vif types and even + * for station mode: a good thing would be to run most of + * the iface type's dependent _stop (ieee80211_mg_stop, + * ieee80211_ibss_stop) etc... + * For now, fix only the specific bug that was seen: race + * between csa_connection_drop_work and us. + */ + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + /* + * This worker is scheduled from the iface worker that + * runs on mac80211's workqueue, so we can't be + * scheduling this worker after the cancel right here. + * The exception is ieee80211_chswitch_done. + * Then we can have a race... + */ + cancel_work_sync(&sdata->u.mgd.csa_connection_drop_work); + } flush_delayed_work(&sdata->dec_tailroom_needed_wk); + } ieee80211_scan_cancel(local); /* make sure any new ROC will consider local->in_reconfig */ @@ -471,10 +490,7 @@ static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = { cpu_to_le32(IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_SHORT_GI_160 | - IEEE80211_VHT_CAP_RXSTBC_1 | - IEEE80211_VHT_CAP_RXSTBC_2 | - IEEE80211_VHT_CAP_RXSTBC_3 | - IEEE80211_VHT_CAP_RXSTBC_4 | + IEEE80211_VHT_CAP_RXSTBC_MASK | IEEE80211_VHT_CAP_TXSTBC | IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE | IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | @@ -1208,6 +1224,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&local->ifa6_notifier); #endif + ieee80211_txq_teardown_flows(local); rtnl_lock(); @@ -1236,7 +1253,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue); skb_queue_purge(&local->skb_queue_unreliable); skb_queue_purge(&local->skb_queue_tdls_chsw); - ieee80211_txq_teardown_flows(local); destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 35ad3983ae4b..daf9db3c8f24 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -572,6 +572,10 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, forward = false; reply = true; target_metric = 0; + + if (SN_GT(target_sn, ifmsh->sn)) + ifmsh->sn = target_sn; + if (time_after(jiffies, ifmsh->last_sn_update + net_traversal_jiffies(sdata)) || time_before(jiffies, ifmsh->last_sn_update)) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 7fb9957359a3..3dbecae4be73 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1073,6 +1073,10 @@ static void ieee80211_chswitch_work(struct work_struct *work) */ if (sdata->reserved_chanctx) { + struct ieee80211_supported_band *sband = NULL; + struct sta_info *mgd_sta = NULL; + enum ieee80211_sta_rx_bandwidth bw = IEEE80211_STA_RX_BW_20; + /* * with multi-vif csa driver may call ieee80211_csa_finish() * many times while waiting for other interfaces to use their @@ -1081,6 +1085,48 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (sdata->reserved_ready) goto out; + if (sdata->vif.bss_conf.chandef.width != + sdata->csa_chandef.width) { + /* + * For managed interface, we need to also update the AP + * station bandwidth and align the rate scale algorithm + * on the bandwidth change. Here we only consider the + * bandwidth of the new channel definition (as channel + * switch flow does not have the full HT/VHT/HE + * information), assuming that if additional changes are + * required they would be done as part of the processing + * of the next beacon from the AP. + */ + switch (sdata->csa_chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + default: + bw = IEEE80211_STA_RX_BW_20; + break; + case NL80211_CHAN_WIDTH_40: + bw = IEEE80211_STA_RX_BW_40; + break; + case NL80211_CHAN_WIDTH_80: + bw = IEEE80211_STA_RX_BW_80; + break; + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + bw = IEEE80211_STA_RX_BW_160; + break; + } + + mgd_sta = sta_info_get(sdata, ifmgd->bssid); + sband = + local->hw.wiphy->bands[sdata->csa_chandef.chan->band]; + } + + if (sdata->vif.bss_conf.chandef.width > + sdata->csa_chandef.width) { + mgd_sta->sta.bandwidth = bw; + rate_control_rate_update(local, sband, mgd_sta, + IEEE80211_RC_BW_CHANGED); + } + ret = ieee80211_vif_use_reserved_context(sdata); if (ret) { sdata_info(sdata, @@ -1091,6 +1137,13 @@ static void ieee80211_chswitch_work(struct work_struct *work) goto out; } + if (sdata->vif.bss_conf.chandef.width < + sdata->csa_chandef.width) { + mgd_sta->sta.bandwidth = bw; + rate_control_rate_update(local, sband, mgd_sta, + IEEE80211_RC_BW_CHANGED); + } + goto out; } @@ -1312,6 +1365,16 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, cbss->beacon_interval)); return; drop_connection: + /* + * This is just so that the disconnect flow will know that + * we were trying to switch channel and failed. In case the + * mode is 1 (we are not allowed to Tx), we will know not to + * send a deauthentication frame. Those two fields will be + * reset when the disconnection worker runs. + */ + sdata->vif.csa_active = true; + sdata->csa_block_tx = csa_ie.mode; + ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); mutex_unlock(&local->chanctx_mtx); mutex_unlock(&local->mtx); @@ -2522,6 +2585,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + bool tx; sdata_lock(sdata); if (!ifmgd->associated) { @@ -2529,6 +2593,8 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) return; } + tx = !sdata->csa_block_tx; + /* AP is probably out of range (or not reachable for another reason) so * remove the bss struct for that AP. */ @@ -2536,7 +2602,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, - true, frame_buf); + tx, frame_buf); mutex_lock(&local->mtx); sdata->vif.csa_active = false; ifmgd->csa_waiting_bcn = false; @@ -2547,7 +2613,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) } mutex_unlock(&local->mtx); - ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, + ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); sdata_unlock(sdata); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 64742f2765c4..96611d5dfadb 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1728,6 +1728,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) */ if (!ieee80211_hw_check(&sta->local->hw, AP_LINK_PS) && !ieee80211_has_morefrags(hdr->frame_control) && + !is_multicast_ether_addr(hdr->addr1) && (ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_data(hdr->frame_control)) && !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index cd332e3e1134..f353d9db54bc 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3078,27 +3078,18 @@ void ieee80211_clear_fast_xmit(struct sta_info *sta) } static bool ieee80211_amsdu_realloc_pad(struct ieee80211_local *local, - struct sk_buff *skb, int headroom, - int *subframe_len) + struct sk_buff *skb, int headroom) { - int amsdu_len = *subframe_len + sizeof(struct ethhdr); - int padding = (4 - amsdu_len) & 3; - - if (skb_headroom(skb) < headroom || skb_tailroom(skb) < padding) { + if (skb_headroom(skb) < headroom) { I802_DEBUG_INC(local->tx_expand_skb_head); - if (pskb_expand_head(skb, headroom, padding, GFP_ATOMIC)) { + if (pskb_expand_head(skb, headroom, 0, GFP_ATOMIC)) { wiphy_debug(local->hw.wiphy, "failed to reallocate TX buffer\n"); return false; } } - if (padding) { - *subframe_len += padding; - skb_put_zero(skb, padding); - } - return true; } @@ -3122,8 +3113,7 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata, if (info->control.flags & IEEE80211_TX_CTRL_AMSDU) return true; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr), - &subframe_len)) + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr))) return false; data = skb_push(skb, sizeof(*amsdu_hdr)); @@ -3189,7 +3179,8 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, void *data; bool ret = false; unsigned int orig_len; - int n = 1, nfrags; + int n = 2, nfrags, pad = 0; + u16 hdrlen; if (!ieee80211_hw_check(&local->hw, TX_AMSDU)) return false; @@ -3222,9 +3213,6 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (skb->len + head->len > max_amsdu_len) goto out; - if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) - goto out; - nfrags = 1 + skb_shinfo(skb)->nr_frags; nfrags += 1 + skb_shinfo(head)->nr_frags; frag_tail = &skb_shinfo(head)->frag_list; @@ -3240,10 +3228,24 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (max_frags && nfrags > max_frags) goto out; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + 2, - &subframe_len)) + if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) goto out; + /* + * Pad out the previous subframe to a multiple of 4 by adding the + * padding to the next one, that's being added. Note that head->len + * is the length of the full A-MSDU, but that works since each time + * we add a new subframe we pad out the previous one to a multiple + * of 4 and thus it no longer matters in the next round. + */ + hdrlen = fast_tx->hdr_len - sizeof(rfc1042_header); + if ((head->len - hdrlen) & 3) + pad = 4 - ((head->len - hdrlen) & 3); + + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + + 2 + pad)) + goto out_recalc; + ret = true; data = skb_push(skb, ETH_ALEN + 2); memmove(data, data + ETH_ALEN + 2, 2 * ETH_ALEN); @@ -3253,15 +3255,19 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, memcpy(data, &len, 2); memcpy(data + 2, rfc1042_header, sizeof(rfc1042_header)); + memset(skb_push(skb, pad), 0, pad); + head->len += skb->len; head->data_len += skb->len; *frag_tail = skb; - flow->backlog += head->len - orig_len; - tin->backlog_bytes += head->len - orig_len; - - fq_recalc_backlog(fq, tin, flow); +out_recalc: + if (head->len != orig_len) { + flow->backlog += head->len - orig_len; + tin->backlog_bytes += head->len - orig_len; + fq_recalc_backlog(fq, tin, flow); + } out: spin_unlock_bh(&fq->lock); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 88efda7c9f8a..716cd6442d86 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1135,7 +1135,7 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, { struct ieee80211_chanctx_conf *chanctx_conf; const struct ieee80211_reg_rule *rrule; - struct ieee80211_wmm_ac *wmm_ac; + const struct ieee80211_wmm_ac *wmm_ac; u16 center_freq = 0; if (sdata->vif.type != NL80211_IFTYPE_AP && @@ -1154,20 +1154,19 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, rrule = freq_reg_info(sdata->wdev.wiphy, MHZ_TO_KHZ(center_freq)); - if (IS_ERR_OR_NULL(rrule) || !rrule->wmm_rule) { + if (IS_ERR_OR_NULL(rrule) || !rrule->has_wmm) { rcu_read_unlock(); return; } if (sdata->vif.type == NL80211_IFTYPE_AP) - wmm_ac = &rrule->wmm_rule->ap[ac]; + wmm_ac = &rrule->wmm_rule.ap[ac]; else - wmm_ac = &rrule->wmm_rule->client[ac]; + wmm_ac = &rrule->wmm_rule.client[ac]; qparam->cw_min = max_t(u16, qparam->cw_min, wmm_ac->cw_min); qparam->cw_max = max_t(u16, qparam->cw_max, wmm_ac->cw_max); qparam->aifs = max_t(u8, qparam->aifs, wmm_ac->aifsn); - qparam->txop = !qparam->txop ? wmm_ac->cot / 32 : - min_t(u16, qparam->txop, wmm_ac->cot / 32); + qparam->txop = min_t(u16, qparam->txop, wmm_ac->cot / 32); rcu_read_unlock(); } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 71709c104081..f61c306de1d0 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -771,13 +771,13 @@ config NETFILTER_XT_TARGET_CHECKSUM depends on NETFILTER_ADVANCED ---help--- This option adds a `CHECKSUM' target, which can be used in the iptables mangle - table. + table to work around buggy DHCP clients in virtualized environments. - You can use this target to compute and fill in the checksum in - a packet that lacks a checksum. This is particularly useful, - if you need to work around old applications such as dhcp clients, - that do not work well with checksum offloads, but don't want to disable - checksum offload in your device. + Some old DHCP clients drop packets because they are not aware + that the checksum would normally be offloaded to hardware and + thus should be considered valid. + This target can be used to fill in the checksum using iptables + when such packets are sent via a virtual network device. To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 9f14b0df6960..51c5d7eec0a3 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -776,9 +776,26 @@ static const struct nf_hook_ops ipv6_conntrack_ops[] = { }; #endif +static int nf_ct_tcp_fixup(struct nf_conn *ct, void *_nfproto) +{ + u8 nfproto = (unsigned long)_nfproto; + + if (nf_ct_l3num(ct) != nfproto) + return 0; + + if (nf_ct_protonum(ct) == IPPROTO_TCP && + ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED) { + ct->proto.tcp.seen[0].td_maxwin = 0; + ct->proto.tcp.seen[1].td_maxwin = 0; + } + + return 0; +} + static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + bool fixup_needed = false; int err = 0; mutex_lock(&nf_ct_proto_mutex); @@ -798,6 +815,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv4_conntrack_ops)); if (err) cnet->users4 = 0; + else + fixup_needed = true; break; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: @@ -814,6 +833,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv6_conntrack_ops)); if (err) cnet->users6 = 0; + else + fixup_needed = true; break; #endif default: @@ -822,6 +843,11 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) } out_unlock: mutex_unlock(&nf_ct_proto_mutex); + + if (fixup_needed) + nf_ct_iterate_cleanup_net(net, nf_ct_tcp_fixup, + (void *)(unsigned long)nfproto, 0, 0); + return err; } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 8c58f96b59e7..f3f91ed2c21a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -675,7 +675,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -697,6 +697,8 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_DCCP_UNSPEC] = timeouts[CTA_TIMEOUT_DCCP_REQUEST]; return 0; } @@ -726,7 +728,7 @@ dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL /* template, data assigned later */ @@ -827,6 +829,11 @@ static int dccp_init_net(struct net *net, u_int16_t proto) dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; + + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } return dccp_kmemdup_sysctl_table(net, pn, dn); @@ -856,7 +863,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -864,7 +871,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; @@ -889,7 +896,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -897,7 +904,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index ac4a0b296dcd..1df3244ecd07 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -70,7 +70,7 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, return ret; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -113,7 +113,7 @@ static const struct nla_policy generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { [CTA_TIMEOUT_GENERIC_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table generic_sysctl_table[] = { @@ -164,7 +164,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .pkt_to_tuple = generic_pkt_to_tuple, .packet = generic_packet, .new = generic_new, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = generic_timeout_nlattr_to_obj, .obj_to_nlattr = generic_timeout_obj_to_nlattr, @@ -172,7 +172,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .obj_size = sizeof(unsigned int), .nla_policy = generic_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = generic_init_net, .get_net_proto = generic_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index d1632252bf5b..650eb4fba2c5 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -285,7 +285,7 @@ static void gre_destroy(struct nf_conn *ct) nf_ct_gre_keymap_destroy(master); } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -334,7 +334,7 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { [CTA_TIMEOUT_GRE_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_GRE_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ static int gre_init_net(struct net *net, u_int16_t proto) { @@ -367,7 +367,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = gre_timeout_nlattr_to_obj, .obj_to_nlattr = gre_timeout_obj_to_nlattr, @@ -375,7 +375,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .obj_size = sizeof(unsigned int) * GRE_CT_MAX, .nla_policy = gre_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .net_id = &proto_gre_net_id, .init_net = gre_init_net, }; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 036670b38282..43c7e1a217b9 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -273,7 +273,7 @@ static unsigned int icmp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -313,7 +313,7 @@ static const struct nla_policy icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmp_sysctl_table[] = { @@ -374,7 +374,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmp_timeout_nlattr_to_obj, .obj_to_nlattr = icmp_timeout_obj_to_nlattr, @@ -382,7 +382,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .obj_size = sizeof(unsigned int), .nla_policy = icmp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmp_init_net, .get_net_proto = icmp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index bed07b998a10..97e40f77d678 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -274,7 +274,7 @@ static unsigned int icmpv6_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -314,7 +314,7 @@ static const struct nla_policy icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmpv6_sysctl_table[] = { @@ -373,7 +373,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, @@ -381,7 +381,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .obj_size = sizeof(unsigned int), .nla_policy = icmpv6_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmpv6_init_net, .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 8d1e085fc14a..e4d738d34cd0 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -591,7 +591,7 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -613,6 +613,8 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_SCTP_UNSPEC] = timeouts[CTA_TIMEOUT_SCTP_CLOSED]; return 0; } @@ -644,7 +646,7 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL @@ -743,6 +745,11 @@ static int sctp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < SCTP_CONNTRACK_MAX; i++) sn->timeouts[i] = sctp_timeouts[i]; + + /* timeouts[0] is unused, init it so ->timeouts[0] contains + * 'new' timeout, like udp or icmp. + */ + sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; } return sctp_kmemdup_sysctl_table(pn, sn); @@ -773,7 +780,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -781,7 +788,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; @@ -806,7 +813,8 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -814,8 +822,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#endif +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d80d322b9d8b..b4bdf9eda7b7 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1279,7 +1279,7 @@ static unsigned int tcp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -1301,6 +1301,7 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_SYN_SENT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; } + if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { timeouts[TCP_CONNTRACK_SYN_RECV] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; @@ -1341,6 +1342,8 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_UNACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; } + + timeouts[CTA_TIMEOUT_TCP_UNSPEC] = timeouts[CTA_TIMEOUT_TCP_SYN_SENT]; return 0; } @@ -1391,7 +1394,7 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { [CTA_TIMEOUT_TCP_RETRANS] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_UNACK] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table tcp_sysctl_table[] = { @@ -1518,6 +1521,10 @@ static int tcp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) tn->timeouts[i] = tcp_timeouts[i]; + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; tn->tcp_loose = nf_ct_tcp_loose; tn->tcp_be_liberal = nf_ct_tcp_be_liberal; tn->tcp_max_retrans = nf_ct_tcp_max_retrans; @@ -1551,7 +1558,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = .nlattr_size = TCP_NLATTR_SIZE, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1560,7 +1567,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; @@ -1586,7 +1593,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1595,7 +1602,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7a1b8988a931..3065fb8ef91b 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -171,7 +171,7 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, return NF_ACCEPT; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -221,7 +221,7 @@ udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { [CTA_TIMEOUT_UDP_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_UDP_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table udp_sysctl_table[] = { @@ -292,7 +292,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -300,7 +300,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -321,7 +321,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -329,7 +329,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -350,7 +350,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -358,7 +358,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -379,7 +379,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -387,10 +387,9 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6); #endif -#include <net/netfilter/nf_conntrack_timeout.h> diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1dca5683f59f..2cfb173cd0b2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4637,6 +4637,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; + nft_set_elem_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index d46a236cdf31..a30f8ba4b89a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -489,8 +489,8 @@ err: return err; } -static struct ctnl_timeout * -ctnl_timeout_find_get(struct net *net, const char *name) +static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, + const char *name) { struct ctnl_timeout *timeout, *matching = NULL; @@ -509,7 +509,7 @@ ctnl_timeout_find_get(struct net *net, const char *name) break; } err: - return matching; + return matching ? &matching->timeout : NULL; } static void ctnl_timeout_put(struct nf_ct_timeout *t) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea4ba551abb2..d33094f4ec41 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -233,6 +233,7 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) int err; if (verdict == NF_ACCEPT || + verdict == NF_REPEAT || verdict == NF_STOP) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 26a8baebd072..5dd87748afa8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -799,7 +799,7 @@ err: } struct nft_ct_timeout_obj { - struct nf_conn *tmpl; + struct nf_ct_timeout *timeout; u8 l4proto; }; @@ -809,26 +809,42 @@ static void nft_ct_timeout_obj_eval(struct nft_object *obj, { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb); - struct sk_buff *skb = pkt->skb; + struct nf_conn_timeout *timeout; + const unsigned int *values; + + if (priv->l4proto != pkt->tprot) + return; - if (ct || - priv->l4proto != pkt->tprot) + if (!ct || nf_ct_is_template(ct) || nf_ct_is_confirmed(ct)) return; - nf_ct_set(skb, priv->tmpl, IP_CT_NEW); + timeout = nf_ct_timeout_find(ct); + if (!timeout) { + timeout = nf_ct_timeout_ext_add(ct, priv->timeout, GFP_ATOMIC); + if (!timeout) { + regs->verdict.code = NF_DROP; + return; + } + } + + rcu_assign_pointer(timeout->timeout, priv->timeout); + + /* adjust the timeout as per 'new' state. ct is unconfirmed, + * so the current timestamp must not be added. + */ + values = nf_ct_timeout_data(timeout); + if (values) + nf_ct_refresh(ct, pkt->skb, values[0]); } static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { - const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; struct nft_ct_timeout_obj *priv = nft_obj_data(obj); const struct nf_conntrack_l4proto *l4proto; - struct nf_conn_timeout *timeout_ext; struct nf_ct_timeout *timeout; int l3num = ctx->family; - struct nf_conn *tmpl; __u8 l4num; int ret; @@ -863,28 +879,14 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, timeout->l3num = l3num; timeout->l4proto = l4proto; - tmpl = nf_ct_tmpl_alloc(ctx->net, zone, GFP_ATOMIC); - if (!tmpl) { - ret = -ENOMEM; - goto err_free_timeout; - } - - timeout_ext = nf_ct_timeout_ext_add(tmpl, timeout, GFP_ATOMIC); - if (!timeout_ext) { - ret = -ENOMEM; - goto err_free_tmpl; - } ret = nf_ct_netns_get(ctx->net, ctx->family); if (ret < 0) - goto err_free_tmpl; - - priv->tmpl = tmpl; + goto err_free_timeout; + priv->timeout = timeout; return 0; -err_free_tmpl: - nf_ct_tmpl_free(tmpl); err_free_timeout: kfree(timeout); err_proto_put: @@ -896,22 +898,19 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - struct nf_ct_timeout *timeout; + struct nf_ct_timeout *timeout = priv->timeout; - timeout = rcu_dereference_raw(t->timeout); nf_ct_untimeout(ctx->net, timeout); nf_ct_l4proto_put(timeout->l4proto); nf_ct_netns_put(ctx->net, ctx->family); - nf_ct_tmpl_free(priv->tmpl); + kfree(priv->timeout); } static int nft_ct_timeout_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - const struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - const struct nf_ct_timeout *timeout = rcu_dereference_raw(t->timeout); + const struct nf_ct_timeout *timeout = priv->timeout; struct nlattr *nest_params; int ret; diff --git a/net/netfilter/xt_CHECKSUM.c b/net/netfilter/xt_CHECKSUM.c index 9f4151ec3e06..6c7aa6a0a0d2 100644 --- a/net/netfilter/xt_CHECKSUM.c +++ b/net/netfilter/xt_CHECKSUM.c @@ -16,6 +16,9 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CHECKSUM.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michael S. Tsirkin <mst@redhat.com>"); MODULE_DESCRIPTION("Xtables: checksum modification"); @@ -25,7 +28,7 @@ MODULE_ALIAS("ip6t_CHECKSUM"); static unsigned int checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) { - if (skb->ip_summed == CHECKSUM_PARTIAL) + if (skb->ip_summed == CHECKSUM_PARTIAL && !skb_is_gso(skb)) skb_checksum_help(skb); return XT_CONTINUE; @@ -34,6 +37,8 @@ checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) static int checksum_tg_check(const struct xt_tgchk_param *par) { const struct xt_CHECKSUM_info *einfo = par->targinfo; + const struct ip6t_ip6 *i6 = par->entryinfo; + const struct ipt_ip *i4 = par->entryinfo; if (einfo->operation & ~XT_CHECKSUM_OP_FILL) { pr_info_ratelimited("unsupported CHECKSUM operation %x\n", @@ -43,6 +48,21 @@ static int checksum_tg_check(const struct xt_tgchk_param *par) if (!einfo->operation) return -EINVAL; + switch (par->family) { + case NFPROTO_IPV4: + if (i4->proto == IPPROTO_UDP && + (i4->invflags & XT_INV_PROTO) == 0) + return 0; + break; + case NFPROTO_IPV6: + if ((i6->flags & IP6T_F_PROTO) && + i6->proto == IPPROTO_UDP && + (i6->invflags & XT_INV_PROTO) == 0) + return 0; + break; + } + + pr_warn_once("CHECKSUM should be avoided. If really needed, restrict with \"-p udp\" and only use in OUTPUT\n"); return 0; } diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index dfbdbb2fc0ed..51d0c257e7a5 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -125,6 +125,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par) static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_cluster_match_info *info = par->matchinfo; + int ret; if (info->total_nodes > XT_CLUSTER_NODES_MAX) { pr_info_ratelimited("you have exceeded the maximum number of cluster nodes (%u > %u)\n", @@ -135,7 +136,17 @@ static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) pr_info_ratelimited("node mask cannot exceed total number of nodes\n"); return -EDOM; } - return 0; + + ret = nf_ct_netns_get(par->net, par->family); + if (ret < 0) + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); + return ret; +} + +static void xt_cluster_mt_destroy(const struct xt_mtdtor_param *par) +{ + nf_ct_netns_put(par->net, par->family); } static struct xt_match xt_cluster_match __read_mostly = { @@ -144,6 +155,7 @@ static struct xt_match xt_cluster_match __read_mostly = { .match = xt_cluster_mt, .checkentry = xt_cluster_mt_checkentry, .matchsize = sizeof(struct xt_cluster_match_info), + .destroy = xt_cluster_mt_destroy, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9b16402f29af..3e7d259e5d8d 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -1057,7 +1057,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); @@ -1074,7 +1074,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos) static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); @@ -1088,7 +1088,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) @@ -1130,7 +1130,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1145,7 +1145,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1160,7 +1160,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1174,7 +1174,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_show_v2(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; @@ -1188,7 +1188,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v) static int dl_seq_show_v1(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; @@ -1202,7 +1202,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) static int dl_seq_show(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5610061e7f2e..75c92a87e7b2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4137,36 +4137,52 @@ static const struct vm_operations_struct packet_mmap_ops = { .close = packet_mm_close, }; -static void free_pg_vec(struct pgv *pg_vec, unsigned int len) +static void free_pg_vec(struct pgv *pg_vec, unsigned int order, + unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { - kvfree(pg_vec[i].buffer); + if (is_vmalloc_addr(pg_vec[i].buffer)) + vfree(pg_vec[i].buffer); + else + free_pages((unsigned long)pg_vec[i].buffer, + order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } -static char *alloc_one_pg_vec_page(unsigned long size) +static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; + gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | + __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; - buffer = kvzalloc(size, GFP_KERNEL); + buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; - buffer = kvzalloc(size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + /* __get_free_pages failed, fall back to vmalloc */ + buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); + if (buffer) + return buffer; - return buffer; + /* vmalloc failed, lets dig into swap here */ + gfp_flags &= ~__GFP_NORETRY; + buffer = (char *) __get_free_pages(gfp_flags, order); + if (buffer) + return buffer; + + /* complete and utter failure */ + return NULL; } -static struct pgv *alloc_pg_vec(struct tpacket_req *req) +static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; - unsigned long size = req->tp_block_size; struct pgv *pg_vec; int i; @@ -4175,7 +4191,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req) goto out; for (i = 0; i < block_nr; i++) { - pg_vec[i].buffer = alloc_one_pg_vec_page(size); + pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } @@ -4184,7 +4200,7 @@ out: return pg_vec; out_free_pgvec: - free_pg_vec(pg_vec, block_nr); + free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } @@ -4194,9 +4210,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); + int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; - int was_running; __be16 num; int err = -EINVAL; /* Added to avoid minimal code churn */ @@ -4258,7 +4274,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; err = -ENOMEM; - pg_vec = alloc_pg_vec(req); + order = get_order(req->tp_block_size); + pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { @@ -4312,6 +4329,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); + swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; @@ -4337,7 +4355,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } if (pg_vec) - free_pg_vec(pg_vec, req->tp_block_nr); + free_pg_vec(pg_vec, order, req->tp_block_nr); out: return err; } diff --git a/net/packet/internal.h b/net/packet/internal.h index 8f50036f62f0..3bb7c5fb3bff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -64,6 +64,7 @@ struct packet_ring_buffer { unsigned int frame_size; unsigned int frame_max; + unsigned int pg_vec_order; unsigned int pg_vec_pages; unsigned int pg_vec_len; diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 01b3bd6a3708..b9092111bc45 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -1,6 +1,6 @@ config RDS - tristate "The RDS Protocol" + tristate "The Reliable Datagram Sockets Protocol" depends on INET ---help--- The RDS (Reliable Datagram Sockets) protocol provides reliable, diff --git a/net/rds/bind.c b/net/rds/bind.c index 3ab55784b637..762d2c6788a3 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -76,11 +76,13 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); - rs = rhashtable_lookup_fast(&bind_hash_table, key, ht_parms); + rcu_read_lock(); + rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) rds_sock_addref(rs); else rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); @@ -235,6 +237,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } + sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) goto out; diff --git a/net/rds/ib.c b/net/rds/ib.c index c1d97640c0be..eba75c1ba359 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -341,15 +341,10 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; - struct rdma_dev_addr *dev_addr; ic = conn->c_transport_data; - dev_addr = &ic->i_cm_id->route.addr.dev_addr; - rdma_addr_get_sgid(dev_addr, - (union ib_gid *)&iinfo6->src_gid); - rdma_addr_get_dgid(dev_addr, - (union ib_gid *)&iinfo6->dst_gid); - + rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo6->src_gid, + (union ib_gid *)&iinfo6->dst_gid); rds_ibdev = ic->rds_ibdev; iinfo6->max_send_wr = ic->i_send_ring.w_nr; iinfo6->max_recv_wr = ic->i_recv_ring.w_nr; diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 00192a996be0..0f8465852254 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/mod_devicetable.h> #include <linux/rfkill.h> #include <linux/platform_device.h> #include <linux/clk.h> diff --git a/net/sched/act_api.c b/net/sched/act_api.c index db83dac1e7f4..e12f8ef7baa4 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -662,6 +662,13 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } +static int tcf_action_destroy_1(struct tc_action *a, int bind) +{ + struct tc_action *actions[] = { a, NULL }; + + return tcf_action_destroy(actions, bind); +} + static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); @@ -881,17 +888,16 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { err = tcf_action_goto_chain_init(a, tp); if (err) { - struct tc_action *actions[] = { a, NULL }; - - tcf_action_destroy(actions, bind); + tcf_action_destroy_1(a, bind); NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); return ERR_PTR(err); } } if (!tcf_action_valid(a->tcfa_action)) { - NL_SET_ERR_MSG(extack, "invalid action value, using TC_ACT_UNSPEC instead"); - a->tcfa_action = TC_ACT_UNSPEC; + tcf_action_destroy_1(a, bind); + NL_SET_ERR_MSG(extack, "Invalid control action value"); + return ERR_PTR(-EINVAL); } return a; @@ -1173,6 +1179,7 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) struct tcf_idrinfo *idrinfo = a->idrinfo; u32 act_index = a->tcfa_index; + actions[i] = NULL; if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); @@ -1184,7 +1191,6 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) if (ret < 0) return ret; } - actions[i] = NULL; } return 0; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 196430aefe87..06a3d4801878 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -326,6 +326,20 @@ static int __add_metainfo(const struct tcf_meta_ops *ops, return ret; } +static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, + bool exists) +{ + int ret; + + if (!try_module_get(ops->owner)) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + if (ret) + module_put(ops->owner); + return ret; +} + static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, int len, bool exists) { @@ -349,7 +363,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = __add_metainfo(o, ife, o->metaid, NULL, 0, true, exists); + rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); if (rc == 0) installed += 1; } @@ -400,7 +414,6 @@ static void _tcf_ife_cleanup(struct tc_action *a) struct tcf_meta_info *e, *n; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { - module_put(e->ops->owner); list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -408,6 +421,7 @@ static void _tcf_ife_cleanup(struct tc_action *a) else kfree(e->metaval); } + module_put(e->ops->owner); kfree(e); } } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 107034070019..ad99a99f11f6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -109,16 +109,18 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, { struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX); + if (!keys_start) + goto nla_failure; for (; n > 0; n--) { struct nlattr *key_start; key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX); + if (!key_start) + goto nla_failure; if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) || - nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) { - nlmsg_trim(skb, keys_start); - return -EINVAL; - } + nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) + goto nla_failure; nla_nest_end(skb, key_start); @@ -128,6 +130,9 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, nla_nest_end(skb, keys_start); return 0; +nla_failure: + nla_nest_cancel(skb, keys_start); + return -EINVAL; } static int tcf_pedit_init(struct net *net, struct nlattr *nla, @@ -418,7 +423,10 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind; if (p->tcfp_keys_ex) { - tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys); + if (tcf_pedit_key_ex_dump(skb, + p->tcfp_keys_ex, + p->tcfp_nkeys)) + goto nla_put_failure; if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt)) goto nla_put_failure; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 44e9c00657bc..6b67aa13d2dd 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/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 420759153d5f..681f6f04e7da 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -317,7 +317,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &metadata->u.tun_info, opts_len, extack); if (ret < 0) - goto err_out; + goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; @@ -333,23 +333,24 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); - goto err_out; + goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!ovr) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "TC IDR already exists"); - return -EEXIST; + ret = -EEXIST; + goto release_tun_meta; } t = to_tunnel_key(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); - return -ENOMEM; + ret = -ENOMEM; + exists = true; + goto release_tun_meta; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -367,6 +368,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; +release_tun_meta: + dst_release(&metadata->dst); + err_out: if (exists) tcf_idr_release(*a, bind); @@ -408,8 +412,10 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, opt->type) || nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, - opt->length * 4, opt + 1)) + opt->length * 4, opt + 1)) { + nla_nest_cancel(skb, start); return -EMSGSIZE; + } len -= sizeof(struct geneve_opt) + opt->length * 4; src += sizeof(struct geneve_opt) + opt->length * 4; @@ -423,7 +429,7 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct nlattr *start; - int err; + int err = -EINVAL; if (!info->options_len) return 0; @@ -435,9 +441,11 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) - return err; + goto err_out; } else { - return -EINVAL; +err_out: + nla_nest_cancel(skb, start); + return err; } nla_nest_end(skb, start); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 31bd1439cf60..0a75cb2e5e7b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1252,7 +1252,7 @@ replay: } chain = tcf_chain_get(block, chain_index, true); if (!chain) { - NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + NL_SET_ERR_MSG(extack, "Cannot create specified filter chain"); err = -ENOMEM; goto errout; } @@ -1399,7 +1399,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); - err = -EINVAL; + err = -ENOENT; goto errout; } @@ -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/sctp/proc.c b/net/sctp/proc.c index ef5c9a82d4e8..a644292f9faf 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -215,7 +215,6 @@ static const struct seq_operations sctp_eps_ops = { struct sctp_ht_iter { struct seq_net_private p; struct rhashtable_iter hti; - int start_fail; }; static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) @@ -224,7 +223,6 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) sctp_transport_walk_start(&iter->hti); - iter->start_fail = 0; return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos); } @@ -232,8 +230,6 @@ static void sctp_transport_seq_stop(struct seq_file *seq, void *v) { struct sctp_ht_iter *iter = seq->private; - if (iter->start_fail) - return; sctp_transport_walk_stop(&iter->hti); } @@ -264,8 +260,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; - if (!sctp_transport_hold(transport)) - return 0; assoc = transport->asoc; epb = &assoc->base; sk = epb->sk; @@ -322,8 +316,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; - if (!sctp_transport_hold(transport)) - return 0; assoc = transport->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e96b15a66aba..f73e9d38d5ba 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2658,20 +2658,23 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } if (params->spp_flags & SPP_IPV6_FLOWLABEL) { - if (trans && trans->ipaddr.sa.sa_family == AF_INET6) { - trans->flowlabel = params->spp_ipv6_flowlabel & - SCTP_FLOWLABEL_VAL_MASK; - trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; - } else if (asoc) { - list_for_each_entry(trans, - &asoc->peer.transport_addr_list, - transports) { - if (trans->ipaddr.sa.sa_family != AF_INET6) - continue; + if (trans) { + if (trans->ipaddr.sa.sa_family == AF_INET6) { trans->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } + } else if (asoc) { + struct sctp_transport *t; + + list_for_each_entry(t, &asoc->peer.transport_addr_list, + transports) { + if (t->ipaddr.sa.sa_family != AF_INET6) + continue; + t->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + t->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } asoc->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK; @@ -2687,12 +2690,13 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; trans->dscp |= SCTP_DSCP_SET_MASK; } else if (asoc) { - list_for_each_entry(trans, - &asoc->peer.transport_addr_list, + struct sctp_transport *t; + + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { - trans->dscp = params->spp_dscp & - SCTP_DSCP_VAL_MASK; - trans->dscp |= SCTP_DSCP_SET_MASK; + t->dscp = params->spp_dscp & + SCTP_DSCP_VAL_MASK; + t->dscp |= SCTP_DSCP_SET_MASK; } asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; asoc->dscp |= SCTP_DSCP_SET_MASK; @@ -5005,9 +5009,14 @@ struct sctp_transport *sctp_transport_get_next(struct net *net, break; } + if (!sctp_transport_hold(t)) + continue; + if (net_eq(sock_net(t->asoc->base.sk), net) && t->asoc->peer.primary_path == t) break; + + sctp_transport_put(t); } return t; @@ -5017,13 +5026,18 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos) { - void *obj = SEQ_START_TOKEN; + struct sctp_transport *t; - while (pos && (obj = sctp_transport_get_next(net, iter)) && - !IS_ERR(obj)) - pos--; + if (!pos) + return SEQ_START_TOKEN; - return obj; + while ((t = sctp_transport_get_next(net, iter)) && !IS_ERR(t)) { + if (!--pos) + break; + sctp_transport_put(t); + } + + return t; } int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), @@ -5082,8 +5096,6 @@ again: tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { - if (!sctp_transport_hold(tsp)) - continue; ret = cb(tsp, p); if (ret) break; 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/tipc/bcast.c b/net/tipc/bcast.c index 9ee6cfea56dd..d8026543bf4c 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -51,12 +51,12 @@ const char tipc_bclink_name[] = "broadcast-link"; * struct tipc_bc_base - base structure for keeping broadcast send state * @link: broadcast send link structure * @inputq: data input queue; will only carry SOCK_WAKEUP messages - * @dest: array keeping number of reachable destinations per bearer + * @dests: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast * @rcast_support: indicates if all peer nodes support replicast * @rc_ratio: dest count as percentage of cluster size where send method changes - * @bc_threshold: calculated drom rc_ratio; if dests > threshold use broadcast + * @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast */ struct tipc_bc_base { struct tipc_link *link; diff --git a/net/tipc/diag.c b/net/tipc/diag.c index aaabb0b776dd..73137f4aeb68 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -84,7 +84,9 @@ static int tipc_sock_diag_handler_dump(struct sk_buff *skb, if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = tipc_dump_start, .dump = tipc_diag_dump, + .done = tipc_dump_done, }; netlink_dump_start(net->diag_nlsk, skb, h, &c); return 0; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 88f027b502f6..66d5b2c5987a 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -980,20 +980,17 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; list_for_each_entry(dst, l, list) { - if (dst->value != value) - continue; - return dst; + if (dst->node == node && dst->port == port) + return dst; } return NULL; } bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; if (tipc_dest_find(l, node, port)) @@ -1002,7 +999,8 @@ bool tipc_dest_push(struct list_head *l, u32 node, u32 port) dst = kmalloc(sizeof(*dst), GFP_ATOMIC); if (unlikely(!dst)) return false; - dst->value = value; + dst->node = node; + dst->port = port; list_add(&dst->list, l); return true; } diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 0febba41da86..892bd750b85f 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -133,13 +133,8 @@ void tipc_nametbl_stop(struct net *net); struct tipc_dest { struct list_head list; - union { - struct { - u32 port; - u32 node; - }; - u64 value; - }; + u32 port; + u32 node; }; struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 6ff2254088f6..99ee419210ba 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -167,7 +167,9 @@ static const struct genl_ops tipc_genl_v2_ops[] = { }, { .cmd = TIPC_NL_SOCK_GET, + .start = tipc_dump_start, .dumpit = tipc_nl_sk_dump, + .done = tipc_dump_done, .policy = tipc_nl_policy, }, { diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index a2f76743c73a..6376467e78f8 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -185,6 +185,10 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; buf->sk = msg->dst_sk; + if (__tipc_dump_start(&cb, msg->net)) { + kfree_skb(buf); + return -ENOMEM; + } do { int rem; @@ -216,6 +220,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, err = 0; err_out: + tipc_dump_done(&cb); kfree_skb(buf); if (err == -EMSGSIZE) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c1e93c9515bc..3f03ddd0e35b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -576,6 +576,7 @@ static int tipc_release(struct socket *sock) sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); + sock_orphan(sk); /* Reject any messages that accumulated in backlog queue */ release_sock(sk); tipc_dest_list_purge(&tsk->cong_links); @@ -2672,6 +2673,8 @@ void tipc_sk_reinit(struct net *net) rhashtable_walk_stop(&iter); } while (tsk == ERR_PTR(-EAGAIN)); + + rhashtable_walk_exit(&iter); } static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) @@ -3227,45 +3230,74 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)) { - struct net *net = sock_net(skb->sk); - struct tipc_net *tn = tipc_net(net); - const struct bucket_table *tbl; - u32 prev_portid = cb->args[1]; - u32 tbl_id = cb->args[0]; - struct rhash_head *pos; + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_sock *tsk; int err; - rcu_read_lock(); - tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht); - for (; tbl_id < tbl->size; tbl_id++) { - rht_for_each_entry_rcu(tsk, pos, tbl, tbl_id, node) { - spin_lock_bh(&tsk->sk.sk_lock.slock); - if (prev_portid && prev_portid != tsk->portid) { - spin_unlock_bh(&tsk->sk.sk_lock.slock); + rhashtable_walk_start(iter); + while ((tsk = rhashtable_walk_next(iter)) != NULL) { + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + if (err == -EAGAIN) { + err = 0; continue; } + break; + } - err = skb_handler(skb, cb, tsk); - if (err) { - prev_portid = tsk->portid; - spin_unlock_bh(&tsk->sk.sk_lock.slock); - goto out; - } - - prev_portid = 0; - spin_unlock_bh(&tsk->sk.sk_lock.slock); + sock_hold(&tsk->sk); + rhashtable_walk_stop(iter); + lock_sock(&tsk->sk); + err = skb_handler(skb, cb, tsk); + if (err) { + release_sock(&tsk->sk); + sock_put(&tsk->sk); + goto out; } + release_sock(&tsk->sk); + rhashtable_walk_start(iter); + sock_put(&tsk->sk); } + rhashtable_walk_stop(iter); out: - rcu_read_unlock(); - cb->args[0] = tbl_id; - cb->args[1] = prev_portid; - return skb->len; } EXPORT_SYMBOL(tipc_nl_sk_walk); +int tipc_dump_start(struct netlink_callback *cb) +{ + return __tipc_dump_start(cb, sock_net(cb->skb->sk)); +} +EXPORT_SYMBOL(tipc_dump_start); + +int __tipc_dump_start(struct netlink_callback *cb, struct net *net) +{ + /* tipc_nl_name_table_dump() uses cb->args[0...3]. */ + struct rhashtable_iter *iter = (void *)cb->args[4]; + struct tipc_net *tn = tipc_net(net); + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[4] = (long)iter; + } + + rhashtable_walk_enter(&tn->sk_rht, iter); + return 0; +} + +int tipc_dump_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *hti = (void *)cb->args[4]; + + rhashtable_walk_exit(hti); + kfree(hti); + return 0; +} +EXPORT_SYMBOL(tipc_dump_done); + int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk, u32 sk_filter_state, u64 (*tipc_diag_gen_cookie)(struct sock *sk)) diff --git a/net/tipc/socket.h b/net/tipc/socket.h index aff9b2ae5a1f..5e575f205afe 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -68,4 +68,7 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, int (*skb_handler)(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk)); +int tipc_dump_start(struct netlink_callback *cb); +int __tipc_dump_start(struct netlink_callback *cb, struct net *net); +int tipc_dump_done(struct netlink_callback *cb); #endif diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index c8e34ef22c30..2627b5d812e9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -313,8 +313,8 @@ static void tipc_conn_send_work(struct work_struct *work) conn_put(con); } -/* tipc_conn_queue_evt() - interrupt level call from a subscription instance - * The queued work is launched into tipc_send_work()->tipc_send_to_sock() +/* tipc_topsrv_queue_evt() - interrupt level call from a subscription instance + * The queued work is launched into tipc_conn_send_work()->tipc_conn_send_to_sock() */ void tipc_topsrv_queue_evt(struct net *net, int conid, u32 event, struct tipc_event *evt) 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 52fbe727d7c1..b9c6ecfbcfea 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -125,6 +125,9 @@ static int alloc_encrypted_sg(struct sock *sk, int len) &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0); + if (rc == -ENOSPC) + ctx->sg_encrypted_num_elem = ARRAY_SIZE(ctx->sg_encrypted_data); + return rc; } @@ -138,6 +141,9 @@ static int alloc_plaintext_sg(struct sock *sk, int len) &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, tls_ctx->pending_open_record_frags); + if (rc == -ENOSPC) + ctx->sg_plaintext_num_elem = ARRAY_SIZE(ctx->sg_plaintext_data); + return rc; } @@ -925,7 +931,15 @@ int tls_sw_recvmsg(struct sock *sk, if (control != TLS_RECORD_TYPE_DATA) goto recv_end; } + } 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. */ if (copied >= target && !ctx->recv_pkt) break; @@ -1049,8 +1063,8 @@ 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; } @@ -1130,7 +1144,6 @@ 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; @@ -1175,12 +1188,12 @@ 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; } @@ -1259,9 +1272,7 @@ 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/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5fb9b7dd9831..4b8ec659e797 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -669,13 +669,13 @@ static int nl80211_msg_put_wmm_rules(struct sk_buff *msg, goto nla_put_failure; if (nla_put_u16(msg, NL80211_WMMR_CW_MIN, - rule->wmm_rule->client[j].cw_min) || + rule->wmm_rule.client[j].cw_min) || nla_put_u16(msg, NL80211_WMMR_CW_MAX, - rule->wmm_rule->client[j].cw_max) || + rule->wmm_rule.client[j].cw_max) || nla_put_u8(msg, NL80211_WMMR_AIFSN, - rule->wmm_rule->client[j].aifsn) || - nla_put_u8(msg, NL80211_WMMR_TXOP, - rule->wmm_rule->client[j].cot)) + rule->wmm_rule.client[j].aifsn) || + nla_put_u16(msg, NL80211_WMMR_TXOP, + rule->wmm_rule.client[j].cot)) goto nla_put_failure; nla_nest_end(msg, nl_wmm_rule); @@ -766,9 +766,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if (large) { const struct ieee80211_reg_rule *rule = - freq_reg_info(wiphy, chan->center_freq); + freq_reg_info(wiphy, MHZ_TO_KHZ(chan->center_freq)); - if (!IS_ERR(rule) && rule->wmm_rule) { + if (!IS_ERR_OR_NULL(rule) && rule->has_wmm) { if (nl80211_msg_put_wmm_rules(msg, rule)) goto nla_put_failure; } @@ -12205,6 +12205,7 @@ static int nl80211_update_ft_ies(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; if (!info->attrs[NL80211_ATTR_MDID] || + !info->attrs[NL80211_ATTR_IE] || !is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 4fc66a117b7d..2f702adf2912 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -425,36 +425,23 @@ static const struct ieee80211_regdomain * reg_copy_regd(const struct ieee80211_regdomain *src_regd) { struct ieee80211_regdomain *regd; - int size_of_regd, size_of_wmms; + int size_of_regd; unsigned int i; - struct ieee80211_wmm_rule *d_wmm, *s_wmm; size_of_regd = sizeof(struct ieee80211_regdomain) + src_regd->n_reg_rules * sizeof(struct ieee80211_reg_rule); - size_of_wmms = src_regd->n_wmm_rules * - sizeof(struct ieee80211_wmm_rule); - regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL); + regd = kzalloc(size_of_regd, GFP_KERNEL); if (!regd) return ERR_PTR(-ENOMEM); memcpy(regd, src_regd, sizeof(struct ieee80211_regdomain)); - d_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd); - s_wmm = (struct ieee80211_wmm_rule *)((u8 *)src_regd + size_of_regd); - memcpy(d_wmm, s_wmm, size_of_wmms); - - for (i = 0; i < src_regd->n_reg_rules; i++) { + for (i = 0; i < src_regd->n_reg_rules; i++) memcpy(®d->reg_rules[i], &src_regd->reg_rules[i], sizeof(struct ieee80211_reg_rule)); - if (!src_regd->reg_rules[i].wmm_rule) - continue; - regd->reg_rules[i].wmm_rule = d_wmm + - (src_regd->reg_rules[i].wmm_rule - s_wmm) / - sizeof(struct ieee80211_wmm_rule); - } return regd; } @@ -860,9 +847,10 @@ static bool valid_regdb(const u8 *data, unsigned int size) return true; } -static void set_wmm_rule(struct ieee80211_wmm_rule *rule, +static void set_wmm_rule(struct ieee80211_reg_rule *rrule, struct fwdb_wmm_rule *wmm) { + struct ieee80211_wmm_rule *rule = &rrule->wmm_rule; unsigned int i; for (i = 0; i < IEEE80211_NUM_ACS; i++) { @@ -876,11 +864,13 @@ static void set_wmm_rule(struct ieee80211_wmm_rule *rule, rule->ap[i].aifsn = wmm->ap[i].aifsn; rule->ap[i].cot = 1000 * be16_to_cpu(wmm->ap[i].cot); } + + rrule->has_wmm = true; } static int __regdb_query_wmm(const struct fwdb_header *db, const struct fwdb_country *country, int freq, - u32 *dbptr, struct ieee80211_wmm_rule *rule) + struct ieee80211_reg_rule *rule) { unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; struct fwdb_collection *coll = (void *)((u8 *)db + ptr); @@ -901,8 +891,6 @@ static int __regdb_query_wmm(const struct fwdb_header *db, wmm_ptr = be16_to_cpu(rrule->wmm_ptr) << 2; wmm = (void *)((u8 *)db + wmm_ptr); set_wmm_rule(rule, wmm); - if (dbptr) - *dbptr = wmm_ptr; return 0; } } @@ -910,8 +898,7 @@ static int __regdb_query_wmm(const struct fwdb_header *db, return -ENODATA; } -int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, - struct ieee80211_wmm_rule *rule) +int reg_query_regdb_wmm(char *alpha2, int freq, struct ieee80211_reg_rule *rule) { const struct fwdb_header *hdr = regdb; const struct fwdb_country *country; @@ -925,8 +912,7 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, country = &hdr->country[0]; while (country->coll_ptr) { if (alpha2_equal(alpha2, country->alpha2)) - return __regdb_query_wmm(regdb, country, freq, dbptr, - rule); + return __regdb_query_wmm(regdb, country, freq, rule); country++; } @@ -935,32 +921,13 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, } EXPORT_SYMBOL(reg_query_regdb_wmm); -struct wmm_ptrs { - struct ieee80211_wmm_rule *rule; - u32 ptr; -}; - -static struct ieee80211_wmm_rule *find_wmm_ptr(struct wmm_ptrs *wmm_ptrs, - u32 wmm_ptr, int n_wmms) -{ - int i; - - for (i = 0; i < n_wmms; i++) { - if (wmm_ptrs[i].ptr == wmm_ptr) - return wmm_ptrs[i].rule; - } - return NULL; -} - static int regdb_query_country(const struct fwdb_header *db, const struct fwdb_country *country) { unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; struct fwdb_collection *coll = (void *)((u8 *)db + ptr); struct ieee80211_regdomain *regdom; - struct ieee80211_regdomain *tmp_rd; - unsigned int size_of_regd, i, n_wmms = 0; - struct wmm_ptrs *wmm_ptrs; + unsigned int size_of_regd, i; size_of_regd = sizeof(struct ieee80211_regdomain) + coll->n_rules * sizeof(struct ieee80211_reg_rule); @@ -969,12 +936,6 @@ static int regdb_query_country(const struct fwdb_header *db, if (!regdom) return -ENOMEM; - wmm_ptrs = kcalloc(coll->n_rules, sizeof(*wmm_ptrs), GFP_KERNEL); - if (!wmm_ptrs) { - kfree(regdom); - return -ENOMEM; - } - regdom->n_reg_rules = coll->n_rules; regdom->alpha2[0] = country->alpha2[0]; regdom->alpha2[1] = country->alpha2[1]; @@ -1013,37 +974,11 @@ static int regdb_query_country(const struct fwdb_header *db, 1000 * be16_to_cpu(rule->cac_timeout); if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) { u32 wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2; - struct ieee80211_wmm_rule *wmm_pos = - find_wmm_ptr(wmm_ptrs, wmm_ptr, n_wmms); - struct fwdb_wmm_rule *wmm; - struct ieee80211_wmm_rule *wmm_rule; - - if (wmm_pos) { - rrule->wmm_rule = wmm_pos; - continue; - } - wmm = (void *)((u8 *)db + wmm_ptr); - tmp_rd = krealloc(regdom, size_of_regd + (n_wmms + 1) * - sizeof(struct ieee80211_wmm_rule), - GFP_KERNEL); - - if (!tmp_rd) { - kfree(regdom); - kfree(wmm_ptrs); - return -ENOMEM; - } - regdom = tmp_rd; - - wmm_rule = (struct ieee80211_wmm_rule *) - ((u8 *)regdom + size_of_regd + n_wmms * - sizeof(struct ieee80211_wmm_rule)); + struct fwdb_wmm_rule *wmm = (void *)((u8 *)db + wmm_ptr); - set_wmm_rule(wmm_rule, wmm); - wmm_ptrs[n_wmms].ptr = wmm_ptr; - wmm_ptrs[n_wmms++].rule = wmm_rule; + set_wmm_rule(rrule, wmm); } } - kfree(wmm_ptrs); return reg_schedule_apply(regdom); } diff --git a/net/wireless/util.c b/net/wireless/util.c index e0825a019e9f..959ed3acd240 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1456,7 +1456,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class) { u8 vht_opclass; - u16 freq = chandef->center_freq1; + u32 freq = chandef->center_freq1; if (freq >= 2412 && freq <= 2472) { if (chandef->width > NL80211_CHAN_WIDTH_40) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 5219280bf7ff..161b0224d6ae 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -380,6 +380,7 @@ our $Attribute = qr{ __noclone| __deprecated| __read_mostly| + __ro_after_init| __kprobes| $InitAttribute| ____cacheline_aligned| @@ -3311,7 +3312,7 @@ sub process { # known declaration macros $sline =~ /^\+\s+$declaration_macros/ || # start of struct or union or enum - $sline =~ /^\+\s+(?:union|struct|enum|typedef)\b/ || + $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || # start or end of block or continuation of declaration $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || # bitfield continuation diff --git a/scripts/depmod.sh b/scripts/depmod.sh index 999d585eaa73..e083bcae343f 100755 --- a/scripts/depmod.sh +++ b/scripts/depmod.sh @@ -11,13 +11,14 @@ DEPMOD=$1 KERNELRELEASE=$2 if ! test -r System.map ; then + echo "Warning: modules_install: missing 'System.map' file. Skipping depmod." >&2 exit 0 fi if [ -z $(command -v $DEPMOD) ]; then - echo "'make modules_install' requires $DEPMOD. Please install it." >&2 + echo "Warning: 'make modules_install' requires $DEPMOD. Please install it." >&2 echo "This is probably in the kmod package." >&2 - exit 1 + exit 0 fi # older versions of depmod require the version string to start with three diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 4a7bd2192073..67ed9f6ccdf8 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -221,7 +221,6 @@ $(obj)/zconf.tab.o: $(obj)/zconf.lex.c # check if necessary packages are available, and configure build flags define filechk_conf_cfg - $(CONFIG_SHELL) $(srctree)/scripts/kconfig/check-pkgconfig.sh; \ $(CONFIG_SHELL) $< endef diff --git a/scripts/kconfig/check-pkgconfig.sh b/scripts/kconfig/check-pkgconfig.sh deleted file mode 100644 index 7a1c40bfb58c..000000000000 --- a/scripts/kconfig/check-pkgconfig.sh +++ /dev/null @@ -1,8 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# Check for pkg-config presence - -if [ -z $(command -v pkg-config) ]; then - echo "'make *config' requires 'pkg-config'. Please install it." 1>&2 - exit 1 -fi diff --git a/scripts/kconfig/gconf-cfg.sh b/scripts/kconfig/gconf-cfg.sh index 533b3d8f8f08..480ecd8b9f41 100755 --- a/scripts/kconfig/gconf-cfg.sh +++ b/scripts/kconfig/gconf-cfg.sh @@ -3,6 +3,13 @@ PKG="gtk+-2.0 gmodule-2.0 libglade-2.0" +if [ -z "$(command -v pkg-config)" ]; then + echo >&2 "*" + echo >&2 "* 'make gconfig' requires 'pkg-config'. Please install it." + echo >&2 "*" + exit 1 +fi + if ! pkg-config --exists $PKG; then echo >&2 "*" echo >&2 "* Unable to find the GTK+ installation. Please make sure that" diff --git a/scripts/kconfig/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh index e6f9facd0077..c812872d7f9d 100755 --- a/scripts/kconfig/mconf-cfg.sh +++ b/scripts/kconfig/mconf-cfg.sh @@ -4,20 +4,23 @@ PKG="ncursesw" PKG2="ncurses" -if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" - exit 0 -fi +if [ -n "$(command -v pkg-config)" ]; then + if pkg-config --exists $PKG; then + echo cflags=\"$(pkg-config --cflags $PKG)\" + echo libs=\"$(pkg-config --libs $PKG)\" + exit 0 + fi -if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" - exit 0 + if pkg-config --exists $PKG2; then + echo cflags=\"$(pkg-config --cflags $PKG2)\" + echo libs=\"$(pkg-config --libs $PKG2)\" + exit 0 + fi fi -# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses -# by pkg-config. +# Check the default paths in case pkg-config is not installed. +# (Even if it is installed, some distributions such as openSUSE cannot +# find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\" echo libs=\"-lncursesw\" diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c index 83b5836615fb..143c05fec161 100644 --- a/scripts/kconfig/mconf.c +++ b/scripts/kconfig/mconf.c @@ -490,7 +490,6 @@ static void build_conf(struct menu *menu) switch (prop->type) { case P_MENU: child_count++; - prompt = prompt; if (single_menu_mode) { item_make("%s%*c%s", menu->data ? "-->" : "++>", diff --git a/scripts/kconfig/nconf-cfg.sh b/scripts/kconfig/nconf-cfg.sh index 42f5ac73548e..001559ef0a60 100644 --- a/scripts/kconfig/nconf-cfg.sh +++ b/scripts/kconfig/nconf-cfg.sh @@ -4,20 +4,23 @@ PKG="ncursesw menuw panelw" PKG2="ncurses menu panel" -if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" - exit 0 -fi +if [ -n "$(command -v pkg-config)" ]; then + if pkg-config --exists $PKG; then + echo cflags=\"$(pkg-config --cflags $PKG)\" + echo libs=\"$(pkg-config --libs $PKG)\" + exit 0 + fi -if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" - exit 0 + if pkg-config --exists $PKG2; then + echo cflags=\"$(pkg-config --cflags $PKG2)\" + echo libs=\"$(pkg-config --libs $PKG2)\" + exit 0 + fi fi -# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses -# by pkg-config. +# Check the default paths in case pkg-config is not installed. +# (Even if it is installed, some distributions such as openSUSE cannot +# find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\" echo libs=\"-lncursesw -lmenuw -lpanelw\" diff --git a/scripts/kconfig/qconf-cfg.sh b/scripts/kconfig/qconf-cfg.sh index 0862e1562536..02ccc0ae1031 100755 --- a/scripts/kconfig/qconf-cfg.sh +++ b/scripts/kconfig/qconf-cfg.sh @@ -4,6 +4,13 @@ PKG="Qt5Core Qt5Gui Qt5Widgets" PKG2="QtCore QtGui" +if [ -z "$(command -v pkg-config)" ]; then + echo >&2 "*" + echo >&2 "* 'make xconfig' requires 'pkg-config'. Please install it." + echo >&2 "*" + exit 1 +fi + if pkg-config --exists $PKG; then echo cflags=\"-std=c++11 -fPIC $(pkg-config --cflags Qt5Core Qt5Gui Qt5Widgets)\" echo libs=\"$(pkg-config --libs $PKG)\" diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index fe06e77c15eb..f599031260d5 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -389,6 +389,9 @@ if ($arch eq "x86_64") { $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL\\s_mcount\$"; $type = ".quad"; $alignment = 2; +} elsif ($arch eq "nds32") { + $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_NDS32_HI20_RELA\\s+_mcount\$"; + $alignment = 2; } else { die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD"; } diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 71f39410691b..79f7dd57d571 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -74,7 +74,7 @@ scm_version() fi # Check for uncommitted changes - if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then + if git status -uno --porcelain | grep -qv '^.. scripts/package'; then printf '%s' -dirty fi 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/security/apparmor/secid.c b/security/apparmor/secid.c index f2f22d00db18..4ccec1bcf6f5 100644 --- a/security/apparmor/secid.c +++ b/security/apparmor/secid.c @@ -79,7 +79,6 @@ int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) struct aa_label *label = aa_secid_to_label(secid); int len; - AA_BUG(!secdata); AA_BUG(!seclen); if (!label) diff --git a/security/keys/dh.c b/security/keys/dh.c index 711e89d8c415..3b602a1e27fa 100644 --- a/security/keys/dh.c +++ b/security/keys/dh.c @@ -300,7 +300,7 @@ long __keyctl_dh_compute(struct keyctl_dh_params __user *params, } dh_inputs.g_size = dlen; - dlen = dh_data_from_key(pcopy.private, &dh_inputs.key); + dlen = dh_data_from_key(pcopy.dh_private, &dh_inputs.key); if (dlen < 0) { ret = dlen; goto out2; diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 69517e18ef07..08d5662039e3 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -129,7 +129,7 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) runtime->avail = 0; else runtime->avail = runtime->buffer_size; - runtime->buffer = kvmalloc(runtime->buffer_size, GFP_KERNEL); + runtime->buffer = kvzalloc(runtime->buffer_size, GFP_KERNEL); if (!runtime->buffer) { kfree(runtime); return -ENOMEM; @@ -655,7 +655,7 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime, if (params->avail_min < 1 || params->avail_min > params->buffer_size) return -EINVAL; if (params->buffer_size != runtime->buffer_size) { - newbuf = kvmalloc(params->buffer_size, GFP_KERNEL); + newbuf = kvzalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock); diff --git a/sound/firewire/bebob/bebob.c b/sound/firewire/bebob/bebob.c index 730ea91d9be8..93676354f87f 100644 --- a/sound/firewire/bebob/bebob.c +++ b/sound/firewire/bebob/bebob.c @@ -263,6 +263,8 @@ do_registration(struct work_struct *work) error: mutex_unlock(&devices_mutex); snd_bebob_stream_destroy_duplex(bebob); + kfree(bebob->maudio_special_quirk); + bebob->maudio_special_quirk = NULL; snd_card_free(bebob->card); dev_info(&bebob->unit->device, "Sound card registration failed: %d\n", err); diff --git a/sound/firewire/bebob/bebob_maudio.c b/sound/firewire/bebob/bebob_maudio.c index bd55620c6a47..c266997ad299 100644 --- a/sound/firewire/bebob/bebob_maudio.c +++ b/sound/firewire/bebob/bebob_maudio.c @@ -96,17 +96,13 @@ int snd_bebob_maudio_load_firmware(struct fw_unit *unit) struct fw_device *device = fw_parent_device(unit); int err, rcode; u64 date; - __le32 cues[3] = { - cpu_to_le32(MAUDIO_BOOTLOADER_CUE1), - cpu_to_le32(MAUDIO_BOOTLOADER_CUE2), - cpu_to_le32(MAUDIO_BOOTLOADER_CUE3) - }; + __le32 *cues; /* check date of software used to build */ err = snd_bebob_read_block(unit, INFO_OFFSET_SW_DATE, &date, sizeof(u64)); if (err < 0) - goto end; + return err; /* * firmware version 5058 or later has date later than "20070401", but * 'date' is not null-terminated. @@ -114,20 +110,28 @@ int snd_bebob_maudio_load_firmware(struct fw_unit *unit) if (date < 0x3230303730343031LL) { dev_err(&unit->device, "Use firmware version 5058 or later\n"); - err = -ENOSYS; - goto end; + return -ENXIO; } + cues = kmalloc_array(3, sizeof(*cues), GFP_KERNEL); + if (!cues) + return -ENOMEM; + + cues[0] = cpu_to_le32(MAUDIO_BOOTLOADER_CUE1); + cues[1] = cpu_to_le32(MAUDIO_BOOTLOADER_CUE2); + cues[2] = cpu_to_le32(MAUDIO_BOOTLOADER_CUE3); + rcode = fw_run_transaction(device->card, TCODE_WRITE_BLOCK_REQUEST, device->node_id, device->generation, device->max_speed, BEBOB_ADDR_REG_REQ, - cues, sizeof(cues)); + cues, 3 * sizeof(*cues)); + kfree(cues); if (rcode != RCODE_COMPLETE) { dev_err(&unit->device, "Failed to send a cue to load firmware\n"); err = -EIO; } -end: + return err; } @@ -290,10 +294,6 @@ snd_bebob_maudio_special_discover(struct snd_bebob *bebob, bool is1814) bebob->midi_output_ports = 2; } end: - if (err < 0) { - kfree(params); - bebob->maudio_special_quirk = NULL; - } mutex_unlock(&bebob->mutex); return err; } diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c index 1f5e1d23f31a..ef689997d6a5 100644 --- a/sound/firewire/digi00x/digi00x.c +++ b/sound/firewire/digi00x/digi00x.c @@ -49,6 +49,7 @@ static void dg00x_free(struct snd_dg00x *dg00x) fw_unit_put(dg00x->unit); mutex_destroy(&dg00x->mutex); + kfree(dg00x); } static void dg00x_card_free(struct snd_card *card) diff --git a/sound/firewire/fireface/ff-protocol-ff400.c b/sound/firewire/fireface/ff-protocol-ff400.c index ad7a0a32557d..64c3cb0fb926 100644 --- a/sound/firewire/fireface/ff-protocol-ff400.c +++ b/sound/firewire/fireface/ff-protocol-ff400.c @@ -146,6 +146,7 @@ static int ff400_switch_fetching_mode(struct snd_ff *ff, bool enable) { __le32 *reg; int i; + int err; reg = kcalloc(18, sizeof(__le32), GFP_KERNEL); if (reg == NULL) @@ -163,9 +164,11 @@ static int ff400_switch_fetching_mode(struct snd_ff *ff, bool enable) reg[i] = cpu_to_le32(0x00000001); } - return snd_fw_transaction(ff->unit, TCODE_WRITE_BLOCK_REQUEST, - FF400_FETCH_PCM_FRAMES, reg, - sizeof(__le32) * 18, 0); + err = snd_fw_transaction(ff->unit, TCODE_WRITE_BLOCK_REQUEST, + FF400_FETCH_PCM_FRAMES, reg, + sizeof(__le32) * 18, 0); + kfree(reg); + return err; } static void ff400_dump_sync_status(struct snd_ff *ff, diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c index 71a0613d3da0..f2d073365cf6 100644 --- a/sound/firewire/fireworks/fireworks.c +++ b/sound/firewire/fireworks/fireworks.c @@ -301,6 +301,8 @@ error: snd_efw_transaction_remove_instance(efw); snd_efw_stream_destroy_duplex(efw); snd_card_free(efw->card); + kfree(efw->resp_buf); + efw->resp_buf = NULL; dev_info(&efw->unit->device, "Sound card registration failed: %d\n", err); } diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index 1e5b2c802635..2ea8be6c8584 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -130,6 +130,7 @@ static void oxfw_free(struct snd_oxfw *oxfw) kfree(oxfw->spec); mutex_destroy(&oxfw->mutex); + kfree(oxfw); } /* @@ -207,6 +208,7 @@ static int detect_quirks(struct snd_oxfw *oxfw) static void do_registration(struct work_struct *work) { struct snd_oxfw *oxfw = container_of(work, struct snd_oxfw, dwork.work); + int i; int err; if (oxfw->registered) @@ -269,7 +271,15 @@ error: snd_oxfw_stream_destroy_simplex(oxfw, &oxfw->rx_stream); if (oxfw->has_output) snd_oxfw_stream_destroy_simplex(oxfw, &oxfw->tx_stream); + for (i = 0; i < SND_OXFW_STREAM_FORMAT_ENTRIES; ++i) { + kfree(oxfw->tx_stream_formats[i]); + oxfw->tx_stream_formats[i] = NULL; + kfree(oxfw->rx_stream_formats[i]); + oxfw->rx_stream_formats[i] = NULL; + } snd_card_free(oxfw->card); + kfree(oxfw->spec); + oxfw->spec = NULL; dev_info(&oxfw->unit->device, "Sound card registration failed: %d\n", err); } diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c index 44ad41fb7374..d3fdc463a884 100644 --- a/sound/firewire/tascam/tascam.c +++ b/sound/firewire/tascam/tascam.c @@ -93,6 +93,7 @@ static void tscm_free(struct snd_tscm *tscm) fw_unit_put(tscm->unit); mutex_destroy(&tscm->mutex); + kfree(tscm); } static void tscm_card_free(struct snd_card *card) diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index 1bd27576db98..a835558ddbc9 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -146,7 +146,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_decouple); */ void snd_hdac_ext_link_stream_start(struct hdac_ext_stream *stream) { - snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, 0, AZX_PPLCCTL_RUN); + snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, + AZX_PPLCCTL_RUN, AZX_PPLCCTL_RUN); } EXPORT_SYMBOL_GPL(snd_hdac_ext_link_stream_start); @@ -171,7 +172,8 @@ void snd_hdac_ext_link_stream_reset(struct hdac_ext_stream *stream) snd_hdac_ext_link_stream_clear(stream); - snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, 0, AZX_PPLCCTL_STRST); + snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, + AZX_PPLCCTL_STRST, AZX_PPLCCTL_STRST); udelay(3); timeout = 50; do { @@ -242,7 +244,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_link_set_stream_id); void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link, int stream) { - snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV, 0, (1 << stream)); + snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV, (1 << stream), 0); } EXPORT_SYMBOL_GPL(snd_hdac_ext_link_clear_stream_id); @@ -415,7 +417,6 @@ void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; - u32 register_mask = 0; if (!bus->spbcap) { dev_err(bus->dev, "Address of SPB capability is NULL\n"); @@ -424,12 +425,8 @@ void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus, mask |= (1 << index); - register_mask = readl(bus->spbcap + AZX_REG_SPB_SPBFCCTL); - - mask |= register_mask; - if (enable) - snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, 0, mask); + snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, mask, mask); else snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, mask, 0); } @@ -503,7 +500,6 @@ void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; - u32 register_mask = 0; if (!bus->drsmcap) { dev_err(bus->dev, "Address of DRSM capability is NULL\n"); @@ -512,12 +508,8 @@ void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, mask |= (1 << index); - register_mask = readl(bus->drsmcap + AZX_REG_SPB_SPBFCCTL); - - mask |= register_mask; - if (enable) - snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, 0, mask); + snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, mask, mask); else snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, mask, 0); } diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index 560ec0986e1a..74244d8e2909 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -40,6 +40,8 @@ static void azx_clear_corbrp(struct hdac_bus *bus) */ void snd_hdac_bus_init_cmd_io(struct hdac_bus *bus) { + WARN_ON_ONCE(!bus->rb.area); + spin_lock_irq(&bus->reg_lock); /* CORB set up */ bus->corb.addr = bus->rb.addr; @@ -383,7 +385,7 @@ void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus) EXPORT_SYMBOL_GPL(snd_hdac_bus_exit_link_reset); /* reset codec link */ -static int azx_reset(struct hdac_bus *bus, bool full_reset) +int snd_hdac_bus_reset_link(struct hdac_bus *bus, bool full_reset) { if (!full_reset) goto skip_reset; @@ -408,7 +410,7 @@ static int azx_reset(struct hdac_bus *bus, bool full_reset) skip_reset: /* check to see if controller is ready */ if (!snd_hdac_chip_readb(bus, GCTL)) { - dev_dbg(bus->dev, "azx_reset: controller not ready!\n"); + dev_dbg(bus->dev, "controller not ready!\n"); return -EBUSY; } @@ -423,6 +425,7 @@ static int azx_reset(struct hdac_bus *bus, bool full_reset) return 0; } +EXPORT_SYMBOL_GPL(snd_hdac_bus_reset_link); /* enable interrupts */ static void azx_int_enable(struct hdac_bus *bus) @@ -477,15 +480,17 @@ bool snd_hdac_bus_init_chip(struct hdac_bus *bus, bool full_reset) return false; /* reset controller */ - azx_reset(bus, full_reset); + snd_hdac_bus_reset_link(bus, full_reset); - /* initialize interrupts */ + /* clear interrupts */ azx_int_clear(bus); - azx_int_enable(bus); /* initialize the codec command I/O */ snd_hdac_bus_init_cmd_io(bus); + /* enable interrupts after CORB/RIRB buffers are initialized above */ + azx_int_enable(bus); + /* program the position buffer */ if (bus->use_posbuf && bus->posbuf.addr) { snd_hdac_chip_writel(bus, DPLBASE, (u32)bus->posbuf.addr); diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c index 90713741c2dc..6ebe817801ea 100644 --- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -2540,7 +2540,7 @@ static int snd_emu10k1_fx8010_ioctl(struct snd_hwdep * hw, struct file *file, un emu->support_tlv = 1; return put_user(SNDRV_EMU10K1_VERSION, (int __user *)argp); case SNDRV_EMU10K1_IOCTL_INFO: - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; snd_emu10k1_fx8010_info(emu, info); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 0a5085537034..26d348b47867 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -3935,7 +3935,8 @@ void snd_hda_bus_reset_codecs(struct hda_bus *bus) list_for_each_codec(codec, bus) { /* FIXME: maybe a better way needed for forced reset */ - cancel_delayed_work_sync(&codec->jackpoll_work); + if (current_work() != &codec->jackpoll_work.work) + cancel_delayed_work_sync(&codec->jackpoll_work); #ifdef CONFIG_PM if (hda_codec_is_power_on(codec)) { hda_call_codec_suspend(codec); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 1b2ce304152a..aa4c672dbaf7 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -365,8 +365,10 @@ enum { */ #ifdef SUPPORT_VGA_SWITCHEROO #define use_vga_switcheroo(chip) ((chip)->use_vga_switcheroo) +#define needs_eld_notify_link(chip) ((chip)->need_eld_notify_link) #else #define use_vga_switcheroo(chip) 0 +#define needs_eld_notify_link(chip) false #endif #define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \ @@ -453,6 +455,7 @@ static inline void mark_runtime_wc(struct azx *chip, struct azx_dev *azx_dev, #endif static int azx_acquire_irq(struct azx *chip, int do_disconnect); +static void set_default_power_save(struct azx *chip); /* * initialize the PCI registers @@ -1201,6 +1204,10 @@ static int azx_runtime_idle(struct device *dev) azx_bus(chip)->codec_powered || !chip->running) return -EBUSY; + /* ELD notification gets broken when HD-audio bus is off */ + if (needs_eld_notify_link(hda)) + return -EBUSY; + return 0; } @@ -1298,6 +1305,36 @@ static bool azx_vs_can_switch(struct pci_dev *pci) return true; } +/* + * The discrete GPU cannot power down unless the HDA controller runtime + * suspends, so activate runtime PM on codecs even if power_save == 0. + */ +static void setup_vga_switcheroo_runtime_pm(struct azx *chip) +{ + struct hda_intel *hda = container_of(chip, struct hda_intel, chip); + struct hda_codec *codec; + + if (hda->use_vga_switcheroo && !hda->need_eld_notify_link) { + list_for_each_codec(codec, &chip->bus) + codec->auto_runtime_pm = 1; + /* reset the power save setup */ + if (chip->running) + set_default_power_save(chip); + } +} + +static void azx_vs_gpu_bound(struct pci_dev *pci, + enum vga_switcheroo_client_id client_id) +{ + struct snd_card *card = pci_get_drvdata(pci); + struct azx *chip = card->private_data; + struct hda_intel *hda = container_of(chip, struct hda_intel, chip); + + if (client_id == VGA_SWITCHEROO_DIS) + hda->need_eld_notify_link = 0; + setup_vga_switcheroo_runtime_pm(chip); +} + static void init_vga_switcheroo(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); @@ -1306,6 +1343,7 @@ static void init_vga_switcheroo(struct azx *chip) dev_info(chip->card->dev, "Handle vga_switcheroo audio client\n"); hda->use_vga_switcheroo = 1; + hda->need_eld_notify_link = 1; /* cleared in gpu_bound op */ chip->driver_caps |= AZX_DCAPS_PM_RUNTIME; pci_dev_put(p); } @@ -1314,6 +1352,7 @@ static void init_vga_switcheroo(struct azx *chip) static const struct vga_switcheroo_client_ops azx_vs_ops = { .set_gpu_state = azx_vs_set_state, .can_switch = azx_vs_can_switch, + .gpu_bound = azx_vs_gpu_bound, }; static int register_vga_switcheroo(struct azx *chip) @@ -1339,6 +1378,7 @@ static int register_vga_switcheroo(struct azx *chip) #define init_vga_switcheroo(chip) /* NOP */ #define register_vga_switcheroo(chip) 0 #define check_hdmi_disabled(pci) false +#define setup_vga_switcheroo_runtime_pm(chip) /* NOP */ #endif /* SUPPORT_VGA_SWITCHER */ /* @@ -1352,6 +1392,7 @@ static int azx_free(struct azx *chip) if (azx_has_pm_runtime(chip) && chip->running) pm_runtime_get_noresume(&pci->dev); + chip->running = 0; azx_del_card_list(chip); @@ -2230,6 +2271,25 @@ static struct snd_pci_quirk power_save_blacklist[] = { }; #endif /* CONFIG_PM */ +static void set_default_power_save(struct azx *chip) +{ + int val = power_save; + +#ifdef CONFIG_PM + if (pm_blacklist) { + const struct snd_pci_quirk *q; + + q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); + if (q && val) { + dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", + q->subvendor, q->subdevice); + val = 0; + } + } +#endif /* CONFIG_PM */ + snd_hda_set_power_save(&chip->bus, val * 1000); +} + /* number of codec slots for each chipset: 0 = default slots (i.e. 4) */ static unsigned int azx_max_codecs[AZX_NUM_DRIVERS] = { [AZX_DRIVER_NVIDIA] = 8, @@ -2241,9 +2301,7 @@ static int azx_probe_continue(struct azx *chip) struct hda_intel *hda = container_of(chip, struct hda_intel, chip); struct hdac_bus *bus = azx_bus(chip); struct pci_dev *pci = chip->pci; - struct hda_codec *codec; int dev = chip->dev_index; - int val; int err; hda->probe_continued = 1; @@ -2322,31 +2380,13 @@ static int azx_probe_continue(struct azx *chip) if (err < 0) goto out_free; + setup_vga_switcheroo_runtime_pm(chip); + chip->running = 1; azx_add_card_list(chip); - val = power_save; -#ifdef CONFIG_PM - if (pm_blacklist) { - const struct snd_pci_quirk *q; - - q = snd_pci_quirk_lookup(chip->pci, power_save_blacklist); - if (q && val) { - dev_info(chip->card->dev, "device %04x:%04x is on the power_save blacklist, forcing power_save to 0\n", - q->subvendor, q->subdevice); - val = 0; - } - } -#endif /* CONFIG_PM */ - /* - * The discrete GPU cannot power down unless the HDA controller runtime - * suspends, so activate runtime PM on codecs even if power_save == 0. - */ - if (use_vga_switcheroo(hda)) - list_for_each_codec(codec, &chip->bus) - codec->auto_runtime_pm = 1; + set_default_power_save(chip); - snd_hda_set_power_save(&chip->bus, val * 1000); if (azx_has_pm_runtime(chip)) pm_runtime_put_autosuspend(&pci->dev); diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h index e3a3d318d2e5..f59719e06b91 100644 --- a/sound/pci/hda/hda_intel.h +++ b/sound/pci/hda/hda_intel.h @@ -37,6 +37,7 @@ struct hda_intel { /* vga_switcheroo setup */ unsigned int use_vga_switcheroo:1; + unsigned int need_eld_notify_link:1; unsigned int vga_switcheroo_registered:1; unsigned int init_failed:1; /* delayed init failed */ diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index e359938e3d7e..77b265bd0505 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/sizes.h> #include <linux/pm_runtime.h> @@ -184,6 +185,24 @@ static void config_dma_descriptor_in_sram(void __iomem *acp_mmio, acp_reg_write(descr_info->xfer_val, acp_mmio, mmACP_SRBM_Targ_Idx_Data); } +static void pre_config_reset(void __iomem *acp_mmio, u16 ch_num) +{ + u32 dma_ctrl; + int ret; + + /* clear the reset bit */ + dma_ctrl = acp_reg_read(acp_mmio, mmACP_DMA_CNTL_0 + ch_num); + dma_ctrl &= ~ACP_DMA_CNTL_0__DMAChRst_MASK; + acp_reg_write(dma_ctrl, acp_mmio, mmACP_DMA_CNTL_0 + ch_num); + /* check the reset bit before programming configuration registers */ + ret = readl_poll_timeout(acp_mmio + ((mmACP_DMA_CNTL_0 + ch_num) * 4), + dma_ctrl, + !(dma_ctrl & ACP_DMA_CNTL_0__DMAChRst_MASK), + 100, ACP_DMA_RESET_TIME); + if (ret < 0) + pr_err("Failed to clear reset of channel : %d\n", ch_num); +} + /* * Initialize the DMA descriptor information for transfer between * system memory <-> ACP SRAM @@ -236,6 +255,7 @@ static void set_acp_sysmem_dma_descriptors(void __iomem *acp_mmio, config_dma_descriptor_in_sram(acp_mmio, dma_dscr_idx, &dmadscr[i]); } + pre_config_reset(acp_mmio, ch); config_acp_dma_channel(acp_mmio, ch, dma_dscr_idx - 1, NUM_DSCRS_PER_CHANNEL, @@ -275,6 +295,7 @@ static void set_acp_to_i2s_dma_descriptors(void __iomem *acp_mmio, u32 size, config_dma_descriptor_in_sram(acp_mmio, dma_dscr_idx, &dmadscr[i]); } + pre_config_reset(acp_mmio, ch); /* Configure the DMA channel with the above descriptore */ config_acp_dma_channel(acp_mmio, ch, dma_dscr_idx - 1, NUM_DSCRS_PER_CHANNEL, diff --git a/sound/soc/codecs/cs4265.c b/sound/soc/codecs/cs4265.c index 275677de669f..407554175282 100644 --- a/sound/soc/codecs/cs4265.c +++ b/sound/soc/codecs/cs4265.c @@ -157,8 +157,8 @@ static const struct snd_kcontrol_new cs4265_snd_controls[] = { SOC_SINGLE("Validity Bit Control Switch", CS4265_SPDIF_CTL2, 3, 1, 0), SOC_ENUM("SPDIF Mono/Stereo", spdif_mono_stereo_enum), - SOC_SINGLE("MMTLR Data Switch", 0, - 1, 1, 0), + SOC_SINGLE("MMTLR Data Switch", CS4265_SPDIF_CTL2, + 0, 1, 0), SOC_ENUM("Mono Channel Select", spdif_mono_select_enum), SND_SOC_BYTES("C Data Buffer", CS4265_C_DATA_BUFF, 24), }; diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c index 92b7125ea169..1093f766d0d2 100644 --- a/sound/soc/codecs/max98373.c +++ b/sound/soc/codecs/max98373.c @@ -520,6 +520,7 @@ static bool max98373_volatile_reg(struct device *dev, unsigned int reg) { switch (reg) { case MAX98373_R2000_SW_RESET ... MAX98373_R2009_INT_FLAG3: + case MAX98373_R203E_AMP_PATH_GAIN: case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK: case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK: case MAX98373_R20B6_BDE_CUR_STATE_READBACK: @@ -729,6 +730,7 @@ static int max98373_probe(struct snd_soc_component *component) /* Software Reset */ regmap_write(max98373->regmap, MAX98373_R2000_SW_RESET, MAX98373_SOFT_RESET); + usleep_range(10000, 11000); /* IV default slot configuration */ regmap_write(max98373->regmap, @@ -817,6 +819,7 @@ static int max98373_resume(struct device *dev) regmap_write(max98373->regmap, MAX98373_R2000_SW_RESET, MAX98373_SOFT_RESET); + usleep_range(10000, 11000); regcache_cache_only(max98373->regmap, false); regcache_sync(max98373->regmap); return 0; diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c index dca82dd6e3bf..32fe76c3134a 100644 --- a/sound/soc/codecs/rt5514.c +++ b/sound/soc/codecs/rt5514.c @@ -64,8 +64,8 @@ static const struct reg_sequence rt5514_patch[] = { {RT5514_ANA_CTRL_LDO10, 0x00028604}, {RT5514_ANA_CTRL_ADCFED, 0x00000800}, {RT5514_ASRC_IN_CTRL1, 0x00000003}, - {RT5514_DOWNFILTER0_CTRL3, 0x10000352}, - {RT5514_DOWNFILTER1_CTRL3, 0x10000352}, + {RT5514_DOWNFILTER0_CTRL3, 0x10000342}, + {RT5514_DOWNFILTER1_CTRL3, 0x10000342}, }; static const struct reg_default rt5514_reg[] = { @@ -92,10 +92,10 @@ static const struct reg_default rt5514_reg[] = { {RT5514_ASRC_IN_CTRL1, 0x00000003}, {RT5514_DOWNFILTER0_CTRL1, 0x00020c2f}, {RT5514_DOWNFILTER0_CTRL2, 0x00020c2f}, - {RT5514_DOWNFILTER0_CTRL3, 0x10000352}, + {RT5514_DOWNFILTER0_CTRL3, 0x10000342}, {RT5514_DOWNFILTER1_CTRL1, 0x00020c2f}, {RT5514_DOWNFILTER1_CTRL2, 0x00020c2f}, - {RT5514_DOWNFILTER1_CTRL3, 0x10000352}, + {RT5514_DOWNFILTER1_CTRL3, 0x10000342}, {RT5514_ANA_CTRL_LDO10, 0x00028604}, {RT5514_ANA_CTRL_LDO18_16, 0x02000345}, {RT5514_ANA_CTRL_ADC12, 0x0000a2a8}, diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 640d400ca013..afe7d5b19313 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -750,8 +750,8 @@ static bool rt5682_readable_register(struct device *dev, unsigned int reg) } static const DECLARE_TLV_DB_SCALE(hp_vol_tlv, -2250, 150, 0); -static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0); -static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0); +static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -6525, 75, 0); +static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -1725, 75, 0); static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0); /* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */ @@ -1114,7 +1114,7 @@ static const struct snd_kcontrol_new rt5682_snd_controls[] = { /* DAC Digital Volume */ SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5682_DAC1_DIG_VOL, - RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 175, 0, dac_vol_tlv), + RT5682_L_VOL_SFT + 1, RT5682_R_VOL_SFT + 1, 86, 0, dac_vol_tlv), /* IN Boost Volume */ SOC_SINGLE_TLV("CBJ Boost Volume", RT5682_CBJ_BST_CTRL, @@ -1124,7 +1124,7 @@ static const struct snd_kcontrol_new rt5682_snd_controls[] = { SOC_DOUBLE("STO1 ADC Capture Switch", RT5682_STO1_ADC_DIG_VOL, RT5682_L_MUTE_SFT, RT5682_R_MUTE_SFT, 1, 1), SOC_DOUBLE_TLV("STO1 ADC Capture Volume", RT5682_STO1_ADC_DIG_VOL, - RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 127, 0, adc_vol_tlv), + RT5682_L_VOL_SFT + 1, RT5682_R_VOL_SFT + 1, 63, 0, adc_vol_tlv), /* ADC Boost Volume Control */ SOC_DOUBLE_TLV("STO1 ADC Boost Gain Volume", RT5682_STO1_ADC_BOOST, diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c index d53680ac78e4..6df158669420 100644 --- a/sound/soc/codecs/sigmadsp.c +++ b/sound/soc/codecs/sigmadsp.c @@ -117,8 +117,7 @@ static int sigmadsp_ctrl_write(struct sigmadsp *sigmadsp, struct sigmadsp_control *ctrl, void *data) { /* safeload loads up to 20 bytes in a atomic operation */ - if (ctrl->num_bytes > 4 && ctrl->num_bytes <= 20 && sigmadsp->ops && - sigmadsp->ops->safeload) + if (ctrl->num_bytes <= 20 && sigmadsp->ops && sigmadsp->ops->safeload) return sigmadsp->ops->safeload(sigmadsp, ctrl->addr, data, ctrl->num_bytes); else diff --git a/sound/soc/codecs/tas6424.c b/sound/soc/codecs/tas6424.c index 14999b999fd3..0d6145549a98 100644 --- a/sound/soc/codecs/tas6424.c +++ b/sound/soc/codecs/tas6424.c @@ -424,8 +424,10 @@ static void tas6424_fault_check_work(struct work_struct *work) TAS6424_FAULT_PVDD_UV | TAS6424_FAULT_VBAT_UV; - if (reg) + if (!reg) { + tas6424->last_fault1 = reg; goto check_global_fault2_reg; + } /* * Only flag errors once for a given occurrence. This is needed as @@ -461,8 +463,10 @@ check_global_fault2_reg: TAS6424_FAULT_OTSD_CH3 | TAS6424_FAULT_OTSD_CH4; - if (!reg) + if (!reg) { + tas6424->last_fault2 = reg; goto check_warn_reg; + } if ((reg & TAS6424_FAULT_OTSD) && !(tas6424->last_fault2 & TAS6424_FAULT_OTSD)) dev_crit(dev, "experienced a global overtemp shutdown\n"); @@ -497,8 +501,10 @@ check_warn_reg: TAS6424_WARN_VDD_OTW_CH3 | TAS6424_WARN_VDD_OTW_CH4; - if (!reg) + if (!reg) { + tas6424->last_warn = reg; goto out; + } if ((reg & TAS6424_WARN_VDD_UV) && !(tas6424->last_warn & TAS6424_WARN_VDD_UV)) dev_warn(dev, "experienced a VDD under voltage condition\n"); diff --git a/sound/soc/codecs/wm8804-i2c.c b/sound/soc/codecs/wm8804-i2c.c index f27464c2c5ba..79541960f45d 100644 --- a/sound/soc/codecs/wm8804-i2c.c +++ b/sound/soc/codecs/wm8804-i2c.c @@ -13,6 +13,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/i2c.h> +#include <linux/acpi.h> #include "wm8804.h" @@ -40,17 +41,29 @@ static const struct i2c_device_id wm8804_i2c_id[] = { }; MODULE_DEVICE_TABLE(i2c, wm8804_i2c_id); +#if defined(CONFIG_OF) static const struct of_device_id wm8804_of_match[] = { { .compatible = "wlf,wm8804", }, { } }; MODULE_DEVICE_TABLE(of, wm8804_of_match); +#endif + +#ifdef CONFIG_ACPI +static const struct acpi_device_id wm8804_acpi_match[] = { + { "1AEC8804", 0 }, /* Wolfson PCI ID + part ID */ + { "10138804", 0 }, /* Cirrus Logic PCI ID + part ID */ + { }, +}; +MODULE_DEVICE_TABLE(acpi, wm8804_acpi_match); +#endif static struct i2c_driver wm8804_i2c_driver = { .driver = { .name = "wm8804", .pm = &wm8804_pm, - .of_match_table = wm8804_of_match, + .of_match_table = of_match_ptr(wm8804_of_match), + .acpi_match_table = ACPI_PTR(wm8804_acpi_match), }, .probe = wm8804_i2c_probe, .remove = wm8804_i2c_remove, diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c index 953d94d50586..ade34c26ad2f 100644 --- a/sound/soc/codecs/wm9712.c +++ b/sound/soc/codecs/wm9712.c @@ -719,7 +719,7 @@ static int wm9712_probe(struct platform_device *pdev) static struct platform_driver wm9712_component_driver = { .driver = { - .name = "wm9712-component", + .name = "wm9712-codec", }, .probe = wm9712_probe, diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index d32844f94d74..b6dc524830b2 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -575,6 +575,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_MONO_SPEAKER | BYT_RT5640_MCLK_EN), }, + { /* Linx Linx7 tablet */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LINX"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "LINX7"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_JD_NOT_INV | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* MSI S100 tablet */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Micro-Star International Co., Ltd."), @@ -602,6 +613,21 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* Onda v975w */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* The above are too generic, also match BIOS info */ + DMI_EXACT_MATCH(DMI_BIOS_VERSION, "5.6.5"), + DMI_EXACT_MATCH(DMI_BIOS_DATE, "07/25/2014"), + }, + .driver_data = (void *)(BYT_RT5640_IN1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_MCLK_EN), + }, { /* Pipo W4 */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index dce649485649..1d17be0f78a0 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -834,7 +834,7 @@ static int skl_first_init(struct hdac_bus *bus) return -ENXIO; } - skl_init_chip(bus, true); + snd_hdac_bus_reset_link(bus, true); snd_hdac_bus_parse_capabilities(bus); diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index dc94c5c53788..c6b51571be94 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -960,8 +960,10 @@ static int msm_routing_probe(struct snd_soc_component *c) { int i; - for (i = 0; i < MAX_SESSIONS; i++) + for (i = 0; i < MAX_SESSIONS; i++) { routing_data->sessions[i].port_id = -1; + routing_data->sessions[i].fedai_id = -1; + } return 0; } diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c index 3a3064dda57f..051f96405346 100644 --- a/sound/soc/sh/rcar/adg.c +++ b/sound/soc/sh/rcar/adg.c @@ -462,6 +462,11 @@ static void rsnd_adg_get_clkout(struct rsnd_priv *priv, goto rsnd_adg_get_clkout_end; req_size = prop->length / sizeof(u32); + if (req_size > REQ_SIZE) { + dev_err(dev, + "too many clock-frequency, use top %d\n", REQ_SIZE); + req_size = REQ_SIZE; + } of_property_read_u32_array(np, "clock-frequency", req_rate, req_size); req_48kHz_rate = 0; diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index f8425d8b44d2..d23c2bbff0cf 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -478,7 +478,7 @@ static int rsnd_status_update(u32 *status, (func_call && (mod)->ops->fn) ? #fn : ""); \ if (func_call && (mod)->ops->fn) \ tmp = (mod)->ops->fn(mod, io, param); \ - if (tmp) \ + if (tmp && (tmp != -EPROBE_DEFER)) \ dev_err(dev, "%s[%d] : %s error %d\n", \ rsnd_mod_name(mod), rsnd_mod_id(mod), \ #fn, tmp); \ @@ -958,12 +958,23 @@ static void rsnd_soc_dai_shutdown(struct snd_pcm_substream *substream, rsnd_dai_stream_quit(io); } +static int rsnd_soc_dai_prepare(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct rsnd_priv *priv = rsnd_dai_to_priv(dai); + struct rsnd_dai *rdai = rsnd_dai_to_rdai(dai); + struct rsnd_dai_stream *io = rsnd_rdai_to_io(rdai, substream); + + return rsnd_dai_call(prepare, io, priv); +} + static const struct snd_soc_dai_ops rsnd_soc_dai_ops = { .startup = rsnd_soc_dai_startup, .shutdown = rsnd_soc_dai_shutdown, .trigger = rsnd_soc_dai_trigger, .set_fmt = rsnd_soc_dai_set_fmt, .set_tdm_slot = rsnd_soc_set_dai_tdm_slot, + .prepare = rsnd_soc_dai_prepare, }; void rsnd_parse_connect_common(struct rsnd_dai *rdai, @@ -1550,6 +1561,14 @@ exit_snd_probe: rsnd_dai_call(remove, &rdai->capture, priv); } + /* + * adg is very special mod which can't use rsnd_dai_call(remove), + * and it registers ADG clock on probe. + * It should be unregister if probe failed. + * Mainly it is assuming -EPROBE_DEFER case + */ + rsnd_adg_remove(priv); + return ret; } diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index fe63ef8600d0..d65ea7bc4dac 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -241,6 +241,10 @@ static int rsnd_dmaen_attach(struct rsnd_dai_stream *io, /* try to get DMAEngine channel */ chan = rsnd_dmaen_request_channel(io, mod_from, mod_to); if (IS_ERR_OR_NULL(chan)) { + /* Let's follow when -EPROBE_DEFER case */ + if (PTR_ERR(chan) == -EPROBE_DEFER) + return PTR_ERR(chan); + /* * DMA failed. try to PIO mode * see diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h index 96d93330b1e1..8f7a0abfa751 100644 --- a/sound/soc/sh/rcar/rsnd.h +++ b/sound/soc/sh/rcar/rsnd.h @@ -280,6 +280,9 @@ struct rsnd_mod_ops { int (*nolock_stop)(struct rsnd_mod *mod, struct rsnd_dai_stream *io, struct rsnd_priv *priv); + int (*prepare)(struct rsnd_mod *mod, + struct rsnd_dai_stream *io, + struct rsnd_priv *priv); }; struct rsnd_dai_stream; @@ -309,6 +312,7 @@ struct rsnd_mod { * H 0: fallback * H 0: hw_params * H 0: pointer + * H 0: prepare */ #define __rsnd_mod_shift_nolock_start 0 #define __rsnd_mod_shift_nolock_stop 0 @@ -323,6 +327,7 @@ struct rsnd_mod { #define __rsnd_mod_shift_fallback 28 /* always called */ #define __rsnd_mod_shift_hw_params 28 /* always called */ #define __rsnd_mod_shift_pointer 28 /* always called */ +#define __rsnd_mod_shift_prepare 28 /* always called */ #define __rsnd_mod_add_probe 0 #define __rsnd_mod_add_remove 0 @@ -337,6 +342,7 @@ struct rsnd_mod { #define __rsnd_mod_add_fallback 0 #define __rsnd_mod_add_hw_params 0 #define __rsnd_mod_add_pointer 0 +#define __rsnd_mod_add_prepare 0 #define __rsnd_mod_call_probe 0 #define __rsnd_mod_call_remove 0 @@ -351,6 +357,7 @@ struct rsnd_mod { #define __rsnd_mod_call_pointer 0 #define __rsnd_mod_call_nolock_start 0 #define __rsnd_mod_call_nolock_stop 1 +#define __rsnd_mod_call_prepare 0 #define rsnd_mod_to_priv(mod) ((mod)->priv) #define rsnd_mod_name(mod) ((mod)->ops->name) diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 8304e4ec9242..3f880ec66459 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -283,7 +283,7 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, if (rsnd_ssi_is_multi_slave(mod, io)) return 0; - if (ssi->usrcnt > 1) { + if (ssi->rate) { if (ssi->rate != rate) { dev_err(dev, "SSI parent/child should use same rate\n"); return -EINVAL; @@ -434,7 +434,6 @@ static int rsnd_ssi_init(struct rsnd_mod *mod, struct rsnd_priv *priv) { struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod); - int ret; if (!rsnd_ssi_is_run_mods(mod, io)) return 0; @@ -443,10 +442,6 @@ static int rsnd_ssi_init(struct rsnd_mod *mod, rsnd_mod_power_on(mod); - ret = rsnd_ssi_master_clk_start(mod, io); - if (ret < 0) - return ret; - rsnd_ssi_config_init(mod, io); rsnd_ssi_register_setup(mod); @@ -852,6 +847,13 @@ static int rsnd_ssi_pio_pointer(struct rsnd_mod *mod, return 0; } +static int rsnd_ssi_prepare(struct rsnd_mod *mod, + struct rsnd_dai_stream *io, + struct rsnd_priv *priv) +{ + return rsnd_ssi_master_clk_start(mod, io); +} + static struct rsnd_mod_ops rsnd_ssi_pio_ops = { .name = SSI_NAME, .probe = rsnd_ssi_common_probe, @@ -864,6 +866,7 @@ static struct rsnd_mod_ops rsnd_ssi_pio_ops = { .pointer = rsnd_ssi_pio_pointer, .pcm_new = rsnd_ssi_pcm_new, .hw_params = rsnd_ssi_hw_params, + .prepare = rsnd_ssi_prepare, }; static int rsnd_ssi_dma_probe(struct rsnd_mod *mod, @@ -940,6 +943,7 @@ static struct rsnd_mod_ops rsnd_ssi_dma_ops = { .pcm_new = rsnd_ssi_pcm_new, .fallback = rsnd_ssi_fallback, .hw_params = rsnd_ssi_hw_params, + .prepare = rsnd_ssi_prepare, }; int rsnd_ssi_is_dma_mode(struct rsnd_mod *mod) diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 9cfe10d8040c..473eefe8658e 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1447,7 +1447,7 @@ static int soc_link_dai_widgets(struct snd_soc_card *card, sink = codec_dai->playback_widget; source = cpu_dai->capture_widget; if (sink && source) { - ret = snd_soc_dapm_new_pcm(card, dai_link->params, + ret = snd_soc_dapm_new_pcm(card, rtd, dai_link->params, dai_link->num_params, source, sink); if (ret != 0) { @@ -1460,7 +1460,7 @@ static int soc_link_dai_widgets(struct snd_soc_card *card, sink = cpu_dai->playback_widget; source = codec_dai->capture_widget; if (sink && source) { - ret = snd_soc_dapm_new_pcm(card, dai_link->params, + ret = snd_soc_dapm_new_pcm(card, rtd, dai_link->params, dai_link->num_params, source, sink); if (ret != 0) { diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 7e96793050c9..461d951917c0 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3652,6 +3652,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, { struct snd_soc_dapm_path *source_p, *sink_p; struct snd_soc_dai *source, *sink; + struct snd_soc_pcm_runtime *rtd = w->priv; const struct snd_soc_pcm_stream *config = w->params + w->params_select; struct snd_pcm_substream substream; struct snd_pcm_hw_params *params = NULL; @@ -3711,6 +3712,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, goto out; } substream.runtime = runtime; + substream.private_data = rtd; switch (event) { case SND_SOC_DAPM_PRE_PMU: @@ -3895,6 +3897,7 @@ outfree_w_param: } int snd_soc_dapm_new_pcm(struct snd_soc_card *card, + struct snd_soc_pcm_runtime *rtd, const struct snd_soc_pcm_stream *params, unsigned int num_params, struct snd_soc_dapm_widget *source, @@ -3963,6 +3966,7 @@ int snd_soc_dapm_new_pcm(struct snd_soc_card *card, w->params = params; w->num_params = num_params; + w->priv = rtd; ret = snd_soc_dapm_add_path(&card->dapm, source, w, NULL, NULL); if (ret) 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/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index b2ec20e562bd..b455930a3eaf 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -68,6 +68,7 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_DEVMAP] = "devmap", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_XSKMAP] = "xskmap", [BPF_MAP_TYPE_SOCKHASH] = "sockhash", [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", }; 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 cf01b6824244..43391e2d1153 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -164,6 +164,8 @@ enum { IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, __IFLA_MAX }; @@ -334,6 +336,7 @@ 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) @@ -459,6 +462,16 @@ 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, @@ -920,6 +933,7 @@ enum { XDP_ATTACHED_DRV, XDP_ATTACHED_SKB, XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, }; enum { @@ -928,6 +942,9 @@ 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/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 56c4b3f8a01b..439b8a27488d 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -759,12 +759,18 @@ class DebugfsProvider(Provider): if len(vms) == 0: self.do_read = False - self.paths = filter(lambda x: "{}-".format(pid) in x, vms) + self.paths = list(filter(lambda x: "{}-".format(pid) in x, vms)) else: self.paths = [] self.do_read = True - self.reset() + + def _verify_paths(self): + """Remove invalid paths""" + for path in self.paths: + if not os.path.exists(os.path.join(PATH_DEBUGFS_KVM, path)): + self.paths.remove(path) + continue def read(self, reset=0, by_guest=0): """Returns a dict with format:'file name / field -> current value'. @@ -780,6 +786,7 @@ class DebugfsProvider(Provider): # If no debugfs filtering support is available, then don't read. if not self.do_read: return results + self._verify_paths() paths = self.paths if self._pid == 0: @@ -1096,15 +1103,16 @@ class Tui(object): pid = self.stats.pid_filter self.screen.erase() gname = self.get_gname_from_pid(pid) + self._gname = gname if gname: gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...' if len(gname) > MAX_GUEST_NAME_LEN else gname)) if pid > 0: - self.screen.addstr(0, 0, 'kvm statistics - pid {0} {1}' - .format(pid, gname), curses.A_BOLD) + self._headline = 'kvm statistics - pid {0} {1}'.format(pid, gname) else: - self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) + self._headline = 'kvm statistics - summary' + self.screen.addstr(0, 0, self._headline, curses.A_BOLD) if self.stats.fields_filter: regex = self.stats.fields_filter if len(regex) > MAX_REGEX_LEN: @@ -1162,6 +1170,19 @@ class Tui(object): return sorted_items + if not self._is_running_guest(self.stats.pid_filter): + if self._gname: + try: # ...to identify the guest by name in case it's back + pids = self.get_pid_from_gname(self._gname) + if len(pids) == 1: + self._refresh_header(pids[0]) + self._update_pid(pids[0]) + return + except: + pass + self._display_guest_dead() + # leave final data on screen + return row = 3 self.screen.move(row, 0) self.screen.clrtobot() @@ -1184,6 +1205,7 @@ class Tui(object): # print events tavg = 0 tcur = 0 + guest_removed = False for key, values in get_sorted_events(self, stats): if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0): break @@ -1191,7 +1213,10 @@ class Tui(object): key = self.get_gname_from_pid(key) if not key: continue - cur = int(round(values.delta / sleeptime)) if values.delta else '' + cur = int(round(values.delta / sleeptime)) if values.delta else 0 + if cur < 0: + guest_removed = True + continue if key[0] != ' ': if values.delta: tcur += values.delta @@ -1204,13 +1229,21 @@ class Tui(object): values.value * 100 / float(ltotal), cur)) row += 1 if row == 3: - self.screen.addstr(4, 1, 'No matching events reported yet') + if guest_removed: + self.screen.addstr(4, 1, 'Guest removed, updating...') + else: + self.screen.addstr(4, 1, 'No matching events reported yet') if row > 4: tavg = int(round(tcur / sleeptime)) if tcur > 0 else '' self.screen.addstr(row, 1, '%-40s %10d %8s' % ('Total', total, tavg), curses.A_BOLD) self.screen.refresh() + def _display_guest_dead(self): + marker = ' Guest is DEAD ' + y = min(len(self._headline), 80 - len(marker)) + self.screen.addstr(0, y, marker, curses.A_BLINK | curses.A_STANDOUT) + def _show_msg(self, text): """Display message centered text and exit on key press""" hint = 'Press any key to continue' @@ -1219,10 +1252,10 @@ class Tui(object): (x, term_width) = self.screen.getmaxyx() row = 2 for line in text: - start = (term_width - len(line)) / 2 + start = (term_width - len(line)) // 2 self.screen.addstr(row, start, line) row += 1 - self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint, + self.screen.addstr(row + 1, (term_width - len(hint)) // 2, hint, curses.A_STANDOUT) self.screen.getkey() @@ -1319,6 +1352,12 @@ class Tui(object): msg = '"' + str(val) + '": Invalid value' self._refresh_header() + def _is_running_guest(self, pid): + """Check if pid is still a running process.""" + if not pid: + return True + return os.path.isdir(os.path.join('/proc/', str(pid))) + def _show_vm_selection_by_guest(self): """Draws guest selection mask. @@ -1346,7 +1385,7 @@ class Tui(object): if not guest or guest == '0': break if guest.isdigit(): - if not os.path.isdir(os.path.join('/proc/', guest)): + if not self._is_running_guest(guest): msg = '"' + guest + '": Not a running process' continue pid = int(guest) diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 13a861135127..6eb9bacd1948 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2abd0f112627..bdb94939fd60 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -50,6 +50,7 @@ #include "libbpf.h" #include "bpf.h" #include "btf.h" +#include "str_error.h" #ifndef EM_BPF #define EM_BPF 247 @@ -469,7 +470,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) obj->efile.fd = open(obj->path, O_RDONLY); if (obj->efile.fd < 0) { char errmsg[STRERR_BUFSIZE]; - char *cp = strerror_r(errno, errmsg, sizeof(errmsg)); + char *cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to open %s: %s\n", obj->path, cp); return -errno; @@ -810,8 +811,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) data->d_size, name, idx); if (err) { char errmsg[STRERR_BUFSIZE]; - char *cp = strerror_r(-err, errmsg, - sizeof(errmsg)); + char *cp = str_error(-err, errmsg, sizeof(errmsg)); pr_warning("failed to alloc program %s (%s): %s", name, obj->path, cp); @@ -1140,7 +1140,7 @@ bpf_object__create_maps(struct bpf_object *obj) *pfd = bpf_create_map_xattr(&create_attr); if (*pfd < 0 && create_attr.btf_key_type_id) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", map->name, cp, errno); create_attr.btf_fd = 0; @@ -1155,7 +1155,7 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; err = *pfd; - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to create map (name: '%s'): %s\n", map->name, cp); for (j = 0; j < i; j++) @@ -1339,7 +1339,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type, } ret = -LIBBPF_ERRNO__LOAD; - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("load bpf program failed: %s\n", cp); if (log_buf && log_buf[0] != '\0') { @@ -1654,7 +1654,7 @@ static int check_path(const char *path) dir = dirname(dname); if (statfs(dir, &st_fs)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to statfs %s: %s\n", dir, cp); err = -errno; } @@ -1690,7 +1690,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, } if (bpf_obj_pin(prog->instances.fds[instance], path)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to pin program: %s\n", cp); return -errno; } @@ -1708,7 +1708,7 @@ static int make_dir(const char *path) err = -errno; if (err) { - cp = strerror_r(-err, errmsg, sizeof(errmsg)); + cp = str_error(-err, errmsg, sizeof(errmsg)); pr_warning("failed to mkdir %s: %s\n", path, cp); } return err; @@ -1770,7 +1770,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path) } if (bpf_obj_pin(map->fd, path)) { - cp = strerror_r(errno, errmsg, sizeof(errmsg)); + cp = str_error(errno, errmsg, sizeof(errmsg)); pr_warning("failed to pin map: %s\n", cp); return -errno; } diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c new file mode 100644 index 000000000000..b8798114a357 --- /dev/null +++ b/tools/lib/bpf/str_error.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: LGPL-2.1 +#undef _GNU_SOURCE +#include <string.h> +#include <stdio.h> +#include "str_error.h" + +/* + * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl + * libc, while checking strerror_r() return to avoid having to check this in + * all places calling it. + */ +char *str_error(int err, char *dst, int len) +{ + int ret = strerror_r(err, dst, len); + if (ret) + snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); + return dst; +} diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h new file mode 100644 index 000000000000..355b1db571d1 --- /dev/null +++ b/tools/lib/bpf/str_error.h @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: LGPL-2.1 +#ifndef BPF_STR_ERROR +#define BPF_STR_ERROR + +char *str_error(int err, char *dst, int len); +#endif // BPF_STR_ERROR diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile index 42261a9b280e..ac841bc5c35b 100644 --- a/tools/perf/Documentation/Makefile +++ b/tools/perf/Documentation/Makefile @@ -280,7 +280,7 @@ $(MAN_HTML): $(OUTPUT)%.html : %.txt mv $@+ $@ ifdef USE_ASCIIDOCTOR -$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt +$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : %.txt $(QUIET_ASCIIDOC)$(RM) $@+ $@ && \ $(ASCIIDOC) -b manpage -d manpage \ $(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \ 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/.gitignore b/tools/testing/selftests/kvm/.gitignore index 4202139d81d9..5c34752e1cff 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,4 +1,5 @@ cr4_cpuid_sync_test +platform_info_test set_sregs_test sync_regs_test vmx_tsc_adjust_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 03b0f551bedf..ec32dad3c3f0 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -6,7 +6,8 @@ UNAME_M := $(shell uname -m) LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c LIBKVM_x86_64 = lib/x86.c lib/vmx.c -TEST_GEN_PROGS_x86_64 = set_sregs_test +TEST_GEN_PROGS_x86_64 = platform_info_test +TEST_GEN_PROGS_x86_64 += set_sregs_test TEST_GEN_PROGS_x86_64 += sync_regs_test TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test @@ -20,7 +21,7 @@ INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I.. -LDFLAGS += -lpthread +LDFLAGS += -pthread # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ @@ -37,9 +38,6 @@ $(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/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bb5a25fb82c6..3acf9a91704c 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -50,6 +50,7 @@ enum vm_mem_backing_src_type { }; int kvm_check_cap(long cap); +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); @@ -108,6 +109,9 @@ void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_events *events); +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index); +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value); const char *exit_reason_str(unsigned int exit_reason); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index e9ba389c48db..6fd8c089cafc 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -63,6 +63,29 @@ int kvm_check_cap(long cap) return ret; } +/* VM Enable Capability + * + * Input Args: + * vm - Virtual Machine + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VM. + */ +int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) +{ + int ret; + + ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n" + " rc: %i errno: %i", ret, errno); + + return ret; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -1220,6 +1243,72 @@ void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, ret, errno); } +/* VCPU Get MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * + * Output Args: None + * + * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced. + * + * Get value of MSR for VCPU. + */ +uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); + + return buffer.entry.data; +} + +/* VCPU Set MSR + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * msr_index - Index of MSR + * msr_value - New value of MSR + * + * Output Args: None + * + * Return: On success, nothing. On failure a TEST_ASSERT is produced. + * + * Set value of MSR for VCPU. + */ +void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, + uint64_t msr_value) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + struct { + struct kvm_msrs header; + struct kvm_msr_entry entry; + } buffer = {}; + int r; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + memset(&buffer, 0, sizeof(buffer)); + buffer.header.nmsrs = 1; + buffer.entry.index = msr_index; + buffer.entry.data = msr_value; + r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header); + TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n" + " rc: %i errno: %i", r, errno); +} + /* VM VCPU Args Set * * Input Args: diff --git a/tools/testing/selftests/kvm/platform_info_test.c b/tools/testing/selftests/kvm/platform_info_test.c new file mode 100644 index 000000000000..3764e7121265 --- /dev/null +++ b/tools/testing/selftests/kvm/platform_info_test.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for x86 KVM_CAP_MSR_PLATFORM_INFO + * + * Copyright (C) 2018, Google LLC. + * + * This work is licensed under the terms of the GNU GPL, version 2. + * + * Verifies expected behavior of controlling guest access to + * MSR_PLATFORM_INFO. + */ + +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "x86.h" + +#define VCPU_ID 0 +#define MSR_PLATFORM_INFO_MAX_TURBO_RATIO 0xff00 + +static void guest_code(void) +{ + uint64_t msr_platform_info; + + for (;;) { + msr_platform_info = rdmsr(MSR_PLATFORM_INFO); + GUEST_SYNC(msr_platform_info); + asm volatile ("inc %r11"); + } +} + +static void set_msr_platform_info_enabled(struct kvm_vm *vm, bool enable) +{ + struct kvm_enable_cap cap = {}; + + cap.cap = KVM_CAP_MSR_PLATFORM_INFO; + cap.flags = 0; + cap.args[0] = (int)enable; + vm_enable_cap(vm, &cap); +} + +static void test_msr_platform_info_enabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + struct guest_args args; + + set_msr_platform_info_enabled(vm, true); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Exit_reason other than KVM_EXIT_IO: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + guest_args_read(vm, VCPU_ID, &args); + TEST_ASSERT(args.port == GUEST_PORT_SYNC, + "Received IO from port other than PORT_HOST_SYNC: %u\n", + run->io.port); + TEST_ASSERT((args.arg1 & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == + MSR_PLATFORM_INFO_MAX_TURBO_RATIO, + "Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.", + MSR_PLATFORM_INFO_MAX_TURBO_RATIO); +} + +static void test_msr_platform_info_disabled(struct kvm_vm *vm) +{ + struct kvm_run *run = vcpu_state(vm, VCPU_ID); + + set_msr_platform_info_enabled(vm, false); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, + "Exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vm *vm; + struct kvm_run *state; + int rv; + uint64_t msr_platform_info; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + rv = kvm_check_cap(KVM_CAP_MSR_PLATFORM_INFO); + if (!rv) { + fprintf(stderr, + "KVM_CAP_MSR_PLATFORM_INFO not supported, skip test\n"); + exit(KSFT_SKIP); + } + + vm = vm_create_default(VCPU_ID, 0, guest_code); + + msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO); + vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, + msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); + test_msr_platform_info_disabled(vm); + test_msr_platform_info_enabled(vm); + vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info); + + kvm_vm_free(vm); + + return 0; +} 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 9cca68e440a0..919aa2ac00af 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 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 $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index f8cc38afffa2..32a194e3e07a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -46,6 +46,9 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +# Some systems don't have a ping6 binary anymore +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + tests=" pmtu_vti6_exception vti6: PMTU exceptions pmtu_vti4_exception vti4: PMTU exceptions @@ -274,7 +277,7 @@ test_pmtu_vti6_exception() { mtu "${ns_b}" veth_b 4000 mtu "${ns_a}" vti6_a 5000 mtu "${ns_b}" vti6_b 5000 - ${ns_a} ping6 -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null + ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null # Check that exception was created if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then @@ -334,7 +337,7 @@ test_pmtu_vti4_link_add_mtu() { fail=0 min=68 - max=$((65528 - 20)) + max=$((65535 - 20)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index b3ebf2646e52..8fdfeafaf8c0 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, 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: $(TEST_PROGS) +top_srcdir = ../../../../.. include ../../lib.mk clean: diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json index f03763d81617..30f9b54bd666 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -313,6 +313,54 @@ ] }, { + "id": "6aaf", + "name": "Add police actions with conform-exceed control pass/pipe [with numeric values]", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed 0/3 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "29b1", + "name": "Add police actions with conform-exceed control <invalid>/drop", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed 10/drop index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action ", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { "id": "c26f", "name": "Add police action with invalid peakrate value", "category": [ diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9881876d2aa0..e94b7b14bcb2 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -26,10 +26,6 @@ TEST_PROGS := run_vmtests include ../lib.mk -$(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 diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 30cb0a0713ff..37908a83ddc2 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -159,12 +159,6 @@ static const char * const page_flag_names[] = { }; -static const char * const debugfs_known_mountpoints[] = { - "/sys/kernel/debug", - "/debug", - 0, -}; - /* * data structures */ diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index f82c2eaa859d..334b16db0ebb 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -30,8 +30,8 @@ struct slabinfo { int alias; int refs; int aliases, align, cache_dma, cpu_slabs, destroy_by_rcu; - int hwcache_align, object_size, objs_per_slab; - int sanity_checks, slab_size, store_user, trace; + unsigned int hwcache_align, object_size, objs_per_slab; + unsigned int sanity_checks, slab_size, store_user, trace; int order, poison, reclaim_account, red_zone; unsigned long partial, objects, slabs, objects_partial, objects_total; unsigned long alloc_fastpath, alloc_slowpath; diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 91aaf73b00df..ed162a6c57c5 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1817,18 +1817,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *dat return 0; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - unsigned long end = hva + PAGE_SIZE; - - if (!kvm->arch.pgd) - return 0; - - trace_kvm_unmap_hva(hva); - handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); - return 0; -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { @@ -1860,13 +1848,20 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) { unsigned long end = hva + PAGE_SIZE; + kvm_pfn_t pfn = pte_pfn(pte); pte_t stage2_pte; if (!kvm->arch.pgd) return; trace_kvm_set_spte_hva(hva); - stage2_pte = pfn_pte(pte_pfn(pte), PAGE_S2); + + /* + * We've moved a page around, probably through CoW, so let's treat it + * just like a translation fault and clean the cache to the PoC. + */ + clean_dcache_guest_page(pfn, PAGE_SIZE); + stage2_pte = pfn_pte(pfn, PAGE_S2); handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); } diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h index e53b596f483b..57b3edebbb40 100644 --- a/virt/kvm/arm/trace.h +++ b/virt/kvm/arm/trace.h @@ -134,21 +134,6 @@ TRACE_EVENT(kvm_mmio_emulate, __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); -TRACE_EVENT(kvm_unmap_hva, - TP_PROTO(unsigned long hva), - TP_ARGS(hva), - - TP_STRUCT__entry( - __field( unsigned long, hva ) - ), - - TP_fast_assign( - __entry->hva = hva; - ), - - TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva) -); - TRACE_EVENT(kvm_unmap_hva_range, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), |