diff options
869 files changed, 12695 insertions, 5634 deletions
diff --git a/.clippy.toml b/.clippy.toml index 815c94732ed7..137f41d203de 100644 --- a/.clippy.toml +++ b/.clippy.toml @@ -7,5 +7,5 @@ check-private-items = true disallowed-macros = [ # The `clippy::dbg_macro` lint only works with `std::dbg!`, thus we simulate # it here, see: https://github.com/rust-lang/rust-clippy/issues/11303. - { path = "kernel::dbg", reason = "the `dbg!` macro is intended as a debugging tool" }, + { path = "kernel::dbg", reason = "the `dbg!` macro is intended as a debugging tool", allow-invalid = true }, ] @@ -102,6 +102,7 @@ Ard Biesheuvel <ardb@kernel.org> <ard.biesheuvel@linaro.org> Arnaud Patard <arnaud.patard@rtp-net.org> Arnd Bergmann <arnd@arndb.de> Arun Kumar Neelakantam <quic_aneela@quicinc.com> <aneela@codeaurora.org> +Asahi Lina <lina+kernel@asahilina.net> <lina@asahilina.net> Ashok Raj Nagarajan <quic_arnagara@quicinc.com> <arnagara@codeaurora.org> Ashwin Chaugule <quic_ashwinc@quicinc.com> <ashwinc@codeaurora.org> Asutosh Das <quic_asutoshd@quicinc.com> <asutoshd@codeaurora.org> @@ -312,6 +313,7 @@ Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com> Jan Kuliga <jtkuliga.kdev@gmail.com> <jankul@alatek.krakow.pl> Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@linux.intel.com> Jarkko Sakkinen <jarkko@kernel.org> <jarkko@profian.com> +Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@opinsys.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> @@ -447,6 +449,8 @@ Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net> Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz> Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com> Luo Jie <quic_luoj@quicinc.com> <luoj@codeaurora.org> +Lance Yang <lance.yang@linux.dev> <ioworker0@gmail.com> +Lance Yang <lance.yang@linux.dev> <mingzhe.yang@ly.com> Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com> Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org> Maharaja Kennadyrajan <quic_mkenna@quicinc.com> <mkenna@codeaurora.org> @@ -483,6 +487,7 @@ Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu> Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net> Matthieu CASTET <castet.matthieu@free.fr> Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com> +Mattijs Korpershoek <mkorpershoek@kernel.org> <mkorpershoek@baylibre.com> Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com> Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting> Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com> @@ -749,6 +754,7 @@ Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net> Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws> Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> +Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com> Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 206079d3bd5b..6a1acabb29d8 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -511,6 +511,7 @@ Description: information about CPUs heterogeneity. What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/indirect_target_selection /sys/devices/system/cpu/vulnerabilities/itlb_multihit /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds diff --git a/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd b/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd index 2a19584d091e..8c9718d83e9d 100644 --- a/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd +++ b/Documentation/ABI/testing/sysfs-driver-hid-appletb-kbd @@ -1,6 +1,6 @@ What: /sys/bus/hid/drivers/hid-appletb-kbd/<dev>/mode -Date: September, 2023 -KernelVersion: 6.5 +Date: March, 2025 +KernelVersion: 6.15 Contact: linux-input@vger.kernel.org Description: The set of keys displayed on the Touch Bar. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 1a16ce68a4d7..9e7de8e70048 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -3019,7 +3019,7 @@ Filesystem Support for Writeback -------------------------------- A filesystem can support cgroup writeback by updating -address_space_operations->writepage[s]() to annotate bio's using the +address_space_operations->writepages() to annotate bio's using the following two functions. wbc_init_bio(@wbc, @bio) diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 451874b8135d..ce296b8430fc 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -23,3 +23,4 @@ are configurable at compile, boot or run time. gather_data_sampling reg-file-data-sampling rsb + indirect-target-selection diff --git a/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst new file mode 100644 index 000000000000..d9ca64108d23 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst @@ -0,0 +1,168 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Indirect Target Selection (ITS) +=============================== + +ITS is a vulnerability in some Intel CPUs that support Enhanced IBRS and were +released before Alder Lake. ITS may allow an attacker to control the prediction +of indirect branches and RETs located in the lower half of a cacheline. + +ITS is assigned CVE-2024-28956 with a CVSS score of 4.7 (Medium). + +Scope of Impact +--------------- +- **eIBRS Guest/Host Isolation**: Indirect branches in KVM/kernel may still be + predicted with unintended target corresponding to a branch in the guest. + +- **Intra-Mode BTI**: In-kernel training such as through cBPF or other native + gadgets. + +- **Indirect Branch Prediction Barrier (IBPB)**: After an IBPB, indirect + branches may still be predicted with targets corresponding to direct branches + executed prior to the IBPB. This is fixed by the IPU 2025.1 microcode, which + should be available via distro updates. Alternatively microcode can be + obtained from Intel's github repository [#f1]_. + +Affected CPUs +------------- +Below is the list of ITS affected CPUs [#f2]_ [#f3]_: + + ======================== ============ ==================== =============== + Common name Family_Model eIBRS Intra-mode BTI + Guest/Host Isolation + ======================== ============ ==================== =============== + SKYLAKE_X (step >= 6) 06_55H Affected Affected + ICELAKE_X 06_6AH Not affected Affected + ICELAKE_D 06_6CH Not affected Affected + ICELAKE_L 06_7EH Not affected Affected + TIGERLAKE_L 06_8CH Not affected Affected + TIGERLAKE 06_8DH Not affected Affected + KABYLAKE_L (step >= 12) 06_8EH Affected Affected + KABYLAKE (step >= 13) 06_9EH Affected Affected + COMETLAKE 06_A5H Affected Affected + COMETLAKE_L 06_A6H Affected Affected + ROCKETLAKE 06_A7H Not affected Affected + ======================== ============ ==================== =============== + +- All affected CPUs enumerate Enhanced IBRS feature. +- IBPB isolation is affected on all ITS affected CPUs, and need a microcode + update for mitigation. +- None of the affected CPUs enumerate BHI_CTRL which was introduced in Golden + Cove (Alder Lake and Sapphire Rapids). This can help guests to determine the + host's affected status. +- Intel Atom CPUs are not affected by ITS. + +Mitigation +---------- +As only the indirect branches and RETs that have their last byte of instruction +in the lower half of the cacheline are vulnerable to ITS, the basic idea behind +the mitigation is to not allow indirect branches in the lower half. + +This is achieved by relying on existing retpoline support in the kernel, and in +compilers. ITS-vulnerable retpoline sites are runtime patched to point to newly +added ITS-safe thunks. These safe thunks consists of indirect branch in the +second half of the cacheline. Not all retpoline sites are patched to thunks, if +a retpoline site is evaluated to be ITS-safe, it is replaced with an inline +indirect branch. + +Dynamic thunks +~~~~~~~~~~~~~~ +From a dynamically allocated pool of safe-thunks, each vulnerable site is +replaced with a new thunk, such that they get a unique address. This could +improve the branch prediction accuracy. Also, it is a defense-in-depth measure +against aliasing. + +Note, for simplicity, indirect branches in eBPF programs are always replaced +with a jump to a static thunk in __x86_indirect_its_thunk_array. If required, +in future this can be changed to use dynamic thunks. + +All vulnerable RETs are replaced with a static thunk, they do not use dynamic +thunks. This is because RETs get their prediction from RSB mostly that does not +depend on source address. RETs that underflow RSB may benefit from dynamic +thunks. But, RETs significantly outnumber indirect branches, and any benefit +from a unique source address could be outweighed by the increased icache +footprint and iTLB pressure. + +Retpoline +~~~~~~~~~ +Retpoline sequence also mitigates ITS-unsafe indirect branches. For this +reason, when retpoline is enabled, ITS mitigation only relocates the RETs to +safe thunks. Unless user requested the RSB-stuffing mitigation. + +RSB Stuffing +~~~~~~~~~~~~ +RSB-stuffing via Call Depth Tracking is a mitigation for Retbleed RSB-underflow +attacks. And it also mitigates RETs that are vulnerable to ITS. + +Mitigation in guests +^^^^^^^^^^^^^^^^^^^^ +All guests deploy ITS mitigation by default, irrespective of eIBRS enumeration +and Family/Model of the guest. This is because eIBRS feature could be hidden +from a guest. One exception to this is when a guest enumerates BHI_DIS_S, which +indicates that the guest is running on an unaffected host. + +To prevent guests from unnecessarily deploying the mitigation on unaffected +platforms, Intel has defined ITS_NO bit(62) in MSR IA32_ARCH_CAPABILITIES. When +a guest sees this bit set, it should not enumerate the ITS bug. Note, this bit +is not set by any hardware, but is **intended for VMMs to synthesize** it for +guests as per the host's affected status. + +Mitigation options +^^^^^^^^^^^^^^^^^^ +The ITS mitigation can be controlled using the "indirect_target_selection" +kernel parameter. The available options are: + + ======== =================================================================== + on (default) Deploy the "Aligned branch/return thunks" mitigation. + If spectre_v2 mitigation enables retpoline, aligned-thunks are only + deployed for the affected RET instructions. Retpoline mitigates + indirect branches. + + off Disable ITS mitigation. + + vmexit Equivalent to "=on" if the CPU is affected by guest/host isolation + part of ITS. Otherwise, mitigation is not deployed. This option is + useful when host userspace is not in the threat model, and only + attacks from guest to host are considered. + + stuff Deploy RSB-fill mitigation when retpoline is also deployed. + Otherwise, deploy the default mitigation. When retpoline mitigation + is enabled, RSB-stuffing via Call-Depth-Tracking also mitigates + ITS. + + force Force the ITS bug and deploy the default mitigation. + ======== =================================================================== + +Sysfs reporting +--------------- + +The sysfs file showing ITS mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/indirect_target_selection + +Note, microcode mitigation status is not reported in this file. + +The possible values in this file are: + +.. list-table:: + + * - Not affected + - The processor is not vulnerable. + * - Vulnerable + - System is vulnerable and no mitigation has been applied. + * - Vulnerable, KVM: Not affected + - System is vulnerable to intra-mode BTI, but not affected by eIBRS + guest/host isolation. + * - Mitigation: Aligned branch/return thunks + - The mitigation is enabled, affected indirect branches and RETs are + relocated to safe thunks. + * - Mitigation: Retpolines, Stuffing RSB + - The mitigation is enabled using retpoline and RSB stuffing. + +References +---------- +.. [#f1] Microcode repository - https://github.com/intel/Intel-Linux-Processor-Microcode-Data-Files + +.. [#f2] Affected Processors list - https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html + +.. [#f3] Affected Processors list (machine readable) - https://github.com/intel/Intel-affected-processor-list diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index d9fd26b95b34..30532eb7bb19 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2202,6 +2202,23 @@ different crypto accelerators. This option can be used to achieve best performance for particular HW. + indirect_target_selection= [X86,Intel] Mitigation control for Indirect + Target Selection(ITS) bug in Intel CPUs. Updated + microcode is also required for a fix in IBPB. + + on: Enable mitigation (default). + off: Disable mitigation. + force: Force the ITS bug and deploy default + mitigation. + vmexit: Only deploy mitigation if CPU is affected by + guest/host isolation part of ITS. + stuff: Deploy RSB-fill mitigation when retpoline is + also deployed. Otherwise, deploy the default + mitigation. + + For details see: + Documentation/admin-guide/hw-vuln/indirect-target-selection.rst + init= [KNL] Format: <full_path> Run specified binary instead of /sbin/init as init @@ -3693,6 +3710,7 @@ expose users to several CPU vulnerabilities. Equivalent to: if nokaslr then kpti=0 [ARM64] gather_data_sampling=off [X86] + indirect_target_selection=off [X86] kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] @@ -6250,7 +6268,7 @@ port and the regular usb controller gets disabled. root= [KNL] Root filesystem - Usually this a a block device specifier of some kind, + Usually this is a block device specifier of some kind, see the early_lookup_bdev comment in block/early-lookup.c for details. Alternatively this can be "ram" for the legacy initial diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 8290177b4f75..d385985b305f 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -75,6 +75,7 @@ Currently, these files are in /proc/sys/vm: - unprivileged_userfaultfd - user_reserve_kbytes - vfs_cache_pressure +- vfs_cache_pressure_denom - watermark_boost_factor - watermark_scale_factor - zone_reclaim_mode @@ -1017,19 +1018,28 @@ vfs_cache_pressure This percentage value controls the tendency of the kernel to reclaim the memory which is used for caching of directory and inode objects. -At the default value of vfs_cache_pressure=100 the kernel will attempt to -reclaim dentries and inodes at a "fair" rate with respect to pagecache and -swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer -to retain dentry and inode caches. When vfs_cache_pressure=0, the kernel will -never reclaim dentries and inodes due to memory pressure and this can easily -lead to out-of-memory conditions. Increasing vfs_cache_pressure beyond 100 -causes the kernel to prefer to reclaim dentries and inodes. +At the default value of vfs_cache_pressure=vfs_cache_pressure_denom the kernel +will attempt to reclaim dentries and inodes at a "fair" rate with respect to +pagecache and swapcache reclaim. Decreasing vfs_cache_pressure causes the +kernel to prefer to retain dentry and inode caches. When vfs_cache_pressure=0, +the kernel will never reclaim dentries and inodes due to memory pressure and +this can easily lead to out-of-memory conditions. Increasing vfs_cache_pressure +beyond vfs_cache_pressure_denom causes the kernel to prefer to reclaim dentries +and inodes. -Increasing vfs_cache_pressure significantly beyond 100 may have negative -performance impact. Reclaim code needs to take various locks to find freeable -directory and inode objects. With vfs_cache_pressure=1000, it will look for -ten times more freeable objects than there are. +Increasing vfs_cache_pressure significantly beyond vfs_cache_pressure_denom may +have negative performance impact. Reclaim code needs to take various locks to +find freeable directory and inode objects. When vfs_cache_pressure equals +(10 * vfs_cache_pressure_denom), it will look for ten times more freeable +objects than there are. +Note: This setting should always be used together with vfs_cache_pressure_denom. + +vfs_cache_pressure_denom +======================== + +Defaults to 100 (minimum allowed value). Requires corresponding +vfs_cache_pressure setting to take effect. watermark_boost_factor ====================== diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml index 517a4ac1bea3..e365413732e7 100644 --- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek's Keypad Controller maintainers: - - Mattijs Korpershoek <mkorpershoek@baylibre.com> + - Mattijs Korpershoek <mkorpershoek@kernel.org> allOf: - $ref: /schemas/input/matrix-keymap.yaml# diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml index e0ec53bc10c6..1525a50ded47 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/can/microchip,mcp2510.yaml# +$id: http://devicetree.org/schemas/net/can/microchip,mcp2510.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip MCP251X stand-alone CAN controller diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 45819b235800..a2d4c626f659 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -74,19 +74,17 @@ properties: - rev-rmii - moca - # RX and TX delays are added by the MAC when required + # RX and TX delays are provided by the PCB. See below - rgmii - # RGMII with internal RX and TX delays provided by the PHY, - # the MAC should not add the RX or TX delays in this case + # RX and TX delays are not provided by the PCB. This is the most + # frequent case. See below - rgmii-id - # RGMII with internal RX delay provided by the PHY, the MAC - # should not add an RX delay in this case + # TX delay is provided by the PCB. See below - rgmii-rxid - # RGMII with internal TX delay provided by the PHY, the MAC - # should not add an TX delay in this case + # RX delay is provided by the PCB. See below - rgmii-txid - rtbi - smii @@ -286,4 +284,89 @@ allOf: additionalProperties: true +# Informative +# =========== +# +# 'phy-modes' & 'phy-connection-type' properties 'rgmii', 'rgmii-id', +# 'rgmii-rxid', and 'rgmii-txid' are frequently used wrongly by +# developers. This informative section clarifies their usage. +# +# The RGMII specification requires a 2ns delay between the data and +# clock signals on the RGMII bus. How this delay is implemented is not +# specified. +# +# One option is to make the clock traces on the PCB longer than the +# data traces. A sufficiently difference in length can provide the 2ns +# delay. If both the RX and TX delays are implemented in this manner, +# 'rgmii' should be used, so indicating the PCB adds the delays. +# +# If the PCB does not add these delays via extra long traces, +# 'rgmii-id' should be used. Here, 'id' refers to 'internal delay', +# where either the MAC or PHY adds the delay. +# +# If only one of the two delays are implemented via extra long clock +# lines, either 'rgmii-rxid' or 'rgmii-txid' should be used, +# indicating the MAC or PHY should implement one of the delays +# internally, while the PCB implements the other delay. +# +# Device Tree describes hardware, and in this case, it describes the +# PCB between the MAC and the PHY, if the PCB implements delays or +# not. +# +# In practice, very few PCBs make use of extra long clock lines. Hence +# any RGMII phy mode other than 'rgmii-id' is probably wrong, and is +# unlikely to be accepted during review without details provided in +# the commit description and comments in the .dts file. +# +# When the PCB does not implement the delays, the MAC or PHY must. As +# such, this is software configuration, and so not described in Device +# Tree. +# +# The following describes how Linux implements the configuration of +# the MAC and PHY to add these delays when the PCB does not. As stated +# above, developers often get this wrong, and the aim of this section +# is reduce the frequency of these errors by Linux developers. Other +# users of the Device Tree may implement it differently, and still be +# consistent with both the normative and informative description +# above. +# +# By default in Linux, when using phylib/phylink, the MAC is expected +# to read the 'phy-mode' from Device Tree, not implement any delays, +# and pass the value to the PHY. The PHY will then implement delays as +# specified by the 'phy-mode'. The PHY should always be reconfigured +# to implement the needed delays, replacing any setting performed by +# strapping or the bootloader, etc. +# +# Experience to date is that all PHYs which implement RGMII also +# implement the ability to add or not add the needed delays. Hence +# this default is expected to work in all cases. Ignoring this default +# is likely to be questioned by Reviews, and require a strong argument +# to be accepted. +# +# There are a small number of cases where the MAC has hard coded +# delays which cannot be disabled. The 'phy-mode' only describes the +# PCB. The inability to disable the delays in the MAC does not change +# the meaning of 'phy-mode'. It does however mean that a 'phy-mode' of +# 'rgmii' is now invalid, it cannot be supported, since both the PCB +# and the MAC and PHY adding delays cannot result in a functional +# link. Thus the MAC should report a fatal error for any modes which +# cannot be supported. When the MAC implements the delay, it must +# ensure that the PHY does not also implement the same delay. So it +# must modify the phy-mode it passes to the PHY, removing the delay it +# has added. Failure to remove the delay will result in a +# non-functioning link. +# +# Sometimes there is a need to fine tune the delays. Often the MAC or +# PHY can perform this fine tuning. In the MAC node, the Device Tree +# properties 'rx-internal-delay-ps' and 'tx-internal-delay-ps' should +# be used to indicate fine tuning performed by the MAC. The values +# expected here are small. A value of 2000ps, i.e 2ns, and a phy-mode +# of 'rgmii' will not be accepted by Reviewers. +# +# If the PHY is to perform fine tuning, the properties +# 'rx-internal-delay-ps' and 'tx-internal-delay-ps' in the PHY node +# should be used. When the PHY is implementing delays, e.g. 'rgmii-id' +# these properties should have a value near to 2000ps. If the PCB is +# implementing delays, e.g. 'rgmii', a small value can be used to fine +# tune the delay added by the PCB. ... diff --git a/Documentation/driver-api/early-userspace/buffer-format.rst b/Documentation/driver-api/early-userspace/buffer-format.rst index 7f74e301fdf3..726bfa2fe70d 100644 --- a/Documentation/driver-api/early-userspace/buffer-format.rst +++ b/Documentation/driver-api/early-userspace/buffer-format.rst @@ -4,20 +4,18 @@ initramfs buffer format Al Viro, H. Peter Anvin -Last revision: 2002-01-13 - -Starting with kernel 2.5.x, the old "initial ramdisk" protocol is -getting {replaced/complemented} with the new "initial ramfs" -(initramfs) protocol. The initramfs contents is passed using the same -memory buffer protocol used by the initrd protocol, but the contents +With kernel 2.5.x, the old "initial ramdisk" protocol was complemented +with an "initial ramfs" protocol. The initramfs content is passed +using the same memory buffer protocol used by initrd, but the content is different. The initramfs buffer contains an archive which is -expanded into a ramfs filesystem; this document details the format of -the initramfs buffer format. +expanded into a ramfs filesystem; this document details the initramfs +buffer format. The initramfs buffer format is based around the "newc" or "crc" CPIO formats, and can be created with the cpio(1) utility. The cpio -archive can be compressed using gzip(1). One valid version of an -initramfs buffer is thus a single .cpio.gz file. +archive can be compressed using gzip(1), or any other algorithm provided +via CONFIG_DECOMPRESS_*. One valid version of an initramfs buffer is +thus a single .cpio.gz file. The full format of the initramfs buffer is defined by the following grammar, where:: @@ -25,12 +23,20 @@ grammar, where:: * is used to indicate "0 or more occurrences of" (|) indicates alternatives + indicates concatenation - GZIP() indicates the gzip(1) of the operand + GZIP() indicates gzip compression of the operand + BZIP2() indicates bzip2 compression of the operand + LZMA() indicates lzma compression of the operand + XZ() indicates xz compression of the operand + LZO() indicates lzo compression of the operand + LZ4() indicates lz4 compression of the operand + ZSTD() indicates zstd compression of the operand ALGN(n) means padding with null bytes to an n-byte boundary - initramfs := ("\0" | cpio_archive | cpio_gzip_archive)* + initramfs := ("\0" | cpio_archive | cpio_compressed_archive)* - cpio_gzip_archive := GZIP(cpio_archive) + cpio_compressed_archive := (GZIP(cpio_archive) | BZIP2(cpio_archive) + | LZMA(cpio_archive) | XZ(cpio_archive) | LZO(cpio_archive) + | LZ4(cpio_archive) | ZSTD(cpio_archive)) cpio_archive := cpio_file* + (<nothing> | cpio_trailer) @@ -75,6 +81,8 @@ c_chksum 8 bytes Checksum of data field if c_magic is 070702; The c_mode field matches the contents of st_mode returned by stat(2) on Linux, and encodes the file type and file permissions. +c_mtime is ignored unless CONFIG_INITRAMFS_PRESERVE_MTIME=y is set. + The c_filesize should be zero for any file which is not a regular file or symlink. diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index e80329908549..3d22e2db732d 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -1409,7 +1409,7 @@ read the ciphertext into the page cache and decrypt it in-place. The folio lock must be held until decryption has finished, to prevent the folio from becoming visible to userspace prematurely. -For the write path (->writepage()) of regular files, filesystems +For the write path (->writepages()) of regular files, filesystems cannot encrypt data in-place in the page cache, since the cached plaintext must be preserved. Instead, filesystems must encrypt into a temporary buffer or "bounce page", then write out the temporary diff --git a/Documentation/filesystems/iomap/design.rst b/Documentation/filesystems/iomap/design.rst index e29651a42eec..f2df9b6df988 100644 --- a/Documentation/filesystems/iomap/design.rst +++ b/Documentation/filesystems/iomap/design.rst @@ -243,13 +243,25 @@ The fields are as follows: regular file data. This is only useful for FIEMAP. - * **IOMAP_F_PRIVATE**: Starting with this value, the upper bits can - be set by the filesystem for its own purposes. + * **IOMAP_F_BOUNDARY**: This indicates I/O and its completion must not be + merged with any other I/O or completion. Filesystems must use this when + submitting I/O to devices that cannot handle I/O crossing certain LBAs + (e.g. ZNS devices). This flag applies only to buffered I/O writeback; all + other functions ignore it. + + * **IOMAP_F_PRIVATE**: This flag is reserved for filesystem private use. * **IOMAP_F_ANON_WRITE**: Indicates that (write) I/O does not have a target block assigned to it yet and the file system will do that in the bio submission handler, splitting the I/O as needed. + * **IOMAP_F_ATOMIC_BIO**: This indicates write I/O must be submitted with the + ``REQ_ATOMIC`` flag set in the bio. Filesystems need to set this flag to + inform iomap that the write I/O operation requires torn-write protection + based on HW-offload mechanism. They must also ensure that mapping updates + upon the completion of the I/O must be performed in a single metadata + update. + These flags can be set by iomap itself during file operations. The filesystem should supply an ``->iomap_end`` function if it needs to observe these flags: diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 0ec0bb6eb0fb..2e567e341c3b 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -249,7 +249,6 @@ address_space_operations ======================== prototypes:: - int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); int (*writepages)(struct address_space *, struct writeback_control *); bool (*dirty_folio)(struct address_space *, struct folio *folio); @@ -280,7 +279,6 @@ locking rules: ====================== ======================== ========= =============== ops folio locked i_rwsem invalidate_lock ====================== ======================== ========= =============== -writepage: yes, unlocks (see below) read_folio: yes, unlocks shared writepages: dirty_folio: maybe @@ -309,54 +307,6 @@ completion. ->readahead() unlocks the folios that I/O is attempted on like ->read_folio(). -->writepage() is used for two purposes: for "memory cleansing" and for -"sync". These are quite different operations and the behaviour may differ -depending upon the mode. - -If writepage is called for sync (wbc->sync_mode != WBC_SYNC_NONE) then -it *must* start I/O against the page, even if that would involve -blocking on in-progress I/O. - -If writepage is called for memory cleansing (sync_mode == -WBC_SYNC_NONE) then its role is to get as much writeout underway as -possible. So writepage should try to avoid blocking against -currently-in-progress I/O. - -If the filesystem is not called for "sync" and it determines that it -would need to block against in-progress I/O to be able to start new I/O -against the page the filesystem should redirty the page with -redirty_page_for_writepage(), then unlock the page and return zero. -This may also be done to avoid internal deadlocks, but rarely. - -If the filesystem is called for sync then it must wait on any -in-progress I/O and then start new I/O. - -The filesystem should unlock the page synchronously, before returning to the -caller, unless ->writepage() returns special WRITEPAGE_ACTIVATE -value. WRITEPAGE_ACTIVATE means that page cannot really be written out -currently, and VM should stop calling ->writepage() on this page for some -time. VM does this by moving page to the head of the active list, hence the -name. - -Unless the filesystem is going to redirty_page_for_writepage(), unlock the page -and return zero, writepage *must* run set_page_writeback() against the page, -followed by unlocking it. Once set_page_writeback() has been run against the -page, write I/O can be submitted and the write I/O completion handler must run -end_page_writeback() once the I/O is complete. If no I/O is submitted, the -filesystem must run end_page_writeback() against the page before returning from -writepage. - -That is: after 2.5.12, pages which are under writeout are *not* locked. Note, -if the filesystem needs the page to be locked during writeout, that is ok, too, -the page is allowed to be unlocked at any point in time between the calls to -set_page_writeback() and end_page_writeback(). - -Note, failure to run either redirty_page_for_writepage() or the combination of -set_page_writeback()/end_page_writeback() on a page submitted to writepage -will leave the page itself marked clean but it will be tagged as dirty in the -radix tree. This incoherency can lead to all sorts of hard-to-debug problems -in the filesystem like having dirty inodes at umount and losing written data. - ->writepages() is used for periodic writeback and for syscall-initiated sync operations. The address_space should start I/O against at least ``*nr_to_write`` pages. ``*nr_to_write`` must be decremented for each page @@ -364,8 +314,8 @@ which is written. The address_space implementation may write more (or less) pages than ``*nr_to_write`` asks for, but it should try to be reasonably close. If nr_to_write is NULL, all dirty pages must be written. -writepages should _only_ write pages which are present on -mapping->io_pages. +writepages should _only_ write pages which are present in +mapping->i_pages. ->dirty_folio() is called from various places in the kernel when the target folio is marked as needing writeback. The folio cannot be diff --git a/Documentation/filesystems/mount_api.rst b/Documentation/filesystems/mount_api.rst index d92c276f1575..e149b89118c8 100644 --- a/Documentation/filesystems/mount_api.rst +++ b/Documentation/filesystems/mount_api.rst @@ -671,7 +671,6 @@ The members are as follows: fsparam_bool() fs_param_is_bool fsparam_u32() fs_param_is_u32 fsparam_u32oct() fs_param_is_u32_octal - fsparam_u32hex() fs_param_is_u32_hex fsparam_s32() fs_param_is_s32 fsparam_u64() fs_param_is_u64 fsparam_enum() fs_param_is_enum @@ -755,21 +754,6 @@ process the parameters it is given. * :: - bool validate_constant_table(const struct constant_table *tbl, - size_t tbl_size, - int low, int high, int special); - - Validate a constant table. Checks that all the elements are appropriately - ordered, that there are no duplicates and that the values are between low - and high inclusive, though provision is made for one allowable special - value outside of that range. If no special value is required, special - should just be set to lie inside the low-to-high range. - - If all is good, true is returned. If the table is invalid, errors are - logged to the kernel log buffer and false is returned. - - * :: - bool fs_validate_description(const char *name, const struct fs_parameter_description *desc); diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 3886c14f89f4..939b4b624fad 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -1,33 +1,187 @@ .. SPDX-License-Identifier: GPL-2.0 -================================= -Network Filesystem Helper Library -================================= +=================================== +Network Filesystem Services Library +=================================== .. Contents: - Overview. + - Requests and streams. + - Subrequests. + - Result collection and retry. + - Local caching. + - Content encryption (fscrypt). - Per-inode context. - Inode context helper functions. - - Buffered read helpers. - - Read helper functions. - - Read helper structures. - - Read helper operations. - - Read helper procedure. - - Read helper cache API. + - Inode locking. + - Inode writeback. + - High-level VFS API. + - Unlocked read/write iter. + - Pre-locked read/write iter. + - Monolithic files API. + - Memory-mapped I/O API. + - High-level VM API. + - Deprecated PG_private2 API. + - I/O request API. + - Request structure. + - Stream structure. + - Subrequest structure. + - Filesystem methods. + - Terminating a subrequest. + - Local cache API. + - API function reference. Overview ======== -The network filesystem helper library is a set of functions designed to aid a -network filesystem in implementing VM/VFS operations. For the moment, that -just includes turning various VM buffered read operations into requests to read -from the server. The helper library, however, can also interpose other -services, such as local caching or local data encryption. +The network filesystem services library, netfslib, is a set of functions +designed to aid a network filesystem in implementing VM/VFS API operations. It +takes over the normal buffered read, readahead, write and writeback and also +handles unbuffered and direct I/O. -Note that the library module doesn't link against local caching directly, so -access must be provided by the netfs. +The library provides support for (re-)negotiation of I/O sizes and retrying +failed I/O as well as local caching and will, in the future, provide content +encryption. + +It insulates the filesystem from VM interface changes as much as possible and +handles VM features such as large multipage folios. The filesystem basically +just has to provide a way to perform read and write RPC calls. + +The way I/O is organised inside netfslib consists of a number of objects: + + * A *request*. A request is used to track the progress of the I/O overall and + to hold on to resources. The collection of results is done at the request + level. The I/O within a request is divided into a number of parallel + streams of subrequests. + + * A *stream*. A non-overlapping series of subrequests. The subrequests + within a stream do not have to be contiguous. + + * A *subrequest*. This is the basic unit of I/O. It represents a single RPC + call or a single cache I/O operation. The library passes these to the + filesystem and the cache to perform. + +Requests and Streams +-------------------- + +When actually performing I/O (as opposed to just copying into the pagecache), +netfslib will create one or more requests to track the progress of the I/O and +to hold resources. + +A read operation will have a single stream and the subrequests within that +stream may be of mixed origins, for instance mixing RPC subrequests and cache +subrequests. + +On the other hand, a write operation may have multiple streams, where each +stream targets a different destination. For instance, there may be one stream +writing to the local cache and one to the server. Currently, only two streams +are allowed, but this could be increased if parallel writes to multiple servers +is desired. + +The subrequests within a write stream do not need to match alignment or size +with the subrequests in another write stream and netfslib performs the tiling +of subrequests in each stream over the source buffer independently. Further, +each stream may contain holes that don't correspond to holes in the other +stream. + +In addition, the subrequests do not need to correspond to the boundaries of the +folios or vectors in the source/destination buffer. The library handles the +collection of results and the wrangling of folio flags and references. + +Subrequests +----------- + +Subrequests are at the heart of the interaction between netfslib and the +filesystem using it. Each subrequest is expected to correspond to a single +read or write RPC or cache operation. The library will stitch together the +results from a set of subrequests to provide a higher level operation. + +Netfslib has two interactions with the filesystem or the cache when setting up +a subrequest. First, there's an optional preparatory step that allows the +filesystem to negotiate the limits on the subrequest, both in terms of maximum +number of bytes and maximum number of vectors (e.g. for RDMA). This may +involve negotiating with the server (e.g. cifs needing to acquire credits). + +And, secondly, there's the issuing step in which the subrequest is handed off +to the filesystem to perform. + +Note that these two steps are done slightly differently between read and write: + + * For reads, the VM/VFS tells us how much is being requested up front, so the + library can preset maximum values that the cache and then the filesystem can + then reduce. The cache also gets consulted first on whether it wants to do + a read before the filesystem is consulted. + + * For writeback, it is unknown how much there will be to write until the + pagecache is walked, so no limit is set by the library. + +Once a subrequest is completed, the filesystem or cache informs the library of +the completion and then collection is invoked. Depending on whether the +request is synchronous or asynchronous, the collection of results will be done +in either the application thread or in a work queue. + +Result Collection and Retry +--------------------------- + +As subrequests complete, the results are collected and collated by the library +and folio unlocking is performed progressively (if appropriate). Once the +request is complete, async completion will be invoked (again, if appropriate). +It is possible for the filesystem to provide interim progress reports to the +library to cause folio unlocking to happen earlier if possible. + +If any subrequests fail, netfslib can retry them. It will wait until all +subrequests are completed, offer the filesystem the opportunity to fiddle with +the resources/state held by the request and poke at the subrequests before +re-preparing and re-issuing the subrequests. + +This allows the tiling of contiguous sets of failed subrequest within a stream +to be changed, adding more subrequests or ditching excess as necessary (for +instance, if the network sizes change or the server decides it wants smaller +chunks). + +Further, if one or more contiguous cache-read subrequests fail, the library +will pass them to the filesystem to perform instead, renegotiating and retiling +them as necessary to fit with the filesystem's parameters rather than those of +the cache. + +Local Caching +------------- + +One of the services netfslib provides, via ``fscache``, is the option to cache +on local disk a copy of the data obtained from/written to a network filesystem. +The library will manage the storing, retrieval and some invalidation of data +automatically on behalf of the filesystem if a cookie is attached to the +``netfs_inode``. + +Note that local caching used to use the PG_private_2 (aliased as PG_fscache) to +keep track of a page that was being written to the cache, but this is now +deprecated as PG_private_2 will be removed. + +Instead, folios that are read from the server for which there was no data in +the cache will be marked as dirty and will have ``folio->private`` set to a +special value (``NETFS_FOLIO_COPY_TO_CACHE``) and left to writeback to write. +If the folio is modified before that happened, the special value will be +cleared and the write will become normally dirty. + +When writeback occurs, folios that are so marked will only be written to the +cache and not to the server. Writeback handles mixed cache-only writes and +server-and-cache writes by using two streams, sending one to the cache and one +to the server. The server stream will have gaps in it corresponding to those +folios. + +Content Encryption (fscrypt) +---------------------------- + +Though it does not do so yet, at some point netfslib will acquire the ability +to do client-side content encryption on behalf of the network filesystem (Ceph, +for example). fscrypt can be used for this if appropriate (it may not be - +cifs, for example). + +The data will be stored encrypted in the local cache using the same manner of +encryption as the data written to the server and the library will impose bounce +buffering and RMW cycles as necessary. Per-Inode Context @@ -40,10 +194,13 @@ structure is defined:: struct netfs_inode { struct inode inode; const struct netfs_request_ops *ops; - struct fscache_cookie *cache; + struct fscache_cookie * cache; + loff_t remote_i_size; + unsigned long flags; + ... }; -A network filesystem that wants to use netfs lib must place one of these in its +A network filesystem that wants to use netfslib must place one of these in its inode wrapper struct instead of the VFS ``struct inode``. This can be done in a way similar to the following:: @@ -56,7 +213,8 @@ This allows netfslib to find its state by using ``container_of()`` from the inode pointer, thereby allowing the netfslib helper functions to be pointed to directly by the VFS/VM operation tables. -The structure contains the following fields: +The structure contains the following fields that are of interest to the +filesystem: * ``inode`` @@ -71,6 +229,37 @@ The structure contains the following fields: Local caching cookie, or NULL if no caching is enabled. This field does not exist if fscache is disabled. + * ``remote_i_size`` + + The size of the file on the server. This differs from inode->i_size if + local modifications have been made but not yet written back. + + * ``flags`` + + A set of flags, some of which the filesystem might be interested in: + + * ``NETFS_ICTX_MODIFIED_ATTR`` + + Set if netfslib modifies mtime/ctime. The filesystem is free to ignore + this or clear it. + + * ``NETFS_ICTX_UNBUFFERED`` + + Do unbuffered I/O upon the file. Like direct I/O but without the + alignment limitations. RMW will be performed if necessary. The pagecache + will not be used unless mmap() is also used. + + * ``NETFS_ICTX_WRITETHROUGH`` + + Do writethrough caching upon the file. I/O will be set up and dispatched + as buffered writes are made to the page cache. mmap() does the normal + writeback thing. + + * ``NETFS_ICTX_SINGLE_NO_UPLOAD`` + + Set if the file has a monolithic content that must be read entirely in a + single go and must not be written back to the server, though it can be + cached (e.g. AFS directories). Inode Context Helper Functions ------------------------------ @@ -84,117 +273,250 @@ set the operations table pointer:: then a function to cast from the VFS inode structure to the netfs context:: - struct netfs_inode *netfs_node(struct inode *inode); + struct netfs_inode *netfs_inode(struct inode *inode); and finally, a function to get the cache cookie pointer from the context attached to an inode (or NULL if fscache is disabled):: struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx); +Inode Locking +------------- + +A number of functions are provided to manage the locking of i_rwsem for I/O and +to effectively extend it to provide more separate classes of exclusion:: + + int netfs_start_io_read(struct inode *inode); + void netfs_end_io_read(struct inode *inode); + int netfs_start_io_write(struct inode *inode); + void netfs_end_io_write(struct inode *inode); + int netfs_start_io_direct(struct inode *inode); + void netfs_end_io_direct(struct inode *inode); + +The exclusion breaks down into four separate classes: + + 1) Buffered reads and writes. + + Buffered reads can run concurrently each other and with buffered writes, + but buffered writes cannot run concurrently with each other. + + 2) Direct reads and writes. + + Direct (and unbuffered) reads and writes can run concurrently since they do + not share local buffering (i.e. the pagecache) and, in a network + filesystem, are expected to have exclusion managed on the server (though + this may not be the case for, say, Ceph). + + 3) Other major inode modifying operations (e.g. truncate, fallocate). + + These should just access i_rwsem directly. + + 4) mmap(). + + mmap'd accesses might operate concurrently with any of the other classes. + They might form the buffer for an intra-file loopback DIO read/write. They + might be permitted on unbuffered files. + +Inode Writeback +--------------- + +Netfslib will pin resources on an inode for future writeback (such as pinning +use of an fscache cookie) when an inode is dirtied. However, this pinning +needs careful management. To manage the pinning, the following sequence +occurs: + + 1) An inode state flag ``I_PINNING_NETFS_WB`` is set by netfslib when the + pinning begins (when a folio is dirtied, for example) if the cache is + active to stop the cache structures from being discarded and the cache + space from being culled. This also prevents re-getting of cache resources + if the flag is already set. + + 2) This flag then cleared inside the inode lock during inode writeback in the + VM - and the fact that it was set is transferred to ``->unpinned_netfs_wb`` + in ``struct writeback_control``. + + 3) If ``->unpinned_netfs_wb`` is now set, the write_inode procedure is forced. + + 4) The filesystem's ``->write_inode()`` function is invoked to do the cleanup. + + 5) The filesystem invokes netfs to do its cleanup. + +To do the cleanup, netfslib provides a function to do the resource unpinning:: + + int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); + +If the filesystem doesn't need to do anything else, this may be set as a its +``.write_inode`` method. + +Further, if an inode is deleted, the filesystem's write_inode method may not +get called, so:: + + void netfs_clear_inode_writeback(struct inode *inode, const void *aux); -Buffered Read Helpers -===================== +must be called from ``->evict_inode()`` *before* ``clear_inode()`` is called. -The library provides a set of read helpers that handle the ->read_folio(), -->readahead() and much of the ->write_begin() VM operations and translate them -into a common call framework. -The following services are provided: +High-Level VFS API +================== - * Handle folios that span multiple pages. +Netfslib provides a number of sets of API calls for the filesystem to delegate +VFS operations to. Netfslib, in turn, will call out to the filesystem and the +cache to negotiate I/O sizes, issue RPCs and provide places for it to intervene +at various times. - * Insulate the netfs from VM interface changes. +Unlocked Read/Write Iter +------------------------ - * Allow the netfs to arbitrarily split reads up into pieces, even ones that - don't match folio sizes or folio alignments and that may cross folios. +The first API set is for the delegation of operations to netfslib when the +filesystem is called through the standard VFS read/write_iter methods:: - * Allow the netfs to expand a readahead request in both directions to meet its - needs. + ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); + ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); + ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); + ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); + ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); - * Allow the netfs to partially fulfil a read, which will then be resubmitted. +They can be assigned directly to ``.read_iter`` and ``.write_iter``. They +perform the inode locking themselves and the first two will switch between +buffered I/O and DIO as appropriate. - * Handle local caching, allowing cached data and server-read data to be - interleaved for a single request. +Pre-Locked Read/Write Iter +-------------------------- - * Handle clearing of bufferage that isn't on the server. +The second API set is for the delegation of operations to netfslib when the +filesystem is called through the standard VFS methods, but needs to do some +other stuff before or after calling netfslib whilst still inside locked section +(e.g. Ceph negotiating caps). The unbuffered read function is:: - * Handle retrying of reads that failed, switching reads from the cache to the - server as necessary. + ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter); - * In the future, this is a place that other services can be performed, such as - local encryption of data to be stored remotely or in the cache. +This must not be assigned directly to ``.read_iter`` and the filesystem is +responsible for performing the inode locking before calling it. In the case of +buffered read, the filesystem should use ``filemap_read()``. -From the network filesystem, the helpers require a table of operations. This -includes a mandatory method to issue a read operation along with a number of -optional methods. +There are three functions for writes:: + ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, + struct netfs_group *netfs_group); + ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group); + ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group); -Read Helper Functions +These must not be assigned directly to ``.write_iter`` and the filesystem is +responsible for performing the inode locking before calling them. + +The first two functions are for buffered writes; the first just adds some +standard write checks and jumps to the second, but if the filesystem wants to +do the checks itself, it can use the second directly. The third function is +for unbuffered or DIO writes. + +On all three write functions, there is a writeback group pointer (which should +be NULL if the filesystem doesn't use this). Writeback groups are set on +folios when they're modified. If a folio to-be-modified is already marked with +a different group, it is flushed first. The writeback API allows writing back +of a specific group. + +Memory-Mapped I/O API --------------------- -Three read helpers are provided:: +An API for support of mmap()'d I/O is provided:: + + vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); + +This allows the filesystem to delegate ``.page_mkwrite`` to netfslib. The +filesystem should not take the inode lock before calling it, but, as with the +locked write functions above, this does take a writeback group pointer. If the +page to be made writable is in a different group, it will be flushed first. + +Monolithic Files API +-------------------- + +There is also a special API set for files for which the content must be read in +a single RPC (and not written back) and is maintained as a monolithic blob +(e.g. an AFS directory), though it can be stored and updated in the local cache:: + + ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_iter *iter); + void netfs_single_mark_inode_dirty(struct inode *inode); + int netfs_writeback_single(struct address_space *mapping, + struct writeback_control *wbc, + struct iov_iter *iter); + +The first function reads from a file into the given buffer, reading from the +cache in preference if the data is cached there; the second function allows the +inode to be marked dirty, causing a later writeback; and the third function can +be called from the writeback code to write the data to the cache, if there is +one. - void netfs_readahead(struct readahead_control *ractl); - int netfs_read_folio(struct file *file, - struct folio *folio); - int netfs_write_begin(struct netfs_inode *ctx, - struct file *file, - struct address_space *mapping, - loff_t pos, - unsigned int len, - struct folio **_folio, - void **_fsdata); +The inode should be marked ``NETFS_ICTX_SINGLE_NO_UPLOAD`` if this API is to be +used. The writeback function requires the buffer to be of ITER_FOLIOQ type. -Each corresponds to a VM address space operation. These operations use the -state in the per-inode context. +High-Level VM API +================== -For ->readahead() and ->read_folio(), the network filesystem just point directly -at the corresponding read helper; whereas for ->write_begin(), it may be a -little more complicated as the network filesystem might want to flush -conflicting writes or track dirty data and needs to put the acquired folio if -an error occurs after calling the helper. +Netfslib also provides a number of sets of API calls for the filesystem to +delegate VM operations to. Again, netfslib, in turn, will call out to the +filesystem and the cache to negotiate I/O sizes, issue RPCs and provide places +for it to intervene at various times:: -The helpers manage the read request, calling back into the network filesystem -through the supplied table of operations. Waits will be performed as -necessary before returning for helpers that are meant to be synchronous. + void netfs_readahead(struct readahead_control *); + int netfs_read_folio(struct file *, struct folio *); + int netfs_writepages(struct address_space *mapping, + struct writeback_control *wbc); + bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio); + void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); + bool netfs_release_folio(struct folio *folio, gfp_t gfp); -If an error occurs, the ->free_request() will be called to clean up the -netfs_io_request struct allocated. If some parts of the request are in -progress when an error occurs, the request will get partially completed if -sufficient data is read. +These are ``address_space_operations`` methods and can be set directly in the +operations table. -Additionally, there is:: +Deprecated PG_private_2 API +--------------------------- - * void netfs_subreq_terminated(struct netfs_io_subrequest *subreq, - ssize_t transferred_or_error, - bool was_async); +There is also a deprecated function for filesystems that still use the +``->write_begin`` method:: -which should be called to complete a read subrequest. This is given the number -of bytes transferred or a negative error code, plus a flag indicating whether -the operation was asynchronous (ie. whether the follow-on processing can be -done in the current context, given this may involve sleeping). + int netfs_write_begin(struct netfs_inode *inode, struct file *file, + struct address_space *mapping, loff_t pos, unsigned int len, + struct folio **_folio, void **_fsdata); +It uses the deprecated PG_private_2 flag and so should not be used. -Read Helper Structures ----------------------- -The read helpers make use of a couple of structures to maintain the state of -the read. The first is a structure that manages a read request as a whole:: +I/O Request API +=============== + +The I/O request API comprises a number of structures and a number of functions +that the filesystem may need to use. + +Request Structure +----------------- + +The request structure manages the request as a whole, holding some resources +and state on behalf of the filesystem and tracking the collection of results:: struct netfs_io_request { + enum netfs_io_origin origin; struct inode *inode; struct address_space *mapping; - struct netfs_cache_resources cache_resources; + struct netfs_group *group; + struct netfs_io_stream io_streams[]; void *netfs_priv; - loff_t start; - size_t len; - loff_t i_size; - const struct netfs_request_ops *netfs_ops; + void *netfs_priv2; + unsigned long long start; + unsigned long long len; + unsigned long long i_size; unsigned int debug_id; + unsigned long flags; ... }; -The above fields are the ones the netfs can use. They are: +Many of the fields are for internal use, but the fields shown here are of +interest to the filesystem: + + * ``origin`` + + The origin of the request (readahead, read_folio, DIO read, writeback, ...). * ``inode`` * ``mapping`` @@ -202,11 +524,19 @@ The above fields are the ones the netfs can use. They are: The inode and the address space of the file being read from. The mapping may or may not point to inode->i_data. - * ``cache_resources`` + * ``group`` + + The writeback group this request is dealing with or NULL. This holds a ref + on the group. + + * ``io_streams`` - Resources for the local cache to use, if present. + The parallel streams of subrequests available to the request. Currently two + are available, but this may be made extensible in future. ``NR_IO_STREAMS`` + indicates the size of the array. * ``netfs_priv`` + * ``netfs_priv2`` The network filesystem's private data. The value for this can be passed in to the helper functions or set during the request. @@ -221,37 +551,121 @@ The above fields are the ones the netfs can use. They are: The size of the file at the start of the request. - * ``netfs_ops`` - - A pointer to the operation table. The value for this is passed into the - helper functions. - * ``debug_id`` A number allocated to this operation that can be displayed in trace lines for reference. + * ``flags`` + + Flags for managing and controlling the operation of the request. Some of + these may be of interest to the filesystem: + + * ``NETFS_RREQ_RETRYING`` + + Netfslib sets this when generating retries. + + * ``NETFS_RREQ_PAUSE`` + + The filesystem can set this to request to pause the library's subrequest + issuing loop - but care needs to be taken as netfslib may also set it. + + * ``NETFS_RREQ_NONBLOCK`` + * ``NETFS_RREQ_BLOCKED`` + + Netfslib sets the first to indicate that non-blocking mode was set by the + caller and the filesystem can set the second to indicate that it would + have had to block. + + * ``NETFS_RREQ_USE_PGPRIV2`` + + The filesystem can set this if it wants to use PG_private_2 to track + whether a folio is being written to the cache. This is deprecated as + PG_private_2 is going to go away. + +If the filesystem wants more private data than is afforded by this structure, +then it should wrap it and provide its own allocator. + +Stream Structure +---------------- + +A request is comprised of one or more parallel streams and each stream may be +aimed at a different target. + +For read requests, only stream 0 is used. This can contain a mixture of +subrequests aimed at different sources. For write requests, stream 0 is used +for the server and stream 1 is used for the cache. For buffered writeback, +stream 0 is not enabled unless a normal dirty folio is encountered, at which +point ->begin_writeback() will be invoked and the filesystem can mark the +stream available. + +The stream struct looks like:: + + struct netfs_io_stream { + unsigned char stream_nr; + bool avail; + size_t sreq_max_len; + unsigned int sreq_max_segs; + unsigned int submit_extendable_to; + ... + }; + +A number of members are available for access/use by the filesystem: + + * ``stream_nr`` + + The number of the stream within the request. + + * ``avail`` + + True if the stream is available for use. The filesystem should set this on + stream zero if in ->begin_writeback(). + + * ``sreq_max_len`` + * ``sreq_max_segs`` + + These are set by the filesystem or the cache in ->prepare_read() or + ->prepare_write() for each subrequest to indicate the maximum number of + bytes and, optionally, the maximum number of segments (if not 0) that that + subrequest can support. + + * ``submit_extendable_to`` -The second structure is used to manage individual slices of the overall read -request:: + The size that a subrequest can be rounded up to beyond the EOF, given the + available buffer. This allows the cache to work out if it can do a DIO read + or write that straddles the EOF marker. + +Subrequest Structure +-------------------- + +Individual units of I/O are managed by the subrequest structure. These +represent slices of the overall request and run independently:: struct netfs_io_subrequest { struct netfs_io_request *rreq; - loff_t start; + struct iov_iter io_iter; + unsigned long long start; size_t len; size_t transferred; unsigned long flags; + short error; unsigned short debug_index; + unsigned char stream_nr; ... }; -Each subrequest is expected to access a single source, though the helpers will +Each subrequest is expected to access a single source, though the library will handle falling back from one source type to another. The members are: * ``rreq`` A pointer to the read request. + * ``io_iter`` + + An I/O iterator representing a slice of the buffer to be read into or + written from. + * ``start`` * ``len`` @@ -260,241 +674,300 @@ handle falling back from one source type to another. The members are: * ``transferred`` - The amount of data transferred so far of the length of this slice. The - network filesystem or cache should start the operation this far into the - slice. If a short read occurs, the helpers will call again, having updated - this to reflect the amount read so far. + The amount of data transferred so far for this subrequest. This should be + added to with the length of the transfer made by this issuance of the + subrequest. If this is less than ``len`` then the subrequest may be + reissued to continue. * ``flags`` - Flags pertaining to the read. There are two of interest to the filesystem - or cache: + Flags for managing the subrequest. There are a number of interest to the + filesystem or cache: + + * ``NETFS_SREQ_MADE_PROGRESS`` + + Set by the filesystem to indicates that at least one byte of data was read + or written. + + * ``NETFS_SREQ_HIT_EOF`` + + The filesystem should set this if a read hit the EOF on the file (in which + case ``transferred`` should stop at the EOF). Netfslib may expand the + subrequest out to the size of the folio containing the EOF on the off + chance that a third party change happened or a DIO read may have asked for + more than is available. The library will clear any excess pagecache. * ``NETFS_SREQ_CLEAR_TAIL`` - This can be set to indicate that the remainder of the slice, from - transferred to len, should be cleared. + The filesystem can set this to indicate that the remainder of the slice, + from transferred to len, should be cleared. Do not set if HIT_EOF is set. + + * ``NETFS_SREQ_NEED_RETRY`` + + The filesystem can set this to tell netfslib to retry the subrequest. + + * ``NETFS_SREQ_BOUNDARY`` + + This can be set by the filesystem on a subrequest to indicate that it ends + at a boundary with the filesystem structure (e.g. at the end of a Ceph + object). It tells netfslib not to retile subrequests across it. * ``NETFS_SREQ_SEEK_DATA_READ`` - This is a hint to the cache that it might want to try skipping ahead to - the next data (ie. using SEEK_DATA). + This is a hint from netfslib to the cache that it might want to try + skipping ahead to the next data (ie. using SEEK_DATA). + + * ``error`` + + This is for the filesystem to store result of the subrequest. It should be + set to 0 if successful and a negative error code otherwise. * ``debug_index`` + * ``stream_nr`` A number allocated to this slice that can be displayed in trace lines for - reference. + reference and the number of the request stream that it belongs to. +If necessary, the filesystem can get and put extra refs on the subrequest it is +given:: -Read Helper Operations ----------------------- + void netfs_get_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what); + void netfs_put_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what); -The network filesystem must provide the read helpers with a table of operations -through which it can issue requests and negotiate:: +using netfs trace codes to indicate the reason. Care must be taken, however, +as once control of the subrequest is returned to netfslib, the same subrequest +can be reissued/retried. + +Filesystem Methods +------------------ + +The filesystem sets a table of operations in ``netfs_inode`` for netfslib to +use:: struct netfs_request_ops { - void (*init_request)(struct netfs_io_request *rreq, struct file *file); + mempool_t *request_pool; + mempool_t *subrequest_pool; + int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); + void (*free_subrequest)(struct netfs_io_subrequest *rreq); void (*expand_readahead)(struct netfs_io_request *rreq); - bool (*clamp_length)(struct netfs_io_subrequest *subreq); + int (*prepare_read)(struct netfs_io_subrequest *subreq); void (*issue_read)(struct netfs_io_subrequest *subreq); - bool (*is_still_valid)(struct netfs_io_request *rreq); - int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct folio **foliop, void **_fsdata); void (*done)(struct netfs_io_request *rreq); + void (*update_i_size)(struct inode *inode, loff_t i_size); + void (*post_modify)(struct inode *inode); + void (*begin_writeback)(struct netfs_io_request *wreq); + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + void (*retry_request)(struct netfs_io_request *wreq, + struct netfs_io_stream *stream); + void (*invalidate_cache)(struct netfs_io_request *wreq); }; -The operations are as follows: - - * ``init_request()`` +The table starts with a pair of optional pointers to memory pools from which +requests and subrequests can be allocated. If these are not given, netfslib +has default pools that it will use instead. If the filesystem wraps the netfs +structs in its own larger structs, then it will need to use its own pools. +Netfslib will allocate directly from the pools. - [Optional] This is called to initialise the request structure. It is given - the file for reference. +The methods defined in the table are: + * ``init_request()`` * ``free_request()`` + * ``free_subrequest()`` - [Optional] This is called as the request is being deallocated so that the - filesystem can clean up any state it has attached there. + [Optional] A filesystem may implement these to initialise or clean up any + resources that it attaches to the request or subrequest. * ``expand_readahead()`` [Optional] This is called to allow the filesystem to expand the size of a - readahead read request. The filesystem gets to expand the request in both - directions, though it's not permitted to reduce it as the numbers may - represent an allocation already made. If local caching is enabled, it gets - to expand the request first. + readahead request. The filesystem gets to expand the request in both + directions, though it must retain the initial region as that may represent + an allocation already made. If local caching is enabled, it gets to expand + the request first. Expansion is communicated by changing ->start and ->len in the request structure. Note that if any change is made, ->len must be increased by at least as much as ->start is reduced. - * ``clamp_length()`` - - [Optional] This is called to allow the filesystem to reduce the size of a - subrequest. The filesystem can use this, for example, to chop up a request - that has to be split across multiple servers or to put multiple reads in - flight. - - This should return 0 on success and an error code on error. - - * ``issue_read()`` + * ``prepare_read()`` - [Required] The helpers use this to dispatch a subrequest to the server for - reading. In the subrequest, ->start, ->len and ->transferred indicate what - data should be read from the server. + [Optional] This is called to allow the filesystem to limit the size of a + subrequest. It may also limit the number of individual regions in iterator, + such as required by RDMA. This information should be set on stream zero in:: - There is no return value; the netfs_subreq_terminated() function should be - called to indicate whether or not the operation succeeded and how much data - it transferred. The filesystem also should not deal with setting folios - uptodate, unlocking them or dropping their refs - the helpers need to deal - with this as they have to coordinate with copying to the local cache. + rreq->io_streams[0].sreq_max_len + rreq->io_streams[0].sreq_max_segs - Note that the helpers have the folios locked, but not pinned. It is - possible to use the ITER_XARRAY iov iterator to refer to the range of the - inode that is being operated upon without the need to allocate large bvec - tables. + The filesystem can use this, for example, to chop up a request that has to + be split across multiple servers or to put multiple reads in flight. - * ``is_still_valid()`` + Zero should be returned on success and an error code otherwise. - [Optional] This is called to find out if the data just read from the local - cache is still valid. It should return true if it is still valid and false - if not. If it's not still valid, it will be reread from the server. + * ``issue_read()`` - * ``check_write_begin()`` + [Required] Netfslib calls this to dispatch a subrequest to the server for + reading. In the subrequest, ->start, ->len and ->transferred indicate what + data should be read from the server and ->io_iter indicates the buffer to be + used. - [Optional] This is called from the netfs_write_begin() helper once it has - allocated/grabbed the folio to be modified to allow the filesystem to flush - conflicting state before allowing it to be modified. + There is no return value; the ``netfs_read_subreq_terminated()`` function + should be called to indicate that the subrequest completed either way. + ->error, ->transferred and ->flags should be updated before completing. The + termination can be done asynchronously. - It may unlock and discard the folio it was given and set the caller's folio - pointer to NULL. It should return 0 if everything is now fine (``*foliop`` - left set) or the op should be retried (``*foliop`` cleared) and any other - error code to abort the operation. + Note: the filesystem must not deal with setting folios uptodate, unlocking + them or dropping their refs - the library deals with this as it may have to + stitch together the results of multiple subrequests that variously overlap + the set of folios. - * ``done`` + * ``done()`` - [Optional] This is called after the folios in the request have all been + [Optional] This is called after the folios in a read request have all been unlocked (and marked uptodate if applicable). + * ``update_i_size()`` + + [Optional] This is invoked by netfslib at various points during the write + paths to ask the filesystem to update its idea of the file size. If not + given, netfslib will set i_size and i_blocks and update the local cache + cookie. + + * ``post_modify()`` + + [Optional] This is called after netfslib writes to the pagecache or when it + allows an mmap'd page to be marked as writable. + + * ``begin_writeback()`` + + [Optional] Netfslib calls this when processing a writeback request if it + finds a dirty page that isn't simply marked NETFS_FOLIO_COPY_TO_CACHE, + indicating it must be written to the server. This allows the filesystem to + only set up writeback resources when it knows it's going to have to perform + a write. + + * ``prepare_write()`` + [Optional] This is called to allow the filesystem to limit the size of a + subrequest. It may also limit the number of individual regions in iterator, + such as required by RDMA. This information should be set on stream to which + the subrequest belongs:: -Read Helper Procedure ---------------------- - -The read helpers work by the following general procedure: - - * Set up the request. - - * For readahead, allow the local cache and then the network filesystem to - propose expansions to the read request. This is then proposed to the VM. - If the VM cannot fully perform the expansion, a partially expanded read will - be performed, though this may not get written to the cache in its entirety. - - * Loop around slicing chunks off of the request to form subrequests: - - * If a local cache is present, it gets to do the slicing, otherwise the - helpers just try to generate maximal slices. - - * The network filesystem gets to clamp the size of each slice if it is to be - the source. This allows rsize and chunking to be implemented. + rreq->io_streams[subreq->stream_nr].sreq_max_len + rreq->io_streams[subreq->stream_nr].sreq_max_segs - * The helpers issue a read from the cache or a read from the server or just - clears the slice as appropriate. + The filesystem can use this, for example, to chop up a request that has to + be split across multiple servers or to put multiple writes in flight. - * The next slice begins at the end of the last one. + This is not permitted to return an error. Instead, in the event of failure, + ``netfs_prepare_write_failed()`` must be called. - * As slices finish being read, they terminate. + * ``issue_write()`` - * When all the subrequests have terminated, the subrequests are assessed and - any that are short or have failed are reissued: + [Required] This is used to dispatch a subrequest to the server for writing. + In the subrequest, ->start, ->len and ->transferred indicate what data + should be written to the server and ->io_iter indicates the buffer to be + used. - * Failed cache requests are issued against the server instead. + There is no return value; the ``netfs_write_subreq_terminated()`` function + should be called to indicate that the subrequest completed either way. + ->error, ->transferred and ->flags should be updated before completing. The + termination can be done asynchronously. - * Failed server requests just fail. + Note: the filesystem must not deal with removing the dirty or writeback + marks on folios involved in the operation and should not take refs or pins + on them, but should leave retention to netfslib. - * Short reads against either source will be reissued against that source - provided they have transferred some more data: + * ``retry_request()`` - * The cache may need to skip holes that it can't do DIO from. + [Optional] Netfslib calls this at the beginning of a retry cycle. This + allows the filesystem to examine the state of the request, the subrequests + in the indicated stream and of its own data and make adjustments or + renegotiate resources. + + * ``invalidate_cache()`` - * If NETFS_SREQ_CLEAR_TAIL was set, a short read will be cleared to the - end of the slice instead of reissuing. + [Optional] This is called by netfslib to invalidate data stored in the local + cache in the event that writing to the local cache fails, providing updated + coherency data that netfs can't provide. - * Once the data is read, the folios that have been fully read/cleared: +Terminating a subrequest +------------------------ - * Will be marked uptodate. +When a subrequest completes, there are a number of functions that the cache or +subrequest can call to inform netfslib of the status change. One function is +provided to terminate a write subrequest at the preparation stage and acts +synchronously: - * If a cache is present, will be marked with PG_fscache. + * ``void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq);`` - * Unlocked + Indicate that the ->prepare_write() call failed. The ``error`` field should + have been updated. - * Any folios that need writing to the cache will then have DIO writes issued. +Note that ->prepare_read() can return an error as a read can simply be aborted. +Dealing with writeback failure is trickier. - * Synchronous operations will wait for reading to be complete. +The other functions are used for subrequests that got as far as being issued: - * Writes to the cache will proceed asynchronously and the folios will have the - PG_fscache mark removed when that completes. + * ``void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq);`` - * The request structures will be cleaned up when everything has completed. + Tell netfslib that a read subrequest has terminated. The ``error``, + ``flags`` and ``transferred`` fields should have been updated. + * ``void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error);`` -Read Helper Cache API ---------------------- + Tell netfslib that a write subrequest has terminated. Either the amount of + data processed or the negative error code can be passed in. This is + can be used as a kiocb completion function. -When implementing a local cache to be used by the read helpers, two things are -required: some way for the network filesystem to initialise the caching for a -read request and a table of operations for the helpers to call. + * ``void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq);`` -To begin a cache operation on an fscache object, the following function is -called:: + This is provided to optionally update netfslib on the incremental progress + of a read, allowing some folios to be unlocked early and does not actually + terminate the subrequest. The ``transferred`` field should have been + updated. - int fscache_begin_read_operation(struct netfs_io_request *rreq, - struct fscache_cookie *cookie); +Local Cache API +--------------- -passing in the request pointer and the cookie corresponding to the file. This -fills in the cache resources mentioned below. +Netfslib provides a separate API for a local cache to implement, though it +provides some somewhat similar routines to the filesystem request API. -The netfs_io_request object contains a place for the cache to hang its +Firstly, the netfs_io_request object contains a place for the cache to hang its state:: struct netfs_cache_resources { const struct netfs_cache_ops *ops; void *cache_priv; void *cache_priv2; + unsigned int debug_id; + unsigned int inval_counter; }; -This contains an operations table pointer and two private pointers. The -operation table looks like the following:: +This contains an operations table pointer and two private pointers plus the +debug ID of the fscache cookie for tracing purposes and an invalidation counter +that is cranked by calls to ``fscache_invalidate()`` allowing cache subrequests +to be invalidated after completion. + +The cache operation table looks like the following:: struct netfs_cache_ops { void (*end_operation)(struct netfs_cache_resources *cres); - void (*expand_readahead)(struct netfs_cache_resources *cres, loff_t *_start, size_t *_len, loff_t i_size); - enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, - loff_t i_size); - + loff_t i_size); int (*read)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, bool seek_data, netfs_io_terminated_t term_func, void *term_func_priv); - - int (*prepare_write)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size, - bool no_space_allocated_yet); - - int (*write)(struct netfs_cache_resources *cres, - loff_t start_pos, - struct iov_iter *iter, - netfs_io_terminated_t term_func, - void *term_func_priv); - - int (*query_occupancy)(struct netfs_cache_resources *cres, - loff_t start, size_t len, size_t granularity, - loff_t *_data_start, size_t *_data_len); + void (*prepare_write_subreq)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); }; With a termination handler function pointer:: @@ -511,10 +984,16 @@ The methods defined in the table are: * ``expand_readahead()`` - [Optional] Called at the beginning of a netfs_readahead() operation to allow - the cache to expand a request in either direction. This allows the cache to + [Optional] Called at the beginning of a readahead operation to allow the + cache to expand a request in either direction. This allows the cache to size the request appropriately for the cache granularity. + * ``prepare_read()`` + + [Required] Called to configure the next slice of a request. ->start and + ->len in the subrequest indicate where and how big the next slice can be; + the cache gets to reduce the length to match its granularity requirements. + The function is passed pointers to the start and length in its parameters, plus the size of the file for reference, and adjusts the start and length appropriately. It should return one of: @@ -528,12 +1007,6 @@ The methods defined in the table are: downloaded from the server or read from the cache - or whether slicing should be given up at the current point. - * ``prepare_read()`` - - [Required] Called to configure the next slice of a request. ->start and - ->len in the subrequest indicate where and how big the next slice can be; - the cache gets to reduce the length to match its granularity requirements. - * ``read()`` [Required] Called to read from the cache. The start file offset is given @@ -547,44 +1020,33 @@ The methods defined in the table are: indicating whether the termination is definitely happening in the caller's context. - * ``prepare_write()`` + * ``prepare_write_subreq()`` - [Required] Called to prepare a write to the cache to take place. This - involves checking to see whether the cache has sufficient space to honour - the write. ``*_start`` and ``*_len`` indicate the region to be written; the - region can be shrunk or it can be expanded to a page boundary either way as - necessary to align for direct I/O. i_size holds the size of the object and - is provided for reference. no_space_allocated_yet is set to true if the - caller is certain that no data has been written to that region - for example - if it tried to do a read from there already. + [Required] This is called to allow the cache to limit the size of a + subrequest. It may also limit the number of individual regions in iterator, + such as required by DIO/DMA. This information should be set on stream to + which the subrequest belongs:: - * ``write()`` + rreq->io_streams[subreq->stream_nr].sreq_max_len + rreq->io_streams[subreq->stream_nr].sreq_max_segs - [Required] Called to write to the cache. The start file offset is given - along with an iterator to write from, which gives the length also. - - Also provided is a pointer to a termination handler function and private - data to pass to that function. The termination function should be called - with the number of bytes transferred or an error code, plus a flag - indicating whether the termination is definitely happening in the caller's - context. + The filesystem can use this, for example, to chop up a request that has to + be split across multiple servers or to put multiple writes in flight. - * ``query_occupancy()`` + This is not permitted to return an error. In the event of failure, + ``netfs_prepare_write_failed()`` must be called. - [Required] Called to find out where the next piece of data is within a - particular region of the cache. The start and length of the region to be - queried are passed in, along with the granularity to which the answer needs - to be aligned. The function passes back the start and length of the data, - if any, available within that region. Note that there may be a hole at the - front. + * ``issue_write()`` - It returns 0 if some data was found, -ENODATA if there was no usable data - within the region or -ENOBUFS if there is no caching on this file. + [Required] This is used to dispatch a subrequest to the cache for writing. + In the subrequest, ->start, ->len and ->transferred indicate what data + should be written to the cache and ->io_iter indicates the buffer to be + used. -Note that these methods are passed a pointer to the cache resource structure, -not the read request structure as they could be used in other situations where -there isn't a read request structure as well, such as writing dirty data to the -cache. + There is no return value; the ``netfs_write_subreq_terminated()`` function + should be called to indicate that the subrequest completed either way. + ->error, ->transferred and ->flags should be updated before completing. The + termination can be done asynchronously. API Function Reference diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index 767b2927c762..3111ef5592f3 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1203,3 +1203,43 @@ should use d_drop();d_splice_alias() and return the result of the latter. If a positive dentry cannot be returned for some reason, in-kernel clients such as cachefiles, nfsd, smb/server may not perform ideally but will fail-safe. + +--- + +** mandatory** + +lookup_one(), lookup_one_unlocked(), lookup_one_positive_unlocked() now +take a qstr instead of a name and len. These, not the "one_len" +versions, should be used whenever accessing a filesystem from outside +that filesysmtem, through a mount point - which will have a mnt_idmap. + +--- + +** mandatory** + +Functions try_lookup_one_len(), lookup_one_len(), +lookup_one_len_unlocked() and lookup_positive_unlocked() have been +renamed to try_lookup_noperm(), lookup_noperm(), +lookup_noperm_unlocked(), lookup_noperm_positive_unlocked(). They now +take a qstr instead of separate name and length. QSTR() can be used +when strlen() is needed for the length. + +For try_lookup_noperm() a reference to the qstr is passed in case the +hash might subsequently be needed. + +These function no longer do any permission checking - they previously +checked that the caller has 'X' permission on the parent. They must +ONLY be used internally by a filesystem on itself when it knows that +permissions are irrelevant or in a context where permission checks have +already been performed such as after vfs_path_parent_lookup() + +--- + +** mandatory** + +d_hash_and_lookup() is no longer exported or available outside the VFS. +Use try_lookup_noperm() instead. This adds name validation and takes +arguments in the opposite order but is otherwise identical. + +Using try_lookup_noperm() will require linux/namei.h to be included. + diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index ae79c30b6c0c..bf051c7da6b8 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -716,9 +716,8 @@ page lookup by address, and keeping track of pages tagged as Dirty or Writeback. The first can be used independently to the others. The VM can try to -either write dirty pages in order to clean them, or release clean pages -in order to reuse them. To do this it can call the ->writepage method -on dirty pages, and ->release_folio on clean folios with the private +release clean pages in order to reuse them. To do this it can call +->release_folio on clean folios with the private flag set. Clean pages without PagePrivate and with no external references will be released without notice being given to the address_space. @@ -731,8 +730,8 @@ maintains information about the PG_Dirty and PG_Writeback status of each page, so that pages with either of these flags can be found quickly. The Dirty tag is primarily used by mpage_writepages - the default -->writepages method. It uses the tag to find dirty pages to call -->writepage on. If mpage_writepages is not used (i.e. the address +->writepages method. It uses the tag to find dirty pages to +write back. If mpage_writepages is not used (i.e. the address provides its own ->writepages) , the PAGECACHE_TAG_DIRTY tag is almost unused. write_inode_now and sync_inode do use it (through __sync_single_inode) to check if ->writepages has been successful in @@ -756,23 +755,23 @@ pages, however the address_space has finer control of write sizes. The read process essentially only requires 'read_folio'. The write process is more complicated and uses write_begin/write_end or -dirty_folio to write data into the address_space, and writepage and +dirty_folio to write data into the address_space, and writepages to writeback data to storage. Adding and removing pages to/from an address_space is protected by the inode's i_mutex. When data is written to a page, the PG_Dirty flag should be set. It -typically remains set until writepage asks for it to be written. This +typically remains set until writepages asks for it to be written. This should clear PG_Dirty and set PG_Writeback. It can be actually written at any point after PG_Dirty is clear. Once it is known to be safe, PG_Writeback is cleared. Writeback makes use of a writeback_control structure to direct the -operations. This gives the writepage and writepages operations some +operations. This gives the writepages operation some information about the nature of and reason for the writeback request, and the constraints under which it is being done. It is also used to -return information back to the caller about the result of a writepage or +return information back to the caller about the result of a writepages request. @@ -819,7 +818,6 @@ cache in your filesystem. The following members are defined: .. code-block:: c struct address_space_operations { - int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); int (*writepages)(struct address_space *, struct writeback_control *); bool (*dirty_folio)(struct address_space *, struct folio *); @@ -848,25 +846,6 @@ cache in your filesystem. The following members are defined: int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; -``writepage`` - called by the VM to write a dirty page to backing store. This - may happen for data integrity reasons (i.e. 'sync'), or to free - up memory (flush). The difference can be seen in - wbc->sync_mode. The PG_Dirty flag has been cleared and - PageLocked is true. writepage should start writeout, should set - PG_Writeback, and should make sure the page is unlocked, either - synchronously or asynchronously when the write operation - completes. - - If wbc->sync_mode is WB_SYNC_NONE, ->writepage doesn't have to - try too hard if there are problems, and may choose to write out - other pages from the mapping if that is easier (e.g. due to - internal dependencies). If it chooses not to start writeout, it - should return AOP_WRITEPAGE_ACTIVATE so that the VM will not - keep calling ->writepage on that page. - - See the file "Locking" for more details. - ``read_folio`` Called by the page cache to read a folio from the backing store. The 'file' argument supplies authentication information to network @@ -909,7 +888,7 @@ cache in your filesystem. The following members are defined: given and that many pages should be written if possible. If no ->writepages is given, then mpage_writepages is used instead. This will choose pages from the address space that are tagged as - DIRTY and will pass them to ->writepage. + DIRTY and will write them back. ``dirty_folio`` called by the VM to mark a folio as dirty. This is particularly diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst index a7762486c93f..f2dcc39044e6 100644 --- a/Documentation/kbuild/reproducible-builds.rst +++ b/Documentation/kbuild/reproducible-builds.rst @@ -46,6 +46,21 @@ The kernel embeds the building user and host names in `KBUILD_BUILD_USER and KBUILD_BUILD_HOST`_ variables. If you are building from a git commit, you could use its committer address. +Absolute filenames +------------------ + +When the kernel is built out-of-tree, debug information may include +absolute filenames for the source files. This must be overridden by +including the ``-fdebug-prefix-map`` option in the `KCFLAGS`_ variable. + +Depending on the compiler used, the ``__FILE__`` macro may also expand +to an absolute filename in an out-of-tree build. Kbuild automatically +uses the ``-fmacro-prefix-map`` option to prevent this, if it is +supported. + +The Reproducible Builds web site has more information about these +`prefix-map options`_. + Generated files in source packages ---------------------------------- @@ -116,5 +131,7 @@ See ``scripts/setlocalversion`` for details. .. _KBUILD_BUILD_TIMESTAMP: kbuild.html#kbuild-build-timestamp .. _KBUILD_BUILD_USER and KBUILD_BUILD_HOST: kbuild.html#kbuild-build-user-kbuild-build-host +.. _KCFLAGS: kbuild.html#kcflags +.. _prefix-map options: https://reproducible-builds.org/docs/build-path/ .. _Reproducible Builds project: https://reproducible-builds.org/ .. _SOURCE_DATE_EPOCH: https://reproducible-builds.org/docs/source-date-epoch/ diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml index aacccea5dfe4..953aa837958b 100644 --- a/Documentation/netlink/specs/tc.yaml +++ b/Documentation/netlink/specs/tc.yaml @@ -2017,7 +2017,8 @@ attribute-sets: attributes: - name: act - type: nest + type: indexed-array + sub-type: nest nested-attributes: tc-act-attrs - name: police @@ -2250,7 +2251,8 @@ attribute-sets: attributes: - name: act - type: nest + type: indexed-array + sub-type: nest nested-attributes: tc-act-attrs - name: police @@ -2745,7 +2747,7 @@ attribute-sets: type: u16 byte-order: big-endian - - name: key-l2-tpv3-sid + name: key-l2tpv3-sid type: u32 byte-order: big-endian - @@ -3504,7 +3506,7 @@ attribute-sets: name: rate64 type: u64 - - name: prate4 + name: prate64 type: u64 - name: burst diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index b8fef8101176..7aabead90648 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -811,11 +811,9 @@ Documentation/devicetree/bindings/ptp/timestamper.txt for more details. 3.2.4 Other caveats for MAC drivers ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -Stacked PHCs, especially DSA (but not only) - since that doesn't require any -modification to MAC drivers, so it is more difficult to ensure correctness of -all possible code paths - is that they uncover bugs which were impossible to -trigger before the existence of stacked PTP clocks. One example has to do with -this line of code, already presented earlier:: +The use of stacked PHCs may uncover MAC driver bugs which were impossible to +trigger without them. One example has to do with this line of code, already +presented earlier:: skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; diff --git a/MAINTAINERS b/MAINTAINERS index 69511c3b2b76..dd844ac8d910 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2519,6 +2519,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git F: arch/arm/boot/dts/nxp/imx/ F: arch/arm/boot/dts/nxp/mxs/ F: arch/arm64/boot/dts/freescale/ +X: Documentation/devicetree/bindings/media/i2c/ X: arch/arm64/boot/dts/freescale/fsl-* X: arch/arm64/boot/dts/freescale/qoriq-* X: drivers/media/i2c/ @@ -8726,6 +8727,7 @@ M: Chao Yu <chao@kernel.org> R: Yue Hu <zbestahu@gmail.com> R: Jeffle Xu <jefflexu@linux.alibaba.com> R: Sandeep Dhavale <dhavale@google.com> +R: Hongbo Li <lihongbo22@huawei.com> L: linux-erofs@lists.ozlabs.org S: Maintained W: https://erofs.docs.kernel.org @@ -10145,6 +10147,13 @@ F: drivers/gpio/gpio-regmap.c F: include/linux/gpio/regmap.h K: (devm_)?gpio_regmap_(un)?register +GPIO SLOPPY LOGIC ANALYZER +M: Wolfram Sang <wsa+renesas@sang-engineering.com> +S: Supported +F: Documentation/dev-tools/gpio-sloppy-logic-analyzer.rst +F: drivers/gpio/gpio-sloppy-logic-analyzer.c +F: tools/gpio/gpio-sloppy-logic-analyzer.sh + GPIO SUBSYSTEM M: Linus Walleij <linus.walleij@linaro.org> M: Bartosz Golaszewski <brgl@bgdev.pl> @@ -11097,6 +11106,14 @@ L: linuxppc-dev@lists.ozlabs.org S: Odd Fixes F: drivers/tty/hvc/ +HUNG TASK DETECTOR +M: Andrew Morton <akpm@linux-foundation.org> +R: Lance Yang <lance.yang@linux.dev> +L: linux-kernel@vger.kernel.org +S: Maintained +F: include/linux/hung_task.h +F: kernel/hung_task.c + I2C ACPI SUPPORT M: Mika Westerberg <westeri@kernel.org> L: linux-i2c@vger.kernel.org @@ -11235,7 +11252,6 @@ S: Maintained F: drivers/i2c/busses/i2c-cht-wc.c I2C/SMBUS ISMT DRIVER -M: Seth Heasley <seth.heasley@intel.com> M: Neil Horman <nhorman@tuxdriver.com> L: linux-i2c@vger.kernel.org F: Documentation/i2c/busses/i2c-ismt.rst @@ -15071,7 +15087,7 @@ F: Documentation/devicetree/bindings/media/mediatek-jpeg-*.yaml F: drivers/media/platform/mediatek/jpeg/ MEDIATEK KEYPAD DRIVER -M: Mattijs Korpershoek <mkorpershoek@baylibre.com> +M: Mattijs Korpershoek <mkorpershoek@kernel.org> S: Supported F: Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml F: drivers/input/keyboard/mt6779-keypad.c @@ -15494,24 +15510,45 @@ F: Documentation/mm/ F: include/linux/gfp.h F: include/linux/gfp_types.h F: include/linux/memfd.h -F: include/linux/memory.h F: include/linux/memory_hotplug.h F: include/linux/memory-tiers.h F: include/linux/mempolicy.h F: include/linux/mempool.h F: include/linux/memremap.h -F: include/linux/mm.h -F: include/linux/mm_*.h F: include/linux/mmzone.h F: include/linux/mmu_notifier.h F: include/linux/pagewalk.h -F: include/linux/rmap.h F: include/trace/events/ksm.h F: mm/ F: tools/mm/ F: tools/testing/selftests/mm/ N: include/linux/page[-_]* +MEMORY MANAGEMENT - CORE +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Vlastimil Babka <vbabka@suse.cz> +R: Mike Rapoport <rppt@kernel.org> +R: Suren Baghdasaryan <surenb@google.com> +R: Michal Hocko <mhocko@suse.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: include/linux/memory.h +F: include/linux/mm.h +F: include/linux/mm_*.h +F: include/linux/mmdebug.h +F: include/linux/pagewalk.h +F: mm/Kconfig +F: mm/debug.c +F: mm/init-mm.c +F: mm/memory.c +F: mm/pagewalk.c +F: mm/util.c + MEMORY MANAGEMENT - EXECMEM M: Andrew Morton <akpm@linux-foundation.org> M: Mike Rapoport <rppt@kernel.org> @@ -15520,6 +15557,53 @@ S: Maintained F: include/linux/execmem.h F: mm/execmem.c +MEMORY MANAGEMENT - GUP (GET USER PAGES) +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Jason Gunthorpe <jgg@nvidia.com> +R: John Hubbard <jhubbard@nvidia.com> +R: Peter Xu <peterx@redhat.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: mm/gup.c + +MEMORY MANAGEMENT - KSM (Kernel Samepage Merging) +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Xu Xin <xu.xin16@zte.com.cn> +R: Chengming Zhou <chengming.zhou@linux.dev> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: Documentation/admin-guide/mm/ksm.rst +F: Documentation/mm/ksm.rst +F: include/linux/ksm.h +F: include/trace/events/ksm.h +F: mm/ksm.c + +MEMORY MANAGEMENT - MEMORY POLICY AND MIGRATION +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Zi Yan <ziy@nvidia.com> +R: Matthew Brost <matthew.brost@intel.com> +R: Joshua Hahn <joshua.hahnjy@gmail.com> +R: Rakie Kim <rakie.kim@sk.com> +R: Byungchul Park <byungchul@sk.com> +R: Gregory Price <gourry@gourry.net> +R: Ying Huang <ying.huang@linux.alibaba.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: include/linux/mempolicy.h +F: include/linux/migrate.h +F: mm/mempolicy.c +F: mm/migrate.c +F: mm/migrate_device.c + MEMORY MANAGEMENT - NUMA MEMBLOCKS AND NUMA EMULATION M: Andrew Morton <akpm@linux-foundation.org> M: Mike Rapoport <rppt@kernel.org> @@ -15532,7 +15616,7 @@ F: mm/numa_memblks.c MEMORY MANAGEMENT - PAGE ALLOCATOR M: Andrew Morton <akpm@linux-foundation.org> -R: Vlastimil Babka <vbabka@suse.cz> +M: Vlastimil Babka <vbabka@suse.cz> R: Suren Baghdasaryan <surenb@google.com> R: Michal Hocko <mhocko@suse.com> R: Brendan Jackman <jackmanb@google.com> @@ -15540,10 +15624,38 @@ R: Johannes Weiner <hannes@cmpxchg.org> R: Zi Yan <ziy@nvidia.com> L: linux-mm@kvack.org S: Maintained +F: include/linux/compaction.h +F: include/linux/gfp.h +F: include/linux/page-isolation.h F: mm/compaction.c F: mm/page_alloc.c -F: include/linux/gfp.h -F: include/linux/compaction.h +F: mm/page_isolation.c + +MEMORY MANAGEMENT - RECLAIM +M: Andrew Morton <akpm@linux-foundation.org> +M: Johannes Weiner <hannes@cmpxchg.org> +R: David Hildenbrand <david@redhat.com> +R: Michal Hocko <mhocko@kernel.org> +R: Qi Zheng <zhengqi.arch@bytedance.com> +R: Shakeel Butt <shakeel.butt@linux.dev> +R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +L: linux-mm@kvack.org +S: Maintained +F: mm/pt_reclaim.c +F: mm/vmscan.c + +MEMORY MANAGEMENT - RMAP (REVERSE MAPPING) +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +R: Rik van Riel <riel@surriel.com> +R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Vlastimil Babka <vbabka@suse.cz> +R: Harry Yoo <harry.yoo@oracle.com> +L: linux-mm@kvack.org +S: Maintained +F: include/linux/rmap.h +F: mm/rmap.c MEMORY MANAGEMENT - SECRETMEM M: Andrew Morton <akpm@linux-foundation.org> @@ -15553,6 +15665,30 @@ S: Maintained F: include/linux/secretmem.h F: mm/secretmem.c +MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Zi Yan <ziy@nvidia.com> +R: Baolin Wang <baolin.wang@linux.alibaba.com> +R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Nico Pache <npache@redhat.com> +R: Ryan Roberts <ryan.roberts@arm.com> +R: Dev Jain <dev.jain@arm.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: Documentation/admin-guide/mm/transhuge.rst +F: include/linux/huge_mm.h +F: include/linux/khugepaged.h +F: include/trace/events/huge_memory.h +F: mm/huge_memory.c +F: mm/khugepaged.c +F: tools/testing/selftests/mm/khugepaged.c +F: tools/testing/selftests/mm/split_huge_page_test.c +F: tools/testing/selftests/mm/transhuge-stress.c + MEMORY MANAGEMENT - USERFAULTFD M: Andrew Morton <akpm@linux-foundation.org> R: Peter Xu <peterx@redhat.com> @@ -18373,7 +18509,7 @@ F: include/uapi/linux/ppdev.h PARAVIRT_OPS INTERFACE M: Juergen Gross <jgross@suse.com> R: Ajay Kaher <ajay.kaher@broadcom.com> -R: Alexey Makhalov <alexey.amakhalov@broadcom.com> +R: Alexey Makhalov <alexey.makhalov@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: virtualization@lists.linux.dev L: x86@kernel.org @@ -20535,8 +20671,8 @@ F: Documentation/devicetree/bindings/i2c/renesas,iic-emev2.yaml F: drivers/i2c/busses/i2c-emev2.c RENESAS ETHERNET AVB DRIVER -M: Paul Barker <paul.barker.ct@bp.renesas.com> M: Niklas Söderlund <niklas.soderlund@ragnatech.se> +R: Paul Barker <paul@pbarker.dev> L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org S: Maintained @@ -22857,7 +22993,6 @@ F: drivers/accessibility/speakup/ SPEAR PLATFORM/CLOCK/PINCTRL SUPPORT M: Viresh Kumar <vireshk@kernel.org> -M: Shiraz Hashim <shiraz.linux.kernel@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: soc@lists.linux.dev S: Maintained @@ -25835,7 +25970,7 @@ F: tools/testing/vsock/ VMALLOC M: Andrew Morton <akpm@linux-foundation.org> -R: Uladzislau Rezki <urezki@gmail.com> +M: Uladzislau Rezki <urezki@gmail.com> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org @@ -25859,7 +25994,7 @@ F: drivers/misc/vmw_balloon.c VMWARE HYPERVISOR INTERFACE M: Ajay Kaher <ajay.kaher@broadcom.com> -M: Alexey Makhalov <alexey.amakhalov@broadcom.com> +M: Alexey Makhalov <alexey.makhalov@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: virtualization@lists.linux.dev L: x86@kernel.org @@ -25887,7 +26022,7 @@ F: drivers/scsi/vmw_pvscsi.h VMWARE VIRTUAL PTP CLOCK DRIVER M: Nick Shi <nick.shi@broadcom.com> R: Ajay Kaher <ajay.kaher@broadcom.com> -R: Alexey Makhalov <alexey.amakhalov@broadcom.com> +R: Alexey Makhalov <alexey.makhalov@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org S: Supported @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -1068,8 +1068,7 @@ KBUILD_CFLAGS += -fno-builtin-wcslen # change __FILE__ to the relative path to the source directory ifdef building_out_of_srctree -KBUILD_CPPFLAGS += $(call cc-option,-ffile-prefix-map=$(srcroot)/=) -KBUILD_RUSTFLAGS += --remap-path-prefix=$(srcroot)/= +KBUILD_CPPFLAGS += $(call cc-option,-fmacro-prefix-map=$(srcroot)/=) endif # include additional Makefiles when needed diff --git a/arch/arm/boot/dts/amlogic/meson8.dtsi b/arch/arm/boot/dts/amlogic/meson8.dtsi index 847f7b1f1e96..f785e0de0847 100644 --- a/arch/arm/boot/dts/amlogic/meson8.dtsi +++ b/arch/arm/boot/dts/amlogic/meson8.dtsi @@ -451,7 +451,7 @@ pwm_ef: pwm@86c0 { compatible = "amlogic,meson8-pwm-v2"; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "Video PLL" */ + <0>, /* unknown/untested, the datasheet calls it "Video PLL" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; reg = <0x86c0 0x10>; @@ -705,7 +705,7 @@ &pwm_ab { compatible = "amlogic,meson8-pwm-v2"; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "Video PLL" */ + <0>, /* unknown/untested, the datasheet calls it "Video PLL" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; @@ -713,7 +713,7 @@ &pwm_cd { compatible = "amlogic,meson8-pwm-v2"; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "Video PLL" */ + <0>, /* unknown/untested, the datasheet calls it "Video PLL" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; diff --git a/arch/arm/boot/dts/amlogic/meson8b.dtsi b/arch/arm/boot/dts/amlogic/meson8b.dtsi index 0876611ce26a..fdb0abe23a0c 100644 --- a/arch/arm/boot/dts/amlogic/meson8b.dtsi +++ b/arch/arm/boot/dts/amlogic/meson8b.dtsi @@ -406,7 +406,7 @@ compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2"; reg = <0x86c0 0x10>; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "Video PLL" */ + <0>, /* unknown/untested, the datasheet calls it "Video PLL" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; #pwm-cells = <3>; @@ -680,7 +680,7 @@ &pwm_ab { compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2"; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "Video PLL" */ + <0>, /* unknown/untested, the datasheet calls it "Video PLL" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; @@ -688,7 +688,7 @@ &pwm_cd { compatible = "amlogic,meson8b-pwm-v2", "amlogic,meson8-pwm-v2"; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "Video PLL" */ + <0>, /* unknown/untested, the datasheet calls it "Video PLL" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi index f2386dcb9ff2..dda4fa91b2f2 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ul-imx6ull-opos6ul.dtsi @@ -40,6 +40,9 @@ reg = <1>; interrupt-parent = <&gpio4>; interrupts = <16 IRQ_TYPE_LEVEL_LOW>; + micrel,led-mode = <1>; + clocks = <&clks IMX6UL_CLK_ENET_REF>; + clock-names = "rmii-ref"; status = "okay"; }; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 13a0e63afeaf..2c64d834a2c4 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -152,28 +152,12 @@ vcc-pg-supply = <®_aldo1>; }; -&r_ir { - linux,rc-map-name = "rc-beelink-gs1"; - status = "okay"; -}; - -&r_pio { - /* - * FIXME: We can't add that supply for now since it would - * create a circular dependency between pinctrl, the regulator - * and the RSB Bus. - * - * vcc-pl-supply = <®_aldo1>; - */ - vcc-pm-supply = <®_aldo1>; -}; - -&r_rsb { +&r_i2c { status = "okay"; - axp805: pmic@745 { + axp805: pmic@36 { compatible = "x-powers,axp805", "x-powers,axp806"; - reg = <0x745>; + reg = <0x36>; interrupt-parent = <&r_intc>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; @@ -291,6 +275,22 @@ }; }; +&r_ir { + linux,rc-map-name = "rc-beelink-gs1"; + status = "okay"; +}; + +&r_pio { + /* + * PL0 and PL1 are used for PMIC I2C + * don't enable the pl-supply else + * it will fail at boot + * + * vcc-pl-supply = <®_aldo1>; + */ + vcc-pm-supply = <®_aldo1>; +}; + &spdif { pinctrl-names = "default"; pinctrl-0 = <&spdif_tx_pin>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts index ab87c3447cd7..f005072c68a1 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi-3.dts @@ -176,16 +176,12 @@ vcc-pg-supply = <®_vcc_wifi_io>; }; -&r_ir { - status = "okay"; -}; - -&r_rsb { +&r_i2c { status = "okay"; - axp805: pmic@745 { + axp805: pmic@36 { compatible = "x-powers,axp805", "x-powers,axp806"; - reg = <0x745>; + reg = <0x36>; interrupt-parent = <&r_intc>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; @@ -296,6 +292,10 @@ }; }; +&r_ir { + status = "okay"; +}; + &rtc { clocks = <&ext_osc32k>; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi index d05dc5d6e6b9..e34dbb992021 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-orangepi.dtsi @@ -113,20 +113,12 @@ vcc-pg-supply = <®_aldo1>; }; -&r_ir { - status = "okay"; -}; - -&r_pio { - vcc-pm-supply = <®_bldo3>; -}; - -&r_rsb { +&r_i2c { status = "okay"; - axp805: pmic@745 { + axp805: pmic@36 { compatible = "x-powers,axp805", "x-powers,axp806"; - reg = <0x745>; + reg = <0x36>; interrupt-parent = <&r_intc>; interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; @@ -241,6 +233,14 @@ }; }; +&r_ir { + status = "okay"; +}; + +&r_pio { + vcc-pm-supply = <®_bldo3>; +}; + &rtc { clocks = <&ext_osc32k>; }; diff --git a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi index da9de4986660..5a72f0b64247 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v2.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v2.dtsi @@ -151,7 +151,7 @@ al,msi-num-spis = <160>; }; - io-fabric@fc000000 { + io-bus@fc000000 { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi index 8b6156b5af65..dea60d136c2e 100644 --- a/arch/arm64/boot/dts/amazon/alpine-v3.dtsi +++ b/arch/arm64/boot/dts/amazon/alpine-v3.dtsi @@ -361,7 +361,7 @@ interrupt-parent = <&gic>; }; - io-fabric@fc000000 { + io-bus@fc000000 { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index ab2b3f15ef19..69834b49673d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -2313,7 +2313,7 @@ "amlogic,meson8-pwm-v2"; reg = <0x0 0x19000 0x0 0x20>; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; #pwm-cells = <3>; @@ -2325,7 +2325,7 @@ "amlogic,meson8-pwm-v2"; reg = <0x0 0x1a000 0x0 0x20>; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; #pwm-cells = <3>; @@ -2337,7 +2337,7 @@ "amlogic,meson8-pwm-v2"; reg = <0x0 0x1b000 0x0 0x20>; clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; #pwm-cells = <3>; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi index de35fa2d7a6d..8e3e3354ed67 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-dreambox.dtsi @@ -116,6 +116,10 @@ status = "okay"; }; +&clkc_audio { + status = "okay"; +}; + &frddr_a { status = "okay"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 8ebce7114a60..6c134592c7bb 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -741,7 +741,7 @@ &pwm_ab { clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; @@ -752,14 +752,14 @@ &pwm_cd { clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; &pwm_ef { clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 2dc2fdaecf9f..19b8a39de6a0 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -811,7 +811,7 @@ &pwm_ab { clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; @@ -822,14 +822,14 @@ &pwm_cd { clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; &pwm_ef { clocks = <&xtal>, - <>, /* unknown/untested, the datasheet calls it "vid_pll" */ + <0>, /* unknown/untested, the datasheet calls it "vid_pll" */ <&clkc CLKID_FCLK_DIV4>, <&clkc CLKID_FCLK_DIV3>; }; diff --git a/arch/arm64/boot/dts/apple/t8103-j293.dts b/arch/arm64/boot/dts/apple/t8103-j293.dts index 2dfe7b895b2b..e2d9439397f7 100644 --- a/arch/arm64/boot/dts/apple/t8103-j293.dts +++ b/arch/arm64/boot/dts/apple/t8103-j293.dts @@ -77,6 +77,16 @@ }; }; +/* + * The driver depends on boot loader initialized state which resets when this + * power-domain is powered off. This happens on suspend or when the driver is + * missing during boot. Mark the domain as always on until the driver can + * handle this. + */ +&ps_dispdfr_be { + apple,always-on; +}; + &display_dfr { status = "okay"; }; diff --git a/arch/arm64/boot/dts/apple/t8112-j493.dts b/arch/arm64/boot/dts/apple/t8112-j493.dts index 3d73f9ee2f46..be86d34c6696 100644 --- a/arch/arm64/boot/dts/apple/t8112-j493.dts +++ b/arch/arm64/boot/dts/apple/t8112-j493.dts @@ -40,6 +40,16 @@ }; }; +/* + * The driver depends on boot loader initialized state which resets when this + * power-domain is powered off. This happens on suspend or when the driver is + * missing during boot. Mark the domain as always on until the driver can + * handle this. + */ +&ps_dispdfr_be { + apple,always-on; +}; + &display_dfr { status = "okay"; }; diff --git a/arch/arm64/boot/dts/arm/morello.dtsi b/arch/arm64/boot/dts/arm/morello.dtsi index 0bab0b3ea969..5bc1c725dc86 100644 --- a/arch/arm64/boot/dts/arm/morello.dtsi +++ b/arch/arm64/boot/dts/arm/morello.dtsi @@ -44,7 +44,7 @@ next-level-cache = <&l2_0>; clocks = <&scmi_dvfs 0>; - l2_0: l2-cache-0 { + l2_0: l2-cache { compatible = "cache"; cache-level = <2>; /* 8 ways set associative */ @@ -53,13 +53,6 @@ cache-sets = <2048>; cache-unified; next-level-cache = <&l3_0>; - - l3_0: l3-cache { - compatible = "cache"; - cache-level = <3>; - cache-size = <0x100000>; - cache-unified; - }; }; }; @@ -78,7 +71,7 @@ next-level-cache = <&l2_1>; clocks = <&scmi_dvfs 0>; - l2_1: l2-cache-1 { + l2_1: l2-cache { compatible = "cache"; cache-level = <2>; /* 8 ways set associative */ @@ -105,7 +98,7 @@ next-level-cache = <&l2_2>; clocks = <&scmi_dvfs 1>; - l2_2: l2-cache-2 { + l2_2: l2-cache { compatible = "cache"; cache-level = <2>; /* 8 ways set associative */ @@ -132,7 +125,7 @@ next-level-cache = <&l2_3>; clocks = <&scmi_dvfs 1>; - l2_3: l2-cache-3 { + l2_3: l2-cache { compatible = "cache"; cache-level = <2>; /* 8 ways set associative */ @@ -143,6 +136,13 @@ next-level-cache = <&l3_0>; }; }; + + l3_0: l3-cache { + compatible = "cache"; + cache-level = <3>; + cache-size = <0x100000>; + cache-unified; + }; }; firmware { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 7251ad3a0017..b46566f3ce20 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -144,6 +144,19 @@ startup-delay-us = <20000>; }; + reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc { + compatible = "regulator-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usdhc2_vsel>; + gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>; + regulator-max-microvolt = <3300000>; + regulator-min-microvolt = <1800000>; + states = <1800000 0x1>, + <3300000 0x0>; + regulator-name = "PMIC_USDHC_VSELECT"; + vin-supply = <®_nvcc_sd>; + }; + reserved-memory { #address-cells = <2>; #size-cells = <2>; @@ -269,7 +282,7 @@ "SODIMM_19", "", "", - "", + "PMIC_USDHC_VSELECT", "", "", "", @@ -785,6 +798,7 @@ pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_cd>; pinctrl-3 = <&pinctrl_usdhc2_sleep>, <&pinctrl_usdhc2_cd_sleep>; vmmc-supply = <®_usdhc2_vmmc>; + vqmmc-supply = <®_usdhc2_vqmmc>; }; &wdog1 { @@ -1206,13 +1220,17 @@ <MX8MM_IOMUXC_NAND_CLE_GPIO3_IO5 0x6>; /* SODIMM 76 */ }; + pinctrl_usdhc2_vsel: usdhc2vselgrp { + fsl,pins = + <MX8MM_IOMUXC_GPIO1_IO04_GPIO1_IO4 0x10>; /* PMIC_USDHC_VSELECT */ + }; + /* * Note: Due to ERR050080 we use discrete external on-module resistors pulling-up to the * on-module +V3.3_1.8_SD (LDO5) rail and explicitly disable the internal pull-ups here. */ pinctrl_usdhc2: usdhc2grp { fsl,pins = - <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>, <MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x90>, /* SODIMM 78 */ <MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x90>, /* SODIMM 74 */ <MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x90>, /* SODIMM 80 */ @@ -1223,7 +1241,6 @@ pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { fsl,pins = - <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>, <MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x94>, <MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x94>, <MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x94>, @@ -1234,7 +1251,6 @@ pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { fsl,pins = - <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x10>, <MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x96>, <MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x96>, <MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x96>, @@ -1246,7 +1262,6 @@ /* Avoid backfeeding with removed card power */ pinctrl_usdhc2_sleep: usdhc2slpgrp { fsl,pins = - <MX8MM_IOMUXC_GPIO1_IO04_USDHC2_VSELECT 0x0>, <MX8MM_IOMUXC_SD2_CLK_USDHC2_CLK 0x0>, <MX8MM_IOMUXC_SD2_CMD_USDHC2_CMD 0x0>, <MX8MM_IOMUXC_SD2_DATA0_USDHC2_DATA0 0x0>, diff --git a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi index a1b75c9068b2..2ce1860b244d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-nominal.dtsi @@ -24,6 +24,20 @@ fsl,operating-mode = "nominal"; }; +&gpu2d { + assigned-clocks = <&clk IMX8MP_CLK_GPU2D_CORE>; + assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>; + assigned-clock-rates = <800000000>; +}; + +&gpu3d { + assigned-clocks = <&clk IMX8MP_CLK_GPU3D_CORE>, + <&clk IMX8MP_CLK_GPU3D_SHADER_CORE>; + assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_SYS_PLL1_800M>; + assigned-clock-rates = <800000000>, <800000000>; +}; + &pgc_hdmimix { assigned-clocks = <&clk IMX8MP_CLK_HDMI_AXI>, <&clk IMX8MP_CLK_HDMI_APB>; @@ -46,6 +60,18 @@ assigned-clock-rates = <600000000>, <300000000>; }; +&pgc_mlmix { + assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>, + <&clk IMX8MP_CLK_ML_AXI>, + <&clk IMX8MP_CLK_ML_AHB>; + assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_SYS_PLL1_800M>; + assigned-clock-rates = <800000000>, + <800000000>, + <300000000>; +}; + &media_blk_ctrl { assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>, <&clk IMX8MP_CLK_MEDIA_APB>, @@ -62,3 +88,5 @@ <0>, <0>, <400000000>, <1039500000>; }; + +/delete-node/ &{noc_opp_table/opp-1000000000}; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi index b2ac2583a592..b59da91fdd04 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-var-som.dtsi @@ -35,7 +35,6 @@ <0x1 0x00000000 0 0xc0000000>; }; - reg_usdhc2_vmmc: regulator-usdhc2-vmmc { compatible = "regulator-fixed"; regulator-name = "VSD_3V3"; @@ -46,6 +45,16 @@ startup-delay-us = <100>; off-on-delay-us = <12000>; }; + + reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc { + compatible = "regulator-gpio"; + regulator-name = "VSD_VSEL"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + gpios = <&gpio2 12 GPIO_ACTIVE_HIGH>; + states = <3300000 0x0 1800000 0x1>; + vin-supply = <&ldo5>; + }; }; &A53_0 { @@ -205,6 +214,7 @@ pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>; cd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; vmmc-supply = <®_usdhc2_vmmc>; + vqmmc-supply = <®_usdhc2_vqmmc>; bus-width = <4>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index ce6793b2d57e..7c1c87eab54c 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1645,6 +1645,12 @@ opp-hz = /bits/ 64 <200000000>; }; + /* Nominal drive mode maximum */ + opp-800000000 { + opp-hz = /bits/ 64 <800000000>; + }; + + /* Overdrive mode maximum */ opp-1000000000 { opp-hz = /bits/ 64 <1000000000>; }; diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index 9bb26b466a06..59f057ba6fa7 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1626,7 +1626,7 @@ reg = <0 0x4c300000 0 0x10000>, <0 0x60100000 0 0xfe00000>, <0 0x4c360000 0 0x10000>, - <0 0x4c340000 0 0x2000>; + <0 0x4c340000 0 0x4000>; reg-names = "dbi", "config", "atu", "app"; ranges = <0x81000000 0x0 0x00000000 0x0 0x6ff00000 0 0x00100000>, <0x82000000 0x0 0x10000000 0x9 0x10000000 0 0x10000000>; @@ -1673,7 +1673,7 @@ reg = <0 0x4c300000 0 0x10000>, <0 0x4c360000 0 0x1000>, <0 0x4c320000 0 0x1000>, - <0 0x4c340000 0 0x2000>, + <0 0x4c340000 0 0x4000>, <0 0x4c370000 0 0x10000>, <0x9 0 1 0>; reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space"; @@ -1700,7 +1700,7 @@ reg = <0 0x4c380000 0 0x10000>, <8 0x80100000 0 0xfe00000>, <0 0x4c3e0000 0 0x10000>, - <0 0x4c3c0000 0 0x2000>; + <0 0x4c3c0000 0 0x4000>; reg-names = "dbi", "config", "atu", "app"; ranges = <0x81000000 0 0x00000000 0x8 0x8ff00000 0 0x00100000>, <0x82000000 0 0x10000000 0xa 0x10000000 0 0x10000000>; @@ -1749,7 +1749,7 @@ reg = <0 0x4c380000 0 0x10000>, <0 0x4c3e0000 0 0x1000>, <0 0x4c3a0000 0 0x1000>, - <0 0x4c3c0000 0 0x2000>, + <0 0x4c3c0000 0 0x4000>, <0 0x4c3f0000 0 0x10000>, <0xa 0 1 0>; reg-names = "dbi", "atu", "dbi2", "app", "dma", "addr_space"; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi index 3a9b6907185d..242820845707 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-3720-uDPU.dtsi @@ -26,6 +26,8 @@ leds { compatible = "gpio-leds"; + pinctrl-names = "default"; + pinctrl-0 = <&spi_quad_pins>; led-power1 { label = "udpu:green:power"; @@ -82,8 +84,6 @@ &spi0 { status = "okay"; - pinctrl-names = "default"; - pinctrl-0 = <&spi_quad_pins>; flash@0 { compatible = "jedec,spi-nor"; @@ -108,6 +108,10 @@ }; }; +&spi_quad_pins { + function = "gpio"; +}; + &pinctrl_nb { i2c2_recovery_pins: i2c2-recovery-pins { groups = "i2c2"; diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi index 1edfd643b25a..a334ef0629d1 100644 --- a/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-engicam-common.dtsi @@ -31,7 +31,7 @@ }; vcc3v3_btreg: vcc3v3-btreg { - compatible = "regulator-gpio"; + compatible = "regulator-fixed"; enable-active-high; pinctrl-names = "default"; pinctrl-0 = <&bt_enable_h>; @@ -39,7 +39,6 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; regulator-always-on; - states = <3300000 0x0>; }; vcc3v3_rf_aux_mod: regulator-vcc3v3-rf-aux-mod { diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi index 80db778c9684..b60e68faa83a 100644 --- a/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-engicam-ctouch2.dtsi @@ -26,5 +26,5 @@ }; &vcc3v3_btreg { - enable-gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>; + gpios = <&gpio1 RK_PC3 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts index 165d09ccb942..5886b802c520 100644 --- a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts +++ b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core-edimm2.2.dts @@ -39,5 +39,5 @@ }; &vcc3v3_btreg { - enable-gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>; + gpios = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi index 541dca12bf1a..046dbe329017 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi @@ -43,7 +43,7 @@ sdio_pwrseq: sdio-pwrseq { compatible = "mmc-pwrseq-simple"; clocks = <&rk808 1>; - clock-names = "lpo"; + clock-names = "ext_clock"; pinctrl-names = "default"; pinctrl-0 = <&wifi_enable_h>; reset-gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi index a48351471764..e7ba477e75f9 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi @@ -775,7 +775,7 @@ rockchip,default-sample-phase = <90>; status = "okay"; - sdio-wifi@1 { + wifi@1 { compatible = "brcm,bcm4329-fmac"; reg = <1>; interrupt-parent = <&gpio2>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts index 7bd32d230ad2..b80d628c426b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-qnap-ts433.dts @@ -619,6 +619,8 @@ bus-width = <8>; max-frequency = <200000000>; non-removable; + pinctrl-names = "default"; + pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd &emmc_datastrobe>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts index 828bde7fab68..314067ba6f3c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts @@ -610,7 +610,7 @@ reg = <0x51>; clock-output-names = "hym8563"; interrupt-parent = <&gpio0>; - interrupts = <RK_PB0 IRQ_TYPE_LEVEL_LOW>; + interrupts = <RK_PA0 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&hym8563_int>; wakeup-source; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi index 1af0a30866f6..af431fdcbea7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-friendlyelec-cm3588.dtsi @@ -222,6 +222,10 @@ compatible = "realtek,rt5616"; reg = <0x1b>; #sound-dai-cells = <0>; + assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; + assigned-clock-rates = <12288000>; + clocks = <&cru I2S0_8CH_MCLKOUT>; + clock-names = "mclk"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi index 711ac4f2c7cb..60ad272982ad 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi @@ -214,6 +214,8 @@ }; &package_thermal { + polling-delay = <1000>; + trips { package_active1: trip-active1 { temperature = <45000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi index bce72bac4503..3045cb3bd68c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi @@ -11,20 +11,15 @@ compatible = "operating-points-v2"; opp-shared; - opp-1416000000 { - opp-hz = /bits/ 64 <1416000000>; + opp-1200000000 { + opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <750000 750000 950000>; clock-latency-ns = <40000>; opp-suspend; }; - opp-1608000000 { - opp-hz = /bits/ 64 <1608000000>; - opp-microvolt = <887500 887500 950000>; - clock-latency-ns = <40000>; - }; - opp-1704000000 { - opp-hz = /bits/ 64 <1704000000>; - opp-microvolt = <937500 937500 950000>; + opp-1296000000 { + opp-hz = /bits/ 64 <1296000000>; + opp-microvolt = <775000 775000 950000>; clock-latency-ns = <40000>; }; }; @@ -33,9 +28,14 @@ compatible = "operating-points-v2"; opp-shared; + opp-1200000000{ + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt = <750000 750000 950000>; + clock-latency-ns = <40000>; + }; opp-1416000000 { opp-hz = /bits/ 64 <1416000000>; - opp-microvolt = <750000 750000 950000>; + opp-microvolt = <762500 762500 950000>; clock-latency-ns = <40000>; }; opp-1608000000 { @@ -43,25 +43,20 @@ opp-microvolt = <787500 787500 950000>; clock-latency-ns = <40000>; }; - opp-1800000000 { - opp-hz = /bits/ 64 <1800000000>; - opp-microvolt = <875000 875000 950000>; - clock-latency-ns = <40000>; - }; - opp-2016000000 { - opp-hz = /bits/ 64 <2016000000>; - opp-microvolt = <950000 950000 950000>; - clock-latency-ns = <40000>; - }; }; cluster2_opp_table: opp-table-cluster2 { compatible = "operating-points-v2"; opp-shared; + opp-1200000000{ + opp-hz = /bits/ 64 <1200000000>; + opp-microvolt = <750000 750000 950000>; + clock-latency-ns = <40000>; + }; opp-1416000000 { opp-hz = /bits/ 64 <1416000000>; - opp-microvolt = <750000 750000 950000>; + opp-microvolt = <762500 762500 950000>; clock-latency-ns = <40000>; }; opp-1608000000 { @@ -69,16 +64,6 @@ opp-microvolt = <787500 787500 950000>; clock-latency-ns = <40000>; }; - opp-1800000000 { - opp-hz = /bits/ 64 <1800000000>; - opp-microvolt = <875000 875000 950000>; - clock-latency-ns = <40000>; - }; - opp-2016000000 { - opp-hz = /bits/ 64 <2016000000>; - opp-microvolt = <950000 950000 950000>; - clock-latency-ns = <40000>; - }; }; gpu_opp_table: opp-table { @@ -104,10 +89,6 @@ opp-hz = /bits/ 64 <700000000>; opp-microvolt = <750000 750000 850000>; }; - opp-850000000 { - opp-hz = /bits/ 64 <800000000>; - opp-microvolt = <787500 787500 850000>; - }; }; }; diff --git a/arch/arm64/boot/dts/st/stm32mp211.dtsi b/arch/arm64/boot/dts/st/stm32mp211.dtsi index 6dd1377f3e1d..bf888d60cd4f 100644 --- a/arch/arm64/boot/dts/st/stm32mp211.dtsi +++ b/arch/arm64/boot/dts/st/stm32mp211.dtsi @@ -116,11 +116,11 @@ }; intc: interrupt-controller@4ac10000 { - compatible = "arm,cortex-a7-gic"; + compatible = "arm,gic-400"; reg = <0x4ac10000 0x0 0x1000>, - <0x4ac20000 0x0 0x2000>, - <0x4ac40000 0x0 0x2000>, - <0x4ac60000 0x0 0x2000>; + <0x4ac20000 0x0 0x20000>, + <0x4ac40000 0x0 0x20000>, + <0x4ac60000 0x0 0x20000>; #interrupt-cells = <3>; interrupt-controller; }; diff --git a/arch/arm64/boot/dts/st/stm32mp231.dtsi b/arch/arm64/boot/dts/st/stm32mp231.dtsi index 8820d219a33e..75697acd1345 100644 --- a/arch/arm64/boot/dts/st/stm32mp231.dtsi +++ b/arch/arm64/boot/dts/st/stm32mp231.dtsi @@ -1201,13 +1201,12 @@ }; intc: interrupt-controller@4ac10000 { - compatible = "arm,cortex-a7-gic"; + compatible = "arm,gic-400"; reg = <0x4ac10000 0x1000>, - <0x4ac20000 0x2000>, - <0x4ac40000 0x2000>, - <0x4ac60000 0x2000>; + <0x4ac20000 0x20000>, + <0x4ac40000 0x20000>, + <0x4ac60000 0x20000>; #interrupt-cells = <3>; - #address-cells = <1>; interrupt-controller; }; }; diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi index f3c6cdfd7008..87110f91e489 100644 --- a/arch/arm64/boot/dts/st/stm32mp251.dtsi +++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi @@ -115,14 +115,13 @@ }; intc: interrupt-controller@4ac00000 { - compatible = "arm,cortex-a7-gic"; + compatible = "arm,gic-400"; #interrupt-cells = <3>; - #address-cells = <1>; interrupt-controller; reg = <0x0 0x4ac10000 0x0 0x1000>, - <0x0 0x4ac20000 0x0 0x2000>, - <0x0 0x4ac40000 0x0 0x2000>, - <0x0 0x4ac60000 0x0 0x2000>; + <0x0 0x4ac20000 0x0 0x20000>, + <0x0 0x4ac40000 0x0 0x20000>, + <0x0 0x4ac60000 0x0 0x20000>; }; psci { diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 5bb8f09422a2..c4ce2c67c0e0 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1729,12 +1729,12 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_SECURITY=y CONFIG_CRYPTO_USER=y +CONFIG_CRYPTO_CHACHA20=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_ECHAINIV=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_ANSI_CPRNG=y CONFIG_CRYPTO_USER_API_RNG=m -CONFIG_CRYPTO_CHACHA20_NEON=m CONFIG_CRYPTO_GHASH_ARM64_CE=y CONFIG_CRYPTO_SHA1_ARM64_CE=y CONFIG_CRYPTO_SHA2_ARM64_CE=y diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index d1cc0571798b..dffff6763812 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -81,6 +81,7 @@ #define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 +#define ARM_CPU_PART_CORTEX_X1C 0xD4C #define ARM_CPU_PART_CORTEX_A520 0xD80 #define ARM_CPU_PART_CORTEX_A710 0xD47 #define ARM_CPU_PART_CORTEX_A715 0xD4D @@ -168,6 +169,7 @@ #define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index ebceaae3c749..d40e427ddad9 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -52,7 +52,7 @@ mrs x0, id_aa64mmfr1_el1 ubfx x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4 cbz x0, .Lskip_hcrx_\@ - mov_q x0, HCRX_HOST_FLAGS + mov_q x0, (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM) /* Enable GCS if supported */ mrs_s x1, SYS_ID_AA64PFR1_EL1 diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 39577f1d079a..18c7811774d3 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -706,6 +706,7 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, } #endif u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type); +u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type); u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, enum aarch64_insn_system_register sysreg); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 974d72b5905b..e9c8a581e16f 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -100,9 +100,8 @@ HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID1) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA) #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) -#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) +#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H | HCR_AMO | HCR_IMO | HCR_FMO) -#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM) #define MPAMHCR_HOST_FLAGS 0 /* TCR_EL2 Registers bits */ diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index f1524cdeacf1..8fef12626090 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -97,6 +97,9 @@ enum mitigation_state arm64_get_meltdown_state(void); enum mitigation_state arm64_get_spectre_bhb_state(void); bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope); +extern bool __nospectre_bhb; +u8 get_spectre_bhb_loop_value(void); +bool is_spectre_bhb_fw_mitigated(void); void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused); bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr); diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index 92a2b59a9f3d..3322c7047d84 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -99,6 +99,19 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return res; } +#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) +static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void) +{ + const struct vdso_time_data *ret = &vdso_u_time_data; + + /* Work around invalid absolute relocations */ + OPTIMIZER_HIDE_VAR(ret); + + return ret; +} +#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data +#endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */ + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 9c4d6d552b25..4c46d80aa64b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -114,7 +114,14 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NC DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS); -bool arm64_use_ng_mappings = false; +/* + * arm64_use_ng_mappings must be placed in the .data section, otherwise it + * ends up in the .bss section where it is initialized in early_map_kernel() + * after the MMU (with the idmap) was enabled. create_init_idmap() - which + * runs before early_map_kernel() and reads the variable via PTE_MAYBE_NG - + * may end up generating an incorrect idmap page table attributes. + */ +bool arm64_use_ng_mappings __read_mostly = false; EXPORT_SYMBOL(arm64_use_ng_mappings); DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors; diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index b607f6dfc5e6..edf1783ffc81 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -891,6 +891,7 @@ static u8 spectre_bhb_loop_affected(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), @@ -999,6 +1000,11 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, return true; } +u8 get_spectre_bhb_loop_value(void) +{ + return max_bhb_k; +} + static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) { const char *v = arm64_get_bp_hardening_vector(slot); @@ -1016,7 +1022,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) isb(); } -static bool __read_mostly __nospectre_bhb; +bool __read_mostly __nospectre_bhb; static int __init parse_spectre_bhb_param(char *str) { __nospectre_bhb = true; @@ -1094,6 +1100,11 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) update_mitigation_state(&spectre_bhb_state, state); } +bool is_spectre_bhb_fw_mitigated(void) +{ + return test_bit(BHB_FW, &system_bhb_mitigations); +} + /* Patched to NOP when enabled */ void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt, __le32 *origptr, diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index b741ea6aefa5..96f625dc7256 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -235,6 +235,8 @@ static inline void __deactivate_traps_mpam(void) static inline void __activate_traps_common(struct kvm_vcpu *vcpu) { + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */ write_sysreg(1 << 15, hstr_el2); @@ -245,11 +247,8 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) * EL1 instead of being trapped to EL2. */ if (system_supports_pmuv3()) { - struct kvm_cpu_context *hctxt; - write_sysreg(0, pmselr_el0); - hctxt = host_data_ptr(host_ctxt); ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0); write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); vcpu_set_flag(vcpu, PMUSERENR_ON_CPU); @@ -269,6 +268,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) hcrx &= ~clr; } + ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2); write_sysreg_s(hcrx, SYS_HCRX_EL2); } @@ -278,19 +278,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) { + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); write_sysreg(0, hstr_el2); if (system_supports_pmuv3()) { - struct kvm_cpu_context *hctxt; - - hctxt = host_data_ptr(host_ctxt); write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU); } if (cpus_have_final_cap(ARM64_HAS_HCX)) - write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2); + write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2); __deactivate_traps_hfgxtr(vcpu); __deactivate_traps_mpam(); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 2a5284f749b4..e80f3ebd3e2a 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -503,7 +503,7 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) { int ret; - if (!addr_is_memory(addr)) + if (!range_is_memory(addr, addr + size)) return -EPERM; ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt, diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index ed363aa3027e..50aa8dbcae75 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -429,23 +429,27 @@ u64 __vgic_v3_get_gic_config(void) /* * To check whether we have a MMIO-based (GICv2 compatible) * CPU interface, we need to disable the system register - * view. To do that safely, we have to prevent any interrupt - * from firing (which would be deadly). + * view. * - * Note that this only makes sense on VHE, as interrupts are - * already masked for nVHE as part of the exception entry to - * EL2. - */ - if (has_vhe()) - flags = local_daif_save(); - - /* * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates * that to be able to set ICC_SRE_EL1.SRE to 0, all the * interrupt overrides must be set. You've got to love this. + * + * As we always run VHE with HCR_xMO set, no extra xMO + * manipulation is required in that case. + * + * To safely disable SRE, we have to prevent any interrupt + * from firing (which would be deadly). This only makes sense + * on VHE, as interrupts are already masked for nVHE as part + * of the exception entry to EL2. */ - sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); - isb(); + if (has_vhe()) { + flags = local_daif_save(); + } else { + sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); + isb(); + } + write_gicreg(0, ICC_SRE_EL1); isb(); @@ -453,11 +457,13 @@ u64 __vgic_v3_get_gic_config(void) write_gicreg(sre, ICC_SRE_EL1); isb(); - sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); - isb(); - if (has_vhe()) + if (has_vhe()) { local_daif_restore(flags); + } else { + sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); + isb(); + } val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63); val |= read_gicreg(ICH_VTR_EL2); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 754f2fe0cc67..eeda92330ade 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1501,6 +1501,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } + if (!is_protected_kvm_enabled()) + memcache = &vcpu->arch.mmu_page_cache; + else + memcache = &vcpu->arch.pkvm_memcache; + /* * Permission faults just need to update the existing leaf entry, * and so normally don't require allocations from the memcache. The @@ -1510,13 +1515,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!fault_is_perm || (logging_active && write_fault)) { int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu); - if (!is_protected_kvm_enabled()) { - memcache = &vcpu->arch.mmu_page_cache; + if (!is_protected_kvm_enabled()) ret = kvm_mmu_topup_memory_cache(memcache, min_pages); - } else { - memcache = &vcpu->arch.pkvm_memcache; + else ret = topup_hyp_memcache(memcache, min_pages); - } + if (ret) return ret; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 005ad28f7306..5dde9285afc8 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1945,6 +1945,12 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, if ((hw_val & mpam_mask) == (user_val & mpam_mask)) user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK; + /* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */ + if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) || + !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) || + (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val))) + return -EINVAL; + return set_id_reg(vcpu, rd, user_val); } diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index 9bef696e2230..4e298baddc2e 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -5,6 +5,7 @@ * * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com> */ +#include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/printk.h> @@ -1500,43 +1501,41 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant, return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm); } -u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) +static u32 __get_barrier_crm_val(enum aarch64_insn_mb_type type) { - u32 opt; - u32 insn; - switch (type) { case AARCH64_INSN_MB_SY: - opt = 0xf; - break; + return 0xf; case AARCH64_INSN_MB_ST: - opt = 0xe; - break; + return 0xe; case AARCH64_INSN_MB_LD: - opt = 0xd; - break; + return 0xd; case AARCH64_INSN_MB_ISH: - opt = 0xb; - break; + return 0xb; case AARCH64_INSN_MB_ISHST: - opt = 0xa; - break; + return 0xa; case AARCH64_INSN_MB_ISHLD: - opt = 0x9; - break; + return 0x9; case AARCH64_INSN_MB_NSH: - opt = 0x7; - break; + return 0x7; case AARCH64_INSN_MB_NSHST: - opt = 0x6; - break; + return 0x6; case AARCH64_INSN_MB_NSHLD: - opt = 0x5; - break; + return 0x5; default: - pr_err("%s: unknown dmb type %d\n", __func__, type); + pr_err("%s: unknown barrier type %d\n", __func__, type); return AARCH64_BREAK_FAULT; } +} + +u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) +{ + u32 opt; + u32 insn; + + opt = __get_barrier_crm_val(type); + if (opt == AARCH64_BREAK_FAULT) + return AARCH64_BREAK_FAULT; insn = aarch64_insn_get_dmb_value(); insn &= ~GENMASK(11, 8); @@ -1545,6 +1544,21 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) return insn; } +u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type) +{ + u32 opt, insn; + + opt = __get_barrier_crm_val(type); + if (opt == AARCH64_BREAK_FAULT) + return AARCH64_BREAK_FAULT; + + insn = aarch64_insn_get_dsb_base_value(); + insn &= ~GENMASK(11, 8); + insn |= (opt << 8); + + return insn; +} + u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, enum aarch64_insn_system_register sysreg) { diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 70d7c89d3ac9..634d78422adb 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "bpf_jit: " fmt +#include <linux/arm-smccc.h> #include <linux/bitfield.h> #include <linux/bpf.h> #include <linux/filter.h> @@ -17,6 +18,7 @@ #include <asm/asm-extable.h> #include <asm/byteorder.h> #include <asm/cacheflush.h> +#include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/insn.h> #include <asm/text-patching.h> @@ -939,7 +941,51 @@ static void build_plt(struct jit_ctx *ctx) plt->target = (u64)&dummy_tramp; } -static void build_epilogue(struct jit_ctx *ctx) +/* Clobbers BPF registers 1-4, aka x0-x3 */ +static void __maybe_unused build_bhb_mitigation(struct jit_ctx *ctx) +{ + const u8 r1 = bpf2a64[BPF_REG_1]; /* aka x0 */ + u8 k = get_spectre_bhb_loop_value(); + + if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) || + cpu_mitigations_off() || __nospectre_bhb || + arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) + return; + + if (capable(CAP_SYS_ADMIN)) + return; + + if (supports_clearbhb(SCOPE_SYSTEM)) { + emit(aarch64_insn_gen_hint(AARCH64_INSN_HINT_CLEARBHB), ctx); + return; + } + + if (k) { + emit_a64_mov_i64(r1, k, ctx); + emit(A64_B(1), ctx); + emit(A64_SUBS_I(true, r1, r1, 1), ctx); + emit(A64_B_(A64_COND_NE, -2), ctx); + emit(aarch64_insn_gen_dsb(AARCH64_INSN_MB_ISH), ctx); + emit(aarch64_insn_get_isb_value(), ctx); + } + + if (is_spectre_bhb_fw_mitigated()) { + emit(A64_ORR_I(false, r1, AARCH64_INSN_REG_ZR, + ARM_SMCCC_ARCH_WORKAROUND_3), ctx); + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: + emit(aarch64_insn_get_hvc_value(), ctx); + break; + case SMCCC_CONDUIT_SMC: + emit(aarch64_insn_get_smc_value(), ctx); + break; + default: + pr_err_once("Firmware mitigation enabled with unknown conduit\n"); + } + } +} + +static void build_epilogue(struct jit_ctx *ctx, bool was_classic) { const u8 r0 = bpf2a64[BPF_REG_0]; const u8 ptr = bpf2a64[TCCNT_PTR]; @@ -952,10 +998,13 @@ static void build_epilogue(struct jit_ctx *ctx) emit(A64_POP(A64_ZR, ptr, A64_SP), ctx); + if (was_classic) + build_bhb_mitigation(ctx); + /* Restore FP/LR registers */ emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); - /* Set return value */ + /* Move the return value from bpf:r0 (aka x7) to x0 */ emit(A64_MOV(1, A64_R(0), r0), ctx); /* Authenticate lr */ @@ -1898,7 +1947,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) } ctx.epilogue_offset = ctx.idx; - build_epilogue(&ctx); + build_epilogue(&ctx, was_classic); build_plt(&ctx); extable_align = __alignof__(struct exception_table_entry); @@ -1961,7 +2010,7 @@ skip_init_ctx: goto out_free_hdr; } - build_epilogue(&ctx); + build_epilogue(&ctx, was_classic); build_plt(&ctx); /* Extra pass to validate JITed code. */ diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index a5b63c84f854..e5d21e836d99 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -55,7 +55,7 @@ static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long v /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); -#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last)) +#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last) - sizeof(unsigned long)) /** * regs_get_register() - get register value from its offset diff --git a/arch/loongarch/include/asm/uprobes.h b/arch/loongarch/include/asm/uprobes.h index 99a0d198927f..025fc3f0a102 100644 --- a/arch/loongarch/include/asm/uprobes.h +++ b/arch/loongarch/include/asm/uprobes.h @@ -15,7 +15,6 @@ typedef u32 uprobe_opcode_t; #define UPROBE_XOLBP_INSN __emit_break(BRK_UPROBE_XOLBP) struct arch_uprobe { - unsigned long resume_era; u32 insn[2]; u32 ixol[2]; bool simulate; diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 4f0912141781..733a7665e434 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -16,6 +16,7 @@ #include <asm/stackframe.h> #include <asm/thread_info.h> + .section .cpuidle.text, "ax" .align 5 SYM_FUNC_START(__arch_cpu_idle) /* start of idle interrupt region */ @@ -31,14 +32,16 @@ SYM_FUNC_START(__arch_cpu_idle) */ idle 0 /* end of idle interrupt region */ -1: jr ra +idle_exit: + jr ra SYM_FUNC_END(__arch_cpu_idle) + .previous SYM_CODE_START(handle_vint) UNWIND_HINT_UNDEFINED BACKUP_T0T1 SAVE_ALL - la_abs t1, 1b + la_abs t1, idle_exit LONG_L t0, sp, PT_ERA /* 3 instructions idle interrupt region */ ori t0, t0, 0b1100 diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c index ec5b28e570c9..4c476904227f 100644 --- a/arch/loongarch/kernel/kfpu.c +++ b/arch/loongarch/kernel/kfpu.c @@ -18,11 +18,28 @@ static unsigned int euen_mask = CSR_EUEN_FPEN; static DEFINE_PER_CPU(bool, in_kernel_fpu); static DEFINE_PER_CPU(unsigned int, euen_current); +static inline void fpregs_lock(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + local_bh_disable(); +} + +static inline void fpregs_unlock(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + local_bh_enable(); +} + void kernel_fpu_begin(void) { unsigned int *euen_curr; - preempt_disable(); + if (!irqs_disabled()) + fpregs_lock(); WARN_ON(this_cpu_read(in_kernel_fpu)); @@ -73,7 +90,8 @@ void kernel_fpu_end(void) this_cpu_write(in_kernel_fpu, false); - preempt_enable(); + if (!irqs_disabled()) + fpregs_unlock(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index e2d3bfeb6366..bc75a3a69fc8 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -111,7 +111,7 @@ static unsigned long __init get_loops_per_jiffy(void) return lpj; } -static long init_offset __nosavedata; +static long init_offset; void save_counter(void) { diff --git a/arch/loongarch/kernel/uprobes.c b/arch/loongarch/kernel/uprobes.c index 87abc7137b73..6022eb0f71db 100644 --- a/arch/loongarch/kernel/uprobes.c +++ b/arch/loongarch/kernel/uprobes.c @@ -42,7 +42,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) utask->autask.saved_trap_nr = current->thread.trap_nr; current->thread.trap_nr = UPROBE_TRAP_NR; instruction_pointer_set(regs, utask->xol_vaddr); - user_enable_single_step(current); return 0; } @@ -53,13 +52,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); current->thread.trap_nr = utask->autask.saved_trap_nr; - - if (auprobe->simulate) - instruction_pointer_set(regs, auprobe->resume_era); - else - instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE); - - user_disable_single_step(current); + instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE); return 0; } @@ -70,7 +63,6 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) current->thread.trap_nr = utask->autask.saved_trap_nr; instruction_pointer_set(regs, utask->vaddr); - user_disable_single_step(current); } bool arch_uprobe_xol_was_trapped(struct task_struct *t) @@ -90,7 +82,6 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) insn.word = auprobe->insn[0]; arch_simulate_insn(insn, regs); - auprobe->resume_era = regs->csr_era; return true; } diff --git a/arch/loongarch/power/hibernate.c b/arch/loongarch/power/hibernate.c index 1e0590542f98..e7b7346592cb 100644 --- a/arch/loongarch/power/hibernate.c +++ b/arch/loongarch/power/hibernate.c @@ -2,6 +2,7 @@ #include <asm/fpu.h> #include <asm/loongson.h> #include <asm/sections.h> +#include <asm/time.h> #include <asm/tlbflush.h> #include <linux/suspend.h> @@ -14,6 +15,7 @@ struct pt_regs saved_regs; void save_processor_state(void) { + save_counter(); saved_crmd = csr_read32(LOONGARCH_CSR_CRMD); saved_prmd = csr_read32(LOONGARCH_CSR_PRMD); saved_euen = csr_read32(LOONGARCH_CSR_EUEN); @@ -26,6 +28,7 @@ void save_processor_state(void) void restore_processor_state(void) { + sync_counter(); csr_write32(saved_crmd, LOONGARCH_CSR_CRMD); csr_write32(saved_prmd, LOONGARCH_CSR_PRMD); csr_write32(saved_euen, LOONGARCH_CSR_EUEN); diff --git a/arch/m68k/configs/amcore_defconfig b/arch/m68k/configs/amcore_defconfig index 110279a64aa4..60767811e34a 100644 --- a/arch/m68k/configs/amcore_defconfig +++ b/arch/m68k/configs/amcore_defconfig @@ -2,7 +2,6 @@ CONFIG_LOCALVERSION="amcore-002" CONFIG_DEFAULT_HOSTNAME="amcore" CONFIG_SYSVIPC=y # CONFIG_FHANDLE is not set -# CONFIG_USELIB is not set CONFIG_LOG_BUF_SHIFT=14 CONFIG_CC_OPTIMIZE_FOR_SIZE=y # CONFIG_AIO is not set diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h index 0992cad9c632..c7d75807d13f 100644 --- a/arch/mips/include/asm/idle.h +++ b/arch/mips/include/asm/idle.h @@ -6,11 +6,10 @@ #include <linux/linkage.h> extern void (*cpu_wait)(void); -extern void r4k_wait(void); -extern asmlinkage void __r4k_wait(void); +extern asmlinkage void r4k_wait(void); extern void r4k_wait_irqoff(void); -static inline int using_rollback_handler(void) +static inline int using_skipover_handler(void) { return cpu_wait == r4k_wait; } diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 85fa9962266a..ef72c46b5568 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs, /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); -#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last)) +#define MAX_REG_OFFSET \ + (offsetof(struct pt_regs, __last) - sizeof(unsigned long)) /** * regs_get_register() - get register value from its offset diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h index 4724a563c5bf..43a09f0dd3ff 100644 --- a/arch/mips/include/asm/socket.h +++ b/arch/mips/include/asm/socket.h @@ -36,15 +36,6 @@ enum sock_type { SOCK_PACKET = 10, }; -#define SOCK_MAX (SOCK_PACKET + 1) -/* Mask which covers at least up to SOCK_MASK-1. The - * * remaining bits are used as flags. */ -#define SOCK_TYPE_MASK 0xf - -/* Flags for socket, socketpair, paccept */ -#define SOCK_CLOEXEC O_CLOEXEC -#define SOCK_NONBLOCK O_NONBLOCK - #define ARCH_HAS_SOCKET_TYPES 1 #endif /* _ASM_SOCKET_H */ diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index a572ce36a24f..08c0a01d9a29 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -104,48 +104,59 @@ handle_vcei: __FINIT - .align 5 /* 32 byte rollback region */ -LEAF(__r4k_wait) - .set push - .set noreorder - /* start of rollback region */ - LONG_L t0, TI_FLAGS($28) - nop - andi t0, _TIF_NEED_RESCHED - bnez t0, 1f - nop - nop - nop -#ifdef CONFIG_CPU_MICROMIPS - nop - nop - nop - nop -#endif + .section .cpuidle.text,"ax" + /* Align to 32 bytes for the maximum idle interrupt region size. */ + .align 5 +LEAF(r4k_wait) + /* Keep the ISA bit clear for calculations on local labels here. */ +0: .fill 0 + /* Start of idle interrupt region. */ + local_irq_enable + /* + * If an interrupt lands here, before going idle on the next + * instruction, we must *NOT* go idle since the interrupt could + * have set TIF_NEED_RESCHED or caused a timer to need resched. + * Fall through -- see skipover_handler below -- and have the + * idle loop take care of things. + */ +1: .fill 0 + /* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up. */ + .if 1b - 0b > 32 + .error "overlong idle interrupt region" + .elseif 1b - 0b > 8 + .align 4 + .endif +2: .fill 0 + .equ r4k_wait_idle_size, 2b - 0b + /* End of idle interrupt region; size has to be a power of 2. */ .set MIPS_ISA_ARCH_LEVEL_RAW +r4k_wait_insn: wait - /* end of rollback region (the region size must be power of two) */ -1: +r4k_wait_exit: + .set mips0 + local_irq_disable jr ra - nop - .set pop - END(__r4k_wait) + END(r4k_wait) + .previous - .macro BUILD_ROLLBACK_PROLOGUE handler - FEXPORT(rollback_\handler) + .macro BUILD_SKIPOVER_PROLOGUE handler + FEXPORT(skipover_\handler) .set push .set noat MFC0 k0, CP0_EPC - PTR_LA k1, __r4k_wait - ori k0, 0x1f /* 32 byte rollback region */ - xori k0, 0x1f + /* Subtract/add 2 to let the ISA bit propagate through the mask. */ + PTR_LA k1, r4k_wait_insn - 2 + ori k0, r4k_wait_idle_size - 2 + .set noreorder bne k0, k1, \handler + PTR_ADDIU k0, r4k_wait_exit - r4k_wait_insn + 2 + .set reorder MTC0 k0, CP0_EPC .set pop .endm .align 5 -BUILD_ROLLBACK_PROLOGUE handle_int +BUILD_SKIPOVER_PROLOGUE handle_int NESTED(handle_int, PT_SIZE, sp) .cfi_signal_frame #ifdef CONFIG_TRACE_IRQFLAGS @@ -265,7 +276,7 @@ NESTED(except_vec_ejtag_debug, 0, sp) * This prototype is copied to ebase + n*IntCtl.VS and patched * to invoke the handler */ -BUILD_ROLLBACK_PROLOGUE except_vec_vi +BUILD_SKIPOVER_PROLOGUE except_vec_vi NESTED(except_vec_vi, 0, sp) SAVE_SOME docfi=1 SAVE_AT docfi=1 diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 5abc8b7340f8..80e8a04a642e 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void) write_c0_conf(cfg | R30XX_CONF_HALT); } -void __cpuidle r4k_wait(void) -{ - raw_local_irq_enable(); - __r4k_wait(); - raw_local_irq_disable(); -} - /* * This variant is preferable as it allows testing need_resched and going to * sleep depending on the outcome atomically. Unfortunately the "It is diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index e85bd087467e..cc26d56f3ab6 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -332,6 +332,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) mips_cps_cluster_bootcfg = kcalloc(nclusters, sizeof(*mips_cps_cluster_bootcfg), GFP_KERNEL); + if (!mips_cps_cluster_bootcfg) + goto err_out; if (nclusters > 1) mips_cm_update_property(); @@ -348,6 +350,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) mips_cps_cluster_bootcfg[cl].core_power = kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long), GFP_KERNEL); + if (!mips_cps_cluster_bootcfg[cl].core_power) + goto err_out; /* Allocate VPE boot configuration structs */ for (c = 0; c < ncores; c++) { diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 39e248d0ed59..8ec1e185b35c 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -77,7 +77,7 @@ #include "access-helper.h" extern void check_wait(void); -extern asmlinkage void rollback_handle_int(void); +extern asmlinkage void skipover_handle_int(void); extern asmlinkage void handle_int(void); extern asmlinkage void handle_adel(void); extern asmlinkage void handle_ades(void); @@ -2066,7 +2066,7 @@ void *set_vi_handler(int n, vi_handler_t addr) { extern const u8 except_vec_vi[]; extern const u8 except_vec_vi_ori[], except_vec_vi_end[]; - extern const u8 rollback_except_vec_vi[]; + extern const u8 skipover_except_vec_vi[]; unsigned long handler; unsigned long old_handler = vi_handlers[n]; int srssets = current_cpu_data.srsets; @@ -2095,7 +2095,7 @@ void *set_vi_handler(int n, vi_handler_t addr) change_c0_srsmap(0xf << n*4, 0 << n*4); } - vec_start = using_rollback_handler() ? rollback_except_vec_vi : + vec_start = using_skipover_handler() ? skipover_except_vec_vi : except_vec_vi; #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN) ori_offset = except_vec_vi_ori - vec_start + 2; @@ -2426,8 +2426,8 @@ void __init trap_init(void) if (board_be_init) board_be_init(); - set_except_vector(EXCCODE_INT, using_rollback_handler() ? - rollback_handle_int : handle_int); + set_except_vector(EXCCODE_INT, using_skipover_handler() ? + skipover_handle_int : handle_int); set_except_vector(EXCCODE_MOD, handle_tlbm); set_except_vector(EXCCODE_TLBL, handle_tlbl); set_except_vector(EXCCODE_TLBS, handle_tlbs); diff --git a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi index c18822ec849f..58cd546392e0 100644 --- a/arch/riscv/boot/dts/sophgo/cv18xx.dtsi +++ b/arch/riscv/boot/dts/sophgo/cv18xx.dtsi @@ -341,7 +341,7 @@ 1024 1024 1024 1024>; snps,priority = <0 1 2 3 4 5 6 7>; snps,dma-masters = <2>; - snps,data-width = <4>; + snps,data-width = <2>; status = "disabled"; }; diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 7c244de77180..15d8f75902f8 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -275,6 +275,9 @@ long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg) unsigned long pmm; u8 pmlen; + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return -EINVAL; + if (is_compat_thread(ti)) return -EINVAL; @@ -330,6 +333,9 @@ long get_tagged_addr_ctrl(struct task_struct *task) struct thread_info *ti = task_thread_info(task); long ret = 0; + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return -EINVAL; + if (is_compat_thread(ti)) return -EINVAL; diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 8ff8e8b36524..9c83848797a7 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -198,47 +198,57 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re DO_ERROR_INFO(do_trap_load_fault, SIGSEGV, SEGV_ACCERR, "load access fault"); -asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs) +enum misaligned_access_type { + MISALIGNED_STORE, + MISALIGNED_LOAD, +}; +static const struct { + const char *type_str; + int (*handler)(struct pt_regs *regs); +} misaligned_handler[] = { + [MISALIGNED_STORE] = { + .type_str = "Oops - store (or AMO) address misaligned", + .handler = handle_misaligned_store, + }, + [MISALIGNED_LOAD] = { + .type_str = "Oops - load address misaligned", + .handler = handle_misaligned_load, + }, +}; + +static void do_trap_misaligned(struct pt_regs *regs, enum misaligned_access_type type) { + irqentry_state_t state; + if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); + local_irq_enable(); + } else { + state = irqentry_nmi_enter(regs); + } - if (handle_misaligned_load(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - load address misaligned"); + if (misaligned_handler[type].handler(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + misaligned_handler[type].type_str); + if (user_mode(regs)) { + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { - irqentry_state_t state = irqentry_nmi_enter(regs); - - if (handle_misaligned_load(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - load address misaligned"); - irqentry_nmi_exit(regs, state); } } -asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs) +asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs) { - if (user_mode(regs)) { - irqentry_enter_from_user_mode(regs); - - if (handle_misaligned_store(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - store (or AMO) address misaligned"); - - irqentry_exit_to_user_mode(regs); - } else { - irqentry_state_t state = irqentry_nmi_enter(regs); - - if (handle_misaligned_store(regs)) - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - store (or AMO) address misaligned"); + do_trap_misaligned(regs, MISALIGNED_LOAD); +} - irqentry_nmi_exit(regs, state); - } +asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs) +{ + do_trap_misaligned(regs, MISALIGNED_STORE); } + DO_ERROR_INFO(do_trap_store_fault, SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault"); DO_ERROR_INFO(do_trap_ecall_s, diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 4354c87c0376..77c788660223 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -88,6 +88,13 @@ #define INSN_MATCH_C_FSWSP 0xe002 #define INSN_MASK_C_FSWSP 0xe003 +#define INSN_MATCH_C_LHU 0x8400 +#define INSN_MASK_C_LHU 0xfc43 +#define INSN_MATCH_C_LH 0x8440 +#define INSN_MASK_C_LH 0xfc43 +#define INSN_MATCH_C_SH 0x8c00 +#define INSN_MASK_C_SH 0xfc43 + #define INSN_LEN(insn) ((((insn) & 0x3) < 0x3) ? 2 : 4) #if defined(CONFIG_64BIT) @@ -268,7 +275,7 @@ static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset, int __ret; \ \ if (user_mode(regs)) { \ - __ret = __get_user(insn, (type __user *) insn_addr); \ + __ret = get_user(insn, (type __user *) insn_addr); \ } else { \ insn = *(type *)insn_addr; \ __ret = 0; \ @@ -431,6 +438,13 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs) fp = 1; len = 4; #endif + } else if ((insn & INSN_MASK_C_LHU) == INSN_MATCH_C_LHU) { + len = 2; + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LH) == INSN_MATCH_C_LH) { + len = 2; + shift = 8 * (sizeof(ulong) - len); + insn = RVC_RS2S(insn) << SH_RD; } else { regs->epc = epc; return -1; @@ -530,6 +544,9 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs) len = 4; val.data_ulong = GET_F32_RS2C(insn, regs); #endif + } else if ((insn & INSN_MASK_C_SH) == INSN_MATCH_C_SH) { + len = 2; + val.data_ulong = GET_RS2S(insn, regs); } else { regs->epc = epc; return -1; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 60d684c76c58..02635bac91f1 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -77,6 +77,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) memcpy(cntx, reset_cntx, sizeof(*cntx)); spin_unlock(&vcpu->arch.reset_cntx_lock); + memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr)); + kvm_riscv_vcpu_fp_reset(vcpu); kvm_riscv_vcpu_vector_reset(vcpu); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 6f2c9ce1b154..24b22f6a9e99 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -38,7 +38,6 @@ CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y -# CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y @@ -92,7 +91,6 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_SLAB_BUCKETS=y CONFIG_SLUB_STATS=y @@ -395,6 +393,9 @@ CONFIG_CLS_U32_MARK=y CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y CONFIG_NET_CLS_BPF=m +CONFIG_NET_CLS_FLOWER=m +CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m @@ -405,6 +406,9 @@ CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_VLAN=m +CONFIG_NET_ACT_TUNNEL_KEY=m +CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_GATE=m CONFIG_NET_TC_SKB_EXT=y CONFIG_DNS_RESOLVER=y @@ -628,8 +632,16 @@ CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_MEM=m CONFIG_VIRTIO_INPUT=y +CONFIG_VDPA=m +CONFIG_VDPA_SIM=m +CONFIG_VDPA_SIM_NET=m +CONFIG_VDPA_SIM_BLOCK=m +CONFIG_VDPA_USER=m +CONFIG_MLX5_VDPA_NET=m +CONFIG_VP_VDPA=m CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +CONFIG_VHOST_VDPA=m CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -654,7 +666,6 @@ CONFIG_NILFS2_FS=m CONFIG_BCACHEFS_FS=y CONFIG_BCACHEFS_QUOTA=y CONFIG_BCACHEFS_POSIX_ACL=y -CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y @@ -724,11 +735,10 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_UNICODE=y CONFIG_PERSISTENT_KEYRINGS=y +CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y -CONFIG_HARDENED_USERCOPY=y -CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_LOCKDOWN_LSM=y @@ -741,6 +751,8 @@ CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_FORTIFY_SOURCE=y +CONFIG_HARDENED_USERCOPY=y CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -756,7 +768,6 @@ CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_ARIA=m CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_DES=m @@ -801,7 +812,6 @@ CONFIG_CRYPTO_SHA3_512_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_DES_S390=m -CONFIG_CRYPTO_CHACHA_S390=m CONFIG_CRYPTO_HMAC_S390=m CONFIG_ZCRYPT=m CONFIG_PKEY=m @@ -812,9 +822,9 @@ CONFIG_PKEY_UV=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_SYSTEM_BLACKLIST_KEYRING=y +CONFIG_CRYPTO_KRB5=m +CONFIG_CRYPTO_KRB5_SELFTESTS=y CONFIG_CORDIC=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_RANDOM32_SELFTEST=y CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index f18a7d97ac21..2b8b42d569bc 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -36,7 +36,6 @@ CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_EXPERT=y -# CONFIG_SYSFS_SYSCALL is not set CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y @@ -86,7 +85,6 @@ CONFIG_UNIXWARE_DISKLABEL=y CONFIG_IOSCHED_BFQ=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_SLAB_BUCKETS=y # CONFIG_COMPAT_BRK is not set @@ -385,6 +383,9 @@ CONFIG_CLS_U32_MARK=y CONFIG_NET_CLS_FLOW=m CONFIG_NET_CLS_CGROUP=y CONFIG_NET_CLS_BPF=m +CONFIG_NET_CLS_FLOWER=m +CONFIG_NET_CLS_MATCHALL=m +CONFIG_NET_EMATCH=y CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m @@ -395,6 +396,9 @@ CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_VLAN=m +CONFIG_NET_ACT_TUNNEL_KEY=m +CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_GATE=m CONFIG_NET_TC_SKB_EXT=y CONFIG_DNS_RESOLVER=y @@ -618,8 +622,16 @@ CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_MEM=m CONFIG_VIRTIO_INPUT=y +CONFIG_VDPA=m +CONFIG_VDPA_SIM=m +CONFIG_VDPA_SIM_NET=m +CONFIG_VDPA_SIM_BLOCK=m +CONFIG_VDPA_USER=m +CONFIG_MLX5_VDPA_NET=m +CONFIG_VP_VDPA=m CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +CONFIG_VHOST_VDPA=m CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -641,7 +653,6 @@ CONFIG_NILFS2_FS=m CONFIG_BCACHEFS_FS=m CONFIG_BCACHEFS_QUOTA=y CONFIG_BCACHEFS_POSIX_ACL=y -CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y CONFIG_FS_VERITY=y @@ -711,6 +722,7 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_UNICODE=y CONFIG_PERSISTENT_KEYRINGS=y +CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y @@ -742,7 +754,6 @@ CONFIG_CRYPTO_AES_TI=m CONFIG_CRYPTO_ANUBIS=m CONFIG_CRYPTO_ARIA=m CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_DES=m @@ -788,7 +799,6 @@ CONFIG_CRYPTO_SHA3_512_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_DES_S390=m -CONFIG_CRYPTO_CHACHA_S390=m CONFIG_CRYPTO_HMAC_S390=m CONFIG_ZCRYPT=m CONFIG_PKEY=m @@ -799,10 +809,10 @@ CONFIG_PKEY_UV=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_SYSTEM_BLACKLIST_KEYRING=y +CONFIG_CRYPTO_KRB5=m +CONFIG_CRYPTO_KRB5_SELFTESTS=y CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 853b2326a171..8163c1702720 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -70,7 +70,6 @@ CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_FS=y CONFIG_PANIC_ON_OOPS=y -# CONFIG_SCHED_DEBUG is not set CONFIG_RCU_CPU_STALL_TIMEOUT=60 # CONFIG_RCU_TRACE is not set # CONFIG_FTRACE is not set diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 04ea1c03a5ff..96409573c75d 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -342,7 +342,7 @@ static struct dentry *hypfs_create_file(struct dentry *parent, const char *name, struct inode *inode; inode_lock(d_inode(parent)); - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_noperm(&QSTR(name), parent); if (IS_ERR(dentry)) { dentry = ERR_PTR(-ENOMEM); goto fail; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index dd291c9ad6a6..9980c17ba22d 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -602,7 +602,8 @@ SYM_CODE_START(stack_invalid) stmg %r0,%r7,__PT_R0(%r11) stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_R8(64,%r11),0(%r14) - stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2 + GET_LC %r2 + mvc __PT_ORIG_GPR2(8,%r11),__LC_PGM_LAST_BREAK(%r2) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs jg kernel_stack_invalid diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 9a929bbcc397..241f7251c873 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -428,6 +428,8 @@ static void __clp_add(struct clp_fh_list_entry *entry, void *data) return; } zdev = zpci_create_device(entry->fid, entry->fh, entry->config_state); + if (IS_ERR(zdev)) + return; list_add_tail(&zdev->entry, scan_list); } diff --git a/arch/um/Makefile b/arch/um/Makefile index 1d36a613aad8..9ed792e565c9 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -154,5 +154,6 @@ MRPROPER_FILES += $(HOST_DIR)/include/generated archclean: @find . \( -name '*.bb' -o -name '*.bbg' -o -name '*.da' \ -o -name '*.gcov' \) -type f -print | xargs rm -f + $(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) clean export HEADER_ARCH SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING DEV_NULL_PATH diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h index 3a08f9029a3f..1c6e0ae41b0c 100644 --- a/arch/um/include/asm/uaccess.h +++ b/arch/um/include/asm/uaccess.h @@ -55,6 +55,7 @@ do { \ goto err_label; \ } \ *((type *)dst) = get_unaligned((type *)(src)); \ + barrier(); \ current->thread.segv_continue = NULL; \ } while (0) @@ -66,6 +67,7 @@ do { \ if (__faulted) \ goto err_label; \ put_unaligned(*((type *)src), (type *)(dst)); \ + barrier(); \ current->thread.segv_continue = NULL; \ } while (0) diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index ce073150dc20..ef2272e92a43 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -225,20 +225,20 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user, panic("Failed to sync kernel TLBs: %d", err); goto out; } - else if (current->mm == NULL) { - if (current->pagefault_disabled) { - if (!mc) { - show_regs(container_of(regs, struct pt_regs, regs)); - panic("Segfault with pagefaults disabled but no mcontext"); - } - if (!current->thread.segv_continue) { - show_regs(container_of(regs, struct pt_regs, regs)); - panic("Segfault without recovery target"); - } - mc_set_rip(mc, current->thread.segv_continue); - current->thread.segv_continue = NULL; - goto out; + else if (current->pagefault_disabled) { + if (!mc) { + show_regs(container_of(regs, struct pt_regs, regs)); + panic("Segfault with pagefaults disabled but no mcontext"); } + if (!current->thread.segv_continue) { + show_regs(container_of(regs, struct pt_regs, regs)); + panic("Segfault without recovery target"); + } + mc_set_rip(mc, current->thread.segv_continue); + current->thread.segv_continue = NULL; + goto out; + } + else if (current->mm == NULL) { show_regs(container_of(regs, struct pt_regs, regs)); panic("Segfault with no mm"); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4b9f378e05f6..e21cca404943 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2368,6 +2368,7 @@ config STRICT_SIGALTSTACK_SIZE config CFI_AUTO_DEFAULT bool "Attempt to use FineIBT by default at boot time" depends on FINEIBT + depends on !RUST || RUSTC_VERSION >= 108800 default y help Attempt to use FineIBT by default at boot time. If enabled, @@ -2710,6 +2711,18 @@ config MITIGATION_SSB of speculative execution in a similar way to the Meltdown and Spectre security vulnerabilities. +config MITIGATION_ITS + bool "Enable Indirect Target Selection mitigation" + depends on CPU_SUP_INTEL && X86_64 + depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK + select EXECMEM + default y + help + Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in + BPU on some Intel CPUs that may allow Spectre V2 style attacks. If + disabled, mitigation cannot be enabled via cmdline. + See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index b0c1a7a57497..36beaac713c1 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -959,6 +959,102 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end) set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE); } +static int vmgexit_ap_control(u64 event, struct sev_es_save_area *vmsa, u32 apic_id) +{ + bool create = event != SVM_VMGEXIT_AP_DESTROY; + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + int ret = 0; + + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + + if (create) + ghcb_set_rax(ghcb, vmsa->sev_features); + + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); + ghcb_set_sw_exit_info_1(ghcb, + ((u64)apic_id << 32) | + ((u64)snp_vmpl << 16) | + event); + ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (!ghcb_sw_exit_info_1_is_valid(ghcb) || + lower_32_bits(ghcb->save.sw_exit_info_1)) { + pr_err("SNP AP %s error\n", (create ? "CREATE" : "DESTROY")); + ret = -EINVAL; + } + + __sev_put_ghcb(&state); + + local_irq_restore(flags); + + return ret; +} + +static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa) +{ + int ret; + + if (snp_vmpl) { + struct svsm_call call = {}; + unsigned long flags; + + local_irq_save(flags); + + call.caa = this_cpu_read(svsm_caa); + call.rcx = __pa(va); + + if (make_vmsa) { + /* Protocol 0, Call ID 2 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU); + call.rdx = __pa(caa); + call.r8 = apic_id; + } else { + /* Protocol 0, Call ID 3 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU); + } + + ret = svsm_perform_call_protocol(&call); + + local_irq_restore(flags); + } else { + /* + * If the kernel runs at VMPL0, it can change the VMSA + * bit for a page using the RMPADJUST instruction. + * However, for the instruction to succeed it must + * target the permissions of a lesser privileged (higher + * numbered) VMPL level, so use VMPL1. + */ + u64 attrs = 1; + + if (make_vmsa) + attrs |= RMPADJUST_VMSA_PAGE_BIT; + + ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); + } + + return ret; +} + +static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id) +{ + int err; + + err = snp_set_vmsa(vmsa, NULL, apic_id, false); + if (err) + pr_err("clear VMSA page failed (%u), leaking page\n", err); + else + free_page((unsigned long)vmsa); +} + static void set_pte_enc(pte_t *kpte, int level, void *va) { struct pte_enc_desc d = { @@ -1005,7 +1101,8 @@ static void unshare_all_memory(void) data = per_cpu(runtime_data, cpu); ghcb = (unsigned long)&data->ghcb_page; - if (addr <= ghcb && ghcb <= addr + size) { + /* Handle the case of a huge page containing the GHCB page */ + if (addr <= ghcb && ghcb < addr + size) { skipped_addr = true; break; } @@ -1055,11 +1152,70 @@ void snp_kexec_begin(void) pr_warn("Failed to stop shared<->private conversions\n"); } +/* + * Shutdown all APs except the one handling kexec/kdump and clearing + * the VMSA tag on AP's VMSA pages as they are not being used as + * VMSA page anymore. + */ +static void shutdown_all_aps(void) +{ + struct sev_es_save_area *vmsa; + int apic_id, this_cpu, cpu; + + this_cpu = get_cpu(); + + /* + * APs are already in HLT loop when enc_kexec_finish() callback + * is invoked. + */ + for_each_present_cpu(cpu) { + vmsa = per_cpu(sev_vmsa, cpu); + + /* + * The BSP or offlined APs do not have guest allocated VMSA + * and there is no need to clear the VMSA tag for this page. + */ + if (!vmsa) + continue; + + /* + * Cannot clear the VMSA tag for the currently running vCPU. + */ + if (this_cpu == cpu) { + unsigned long pa; + struct page *p; + + pa = __pa(vmsa); + /* + * Mark the VMSA page of the running vCPU as offline + * so that is excluded and not touched by makedumpfile + * while generating vmcore during kdump. + */ + p = pfn_to_online_page(pa >> PAGE_SHIFT); + if (p) + __SetPageOffline(p); + continue; + } + + apic_id = cpuid_to_apicid[cpu]; + + /* + * Issue AP destroy to ensure AP gets kicked out of guest mode + * to allow using RMPADJUST to remove the VMSA tag on it's + * VMSA page. + */ + vmgexit_ap_control(SVM_VMGEXIT_AP_DESTROY, vmsa, apic_id); + snp_cleanup_vmsa(vmsa, apic_id); + } + + put_cpu(); +} + void snp_kexec_finish(void) { struct sev_es_runtime_data *data; + unsigned long size, addr; unsigned int level, cpu; - unsigned long size; struct ghcb *ghcb; pte_t *pte; @@ -1069,6 +1225,8 @@ void snp_kexec_finish(void) if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; + shutdown_all_aps(); + unshare_all_memory(); /* @@ -1085,54 +1243,11 @@ void snp_kexec_finish(void) ghcb = &data->ghcb_page; pte = lookup_address((unsigned long)ghcb, &level); size = page_level_size(level); - set_pte_enc(pte, level, (void *)ghcb); - snp_set_memory_private((unsigned long)ghcb, (size / PAGE_SIZE)); - } -} - -static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa) -{ - int ret; - - if (snp_vmpl) { - struct svsm_call call = {}; - unsigned long flags; - - local_irq_save(flags); - - call.caa = this_cpu_read(svsm_caa); - call.rcx = __pa(va); - - if (make_vmsa) { - /* Protocol 0, Call ID 2 */ - call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU); - call.rdx = __pa(caa); - call.r8 = apic_id; - } else { - /* Protocol 0, Call ID 3 */ - call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU); - } - - ret = svsm_perform_call_protocol(&call); - - local_irq_restore(flags); - } else { - /* - * If the kernel runs at VMPL0, it can change the VMSA - * bit for a page using the RMPADJUST instruction. - * However, for the instruction to succeed it must - * target the permissions of a lesser privileged (higher - * numbered) VMPL level, so use VMPL1. - */ - u64 attrs = 1; - - if (make_vmsa) - attrs |= RMPADJUST_VMSA_PAGE_BIT; - - ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); + /* Handle the case of a huge page containing the GHCB page */ + addr = (unsigned long)ghcb & page_level_mask(level); + set_pte_enc(pte, level, (void *)addr); + snp_set_memory_private(addr, (size / PAGE_SIZE)); } - - return ret; } #define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK) @@ -1166,24 +1281,10 @@ static void *snp_alloc_vmsa_page(int cpu) return page_address(p + 1); } -static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id) -{ - int err; - - err = snp_set_vmsa(vmsa, NULL, apic_id, false); - if (err) - pr_err("clear VMSA page failed (%u), leaking page\n", err); - else - free_page((unsigned long)vmsa); -} - static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) { struct sev_es_save_area *cur_vmsa, *vmsa; - struct ghcb_state state; struct svsm_ca *caa; - unsigned long flags; - struct ghcb *ghcb; u8 sipi_vector; int cpu, ret; u64 cr4; @@ -1297,33 +1398,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) } /* Issue VMGEXIT AP Creation NAE event */ - local_irq_save(flags); - - ghcb = __sev_get_ghcb(&state); - - vc_ghcb_invalidate(ghcb); - ghcb_set_rax(ghcb, vmsa->sev_features); - ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); - ghcb_set_sw_exit_info_1(ghcb, - ((u64)apic_id << 32) | - ((u64)snp_vmpl << 16) | - SVM_VMGEXIT_AP_CREATE); - ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); - - sev_es_wr_ghcb_msr(__pa(ghcb)); - VMGEXIT(); - - if (!ghcb_sw_exit_info_1_is_valid(ghcb) || - lower_32_bits(ghcb->save.sw_exit_info_1)) { - pr_err("SNP AP Creation error\n"); - ret = -EINVAL; - } - - __sev_put_ghcb(&state); - - local_irq_restore(flags); - - /* Perform cleanup if there was an error */ + ret = vmgexit_ap_control(SVM_VMGEXIT_AP_CREATE, vmsa, apic_id); if (ret) { snp_cleanup_vmsa(vmsa, apic_id); vmsa = NULL; diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 91801138b10b..7cd2f395f301 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -1,7 +1,6 @@ CONFIG_WERROR=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_USELIB=y CONFIG_AUDIT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f40bdf97d390..ed04a968cc7d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1525,7 +1525,9 @@ SYM_CODE_END(rewind_stack_and_make_dead) * ORC to unwind properly. * * The alignment is for performance and not for safety, and may be safely - * refactored in the future if needed. + * refactored in the future if needed. The .skips are for safety, to ensure + * that all RETs are in the second half of a cacheline to mitigate Indirect + * Target Selection, rather than taking the slowpath via its_return_thunk. */ SYM_FUNC_START(clear_bhb_loop) ANNOTATE_NOENDBR @@ -1536,10 +1538,22 @@ SYM_FUNC_START(clear_bhb_loop) call 1f jmp 5f .align 64, 0xcc + /* + * Shift instructions so that the RET is in the upper half of the + * cacheline and don't take the slowpath to its_return_thunk. + */ + .skip 32 - (.Lret1 - 1f), 0xcc ANNOTATE_INTRA_FUNCTION_CALL 1: call 2f - RET +.Lret1: RET .align 64, 0xcc + /* + * As above shift instructions for RET at .Lret2 as well. + * + * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc + * but some Clang versions (e.g. 18) don't like this. + */ + .skip 32 - 18, 0xcc 2: movl $5, %eax 3: jmp 4f nop @@ -1547,7 +1561,7 @@ SYM_FUNC_START(clear_bhb_loop) jnz 3b sub $1, %ecx jnz 1b - RET +.Lret2: RET 5: lfence pop %rbp RET diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 9b20acc0e932..8d86e91bd5e5 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2465,8 +2465,9 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_ setup_pebs_fixed_sample_data); } -static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) +static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, u64 mask) { + u64 pebs_enabled = cpuc->pebs_enabled & mask; struct perf_event *event; int bit; @@ -2477,7 +2478,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int * It needs to call intel_pmu_save_and_restart_reload() to * update the event->count for this case. */ - for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) { + for_each_set_bit(bit, (unsigned long *)&pebs_enabled, X86_PMC_IDX_MAX) { event = cpuc->events[bit]; if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_save_and_restart_reload(event, 0); @@ -2512,7 +2513,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d } if (unlikely(base >= top)) { - intel_pmu_pebs_event_update_no_drain(cpuc, size); + intel_pmu_pebs_event_update_no_drain(cpuc, mask); return; } @@ -2626,7 +2627,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED); if (unlikely(base >= top)) { - intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX); + intel_pmu_pebs_event_update_no_drain(cpuc, mask); return; } diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4a37a8bd87fd..f2294784babc 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -6,6 +6,7 @@ #include <linux/stringify.h> #include <linux/objtool.h> #include <asm/asm.h> +#include <asm/bug.h> #define ALT_FLAGS_SHIFT 16 @@ -124,6 +125,37 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, } #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_init_mod(struct module *mod); +extern void its_fini_mod(struct module *mod); +extern void its_free_mod(struct module *mod); +extern u8 *its_static_thunk(int reg); +#else /* CONFIG_MITIGATION_ITS */ +static inline void its_init_mod(struct module *mod) { } +static inline void its_fini_mod(struct module *mod) { } +static inline void its_free_mod(struct module *mod) { } +static inline u8 *its_static_thunk(int reg) +{ + WARN_ONCE(1, "ITS not compiled in"); + + return NULL; +} +#endif + +#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL) +extern bool cpu_wants_rethunk(void); +extern bool cpu_wants_rethunk_at(void *addr); +#else +static __always_inline bool cpu_wants_rethunk(void) +{ + return false; +} +static __always_inline bool cpu_wants_rethunk_at(void *addr) +{ + return false; +} +#endif + #ifdef CONFIG_SMP extern void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6c2c152d8a67..30144ef9ef02 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -75,7 +75,7 @@ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ #define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ #define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ -/* Free ( 3*32+ 6) */ +#define X86_FEATURE_ZEN6 ( 3*32+ 6) /* CPU based on Zen6 microarchitecture */ /* Free ( 3*32+ 7) */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ #define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ @@ -481,6 +481,7 @@ #define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */ #define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */ #define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */ +#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 9) /* Use thunk for indirect branches in lower half of cacheline */ /* * BUG word(s) @@ -533,4 +534,6 @@ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ #define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */ +#define X86_BUG_ITS X86_BUG(1*32 + 6) /* "its" CPU is affected by Indirect Target Selection */ +#define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 695e569159c1..be7cddc414e4 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -17,10 +17,12 @@ struct ucode_cpu_info { void load_ucode_bsp(void); void load_ucode_ap(void); void microcode_bsp_resume(void); +bool __init microcode_loader_disabled(void); #else static inline void load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void microcode_bsp_resume(void) { } +static inline bool __init microcode_loader_disabled(void) { return false; } #endif extern unsigned long initrd_start_early; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e6134ef2263d..e7d2f460fcc6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -211,6 +211,14 @@ * VERW clears CPU Register * File. */ +#define ARCH_CAP_ITS_NO BIT_ULL(62) /* + * Not susceptible to + * Indirect Target Selection. + * This bit is not set by + * HW, but is synthesized by + * VMMs for guests to know + * their affected status. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 5c43f145454d..7d04ade33541 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -336,10 +336,14 @@ #else /* __ASSEMBLER__ */ +#define ITS_THUNK_SIZE 64 + typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +typedef u8 its_thunk_t[ITS_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; +extern its_thunk_t __x86_indirect_its_thunk_array[]; #ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); @@ -363,6 +367,12 @@ static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_return_thunk(void); +#else +static inline void its_return_thunk(void) {} +#endif + extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index acb85b9346d8..0020d77a0800 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -116,7 +116,7 @@ enum psc_op { #define GHCB_MSR_VMPL_REQ 0x016 #define GHCB_MSR_VMPL_REQ_LEVEL(v) \ /* GHCBData[39:32] */ \ - (((u64)(v) & GENMASK_ULL(7, 0) << 32) | \ + ((((u64)(v) & GENMASK_ULL(7, 0)) << 32) | \ /* GHCBDdata[11:0] */ \ GHCB_MSR_VMPL_REQ) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index bf82c6f7d690..45bcff181cba 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -18,6 +18,7 @@ #include <linux/mmu_context.h> #include <linux/bsearch.h> #include <linux/sync_core.h> +#include <linux/execmem.h> #include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/sections.h> @@ -31,6 +32,8 @@ #include <asm/paravirt.h> #include <asm/asm-prototypes.h> #include <asm/cfi.h> +#include <asm/ibt.h> +#include <asm/set_memory.h> int __read_mostly alternatives_patched; @@ -124,6 +127,171 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = #endif }; +#ifdef CONFIG_FINEIBT +static bool cfi_paranoid __ro_after_init; +#endif + +#ifdef CONFIG_MITIGATION_ITS + +#ifdef CONFIG_MODULES +static struct module *its_mod; +#endif +static void *its_page; +static unsigned int its_offset; + +/* Initialize a thunk with the "jmp *reg; int3" instructions. */ +static void *its_init_thunk(void *thunk, int reg) +{ + u8 *bytes = thunk; + int offset = 0; + int i = 0; + +#ifdef CONFIG_FINEIBT + if (cfi_paranoid) { + /* + * When ITS uses indirect branch thunk the fineibt_paranoid + * caller sequence doesn't fit in the caller site. So put the + * remaining part of the sequence (<ea> + JNE) into the ITS + * thunk. + */ + bytes[i++] = 0xea; /* invalid instruction */ + bytes[i++] = 0x75; /* JNE */ + bytes[i++] = 0xfd; + + offset = 1; + } +#endif + + if (reg >= 8) { + bytes[i++] = 0x41; /* REX.B prefix */ + reg -= 8; + } + bytes[i++] = 0xff; + bytes[i++] = 0xe0 + reg; /* jmp *reg */ + bytes[i++] = 0xcc; + + return thunk + offset; +} + +#ifdef CONFIG_MODULES +void its_init_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + mutex_lock(&text_mutex); + its_mod = mod; + its_page = NULL; +} + +void its_fini_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + WARN_ON_ONCE(its_mod != mod); + + its_mod = NULL; + its_page = NULL; + mutex_unlock(&text_mutex); + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +void its_free_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_free(page); + } + kfree(mod->its_page_array); +} +#endif /* CONFIG_MODULES */ + +static void *its_alloc(void) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + + if (!page) + return NULL; + +#ifdef CONFIG_MODULES + if (its_mod) { + void *tmp = krealloc(its_mod->its_page_array, + (its_mod->its_num_pages+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + its_mod->its_page_array = tmp; + its_mod->its_page_array[its_mod->its_num_pages++] = page; + + execmem_make_temp_rw(page, PAGE_SIZE); + } +#endif /* CONFIG_MODULES */ + + return no_free_ptr(page); +} + +static void *its_allocate_thunk(int reg) +{ + int size = 3 + (reg / 8); + void *thunk; + +#ifdef CONFIG_FINEIBT + /* + * The ITS thunk contains an indirect jump and an int3 instruction so + * its size is 3 or 4 bytes depending on the register used. If CFI + * paranoid is used then 3 extra bytes are added in the ITS thunk to + * complete the fineibt_paranoid caller sequence. + */ + if (cfi_paranoid) + size += 3; +#endif + + if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) { + its_page = its_alloc(); + if (!its_page) { + pr_err("ITS page allocation failed\n"); + return NULL; + } + memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE); + its_offset = 32; + } + + /* + * If the indirect branch instruction will be in the lower half + * of a cacheline, then update the offset to reach the upper half. + */ + if ((its_offset + size - 1) % 64 < 32) + its_offset = ((its_offset - 1) | 0x3F) + 33; + + thunk = its_page + its_offset; + its_offset += size; + + return its_init_thunk(thunk, reg); +} + +u8 *its_static_thunk(int reg) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + +#ifdef CONFIG_FINEIBT + /* Paranoid thunk starts 2 bytes before */ + if (cfi_paranoid) + return thunk - 2; +#endif + return thunk; +} + +#endif + /* * Nomenclature for variable names to simplify and clarify this code and ease * any potential staring at it: @@ -581,7 +749,8 @@ static int emit_indirect(int op, int reg, u8 *bytes) return i; } -static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) +static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes, + void *call_dest, void *jmp_dest) { u8 op = insn->opcode.bytes[0]; int i = 0; @@ -602,7 +771,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 switch (op) { case CALL_INSN_OPCODE: __text_gen_insn(bytes+i, op, addr+i, - __x86_indirect_call_thunk_array[reg], + call_dest, CALL_INSN_SIZE); i += CALL_INSN_SIZE; break; @@ -610,7 +779,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 case JMP32_INSN_OPCODE: clang_jcc: __text_gen_insn(bytes+i, op, addr+i, - __x86_indirect_jump_thunk_array[reg], + jmp_dest, JMP32_INSN_SIZE); i += JMP32_INSN_SIZE; break; @@ -625,6 +794,48 @@ clang_jcc: return i; } +static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + return __emit_trampoline(addr, insn, bytes, + __x86_indirect_call_thunk_array[reg], + __x86_indirect_jump_thunk_array[reg]); +} + +#ifdef CONFIG_MITIGATION_ITS +static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + u8 *tmp = its_allocate_thunk(reg); + + if (tmp) + thunk = tmp; + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); +} + +/* Check if an indirect branch is at ITS-unsafe address */ +static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return false; + + /* Indirect branch opcode is 2 or 3 bytes depending on reg */ + addr += 1 + reg / 8; + + /* Lower-half of the cacheline? */ + return !(addr & 0x20); +} +#else /* CONFIG_MITIGATION_ITS */ + +#ifdef CONFIG_FINEIBT +static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg) +{ + return false; +} +#endif + +#endif /* CONFIG_MITIGATION_ITS */ + /* * Rewrite the compiler generated retpoline thunk calls. * @@ -699,6 +910,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) bytes[i++] = 0xe8; /* LFENCE */ } +#ifdef CONFIG_MITIGATION_ITS + /* + * Check if the address of last byte of emitted-indirect is in + * lower-half of the cacheline. Such branches need ITS mitigation. + */ + if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg)) + return emit_its_trampoline(addr, insn, reg, bytes); +#endif + ret = emit_indirect(op, reg, bytes + i); if (ret < 0) return ret; @@ -732,6 +952,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) int len, ret; u8 bytes[16]; u8 op1, op2; + u8 *dest; ret = insn_decode_kernel(&insn, addr); if (WARN_ON_ONCE(ret < 0)) @@ -748,6 +969,12 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) case CALL_INSN_OPCODE: case JMP32_INSN_OPCODE: + /* Check for cfi_paranoid + ITS */ + dest = addr + insn.length + insn.immediate.value; + if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) { + WARN_ON_ONCE(cfi_mode != CFI_FINEIBT); + continue; + } break; case 0x0f: /* escape */ @@ -775,6 +1002,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) #ifdef CONFIG_MITIGATION_RETHUNK +bool cpu_wants_rethunk(void) +{ + return cpu_feature_enabled(X86_FEATURE_RETHUNK); +} + +bool cpu_wants_rethunk_at(void *addr) +{ + if (!cpu_feature_enabled(X86_FEATURE_RETHUNK)) + return false; + if (x86_return_thunk != its_return_thunk) + return true; + + return !((unsigned long)addr & 0x20); +} + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -791,7 +1033,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) int i = 0; /* Patch the custom return thunks... */ - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (cpu_wants_rethunk_at(addr)) { i = JMP32_INSN_SIZE; __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); } else { @@ -808,7 +1050,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { s32 *s; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk()) static_call_force_reinit(); for (s = start; s < end; s++) { @@ -1022,8 +1264,6 @@ int cfi_get_func_arity(void *func) static bool cfi_rand __ro_after_init = true; static u32 cfi_seed __ro_after_init; -static bool cfi_paranoid __ro_after_init = false; - /* * Re-hash the CFI hash with a boot-time seed while making sure the result is * not a valid ENDBR instruction. @@ -1436,6 +1676,19 @@ static int cfi_rand_callers(s32 *start, s32 *end) return 0; } +static int emit_paranoid_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 *thunk = (void *)__x86_indirect_its_thunk_array[reg] - 2; + +#ifdef CONFIG_MITIGATION_ITS + u8 *tmp = its_allocate_thunk(reg); + if (tmp) + thunk = tmp; +#endif + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); +} + static int cfi_rewrite_callers(s32 *start, s32 *end) { s32 *s; @@ -1477,9 +1730,14 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size); memcpy(bytes + fineibt_caller_hash, &hash, 4); - ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind); - if (WARN_ON_ONCE(ret != 3)) - continue; + if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + fineibt_paranoid_ind, 11)) { + emit_paranoid_trampoline(addr + fineibt_caller_size, + &insn, 11, bytes + fineibt_caller_size); + } else { + ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind); + if (WARN_ON_ONCE(ret != 3)) + continue; + } text_poke_early(addr, bytes, fineibt_paranoid_size); } @@ -1706,29 +1964,66 @@ Efault: return false; } +static bool is_paranoid_thunk(unsigned long addr) +{ + u32 thunk; + + __get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault); + return (thunk & 0x00FFFFFF) == 0xfd75ea; + +Efault: + return false; +} + /* * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[] - * sequence. + * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS + * thunk. */ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type) { unsigned long addr = regs->ip - fineibt_paranoid_ud; - u32 hash; - if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) + if (!cfi_paranoid) return false; - __get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault); - *target = regs->r11 + fineibt_preamble_size; - *type = regs->r10; + if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) { + *target = regs->r11 + fineibt_preamble_size; + *type = regs->r10; + + /* + * Since the trapping instruction is the exact, but LOCK prefixed, + * Jcc.d8 that got us here, the normal fixup will work. + */ + return true; + } /* - * Since the trapping instruction is the exact, but LOCK prefixed, - * Jcc.d8 that got us here, the normal fixup will work. + * The cfi_paranoid + ITS thunk combination results in: + * + * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d + * 6: 45 3b 53 f7 cmp -0x9(%r11), %r10d + * a: 4d 8d 5b f0 lea -0x10(%r11), %r11 + * e: 2e e8 XX XX XX XX cs call __x86_indirect_paranoid_thunk_r11 + * + * Where the paranoid_thunk looks like: + * + * 1d: <ea> (bad) + * __x86_indirect_paranoid_thunk_r11: + * 1e: 75 fd jne 1d + * __x86_indirect_its_thunk_r11: + * 20: 41 ff eb jmp *%r11 + * 23: cc int3 + * */ - return true; + if (is_paranoid_thunk(regs->ip)) { + *target = regs->r11 + fineibt_preamble_size; + *type = regs->r10; + + regs->ip = *target; + return true; + } -Efault: return false; } @@ -2031,6 +2326,8 @@ static noinline void __init alt_reloc_selftest(void) void __init alternative_instructions(void) { + u64 ibt; + int3_selftest(); /* @@ -2057,6 +2354,9 @@ void __init alternative_instructions(void) */ paravirt_set_cap(); + /* Keep CET-IBT disabled until caller/callee are patched */ + ibt = ibt_save(/*disable*/ true); + __apply_fineibt(__retpoline_sites, __retpoline_sites_end, __cfi_sites, __cfi_sites_end, true); @@ -2080,6 +2380,8 @@ void __init alternative_instructions(void) */ apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + ibt_restore(ibt); + #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2b36379ff675..4e06baab40bb 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -472,6 +472,11 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) case 0x60 ... 0x7f: setup_force_cpu_cap(X86_FEATURE_ZEN5); break; + case 0x50 ... 0x5f: + case 0x90 ... 0xaf: + case 0xc0 ... 0xcf: + setup_force_cpu_cap(X86_FEATURE_ZEN6); + break; default: goto warn; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 362602b705cc..8596ce85026c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); +static void __init its_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -66,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; +static void __init set_return_thunk(void *thunk) +{ + if (x86_return_thunk != __x86_return_thunk) + pr_warn("x86/bugs: return thunk changed\n"); + + x86_return_thunk = thunk; +} + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { @@ -178,6 +187,7 @@ void __init cpu_select_mitigations(void) */ srso_select_mitigation(); gds_select_mitigation(); + its_select_mitigation(); } /* @@ -1118,7 +1128,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); - x86_return_thunk = retbleed_return_thunk; + set_return_thunk(retbleed_return_thunk); if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -1153,7 +1163,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); - x86_return_thunk = call_depth_return_thunk; + set_return_thunk(call_depth_return_thunk); break; default: @@ -1188,6 +1198,145 @@ do_cmd_auto: } #undef pr_fmt +#define pr_fmt(fmt) "ITS: " fmt + +enum its_mitigation_cmd { + ITS_CMD_OFF, + ITS_CMD_ON, + ITS_CMD_VMEXIT, + ITS_CMD_RSB_STUFF, +}; + +enum its_mitigation { + ITS_MITIGATION_OFF, + ITS_MITIGATION_VMEXIT_ONLY, + ITS_MITIGATION_ALIGNED_THUNKS, + ITS_MITIGATION_RETPOLINE_STUFF, +}; + +static const char * const its_strings[] = { + [ITS_MITIGATION_OFF] = "Vulnerable", + [ITS_MITIGATION_VMEXIT_ONLY] = "Mitigation: Vulnerable, KVM: Not affected", + [ITS_MITIGATION_ALIGNED_THUNKS] = "Mitigation: Aligned branch/return thunks", + [ITS_MITIGATION_RETPOLINE_STUFF] = "Mitigation: Retpolines, Stuffing RSB", +}; + +static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS; + +static enum its_mitigation_cmd its_cmd __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF; + +static int __init its_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) { + pr_err("Mitigation disabled at compile time, ignoring option (%s)", str); + return 0; + } + + if (!strcmp(str, "off")) { + its_cmd = ITS_CMD_OFF; + } else if (!strcmp(str, "on")) { + its_cmd = ITS_CMD_ON; + } else if (!strcmp(str, "force")) { + its_cmd = ITS_CMD_ON; + setup_force_cpu_bug(X86_BUG_ITS); + } else if (!strcmp(str, "vmexit")) { + its_cmd = ITS_CMD_VMEXIT; + } else if (!strcmp(str, "stuff")) { + its_cmd = ITS_CMD_RSB_STUFF; + } else { + pr_err("Ignoring unknown indirect_target_selection option (%s).", str); + } + + return 0; +} +early_param("indirect_target_selection", its_parse_cmdline); + +static void __init its_select_mitigation(void) +{ + enum its_mitigation_cmd cmd = its_cmd; + + if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) { + its_mitigation = ITS_MITIGATION_OFF; + return; + } + + /* Retpoline+CDT mitigates ITS, bail out */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + boot_cpu_has(X86_FEATURE_CALL_DEPTH)) { + its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF; + goto out; + } + + /* Exit early to avoid irrelevant warnings */ + if (cmd == ITS_CMD_OFF) { + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (spectre_v2_enabled == SPECTRE_V2_NONE) { + pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || + !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) { + pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) { + pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + + if (cmd == ITS_CMD_RSB_STUFF && + (!boot_cpu_has(X86_FEATURE_RETPOLINE) || !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))) { + pr_err("RSB stuff mitigation not supported, using default\n"); + cmd = ITS_CMD_ON; + } + + switch (cmd) { + case ITS_CMD_OFF: + its_mitigation = ITS_MITIGATION_OFF; + break; + case ITS_CMD_VMEXIT: + if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) { + its_mitigation = ITS_MITIGATION_VMEXIT_ONLY; + goto out; + } + fallthrough; + case ITS_CMD_ON: + its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS; + if (!boot_cpu_has(X86_FEATURE_RETPOLINE)) + setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS); + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + set_return_thunk(its_return_thunk); + break; + case ITS_CMD_RSB_STUFF: + its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF; + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); + set_return_thunk(call_depth_return_thunk); + if (retbleed_mitigation == RETBLEED_MITIGATION_NONE) { + retbleed_mitigation = RETBLEED_MITIGATION_STUFF; + pr_info("Retbleed mitigation updated to stuffing\n"); + } + break; + } +out: + pr_info("%s\n", its_strings[its_mitigation]); +} + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = @@ -1697,11 +1846,11 @@ static void __init bhi_select_mitigation(void) return; } - /* Mitigate in hardware if supported */ - if (spec_ctrl_bhi_dis()) + if (!IS_ENABLED(CONFIG_X86_64)) return; - if (!IS_ENABLED(CONFIG_X86_64)) + /* Mitigate in hardware if supported */ + if (spec_ctrl_bhi_dis()) return; if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) { @@ -2607,10 +2756,10 @@ static void __init srso_select_mitigation(void) if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); - x86_return_thunk = srso_alias_return_thunk; + set_return_thunk(srso_alias_return_thunk); } else { setup_force_cpu_cap(X86_FEATURE_SRSO); - x86_return_thunk = srso_return_thunk; + set_return_thunk(srso_return_thunk); } if (has_microcode) srso_mitigation = SRSO_MITIGATION_SAFE_RET; @@ -2800,6 +2949,11 @@ static ssize_t rfds_show_state(char *buf) return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); } +static ssize_t its_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2982,6 +3136,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RFDS: return rfds_show_state(buf); + case X86_BUG_ITS: + return its_show_state(buf); + default: break; } @@ -3061,6 +3218,11 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib { return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } + +ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITS); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 12126adbc3a9..0ff057ff11ce 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1227,6 +1227,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define GDS BIT(6) /* CPU is affected by Register File Data Sampling */ #define RFDS BIT(7) +/* CPU is affected by Indirect Target Selection */ +#define ITS BIT(8) +/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */ +#define ITS_NATIVE_ONLY BIT(9) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), @@ -1238,22 +1242,25 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS), VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO), VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS), VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS), - VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS), VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS), VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS), @@ -1318,6 +1325,32 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) return cpu_matches(cpu_vuln_blacklist, RFDS); } +static bool __init vulnerable_to_its(u64 x86_arch_cap_msr) +{ + /* The "immunity" bit trumps everything else: */ + if (x86_arch_cap_msr & ARCH_CAP_ITS_NO) + return false; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + /* None of the affected CPUs have BHI_CTRL */ + if (boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + /* + * If a VMM did not expose ITS_NO, assume that a guest could + * be running on a vulnerable hardware or may migrate to such + * hardware. + */ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; + + if (cpu_matches(cpu_vuln_blacklist, ITS)) + return true; + + return false; +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); @@ -1439,9 +1472,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (vulnerable_to_rfds(x86_arch_cap_msr)) setup_force_cpu_bug(X86_BUG_RFDS); - /* When virtualized, eIBRS could be hidden, assume vulnerable */ - if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && - !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + /* + * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with + * BHI_NO still need to use the BHI mitigation to prevent Intra-mode + * attacks. When virtualized, eIBRS could be hidden, assume vulnerable. + */ + if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) && (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || boot_cpu_has(X86_FEATURE_HYPERVISOR))) setup_force_cpu_bug(X86_BUG_BHI); @@ -1449,6 +1485,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + if (vulnerable_to_its(x86_arch_cap_msr)) { + setup_force_cpu_bug(X86_BUG_ITS); + if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY)) + setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY); + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 4a10d35e70aa..96cb992d50ef 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -1098,15 +1098,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz static int __init save_microcode_in_initrd(void) { - unsigned int cpuid_1_eax = native_cpuid_eax(1); struct cpuinfo_x86 *c = &boot_cpu_data; struct cont_desc desc = { 0 }; + unsigned int cpuid_1_eax; enum ucode_state ret; struct cpio_data cp; - if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) + if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) return 0; + cpuid_1_eax = native_cpuid_eax(1); + if (!find_blobs_in_containers(&cp)) return -EINVAL; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3658d11e7b6..079f046ee26d 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -41,8 +41,8 @@ #include "internal.h" -static struct microcode_ops *microcode_ops; -bool dis_ucode_ldr = true; +static struct microcode_ops *microcode_ops; +static bool dis_ucode_ldr = false; bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV); module_param(force_minrev, bool, S_IRUSR | S_IWUSR); @@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void) u32 lvl, dummy, i; u32 *levels; + if (x86_cpuid_vendor() != X86_VENDOR_AMD) + return false; + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); levels = final_levels; @@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void) return false; } -static bool __init check_loader_disabled_bsp(void) +bool __init microcode_loader_disabled(void) { - static const char *__dis_opt_str = "dis_ucode_ldr"; - const char *cmdline = boot_command_line; - const char *option = __dis_opt_str; + if (dis_ucode_ldr) + return true; /* - * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not - * completely accurate as xen pv guests don't see that CPUID bit set but - * that's good enough as they don't land on the BSP path anyway. + * Disable when: + * + * 1) The CPU does not support CPUID. + * + * 2) Bit 31 in CPUID[1]:ECX is clear + * The bit is reserved for hypervisor use. This is still not + * completely accurate as XEN PV guests don't see that CPUID bit + * set, but that's good enough as they don't land on the BSP + * path anyway. + * + * 3) Certain AMD patch levels are not allowed to be + * overwritten. */ - if (native_cpuid_ecx(1) & BIT(31)) - return true; - - if (x86_cpuid_vendor() == X86_VENDOR_AMD) { - if (amd_check_current_patch_level()) - return true; - } - - if (cmdline_find_option_bool(cmdline, option) <= 0) - dis_ucode_ldr = false; + if (!have_cpuid_p() || + native_cpuid_ecx(1) & BIT(31) || + amd_check_current_patch_level()) + dis_ucode_ldr = true; return dis_ucode_ldr; } @@ -125,7 +130,10 @@ void __init load_ucode_bsp(void) unsigned int cpuid_1_eax; bool intel = true; - if (!have_cpuid_p()) + if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0) + dis_ucode_ldr = true; + + if (microcode_loader_disabled()) return; cpuid_1_eax = native_cpuid_eax(1); @@ -146,9 +154,6 @@ void __init load_ucode_bsp(void) return; } - if (check_loader_disabled_bsp()) - return; - if (intel) load_ucode_intel_bsp(&early_data); else @@ -159,6 +164,11 @@ void load_ucode_ap(void) { unsigned int cpuid_1_eax; + /* + * Can't use microcode_loader_disabled() here - .init section + * hell. It doesn't have to either - the BSP variant must've + * parsed cmdline already anyway. + */ if (dis_ucode_ldr) return; @@ -810,7 +820,7 @@ static int __init microcode_init(void) struct cpuinfo_x86 *c = &boot_cpu_data; int error; - if (dis_ucode_ldr) + if (microcode_loader_disabled()) return -EINVAL; if (c->x86_vendor == X86_VENDOR_INTEL) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 819199bc0119..2a397da43923 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void) if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED) return 0; - if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; uci.mc = get_microcode_blob(&uci, true); diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h index 5df621752fef..50a9702ae4e2 100644 --- a/arch/x86/kernel/cpu/microcode/internal.h +++ b/arch/x86/kernel/cpu/microcode/internal.h @@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void) return x86_family(eax); } -extern bool dis_ucode_ldr; extern bool force_minrev; #ifdef CONFIG_CPU_SUP_AMD diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cace6e8d7cc7..5eb1514af559 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(ip)) __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index de001b2146ab..375f2d7f1762 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void) *ptr = (unsigned long)ptep + PAGE_OFFSET; #ifdef CONFIG_MICROCODE_INITRD32 - /* Running on a hypervisor? */ - if (native_cpuid_ecx(1) & BIT(31)) - return; - params = (struct boot_params *)__pa_nodebug(&boot_params); if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image) return; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index a7998f351701..ff07558b7ebc 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -266,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr, ibt_endbr = s; } + its_init_mod(me); + if (retpolines || cfi) { void *rseg = NULL, *cseg = NULL; unsigned int rsize = 0, csize = 0; @@ -286,6 +288,9 @@ int module_finalize(const Elf_Ehdr *hdr, void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); } + + its_fini_mod(me); + if (returns) { void *rseg = (void *)returns->sh_addr; apply_returns(rseg, rseg + returns->sh_size); @@ -326,4 +331,5 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); + its_free_mod(mod); } diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index a59c72e77645..c3d7ff44b29a 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, break; case RET: - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(insn)) code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; @@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, case JCC: if (!func) { func = __static_call_return; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk()) func = x86_return_thunk; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index ccdc45e5b759..cda5f8362e9d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -466,10 +466,18 @@ SECTIONS } /* - * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: + * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause + * this. Let's assume that nobody will be running a COMPILE_TEST kernel and + * let's assert that fuller build coverage is more valuable than being able to + * run a COMPILE_TEST kernel. + */ +#ifndef CONFIG_COMPILE_TEST +/* + * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility: */ . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); +#endif /* needed for Clang - see arch/x86/entry/entry.S */ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); @@ -497,6 +505,16 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); "SRSO function pair won't alias"); #endif +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline"); +. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart"); +. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array"); +#endif + +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline"); +#endif + #endif /* CONFIG_X86_64 */ /* diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 050a0e229a4d..f2b36d32ef40 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { + if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) + kvm_mmu_free_obsolete_roots(vcpu); + /* * Checking root.hpa is sufficient even when KVM has mirror root. * We can have either: diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 63bb77ee1bb1..8d1b632e33d2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5974,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu); __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } +EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots); static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) @@ -7669,9 +7670,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { + struct kvm_memory_slot *slot = range->slot; + int level; + /* * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM @@ -7686,6 +7708,38 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; + if (WARN_ON_ONCE(range->end <= range->start)) + return false; + + /* + * If the head and tail pages of the range currently allow a hugepage, + * i.e. reside fully in the slot and don't have mixed attributes, then + * add each corresponding hugepage range to the ongoing invalidation, + * e.g. to prevent KVM from creating a hugepage in response to a fault + * for a gfn whose attributes aren't changing. Note, only the range + * of gfns whose attributes are being modified needs to be explicitly + * unmapped, as that will unmap any existing hugepages. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t start = gfn_round_for_level(range->start, level); + gfn_t end = gfn_round_for_level(range->end - 1, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + + if ((start != range->start || start + nr_pages > range->end) && + start >= slot->base_gfn && + start + nr_pages <= slot->base_gfn + slot->npages && + !hugepage_test_mixed(slot, start, level)) + kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages); + + if (end == start) + continue; + + if ((end + nr_pages) > range->end && + (end + nr_pages) <= (slot->base_gfn + slot->npages) && + !hugepage_test_mixed(slot, end, level)) + kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages); + } + /* Unmap the old attribute page. */ if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) range->attr_filter = KVM_FILTER_SHARED; @@ -7695,23 +7749,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, return kvm_unmap_gfn_range(kvm, range); } -static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; -} - -static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; -} -static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; -} static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long attrs) diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 699e551ec93b..9864c057187d 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) kvm_mmu_reset_context(vcpu); } +EXPORT_SYMBOL_GPL(kvm_smm_changed); void process_smi(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0bc708ee2788..a7a7dc507336 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -3173,9 +3173,14 @@ skip_vmsa_free: kvfree(svm->sev_es.ghcb_sa); } +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + static void dump_ghcb(struct vcpu_svm *svm) { - struct ghcb *ghcb = svm->sev_es.ghcb; + struct vmcb_control_area *control = &svm->vmcb->control; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ @@ -3184,18 +3189,24 @@ static void dump_ghcb(struct vcpu_svm *svm) return; } - nbits = sizeof(ghcb->save.valid_bitmap) * 8; + nbits = sizeof(svm->sev_es.valid_bitmap) * 8; - pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa); + /* + * Print KVM's snapshot of the GHCB values that were (unsuccessfully) + * used to handle the exit. If the guest has since modified the GHCB + * itself, dumping the raw GHCB won't help debug why KVM was unable to + * handle the VMGEXIT that KVM observed. + */ + pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code", - ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb)); + kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1", - ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb)); + control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2", - ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb)); + control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch", - ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb)); - pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap); + svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm)); + pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap); } static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) @@ -3266,11 +3277,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } -static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) -{ - return (((u64)control->exit_code_hi) << 32) | control->exit_code; -} - static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d5d0c5c3300b..a89c271a1951 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -607,9 +607,6 @@ static void svm_disable_virtualization_cpu(void) kvm_cpu_svm_disable(); amd_pmu_disable_virt(); - - if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) - msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); } static int svm_enable_virtualization_cpu(void) @@ -687,9 +684,6 @@ static int svm_enable_virtualization_cpu(void) rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi); } - if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) - msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); - return 0; } @@ -1518,6 +1512,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +#ifdef CONFIG_CPU_MITIGATIONS +static DEFINE_SPINLOCK(srso_lock); +static atomic_t srso_nr_vms; + +static void svm_srso_clear_bp_spec_reduce(void *ign) +{ + struct svm_cpu_data *sd = this_cpu_ptr(&svm_data); + + if (!sd->bp_spec_reduce_set) + return; + + msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); + sd->bp_spec_reduce_set = false; +} + +static void svm_srso_vm_destroy(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) + return; + + if (atomic_dec_return(&srso_nr_vms)) + return; + + guard(spinlock)(&srso_lock); + + /* + * Verify a new VM didn't come along, acquire the lock, and increment + * the count before this task acquired the lock. + */ + if (atomic_read(&srso_nr_vms)) + return; + + on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1); +} + +static void svm_srso_vm_init(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) + return; + + /* + * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0 + * transition, i.e. destroying the last VM, is fully complete, e.g. so + * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs. + */ + if (atomic_inc_not_zero(&srso_nr_vms)) + return; + + guard(spinlock)(&srso_lock); + + atomic_inc(&srso_nr_vms); +} +#else +static void svm_srso_vm_init(void) { } +static void svm_srso_vm_destroy(void) { } +#endif + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1550,6 +1601,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); + if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) && + !sd->bp_spec_reduce_set) { + sd->bp_spec_reduce_set = true; + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); + } svm->guest_state_loaded = true; } @@ -2231,6 +2287,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) */ if (!sev_es_guest(vcpu->kvm)) { clear_page(svm->vmcb); +#ifdef CONFIG_KVM_SMM + if (is_smm(vcpu)) + kvm_smm_changed(vcpu, false); +#endif kvm_vcpu_reset(vcpu, true); } @@ -5036,6 +5096,8 @@ static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); sev_vm_destroy(kvm); + + svm_srso_vm_destroy(); } static int svm_vm_init(struct kvm *kvm) @@ -5061,6 +5123,7 @@ static int svm_vm_init(struct kvm *kvm) return ret; } + svm_srso_vm_init(); return 0; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index d4490eaed55d..f16b068c4228 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -335,6 +335,8 @@ struct svm_cpu_data { u32 next_asid; u32 min_asid; + bool bp_spec_reduce_set; + struct vmcb *save_area; unsigned long save_area_pa; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index df5b99ea1f18..be7bb6d20129 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1584,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ - ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1618,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_MDS_NO; if (!boot_cpu_has_bug(X86_BUG_RFDS)) data |= ARCH_CAP_RFDS_NO; + if (!boot_cpu_has_bug(X86_BUG_ITS)) + data |= ARCH_CAP_ITS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -4597,7 +4599,7 @@ static bool kvm_is_vm_type_supported(unsigned long type) return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); } -static inline u32 kvm_sync_valid_fields(struct kvm *kvm) +static inline u64 kvm_sync_valid_fields(struct kvm *kvm) { return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS; } @@ -11493,7 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; - u32 sync_valid_fields; + u64 sync_valid_fields; int r; r = kvm_mmu_post_init_vm(vcpu->kvm); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index a26c43abd47d..39374949daa2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -367,6 +367,54 @@ SYM_FUNC_END(call_depth_return_thunk) #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ +#ifdef CONFIG_MITIGATION_ITS + +.macro ITS_THUNK reg + +/* + * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b) + * that complete the fineibt_paranoid caller sequence. + */ +1: .byte 0xea +SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + jne 1b +SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + jmp *%\reg + int3 + .align 32, 0xcc /* fill to the end of the line */ + .skip 32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */ +.endm + +/* ITS mitigation requires thunks be aligned to upper half of cacheline */ +.align 64, 0xcc +.skip 29, 0xcc + +#define GEN(reg) ITS_THUNK reg +#include <asm/GEN-for-each-reg.h> +#undef GEN + + .align 64, 0xcc +SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax) +SYM_CODE_END(__x86_indirect_its_thunk_array) + +.align 64, 0xcc +.skip 32, 0xcc +SYM_CODE_START(its_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(its_return_thunk) +EXPORT_SYMBOL(its_return_thunk) + +#endif /* CONFIG_MITIGATION_ITS */ + /* * This function name is magical and is used by -mfunction-return=thunk-extern * for the compiler to generate JMPs to it. diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ad662cc4605c..bb8d99e717b9 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -30,6 +30,7 @@ #include <linux/initrd.h> #include <linux/cpumask.h> #include <linux/gfp.h> +#include <linux/execmem.h> #include <asm/asm.h> #include <asm/bios_ebda.h> @@ -565,7 +566,7 @@ static void __init lowmem_pfn_init(void) "only %luMB highmem pages available, ignoring highmem size of %luMB!\n" #define MSG_HIGHMEM_TRIMMED \ - "Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n" + "Warning: only 4GB will be used. Support for CONFIG_HIGHMEM64G was removed!\n" /* * We have more RAM than fits into lowmem - we try to put it into * highmem, also taking the highmem=x boot parameter into account: @@ -755,6 +756,8 @@ void mark_rodata_ro(void) pr_info("Write protecting kernel text and read-only data: %luk\n", size >> 10); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; #ifdef CONFIG_CPA_DEBUG diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7c4f6f591f2b..949a447f75ec 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -34,6 +34,7 @@ #include <linux/gfp.h> #include <linux/kcore.h> #include <linux/bootmem_info.h> +#include <linux/execmem.h> #include <asm/processor.h> #include <asm/bios_ebda.h> @@ -1391,6 +1392,8 @@ void mark_rodata_ro(void) (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; /* diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index eb83348f9305..b6d6750e4bd1 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -899,8 +899,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, cond_mitigation(tsk); /* - * Let nmi_uaccess_okay() and finish_asid_transition() - * know that CR3 is changing. + * Indicate that CR3 is about to change. nmi_uaccess_okay() + * and others are sensitive to the window where mm_cpumask(), + * CR3 and cpu_tlbstate.loaded_mm are not all in sync. */ this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); barrier(); @@ -1204,8 +1205,16 @@ done: static bool should_flush_tlb(int cpu, void *data) { + struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu); struct flush_tlb_info *info = data; + /* + * Order the 'loaded_mm' and 'is_lazy' against their + * write ordering in switch_mm_irqs_off(). Ensure + * 'is_lazy' is at least as new as 'loaded_mm'. + */ + smp_rmb(); + /* Lazy TLB will get flushed at the next context switch. */ if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu)) return false; @@ -1214,8 +1223,15 @@ static bool should_flush_tlb(int cpu, void *data) if (!info->mm) return true; + /* + * While switching, the remote CPU could have state from + * either the prev or next mm. Assume the worst and flush. + */ + if (loaded_mm == LOADED_MM_SWITCHING) + return true; + /* The target mm is loaded, and the CPU is not lazy. */ - if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm) + if (loaded_mm == info->mm) return true; /* In cpumask, but not the loaded mm? Periodically remove by flushing. */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 9e5fe2ba858f..ea4dd5b393aa 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) +#define EMIT5(b1, b2, b3, b4, b5) \ + do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0) #define EMIT1_off32(b1, off) \ do { EMIT1(b1); EMIT(off, 4); } while (0) @@ -661,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { + if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) { + OPTIMIZER_HIDE_VAR(reg); + emit_jump(&prog, its_static_thunk(reg), ip); + } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { @@ -683,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (cpu_wants_rethunk()) { emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ @@ -1502,6 +1507,48 @@ static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr) #define PRIV_STACK_GUARD_SZ 8 #define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL +static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip, + struct bpf_prog *bpf_prog) +{ + u8 *prog = *pprog; + u8 *func; + + if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) { + /* The clearing sequence clobbers eax and ecx. */ + EMIT1(0x50); /* push rax */ + EMIT1(0x51); /* push rcx */ + ip += 2; + + func = (u8 *)clear_bhb_loop; + ip += x86_call_depth_emit_accounting(&prog, func, ip); + + if (emit_call(&prog, func, ip)) + return -EINVAL; + EMIT1(0x59); /* pop rcx */ + EMIT1(0x58); /* pop rax */ + } + /* Insert IBHF instruction */ + if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) && + cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) || + cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) { + /* + * Add an Indirect Branch History Fence (IBHF). IBHF acts as a + * fence preventing branch history from before the fence from + * affecting indirect branches after the fence. This is + * specifically used in cBPF jitted code to prevent Intra-mode + * BHI attacks. The IBHF instruction is designed to be a NOP on + * hardware that doesn't need or support it. The REP and REX.W + * prefixes are required by the microcode, and they also ensure + * that the NOP is unlikely to be used in existing code. + * + * IBHF is not a valid instruction in 32-bit mode. + */ + EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */ + } + *pprog = prog; + return 0; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -2544,6 +2591,13 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; + if (bpf_prog_was_classic(bpf_prog) && + !capable(CAP_SYS_ADMIN)) { + u8 *ip = image + addrs[i - 1]; + + if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog)) + return -EINVAL; + } if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h index ab5c8e47049c..9193a7790a71 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_32.h +++ b/arch/x86/um/shared/sysdep/faultinfo_32.h @@ -31,8 +31,8 @@ struct faultinfo { #define ___backtrack_faulted(_faulted) \ asm volatile ( \ - "mov $0, %0\n" \ "movl $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ "jmp _end_%=\n" \ "__get_kernel_nofault_faulted_%=:\n" \ "mov $1, %0;" \ diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h index 26fb4835d3e9..61e4ca1e0ab5 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_64.h +++ b/arch/x86/um/shared/sysdep/faultinfo_64.h @@ -31,8 +31,8 @@ struct faultinfo { #define ___backtrack_faulted(_faulted) \ asm volatile ( \ - "mov $0, %0\n" \ "movq $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ "jmp _end_%=\n" \ "__get_kernel_nofault_faulted_%=:\n" \ "mov $1, %0;" \ diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig index 91c4c4cae8a7..49f50d1bd724 100644 --- a/arch/xtensa/configs/cadence_csp_defconfig +++ b/arch/xtensa/configs/cadence_csp_defconfig @@ -1,6 +1,5 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_USELIB=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IRQ_TIME_ACCOUNTING=y diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c index e524c609be50..9c6657664792 100644 --- a/block/bio-integrity-auto.c +++ b/block/bio-integrity-auto.c @@ -9,6 +9,7 @@ * not aware of PI. */ #include <linux/blk-integrity.h> +#include <linux/t10-pi.h> #include <linux/workqueue.h> #include "blk.h" @@ -43,6 +44,29 @@ static void bio_integrity_verify_fn(struct work_struct *work) bio_endio(bio); } +#define BIP_CHECK_FLAGS (BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG) +static bool bip_should_check(struct bio_integrity_payload *bip) +{ + return bip->bip_flags & BIP_CHECK_FLAGS; +} + +static bool bi_offload_capable(struct blk_integrity *bi) +{ + switch (bi->csum_type) { + case BLK_INTEGRITY_CSUM_CRC64: + return bi->tuple_size == sizeof(struct crc64_pi_tuple); + case BLK_INTEGRITY_CSUM_CRC: + case BLK_INTEGRITY_CSUM_IP: + return bi->tuple_size == sizeof(struct t10_pi_tuple); + default: + pr_warn_once("%s: unknown integrity checksum type:%d\n", + __func__, bi->csum_type); + fallthrough; + case BLK_INTEGRITY_CSUM_NONE: + return false; + } +} + /** * __bio_integrity_endio - Integrity I/O completion function * @bio: Protected bio @@ -54,12 +78,12 @@ static void bio_integrity_verify_fn(struct work_struct *work) */ bool __bio_integrity_endio(struct bio *bio) { - struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_integrity_data *bid = container_of(bip, struct bio_integrity_data, bip); - if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) { + if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && + bip_should_check(bip)) { INIT_WORK(&bid->work, bio_integrity_verify_fn); queue_work(kintegrityd_wq, &bid->work); return false; @@ -84,6 +108,7 @@ bool bio_integrity_prep(struct bio *bio) { struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); struct bio_integrity_data *bid; + bool set_flags = true; gfp_t gfp = GFP_NOIO; unsigned int len; void *buf; @@ -100,19 +125,24 @@ bool bio_integrity_prep(struct bio *bio) switch (bio_op(bio)) { case REQ_OP_READ: - if (bi->flags & BLK_INTEGRITY_NOVERIFY) - return true; + if (bi->flags & BLK_INTEGRITY_NOVERIFY) { + if (bi_offload_capable(bi)) + return true; + set_flags = false; + } break; case REQ_OP_WRITE: - if (bi->flags & BLK_INTEGRITY_NOGENERATE) - return true; - /* * Zero the memory allocated to not leak uninitialized kernel * memory to disk for non-integrity metadata where nothing else * initializes the memory. */ - if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) + if (bi->flags & BLK_INTEGRITY_NOGENERATE) { + if (bi_offload_capable(bi)) + return true; + set_flags = false; + gfp |= __GFP_ZERO; + } else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE) gfp |= __GFP_ZERO; break; default: @@ -137,19 +167,21 @@ bool bio_integrity_prep(struct bio *bio) bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY; bip_set_seed(&bid->bip, bio->bi_iter.bi_sector); - if (bi->csum_type == BLK_INTEGRITY_CSUM_IP) - bid->bip.bip_flags |= BIP_IP_CHECKSUM; - if (bi->csum_type) - bid->bip.bip_flags |= BIP_CHECK_GUARD; - if (bi->flags & BLK_INTEGRITY_REF_TAG) - bid->bip.bip_flags |= BIP_CHECK_REFTAG; + if (set_flags) { + if (bi->csum_type == BLK_INTEGRITY_CSUM_IP) + bid->bip.bip_flags |= BIP_IP_CHECKSUM; + if (bi->csum_type) + bid->bip.bip_flags |= BIP_CHECK_GUARD; + if (bi->flags & BLK_INTEGRITY_REF_TAG) + bid->bip.bip_flags |= BIP_CHECK_REFTAG; + } if (bio_integrity_add_page(bio, virt_to_page(buf), len, offset_in_page(buf)) < len) goto err_end_io; /* Auto-generate integrity metadata if this is a write */ - if (bio_data_dir(bio) == WRITE) + if (bio_data_dir(bio) == WRITE && bip_should_check(&bid->bip)) blk_integrity_generate(bio); else bid->saved_bio_iter = bio->bi_iter; diff --git a/block/bio.c b/block/bio.c index 4e6c85a33d74..4be592d37fb6 100644 --- a/block/bio.c +++ b/block/bio.c @@ -611,7 +611,7 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask) { struct bio *bio; - if (nr_vecs > UIO_MAXIOV) + if (nr_vecs > BIO_MAX_INLINE_VECS) return NULL; return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask); } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index f1754d07f7e0..60885731e8ab 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -37,7 +37,7 @@ enum wbt_flags { WBT_TRACKED = 1, /* write, tracked for throttling */ WBT_READ = 2, /* read */ - WBT_SWAP = 4, /* write, from swap_writepage() */ + WBT_SWAP = 4, /* write, from swap_writeout() */ WBT_DISCARD = 8, /* discard */ WBT_NR_BITS = 4, /* number of bits */ diff --git a/block/blk.h b/block/blk.h index 328075787814..594eeba7b949 100644 --- a/block/blk.h +++ b/block/blk.h @@ -480,7 +480,8 @@ static inline void blk_zone_update_request_bio(struct request *rq, * the original BIO sector so that blk_zone_write_plug_bio_endio() can * lookup the zone write plug. */ - if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio)) + if (req_op(rq) == REQ_OP_ZONE_APPEND || + bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) bio->bi_iter.bi_sector = rq->__sector; } void blk_zone_write_plug_bio_endio(struct bio *bio); diff --git a/block/ioprio.c b/block/ioprio.c index 73301a261429..f0ee2798539c 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -46,12 +46,8 @@ int ioprio_check_cap(int ioprio) */ if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE)) return -EPERM; - fallthrough; - /* rt has prio field too */ - case IOPRIO_CLASS_BE: - if (level >= IOPRIO_NR_LEVELS) - return -EINVAL; break; + case IOPRIO_CLASS_BE: case IOPRIO_CLASS_IDLE: break; case IOPRIO_CLASS_NONE: diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 5498a87249d3..e3f1a4852737 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -265,10 +265,6 @@ static int hash_accept(struct socket *sock, struct socket *newsock, goto out_free_state; err = crypto_ahash_import(&ctx2->req, state); - if (err) { - sock_orphan(sk2); - sock_put(sk2); - } out_free_state: kfree_sensitive(state); diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c index f0dad0c9ce33..cd24ccd20ba6 100644 --- a/drivers/accel/ivpu/ivpu_debugfs.c +++ b/drivers/accel/ivpu/ivpu_debugfs.c @@ -455,7 +455,7 @@ priority_bands_fops_write(struct file *file, const char __user *user_buf, size_t if (ret < 0) return ret; - buf[size] = '\0'; + buf[ret] = '\0'; ret = sscanf(buf, "%u %u %u %u", &band, &grace_period, &process_grace_period, &process_quantum); if (ret != 4) diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c index ec9a3629da3a..633160470c93 100644 --- a/drivers/accel/ivpu/ivpu_hw.c +++ b/drivers/accel/ivpu/ivpu_hw.c @@ -119,7 +119,7 @@ static void timeouts_init(struct ivpu_device *vdev) else vdev->timeout.autosuspend = 100; vdev->timeout.d0i3_entry_msg = 5; - vdev->timeout.state_dump_msg = 10; + vdev->timeout.state_dump_msg = 100; } } diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 863e3cd6ace5..b28da35c30b6 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -681,8 +681,8 @@ static int ivpu_job_submit(struct ivpu_job *job, u8 priority, u32 cmdq_id) err_erase_xa: xa_erase(&vdev->submitted_jobs_xa, job->job_id); err_unlock: - mutex_unlock(&vdev->submitted_jobs_lock); mutex_unlock(&file_priv->lock); + mutex_unlock(&vdev->submitted_jobs_lock); ivpu_rpm_put(vdev); return ret; } @@ -874,15 +874,21 @@ int ivpu_cmdq_submit_ioctl(struct drm_device *dev, void *data, struct drm_file * int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct ivpu_file_priv *file_priv = file->driver_priv; + struct ivpu_device *vdev = file_priv->vdev; struct drm_ivpu_cmdq_create *args = data; struct ivpu_cmdq *cmdq; + int ret; - if (!ivpu_is_capable(file_priv->vdev, DRM_IVPU_CAP_MANAGE_CMDQ)) + if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ)) return -ENODEV; if (args->priority > DRM_IVPU_JOB_PRIORITY_REALTIME) return -EINVAL; + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; + mutex_lock(&file_priv->lock); cmdq = ivpu_cmdq_create(file_priv, ivpu_job_to_jsm_priority(args->priority), false); @@ -891,6 +897,8 @@ int ivpu_cmdq_create_ioctl(struct drm_device *dev, void *data, struct drm_file * mutex_unlock(&file_priv->lock); + ivpu_rpm_put(vdev); + return cmdq ? 0 : -ENOMEM; } @@ -900,28 +908,35 @@ int ivpu_cmdq_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file struct ivpu_device *vdev = file_priv->vdev; struct drm_ivpu_cmdq_destroy *args = data; struct ivpu_cmdq *cmdq; - u32 cmdq_id; + u32 cmdq_id = 0; int ret; if (!ivpu_is_capable(vdev, DRM_IVPU_CAP_MANAGE_CMDQ)) return -ENODEV; + ret = ivpu_rpm_get(vdev); + if (ret < 0) + return ret; + mutex_lock(&file_priv->lock); cmdq = xa_load(&file_priv->cmdq_xa, args->cmdq_id); if (!cmdq || cmdq->is_legacy) { ret = -ENOENT; - goto err_unlock; + } else { + cmdq_id = cmdq->id; + ivpu_cmdq_destroy(file_priv, cmdq); + ret = 0; } - cmdq_id = cmdq->id; - ivpu_cmdq_destroy(file_priv, cmdq); mutex_unlock(&file_priv->lock); - ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id); - return 0; -err_unlock: - mutex_unlock(&file_priv->lock); + /* Abort any pending jobs only if cmdq was destroyed */ + if (!ret) + ivpu_cmdq_abort_all_jobs(vdev, file_priv->ctx.id, cmdq_id); + + ivpu_rpm_put(vdev); + return ret; } diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c index f73ce6e13065..54676e3d82dd 100644 --- a/drivers/acpi/pptt.c +++ b/drivers/acpi/pptt.c @@ -231,16 +231,18 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr, sizeof(struct acpi_table_pptt)); proc_sz = sizeof(struct acpi_pptt_processor); - while ((unsigned long)entry + proc_sz < table_end) { + /* ignore subtable types that are smaller than a processor node */ + while ((unsigned long)entry + proc_sz <= table_end) { cpu_node = (struct acpi_pptt_processor *)entry; + if (entry->type == ACPI_PPTT_TYPE_PROCESSOR && cpu_node->parent == node_entry) return 0; if (entry->length == 0) return 0; + entry = ACPI_ADD_PTR(struct acpi_subtable_header, entry, entry->length); - } return 1; } @@ -273,15 +275,18 @@ static struct acpi_pptt_processor *acpi_find_processor_node(struct acpi_table_he proc_sz = sizeof(struct acpi_pptt_processor); /* find the processor structure associated with this cpuid */ - while ((unsigned long)entry + proc_sz < table_end) { + while ((unsigned long)entry + proc_sz <= table_end) { cpu_node = (struct acpi_pptt_processor *)entry; if (entry->length == 0) { pr_warn("Invalid zero length subtable\n"); break; } + /* entry->length may not equal proc_sz, revalidate the processor structure length */ if (entry->type == ACPI_PPTT_TYPE_PROCESSOR && acpi_cpu_id == cpu_node->acpi_processor_id && + (unsigned long)entry + entry->length <= table_end && + entry->length == proc_sz + cpu_node->number_of_priv_resources * sizeof(u32) && acpi_pptt_leaf_node(table_hdr, cpu_node)) { return (struct acpi_pptt_processor *)entry; } diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 94c6446604fc..98da8c4eea59 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -187,7 +187,7 @@ static int binderfs_binder_device_create(struct inode *ref_inode, inode_lock(d_inode(root)); /* look it up */ - dentry = lookup_one_len(name, root, name_len); + dentry = lookup_noperm(&QSTR(name), root); if (IS_ERR(dentry)) { inode_unlock(d_inode(root)); ret = PTR_ERR(dentry); @@ -487,7 +487,7 @@ static struct dentry *binderfs_create_dentry(struct dentry *parent, { struct dentry *dentry; - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_noperm(&QSTR(name), parent); if (IS_ERR(dentry)) return dentry; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index a7e511849875..50651435577c 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -600,6 +600,7 @@ CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); CPU_SHOW_VULN_FALLBACK(ghostwrite); +CPU_SHOW_VULN_FALLBACK(indirect_target_selection); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -616,6 +617,7 @@ static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NU static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); +static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -633,6 +635,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_gather_data_sampling.attr, &dev_attr_reg_file_data_sampling.attr, &dev_attr_ghostwrite.attr, + &dev_attr_indirect_target_selection.attr, NULL }; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 1813cfd0c4bd..cfccf3ff36e7 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1440,7 +1440,7 @@ static void platform_shutdown(struct device *_dev) static int platform_dma_configure(struct device *dev) { - struct platform_driver *drv = to_platform_driver(dev->driver); + struct device_driver *drv = READ_ONCE(dev->driver); struct fwnode_handle *fwnode = dev_fwnode(dev); enum dev_dma_attr attr; int ret = 0; @@ -1451,8 +1451,8 @@ static int platform_dma_configure(struct device *dev) attr = acpi_get_dma_attr(to_acpi_device_node(fwnode)); ret = acpi_dma_configure(dev, attr); } - /* @drv may not be valid when we're called from the IOMMU layer */ - if (ret || !dev->driver || drv->driver_managed_dma) + /* @dev->driver may not be valid when we're called from the IOMMU layer */ + if (ret || !drv || to_platform_driver(drv)->driver_managed_dma) return ret; ret = iommu_device_use_default_domain(dev); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 46cba261075f..e2b1f377f585 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -505,6 +505,17 @@ static void loop_assign_backing_file(struct loop_device *lo, struct file *file) lo->lo_min_dio_size = loop_query_min_dio_size(lo); } +static int loop_check_backing_file(struct file *file) +{ + if (!file->f_op->read_iter) + return -EINVAL; + + if ((file->f_mode & FMODE_WRITE) && !file->f_op->write_iter) + return -EINVAL; + + return 0; +} + /* * loop_change_fd switched the backing store of a loopback device to * a new file. This is useful for operating system installers to free up @@ -526,6 +537,10 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, if (!file) return -EBADF; + error = loop_check_backing_file(file); + if (error) + return error; + /* suppress uevents while reconfiguring the device */ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); @@ -963,6 +978,11 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, if (!file) return -EBADF; + + error = loop_check_backing_file(file); + if (error) + return error; + is_loop = is_loop_device(file); /* This is safe, since we have a reference from open(). */ diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index f9032076bc06..dc104c025cd5 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1708,7 +1708,7 @@ static void ublk_cancel_cmd(struct ublk_queue *ubq, unsigned tag, * that ublk_dispatch_req() is always called */ req = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], tag); - if (req && blk_mq_request_started(req)) + if (req && blk_mq_request_started(req) && req->tag == tag) return; spin_lock(&ubq->cancel_lock); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a42dedb78e0a..256b451bbe06 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -3014,9 +3014,8 @@ static void btusb_coredump_qca(struct hci_dev *hdev) static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb) { int ret = 0; + unsigned int skip = 0; u8 pkt_type; - u8 *sk_ptr; - unsigned int sk_len; u16 seqno; u32 dump_size; @@ -3025,18 +3024,13 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb) struct usb_device *udev = btdata->udev; pkt_type = hci_skb_pkt_type(skb); - sk_ptr = skb->data; - sk_len = skb->len; + skip = sizeof(struct hci_event_hdr); + if (pkt_type == HCI_ACLDATA_PKT) + skip += sizeof(struct hci_acl_hdr); - if (pkt_type == HCI_ACLDATA_PKT) { - sk_ptr += HCI_ACL_HDR_SIZE; - sk_len -= HCI_ACL_HDR_SIZE; - } - - sk_ptr += HCI_EVENT_HDR_SIZE; - sk_len -= HCI_EVENT_HDR_SIZE; + skb_pull(skb, skip); + dump_hdr = (struct qca_dump_hdr *)skb->data; - dump_hdr = (struct qca_dump_hdr *)sk_ptr; seqno = le16_to_cpu(dump_hdr->seqno); if (seqno == 0) { set_bit(BTUSB_HW_SSR_ACTIVE, &btdata->flags); @@ -3056,16 +3050,15 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb) btdata->qca_dump.ram_dump_size = dump_size; btdata->qca_dump.ram_dump_seqno = 0; - sk_ptr += offsetof(struct qca_dump_hdr, data0); - sk_len -= offsetof(struct qca_dump_hdr, data0); + + skb_pull(skb, offsetof(struct qca_dump_hdr, data0)); usb_disable_autosuspend(udev); bt_dev_info(hdev, "%s memdump size(%u)\n", (pkt_type == HCI_ACLDATA_PKT) ? "ACL" : "event", dump_size); } else { - sk_ptr += offsetof(struct qca_dump_hdr, data); - sk_len -= offsetof(struct qca_dump_hdr, data); + skb_pull(skb, offsetof(struct qca_dump_hdr, data)); } if (!btdata->qca_dump.ram_dump_size) { @@ -3085,7 +3078,6 @@ static int handle_dump_pkt_qca(struct hci_dev *hdev, struct sk_buff *skb) return ret; } - skb_pull(skb, skb->len - sk_len); hci_devcd_append(hdev, skb); btdata->qca_dump.ram_dump_seqno++; if (seqno == QCA_LAST_SEQUENCE_NUM) { @@ -3113,68 +3105,58 @@ out: /* Return: true if the ACL packet is a dump packet, false otherwise. */ static bool acl_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb) { - u8 *sk_ptr; - unsigned int sk_len; - struct hci_event_hdr *event_hdr; struct hci_acl_hdr *acl_hdr; struct qca_dump_hdr *dump_hdr; + struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); + bool is_dump = false; - sk_ptr = skb->data; - sk_len = skb->len; - - acl_hdr = hci_acl_hdr(skb); - if (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE) + if (!clone) return false; - sk_ptr += HCI_ACL_HDR_SIZE; - sk_len -= HCI_ACL_HDR_SIZE; - event_hdr = (struct hci_event_hdr *)sk_ptr; - - if ((event_hdr->evt != HCI_VENDOR_PKT) || - (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE))) - return false; + acl_hdr = skb_pull_data(clone, sizeof(*acl_hdr)); + if (!acl_hdr || (le16_to_cpu(acl_hdr->handle) != QCA_MEMDUMP_ACL_HANDLE)) + goto out; - sk_ptr += HCI_EVENT_HDR_SIZE; - sk_len -= HCI_EVENT_HDR_SIZE; + event_hdr = skb_pull_data(clone, sizeof(*event_hdr)); + if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT)) + goto out; - dump_hdr = (struct qca_dump_hdr *)sk_ptr; - if ((sk_len < offsetof(struct qca_dump_hdr, data)) || - (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) || - (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE)) - return false; + dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr)); + if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) || + (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE)) + goto out; - return true; + is_dump = true; +out: + consume_skb(clone); + return is_dump; } /* Return: true if the event packet is a dump packet, false otherwise. */ static bool evt_pkt_is_dump_qca(struct hci_dev *hdev, struct sk_buff *skb) { - u8 *sk_ptr; - unsigned int sk_len; - struct hci_event_hdr *event_hdr; struct qca_dump_hdr *dump_hdr; + struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); + bool is_dump = false; - sk_ptr = skb->data; - sk_len = skb->len; - - event_hdr = hci_event_hdr(skb); - - if ((event_hdr->evt != HCI_VENDOR_PKT) - || (event_hdr->plen != (sk_len - HCI_EVENT_HDR_SIZE))) + if (!clone) return false; - sk_ptr += HCI_EVENT_HDR_SIZE; - sk_len -= HCI_EVENT_HDR_SIZE; + event_hdr = skb_pull_data(clone, sizeof(*event_hdr)); + if (!event_hdr || (event_hdr->evt != HCI_VENDOR_PKT)) + goto out; - dump_hdr = (struct qca_dump_hdr *)sk_ptr; - if ((sk_len < offsetof(struct qca_dump_hdr, data)) || - (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) || - (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE)) - return false; + dump_hdr = skb_pull_data(clone, sizeof(*dump_hdr)); + if (!dump_hdr || (dump_hdr->vse_class != QCA_MEMDUMP_VSE_CLASS) || + (dump_hdr->msg_type != QCA_MEMDUMP_MSG_TYPE)) + goto out; - return true; + is_dump = true; +out: + consume_skb(clone); + return is_dump; } static int btusb_recv_acl_qca(struct hci_dev *hdev, struct sk_buff *skb) diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c index e49a19fea3bd..dc882fc9fa9e 100644 --- a/drivers/char/tpm/tpm-buf.c +++ b/drivers/char/tpm/tpm-buf.c @@ -201,7 +201,7 @@ static void tpm_buf_read(struct tpm_buf *buf, off_t *offset, size_t count, void */ u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset) { - u8 value; + u8 value = 0; tpm_buf_read(buf, offset, sizeof(value), &value); @@ -218,7 +218,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u8); */ u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset) { - u16 value; + u16 value = 0; tpm_buf_read(buf, offset, sizeof(value), &value); @@ -235,7 +235,7 @@ EXPORT_SYMBOL_GPL(tpm_buf_read_u16); */ u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset) { - u32 value; + u32 value = 0; tpm_buf_read(buf, offset, sizeof(value), &value); diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 3f89635ba5e8..7b5049b3d476 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -40,11 +40,6 @@ * * These are the usage functions: * - * tpm2_start_auth_session() which allocates the opaque auth structure - * and gets a session from the TPM. This must be called before - * any of the following functions. The session is protected by a - * session_key which is derived from a random salt value - * encrypted to the NULL seed. * tpm2_end_auth_session() kills the session and frees the resources. * Under normal operation this function is done by * tpm_buf_check_hmac_response(), so this is only to be used on @@ -963,16 +958,13 @@ err: } /** - * tpm2_start_auth_session() - create a HMAC authentication session with the TPM - * @chip: the TPM chip structure to create the session with + * tpm2_start_auth_session() - Create an a HMAC authentication session + * @chip: A TPM chip * - * This function loads the NULL seed from its saved context and starts - * an authentication session on the null seed, fills in the - * @chip->auth structure to contain all the session details necessary - * for performing the HMAC, encrypt and decrypt operations and - * returns. The NULL seed is flushed before this function returns. + * Loads the ephemeral key (null seed), and starts an HMAC authenticated + * session. The null seed is flushed before the return. * - * Return: zero on success or actual error encountered. + * Returns zero on success, or a POSIX error code. */ int tpm2_start_auth_session(struct tpm_chip *chip) { @@ -1024,7 +1016,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip) /* hash algorithm for session */ tpm_buf_append_u16(&buf, TPM_ALG_SHA256); - rc = tpm_transmit_cmd(chip, &buf, 0, "start auth session"); + rc = tpm_ret_to_err(tpm_transmit_cmd(chip, &buf, 0, "StartAuthSession")); tpm2_flush_context(chip, null_key); if (rc == TPM2_RC_SUCCESS) diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index 970d02c337c7..6c3aa480396b 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -54,7 +54,7 @@ enum tis_int_flags { enum tis_defaults { TIS_MEM_LEN = 0x5000, TIS_SHORT_TIMEOUT = 750, /* ms */ - TIS_LONG_TIMEOUT = 2000, /* 2 sec */ + TIS_LONG_TIMEOUT = 4000, /* 4 secs */ TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */ TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */ }; diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c index 014db6386624..8ddf3a9a53df 100644 --- a/drivers/clk/clk-s2mps11.c +++ b/drivers/clk/clk-s2mps11.c @@ -137,6 +137,8 @@ static int s2mps11_clk_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; + clk_data->num = S2MPS11_CLKS_NUM; + switch (hwid) { case S2MPS11X: s2mps11_reg = S2MPS11_REG_RTC_CTRL; @@ -186,7 +188,6 @@ static int s2mps11_clk_probe(struct platform_device *pdev) clk_data->hws[i] = &s2mps11_clks[i].hw; } - clk_data->num = S2MPS11_CLKS_NUM; of_clk_add_hw_provider(s2mps11_clks->clk_np, of_clk_hw_onecell_get, clk_data); diff --git a/drivers/clk/rockchip/clk-rk3576.c b/drivers/clk/rockchip/clk-rk3576.c index 595e010341f7..be703f250197 100644 --- a/drivers/clk/rockchip/clk-rk3576.c +++ b/drivers/clk/rockchip/clk-rk3576.c @@ -541,6 +541,8 @@ static struct rockchip_clk_branch rk3576_clk_branches[] __initdata = { RK3576_CLKGATE_CON(5), 14, GFLAGS), GATE(CLK_OTPC_AUTO_RD_G, "clk_otpc_auto_rd_g", "xin24m", 0, RK3576_CLKGATE_CON(5), 15, GFLAGS), + GATE(CLK_OTP_PHY_G, "clk_otp_phy_g", "xin24m", 0, + RK3576_CLKGATE_CON(6), 0, GFLAGS), COMPOSITE(CLK_MIPI_CAMERAOUT_M0, "clk_mipi_cameraout_m0", mux_24m_spll_gpll_cpll_p, 0, RK3576_CLKSEL_CON(38), 8, 2, MFLAGS, 0, 8, DFLAGS, RK3576_CLKGATE_CON(6), 3, GFLAGS), diff --git a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c index bb66c906ebbb..e83d4fd40240 100644 --- a/drivers/clk/sunxi-ng/ccu-sun20i-d1.c +++ b/drivers/clk/sunxi-ng/ccu-sun20i-d1.c @@ -412,19 +412,23 @@ static const struct clk_parent_data mmc0_mmc1_parents[] = { { .hw = &pll_periph0_2x_clk.common.hw }, { .hw = &pll_audio1_div2_clk.common.hw }, }; -static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc0_clk, "mmc0", mmc0_mmc1_parents, 0x830, - 0, 4, /* M */ - 8, 2, /* P */ - 24, 3, /* mux */ - BIT(31), /* gate */ - 0); - -static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc1_clk, "mmc1", mmc0_mmc1_parents, 0x834, - 0, 4, /* M */ - 8, 2, /* P */ - 24, 3, /* mux */ - BIT(31), /* gate */ - 0); +static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc0_clk, "mmc0", + mmc0_mmc1_parents, 0x830, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); + +static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc1_clk, "mmc1", + mmc0_mmc1_parents, 0x834, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); static const struct clk_parent_data mmc2_parents[] = { { .fw_name = "hosc" }, @@ -433,12 +437,14 @@ static const struct clk_parent_data mmc2_parents[] = { { .hw = &pll_periph0_800M_clk.common.hw }, { .hw = &pll_audio1_div2_clk.common.hw }, }; -static SUNXI_CCU_MP_DATA_WITH_MUX_GATE(mmc2_clk, "mmc2", mmc2_parents, 0x838, - 0, 4, /* M */ - 8, 2, /* P */ - 24, 3, /* mux */ - BIT(31), /* gate */ - 0); +static SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(mmc2_clk, "mmc2", mmc2_parents, + 0x838, + 0, 4, /* M */ + 8, 2, /* P */ + 24, 3, /* mux */ + BIT(31), /* gate */ + 2, /* post-div */ + 0); static SUNXI_CCU_GATE_HWS(bus_mmc0_clk, "bus-mmc0", psi_ahb_hws, 0x84c, BIT(0), 0); diff --git a/drivers/clk/sunxi-ng/ccu_mp.h b/drivers/clk/sunxi-ng/ccu_mp.h index b35aeec70484..bb09c649bfa3 100644 --- a/drivers/clk/sunxi-ng/ccu_mp.h +++ b/drivers/clk/sunxi-ng/ccu_mp.h @@ -52,6 +52,28 @@ struct ccu_mp { } \ } +#define SUNXI_CCU_MP_DATA_WITH_MUX_GATE_POSTDIV(_struct, _name, _parents, \ + _reg, \ + _mshift, _mwidth, \ + _pshift, _pwidth, \ + _muxshift, _muxwidth, \ + _gate, _postdiv, _flags)\ + struct ccu_mp _struct = { \ + .enable = _gate, \ + .m = _SUNXI_CCU_DIV(_mshift, _mwidth), \ + .p = _SUNXI_CCU_DIV(_pshift, _pwidth), \ + .mux = _SUNXI_CCU_MUX(_muxshift, _muxwidth), \ + .fixed_post_div = _postdiv, \ + .common = { \ + .reg = _reg, \ + .features = CCU_FEATURE_FIXED_POSTDIV, \ + .hw.init = CLK_HW_INIT_PARENTS_DATA(_name, \ + _parents, \ + &ccu_mp_ops, \ + _flags), \ + } \ + } + #define SUNXI_CCU_MP_WITH_MUX_GATE(_struct, _name, _parents, _reg, \ _mshift, _mwidth, \ _pshift, _pwidth, \ @@ -109,8 +131,7 @@ struct ccu_mp { _mshift, _mwidth, \ _pshift, _pwidth, \ _muxshift, _muxwidth, \ - _gate, _features, \ - _flags) \ + _gate, _flags, _features) \ struct ccu_mp _struct = { \ .enable = _gate, \ .m = _SUNXI_CCU_DIV(_mshift, _mwidth), \ diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 39f7c2d736d1..b603c25f3dfa 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void) #ifdef CONFIG_CLKEVT_I8253 void clockevent_i8253_disable(void) { - raw_spin_lock(&i8253_lock); + guard(raw_spinlock_irqsave)(&i8253_lock); /* * Writing the MODE register should stop the counter, according to @@ -132,8 +132,6 @@ void clockevent_i8253_disable(void) outb_p(0, PIT_CH0); outb_p(0x30, PIT_MODE); - - raw_spin_unlock(&i8253_lock); } static int pit_shutdown(struct clock_event_device *evt) diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 5f8d010516f0..b1ef4546346d 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -320,8 +320,9 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, count++; dma_resv_list_set(fobj, i, fence, usage); - /* pointer update must be visible before we extend the num_fences */ - smp_store_mb(fobj->num_fences, count); + /* fence update must be visible before we extend the num_fences */ + smp_wmb(); + fobj->num_fences = count; } EXPORT_SYMBOL(dma_resv_add_fence); diff --git a/drivers/dma/amd/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c index 715ac3ae067b..81339664036f 100644 --- a/drivers/dma/amd/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c @@ -342,6 +342,9 @@ static void pt_cmd_callback_work(void *data, int err) struct pt_dma_chan *chan; unsigned long flags; + if (!desc) + return; + dma_chan = desc->vd.tx.chan; chan = to_pt_chan(dma_chan); @@ -355,16 +358,14 @@ static void pt_cmd_callback_work(void *data, int err) desc->status = DMA_ERROR; spin_lock_irqsave(&chan->vc.lock, flags); - if (desc) { - if (desc->status != DMA_COMPLETE) { - if (desc->status != DMA_ERROR) - desc->status = DMA_COMPLETE; + if (desc->status != DMA_COMPLETE) { + if (desc->status != DMA_ERROR) + desc->status = DMA_COMPLETE; - dma_cookie_complete(tx_desc); - dma_descriptor_unmap(tx_desc); - } else { - tx_desc = NULL; - } + dma_cookie_complete(tx_desc); + dma_descriptor_unmap(tx_desc); + } else { + tx_desc = NULL; } spin_unlock_irqrestore(&chan->vc.lock, flags); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index d891dfca358e..91b2fbc0b864 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -841,9 +841,9 @@ static int dmatest_func(void *data) } else { dma_async_issue_pending(chan); - wait_event_timeout(thread->done_wait, - done->done, - msecs_to_jiffies(params->timeout)); + wait_event_freezable_timeout(thread->done_wait, + done->done, + msecs_to_jiffies(params->timeout)); status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 756d67325db5..66bfa28d984e 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -57,7 +57,7 @@ static irqreturn_t fsl_edma3_tx_handler(int irq, void *dev_id) intr = edma_readl_chreg(fsl_chan, ch_int); if (!intr) - return IRQ_HANDLED; + return IRQ_NONE; edma_writel_chreg(fsl_chan, 1, ch_int); diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index ff94ee892339..6d12033649f8 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -222,7 +222,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) struct idxd_wq *wq; struct device *dev, *fdev; int rc = 0; - struct iommu_sva *sva; + struct iommu_sva *sva = NULL; unsigned int pasid; struct idxd_cdev *idxd_cdev; @@ -317,7 +317,7 @@ failed_set_pasid: if (device_user_pasid_enabled(idxd)) idxd_xa_pasid_remove(ctx); failed_get_pasid: - if (device_user_pasid_enabled(idxd)) + if (device_user_pasid_enabled(idxd) && !IS_ERR_OR_NULL(sva)) iommu_sva_unbind_device(sva); failed: mutex_unlock(&wq->wq_lock); @@ -407,6 +407,9 @@ static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma) if (!idxd->user_submission_safe && !capable(CAP_SYS_RAWIO)) return -EPERM; + if (current->mm != ctx->mm) + return -EPERM; + rc = check_vma(wq, vma, __func__); if (rc < 0) return rc; @@ -473,6 +476,9 @@ static ssize_t idxd_cdev_write(struct file *filp, const char __user *buf, size_t ssize_t written = 0; int i; + if (current->mm != ctx->mm) + return -EPERM; + for (i = 0; i < len/sizeof(struct dsa_hw_desc); i++) { int rc = idxd_submit_user_descriptor(ctx, udesc + i); @@ -493,6 +499,9 @@ static __poll_t idxd_cdev_poll(struct file *filp, struct idxd_device *idxd = wq->idxd; __poll_t out = 0; + if (current->mm != ctx->mm) + return POLLNVAL; + poll_wait(filp, &wq->err_queue, wait); spin_lock(&idxd->dev_lock); if (idxd->sw_err.valid) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index fca1d2924999..760b7d81fcd8 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -155,6 +155,25 @@ static void idxd_cleanup_interrupts(struct idxd_device *idxd) pci_free_irq_vectors(pdev); } +static void idxd_clean_wqs(struct idxd_device *idxd) +{ + struct idxd_wq *wq; + struct device *conf_dev; + int i; + + for (i = 0; i < idxd->max_wqs; i++) { + wq = idxd->wqs[i]; + if (idxd->hw.wq_cap.op_config) + bitmap_free(wq->opcap_bmap); + kfree(wq->wqcfg); + conf_dev = wq_confdev(wq); + put_device(conf_dev); + kfree(wq); + } + bitmap_free(idxd->wq_enable_map); + kfree(idxd->wqs); +} + static int idxd_setup_wqs(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; @@ -169,8 +188,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd) idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev)); if (!idxd->wq_enable_map) { - kfree(idxd->wqs); - return -ENOMEM; + rc = -ENOMEM; + goto err_bitmap; } for (i = 0; i < idxd->max_wqs; i++) { @@ -189,10 +208,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd) conf_dev->bus = &dsa_bus_type; conf_dev->type = &idxd_wq_device_type; rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id); - if (rc < 0) { - put_device(conf_dev); + if (rc < 0) goto err; - } mutex_init(&wq->wq_lock); init_waitqueue_head(&wq->err_queue); @@ -203,7 +220,6 @@ static int idxd_setup_wqs(struct idxd_device *idxd) wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); if (!wq->wqcfg) { - put_device(conf_dev); rc = -ENOMEM; goto err; } @@ -211,9 +227,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd) if (idxd->hw.wq_cap.op_config) { wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL); if (!wq->opcap_bmap) { - put_device(conf_dev); rc = -ENOMEM; - goto err; + goto err_opcap_bmap; } bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); } @@ -224,15 +239,46 @@ static int idxd_setup_wqs(struct idxd_device *idxd) return 0; - err: +err_opcap_bmap: + kfree(wq->wqcfg); + +err: + put_device(conf_dev); + kfree(wq); + while (--i >= 0) { wq = idxd->wqs[i]; + if (idxd->hw.wq_cap.op_config) + bitmap_free(wq->opcap_bmap); + kfree(wq->wqcfg); conf_dev = wq_confdev(wq); put_device(conf_dev); + kfree(wq); + } + bitmap_free(idxd->wq_enable_map); + +err_bitmap: + kfree(idxd->wqs); + return rc; } +static void idxd_clean_engines(struct idxd_device *idxd) +{ + struct idxd_engine *engine; + struct device *conf_dev; + int i; + + for (i = 0; i < idxd->max_engines; i++) { + engine = idxd->engines[i]; + conf_dev = engine_confdev(engine); + put_device(conf_dev); + kfree(engine); + } + kfree(idxd->engines); +} + static int idxd_setup_engines(struct idxd_device *idxd) { struct idxd_engine *engine; @@ -263,6 +309,7 @@ static int idxd_setup_engines(struct idxd_device *idxd) rc = dev_set_name(conf_dev, "engine%d.%d", idxd->id, engine->id); if (rc < 0) { put_device(conf_dev); + kfree(engine); goto err; } @@ -276,10 +323,26 @@ static int idxd_setup_engines(struct idxd_device *idxd) engine = idxd->engines[i]; conf_dev = engine_confdev(engine); put_device(conf_dev); + kfree(engine); } + kfree(idxd->engines); + return rc; } +static void idxd_clean_groups(struct idxd_device *idxd) +{ + struct idxd_group *group; + int i; + + for (i = 0; i < idxd->max_groups; i++) { + group = idxd->groups[i]; + put_device(group_confdev(group)); + kfree(group); + } + kfree(idxd->groups); +} + static int idxd_setup_groups(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; @@ -310,6 +373,7 @@ static int idxd_setup_groups(struct idxd_device *idxd) rc = dev_set_name(conf_dev, "group%d.%d", idxd->id, group->id); if (rc < 0) { put_device(conf_dev); + kfree(group); goto err; } @@ -334,20 +398,18 @@ static int idxd_setup_groups(struct idxd_device *idxd) while (--i >= 0) { group = idxd->groups[i]; put_device(group_confdev(group)); + kfree(group); } + kfree(idxd->groups); + return rc; } static void idxd_cleanup_internals(struct idxd_device *idxd) { - int i; - - for (i = 0; i < idxd->max_groups; i++) - put_device(group_confdev(idxd->groups[i])); - for (i = 0; i < idxd->max_engines; i++) - put_device(engine_confdev(idxd->engines[i])); - for (i = 0; i < idxd->max_wqs; i++) - put_device(wq_confdev(idxd->wqs[i])); + idxd_clean_groups(idxd); + idxd_clean_engines(idxd); + idxd_clean_wqs(idxd); destroy_workqueue(idxd->wq); } @@ -390,7 +452,7 @@ static int idxd_init_evl(struct idxd_device *idxd) static int idxd_setup_internals(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; - int rc, i; + int rc; init_waitqueue_head(&idxd->cmd_waitq); @@ -421,14 +483,11 @@ static int idxd_setup_internals(struct idxd_device *idxd) err_evl: destroy_workqueue(idxd->wq); err_wkq_create: - for (i = 0; i < idxd->max_groups; i++) - put_device(group_confdev(idxd->groups[i])); + idxd_clean_groups(idxd); err_group: - for (i = 0; i < idxd->max_engines; i++) - put_device(engine_confdev(idxd->engines[i])); + idxd_clean_engines(idxd); err_engine: - for (i = 0; i < idxd->max_wqs; i++) - put_device(wq_confdev(idxd->wqs[i])); + idxd_clean_wqs(idxd); err_wqs: return rc; } @@ -528,6 +587,17 @@ static void idxd_read_caps(struct idxd_device *idxd) idxd->hw.iaa_cap.bits = ioread64(idxd->reg_base + IDXD_IAACAP_OFFSET); } +static void idxd_free(struct idxd_device *idxd) +{ + if (!idxd) + return; + + put_device(idxd_confdev(idxd)); + bitmap_free(idxd->opcap_bmap); + ida_free(&idxd_ida, idxd->id); + kfree(idxd); +} + static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data) { struct device *dev = &pdev->dev; @@ -545,28 +615,34 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d idxd_dev_set_type(&idxd->idxd_dev, idxd->data->type); idxd->id = ida_alloc(&idxd_ida, GFP_KERNEL); if (idxd->id < 0) - return NULL; + goto err_ida; idxd->opcap_bmap = bitmap_zalloc_node(IDXD_MAX_OPCAP_BITS, GFP_KERNEL, dev_to_node(dev)); - if (!idxd->opcap_bmap) { - ida_free(&idxd_ida, idxd->id); - return NULL; - } + if (!idxd->opcap_bmap) + goto err_opcap; device_initialize(conf_dev); conf_dev->parent = dev; conf_dev->bus = &dsa_bus_type; conf_dev->type = idxd->data->dev_type; rc = dev_set_name(conf_dev, "%s%d", idxd->data->name_prefix, idxd->id); - if (rc < 0) { - put_device(conf_dev); - return NULL; - } + if (rc < 0) + goto err_name; spin_lock_init(&idxd->dev_lock); spin_lock_init(&idxd->cmd_lock); return idxd; + +err_name: + put_device(conf_dev); + bitmap_free(idxd->opcap_bmap); +err_opcap: + ida_free(&idxd_ida, idxd->id); +err_ida: + kfree(idxd); + + return NULL; } static int idxd_enable_system_pasid(struct idxd_device *idxd) @@ -1190,7 +1266,7 @@ int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev, err: pci_iounmap(pdev, idxd->reg_base); err_iomap: - put_device(idxd_confdev(idxd)); + idxd_free(idxd); err_idxd_alloc: pci_disable_device(pdev); return rc; @@ -1232,7 +1308,6 @@ static void idxd_shutdown(struct pci_dev *pdev) static void idxd_remove(struct pci_dev *pdev) { struct idxd_device *idxd = pci_get_drvdata(pdev); - struct idxd_irq_entry *irq_entry; idxd_unregister_devices(idxd); /* @@ -1245,20 +1320,12 @@ static void idxd_remove(struct pci_dev *pdev) get_device(idxd_confdev(idxd)); device_unregister(idxd_confdev(idxd)); idxd_shutdown(pdev); - if (device_pasid_enabled(idxd)) - idxd_disable_system_pasid(idxd); idxd_device_remove_debugfs(idxd); - - irq_entry = idxd_get_ie(idxd, 0); - free_irq(irq_entry->vector, irq_entry); - pci_free_irq_vectors(pdev); + idxd_cleanup(idxd); pci_iounmap(pdev, idxd->reg_base); - if (device_user_pasid_enabled(idxd)) - idxd_disable_sva(pdev); - pci_disable_device(pdev); - destroy_workqueue(idxd->wq); - perfmon_pmu_remove(idxd); put_device(idxd_confdev(idxd)); + idxd_free(idxd); + pci_disable_device(pdev); } static struct pci_driver idxd_pci_driver = { diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c index d5ddb4e30e71..47c8adfdc155 100644 --- a/drivers/dma/mediatek/mtk-cqdma.c +++ b/drivers/dma/mediatek/mtk-cqdma.c @@ -420,15 +420,11 @@ static struct virt_dma_desc *mtk_cqdma_find_active_desc(struct dma_chan *c, { struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c); struct virt_dma_desc *vd; - unsigned long flags; - spin_lock_irqsave(&cvc->pc->lock, flags); list_for_each_entry(vd, &cvc->pc->queue, node) if (vd->tx.cookie == cookie) { - spin_unlock_irqrestore(&cvc->pc->lock, flags); return vd; } - spin_unlock_irqrestore(&cvc->pc->lock, flags); list_for_each_entry(vd, &cvc->vc.desc_issued, node) if (vd->tx.cookie == cookie) @@ -452,9 +448,11 @@ static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c, if (ret == DMA_COMPLETE || !txstate) return ret; + spin_lock_irqsave(&cvc->pc->lock, flags); spin_lock_irqsave(&cvc->vc.lock, flags); vd = mtk_cqdma_find_active_desc(c, cookie); spin_unlock_irqrestore(&cvc->vc.lock, flags); + spin_unlock_irqrestore(&cvc->pc->lock, flags); if (vd) { cvd = to_cqdma_vdesc(vd); diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index b223a7aacb0c..b6255c0601bb 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -1091,8 +1091,11 @@ static void udma_check_tx_completion(struct work_struct *work) u32 residue_diff; ktime_t time_diff; unsigned long delay; + unsigned long flags; while (1) { + spin_lock_irqsave(&uc->vc.lock, flags); + if (uc->desc) { /* Get previous residue and time stamp */ residue_diff = uc->tx_drain.residue; @@ -1127,6 +1130,8 @@ static void udma_check_tx_completion(struct work_struct *work) break; } + spin_unlock_irqrestore(&uc->vc.lock, flags); + usleep_range(ktime_to_us(delay), ktime_to_us(delay) + 10); continue; @@ -1143,6 +1148,8 @@ static void udma_check_tx_completion(struct work_struct *work) break; } + + spin_unlock_irqrestore(&uc->vc.lock, flags); } static irqreturn_t udma_ring_irq_handler(int irq, void *data) @@ -4246,7 +4253,6 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec, struct of_dma *ofdma) { struct udma_dev *ud = ofdma->of_dma_data; - dma_cap_mask_t mask = ud->ddev.cap_mask; struct udma_filter_param filter_param; struct dma_chan *chan; @@ -4278,7 +4284,7 @@ static struct dma_chan *udma_of_xlate(struct of_phandle_args *dma_spec, } } - chan = __dma_request_channel(&mask, udma_dma_filter_fn, &filter_param, + chan = __dma_request_channel(&ud->ddev.cap_mask, udma_dma_filter_fn, &filter_param, ofdma->of_node); if (!chan) { dev_err(ud->dev, "get channel fail in %s.\n", __func__); diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 19295282de24..fe55613a8ea9 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -299,7 +299,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, import_uuid(&buf->uuid, (u8 *)&rx_buf->uuid); } - ffa_rx_release(); + if (!(flags & PARTITION_INFO_GET_RETURN_COUNT_ONLY)) + ffa_rx_release(); mutex_unlock(&drv_info->rx_lock); diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 7af01664ce7e..3a5474015f7d 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -255,6 +255,9 @@ static struct scmi_device *scmi_child_dev_find(struct device *parent, if (!dev) return NULL; + /* Drop the refcnt bumped implicitly by device_find_child */ + put_device(dev); + return to_scmi_dev(dev); } diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 1c75a4c9c371..0390d5ff195e 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1248,7 +1248,8 @@ static void xfer_put(const struct scmi_protocol_handle *ph, } static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo, - struct scmi_xfer *xfer, ktime_t stop) + struct scmi_xfer *xfer, ktime_t stop, + bool *ooo) { struct scmi_info *info = handle_to_scmi_info(cinfo->handle); @@ -1257,7 +1258,7 @@ static bool scmi_xfer_done_no_timeout(struct scmi_chan_info *cinfo, * in case of out-of-order receptions of delayed responses */ return info->desc->ops->poll_done(cinfo, xfer) || - try_wait_for_completion(&xfer->done) || + (*ooo = try_wait_for_completion(&xfer->done)) || ktime_after(ktime_get(), stop); } @@ -1274,15 +1275,17 @@ static int scmi_wait_for_reply(struct device *dev, const struct scmi_desc *desc, * itself to support synchronous commands replies. */ if (!desc->sync_cmds_completed_on_ret) { + bool ooo = false; + /* * Poll on xfer using transport provided .poll_done(); * assumes no completion interrupt was available. */ ktime_t stop = ktime_add_ms(ktime_get(), timeout_ms); - spin_until_cond(scmi_xfer_done_no_timeout(cinfo, - xfer, stop)); - if (ktime_after(ktime_get(), stop)) { + spin_until_cond(scmi_xfer_done_no_timeout(cinfo, xfer, + stop, &ooo)); + if (!ooo && !info->desc->ops->poll_done(cinfo, xfer)) { dev_err(dev, "timed out in resp(caller: %pS) - polling\n", (void *)_RET_IP_); diff --git a/drivers/firmware/samsung/exynos-acpm.c b/drivers/firmware/samsung/exynos-acpm.c index a85b2dbdd9f0..15e991b99f5a 100644 --- a/drivers/firmware/samsung/exynos-acpm.c +++ b/drivers/firmware/samsung/exynos-acpm.c @@ -185,6 +185,29 @@ struct acpm_match_data { #define handle_to_acpm_info(h) container_of(h, struct acpm_info, handle) /** + * acpm_get_saved_rx() - get the response if it was already saved. + * @achan: ACPM channel info. + * @xfer: reference to the transfer to get response for. + * @tx_seqnum: xfer TX sequence number. + */ +static void acpm_get_saved_rx(struct acpm_chan *achan, + const struct acpm_xfer *xfer, u32 tx_seqnum) +{ + const struct acpm_rx_data *rx_data = &achan->rx_data[tx_seqnum - 1]; + u32 rx_seqnum; + + if (!rx_data->response) + return; + + rx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, rx_data->cmd[0]); + + if (rx_seqnum == tx_seqnum) { + memcpy(xfer->rxd, rx_data->cmd, xfer->rxlen); + clear_bit(rx_seqnum - 1, achan->bitmap_seqnum); + } +} + +/** * acpm_get_rx() - get response from RX queue. * @achan: ACPM channel info. * @xfer: reference to the transfer to get response for. @@ -204,15 +227,16 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer) rx_front = readl(achan->rx.front); i = readl(achan->rx.rear); - /* Bail out if RX is empty. */ - if (i == rx_front) + tx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, xfer->txd[0]); + + if (i == rx_front) { + acpm_get_saved_rx(achan, xfer, tx_seqnum); return 0; + } base = achan->rx.base; mlen = achan->mlen; - tx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, xfer->txd[0]); - /* Drain RX queue. */ do { /* Read RX seqnum. */ @@ -259,16 +283,8 @@ static int acpm_get_rx(struct acpm_chan *achan, const struct acpm_xfer *xfer) * If the response was not in this iteration of the queue, check if the * RX data was previously saved. */ - rx_data = &achan->rx_data[tx_seqnum - 1]; - if (!rx_set && rx_data->response) { - rx_seqnum = FIELD_GET(ACPM_PROTOCOL_SEQNUM, - rx_data->cmd[0]); - - if (rx_seqnum == tx_seqnum) { - memcpy(xfer->rxd, rx_data->cmd, xfer->rxlen); - clear_bit(rx_seqnum - 1, achan->bitmap_seqnum); - } - } + if (!rx_set) + acpm_get_saved_rx(achan, xfer, tx_seqnum); return 0; } diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 442435ded020..13cc120cf11f 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -1204,6 +1204,8 @@ static int pca953x_restore_context(struct pca953x_chip *chip) guard(mutex)(&chip->i2c_lock); + if (chip->client->irq > 0) + enable_irq(chip->client->irq); regcache_cache_only(chip->regmap, false); regcache_mark_dirty(chip->regmap); ret = pca953x_regcache_sync(chip); @@ -1216,6 +1218,10 @@ static int pca953x_restore_context(struct pca953x_chip *chip) static void pca953x_save_context(struct pca953x_chip *chip) { guard(mutex)(&chip->i2c_lock); + + /* Disable IRQ to prevent early triggering while regmap "cache only" is on */ + if (chip->client->irq > 0) + disable_irq(chip->client->irq); regcache_cache_only(chip->regmap, true); } diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c index 13407fd4f0eb..eab6726953b4 100644 --- a/drivers/gpio/gpio-virtuser.c +++ b/drivers/gpio/gpio-virtuser.c @@ -401,10 +401,15 @@ static ssize_t gpio_virtuser_direction_do_write(struct file *file, char buf[32], *trimmed; int ret, dir, val = 0; - ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count); + if (count >= sizeof(buf)) + return -EINVAL; + + ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count); if (ret < 0) return ret; + buf[ret] = '\0'; + trimmed = strim(buf); if (strcmp(trimmed, "input") == 0) { @@ -623,12 +628,15 @@ static ssize_t gpio_virtuser_consumer_write(struct file *file, char buf[GPIO_VIRTUSER_NAME_BUF_LEN + 2]; int ret; + if (count >= sizeof(buf)) + return -EINVAL; + ret = simple_write_to_buffer(buf, GPIO_VIRTUSER_NAME_BUF_LEN, ppos, user_buf, count); if (ret < 0) return ret; - buf[strlen(buf) - 1] = '\0'; + buf[ret] = '\0'; ret = gpiod_set_consumer_name(data->ad.desc, buf); if (ret) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index cd4fecbb41f2..113c5d90f2df 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -742,6 +742,12 @@ EXPORT_SYMBOL_GPL(gpiochip_query_valid_mask); bool gpiochip_line_is_valid(const struct gpio_chip *gc, unsigned int offset) { + /* + * hog pins are requested before registering GPIO chip + */ + if (!gc->gpiodev) + return true; + /* No mask means all valid */ if (likely(!gc->gpiodev->valid_mask)) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index ef6e78224fdf..c3641331d4de 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1614,11 +1614,9 @@ static inline void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_cap #if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev); bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev); -void amdgpu_choose_low_power_state(struct amdgpu_device *adev); #else static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; } static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; } -static inline void amdgpu_choose_low_power_state(struct amdgpu_device *adev) { } #endif void amdgpu_register_gpu_instance(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index b7f8f2ff143d..707e131f89d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1533,22 +1533,4 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) #endif /* CONFIG_AMD_PMC */ } -/** - * amdgpu_choose_low_power_state - * - * @adev: amdgpu_device_pointer - * - * Choose the target low power state for the GPU - */ -void amdgpu_choose_low_power_state(struct amdgpu_device *adev) -{ - if (adev->in_runpm) - return; - - if (amdgpu_acpi_is_s0ix_active(adev)) - adev->in_s0ix = true; - else if (amdgpu_acpi_is_s3_active(adev)) - adev->in_s3 = true; -} - #endif /* CONFIG_SUSPEND */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index cfdf558b48b6..02138aa55793 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -109,7 +109,7 @@ int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct drm_exec exec; int r; - drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT, 0); + drm_exec_init(&exec, 0, 0); drm_exec_until_all_locked(&exec) { r = amdgpu_vm_lock_pd(vm, &exec, 0); if (likely(!r)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 7f354cd532dc..f8b3e04d71ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4907,28 +4907,20 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev) * @data: data * * This function is called when the system is about to suspend or hibernate. - * It is used to evict resources from the device before the system goes to - * sleep while there is still access to swap. + * It is used to set the appropriate flags so that eviction can be optimized + * in the pm prepare callback. */ static int amdgpu_device_pm_notifier(struct notifier_block *nb, unsigned long mode, void *data) { struct amdgpu_device *adev = container_of(nb, struct amdgpu_device, pm_nb); - int r; switch (mode) { case PM_HIBERNATION_PREPARE: adev->in_s4 = true; - fallthrough; - case PM_SUSPEND_PREPARE: - r = amdgpu_device_evict_resources(adev); - /* - * This is considered non-fatal at this time because - * amdgpu_device_prepare() will also fatally evict resources. - * See https://gitlab.freedesktop.org/drm/amd/-/issues/3781 - */ - if (r) - drm_warn(adev_to_drm(adev), "Failed to evict resources, freeze active processes if problems occur: %d\n", r); + break; + case PM_POST_HIBERNATION: + adev->in_s4 = false; break; } @@ -4949,15 +4941,13 @@ int amdgpu_device_prepare(struct drm_device *dev) struct amdgpu_device *adev = drm_to_adev(dev); int i, r; - amdgpu_choose_low_power_state(adev); - if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; /* Evict the majority of BOs before starting suspend sequence */ r = amdgpu_device_evict_resources(adev); if (r) - goto unprepare; + return r; flush_delayed_work(&adev->gfx.gfx_off_delay_work); @@ -4968,15 +4958,10 @@ int amdgpu_device_prepare(struct drm_device *dev) continue; r = adev->ip_blocks[i].version->funcs->prepare_suspend(&adev->ip_blocks[i]); if (r) - goto unprepare; + return r; } return 0; - -unprepare: - adev->in_s0ix = adev->in_s3 = adev->in_s4 = false; - - return r; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 24ee4710f807..72c807f5822e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2615,13 +2615,8 @@ static int amdgpu_pmops_freeze(struct device *dev) static int amdgpu_pmops_thaw(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; - - r = amdgpu_device_resume(drm_dev, true); - adev->in_s4 = false; - return r; + return amdgpu_device_resume(drm_dev, true); } static int amdgpu_pmops_poweroff(struct device *dev) @@ -2634,9 +2629,6 @@ static int amdgpu_pmops_poweroff(struct device *dev) static int amdgpu_pmops_restore(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct amdgpu_device *adev = drm_to_adev(drm_dev); - - adev->in_s4 = false; return amdgpu_device_resume(drm_dev, true); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index cdcdae7f71ce..83adf81defc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -66,7 +66,6 @@ #define VCN_ENC_CMD_REG_WAIT 0x0000000c #define VCN_AON_SOC_ADDRESS_2_0 0x1f800 -#define VCN1_AON_SOC_ADDRESS_3_0 0x48000 #define VCN_VID_IP_ADDRESS_2_0 0x0 #define VCN_AON_IP_ADDRESS_2_0 0x30000 diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index e74e26b6a4f2..fec9a007533a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -752,6 +752,18 @@ static int gmc_v11_0_sw_init(struct amdgpu_ip_block *ip_block) adev->gmc.vram_type = vram_type; adev->gmc.vram_vendor = vram_vendor; + /* The mall_size is already calculated as mall_size_per_umc * num_umc. + * However, for gfx1151, which features a 2-to-1 UMC mapping, + * the result must be multiplied by 2 to determine the actual mall size. + */ + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { + case IP_VERSION(11, 5, 1): + adev->gmc.mall_size *= 2; + break; + default: + break; + } + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(11, 0, 0): case IP_VERSION(11, 0, 1): diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c index f1dc13b3ab38..cbbeadeb53f7 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v4_0.c @@ -41,7 +41,12 @@ static void hdp_v4_0_flush_hdp(struct amdgpu_device *adev, { if (!ring || !ring->funcs->emit_wreg) { WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); - RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + /* We just need to read back a register to post the write. + * Reading back the remapped register causes problems on + * some platforms so just read back the memory size register. + */ + if (adev->nbio.funcs->get_memsize) + adev->nbio.funcs->get_memsize(adev); } else { amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c index 43195c079748..086a647308df 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c @@ -32,7 +32,12 @@ static void hdp_v5_0_flush_hdp(struct amdgpu_device *adev, { if (!ring || !ring->funcs->emit_wreg) { WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); - RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + /* We just need to read back a register to post the write. + * Reading back the remapped register causes problems on + * some platforms so just read back the memory size register. + */ + if (adev->nbio.funcs->get_memsize) + adev->nbio.funcs->get_memsize(adev); } else { amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c index fcb8dd2876bc..40940b4ab400 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_2.c @@ -33,7 +33,17 @@ static void hdp_v5_2_flush_hdp(struct amdgpu_device *adev, if (!ring || !ring->funcs->emit_wreg) { WREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); - RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + if (amdgpu_sriov_vf(adev)) { + /* this is fine because SR_IOV doesn't remap the register */ + RREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + } else { + /* We just need to read back a register to post the write. + * Reading back the remapped register causes problems on + * some platforms so just read back the memory size register. + */ + if (adev->nbio.funcs->get_memsize) + adev->nbio.funcs->get_memsize(adev); + } } else { amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c index a88d25a06c29..6ccd31c8bc69 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v6_0.c @@ -35,7 +35,12 @@ static void hdp_v6_0_flush_hdp(struct amdgpu_device *adev, { if (!ring || !ring->funcs->emit_wreg) { WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); - RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + /* We just need to read back a register to post the write. + * Reading back the remapped register causes problems on + * some platforms so just read back the memory size register. + */ + if (adev->nbio.funcs->get_memsize) + adev->nbio.funcs->get_memsize(adev); } else { amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c index 49f7eb4fbd11..2c9239a22f39 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v7_0.c @@ -32,7 +32,12 @@ static void hdp_v7_0_flush_hdp(struct amdgpu_device *adev, { if (!ring || !ring->funcs->emit_wreg) { WREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); - RREG32((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2); + /* We just need to read back a register to post the write. + * Reading back the remapped register causes problems on + * some platforms so just read back the memory size register. + */ + if (adev->nbio.funcs->get_memsize) + adev->nbio.funcs->get_memsize(adev); } else { amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index 8e7a36f26e9c..b8d835c9e17e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c @@ -39,6 +39,7 @@ #define VCN_VID_SOC_ADDRESS_2_0 0x1fa00 #define VCN1_VID_SOC_ADDRESS_3_0 0x48200 +#define VCN1_AON_SOC_ADDRESS_3_0 0x48000 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x1fd #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x503 diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index d716510b8dd6..3eec1b8feaee 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -39,6 +39,7 @@ #define VCN_VID_SOC_ADDRESS_2_0 0x1fa00 #define VCN1_VID_SOC_ADDRESS_3_0 0x48200 +#define VCN1_AON_SOC_ADDRESS_3_0 0x48000 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x27 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x0f diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 22ae1939476f..0b19f0ab4480 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -40,6 +40,7 @@ #define VCN_VID_SOC_ADDRESS_2_0 0x1fa00 #define VCN1_VID_SOC_ADDRESS_3_0 0x48200 +#define VCN1_AON_SOC_ADDRESS_3_0 0x48000 #define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x27 #define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x0f diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index c6f6392c1c20..1f777c125b00 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -46,6 +46,7 @@ #define VCN_VID_SOC_ADDRESS_2_0 0x1fb00 #define VCN1_VID_SOC_ADDRESS_3_0 0x48300 +#define VCN1_AON_SOC_ADDRESS_3_0 0x48000 #define VCN_HARVEST_MMSCH 0 @@ -614,7 +615,8 @@ static void vcn_v4_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, /* VCN global tiling registers */ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( - VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG), + adev->gfx.config.gb_addr_config, 0, indirect); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index 3e176b4b7c69..012f6ea928ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -45,6 +45,7 @@ #define VCN_VID_SOC_ADDRESS_2_0 0x1fb00 #define VCN1_VID_SOC_ADDRESS_3_0 0x48300 +#define VCN1_AON_SOC_ADDRESS_3_0 0x48000 static const struct amdgpu_hwip_reg_entry vcn_reg_list_4_0_3[] = { SOC15_REG_ENTRY_STR(VCN, 0, regUVD_POWER_STATUS), diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c index ba603b2246e2..f11df9c2ec13 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c @@ -46,6 +46,7 @@ #define VCN_VID_SOC_ADDRESS_2_0 0x1fb00 #define VCN1_VID_SOC_ADDRESS_3_0 (0x48300 + 0x38000) +#define VCN1_AON_SOC_ADDRESS_3_0 (0x48000 + 0x38000) #define VCN_HARVEST_MMSCH 0 @@ -1022,6 +1023,10 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, ring->doorbell_index << VCN_RB1_DB_CTRL__OFFSET__SHIFT | VCN_RB1_DB_CTRL__EN_MASK); + /* Keeping one read-back to ensure all register writes are done, otherwise + * it may introduce race conditions */ + RREG32_SOC15(VCN, inst_idx, regVCN_RB1_DB_CTRL); + return 0; } @@ -1204,6 +1209,10 @@ static int vcn_v4_0_5_start(struct amdgpu_vcn_inst *vinst) WREG32_SOC15(VCN, i, regVCN_RB_ENABLE, tmp); fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF); + /* Keeping one read-back to ensure all register writes are done, otherwise + * it may introduce race conditions */ + RREG32_SOC15(VCN, i, regVCN_RB_ENABLE); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index d99d05f42f1d..b90da3d3e140 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -533,7 +533,8 @@ static void vcn_v5_0_0_mc_resume_dpg_mode(struct amdgpu_vcn_inst *vinst, /* VCN global tiling registers */ WREG32_SOC24_DPG_MODE(inst_idx, SOC24_DPG_MODE_OFFSET( - VCN, 0, regUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + VCN, inst_idx, regUVD_GFX10_ADDR_CONFIG), + adev->gfx.config.gb_addr_config, 0, indirect); return; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 536f73131c2d..a187cdb43e7e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -372,6 +372,8 @@ get_crtc_by_otg_inst(struct amdgpu_device *adev, static inline bool is_dc_timing_adjust_needed(struct dm_crtc_state *old_state, struct dm_crtc_state *new_state) { + if (new_state->stream->adjust.timing_adjust_pending) + return true; if (new_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED) return true; else if (amdgpu_dm_crtc_vrr_active(old_state) != amdgpu_dm_crtc_vrr_active(new_state)) @@ -673,15 +675,21 @@ static void dm_crtc_high_irq(void *interrupt_params) spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); if (acrtc->dm_irq_params.stream && - acrtc->dm_irq_params.vrr_params.supported && - acrtc->dm_irq_params.freesync_config.state == - VRR_STATE_ACTIVE_VARIABLE) { + acrtc->dm_irq_params.vrr_params.supported) { + bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled; + bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled; + bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state == VRR_STATE_ACTIVE_VARIABLE; + mod_freesync_handle_v_update(adev->dm.freesync_module, acrtc->dm_irq_params.stream, &acrtc->dm_irq_params.vrr_params); - dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc->dm_irq_params.stream, - &acrtc->dm_irq_params.vrr_params.adjust); + /* update vmin_vmax only if freesync is enabled, or only if PSR and REPLAY are disabled */ + if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) { + dc_stream_adjust_vmin_vmax(adev->dm.dc, + acrtc->dm_irq_params.stream, + &acrtc->dm_irq_params.vrr_params.adjust); + } } /* @@ -3461,11 +3469,6 @@ static int dm_resume(struct amdgpu_ip_block *ip_block) return 0; } - - /* leave display off for S4 sequence */ - if (adev->in_s4) - return 0; - /* Recreate dc_state - DC invalidates it when setting power state to S3. */ dc_state_release(dm_state->context); dm_state->context = dc_state_create(dm->dc, NULL); @@ -12743,7 +12746,7 @@ int amdgpu_dm_process_dmub_aux_transfer_sync( * Transient states before tunneling is enabled could * lead to this error. We can ignore this for now. */ - if (p_notify->result != AUX_RET_ERROR_PROTOCOL_ERROR) { + if (p_notify->result == AUX_RET_ERROR_PROTOCOL_ERROR) { DRM_WARN("DPIA AUX failed on 0x%x(%d), error %d\n", payload->address, payload->length, p_notify->result); @@ -12752,22 +12755,15 @@ int amdgpu_dm_process_dmub_aux_transfer_sync( goto out; } + payload->reply[0] = adev->dm.dmub_notify->aux_reply.command & 0xF; + if (adev->dm.dmub_notify->aux_reply.command & 0xF0) + /* The reply is stored in the top nibble of the command. */ + payload->reply[0] = (adev->dm.dmub_notify->aux_reply.command >> 4) & 0xF; - payload->reply[0] = adev->dm.dmub_notify->aux_reply.command; - if (!payload->write && p_notify->aux_reply.length && - (payload->reply[0] == AUX_TRANSACTION_REPLY_AUX_ACK)) { - - if (payload->length != p_notify->aux_reply.length) { - DRM_WARN("invalid read length %d from DPIA AUX 0x%x(%d)!\n", - p_notify->aux_reply.length, - payload->address, payload->length); - *operation_result = AUX_RET_ERROR_INVALID_REPLY; - goto out; - } - + /*write req may receive a byte indicating partially written number as well*/ + if (p_notify->aux_reply.length) memcpy(payload->data, p_notify->aux_reply.data, p_notify->aux_reply.length); - } /* success */ ret = p_notify->aux_reply.length; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 7ceedf626d23..5cdbc86ef8f5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -51,6 +51,9 @@ #define PEAK_FACTOR_X1000 1006 +/* + * This function handles both native AUX and I2C-Over-AUX transactions. + */ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) { @@ -59,6 +62,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, enum aux_return_code_type operation_result; struct amdgpu_device *adev; struct ddc_service *ddc; + uint8_t copy[16]; if (WARN_ON(msg->size > 16)) return -E2BIG; @@ -74,6 +78,11 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, (msg->request & DP_AUX_I2C_WRITE_STATUS_UPDATE) != 0; payload.defer_delay = 0; + if (payload.write) { + memcpy(copy, msg->buffer, msg->size); + payload.data = copy; + } + result = dc_link_aux_transfer_raw(TO_DM_AUX(aux)->ddc_service, &payload, &operation_result); @@ -87,15 +96,25 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, if (adev->dm.aux_hpd_discon_quirk) { if (msg->address == DP_SIDEBAND_MSG_DOWN_REQ_BASE && operation_result == AUX_RET_ERROR_HPD_DISCON) { - result = 0; + result = msg->size; operation_result = AUX_RET_SUCCESS; } } - if (payload.write && result >= 0) - result = msg->size; + /* + * result equals to 0 includes the cases of AUX_DEFER/I2C_DEFER + */ + if (payload.write && result >= 0) { + if (result) { + /*one byte indicating partially written bytes*/ + drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX partially written\n"); + result = payload.data[0]; + } else if (!payload.reply[0]) + /*I2C_ACK|AUX_ACK*/ + result = msg->size; + } - if (result < 0) + if (result < 0) { switch (operation_result) { case AUX_RET_SUCCESS: break; @@ -114,6 +133,13 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, break; } + drm_dbg_dp(adev_to_drm(adev), "amdgpu: DP AUX transfer fail:%d\n", operation_result); + } + + if (payload.reply[0]) + drm_dbg_dp(adev_to_drm(adev), "amdgpu: AUX reply command not ACK: 0x%02x.", + payload.reply[0]); + return result; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 28d1353f403d..ba4ce8a63158 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -439,9 +439,12 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc, * Don't adjust DRR while there's bandwidth optimizations pending to * avoid conflicting with firmware updates. */ - if (dc->ctx->dce_version > DCE_VERSION_MAX) - if (dc->optimized_required || dc->wm_optimized_required) + if (dc->ctx->dce_version > DCE_VERSION_MAX) { + if (dc->optimized_required || dc->wm_optimized_required) { + stream->adjust.timing_adjust_pending = true; return false; + } + } dc_exit_ips_for_hw_access(dc); @@ -3168,7 +3171,8 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->crtc_timing_adjust) { if (stream->adjust.v_total_min != update->crtc_timing_adjust->v_total_min || - stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max) + stream->adjust.v_total_max != update->crtc_timing_adjust->v_total_max || + stream->adjust.timing_adjust_pending) update->crtc_timing_adjust->timing_adjust_pending = true; stream->adjust = *update->crtc_timing_adjust; update->crtc_timing_adjust->timing_adjust_pending = false; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index d9159ca55412..92f0a099d089 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -195,9 +195,9 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .dcn_downspread_percent = 0.5, .gpuvm_min_page_size_bytes = 4096, .hostvm_min_page_size_bytes = 4096, - .do_urgent_latency_adjustment = 1, + .do_urgent_latency_adjustment = 0, .urgent_latency_adjustment_fabric_clock_component_us = 0, - .urgent_latency_adjustment_fabric_clock_reference_mhz = 3000, + .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, }; void dcn35_build_wm_range_table_fpu(struct clk_mgr *clk_mgr) diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c index 0c8ec30ea672..731fbd4bc600 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c @@ -910,7 +910,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm } //TODO : Could be possibly moved to a common helper layer. -static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const struct dc_plane_state *plane, unsigned int *plane_id) +static bool dml21_wrapper_get_plane_id(const struct dc_state *context, unsigned int stream_id, const struct dc_plane_state *plane, unsigned int *plane_id) { int i, j; @@ -918,10 +918,12 @@ static bool dml21_wrapper_get_plane_id(const struct dc_state *context, const str return false; for (i = 0; i < context->stream_count; i++) { - for (j = 0; j < context->stream_status[i].plane_count; j++) { - if (context->stream_status[i].plane_states[j] == plane) { - *plane_id = (i << 16) | j; - return true; + if (context->streams[i]->stream_id == stream_id) { + for (j = 0; j < context->stream_status[i].plane_count; j++) { + if (context->stream_status[i].plane_states[j] == plane) { + *plane_id = (i << 16) | j; + return true; + } } } } @@ -944,14 +946,14 @@ static unsigned int map_stream_to_dml21_display_cfg(const struct dml2_context *d return location; } -static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx, +static unsigned int map_plane_to_dml21_display_cfg(const struct dml2_context *dml_ctx, unsigned int stream_id, const struct dc_plane_state *plane, const struct dc_state *context) { unsigned int plane_id; int i = 0; int location = -1; - if (!dml21_wrapper_get_plane_id(context, plane, &plane_id)) { + if (!dml21_wrapper_get_plane_id(context, stream_id, plane, &plane_id)) { ASSERT(false); return -1; } @@ -1037,7 +1039,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location; } else { for (plane_index = 0; plane_index < context->stream_status[stream_index].plane_count; plane_index++) { - disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->stream_status[stream_index].plane_states[plane_index], context); + disp_cfg_plane_location = map_plane_to_dml21_display_cfg(dml_ctx, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], context); if (disp_cfg_plane_location < 0) disp_cfg_plane_location = dml_dispcfg->num_planes++; @@ -1048,7 +1050,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s populate_dml21_plane_config_from_plane_state(dml_ctx, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location], context->stream_status[stream_index].plane_states[plane_index], context, stream_index); dml_dispcfg->plane_descriptors[disp_cfg_plane_location].stream_index = disp_cfg_stream_location; - if (dml21_wrapper_get_plane_id(context, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location])) + if (dml21_wrapper_get_plane_id(context, context->streams[stream_index]->stream_id, context->stream_status[stream_index].plane_states[plane_index], &dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[disp_cfg_plane_location])) dml_ctx->v21.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id_valid[disp_cfg_plane_location] = true; /* apply forced pstate policy */ diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c index 5d16f36ec95c..ed6584535e89 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c @@ -234,7 +234,9 @@ static bool dml21_mode_check_and_programming(const struct dc *in_dc, struct dc_s if (!result) return false; + DC_FP_START(); result = dml2_build_mode_programming(mode_programming); + DC_FP_END(); if (!result) return false; @@ -277,7 +279,9 @@ static bool dml21_check_mode_support(const struct dc *in_dc, struct dc_state *co mode_support->dml2_instance = dml_init->dml2_instance; dml21_map_dc_state_into_dml_display_cfg(in_dc, context, dml_ctx); dml_ctx->v21.mode_programming.dml2_instance->scratch.build_mode_programming_locals.mode_programming_params.programming = dml_ctx->v21.mode_programming.programming; + DC_FP_START(); is_supported = dml2_check_mode_supported(mode_support); + DC_FP_END(); if (!is_supported) return false; @@ -288,16 +292,12 @@ bool dml21_validate(const struct dc *in_dc, struct dc_state *context, struct dml { bool out = false; - DC_FP_START(); - /* Use dml_validate_only for fast_validate path */ if (fast_validate) out = dml21_check_mode_support(in_dc, context, dml_ctx); else out = dml21_mode_check_and_programming(in_dc, context, dml_ctx); - DC_FP_END(); - return out; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index 2061d43b92e1..ab6baf269801 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -973,7 +973,9 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p } } -static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context, struct scaler_data *out) +static struct scaler_data *get_scaler_data_for_plane( + const struct dc_plane_state *in, + struct dc_state *context) { int i; struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe; @@ -994,7 +996,7 @@ static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc } ASSERT(i < MAX_PIPES); - memcpy(out, &temp_pipe->plane_res.scl_data, sizeof(*out)); + return &temp_pipe->plane_res.scl_data; } static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, @@ -1057,11 +1059,7 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out const struct dc_plane_state *in, struct dc_state *context, const struct soc_bounding_box_st *soc) { - struct scaler_data *scaler_data = kzalloc(sizeof(*scaler_data), GFP_KERNEL); - if (!scaler_data) - return; - - get_scaler_data_for_plane(in, context, scaler_data); + struct scaler_data *scaler_data = get_scaler_data_for_plane(in, context); out->CursorBPP[location] = dml_cur_32bit; out->CursorWidth[location] = 256; @@ -1126,8 +1124,6 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out out->DynamicMetadataTransmittedBytes[location] = 0; out->NumberOfCursors[location] = 1; - - kfree(scaler_data); } static unsigned int map_stream_to_dml_display_cfg(const struct dml2_context *dml2, diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c index 1236e0f9a256..712aff7e17f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_cm.c @@ -120,10 +120,11 @@ void dpp401_set_cursor_attributes( enum dc_cursor_color_format color_format = cursor_attributes->color_format; int cur_rom_en = 0; - // DCN4 should always do Cursor degamma for Cursor Color modes if (color_format == CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA || color_format == CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA) { - cur_rom_en = 1; + if (cursor_attributes->attribute_flags.bits.ENABLE_CURSOR_DEGAMMA) { + cur_rom_en = 1; + } } REG_UPDATE_3(CURSOR0_CONTROL, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c index 5489f3d431f6..3af6a3402b89 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c @@ -1980,9 +1980,9 @@ void dcn401_program_pipe( dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->hubp_regs.det_size); } - if (pipe_ctx->update_flags.raw || - (pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) || - pipe_ctx->stream->update_flags.raw) + if (pipe_ctx->plane_state && (pipe_ctx->update_flags.raw || + pipe_ctx->plane_state->update_flags.raw || + pipe_ctx->stream->update_flags.raw)) dc->hwss.update_dchubp_dpp(dc, pipe_ctx, context); if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable || diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 268626e73c54..53c961f86d43 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -148,6 +148,7 @@ void link_blank_dp_stream(struct dc_link *link, bool hw_init) void link_set_all_streams_dpms_off_for_link(struct dc_link *link) { struct pipe_ctx *pipes[MAX_PIPES]; + struct dc_stream_state *streams[MAX_PIPES]; struct dc_state *state = link->dc->current_state; uint8_t count; int i; @@ -160,10 +161,18 @@ void link_set_all_streams_dpms_off_for_link(struct dc_link *link) link_get_master_pipes_with_dpms_on(link, state, &count, pipes); + /* The subsequent call to dc_commit_updates_for_stream for a full update + * will release the current state and swap to a new state. Releasing the + * current state results in the stream pointers in the pipe_ctx structs + * to be zero'd. Hence, cache all streams prior to dc_commit_updates_for_stream. + */ + for (i = 0; i < count; i++) + streams[i] = pipes[i]->stream; + for (i = 0; i < count; i++) { - stream_update.stream = pipes[i]->stream; + stream_update.stream = streams[i]; dc_commit_updates_for_stream(link->ctx->dc, NULL, 0, - pipes[i]->stream, &stream_update, + streams[i], &stream_update, state); } diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index 2a59cc61ed8c..944650cb13de 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -2114,8 +2114,6 @@ static bool dcn32_resource_construct( #define REG_STRUCT dccg_regs dccg_regs_init(); - DC_FP_START(); - ctx->dc_bios->regs = &bios_regs; pool->base.res_cap = &res_cap_dcn32; @@ -2501,14 +2499,10 @@ static bool dcn32_resource_construct( if (ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev) && (dc->config.sdpif_request_limit_words_per_umc == 0)) dc->config.sdpif_request_limit_words_per_umc = 16; - DC_FP_END(); - return true; create_fail: - DC_FP_END(); - dcn32_resource_destruct(pool); return false; diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 17fc5dc708f4..60e5ac179c15 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -549,7 +549,7 @@ int drm_dev_wedged_event(struct drm_device *dev, unsigned long method) if (drm_WARN_ONCE(dev, !recovery, "invalid recovery method %u\n", opt)) break; - len += scnprintf(event_string + len, sizeof(event_string), "%s,", recovery); + len += scnprintf(event_string + len, sizeof(event_string) - len, "%s,", recovery); } if (recovery) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 13bc4c290b17..9edb3247c767 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -6596,6 +6596,7 @@ static void drm_reset_display_info(struct drm_connector *connector) info->has_hdmi_infoframe = false; info->rgb_quant_range_selectable = false; memset(&info->hdmi, 0, sizeof(info->hdmi)); + memset(&connector->hdr_sink_metadata, 0, sizeof(connector->hdr_sink_metadata)); info->edid_hdmi_rgb444_dc_modes = 0; info->edid_hdmi_ycbcr444_dc_modes = 0; diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index de424e670995..4b2f32889f00 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -1118,6 +1118,10 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm, lockdep_assert_held(&gpusvm->notifier_lock); if (range->flags.has_dma_mapping) { + struct drm_gpusvm_range_flags flags = { + .__flags = range->flags.__flags, + }; + for (i = 0, j = 0; i < npages; j++) { struct drm_pagemap_device_addr *addr = &range->dma_addr[j]; @@ -1131,8 +1135,12 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm, dev, *addr); i += 1 << addr->order; } - range->flags.has_devmem_pages = false; - range->flags.has_dma_mapping = false; + + /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */ + flags.has_devmem_pages = false; + flags.has_dma_mapping = false; + WRITE_ONCE(range->flags.__flags, flags.__flags); + range->dpagemap = NULL; } } @@ -1334,6 +1342,7 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm, int err = 0; struct dev_pagemap *pagemap; struct drm_pagemap *dpagemap; + struct drm_gpusvm_range_flags flags; retry: hmm_range.notifier_seq = mmu_interval_read_begin(notifier); @@ -1378,7 +1387,8 @@ map_pages: */ drm_gpusvm_notifier_lock(gpusvm); - if (range->flags.unmapped) { + flags.__flags = range->flags.__flags; + if (flags.unmapped) { drm_gpusvm_notifier_unlock(gpusvm); err = -EFAULT; goto err_free; @@ -1454,6 +1464,11 @@ map_pages: goto err_unmap; } + if (ctx->devmem_only) { + err = -EFAULT; + goto err_unmap; + } + addr = dma_map_page(gpusvm->drm->dev, page, 0, PAGE_SIZE << order, @@ -1469,14 +1484,17 @@ map_pages: } i += 1 << order; num_dma_mapped = i; - range->flags.has_dma_mapping = true; + flags.has_dma_mapping = true; } if (zdd) { - range->flags.has_devmem_pages = true; + flags.has_devmem_pages = true; range->dpagemap = dpagemap; } + /* WRITE_ONCE pairs with READ_ONCE for opportunistic checks */ + WRITE_ONCE(range->flags.__flags, flags.__flags); + drm_gpusvm_notifier_unlock(gpusvm); kvfree(pfns); set_seqno: @@ -1765,6 +1783,8 @@ int drm_gpusvm_migrate_to_devmem(struct drm_gpusvm *gpusvm, goto err_finalize; /* Upon success bind devmem allocation to range and zdd */ + devmem_allocation->timeslice_expiration = get_jiffies_64() + + msecs_to_jiffies(ctx->timeslice_ms); zdd->devmem_allocation = devmem_allocation; /* Owns ref */ err_finalize: @@ -1985,6 +2005,13 @@ static int __drm_gpusvm_migrate_to_ram(struct vm_area_struct *vas, void *buf; int i, err = 0; + if (page) { + zdd = page->zone_device_data; + if (time_before64(get_jiffies_64(), + zdd->devmem_allocation->timeslice_expiration)) + return 0; + } + start = ALIGN_DOWN(fault_addr, size); end = ALIGN(fault_addr + 1, size); diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 02f95108c637..6dc2d31ccb5a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -242,7 +242,7 @@ int intel_dp_mtp_tu_compute_config(struct intel_dp *intel_dp, to_intel_connector(conn_state->connector); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - bool is_mst = intel_dp->is_mst; + bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST); int bpp_x16, slots = -EINVAL; int dsc_slice_count = 0; int max_dpt_bpp_x16; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index ae3343c81a64..5e784db9f315 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -305,36 +305,20 @@ void __shmem_writeback(size_t size, struct address_space *mapping) .range_end = LLONG_MAX, .for_reclaim = 1, }; - unsigned long i; + struct folio *folio = NULL; + int error = 0; /* * Leave mmapings intact (GTT will have been revoked on unbinding, - * leaving only CPU mmapings around) and add those pages to the LRU + * leaving only CPU mmapings around) and add those folios to the LRU * instead of invoking writeback so they are aged and paged out * as normal. */ - - /* Begin writeback on each dirty page */ - for (i = 0; i < size >> PAGE_SHIFT; i++) { - struct page *page; - - page = find_lock_page(mapping, i); - if (!page) - continue; - - if (!page_mapped(page) && clear_page_dirty_for_io(page)) { - int ret; - - SetPageReclaim(page); - ret = mapping->a_ops->writepage(page, &wbc); - if (!PageWriteback(page)) - ClearPageReclaim(page); - if (!ret) - goto put; - } - unlock_page(page); -put: - put_page(page); + while ((folio = writeback_iter(mapping, &wbc, folio, &error))) { + if (folio_mapped(folio)) + folio_redirty_for_writepage(&wbc, folio); + else + error = shmem_writeout(folio, &wbc); } } diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 64e9317f58fb..71ee01d9ef64 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1001,6 +1001,10 @@ void intel_rps_dec_waiters(struct intel_rps *rps) if (rps_uses_slpc(rps)) { slpc = rps_to_slpc(rps); + /* Don't decrement num_waiters for req where increment was skipped */ + if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING) + return; + intel_guc_slpc_dec_waiters(slpc); } else { atomic_dec(&rps->num_waiters); @@ -1029,11 +1033,15 @@ void intel_rps_boost(struct i915_request *rq) if (slpc->power_profile == SLPC_POWER_PROFILES_POWER_SAVING) return; - if (slpc->min_freq_softlimit >= slpc->boost_freq) - return; - /* Return if old value is non zero */ if (!atomic_fetch_inc(&slpc->num_waiters)) { + /* + * Skip queuing boost work if frequency is already boosted, + * but still increment num_waiters. + */ + if (slpc->min_freq_softlimit >= slpc->boost_freq) + return; + GT_TRACE(rps_to_gt(rps), "boost fence:%llx:%llx\n", rq->fence.context, rq->fence.seqno); queue_work(rps_to_gt(rps)->i915->unordered_wq, diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c index 7752d8ac85f0..c08fa93e50a3 100644 --- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c +++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c @@ -75,7 +75,7 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi, unsigned long long venc_freq; unsigned long long hdmi_freq; - vclk_freq = mode->clock * 1000; + vclk_freq = mode->clock * 1000ULL; /* For 420, pixel clock is half unlike venc clock */ if (encoder_hdmi->output_bus_fmt == MEDIA_BUS_FMT_UYYVYY8_0_5X24) @@ -123,7 +123,7 @@ static enum drm_mode_status meson_encoder_hdmi_mode_valid(struct drm_bridge *bri struct meson_encoder_hdmi *encoder_hdmi = bridge_to_meson_encoder_hdmi(bridge); struct meson_drm *priv = encoder_hdmi->priv; bool is_hdmi2_sink = display_info->hdmi.scdc.supported; - unsigned long long clock = mode->clock * 1000; + unsigned long long clock = mode->clock * 1000ULL; unsigned long long phy_freq; unsigned long long vclk_freq; unsigned long long venc_freq; diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 232b03c1a259..33a37539de57 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -1027,27 +1027,28 @@ static const struct panel_desc auo_g070vvn01 = { }, }; -static const struct drm_display_mode auo_g101evn010_mode = { - .clock = 68930, - .hdisplay = 1280, - .hsync_start = 1280 + 82, - .hsync_end = 1280 + 82 + 2, - .htotal = 1280 + 82 + 2 + 84, - .vdisplay = 800, - .vsync_start = 800 + 8, - .vsync_end = 800 + 8 + 2, - .vtotal = 800 + 8 + 2 + 6, +static const struct display_timing auo_g101evn010_timing = { + .pixelclock = { 64000000, 68930000, 85000000 }, + .hactive = { 1280, 1280, 1280 }, + .hfront_porch = { 8, 64, 256 }, + .hback_porch = { 8, 64, 256 }, + .hsync_len = { 40, 168, 767 }, + .vactive = { 800, 800, 800 }, + .vfront_porch = { 4, 8, 100 }, + .vback_porch = { 4, 8, 100 }, + .vsync_len = { 8, 16, 223 }, }; static const struct panel_desc auo_g101evn010 = { - .modes = &auo_g101evn010_mode, - .num_modes = 1, + .timings = &auo_g101evn010_timing, + .num_timings = 1, .bpc = 6, .size = { .width = 216, .height = 135, }, .bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, .connector_type = DRM_MODE_CONNECTOR_LVDS, }; diff --git a/drivers/gpu/drm/tiny/panel-mipi-dbi.c b/drivers/gpu/drm/tiny/panel-mipi-dbi.c index 0460ecaef4bd..23914a9f7fd3 100644 --- a/drivers/gpu/drm/tiny/panel-mipi-dbi.c +++ b/drivers/gpu/drm/tiny/panel-mipi-dbi.c @@ -390,7 +390,10 @@ static int panel_mipi_dbi_spi_probe(struct spi_device *spi) spi_set_drvdata(spi, drm); - drm_client_setup(drm, NULL); + if (bpp == 16) + drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB565); + else + drm_client_setup_with_fourcc(drm, DRM_FORMAT_RGB888); return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_backup.c b/drivers/gpu/drm/ttm/ttm_backup.c index 93c007f18855..ffaab68bd5dd 100644 --- a/drivers/gpu/drm/ttm/ttm_backup.c +++ b/drivers/gpu/drm/ttm/ttm_backup.c @@ -8,20 +8,6 @@ #include <linux/swap.h> /* - * Casting from randomized struct file * to struct ttm_backup * is fine since - * struct ttm_backup is never defined nor dereferenced. - */ -static struct file *ttm_backup_to_file(struct ttm_backup *backup) -{ - return (void *)backup; -} - -static struct ttm_backup *ttm_file_to_backup(struct file *file) -{ - return (void *)file; -} - -/* * Need to map shmem indices to handle since a handle value * of 0 means error, following the swp_entry_t convention. */ @@ -40,12 +26,12 @@ static pgoff_t ttm_backup_handle_to_shmem_idx(pgoff_t handle) * @backup: The struct backup pointer used to obtain the handle * @handle: The handle obtained from the @backup_page function. */ -void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle) +void ttm_backup_drop(struct file *backup, pgoff_t handle) { loff_t start = ttm_backup_handle_to_shmem_idx(handle); start <<= PAGE_SHIFT; - shmem_truncate_range(file_inode(ttm_backup_to_file(backup)), start, + shmem_truncate_range(file_inode(backup), start, start + PAGE_SIZE - 1); } @@ -55,16 +41,15 @@ void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle) * @backup: The struct backup pointer used to back up the page. * @dst: The struct page to copy into. * @handle: The handle returned when the page was backed up. - * @intr: Try to perform waits interruptable or at least killable. + * @intr: Try to perform waits interruptible or at least killable. * * Return: 0 on success, Negative error code on failure, notably * -EINTR if @intr was set to true and a signal is pending. */ -int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst, +int ttm_backup_copy_page(struct file *backup, struct page *dst, pgoff_t handle, bool intr) { - struct file *filp = ttm_backup_to_file(backup); - struct address_space *mapping = filp->f_mapping; + struct address_space *mapping = backup->f_mapping; struct folio *from_folio; pgoff_t idx = ttm_backup_handle_to_shmem_idx(handle); @@ -106,12 +91,11 @@ int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst, * the folio size- and usage. */ s64 -ttm_backup_backup_page(struct ttm_backup *backup, struct page *page, +ttm_backup_backup_page(struct file *backup, struct page *page, bool writeback, pgoff_t idx, gfp_t page_gfp, gfp_t alloc_gfp) { - struct file *filp = ttm_backup_to_file(backup); - struct address_space *mapping = filp->f_mapping; + struct address_space *mapping = backup->f_mapping; unsigned long handle = 0; struct folio *to_folio; int ret; @@ -136,13 +120,13 @@ ttm_backup_backup_page(struct ttm_backup *backup, struct page *page, .for_reclaim = 1, }; folio_set_reclaim(to_folio); - ret = mapping->a_ops->writepage(folio_file_page(to_folio, idx), &wbc); + ret = shmem_writeout(to_folio, &wbc); if (!folio_test_writeback(to_folio)) folio_clear_reclaim(to_folio); /* - * If writepage succeeds, it unlocks the folio. - * writepage() errors are otherwise dropped, since writepage() - * is only best effort here. + * If writeout succeeds, it unlocks the folio. errors + * are otherwise dropped, since writeout is only best + * effort here. */ if (ret) folio_unlock(to_folio); @@ -161,9 +145,9 @@ ttm_backup_backup_page(struct ttm_backup *backup, struct page *page, * * After a call to this function, it's illegal to use the @backup pointer. */ -void ttm_backup_fini(struct ttm_backup *backup) +void ttm_backup_fini(struct file *backup) { - fput(ttm_backup_to_file(backup)); + fput(backup); } /** @@ -194,14 +178,10 @@ EXPORT_SYMBOL_GPL(ttm_backup_bytes_avail); * * Create a backup utilizing shmem objects. * - * Return: A pointer to a struct ttm_backup on success, + * Return: A pointer to a struct file on success, * an error pointer on error. */ -struct ttm_backup *ttm_backup_shmem_create(loff_t size) +struct file *ttm_backup_shmem_create(loff_t size) { - struct file *filp; - - filp = shmem_file_setup("ttm shmem backup", size, 0); - - return ttm_file_to_backup(filp); + return shmem_file_setup("ttm shmem backup", size, 0); } diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 83b10706ba89..c2ea865be657 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -506,7 +506,7 @@ static void ttm_pool_allocated_page_commit(struct page *allocated, * if successful, populate the page-table and dma-address arrays. */ static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore, - struct ttm_backup *backup, + struct file *backup, const struct ttm_operation_ctx *ctx, struct ttm_pool_alloc_state *alloc) @@ -655,7 +655,7 @@ static void ttm_pool_free_range(struct ttm_pool *pool, struct ttm_tt *tt, pgoff_t start_page, pgoff_t end_page) { struct page **pages = &tt->pages[start_page]; - struct ttm_backup *backup = tt->backup; + struct file *backup = tt->backup; pgoff_t i, nr; for (i = start_page; i < end_page; i += nr, pages += nr) { @@ -963,7 +963,7 @@ void ttm_pool_drop_backed_up(struct ttm_tt *tt) long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt, const struct ttm_backup_flags *flags) { - struct ttm_backup *backup = tt->backup; + struct file *backup = tt->backup; struct page *page; unsigned long handle; gfp_t alloc_gfp; diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index df0aa6c4b8b8..698cd4bf5e46 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -544,7 +544,7 @@ EXPORT_SYMBOL(ttm_tt_pages_limit); */ int ttm_tt_setup_backup(struct ttm_tt *tt) { - struct ttm_backup *backup = + struct file *backup = ttm_backup_shmem_create(((loff_t)tt->num_pages) << PAGE_SHIFT); if (WARN_ON_ONCE(!(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE))) diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 4a7701a33cf8..eb35482f6fb5 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -744,11 +744,16 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job) return DRM_GPU_SCHED_STAT_NOMINAL; } -/* If the current address or return address have changed, then the GPU - * has probably made progress and we should delay the reset. This - * could fail if the GPU got in an infinite loop in the CL, but that - * is pretty unlikely outside of an i-g-t testcase. - */ +static void +v3d_sched_skip_reset(struct drm_sched_job *sched_job) +{ + struct drm_gpu_scheduler *sched = sched_job->sched; + + spin_lock(&sched->job_list_lock); + list_add(&sched_job->list, &sched->pending_list); + spin_unlock(&sched->job_list_lock); +} + static enum drm_gpu_sched_stat v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, u32 *timedout_ctca, u32 *timedout_ctra) @@ -758,9 +763,16 @@ v3d_cl_job_timedout(struct drm_sched_job *sched_job, enum v3d_queue q, u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(q)); u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(q)); + /* If the current address or return address have changed, then the GPU + * has probably made progress and we should delay the reset. This + * could fail if the GPU got in an infinite loop in the CL, but that + * is pretty unlikely outside of an i-g-t testcase. + */ if (*timedout_ctca != ctca || *timedout_ctra != ctra) { *timedout_ctca = ctca; *timedout_ctra = ctra; + + v3d_sched_skip_reset(sched_job); return DRM_GPU_SCHED_STAT_NOMINAL; } @@ -800,11 +812,13 @@ v3d_csd_job_timedout(struct drm_sched_job *sched_job) struct v3d_dev *v3d = job->base.v3d; u32 batches = V3D_CORE_READ(0, V3D_CSD_CURRENT_CFG4(v3d->ver)); - /* If we've made progress, skip reset and let the timer get - * rearmed. + /* If we've made progress, skip reset, add the job to the pending + * list, and let the timer get rearmed. */ if (job->timedout_batches != batches) { job->timedout_batches = batches; + + v3d_sched_skip_reset(sched_job); return DRM_GPU_SCHED_STAT_NOMINAL; } diff --git a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h index 167fb0f742de..5a47991b4b81 100644 --- a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h +++ b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h @@ -47,6 +47,10 @@ #define MI_LRI_FORCE_POSTED REG_BIT(12) #define MI_LRI_LEN(x) (((x) & 0xff) + 1) +#define MI_STORE_REGISTER_MEM (__MI_INSTR(0x24) | XE_INSTR_NUM_DW(4)) +#define MI_SRM_USE_GGTT REG_BIT(22) +#define MI_SRM_ADD_CS_OFFSET REG_BIT(19) + #define MI_FLUSH_DW __MI_INSTR(0x26) #define MI_FLUSH_DW_PROTECTED_MEM_EN REG_BIT(22) #define MI_FLUSH_DW_STORE_INDEX REG_BIT(21) diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h index fb8ec317b6ee..891f928d80ce 100644 --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h @@ -43,6 +43,10 @@ #define XEHPC_BCS8_RING_BASE 0x3ee000 #define GSCCS_RING_BASE 0x11a000 +#define ENGINE_ID(base) XE_REG((base) + 0x8c) +#define ENGINE_INSTANCE_ID REG_GENMASK(9, 4) +#define ENGINE_CLASS_ID REG_GENMASK(2, 0) + #define RING_TAIL(base) XE_REG((base) + 0x30) #define TAIL_ADDR REG_GENMASK(20, 3) @@ -154,6 +158,7 @@ #define STOP_RING REG_BIT(8) #define RING_CTX_TIMESTAMP(base) XE_REG((base) + 0x3a8) +#define RING_CTX_TIMESTAMP_UDW(base) XE_REG((base) + 0x3ac) #define CSBE_DEBUG_STATUS(base) XE_REG((base) + 0x3fc) #define RING_FORCE_TO_NONPRIV(base, i) XE_REG(((base) + 0x4d0) + (i) * 4) diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index da1f198ac107..181913967ac9 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -157,6 +157,7 @@ #define XEHPG_SC_INSTDONE_EXTRA2 XE_REG_MCR(0x7108) #define COMMON_SLICE_CHICKEN4 XE_REG(0x7300, XE_REG_OPTION_MASKED) +#define SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE REG_BIT(12) #define DISABLE_TDC_LOAD_BALANCING_CALC REG_BIT(6) #define COMMON_SLICE_CHICKEN3 XE_REG(0x7304, XE_REG_OPTION_MASKED) diff --git a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h index 57944f90bbf6..994af591a2e8 100644 --- a/drivers/gpu/drm/xe/regs/xe_lrc_layout.h +++ b/drivers/gpu/drm/xe/regs/xe_lrc_layout.h @@ -11,7 +11,9 @@ #define CTX_RING_TAIL (0x06 + 1) #define CTX_RING_START (0x08 + 1) #define CTX_RING_CTL (0x0a + 1) +#define CTX_BB_PER_CTX_PTR (0x12 + 1) #define CTX_TIMESTAMP (0x22 + 1) +#define CTX_TIMESTAMP_UDW (0x24 + 1) #define CTX_INDIRECT_RING_STATE (0x26 + 1) #define CTX_PDP0_UDW (0x30 + 1) #define CTX_PDP0_LDW (0x32 + 1) diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c index ef1e5256c56a..0e502feaca81 100644 --- a/drivers/gpu/drm/xe/tests/xe_mocs.c +++ b/drivers/gpu/drm/xe/tests/xe_mocs.c @@ -46,8 +46,11 @@ static void read_l3cc_table(struct xe_gt *gt, unsigned int fw_ref, i; u32 reg_val; - fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); - KUNIT_ASSERT_NE_MSG(test, fw_ref, 0, "Forcewake Failed.\n"); + fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); + if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) { + xe_force_wake_put(gt_to_fw(gt), fw_ref); + KUNIT_ASSERT_TRUE_MSG(test, true, "Forcewake Failed.\n"); + } for (i = 0; i < info->num_mocs_regs; i++) { if (!(i & 1)) { diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 9f8667ebba85..0482f26aa480 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -330,6 +330,8 @@ struct xe_device { u8 has_sriov:1; /** @info.has_usm: Device has unified shared memory support */ u8 has_usm:1; + /** @info.has_64bit_timestamp: Device supports 64-bit timestamps */ + u8 has_64bit_timestamp:1; /** @info.is_dgfx: is discrete device */ u8 is_dgfx:1; /** diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 606922d9dd73..cd9b1c32f30f 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -830,7 +830,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) { struct xe_device *xe = gt_to_xe(q->gt); struct xe_lrc *lrc; - u32 old_ts, new_ts; + u64 old_ts, new_ts; int idx; /* diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c index fd41113f8572..0bcf97063ff6 100644 --- a/drivers/gpu/drm/xe/xe_gsc.c +++ b/drivers/gpu/drm/xe/xe_gsc.c @@ -555,6 +555,28 @@ void xe_gsc_wait_for_worker_completion(struct xe_gsc *gsc) flush_work(&gsc->work); } +void xe_gsc_stop_prepare(struct xe_gsc *gsc) +{ + struct xe_gt *gt = gsc_to_gt(gsc); + int ret; + + if (!xe_uc_fw_is_loadable(&gsc->fw) || xe_uc_fw_is_in_error_state(&gsc->fw)) + return; + + xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GSC); + + /* + * If the GSC FW load or the proxy init are interrupted, the only way + * to recover it is to do an FLR and reload the GSC from scratch. + * Therefore, let's wait for the init to complete before stopping + * operations. The proxy init is the last step, so we can just wait on + * that + */ + ret = xe_gsc_wait_for_proxy_init_done(gsc); + if (ret) + xe_gt_err(gt, "failed to wait for GSC init completion before uc stop\n"); +} + /* * wa_14015076503: if the GSC FW is loaded, we need to alert it before doing a * GSC engine reset by writing a notification bit in the GS1 register and then diff --git a/drivers/gpu/drm/xe/xe_gsc.h b/drivers/gpu/drm/xe/xe_gsc.h index d99f66c38075..b8b8e0810ad9 100644 --- a/drivers/gpu/drm/xe/xe_gsc.h +++ b/drivers/gpu/drm/xe/xe_gsc.h @@ -16,6 +16,7 @@ struct xe_hw_engine; int xe_gsc_init(struct xe_gsc *gsc); int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc); void xe_gsc_wait_for_worker_completion(struct xe_gsc *gsc); +void xe_gsc_stop_prepare(struct xe_gsc *gsc); void xe_gsc_load_start(struct xe_gsc *gsc); void xe_gsc_hwe_irq_handler(struct xe_hw_engine *hwe, u16 intr_vec); diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.c b/drivers/gpu/drm/xe/xe_gsc_proxy.c index 8cf70b228ff3..d0519cd6704a 100644 --- a/drivers/gpu/drm/xe/xe_gsc_proxy.c +++ b/drivers/gpu/drm/xe/xe_gsc_proxy.c @@ -71,6 +71,17 @@ bool xe_gsc_proxy_init_done(struct xe_gsc *gsc) HECI1_FWSTS1_PROXY_STATE_NORMAL; } +int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc) +{ + struct xe_gt *gt = gsc_to_gt(gsc); + + /* Proxy init can take up to 500ms, so wait double that for safety */ + return xe_mmio_wait32(>->mmio, HECI_FWSTS1(MTL_GSC_HECI1_BASE), + HECI1_FWSTS1_CURRENT_STATE, + HECI1_FWSTS1_PROXY_STATE_NORMAL, + USEC_PER_SEC, NULL, false); +} + static void __gsc_proxy_irq_rmw(struct xe_gsc *gsc, u32 clr, u32 set) { struct xe_gt *gt = gsc_to_gt(gsc); diff --git a/drivers/gpu/drm/xe/xe_gsc_proxy.h b/drivers/gpu/drm/xe/xe_gsc_proxy.h index fdef56995cd4..765602221dbc 100644 --- a/drivers/gpu/drm/xe/xe_gsc_proxy.h +++ b/drivers/gpu/drm/xe/xe_gsc_proxy.h @@ -12,6 +12,7 @@ struct xe_gsc; int xe_gsc_proxy_init(struct xe_gsc *gsc); bool xe_gsc_proxy_init_done(struct xe_gsc *gsc); +int xe_gsc_wait_for_proxy_init_done(struct xe_gsc *gsc); int xe_gsc_proxy_start(struct xe_gsc *gsc); int xe_gsc_proxy_request_handler(struct xe_gsc *gsc); diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 10a9e3c72b36..66198cf2662c 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -857,7 +857,7 @@ void xe_gt_suspend_prepare(struct xe_gt *gt) fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); - xe_uc_stop_prepare(>->uc); + xe_uc_suspend_prepare(>->uc); xe_force_wake_put(gt_to_fw(gt), fw_ref); } diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c index 2d63a69cbfa3..f7005a3643e6 100644 --- a/drivers/gpu/drm/xe/xe_gt_debugfs.c +++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c @@ -92,22 +92,23 @@ static int hw_engines(struct xe_gt *gt, struct drm_printer *p) struct xe_hw_engine *hwe; enum xe_hw_engine_id id; unsigned int fw_ref; + int ret = 0; xe_pm_runtime_get(xe); fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) { - xe_pm_runtime_put(xe); - xe_force_wake_put(gt_to_fw(gt), fw_ref); - return -ETIMEDOUT; + ret = -ETIMEDOUT; + goto fw_put; } for_each_hw_engine(hwe, gt, id) xe_hw_engine_print(hwe, p); +fw_put: xe_force_wake_put(gt_to_fw(gt), fw_ref); xe_pm_runtime_put(xe); - return 0; + return ret; } static int powergate_info(struct xe_gt *gt, struct drm_printer *p) diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index c5ad9a0a89c2..0c22b3a36655 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -435,9 +435,16 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue) num_eus = bitmap_weight(gt->fuse_topo.eu_mask_per_dss, XE_MAX_EU_FUSE_BITS) * num_dss; - /* user can issue separate page faults per EU and per CS */ + /* + * user can issue separate page faults per EU and per CS + * + * XXX: Multiplier required as compute UMD are getting PF queue errors + * without it. Follow on why this multiplier is required. + */ +#define PF_MULTIPLIER 8 pf_queue->num_dw = - (num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW; + (num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER; +#undef PF_MULTIPLIER pf_queue->gt = gt; pf_queue->data = devm_kcalloc(xe->drm.dev, pf_queue->num_dw, diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 31bc2022bfc2..769781d577df 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -941,7 +941,7 @@ static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job) return xe_sched_invalidate_job(job, 2); } - ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]); + ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(q->lrc[0])); ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]); /* diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index df3ceddede07..03bfba696b37 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -24,6 +24,7 @@ #include "xe_hw_fence.h" #include "xe_map.h" #include "xe_memirq.h" +#include "xe_mmio.h" #include "xe_sriov.h" #include "xe_trace_lrc.h" #include "xe_vm.h" @@ -650,6 +651,7 @@ u32 xe_lrc_pphwsp_offset(struct xe_lrc *lrc) #define LRC_START_SEQNO_PPHWSP_OFFSET (LRC_SEQNO_PPHWSP_OFFSET + 8) #define LRC_CTX_JOB_TIMESTAMP_OFFSET (LRC_START_SEQNO_PPHWSP_OFFSET + 8) #define LRC_PARALLEL_PPHWSP_OFFSET 2048 +#define LRC_ENGINE_ID_PPHWSP_OFFSET 2096 #define LRC_PPHWSP_SIZE SZ_4K u32 xe_lrc_regs_offset(struct xe_lrc *lrc) @@ -684,7 +686,7 @@ static inline u32 __xe_lrc_start_seqno_offset(struct xe_lrc *lrc) static u32 __xe_lrc_ctx_job_timestamp_offset(struct xe_lrc *lrc) { - /* The start seqno is stored in the driver-defined portion of PPHWSP */ + /* This is stored in the driver-defined portion of PPHWSP */ return xe_lrc_pphwsp_offset(lrc) + LRC_CTX_JOB_TIMESTAMP_OFFSET; } @@ -694,11 +696,21 @@ static inline u32 __xe_lrc_parallel_offset(struct xe_lrc *lrc) return xe_lrc_pphwsp_offset(lrc) + LRC_PARALLEL_PPHWSP_OFFSET; } +static inline u32 __xe_lrc_engine_id_offset(struct xe_lrc *lrc) +{ + return xe_lrc_pphwsp_offset(lrc) + LRC_ENGINE_ID_PPHWSP_OFFSET; +} + static u32 __xe_lrc_ctx_timestamp_offset(struct xe_lrc *lrc) { return __xe_lrc_regs_offset(lrc) + CTX_TIMESTAMP * sizeof(u32); } +static u32 __xe_lrc_ctx_timestamp_udw_offset(struct xe_lrc *lrc) +{ + return __xe_lrc_regs_offset(lrc) + CTX_TIMESTAMP_UDW * sizeof(u32); +} + static inline u32 __xe_lrc_indirect_ring_offset(struct xe_lrc *lrc) { /* Indirect ring state page is at the very end of LRC */ @@ -726,8 +738,10 @@ DECL_MAP_ADDR_HELPERS(regs) DECL_MAP_ADDR_HELPERS(start_seqno) DECL_MAP_ADDR_HELPERS(ctx_job_timestamp) DECL_MAP_ADDR_HELPERS(ctx_timestamp) +DECL_MAP_ADDR_HELPERS(ctx_timestamp_udw) DECL_MAP_ADDR_HELPERS(parallel) DECL_MAP_ADDR_HELPERS(indirect_ring) +DECL_MAP_ADDR_HELPERS(engine_id) #undef DECL_MAP_ADDR_HELPERS @@ -743,18 +757,37 @@ u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc) } /** + * xe_lrc_ctx_timestamp_udw_ggtt_addr() - Get ctx timestamp udw GGTT address + * @lrc: Pointer to the lrc. + * + * Returns: ctx timestamp udw GGTT address + */ +u32 xe_lrc_ctx_timestamp_udw_ggtt_addr(struct xe_lrc *lrc) +{ + return __xe_lrc_ctx_timestamp_udw_ggtt_addr(lrc); +} + +/** * xe_lrc_ctx_timestamp() - Read ctx timestamp value * @lrc: Pointer to the lrc. * * Returns: ctx timestamp value */ -u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc) +u64 xe_lrc_ctx_timestamp(struct xe_lrc *lrc) { struct xe_device *xe = lrc_to_xe(lrc); struct iosys_map map; + u32 ldw, udw = 0; map = __xe_lrc_ctx_timestamp_map(lrc); - return xe_map_read32(xe, &map); + ldw = xe_map_read32(xe, &map); + + if (xe->info.has_64bit_timestamp) { + map = __xe_lrc_ctx_timestamp_udw_map(lrc); + udw = xe_map_read32(xe, &map); + } + + return (u64)udw << 32 | ldw; } /** @@ -864,7 +897,7 @@ static void *empty_lrc_data(struct xe_hw_engine *hwe) static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm) { - u64 desc = xe_vm_pdp4_descriptor(vm, lrc->tile); + u64 desc = xe_vm_pdp4_descriptor(vm, gt_to_tile(lrc->gt)); xe_lrc_write_ctx_reg(lrc, CTX_PDP0_UDW, upper_32_bits(desc)); xe_lrc_write_ctx_reg(lrc, CTX_PDP0_LDW, lower_32_bits(desc)); @@ -877,6 +910,65 @@ static void xe_lrc_finish(struct xe_lrc *lrc) xe_bo_unpin(lrc->bo); xe_bo_unlock(lrc->bo); xe_bo_put(lrc->bo); + xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo); +} + +/* + * xe_lrc_setup_utilization() - Setup wa bb to assist in calculating active + * context run ticks. + * @lrc: Pointer to the lrc. + * + * Context Timestamp (CTX_TIMESTAMP) in the LRC accumulates the run ticks of the + * context, but only gets updated when the context switches out. In order to + * check how long a context has been active before it switches out, two things + * are required: + * + * (1) Determine if the context is running: + * To do so, we program the WA BB to set an initial value for CTX_TIMESTAMP in + * the LRC. The value chosen is 1 since 0 is the initial value when the LRC is + * initialized. During a query, we just check for this value to determine if the + * context is active. If the context switched out, it would overwrite this + * location with the actual CTX_TIMESTAMP MMIO value. Note that WA BB runs as + * the last part of context restore, so reusing this LRC location will not + * clobber anything. + * + * (2) Calculate the time that the context has been active for: + * The CTX_TIMESTAMP ticks only when the context is active. If a context is + * active, we just use the CTX_TIMESTAMP MMIO as the new value of utilization. + * While doing so, we need to read the CTX_TIMESTAMP MMIO for the specific + * engine instance. Since we do not know which instance the context is running + * on until it is scheduled, we also read the ENGINE_ID MMIO in the WA BB and + * store it in the PPHSWP. + */ +#define CONTEXT_ACTIVE 1ULL +static void xe_lrc_setup_utilization(struct xe_lrc *lrc) +{ + u32 *cmd; + + cmd = lrc->bb_per_ctx_bo->vmap.vaddr; + + *cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET; + *cmd++ = ENGINE_ID(0).addr; + *cmd++ = __xe_lrc_engine_id_ggtt_addr(lrc); + *cmd++ = 0; + + *cmd++ = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1); + *cmd++ = __xe_lrc_ctx_timestamp_ggtt_addr(lrc); + *cmd++ = 0; + *cmd++ = lower_32_bits(CONTEXT_ACTIVE); + + if (lrc_to_xe(lrc)->info.has_64bit_timestamp) { + *cmd++ = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1); + *cmd++ = __xe_lrc_ctx_timestamp_udw_ggtt_addr(lrc); + *cmd++ = 0; + *cmd++ = upper_32_bits(CONTEXT_ACTIVE); + } + + *cmd++ = MI_BATCH_BUFFER_END; + + xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, + xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1); + } #define PVC_CTX_ASID (0x2e + 1) @@ -893,31 +985,40 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, void *init_data = NULL; u32 arb_enable; u32 lrc_size; + u32 bo_flags; int err; kref_init(&lrc->refcount); + lrc->gt = gt; lrc->flags = 0; lrc_size = ring_size + xe_gt_lrc_size(gt, hwe->class); if (xe_gt_has_indirect_ring_state(gt)) lrc->flags |= XE_LRC_FLAG_INDIRECT_RING_STATE; + bo_flags = XE_BO_FLAG_VRAM_IF_DGFX(tile) | XE_BO_FLAG_GGTT | + XE_BO_FLAG_GGTT_INVALIDATE; + /* * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address * via VM bind calls. */ lrc->bo = xe_bo_create_pin_map(xe, tile, vm, lrc_size, ttm_bo_type_kernel, - XE_BO_FLAG_VRAM_IF_DGFX(tile) | - XE_BO_FLAG_GGTT | - XE_BO_FLAG_GGTT_INVALIDATE); + bo_flags); if (IS_ERR(lrc->bo)) return PTR_ERR(lrc->bo); + lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K, + ttm_bo_type_kernel, + bo_flags); + if (IS_ERR(lrc->bb_per_ctx_bo)) { + err = PTR_ERR(lrc->bb_per_ctx_bo); + goto err_lrc_finish; + } + lrc->size = lrc_size; - lrc->tile = gt_to_tile(hwe->gt); lrc->ring.size = ring_size; lrc->ring.tail = 0; - lrc->ctx_timestamp = 0; xe_hw_fence_ctx_init(&lrc->fence_ctx, hwe->gt, hwe->fence_irq, hwe->name); @@ -990,7 +1091,10 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, xe_lrc_read_ctx_reg(lrc, CTX_CONTEXT_CONTROL) | _MASKED_BIT_ENABLE(CTX_CTRL_PXP_ENABLE)); + lrc->ctx_timestamp = 0; xe_lrc_write_ctx_reg(lrc, CTX_TIMESTAMP, 0); + if (lrc_to_xe(lrc)->info.has_64bit_timestamp) + xe_lrc_write_ctx_reg(lrc, CTX_TIMESTAMP_UDW, 0); if (xe->info.has_asid && vm) xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid); @@ -1019,6 +1123,8 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, map = __xe_lrc_start_seqno_map(lrc); xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1); + xe_lrc_setup_utilization(lrc); + return 0; err_lrc_finish: @@ -1238,6 +1344,21 @@ struct iosys_map xe_lrc_parallel_map(struct xe_lrc *lrc) return __xe_lrc_parallel_map(lrc); } +/** + * xe_lrc_engine_id() - Read engine id value + * @lrc: Pointer to the lrc. + * + * Returns: context id value + */ +static u32 xe_lrc_engine_id(struct xe_lrc *lrc) +{ + struct xe_device *xe = lrc_to_xe(lrc); + struct iosys_map map; + + map = __xe_lrc_engine_id_map(lrc); + return xe_map_read32(xe, &map); +} + static int instr_dw(u32 cmd_header) { /* GFXPIPE "SINGLE_DW" opcodes are a single dword */ @@ -1684,7 +1805,7 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc) snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc); snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset; snapshot->lrc_snapshot = NULL; - snapshot->ctx_timestamp = xe_lrc_ctx_timestamp(lrc); + snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc)); snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc); return snapshot; } @@ -1784,22 +1905,74 @@ void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot) kfree(snapshot); } +static int get_ctx_timestamp(struct xe_lrc *lrc, u32 engine_id, u64 *reg_ctx_ts) +{ + u16 class = REG_FIELD_GET(ENGINE_CLASS_ID, engine_id); + u16 instance = REG_FIELD_GET(ENGINE_INSTANCE_ID, engine_id); + struct xe_hw_engine *hwe; + u64 val; + + hwe = xe_gt_hw_engine(lrc->gt, class, instance, false); + if (xe_gt_WARN_ONCE(lrc->gt, !hwe || xe_hw_engine_is_reserved(hwe), + "Unexpected engine class:instance %d:%d for context utilization\n", + class, instance)) + return -1; + + if (lrc_to_xe(lrc)->info.has_64bit_timestamp) + val = xe_mmio_read64_2x32(&hwe->gt->mmio, + RING_CTX_TIMESTAMP(hwe->mmio_base)); + else + val = xe_mmio_read32(&hwe->gt->mmio, + RING_CTX_TIMESTAMP(hwe->mmio_base)); + + *reg_ctx_ts = val; + + return 0; +} + /** * xe_lrc_update_timestamp() - Update ctx timestamp * @lrc: Pointer to the lrc. * @old_ts: Old timestamp value * * Populate @old_ts current saved ctx timestamp, read new ctx timestamp and - * update saved value. + * update saved value. With support for active contexts, the calculation may be + * slightly racy, so follow a read-again logic to ensure that the context is + * still active before returning the right timestamp. * * Returns: New ctx timestamp value */ -u32 xe_lrc_update_timestamp(struct xe_lrc *lrc, u32 *old_ts) +u64 xe_lrc_update_timestamp(struct xe_lrc *lrc, u64 *old_ts) { + u64 lrc_ts, reg_ts; + u32 engine_id; + *old_ts = lrc->ctx_timestamp; - lrc->ctx_timestamp = xe_lrc_ctx_timestamp(lrc); + lrc_ts = xe_lrc_ctx_timestamp(lrc); + /* CTX_TIMESTAMP mmio read is invalid on VF, so return the LRC value */ + if (IS_SRIOV_VF(lrc_to_xe(lrc))) { + lrc->ctx_timestamp = lrc_ts; + goto done; + } + + if (lrc_ts == CONTEXT_ACTIVE) { + engine_id = xe_lrc_engine_id(lrc); + if (!get_ctx_timestamp(lrc, engine_id, ®_ts)) + lrc->ctx_timestamp = reg_ts; + + /* read lrc again to ensure context is still active */ + lrc_ts = xe_lrc_ctx_timestamp(lrc); + } + + /* + * If context switched out, just use the lrc_ts. Note that this needs to + * be a separate if condition. + */ + if (lrc_ts != CONTEXT_ACTIVE) + lrc->ctx_timestamp = lrc_ts; +done: trace_xe_lrc_update_timestamp(lrc, *old_ts); return lrc->ctx_timestamp; diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h index 0b40f349ab95..eb6e8de8c939 100644 --- a/drivers/gpu/drm/xe/xe_lrc.h +++ b/drivers/gpu/drm/xe/xe_lrc.h @@ -120,7 +120,8 @@ void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot); u32 xe_lrc_ctx_timestamp_ggtt_addr(struct xe_lrc *lrc); -u32 xe_lrc_ctx_timestamp(struct xe_lrc *lrc); +u32 xe_lrc_ctx_timestamp_udw_ggtt_addr(struct xe_lrc *lrc); +u64 xe_lrc_ctx_timestamp(struct xe_lrc *lrc); u32 xe_lrc_ctx_job_timestamp_ggtt_addr(struct xe_lrc *lrc); u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc); @@ -136,6 +137,6 @@ u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc); * * Returns the current LRC timestamp */ -u32 xe_lrc_update_timestamp(struct xe_lrc *lrc, u32 *old_ts); +u64 xe_lrc_update_timestamp(struct xe_lrc *lrc, u64 *old_ts); #endif diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h index 71ecb453f811..ae24cf6f8dd9 100644 --- a/drivers/gpu/drm/xe/xe_lrc_types.h +++ b/drivers/gpu/drm/xe/xe_lrc_types.h @@ -25,8 +25,8 @@ struct xe_lrc { /** @size: size of lrc including any indirect ring state page */ u32 size; - /** @tile: tile which this LRC belongs to */ - struct xe_tile *tile; + /** @gt: gt which this LRC belongs to */ + struct xe_gt *gt; /** @flags: LRC flags */ #define XE_LRC_FLAG_INDIRECT_RING_STATE 0x1 @@ -52,7 +52,10 @@ struct xe_lrc { struct xe_hw_fence_ctx fence_ctx; /** @ctx_timestamp: readout value of CTX_TIMESTAMP on last update */ - u32 ctx_timestamp; + u64 ctx_timestamp; + + /** @bb_per_ctx_bo: buffer object for per context batch wa buffer */ + struct xe_bo *bb_per_ctx_bo; }; struct xe_lrc_snapshot; diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index 70a36e777546..46301f341773 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -75,12 +75,12 @@ static void mmio_multi_tile_setup(struct xe_device *xe, size_t tile_mmio_size) * is fine as it's going to the root tile's mmio, that's * guaranteed to be initialized earlier in xe_mmio_probe_early() */ - mtcfg = xe_mmio_read64_2x32(mmio, XEHP_MTCFG_ADDR); + mtcfg = xe_mmio_read32(mmio, XEHP_MTCFG_ADDR); tile_count = REG_FIELD_GET(TILE_COUNT, mtcfg) + 1; if (tile_count < xe->info.tile_count) { drm_info(&xe->drm, "tile_count: %d, reduced_tile_count %d\n", - xe->info.tile_count, tile_count); + xe->info.tile_count, tile_count); xe->info.tile_count = tile_count; /* @@ -128,7 +128,7 @@ int xe_mmio_probe_early(struct xe_device *xe) */ xe->mmio.size = pci_resource_len(pdev, GTTMMADR_BAR); xe->mmio.regs = pci_iomap(pdev, GTTMMADR_BAR, 0); - if (xe->mmio.regs == NULL) { + if (!xe->mmio.regs) { drm_err(&xe->drm, "failed to map registers\n"); return -EIO; } @@ -309,8 +309,8 @@ u64 xe_mmio_read64_2x32(struct xe_mmio *mmio, struct xe_reg reg) return (u64)udw << 32 | ldw; } -static int __xe_mmio_wait32(struct xe_mmio *mmio, struct xe_reg reg, u32 mask, u32 val, u32 timeout_us, - u32 *out_val, bool atomic, bool expect_match) +static int __xe_mmio_wait32(struct xe_mmio *mmio, struct xe_reg reg, u32 mask, u32 val, + u32 timeout_us, u32 *out_val, bool atomic, bool expect_match) { ktime_t cur = ktime_get_raw(); const ktime_t end = ktime_add_us(cur, timeout_us); diff --git a/drivers/gpu/drm/xe/xe_mocs.c b/drivers/gpu/drm/xe/xe_mocs.c index 31dade91a089..0c737413fcb6 100644 --- a/drivers/gpu/drm/xe/xe_mocs.c +++ b/drivers/gpu/drm/xe/xe_mocs.c @@ -775,22 +775,23 @@ void xe_mocs_init(struct xe_gt *gt) void xe_mocs_dump(struct xe_gt *gt, struct drm_printer *p) { struct xe_device *xe = gt_to_xe(gt); + enum xe_force_wake_domains domain; struct xe_mocs_info table; unsigned int fw_ref, flags; flags = get_mocs_settings(xe, &table); + domain = flags & HAS_LNCF_MOCS ? XE_FORCEWAKE_ALL : XE_FW_GT; xe_pm_runtime_get_noresume(xe); - fw_ref = xe_force_wake_get(gt_to_fw(gt), - flags & HAS_LNCF_MOCS ? - XE_FORCEWAKE_ALL : XE_FW_GT); - if (!fw_ref) + fw_ref = xe_force_wake_get(gt_to_fw(gt), domain); + + if (!xe_force_wake_ref_has_domain(fw_ref, domain)) goto err_fw; table.ops->dump(&table, flags, gt, p); - xe_force_wake_put(gt_to_fw(gt), fw_ref); err_fw: + xe_force_wake_put(gt_to_fw(gt), fw_ref); xe_pm_runtime_put(xe); } diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c index 9f4632e39a1a..e861c694f336 100644 --- a/drivers/gpu/drm/xe/xe_module.c +++ b/drivers/gpu/drm/xe/xe_module.c @@ -29,9 +29,6 @@ struct xe_modparam xe_modparam = { module_param_named(svm_notifier_size, xe_modparam.svm_notifier_size, uint, 0600); MODULE_PARM_DESC(svm_notifier_size, "Set the svm notifier size(in MiB), must be power of 2"); -module_param_named(always_migrate_to_vram, xe_modparam.always_migrate_to_vram, bool, 0444); -MODULE_PARM_DESC(always_migrate_to_vram, "Always migrate to VRAM on GPU fault"); - module_param_named_unsafe(force_execlist, xe_modparam.force_execlist, bool, 0444); MODULE_PARM_DESC(force_execlist, "Force Execlist submission"); diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h index 84339e509c80..5a3bfea8b7b4 100644 --- a/drivers/gpu/drm/xe/xe_module.h +++ b/drivers/gpu/drm/xe/xe_module.h @@ -12,7 +12,6 @@ struct xe_modparam { bool force_execlist; bool probe_display; - bool always_migrate_to_vram; u32 force_vram_bar_size; int guc_log_level; char *guc_firmware_path; diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 818f023166d5..f4d108dc49b1 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -140,6 +140,7 @@ static const struct xe_graphics_desc graphics_xelpg = { .has_indirect_ring_state = 1, \ .has_range_tlb_invalidation = 1, \ .has_usm = 1, \ + .has_64bit_timestamp = 1, \ .va_bits = 48, \ .vm_max_level = 4, \ .hw_engine_mask = \ @@ -668,6 +669,7 @@ static int xe_info_init(struct xe_device *xe, xe->info.has_range_tlb_invalidation = graphics_desc->has_range_tlb_invalidation; xe->info.has_usm = graphics_desc->has_usm; + xe->info.has_64bit_timestamp = graphics_desc->has_64bit_timestamp; for_each_remote_tile(tile, xe, id) { int err; diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h index e9b9bbc138d3..ca6b10d35573 100644 --- a/drivers/gpu/drm/xe/xe_pci_types.h +++ b/drivers/gpu/drm/xe/xe_pci_types.h @@ -21,6 +21,7 @@ struct xe_graphics_desc { u8 has_indirect_ring_state:1; u8 has_range_tlb_invalidation:1; u8 has_usm:1; + u8 has_64bit_timestamp:1; }; struct xe_media_desc { diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index ffaf0d02dc7d..856038553b81 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -2232,11 +2232,19 @@ static void op_commit(struct xe_vm *vm, } case DRM_GPUVA_OP_DRIVER: { + /* WRITE_ONCE pairs with READ_ONCE in xe_svm.c */ + if (op->subop == XE_VMA_SUBOP_MAP_RANGE) { - op->map_range.range->tile_present |= BIT(tile->id); - op->map_range.range->tile_invalidated &= ~BIT(tile->id); + WRITE_ONCE(op->map_range.range->tile_present, + op->map_range.range->tile_present | + BIT(tile->id)); + WRITE_ONCE(op->map_range.range->tile_invalidated, + op->map_range.range->tile_invalidated & + ~BIT(tile->id)); } else if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE) { - op->unmap_range.range->tile_present &= ~BIT(tile->id); + WRITE_ONCE(op->unmap_range.range->tile_present, + op->unmap_range.range->tile_present & + ~BIT(tile->id)); } break; } diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index a7582b097ae6..bc1689db4cd7 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -234,13 +234,10 @@ static u32 get_ppgtt_flag(struct xe_sched_job *job) static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i) { - dw[i++] = MI_COPY_MEM_MEM | MI_COPY_MEM_MEM_SRC_GGTT | - MI_COPY_MEM_MEM_DST_GGTT; + dw[i++] = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET; + dw[i++] = RING_CTX_TIMESTAMP(0).addr; dw[i++] = xe_lrc_ctx_job_timestamp_ggtt_addr(lrc); dw[i++] = 0; - dw[i++] = xe_lrc_ctx_timestamp_ggtt_addr(lrc); - dw[i++] = 0; - dw[i++] = MI_NOOP; return i; } diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c index 8184390f9c7b..86d47aaf0358 100644 --- a/drivers/gpu/drm/xe/xe_shrinker.c +++ b/drivers/gpu/drm/xe/xe_shrinker.c @@ -227,7 +227,7 @@ struct xe_shrinker *xe_shrinker_create(struct xe_device *xe) if (!shrinker) return ERR_PTR(-ENOMEM); - shrinker->shrink = shrinker_alloc(0, "xe system shrinker"); + shrinker->shrink = shrinker_alloc(0, "drm-xe_gem:%s", xe->drm.unique); if (!shrinker->shrink) { kfree(shrinker); return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 0b6547c06961..975094c1a582 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -15,8 +15,17 @@ static bool xe_svm_range_in_vram(struct xe_svm_range *range) { - /* Not reliable without notifier lock */ - return range->base.flags.has_devmem_pages; + /* + * Advisory only check whether the range is currently backed by VRAM + * memory. + */ + + struct drm_gpusvm_range_flags flags = { + /* Pairs with WRITE_ONCE in drm_gpusvm.c */ + .__flags = READ_ONCE(range->base.flags.__flags), + }; + + return flags.has_devmem_pages; } static bool xe_svm_range_has_vram_binding(struct xe_svm_range *range) @@ -645,9 +654,16 @@ void xe_svm_fini(struct xe_vm *vm) } static bool xe_svm_range_is_valid(struct xe_svm_range *range, - struct xe_tile *tile) + struct xe_tile *tile, + bool devmem_only) { - return (range->tile_present & ~range->tile_invalidated) & BIT(tile->id); + /* + * Advisory only check whether the range currently has a valid mapping, + * READ_ONCE pairs with WRITE_ONCE in xe_pt.c + */ + return ((READ_ONCE(range->tile_present) & + ~READ_ONCE(range->tile_invalidated)) & BIT(tile->id)) && + (!devmem_only || xe_svm_range_in_vram(range)); } static struct xe_vram_region *tile_to_vr(struct xe_tile *tile) @@ -712,6 +728,36 @@ unlock: return err; } +static bool supports_4K_migration(struct xe_device *xe) +{ + if (xe->info.vram_flags & XE_VRAM_FLAGS_NEED64K) + return false; + + return true; +} + +static bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, + struct xe_vma *vma) +{ + struct xe_vm *vm = range_to_vm(&range->base); + u64 range_size = xe_svm_range_size(range); + + if (!range->base.flags.migrate_devmem) + return false; + + if (xe_svm_range_in_vram(range)) { + drm_dbg(&vm->xe->drm, "Range is already in VRAM\n"); + return false; + } + + if (range_size <= SZ_64K && !supports_4K_migration(vm->xe)) { + drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n"); + return false; + } + + return true; +} + /** * xe_svm_handle_pagefault() - SVM handle page fault * @vm: The VM. @@ -735,11 +781,16 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma, IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR), .check_pages_threshold = IS_DGFX(vm->xe) && IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? SZ_64K : 0, + .devmem_only = atomic && IS_DGFX(vm->xe) && + IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR), + .timeslice_ms = atomic && IS_DGFX(vm->xe) && + IS_ENABLED(CONFIG_DRM_XE_DEVMEM_MIRROR) ? 5 : 0, }; struct xe_svm_range *range; struct drm_gpusvm_range *r; struct drm_exec exec; struct dma_fence *fence; + int migrate_try_count = ctx.devmem_only ? 3 : 1; ktime_t end = 0; int err; @@ -758,24 +809,31 @@ retry: if (IS_ERR(r)) return PTR_ERR(r); + if (ctx.devmem_only && !r->flags.migrate_devmem) + return -EACCES; + range = to_xe_range(r); - if (xe_svm_range_is_valid(range, tile)) + if (xe_svm_range_is_valid(range, tile, ctx.devmem_only)) return 0; range_debug(range, "PAGE FAULT"); - /* XXX: Add migration policy, for now migrate range once */ - if (!range->skip_migrate && range->base.flags.migrate_devmem && - xe_svm_range_size(range) >= SZ_64K) { - range->skip_migrate = true; - + if (--migrate_try_count >= 0 && + xe_svm_range_needs_migrate_to_vram(range, vma)) { err = xe_svm_alloc_vram(vm, tile, range, &ctx); + ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */ if (err) { - drm_dbg(&vm->xe->drm, - "VRAM allocation failed, falling back to " - "retrying fault, asid=%u, errno=%pe\n", - vm->usm.asid, ERR_PTR(err)); - goto retry; + if (migrate_try_count || !ctx.devmem_only) { + drm_dbg(&vm->xe->drm, + "VRAM allocation failed, falling back to retrying fault, asid=%u, errno=%pe\n", + vm->usm.asid, ERR_PTR(err)); + goto retry; + } else { + drm_err(&vm->xe->drm, + "VRAM allocation failed, retry count exceeded, asid=%u, errno=%pe\n", + vm->usm.asid, ERR_PTR(err)); + return err; + } } } @@ -783,15 +841,23 @@ retry: err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r, &ctx); /* Corner where CPU mappings have changed */ if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) { - if (err == -EOPNOTSUPP) { - range_debug(range, "PAGE FAULT - EVICT PAGES"); - drm_gpusvm_range_evict(&vm->svm.gpusvm, &range->base); + ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */ + if (migrate_try_count > 0 || !ctx.devmem_only) { + if (err == -EOPNOTSUPP) { + range_debug(range, "PAGE FAULT - EVICT PAGES"); + drm_gpusvm_range_evict(&vm->svm.gpusvm, + &range->base); + } + drm_dbg(&vm->xe->drm, + "Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n", + vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err)); + range_debug(range, "PAGE FAULT - RETRY PAGES"); + goto retry; + } else { + drm_err(&vm->xe->drm, + "Get pages failed, retry count exceeded, asid=%u, gpusvm=%p, errno=%pe\n", + vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err)); } - drm_dbg(&vm->xe->drm, - "Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno=%pe\n", - vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err)); - range_debug(range, "PAGE FAULT - RETRY PAGES"); - goto retry; } if (err) { range_debug(range, "PAGE FAULT - FAIL PAGE COLLECT"); @@ -815,6 +881,7 @@ retry_bind: drm_exec_fini(&exec); err = PTR_ERR(fence); if (err == -EAGAIN) { + ctx.timeslice_ms <<= 1; /* Double timeslice if we have to retry */ range_debug(range, "PAGE FAULT - RETRY BIND"); goto retry; } @@ -825,9 +892,6 @@ retry_bind: } drm_exec_fini(&exec); - if (xe_modparam.always_migrate_to_vram) - range->skip_migrate = false; - dma_fence_wait(fence, false); dma_fence_put(fence); @@ -947,3 +1011,15 @@ int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr) return 0; } #endif + +/** + * xe_svm_flush() - SVM flush + * @vm: The VM. + * + * Flush all SVM actions. + */ +void xe_svm_flush(struct xe_vm *vm) +{ + if (xe_vm_in_fault_mode(vm)) + flush_work(&vm->svm.garbage_collector.work); +} diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h index e059590e5076..fe58ac2f4baa 100644 --- a/drivers/gpu/drm/xe/xe_svm.h +++ b/drivers/gpu/drm/xe/xe_svm.h @@ -36,11 +36,6 @@ struct xe_svm_range { * range. Protected by GPU SVM notifier lock. */ u8 tile_invalidated; - /** - * @skip_migrate: Skip migration to VRAM, protected by GPU fault handler - * locking. - */ - u8 skip_migrate :1; }; #if IS_ENABLED(CONFIG_DRM_GPUSVM) @@ -72,6 +67,9 @@ bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end); int xe_svm_bo_evict(struct xe_bo *bo); void xe_svm_range_debug(struct xe_svm_range *range, const char *operation); + +void xe_svm_flush(struct xe_vm *vm); + #else static inline bool xe_svm_range_pages_valid(struct xe_svm_range *range) { @@ -124,6 +122,11 @@ static inline void xe_svm_range_debug(struct xe_svm_range *range, const char *operation) { } + +static inline void xe_svm_flush(struct xe_vm *vm) +{ +} + #endif /** diff --git a/drivers/gpu/drm/xe/xe_trace_lrc.h b/drivers/gpu/drm/xe/xe_trace_lrc.h index 5c669a0b2180..d525cbee1e34 100644 --- a/drivers/gpu/drm/xe/xe_trace_lrc.h +++ b/drivers/gpu/drm/xe/xe_trace_lrc.h @@ -19,12 +19,12 @@ #define __dev_name_lrc(lrc) dev_name(gt_to_xe((lrc)->fence_ctx.gt)->drm.dev) TRACE_EVENT(xe_lrc_update_timestamp, - TP_PROTO(struct xe_lrc *lrc, uint32_t old), + TP_PROTO(struct xe_lrc *lrc, uint64_t old), TP_ARGS(lrc, old), TP_STRUCT__entry( __field(struct xe_lrc *, lrc) - __field(u32, old) - __field(u32, new) + __field(u64, old) + __field(u64, new) __string(name, lrc->fence_ctx.name) __string(device_id, __dev_name_lrc(lrc)) ), @@ -36,7 +36,7 @@ TRACE_EVENT(xe_lrc_update_timestamp, __assign_str(name); __assign_str(device_id); ), - TP_printk("lrc=:%p lrc->name=%s old=%u new=%u device_id:%s", + TP_printk("lrc=:%p lrc->name=%s old=%llu new=%llu device_id:%s", __entry->lrc, __get_str(name), __entry->old, __entry->new, __get_str(device_id)) diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c index c14bd2282044..3a8751a8b92d 100644 --- a/drivers/gpu/drm/xe/xe_uc.c +++ b/drivers/gpu/drm/xe/xe_uc.c @@ -244,7 +244,7 @@ void xe_uc_gucrc_disable(struct xe_uc *uc) void xe_uc_stop_prepare(struct xe_uc *uc) { - xe_gsc_wait_for_worker_completion(&uc->gsc); + xe_gsc_stop_prepare(&uc->gsc); xe_guc_stop_prepare(&uc->guc); } @@ -278,6 +278,12 @@ again: goto again; } +void xe_uc_suspend_prepare(struct xe_uc *uc) +{ + xe_gsc_wait_for_worker_completion(&uc->gsc); + xe_guc_stop_prepare(&uc->guc); +} + int xe_uc_suspend(struct xe_uc *uc) { /* GuC submission not enabled, nothing to do */ diff --git a/drivers/gpu/drm/xe/xe_uc.h b/drivers/gpu/drm/xe/xe_uc.h index 3813c1ede450..c23e6f5e2514 100644 --- a/drivers/gpu/drm/xe/xe_uc.h +++ b/drivers/gpu/drm/xe/xe_uc.h @@ -18,6 +18,7 @@ int xe_uc_reset_prepare(struct xe_uc *uc); void xe_uc_stop_prepare(struct xe_uc *uc); void xe_uc_stop(struct xe_uc *uc); int xe_uc_start(struct xe_uc *uc); +void xe_uc_suspend_prepare(struct xe_uc *uc); int xe_uc_suspend(struct xe_uc *uc); int xe_uc_sanitize_reset(struct xe_uc *uc); void xe_uc_declare_wedged(struct xe_uc *uc); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 60303998bd61..367c84b90e9e 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3312,8 +3312,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) } /* Ensure all UNMAPs visible */ - if (xe_vm_in_fault_mode(vm)) - flush_work(&vm->svm.garbage_collector.work); + xe_svm_flush(vm); err = down_write_killable(&vm->lock); if (err) diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index 24f644c0a673..2f833f0d575f 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -815,6 +815,10 @@ static const struct xe_rtp_entry_sr lrc_was[] = { XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX)) }, + { XE_RTP_NAME("22021007897"), + XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)), + XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN4, SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE)) + }, /* Xe3_LPG */ { XE_RTP_NAME("14021490052"), diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs index 17c9660da450..ab0e5a72a059 100644 --- a/drivers/gpu/nova-core/gpu.rs +++ b/drivers/gpu/nova-core/gpu.rs @@ -93,7 +93,7 @@ impl Chipset { // For now, redirect to fmt::Debug for convenience. impl fmt::Display for Chipset { fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - write!(f, "{:?}", self) + write!(f, "{self:?}") } } diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c index 25f0ebfcbd5f..0a9b44ce4904 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c @@ -83,6 +83,9 @@ static int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata) case ALS_IDX: privdata->dev_en.is_als_present = false; break; + case SRA_IDX: + privdata->dev_en.is_sra_present = false; + break; } if (cl_data->sensor_sts[i] == SENSOR_ENABLED) { @@ -134,9 +137,6 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) for (i = 0; i < cl_data->num_hid_devices; i++) { cl_data->sensor_sts[i] = SENSOR_DISABLED; - if (cl_data->num_hid_devices == 1 && cl_data->sensor_idx[0] == SRA_IDX) - break; - if (cl_data->sensor_idx[i] == SRA_IDX) { info.sensor_idx = cl_data->sensor_idx[i]; writel(0, privdata->mmio + amd_get_p2c_val(privdata, 0)); @@ -145,8 +145,10 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) (privdata, cl_data->sensor_idx[i], ENABLE_SENSOR); cl_data->sensor_sts[i] = (status == 0) ? SENSOR_ENABLED : SENSOR_DISABLED; - if (cl_data->sensor_sts[i] == SENSOR_ENABLED) + if (cl_data->sensor_sts[i] == SENSOR_ENABLED) { + cl_data->is_any_sensor_enabled = true; privdata->dev_en.is_sra_present = true; + } continue; } @@ -238,6 +240,8 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) cleanup: amd_sfh_hid_client_deinit(privdata); for (i = 0; i < cl_data->num_hid_devices; i++) { + if (cl_data->sensor_idx[i] == SRA_IDX) + continue; devm_kfree(dev, cl_data->feature_report[i]); devm_kfree(dev, in_data->input_report[i]); devm_kfree(dev, cl_data->report_descr[i]); diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index 2e96ec6a3073..9a06f9b0e4ef 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -38,6 +38,9 @@ dispatch_hid_bpf_device_event(struct hid_device *hdev, enum hid_report_type type struct hid_bpf_ops *e; int ret; + if (unlikely(hdev->bpf.destroyed)) + return ERR_PTR(-ENODEV); + if (type >= HID_REPORT_TYPES) return ERR_PTR(-EINVAL); @@ -93,6 +96,9 @@ int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, struct hid_bpf_ops *e; int ret, idx; + if (unlikely(hdev->bpf.destroyed)) + return -ENODEV; + if (rtype >= HID_REPORT_TYPES) return -EINVAL; @@ -130,6 +136,9 @@ int dispatch_hid_bpf_output_report(struct hid_device *hdev, struct hid_bpf_ops *e; int ret, idx; + if (unlikely(hdev->bpf.destroyed)) + return -ENODEV; + idx = srcu_read_lock(&hdev->bpf.srcu); list_for_each_entry_srcu(e, &hdev->bpf.prog_list, list, srcu_read_lock_held(&hdev->bpf.srcu)) { diff --git a/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c b/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c index 1a0aeea6a081..a754710fc90b 100644 --- a/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c +++ b/drivers/hid/bpf/progs/XPPen__ACK05.bpf.c @@ -157,6 +157,7 @@ static const __u8 fixed_rdesc_vendor[] = { ReportCount(5) // padding Input(Const) // Byte 4 in report - just exists so we get to be a tablet pad + UsagePage_Digitizers Usage_Dig_BarrelSwitch // BTN_STYLUS ReportCount(1) ReportSize(1) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 288a2b864cc4..1062731315a2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -41,6 +41,10 @@ #define USB_VENDOR_ID_ACTIONSTAR 0x2101 #define USB_DEVICE_ID_ACTIONSTAR_1011 0x1011 +#define USB_VENDOR_ID_ADATA_XPG 0x125f +#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE 0x7505 +#define USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE 0x7506 + #define USB_VENDOR_ID_ADS_TECH 0x06e1 #define USB_DEVICE_ID_ADS_TECH_RADIO_SI470X 0xa155 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 646171598e41..0731473cc9b1 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -27,6 +27,8 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_GAMEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_AASHIMA, USB_DEVICE_ID_AASHIMA_PREDATOR), HID_QUIRK_BADPAD }, + { HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_ADATA_XPG, USB_VENDOR_ID_ADATA_XPG_WL_GAMING_MOUSE_DONGLE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_AFATECH, USB_DEVICE_ID_AFATECH_AF9016), HID_QUIRK_FULLSPEED_INTERVAL }, { HID_USB_DEVICE(USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX), HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index dfd9d22ed559..949d307c66a8 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -1150,11 +1150,9 @@ static void steam_client_ll_close(struct hid_device *hdev) struct steam_device *steam = hdev->driver_data; unsigned long flags; - bool connected; spin_lock_irqsave(&steam->lock, flags); steam->client_opened--; - connected = steam->connected && !steam->client_opened; spin_unlock_irqrestore(&steam->lock, flags); schedule_work(&steam->unregister_work); diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index 3b81468a1df2..0bf70664c35e 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -174,6 +174,7 @@ static void thrustmaster_interrupts(struct hid_device *hdev) u8 ep_addr[2] = {b_ep, 0}; if (!usb_check_int_endpoints(usbif, ep_addr)) { + kfree(send_buf); hid_err(hdev, "Unexpected non-int endpoint\n"); return; } diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index a367df6ea01f..61a4019ddc74 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -142,11 +142,12 @@ static int uclogic_input_configured(struct hid_device *hdev, suffix = "System Control"; break; } - } - - if (suffix) + } else { hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s %s", hdev->name, suffix); + if (!hi->input->name) + return -ENOMEM; + } return 0; } diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 1556d4287fa5..eaf099b2efdb 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -70,10 +70,16 @@ static void wacom_wac_queue_flush(struct hid_device *hdev, { while (!kfifo_is_empty(fifo)) { int size = kfifo_peek_len(fifo); - u8 *buf = kzalloc(size, GFP_KERNEL); + u8 *buf; unsigned int count; int err; + buf = kzalloc(size, GFP_KERNEL); + if (!buf) { + kfifo_skip(fifo); + continue; + } + count = kfifo_out(fifo, buf, size); if (count != size) { // Hard to say what is the "right" action in this @@ -81,6 +87,7 @@ static void wacom_wac_queue_flush(struct hid_device *hdev, // to flush seems reasonable enough, however. hid_warn(hdev, "%s: removed fifo entry with unexpected size\n", __func__); + kfree(buf); continue; } err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, false); @@ -2361,6 +2368,8 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) unsigned int connect_mask = HID_CONNECT_HIDRAW; features->pktlen = wacom_compute_pktlen(hdev); + if (!features->pktlen) + return -ENODEV; if (!devres_open_group(&hdev->dev, wacom, GFP_KERNEL)) return -ENOMEM; diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index fb8cd8469328..35f26fa1ffe7 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -1077,68 +1077,10 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, EXPORT_SYMBOL(vmbus_sendpacket); /* - * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer - * packets using a GPADL Direct packet type. This interface allows you - * to control notifying the host. This will be useful for sending - * batched data. Also the sender can control the send flags - * explicitly. - */ -int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, void *buffer, u32 bufferlen, - u64 requestid) -{ - int i; - struct vmbus_channel_packet_page_buffer desc; - u32 descsize; - u32 packetlen; - u32 packetlen_aligned; - struct kvec bufferlist[3]; - u64 aligned_data = 0; - - if (pagecount > MAX_PAGE_BUFFER_COUNT) - return -EINVAL; - - /* - * Adjust the size down since vmbus_channel_packet_page_buffer is the - * largest size we support - */ - descsize = sizeof(struct vmbus_channel_packet_page_buffer) - - ((MAX_PAGE_BUFFER_COUNT - pagecount) * - sizeof(struct hv_page_buffer)); - packetlen = descsize + bufferlen; - packetlen_aligned = ALIGN(packetlen, sizeof(u64)); - - /* Setup the descriptor */ - desc.type = VM_PKT_DATA_USING_GPA_DIRECT; - desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; - desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */ - desc.length8 = (u16)(packetlen_aligned >> 3); - desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ - desc.reserved = 0; - desc.rangecount = pagecount; - - for (i = 0; i < pagecount; i++) { - desc.range[i].len = pagebuffers[i].len; - desc.range[i].offset = pagebuffers[i].offset; - desc.range[i].pfn = pagebuffers[i].pfn; - } - - bufferlist[0].iov_base = &desc; - bufferlist[0].iov_len = descsize; - bufferlist[1].iov_base = buffer; - bufferlist[1].iov_len = bufferlen; - bufferlist[2].iov_base = &aligned_data; - bufferlist[2].iov_len = (packetlen_aligned - packetlen); - - return hv_ringbuffer_write(channel, bufferlist, 3, requestid, NULL); -} -EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer); - -/* - * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet + * vmbus_sendpacket_mpb_desc - Send one or more multi-page buffer packets * using a GPADL Direct packet type. - * The buffer includes the vmbus descriptor. + * The desc argument must include space for the VMBus descriptor. The + * rangecount field must already be set. */ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *desc, @@ -1160,7 +1102,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, desc->length8 = (u16)(packetlen_aligned >> 3); desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ desc->reserved = 0; - desc->rangecount = 1; bufferlist[0].iov_base = desc; bufferlist[0].iov_len = desc_size; diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 29780f3a7478..0b450e53161e 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev) #endif /* CONFIG_HYPERV_TESTING */ +/* Create and remove sysfs entry for memory mapped ring buffers for a channel */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)); +int hv_remove_ring_sysfs(struct vmbus_channel *channel); + #endif /* _HYPERV_VMBUS_H */ diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8d3cff42bdbb..e3d51a316316 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1802,6 +1802,26 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel, } static VMBUS_CHAN_ATTR_RO(subchannel_id); +static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj); + + /* + * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer + * is not NULL. + */ + return channel->mmap_ring_buffer(channel, vma); +} + +static struct bin_attribute chan_attr_ring_buffer = { + .attr = { + .name = "ring", + .mode = 0600, + }, + .mmap = hv_mmap_ring_buffer_wrapper, +}; static struct attribute *vmbus_chan_attrs[] = { &chan_attr_out_mask.attr, &chan_attr_in_mask.attr, @@ -1821,6 +1841,11 @@ static struct attribute *vmbus_chan_attrs[] = { NULL }; +static struct bin_attribute *vmbus_chan_bin_attrs[] = { + &chan_attr_ring_buffer, + NULL +}; + /* * Channel-level attribute_group callback function. Returns the permission for * each attribute, and returns 0 if an attribute is not visible. @@ -1841,9 +1866,34 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj, return attr->mode; } +static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj, + const struct bin_attribute *attr, int idx) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + /* Hide ring attribute if channel's ring_sysfs_visible is set to false */ + if (attr == &chan_attr_ring_buffer && !channel->ring_sysfs_visible) + return 0; + + return attr->attr.mode; +} + +static size_t vmbus_chan_bin_size(struct kobject *kobj, + const struct bin_attribute *bin_attr, int a) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + return channel->ringbuffer_pagecount << PAGE_SHIFT; +} + static const struct attribute_group vmbus_chan_group = { .attrs = vmbus_chan_attrs, - .is_visible = vmbus_chan_attr_is_visible + .bin_attrs = vmbus_chan_bin_attrs, + .is_visible = vmbus_chan_attr_is_visible, + .is_bin_visible = vmbus_chan_bin_attr_is_visible, + .bin_size = vmbus_chan_bin_size, }; static const struct kobj_type vmbus_chan_ktype = { @@ -1851,6 +1901,63 @@ static const struct kobj_type vmbus_chan_ktype = { .release = vmbus_chan_release, }; +/** + * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of + * channel's "ring" sysfs node, which is for the ring buffer of that channel. + * Function pointer is of below type: + * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + * struct vm_area_struct *vma)) + * This has a pointer to the channel and a pointer to vm_area_struct, + * used for mmap, as arguments. + * + * Sysfs node for ring buffer of a channel is created along with other fields, however its + * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case + * is running. + * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of + * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid + * exposing the ring buffer by default, this function is reponsible to enable visibility of + * ring for userspace to use. + * Note: Race conditions can happen with userspace and it is not encouraged to create new + * use-cases for this. This was added to maintain backward compatibility, while solving + * one of the race conditions in uio_hv_generic while creating sysfs. + * + * Returns 0 on success or error code on failure. + */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)) +{ + struct kobject *kobj = &channel->kobj; + + channel->mmap_ring_buffer = hv_mmap_ring_buffer; + channel->ring_sysfs_visible = true; + + return sysfs_update_group(kobj, &vmbus_chan_group); +} +EXPORT_SYMBOL_GPL(hv_create_ring_sysfs); + +/** + * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * + * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group. + * + * Returns 0 on success or error code on failure. + */ +int hv_remove_ring_sysfs(struct vmbus_channel *channel) +{ + struct kobject *kobj = &channel->kobj; + int ret; + + channel->ring_sysfs_visible = false; + ret = sysfs_update_group(kobj, &vmbus_chan_group); + channel->mmap_ring_buffer = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs); + /* * vmbus_add_channel_kobj - setup a sub-directory under device/channels */ diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c index 8e0267c7cc29..f21f9877c040 100644 --- a/drivers/i2c/busses/i2c-designware-pcidrv.c +++ b/drivers/i2c/busses/i2c-designware-pcidrv.c @@ -278,9 +278,11 @@ static int i2c_dw_pci_probe(struct pci_dev *pdev, if ((dev->flags & MODEL_MASK) == MODEL_AMD_NAVI_GPU) { dev->slave = i2c_new_ccgx_ucsi(&dev->adapter, dev->irq, &dgpu_node); - if (IS_ERR(dev->slave)) + if (IS_ERR(dev->slave)) { + i2c_del_adapter(&dev->adapter); return dev_err_probe(device, PTR_ERR(dev->slave), "register UCSI failed\n"); + } } pm_runtime_set_autosuspend_delay(device, 1000); diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 16afb9ca19bb..876791d20ed5 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1454,7 +1454,7 @@ omap_i2c_probe(struct platform_device *pdev) (1000 * omap->speed / 8); } - if (of_property_read_bool(node, "mux-states")) { + if (of_property_present(node, "mux-states")) { struct mux_state *mux_state; mux_state = devm_mux_state_get(&pdev->dev, NULL); diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c index 8601b9a8b8e7..5127e58eebc7 100644 --- a/drivers/iio/accel/adis16201.c +++ b/drivers/iio/accel/adis16201.c @@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = { BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12), ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X, - BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), + BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12), ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y, - BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), + BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12), IIO_CHAN_SOFT_TIMESTAMP(7) }; diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c index e8cd21fa77a6..cbac622ef821 100644 --- a/drivers/iio/accel/adxl355_core.c +++ b/drivers/iio/accel/adxl355_core.c @@ -231,7 +231,7 @@ struct adxl355_data { u8 transf_buf[3]; struct { u8 buf[14]; - s64 ts; + aligned_s64 ts; } buffer; } __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c index add4053e7a02..0c04b2bb7efb 100644 --- a/drivers/iio/accel/adxl367.c +++ b/drivers/iio/accel/adxl367.c @@ -601,18 +601,14 @@ static int _adxl367_set_odr(struct adxl367_state *st, enum adxl367_odr odr) if (ret) return ret; + st->odr = odr; + /* Activity timers depend on ODR */ ret = _adxl367_set_act_time_ms(st, st->act_time_ms); if (ret) return ret; - ret = _adxl367_set_inact_time_ms(st, st->inact_time_ms); - if (ret) - return ret; - - st->odr = odr; - - return 0; + return _adxl367_set_inact_time_ms(st, st->inact_time_ms); } static int adxl367_set_odr(struct iio_dev *indio_dev, enum adxl367_odr odr) diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 48e4282964a0..bf1d3923a181 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -1226,8 +1226,11 @@ int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq) if (ret) return ret; - if (device_property_read_bool(dev, "wakeup-source")) - device_init_wakeup(dev, true); + if (device_property_read_bool(dev, "wakeup-source")) { + ret = devm_device_init_wakeup(dev); + if (ret) + return dev_err_probe(dev, ret, "Failed to init wakeup\n"); + } return devm_iio_device_register(dev, indio_dev); } diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c index 18559757f908..7fef2727f89e 100644 --- a/drivers/iio/adc/ad7266.c +++ b/drivers/iio/adc/ad7266.c @@ -45,7 +45,7 @@ struct ad7266_state { */ struct { __be16 sample[2]; - s64 timestamp; + aligned_s64 timestamp; } data __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c index 4fcb49fdf566..aef85093eb16 100644 --- a/drivers/iio/adc/ad7380.c +++ b/drivers/iio/adc/ad7380.c @@ -1211,6 +1211,9 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev) struct ad7380_state *st = iio_priv(indio_dev); int ret; + spi_offload_trigger_disable(st->offload, st->offload_trigger); + spi_unoptimize_message(&st->offload_msg); + if (st->seq) { ret = regmap_update_bits(st->regmap, AD7380_REG_ADDR_CONFIG1, @@ -1222,10 +1225,6 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev) st->seq = false; } - spi_offload_trigger_disable(st->offload, st->offload_trigger); - - spi_unoptimize_message(&st->offload_msg); - return 0; } @@ -1611,11 +1610,25 @@ static int ad7380_write_event_config(struct iio_dev *indio_dev, return ret; } -static int ad7380_get_alert_th(struct ad7380_state *st, +static int ad7380_get_alert_th(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, enum iio_event_direction dir, int *val) { - int ret, tmp; + struct ad7380_state *st = iio_priv(indio_dev); + const struct iio_scan_type *scan_type; + int ret, tmp, shift; + + scan_type = iio_get_current_scan_type(indio_dev, chan); + if (IS_ERR(scan_type)) + return PTR_ERR(scan_type); + + /* + * The register value is 12-bits and is compared to the most significant + * bits of raw value, therefore a shift is required to convert this to + * the same scale as the raw value. + */ + shift = scan_type->realbits - 12; switch (dir) { case IIO_EV_DIR_RISING: @@ -1625,7 +1638,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st, if (ret) return ret; - *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp); + *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp) << shift; return IIO_VAL_INT; case IIO_EV_DIR_FALLING: ret = regmap_read(st->regmap, @@ -1634,7 +1647,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st, if (ret) return ret; - *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp); + *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp) << shift; return IIO_VAL_INT; default: return -EINVAL; @@ -1648,7 +1661,6 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev, enum iio_event_info info, int *val, int *val2) { - struct ad7380_state *st = iio_priv(indio_dev); int ret; switch (info) { @@ -1656,7 +1668,7 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev, if (!iio_device_claim_direct(indio_dev)) return -EBUSY; - ret = ad7380_get_alert_th(st, dir, val); + ret = ad7380_get_alert_th(indio_dev, chan, dir, val); iio_device_release_direct(indio_dev); return ret; diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c index 1a314fddd7eb..703556eb7257 100644 --- a/drivers/iio/adc/ad7606.c +++ b/drivers/iio/adc/ad7606.c @@ -1236,9 +1236,11 @@ static int ad7616_sw_mode_setup(struct iio_dev *indio_dev) st->write_scale = ad7616_write_scale_sw; st->write_os = &ad7616_write_os_sw; - ret = st->bops->sw_mode_config(indio_dev); - if (ret) - return ret; + if (st->bops->sw_mode_config) { + ret = st->bops->sw_mode_config(indio_dev); + if (ret) + return ret; + } /* Activate Burst mode and SEQEN MODE */ return ad7606_write_mask(st, AD7616_CONFIGURATION_REGISTER, @@ -1268,6 +1270,9 @@ static int ad7606b_sw_mode_setup(struct iio_dev *indio_dev) st->write_scale = ad7606_write_scale_sw; st->write_os = &ad7606_write_os_sw; + if (!st->bops->sw_mode_config) + return 0; + return st->bops->sw_mode_config(indio_dev); } diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c index 885bf0b68e77..179115e90988 100644 --- a/drivers/iio/adc/ad7606_spi.c +++ b/drivers/iio/adc/ad7606_spi.c @@ -131,7 +131,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr) { .tx_buf = &st->d16[0], .len = 2, - .cs_change = 0, + .cs_change = 1, }, { .rx_buf = &st->d16[1], .len = 2, diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index 5a863005aca6..5e0be36af0c5 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -168,7 +168,7 @@ struct ad7768_state { union { struct { __be32 chan; - s64 timestamp; + aligned_s64 timestamp; } scan; __be32 d32; u8 d8[2]; diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c index a1e48a756a7b..359e26e3f5bc 100644 --- a/drivers/iio/adc/dln2-adc.c +++ b/drivers/iio/adc/dln2-adc.c @@ -466,7 +466,7 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct { __le16 values[DLN2_ADC_MAX_CHANNELS]; - int64_t timestamp_space; + aligned_s64 timestamp_space; } data; struct dln2_adc_get_all_vals dev_data; struct dln2_adc *dln2 = iio_priv(indio_dev); diff --git a/drivers/iio/adc/qcom-spmi-iadc.c b/drivers/iio/adc/qcom-spmi-iadc.c index 7fb8b2499a1d..b64a8a407168 100644 --- a/drivers/iio/adc/qcom-spmi-iadc.c +++ b/drivers/iio/adc/qcom-spmi-iadc.c @@ -543,7 +543,9 @@ static int iadc_probe(struct platform_device *pdev) else return ret; } else { - device_init_wakeup(iadc->dev, 1); + ret = devm_device_init_wakeup(iadc->dev); + if (ret) + return dev_err_probe(iadc->dev, ret, "Failed to init wakeup\n"); } ret = iadc_update_offset(iadc); diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index 9a099df79518..5e28bd28b81a 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -520,15 +520,6 @@ static int rockchip_saradc_probe(struct platform_device *pdev) if (info->reset) rockchip_saradc_reset_controller(info->reset); - /* - * Use a default value for the converter clock. - * This may become user-configurable in the future. - */ - ret = clk_set_rate(info->clk, info->data->clk_rate); - if (ret < 0) - return dev_err_probe(&pdev->dev, ret, - "failed to set adc clk rate\n"); - ret = regulator_enable(info->vref); if (ret < 0) return dev_err_probe(&pdev->dev, ret, @@ -555,6 +546,14 @@ static int rockchip_saradc_probe(struct platform_device *pdev) if (IS_ERR(info->clk)) return dev_err_probe(&pdev->dev, PTR_ERR(info->clk), "failed to get adc clock\n"); + /* + * Use a default value for the converter clock. + * This may become user-configurable in the future. + */ + ret = clk_set_rate(info->clk, info->data->clk_rate); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "failed to set adc clk rate\n"); platform_set_drvdata(pdev, indio_dev); diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c index d0bd94912e0a..e05ce1f12065 100644 --- a/drivers/iio/chemical/pms7003.c +++ b/drivers/iio/chemical/pms7003.c @@ -5,7 +5,6 @@ * Copyright (c) Tomasz Duszynski <tduszyns@gmail.com> */ -#include <linux/unaligned.h> #include <linux/completion.h> #include <linux/device.h> #include <linux/errno.h> @@ -19,6 +18,8 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/serdev.h> +#include <linux/types.h> +#include <linux/unaligned.h> #define PMS7003_DRIVER_NAME "pms7003" @@ -76,7 +77,7 @@ struct pms7003_state { /* Used to construct scan to push to the IIO buffer */ struct { u16 data[3]; /* PM1, PM2P5, PM10 */ - s64 ts; + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c index 6f4f2ba2c09d..a7888146188d 100644 --- a/drivers/iio/chemical/sps30.c +++ b/drivers/iio/chemical/sps30.c @@ -108,7 +108,7 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p) int ret; struct { s32 data[4]; /* PM1, PM2P5, PM4, PM10 */ - s64 ts; + aligned_s64 ts; } scan; mutex_lock(&state->lock); diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c index ad1882f608c0..2055a03cbeb1 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c @@ -66,6 +66,10 @@ static struct { {HID_USAGE_SENSOR_HUMIDITY, 0, 1000, 0}, {HID_USAGE_SENSOR_HINGE, 0, 0, 17453293}, {HID_USAGE_SENSOR_HINGE, HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293}, + + {HID_USAGE_SENSOR_HUMAN_PRESENCE, 0, 1, 0}, + {HID_USAGE_SENSOR_HUMAN_PROXIMITY, 0, 1, 0}, + {HID_USAGE_SENSOR_HUMAN_ATTENTION, 0, 1, 0}, }; static void simple_div(int dividend, int divisor, int *whole, diff --git a/drivers/iio/imu/adis16550.c b/drivers/iio/imu/adis16550.c index b14ea8937c7f..28f0dbd0226c 100644 --- a/drivers/iio/imu/adis16550.c +++ b/drivers/iio/imu/adis16550.c @@ -836,7 +836,7 @@ static irqreturn_t adis16550_trigger_handler(int irq, void *p) u16 dummy; bool valid; struct iio_poll_func *pf = p; - __be32 data[ADIS16550_MAX_SCAN_DATA]; + __be32 data[ADIS16550_MAX_SCAN_DATA] __aligned(8); struct iio_dev *indio_dev = pf->indio_dev; struct adis16550 *st = iio_priv(indio_dev); struct adis *adis = iio_device_get_drvdata(indio_dev); diff --git a/drivers/iio/imu/bmi270/bmi270_core.c b/drivers/iio/imu/bmi270/bmi270_core.c index a86be5af5ccb..2e4469f30d53 100644 --- a/drivers/iio/imu/bmi270/bmi270_core.c +++ b/drivers/iio/imu/bmi270/bmi270_core.c @@ -918,8 +918,7 @@ static int bmi270_configure_imu(struct bmi270_data *data) FIELD_PREP(BMI270_ACC_CONF_ODR_MSK, BMI270_ACC_CONF_ODR_100HZ) | FIELD_PREP(BMI270_ACC_CONF_BWP_MSK, - BMI270_ACC_CONF_BWP_NORMAL_MODE) | - BMI270_PWR_CONF_ADV_PWR_SAVE_MSK); + BMI270_ACC_CONF_BWP_NORMAL_MODE)); if (ret) return dev_err_probe(dev, ret, "Failed to configure accelerometer"); @@ -927,8 +926,7 @@ static int bmi270_configure_imu(struct bmi270_data *data) FIELD_PREP(BMI270_GYR_CONF_ODR_MSK, BMI270_GYR_CONF_ODR_200HZ) | FIELD_PREP(BMI270_GYR_CONF_BWP_MSK, - BMI270_GYR_CONF_BWP_NORMAL_MODE) | - BMI270_PWR_CONF_ADV_PWR_SAVE_MSK); + BMI270_GYR_CONF_BWP_NORMAL_MODE)); if (ret) return dev_err_probe(dev, ret, "Failed to configure gyroscope"); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 3d3b27f28c9d..273196e647a2 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -50,7 +50,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) u16 fifo_count; u32 fifo_period; s64 timestamp; - u8 data[INV_MPU6050_OUTPUT_DATA_SIZE]; + u8 data[INV_MPU6050_OUTPUT_DATA_SIZE] __aligned(8); size_t i, nb; mutex_lock(&st->lock); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index 0a7cd8c1aa33..8a9d2593576a 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -392,6 +392,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw) if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK)) return 0; + if (!pattern_len) + pattern_len = ST_LSM6DSX_SAMPLE_SIZE; + fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) * ST_LSM6DSX_CHAN_SIZE; fifo_len = (fifo_len / pattern_len) * pattern_len; @@ -623,6 +626,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw) if (!fifo_len) return 0; + if (!pattern_len) + pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE; + for (read_len = 0; read_len < fifo_len; read_len += pattern_len) { err = st_lsm6dsx_read_block(hw, ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR, diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 4fdcc2acc94e..96c6106b95ee 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -2719,8 +2719,11 @@ int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id, } if (device_property_read_bool(dev, "wakeup-source") || - (pdata && pdata->wakeup_source)) - device_init_wakeup(dev, true); + (pdata && pdata->wakeup_source)) { + err = devm_device_init_wakeup(dev); + if (err) + return dev_err_probe(dev, err, "Failed to init wakeup\n"); + } return 0; } diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c index 76b76d12b388..4c65b32d34ce 100644 --- a/drivers/iio/light/hid-sensor-prox.c +++ b/drivers/iio/light/hid-sensor-prox.c @@ -34,9 +34,9 @@ struct prox_state { struct iio_chan_spec channels[MAX_CHANNELS]; u32 channel2usage[MAX_CHANNELS]; u32 human_presence[MAX_CHANNELS]; - int scale_pre_decml; - int scale_post_decml; - int scale_precision; + int scale_pre_decml[MAX_CHANNELS]; + int scale_post_decml[MAX_CHANNELS]; + int scale_precision[MAX_CHANNELS]; unsigned long scan_mask[2]; /* One entry plus one terminator. */ int num_channels; }; @@ -116,13 +116,15 @@ static int prox_read_raw(struct iio_dev *indio_dev, ret_type = IIO_VAL_INT; break; case IIO_CHAN_INFO_SCALE: - *val = prox_state->scale_pre_decml; - *val2 = prox_state->scale_post_decml; - ret_type = prox_state->scale_precision; + if (chan->scan_index >= prox_state->num_channels) + return -EINVAL; + + *val = prox_state->scale_pre_decml[chan->scan_index]; + *val2 = prox_state->scale_post_decml[chan->scan_index]; + ret_type = prox_state->scale_precision[chan->scan_index]; break; case IIO_CHAN_INFO_OFFSET: - *val = hid_sensor_convert_exponent( - prox_state->prox_attr[chan->scan_index].unit_expo); + *val = 0; ret_type = IIO_VAL_INT; break; case IIO_CHAN_INFO_SAMP_FREQ: @@ -249,6 +251,10 @@ static int prox_parse_report(struct platform_device *pdev, st->prox_attr[index].size); dev_dbg(&pdev->dev, "prox %x:%x\n", st->prox_attr[index].index, st->prox_attr[index].report_id); + st->scale_precision[index] = + hid_sensor_format_scale(usage_id, &st->prox_attr[index], + &st->scale_pre_decml[index], + &st->scale_post_decml[index]); index++; } diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c index 65b295877b41..393a3d2fbe1d 100644 --- a/drivers/iio/light/opt3001.c +++ b/drivers/iio/light/opt3001.c @@ -788,8 +788,9 @@ static irqreturn_t opt3001_irq(int irq, void *_iio) int ret; bool wake_result_ready_queue = false; enum iio_chan_type chan_type = opt->chip_info->chan_type; + bool ok_to_ignore_lock = opt->ok_to_ignore_lock; - if (!opt->ok_to_ignore_lock) + if (!ok_to_ignore_lock) mutex_lock(&opt->lock); ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_CONFIGURATION); @@ -826,7 +827,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio) } out: - if (!opt->ok_to_ignore_lock) + if (!ok_to_ignore_lock) mutex_unlock(&opt->lock); if (wake_result_ready_queue) diff --git a/drivers/iio/pressure/mprls0025pa.h b/drivers/iio/pressure/mprls0025pa.h index 9d5c30afa9d6..d62a018eaff3 100644 --- a/drivers/iio/pressure/mprls0025pa.h +++ b/drivers/iio/pressure/mprls0025pa.h @@ -34,16 +34,6 @@ struct iio_dev; struct mpr_data; struct mpr_ops; -/** - * struct mpr_chan - * @pres: pressure value - * @ts: timestamp - */ -struct mpr_chan { - s32 pres; - s64 ts; -}; - enum mpr_func_id { MPR_FUNCTION_A, MPR_FUNCTION_B, @@ -69,6 +59,8 @@ enum mpr_func_id { * reading in a loop until data is ready * @completion: handshake from irq to read * @chan: channel values for buffered mode + * @chan.pres: pressure value + * @chan.ts: timestamp * @buffer: raw conversion data */ struct mpr_data { @@ -87,7 +79,10 @@ struct mpr_data { struct gpio_desc *gpiod_reset; int irq; struct completion completion; - struct mpr_chan chan; + struct { + s32 pres; + aligned_s64 ts; + } chan; u8 buffer[MPR_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c index c28a7a6dea5f..555a61e2f3fd 100644 --- a/drivers/iio/temperature/maxim_thermocouple.c +++ b/drivers/iio/temperature/maxim_thermocouple.c @@ -121,9 +121,9 @@ static const struct maxim_thermocouple_chip maxim_thermocouple_chips[] = { struct maxim_thermocouple_data { struct spi_device *spi; const struct maxim_thermocouple_chip *chip; + char tc_type; u8 buffer[16] __aligned(IIO_DMA_MINALIGN); - char tc_type; }; static int maxim_thermocouple_read(struct maxim_thermocouple_data *data, diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index b4e3e4beb7f4..d4263385850a 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1352,6 +1352,9 @@ static void ib_device_notify_register(struct ib_device *device) down_read(&devices_rwsem); + /* Mark for userspace that device is ready */ + kobject_uevent(&device->dev.kobj, KOBJ_ADD); + ret = rdma_nl_notify_event(device, 0, RDMA_REGISTER_EVENT); if (ret) goto out; @@ -1468,10 +1471,9 @@ int ib_register_device(struct ib_device *device, const char *name, return ret; } dev_set_uevent_suppress(&device->dev, false); - /* Mark for userspace that device is ready */ - kobject_uevent(&device->dev.kobj, KOBJ_ADD); ib_device_notify_register(device); + ib_device_put(device); return 0; diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c index 1ee8969595d3..7599e31b5743 100644 --- a/drivers/infiniband/hw/irdma/main.c +++ b/drivers/infiniband/hw/irdma/main.c @@ -221,7 +221,7 @@ static int irdma_init_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf) break; if (i < IRDMA_MIN_MSIX) { - for (; i > 0; i--) + while (--i >= 0) ice_free_rdma_qvector(pf, &rf->msix_entries[i]); kfree(rf->msix_entries); @@ -255,6 +255,8 @@ static void irdma_remove(struct auxiliary_device *aux_dev) ice_rdma_update_vsi_filter(pf, iwdev->vsi_num, false); irdma_deinit_interrupts(iwdev->rf, pf); + kfree(iwdev->rf); + pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn)); } diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index eeb932e58730..1e8c92826de2 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -4871,5 +4871,4 @@ void irdma_ib_dealloc_device(struct ib_device *ibdev) irdma_rt_deinit_hw(iwdev); irdma_ctrl_deinit_hw(iwdev->rf); - kfree(iwdev->rf); } diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index b9f4a2937c3a..2098de762bf5 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -90,7 +90,7 @@ static int create_file(const char *name, umode_t mode, int error; inode_lock(d_inode(parent)); - *dentry = lookup_one_len(name, parent, strlen(name)); + *dentry = lookup_noperm(&QSTR(name), parent); if (!IS_ERR(*dentry)) error = qibfs_mknod(d_inode(parent), *dentry, mode, fops, data); @@ -433,7 +433,7 @@ static int remove_device_files(struct super_block *sb, char unit[10]; snprintf(unit, sizeof(unit), "%u", dd->unit); - dir = lookup_one_len_unlocked(unit, sb->s_root, strlen(unit)); + dir = lookup_noperm_unlocked(&QSTR(unit), sb->s_root); if (IS_ERR(dir)) { pr_err("Lookup of %s failed\n", unit); diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index fec87c9030ab..fffd144d509e 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -56,11 +56,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, err = do_mmap_info(rxe, uresp ? &uresp->mi : NULL, udata, cq->queue->buf, cq->queue->buf_size, &cq->queue->ip); - if (err) { - vfree(cq->queue->buf); - kfree(cq->queue); + if (err) return err; - } cq->is_user = uresp; diff --git a/drivers/input/joystick/magellan.c b/drivers/input/joystick/magellan.c index d73389af4dd5..7622638e5bb8 100644 --- a/drivers/input/joystick/magellan.c +++ b/drivers/input/joystick/magellan.c @@ -48,7 +48,7 @@ struct magellan { static int magellan_crunch_nibbles(unsigned char *data, int count) { - static unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?"; + static const unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?"; do { if (data[count] == nibbles[data[count] & 0xf]) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index c33e6f33265b..1008858f78e2 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -77,12 +77,13 @@ * xbox d-pads should map to buttons, as is required for DDR pads * but we map them to axes when possible to simplify things */ -#define MAP_DPAD_TO_BUTTONS (1 << 0) -#define MAP_TRIGGERS_TO_BUTTONS (1 << 1) -#define MAP_STICKS_TO_NULL (1 << 2) -#define MAP_SELECT_BUTTON (1 << 3) -#define MAP_PADDLES (1 << 4) -#define MAP_PROFILE_BUTTON (1 << 5) +#define MAP_DPAD_TO_BUTTONS BIT(0) +#define MAP_TRIGGERS_TO_BUTTONS BIT(1) +#define MAP_STICKS_TO_NULL BIT(2) +#define MAP_SHARE_BUTTON BIT(3) +#define MAP_PADDLES BIT(4) +#define MAP_PROFILE_BUTTON BIT(5) +#define MAP_SHARE_OFFSET BIT(6) #define DANCEPAD_MAP_CONFIG (MAP_DPAD_TO_BUTTONS | \ MAP_TRIGGERS_TO_BUTTONS | MAP_STICKS_TO_NULL) @@ -135,14 +136,14 @@ static const struct xpad_device { { 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 }, /* wireless */ { 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, { 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE }, - { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, /* v2 */ + { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, /* v2 */ { 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE }, { 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX }, - { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE }, { 0x044f, 0x0f10, "Thrustmaster Modena GT Wheel", 0, XTYPE_XBOX }, { 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 }, + { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE }, { 0x045e, 0x0202, "Microsoft X-Box pad v1 (US)", 0, XTYPE_XBOX }, { 0x045e, 0x0285, "Microsoft X-Box pad (Japan)", 0, XTYPE_XBOX }, { 0x045e, 0x0287, "Microsoft Xbox Controller S", 0, XTYPE_XBOX }, @@ -159,7 +160,7 @@ static const struct xpad_device { { 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W }, { 0x045e, 0x0b00, "Microsoft X-Box One Elite 2 pad", MAP_PADDLES, XTYPE_XBOXONE }, { 0x045e, 0x0b0a, "Microsoft X-Box Adaptive Controller", MAP_PROFILE_BUTTON, XTYPE_XBOXONE }, - { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE }, + { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SHARE_BUTTON | MAP_SHARE_OFFSET, XTYPE_XBOXONE }, { 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 }, { 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 }, { 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 }, @@ -205,13 +206,13 @@ static const struct xpad_device { { 0x0738, 0x9871, "Mad Catz Portable Drum", 0, XTYPE_XBOX360 }, { 0x0738, 0xb726, "Mad Catz Xbox controller - MW2", 0, XTYPE_XBOX360 }, { 0x0738, 0xb738, "Mad Catz MVC2TE Stick 2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, - { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 }, + { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", 0, XTYPE_XBOX360 }, { 0x0738, 0xcb02, "Saitek Cyborg Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 }, { 0x0738, 0xcb03, "Saitek P3200 Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 }, { 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 }, { 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 }, { 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 }, - { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE }, + { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x0b05, 0x1abb, "ASUS ROG RAIKIRI PRO", 0, XTYPE_XBOXONE }, { 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX }, { 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX }, @@ -240,7 +241,7 @@ static const struct xpad_device { { 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0147, "PDP Marvel Xbox One Controller", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x015c, "PDP Xbox One Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, - { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", XTYPE_XBOXONE }, + { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0161, "PDP Xbox One Controller", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0162, "PDP Xbox One Controller", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0163, "PDP Xbox One Controller", 0, XTYPE_XBOXONE }, @@ -281,6 +282,7 @@ static const struct xpad_device { { 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f0d, 0x0151, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE }, { 0x0f0d, 0x0152, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE }, + { 0x0f0d, 0x01b2, "HORI Taiko No Tatsujin Drum Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX }, { 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX }, { 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX }, @@ -288,6 +290,8 @@ static const struct xpad_device { { 0x1038, 0x1430, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x1038, 0x1431, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x10f5, 0x7005, "Turtle Beach Recon Controller", 0, XTYPE_XBOXONE }, + { 0x10f5, 0x7008, "Turtle Beach Recon Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, + { 0x10f5, 0x7073, "Turtle Beach Stealth Ultra Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x11c9, 0x55f0, "Nacon GC-100XF", 0, XTYPE_XBOX360 }, { 0x11ff, 0x0511, "PXN V900", 0, XTYPE_XBOX360 }, { 0x1209, 0x2882, "Ardwiino Controller", 0, XTYPE_XBOX360 }, @@ -352,7 +356,10 @@ static const struct xpad_device { { 0x1ee9, 0x1590, "ZOTAC Gaming Zone", 0, XTYPE_XBOX360 }, { 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE }, { 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE }, + { 0x20d6, 0x2064, "PowerA Wired Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 }, + { 0x20d6, 0x400b, "PowerA FUSION Pro 4 Wired Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, + { 0x20d6, 0x890b, "PowerA MOGA XP-Ultra Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x2345, 0xe00b, "Machenike G5 Pro Controller", 0, XTYPE_XBOX360 }, { 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 }, @@ -384,13 +391,16 @@ static const struct xpad_device { { 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE }, { 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE }, + { 0x2dc8, 0x200f, "8BitDo Ultimate 3-mode Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 }, + { 0x2dc8, 0x310b, "8BitDo Ultimate 2 Wireless Controller", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 }, + { 0x2e24, 0x0423, "Hyperkin DuchesS Xbox One pad", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE }, { 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE }, - { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE }, + { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 }, @@ -714,8 +724,10 @@ static const struct xboxone_init_packet xboxone_init_packets[] = { XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init), XBOXONE_INIT_PKT(0x045e, 0x0b00, extra_input_packet_init), XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_led_on), + XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_led_on), XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_led_on), XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_auth), + XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_auth), XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_auth), XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init), XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init), @@ -1027,7 +1039,7 @@ static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned cha * The report format was gleaned from * https://github.com/kylelemons/xbox/blob/master/xbox.go */ -static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data) +static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data, u32 len) { struct input_dev *dev = xpad->dev; bool do_sync = false; @@ -1068,8 +1080,12 @@ static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char /* menu/view buttons */ input_report_key(dev, BTN_START, data[4] & BIT(2)); input_report_key(dev, BTN_SELECT, data[4] & BIT(3)); - if (xpad->mapping & MAP_SELECT_BUTTON) - input_report_key(dev, KEY_RECORD, data[22] & BIT(0)); + if (xpad->mapping & MAP_SHARE_BUTTON) { + if (xpad->mapping & MAP_SHARE_OFFSET) + input_report_key(dev, KEY_RECORD, data[len - 26] & BIT(0)); + else + input_report_key(dev, KEY_RECORD, data[len - 18] & BIT(0)); + } /* buttons A,B,X,Y */ input_report_key(dev, BTN_A, data[4] & BIT(4)); @@ -1217,7 +1233,7 @@ static void xpad_irq_in(struct urb *urb) xpad360w_process_packet(xpad, 0, xpad->idata); break; case XTYPE_XBOXONE: - xpadone_process_packet(xpad, 0, xpad->idata); + xpadone_process_packet(xpad, 0, xpad->idata, urb->actual_length); break; default: xpad_process_packet(xpad, 0, xpad->idata); @@ -1944,7 +1960,7 @@ static int xpad_init_input(struct usb_xpad *xpad) xpad->xtype == XTYPE_XBOXONE) { for (i = 0; xpad360_btn[i] >= 0; i++) input_set_capability(input_dev, EV_KEY, xpad360_btn[i]); - if (xpad->mapping & MAP_SELECT_BUTTON) + if (xpad->mapping & MAP_SHARE_BUTTON) input_set_capability(input_dev, EV_KEY, KEY_RECORD); } else { for (i = 0; xpad_btn[i] >= 0; i++) diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c index 5ad6be914160..061d48350df6 100644 --- a/drivers/input/keyboard/mtk-pmic-keys.c +++ b/drivers/input/keyboard/mtk-pmic-keys.c @@ -147,8 +147,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys, u32 value, mask; int error; - kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs; - kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs; + kregs_home = ®s->keys_regs[MTK_PMIC_HOMEKEY_INDEX]; + kregs_pwr = ®s->keys_regs[MTK_PMIC_PWRKEY_INDEX]; error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec", &long_press_debounce); diff --git a/drivers/input/misc/hisi_powerkey.c b/drivers/input/misc/hisi_powerkey.c index d3c293a95d32..d315017324d9 100644 --- a/drivers/input/misc/hisi_powerkey.c +++ b/drivers/input/misc/hisi_powerkey.c @@ -30,7 +30,7 @@ static irqreturn_t hi65xx_power_press_isr(int irq, void *q) { struct input_dev *input = q; - pm_wakeup_event(input->dev.parent, MAX_HELD_TIME); + pm_wakeup_dev_event(input->dev.parent, MAX_HELD_TIME, true); input_report_key(input, KEY_POWER, 1); input_sync(input); diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c index 8d7303fc13bc..1cfadd73829f 100644 --- a/drivers/input/misc/sparcspkr.c +++ b/drivers/input/misc/sparcspkr.c @@ -74,9 +74,14 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int return -1; switch (code) { - case SND_BELL: if (value) value = 1000; - case SND_TONE: break; - default: return -1; + case SND_BELL: + if (value) + value = 1000; + break; + case SND_TONE: + break; + default: + return -1; } if (value > 20 && value < 32767) @@ -109,9 +114,14 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned return -1; switch (code) { - case SND_BELL: if (value) value = 1000; - case SND_TONE: break; - default: return -1; + case SND_BELL: + if (value) + value = 1000; + break; + case SND_TONE: + break; + default: + return -1; } if (value > 20 && value < 32767) diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 309c360aab55..c5c88a75a019 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -164,6 +164,7 @@ static const char * const topbuttonpad_pnp_ids[] = { #ifdef CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS static const char * const smbus_pnp_ids[] = { /* all of the topbuttonpad_pnp_ids are valid, we just add some extras */ + "DLL060d", /* Dell Precision M3800 */ "LEN0048", /* X1 Carbon 3 */ "LEN0046", /* X250 */ "LEN0049", /* Yoga 11e */ @@ -190,11 +191,15 @@ static const char * const smbus_pnp_ids[] = { "LEN2054", /* E480 */ "LEN2055", /* E580 */ "LEN2068", /* T14 Gen 1 */ + "SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */ + "SYN3003", /* HP EliteBook 850 G1 */ "SYN3015", /* HP EliteBook 840 G2 */ "SYN3052", /* HP EliteBook 840 G4 */ "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ + "TOS01f6", /* Dynabook Portege X30L-G */ + "TOS0213", /* Dynabook Portege X30-D */ NULL }; #endif diff --git a/drivers/input/rmi4/rmi_f34.c b/drivers/input/rmi4/rmi_f34.c index d760af4cc12e..f1947f03b06a 100644 --- a/drivers/input/rmi4/rmi_f34.c +++ b/drivers/input/rmi4/rmi_f34.c @@ -4,6 +4,7 @@ * Copyright (C) 2016 Zodiac Inflight Innovations */ +#include "linux/device.h" #include <linux/kernel.h> #include <linux/rmi.h> #include <linux/firmware.h> @@ -289,39 +290,30 @@ static int rmi_f34_update_firmware(struct f34_data *f34, return rmi_f34_flash_firmware(f34, syn_fw); } -static int rmi_f34_status(struct rmi_function *fn) -{ - struct f34_data *f34 = dev_get_drvdata(&fn->dev); - - /* - * The status is the percentage complete, or once complete, - * zero for success or a negative return code. - */ - return f34->update_status; -} - static ssize_t rmi_driver_bootloader_id_show(struct device *dev, struct device_attribute *dattr, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - struct rmi_function *fn = data->f34_container; + struct rmi_function *fn; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); - - if (f34->bl_version == 5) - return sysfs_emit(buf, "%c%c\n", - f34->bootloader_id[0], - f34->bootloader_id[1]); - else - return sysfs_emit(buf, "V%d.%d\n", - f34->bootloader_id[1], - f34->bootloader_id[0]); - } + fn = data->f34_container; + if (!fn) + return -ENODEV; - return 0; + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; + + if (f34->bl_version == 5) + return sysfs_emit(buf, "%c%c\n", + f34->bootloader_id[0], + f34->bootloader_id[1]); + else + return sysfs_emit(buf, "V%d.%d\n", + f34->bootloader_id[1], + f34->bootloader_id[0]); } static DEVICE_ATTR(bootloader_id, 0444, rmi_driver_bootloader_id_show, NULL); @@ -334,13 +326,16 @@ static ssize_t rmi_driver_configuration_id_show(struct device *dev, struct rmi_function *fn = data->f34_container; struct f34_data *f34; - if (fn) { - f34 = dev_get_drvdata(&fn->dev); + fn = data->f34_container; + if (!fn) + return -ENODEV; + + f34 = dev_get_drvdata(&fn->dev); + if (!f34) + return -ENODEV; - return sysfs_emit(buf, "%s\n", f34->configuration_id); - } - return 0; + return sysfs_emit(buf, "%s\n", f34->configuration_id); } static DEVICE_ATTR(configuration_id, 0444, @@ -356,10 +351,14 @@ static int rmi_firmware_update(struct rmi_driver_data *data, if (!data->f34_container) { dev_warn(dev, "%s: No F34 present!\n", __func__); - return -EINVAL; + return -ENODEV; } f34 = dev_get_drvdata(&data->f34_container->dev); + if (!f34) { + dev_warn(dev, "%s: No valid F34 present!\n", __func__); + return -ENODEV; + } if (f34->bl_version >= 7) { if (data->pdt_props & HAS_BSR) { @@ -485,10 +484,18 @@ static ssize_t rmi_driver_update_fw_status_show(struct device *dev, char *buf) { struct rmi_driver_data *data = dev_get_drvdata(dev); - int update_status = 0; + struct f34_data *f34; + int update_status = -ENODEV; - if (data->f34_container) - update_status = rmi_f34_status(data->f34_container); + /* + * The status is the percentage complete, or once complete, + * zero for success or a negative return code. + */ + if (data->f34_container) { + f34 = dev_get_drvdata(&data->f34_container->dev); + if (f34) + update_status = f34->update_status; + } return sysfs_emit(buf, "%d\n", update_status); } @@ -508,33 +515,21 @@ static const struct attribute_group rmi_firmware_attr_group = { .attrs = rmi_firmware_attrs, }; -static int rmi_f34_probe(struct rmi_function *fn) +static int rmi_f34v5_probe(struct f34_data *f34) { - struct f34_data *f34; - unsigned char f34_queries[9]; + struct rmi_function *fn = f34->fn; + u8 f34_queries[9]; bool has_config_id; - u8 version = fn->fd.function_version; - int ret; - - f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); - if (!f34) - return -ENOMEM; - - f34->fn = fn; - dev_set_drvdata(&fn->dev, f34); - - /* v5 code only supported version 0, try V7 probe */ - if (version > 0) - return rmi_f34v7_probe(f34); + int error; f34->bl_version = 5; - ret = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.query_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "%s: Failed to query properties\n", __func__); - return ret; + return error; } snprintf(f34->bootloader_id, sizeof(f34->bootloader_id), @@ -560,11 +555,11 @@ static int rmi_f34_probe(struct rmi_function *fn) f34->v5.config_blocks); if (has_config_id) { - ret = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, - f34_queries, sizeof(f34_queries)); - if (ret) { + error = rmi_read_block(fn->rmi_dev, fn->fd.control_base_addr, + f34_queries, sizeof(f34_queries)); + if (error) { dev_err(&fn->dev, "Failed to read F34 config ID\n"); - return ret; + return error; } snprintf(f34->configuration_id, sizeof(f34->configuration_id), @@ -573,12 +568,34 @@ static int rmi_f34_probe(struct rmi_function *fn) f34_queries[2], f34_queries[3]); rmi_dbg(RMI_DEBUG_FN, &fn->dev, "Configuration ID: %s\n", - f34->configuration_id); + f34->configuration_id); } return 0; } +static int rmi_f34_probe(struct rmi_function *fn) +{ + struct f34_data *f34; + u8 version = fn->fd.function_version; + int error; + + f34 = devm_kzalloc(&fn->dev, sizeof(struct f34_data), GFP_KERNEL); + if (!f34) + return -ENOMEM; + + f34->fn = fn; + + /* v5 code only supported version 0 */ + error = version == 0 ? rmi_f34v5_probe(f34) : rmi_f34v7_probe(f34); + if (error) + return error; + + dev_set_drvdata(&fn->dev, f34); + + return 0; +} + int rmi_f34_create_sysfs(struct rmi_device *rmi_dev) { return sysfs_create_group(&rmi_dev->dev.kobj, &rmi_firmware_attr_group); diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c index eafe5a9b8964..071b7c9bf566 100644 --- a/drivers/input/touchscreen/cyttsp5.c +++ b/drivers/input/touchscreen/cyttsp5.c @@ -580,7 +580,7 @@ static int cyttsp5_power_control(struct cyttsp5 *ts, bool on) int rc; SET_CMD_REPORT_TYPE(cmd[0], 0); - SET_CMD_REPORT_ID(cmd[0], HID_POWER_SLEEP); + SET_CMD_REPORT_ID(cmd[0], state); SET_CMD_OPCODE(cmd[1], HID_CMD_SET_POWER); rc = cyttsp5_write(ts, HID_COMMAND_REG, cmd, sizeof(cmd)); @@ -870,13 +870,16 @@ static int cyttsp5_probe(struct device *dev, struct regmap *regmap, int irq, ts->input->phys = ts->phys; input_set_drvdata(ts->input, ts); - /* Reset the gpio to be in a reset state */ + /* Assert gpio to be in a reset state */ ts->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(ts->reset_gpio)) { error = PTR_ERR(ts->reset_gpio); dev_err(dev, "Failed to request reset gpio, error %d\n", error); return error; } + + fsleep(10); /* Ensure long-enough reset pulse (minimum 10us). */ + gpiod_set_value_cansleep(ts->reset_gpio, 0); /* Need a delay to have device up */ diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c index a94a1997f96b..af0fb38bcfdc 100644 --- a/drivers/input/touchscreen/stmpe-ts.c +++ b/drivers/input/touchscreen/stmpe-ts.c @@ -366,12 +366,7 @@ static struct platform_driver stmpe_ts_driver = { }; module_platform_driver(stmpe_ts_driver); -static const struct of_device_id stmpe_ts_ids[] = { - { .compatible = "st,stmpe-ts", }, - { }, -}; -MODULE_DEVICE_TABLE(of, stmpe_ts_ids); - +MODULE_ALIAS("platform:stmpe-ts"); MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>"); MODULE_DESCRIPTION("STMPEXXX touchscreen driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 4f91a740c15f..9d728800a862 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3366,10 +3366,12 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain, int ret; for_each_group_device(group, device) { - ret = domain->ops->set_dev_pasid(domain, device->dev, - pasid, old); - if (ret) - goto err_revert; + if (device->dev->iommu->max_pasids > 0) { + ret = domain->ops->set_dev_pasid(domain, device->dev, + pasid, old); + if (ret) + goto err_revert; + } } return 0; @@ -3379,15 +3381,18 @@ err_revert: for_each_group_device(group, device) { if (device == last_gdev) break; - /* - * If no old domain, undo the succeeded devices/pasid. - * Otherwise, rollback the succeeded devices/pasid to the old - * domain. And it is a driver bug to fail attaching with a - * previously good domain. - */ - if (!old || WARN_ON(old->ops->set_dev_pasid(old, device->dev, + if (device->dev->iommu->max_pasids > 0) { + /* + * If no old domain, undo the succeeded devices/pasid. + * Otherwise, rollback the succeeded devices/pasid to + * the old domain. And it is a driver bug to fail + * attaching with a previously good domain. + */ + if (!old || + WARN_ON(old->ops->set_dev_pasid(old, device->dev, pasid, domain))) - iommu_remove_dev_pasid(device->dev, pasid, domain); + iommu_remove_dev_pasid(device->dev, pasid, domain); + } } return ret; } @@ -3398,8 +3403,10 @@ static void __iommu_remove_group_pasid(struct iommu_group *group, { struct group_device *device; - for_each_group_device(group, device) - iommu_remove_dev_pasid(device->dev, pasid, domain); + for_each_group_device(group, device) { + if (device->dev->iommu->max_pasids > 0) + iommu_remove_dev_pasid(device->dev, pasid, domain); + } } /* @@ -3440,7 +3447,13 @@ int iommu_attach_device_pasid(struct iommu_domain *domain, mutex_lock(&group->mutex); for_each_group_device(group, device) { - if (pasid >= device->dev->iommu->max_pasids) { + /* + * Skip PASID validation for devices without PASID support + * (max_pasids = 0). These devices cannot issue transactions + * with PASID, so they don't affect group's PASID usage. + */ + if ((device->dev->iommu->max_pasids > 0) && + (pasid >= device->dev->iommu->max_pasids)) { ret = -EINVAL; goto out_unlock; } diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index dc98c39d2b20..cc6a6c1585d2 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -252,7 +252,7 @@ static void __init gicv2m_teardown(void) static struct msi_parent_ops gicv2m_msi_parent_ops = { .supported_flags = GICV2M_MSI_FLAGS_SUPPORTED, .required_flags = GICV2M_MSI_FLAGS_REQUIRED, - .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK, + .chip_flags = MSI_CHIP_FLAG_SET_EOI, .bus_select_token = DOMAIN_BUS_NEXUS, .bus_select_mask = MATCH_PCI_MSI | MATCH_PLATFORM_MSI, .prefix = "GICv2m-", diff --git a/drivers/irqchip/irq-gic-v3-its-msi-parent.c b/drivers/irqchip/irq-gic-v3-its-msi-parent.c index bdb04c808148..c5a7eb1c0419 100644 --- a/drivers/irqchip/irq-gic-v3-its-msi-parent.c +++ b/drivers/irqchip/irq-gic-v3-its-msi-parent.c @@ -203,7 +203,7 @@ static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain, const struct msi_parent_ops gic_v3_its_msi_parent_ops = { .supported_flags = ITS_MSI_FLAGS_SUPPORTED, .required_flags = ITS_MSI_FLAGS_REQUIRED, - .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK, + .chip_flags = MSI_CHIP_FLAG_SET_EOI, .bus_select_token = DOMAIN_BUS_NEXUS, .bus_select_mask = MATCH_PCI_MSI | MATCH_PLATFORM_MSI, .prefix = "ITS-", diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c index 34e9ca77a8c3..647b18e24e0c 100644 --- a/drivers/irqchip/irq-gic-v3-mbi.c +++ b/drivers/irqchip/irq-gic-v3-mbi.c @@ -197,7 +197,7 @@ static bool mbi_init_dev_msi_info(struct device *dev, struct irq_domain *domain, static const struct msi_parent_ops gic_v3_mbi_msi_parent_ops = { .supported_flags = MBI_MSI_FLAGS_SUPPORTED, .required_flags = MBI_MSI_FLAGS_REQUIRED, - .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK, + .chip_flags = MSI_CHIP_FLAG_SET_EOI, .bus_select_token = DOMAIN_BUS_NEXUS, .bus_select_mask = MATCH_PCI_MSI | MATCH_PLATFORM_MSI, .prefix = "MBI-", diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c index d67f93f6d750..60b976286636 100644 --- a/drivers/irqchip/irq-mvebu-gicp.c +++ b/drivers/irqchip/irq-mvebu-gicp.c @@ -161,7 +161,7 @@ static const struct irq_domain_ops gicp_domain_ops = { static const struct msi_parent_ops gicp_msi_parent_ops = { .supported_flags = GICP_MSI_FLAGS_SUPPORTED, .required_flags = GICP_MSI_FLAGS_REQUIRED, - .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK, + .chip_flags = MSI_CHIP_FLAG_SET_EOI, .bus_select_token = DOMAIN_BUS_GENERIC_MSI, .bus_select_mask = MATCH_PLATFORM_MSI, .prefix = "GICP-", diff --git a/drivers/irqchip/irq-mvebu-odmi.c b/drivers/irqchip/irq-mvebu-odmi.c index 28f7e81df94f..54f6f0811573 100644 --- a/drivers/irqchip/irq-mvebu-odmi.c +++ b/drivers/irqchip/irq-mvebu-odmi.c @@ -157,7 +157,7 @@ static const struct irq_domain_ops odmi_domain_ops = { static const struct msi_parent_ops odmi_msi_parent_ops = { .supported_flags = ODMI_MSI_FLAGS_SUPPORTED, .required_flags = ODMI_MSI_FLAGS_REQUIRED, - .chip_flags = MSI_CHIP_FLAG_SET_EOI | MSI_CHIP_FLAG_SET_ACK, + .chip_flags = MSI_CHIP_FLAG_SET_EOI, .bus_select_token = DOMAIN_BUS_GENERIC_MSI, .bus_select_mask = MATCH_PLATFORM_MSI, .prefix = "ODMI-", diff --git a/drivers/irqchip/irq-riscv-imsic-state.c b/drivers/irqchip/irq-riscv-imsic-state.c index bdf5cd2037f2..62f76950a113 100644 --- a/drivers/irqchip/irq-riscv-imsic-state.c +++ b/drivers/irqchip/irq-riscv-imsic-state.c @@ -208,17 +208,17 @@ skip: } #ifdef CONFIG_SMP -static void __imsic_local_timer_start(struct imsic_local_priv *lpriv) +static void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu) { lockdep_assert_held(&lpriv->lock); if (!timer_pending(&lpriv->timer)) { lpriv->timer.expires = jiffies + 1; - add_timer_on(&lpriv->timer, smp_processor_id()); + add_timer_on(&lpriv->timer, cpu); } } #else -static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv) +static inline void __imsic_local_timer_start(struct imsic_local_priv *lpriv, unsigned int cpu) { } #endif @@ -233,7 +233,7 @@ void imsic_local_sync_all(bool force_all) if (force_all) bitmap_fill(lpriv->dirty_bitmap, imsic->global.nr_ids + 1); if (!__imsic_local_sync(lpriv)) - __imsic_local_timer_start(lpriv); + __imsic_local_timer_start(lpriv, smp_processor_id()); raw_spin_unlock_irqrestore(&lpriv->lock, flags); } @@ -278,7 +278,7 @@ static void __imsic_remote_sync(struct imsic_local_priv *lpriv, unsigned int cpu return; } - __imsic_local_timer_start(lpriv); + __imsic_local_timer_start(lpriv, cpu); } } #else diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 9e175c5e0634..6b23e777e10e 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -524,9 +524,9 @@ static char **realloc_argv(unsigned int *size, char **old_argv) } argv = kmalloc_array(new_size, sizeof(*argv), gfp); if (argv) { - *size = new_size; if (old_argv) memcpy(argv, old_argv, *size * sizeof(*argv)); + *size = new_size; } kfree(old_argv); @@ -1173,7 +1173,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile, t = dm_get_live_table(md, &srcu_idx); if (!t) - return 0; + goto put_live_table; for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); @@ -1184,6 +1184,7 @@ static int dm_keyslot_evict(struct blk_crypto_profile *profile, (void *)key); } +put_live_table: dm_put_live_table(md, srcu_idx); return 0; } diff --git a/drivers/media/cec/i2c/Kconfig b/drivers/media/cec/i2c/Kconfig index b9d21643eef1..c31abc26f602 100644 --- a/drivers/media/cec/i2c/Kconfig +++ b/drivers/media/cec/i2c/Kconfig @@ -16,6 +16,7 @@ config CEC_CH7322 config CEC_NXP_TDA9950 tristate "NXP Semiconductors TDA9950/TDA998X HDMI CEC" + depends on I2C select CEC_NOTIFIER select CEC_CORE default DRM_I2C_NXP_TDA998X diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig index e576b213084d..e45ba127069f 100644 --- a/drivers/media/i2c/Kconfig +++ b/drivers/media/i2c/Kconfig @@ -1149,8 +1149,11 @@ config VIDEO_ISL7998X config VIDEO_LT6911UXE tristate "Lontium LT6911UXE decoder" - depends on ACPI && VIDEO_DEV + depends on ACPI && VIDEO_DEV && I2C select V4L2_FWNODE + select V4L2_CCI_I2C + select MEDIA_CONTROLLER + select VIDEO_V4L2_SUBDEV_API help This is a Video4Linux2 sensor-level driver for the Lontium LT6911UXE HDMI to MIPI CSI-2 bridge. diff --git a/drivers/media/platform/synopsys/hdmirx/Kconfig b/drivers/media/platform/synopsys/hdmirx/Kconfig index 27e6706f84a3..4321f985f632 100644 --- a/drivers/media/platform/synopsys/hdmirx/Kconfig +++ b/drivers/media/platform/synopsys/hdmirx/Kconfig @@ -2,6 +2,7 @@ config VIDEO_SYNOPSYS_HDMIRX tristate "Synopsys DesignWare HDMI Receiver driver" + depends on ARCH_ROCKCHIP || COMPILE_TEST depends on VIDEO_DEV select MEDIA_CONTROLLER select VIDEO_V4L2_SUBDEV_API diff --git a/drivers/media/test-drivers/vivid/Kconfig b/drivers/media/test-drivers/vivid/Kconfig index e95edc0f22bf..cc470070a7a5 100644 --- a/drivers/media/test-drivers/vivid/Kconfig +++ b/drivers/media/test-drivers/vivid/Kconfig @@ -32,7 +32,8 @@ config VIDEO_VIVID_CEC config VIDEO_VIVID_OSD bool "Enable Framebuffer for testing Output Overlay" - depends on VIDEO_VIVID && FB + depends on VIDEO_VIVID && FB_CORE + depends on VIDEO_VIVID=m || FB_CORE=y default y select FB_IOMEM_HELPERS help diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index 09b9ab15e499..a20d03fdd6a9 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/sizes.h> @@ -745,6 +746,29 @@ static void dwcmshc_rk35xx_postinit(struct sdhci_host *host, struct dwcmshc_priv } } +static void dwcmshc_rk3576_postinit(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv) +{ + struct device *dev = mmc_dev(host->mmc); + int ret; + + /* + * This works around the design of the RK3576's power domains, which + * makes the PD_NVM power domain, which the sdhci controller on the + * RK3576 is in, never come back the same way once it's run-time + * suspended once. This can happen during early kernel boot if no driver + * is using either PD_NVM or its child power domain PD_SDGMAC for a + * short moment, leading to it being turned off to save power. By + * keeping it on, sdhci suspending won't lead to PD_NVM becoming a + * candidate for getting turned off. + */ + ret = dev_pm_genpd_rpm_always_on(dev, true); + if (ret && ret != -EOPNOTSUPP) + dev_warn(dev, "failed to set PD rpm always on, SoC may hang later: %pe\n", + ERR_PTR(ret)); + + dwcmshc_rk35xx_postinit(host, dwc_priv); +} + static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); @@ -1176,6 +1200,18 @@ static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk35xx_pdata = { .postinit = dwcmshc_rk35xx_postinit, }; +static const struct dwcmshc_pltfm_data sdhci_dwcmshc_rk3576_pdata = { + .pdata = { + .ops = &sdhci_dwcmshc_rk35xx_ops, + .quirks = SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN | + SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_CLOCK_DIV_ZERO_BROKEN, + }, + .init = dwcmshc_rk35xx_init, + .postinit = dwcmshc_rk3576_postinit, +}; + static const struct dwcmshc_pltfm_data sdhci_dwcmshc_th1520_pdata = { .pdata = { .ops = &sdhci_dwcmshc_th1520_ops, @@ -1275,6 +1311,10 @@ static const struct of_device_id sdhci_dwcmshc_dt_ids[] = { .data = &sdhci_dwcmshc_rk35xx_pdata, }, { + .compatible = "rockchip,rk3576-dwcmshc", + .data = &sdhci_dwcmshc_rk3576_pdata, + }, + { .compatible = "rockchip,rk3568-dwcmshc", .data = &sdhci_dwcmshc_rk35xx_pdata, }, diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index f75c31815ab0..73385ff4c0f3 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -155,6 +155,7 @@ struct sdhci_am654_data { u32 tuning_loop; #define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0) +#define SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA BIT(1) }; struct window { @@ -166,6 +167,7 @@ struct window { struct sdhci_am654_driver_data { const struct sdhci_pltfm_data *pdata; u32 flags; + u32 quirks; #define IOMUX_PRESENT (1 << 0) #define FREQSEL_2_BIT (1 << 1) #define STRBSEL_4_BIT (1 << 2) @@ -356,6 +358,29 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host, sdhci_set_clock(host, clock); } +static int sdhci_am654_start_signal_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios) +{ + struct sdhci_host *host = mmc_priv(mmc); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); + int ret; + + if ((sdhci_am654->quirks & SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA) && + ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) { + if (!IS_ERR(mmc->supply.vqmmc)) { + ret = mmc_regulator_set_vqmmc(mmc, ios); + if (ret < 0) { + pr_err("%s: Switching to 1.8V signalling voltage failed,\n", + mmc_hostname(mmc)); + return -EIO; + } + } + return 0; + } + + return sdhci_start_signal_voltage_switch(mmc, ios); +} + static u8 sdhci_am654_write_power_on(struct sdhci_host *host, u8 val, int reg) { writeb(val, host->ioaddr + reg); @@ -650,6 +675,12 @@ static const struct sdhci_am654_driver_data sdhci_j721e_4bit_drvdata = { .flags = IOMUX_PRESENT, }; +static const struct sdhci_am654_driver_data sdhci_am62_4bit_drvdata = { + .pdata = &sdhci_j721e_4bit_pdata, + .flags = IOMUX_PRESENT, + .quirks = SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA, +}; + static const struct soc_device_attribute sdhci_am654_devices[] = { { .family = "AM65X", .revision = "SR1.0", @@ -872,7 +903,7 @@ static const struct of_device_id sdhci_am654_of_match[] = { }, { .compatible = "ti,am62-sdhci", - .data = &sdhci_j721e_4bit_drvdata, + .data = &sdhci_am62_4bit_drvdata, }, { /* sentinel */ } }; @@ -906,6 +937,7 @@ static int sdhci_am654_probe(struct platform_device *pdev) pltfm_host = sdhci_priv(host); sdhci_am654 = sdhci_pltfm_priv(pltfm_host); sdhci_am654->flags = drvdata->flags; + sdhci_am654->quirks = drvdata->quirks; clk_xin = devm_clk_get(dev, "clk_xin"); if (IS_ERR(clk_xin)) { @@ -940,6 +972,7 @@ static int sdhci_am654_probe(struct platform_device *pdev) goto err_pltfm_free; } + host->mmc_host_ops.start_signal_voltage_switch = sdhci_am654_start_signal_voltage_switch; host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning; pm_runtime_get_noresume(dev); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index cf0d51805272..f6921368cd14 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -16,6 +16,7 @@ #include <linux/netdevice.h> #include <linux/pci.h> #include <linux/timer.h> +#include <net/netdev_queues.h> MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Kvaser AB <support@kvaser.com>"); @@ -410,10 +411,13 @@ struct kvaser_pciefd_can { void __iomem *reg_base; struct can_berr_counter bec; u8 cmd_seq; + u8 tx_max_count; + u8 tx_idx; + u8 ack_idx; int err_rep_cnt; - int echo_idx; + unsigned int completed_tx_pkts; + unsigned int completed_tx_bytes; spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */ - spinlock_t echo_lock; /* Locks the message echo buffer */ struct timer_list bec_poll_timer; struct completion start_comp, flush_comp; }; @@ -714,6 +718,9 @@ static int kvaser_pciefd_open(struct net_device *netdev) int ret; struct kvaser_pciefd_can *can = netdev_priv(netdev); + can->tx_idx = 0; + can->ack_idx = 0; + ret = open_candev(netdev); if (ret) return ret; @@ -745,21 +752,26 @@ static int kvaser_pciefd_stop(struct net_device *netdev) timer_delete(&can->bec_poll_timer); } can->can.state = CAN_STATE_STOPPED; + netdev_reset_queue(netdev); close_candev(netdev); return ret; } +static unsigned int kvaser_pciefd_tx_avail(const struct kvaser_pciefd_can *can) +{ + return can->tx_max_count - (READ_ONCE(can->tx_idx) - READ_ONCE(can->ack_idx)); +} + static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p, - struct kvaser_pciefd_can *can, + struct can_priv *can, u8 seq, struct sk_buff *skb) { struct canfd_frame *cf = (struct canfd_frame *)skb->data; int packet_size; - int seq = can->echo_idx; memset(p, 0, sizeof(*p)); - if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + if (can->ctrlmode & CAN_CTRLMODE_ONE_SHOT) p->header[1] |= KVASER_PCIEFD_TPACKET_SMS; if (cf->can_id & CAN_RTR_FLAG) @@ -782,7 +794,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p, } else { p->header[1] |= FIELD_PREP(KVASER_PCIEFD_RPACKET_DLC_MASK, - can_get_cc_dlc((struct can_frame *)cf, can->can.ctrlmode)); + can_get_cc_dlc((struct can_frame *)cf, can->ctrlmode)); } p->header[1] |= FIELD_PREP(KVASER_PCIEFD_PACKET_SEQ_MASK, seq); @@ -797,22 +809,24 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb, struct net_device *netdev) { struct kvaser_pciefd_can *can = netdev_priv(netdev); - unsigned long irq_flags; struct kvaser_pciefd_tx_packet packet; + unsigned int seq = can->tx_idx & (can->can.echo_skb_max - 1); + unsigned int frame_len; int nr_words; - u8 count; if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; + if (!netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1)) + return NETDEV_TX_BUSY; - nr_words = kvaser_pciefd_prepare_tx_packet(&packet, can, skb); + nr_words = kvaser_pciefd_prepare_tx_packet(&packet, &can->can, seq, skb); - spin_lock_irqsave(&can->echo_lock, irq_flags); /* Prepare and save echo skb in internal slot */ - can_put_echo_skb(skb, netdev, can->echo_idx, 0); - - /* Move echo index to the next slot */ - can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max; + WRITE_ONCE(can->can.echo_skb[seq], NULL); + frame_len = can_skb_get_frame_len(skb); + can_put_echo_skb(skb, netdev, seq, frame_len); + netdev_sent_queue(netdev, frame_len); + WRITE_ONCE(can->tx_idx, can->tx_idx + 1); /* Write header to fifo */ iowrite32(packet.header[0], @@ -836,14 +850,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb, KVASER_PCIEFD_KCAN_FIFO_LAST_REG); } - count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK, - ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG)); - /* No room for a new message, stop the queue until at least one - * successful transmit - */ - if (count >= can->can.echo_skb_max || can->can.echo_skb[can->echo_idx]) - netif_stop_queue(netdev); - spin_unlock_irqrestore(&can->echo_lock, irq_flags); + netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1); return NETDEV_TX_OK; } @@ -970,6 +977,8 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) can->kv_pcie = pcie; can->cmd_seq = 0; can->err_rep_cnt = 0; + can->completed_tx_pkts = 0; + can->completed_tx_bytes = 0; can->bec.txerr = 0; can->bec.rxerr = 0; @@ -983,11 +992,10 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) tx_nr_packets_max = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_MAX_MASK, ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG)); + can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1); can->can.clock.freq = pcie->freq; - can->can.echo_skb_max = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1); - can->echo_idx = 0; - spin_lock_init(&can->echo_lock); + can->can.echo_skb_max = roundup_pow_of_two(can->tx_max_count); spin_lock_init(&can->lock); can->can.bittiming_const = &kvaser_pciefd_bittiming_const; @@ -1201,7 +1209,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie, skb = alloc_canfd_skb(priv->dev, &cf); if (!skb) { priv->dev->stats.rx_dropped++; - return -ENOMEM; + return 0; } cf->len = can_fd_dlc2len(dlc); @@ -1213,7 +1221,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie, skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf); if (!skb) { priv->dev->stats.rx_dropped++; - return -ENOMEM; + return 0; } can_frame_set_cc_len((struct can_frame *)cf, dlc, priv->ctrlmode); } @@ -1231,7 +1239,9 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie, priv->dev->stats.rx_packets++; kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp); - return netif_rx(skb); + netif_rx(skb); + + return 0; } static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can, @@ -1510,19 +1520,21 @@ static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie, netdev_dbg(can->can.dev, "Packet was flushed\n"); } else { int echo_idx = FIELD_GET(KVASER_PCIEFD_PACKET_SEQ_MASK, p->header[0]); - int len; - u8 count; + unsigned int len, frame_len = 0; struct sk_buff *skb; + if (echo_idx != (can->ack_idx & (can->can.echo_skb_max - 1))) + return 0; skb = can->can.echo_skb[echo_idx]; - if (skb) - kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp); - len = can_get_echo_skb(can->can.dev, echo_idx, NULL); - count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK, - ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG)); + if (!skb) + return 0; + kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp); + len = can_get_echo_skb(can->can.dev, echo_idx, &frame_len); - if (count < can->can.echo_skb_max && netif_queue_stopped(can->can.dev)) - netif_wake_queue(can->can.dev); + /* Pairs with barrier in kvaser_pciefd_start_xmit() */ + smp_store_release(&can->ack_idx, can->ack_idx + 1); + can->completed_tx_pkts++; + can->completed_tx_bytes += frame_len; if (!one_shot_fail) { can->can.dev->stats.tx_bytes += len; @@ -1638,32 +1650,51 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf) { int pos = 0; int res = 0; + unsigned int i; do { res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf); } while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE); + /* Report ACKs in this buffer to BQL en masse for correct periods */ + for (i = 0; i < pcie->nr_channels; ++i) { + struct kvaser_pciefd_can *can = pcie->can[i]; + + if (!can->completed_tx_pkts) + continue; + netif_subqueue_completed_wake(can->can.dev, 0, + can->completed_tx_pkts, + can->completed_tx_bytes, + kvaser_pciefd_tx_avail(can), 1); + can->completed_tx_pkts = 0; + can->completed_tx_bytes = 0; + } + return res; } -static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie) +static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie) { + void __iomem *srb_cmd_reg = KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG; u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); - if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) + iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); + + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) { kvaser_pciefd_read_buffer(pcie, 0); + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, srb_cmd_reg); /* Rearm buffer */ + } - if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) + if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) { kvaser_pciefd_read_buffer(pcie, 1); + iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, srb_cmd_reg); /* Rearm buffer */ + } if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 || irq & KVASER_PCIEFD_SRB_IRQ_DOF1 || irq & KVASER_PCIEFD_SRB_IRQ_DUF0 || irq & KVASER_PCIEFD_SRB_IRQ_DUF1)) dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq); - - iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG); - return irq; } static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) @@ -1691,29 +1722,22 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev) struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev; const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask; u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie)); - u32 srb_irq = 0; - u32 srb_release = 0; int i; if (!(pci_irq & irq_mask->all)) return IRQ_NONE; + iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); + if (pci_irq & irq_mask->kcan_rx0) - srb_irq = kvaser_pciefd_receive_irq(pcie); + kvaser_pciefd_receive_irq(pcie); for (i = 0; i < pcie->nr_channels; i++) { if (pci_irq & irq_mask->kcan_tx[i]) kvaser_pciefd_transmit_irq(pcie->can[i]); } - if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0) - srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0; - - if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1) - srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1; - - if (srb_release) - iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); + iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); return IRQ_HANDLED; } @@ -1733,13 +1757,22 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie) } } +static void kvaser_pciefd_disable_irq_srcs(struct kvaser_pciefd *pcie) +{ + unsigned int i; + + /* Masking PCI_IRQ is insufficient as running ISR will unmask it */ + iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG); + for (i = 0; i < pcie->nr_channels; ++i) + iowrite32(0, pcie->can[i]->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); +} + static int kvaser_pciefd_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int ret; struct kvaser_pciefd *pcie; const struct kvaser_pciefd_irq_mask *irq_mask; - void __iomem *irq_en_base; pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) @@ -1805,8 +1838,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG); /* Enable PCI interrupts */ - irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie); - iowrite32(irq_mask->all, irq_en_base); + iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); /* Ready the DMA buffers */ iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG); @@ -1820,8 +1852,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return 0; err_free_irq: - /* Disable PCI interrupts */ - iowrite32(0, irq_en_base); + kvaser_pciefd_disable_irq_srcs(pcie); free_irq(pcie->pci->irq, pcie); err_pci_free_irq_vectors: @@ -1844,35 +1875,26 @@ err_disable_pci: return ret; } -static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie) -{ - int i; - - for (i = 0; i < pcie->nr_channels; i++) { - struct kvaser_pciefd_can *can = pcie->can[i]; - - if (can) { - iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); - unregister_candev(can->can.dev); - timer_delete(&can->bec_poll_timer); - kvaser_pciefd_pwm_stop(can); - free_candev(can->can.dev); - } - } -} - static void kvaser_pciefd_remove(struct pci_dev *pdev) { struct kvaser_pciefd *pcie = pci_get_drvdata(pdev); + unsigned int i; - kvaser_pciefd_remove_all_ctrls(pcie); + for (i = 0; i < pcie->nr_channels; ++i) { + struct kvaser_pciefd_can *can = pcie->can[i]; - /* Disable interrupts */ - iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG); - iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie)); + unregister_candev(can->can.dev); + timer_delete(&can->bec_poll_timer); + kvaser_pciefd_pwm_stop(can); + } + kvaser_pciefd_disable_irq_srcs(pcie); free_irq(pcie->pci->irq, pcie); pci_free_irq_vectors(pcie->pci); + + for (i = 0; i < pcie->nr_channels; ++i) + free_candev(pcie->can[i]->can.dev); + pci_iounmap(pdev, pcie->reg_base); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 884a6352c42b..c2c116ce1087 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -2379,6 +2379,7 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, SET_NETDEV_DEV(net_dev, dev); m_can_of_parse_mram(class_dev, mram_config_vals); + spin_lock_init(&class_dev->tx_handling_spinlock); out: return class_dev; } @@ -2462,9 +2463,9 @@ EXPORT_SYMBOL_GPL(m_can_class_register); void m_can_class_unregister(struct m_can_classdev *cdev) { + unregister_candev(cdev->net); if (cdev->is_peripheral) can_rx_offload_del(&cdev->offload); - unregister_candev(cdev->net); } EXPORT_SYMBOL_GPL(m_can_class_unregister); diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c index 7107a37da36c..c3fb3176ce42 100644 --- a/drivers/net/can/rockchip/rockchip_canfd-core.c +++ b/drivers/net/can/rockchip/rockchip_canfd-core.c @@ -937,8 +937,8 @@ static void rkcanfd_remove(struct platform_device *pdev) struct rkcanfd_priv *priv = platform_get_drvdata(pdev); struct net_device *ndev = priv->ndev; - can_rx_offload_del(&priv->offload); rkcanfd_unregister(priv); + can_rx_offload_del(&priv->offload); free_candev(ndev); } diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index 24c6622d36bd..58ff2ec1d975 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -71,12 +71,21 @@ MODULE_AUTHOR("Dario Binacchi <dario.binacchi@amarulasolutions.com>"); #define SLCAN_CMD_LEN 1 #define SLCAN_SFF_ID_LEN 3 #define SLCAN_EFF_ID_LEN 8 +#define SLCAN_DATA_LENGTH_LEN 1 +#define SLCAN_ERROR_LEN 1 #define SLCAN_STATE_LEN 1 #define SLCAN_STATE_BE_RXCNT_LEN 3 #define SLCAN_STATE_BE_TXCNT_LEN 3 -#define SLCAN_STATE_FRAME_LEN (1 + SLCAN_CMD_LEN + \ - SLCAN_STATE_BE_RXCNT_LEN + \ - SLCAN_STATE_BE_TXCNT_LEN) +#define SLCAN_STATE_MSG_LEN (SLCAN_CMD_LEN + \ + SLCAN_STATE_LEN + \ + SLCAN_STATE_BE_RXCNT_LEN + \ + SLCAN_STATE_BE_TXCNT_LEN) +#define SLCAN_ERROR_MSG_LEN_MIN (SLCAN_CMD_LEN + \ + SLCAN_ERROR_LEN + \ + SLCAN_DATA_LENGTH_LEN) +#define SLCAN_FRAME_MSG_LEN_MIN (SLCAN_CMD_LEN + \ + SLCAN_SFF_ID_LEN + \ + SLCAN_DATA_LENGTH_LEN) struct slcan { struct can_priv can; @@ -176,6 +185,9 @@ static void slcan_bump_frame(struct slcan *sl) u32 tmpid; char *cmd = sl->rbuff; + if (sl->rcount < SLCAN_FRAME_MSG_LEN_MIN) + return; + skb = alloc_can_skb(sl->dev, &cf); if (unlikely(!skb)) { sl->dev->stats.rx_dropped++; @@ -281,7 +293,7 @@ static void slcan_bump_state(struct slcan *sl) return; } - if (state == sl->can.state || sl->rcount < SLCAN_STATE_FRAME_LEN) + if (state == sl->can.state || sl->rcount != SLCAN_STATE_MSG_LEN) return; cmd += SLCAN_STATE_BE_RXCNT_LEN + SLCAN_CMD_LEN + 1; @@ -328,6 +340,9 @@ static void slcan_bump_err(struct slcan *sl) bool rx_errors = false, tx_errors = false, rx_over_errors = false; int i, len; + if (sl->rcount < SLCAN_ERROR_MSG_LEN_MIN) + return; + /* get len from sanitized ASCII value */ len = cmd[1]; if (len >= '0' && len < '9') @@ -456,8 +471,7 @@ static void slcan_bump(struct slcan *sl) static void slcan_unesc(struct slcan *sl, unsigned char s) { if ((s == '\r') || (s == '\a')) { /* CR or BEL ends the pdu */ - if (!test_and_clear_bit(SLF_ERROR, &sl->flags) && - sl->rcount > 4) + if (!test_and_clear_bit(SLF_ERROR, &sl->flags)) slcan_bump(sl); sl->rcount = 0; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 3bc56517fe7a..c30b04f8fc0d 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -75,6 +75,24 @@ static const struct can_bittiming_const mcp251xfd_data_bittiming_const = { .brp_inc = 1, }; +/* The datasheet of the mcp2518fd (DS20006027B) specifies a range of + * [-64,63] for TDCO, indicating a relative TDCO. + * + * Manual tests have shown, that using a relative TDCO configuration + * results in bus off, while an absolute configuration works. + * + * For TDCO use the max value (63) from the data sheet, but 0 as the + * minimum. + */ +static const struct can_tdc_const mcp251xfd_tdc_const = { + .tdcv_min = 0, + .tdcv_max = 63, + .tdco_min = 0, + .tdco_max = 63, + .tdcf_min = 0, + .tdcf_max = 0, +}; + static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model) { switch (model) { @@ -510,8 +528,7 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv) { const struct can_bittiming *bt = &priv->can.bittiming; const struct can_bittiming *dbt = &priv->can.data_bittiming; - u32 val = 0; - s8 tdco; + u32 tdcmod, val = 0; int err; /* CAN Control Register @@ -575,11 +592,16 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv) return err; /* Transmitter Delay Compensation */ - tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1), - -64, 63); - val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, - MCP251XFD_REG_TDC_TDCMOD_AUTO) | - FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco); + if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO) + tdcmod = MCP251XFD_REG_TDC_TDCMOD_AUTO; + else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL) + tdcmod = MCP251XFD_REG_TDC_TDCMOD_MANUAL; + else + tdcmod = MCP251XFD_REG_TDC_TDCMOD_DISABLED; + + val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, tdcmod) | + FIELD_PREP(MCP251XFD_REG_TDC_TDCV_MASK, priv->can.tdc.tdcv) | + FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, priv->can.tdc.tdco); return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val); } @@ -2083,10 +2105,12 @@ static int mcp251xfd_probe(struct spi_device *spi) priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter; priv->can.bittiming_const = &mcp251xfd_bittiming_const; priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const; + priv->can.tdc_const = &mcp251xfd_tdc_const; priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | - CAN_CTRLMODE_CC_LEN8_DLC; + CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO | + CAN_CTRLMODE_TDC_MANUAL; set_bit(MCP251XFD_FLAGS_DOWN, priv->flags); priv->ndev = ndev; priv->spi = spi; @@ -2174,8 +2198,8 @@ static void mcp251xfd_remove(struct spi_device *spi) struct mcp251xfd_priv *priv = spi_get_drvdata(spi); struct net_device *ndev = priv->ndev; - can_rx_offload_del(&priv->offload); mcp251xfd_unregister(priv); + can_rx_offload_del(&priv->offload); spi->max_speed_hz = priv->spi_max_speed_hz_orig; free_candev(ndev); } diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index e5ba71897906..7216eb8f9493 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -326,6 +326,26 @@ static void b53_get_vlan_entry(struct b53_device *dev, u16 vid, } } +static void b53_set_eap_mode(struct b53_device *dev, int port, int mode) +{ + u64 eap_conf; + + if (is5325(dev) || is5365(dev) || dev->chip_id == BCM5389_DEVICE_ID) + return; + + b53_read64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), &eap_conf); + + if (is63xx(dev)) { + eap_conf &= ~EAP_MODE_MASK_63XX; + eap_conf |= (u64)mode << EAP_MODE_SHIFT_63XX; + } else { + eap_conf &= ~EAP_MODE_MASK; + eap_conf |= (u64)mode << EAP_MODE_SHIFT; + } + + b53_write64(dev, B53_EAP_PAGE, B53_PORT_EAP_CONF(port), eap_conf); +} + static void b53_set_forwarding(struct b53_device *dev, int enable) { u8 mgmt; @@ -373,15 +393,17 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable, b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5); } + vc1 &= ~VC1_RX_MCST_FWD_EN; + if (enable) { vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID; - vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN; + vc1 |= VC1_RX_MCST_UNTAG_EN; vc4 &= ~VC4_ING_VID_CHECK_MASK; if (enable_filtering) { vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; vc5 |= VC5_DROP_VTABLE_MISS; } else { - vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S; + vc4 |= VC4_NO_ING_VID_CHK << VC4_ING_VID_CHECK_S; vc5 &= ~VC5_DROP_VTABLE_MISS; } @@ -393,7 +415,7 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable, } else { vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID); - vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN); + vc1 &= ~VC1_RX_MCST_UNTAG_EN; vc4 &= ~VC4_ING_VID_CHECK_MASK; vc5 &= ~VC5_DROP_VTABLE_MISS; @@ -576,6 +598,25 @@ static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable) b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg); } +int b53_setup_port(struct dsa_switch *ds, int port) +{ + struct b53_device *dev = ds->priv; + + b53_port_set_ucast_flood(dev, port, true); + b53_port_set_mcast_flood(dev, port, true); + b53_port_set_learning(dev, port, false); + + /* Force all traffic to go to the CPU port to prevent the ASIC from + * trying to forward to bridged ports on matching FDB entries, then + * dropping frames because it isn't allowed to forward there. + */ + if (dsa_is_user_port(ds, port)) + b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED); + + return 0; +} +EXPORT_SYMBOL(b53_setup_port); + int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) { struct b53_device *dev = ds->priv; @@ -588,10 +629,6 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) cpu_port = dsa_to_port(ds, port)->cpu_dp->index; - b53_port_set_ucast_flood(dev, port, true); - b53_port_set_mcast_flood(dev, port, true); - b53_port_set_learning(dev, port, false); - if (dev->ops->irq_enable) ret = dev->ops->irq_enable(dev, port); if (ret) @@ -722,10 +759,6 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port) b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl); b53_brcm_hdr_setup(dev->ds, port); - - b53_port_set_ucast_flood(dev, port, true); - b53_port_set_mcast_flood(dev, port, true); - b53_port_set_learning(dev, port, false); } static void b53_enable_mib(struct b53_device *dev) @@ -761,6 +794,22 @@ static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port) return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port); } +static bool b53_vlan_port_may_join_untagged(struct dsa_switch *ds, int port) +{ + struct b53_device *dev = ds->priv; + struct dsa_port *dp; + + if (!dev->vlan_filtering) + return true; + + dp = dsa_to_port(ds, port); + + if (dsa_port_is_cpu(dp)) + return true; + + return dp->bridge == NULL; +} + int b53_configure_vlan(struct dsa_switch *ds) { struct b53_device *dev = ds->priv; @@ -779,7 +828,7 @@ int b53_configure_vlan(struct dsa_switch *ds) b53_do_vlan_op(dev, VTA_CMD_CLEAR); } - b53_enable_vlan(dev, -1, dev->vlan_enabled, ds->vlan_filtering); + b53_enable_vlan(dev, -1, dev->vlan_enabled, dev->vlan_filtering); /* Create an untagged VLAN entry for the default PVID in case * CONFIG_VLAN_8021Q is disabled and there are no calls to @@ -787,26 +836,39 @@ int b53_configure_vlan(struct dsa_switch *ds) * entry. Do this only when the tagging protocol is not * DSA_TAG_PROTO_NONE */ + v = &dev->vlans[def_vid]; b53_for_each_port(dev, i) { - v = &dev->vlans[def_vid]; - v->members |= BIT(i); + if (!b53_vlan_port_may_join_untagged(ds, i)) + continue; + + vl.members |= BIT(i); if (!b53_vlan_port_needs_forced_tagged(ds, i)) - v->untag = v->members; - b53_write16(dev, B53_VLAN_PAGE, - B53_VLAN_PORT_DEF_TAG(i), def_vid); + vl.untag = vl.members; + b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(i), + def_vid); } + b53_set_vlan_entry(dev, def_vid, &vl); - /* Upon initial call we have not set-up any VLANs, but upon - * system resume, we need to restore all VLAN entries. - */ - for (vid = def_vid; vid < dev->num_vlans; vid++) { - v = &dev->vlans[vid]; + if (dev->vlan_filtering) { + /* Upon initial call we have not set-up any VLANs, but upon + * system resume, we need to restore all VLAN entries. + */ + for (vid = def_vid + 1; vid < dev->num_vlans; vid++) { + v = &dev->vlans[vid]; - if (!v->members) - continue; + if (!v->members) + continue; - b53_set_vlan_entry(dev, vid, v); - b53_fast_age_vlan(dev, vid); + b53_set_vlan_entry(dev, vid, v); + b53_fast_age_vlan(dev, vid); + } + + b53_for_each_port(dev, i) { + if (!dsa_is_cpu_port(ds, i)) + b53_write16(dev, B53_VLAN_PAGE, + B53_VLAN_PORT_DEF_TAG(i), + dev->ports[i].pvid); + } } return 0; @@ -1125,7 +1187,9 @@ EXPORT_SYMBOL(b53_setup_devlink_resources); static int b53_setup(struct dsa_switch *ds) { struct b53_device *dev = ds->priv; + struct b53_vlan *vl; unsigned int port; + u16 pvid; int ret; /* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set @@ -1133,12 +1197,26 @@ static int b53_setup(struct dsa_switch *ds) */ ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE; + /* The switch does not tell us the original VLAN for untagged + * packets, so keep the CPU port always tagged. + */ + ds->untag_vlan_aware_bridge_pvid = true; + ret = b53_reset_switch(dev); if (ret) { dev_err(ds->dev, "failed to reset switch\n"); return ret; } + /* setup default vlan for filtering mode */ + pvid = b53_default_pvid(dev); + vl = &dev->vlans[pvid]; + b53_for_each_port(dev, port) { + vl->members |= BIT(port); + if (!b53_vlan_port_needs_forced_tagged(ds, port)) + vl->untag |= BIT(port); + } + b53_reset_mib(dev); ret = b53_apply_config(dev); @@ -1492,7 +1570,10 @@ int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, { struct b53_device *dev = ds->priv; - b53_enable_vlan(dev, port, dev->vlan_enabled, vlan_filtering); + if (dev->vlan_filtering != vlan_filtering) { + dev->vlan_filtering = vlan_filtering; + b53_apply_config(dev); + } return 0; } @@ -1517,7 +1598,7 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port, if (vlan->vid >= dev->num_vlans) return -ERANGE; - b53_enable_vlan(dev, port, true, ds->vlan_filtering); + b53_enable_vlan(dev, port, true, dev->vlan_filtering); return 0; } @@ -1530,18 +1611,29 @@ int b53_vlan_add(struct dsa_switch *ds, int port, bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; struct b53_vlan *vl; + u16 old_pvid, new_pvid; int err; err = b53_vlan_prepare(ds, port, vlan); if (err) return err; - vl = &dev->vlans[vlan->vid]; + if (vlan->vid == 0) + return 0; - b53_get_vlan_entry(dev, vlan->vid, vl); + old_pvid = dev->ports[port].pvid; + if (pvid) + new_pvid = vlan->vid; + else if (!pvid && vlan->vid == old_pvid) + new_pvid = b53_default_pvid(dev); + else + new_pvid = old_pvid; + dev->ports[port].pvid = new_pvid; - if (vlan->vid == 0 && vlan->vid == b53_default_pvid(dev)) - untagged = true; + vl = &dev->vlans[vlan->vid]; + + if (dsa_is_cpu_port(ds, port)) + untagged = false; vl->members |= BIT(port); if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port)) @@ -1549,13 +1641,16 @@ int b53_vlan_add(struct dsa_switch *ds, int port, else vl->untag &= ~BIT(port); + if (!dev->vlan_filtering) + return 0; + b53_set_vlan_entry(dev, vlan->vid, vl); b53_fast_age_vlan(dev, vlan->vid); - if (pvid && !dsa_is_cpu_port(ds, port)) { + if (!dsa_is_cpu_port(ds, port) && new_pvid != old_pvid) { b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), - vlan->vid); - b53_fast_age_vlan(dev, vlan->vid); + new_pvid); + b53_fast_age_vlan(dev, old_pvid); } return 0; @@ -1570,20 +1665,25 @@ int b53_vlan_del(struct dsa_switch *ds, int port, struct b53_vlan *vl; u16 pvid; - b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid); + if (vlan->vid == 0) + return 0; - vl = &dev->vlans[vlan->vid]; + pvid = dev->ports[port].pvid; - b53_get_vlan_entry(dev, vlan->vid, vl); + vl = &dev->vlans[vlan->vid]; vl->members &= ~BIT(port); if (pvid == vlan->vid) pvid = b53_default_pvid(dev); + dev->ports[port].pvid = pvid; if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port)) vl->untag &= ~(BIT(port)); + if (!dev->vlan_filtering) + return 0; + b53_set_vlan_entry(dev, vlan->vid, vl); b53_fast_age_vlan(dev, vlan->vid); @@ -1916,8 +2016,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack) { struct b53_device *dev = ds->priv; + struct b53_vlan *vl; s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index; - u16 pvlan, reg; + u16 pvlan, reg, pvid; unsigned int i; /* On 7278, port 7 which connects to the ASP should only receive @@ -1926,15 +2027,29 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, if (dev->chip_id == BCM7278_DEVICE_ID && port == 7) return -EINVAL; - /* Make this port leave the all VLANs join since we will have proper - * VLAN entries from now on - */ - if (is58xx(dev)) { - b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®); - reg &= ~BIT(port); - if ((reg & BIT(cpu_port)) == BIT(cpu_port)) - reg &= ~BIT(cpu_port); - b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg); + pvid = b53_default_pvid(dev); + vl = &dev->vlans[pvid]; + + if (dev->vlan_filtering) { + /* Make this port leave the all VLANs join since we will have + * proper VLAN entries from now on + */ + if (is58xx(dev)) { + b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, + ®); + reg &= ~BIT(port); + if ((reg & BIT(cpu_port)) == BIT(cpu_port)) + reg &= ~BIT(cpu_port); + b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, + reg); + } + + b53_get_vlan_entry(dev, pvid, vl); + vl->members &= ~BIT(port); + if (vl->members == BIT(cpu_port)) + vl->members &= ~BIT(cpu_port); + vl->untag = vl->members; + b53_set_vlan_entry(dev, pvid, vl); } b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan); @@ -1954,6 +2069,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, pvlan |= BIT(i); } + /* Disable redirection of unknown SA to the CPU port */ + b53_set_eap_mode(dev, port, EAP_MODE_BASIC); + /* Configure the local port VLAN control membership to include * remote ports and update the local port bitmask */ @@ -1967,7 +2085,7 @@ EXPORT_SYMBOL(b53_br_join); void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct b53_device *dev = ds->priv; - struct b53_vlan *vl = &dev->vlans[0]; + struct b53_vlan *vl; s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index; unsigned int i; u16 pvlan, reg, pvid; @@ -1989,19 +2107,25 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) pvlan &= ~BIT(i); } + /* Enable redirection of unknown SA to the CPU port */ + b53_set_eap_mode(dev, port, EAP_MODE_SIMPLIFIED); + b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan); dev->ports[port].vlan_ctl_mask = pvlan; pvid = b53_default_pvid(dev); + vl = &dev->vlans[pvid]; + + if (dev->vlan_filtering) { + /* Make this port join all VLANs without VLAN entries */ + if (is58xx(dev)) { + b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®); + reg |= BIT(port); + if (!(reg & BIT(cpu_port))) + reg |= BIT(cpu_port); + b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg); + } - /* Make this port join all VLANs without VLAN entries */ - if (is58xx(dev)) { - b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®); - reg |= BIT(port); - if (!(reg & BIT(cpu_port))) - reg |= BIT(cpu_port); - b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg); - } else { b53_get_vlan_entry(dev, pvid, vl); vl->members |= BIT(port) | BIT(cpu_port); vl->untag |= BIT(port) | BIT(cpu_port); @@ -2300,6 +2424,7 @@ static const struct dsa_switch_ops b53_switch_ops = { .phy_read = b53_phy_read16, .phy_write = b53_phy_write16, .phylink_get_caps = b53_phylink_get_caps, + .port_setup = b53_setup_port, .port_enable = b53_enable_port, .port_disable = b53_disable_port, .support_eee = b53_support_eee, @@ -2757,6 +2882,7 @@ struct b53_device *b53_switch_alloc(struct device *base, ds->ops = &b53_switch_ops; ds->phylink_mac_ops = &b53_phylink_mac_ops; dev->vlan_enabled = true; + dev->vlan_filtering = false; /* Let DSA handle the case were multiple bridges span the same switch * device and different VLAN awareness settings are requested, which * would be breaking filtering semantics for any of the other bridge diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 0166c37a13a7..2cf3e6a81e37 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -96,6 +96,7 @@ struct b53_pcs { struct b53_port { u16 vlan_ctl_mask; + u16 pvid; struct ethtool_keee eee; }; @@ -147,6 +148,7 @@ struct b53_device { unsigned int num_vlans; struct b53_vlan *vlans; bool vlan_enabled; + bool vlan_filtering; unsigned int num_ports; struct b53_port *ports; @@ -382,6 +384,7 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); void b53_mirror_del(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); +int b53_setup_port(struct dsa_switch *ds, int port); int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy); void b53_disable_port(struct dsa_switch *ds, int port); void b53_brcm_hdr_setup(struct dsa_switch *ds, int port); diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index bfbcb66bef66..5f7a0e5c5709 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -50,6 +50,9 @@ /* Jumbo Frame Registers */ #define B53_JUMBO_PAGE 0x40 +/* EAP Registers */ +#define B53_EAP_PAGE 0x42 + /* EEE Control Registers Page */ #define B53_EEE_PAGE 0x92 @@ -481,6 +484,17 @@ #define JMS_MAX_SIZE 9724 /************************************************************************* + * EAP Page Registers + *************************************************************************/ +#define B53_PORT_EAP_CONF(i) (0x20 + 8 * (i)) +#define EAP_MODE_SHIFT 51 +#define EAP_MODE_SHIFT_63XX 50 +#define EAP_MODE_MASK (0x3ull << EAP_MODE_SHIFT) +#define EAP_MODE_MASK_63XX (0x3ull << EAP_MODE_SHIFT_63XX) +#define EAP_MODE_BASIC 0 +#define EAP_MODE_SIMPLIFIED 3 + +/************************************************************************* * EEE Configuration Page Registers *************************************************************************/ diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index fa2bf3fa9019..454a8c7fd7ee 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1230,6 +1230,7 @@ static const struct dsa_switch_ops bcm_sf2_ops = { .resume = bcm_sf2_sw_resume, .get_wol = bcm_sf2_sw_get_wol, .set_wol = bcm_sf2_sw_set_wol, + .port_setup = b53_setup_port, .port_enable = bcm_sf2_port_setup, .port_disable = bcm_sf2_port_disable, .support_eee = b53_support_eee, diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 89f0796894af..f95a9aac56ee 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -265,16 +265,70 @@ static void ksz_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface); +/** + * ksz_phylink_mac_disable_tx_lpi() - Callback to signal LPI support (Dummy) + * @config: phylink config structure + * + * This function is a dummy handler. See ksz_phylink_mac_enable_tx_lpi() for + * a detailed explanation of EEE/LPI handling in KSZ switches. + */ +static void ksz_phylink_mac_disable_tx_lpi(struct phylink_config *config) +{ +} + +/** + * ksz_phylink_mac_enable_tx_lpi() - Callback to signal LPI support (Dummy) + * @config: phylink config structure + * @timer: timer value before entering LPI (unused) + * @tx_clock_stop: whether to stop the TX clock in LPI mode (unused) + * + * This function signals to phylink that the driver architecture supports + * LPI management, enabling phylink to control EEE advertisement during + * negotiation according to IEEE Std 802.3 (Clause 78). + * + * Hardware Management of EEE/LPI State: + * For KSZ switch ports with integrated PHYs (e.g., KSZ9893R ports 1-2), + * observation and testing suggest that the actual EEE / Low Power Idle (LPI) + * state transitions are managed autonomously by the hardware based on + * the auto-negotiation results. (Note: While the datasheet describes EEE + * operation based on negotiation, it doesn't explicitly detail the internal + * MAC/PHY interaction, so autonomous hardware management of the MAC state + * for LPI is inferred from observed behavior). + * This hardware control, consistent with the switch's ability to operate + * autonomously via strapping, means MAC-level software intervention is not + * required or exposed for managing the LPI state once EEE is negotiated. + * (Ref: KSZ9893R Data Sheet DS00002420D, primarily Section 4.7.5 explaining + * EEE, also Sections 4.1.7 on Auto-Negotiation and 3.2.1 on Configuration + * Straps). + * + * Additionally, ports configured as MAC interfaces (e.g., KSZ9893R port 3) + * lack documented MAC-level LPI control. + * + * Therefore, this callback performs no action and serves primarily to inform + * phylink of LPI awareness and to document the inferred hardware behavior. + * + * Returns: 0 (Always success) + */ +static int ksz_phylink_mac_enable_tx_lpi(struct phylink_config *config, + u32 timer, bool tx_clock_stop) +{ + return 0; +} + static const struct phylink_mac_ops ksz88x3_phylink_mac_ops = { .mac_config = ksz88x3_phylink_mac_config, .mac_link_down = ksz_phylink_mac_link_down, .mac_link_up = ksz8_phylink_mac_link_up, + .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi, + .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi, }; static const struct phylink_mac_ops ksz8_phylink_mac_ops = { .mac_config = ksz_phylink_mac_config, .mac_link_down = ksz_phylink_mac_link_down, .mac_link_up = ksz8_phylink_mac_link_up, + .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi, + .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi, }; static const struct ksz_dev_ops ksz88xx_dev_ops = { @@ -358,6 +412,8 @@ static const struct phylink_mac_ops ksz9477_phylink_mac_ops = { .mac_config = ksz_phylink_mac_config, .mac_link_down = ksz_phylink_mac_link_down, .mac_link_up = ksz9477_phylink_mac_link_up, + .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi, + .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi, }; static const struct ksz_dev_ops ksz9477_dev_ops = { @@ -401,6 +457,8 @@ static const struct phylink_mac_ops lan937x_phylink_mac_ops = { .mac_config = ksz_phylink_mac_config, .mac_link_down = ksz_phylink_mac_link_down, .mac_link_up = ksz9477_phylink_mac_link_up, + .mac_disable_tx_lpi = ksz_phylink_mac_disable_tx_lpi, + .mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi, }; static const struct ksz_dev_ops lan937x_dev_ops = { @@ -2016,6 +2074,18 @@ static void ksz_phylink_get_caps(struct dsa_switch *ds, int port, if (dev->dev_ops->get_caps) dev->dev_ops->get_caps(dev, port, config); + + if (ds->ops->support_eee && ds->ops->support_eee(ds, port)) { + memcpy(config->lpi_interfaces, config->supported_interfaces, + sizeof(config->lpi_interfaces)); + + config->lpi_capabilities = MAC_100FD; + if (dev->info->gbit_capable[port]) + config->lpi_capabilities |= MAC_1000FD; + + /* EEE is fully operational */ + config->eee_enabled_default = true; + } } void ksz_r_mib_stats64(struct ksz_device *dev, int port) @@ -3008,31 +3078,6 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port) if (!port) return MICREL_KSZ8_P1_ERRATA; break; - case KSZ8567_CHIP_ID: - /* KSZ8567R Errata DS80000752C Module 4 */ - case KSZ8765_CHIP_ID: - case KSZ8794_CHIP_ID: - case KSZ8795_CHIP_ID: - /* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */ - case KSZ9477_CHIP_ID: - /* KSZ9477S Errata DS80000754A Module 4 */ - case KSZ9567_CHIP_ID: - /* KSZ9567S Errata DS80000756A Module 4 */ - case KSZ9896_CHIP_ID: - /* KSZ9896C Errata DS80000757A Module 3 */ - case KSZ9897_CHIP_ID: - case LAN9646_CHIP_ID: - /* KSZ9897R Errata DS80000758C Module 4 */ - /* Energy Efficient Ethernet (EEE) feature select must be manually disabled - * The EEE feature is enabled by default, but it is not fully - * operational. It must be manually disabled through register - * controls. If not disabled, the PHY ports can auto-negotiate - * to enable EEE, and this feature can cause link drops when - * linked to another device supporting EEE. - * - * The same item appears in the errata for all switches above. - */ - return MICREL_NO_EEE; } return 0; @@ -3466,6 +3511,20 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port) return -EOPNOTSUPP; } +/** + * ksz_support_eee - Determine Energy Efficient Ethernet (EEE) support for a + * port + * @ds: Pointer to the DSA switch structure + * @port: Port number to check + * + * This function also documents devices where EEE was initially advertised but + * later withdrawn due to reliability issues, as described in official errata + * documents. These devices are explicitly listed to record known limitations, + * even if there is no technical necessity for runtime checks. + * + * Returns: true if the internal PHY on the given port supports fully + * operational EEE, false otherwise. + */ static bool ksz_support_eee(struct dsa_switch *ds, int port) { struct ksz_device *dev = ds->priv; @@ -3475,15 +3534,35 @@ static bool ksz_support_eee(struct dsa_switch *ds, int port) switch (dev->chip_id) { case KSZ8563_CHIP_ID: + case KSZ9563_CHIP_ID: + case KSZ9893_CHIP_ID: + return true; case KSZ8567_CHIP_ID: + /* KSZ8567R Errata DS80000752C Module 4 */ + case KSZ8765_CHIP_ID: + case KSZ8794_CHIP_ID: + case KSZ8795_CHIP_ID: + /* KSZ879x/KSZ877x/KSZ876x Errata DS80000687C Module 2 */ case KSZ9477_CHIP_ID: - case KSZ9563_CHIP_ID: + /* KSZ9477S Errata DS80000754A Module 4 */ case KSZ9567_CHIP_ID: - case KSZ9893_CHIP_ID: + /* KSZ9567S Errata DS80000756A Module 4 */ case KSZ9896_CHIP_ID: + /* KSZ9896C Errata DS80000757A Module 3 */ case KSZ9897_CHIP_ID: case LAN9646_CHIP_ID: - return true; + /* KSZ9897R Errata DS80000758C Module 4 */ + /* Energy Efficient Ethernet (EEE) feature select must be + * manually disabled + * The EEE feature is enabled by default, but it is not fully + * operational. It must be manually disabled through register + * controls. If not disabled, the PHY ports can auto-negotiate + * to enable EEE, and this feature can cause link drops when + * linked to another device supporting EEE. + * + * The same item appears in the errata for all switches above. + */ + break; } return false; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index f8454f3b6f9c..f674c400f05b 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2081,6 +2081,7 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port, switch (state) { case BR_STATE_DISABLED: case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: /* From UM10944 description of DRPDTAG (why put this there?): * "Management traffic flows to the port regardless of the state * of the INGRESS flag". So BPDUs are still be allowed to pass. @@ -2090,11 +2091,6 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port, mac[port].egress = false; mac[port].dyn_learn = false; break; - case BR_STATE_LISTENING: - mac[port].ingress = true; - mac[port].egress = false; - mac[port].dyn_learn = false; - break; case BR_STATE_LEARNING: mac[port].ingress = true; mac[port].egress = false; diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index d748dc6de923..1e9ab65218ff 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -614,7 +614,6 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) struct airoha_queue_entry *e = &q->entry[q->tail]; struct airoha_qdma_desc *desc = &q->desc[q->tail]; u32 hash, reason, msg1 = le32_to_cpu(desc->msg1); - dma_addr_t dma_addr = le32_to_cpu(desc->addr); struct page *page = virt_to_head_page(e->buf); u32 desc_ctrl = le32_to_cpu(desc->ctrl); struct airoha_gdm_port *port; @@ -623,22 +622,16 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) if (!(desc_ctrl & QDMA_DESC_DONE_MASK)) break; - if (!dma_addr) - break; - - len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl); - if (!len) - break; - q->tail = (q->tail + 1) % q->ndesc; q->queued--; - dma_sync_single_for_cpu(eth->dev, dma_addr, + dma_sync_single_for_cpu(eth->dev, e->dma_addr, SKB_WITH_OVERHEAD(q->buf_size), dir); + len = FIELD_GET(QDMA_DESC_LEN_MASK, desc_ctrl); data_len = q->skb ? q->buf_size : SKB_WITH_OVERHEAD(q->buf_size); - if (data_len < len) + if (!len || data_len < len) goto free_frag; p = airoha_qdma_get_gdm_port(eth, desc); @@ -701,9 +694,12 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) q->skb = NULL; continue; free_frag: - page_pool_put_full_page(q->page_pool, page, true); - dev_kfree_skb(q->skb); - q->skb = NULL; + if (q->skb) { + dev_kfree_skb(q->skb); + q->skb = NULL; + } else { + page_pool_put_full_page(q->page_pool, page, true); + } } airoha_qdma_fill_rx_queue(q); diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c index 7a5710f9ccf6..ead0625e781f 100644 --- a/drivers/net/ethernet/airoha/airoha_npu.c +++ b/drivers/net/ethernet/airoha/airoha_npu.c @@ -104,12 +104,14 @@ struct ppe_mbox_data { u8 xpon_hal_api; u8 wan_xsi; u8 ct_joyme4; - int ppe_type; - int wan_mode; - int wan_sel; + u8 max_packet; + u8 rsv[3]; + u32 ppe_type; + u32 wan_mode; + u32 wan_sel; } init_info; struct { - int func_id; + u32 func_id; u32 size; u32 data; } set_info; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 86a5de44b6f3..6afc2ab6fad2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -14013,13 +14013,28 @@ static void bnxt_unlock_sp(struct bnxt *bp) netdev_unlock(bp->dev); } +/* Same as bnxt_lock_sp() with additional rtnl_lock */ +static void bnxt_rtnl_lock_sp(struct bnxt *bp) +{ + clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + rtnl_lock(); + netdev_lock(bp->dev); +} + +static void bnxt_rtnl_unlock_sp(struct bnxt *bp) +{ + set_bit(BNXT_STATE_IN_SP_TASK, &bp->state); + netdev_unlock(bp->dev); + rtnl_unlock(); +} + /* Only called from bnxt_sp_task() */ static void bnxt_reset(struct bnxt *bp, bool silent) { - bnxt_lock_sp(bp); + bnxt_rtnl_lock_sp(bp); if (test_bit(BNXT_STATE_OPEN, &bp->state)) bnxt_reset_task(bp, silent); - bnxt_unlock_sp(bp); + bnxt_rtnl_unlock_sp(bp); } /* Only called from bnxt_sp_task() */ @@ -14027,9 +14042,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) { int i; - bnxt_lock_sp(bp); + bnxt_rtnl_lock_sp(bp); if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { - bnxt_unlock_sp(bp); + bnxt_rtnl_unlock_sp(bp); return; } /* Disable and flush TPA before resetting the RX ring */ @@ -14068,7 +14083,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) } if (bp->flags & BNXT_FLAG_TPA) bnxt_set_tpa(bp, true); - bnxt_unlock_sp(bp); + bnxt_rtnl_unlock_sp(bp); } static void bnxt_fw_fatal_close(struct bnxt *bp) @@ -14960,15 +14975,17 @@ static void bnxt_fw_reset_task(struct work_struct *work) bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING; fallthrough; case BNXT_FW_RESET_STATE_OPENING: - while (!netdev_trylock(bp->dev)) { + while (!rtnl_trylock()) { bnxt_queue_fw_reset_work(bp, HZ / 10); return; } + netdev_lock(bp->dev); rc = bnxt_open(bp->dev); if (rc) { netdev_err(bp->dev, "bnxt_open() failed during FW reset\n"); bnxt_fw_reset_abort(bp, rc); netdev_unlock(bp->dev); + rtnl_unlock(); goto ulp_start; } @@ -14988,6 +15005,7 @@ static void bnxt_fw_reset_task(struct work_struct *work) bnxt_dl_health_fw_status_update(bp, true); } netdev_unlock(bp->dev); + rtnl_unlock(); bnxt_ulp_start(bp, 0); bnxt_reenable_sriov(bp); netdev_lock(bp->dev); @@ -15936,7 +15954,7 @@ err_reset: rc); napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); - bnxt_reset_task(bp, true); + netif_close(dev); return rc; } @@ -16752,6 +16770,7 @@ static int bnxt_resume(struct device *device) struct bnxt *bp = netdev_priv(dev); int rc = 0; + rtnl_lock(); netdev_lock(dev); rc = pci_enable_device(bp->pdev); if (rc) { @@ -16796,6 +16815,7 @@ static int bnxt_resume(struct device *device) resume_exit: netdev_unlock(bp->dev); + rtnl_unlock(); bnxt_ulp_start(bp, rc); if (!rc) bnxt_reenable_sriov(bp); @@ -16961,6 +16981,7 @@ static void bnxt_io_resume(struct pci_dev *pdev) int err; netdev_info(bp->dev, "PCI Slot Resume\n"); + rtnl_lock(); netdev_lock(netdev); err = bnxt_hwrm_func_qcaps(bp); @@ -16978,6 +16999,7 @@ static void bnxt_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); netdev_unlock(netdev); + rtnl_unlock(); bnxt_ulp_start(bp, err); if (!err) bnxt_reenable_sriov(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index a8e930d5dbb0..7564705d6478 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -20,6 +20,7 @@ #include <asm/byteorder.h> #include <linux/bitmap.h> #include <linux/auxiliary_bus.h> +#include <net/netdev_lock.h> #include "bnxt_hsi.h" #include "bnxt.h" @@ -309,14 +310,12 @@ void bnxt_ulp_irq_stop(struct bnxt *bp) if (!ulp->msix_requested) return; - netdev_lock(bp->dev); - ops = rcu_dereference(ulp->ulp_ops); + ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev); if (!ops || !ops->ulp_irq_stop) return; if (test_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) reset = true; ops->ulp_irq_stop(ulp->handle, reset); - netdev_unlock(bp->dev); } } @@ -335,8 +334,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) if (!ulp->msix_requested) return; - netdev_lock(bp->dev); - ops = rcu_dereference(ulp->ulp_ops); + ops = netdev_lock_dereference(ulp->ulp_ops, bp->dev); if (!ops || !ops->ulp_irq_restart) return; @@ -348,7 +346,6 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) bnxt_fill_msix_vecs(bp, ent); } ops->ulp_irq_restart(ulp->handle, ent); - netdev_unlock(bp->dev); kfree(ent); } } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 1fe8ec37491b..e1e8bd2ec155 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -997,22 +997,15 @@ static void macb_update_stats(struct macb *bp) static int macb_halt_tx(struct macb *bp) { - unsigned long halt_time, timeout; - u32 status; + u32 status; macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT)); - timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT); - do { - halt_time = jiffies; - status = macb_readl(bp, TSR); - if (!(status & MACB_BIT(TGO))) - return 0; - - udelay(250); - } while (time_before(halt_time, timeout)); - - return -ETIMEDOUT; + /* Poll TSR until TGO is cleared or timeout. */ + return read_poll_timeout_atomic(macb_readl, status, + !(status & MACB_BIT(TGO)), + 250, MACB_HALT_TIMEOUT, false, + bp, TSR); } static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budget) diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 625245b0845c..eba73246f986 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -67,6 +67,8 @@ #define TSNEP_TX_TYPE_XDP_NDO_MAP_PAGE (TSNEP_TX_TYPE_XDP_NDO | TSNEP_TX_TYPE_MAP_PAGE) #define TSNEP_TX_TYPE_XDP (TSNEP_TX_TYPE_XDP_TX | TSNEP_TX_TYPE_XDP_NDO) #define TSNEP_TX_TYPE_XSK BIT(12) +#define TSNEP_TX_TYPE_TSTAMP BIT(13) +#define TSNEP_TX_TYPE_SKB_TSTAMP (TSNEP_TX_TYPE_SKB | TSNEP_TX_TYPE_TSTAMP) #define TSNEP_XDP_TX BIT(0) #define TSNEP_XDP_REDIRECT BIT(1) @@ -386,8 +388,7 @@ static void tsnep_tx_activate(struct tsnep_tx *tx, int index, int length, if (entry->skb) { entry->properties = length & TSNEP_DESC_LENGTH_MASK; entry->properties |= TSNEP_DESC_INTERRUPT_FLAG; - if ((entry->type & TSNEP_TX_TYPE_SKB) && - (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS)) + if ((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP) entry->properties |= TSNEP_DESC_EXTENDED_WRITEBACK_FLAG; /* toggle user flag to prevent false acknowledge @@ -479,7 +480,8 @@ static int tsnep_tx_map_frag(skb_frag_t *frag, struct tsnep_tx_entry *entry, return mapped; } -static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count) +static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count, + bool do_tstamp) { struct device *dmadev = tx->adapter->dmadev; struct tsnep_tx_entry *entry; @@ -505,6 +507,9 @@ static int tsnep_tx_map(struct sk_buff *skb, struct tsnep_tx *tx, int count) entry->type = TSNEP_TX_TYPE_SKB_INLINE; mapped = 0; } + + if (do_tstamp) + entry->type |= TSNEP_TX_TYPE_TSTAMP; } else { skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; @@ -558,11 +563,12 @@ static int tsnep_tx_unmap(struct tsnep_tx *tx, int index, int count) static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, struct tsnep_tx *tx) { - int count = 1; struct tsnep_tx_entry *entry; + bool do_tstamp = false; + int count = 1; int length; - int i; int retval; + int i; if (skb_shinfo(skb)->nr_frags > 0) count += skb_shinfo(skb)->nr_frags; @@ -579,7 +585,13 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, entry = &tx->entry[tx->write]; entry->skb = skb; - retval = tsnep_tx_map(skb, tx, count); + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + tx->adapter->hwtstamp_config.tx_type == HWTSTAMP_TX_ON) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + do_tstamp = true; + } + + retval = tsnep_tx_map(skb, tx, count, do_tstamp); if (retval < 0) { tsnep_tx_unmap(tx, tx->write, count); dev_kfree_skb_any(entry->skb); @@ -591,9 +603,6 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, } length = retval; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - for (i = 0; i < count; i++) tsnep_tx_activate(tx, (tx->write + i) & TSNEP_RING_MASK, length, i == count - 1); @@ -844,8 +853,7 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) length = tsnep_tx_unmap(tx, tx->read, count); - if ((entry->type & TSNEP_TX_TYPE_SKB) && - (skb_shinfo(entry->skb)->tx_flags & SKBTX_IN_PROGRESS) && + if (((entry->type & TSNEP_TX_TYPE_SKB_TSTAMP) == TSNEP_TX_TYPE_SKB_TSTAMP) && (__le32_to_cpu(entry->desc_wb->properties) & TSNEP_DESC_EXTENDED_WRITEBACK_FLAG)) { struct skb_shared_hwtstamps hwtstamps; diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c index a0bcfb5a713d..ff3295b60a69 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c @@ -61,6 +61,8 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) return -EBUSY; } + netif_device_detach(priv->netdev); + priv->reset_type = type; set_bit(HBG_NIC_STATE_RESETTING, &priv->state); clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); @@ -91,6 +93,8 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type) return ret; } + netif_device_attach(priv->netdev); + dev_info(&priv->pdev->dev, "reset done\n"); return ret; } @@ -117,16 +121,13 @@ void hbg_err_reset(struct hbg_priv *priv) if (running) dev_close(priv->netdev); - hbg_reset(priv); - - /* in hbg_pci_err_detected(), we will detach first, - * so we need to attach before open - */ - if (!netif_device_present(priv->netdev)) - netif_device_attach(priv->netdev); + if (hbg_reset(priv)) + goto err_unlock; if (running) dev_open(priv->netdev, NULL); + +err_unlock: rtnl_unlock(); } @@ -160,7 +161,6 @@ static pci_ers_result_t hbg_pci_err_slot_reset(struct pci_dev *pdev) pci_save_state(pdev); hbg_err_reset(priv); - netif_device_attach(netdev); return PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c index 8f1107b85fbb..55520053270a 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c @@ -317,6 +317,9 @@ static void hbg_update_stats_by_info(struct hbg_priv *priv, const struct hbg_ethtool_stats *stats; u32 i; + if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state)) + return; + for (i = 0; i < info_len; i++) { stats = &info[i]; if (!stats->reg) diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c index 01a08cfd0090..66e070095d1b 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.c +++ b/drivers/net/ethernet/intel/ice/ice_adapter.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only // SPDX-FileCopyrightText: Copyright Red Hat -#include <linux/bitfield.h> #include <linux/cleanup.h> #include <linux/mutex.h> #include <linux/pci.h> @@ -14,32 +13,16 @@ static DEFINE_XARRAY(ice_adapters); static DEFINE_MUTEX(ice_adapters_mutex); -/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */ -#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13) -#define INDEX_FIELD_DEV GENMASK(31, 16) -#define INDEX_FIELD_BUS GENMASK(12, 5) -#define INDEX_FIELD_SLOT GENMASK(4, 0) - -static unsigned long ice_adapter_index(const struct pci_dev *pdev) +static unsigned long ice_adapter_index(u64 dsn) { - unsigned int domain = pci_domain_nr(pdev->bus); - - WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN)); - - switch (pdev->device) { - case ICE_DEV_ID_E825C_BACKPLANE: - case ICE_DEV_ID_E825C_QSFP: - case ICE_DEV_ID_E825C_SFP: - case ICE_DEV_ID_E825C_SGMII: - return FIELD_PREP(INDEX_FIELD_DEV, pdev->device); - default: - return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) | - FIELD_PREP(INDEX_FIELD_BUS, pdev->bus->number) | - FIELD_PREP(INDEX_FIELD_SLOT, PCI_SLOT(pdev->devfn)); - } +#if BITS_PER_LONG == 64 + return dsn; +#else + return (u32)dsn ^ (u32)(dsn >> 32); +#endif } -static struct ice_adapter *ice_adapter_new(void) +static struct ice_adapter *ice_adapter_new(u64 dsn) { struct ice_adapter *adapter; @@ -47,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void) if (!adapter) return NULL; + adapter->device_serial_number = dsn; spin_lock_init(&adapter->ptp_gltsyn_time_lock); refcount_set(&adapter->refcount, 1); @@ -77,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter) * Return: Pointer to ice_adapter on success. * ERR_PTR() on error. -ENOMEM is the only possible error. */ -struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev) +struct ice_adapter *ice_adapter_get(struct pci_dev *pdev) { - unsigned long index = ice_adapter_index(pdev); + u64 dsn = pci_get_dsn(pdev); struct ice_adapter *adapter; + unsigned long index; int err; + index = ice_adapter_index(dsn); scoped_guard(mutex, &ice_adapters_mutex) { err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL); if (err == -EBUSY) { adapter = xa_load(&ice_adapters, index); refcount_inc(&adapter->refcount); + WARN_ON_ONCE(adapter->device_serial_number != dsn); return adapter; } if (err) return ERR_PTR(err); - adapter = ice_adapter_new(); + adapter = ice_adapter_new(dsn); if (!adapter) return ERR_PTR(-ENOMEM); xa_store(&ice_adapters, index, adapter, GFP_KERNEL); @@ -110,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev) * * Context: Process, may sleep. */ -void ice_adapter_put(const struct pci_dev *pdev) +void ice_adapter_put(struct pci_dev *pdev) { - unsigned long index = ice_adapter_index(pdev); + u64 dsn = pci_get_dsn(pdev); struct ice_adapter *adapter; + unsigned long index; + index = ice_adapter_index(dsn); scoped_guard(mutex, &ice_adapters_mutex) { adapter = xa_load(&ice_adapters, index); if (WARN_ON(!adapter)) diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h index e233225848b3..ac15c0d2bc1a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adapter.h +++ b/drivers/net/ethernet/intel/ice/ice_adapter.h @@ -32,6 +32,7 @@ struct ice_port_list { * @refcount: Reference count. struct ice_pf objects hold the references. * @ctrl_pf: Control PF of the adapter * @ports: Ports list + * @device_serial_number: DSN cached for collision detection on 32bit systems */ struct ice_adapter { refcount_t refcount; @@ -40,9 +41,10 @@ struct ice_adapter { struct ice_pf *ctrl_pf; struct ice_port_list ports; + u64 device_serial_number; }; -struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev); -void ice_adapter_put(const struct pci_dev *pdev); +struct ice_adapter *ice_adapter_get(struct pci_dev *pdev); +void ice_adapter_put(struct pci_dev *pdev); #endif /* _ICE_ADAPTER_H */ diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 22371011c249..2410aee59fb2 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -1321,12 +1321,18 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) */ if (!primary_lag) { lag->primary = true; + if (!ice_is_switchdev_running(lag->pf)) + return; + /* Configure primary's SWID to be shared */ ice_lag_primary_swid(lag, true); primary_lag = lag; } else { u16 swid; + if (!ice_is_switchdev_running(primary_lag->pf)) + return; + swid = primary_lag->pf->hw.port_info->sw_id; ice_lag_set_swid(swid, lag, true); ice_lag_add_prune_list(primary_lag, lag->pf); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 7c3006eb68dd..6446d0fcc052 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -4275,7 +4275,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) } ice_vfhw_mac_add(vf, &al->list[i]); - vf->num_mac++; break; } diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index aef0e9775a33..70dbf80f3bb7 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -143,6 +143,7 @@ enum idpf_vport_state { * @vport_id: Vport identifier * @link_speed_mbps: Link speed in mbps * @vport_idx: Relative vport index + * @max_tx_hdr_size: Max header length hardware can support * @state: See enum idpf_vport_state * @netstats: Packet and byte stats * @stats_lock: Lock to protect stats update @@ -153,6 +154,7 @@ struct idpf_netdev_priv { u32 vport_id; u32 link_speed_mbps; u16 vport_idx; + u16 max_tx_hdr_size; enum idpf_vport_state state; struct rtnl_link_stats64 netstats; spinlock_t stats_lock; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 82f09b4030bc..3a033ce19cda 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -723,6 +723,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) np->vport = vport; np->vport_idx = vport->idx; np->vport_id = vport->vport_id; + np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter); vport->netdev = netdev; return idpf_init_mac_addr(vport, netdev); @@ -740,6 +741,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) np->adapter = adapter; np->vport_idx = vport->idx; np->vport_id = vport->vport_id; + np->max_tx_hdr_size = idpf_get_max_tx_hdr_size(adapter); spin_lock_init(&np->stats_lock); @@ -2203,8 +2205,8 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb, struct net_device *netdev, netdev_features_t features) { - struct idpf_vport *vport = idpf_netdev_to_vport(netdev); - struct idpf_adapter *adapter = vport->adapter; + struct idpf_netdev_priv *np = netdev_priv(netdev); + u16 max_tx_hdr_size = np->max_tx_hdr_size; size_t len; /* No point in doing any of this if neither checksum nor GSO are @@ -2227,7 +2229,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb, goto unsupported; len = skb_network_header_len(skb); - if (unlikely(len > idpf_get_max_tx_hdr_size(adapter))) + if (unlikely(len > max_tx_hdr_size)) goto unsupported; if (!skb->encapsulation) @@ -2240,7 +2242,7 @@ static netdev_features_t idpf_features_check(struct sk_buff *skb, /* IPLEN can support at most 127 dwords */ len = skb_inner_network_header_len(skb); - if (unlikely(len > idpf_get_max_tx_hdr_size(adapter))) + if (unlikely(len > max_tx_hdr_size)) goto unsupported; /* No need to validate L4LEN as TCP is the only protocol with a diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index bdf52cef3891..2d5f5c9f91ce 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -4025,6 +4025,14 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) return budget; } + /* Switch to poll mode in the tear-down path after sending disable + * queues virtchnl message, as the interrupts will be disabled after + * that. + */ + if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE, + q_vector->tx[0]))) + return budget; + work_done = min_t(int, work_done, budget - 1); /* Exit the polling mode, but don't re-enable interrupts if stack might @@ -4035,15 +4043,7 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget) else idpf_vport_intr_set_wb_on_itr(q_vector); - /* Switch to poll mode in the tear-down path after sending disable - * queues virtchnl message, as the interrupts will be disabled after - * that - */ - if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE, - q_vector->tx[0]))) - return budget; - else - return work_done; + return work_done; } /** diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 0b27a695008b..971993586fb4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -717,6 +717,11 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat) if (!is_lmac_valid(cgx, lmac_id)) return -ENODEV; + + /* pass lmac as 0 for CGX_CMR_RX_STAT9-12 */ + if (idx >= CGX_RX_STAT_GLOBAL_INDEX) + lmac_id = 0; + *rx_stat = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_STAT0 + (idx * 8)); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 7fa98aeb3663..4a3370a40dd8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -13,19 +13,26 @@ /* RVU LMTST */ #define LMT_TBL_OP_READ 0 #define LMT_TBL_OP_WRITE 1 -#define LMT_MAP_TABLE_SIZE (128 * 1024) #define LMT_MAPTBL_ENTRY_SIZE 16 +#define LMT_MAX_VFS 256 + +#define LMT_MAP_ENTRY_ENA BIT_ULL(20) +#define LMT_MAP_ENTRY_LINES GENMASK_ULL(18, 16) /* Function to perform operations (read/write) on lmtst map table */ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, int lmt_tbl_op) { void __iomem *lmt_map_base; - u64 tbl_base; + u64 tbl_base, cfg; + int pfs, vfs; tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE); + cfg = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG); + vfs = 1 << (cfg & 0xF); + pfs = 1 << ((cfg >> 4) & 0x7); - lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE); + lmt_map_base = ioremap_wc(tbl_base, pfs * vfs * LMT_MAPTBL_ENTRY_SIZE); if (!lmt_map_base) { dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n"); return -ENOMEM; @@ -35,6 +42,13 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, *val = readq(lmt_map_base + index); } else { writeq((*val), (lmt_map_base + index)); + + cfg = FIELD_PREP(LMT_MAP_ENTRY_ENA, 0x1); + /* 2048 LMTLINES */ + cfg |= FIELD_PREP(LMT_MAP_ENTRY_LINES, 0x6); + + writeq(cfg, (lmt_map_base + (index + 8))); + /* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S * changes effective. Write 1 for flush and read is being used as a * barrier and sets up a data dependency. Write to 0 after a write @@ -52,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val, #define LMT_MAP_TBL_W1_OFF 8 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc) { - return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) + + return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) + (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE; } @@ -69,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, mutex_lock(&rvu->rsrc_lock); rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova); - pf = rvu_get_pf(pcifunc) & 0x1F; + pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK; val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 | ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF); rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index a1f9ec03c2ce..c827da626471 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -553,6 +553,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, u64 lmt_addr, val, tbl_base; int pf, vf, num_vfs, hw_vfs; void __iomem *lmt_map_base; + int apr_pfs, apr_vfs; int buf_size = 10240; size_t off = 0; int index = 0; @@ -568,8 +569,12 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, return -ENOMEM; tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE); + val = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CFG); + apr_vfs = 1 << (val & 0xF); + apr_pfs = 1 << ((val >> 4) & 0x7); - lmt_map_base = ioremap_wc(tbl_base, 128 * 1024); + lmt_map_base = ioremap_wc(tbl_base, apr_pfs * apr_vfs * + LMT_MAPTBL_ENTRY_SIZE); if (!lmt_map_base) { dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n"); kfree(buf); @@ -591,7 +596,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d \t\t\t", pf); - index = pf * rvu->hw->total_vfs * LMT_MAPTBL_ENTRY_SIZE; + index = pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE; off += scnprintf(&buf[off], buf_size - 1 - off, " 0x%llx\t\t", (tbl_base + index)); lmt_addr = readq(lmt_map_base + index); @@ -604,7 +609,7 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, /* Reading num of VFs per PF */ rvu_get_pf_numvfs(rvu, pf, &num_vfs, &hw_vfs); for (vf = 0; vf < num_vfs; vf++) { - index = (pf * rvu->hw->total_vfs * 16) + + index = (pf * apr_vfs * LMT_MAPTBL_ENTRY_SIZE) + ((vf + 1) * LMT_MAPTBL_ENTRY_SIZE); off += scnprintf(&buf[off], buf_size - 1 - off, "PF%d:VF%d \t\t", pf, vf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index f3b9daffaec3..4c7e0f345cb5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -531,7 +531,8 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf, if (sw_tx_sc->encrypt) sectag_tci |= (MCS_TCI_E | MCS_TCI_C); - policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, secy->netdev->mtu); + policy = FIELD_PREP(MCS_TX_SECY_PLCY_MTU, + pfvf->netdev->mtu + OTX2_ETH_HLEN); /* Write SecTag excluding AN bits(1..0) */ policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_TCI, sectag_tci >> 2); policy |= FIELD_PREP(MCS_TX_SECY_PLCY_ST_OFFSET, tag_offset); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 1e88422825be..d6b4b74e4002 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -356,6 +356,7 @@ struct otx2_flow_config { struct list_head flow_list_tc; u8 ucast_flt_cnt; bool ntuple; + u16 ntuple_cnt; }; struct dev_hw_ops { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 33ec9a7f7c03..e13ae5484c19 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -41,6 +41,7 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id, if (!pfvf->flow_cfg) return 0; + pfvf->flow_cfg->ntuple_cnt = ctx->val.vu16; otx2_alloc_mcam_entries(pfvf, ctx->val.vu16); return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 010385b29988..45b8c9230184 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -315,7 +315,7 @@ static void otx2_get_pauseparam(struct net_device *netdev, struct otx2_nic *pfvf = netdev_priv(netdev); struct cgx_pause_frm_cfg *req, *rsp; - if (is_otx2_lbkvf(pfvf->pdev)) + if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) return; mutex_lock(&pfvf->mbox.lock); @@ -347,7 +347,7 @@ static int otx2_set_pauseparam(struct net_device *netdev, if (pause->autoneg) return -EOPNOTSUPP; - if (is_otx2_lbkvf(pfvf->pdev)) + if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) return -EOPNOTSUPP; if (pause->rx_pause) @@ -941,8 +941,8 @@ static u32 otx2_get_link(struct net_device *netdev) { struct otx2_nic *pfvf = netdev_priv(netdev); - /* LBK link is internal and always UP */ - if (is_otx2_lbkvf(pfvf->pdev)) + /* LBK and SDP links are internal and always UP */ + if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) return 1; return pfvf->linfo.link_up; } @@ -1413,7 +1413,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev, { struct otx2_nic *pfvf = netdev_priv(netdev); - if (is_otx2_lbkvf(pfvf->pdev)) { + if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) { cmd->base.duplex = DUPLEX_FULL; cmd->base.speed = SPEED_100000; } else { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 47bfd1fb37d4..64c6d9162ef6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -247,7 +247,7 @@ int otx2_mcam_entry_init(struct otx2_nic *pfvf) mutex_unlock(&pfvf->mbox.lock); /* Allocate entries for Ntuple filters */ - count = otx2_alloc_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT); + count = otx2_alloc_mcam_entries(pfvf, flow_cfg->ntuple_cnt); if (count <= 0) { otx2_clear_ntuple_flow_info(pfvf, flow_cfg); return 0; @@ -307,6 +307,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc); pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS; + pf->flow_cfg->ntuple_cnt = OTX2_DEFAULT_FLOWCOUNT; /* Allocate bare minimum number of MCAM entries needed for * unicast and ntuple filters. diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 7ef3ba477d49..9b28be4c4a5d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -729,9 +729,12 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) } #ifdef CONFIG_DCB - err = otx2_dcbnl_set_ops(netdev); - if (err) - goto err_free_zc_bmap; + /* Priority flow control is not supported for LBK and SDP vf(s) */ + if (!(is_otx2_lbkvf(vf->pdev) || is_otx2_sdp_rep(vf->pdev))) { + err = otx2_dcbnl_set_ops(netdev); + if (err) + goto err_free_zc_bmap; + } #endif otx2_qos_init(vf, qos_txqs); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 8fda4ce80d81..6c92072b4c28 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3186,11 +3186,19 @@ static int mtk_dma_init(struct mtk_eth *eth) static void mtk_dma_free(struct mtk_eth *eth) { const struct mtk_soc_data *soc = eth->soc; - int i; + int i, j, txqs = 1; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + txqs = MTK_QDMA_NUM_QUEUES; + + for (i = 0; i < MTK_MAX_DEVS; i++) { + if (!eth->netdev[i]) + continue; + + for (j = 0; j < txqs; j++) + netdev_tx_reset_subqueue(eth->netdev[i], j); + } - for (i = 0; i < MTK_MAX_DEVS; i++) - if (eth->netdev[i]) - netdev_reset_queue(eth->netdev[i]); if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) { dma_free_coherent(eth->dma_dev, MTK_QDMA_RING_SIZE * soc->tx.desc_size, @@ -3465,9 +3473,6 @@ static int mtk_open(struct net_device *dev) } mtk_gdm_config(eth, target_mac->id, gdm_config); } - /* Reset and enable PSE */ - mtk_w32(eth, RST_GL_PSE, MTK_RST_GL); - mtk_w32(eth, 0, MTK_RST_GL); napi_enable(ð->tx_napi); napi_enable(ð->rx_napi); @@ -4743,7 +4748,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) } if (mtk_is_netsys_v3_or_greater(mac->hw) && - MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW_BIT) && + MTK_HAS_CAPS(mac->hw->soc->caps, MTK_ESW) && id == MTK_GMAC1_ID) { mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 3506024c2453..9bd166f489e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4349,6 +4349,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n"); + features &= ~NETIF_F_HW_MACSEC; + if (netdev->features & NETIF_F_HW_MACSEC) + netdev_warn(netdev, "Disabling HW MACsec offload, not supported in switchdev mode\n"); + return features; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 464821dd492d..a2033837182e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -3014,6 +3014,9 @@ static int mlxsw_sp_neigh_rif_made_sync(struct mlxsw_sp *mlxsw_sp, .rif = rif, }; + if (!mlxsw_sp_dev_lower_is_port(mlxsw_sp_rif_dev(rif))) + return 0; + neigh_for_each(&arp_tbl, mlxsw_sp_neigh_rif_made_sync_each, &rms); if (rms.err) goto err_arp; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index 4ca7b99ef131..de6b1a340f55 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -154,14 +154,14 @@ struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev); void fbnic_devlink_register(struct fbnic_dev *fbd); void fbnic_devlink_unregister(struct fbnic_dev *fbd); -int fbnic_fw_enable_mbx(struct fbnic_dev *fbd); -void fbnic_fw_disable_mbx(struct fbnic_dev *fbd); +int fbnic_fw_request_mbx(struct fbnic_dev *fbd); +void fbnic_fw_free_mbx(struct fbnic_dev *fbd); void fbnic_hwmon_register(struct fbnic_dev *fbd); void fbnic_hwmon_unregister(struct fbnic_dev *fbd); -int fbnic_pcs_irq_enable(struct fbnic_dev *fbd); -void fbnic_pcs_irq_disable(struct fbnic_dev *fbd); +int fbnic_pcs_request_irq(struct fbnic_dev *fbd); +void fbnic_pcs_free_irq(struct fbnic_dev *fbd); void fbnic_napi_name_irqs(struct fbnic_dev *fbd); int fbnic_napi_request_irq(struct fbnic_dev *fbd, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h index 3b12a0ab5906..51bee8072420 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h @@ -796,8 +796,10 @@ enum { /* PUL User Registers */ #define FBNIC_CSR_START_PUL_USER 0x31000 /* CSR section delimiter */ #define FBNIC_PUL_OB_TLP_HDR_AW_CFG 0x3103d /* 0xc40f4 */ +#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH CSR_BIT(19) #define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME CSR_BIT(18) #define FBNIC_PUL_OB_TLP_HDR_AR_CFG 0x3103e /* 0xc40f8 */ +#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH CSR_BIT(19) #define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME CSR_BIT(18) #define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \ 0x3106e /* 0xc41b8 */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c index 88db3dacb940..3d9636a6c968 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c @@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx, { u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx); + /* Write the upper 32b and then the lower 32b. Doing this the + * FW can then read lower, upper, lower to verify that the state + * of the descriptor wasn't changed mid-transaction. + */ fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc)); fw_wrfl(fbd); fw_wr32(fbd, desc_offset, lower_32_bits(desc)); } +static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx, + int desc_idx, u32 desc) +{ + u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx); + + /* For initialization we write the lower 32b of the descriptor first. + * This way we can set the state to mark it invalid before we clear the + * upper 32b. + */ + fw_wr32(fbd, desc_offset, desc); + fw_wrfl(fbd); + fw_wr32(fbd, desc_offset + 1, 0); +} + static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx) { u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx); @@ -33,29 +51,41 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx) return desc; } -static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx) +static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx) { int desc_idx; + /* Disable DMA transactions from the device, + * and flush any transactions triggered during cleaning + */ + switch (mbx_idx) { + case FBNIC_IPC_MBX_RX_IDX: + wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG, + FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH); + break; + case FBNIC_IPC_MBX_TX_IDX: + wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG, + FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH); + break; + } + + wrfl(fbd); + /* Initialize first descriptor to all 0s. Doing this gives us a * solid stop for the firmware to hit when it is done looping * through the ring. */ - __fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0); - - fw_wrfl(fbd); + __fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0); /* We then fill the rest of the ring starting at the end and moving * back toward descriptor 0 with skip descriptors that have no * length nor address, and tell the firmware that they can skip * them and just move past them to the one we initialized to 0. */ - for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) { - __fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx, - FBNIC_IPC_MBX_DESC_FW_CMPL | - FBNIC_IPC_MBX_DESC_HOST_CMPL); - fw_wrfl(fbd); - } + for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) + __fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx, + FBNIC_IPC_MBX_DESC_FW_CMPL | + FBNIC_IPC_MBX_DESC_HOST_CMPL); } void fbnic_mbx_init(struct fbnic_dev *fbd) @@ -76,7 +106,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd) wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY); for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++) - fbnic_mbx_init_desc_ring(fbd, i); + fbnic_mbx_reset_desc_ring(fbd, i); } static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx, @@ -141,7 +171,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx) { int i; - fbnic_mbx_init_desc_ring(fbd, mbx_idx); + fbnic_mbx_reset_desc_ring(fbd, mbx_idx); for (i = FBNIC_IPC_MBX_DESC_LEN; i--;) fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i); @@ -322,67 +352,41 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type) return err; } -/** - * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message - * @fbd: FBNIC device structure - * - * Return: NULL on failure to allocate, error pointer on error, or pointer - * to new TLV test message. - * - * Sends a single TLV header indicating the host wants the firmware to - * confirm the capabilities and version. - **/ -static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd) -{ - int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ); - - /* Return 0 if we are not calling this on ASIC */ - return (err == -EOPNOTSUPP) ? 0 : err; -} - -static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx) +static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx) { struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx]; - /* This is a one time init, so just exit if it is completed */ - if (mbx->ready) - return; - mbx->ready = true; switch (mbx_idx) { case FBNIC_IPC_MBX_RX_IDX: + /* Enable DMA writes from the device */ + wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG, + FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME); + /* Make sure we have a page for the FW to write to */ fbnic_mbx_alloc_rx_msgs(fbd); break; case FBNIC_IPC_MBX_TX_IDX: - /* Force version to 1 if we successfully requested an update - * from the firmware. This should be overwritten once we get - * the actual version from the firmware in the capabilities - * request message. - */ - if (!fbnic_fw_xmit_cap_msg(fbd) && - !fbd->fw_cap.running.mgmt.version) - fbd->fw_cap.running.mgmt.version = 1; + /* Enable DMA reads from the device */ + wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG, + FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME); break; } } -static void fbnic_mbx_postinit(struct fbnic_dev *fbd) +static bool fbnic_mbx_event(struct fbnic_dev *fbd) { - int i; - - /* We only need to do this on the first interrupt following init. + /* We only need to do this on the first interrupt following reset. * this primes the mailbox so that we will have cleared all the * skip descriptors. */ if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY))) - return; + return false; wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY); - for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++) - fbnic_mbx_postinit_desc_ring(fbd, i); + return true; } /** @@ -859,7 +863,7 @@ next_page: void fbnic_mbx_poll(struct fbnic_dev *fbd) { - fbnic_mbx_postinit(fbd); + fbnic_mbx_event(fbd); fbnic_mbx_process_tx_msgs(fbd); fbnic_mbx_process_rx_msgs(fbd); @@ -867,60 +871,97 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd) int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd) { - struct fbnic_fw_mbx *tx_mbx; - int attempts = 50; + unsigned long timeout = jiffies + 10 * HZ + 1; + int err, i; - /* Immediate fail if BAR4 isn't there */ - if (!fbnic_fw_present(fbd)) - return -ENODEV; + do { + if (!time_is_after_jiffies(timeout)) + return -ETIMEDOUT; - tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX]; - while (!tx_mbx->ready && --attempts) { /* Force the firmware to trigger an interrupt response to * avoid the mailbox getting stuck closed if the interrupt * is reset. */ - fbnic_mbx_init_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX); + fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX); - msleep(200); + /* Immediate fail if BAR4 went away */ + if (!fbnic_fw_present(fbd)) + return -ENODEV; - fbnic_mbx_poll(fbd); - } + msleep(20); + } while (!fbnic_mbx_event(fbd)); + + /* FW has shown signs of life. Enable DMA and start Tx/Rx */ + for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++) + fbnic_mbx_init_desc_ring(fbd, i); + + /* Request an update from the firmware. This should overwrite + * mgmt.version once we get the actual version from the firmware + * in the capabilities request message. + */ + err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ); + if (err) + goto clean_mbx; + + /* Use "1" to indicate we entered the state waiting for a response */ + fbd->fw_cap.running.mgmt.version = 1; + + return 0; +clean_mbx: + /* Cleanup Rx buffers and disable mailbox */ + fbnic_mbx_clean(fbd); + return err; +} + +static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data) +{ + cmpl_data->result = -EPIPE; + complete(&cmpl_data->done); +} - return attempts ? 0 : -ETIMEDOUT; +static void fbnic_mbx_evict_all_cmpl(struct fbnic_dev *fbd) +{ + if (fbd->cmpl_data) { + __fbnic_fw_evict_cmpl(fbd->cmpl_data); + fbd->cmpl_data = NULL; + } } void fbnic_mbx_flush_tx(struct fbnic_dev *fbd) { + unsigned long timeout = jiffies + 10 * HZ + 1; struct fbnic_fw_mbx *tx_mbx; - int attempts = 50; - u8 count = 0; - - /* Nothing to do if there is no mailbox */ - if (!fbnic_fw_present(fbd)) - return; + u8 tail; /* Record current Rx stats */ tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX]; - /* Nothing to do if mailbox never got to ready */ - if (!tx_mbx->ready) - return; + spin_lock_irq(&fbd->fw_tx_lock); + + /* Clear ready to prevent any further attempts to transmit */ + tx_mbx->ready = false; + + /* Read tail to determine the last tail state for the ring */ + tail = tx_mbx->tail; + + /* Flush any completions as we are no longer processing Rx */ + fbnic_mbx_evict_all_cmpl(fbd); + + spin_unlock_irq(&fbd->fw_tx_lock); /* Give firmware time to process packet, - * we will wait up to 10 seconds which is 50 waits of 200ms. + * we will wait up to 10 seconds which is 500 waits of 20ms. */ do { u8 head = tx_mbx->head; - if (head == tx_mbx->tail) + /* Tx ring is empty once head == tail */ + if (head == tail) break; - msleep(200); + msleep(20); fbnic_mbx_process_tx_msgs(fbd); - - count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN; - } while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts); + } while (time_is_after_jiffies(timeout)); } void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c index 1bbc0e56f3a0..1c88a2bf3a7a 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c @@ -19,69 +19,105 @@ static irqreturn_t fbnic_fw_msix_intr(int __always_unused irq, void *data) return IRQ_HANDLED; } +static int __fbnic_fw_enable_mbx(struct fbnic_dev *fbd, int vector) +{ + int err; + + /* Initialize mailbox and attempt to poll it into ready state */ + fbnic_mbx_init(fbd); + err = fbnic_mbx_poll_tx_ready(fbd); + if (err) { + dev_warn(fbd->dev, "FW mailbox did not enter ready state\n"); + return err; + } + + /* Enable interrupt and unmask the vector */ + enable_irq(vector); + fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY); + + return 0; +} + /** - * fbnic_fw_enable_mbx - Configure and initialize Firmware Mailbox + * fbnic_fw_request_mbx - Configure and initialize Firmware Mailbox * @fbd: Pointer to device to initialize * - * This function will initialize the firmware mailbox rings, enable the IRQ - * and initialize the communication between the Firmware and the host. The - * firmware is expected to respond to the initialization by sending an - * interrupt essentially notifying the host that it has seen the - * initialization and is now synced up. + * This function will allocate the IRQ and then reinitialize the mailbox + * starting communication between the host and firmware. * * Return: non-zero on failure. **/ -int fbnic_fw_enable_mbx(struct fbnic_dev *fbd) +int fbnic_fw_request_mbx(struct fbnic_dev *fbd) { - u32 vector = fbd->fw_msix_vector; - int err; + struct pci_dev *pdev = to_pci_dev(fbd->dev); + int vector, err; + + WARN_ON(fbd->fw_msix_vector); + + vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY); + if (vector < 0) + return vector; /* Request the IRQ for FW Mailbox vector. */ err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr, - IRQF_ONESHOT, dev_name(fbd->dev), fbd); + IRQF_ONESHOT | IRQF_NO_AUTOEN, + dev_name(fbd->dev), fbd); if (err) return err; /* Initialize mailbox and attempt to poll it into ready state */ - fbnic_mbx_init(fbd); - err = fbnic_mbx_poll_tx_ready(fbd); - if (err) { - dev_warn(fbd->dev, "FW mailbox did not enter ready state\n"); + err = __fbnic_fw_enable_mbx(fbd, vector); + if (err) free_irq(vector, fbd); - return err; - } - /* Enable interrupts */ - fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY); + fbd->fw_msix_vector = vector; - return 0; + return err; } /** - * fbnic_fw_disable_mbx - Disable mailbox and place it in standby state - * @fbd: Pointer to device to disable + * fbnic_fw_disable_mbx - Temporarily place mailbox in standby state + * @fbd: Pointer to device * - * This function will disable the mailbox interrupt, free any messages still - * in the mailbox and place it into a standby state. The firmware is - * expected to see the update and assume that the host is in the reset state. + * Shutdown the mailbox by notifying the firmware to stop sending us logs, mask + * and synchronize the IRQ, and then clean up the rings. **/ -void fbnic_fw_disable_mbx(struct fbnic_dev *fbd) +static void fbnic_fw_disable_mbx(struct fbnic_dev *fbd) { - /* Disable interrupt and free vector */ - fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY); + /* Disable interrupt and synchronize the IRQ */ + disable_irq(fbd->fw_msix_vector); - /* Free the vector */ - free_irq(fbd->fw_msix_vector, fbd); + /* Mask the vector */ + fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY); /* Make sure disabling logs message is sent, must be done here to * avoid risk of completing without a running interrupt. */ fbnic_mbx_flush_tx(fbd); - - /* Reset the mailboxes to the initialized state */ fbnic_mbx_clean(fbd); } +/** + * fbnic_fw_free_mbx - Disable mailbox and place it in standby state + * @fbd: Pointer to device to disable + * + * This function will disable the mailbox interrupt, free any messages still + * in the mailbox and place it into a disabled state. The firmware is + * expected to see the update and assume that the host is in the reset state. + **/ +void fbnic_fw_free_mbx(struct fbnic_dev *fbd) +{ + /* Vector has already been freed */ + if (!fbd->fw_msix_vector) + return; + + fbnic_fw_disable_mbx(fbd); + + /* Free the vector */ + free_irq(fbd->fw_msix_vector, fbd); + fbd->fw_msix_vector = 0; +} + static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data) { struct fbnic_dev *fbd = data; @@ -101,7 +137,7 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data) } /** - * fbnic_pcs_irq_enable - Configure the MAC to enable it to advertise link + * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link * @fbd: Pointer to device to initialize * * This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ @@ -109,41 +145,61 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data) * * Return: non-zero on failure. **/ -int fbnic_pcs_irq_enable(struct fbnic_dev *fbd) +int fbnic_pcs_request_irq(struct fbnic_dev *fbd) { - u32 vector = fbd->pcs_msix_vector; - int err; + struct pci_dev *pdev = to_pci_dev(fbd->dev); + int vector, err; - /* Request the IRQ for MAC link vector. - * Map MAC cause to it, and unmask it + WARN_ON(fbd->pcs_msix_vector); + + vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY); + if (vector < 0) + return vector; + + /* Request the IRQ for PCS link vector. + * Map PCS cause to it, and unmask it */ err = request_irq(vector, &fbnic_pcs_msix_intr, 0, fbd->netdev->name, fbd); if (err) return err; + /* Map and enable interrupt, unmask vector after link is configured */ fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX), FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE); + fbd->pcs_msix_vector = vector; + return 0; } /** - * fbnic_pcs_irq_disable - Teardown the MAC IRQ to prepare for stopping + * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping * @fbd: Pointer to device that is stopping * - * This function undoes the work done in fbnic_pcs_irq_enable and prepares + * This function undoes the work done in fbnic_pcs_request_irq and prepares * the device to no longer receive traffic on the host interface. **/ -void fbnic_pcs_irq_disable(struct fbnic_dev *fbd) +void fbnic_pcs_free_irq(struct fbnic_dev *fbd) { + /* Vector has already been freed */ + if (!fbd->pcs_msix_vector) + return; + /* Disable interrupt */ fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX), FBNIC_PCS_MSIX_ENTRY); + fbnic_wrfl(fbd); + + /* Synchronize IRQ to prevent race that would unmask vector */ + synchronize_irq(fbd->pcs_msix_vector); + + /* Mask the vector */ fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY); /* Free the vector */ free_irq(fbd->pcs_msix_vector, fbd); + fbd->pcs_msix_vector = 0; } void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr) @@ -226,9 +282,6 @@ void fbnic_free_irqs(struct fbnic_dev *fbd) { struct pci_dev *pdev = to_pci_dev(fbd->dev); - fbd->pcs_msix_vector = 0; - fbd->fw_msix_vector = 0; - fbd->num_irqs = 0; pci_free_irq_vectors(pdev); @@ -254,8 +307,5 @@ int fbnic_alloc_irqs(struct fbnic_dev *fbd) fbd->num_irqs = num_irqs; - fbd->pcs_msix_vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY); - fbd->fw_msix_vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY); - return 0; } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c index 14291401f463..dde4a37116e2 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c @@ -79,12 +79,6 @@ static void fbnic_mac_init_axi(struct fbnic_dev *fbd) fbnic_init_readrq(fbd, FBNIC_QM_RNI_RBP_CTL, cls, readrq); fbnic_init_mps(fbd, FBNIC_QM_RNI_RDE_CTL, cls, mps); fbnic_init_mps(fbd, FBNIC_QM_RNI_RCM_CTL, cls, mps); - - /* Enable XALI AR/AW outbound */ - wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG, - FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME); - wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG, - FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME); } static void fbnic_mac_init_qm(struct fbnic_dev *fbd) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index 79a01fdd1dd1..2524d9b88d59 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -44,9 +44,10 @@ int __fbnic_open(struct fbnic_net *fbn) if (err) goto time_stop; - err = fbnic_pcs_irq_enable(fbd); + err = fbnic_pcs_request_irq(fbd); if (err) goto time_stop; + /* Pull the BMC config and initialize the RPC */ fbnic_bmc_rpc_init(fbd); fbnic_rss_reinit(fbd, fbn); @@ -82,7 +83,7 @@ static int fbnic_stop(struct net_device *netdev) struct fbnic_net *fbn = netdev_priv(netdev); fbnic_down(fbn); - fbnic_pcs_irq_disable(fbn->fbd); + fbnic_pcs_free_irq(fbn->fbd); fbnic_time_stop(fbn); fbnic_fw_xmit_ownership_msg(fbn->fbd, false); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 6cbbc2ee3e1f..4e8595239c0f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -283,7 +283,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto free_irqs; } - err = fbnic_fw_enable_mbx(fbd); + err = fbnic_fw_request_mbx(fbd); if (err) { dev_err(&pdev->dev, "Firmware mailbox initialization failure\n"); @@ -363,7 +363,7 @@ static void fbnic_remove(struct pci_dev *pdev) fbnic_hwmon_unregister(fbd); fbnic_dbg_fbd_exit(fbd); fbnic_devlink_unregister(fbd); - fbnic_fw_disable_mbx(fbd); + fbnic_fw_free_mbx(fbd); fbnic_free_irqs(fbd); fbnic_devlink_free(fbd); @@ -387,7 +387,7 @@ static int fbnic_pm_suspend(struct device *dev) rtnl_unlock(); null_uc_addr: - fbnic_fw_disable_mbx(fbd); + fbnic_fw_free_mbx(fbd); /* Free the IRQs so they aren't trying to occupy sleeping CPUs */ fbnic_free_irqs(fbd); @@ -420,7 +420,7 @@ static int __fbnic_pm_resume(struct device *dev) fbd->mac->init_regs(fbd); /* Re-enable mailbox */ - err = fbnic_fw_enable_mbx(fbd); + err = fbnic_fw_request_mbx(fbd); if (err) goto err_free_irqs; @@ -438,15 +438,15 @@ static int __fbnic_pm_resume(struct device *dev) if (netif_running(netdev)) { err = __fbnic_open(fbn); if (err) - goto err_disable_mbx; + goto err_free_mbx; } rtnl_unlock(); return 0; -err_disable_mbx: +err_free_mbx: rtnl_unlock(); - fbnic_fw_disable_mbx(fbd); + fbnic_fw_free_mbx(fbd); err_free_irqs: fbnic_free_irqs(fbd); err_invalidate_uc_addr: diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e2d6bfb5d693..a70b88037a20 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3495,6 +3495,7 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, struct pci_dev *pdev) { struct lan743x_tx *tx; + u32 sgmii_ctl; int index; int ret; @@ -3507,6 +3508,15 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, spin_lock_init(&adapter->eth_syslock_spinlock); mutex_init(&adapter->sgmii_rw_lock); pci11x1x_set_rfe_rd_fifo_threshold(adapter); + sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); + if (adapter->is_sgmii_en) { + sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_; + sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_; + } else { + sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_; + sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_; + } + lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); } else { adapter->max_tx_channels = LAN743X_MAX_TX_CHANNELS; adapter->used_tx_channels = LAN743X_USED_TX_CHANNELS; @@ -3558,7 +3568,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) { - u32 sgmii_ctl; int ret; adapter->mdiobus = devm_mdiobus_alloc(&adapter->pdev->dev); @@ -3570,10 +3579,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) adapter->mdiobus->priv = (void *)adapter; if (adapter->is_pci11x1x) { if (adapter->is_sgmii_en) { - sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); - sgmii_ctl |= SGMII_CTL_SGMII_ENABLE_; - sgmii_ctl &= ~SGMII_CTL_SGMII_POWER_DN_; - lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); netif_dbg(adapter, drv, adapter->netdev, "SGMII operation\n"); adapter->mdiobus->read = lan743x_mdiobus_read_c22; @@ -3584,10 +3589,6 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) netif_dbg(adapter, drv, adapter->netdev, "lan743x-mdiobus-c45\n"); } else { - sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL); - sgmii_ctl &= ~SGMII_CTL_SGMII_ENABLE_; - sgmii_ctl |= SGMII_CTL_SGMII_POWER_DN_; - lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl); netif_dbg(adapter, drv, adapter->netdev, "RGMII operation\n"); // Only C22 support when RGMII I/F diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 99df00c30b8c..b5d744d2586f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -203,7 +203,7 @@ static struct pci_driver qede_pci_driver = { }; static struct qed_eth_cb_ops qede_ll_ops = { - { + .common = { #ifdef CONFIG_RFS_ACCEL .arfs_filter_op = qede_arfs_filter_op, #endif diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 28d24d59efb8..d57b976b9040 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -1484,8 +1484,11 @@ static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *adapter, u8 cmd_o } cmd_op = (cmd.rsp.arg[0] & 0xff); - if (cmd.rsp.arg[0] >> 25 == 2) - return 2; + if (cmd.rsp.arg[0] >> 25 == 2) { + ret = 2; + goto out; + } + if (cmd_op == QLCNIC_BC_CMD_CHANNEL_INIT) set_bit(QLC_BC_VF_STATE, &vf->state); else diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 85723a78793a..6c7e8655a7eb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -964,7 +964,7 @@ static int sun8i_dwmac_set_syscon(struct device *dev, /* of_mdio_parse_addr returns a valid (0 ~ 31) PHY * address. No need to mask it again. */ - reg |= 1 << H3_EPHY_ADDR_SHIFT; + reg |= ret << H3_EPHY_ADDR_SHIFT; } else { /* For SoCs without internal PHY the PHY selection bit should be * set to 0 (external PHY). diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 1e6d2335293d..30665ffe78cf 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2685,7 +2685,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) port->slave.mac_addr); if (!is_valid_ether_addr(port->slave.mac_addr)) { eth_random_addr(port->slave.mac_addr); - dev_err(dev, "Use random MAC address\n"); + dev_info(dev, "Use random MAC address\n"); } } diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index b4be76e13a2f..d88a0180294e 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -187,7 +187,6 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn, xdp_return_frame(xdpf); break; default: - netdev_err(ndev, "tx_complete: invalid swdata type %d\n", swdata->type); prueth_xmit_free(tx_chn, desc_tx); ndev->stats.tx_dropped++; continue; @@ -567,6 +566,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac, { struct cppi5_host_desc_t *first_desc; struct net_device *ndev = emac->ndev; + struct netdev_queue *netif_txq; struct prueth_tx_chn *tx_chn; dma_addr_t desc_dma, buf_dma; struct prueth_swdata *swdata; @@ -620,12 +620,17 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac, swdata->data.xdpf = xdpf; } + /* Report BQL before sending the packet */ + netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); + netdev_tx_sent_queue(netif_txq, xdpf->len); + cppi5_hdesc_set_pktlen(first_desc, xdpf->len); desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc); ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); if (ret) { netdev_err(ndev, "xdp tx: push failed: %d\n", ret); + netdev_tx_completed_queue(netif_txq, 1, xdpf->len); goto drop_free_descs; } @@ -650,6 +655,8 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp, struct page *page, u32 *len) { struct net_device *ndev = emac->ndev; + struct netdev_queue *netif_txq; + int cpu = smp_processor_id(); struct bpf_prog *xdp_prog; struct xdp_frame *xdpf; u32 pkt_len = *len; @@ -669,8 +676,11 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp, goto drop; } - q_idx = smp_processor_id() % emac->tx_ch_num; + q_idx = cpu % emac->tx_ch_num; + netif_txq = netdev_get_tx_queue(ndev, q_idx); + __netif_tx_lock(netif_txq, cpu); result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx); + __netif_tx_unlock(netif_txq); if (result == ICSSG_XDP_CONSUMED) { ndev->stats.tx_dropped++; goto drop; @@ -979,6 +989,7 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); if (ret) { netdev_err(ndev, "tx: push failed: %d\n", ret); + netdev_tx_completed_queue(netif_txq, 1, pkt_len); goto drop_free_descs; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 443f90fa6557..86fc1278127c 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1075,17 +1075,21 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame { struct prueth_emac *emac = netdev_priv(dev); struct net_device *ndev = emac->ndev; + struct netdev_queue *netif_txq; + int cpu = smp_processor_id(); struct xdp_frame *xdpf; unsigned int q_idx; int nxmit = 0; u32 err; int i; - q_idx = smp_processor_id() % emac->tx_ch_num; + q_idx = cpu % emac->tx_ch_num; + netif_txq = netdev_get_tx_queue(ndev, q_idx); if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; + __netif_tx_lock(netif_txq, cpu); for (i = 0; i < n; i++) { xdpf = frames[i]; err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx); @@ -1095,6 +1099,7 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame } nxmit++; } + __netif_tx_unlock(netif_txq); return nxmit; } @@ -1109,11 +1114,6 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame static int emac_xdp_setup(struct prueth_emac *emac, struct netdev_bpf *bpf) { struct bpf_prog *prog = bpf->prog; - xdp_features_t val; - - val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT; - xdp_set_features_flag(emac->ndev, val); if (!emac->xdpi.prog && !prog) return 0; @@ -1291,6 +1291,10 @@ static int prueth_netdev_init(struct prueth *prueth, ndev->hw_features = NETIF_F_SG; ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES; + xdp_set_features_flag(ndev, + NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT); netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll); hrtimer_setup(&emac->rx_hrtimer, &emac_rx_timer_callback, CLOCK_MONOTONIC, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index aed45abafb1b..490d34233d38 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -434,14 +434,20 @@ static int wx_host_interface_command_r(struct wx *wx, u32 *buffer, wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, WX_SW2FW_MBOX_CMD_VLD); /* polling reply from FW */ - err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 1000, 50000, - true, wx, buffer, send_cmd); + err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 2000, + timeout * 1000, true, wx, buffer, send_cmd); if (err) { wx_err(wx, "Polling from FW messages timeout, cmd: 0x%x, index: %d\n", send_cmd, wx->swfw_index); goto rel_out; } + if (hdr->cmd_or_resp.ret_status == 0x80) { + wx_err(wx, "Unknown FW command: 0x%x\n", send_cmd); + err = -EINVAL; + goto rel_out; + } + /* expect no reply from FW then return */ if (!return_data) goto rel_out; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c index 4b9921b7bb11..a054b259d435 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -99,9 +99,15 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum) } local_buffer = eeprom_ptrs; - for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++) + for (i = 0; i < TXGBE_EEPROM_LAST_WORD; i++) { + if (wx->mac.type == wx_mac_aml) { + if (i >= TXGBE_EEPROM_I2C_SRART_PTR && + i < TXGBE_EEPROM_I2C_END_PTR) + local_buffer[i] = 0xffff; + } if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM) *checksum += local_buffer[i]; + } kvfree(eeprom_ptrs); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index 9c1c26234cad..f423012dec22 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -158,6 +158,8 @@ #define TXGBE_EEPROM_VERSION_L 0x1D #define TXGBE_EEPROM_VERSION_H 0x1E #define TXGBE_ISCSI_BOOT_CONFIG 0x07 +#define TXGBE_EEPROM_I2C_SRART_PTR 0x580 +#define TXGBE_EEPROM_I2C_END_PTR 0x800 #define TXGBE_MAX_MSIX_VECTORS 64 #define TXGBE_MAX_FDIR_INDICES 63 diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 70f7cb383228..cb6f5482d203 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -158,7 +158,6 @@ struct hv_netvsc_packet { u8 cp_partial; /* partial copy into send buffer */ u8 rmsg_size; /* RNDIS header and PPI size */ - u8 rmsg_pgcnt; /* page count of RNDIS header and PPI */ u8 page_buf_cnt; u16 q_idx; @@ -893,6 +892,18 @@ struct nvsp_message { sizeof(struct nvsp_message)) #define NETVSC_MIN_IN_MSG_SIZE sizeof(struct vmpacket_descriptor) +/* Maximum # of contiguous data ranges that can make up a trasmitted packet. + * Typically it's the max SKB fragments plus 2 for the rndis packet and the + * linear portion of the SKB. But if MAX_SKB_FRAGS is large, the value may + * need to be limited to MAX_PAGE_BUFFER_COUNT, which is the max # of entries + * in a GPA direct packet sent to netvsp over VMBus. + */ +#if MAX_SKB_FRAGS + 2 < MAX_PAGE_BUFFER_COUNT +#define MAX_DATA_RANGES (MAX_SKB_FRAGS + 2) +#else +#define MAX_DATA_RANGES MAX_PAGE_BUFFER_COUNT +#endif + /* Estimated requestor size: * out_ring_size/min_out_msg_size + in_ring_size/min_in_msg_size */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index d6f5b9ea3109..720104661d7f 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -953,8 +953,7 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device, + pend_size; int i; u32 padding = 0; - u32 page_count = packet->cp_partial ? packet->rmsg_pgcnt : - packet->page_buf_cnt; + u32 page_count = packet->cp_partial ? 1 : packet->page_buf_cnt; u32 remain; /* Add padding */ @@ -1055,6 +1054,42 @@ static int netvsc_dma_map(struct hv_device *hv_dev, return 0; } +/* Build an "array" of mpb entries describing the data to be transferred + * over VMBus. After the desc header fields, each "array" entry is variable + * size, and each entry starts after the end of the previous entry. The + * "offset" and "len" fields for each entry imply the size of the entry. + * + * The pfns are in HV_HYP_PAGE_SIZE, because all communication with Hyper-V + * uses that granularity, even if the system page size of the guest is larger. + * Each entry in the input "pb" array must describe a contiguous range of + * guest physical memory so that the pfns are sequential if the range crosses + * a page boundary. The offset field must be < HV_HYP_PAGE_SIZE. + */ +static inline void netvsc_build_mpb_array(struct hv_page_buffer *pb, + u32 page_buffer_count, + struct vmbus_packet_mpb_array *desc, + u32 *desc_size) +{ + struct hv_mpb_array *mpb_entry = &desc->range; + int i, j; + + for (i = 0; i < page_buffer_count; i++) { + u32 offset = pb[i].offset; + u32 len = pb[i].len; + + mpb_entry->offset = offset; + mpb_entry->len = len; + + for (j = 0; j < HVPFN_UP(offset + len); j++) + mpb_entry->pfn_array[j] = pb[i].pfn + j; + + mpb_entry = (struct hv_mpb_array *)&mpb_entry->pfn_array[j]; + } + + desc->rangecount = page_buffer_count; + *desc_size = (char *)mpb_entry - (char *)desc; +} + static inline int netvsc_send_pkt( struct hv_device *device, struct hv_netvsc_packet *packet, @@ -1097,8 +1132,11 @@ static inline int netvsc_send_pkt( packet->dma_range = NULL; if (packet->page_buf_cnt) { + struct vmbus_channel_packet_page_buffer desc; + u32 desc_size; + if (packet->cp_partial) - pb += packet->rmsg_pgcnt; + pb++; ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb); if (ret) { @@ -1106,11 +1144,12 @@ static inline int netvsc_send_pkt( goto exit; } - ret = vmbus_sendpacket_pagebuffer(out_channel, - pb, packet->page_buf_cnt, - &nvmsg, sizeof(nvmsg), - req_id); - + netvsc_build_mpb_array(pb, packet->page_buf_cnt, + (struct vmbus_packet_mpb_array *)&desc, + &desc_size); + ret = vmbus_sendpacket_mpb_desc(out_channel, + (struct vmbus_packet_mpb_array *)&desc, + desc_size, &nvmsg, sizeof(nvmsg), req_id); if (ret) netvsc_dma_unmap(ndev_ctx->device_ctx, packet); } else { @@ -1259,7 +1298,7 @@ int netvsc_send(struct net_device *ndev, packet->send_buf_index = section_index; if (packet->cp_partial) { - packet->page_buf_cnt -= packet->rmsg_pgcnt; + packet->page_buf_cnt--; packet->total_data_buflen = msd_len + packet->rmsg_size; } else { packet->page_buf_cnt = 0; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c51b318b8a72..d8b169ac0343 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -326,43 +326,10 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, return txq; } -static u32 fill_pg_buf(unsigned long hvpfn, u32 offset, u32 len, - struct hv_page_buffer *pb) -{ - int j = 0; - - hvpfn += offset >> HV_HYP_PAGE_SHIFT; - offset = offset & ~HV_HYP_PAGE_MASK; - - while (len > 0) { - unsigned long bytes; - - bytes = HV_HYP_PAGE_SIZE - offset; - if (bytes > len) - bytes = len; - pb[j].pfn = hvpfn; - pb[j].offset = offset; - pb[j].len = bytes; - - offset += bytes; - len -= bytes; - - if (offset == HV_HYP_PAGE_SIZE && len) { - hvpfn++; - offset = 0; - j++; - } - } - - return j + 1; -} - static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, struct hv_netvsc_packet *packet, struct hv_page_buffer *pb) { - u32 slots_used = 0; - char *data = skb->data; int frags = skb_shinfo(skb)->nr_frags; int i; @@ -371,28 +338,27 @@ static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, * 2. skb linear data * 3. skb fragment data */ - slots_used += fill_pg_buf(virt_to_hvpfn(hdr), - offset_in_hvpage(hdr), - len, - &pb[slots_used]); + pb[0].offset = offset_in_hvpage(hdr); + pb[0].len = len; + pb[0].pfn = virt_to_hvpfn(hdr); packet->rmsg_size = len; - packet->rmsg_pgcnt = slots_used; - slots_used += fill_pg_buf(virt_to_hvpfn(data), - offset_in_hvpage(data), - skb_headlen(skb), - &pb[slots_used]); + pb[1].offset = offset_in_hvpage(skb->data); + pb[1].len = skb_headlen(skb); + pb[1].pfn = virt_to_hvpfn(skb->data); for (i = 0; i < frags; i++) { skb_frag_t *frag = skb_shinfo(skb)->frags + i; + struct hv_page_buffer *cur_pb = &pb[i + 2]; + u64 pfn = page_to_hvpfn(skb_frag_page(frag)); + u32 offset = skb_frag_off(frag); - slots_used += fill_pg_buf(page_to_hvpfn(skb_frag_page(frag)), - skb_frag_off(frag), - skb_frag_size(frag), - &pb[slots_used]); + cur_pb->offset = offset_in_hvpage(offset); + cur_pb->len = skb_frag_size(frag); + cur_pb->pfn = pfn + (offset >> HV_HYP_PAGE_SHIFT); } - return slots_used; + return frags + 2; } static int count_skb_frag_slots(struct sk_buff *skb) @@ -483,7 +449,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx) struct net_device *vf_netdev; u32 rndis_msg_size; u32 hash; - struct hv_page_buffer pb[MAX_PAGE_BUFFER_COUNT]; + struct hv_page_buffer pb[MAX_DATA_RANGES]; /* If VF is present and up then redirect packets to it. * Skip the VF if it is marked down or has no carrier. diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 82747dfacd70..9e73959e61ee 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -225,8 +225,7 @@ static int rndis_filter_send_request(struct rndis_device *dev, struct rndis_request *req) { struct hv_netvsc_packet *packet; - struct hv_page_buffer page_buf[2]; - struct hv_page_buffer *pb = page_buf; + struct hv_page_buffer pb; int ret; /* Setup the packet to send it */ @@ -235,27 +234,14 @@ static int rndis_filter_send_request(struct rndis_device *dev, packet->total_data_buflen = req->request_msg.msg_len; packet->page_buf_cnt = 1; - pb[0].pfn = virt_to_phys(&req->request_msg) >> - HV_HYP_PAGE_SHIFT; - pb[0].len = req->request_msg.msg_len; - pb[0].offset = offset_in_hvpage(&req->request_msg); - - /* Add one page_buf when request_msg crossing page boundary */ - if (pb[0].offset + pb[0].len > HV_HYP_PAGE_SIZE) { - packet->page_buf_cnt++; - pb[0].len = HV_HYP_PAGE_SIZE - - pb[0].offset; - pb[1].pfn = virt_to_phys((void *)&req->request_msg - + pb[0].len) >> HV_HYP_PAGE_SHIFT; - pb[1].offset = 0; - pb[1].len = req->request_msg.msg_len - - pb[0].len; - } + pb.pfn = virt_to_phys(&req->request_msg) >> HV_HYP_PAGE_SHIFT; + pb.len = req->request_msg.msg_len; + pb.offset = offset_in_hvpage(&req->request_msg); trace_rndis_send(dev->ndev, 0, &req->request_msg); rcu_read_lock_bh(); - ret = netvsc_send(dev->ndev, packet, NULL, pb, NULL, false); + ret = netvsc_send(dev->ndev, packet, NULL, &pb, NULL, false); rcu_read_unlock_bh(); return ret; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 24882d30f685..e2c6569d8c45 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2027,12 +2027,6 @@ static int ksz9477_config_init(struct phy_device *phydev) return err; } - /* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes - * in this switch shall be regarded as broken. - */ - if (phydev->dev_flags & MICREL_NO_EEE) - phy_disable_eee(phydev); - return kszphy_config_init(phydev); } @@ -5705,7 +5699,6 @@ static struct phy_driver ksphy_driver[] = { .handle_interrupt = kszphy_handle_interrupt, .suspend = genphy_suspend, .resume = ksz9477_resume, - .get_features = ksz9477_get_features, } }; module_phy_driver(ksphy_driver); diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index d8fc0c79745d..b75ceb90359f 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -1778,8 +1778,8 @@ static void team_change_rx_flags(struct net_device *dev, int change) struct team_port *port; int inc; - rcu_read_lock(); - list_for_each_entry_rcu(port, &team->port_list, list) { + mutex_lock(&team->lock); + list_for_each_entry(port, &team->port_list, list) { if (change & IFF_PROMISC) { inc = dev->flags & IFF_PROMISC ? 1 : -1; dev_set_promiscuity(port->dev, inc); @@ -1789,7 +1789,7 @@ static void team_change_rx_flags(struct net_device *dev, int change) dev_set_allmulti(port->dev, inc); } } - rcu_read_unlock(); + mutex_unlock(&team->lock); } static void team_set_rx_mode(struct net_device *dev) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 848fab51dfa1..e53ba600605a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3383,12 +3383,15 @@ static void __virtnet_rx_resume(struct virtnet_info *vi, bool refill) { bool running = netif_running(vi->dev); + bool schedule_refill = false; if (refill && !try_fill_recv(vi, rq, GFP_KERNEL)) - schedule_delayed_work(&vi->refill, 0); - + schedule_refill = true; if (running) virtnet_napi_enable(rq); + + if (schedule_refill) + schedule_delayed_work(&vi->refill, 0); } static void virtnet_rx_resume_all(struct virtnet_info *vi) @@ -3728,8 +3731,10 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) succ: vi->curr_queue_pairs = queue_pairs; /* virtnet_open() will refill when device is going to up. */ - if (dev->flags & IFF_UP) + spin_lock_bh(&vi->refill_lock); + if (dev->flags & IFF_UP && vi->refill_enabled) schedule_delayed_work(&vi->refill, 0); + spin_unlock_bh(&vi->refill_lock); return 0; } @@ -5673,6 +5678,10 @@ static void virtnet_get_base_stats(struct net_device *dev, if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) tx->hw_drop_ratelimits = 0; + + netdev_stat_queue_sum(dev, + dev->real_num_rx_queues, vi->max_queue_pairs, rx, + dev->real_num_tx_queues, vi->max_queue_pairs, tx); } static const struct netdev_stat_ops virtnet_stat_ops = { @@ -5885,8 +5894,10 @@ static int virtnet_xsk_pool_enable(struct net_device *dev, hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len, DMA_TO_DEVICE, 0); - if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) - return -ENOMEM; + if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) { + err = -ENOMEM; + goto err_free_buffs; + } err = xsk_pool_dma_map(pool, dma_dev, 0); if (err) @@ -5914,6 +5925,8 @@ err_rq: err_xsk_map: virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len, DMA_TO_DEVICE, 0); +err_free_buffs: + kvfree(rq->xsk_buffs); return err; } diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 3df6aabc7e33..c676979c7ab9 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -3607,8 +3607,6 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) struct vmxnet3_adapter *adapter = netdev_priv(netdev); int err = 0; - WRITE_ONCE(netdev->mtu, new_mtu); - /* * Reset_work may be in the middle of resetting the device, wait for its * completion. @@ -3622,6 +3620,7 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) /* we need to re-create the rx queue based on the new mtu */ vmxnet3_rq_destroy_all(adapter); + WRITE_ONCE(netdev->mtu, new_mtu); vmxnet3_adjust_rx_ring_size(adapter); err = vmxnet3_rq_create_all(adapter); if (err) { @@ -3638,6 +3637,8 @@ vmxnet3_change_mtu(struct net_device *netdev, int new_mtu) "Closing it\n", err); goto out; } + } else { + WRITE_ONCE(netdev->mtu, new_mtu); } out: diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index debeea2b3ae5..00056e76ea3d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -588,6 +588,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x7A70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), IWL_DEV_INFO(0x7AF0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name), IWL_DEV_INFO(0x7AF0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), + IWL_DEV_INFO(0x7F70, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name), + IWL_DEV_INFO(0x7F70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name), IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name), IWL_DEV_INFO(0x7E40, 0x1691, iwl_cfg_ma, iwl_ax411_killer_1690s_name), diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 844af16ee551..35b4ec91979e 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -1011,6 +1011,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev) int i; mt76_worker_disable(&dev->tx_worker); + napi_disable(&dev->tx_napi); netif_napi_del(&dev->tx_napi); for (i = 0; i < ARRAY_SIZE(dev->phys); i++) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index e61da76b2097..14b1f603fb62 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -1924,14 +1924,14 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, mt7925_mcu_sta_mld_tlv(skb, info->vif, info->link_sta->sta); mt7925_mcu_sta_eht_mld_tlv(skb, info->vif, info->link_sta->sta); } - - mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta); } if (!info->enable) { mt7925_mcu_sta_remove_tlv(skb); mt76_connac_mcu_add_tlv(skb, STA_REC_MLD_OFF, sizeof(struct tlv)); + } else { + mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta); } return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index eb6ea8acb3cc..6b04473c0ab7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2059,7 +2059,21 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id, if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs; else - atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs; + atomic_bs = (1 + ns->ctrl->awupf) * bs; + + /* + * Set subsystem atomic bs. + */ + if (ns->ctrl->subsys->atomic_bs) { + if (atomic_bs != ns->ctrl->subsys->atomic_bs) { + dev_err_ratelimited(ns->ctrl->device, + "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n", + ns->disk ? ns->disk->disk_name : "?", + ns->ctrl->subsys->atomic_bs, + atomic_bs); + } + } else + ns->ctrl->subsys->atomic_bs = atomic_bs; nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs); } @@ -2201,6 +2215,17 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, nvme_set_chunk_sectors(ns, id, &lim); if (!nvme_update_disk_info(ns, id, &lim)) capacity = 0; + + /* + * Validate the max atomic write size fits within the subsystem's + * atomic write capabilities. + */ + if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) { + blk_mq_unfreeze_queue(ns->disk->queue, memflags); + ret = -ENXIO; + goto out; + } + nvme_config_discard(ns, &lim); if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && ns->head->ids.csi == NVME_CSI_ZNS) @@ -3031,7 +3056,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) kfree(subsys); return -EINVAL; } - subsys->awupf = le16_to_cpu(id->awupf); nvme_mpath_default_iopolicy(subsys); subsys->dev.class = &nvme_subsys_class; @@ -3441,7 +3465,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) dev_pm_qos_expose_latency_tolerance(ctrl->device); else if (!ctrl->apst_enabled && prev_apst_enabled) dev_pm_qos_hide_latency_tolerance(ctrl->device); - + ctrl->awupf = le16_to_cpu(id->awupf); out_free: kfree(id); return ret; @@ -4493,7 +4517,8 @@ static void nvme_fw_act_work(struct work_struct *work) msleep(100); } - if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING) || + !nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) return; nvme_unquiesce_io_queues(ctrl); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 250f3da67cc9..cf0ef4745564 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -638,7 +638,8 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) blk_set_stacking_limits(&lim); lim.dma_alignment = 3; - lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL; + lim.features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | + BLK_FEAT_POLL | BLK_FEAT_ATOMIC_WRITES; if (head->ids.csi == NVME_CSI_ZNS) lim.features |= BLK_FEAT_ZONED; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 51e078642127..8fc4683418a3 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -410,6 +410,7 @@ struct nvme_ctrl { enum nvme_ctrl_type cntrltype; enum nvme_dctype dctype; + u16 awupf; /* 0's based value. */ }; static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl) @@ -442,11 +443,11 @@ struct nvme_subsystem { u8 cmic; enum nvme_subsys_type subtype; u16 vendor_id; - u16 awupf; /* 0's based awupf value. */ struct ida ns_ida; #ifdef CONFIG_NVME_MULTIPATH enum nvme_iopolicy iopolicy; #endif + u32 atomic_bs; }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 2e30e9be7408..f1dd804151b1 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -390,7 +390,7 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db, * as it only leads to a small amount of wasted memory for the lifetime of * the I/O. */ -static int nvme_pci_npages_prp(void) +static __always_inline int nvme_pci_npages_prp(void) { unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE; unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE); @@ -1202,7 +1202,9 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq) WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags)); disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); + spin_lock(&nvmeq->cq_poll_lock); nvme_poll_cq(nvmeq, NULL); + spin_unlock(&nvmeq->cq_poll_lock); enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); } @@ -3737,6 +3739,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x025e, 0xf1ac), /* SOLIDIGM P44 pro SSDPFKKW020X7 */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */ diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 6d31226f7a4f..a5bc3bb483d5 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -306,13 +306,41 @@ static const struct attribute_group nvme_ns_attr_group = { }; #ifdef CONFIG_NVME_MULTIPATH +/* + * NOTE: The dummy attribute does not appear in sysfs. It exists solely to allow + * control over the visibility of the multipath sysfs node. Without at least one + * attribute defined in nvme_ns_mpath_attrs[], the sysfs implementation does not + * invoke the multipath_sysfs_group_visible() method. As a result, we would not + * be able to control the visibility of the multipath sysfs node. + */ +static struct attribute dummy_attr = { + .name = "dummy", +}; + static struct attribute *nvme_ns_mpath_attrs[] = { + &dummy_attr, NULL, }; +static bool multipath_sysfs_group_visible(struct kobject *kobj) +{ + struct device *dev = container_of(kobj, struct device, kobj); + + return nvme_disk_is_ns_head(dev_to_disk(dev)); +} + +static bool multipath_sysfs_attr_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + return false; +} + +DEFINE_SYSFS_GROUP_VISIBLE(multipath_sysfs) + const struct attribute_group nvme_ns_mpath_attr_group = { .name = "multipath", .attrs = nvme_ns_mpath_attrs, + .is_visible = SYSFS_GROUP_VISIBLE(multipath_sysfs), }; #endif diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c index 7fab7f3d79b7..7123c855b5a6 100644 --- a/drivers/nvme/target/pci-epf.c +++ b/drivers/nvme/target/pci-epf.c @@ -62,8 +62,7 @@ static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex); #define NVMET_PCI_EPF_CQ_RETRY_INTERVAL msecs_to_jiffies(1) enum nvmet_pci_epf_queue_flags { - NVMET_PCI_EPF_Q_IS_SQ = 0, /* The queue is a submission queue */ - NVMET_PCI_EPF_Q_LIVE, /* The queue is live */ + NVMET_PCI_EPF_Q_LIVE = 0, /* The queue is live */ NVMET_PCI_EPF_Q_IRQ_ENABLED, /* IRQ is enabled for this queue */ }; @@ -596,9 +595,6 @@ static bool nvmet_pci_epf_should_raise_irq(struct nvmet_pci_epf_ctrl *ctrl, struct nvmet_pci_epf_irq_vector *iv = cq->iv; bool ret; - if (!test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags)) - return false; - /* IRQ coalescing for the admin queue is not allowed. */ if (!cq->qid) return true; @@ -625,7 +621,8 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl, struct pci_epf *epf = nvme_epf->epf; int ret = 0; - if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags)) + if (!test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags) || + !test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags)) return; mutex_lock(&ctrl->irq_lock); @@ -636,14 +633,16 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl, switch (nvme_epf->irq_type) { case PCI_IRQ_MSIX: case PCI_IRQ_MSI: + /* + * If we fail to raise an MSI or MSI-X interrupt, it is likely + * because the host is using legacy INTX IRQs (e.g. BIOS, + * grub), but we can fallback to the INTX type only if the + * endpoint controller supports this type. + */ ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no, nvme_epf->irq_type, cq->vector + 1); - if (!ret) + if (!ret || !nvme_epf->epc_features->intx_capable) break; - /* - * If we got an error, it is likely because the host is using - * legacy IRQs (e.g. BIOS, grub). - */ fallthrough; case PCI_IRQ_INTX: ret = pci_epc_raise_irq(epf->epc, epf->func_no, epf->vfunc_no, @@ -656,7 +655,9 @@ static void nvmet_pci_epf_raise_irq(struct nvmet_pci_epf_ctrl *ctrl, } if (ret) - dev_err(ctrl->dev, "Failed to raise IRQ (err=%d)\n", ret); + dev_err_ratelimited(ctrl->dev, + "CQ[%u]: Failed to raise IRQ (err=%d)\n", + cq->qid, ret); unlock: mutex_unlock(&ctrl->irq_lock); @@ -1319,8 +1320,14 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl, set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags); - dev_dbg(ctrl->dev, "CQ[%u]: %u entries of %zu B, IRQ vector %u\n", - cqid, qsize, cq->qes, cq->vector); + if (test_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags)) + dev_dbg(ctrl->dev, + "CQ[%u]: %u entries of %zu B, IRQ vector %u\n", + cqid, qsize, cq->qes, cq->vector); + else + dev_dbg(ctrl->dev, + "CQ[%u]: %u entries of %zu B, IRQ disabled\n", + cqid, qsize, cq->qes); return NVME_SC_SUCCESS; @@ -1344,7 +1351,8 @@ static u16 nvmet_pci_epf_delete_cq(struct nvmet_ctrl *tctrl, u16 cqid) cancel_delayed_work_sync(&cq->work); nvmet_pci_epf_drain_queue(cq); - nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector); + if (test_and_clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags)) + nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector); nvmet_pci_epf_mem_unmap(ctrl->nvme_epf, &cq->pci_map); return NVME_SC_SUCCESS; @@ -1533,7 +1541,6 @@ static void nvmet_pci_epf_init_queue(struct nvmet_pci_epf_ctrl *ctrl, if (sq) { queue = &ctrl->sq[qid]; - set_bit(NVMET_PCI_EPF_Q_IS_SQ, &queue->flags); } else { queue = &ctrl->cq[qid]; INIT_DELAYED_WORK(&queue->work, nvmet_pci_epf_cq_work); diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index 055518ee354d..e9e9aaa91770 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -59,7 +59,6 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); if (pdev && pci_num_vf(pdev)) { - pci_dev_put(pdev); rc = -EBUSY; goto out; } diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c index 2bec70615449..f59caff4b3d4 100644 --- a/drivers/phy/phy-can-transceiver.c +++ b/drivers/phy/phy-can-transceiver.c @@ -93,6 +93,16 @@ static const struct of_device_id can_transceiver_phy_ids[] = { }; MODULE_DEVICE_TABLE(of, can_transceiver_phy_ids); +/* Temporary wrapper until the multiplexer subsystem supports optional muxes */ +static inline struct mux_state * +devm_mux_state_get_optional(struct device *dev, const char *mux_name) +{ + if (!of_property_present(dev->of_node, "mux-states")) + return NULL; + + return devm_mux_state_get(dev, mux_name); +} + static int can_transceiver_phy_probe(struct platform_device *pdev) { struct phy_provider *phy_provider; @@ -114,13 +124,11 @@ static int can_transceiver_phy_probe(struct platform_device *pdev) match = of_match_node(can_transceiver_phy_ids, pdev->dev.of_node); drvdata = match->data; - mux_state = devm_mux_state_get(dev, NULL); - if (IS_ERR(mux_state)) { - if (PTR_ERR(mux_state) == -EPROBE_DEFER) - return PTR_ERR(mux_state); - } else { - can_transceiver_phy->mux_state = mux_state; - } + mux_state = devm_mux_state_get_optional(dev, NULL); + if (IS_ERR(mux_state)) + return PTR_ERR(mux_state); + + can_transceiver_phy->mux_state = mux_state; phy = devm_phy_create(dev, dev->of_node, &can_transceiver_phy_ops); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c index 45b3b792696e..b33e2e2b5014 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c @@ -1754,7 +1754,8 @@ static void qmp_ufs_init_registers(struct qmp_ufs *qmp, const struct qmp_phy_cfg qmp_ufs_init_all(qmp, &cfg->tbls_hs_overlay[i]); } - qmp_ufs_init_all(qmp, &cfg->tbls_hs_b); + if (qmp->mode == PHY_MODE_UFS_HS_B) + qmp_ufs_init_all(qmp, &cfg->tbls_hs_b); } static int qmp_ufs_com_init(struct qmp_ufs *qmp) diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 775f4f973a6c..9fdf17e0848a 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -9,6 +9,7 @@ * Copyright (C) 2014 Cogent Embedded, Inc. */ +#include <linux/cleanup.h> #include <linux/extcon-provider.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -107,7 +108,6 @@ struct rcar_gen3_phy { struct rcar_gen3_chan *ch; u32 int_enable_bits; bool initialized; - bool otg_initialized; bool powered; }; @@ -119,9 +119,8 @@ struct rcar_gen3_chan { struct regulator *vbus; struct reset_control *rstc; struct work_struct work; - struct mutex lock; /* protects rphys[...].powered */ + spinlock_t lock; /* protects access to hardware and driver data structure. */ enum usb_dr_mode dr_mode; - int irq; u32 obint_enable_bits; bool extcon_host; bool is_otg_channel; @@ -320,16 +319,15 @@ static bool rcar_gen3_is_any_rphy_initialized(struct rcar_gen3_chan *ch) return false; } -static bool rcar_gen3_needs_init_otg(struct rcar_gen3_chan *ch) +static bool rcar_gen3_is_any_otg_rphy_initialized(struct rcar_gen3_chan *ch) { - int i; - - for (i = 0; i < NUM_OF_PHYS; i++) { - if (ch->rphys[i].otg_initialized) - return false; + for (enum rcar_gen3_phy_index i = PHY_INDEX_BOTH_HC; i <= PHY_INDEX_EHCI; + i++) { + if (ch->rphys[i].initialized) + return true; } - return true; + return false; } static bool rcar_gen3_are_all_rphys_power_off(struct rcar_gen3_chan *ch) @@ -351,7 +349,9 @@ static ssize_t role_store(struct device *dev, struct device_attribute *attr, bool is_b_device; enum phy_mode cur_mode, new_mode; - if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch)) + guard(spinlock_irqsave)(&ch->lock); + + if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch)) return -EIO; if (sysfs_streq(buf, "host")) @@ -389,7 +389,7 @@ static ssize_t role_show(struct device *dev, struct device_attribute *attr, { struct rcar_gen3_chan *ch = dev_get_drvdata(dev); - if (!ch->is_otg_channel || !rcar_gen3_is_any_rphy_initialized(ch)) + if (!ch->is_otg_channel || !rcar_gen3_is_any_otg_rphy_initialized(ch)) return -EIO; return sprintf(buf, "%s\n", rcar_gen3_is_host(ch) ? "host" : @@ -402,6 +402,9 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch) void __iomem *usb2_base = ch->base; u32 val; + if (!ch->is_otg_channel || rcar_gen3_is_any_otg_rphy_initialized(ch)) + return; + /* Should not use functions of read-modify-write a register */ val = readl(usb2_base + USB2_LINECTRL1); val = (val & ~USB2_LINECTRL1_DP_RPD) | USB2_LINECTRL1_DPRPD_EN | @@ -415,7 +418,7 @@ static void rcar_gen3_init_otg(struct rcar_gen3_chan *ch) val = readl(usb2_base + USB2_ADPCTRL); writel(val | USB2_ADPCTRL_IDPULLUP, usb2_base + USB2_ADPCTRL); } - msleep(20); + mdelay(20); writel(0xffffffff, usb2_base + USB2_OBINTSTA); writel(ch->obint_enable_bits, usb2_base + USB2_OBINTEN); @@ -427,16 +430,27 @@ static irqreturn_t rcar_gen3_phy_usb2_irq(int irq, void *_ch) { struct rcar_gen3_chan *ch = _ch; void __iomem *usb2_base = ch->base; - u32 status = readl(usb2_base + USB2_OBINTSTA); + struct device *dev = ch->dev; irqreturn_t ret = IRQ_NONE; + u32 status; + + pm_runtime_get_noresume(dev); + + if (pm_runtime_suspended(dev)) + goto rpm_put; - if (status & ch->obint_enable_bits) { - dev_vdbg(ch->dev, "%s: %08x\n", __func__, status); - writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA); - rcar_gen3_device_recognition(ch); - ret = IRQ_HANDLED; + scoped_guard(spinlock, &ch->lock) { + status = readl(usb2_base + USB2_OBINTSTA); + if (status & ch->obint_enable_bits) { + dev_vdbg(dev, "%s: %08x\n", __func__, status); + writel(ch->obint_enable_bits, usb2_base + USB2_OBINTSTA); + rcar_gen3_device_recognition(ch); + ret = IRQ_HANDLED; + } } +rpm_put: + pm_runtime_put_noidle(dev); return ret; } @@ -446,32 +460,23 @@ static int rcar_gen3_phy_usb2_init(struct phy *p) struct rcar_gen3_chan *channel = rphy->ch; void __iomem *usb2_base = channel->base; u32 val; - int ret; - if (!rcar_gen3_is_any_rphy_initialized(channel) && channel->irq >= 0) { - INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work); - ret = request_irq(channel->irq, rcar_gen3_phy_usb2_irq, - IRQF_SHARED, dev_name(channel->dev), channel); - if (ret < 0) { - dev_err(channel->dev, "No irq handler (%d)\n", channel->irq); - return ret; - } - } + guard(spinlock_irqsave)(&channel->lock); /* Initialize USB2 part */ val = readl(usb2_base + USB2_INT_ENABLE); val |= USB2_INT_ENABLE_UCOM_INTEN | rphy->int_enable_bits; writel(val, usb2_base + USB2_INT_ENABLE); - writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET); - writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET); - - /* Initialize otg part */ - if (channel->is_otg_channel) { - if (rcar_gen3_needs_init_otg(channel)) - rcar_gen3_init_otg(channel); - rphy->otg_initialized = true; + + if (!rcar_gen3_is_any_rphy_initialized(channel)) { + writel(USB2_SPD_RSM_TIMSET_INIT, usb2_base + USB2_SPD_RSM_TIMSET); + writel(USB2_OC_TIMSET_INIT, usb2_base + USB2_OC_TIMSET); } + /* Initialize otg part (only if we initialize a PHY with IRQs). */ + if (rphy->int_enable_bits) + rcar_gen3_init_otg(channel); + rphy->initialized = true; return 0; @@ -484,10 +489,9 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p) void __iomem *usb2_base = channel->base; u32 val; - rphy->initialized = false; + guard(spinlock_irqsave)(&channel->lock); - if (channel->is_otg_channel) - rphy->otg_initialized = false; + rphy->initialized = false; val = readl(usb2_base + USB2_INT_ENABLE); val &= ~rphy->int_enable_bits; @@ -495,9 +499,6 @@ static int rcar_gen3_phy_usb2_exit(struct phy *p) val &= ~USB2_INT_ENABLE_UCOM_INTEN; writel(val, usb2_base + USB2_INT_ENABLE); - if (channel->irq >= 0 && !rcar_gen3_is_any_rphy_initialized(channel)) - free_irq(channel->irq, channel); - return 0; } @@ -509,16 +510,17 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p) u32 val; int ret = 0; - mutex_lock(&channel->lock); - if (!rcar_gen3_are_all_rphys_power_off(channel)) - goto out; - if (channel->vbus) { ret = regulator_enable(channel->vbus); if (ret) - goto out; + return ret; } + guard(spinlock_irqsave)(&channel->lock); + + if (!rcar_gen3_are_all_rphys_power_off(channel)) + goto out; + val = readl(usb2_base + USB2_USBCTR); val |= USB2_USBCTR_PLL_RST; writel(val, usb2_base + USB2_USBCTR); @@ -528,7 +530,6 @@ static int rcar_gen3_phy_usb2_power_on(struct phy *p) out: /* The powered flag should be set for any other phys anyway */ rphy->powered = true; - mutex_unlock(&channel->lock); return 0; } @@ -539,18 +540,20 @@ static int rcar_gen3_phy_usb2_power_off(struct phy *p) struct rcar_gen3_chan *channel = rphy->ch; int ret = 0; - mutex_lock(&channel->lock); - rphy->powered = false; + scoped_guard(spinlock_irqsave, &channel->lock) { + rphy->powered = false; - if (!rcar_gen3_are_all_rphys_power_off(channel)) - goto out; + if (rcar_gen3_are_all_rphys_power_off(channel)) { + u32 val = readl(channel->base + USB2_USBCTR); + + val |= USB2_USBCTR_PLL_RST; + writel(val, channel->base + USB2_USBCTR); + } + } if (channel->vbus) ret = regulator_disable(channel->vbus); -out: - mutex_unlock(&channel->lock); - return ret; } @@ -703,7 +706,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct rcar_gen3_chan *channel; struct phy_provider *provider; - int ret = 0, i; + int ret = 0, i, irq; if (!dev->of_node) { dev_err(dev, "This driver needs device tree\n"); @@ -719,8 +722,6 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) return PTR_ERR(channel->base); channel->obint_enable_bits = USB2_OBINT_BITS; - /* get irq number here and request_irq for OTG in phy_init */ - channel->irq = platform_get_irq_optional(pdev, 0); channel->dr_mode = rcar_gen3_get_dr_mode(dev->of_node); if (channel->dr_mode != USB_DR_MODE_UNKNOWN) { channel->is_otg_channel = true; @@ -763,7 +764,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) if (phy_data->no_adp_ctrl) channel->obint_enable_bits = USB2_OBINT_IDCHG_EN; - mutex_init(&channel->lock); + spin_lock_init(&channel->lock); for (i = 0; i < NUM_OF_PHYS; i++) { channel->rphys[i].phy = devm_phy_create(dev, NULL, phy_data->phy_usb2_ops); @@ -789,6 +790,20 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) channel->vbus = NULL; } + irq = platform_get_irq_optional(pdev, 0); + if (irq < 0 && irq != -ENXIO) { + ret = irq; + goto error; + } else if (irq > 0) { + INIT_WORK(&channel->work, rcar_gen3_phy_usb2_work); + ret = devm_request_irq(dev, irq, rcar_gen3_phy_usb2_irq, + IRQF_SHARED, dev_name(dev), channel); + if (ret < 0) { + dev_err(dev, "Failed to request irq (%d)\n", irq); + goto error; + } + } + provider = devm_of_phy_provider_register(dev, rcar_gen3_phy_usb2_xlate); if (IS_ERR(provider)) { dev_err(dev, "Failed to register PHY provider\n"); diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c index 08c78c1bafc9..28a052e17366 100644 --- a/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c +++ b/drivers/phy/rockchip/phy-rockchip-samsung-dcphy.c @@ -1653,7 +1653,7 @@ static __maybe_unused int samsung_mipi_dcphy_runtime_resume(struct device *dev) return ret; } - clk_prepare_enable(samsung->ref_clk); + ret = clk_prepare_enable(samsung->ref_clk); if (ret) { dev_err(samsung->dev, "Failed to enable reference clock, %d\n", ret); clk_disable_unprepare(samsung->pclk); diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c index fe7c05748356..77236f012a1f 100644 --- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c +++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c @@ -476,6 +476,8 @@ static const struct ropll_config ropll_tmds_cfg[] = { 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, }, { 650000, 162, 162, 1, 1, 11, 1, 1, 1, 1, 1, 1, 1, 54, 0, 16, 4, 1, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, }, + { 502500, 84, 84, 1, 1, 7, 1, 1, 1, 1, 1, 1, 1, 11, 1, 4, 5, + 4, 11, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, }, { 337500, 0x70, 0x70, 1, 1, 0xf, 1, 1, 1, 1, 1, 1, 1, 0x2, 0, 0x01, 5, 1, 1, 1, 0, 0x20, 0x0c, 1, 0x0e, 0, 0, }, { 400000, 100, 100, 1, 1, 11, 1, 1, 0, 1, 0, 1, 1, 0x9, 0, 0x05, 0, diff --git a/drivers/phy/starfive/phy-jh7110-usb.c b/drivers/phy/starfive/phy-jh7110-usb.c index cb5454fbe2c8..b505d89860b4 100644 --- a/drivers/phy/starfive/phy-jh7110-usb.c +++ b/drivers/phy/starfive/phy-jh7110-usb.c @@ -18,6 +18,8 @@ #include <linux/usb/of.h> #define USB_125M_CLK_RATE 125000000 +#define USB_CLK_MODE_OFF 0x0 +#define USB_CLK_MODE_RX_NORMAL_PWR BIT(1) #define USB_LS_KEEPALIVE_OFF 0x4 #define USB_LS_KEEPALIVE_ENABLE BIT(4) @@ -78,6 +80,7 @@ static int jh7110_usb2_phy_init(struct phy *_phy) { struct jh7110_usb2_phy *phy = phy_get_drvdata(_phy); int ret; + unsigned int val; ret = clk_set_rate(phy->usb_125m_clk, USB_125M_CLK_RATE); if (ret) @@ -87,6 +90,10 @@ static int jh7110_usb2_phy_init(struct phy *_phy) if (ret) return ret; + val = readl(phy->regs + USB_CLK_MODE_OFF); + val |= USB_CLK_MODE_RX_NORMAL_PWR; + writel(val, phy->regs + USB_CLK_MODE_OFF); + return 0; } diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index fae6242aa730..23a23f2d64e5 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -237,6 +237,8 @@ #define DATA0_VAL_PD BIT(1) #define USE_XUSB_AO BIT(4) +#define TEGRA_UTMI_PAD_MAX 4 + #define TEGRA186_LANE(_name, _offset, _shift, _mask, _type) \ { \ .name = _name, \ @@ -269,7 +271,7 @@ struct tegra186_xusb_padctl { /* UTMI bias and tracking */ struct clk *usb2_trk_clk; - unsigned int bias_pad_enable; + DECLARE_BITMAP(utmi_pad_enabled, TEGRA_UTMI_PAD_MAX); /* padctl context */ struct tegra186_xusb_padctl_context context; @@ -603,12 +605,8 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl) u32 value; int err; - mutex_lock(&padctl->lock); - - if (priv->bias_pad_enable++ > 0) { - mutex_unlock(&padctl->lock); + if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX)) return; - } err = clk_prepare_enable(priv->usb2_trk_clk); if (err < 0) @@ -658,8 +656,6 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl) } else { clk_disable_unprepare(priv->usb2_trk_clk); } - - mutex_unlock(&padctl->lock); } static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl) @@ -667,17 +663,8 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl) struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl); u32 value; - mutex_lock(&padctl->lock); - - if (WARN_ON(priv->bias_pad_enable == 0)) { - mutex_unlock(&padctl->lock); - return; - } - - if (--priv->bias_pad_enable > 0) { - mutex_unlock(&padctl->lock); + if (!bitmap_empty(priv->utmi_pad_enabled, TEGRA_UTMI_PAD_MAX)) return; - } value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL1); value |= USB2_PD_TRK; @@ -690,13 +677,13 @@ static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl) clk_disable_unprepare(priv->usb2_trk_clk); } - mutex_unlock(&padctl->lock); } static void tegra186_utmi_pad_power_on(struct phy *phy) { struct tegra_xusb_lane *lane = phy_get_drvdata(phy); struct tegra_xusb_padctl *padctl = lane->pad->padctl; + struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl); struct tegra_xusb_usb2_port *port; struct device *dev = padctl->dev; unsigned int index = lane->index; @@ -705,9 +692,16 @@ static void tegra186_utmi_pad_power_on(struct phy *phy) if (!phy) return; + mutex_lock(&padctl->lock); + if (test_bit(index, priv->utmi_pad_enabled)) { + mutex_unlock(&padctl->lock); + return; + } + port = tegra_xusb_find_usb2_port(padctl, index); if (!port) { dev_err(dev, "no port found for USB2 lane %u\n", index); + mutex_unlock(&padctl->lock); return; } @@ -724,18 +718,28 @@ static void tegra186_utmi_pad_power_on(struct phy *phy) value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index)); value &= ~USB2_OTG_PD_DR; padctl_writel(padctl, value, XUSB_PADCTL_USB2_OTG_PADX_CTL1(index)); + + set_bit(index, priv->utmi_pad_enabled); + mutex_unlock(&padctl->lock); } static void tegra186_utmi_pad_power_down(struct phy *phy) { struct tegra_xusb_lane *lane = phy_get_drvdata(phy); struct tegra_xusb_padctl *padctl = lane->pad->padctl; + struct tegra186_xusb_padctl *priv = to_tegra186_xusb_padctl(padctl); unsigned int index = lane->index; u32 value; if (!phy) return; + mutex_lock(&padctl->lock); + if (!test_bit(index, priv->utmi_pad_enabled)) { + mutex_unlock(&padctl->lock); + return; + } + dev_dbg(padctl->dev, "power down UTMI pad %u\n", index); value = padctl_readl(padctl, XUSB_PADCTL_USB2_OTG_PADX_CTL0(index)); @@ -748,7 +752,11 @@ static void tegra186_utmi_pad_power_down(struct phy *phy) udelay(2); + clear_bit(index, priv->utmi_pad_enabled); + tegra186_utmi_bias_pad_power_off(padctl); + + mutex_unlock(&padctl->lock); } static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl, diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 79d4814d758d..c89df95aa6ca 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -548,16 +548,16 @@ static int tegra_xusb_port_init(struct tegra_xusb_port *port, err = dev_set_name(&port->dev, "%s-%u", name, index); if (err < 0) - goto unregister; + goto put_device; err = device_add(&port->dev); if (err < 0) - goto unregister; + goto put_device; return 0; -unregister: - device_unregister(&port->dev); +put_device: + put_device(&port->dev); return err; } diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 82f0cc43bbf4..0eb816395dc6 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -44,7 +44,6 @@ * @pctrl: pinctrl handle. * @chip: gpiochip handle. * @desc: pin controller descriptor - * @restart_nb: restart notifier block. * @irq: parent irq for the TLMM irq_chip. * @intr_target_use_scm: route irq to application cpu using scm calls * @lock: Spinlock to protect register resources as well @@ -64,7 +63,6 @@ struct msm_pinctrl { struct pinctrl_dev *pctrl; struct gpio_chip chip; struct pinctrl_desc desc; - struct notifier_block restart_nb; int irq; @@ -1471,10 +1469,9 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) return 0; } -static int msm_ps_hold_restart(struct notifier_block *nb, unsigned long action, - void *data) +static int msm_ps_hold_restart(struct sys_off_data *data) { - struct msm_pinctrl *pctrl = container_of(nb, struct msm_pinctrl, restart_nb); + struct msm_pinctrl *pctrl = data->cb_data; writel(0, pctrl->regs[0] + PS_HOLD_OFFSET); mdelay(1000); @@ -1485,7 +1482,11 @@ static struct msm_pinctrl *poweroff_pctrl; static void msm_ps_hold_poweroff(void) { - msm_ps_hold_restart(&poweroff_pctrl->restart_nb, 0, NULL); + struct sys_off_data data = { + .cb_data = poweroff_pctrl, + }; + + msm_ps_hold_restart(&data); } static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl) @@ -1495,9 +1496,11 @@ static void msm_pinctrl_setup_pm_reset(struct msm_pinctrl *pctrl) for (i = 0; i < pctrl->soc->nfunctions; i++) if (!strcmp(func[i].name, "ps_hold")) { - pctrl->restart_nb.notifier_call = msm_ps_hold_restart; - pctrl->restart_nb.priority = 128; - if (register_restart_handler(&pctrl->restart_nb)) + if (devm_register_sys_off_handler(pctrl->dev, + SYS_OFF_MODE_RESTART, + 128, + msm_ps_hold_restart, + pctrl)) dev_err(pctrl->dev, "failed to setup restart handler.\n"); poweroff_pctrl = pctrl; @@ -1599,8 +1602,6 @@ void msm_pinctrl_remove(struct platform_device *pdev) struct msm_pinctrl *pctrl = platform_get_drvdata(pdev); gpiochip_remove(&pctrl->chip); - - unregister_restart_handler(&pctrl->restart_nb); } EXPORT_SYMBOL(msm_pinctrl_remove); diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c index c1eccb3c80c5..eaae044e4f82 100644 --- a/drivers/platform/x86/amd/hsmp/acpi.c +++ b/drivers/platform/x86/amd/hsmp/acpi.c @@ -27,9 +27,8 @@ #include "hsmp.h" -#define DRIVER_NAME "amd_hsmp" +#define DRIVER_NAME "hsmp_acpi" #define DRIVER_VERSION "2.3" -#define ACPI_HSMP_DEVICE_HID "AMDI0097" /* These are the strings specified in ACPI table */ #define MSG_IDOFF_STR "MsgIdOffset" diff --git a/drivers/platform/x86/amd/hsmp/hsmp.h b/drivers/platform/x86/amd/hsmp/hsmp.h index af8b21f821d6..d58d4f0c20d5 100644 --- a/drivers/platform/x86/amd/hsmp/hsmp.h +++ b/drivers/platform/x86/amd/hsmp/hsmp.h @@ -23,6 +23,7 @@ #define HSMP_CDEV_NAME "hsmp_cdev" #define HSMP_DEVNODE_NAME "hsmp" +#define ACPI_HSMP_DEVICE_HID "AMDI0097" struct hsmp_mbaddr_info { u32 base_addr; diff --git a/drivers/platform/x86/amd/hsmp/plat.c b/drivers/platform/x86/amd/hsmp/plat.c index b9782a078dbd..81931e808bbc 100644 --- a/drivers/platform/x86/amd/hsmp/plat.c +++ b/drivers/platform/x86/amd/hsmp/plat.c @@ -11,6 +11,7 @@ #include <asm/amd_hsmp.h> +#include <linux/acpi.h> #include <linux/build_bug.h> #include <linux/device.h> #include <linux/module.h> @@ -266,7 +267,7 @@ static bool legacy_hsmp_support(void) } case 0x1A: switch (boot_cpu_data.x86_model) { - case 0x00 ... 0x1F: + case 0x00 ... 0x0F: return true; default: return false; @@ -288,6 +289,9 @@ static int __init hsmp_plt_init(void) return ret; } + if (acpi_dev_present(ACPI_HSMP_DEVICE_HID, NULL, -1)) + return -ENODEV; + hsmp_pdev = get_hsmp_pdev(); if (!hsmp_pdev) return -ENOMEM; diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index b4f49720c87f..2e3f6fc67c56 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -217,6 +217,13 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BIOS_VERSION, "03.05"), } }, + { + .ident = "MECHREVO Wujie 14X (GX4HRXL)", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"), + } + }, {} }; diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index 14b99d8b63d2..d3bd12ad036a 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -334,6 +334,11 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev) return 0; } +static inline bool amd_pmf_pb_valid(struct amd_pmf_dev *dev) +{ + return memchr_inv(dev->policy_buf, 0xff, dev->policy_sz); +} + #ifdef CONFIG_AMD_PMF_DEBUG static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev) { @@ -361,12 +366,22 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf, dev->policy_buf = new_policy_buf; dev->policy_sz = length; + if (!amd_pmf_pb_valid(dev)) { + ret = -EINVAL; + goto cleanup; + } + amd_pmf_hex_dump_pb(dev); ret = amd_pmf_start_policy_engine(dev); if (ret < 0) - return ret; + goto cleanup; return length; + +cleanup: + kfree(dev->policy_buf); + dev->policy_buf = NULL; + return ret; } static const struct file_operations pb_fops = { @@ -528,6 +543,12 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev) memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz); + if (!amd_pmf_pb_valid(dev)) { + dev_info(dev->dev, "No Smart PC policy present\n"); + ret = -EINVAL; + goto err_free_policy; + } + amd_pmf_hex_dump_pb(dev); dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 0c697b46f436..47cc766624d7 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -4779,7 +4779,8 @@ static int asus_wmi_add(struct platform_device *pdev) goto fail_leds; asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result); - if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) + if ((result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) == + (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) asus->driver->wlan_ctrl_by_user = 1; if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) { diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c index 230e6ee96636..d8f1bf5e58a0 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c @@ -45,7 +45,7 @@ static ssize_t current_password_store(struct kobject *kobj, int length; length = strlen(buf); - if (buf[length-1] == '\n') + if (length && buf[length - 1] == '\n') length--; /* firmware does verifiation of min/max password length, diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c index a0eae24ca9e6..162809140f68 100644 --- a/drivers/platform/x86/fujitsu-laptop.c +++ b/drivers/platform/x86/fujitsu-laptop.c @@ -17,13 +17,13 @@ /* * fujitsu-laptop.c - Fujitsu laptop support, providing access to additional * features made available on a range of Fujitsu laptops including the - * P2xxx/P5xxx/S6xxx/S7xxx series. + * P2xxx/P5xxx/S2xxx/S6xxx/S7xxx series. * * This driver implements a vendor-specific backlight control interface for * Fujitsu laptops and provides support for hotkeys present on certain Fujitsu * laptops. * - * This driver has been tested on a Fujitsu Lifebook S6410, S7020 and + * This driver has been tested on a Fujitsu Lifebook S2110, S6410, S7020 and * P8010. It should work on most P-series and S-series Lifebooks, but * YMMV. * @@ -107,7 +107,11 @@ #define KEY2_CODE 0x411 #define KEY3_CODE 0x412 #define KEY4_CODE 0x413 -#define KEY5_CODE 0x420 +#define KEY5_CODE 0x414 +#define KEY6_CODE 0x415 +#define KEY7_CODE 0x416 +#define KEY8_CODE 0x417 +#define KEY9_CODE 0x420 /* Hotkey ringbuffer limits */ #define MAX_HOTKEY_RINGBUFFER_SIZE 100 @@ -560,7 +564,7 @@ static const struct key_entry keymap_default[] = { { KE_KEY, KEY2_CODE, { KEY_PROG2 } }, { KE_KEY, KEY3_CODE, { KEY_PROG3 } }, { KE_KEY, KEY4_CODE, { KEY_PROG4 } }, - { KE_KEY, KEY5_CODE, { KEY_RFKILL } }, + { KE_KEY, KEY9_CODE, { KEY_RFKILL } }, /* Soft keys read from status flags */ { KE_KEY, FLAG_RFKILL, { KEY_RFKILL } }, { KE_KEY, FLAG_TOUCHPAD_TOGGLE, { KEY_TOUCHPAD_TOGGLE } }, @@ -584,6 +588,18 @@ static const struct key_entry keymap_p8010[] = { { KE_END, 0 } }; +static const struct key_entry keymap_s2110[] = { + { KE_KEY, KEY1_CODE, { KEY_PROG1 } }, /* "A" */ + { KE_KEY, KEY2_CODE, { KEY_PROG2 } }, /* "B" */ + { KE_KEY, KEY3_CODE, { KEY_WWW } }, /* "Internet" */ + { KE_KEY, KEY4_CODE, { KEY_EMAIL } }, /* "E-mail" */ + { KE_KEY, KEY5_CODE, { KEY_STOPCD } }, + { KE_KEY, KEY6_CODE, { KEY_PLAYPAUSE } }, + { KE_KEY, KEY7_CODE, { KEY_PREVIOUSSONG } }, + { KE_KEY, KEY8_CODE, { KEY_NEXTSONG } }, + { KE_END, 0 } +}; + static const struct key_entry *keymap = keymap_default; static int fujitsu_laptop_dmi_keymap_override(const struct dmi_system_id *id) @@ -621,6 +637,15 @@ static const struct dmi_system_id fujitsu_laptop_dmi_table[] = { }, .driver_data = (void *)keymap_p8010 }, + { + .callback = fujitsu_laptop_dmi_keymap_override, + .ident = "Fujitsu LifeBook S2110", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK S2110"), + }, + .driver_data = (void *)keymap_s2110 + }, {} }; diff --git a/drivers/platform/x86/intel/pmc/arl.c b/drivers/platform/x86/intel/pmc/arl.c index 320993bd6d31..f9c48738b853 100644 --- a/drivers/platform/x86/intel/pmc/arl.c +++ b/drivers/platform/x86/intel/pmc/arl.c @@ -681,6 +681,7 @@ static struct pmc_info arl_pmc_info_list[] = { #define ARL_NPU_PCI_DEV 0xad1d #define ARL_GNA_PCI_DEV 0xae4c +#define ARL_H_NPU_PCI_DEV 0x7d1d #define ARL_H_GNA_PCI_DEV 0x774c /* * Set power state of select devices that do not have drivers to D3 @@ -694,7 +695,7 @@ static void arl_d3_fixup(void) static void arl_h_d3_fixup(void) { - pmc_core_set_device_d3(ARL_NPU_PCI_DEV); + pmc_core_set_device_d3(ARL_H_NPU_PCI_DEV); pmc_core_set_device_d3(ARL_H_GNA_PCI_DEV); } diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 0fc275e461be..00b1e7c79a3d 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -1061,8 +1061,8 @@ static ssize_t current_value_store(struct kobject *kobj, ret = -EINVAL; goto out; } - set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->display_name, - new_setting, tlmi_priv.pwd_admin->signature); + set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->name, + new_setting, tlmi_priv.pwd_admin->signature); if (!set_str) { ret = -ENOMEM; goto out; @@ -1092,7 +1092,7 @@ static ssize_t current_value_store(struct kobject *kobj, goto out; } - set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name, + set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->name, new_setting); if (!set_str) { ret = -ENOMEM; @@ -1120,11 +1120,11 @@ static ssize_t current_value_store(struct kobject *kobj, } if (auth_str) - set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->display_name, - new_setting, auth_str); + set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->name, + new_setting, auth_str); else - set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name, - new_setting); + set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->name, + new_setting); if (!set_str) { ret = -ENOMEM; goto out; @@ -1629,9 +1629,6 @@ static int tlmi_analyze(struct wmi_device *wdev) continue; } - /* It is not allowed to have '/' for file name. Convert it into '\'. */ - strreplace(item, '/', '\\'); - /* Remove the value part */ strreplace(item, ',', '\0'); @@ -1644,11 +1641,16 @@ static int tlmi_analyze(struct wmi_device *wdev) } setting->wdev = wdev; setting->index = i; + + strscpy(setting->name, item); + /* It is not allowed to have '/' for file name. Convert it into '\'. */ + strreplace(item, '/', '\\'); strscpy(setting->display_name, item); + /* If BIOS selections supported, load those */ if (tlmi_priv.can_get_bios_selections) { - ret = tlmi_get_bios_selections(setting->display_name, - &setting->possible_values); + ret = tlmi_get_bios_selections(setting->name, + &setting->possible_values); if (ret || !setting->possible_values) pr_info("Error retrieving possible values for %d : %s\n", i, setting->display_name); diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h index a80452482227..9b014644d316 100644 --- a/drivers/platform/x86/think-lmi.h +++ b/drivers/platform/x86/think-lmi.h @@ -90,6 +90,7 @@ struct tlmi_attr_setting { struct kobject kobj; struct wmi_device *wdev; int index; + char name[TLMI_SETTINGS_MAXLEN]; char display_name[TLMI_SETTINGS_MAXLEN]; char *possible_values; }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 5790095c175e..657625dd60a0 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -231,6 +231,7 @@ enum tpacpi_hkey_event_t { /* Thermal events */ TP_HKEY_EV_ALARM_BAT_HOT = 0x6011, /* battery too hot */ TP_HKEY_EV_ALARM_BAT_XHOT = 0x6012, /* battery critically hot */ + TP_HKEY_EV_ALARM_BAT_LIM_CHANGE = 0x6013, /* battery charge limit changed*/ TP_HKEY_EV_ALARM_SENSOR_HOT = 0x6021, /* sensor too hot */ TP_HKEY_EV_ALARM_SENSOR_XHOT = 0x6022, /* sensor critically hot */ TP_HKEY_EV_THM_TABLE_CHANGED = 0x6030, /* windows; thermal table changed */ @@ -3777,6 +3778,10 @@ static bool hotkey_notify_6xxx(const u32 hkey, bool *send_acpi_ev) pr_alert("THERMAL EMERGENCY: battery is extremely hot!\n"); /* recommended action: immediate sleep/hibernate */ break; + case TP_HKEY_EV_ALARM_BAT_LIM_CHANGE: + pr_debug("Battery Info: battery charge threshold changed\n"); + /* User changed charging threshold. No action needed */ + return true; case TP_HKEY_EV_ALARM_SENSOR_HOT: pr_crit("THERMAL ALARM: a sensor reports something is too hot!\n"); /* recommended action: warn user through gui, that */ @@ -11478,6 +11483,8 @@ static int __must_check __init get_thinkpad_model_data( tp->vendor = PCI_VENDOR_ID_IBM; else if (dmi_name_in_vendors("LENOVO")) tp->vendor = PCI_VENDOR_ID_LENOVO; + else if (dmi_name_in_vendors("NEC")) + tp->vendor = PCI_VENDOR_ID_LENOVO; else return 0; diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 9b2f28b34bb5..d6c1ddb807b2 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -3126,7 +3126,7 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev, /* Verify that the index is within a valid range. */ num_domains = of_count_phandle_with_args(dev->of_node, "power-domains", "#power-domain-cells"); - if (index >= num_domains) + if (num_domains < 0 || index >= num_domains) return NULL; /* Allocate and register device on the genpd bus. */ diff --git a/drivers/pmdomain/renesas/rcar-gen4-sysc.c b/drivers/pmdomain/renesas/rcar-gen4-sysc.c index 66409cff2083..e001b5c25bed 100644 --- a/drivers/pmdomain/renesas/rcar-gen4-sysc.c +++ b/drivers/pmdomain/renesas/rcar-gen4-sysc.c @@ -338,11 +338,6 @@ static int __init rcar_gen4_sysc_pd_init(void) struct rcar_gen4_sysc_pd *pd; size_t n; - if (!area->name) { - /* Skip NULLified area */ - continue; - } - n = strlen(area->name) + 1; pd = kzalloc(sizeof(*pd) + n, GFP_KERNEL); if (!pd) { diff --git a/drivers/pmdomain/renesas/rcar-sysc.c b/drivers/pmdomain/renesas/rcar-sysc.c index dce1a6d37e80..047495f54e8a 100644 --- a/drivers/pmdomain/renesas/rcar-sysc.c +++ b/drivers/pmdomain/renesas/rcar-sysc.c @@ -396,11 +396,6 @@ static int __init rcar_sysc_pd_init(void) struct rcar_sysc_pd *pd; size_t n; - if (!area->name) { - /* Skip NULLified area */ - continue; - } - n = strlen(area->name) + 1; pd = kzalloc(sizeof(*pd) + n, GFP_KERNEL); if (!pd) { diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 2ccdca4f6960..e63481f24238 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -315,6 +315,8 @@ struct ptp_ocp_serial_port { #define OCP_BOARD_ID_LEN 13 #define OCP_SERIAL_LEN 6 #define OCP_SMA_NUM 4 +#define OCP_SIGNAL_NUM 4 +#define OCP_FREQ_NUM 4 enum { PORT_GNSS, @@ -342,8 +344,8 @@ struct ptp_ocp { struct dcf_master_reg __iomem *dcf_out; struct dcf_slave_reg __iomem *dcf_in; struct tod_reg __iomem *nmea_out; - struct frequency_reg __iomem *freq_in[4]; - struct ptp_ocp_ext_src *signal_out[4]; + struct frequency_reg __iomem *freq_in[OCP_FREQ_NUM]; + struct ptp_ocp_ext_src *signal_out[OCP_SIGNAL_NUM]; struct ptp_ocp_ext_src *pps; struct ptp_ocp_ext_src *ts0; struct ptp_ocp_ext_src *ts1; @@ -378,10 +380,12 @@ struct ptp_ocp { u32 utc_tai_offset; u32 ts_window_adjust; u64 fw_cap; - struct ptp_ocp_signal signal[4]; + struct ptp_ocp_signal signal[OCP_SIGNAL_NUM]; struct ptp_ocp_sma_connector sma[OCP_SMA_NUM]; const struct ocp_sma_op *sma_op; struct dpll_device *dpll; + int signals_nr; + int freq_in_nr; }; #define OCP_REQ_TIMESTAMP BIT(0) @@ -2697,6 +2701,8 @@ ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) bp->eeprom_map = fb_eeprom_map; bp->fw_version = ioread32(&bp->image->version); bp->sma_op = &ocp_fb_sma_op; + bp->signals_nr = 4; + bp->freq_in_nr = 4; ptp_ocp_fb_set_version(bp); @@ -2862,6 +2868,8 @@ ptp_ocp_art_board_init(struct ptp_ocp *bp, struct ocp_resource *r) bp->fw_version = ioread32(&bp->reg->version); bp->fw_tag = 2; bp->sma_op = &ocp_art_sma_op; + bp->signals_nr = 4; + bp->freq_in_nr = 4; /* Enable MAC serial port during initialisation */ iowrite32(1, &bp->board_config->mro50_serial_activate); @@ -2888,6 +2896,8 @@ ptp_ocp_adva_board_init(struct ptp_ocp *bp, struct ocp_resource *r) bp->flash_start = 0xA00000; bp->eeprom_map = fb_eeprom_map; bp->sma_op = &ocp_adva_sma_op; + bp->signals_nr = 2; + bp->freq_in_nr = 2; version = ioread32(&bp->image->version); /* if lower 16 bits are empty, this is the fw loader. */ @@ -4008,7 +4018,7 @@ _signal_summary_show(struct seq_file *s, struct ptp_ocp *bp, int nr) { struct signal_reg __iomem *reg = bp->signal_out[nr]->mem; struct ptp_ocp_signal *signal = &bp->signal[nr]; - char label[8]; + char label[16]; bool on; u32 val; @@ -4031,7 +4041,7 @@ static void _frequency_summary_show(struct seq_file *s, int nr, struct frequency_reg __iomem *reg) { - char label[8]; + char label[16]; bool on; u32 val; @@ -4175,11 +4185,11 @@ ptp_ocp_summary_show(struct seq_file *s, void *data) } if (bp->fw_cap & OCP_CAP_SIGNAL) - for (i = 0; i < 4; i++) + for (i = 0; i < bp->signals_nr; i++) _signal_summary_show(s, bp, i); if (bp->fw_cap & OCP_CAP_FREQ) - for (i = 0; i < 4; i++) + for (i = 0; i < bp->freq_in_nr; i++) _frequency_summary_show(s, i, bp->freq_in[i]); if (bp->irig_out) { diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c index 59eb23d467ec..198d45f8e884 100644 --- a/drivers/regulator/max20086-regulator.c +++ b/drivers/regulator/max20086-regulator.c @@ -132,7 +132,7 @@ static int max20086_regulators_register(struct max20086 *chip) static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on) { - struct of_regulator_match matches[MAX20086_MAX_REGULATORS] = { }; + struct of_regulator_match *matches; struct device_node *node; unsigned int i; int ret; @@ -143,6 +143,11 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on) return -ENODEV; } + matches = devm_kcalloc(chip->dev, chip->info->num_outputs, + sizeof(*matches), GFP_KERNEL); + if (!matches) + return -ENOMEM; + for (i = 0; i < chip->info->num_outputs; ++i) matches[i].name = max20086_output_names[i]; diff --git a/drivers/remoteproc/qcom_wcnss.c b/drivers/remoteproc/qcom_wcnss.c index 775b056d795a..2c7e519a2254 100644 --- a/drivers/remoteproc/qcom_wcnss.c +++ b/drivers/remoteproc/qcom_wcnss.c @@ -456,7 +456,8 @@ static int wcnss_init_regulators(struct qcom_wcnss *wcnss, if (wcnss->num_pds) { info += wcnss->num_pds; /* Handle single power domain case */ - num_vregs += num_pd_vregs - wcnss->num_pds; + if (wcnss->num_pds < num_pd_vregs) + num_vregs += num_pd_vregs - wcnss->num_pds; } else { num_vregs += num_pd_vregs; } diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig index 4bfe469c04aa..8c1c908d2c6e 100644 --- a/drivers/s390/block/Kconfig +++ b/drivers/s390/block/Kconfig @@ -5,7 +5,7 @@ comment "S/390 block device drivers" config DCSSBLK def_tristate m prompt "DCSSBLK support" - depends on S390 && BLOCK + depends on S390 && BLOCK && (DAX || DAX=n) help Support for dcss block device @@ -14,7 +14,6 @@ config DCSSBLK_DAX depends on DCSSBLK # requires S390 ZONE_DEVICE support depends on BROKEN - select DAX prompt "DCSSBLK DAX support" help Enable DAX operation for the dcss block device diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 7a447ff600d2..a8db66428f80 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -169,6 +169,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, unsigned int nr_zones, size_t *buflen) { struct request_queue *q = sdkp->disk->queue; + unsigned int max_segments; size_t bufsize; void *buf; @@ -180,12 +181,15 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp, * Furthermore, since the report zone command cannot be split, make * sure that the allocated buffer can always be mapped by limiting the * number of pages allocated to the HBA max segments limit. + * Since max segments can be larger than the max inline bio vectors, + * further limit the allocated buffer to BIO_MAX_INLINE_VECS. */ nr_zones = min(nr_zones, sdkp->zone_info.nr_zones); bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE); bufsize = min_t(size_t, bufsize, queue_max_hw_sectors(q) << SECTOR_SHIFT); - bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT); + max_segments = min(BIO_MAX_INLINE_VECS, queue_max_segments(q)); + bufsize = min_t(size_t, bufsize, max_segments << PAGE_SHIFT); while (bufsize >= SECTOR_SIZE) { buf = kvzalloc(bufsize, GFP_KERNEL | __GFP_NORETRY); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 35db061ae3ec..2e6b2412d2c9 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1819,6 +1819,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) return SCSI_MLQUEUE_DEVICE_BUSY; } + payload->rangecount = 1; payload->range.len = length; payload->range.offset = offset_in_hvpg; diff --git a/drivers/soc/samsung/exynos-usi.c b/drivers/soc/samsung/exynos-usi.c index c5661ac19f7b..5f7bdf3bab05 100644 --- a/drivers/soc/samsung/exynos-usi.c +++ b/drivers/soc/samsung/exynos-usi.c @@ -233,7 +233,7 @@ static void exynos_usi_unconfigure(void *data) /* Make sure that we've stopped providing the clock to USI IP */ val = readl(usi->regs + USI_OPTION); val &= ~USI_OPTION_CLKREQ_ON; - val |= ~USI_OPTION_CLKSTOP_ON; + val |= USI_OPTION_CLKSTOP_ON; writel(val, usi->regs + USI_OPTION); /* Set USI block state to reset */ diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 6f8a20014e76..39aecd34c641 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -122,6 +122,10 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, set_bit(SDW_GROUP13_DEV_NUM, bus->assigned); set_bit(SDW_MASTER_DEV_NUM, bus->assigned); + ret = sdw_irq_create(bus, fwnode); + if (ret) + return ret; + /* * SDW is an enumerable bus, but devices can be powered off. So, * they won't be able to report as present. @@ -138,6 +142,7 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, if (ret < 0) { dev_err(bus->dev, "Finding slaves failed:%d\n", ret); + sdw_irq_delete(bus); return ret; } @@ -156,10 +161,6 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, bus->params.curr_bank = SDW_BANK0; bus->params.next_bank = SDW_BANK1; - ret = sdw_irq_create(bus, fwnode); - if (ret) - return ret; - return 0; } EXPORT_SYMBOL(sdw_bus_master_add); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 067c954cb6ea..863781ba6c16 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0+ // // Copyright 2013 Freescale Semiconductor, Inc. -// Copyright 2020 NXP +// Copyright 2020-2025 NXP // // Freescale DSPI driver // This file contains a driver for the Freescale DSPI @@ -62,6 +62,7 @@ #define SPI_SR_TFIWF BIT(18) #define SPI_SR_RFDF BIT(17) #define SPI_SR_CMDFFF BIT(16) +#define SPI_SR_TXRXS BIT(30) #define SPI_SR_CLEAR (SPI_SR_TCFQF | \ SPI_SR_TFUF | SPI_SR_TFFF | \ SPI_SR_CMDTCF | SPI_SR_SPEF | \ @@ -921,9 +922,20 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, struct spi_transfer *transfer; bool cs = false; int status = 0; + u32 val = 0; + bool cs_change = false; message->actual_length = 0; + /* Put DSPI in running mode if halted. */ + regmap_read(dspi->regmap, SPI_MCR, &val); + if (val & SPI_MCR_HALT) { + regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_HALT, 0); + while (regmap_read(dspi->regmap, SPI_SR, &val) >= 0 && + !(val & SPI_SR_TXRXS)) + ; + } + list_for_each_entry(transfer, &message->transfers, transfer_list) { dspi->cur_transfer = transfer; dspi->cur_msg = message; @@ -953,6 +965,7 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, dspi->tx_cmd |= SPI_PUSHR_CMD_CONT; } + cs_change = transfer->cs_change; dspi->tx = transfer->tx_buf; dspi->rx = transfer->rx_buf; dspi->len = transfer->len; @@ -962,6 +975,8 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF); + regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR); + spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer, dspi->progress, !dspi->irq); @@ -988,6 +1003,15 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr, dspi_deassert_cs(spi, &cs); } + if (status || !cs_change) { + /* Put DSPI in stop mode */ + regmap_update_bits(dspi->regmap, SPI_MCR, + SPI_MCR_HALT, SPI_MCR_HALT); + while (regmap_read(dspi->regmap, SPI_SR, &val) >= 0 && + val & SPI_SR_TXRXS) + ; + } + message->status = status; spi_finalize_current_message(ctlr); @@ -1167,6 +1191,20 @@ static int dspi_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(dspi_pm, dspi_suspend, dspi_resume); +static const struct regmap_range dspi_yes_ranges[] = { + regmap_reg_range(SPI_MCR, SPI_MCR), + regmap_reg_range(SPI_TCR, SPI_CTAR(3)), + regmap_reg_range(SPI_SR, SPI_TXFR3), + regmap_reg_range(SPI_RXFR0, SPI_RXFR3), + regmap_reg_range(SPI_CTARE(0), SPI_CTARE(3)), + regmap_reg_range(SPI_SREX, SPI_SREX), +}; + +static const struct regmap_access_table dspi_access_table = { + .yes_ranges = dspi_yes_ranges, + .n_yes_ranges = ARRAY_SIZE(dspi_yes_ranges), +}; + static const struct regmap_range dspi_volatile_ranges[] = { regmap_reg_range(SPI_MCR, SPI_TCR), regmap_reg_range(SPI_SR, SPI_SR), @@ -1184,6 +1222,8 @@ static const struct regmap_config dspi_regmap_config = { .reg_stride = 4, .max_register = 0x88, .volatile_table = &dspi_volatile_table, + .rd_table = &dspi_access_table, + .wr_table = &dspi_access_table, }; static const struct regmap_range dspi_xspi_volatile_ranges[] = { @@ -1205,6 +1245,8 @@ static const struct regmap_config dspi_xspi_regmap_config[] = { .reg_stride = 4, .max_register = 0x13c, .volatile_table = &dspi_xspi_volatile_table, + .rd_table = &dspi_access_table, + .wr_table = &dspi_access_table, }, { .name = "pushr", @@ -1227,6 +1269,8 @@ static int dspi_init(struct fsl_dspi *dspi) if (!spi_controller_is_target(dspi->ctlr)) mcr |= SPI_MCR_HOST; + mcr |= SPI_MCR_HALT; + regmap_write(dspi->regmap, SPI_MCR, mcr); regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR); diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c index 31a878d9458d..7740f94847a8 100644 --- a/drivers/spi/spi-loopback-test.c +++ b/drivers/spi/spi-loopback-test.c @@ -420,7 +420,7 @@ MODULE_LICENSE("GPL"); static void spi_test_print_hex_dump(char *pre, const void *ptr, size_t len) { /* limit the hex_dump */ - if (len < 1024) { + if (len <= 1024) { print_hex_dump(KERN_INFO, pre, DUMP_PREFIX_OFFSET, 16, 1, ptr, len, 0); diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c index f89826d7dc49..aa92fd5a35a9 100644 --- a/drivers/spi/spi-sun4i.c +++ b/drivers/spi/spi-sun4i.c @@ -264,6 +264,9 @@ static int sun4i_spi_transfer_one(struct spi_controller *host, else reg |= SUN4I_CTL_DHB; + /* Now that the settings are correct, enable the interface */ + reg |= SUN4I_CTL_ENABLE; + sun4i_spi_write(sspi, SUN4I_CTL_REG, reg); /* Ensure that we have a parent clock fast enough */ @@ -404,7 +407,7 @@ static int sun4i_spi_runtime_resume(struct device *dev) } sun4i_spi_write(sspi, SUN4I_CTL_REG, - SUN4I_CTL_ENABLE | SUN4I_CTL_MASTER | SUN4I_CTL_TP); + SUN4I_CTL_MASTER | SUN4I_CTL_TP); return 0; diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c index 2a8bb798e95b..795a8482c2c7 100644 --- a/drivers/spi/spi-tegra114.c +++ b/drivers/spi/spi-tegra114.c @@ -728,9 +728,9 @@ static int tegra_spi_set_hw_cs_timing(struct spi_device *spi) u32 inactive_cycles; u8 cs_state; - if ((setup->unit && setup->unit != SPI_DELAY_UNIT_SCK) || - (hold->unit && hold->unit != SPI_DELAY_UNIT_SCK) || - (inactive->unit && inactive->unit != SPI_DELAY_UNIT_SCK)) { + if ((setup->value && setup->unit != SPI_DELAY_UNIT_SCK) || + (hold->value && hold->unit != SPI_DELAY_UNIT_SCK) || + (inactive->value && inactive->unit != SPI_DELAY_UNIT_SCK)) { dev_err(&spi->dev, "Invalid delay unit %d, should be SPI_DELAY_UNIT_SCK\n", SPI_DELAY_UNIT_SCK); diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c index 7540c20090c7..351f983ef914 100644 --- a/drivers/staging/axis-fifo/axis-fifo.c +++ b/drivers/staging/axis-fifo/axis-fifo.c @@ -393,16 +393,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET); if (!bytes_available) { - dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet of length 0\n"); ret = -EIO; goto end_unlock; } if (bytes_available > len) { - dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n", + dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n", bytes_available, len); - reset_ip_core(fifo); ret = -EINVAL; goto end_unlock; } @@ -411,8 +409,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, /* this probably can't happen unless IP * registers were previously mishandled */ - dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n"); ret = -EIO; goto end_unlock; } @@ -433,7 +430,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, if (copy_to_user(buf + copied * sizeof(u32), tmp_buf, copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; } @@ -542,7 +538,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf, if (copy_from_user(tmp_buf, buf + copied * sizeof(u32), copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; } @@ -775,9 +770,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo) goto end; } - /* IP sets TDFV to fifo depth - 4 so we will do the same */ - fifo->tx_fifo_depth -= 4; - ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo); if (ret) { dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n"); diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c index 6c14d7bcdd67..081b17f49863 100644 --- a/drivers/staging/iio/adc/ad7816.c +++ b/drivers/staging/iio/adc/ad7816.c @@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev, struct iio_dev *indio_dev = dev_to_iio_dev(dev); struct ad7816_chip_info *chip = iio_priv(indio_dev); - if (strcmp(buf, "full")) { + if (strcmp(buf, "full") == 0) { gpiod_set_value(chip->rdwr_pin, 1); chip->mode = AD7816_FULL; } else { diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c index b839b50ac26a..fa7ea4ca4c36 100644 --- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c +++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c @@ -1900,6 +1900,7 @@ static int bcm2835_mmal_probe(struct vchiq_device *device) __func__, ret); goto free_dev; } + dev->v4l2_dev.dev = &device->dev; /* setup v4l controls */ ret = bcm2835_mmal_init_controls(dev, &dev->ctrl_handler); diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c index 496abf8e55e0..2841d14914b7 100644 --- a/drivers/thermal/intel/x86_pkg_temp_thermal.c +++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c @@ -329,6 +329,7 @@ static int pkg_temp_thermal_device_add(unsigned int cpu) tj_max = intel_tcc_get_tjmax(cpu); if (tj_max < 0) return tj_max; + tj_max *= 1000; zonedev = kzalloc(sizeof(*zonedev), GFP_KERNEL); if (!zonedev) diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 1b19b5647495..69c1df0f4ca5 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel) vmbus_device_unregister(channel->device_obj); } -/* Sysfs API to allow mmap of the ring buffers +/* Function used for mmap of ring buffer sysfs interface. * The ring buffer is allocated as contiguous memory by vmbus_open */ -static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, - const struct bin_attribute *attr, - struct vm_area_struct *vma) +static int +hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma) { - struct vmbus_channel *channel - = container_of(kobj, struct vmbus_channel, kobj); void *ring_buffer = page_address(channel->ringbuffer_page); if (channel->state != CHANNEL_OPENED_STATE) @@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, channel->ringbuffer_pagecount << PAGE_SHIFT); } -static const struct bin_attribute ring_buffer_bin_attr = { - .attr = { - .name = "ring", - .mode = 0600, - }, - .size = 2 * SZ_2M, - .mmap = hv_uio_ring_mmap, -}; - /* Callback from VMBUS subsystem when new channel created. */ static void hv_uio_new_channel(struct vmbus_channel *new_sc) @@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) /* Disable interrupts on sub channel */ new_sc->inbound.ring_buffer->interrupt_mask = 1; set_channel_read_mode(new_sc, HV_CALL_ISR); - - ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr); + ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap); if (ret) { dev_err(device, "sysfs create ring bin file failed; %d\n", ret); vmbus_close(new_sc); @@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev, goto fail_close; } - ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr); - if (ret) - dev_notice(&dev->device, - "sysfs create ring bin file failed; %d\n", ret); + /* + * This internally calls sysfs_update_group, which returns a non-zero value if it executes + * before sysfs_create_group. This is expected as the 'ring' will be created later in + * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return + * value and print warning. + * + * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race + * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed + * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify + * APIs to make sure that ring is created. + */ + hv_create_ring_sysfs(channel, hv_uio_ring_mmap); hv_set_drvdata(dev, pdata); @@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev) if (!pdata) return; - sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr); + hv_remove_ring_sysfs(dev->channel); uio_unregister_device(&pdata->info); hv_uio_cleanup(dev, pdata); diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 87f310841735..4824a10df07e 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -139,6 +139,26 @@ static void cdnsp_clear_port_change_bit(struct cdnsp_device *pdev, (portsc & PORT_CHANGE_BITS), port_regs); } +static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev) +{ + struct cdns *cdns = dev_get_drvdata(pdev->dev); + __le32 __iomem *reg; + void __iomem *base; + u32 offset = 0; + u32 val; + + if (!cdns->override_apb_timeout) + return; + + base = &pdev->cap_regs->hc_capbase; + offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP); + reg = base + offset + REG_CHICKEN_BITS_3_OFFSET; + + val = le32_to_cpu(readl(reg)); + val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout); + writel(cpu_to_le32(val), reg); +} + static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit) { __le32 __iomem *reg; @@ -1773,6 +1793,8 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev) reg += cdnsp_find_next_ext_cap(reg, 0, RTL_REV_CAP); pdev->rev_cap = reg; + pdev->rtl_revision = readl(&pdev->rev_cap->rtl_revision); + dev_info(pdev->dev, "Rev: %08x/%08x, eps: %08x, buff: %08x/%08x\n", readl(&pdev->rev_cap->ctrl_revision), readl(&pdev->rev_cap->rtl_revision), @@ -1798,6 +1820,15 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev) pdev->hci_version = HC_VERSION(pdev->hcc_params); pdev->hcc_params = readl(&pdev->cap_regs->hcc_params); + /* + * Override the APB timeout value to give the controller more time for + * enabling UTMI clock and synchronizing APB and UTMI clock domains. + * This fix is platform specific and is required to fixes issue with + * reading incorrect value from PORTSC register after resuming + * from L1 state. + */ + cdnsp_set_apb_timeout_value(pdev); + cdnsp_get_rev_cap(pdev); /* Make sure the Device Controller is halted. */ diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h index 84887dfea763..12534be52f39 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.h +++ b/drivers/usb/cdns3/cdnsp-gadget.h @@ -520,6 +520,9 @@ struct cdnsp_rev_cap { #define REG_CHICKEN_BITS_2_OFFSET 0x48 #define CHICKEN_XDMA_2_TP_CACHE_DIS BIT(28) +#define REG_CHICKEN_BITS_3_OFFSET 0x4C +#define CHICKEN_APB_TIMEOUT_SET(p, val) (((p) & ~GENMASK(21, 0)) | (val)) + /* XBUF Extended Capability ID. */ #define XBUF_CAP_ID 0xCB #define XBUF_RX_TAG_MASK_0_OFFSET 0x1C @@ -1357,6 +1360,7 @@ struct cdnsp_port { * @rev_cap: Controller Capabilities Registers. * @hcs_params1: Cached register copies of read-only HCSPARAMS1 * @hcc_params: Cached register copies of read-only HCCPARAMS1 + * @rtl_revision: Cached controller rtl revision. * @setup: Temporary buffer for setup packet. * @ep0_preq: Internal allocated request used during enumeration. * @ep0_stage: ep0 stage during enumeration process. @@ -1411,6 +1415,8 @@ struct cdnsp_device { __u32 hcs_params1; __u32 hcs_params3; __u32 hcc_params; + #define RTL_REVISION_NEW_LPM 0x2700 + __u32 rtl_revision; /* Lock used in interrupt thread context. */ spinlock_t lock; struct usb_ctrlrequest setup; diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c index a51144504ff3..8c361b8394e9 100644 --- a/drivers/usb/cdns3/cdnsp-pci.c +++ b/drivers/usb/cdns3/cdnsp-pci.c @@ -28,6 +28,8 @@ #define PCI_DRIVER_NAME "cdns-pci-usbssp" #define PLAT_DRIVER_NAME "cdns-usbssp" +#define CHICKEN_APB_TIMEOUT_VALUE 0x1C20 + static struct pci_dev *cdnsp_get_second_fun(struct pci_dev *pdev) { /* @@ -139,6 +141,14 @@ static int cdnsp_pci_probe(struct pci_dev *pdev, cdnsp->otg_irq = pdev->irq; } + /* + * Cadence PCI based platform require some longer timeout for APB + * to fixes domain clock synchronization issue after resuming + * controller from L1 state. + */ + cdnsp->override_apb_timeout = CHICKEN_APB_TIMEOUT_VALUE; + pci_set_drvdata(pdev, cdnsp); + if (pci_is_enabled(func)) { cdnsp->dev = dev; cdnsp->gadget_init = cdnsp_gadget_init; @@ -148,8 +158,6 @@ static int cdnsp_pci_probe(struct pci_dev *pdev, goto free_cdnsp; } - pci_set_drvdata(pdev, cdnsp); - device_wakeup_enable(&pdev->dev); if (pci_dev_run_wake(pdev)) pm_runtime_put_noidle(&pdev->dev); diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 46852529499d..fd06cb85c4ea 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -308,7 +308,8 @@ static bool cdnsp_ring_ep_doorbell(struct cdnsp_device *pdev, writel(db_value, reg_addr); - cdnsp_force_l0_go(pdev); + if (pdev->rtl_revision < RTL_REVISION_NEW_LPM) + cdnsp_force_l0_go(pdev); /* Doorbell was set. */ return true; diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h index 921cccf1ca9d..801be9e61340 100644 --- a/drivers/usb/cdns3/core.h +++ b/drivers/usb/cdns3/core.h @@ -79,6 +79,8 @@ struct cdns3_platform_data { * @pdata: platform data from glue layer * @lock: spinlock structure * @xhci_plat_data: xhci private data structure pointer + * @override_apb_timeout: hold value of APB timeout. For value 0 the default + * value in CHICKEN_BITS_3 will be preserved. * @gadget_init: pointer to gadget initialization function */ struct cdns { @@ -117,6 +119,7 @@ struct cdns { struct cdns3_platform_data *pdata; spinlock_t lock; struct xhci_plat_priv *xhci_plat_data; + u32 override_apb_timeout; int (*gadget_init)(struct cdns *cdns); }; diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 34e46ef308ab..740d2d2b19fb 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -482,6 +482,7 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) u8 *buffer; u8 tag; int rv; + long wait_rv; dev_dbg(dev, "Enter ioctl_read_stb iin_ep_present: %d\n", data->iin_ep_present); @@ -511,16 +512,17 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) } if (data->iin_ep_present) { - rv = wait_event_interruptible_timeout( + wait_rv = wait_event_interruptible_timeout( data->waitq, atomic_read(&data->iin_data_valid) != 0, file_data->timeout); - if (rv < 0) { - dev_dbg(dev, "wait interrupted %d\n", rv); + if (wait_rv < 0) { + dev_dbg(dev, "wait interrupted %ld\n", wait_rv); + rv = wait_rv; goto exit; } - if (rv == 0) { + if (wait_rv == 0) { dev_dbg(dev, "wait timed out\n"); rv = -ETIMEDOUT; goto exit; @@ -539,6 +541,8 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) dev_dbg(dev, "stb:0x%02x received %d\n", (unsigned int)*stb, rv); + rv = 0; + exit: /* bump interrupt bTag */ data->iin_bTag += 1; @@ -602,9 +606,9 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data, { struct usbtmc_device_data *data = file_data->data; struct device *dev = &data->intf->dev; - int rv; u32 timeout; unsigned long expire; + long wait_rv; if (!data->iin_ep_present) { dev_dbg(dev, "no interrupt endpoint present\n"); @@ -618,25 +622,24 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data, mutex_unlock(&data->io_mutex); - rv = wait_event_interruptible_timeout( - data->waitq, - atomic_read(&file_data->srq_asserted) != 0 || - atomic_read(&file_data->closing), - expire); + wait_rv = wait_event_interruptible_timeout( + data->waitq, + atomic_read(&file_data->srq_asserted) != 0 || + atomic_read(&file_data->closing), + expire); mutex_lock(&data->io_mutex); /* Note! disconnect or close could be called in the meantime */ if (atomic_read(&file_data->closing) || data->zombie) - rv = -ENODEV; + return -ENODEV; - if (rv < 0) { - /* dev can be invalid now! */ - pr_debug("%s - wait interrupted %d\n", __func__, rv); - return rv; + if (wait_rv < 0) { + dev_dbg(dev, "%s - wait interrupted %ld\n", __func__, wait_rv); + return wait_rv; } - if (rv == 0) { + if (wait_rv == 0) { dev_dbg(dev, "%s - wait timed out\n", __func__); return -ETIMEDOUT; } @@ -830,6 +833,7 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data, unsigned long expire; int bufcount = 1; int again = 0; + long wait_rv; /* mutex already locked */ @@ -942,19 +946,24 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data, if (!(flags & USBTMC_FLAG_ASYNC)) { dev_dbg(dev, "%s: before wait time %lu\n", __func__, expire); - retval = wait_event_interruptible_timeout( + wait_rv = wait_event_interruptible_timeout( file_data->wait_bulk_in, usbtmc_do_transfer(file_data), expire); - dev_dbg(dev, "%s: wait returned %d\n", - __func__, retval); + dev_dbg(dev, "%s: wait returned %ld\n", + __func__, wait_rv); + + if (wait_rv < 0) { + retval = wait_rv; + goto error; + } - if (retval <= 0) { - if (retval == 0) - retval = -ETIMEDOUT; + if (wait_rv == 0) { + retval = -ETIMEDOUT; goto error; } + } urb = usb_get_from_anchor(&file_data->in_anchor); @@ -1380,7 +1389,10 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, if (!buffer) return -ENOMEM; - mutex_lock(&data->io_mutex); + retval = mutex_lock_interruptible(&data->io_mutex); + if (retval < 0) + goto exit_nolock; + if (data->zombie) { retval = -ENODEV; goto exit; @@ -1503,6 +1515,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, exit: mutex_unlock(&data->io_mutex); +exit_nolock: kfree(buffer); return retval; } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index aaa39e663f60..27eae4cf223d 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1164,6 +1164,9 @@ struct dwc3_scratchpad_array { * @gsbuscfg0_reqinfo: store GSBUSCFG0.DATRDREQINFO, DESRDREQINFO, * DATWRREQINFO, and DESWRREQINFO value passed from * glue driver. + * @wakeup_pending_funcs: Indicates whether any interface has requested for + * function wakeup in bitmap format where bit position + * represents interface_id. */ struct dwc3 { struct work_struct drd_work; @@ -1394,6 +1397,7 @@ struct dwc3 { int num_ep_resized; struct dentry *debug_root; u32 gsbuscfg0_reqinfo; + u32 wakeup_pending_funcs; }; #define INCRX_BURST_MODE 0 diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 8c30d86cc4e3..321361288935 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -276,8 +276,6 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd, return ret; } -static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async); - /** * dwc3_send_gadget_ep_cmd - issue an endpoint command * @dep: the endpoint to which the command is going to be issued @@ -2359,10 +2357,8 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g) return __dwc3_gadget_get_frame(dwc); } -static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async) +static int __dwc3_gadget_wakeup(struct dwc3 *dwc) { - int retries; - int ret; u32 reg; @@ -2390,8 +2386,7 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async) return -EINVAL; } - if (async) - dwc3_gadget_enable_linksts_evts(dwc, true); + dwc3_gadget_enable_linksts_evts(dwc, true); ret = dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RECOV); if (ret < 0) { @@ -2410,27 +2405,8 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async) /* * Since link status change events are enabled we will receive - * an U0 event when wakeup is successful. So bail out. + * an U0 event when wakeup is successful. */ - if (async) - return 0; - - /* poll until Link State changes to ON */ - retries = 20000; - - while (retries--) { - reg = dwc3_readl(dwc->regs, DWC3_DSTS); - - /* in HS, means ON */ - if (DWC3_DSTS_USBLNKST(reg) == DWC3_LINK_STATE_U0) - break; - } - - if (DWC3_DSTS_USBLNKST(reg) != DWC3_LINK_STATE_U0) { - dev_err(dwc->dev, "failed to send remote wakeup\n"); - return -EINVAL; - } - return 0; } @@ -2451,7 +2427,7 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g) spin_unlock_irqrestore(&dwc->lock, flags); return -EINVAL; } - ret = __dwc3_gadget_wakeup(dwc, true); + ret = __dwc3_gadget_wakeup(dwc); spin_unlock_irqrestore(&dwc->lock, flags); @@ -2479,14 +2455,10 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) */ link_state = dwc3_gadget_get_link_state(dwc); if (link_state == DWC3_LINK_STATE_U3) { - ret = __dwc3_gadget_wakeup(dwc, false); - if (ret) { - spin_unlock_irqrestore(&dwc->lock, flags); - return -EINVAL; - } - dwc3_resume_gadget(dwc); - dwc->suspended = false; - dwc->link_state = DWC3_LINK_STATE_U0; + dwc->wakeup_pending_funcs |= BIT(intf_id); + ret = __dwc3_gadget_wakeup(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); + return ret; } ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION, @@ -4353,6 +4325,8 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, { enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK; unsigned int pwropt; + int ret; + int intf_id; /* * WORKAROUND: DWC3 < 2.50a have an issue when configured without @@ -4428,7 +4402,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, switch (next) { case DWC3_LINK_STATE_U0: - if (dwc->gadget->wakeup_armed) { + if (dwc->gadget->wakeup_armed || dwc->wakeup_pending_funcs) { dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_resume_gadget(dwc); dwc->suspended = false; @@ -4451,6 +4425,18 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, } dwc->link_state = next; + + /* Proceed with func wakeup if any interfaces that has requested */ + while (dwc->wakeup_pending_funcs && (next == DWC3_LINK_STATE_U0)) { + intf_id = ffs(dwc->wakeup_pending_funcs) - 1; + ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION, + DWC3_DGCMDPAR_DN_FUNC_WAKE | + DWC3_DGCMDPAR_INTF_SEL(intf_id)); + if (ret) + dev_err(dwc->dev, "Failed to send DN wake for intf %d\n", intf_id); + + dwc->wakeup_pending_funcs &= ~BIT(intf_id); + } } static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 869ad99afb48..8dbc132a505e 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2011,15 +2011,13 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) if (f->get_status) { status = f->get_status(f); + if (status < 0) break; - } else { - /* Set D0 and D1 bits based on func wakeup capability */ - if (f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP) { - status |= USB_INTRF_STAT_FUNC_RW_CAP; - if (f->func_wakeup_armed) - status |= USB_INTRF_STAT_FUNC_RW; - } + + /* if D5 is not set, then device is not wakeup capable */ + if (!(f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP)) + status &= ~(USB_INTRF_STAT_FUNC_RW_CAP | USB_INTRF_STAT_FUNC_RW); } put_unaligned_le16(status & 0x0000ffff, req->buf); diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c index 80841de845b0..027226325039 100644 --- a/drivers/usb/gadget/function/f_ecm.c +++ b/drivers/usb/gadget/function/f_ecm.c @@ -892,6 +892,12 @@ static void ecm_resume(struct usb_function *f) gether_resume(&ecm->port); } +static int ecm_get_status(struct usb_function *f) +{ + return (f->func_wakeup_armed ? USB_INTRF_STAT_FUNC_RW : 0) | + USB_INTRF_STAT_FUNC_RW_CAP; +} + static void ecm_free(struct usb_function *f) { struct f_ecm *ecm; @@ -960,6 +966,7 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi) ecm->port.func.disable = ecm_disable; ecm->port.func.free_func = ecm_free; ecm->port.func.suspend = ecm_suspend; + ecm->port.func.get_status = ecm_get_status; ecm->port.func.resume = ecm_resume; return &ecm->port.func; diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index 12e866fb311d..0a800ba53816 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -475,7 +475,7 @@ static void reply_ump_stream_ep_info(struct f_midi2_ep *ep) /* reply a UMP EP device info */ static void reply_ump_stream_ep_device(struct f_midi2_ep *ep) { - struct snd_ump_stream_msg_devince_info rep = { + struct snd_ump_stream_msg_device_info rep = { .type = UMP_MSG_TYPE_STREAM, .status = UMP_STREAM_MSG_STATUS_DEVICE_INFO, .manufacture_id = ep->info.manufacturer, diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index c7fdbc55fb0b..2957316fd3d0 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -1749,6 +1749,10 @@ static int __tegra_xudc_ep_disable(struct tegra_xudc_ep *ep) val = xudc_readl(xudc, CTRL); val &= ~CTRL_RUN; xudc_writel(xudc, val, CTRL); + + val = xudc_readl(xudc, ST); + if (val & ST_RC) + xudc_writel(xudc, ST_RC, ST); } dev_info(xudc->dev, "ep %u disabled\n", ep->index); diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c index a7c934404ebc..62318291f566 100644 --- a/drivers/usb/host/uhci-platform.c +++ b/drivers/usb/host/uhci-platform.c @@ -121,7 +121,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev) } /* Get and enable clock if any specified */ - uhci->clk = devm_clk_get(&pdev->dev, NULL); + uhci->clk = devm_clk_get_optional(&pdev->dev, NULL); if (IS_ERR(uhci->clk)) { ret = PTR_ERR(uhci->clk); goto err_rmr; diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index fd7895b24367..0d4ce5734165 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -823,6 +823,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) { dma_addr_t deq; union xhci_trb *evt; + enum evtreturn ret = EVT_DONE; u32 ctrl, portsc; bool update_erdp = false; @@ -909,6 +910,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) break; case TRB_TYPE(TRB_TRANSFER): dbc_handle_xfer_event(dbc, evt); + ret = EVT_XFER_DONE; break; default: break; @@ -927,7 +929,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) lo_hi_writeq(deq, &dbc->regs->erdp); } - return EVT_DONE; + return ret; } static void xhci_dbc_handle_events(struct work_struct *work) @@ -936,6 +938,7 @@ static void xhci_dbc_handle_events(struct work_struct *work) struct xhci_dbc *dbc; unsigned long flags; unsigned int poll_interval; + unsigned long busypoll_timelimit; dbc = container_of(to_delayed_work(work), struct xhci_dbc, event_work); poll_interval = dbc->poll_interval; @@ -954,11 +957,21 @@ static void xhci_dbc_handle_events(struct work_struct *work) dbc->driver->disconnect(dbc); break; case EVT_DONE: - /* set fast poll rate if there are pending data transfers */ + /* + * Set fast poll rate if there are pending out transfers, or + * a transfer was recently processed + */ + busypoll_timelimit = dbc->xfer_timestamp + + msecs_to_jiffies(DBC_XFER_INACTIVITY_TIMEOUT); + if (!list_empty(&dbc->eps[BULK_OUT].list_pending) || - !list_empty(&dbc->eps[BULK_IN].list_pending)) + time_is_after_jiffies(busypoll_timelimit)) poll_interval = 0; break; + case EVT_XFER_DONE: + dbc->xfer_timestamp = jiffies; + poll_interval = 0; + break; default: dev_info(dbc->dev, "stop handling dbc events\n"); return; diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h index 9dc8f4d8077c..47ac72c2286d 100644 --- a/drivers/usb/host/xhci-dbgcap.h +++ b/drivers/usb/host/xhci-dbgcap.h @@ -96,6 +96,7 @@ struct dbc_ep { #define DBC_WRITE_BUF_SIZE 8192 #define DBC_POLL_INTERVAL_DEFAULT 64 /* milliseconds */ #define DBC_POLL_INTERVAL_MAX 5000 /* milliseconds */ +#define DBC_XFER_INACTIVITY_TIMEOUT 10 /* milliseconds */ /* * Private structure for DbC hardware state: */ @@ -142,6 +143,7 @@ struct xhci_dbc { enum dbc_state state; struct delayed_work event_work; unsigned int poll_interval; /* ms */ + unsigned long xfer_timestamp; unsigned resume_required:1; struct dbc_ep eps[2]; @@ -187,6 +189,7 @@ struct dbc_request { enum evtreturn { EVT_ERR = -1, EVT_DONE, + EVT_XFER_DONE, EVT_GSER, EVT_DISC, }; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index b906bc2eea5f..423bf3649570 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -699,7 +699,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, int new_cycle; dma_addr_t addr; u64 hw_dequeue; - bool cycle_found = false; + bool hw_dequeue_found = false; bool td_last_trb_found = false; u32 trb_sct = 0; int ret; @@ -715,25 +715,24 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, hw_dequeue = xhci_get_hw_deq(xhci, dev, ep_index, stream_id); new_seg = ep_ring->deq_seg; new_deq = ep_ring->dequeue; - new_cycle = hw_dequeue & 0x1; + new_cycle = le32_to_cpu(td->end_trb->generic.field[3]) & TRB_CYCLE; /* - * We want to find the pointer, segment and cycle state of the new trb - * (the one after current TD's end_trb). We know the cycle state at - * hw_dequeue, so walk the ring until both hw_dequeue and end_trb are - * found. + * Walk the ring until both the next TRB and hw_dequeue are found (don't + * move hw_dequeue back if it went forward due to a HW bug). Cycle state + * is loaded from a known good TRB, track later toggles to maintain it. */ do { - if (!cycle_found && xhci_trb_virt_to_dma(new_seg, new_deq) + if (!hw_dequeue_found && xhci_trb_virt_to_dma(new_seg, new_deq) == (dma_addr_t)(hw_dequeue & ~0xf)) { - cycle_found = true; + hw_dequeue_found = true; if (td_last_trb_found) break; } if (new_deq == td->end_trb) td_last_trb_found = true; - if (cycle_found && trb_is_link(new_deq) && + if (td_last_trb_found && trb_is_link(new_deq) && link_trb_toggles_cycle(new_deq)) new_cycle ^= 0x1; @@ -745,7 +744,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, return -EINVAL; } - } while (!cycle_found || !td_last_trb_found); + } while (!hw_dequeue_found || !td_last_trb_found); /* Don't update the ring cycle state for the producer (us). */ addr = xhci_trb_virt_to_dma(new_seg, new_deq); diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index b5c362c2051d..0c7af44d4dae 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1364,6 +1364,7 @@ static void tegra_xhci_id_work(struct work_struct *work) tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl, tegra->otg_usb2_port); + pm_runtime_get_sync(tegra->dev); if (tegra->host_mode) { /* switch to host mode */ if (tegra->otg_usb3_port >= 0) { @@ -1393,6 +1394,7 @@ static void tegra_xhci_id_work(struct work_struct *work) } tegra_xhci_set_port_power(tegra, true, true); + pm_runtime_mark_last_busy(tegra->dev); } else { if (tegra->otg_usb3_port >= 0) @@ -1400,6 +1402,7 @@ static void tegra_xhci_id_work(struct work_struct *work) tegra_xhci_set_port_power(tegra, true, false); } + pm_runtime_put_autosuspend(tegra->dev); } #if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP) diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c index 75ac3c6aa92d..f5372dfa241a 100644 --- a/drivers/usb/misc/onboard_usb_dev.c +++ b/drivers/usb/misc/onboard_usb_dev.c @@ -569,8 +569,14 @@ static void onboard_dev_usbdev_disconnect(struct usb_device *udev) } static const struct usb_device_id onboard_dev_id_table[] = { - { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 HUB */ - { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6500) }, /* CYUSB330x 3.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6502) }, /* CYUSB330x 2.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6503) }, /* CYUSB33{0,1}x 2.0 HUB, Vendor Mode */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB331x 3.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB331x 2.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6507) }, /* CYUSB332x 2.0 HUB, Vendor Mode */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6508) }, /* CYUSB332x 3.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x650a) }, /* CYUSB332x 2.0 HUB */ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 HUB */ { USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 HUB */ { USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 HUB */ diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index a99db4e025cd..8adf6f954633 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5965,7 +5965,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, case SNK_TRY_WAIT_DEBOUNCE: if (!tcpm_port_is_sink(port)) { port->max_wait = 0; - tcpm_set_state(port, SRC_TRYWAIT, 0); + tcpm_set_state(port, SRC_TRYWAIT, PD_T_PD_DEBOUNCE); } break; case SRC_TRY_WAIT: diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 420af5139c70..8aae80b457d7 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) u8 cur = 0; int ret; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) schedule_work(&dp->work); ret = 0; err_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) u64 command; int ret = 0; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) schedule_work(&dp->work); out_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, int cmd = PD_VDO_CMD(header); int svdm_version; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); dev_warn(&p->dev, "firmware doesn't support alternate mode overriding\n"); - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return -EOPNOTSUPP; } svdm_version = typec_altmode_get_svdm_version(alt); if (svdm_version < 0) { - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return svdm_version; } @@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, break; } - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return 0; } @@ -296,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt) if (!dp) return; + cancel_work_sync(&dp->work); + dp->data.conf = 0; dp->data.status = 0; dp->initialized = false; diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index e8c7e9dc4930..01ce858a1a2b 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1923,6 +1923,40 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data) EXPORT_SYMBOL_GPL(ucsi_set_drvdata); /** + * ucsi_con_mutex_lock - Acquire the connector mutex + * @con: The connector interface to lock + * + * Returns true on success, false if the connector is disconnected + */ +bool ucsi_con_mutex_lock(struct ucsi_connector *con) +{ + bool mutex_locked = false; + bool connected = true; + + while (connected && !mutex_locked) { + mutex_locked = mutex_trylock(&con->lock) != 0; + connected = UCSI_CONSTAT(con, CONNECTED); + if (connected && !mutex_locked) + msleep(20); + } + + connected = connected && con->partner; + if (!connected && mutex_locked) + mutex_unlock(&con->lock); + + return connected; +} + +/** + * ucsi_con_mutex_unlock - Release the connector mutex + * @con: The connector interface to unlock + */ +void ucsi_con_mutex_unlock(struct ucsi_connector *con) +{ + mutex_unlock(&con->lock); +} + +/** * ucsi_create - Allocate UCSI instance * @dev: Device interface to the PPM (Platform Policy Manager) * @ops: I/O routines diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 3a2c1762bec1..9c5278a0c5d4 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -94,6 +94,8 @@ int ucsi_register(struct ucsi *ucsi); void ucsi_unregister(struct ucsi *ucsi); void *ucsi_get_drvdata(struct ucsi *ucsi); void ucsi_set_drvdata(struct ucsi *ucsi, void *data); +bool ucsi_con_mutex_lock(struct ucsi_connector *con); +void ucsi_con_mutex_unlock(struct ucsi_connector *con); void ucsi_connector_change(struct ucsi *ucsi, u8 num); diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 35f9046af315..6328c3a05bcd 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1646,14 +1646,14 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, { struct vm_area_struct *vma = vmf->vma; struct vfio_pci_core_device *vdev = vma->vm_private_data; - unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff; + unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1); + unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; + unsigned long pfn = vma_to_pfn(vma) + pgoff; vm_fault_t ret = VM_FAULT_SIGBUS; - pfn = vma_to_pfn(vma) + pgoff; - - if (order && (pfn & ((1 << order) - 1) || - vmf->address & ((PAGE_SIZE << order) - 1) || - vmf->address + (PAGE_SIZE << order) > vma->vm_end)) { + if (order && (addr < vma->vm_start || + addr + (PAGE_SIZE << order) > vma->vm_end || + pfn & ((1 << order) - 1))) { ret = VM_FAULT_FALLBACK; goto out; } diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 1f65795cf5d7..ef56a2500ed6 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -217,6 +217,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * buffering it. */ if (dma_capable(dev, dev_addr, size, true) && + !dma_kmalloc_needs_bounce(dev, size, dir) && !range_straddles_page_boundary(phys, size) && !xen_arch_need_swiotlb(dev, phys, dev_addr) && !is_swiotlb_force_bounce(dev)) diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 13821e7e825e..9ac0427724a3 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -77,6 +77,7 @@ enum xb_req_state { struct xb_req_data { struct list_head list; wait_queue_head_t wq; + struct kref kref; struct xsd_sockmsg msg; uint32_t caller_req_id; enum xsd_sockmsg_type type; @@ -103,6 +104,7 @@ int xb_init_comms(void); void xb_deinit_comms(void); int xs_watch_msg(struct xs_watch_event *event); void xs_request_exit(struct xb_req_data *req); +void xs_free_req(struct kref *kref); int xenbus_match(struct device *_dev, const struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index e5fda0256feb..82df2da1b880 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,8 +309,8 @@ static int process_msg(void) virt_wmb(); req->state = xb_req_state_got_reply; req->cb(req); - } else - kfree(req); + } + kref_put(&req->kref, xs_free_req); } mutex_unlock(&xs_response_mutex); @@ -386,14 +386,13 @@ static int process_writes(void) state.req->msg.type = XS_ERROR; state.req->err = err; list_del(&state.req->list); - if (state.req->state == xb_req_state_aborted) - kfree(state.req); - else { + if (state.req->state != xb_req_state_aborted) { /* write err, then update state */ virt_wmb(); state.req->state = xb_req_state_got_reply; wake_up(&state.req->wq); } + kref_put(&state.req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 46f8916597e5..f5c21ba64df5 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req) mutex_unlock(&u->reply_mutex); kfree(req->body); - kfree(req); + kref_put(&req->kref, xs_free_req); kref_put(&u->kref, xenbus_file_free); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 6d32ffb01136..86fe6e779056 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -966,9 +966,15 @@ static int __init xenbus_init(void) if (xen_pv_domain()) xen_store_domain_type = XS_PV; if (xen_hvm_domain()) + { xen_store_domain_type = XS_HVM; - if (xen_hvm_domain() && xen_initial_domain()) - xen_store_domain_type = XS_LOCAL; + err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); + if (err) + goto out_error; + xen_store_evtchn = (int)v; + if (!v && xen_initial_domain()) + xen_store_domain_type = XS_LOCAL; + } if (xen_pv_domain() && !xen_start_info->store_evtchn) xen_store_domain_type = XS_LOCAL; if (xen_pv_domain() && xen_start_info->store_evtchn) @@ -987,10 +993,6 @@ static int __init xenbus_init(void) xen_store_interface = gfn_to_virt(xen_store_gfn); break; case XS_HVM: - err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); - if (err) - goto out_error; - xen_store_evtchn = (int)v; err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); if (err) goto out_error; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index d32c726f7a12..dcf9182c8451 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -112,6 +112,12 @@ static void xs_suspend_exit(void) wake_up_all(&xs_state_enter_wq); } +void xs_free_req(struct kref *kref) +{ + struct xb_req_data *req = container_of(kref, struct xb_req_data, kref); + kfree(req); +} + static uint32_t xs_request_enter(struct xb_req_data *req) { uint32_t rq_id; @@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); + /* + * Take 2nd ref. One for this thread, and the second for the + * xenbus_thread. + */ + kref_get(&req->kref); + mutex_lock(&xb_write_mutex); list_add_tail(&req->list, &xb_write_list); notify = list_is_singular(&xb_write_list); @@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg) if (req->state == xb_req_state_queued || req->state == xb_req_state_wait_reply) req->state = xb_req_state_aborted; - else - kfree(req); + + kref_put(&req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); return ret; @@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par) req->cb = xenbus_dev_queue_reply; req->par = par; req->user_req = true; + kref_init(&req->kref); xs_send(req, msg); @@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; req->user_req = false; + kref_init(&req->kref); msg.req_id = 0; msg.tx_id = t.id; diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 32619d146cbc..1286d96a29bc 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -164,4 +164,5 @@ const struct address_space_operations v9fs_addr_operations = { .invalidate_folio = netfs_invalidate_folio, .direct_IO = noop_direct_IO, .writepages = netfs_writepages, + .migrate_folio = filemap_migrate_folio, }; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 9e7b1fe82c27..bfb69e066672 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -943,7 +943,7 @@ static struct dentry *afs_lookup_atsys(struct inode *dir, struct dentry *dentry) } strcpy(p, name); - ret = lookup_one_len(buf, dentry->d_parent, len); + ret = lookup_noperm(&QSTR(buf), dentry->d_parent); if (IS_ERR(ret) || d_is_positive(ret)) goto out_s; dput(ret); diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index a1e581946b93..0b80eb93fa40 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -113,16 +113,14 @@ int afs_sillyrename(struct afs_vnode *dvnode, struct afs_vnode *vnode, sdentry = NULL; do { - int slen; - dput(sdentry); sillycounter++; /* Create a silly name. Note that the ".__afs" prefix is * understood by the salvager and must not be changed. */ - slen = scnprintf(silly, sizeof(silly), ".__afs%04X", sillycounter); - sdentry = lookup_one_len(silly, dentry->d_parent, slen); + scnprintf(silly, sizeof(silly), ".__afs%04X", sillycounter); + sdentry = lookup_noperm(&QSTR(silly), dentry->d_parent); /* N.B. Better to return EBUSY here ... it could be dangerous * to delete the file while it's in use. diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 583ac81669c2..e51e7d88980a 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -24,10 +24,51 @@ #include <linux/uaccess.h> +#include "internal.h" + static struct vfsmount *anon_inode_mnt __ro_after_init; static struct inode *anon_inode_inode __ro_after_init; /* + * User space expects anonymous inodes to have no file type in st_mode. + * + * In particular, 'lsof' has this legacy logic: + * + * type = s->st_mode & S_IFMT; + * switch (type) { + * ... + * case 0: + * if (!strcmp(p, "anon_inode")) + * Lf->ntype = Ntype = N_ANON_INODE; + * + * to detect our old anon_inode logic. + * + * Rather than mess with our internal sane inode data, just fix it + * up here in getattr() by masking off the format bits. + */ +int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + + generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); + stat->mode &= ~S_IFMT; + return 0; +} + +int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + return -EOPNOTSUPP; +} + +static const struct inode_operations anon_inode_operations = { + .getattr = anon_inode_getattr, + .setattr = anon_inode_setattr, +}; + +/* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) @@ -45,6 +86,8 @@ static int anon_inodefs_init_fs_context(struct fs_context *fc) struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; + fc->s_iflags |= SB_I_NOEXEC; + fc->s_iflags |= SB_I_NODEV; ctx->dops = &anon_inodefs_dentry_operations; return 0; } @@ -66,6 +109,7 @@ static struct inode *anon_inode_make_secure_inode( if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; + inode->i_op = &anon_inode_operations; error = security_inode_init_security_anon(inode, &QSTR(name), context_inode); if (error) { @@ -313,6 +357,7 @@ static int __init anon_inode_init(void) anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); + anon_inode_inode->i_op = &anon_inode_operations; return 0; } diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index c5a6aae12d2c..d8dd150cbd74 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -459,7 +459,8 @@ static int autofs_dev_ioctl_timeout(struct file *fp, "the parent autofs mount timeout which could " "prevent shutdown\n"); - dentry = try_lookup_one_len(param->path, base, path_len); + dentry = try_lookup_noperm(&QSTR_LEN(param->path, path_len), + base); if (IS_ERR_OR_NULL(dentry)) return dentry ? PTR_ERR(dentry) : -ENOENT; ino = autofs_dentry_ino(dentry); diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index effafc3e0ced..7ec022e9361a 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -1422,11 +1422,31 @@ alloc_done: wp->sectors_free = UINT_MAX; - open_bucket_for_each(c, &wp->ptrs, ob, i) + open_bucket_for_each(c, &wp->ptrs, ob, i) { + /* + * Ensure proper write alignment - either due to misaligned + * bucket sizes (from buggy bcachefs-tools), or writes that mix + * logical/physical alignment: + */ + struct bch_dev *ca = ob_dev(c, ob); + u64 offset = bucket_to_sector(ca, ob->bucket) + + ca->mi.bucket_size - + ob->sectors_free; + unsigned align = round_up(offset, block_sectors(c)) - offset; + + ob->sectors_free = max_t(int, 0, ob->sectors_free - align); + wp->sectors_free = min(wp->sectors_free, ob->sectors_free); + } wp->sectors_free = rounddown(wp->sectors_free, block_sectors(c)); + /* Did alignment use up space in an open_bucket? */ + if (unlikely(!wp->sectors_free)) { + bch2_alloc_sectors_done(c, wp); + goto retry; + } + BUG_ON(!wp->sectors_free || wp->sectors_free == UINT_MAX); return 0; diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index ff26bb515150..5f195d2280a4 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -192,7 +192,8 @@ static inline int bch2_backpointers_maybe_flush(struct btree_trans *trans, static int backpointer_target_not_found(struct btree_trans *trans, struct bkey_s_c_backpointer bp, struct bkey_s_c target_k, - struct bkey_buf *last_flushed) + struct bkey_buf *last_flushed, + bool commit) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; @@ -228,18 +229,77 @@ static int backpointer_target_not_found(struct btree_trans *trans, } if (fsck_err(trans, backpointer_to_missing_ptr, - "%s", buf.buf)) + "%s", buf.buf)) { ret = bch2_backpointer_del(trans, bp.k->p); + if (ret || !commit) + goto out; + + /* + * Normally, on transaction commit from inside a transaction, + * we'll return -BCH_ERR_transaction_restart_nested, since a + * transaction commit invalidates pointers given out by peek(). + * + * However, since we're updating a write buffer btree, if we + * return a transaction restart and loop we won't see that the + * backpointer has been deleted without an additional write + * buffer flush - and those are expensive. + * + * So we're relying on the caller immediately advancing to the + * next backpointer and starting a new transaction immediately + * after backpointer_get_key() returns NULL: + */ + ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + } +out: fsck_err: printbuf_exit(&buf); return ret; } -struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans, - struct bkey_s_c_backpointer bp, - struct btree_iter *iter, - unsigned iter_flags, - struct bkey_buf *last_flushed) +static struct btree *__bch2_backpointer_get_node(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, + struct btree_iter *iter, + struct bkey_buf *last_flushed, + bool commit) +{ + struct bch_fs *c = trans->c; + + BUG_ON(!bp.v->level); + + bch2_trans_node_iter_init(trans, iter, + bp.v->btree_id, + bp.v->pos, + 0, + bp.v->level - 1, + 0); + struct btree *b = bch2_btree_iter_peek_node(trans, iter); + if (IS_ERR_OR_NULL(b)) + goto err; + + BUG_ON(b->c.level != bp.v->level - 1); + + if (extent_matches_bp(c, bp.v->btree_id, bp.v->level, + bkey_i_to_s_c(&b->key), bp)) + return b; + + if (btree_node_will_make_reachable(b)) { + b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node); + } else { + int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key), + last_flushed, commit); + b = ret ? ERR_PTR(ret) : NULL; + } +err: + bch2_trans_iter_exit(trans, iter); + return b; +} + +static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, + struct btree_iter *iter, + unsigned iter_flags, + struct bkey_buf *last_flushed, + bool commit) { struct bch_fs *c = trans->c; @@ -277,10 +337,10 @@ struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans, bch2_trans_iter_exit(trans, iter); if (!bp.v->level) { - int ret = backpointer_target_not_found(trans, bp, k, last_flushed); + int ret = backpointer_target_not_found(trans, bp, k, last_flushed, commit); return ret ? bkey_s_c_err(ret) : bkey_s_c_null; } else { - struct btree *b = bch2_backpointer_get_node(trans, bp, iter, last_flushed); + struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit); if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node)) return bkey_s_c_null; if (IS_ERR_OR_NULL(b)) @@ -295,35 +355,16 @@ struct btree *bch2_backpointer_get_node(struct btree_trans *trans, struct btree_iter *iter, struct bkey_buf *last_flushed) { - struct bch_fs *c = trans->c; - - BUG_ON(!bp.v->level); - - bch2_trans_node_iter_init(trans, iter, - bp.v->btree_id, - bp.v->pos, - 0, - bp.v->level - 1, - 0); - struct btree *b = bch2_btree_iter_peek_node(trans, iter); - if (IS_ERR_OR_NULL(b)) - goto err; - - BUG_ON(b->c.level != bp.v->level - 1); - - if (extent_matches_bp(c, bp.v->btree_id, bp.v->level, - bkey_i_to_s_c(&b->key), bp)) - return b; + return __bch2_backpointer_get_node(trans, bp, iter, last_flushed, true); +} - if (btree_node_will_make_reachable(b)) { - b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node); - } else { - int ret = backpointer_target_not_found(trans, bp, bkey_i_to_s_c(&b->key), last_flushed); - b = ret ? ERR_PTR(ret) : NULL; - } -err: - bch2_trans_iter_exit(trans, iter); - return b; +struct bkey_s_c bch2_backpointer_get_key(struct btree_trans *trans, + struct bkey_s_c_backpointer bp, + struct btree_iter *iter, + unsigned iter_flags, + struct bkey_buf *last_flushed) +{ + return __bch2_backpointer_get_key(trans, bp, iter, iter_flags, last_flushed, true); } static int bch2_check_backpointer_has_valid_bucket(struct btree_trans *trans, struct bkey_s_c k, @@ -521,7 +562,7 @@ check_existing_bp: struct bkey_s_c_backpointer other_bp = bkey_s_c_to_backpointer(bp_k); struct bkey_s_c other_extent = - bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL); + __bch2_backpointer_get_key(trans, other_bp, &other_extent_iter, 0, NULL, false); ret = bkey_err(other_extent); if (ret == -BCH_ERR_backpointer_to_overwritten_btree_node) ret = 0; diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 9b80201c7982..899891295797 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -852,7 +852,6 @@ out: b->sib_u64s[1] = 0; b->whiteout_u64s = 0; bch2_btree_keys_init(b); - set_btree_node_accessed(b); bch2_time_stats_update(&c->times[BCH_TIME_btree_node_mem_alloc], start_time); @@ -1286,6 +1285,10 @@ lock_node: six_unlock_read(&b->c.lock); goto retry; } + + /* avoid atomic set bit if it's not needed: */ + if (!btree_node_accessed(b)) + set_btree_node_accessed(b); } /* XXX: waiting on IO with btree locks held: */ @@ -1301,10 +1304,6 @@ lock_node: prefetch(p + L1_CACHE_BYTES * 2); } - /* avoid atomic set bit if it's not needed: */ - if (!btree_node_accessed(b)) - set_btree_node_accessed(b); - if (unlikely(btree_node_read_error(b))) { six_unlock_read(&b->c.lock); b = ERR_PTR(-BCH_ERR_btree_node_read_err_cached); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 5fd4a58d2ad2..60782f3e5aec 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -41,6 +41,7 @@ void bch2_btree_node_io_unlock(struct btree *b) clear_btree_node_write_in_flight_inner(b); clear_btree_node_write_in_flight(b); + smp_mb__after_atomic(); wake_up_bit(&b->flags, BTREE_NODE_write_in_flight); } @@ -1400,6 +1401,7 @@ start: printbuf_exit(&buf); clear_btree_node_read_in_flight(b); + smp_mb__after_atomic(); wake_up_bit(&b->flags, BTREE_NODE_read_in_flight); } @@ -1595,6 +1597,7 @@ fsck_err: printbuf_exit(&buf); clear_btree_node_read_in_flight(b); + smp_mb__after_atomic(); wake_up_bit(&b->flags, BTREE_NODE_read_in_flight); } @@ -1721,6 +1724,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b, set_btree_node_read_error(b); bch2_btree_lost_data(c, b->c.btree_id); clear_btree_node_read_in_flight(b); + smp_mb__after_atomic(); wake_up_bit(&b->flags, BTREE_NODE_read_in_flight); printbuf_exit(&buf); return; @@ -2061,8 +2065,10 @@ static void __btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start if (new & (1U << BTREE_NODE_write_in_flight)) __bch2_btree_node_write(c, b, BTREE_WRITE_ALREADY_STARTED|type); - else + else { + smp_mb__after_atomic(); wake_up_bit(&b->flags, BTREE_NODE_write_in_flight); + } } static void btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start_time) @@ -2175,6 +2181,7 @@ static void btree_node_write_endio(struct bio *bio) } clear_btree_node_write_in_flight_inner(b); + smp_mb__after_atomic(); wake_up_bit(&b->flags, BTREE_NODE_write_in_flight_inner); INIT_WORK(&wb->work, btree_node_write_work); queue_work(c->btree_io_complete_wq, &wb->work); diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 59fa527ac685..ac5f2046550d 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -1162,7 +1162,7 @@ int bch2_btree_path_traverse_one(struct btree_trans *trans, } if (path->cached) { - ret = bch2_btree_path_traverse_cached(trans, path, flags); + ret = bch2_btree_path_traverse_cached(trans, path_idx, flags); goto out; } @@ -1971,6 +1971,12 @@ struct btree *bch2_btree_iter_next_node(struct btree_trans *trans, struct btree_ return NULL; } + /* + * We don't correctly handle nodes with extra intent locks here: + * downgrade so we don't violate locking invariants + */ + bch2_btree_path_downgrade(trans, path); + if (!bch2_btree_node_relock(trans, path, path->level + 1)) { __bch2_btree_path_unlock(trans, path); path->l[path->level].b = ERR_PTR(-BCH_ERR_no_btree_node_relock); @@ -2743,7 +2749,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre ret = trans_maybe_inject_restart(trans, _RET_IP_); if (unlikely(ret)) { k = bkey_s_c_err(ret); - goto out_no_locked; + goto out; } /* extents can't span inode numbers: */ @@ -2763,13 +2769,15 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (unlikely(ret)) { k = bkey_s_c_err(ret); - goto out_no_locked; + goto out; } struct btree_path *path = btree_iter_path(trans, iter); if (unlikely(!btree_path_node(path, path->level))) return bkey_s_c_null; + btree_path_set_should_be_locked(trans, path); + if ((iter->flags & BTREE_ITER_cached) || !(iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots))) { k = bkey_s_c_null; @@ -2790,12 +2798,12 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre if (!bkey_err(k)) iter->k = *k.k; /* We're not returning a key from iter->path: */ - goto out_no_locked; + goto out; } - k = bch2_btree_path_peek_slot(trans->paths + iter->path, &iter->k); + k = bch2_btree_path_peek_slot(btree_iter_path(trans, iter), &iter->k); if (unlikely(!k.k)) - goto out_no_locked; + goto out; if (unlikely(k.k->type == KEY_TYPE_whiteout && (iter->flags & BTREE_ITER_filter_snapshots) && @@ -2833,7 +2841,7 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre } if (unlikely(bkey_err(k))) - goto out_no_locked; + goto out; next = k.k ? bkey_start_pos(k.k) : POS_MAX; @@ -2855,8 +2863,6 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre } } out: - btree_path_set_should_be_locked(trans, btree_iter_path(trans, iter)); -out_no_locked: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(trans, iter); ret = bch2_btree_iter_verify_ret(trans, iter, k); diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 2b186584a291..669825f89cdd 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -301,9 +301,11 @@ static noinline_for_stack void do_trace_key_cache_fill(struct btree_trans *trans } static noinline int btree_key_cache_fill(struct btree_trans *trans, - struct btree_path *ck_path, + btree_path_idx_t ck_path_idx, unsigned flags) { + struct btree_path *ck_path = trans->paths + ck_path_idx; + if (flags & BTREE_ITER_cached_nofill) { ck_path->l[0].b = NULL; return 0; @@ -325,6 +327,7 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, goto err; /* Recheck after btree lookup, before allocating: */ + ck_path = trans->paths + ck_path_idx; ret = bch2_btree_key_cache_find(c, ck_path->btree_id, ck_path->pos) ? -EEXIST : 0; if (unlikely(ret)) goto out; @@ -344,10 +347,11 @@ err: } static inline int btree_path_traverse_cached_fast(struct btree_trans *trans, - struct btree_path *path) + btree_path_idx_t path_idx) { struct bch_fs *c = trans->c; struct bkey_cached *ck; + struct btree_path *path = trans->paths + path_idx; retry: ck = bch2_btree_key_cache_find(c, path->btree_id, path->pos); if (!ck) @@ -373,27 +377,32 @@ retry: return 0; } -int bch2_btree_path_traverse_cached(struct btree_trans *trans, struct btree_path *path, +int bch2_btree_path_traverse_cached(struct btree_trans *trans, + btree_path_idx_t path_idx, unsigned flags) { - EBUG_ON(path->level); - - path->l[1].b = NULL; + EBUG_ON(trans->paths[path_idx].level); int ret; do { - ret = btree_path_traverse_cached_fast(trans, path); + ret = btree_path_traverse_cached_fast(trans, path_idx); if (unlikely(ret == -ENOENT)) - ret = btree_key_cache_fill(trans, path, flags); + ret = btree_key_cache_fill(trans, path_idx, flags); } while (ret == -EEXIST); + struct btree_path *path = trans->paths + path_idx; + if (unlikely(ret)) { path->uptodate = BTREE_ITER_NEED_TRAVERSE; if (!bch2_err_matches(ret, BCH_ERR_transaction_restart)) { btree_node_unlock(trans, path, 0); path->l[0].b = ERR_PTR(ret); } + } else { + BUG_ON(path->uptodate); + BUG_ON(!path->nodes_locked); } + return ret; } diff --git a/fs/bcachefs/btree_key_cache.h b/fs/bcachefs/btree_key_cache.h index 51d6289b8dee..82d8c72512a9 100644 --- a/fs/bcachefs/btree_key_cache.h +++ b/fs/bcachefs/btree_key_cache.h @@ -40,8 +40,7 @@ int bch2_btree_key_cache_journal_flush(struct journal *, struct bkey_cached * bch2_btree_key_cache_find(struct bch_fs *, enum btree_id, struct bpos); -int bch2_btree_path_traverse_cached(struct btree_trans *, struct btree_path *, - unsigned); +int bch2_btree_path_traverse_cached(struct btree_trans *, btree_path_idx_t, unsigned); bool bch2_btree_insert_key_cached(struct btree_trans *, unsigned, struct btree_insert_entry *); diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index 8d75b27a1418..af1532de4a37 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -44,6 +44,7 @@ static inline void bucket_unlock(struct bucket *b) BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte); clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock); + smp_mb__after_atomic(); wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR); } diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index 8a680e52c1ed..a51195088227 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -288,6 +288,7 @@ static void dirent_init_casefolded_name(struct bkey_i_dirent *dirent, } static struct bkey_i_dirent *dirent_create_key(struct btree_trans *trans, + const struct bch_hash_info *hash_info, subvol_inum dir, u8 type, const struct qstr *name, @@ -295,10 +296,19 @@ static struct bkey_i_dirent *dirent_create_key(struct btree_trans *trans, u64 dst) { struct bkey_i_dirent *dirent; + struct qstr _cf_name; if (name->len > BCH_NAME_MAX) return ERR_PTR(-ENAMETOOLONG); + if (hash_info->cf_encoding && !cf_name) { + int ret = bch2_casefold(trans, hash_info, name, &_cf_name); + if (ret) + return ERR_PTR(ret); + + cf_name = &_cf_name; + } + dirent = dirent_alloc_key(trans, dir, type, name->len, cf_name ? cf_name->len : 0, dst); if (IS_ERR(dirent)) return dirent; @@ -324,7 +334,7 @@ int bch2_dirent_create_snapshot(struct btree_trans *trans, struct bkey_i_dirent *dirent; int ret; - dirent = dirent_create_key(trans, dir_inum, type, name, NULL, dst_inum); + dirent = dirent_create_key(trans, hash_info, dir_inum, type, name, NULL, dst_inum); ret = PTR_ERR_OR_ZERO(dirent); if (ret) return ret; @@ -333,8 +343,7 @@ int bch2_dirent_create_snapshot(struct btree_trans *trans, dirent->k.p.snapshot = snapshot; ret = bch2_hash_set_in_snapshot(trans, bch2_dirent_hash_desc, hash_info, - dir_inum, snapshot, &dirent->k_i, - flags|BTREE_UPDATE_internal_snapshot_node); + dir_inum, snapshot, &dirent->k_i, flags); *dir_offset = dirent->k.p.offset; return ret; @@ -344,28 +353,16 @@ int bch2_dirent_create(struct btree_trans *trans, subvol_inum dir, const struct bch_hash_info *hash_info, u8 type, const struct qstr *name, u64 dst_inum, u64 *dir_offset, - u64 *i_size, enum btree_iter_update_trigger_flags flags) { struct bkey_i_dirent *dirent; int ret; - if (hash_info->cf_encoding) { - struct qstr cf_name; - ret = bch2_casefold(trans, hash_info, name, &cf_name); - if (ret) - return ret; - dirent = dirent_create_key(trans, dir, type, name, &cf_name, dst_inum); - } else { - dirent = dirent_create_key(trans, dir, type, name, NULL, dst_inum); - } - + dirent = dirent_create_key(trans, hash_info, dir, type, name, NULL, dst_inum); ret = PTR_ERR_OR_ZERO(dirent); if (ret) return ret; - *i_size += bkey_bytes(&dirent->k); - ret = bch2_hash_set(trans, bch2_dirent_hash_desc, hash_info, dir, &dirent->k_i, flags); *dir_offset = dirent->k.p.offset; @@ -466,7 +463,7 @@ int bch2_dirent_rename(struct btree_trans *trans, *src_offset = dst_iter.pos.offset; /* Create new dst key: */ - new_dst = dirent_create_key(trans, dst_dir, 0, dst_name, + new_dst = dirent_create_key(trans, dst_hash, dst_dir, 0, dst_name, dst_hash->cf_encoding ? &dst_name_lookup : NULL, 0); ret = PTR_ERR_OR_ZERO(new_dst); if (ret) @@ -477,7 +474,7 @@ int bch2_dirent_rename(struct btree_trans *trans, /* Create new src key: */ if (mode == BCH_RENAME_EXCHANGE) { - new_src = dirent_create_key(trans, src_dir, 0, src_name, + new_src = dirent_create_key(trans, src_hash, src_dir, 0, src_name, src_hash->cf_encoding ? &src_name_lookup : NULL, 0); ret = PTR_ERR_OR_ZERO(new_src); if (ret) diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index 9838a7ba7ed1..d3e7ae669575 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -65,7 +65,7 @@ int bch2_dirent_create_snapshot(struct btree_trans *, u32, u64, u32, enum btree_iter_update_trigger_flags); int bch2_dirent_create(struct btree_trans *, subvol_inum, const struct bch_hash_info *, u8, - const struct qstr *, u64, u64 *, u64 *, + const struct qstr *, u64, u64 *, enum btree_iter_update_trigger_flags); static inline unsigned vfs_d_type(unsigned type) diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c index b007319b72e9..1f0422bfae35 100644 --- a/fs/bcachefs/disk_accounting.c +++ b/fs/bcachefs/disk_accounting.c @@ -376,6 +376,19 @@ int bch2_accounting_mem_insert(struct bch_fs *c, struct bkey_s_c_accounting a, return ret; } +int bch2_accounting_mem_insert_locked(struct bch_fs *c, struct bkey_s_c_accounting a, + enum bch_accounting_mode mode) +{ + struct bch_replicas_padded r; + + if (mode != BCH_ACCOUNTING_read && + accounting_to_replicas(&r.e, a.k->p) && + !bch2_replicas_marked_locked(c, &r.e)) + return -BCH_ERR_btree_insert_need_mark_replicas; + + return __bch2_accounting_mem_insert(c, a); +} + static bool accounting_mem_entry_is_zero(struct accounting_mem_entry *e) { for (unsigned i = 0; i < e->nr_counters; i++) @@ -583,7 +596,7 @@ int bch2_gc_accounting_done(struct bch_fs *c) accounting_key_init(&k_i.k, &acc_k, src_v, nr); bch2_accounting_mem_mod_locked(trans, bkey_i_to_s_c_accounting(&k_i.k), - BCH_ACCOUNTING_normal); + BCH_ACCOUNTING_normal, true); preempt_disable(); struct bch_fs_usage_base *dst = this_cpu_ptr(c->usage); @@ -612,7 +625,7 @@ static int accounting_read_key(struct btree_trans *trans, struct bkey_s_c k) percpu_down_read(&c->mark_lock); int ret = bch2_accounting_mem_mod_locked(trans, bkey_s_c_to_accounting(k), - BCH_ACCOUNTING_read); + BCH_ACCOUNTING_read, false); percpu_up_read(&c->mark_lock); return ret; } diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index abb1f6206fe9..d557b99b3c0a 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -136,6 +136,7 @@ enum bch_accounting_mode { }; int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode); +int bch2_accounting_mem_insert_locked(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode); void bch2_accounting_mem_gc(struct bch_fs *); static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc) @@ -150,7 +151,8 @@ static inline bool bch2_accounting_is_mem(struct disk_accounting_pos acc) */ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, struct bkey_s_c_accounting a, - enum bch_accounting_mode mode) + enum bch_accounting_mode mode, + bool write_locked) { struct bch_fs *c = trans->c; struct bch_accounting_mem *acc = &c->accounting; @@ -189,7 +191,11 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, while ((idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), accounting_pos_cmp, &a.k->p)) >= acc->k.nr) { - int ret = bch2_accounting_mem_insert(c, a, mode); + int ret = 0; + if (unlikely(write_locked)) + ret = bch2_accounting_mem_insert_locked(c, a, mode); + else + ret = bch2_accounting_mem_insert(c, a, mode); if (ret) return ret; } @@ -206,7 +212,7 @@ static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans, static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc) { percpu_down_read(&trans->c->mark_lock); - int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal); + int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal, false); percpu_up_read(&trans->c->mark_lock); return ret; } @@ -259,7 +265,7 @@ static inline int bch2_accounting_trans_commit_hook(struct btree_trans *trans, EBUG_ON(bversion_zero(a->k.bversion)); return likely(!(commit_flags & BCH_TRANS_COMMIT_skip_accounting_apply)) - ? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal) + ? bch2_accounting_mem_mod_locked(trans, accounting_i_to_s_c(a), BCH_ACCOUNTING_normal, false) : 0; } @@ -271,7 +277,7 @@ static inline void bch2_accounting_trans_commit_revert(struct btree_trans *trans struct bkey_s_accounting a = accounting_i_to_s(a_i); bch2_accounting_neg(a); - bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal); + bch2_accounting_mem_mod_locked(trans, a.c, BCH_ACCOUNTING_normal, false); bch2_accounting_neg(a); } } diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index fff58b78327c..c6cb26981923 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -507,20 +507,14 @@ static const struct bch_extent_ptr *bkey_matches_stripe(struct bch_stripe *s, static bool extent_has_stripe_ptr(struct bkey_s_c k, u64 idx) { - switch (k.k->type) { - case KEY_TYPE_extent: { - struct bkey_s_c_extent e = bkey_s_c_to_extent(k); - const union bch_extent_entry *entry; - - extent_for_each_entry(e, entry) - if (extent_entry_type(entry) == - BCH_EXTENT_ENTRY_stripe_ptr && - entry->stripe_ptr.idx == idx) - return true; + struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); + const union bch_extent_entry *entry; - break; - } - } + bkey_extent_entry_for_each(ptrs, entry) + if (extent_entry_type(entry) == + BCH_EXTENT_ENTRY_stripe_ptr && + entry->stripe_ptr.idx == idx) + return true; return false; } diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h index 62d27e04d763..51893e1ee874 100644 --- a/fs/bcachefs/ec.h +++ b/fs/bcachefs/ec.h @@ -160,6 +160,7 @@ static inline void gc_stripe_unlock(struct gc_stripe *s) BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte); clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &s->lock); + smp_mb__after_atomic(); wake_up_bit((void *) &s->lock, BUCKET_LOCK_BITNR); } diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index a615e4852ded..d9ebffa5b3a2 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -269,7 +269,7 @@ x(BCH_ERR_invalid_sb, invalid_sb_downgrade) \ x(BCH_ERR_invalid, invalid_bkey) \ x(BCH_ERR_operation_blocked, nocow_lock_blocked) \ - x(EIO, journal_shutdown) \ + x(EROFS, journal_shutdown) \ x(EIO, journal_flush_err) \ x(EIO, journal_write_err) \ x(EIO, btree_node_read_err) \ diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index dca2b8425cc0..e597fb9c9823 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -1056,8 +1056,9 @@ bch2_extent_has_ptr(struct bkey_s_c k1, struct extent_ptr_decoded p1, struct bke static bool want_cached_ptr(struct bch_fs *c, struct bch_io_opts *opts, struct bch_extent_ptr *ptr) { - if (!opts->promote_target || - !bch2_dev_in_target(c, ptr->dev, opts->promote_target)) + unsigned target = opts->promote_target ?: opts->foreground_target; + + if (target && !bch2_dev_in_target(c, ptr->dev, target)) return false; struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev); diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index e78a39e7e18f..9fe153183b36 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -380,13 +380,6 @@ out: \ /* Iterate over pointers in KEY_TYPE_extent: */ -#define extent_for_each_entry_from(_e, _entry, _start) \ - __bkey_extent_entry_for_each_from(_start, \ - extent_entry_last(_e), _entry) - -#define extent_for_each_entry(_e, _entry) \ - extent_for_each_entry_from(_e, _entry, (_e).v->start) - #define extent_ptr_next(_e, _ptr) \ __bkey_ptr_next(_ptr, extent_entry_last(_e)) diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c index e072900e6a5b..fbae9c1de746 100644 --- a/fs/bcachefs/fs-io-pagecache.c +++ b/fs/bcachefs/fs-io-pagecache.c @@ -605,10 +605,14 @@ vm_fault_t bch2_page_mkwrite(struct vm_fault *vmf) struct address_space *mapping = file->f_mapping; struct bch_fs *c = inode->v.i_sb->s_fs_info; struct bch2_folio_reservation res; - unsigned len; - loff_t isize; vm_fault_t ret; + loff_t file_offset = round_down(vmf->pgoff << PAGE_SHIFT, block_bytes(c)); + unsigned offset = file_offset - folio_pos(folio); + unsigned len = max(PAGE_SIZE, block_bytes(c)); + + BUG_ON(offset + len > folio_size(folio)); + bch2_folio_reservation_init(c, inode, &res); sb_start_pagefault(inode->v.i_sb); @@ -623,24 +627,24 @@ vm_fault_t bch2_page_mkwrite(struct vm_fault *vmf) bch2_pagecache_add_get(inode); folio_lock(folio); - isize = i_size_read(&inode->v); + u64 isize = i_size_read(&inode->v); - if (folio->mapping != mapping || folio_pos(folio) >= isize) { + if (folio->mapping != mapping || file_offset >= isize) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } - len = min_t(loff_t, folio_size(folio), isize - folio_pos(folio)); + len = min_t(unsigned, len, isize - file_offset); if (bch2_folio_set(c, inode_inum(inode), &folio, 1) ?: - bch2_folio_reservation_get(c, inode, folio, &res, 0, len)) { + bch2_folio_reservation_get(c, inode, folio, &res, offset, len)) { folio_unlock(folio); ret = VM_FAULT_SIGBUS; goto out; } - bch2_set_folio_dirty(c, inode, folio, &res, 0, len); + bch2_set_folio_dirty(c, inode, folio, &res, offset, len); bch2_folio_reservation_put(c, inode, &res); folio_wait_stable(folio); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 113db85b6ef9..47f1a64c5c8d 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1429,7 +1429,9 @@ static int bch2_next_fiemap_extent(struct btree_trans *trans, if (ret) goto err; - ret = bch2_next_fiemap_pagecache_extent(trans, inode, start, end, cur); + u64 pagecache_end = k.k ? max(start, bkey_start_offset(k.k)) : end; + + ret = bch2_next_fiemap_pagecache_extent(trans, inode, start, pagecache_end, cur); if (ret) goto err; @@ -1662,33 +1664,9 @@ static int fssetxattr_inode_update_fn(struct btree_trans *trans, return -EINVAL; if (s->casefold != bch2_inode_casefold(c, bi)) { -#ifdef CONFIG_UNICODE - int ret = 0; - /* Not supported on individual files. */ - if (!S_ISDIR(bi->bi_mode)) - return -EOPNOTSUPP; - - /* - * Make sure the dir is empty, as otherwise we'd need to - * rehash everything and update the dirent keys. - */ - ret = bch2_empty_dir_trans(trans, inode_inum(inode)); - if (ret < 0) - return ret; - - ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding); + int ret = bch2_inode_set_casefold(trans, inode_inum(inode), bi, s->casefold); if (ret) return ret; - - bch2_check_set_feature(c, BCH_FEATURE_casefolding); - - bi->bi_casefold = s->casefold + 1; - bi->bi_fields_set |= BIT(Inode_opt_casefold); - -#else - printk(KERN_ERR "Cannot use casefolding on a kernel without CONFIG_UNICODE\n"); - return -EOPNOTSUPP; -#endif } if (s->set_project) { @@ -2502,10 +2480,9 @@ static int bch2_fs_get_tree(struct fs_context *fc) bch2_opts_apply(&c->opts, opts); - /* - * need to initialise sb and set c->vfs_sb _before_ starting fs, - * for blk_holder_ops - */ + ret = bch2_fs_start(c); + if (ret) + goto err_stop_fs; sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c); ret = PTR_ERR_OR_ZERO(sb); @@ -2567,10 +2544,6 @@ got_sb: sb->s_shrink->seeks = 0; - ret = bch2_fs_start(c); - if (ret) - goto err_put_super; - #ifdef CONFIG_UNICODE sb->s_encoding = c->cf_encoding; #endif diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 7b25cedd3e40..aaf187085276 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -306,6 +306,7 @@ create_lostfound: &lostfound_str, lostfound->bi_inum, &lostfound->bi_dir_offset, + BTREE_UPDATE_internal_snapshot_node| STR_HASH_must_create) ?: bch2_inode_write_flags(trans, &lostfound_iter, lostfound, BTREE_UPDATE_internal_snapshot_node); @@ -431,6 +432,7 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * &name, inode->bi_subvol ?: inode->bi_inum, &inode->bi_dir_offset, + BTREE_UPDATE_internal_snapshot_node| STR_HASH_must_create); if (ret) { bch_err_msg(c, ret, "error creating dirent"); @@ -2188,6 +2190,41 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); + /* check casefold */ + if (fsck_err_on(d.v->d_casefold != !!hash_info->cf_encoding, + trans, dirent_casefold_mismatch, + "dirent casefold does not match dir casefold\n%s", + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), + buf.buf))) { + struct qstr name = bch2_dirent_get_name(d); + u32 subvol = d.v->d_type == DT_SUBVOL + ? d.v->d_parent_subvol + : 0; + u64 target = d.v->d_type == DT_SUBVOL + ? d.v->d_child_subvol + : d.v->d_inum; + u64 dir_offset; + + ret = bch2_hash_delete_at(trans, + bch2_dirent_hash_desc, hash_info, iter, + BTREE_UPDATE_internal_snapshot_node) ?: + bch2_dirent_create_snapshot(trans, subvol, + d.k->p.inode, d.k->p.snapshot, + hash_info, + d.v->d_type, + &name, + target, + &dir_offset, + BTREE_ITER_with_updates| + BTREE_UPDATE_internal_snapshot_node| + STR_HASH_must_create) ?: + bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); + + /* might need another check_dirents pass */ + goto out; + } + if (d.v->d_type == DT_SUBVOL) { ret = check_dirent_to_subvol(trans, iter, d); if (ret) @@ -2446,7 +2483,7 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, u32 parent = le32_to_cpu(s.v->fs_path_parent); if (darray_u32_has(&subvol_path, parent)) { - if (fsck_err(c, subvol_loop, "subvolume loop")) + if (fsck_err(trans, subvol_loop, "subvolume loop")) ret = reattach_subvol(trans, s); break; } diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index b51d98cf8a80..490b85841de9 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -14,6 +14,7 @@ #include "extent_update.h" #include "fs.h" #include "inode.h" +#include "namei.h" #include "opts.h" #include "str_hash.h" #include "snapshot.h" @@ -1204,6 +1205,41 @@ int bch2_inum_opts_get(struct btree_trans *trans, subvol_inum inum, struct bch_i return 0; } +int bch2_inode_set_casefold(struct btree_trans *trans, subvol_inum inum, + struct bch_inode_unpacked *bi, unsigned v) +{ + struct bch_fs *c = trans->c; + +#ifdef CONFIG_UNICODE + int ret = 0; + /* Not supported on individual files. */ + if (!S_ISDIR(bi->bi_mode)) + return -EOPNOTSUPP; + + /* + * Make sure the dir is empty, as otherwise we'd need to + * rehash everything and update the dirent keys. + */ + ret = bch2_empty_dir_trans(trans, inum); + if (ret < 0) + return ret; + + ret = bch2_request_incompat_feature(c, bcachefs_metadata_version_casefolding); + if (ret) + return ret; + + bch2_check_set_feature(c, BCH_FEATURE_casefolding); + + bi->bi_casefold = v + 1; + bi->bi_fields_set |= BIT(Inode_opt_casefold); + + return 0; +#else + bch_err(c, "Cannot use casefolding on a kernel without CONFIG_UNICODE"); + return -EOPNOTSUPP; +#endif +} + static noinline int __bch2_inode_rm_snapshot(struct btree_trans *trans, u64 inum, u32 snapshot) { struct bch_fs *c = trans->c; diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index c74af15b14f2..5cfba9e98966 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -292,7 +292,9 @@ static inline bool bch2_inode_should_have_single_bp(struct bch_inode_unpacked *i struct bch_opts bch2_inode_opts_to_opts(struct bch_inode_unpacked *); void bch2_inode_opts_get(struct bch_io_opts *, struct bch_fs *, struct bch_inode_unpacked *); -int bch2_inum_opts_get(struct btree_trans*, subvol_inum, struct bch_io_opts *); +int bch2_inum_opts_get(struct btree_trans *, subvol_inum, struct bch_io_opts *); +int bch2_inode_set_casefold(struct btree_trans *, subvol_inum, + struct bch_inode_unpacked *, unsigned); #include "rebalance.h" diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 63cdf885c9e2..ded18a94ed02 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -19,6 +19,7 @@ #include <linux/ioprio.h> #include <linux/string_choices.h> +#include <linux/sched/sysctl.h> void bch2_journal_pos_from_member_info_set(struct bch_fs *c) { @@ -1262,7 +1263,8 @@ int bch2_journal_read(struct bch_fs *c, degraded = true; } - closure_sync(&jlist.cl); + while (closure_sync_timeout(&jlist.cl, sysctl_hung_task_timeout_secs * HZ / 2)) + ; if (jlist.ret) return jlist.ret; diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index ea670c3c43d8..cc00b0fc40d8 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -17,6 +17,8 @@ #include <linux/kthread.h> #include <linux/sched/mm.h> +static bool __should_discard_bucket(struct journal *, struct journal_device *); + /* Free space calculations: */ static unsigned journal_space_from(struct journal_device *ja, @@ -203,8 +205,7 @@ void bch2_journal_space_available(struct journal *j) ja->bucket_seq[ja->dirty_idx_ondisk] < j->last_seq_ondisk) ja->dirty_idx_ondisk = (ja->dirty_idx_ondisk + 1) % ja->nr; - if (ja->discard_idx != ja->dirty_idx_ondisk) - can_discard = true; + can_discard |= __should_discard_bucket(j, ja); max_entry_size = min_t(unsigned, max_entry_size, ca->mi.bucket_size); nr_online++; @@ -264,12 +265,19 @@ out: /* Discards - last part of journal reclaim: */ -static bool should_discard_bucket(struct journal *j, struct journal_device *ja) +static bool __should_discard_bucket(struct journal *j, struct journal_device *ja) { - bool ret; + unsigned min_free = max(4, ja->nr / 8); + + return bch2_journal_dev_buckets_available(j, ja, journal_space_discarded) < + min_free && + ja->discard_idx != ja->dirty_idx_ondisk; +} +static bool should_discard_bucket(struct journal *j, struct journal_device *ja) +{ spin_lock(&j->lock); - ret = ja->discard_idx != ja->dirty_idx_ondisk; + bool ret = __should_discard_bucket(j, ja); spin_unlock(&j->lock); return ret; diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c index fc396b9fa754..dfdbb9259985 100644 --- a/fs/bcachefs/move.c +++ b/fs/bcachefs/move.c @@ -784,7 +784,8 @@ static int __bch2_move_data_phys(struct moving_context *ctxt, goto err; ret = bch2_btree_write_buffer_tryflush(trans); - bch_err_msg(c, ret, "flushing btree write buffer"); + if (!bch2_err_matches(ret, EROFS)) + bch_err_msg(c, ret, "flushing btree write buffer"); if (ret) goto err; diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c index 52c58c6d53d2..9136a9097789 100644 --- a/fs/bcachefs/namei.c +++ b/fs/bcachefs/namei.c @@ -158,7 +158,6 @@ int bch2_create_trans(struct btree_trans *trans, name, dir_target, &dir_offset, - &dir_u->bi_size, STR_HASH_must_create|BTREE_ITER_with_updates) ?: bch2_inode_write(trans, &dir_iter, dir_u); if (ret) @@ -225,7 +224,6 @@ int bch2_link_trans(struct btree_trans *trans, mode_to_type(inode_u->bi_mode), name, inum.inum, &dir_offset, - &dir_u->bi_size, STR_HASH_must_create); if (ret) goto err; diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c index 4ccdfc1f34aa..623273556aa9 100644 --- a/fs/bcachefs/rebalance.c +++ b/fs/bcachefs/rebalance.c @@ -309,7 +309,7 @@ static int bch2_bkey_clear_needs_rebalance(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { - if (!bch2_bkey_rebalance_opts(k)) + if (k.k->type == KEY_TYPE_reflink_v || !bch2_bkey_rebalance_opts(k)) return 0; struct bkey_i *n = bch2_bkey_make_mut(trans, iter, &k, 0); diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index 3b69a924086f..4036a20c6adc 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -209,6 +209,7 @@ enum bch_fsck_flags { x(subvol_to_missing_root, 188, 0) \ x(subvol_root_wrong_bi_subvol, 189, FSCK_AUTOFIX) \ x(bkey_in_missing_snapshot, 190, 0) \ + x(bkey_in_deleted_snapshot, 315, 0) \ x(inode_pos_inode_nonzero, 191, 0) \ x(inode_pos_blockdev_range, 192, 0) \ x(inode_alloc_cursor_inode_bad, 301, 0) \ @@ -216,6 +217,7 @@ enum bch_fsck_flags { x(inode_str_hash_invalid, 194, 0) \ x(inode_v3_fields_start_bad, 195, 0) \ x(inode_snapshot_mismatch, 196, 0) \ + x(snapshot_key_missing_inode_snapshot, 314, 0) \ x(inode_unlinked_but_clean, 197, 0) \ x(inode_unlinked_but_nlink_nonzero, 198, 0) \ x(inode_unlinked_and_not_open, 281, 0) \ @@ -237,6 +239,8 @@ enum bch_fsck_flags { x(inode_unreachable, 210, FSCK_AUTOFIX) \ x(inode_journal_seq_in_future, 299, FSCK_AUTOFIX) \ x(inode_i_sectors_underflow, 312, FSCK_AUTOFIX) \ + x(inode_has_case_insensitive_not_set, 316, FSCK_AUTOFIX) \ + x(inode_parent_has_case_insensitive_not_set, 317, FSCK_AUTOFIX) \ x(vfs_inode_i_blocks_underflow, 311, FSCK_AUTOFIX) \ x(vfs_inode_i_blocks_not_zero_at_truncate, 313, FSCK_AUTOFIX) \ x(deleted_inode_but_clean, 211, FSCK_AUTOFIX) \ @@ -262,6 +266,7 @@ enum bch_fsck_flags { x(dirent_to_overwritten_inode, 302, 0) \ x(dirent_to_missing_subvol, 230, 0) \ x(dirent_to_itself, 231, 0) \ + x(dirent_casefold_mismatch, 318, FSCK_AUTOFIX) \ x(quota_type_invalid, 232, 0) \ x(xattr_val_size_too_small, 233, 0) \ x(xattr_val_size_too_big, 234, 0) \ @@ -301,6 +306,7 @@ enum bch_fsck_flags { x(btree_ptr_v2_written_0, 268, 0) \ x(subvol_snapshot_bad, 269, 0) \ x(subvol_inode_bad, 270, 0) \ + x(subvol_missing, 308, FSCK_AUTOFIX) \ x(alloc_key_stripe_sectors_wrong, 271, FSCK_AUTOFIX) \ x(accounting_mismatch, 272, FSCK_AUTOFIX) \ x(accounting_replicas_not_marked, 273, 0) \ @@ -322,7 +328,7 @@ enum bch_fsck_flags { x(dirent_stray_data_after_cf_name, 305, 0) \ x(rebalance_work_incorrectly_set, 309, FSCK_AUTOFIX) \ x(rebalance_work_incorrectly_unset, 310, FSCK_AUTOFIX) \ - x(MAX, 314, 0) + x(MAX, 319, 0) enum bch_sb_error_id { #define x(t, n, ...) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 27943082c093..84a37d971ffd 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -377,6 +377,11 @@ void bch2_fs_read_only(struct bch_fs *c) bch_verbose(c, "marking filesystem clean"); bch2_fs_mark_clean(c); } else { + /* Make sure error counts/counters are persisted */ + mutex_lock(&c->sb_lock); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); + bch_verbose(c, "done going read-only, filesystem not clean"); } } diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c index dea73bc1cb51..314a24d15d4e 100644 --- a/fs/bcachefs/thread_with_file.c +++ b/fs/bcachefs/thread_with_file.c @@ -455,8 +455,10 @@ ssize_t bch2_stdio_redirect_vprintf(struct stdio_redirect *stdio, bool nonblocki struct stdio_buf *buf = &stdio->output; unsigned long flags; ssize_t ret; - again: + if (stdio->done) + return -EPIPE; + spin_lock_irqsave(&buf->lock, flags); ret = bch2_darray_vprintf(&buf->buf, GFP_NOWAIT, fmt, args); spin_unlock_irqrestore(&buf->lock, flags); diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index 651da52b2cbc..e6be32003f3b 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -473,6 +473,12 @@ static int inode_opt_set_fn(struct btree_trans *trans, { struct inode_opt_set *s = p; + if (s->id == Inode_opt_casefold) { + int ret = bch2_inode_set_casefold(trans, inode_inum(inode), bi, s->v); + if (ret) + return ret; + } + if (s->defined) bi->bi_fields_set |= 1U << s->id; else diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index db81570c9637..1d41ce477df5 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -17,6 +17,7 @@ #include <linux/writeback.h> #include <linux/uio.h> #include <linux/uaccess.h> +#include <linux/fs_context.h> #include "bfs.h" MODULE_AUTHOR("Tigran Aivazian <aivazian.tigran@gmail.com>"); @@ -305,7 +306,7 @@ void bfs_dump_imap(const char *prefix, struct super_block *s) #endif } -static int bfs_fill_super(struct super_block *s, void *data, int silent) +static int bfs_fill_super(struct super_block *s, struct fs_context *fc) { struct buffer_head *bh, *sbh; struct bfs_super_block *bfs_sb; @@ -314,6 +315,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) struct bfs_sb_info *info; int ret = -EINVAL; unsigned long i_sblock, i_eblock, i_eoff, s_size; + int silent = fc->sb_flags & SB_SILENT; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) @@ -446,18 +448,28 @@ out: return ret; } -static struct dentry *bfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int bfs_get_tree(struct fs_context *fc) { - return mount_bdev(fs_type, flags, dev_name, data, bfs_fill_super); + return get_tree_bdev(fc, bfs_fill_super); +} + +static const struct fs_context_operations bfs_context_ops = { + .get_tree = bfs_get_tree, +}; + +static int bfs_init_fs_context(struct fs_context *fc) +{ + fc->ops = &bfs_context_ops; + + return 0; } static struct file_system_type bfs_fs_type = { - .owner = THIS_MODULE, - .name = "bfs", - .mount = bfs_mount, - .kill_sb = kill_block_super, - .fs_flags = FS_REQUIRES_DEV, + .owner = THIS_MODULE, + .name = "bfs", + .init_fs_context = bfs_init_fs_context, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("bfs"); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 584fa89bc877..a43363d593e5 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -68,12 +68,6 @@ static int load_elf_binary(struct linux_binprm *bprm); -#ifdef CONFIG_USELIB -static int load_elf_library(struct file *); -#else -#define load_elf_library NULL -#endif - /* * If we don't support core dumping, then supply a NULL so we * don't even try. @@ -101,7 +95,6 @@ static int elf_core_dump(struct coredump_params *cprm); static struct linux_binfmt elf_format = { .module = THIS_MODULE, .load_binary = load_elf_binary, - .load_shlib = load_elf_library, #ifdef CONFIG_COREDUMP .core_dump = elf_core_dump, .min_coredump = ELF_EXEC_PAGESIZE, @@ -830,6 +823,7 @@ static int load_elf_binary(struct linux_binprm *bprm) struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; struct elf_phdr *elf_property_phdata = NULL; unsigned long elf_brk; + bool brk_moved = false; int retval, i; unsigned long elf_entry; unsigned long e_entry; @@ -1097,15 +1091,19 @@ out_free_interp: /* Calculate any requested alignment. */ alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); - /* - * There are effectively two types of ET_DYN - * binaries: programs (i.e. PIE: ET_DYN with PT_INTERP) - * and loaders (ET_DYN without PT_INTERP, since they - * _are_ the ELF interpreter). The loaders must - * be loaded away from programs since the program - * may otherwise collide with the loader (especially - * for ET_EXEC which does not have a randomized - * position). For example to handle invocations of + /** + * DOC: PIE handling + * + * There are effectively two types of ET_DYN ELF + * binaries: programs (i.e. PIE: ET_DYN with + * PT_INTERP) and loaders (i.e. static PIE: ET_DYN + * without PT_INTERP, usually the ELF interpreter + * itself). Loaders must be loaded away from programs + * since the program may otherwise collide with the + * loader (especially for ET_EXEC which does not have + * a randomized position). + * + * For example, to handle invocations of * "./ld.so someprog" to test out a new version of * the loader, the subsequent program that the * loader loads must avoid the loader itself, so @@ -1118,6 +1116,9 @@ out_free_interp: * ELF_ET_DYN_BASE and loaders are loaded into the * independently randomized mmap region (0 load_bias * without MAP_FIXED nor MAP_FIXED_NOREPLACE). + * + * See below for "brk" handling details, which is + * also affected by program vs loader and ASLR. */ if (interpreter) { /* On ET_DYN with PT_INTERP, we do the ASLR. */ @@ -1234,8 +1235,6 @@ out_free_interp: start_data += load_bias; end_data += load_bias; - current->mm->start_brk = current->mm->brk = ELF_PAGEALIGN(elf_brk); - if (interpreter) { elf_entry = load_elf_interp(interp_elf_ex, interpreter, @@ -1291,27 +1290,44 @@ out_free_interp: mm->end_data = end_data; mm->start_stack = bprm->p; - if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) { + /** + * DOC: "brk" handling + * + * For architectures with ELF randomization, when executing a + * loader directly (i.e. static PIE: ET_DYN without PT_INTERP), + * move the brk area out of the mmap region and into the unused + * ELF_ET_DYN_BASE region. Since "brk" grows up it may collide + * early with the stack growing down or other regions being put + * into the mmap region by the kernel (e.g. vdso). + * + * In the CONFIG_COMPAT_BRK case, though, everything is turned + * off because we're not allowed to move the brk at all. + */ + if (!IS_ENABLED(CONFIG_COMPAT_BRK) && + IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && + elf_ex->e_type == ET_DYN && !interpreter) { + elf_brk = ELF_ET_DYN_BASE; + /* This counts as moving the brk, so let brk(2) know. */ + brk_moved = true; + } + mm->start_brk = mm->brk = ELF_PAGEALIGN(elf_brk); + + if ((current->flags & PF_RANDOMIZE) && snapshot_randomize_va_space > 1) { /* - * For architectures with ELF randomization, when executing - * a loader directly (i.e. no interpreter listed in ELF - * headers), move the brk area out of the mmap region - * (since it grows up, and may collide early with the stack - * growing down), and into the unused ELF_ET_DYN_BASE region. + * If we didn't move the brk to ELF_ET_DYN_BASE (above), + * leave a gap between .bss and brk. */ - if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && - elf_ex->e_type == ET_DYN && !interpreter) { - mm->brk = mm->start_brk = ELF_ET_DYN_BASE; - } else { - /* Otherwise leave a gap between .bss and brk. */ + if (!brk_moved) mm->brk = mm->start_brk = mm->brk + PAGE_SIZE; - } mm->brk = mm->start_brk = arch_randomize_brk(mm); + brk_moved = true; + } + #ifdef compat_brk_randomized + if (brk_moved) current->brk_randomized = 1; #endif - } if (current->personality & MMAP_PAGE_ZERO) { /* Why this, you ask??? Well SVr4 maps page 0 as read-only, @@ -1361,75 +1377,6 @@ out_free_ph: goto out; } -#ifdef CONFIG_USELIB -/* This is really simpleminded and specialized - we are loading an - a.out library that is given an ELF header. */ -static int load_elf_library(struct file *file) -{ - struct elf_phdr *elf_phdata; - struct elf_phdr *eppnt; - int retval, error, i, j; - struct elfhdr elf_ex; - - error = -ENOEXEC; - retval = elf_read(file, &elf_ex, sizeof(elf_ex), 0); - if (retval < 0) - goto out; - - if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0) - goto out; - - /* First of all, some simple consistency checks */ - if (elf_ex.e_type != ET_EXEC || elf_ex.e_phnum > 2 || - !elf_check_arch(&elf_ex) || !file->f_op->mmap) - goto out; - if (elf_check_fdpic(&elf_ex)) - goto out; - - /* Now read in all of the header information */ - - j = sizeof(struct elf_phdr) * elf_ex.e_phnum; - /* j < ELF_MIN_ALIGN because elf_ex.e_phnum <= 2 */ - - error = -ENOMEM; - elf_phdata = kmalloc(j, GFP_KERNEL); - if (!elf_phdata) - goto out; - - eppnt = elf_phdata; - error = -ENOEXEC; - retval = elf_read(file, eppnt, j, elf_ex.e_phoff); - if (retval < 0) - goto out_free_ph; - - for (j = 0, i = 0; i<elf_ex.e_phnum; i++) - if ((eppnt + i)->p_type == PT_LOAD) - j++; - if (j != 1) - goto out_free_ph; - - while (eppnt->p_type != PT_LOAD) - eppnt++; - - /* Now use mmap to map the library into memory. */ - error = elf_load(file, ELF_PAGESTART(eppnt->p_vaddr), - eppnt, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED_NOREPLACE | MAP_PRIVATE, - 0); - - if (error != ELF_PAGESTART(eppnt->p_vaddr)) - goto out_free_ph; - - error = 0; - -out_free_ph: - kfree(elf_phdata); -out: - return error; -} -#endif /* #ifdef CONFIG_USELIB */ - #ifdef CONFIG_ELF_CORE /* * ELF core dumper diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 5a7ebd160724..432fbf4fc334 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -842,7 +842,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, } inode_lock(d_inode(root)); - dentry = lookup_one_len(e->name, root, strlen(e->name)); + dentry = lookup_noperm(&QSTR(e->name), root); err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index e7f8ee5d48a4..7f11ef559be6 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -606,7 +606,7 @@ void btrfs_submit_compressed_read(struct btrfs_bio *bbio) free_extent_map(em); cb->nr_folios = DIV_ROUND_UP(compressed_len, PAGE_SIZE); - cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct page *), GFP_NOFS); + cb->compressed_folios = kcalloc(cb->nr_folios, sizeof(struct folio *), GFP_NOFS); if (!cb->compressed_folios) { ret = BLK_STS_RESOURCE; goto out_free_bio; diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index d6eef4bd9e9d..de23c4b3515e 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -94,8 +94,6 @@ static void __add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, struct btrfs_block_group *block_group) { lockdep_assert_held(&discard_ctl->lock); - if (!btrfs_run_discard_work(discard_ctl)) - return; if (list_empty(&block_group->discard_list) || block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED) { @@ -118,6 +116,9 @@ static void add_to_discard_list(struct btrfs_discard_ctl *discard_ctl, if (!btrfs_is_block_group_data_only(block_group)) return; + if (!btrfs_run_discard_work(discard_ctl)) + return; + spin_lock(&discard_ctl->lock); __add_to_discard_list(discard_ctl, block_group); spin_unlock(&discard_ctl->lock); @@ -244,6 +245,18 @@ again: block_group->used != 0) { if (btrfs_is_block_group_data_only(block_group)) { __add_to_discard_list(discard_ctl, block_group); + /* + * The block group must have been moved to other + * discard list even if discard was disabled in + * the meantime or a transaction abort happened, + * otherwise we can end up in an infinite loop, + * always jumping into the 'again' label and + * keep getting this block group over and over + * in case there are no other block groups in + * the discard lists. + */ + ASSERT(block_group->discard_index != + BTRFS_DISCARD_INDEX_UNUSED); } else { list_del_init(&block_group->discard_list); btrfs_put_block_group(block_group); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 8515c31f563b..13bdd60da3c7 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3508,8 +3508,8 @@ static void btree_clear_folio_dirty_tag(struct folio *folio) ASSERT(folio_test_locked(folio)); xa_lock_irq(&folio->mapping->i_pages); if (!folio_test_dirty(folio)) - __xa_clear_mark(&folio->mapping->i_pages, - folio_index(folio), PAGECACHE_TAG_DIRTY); + __xa_clear_mark(&folio->mapping->i_pages, folio->index, + PAGECACHE_TAG_DIRTY); xa_unlock_irq(&folio->mapping->i_pages); } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 2e261892c7bc..f5b28b5c4908 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -298,6 +298,8 @@ static inline int __pure num_extent_pages(const struct extent_buffer *eb) */ static inline int __pure num_extent_folios(const struct extent_buffer *eb) { + if (!eb->folios[0]) + return 0; if (folio_order(eb->folios[0])) return 1; return num_extent_pages(eb); diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index bcca43046064..7baa2ed45198 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -300,6 +300,7 @@ enum { #define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL #define BTRFS_DEFAULT_COMMIT_INTERVAL (30) +#define BTRFS_WARNING_COMMIT_INTERVAL (300) #define BTRFS_DEFAULT_MAX_INLINE (2048) struct btrfs_dev_replace { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index bdafe4d4c4a5..90f5da3c520a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1109,6 +1109,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, struct extent_state *cached = NULL; struct extent_map *em; int ret = 0; + bool free_pages = false; u64 start = async_extent->start; u64 end = async_extent->start + async_extent->ram_size - 1; @@ -1129,7 +1130,10 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, } if (async_extent->compress_type == BTRFS_COMPRESS_NONE) { + ASSERT(!async_extent->folios); + ASSERT(async_extent->nr_folios == 0); submit_uncompressed_range(inode, async_extent, locked_folio); + free_pages = true; goto done; } @@ -1145,6 +1149,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, * fall back to uncompressed. */ submit_uncompressed_range(inode, async_extent, locked_folio); + free_pages = true; goto done; } @@ -1186,6 +1191,8 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, done: if (async_chunk->blkcg_css) kthread_associate_blkcg(NULL); + if (free_pages) + free_async_extent_pages(async_extent); kfree(async_extent); return; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 63aeacc54945..0e2271c16eeb 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -909,7 +909,7 @@ static noinline int btrfs_mksubvol(const struct path *parent, if (error == -EINTR) return error; - dentry = lookup_one(idmap, name, parent->dentry, namelen); + dentry = lookup_one(idmap, &QSTR_LEN(name, namelen), parent->dentry); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_unlock; @@ -2288,7 +2288,6 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, struct btrfs_ioctl_vol_args_v2 *vol_args2 = NULL; struct mnt_idmap *idmap = file_mnt_idmap(file); char *subvol_name, *subvol_name_ptr = NULL; - int subvol_namelen; int ret = 0; bool destroy_parent = false; @@ -2411,10 +2410,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, goto out; } - subvol_namelen = strlen(subvol_name); - if (strchr(subvol_name, '/') || - strncmp(subvol_name, "..", subvol_namelen) == 0) { + strcmp(subvol_name, "..") == 0) { ret = -EINVAL; goto free_subvol_name; } @@ -2427,7 +2424,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, ret = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT); if (ret == -EINTR) goto free_subvol_name; - dentry = lookup_one(idmap, subvol_name, parent, subvol_namelen); + dentry = lookup_one(idmap, &QSTR(subvol_name), parent); if (IS_ERR(dentry)) { ret = PTR_ERR(dentry); goto out_unlock_dir; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 2c5edcee9450..c3b2e29e3e01 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1541,8 +1541,8 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, u64 extent_gen; int ret; - if (unlikely(!extent_root)) { - btrfs_err(fs_info, "no valid extent root for scrub"); + if (unlikely(!extent_root || !csum_root)) { + btrfs_err(fs_info, "no valid extent or csum root for scrub"); return -EUCLEAN; } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 7121d8c7a318..7310e2fa8526 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -569,6 +569,10 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param) break; case Opt_commit_interval: ctx->commit_interval = result.uint_32; + if (ctx->commit_interval > BTRFS_WARNING_COMMIT_INTERVAL) { + btrfs_warn(NULL, "excessive commit interval %u, use with care", + ctx->commit_interval); + } if (ctx->commit_interval == 0) ctx->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; break; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index c8c21c55be53..8e6b6fed7429 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -733,82 +733,6 @@ const u8 *btrfs_sb_fsid_ptr(const struct btrfs_super_block *sb) return has_metadata_uuid ? sb->metadata_uuid : sb->fsid; } -/* - * We can have very weird soft links passed in. - * One example is "/proc/self/fd/<fd>", which can be a soft link to - * a block device. - * - * But it's never a good idea to use those weird names. - * Here we check if the path (not following symlinks) is a good one inside - * "/dev/". - */ -static bool is_good_dev_path(const char *dev_path) -{ - struct path path = { .mnt = NULL, .dentry = NULL }; - char *path_buf = NULL; - char *resolved_path; - bool is_good = false; - int ret; - - if (!dev_path) - goto out; - - path_buf = kmalloc(PATH_MAX, GFP_KERNEL); - if (!path_buf) - goto out; - - /* - * Do not follow soft link, just check if the original path is inside - * "/dev/". - */ - ret = kern_path(dev_path, 0, &path); - if (ret) - goto out; - resolved_path = d_path(&path, path_buf, PATH_MAX); - if (IS_ERR(resolved_path)) - goto out; - if (strncmp(resolved_path, "/dev/", strlen("/dev/"))) - goto out; - is_good = true; -out: - kfree(path_buf); - path_put(&path); - return is_good; -} - -static int get_canonical_dev_path(const char *dev_path, char *canonical) -{ - struct path path = { .mnt = NULL, .dentry = NULL }; - char *path_buf = NULL; - char *resolved_path; - int ret; - - if (!dev_path) { - ret = -EINVAL; - goto out; - } - - path_buf = kmalloc(PATH_MAX, GFP_KERNEL); - if (!path_buf) { - ret = -ENOMEM; - goto out; - } - - ret = kern_path(dev_path, LOOKUP_FOLLOW, &path); - if (ret) - goto out; - resolved_path = d_path(&path, path_buf, PATH_MAX); - if (IS_ERR(resolved_path)) { - ret = PTR_ERR(resolved_path); - goto out; - } - ret = strscpy(canonical, resolved_path, PATH_MAX); -out: - kfree(path_buf); - path_put(&path); - return ret; -} - static bool is_same_device(struct btrfs_device *device, const char *new_path) { struct path old = { .mnt = NULL, .dentry = NULL }; @@ -1513,23 +1437,12 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags, bool new_device_added = false; struct btrfs_device *device = NULL; struct file *bdev_file; - char *canonical_path = NULL; u64 bytenr; dev_t devt; int ret; lockdep_assert_held(&uuid_mutex); - if (!is_good_dev_path(path)) { - canonical_path = kmalloc(PATH_MAX, GFP_KERNEL); - if (canonical_path) { - ret = get_canonical_dev_path(path, canonical_path); - if (ret < 0) { - kfree(canonical_path); - canonical_path = NULL; - } - } - } /* * Avoid an exclusive open here, as the systemd-udev may initiate the * device scan which may race with the user's mount or mkfs command, @@ -1574,8 +1487,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags, goto free_disk_super; } - device = device_list_add(canonical_path ? : path, disk_super, - &new_device_added); + device = device_list_add(path, disk_super, &new_device_added); if (!IS_ERR(device) && new_device_added) btrfs_free_stale_devices(device->devt, device); @@ -1584,7 +1496,6 @@ free_disk_super: error_bdev_put: fput(bdev_file); - kfree(canonical_path); return device; } diff --git a/fs/buffer.c b/fs/buffer.c index 7be23ff20b27..8cf4a1dc481e 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -297,7 +297,6 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); - return; } struct postprocess_bh_ctx { @@ -422,7 +421,6 @@ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); - return; } /* @@ -1122,6 +1120,8 @@ static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { + bool blocking = gfpflags_allow_blocking(gfp); + /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { @@ -1137,12 +1137,15 @@ __getblk_slow(struct block_device *bdev, sector_t block, for (;;) { struct buffer_head *bh; - bh = __find_get_block(bdev, block, size); - if (bh) - return bh; - if (!grow_buffers(bdev, block, size, gfp)) return NULL; + + if (blocking) + bh = __find_get_block_nonatomic(bdev, block, size); + else + bh = __find_get_block(bdev, block, size); + if (bh) + return bh; } } @@ -1220,10 +1223,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh) /* FIXME: do we need to set this in both places? */ if (bh->b_folio && bh->b_folio->mapping) mapping_set_error(bh->b_folio->mapping, -EIO); - if (bh->b_assoc_map) { + if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); - errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO); - } } EXPORT_SYMBOL(mark_buffer_write_io_error); @@ -1613,8 +1614,8 @@ static void discard_buffer(struct buffer_head * bh) bh->b_bdev = NULL; b_state = READ_ONCE(bh->b_state); do { - } while (!try_cmpxchg(&bh->b_state, &b_state, - b_state & ~BUFFER_FLAGS_DISCARD)); + } while (!try_cmpxchg_relaxed(&bh->b_state, &b_state, + b_state & ~BUFFER_FLAGS_DISCARD)); unlock_buffer(bh); } @@ -1679,7 +1680,6 @@ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length) filemap_release_folio(folio, 0); out: folio_clear_mappedtodisk(folio); - return; } EXPORT_SYMBOL(block_invalidate_folio); @@ -2730,7 +2730,7 @@ unlock: EXPORT_SYMBOL(block_truncate_page); /* - * The generic ->writepage function for buffer-backed address_spaces + * The generic write folio function for buffer-backed address_spaces */ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, void *get_block) @@ -2750,7 +2750,7 @@ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, /* * The folio straddles i_size. It must be zeroed out on each and every - * writepage invocation because it may be mmapped. "A file is mapped + * writeback invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 38c236e38cef..b62cd3e9a18e 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -71,7 +71,6 @@ struct cachefiles_object { int debug_id; spinlock_t lock; refcount_t ref; - u8 d_name_len; /* Length of filename */ enum cachefiles_content content_info:8; /* Info about content presence */ unsigned long flags; #define CACHEFILES_OBJECT_USING_TMPFILE 0 /* Have an unlinked tmpfile */ diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c index b48525680e73..aae86af48ed5 100644 --- a/fs/cachefiles/key.c +++ b/fs/cachefiles/key.c @@ -132,7 +132,6 @@ bool cachefiles_cook_key(struct cachefiles_object *object) success: name[len] = 0; object->d_name = name; - object->d_name_len = len; _leave(" = %s", object->d_name); return true; } diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 14d0cc894000..aecfc5c37b49 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -98,7 +98,7 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, retry: ret = cachefiles_inject_read_error(); if (ret == 0) - subdir = lookup_one_len(dirname, dir, strlen(dirname)); + subdir = lookup_one(&nop_mnt_idmap, &QSTR(dirname), dir); else subdir = ERR_PTR(ret); trace_cachefiles_lookup(NULL, dir, subdir); @@ -338,7 +338,7 @@ try_again: return -EIO; } - grave = lookup_one_len(nbuffer, cache->graveyard, strlen(nbuffer)); + grave = lookup_one(&nop_mnt_idmap, &QSTR(nbuffer), cache->graveyard); if (IS_ERR(grave)) { unlock_rename(cache->graveyard, dir); trace_cachefiles_vfs_error(object, d_inode(cache->graveyard), @@ -630,8 +630,8 @@ bool cachefiles_look_up_object(struct cachefiles_object *object) /* Look up path "cache/vol/fanout/file". */ ret = cachefiles_inject_read_error(); if (ret == 0) - dentry = lookup_positive_unlocked(object->d_name, fan, - object->d_name_len); + dentry = lookup_one_positive_unlocked(&nop_mnt_idmap, + &QSTR(object->d_name), fan); else dentry = ERR_PTR(ret); trace_cachefiles_lookup(object, fan, dentry); @@ -683,7 +683,7 @@ bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); ret = cachefiles_inject_read_error(); if (ret == 0) - dentry = lookup_one_len(object->d_name, fan, object->d_name_len); + dentry = lookup_one(&nop_mnt_idmap, &QSTR(object->d_name), fan); else dentry = ERR_PTR(ret); if (IS_ERR(dentry)) { @@ -702,7 +702,7 @@ bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, dput(dentry); ret = cachefiles_inject_read_error(); if (ret == 0) - dentry = lookup_one_len(object->d_name, fan, object->d_name_len); + dentry = lookup_one(&nop_mnt_idmap, &QSTR(object->d_name), fan); else dentry = ERR_PTR(ret); if (IS_ERR(dentry)) { @@ -751,7 +751,7 @@ static struct dentry *cachefiles_lookup_for_cull(struct cachefiles_cache *cache, inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - victim = lookup_one_len(filename, dir, strlen(filename)); + victim = lookup_one(&nop_mnt_idmap, &QSTR(filename), dir); if (IS_ERR(victim)) goto lookup_error; if (d_is_negative(victim)) diff --git a/fs/coredump.c b/fs/coredump.c index c33c177a701b..f217ebf2b3b6 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -43,6 +43,14 @@ #include <linux/timekeeping.h> #include <linux/sysctl.h> #include <linux/elf.h> +#include <linux/pidfs.h> +#include <linux/net.h> +#include <linux/socket.h> +#include <net/af_unix.h> +#include <net/net_namespace.h> +#include <net/sock.h> +#include <uapi/linux/pidfd.h> +#include <uapi/linux/un.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -60,6 +68,12 @@ static void free_vma_snapshot(struct coredump_params *cprm); #define CORE_FILE_NOTE_SIZE_DEFAULT (4*1024*1024) /* Define a reasonable max cap */ #define CORE_FILE_NOTE_SIZE_MAX (16*1024*1024) +/* + * File descriptor number for the pidfd for the thread-group leader of + * the coredumping task installed into the usermode helper's file + * descriptor table. + */ +#define COREDUMP_PIDFD_NUMBER 3 static int core_uses_pid; static unsigned int core_pipe_limit; @@ -68,9 +82,16 @@ static char core_pattern[CORENAME_MAX_SIZE] = "core"; static int core_name_size = CORENAME_MAX_SIZE; unsigned int core_file_note_size_limit = CORE_FILE_NOTE_SIZE_DEFAULT; +enum coredump_type_t { + COREDUMP_FILE = 1, + COREDUMP_PIPE = 2, + COREDUMP_SOCK = 3, +}; + struct core_name { char *corename; int used, size; + enum coredump_type_t core_type; }; static int expand_corename(struct core_name *cn, int size) @@ -210,18 +231,24 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; - int ispipe = (*pat_ptr == '|'); bool was_space = false; int pid_in_pattern = 0; int err = 0; cn->used = 0; cn->corename = NULL; + if (*pat_ptr == '|') + cn->core_type = COREDUMP_PIPE; + else if (*pat_ptr == '@') + cn->core_type = COREDUMP_SOCK; + else + cn->core_type = COREDUMP_FILE; if (expand_corename(cn, core_name_size)) return -ENOMEM; cn->corename[0] = '\0'; - if (ispipe) { + switch (cn->core_type) { + case COREDUMP_PIPE: { int argvs = sizeof(core_pattern) / 2; (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL); if (!(*argv)) @@ -230,6 +257,45 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, ++pat_ptr; if (!(*pat_ptr)) return -ENOMEM; + break; + } + case COREDUMP_SOCK: { + /* skip the @ */ + pat_ptr++; + if (!(*pat_ptr)) + return -ENOMEM; + + err = cn_printf(cn, "%s", pat_ptr); + if (err) + return err; + + /* Require absolute paths. */ + if (cn->corename[0] != '/') + return -EINVAL; + + /* + * Ensure we can uses spaces to indicate additional + * parameters in the future. + */ + if (strchr(cn->corename, ' ')) { + coredump_report_failure("Coredump socket may not %s contain spaces", cn->corename); + return -EINVAL; + } + + /* + * Currently no need to parse any other options. + * Relevant information can be retrieved from the peer + * pidfd retrievable via SO_PEERPIDFD by the receiver or + * via /proc/<pid>, using the SO_PEERPIDFD to guard + * against pid recycling when opening /proc/<pid>. + */ + return 0; + } + case COREDUMP_FILE: + break; + default: + WARN_ON_ONCE(true); + return -EINVAL; } /* Repeat as long as we have more pattern to process and more output @@ -239,7 +305,7 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, * Split on spaces before doing template expansion so that * %e and %E don't get split if they have spaces in them */ - if (ispipe) { + if (cn->core_type == COREDUMP_PIPE) { if (isspace(*pat_ptr)) { if (cn->used != 0) was_space = true; @@ -339,6 +405,27 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm, case 'C': err = cn_printf(cn, "%d", cprm->cpu); break; + /* pidfd number */ + case 'F': { + /* + * Installing a pidfd only makes sense if + * we actually spawn a usermode helper. + */ + if (cn->core_type != COREDUMP_PIPE) + break; + + /* + * Note that we'll install a pidfd for the + * thread-group leader. We know that task + * linkage hasn't been removed yet and even if + * this @current isn't the actual thread-group + * leader we know that the thread-group leader + * cannot be reaped until @current has exited. + */ + cprm->pid = task_tgid(current); + err = cn_printf(cn, "%d", COREDUMP_PIDFD_NUMBER); + break; + } default: break; } @@ -355,12 +442,10 @@ out: * If core_pattern does not include a %p (as is the default) * and core_uses_pid is set, then .%pid will be appended to * the filename. Do not do this for piped commands. */ - if (!ispipe && !pid_in_pattern && core_uses_pid) { - err = cn_printf(cn, ".%d", task_tgid_vnr(current)); - if (err) - return err; - } - return ispipe; + if (cn->core_type == COREDUMP_FILE && !pid_in_pattern && core_uses_pid) + return cn_printf(cn, ".%d", task_tgid_vnr(current)); + + return 0; } static int zap_process(struct signal_struct *signal, int exit_code) @@ -493,7 +578,7 @@ static void wait_for_dump_helpers(struct file *file) } /* - * umh_pipe_setup + * umh_coredump_setup * helper function to customize the process used * to collect the core in userspace. Specifically * it sets up a pipe and installs it as fd 0 (stdin) @@ -503,11 +588,34 @@ static void wait_for_dump_helpers(struct file *file) * is a special value that we use to trap recursive * core dumps */ -static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) +static int umh_coredump_setup(struct subprocess_info *info, struct cred *new) { struct file *files[2]; struct coredump_params *cp = (struct coredump_params *)info->data; - int err = create_pipe_files(files, 0); + int err; + + if (cp->pid) { + struct file *pidfs_file __free(fput) = NULL; + + pidfs_file = pidfs_alloc_file(cp->pid, 0); + if (IS_ERR(pidfs_file)) + return PTR_ERR(pidfs_file); + + pidfs_coredump(cp); + + /* + * Usermode helpers are childen of either + * system_unbound_wq or of kthreadd. So we know that + * we're starting off with a clean file descriptor + * table. So we should always be able to use + * COREDUMP_PIDFD_NUMBER as our file descriptor value. + */ + err = replace_fd(COREDUMP_PIDFD_NUMBER, pidfs_file, 0); + if (err < 0) + return err; + } + + err = create_pipe_files(files, 0); if (err) return err; @@ -515,10 +623,13 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) err = replace_fd(0, files[0], 0); fput(files[0]); + if (err < 0) + return err; + /* and disallow core files too */ current->signal->rlim[RLIMIT_CORE] = (struct rlimit){1, 1}; - return err; + return 0; } void do_coredump(const kernel_siginfo_t *siginfo) @@ -530,7 +641,6 @@ void do_coredump(const kernel_siginfo_t *siginfo) const struct cred *old_cred; struct cred *cred; int retval = 0; - int ispipe; size_t *argv = NULL; int argc = 0; /* require nonrelative corefile path and be extra careful */ @@ -579,70 +689,14 @@ void do_coredump(const kernel_siginfo_t *siginfo) old_cred = override_creds(cred); - ispipe = format_corename(&cn, &cprm, &argv, &argc); - - if (ispipe) { - int argi; - int dump_count; - char **helper_argv; - struct subprocess_info *sub_info; - - if (ispipe < 0) { - coredump_report_failure("format_corename failed, aborting core"); - goto fail_unlock; - } - - if (cprm.limit == 1) { - /* See umh_pipe_setup() which sets RLIMIT_CORE = 1. - * - * Normally core limits are irrelevant to pipes, since - * we're not writing to the file system, but we use - * cprm.limit of 1 here as a special value, this is a - * consistent way to catch recursive crashes. - * We can still crash if the core_pattern binary sets - * RLIM_CORE = !1, but it runs as root, and can do - * lots of stupid things. - * - * Note that we use task_tgid_vnr here to grab the pid - * of the process group leader. That way we get the - * right pid if a thread in a multi-threaded - * core_pattern process dies. - */ - coredump_report_failure("RLIMIT_CORE is set to 1, aborting core"); - goto fail_unlock; - } - cprm.limit = RLIM_INFINITY; - - dump_count = atomic_inc_return(&core_dump_count); - if (core_pipe_limit && (core_pipe_limit < dump_count)) { - coredump_report_failure("over core_pipe_limit, skipping core dump"); - goto fail_dropcount; - } - - helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), - GFP_KERNEL); - if (!helper_argv) { - coredump_report_failure("%s failed to allocate memory", __func__); - goto fail_dropcount; - } - for (argi = 0; argi < argc; argi++) - helper_argv[argi] = cn.corename + argv[argi]; - helper_argv[argi] = NULL; - - retval = -ENOMEM; - sub_info = call_usermodehelper_setup(helper_argv[0], - helper_argv, NULL, GFP_KERNEL, - umh_pipe_setup, NULL, &cprm); - if (sub_info) - retval = call_usermodehelper_exec(sub_info, - UMH_WAIT_EXEC); + retval = format_corename(&cn, &cprm, &argv, &argc); + if (retval < 0) { + coredump_report_failure("format_corename failed, aborting core"); + goto fail_unlock; + } - kfree(helper_argv); - if (retval) { - coredump_report_failure("|%s pipe failed", cn.corename); - goto close_fail; - } - } else { + switch (cn.core_type) { + case COREDUMP_FILE: { struct mnt_idmap *idmap; struct inode *inode; int open_flags = O_CREAT | O_WRONLY | O_NOFOLLOW | @@ -736,6 +790,143 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (do_truncate(idmap, cprm.file->f_path.dentry, 0, 0, cprm.file)) goto close_fail; + break; + } + case COREDUMP_PIPE: { + int argi; + int dump_count; + char **helper_argv; + struct subprocess_info *sub_info; + + if (cprm.limit == 1) { + /* See umh_coredump_setup() which sets RLIMIT_CORE = 1. + * + * Normally core limits are irrelevant to pipes, since + * we're not writing to the file system, but we use + * cprm.limit of 1 here as a special value, this is a + * consistent way to catch recursive crashes. + * We can still crash if the core_pattern binary sets + * RLIM_CORE = !1, but it runs as root, and can do + * lots of stupid things. + * + * Note that we use task_tgid_vnr here to grab the pid + * of the process group leader. That way we get the + * right pid if a thread in a multi-threaded + * core_pattern process dies. + */ + coredump_report_failure("RLIMIT_CORE is set to 1, aborting core"); + goto fail_unlock; + } + cprm.limit = RLIM_INFINITY; + + dump_count = atomic_inc_return(&core_dump_count); + if (core_pipe_limit && (core_pipe_limit < dump_count)) { + coredump_report_failure("over core_pipe_limit, skipping core dump"); + goto fail_dropcount; + } + + helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), + GFP_KERNEL); + if (!helper_argv) { + coredump_report_failure("%s failed to allocate memory", __func__); + goto fail_dropcount; + } + for (argi = 0; argi < argc; argi++) + helper_argv[argi] = cn.corename + argv[argi]; + helper_argv[argi] = NULL; + + retval = -ENOMEM; + sub_info = call_usermodehelper_setup(helper_argv[0], + helper_argv, NULL, GFP_KERNEL, + umh_coredump_setup, NULL, &cprm); + if (sub_info) + retval = call_usermodehelper_exec(sub_info, + UMH_WAIT_EXEC); + + kfree(helper_argv); + if (retval) { + coredump_report_failure("|%s pipe failed", cn.corename); + goto close_fail; + } + break; + } + case COREDUMP_SOCK: { +#ifdef CONFIG_UNIX + struct file *file __free(fput) = NULL; + struct sockaddr_un addr = { + .sun_family = AF_UNIX, + }; + ssize_t addr_len; + struct socket *socket; + + addr_len = strscpy(addr.sun_path, cn.corename); + if (addr_len < 0) + goto close_fail; + addr_len += offsetof(struct sockaddr_un, sun_path) + 1; + + /* + * It is possible that the userspace process which is + * supposed to handle the coredump and is listening on + * the AF_UNIX socket coredumps. Userspace should just + * mark itself non dumpable. + */ + + retval = sock_create_kern(&init_net, AF_UNIX, SOCK_STREAM, 0, &socket); + if (retval < 0) + goto close_fail; + + file = sock_alloc_file(socket, 0, NULL); + if (IS_ERR(file)) + goto close_fail; + + /* + * Set the thread-group leader pid which is used for the + * peer credentials during connect() below. Then + * immediately register it in pidfs... + */ + cprm.pid = task_tgid(current); + retval = pidfs_register_pid(cprm.pid); + if (retval) + goto close_fail; + + /* + * ... and set the coredump information so userspace + * has it available after connect()... + */ + pidfs_coredump(&cprm); + + retval = kernel_connect(socket, (struct sockaddr *)(&addr), + addr_len, O_NONBLOCK | SOCK_COREDUMP); + + /* + * ... Make sure to only put our reference after connect() took + * its own reference keeping the pidfs entry alive ... + */ + pidfs_put_pid(cprm.pid); + + if (retval) { + if (retval == -EAGAIN) + coredump_report_failure("Coredump socket %s receive queue full", addr.sun_path); + else + coredump_report_failure("Coredump socket connection %s failed %d", addr.sun_path, retval); + goto close_fail; + } + + /* ... and validate that @sk_peer_pid matches @cprm.pid. */ + if (WARN_ON_ONCE(unix_peer(socket->sk)->sk_peer_pid != cprm.pid)) + goto close_fail; + + cprm.limit = RLIM_INFINITY; + cprm.file = no_free_ptr(file); +#else + coredump_report_failure("Core dump socket support %s disabled", cn.corename); + goto close_fail; +#endif + break; + } + default: + WARN_ON_ONCE(true); + goto close_fail; } /* get us an unshared descriptor table; almost always a no-op */ @@ -770,13 +961,49 @@ void do_coredump(const kernel_siginfo_t *siginfo) file_end_write(cprm.file); free_vma_snapshot(&cprm); } - if (ispipe && core_pipe_limit) - wait_for_dump_helpers(cprm.file); + +#ifdef CONFIG_UNIX + /* Let userspace know we're done processing the coredump. */ + if (sock_from_file(cprm.file)) + kernel_sock_shutdown(sock_from_file(cprm.file), SHUT_WR); +#endif + + /* + * When core_pipe_limit is set we wait for the coredump server + * or usermodehelper to finish before exiting so it can e.g., + * inspect /proc/<pid>. + */ + if (core_pipe_limit) { + switch (cn.core_type) { + case COREDUMP_PIPE: + wait_for_dump_helpers(cprm.file); + break; +#ifdef CONFIG_UNIX + case COREDUMP_SOCK: { + ssize_t n; + + /* + * We use a simple read to wait for the coredump + * processing to finish. Either the socket is + * closed or we get sent unexpected data. In + * both cases, we're done. + */ + n = __kernel_read(cprm.file, &(char){ 0 }, 1, NULL); + if (n != 0) + coredump_report_failure("Unexpected data on coredump socket"); + break; + } +#endif + default: + break; + } + } + close_fail: if (cprm.file) filp_close(cprm.file, NULL); fail_dropcount: - if (ispipe) + if (cn.core_type == COREDUMP_PIPE) atomic_dec(&core_dump_count); fail_unlock: kfree(argv); @@ -799,10 +1026,9 @@ static int __dump_emit(struct coredump_params *cprm, const void *addr, int nr) struct file *file = cprm->file; loff_t pos = file->f_pos; ssize_t n; + if (cprm->written + nr > cprm->limit) return 0; - - if (dump_interrupted()) return 0; n = __kernel_write(file, addr, nr, &pos); @@ -819,20 +1045,21 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr) { static char zeroes[PAGE_SIZE]; struct file *file = cprm->file; + if (file->f_mode & FMODE_LSEEK) { - if (dump_interrupted() || - vfs_llseek(file, nr, SEEK_CUR) < 0) + if (dump_interrupted() || vfs_llseek(file, nr, SEEK_CUR) < 0) return 0; cprm->pos += nr; return 1; - } else { - while (nr > PAGE_SIZE) { - if (!__dump_emit(cprm, zeroes, PAGE_SIZE)) - return 0; - nr -= PAGE_SIZE; - } - return __dump_emit(cprm, zeroes, nr); } + + while (nr > PAGE_SIZE) { + if (!__dump_emit(cprm, zeroes, PAGE_SIZE)) + return 0; + nr -= PAGE_SIZE; + } + + return __dump_emit(cprm, zeroes, nr); } int dump_emit(struct coredump_params *cprm, const void *addr, int nr) @@ -1001,7 +1228,7 @@ EXPORT_SYMBOL(dump_align); void validate_coredump_safety(void) { if (suid_dumpable == SUID_DUMP_ROOT && - core_pattern[0] != '/' && core_pattern[0] != '|') { + core_pattern[0] != '/' && core_pattern[0] != '|' && core_pattern[0] != '@') { coredump_report_failure("Unsafe core_pattern used with fs.suid_dumpable=2: " "pipe handler or fully qualified core dump path required. " @@ -1009,18 +1236,55 @@ void validate_coredump_safety(void) } } +static inline bool check_coredump_socket(void) +{ + if (core_pattern[0] != '@') + return true; + + /* + * Coredump socket must be located in the initial mount + * namespace. Don't give the impression that anything else is + * supported right now. + */ + if (current->nsproxy->mnt_ns != init_task.nsproxy->mnt_ns) + return false; + + /* Must be an absolute path. */ + if (*(core_pattern + 1) != '/') + return false; + + return true; +} + static int proc_dostring_coredump(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - int error = proc_dostring(table, write, buffer, lenp, ppos); + int error; + ssize_t retval; + char old_core_pattern[CORENAME_MAX_SIZE]; + + retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE); + + error = proc_dostring(table, write, buffer, lenp, ppos); + if (error) + return error; + if (!check_coredump_socket()) { + strscpy(core_pattern, old_core_pattern, retval + 1); + return -EINVAL; + } - if (!error) - validate_coredump_safety(); + validate_coredump_safety(); return error; } static const unsigned int core_file_note_size_min = CORE_FILE_NOTE_SIZE_DEFAULT; static const unsigned int core_file_note_size_max = CORE_FILE_NOTE_SIZE_MAX; +static char core_modes[] = { + "file\npipe" +#ifdef CONFIG_UNIX + "\nsocket" +#endif +}; static const struct ctl_table coredump_sysctls[] = { { @@ -1064,6 +1328,13 @@ static const struct ctl_table coredump_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "core_modes", + .data = core_modes, + .maxlen = sizeof(core_modes) - 1, + .mode = 0444, + .proc_handler = proc_dostring, + }, }; static int __init init_fs_coredump_sysctls(void) diff --git a/fs/dcache.c b/fs/dcache.c index bd5aa136153a..03d58b2d4fa3 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -74,10 +74,11 @@ * arbitrary, since it's serialized on rename_lock */ static int sysctl_vfs_cache_pressure __read_mostly = 100; +static int sysctl_vfs_cache_pressure_denom __read_mostly = 100; unsigned long vfs_pressure_ratio(unsigned long val) { - return mult_frac(val, sysctl_vfs_cache_pressure, 100); + return mult_frac(val, sysctl_vfs_cache_pressure, sysctl_vfs_cache_pressure_denom); } EXPORT_SYMBOL_GPL(vfs_pressure_ratio); @@ -225,6 +226,14 @@ static const struct ctl_table vm_dcache_sysctls[] = { .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, + { + .procname = "vfs_cache_pressure_denom", + .data = &sysctl_vfs_cache_pressure_denom, + .maxlen = sizeof(sysctl_vfs_cache_pressure_denom), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE_HUNDRED, + }, }; static int __init init_fs_dcache_sysctls(void) @@ -2412,7 +2421,6 @@ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) } return d_lookup(dir, name); } -EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 75715d8877ee..30c4944e1862 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -346,7 +346,7 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) if (!parent) parent = debugfs_mount->mnt_root; - dentry = lookup_positive_unlocked(name, parent, strlen(name)); + dentry = lookup_noperm_positive_unlocked(&QSTR(name), parent); if (IS_ERR(dentry)) return NULL; return dentry; @@ -388,7 +388,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) if (unlikely(IS_DEADDIR(d_inode(parent)))) dentry = ERR_PTR(-ENOENT); else - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_noperm(&QSTR(name), parent); if (!IS_ERR(dentry) && d_really_is_positive(dentry)) { if (d_is_dir(dentry)) pr_err("Directory '%s' with parent '%s' already present!\n", @@ -872,7 +872,7 @@ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, . } if (strcmp(old_name.name.name, new_name) == 0) goto out; - target = lookup_one_len(new_name, parent, strlen(new_name)); + target = lookup_noperm(&QSTR(new_name), parent); if (IS_ERR(target)) { error = PTR_ERR(target); goto out; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 51a5c54eb740..493d7f194956 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -394,8 +394,8 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, char *encrypted_and_encoded_name = NULL; struct ecryptfs_mount_crypt_stat *mount_crypt_stat; struct dentry *lower_dir_dentry, *lower_dentry; - const char *name = ecryptfs_dentry->d_name.name; - size_t len = ecryptfs_dentry->d_name.len; + struct qstr qname = QSTR_INIT(ecryptfs_dentry->d_name.name, + ecryptfs_dentry->d_name.len); struct dentry *res; int rc = 0; @@ -404,23 +404,25 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, mount_crypt_stat = &ecryptfs_superblock_to_private( ecryptfs_dentry->d_sb)->mount_crypt_stat; if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) { + size_t len = qname.len; rc = ecryptfs_encrypt_and_encode_filename( &encrypted_and_encoded_name, &len, - mount_crypt_stat, name, len); + mount_crypt_stat, qname.name, len); if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt and encode " "filename; rc = [%d]\n", __func__, rc); return ERR_PTR(rc); } - name = encrypted_and_encoded_name; + qname.name = encrypted_and_encoded_name; + qname.len = len; } - lower_dentry = lookup_one_len_unlocked(name, lower_dir_dentry, len); + lower_dentry = lookup_noperm_unlocked(&qname, lower_dir_dentry); if (IS_ERR(lower_dentry)) { - ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " + ecryptfs_printk(KERN_DEBUG, "%s: lookup_noperm() returned " "[%ld] on lower_dentry = [%s]\n", __func__, PTR_ERR(lower_dentry), - name); + qname.name); res = ERR_CAST(lower_dentry); } else { res = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry); diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index ac6a1dd0a6a5..f913b6824289 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -17,7 +17,6 @@ struct efivarfs_fs_info { struct efivarfs_mount_opts mount_opts; struct super_block *sb; struct notifier_block nb; - struct notifier_block pm_nb; }; struct efi_variable { diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 0486e9b68bc6..c900d98bf494 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -18,8 +18,10 @@ #include <linux/statfs.h> #include <linux/notifier.h> #include <linux/printk.h> +#include <linux/namei.h> #include "internal.h" +#include "../internal.h" static int efivarfs_ops_notifier(struct notifier_block *nb, unsigned long event, void *data) @@ -119,12 +121,18 @@ static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } + +static int efivarfs_freeze_fs(struct super_block *sb); +static int efivarfs_unfreeze_fs(struct super_block *sb); + static const struct super_operations efivarfs_ops = { .statfs = efivarfs_statfs, .drop_inode = generic_delete_inode, .alloc_inode = efivarfs_alloc_inode, .free_inode = efivarfs_free_inode, .show_options = efivarfs_show_options, + .freeze_fs = efivarfs_freeze_fs, + .unfreeze_fs = efivarfs_unfreeze_fs, }; /* @@ -204,7 +212,6 @@ bool efivarfs_variable_is_present(efi_char16_t *variable_name, char *name = efivar_get_utf8name(variable_name, vendor); struct super_block *sb = data; struct dentry *dentry; - struct qstr qstr; if (!name) /* @@ -217,9 +224,7 @@ bool efivarfs_variable_is_present(efi_char16_t *variable_name, */ return true; - qstr.name = name; - qstr.len = strlen(name); - dentry = d_hash_and_lookup(sb->s_root, &qstr); + dentry = try_lookup_noperm(&QSTR(name), sb->s_root); kfree(name); if (!IS_ERR_OR_NULL(dentry)) dput(dentry); @@ -367,8 +372,6 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - register_pm_notifier(&sfi->pm_nb); - return efivar_init(efivarfs_callback, sb, true); } @@ -393,55 +396,12 @@ static const struct fs_context_operations efivarfs_context_ops = { .reconfigure = efivarfs_reconfigure, }; -struct efivarfs_ctx { - struct dir_context ctx; - struct super_block *sb; - struct dentry *dentry; -}; - -static bool efivarfs_actor(struct dir_context *ctx, const char *name, int len, - loff_t offset, u64 ino, unsigned mode) -{ - unsigned long size; - struct efivarfs_ctx *ectx = container_of(ctx, struct efivarfs_ctx, ctx); - struct qstr qstr = { .name = name, .len = len }; - struct dentry *dentry = d_hash_and_lookup(ectx->sb->s_root, &qstr); - struct inode *inode; - struct efivar_entry *entry; - int err; - - if (IS_ERR_OR_NULL(dentry)) - return true; - - inode = d_inode(dentry); - entry = efivar_entry(inode); - - err = efivar_entry_size(entry, &size); - size += sizeof(__u32); /* attributes */ - if (err) - size = 0; - - inode_lock_nested(inode, I_MUTEX_CHILD); - i_size_write(inode, size); - inode_unlock(inode); - - if (!size) { - ectx->dentry = dentry; - return false; - } - - dput(dentry); - - return true; -} - static int efivarfs_check_missing(efi_char16_t *name16, efi_guid_t vendor, unsigned long name_size, void *data) { char *name; struct super_block *sb = data; struct dentry *dentry; - struct qstr qstr; int err; if (guid_equal(&vendor, &LINUX_EFI_RANDOM_SEED_TABLE_GUID)) @@ -451,9 +411,7 @@ static int efivarfs_check_missing(efi_char16_t *name16, efi_guid_t vendor, if (!name) return -ENOMEM; - qstr.name = name; - qstr.len = strlen(name); - dentry = d_hash_and_lookup(sb->s_root, &qstr); + dentry = try_lookup_noperm(&QSTR(name), sb->s_root); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out; @@ -474,111 +432,59 @@ static int efivarfs_check_missing(efi_char16_t *name16, efi_guid_t vendor, return err; } -static void efivarfs_deactivate_super_work(struct work_struct *work) -{ - struct super_block *s = container_of(work, struct super_block, - destroy_work); - /* - * note: here s->destroy_work is free for reuse (which - * will happen in deactivate_super) - */ - deactivate_super(s); -} - static struct file_system_type efivarfs_type; -static int efivarfs_pm_notify(struct notifier_block *nb, unsigned long action, - void *ptr) +static int efivarfs_freeze_fs(struct super_block *sb) { - struct efivarfs_fs_info *sfi = container_of(nb, struct efivarfs_fs_info, - pm_nb); - struct path path; - struct efivarfs_ctx ectx = { - .ctx = { - .actor = efivarfs_actor, - }, - .sb = sfi->sb, - }; - struct file *file; - struct super_block *s = sfi->sb; - static bool rescan_done = true; - - if (action == PM_HIBERNATION_PREPARE) { - rescan_done = false; - return NOTIFY_OK; - } else if (action != PM_POST_HIBERNATION) { - return NOTIFY_DONE; - } - - if (rescan_done) - return NOTIFY_DONE; - - /* ensure single superblock is alive and pin it */ - if (!atomic_inc_not_zero(&s->s_active)) - return NOTIFY_DONE; - - pr_info("efivarfs: resyncing variable state\n"); - - path.dentry = sfi->sb->s_root; - - /* - * do not add SB_KERNMOUNT which a single superblock could - * expose to userspace and which also causes MNT_INTERNAL, see - * below - */ - path.mnt = vfs_kern_mount(&efivarfs_type, 0, - efivarfs_type.name, NULL); - if (IS_ERR(path.mnt)) { - pr_err("efivarfs: internal mount failed\n"); - /* - * We may be the last pinner of the superblock but - * calling efivarfs_kill_sb from within the notifier - * here would deadlock trying to unregister it - */ - INIT_WORK(&s->destroy_work, efivarfs_deactivate_super_work); - schedule_work(&s->destroy_work); - return PTR_ERR(path.mnt); - } - - /* path.mnt now has pin on superblock, so this must be above one */ - atomic_dec(&s->s_active); - - file = kernel_file_open(&path, O_RDONLY | O_DIRECTORY | O_NOATIME, - current_cred()); - /* - * safe even if last put because no MNT_INTERNAL means this - * will do delayed deactivate_super and not deadlock - */ - mntput(path.mnt); - if (IS_ERR(file)) - return NOTIFY_DONE; + /* Nothing for us to do. */ + return 0; +} - rescan_done = true; +static int efivarfs_unfreeze_fs(struct super_block *sb) +{ + struct dentry *child = NULL; /* - * First loop over the directory and verify each entry exists, - * removing it if it doesn't + * Unconditionally resync the variable state on a thaw request. + * Given the size of efivarfs it really doesn't matter to simply + * iterate through all of the entries and resync. Freeze/thaw + * requests are rare enough for that to not matter and the + * number of entries is pretty low too. So we really don't care. */ - file->f_pos = 2; /* skip . and .. */ - do { - ectx.dentry = NULL; - iterate_dir(file, &ectx.ctx); - if (ectx.dentry) { - pr_info("efivarfs: removing variable %pd\n", - ectx.dentry); - simple_recursive_removal(ectx.dentry, NULL); - dput(ectx.dentry); + pr_info("efivarfs: resyncing variable state\n"); + for (;;) { + int err; + unsigned long size = 0; + struct inode *inode; + struct efivar_entry *entry; + + child = find_next_child(sb->s_root, child); + if (!child) + break; + + inode = d_inode(child); + entry = efivar_entry(inode); + + err = efivar_entry_size(entry, &size); + if (err) + size = 0; + else + size += sizeof(__u32); + + inode_lock(inode); + i_size_write(inode, size); + inode_unlock(inode); + + /* The variable doesn't exist anymore, delete it. */ + if (!size) { + pr_info("efivarfs: removing variable %pd\n", child); + simple_recursive_removal(child, NULL); } - } while (ectx.dentry); - fput(file); - - /* - * then loop over variables, creating them if there's no matching - * dentry - */ - efivar_init(efivarfs_check_missing, sfi->sb, false); + } - return NOTIFY_OK; + efivar_init(efivarfs_check_missing, sb, false); + pr_info("efivarfs: finished resyncing variable state\n"); + return 0; } static int efivarfs_init_fs_context(struct fs_context *fc) @@ -598,9 +504,6 @@ static int efivarfs_init_fs_context(struct fs_context *fc) fc->s_fs_info = sfi; fc->ops = &efivarfs_context_ops; - sfi->pm_nb.notifier_call = efivarfs_pm_notify; - sfi->pm_nb.priority = 0; - return 0; } @@ -610,7 +513,6 @@ static void efivarfs_kill_sb(struct super_block *sb) blocking_notifier_chain_unregister(&efivar_ops_nh, &sfi->nb); kill_litter_super(sb); - unregister_pm_notifier(&sfi->pm_nb); kfree(sfi); } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 4fa0a0121288..60c7cc4c105c 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -150,10 +150,10 @@ io_retry: io->rq->bio.bi_iter.bi_sector = io->dev.m_pa >> 9; attached = 0; } - if (!attached++) - erofs_onlinefolio_split(folio); if (!bio_add_folio(&io->rq->bio, folio, len, cur)) goto io_retry; + if (!attached++) + erofs_onlinefolio_split(folio); io->dev.m_pa += len; } cur += len; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index cadec6b1b554..da6ee7c39290 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -357,7 +357,6 @@ static void erofs_default_options(struct erofs_sb_info *sbi) enum { Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, - Opt_err }; static const struct constant_table erofs_param_cache_strategy[] = { diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 5c061aaeeb45..b8e6b76c23d5 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -79,9 +79,6 @@ struct z_erofs_pcluster { /* L: whether partial decompression or not */ bool partial; - /* L: indicate several pageofs_outs or not */ - bool multibases; - /* L: whether extra buffer allocations are best-effort */ bool besteffort; @@ -1046,8 +1043,6 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f, break; erofs_onlinefolio_split(folio); - if (f->pcl->pageofs_out != (map->m_la & ~PAGE_MASK)) - f->pcl->multibases = true; if (f->pcl->length < offset + end - map->m_la) { f->pcl->length = offset + end - map->m_la; f->pcl->pageofs_out = map->m_la & ~PAGE_MASK; @@ -1093,7 +1088,6 @@ struct z_erofs_backend { struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES]; struct super_block *sb; struct z_erofs_pcluster *pcl; - /* pages with the longest decompressed length for deduplication */ struct page **decompressed_pages; /* pages to keep the compressed data */ @@ -1102,6 +1096,8 @@ struct z_erofs_backend { struct list_head decompressed_secondary_bvecs; struct page **pagepool; unsigned int onstack_used, nr_pages; + /* indicate if temporary copies should be preserved for later use */ + bool keepxcpy; }; struct z_erofs_bvec_item { @@ -1112,18 +1108,20 @@ struct z_erofs_bvec_item { static void z_erofs_do_decompressed_bvec(struct z_erofs_backend *be, struct z_erofs_bvec *bvec) { + int poff = bvec->offset + be->pcl->pageofs_out; struct z_erofs_bvec_item *item; - unsigned int pgnr; - - if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK) && - (bvec->end == PAGE_SIZE || - bvec->offset + bvec->end == be->pcl->length)) { - pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; - DBG_BUGON(pgnr >= be->nr_pages); - if (!be->decompressed_pages[pgnr]) { - be->decompressed_pages[pgnr] = bvec->page; + struct page **page; + + if (!(poff & ~PAGE_MASK) && (bvec->end == PAGE_SIZE || + bvec->offset + bvec->end == be->pcl->length)) { + DBG_BUGON((poff >> PAGE_SHIFT) >= be->nr_pages); + page = be->decompressed_pages + (poff >> PAGE_SHIFT); + if (!*page) { + *page = bvec->page; return; } + } else { + be->keepxcpy = true; } /* (cold path) one pcluster is requested multiple times */ @@ -1289,7 +1287,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) .alg = pcl->algorithmformat, .inplace_io = overlapped, .partial_decoding = pcl->partial, - .fillgaps = pcl->multibases, + .fillgaps = be->keepxcpy, .gfp = pcl->besteffort ? GFP_KERNEL : GFP_NOWAIT | __GFP_NORETRY }, be->pagepool); @@ -1346,7 +1344,6 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) pcl->length = 0; pcl->partial = true; - pcl->multibases = false; pcl->besteffort = false; pcl->bvset.nextpage = NULL; pcl->vcnt = 0; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 4bc264b854c4..d4dbffdedd08 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -2111,9 +2111,10 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, write_unlock_irq(&ep->lock); - if (!eavail && ep_schedule_timeout(to)) - timed_out = !schedule_hrtimeout_range(to, slack, - HRTIMER_MODE_ABS); + if (!eavail) + timed_out = !ep_schedule_timeout(to) || + !schedule_hrtimeout_range(to, slack, + HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* diff --git a/fs/exec.c b/fs/exec.c index 8e4ea5f1e64c..cfbb2b9ee3c9 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -115,66 +115,6 @@ bool path_noexec(const struct path *path) (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } -#ifdef CONFIG_USELIB -/* - * Note that a shared library must be both readable and executable due to - * security reasons. - * - * Also note that we take the address to load from the file itself. - */ -SYSCALL_DEFINE1(uselib, const char __user *, library) -{ - struct linux_binfmt *fmt; - struct file *file; - struct filename *tmp = getname(library); - int error = PTR_ERR(tmp); - static const struct open_flags uselib_flags = { - .open_flag = O_LARGEFILE | O_RDONLY, - .acc_mode = MAY_READ | MAY_EXEC, - .intent = LOOKUP_OPEN, - .lookup_flags = LOOKUP_FOLLOW, - }; - - if (IS_ERR(tmp)) - goto out; - - file = do_filp_open(AT_FDCWD, tmp, &uselib_flags); - putname(tmp); - error = PTR_ERR(file); - if (IS_ERR(file)) - goto out; - - /* - * Check do_open_execat() for an explanation. - */ - error = -EACCES; - if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) || - path_noexec(&file->f_path)) - goto exit; - - error = -ENOEXEC; - - read_lock(&binfmt_lock); - list_for_each_entry(fmt, &formats, lh) { - if (!fmt->load_shlib) - continue; - if (!try_module_get(fmt->module)) - continue; - read_unlock(&binfmt_lock); - error = fmt->load_shlib(file); - read_lock(&binfmt_lock); - put_binfmt(fmt); - if (error != -ENOEXEC) - break; - } - read_unlock(&binfmt_lock); -exit: - fput(file); -out: - return error; -} -#endif /* #ifdef CONFIG_USELIB */ - #ifdef CONFIG_MMU /* * The nascent bprm->mm is not visible until exec_mmap() but it can diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 128dd092916b..cdefea17986a 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -143,7 +143,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, if (err) goto out_err; dprintk("%s: found name: %s\n", __func__, nbuf); - tmp = lookup_one_unlocked(mnt_idmap(mnt), nbuf, parent, strlen(nbuf)); + tmp = lookup_one_unlocked(mnt_idmap(mnt), &QSTR(nbuf), parent); if (IS_ERR(tmp)) { dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); err = PTR_ERR(tmp); @@ -284,6 +284,7 @@ static int get_name(const struct path *path, char *name, struct dentry *child) }; struct getdents_callback buffer = { .ctx.actor = filldir_one, + .ctx.count = INT_MAX, .name = name, }; @@ -549,8 +550,7 @@ exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, } inode_lock(target_dir->d_inode); - nresult = lookup_one(mnt_idmap(mnt), nbuf, - target_dir, strlen(nbuf)); + nresult = lookup_one(mnt_idmap(mnt), &QSTR(nbuf), target_dir); if (!IS_ERR(nresult)) { if (unlikely(nresult->d_inode != result->d_inode)) { dput(nresult); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 2b8f9239bede..dd0ba0532e01 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -2271,12 +2271,12 @@ out_drop_write: if (err) return err; - err = freeze_super(sbi->sb, FREEZE_HOLDER_USERSPACE); + err = freeze_super(sbi->sb, FREEZE_HOLDER_KERNEL, NULL); if (err) return err; if (f2fs_readonly(sbi->sb)) { - err = thaw_super(sbi->sb, FREEZE_HOLDER_USERSPACE); + err = thaw_super(sbi->sb, FREEZE_HOLDER_KERNEL, NULL); if (err) return err; return -EROFS; @@ -2333,6 +2333,6 @@ recover_out: out_err: f2fs_up_write(&sbi->cp_global_sem); f2fs_up_write(&sbi->gc_lock); - thaw_super(sbi->sb, FREEZE_HOLDER_USERSPACE); + thaw_super(sbi->sb, FREEZE_HOLDER_KERNEL, NULL); return err; } diff --git a/fs/file_table.c b/fs/file_table.c index c04ed94cdc4b..138114d64307 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -102,7 +102,7 @@ EXPORT_SYMBOL_GPL(get_max_files); static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - files_stat.nr_files = get_nr_files(); + files_stat.nr_files = percpu_counter_sum_positive(&nr_files); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } diff --git a/fs/filesystems.c b/fs/filesystems.c index 58b9067b2391..95e5256821a5 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -156,15 +156,19 @@ static int fs_index(const char __user * __name) static int fs_name(unsigned int index, char __user * buf) { struct file_system_type * tmp; - int len, res; + int len, res = -EINVAL; read_lock(&file_systems_lock); - for (tmp = file_systems; tmp; tmp = tmp->next, index--) - if (index <= 0 && try_module_get(tmp->owner)) + for (tmp = file_systems; tmp; tmp = tmp->next, index--) { + if (index == 0) { + if (try_module_get(tmp->owner)) + res = 0; break; + } + } read_unlock(&file_systems_lock); - if (!tmp) - return -EINVAL; + if (res) + return res; /* OK, we got the reference, so we can safely block */ len = strlen(tmp->name) + 1; diff --git a/fs/fs_context.c b/fs/fs_context.c index 582d33e81117..666e61753aed 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -222,7 +222,7 @@ int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, char *value = strchr(key, '='); if (value) { - if (value == key) + if (unlikely(value == key)) continue; *value++ = 0; v_len = strlen(value); @@ -449,6 +449,10 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, printk(KERN_ERR "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; + case 'i': + printk(KERN_INFO "%s%s%pV\n", prefix ? prefix : "", + prefix ? ": " : "", &vaf); + break; default: printk(KERN_NOTICE "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); diff --git a/fs/fs_parser.c b/fs/fs_parser.c index e635a81e17d9..c092a9f79e32 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -380,58 +380,9 @@ EXPORT_SYMBOL(fs_param_is_path); #ifdef CONFIG_VALIDATE_FS_PARSER /** - * validate_constant_table - Validate a constant table - * @tbl: The constant table to validate. - * @tbl_size: The size of the table. - * @low: The lowest permissible value. - * @high: The highest permissible value. - * @special: One special permissible value outside of the range. - */ -bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, - int low, int high, int special) -{ - size_t i; - bool good = true; - - if (tbl_size == 0) { - pr_warn("VALIDATE C-TBL: Empty\n"); - return true; - } - - for (i = 0; i < tbl_size; i++) { - if (!tbl[i].name) { - pr_err("VALIDATE C-TBL[%zu]: Null\n", i); - good = false; - } else if (i > 0 && tbl[i - 1].name) { - int c = strcmp(tbl[i-1].name, tbl[i].name); - - if (c == 0) { - pr_err("VALIDATE C-TBL[%zu]: Duplicate %s\n", - i, tbl[i].name); - good = false; - } - if (c > 0) { - pr_err("VALIDATE C-TBL[%zu]: Missorted %s>=%s\n", - i, tbl[i-1].name, tbl[i].name); - good = false; - } - } - - if (tbl[i].value != special && - (tbl[i].value < low || tbl[i].value > high)) { - pr_err("VALIDATE C-TBL[%zu]: %s->%d const out of range (%d-%d)\n", - i, tbl[i].name, tbl[i].value, low, high); - good = false; - } - } - - return good; -} - -/** - * fs_validate_description - Validate a parameter description - * @name: The parameter name to search for. - * @desc: The parameter description to validate. + * fs_validate_description - Validate a parameter specification array + * @name: Owner name of the parameter specification array + * @desc: The parameter specification array to validate. */ bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 83ac192e7fdd..33b82529cb6e 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1676,7 +1676,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode, goto out_err; } - set_delayed_call(callback, page_put_link, &folio->page); + set_delayed_call(callback, page_put_link, folio); return folio_address(folio); diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 17ce9636a2b1..edcd6f18a8a8 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -120,7 +120,7 @@ static bool fuse_emit(struct file *file, struct dir_context *ctx, fuse_add_dirent_to_cache(file, dirent, ctx->pos); return dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino, - dirent->type); + dirent->type | FILLDIR_FLAG_NOINTR); } static int parse_dirfile(char *buf, size_t nbytes, struct file *file, @@ -419,7 +419,7 @@ static enum fuse_parse_result fuse_parse_cache(struct fuse_file *ff, if (ff->readdir.pos == ctx->pos) { res = FOUND_SOME; if (!dir_emit(ctx, dirent->name, dirent->namelen, - dirent->ino, dirent->type)) + dirent->ino, dirent->type | FILLDIR_FLAG_NOINTR)) return FOUND_ALL; ctx->pos = dirent->off; } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 44e5658b896c..436cf168a9f5 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -674,7 +674,7 @@ static int gfs2_sync_fs(struct super_block *sb, int wait) return sdp->sd_log_error; } -static int gfs2_do_thaw(struct gfs2_sbd *sdp) +static int gfs2_do_thaw(struct gfs2_sbd *sdp, enum freeze_holder who, const void *freeze_owner) { struct super_block *sb = sdp->sd_vfs; int error; @@ -682,7 +682,7 @@ static int gfs2_do_thaw(struct gfs2_sbd *sdp) error = gfs2_freeze_lock_shared(sdp); if (error) goto fail; - error = thaw_super(sb, FREEZE_HOLDER_USERSPACE); + error = thaw_super(sb, who, freeze_owner); if (!error) return 0; @@ -703,14 +703,14 @@ void gfs2_freeze_func(struct work_struct *work) if (test_bit(SDF_FROZEN, &sdp->sd_flags)) goto freeze_failed; - error = freeze_super(sb, FREEZE_HOLDER_USERSPACE); + error = freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL); if (error) goto freeze_failed; gfs2_freeze_unlock(sdp); set_bit(SDF_FROZEN, &sdp->sd_flags); - error = gfs2_do_thaw(sdp); + error = gfs2_do_thaw(sdp, FREEZE_HOLDER_USERSPACE, NULL); if (error) goto out; @@ -728,10 +728,13 @@ out: /** * gfs2_freeze_super - prevent further writes to the filesystem * @sb: the VFS structure for the filesystem + * @who: freeze flags + * @freeze_owner: owner of the freeze * */ -static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who) +static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) { struct gfs2_sbd *sdp = sb->s_fs_info; int error; @@ -744,7 +747,7 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who) } for (;;) { - error = freeze_super(sb, FREEZE_HOLDER_USERSPACE); + error = freeze_super(sb, who, freeze_owner); if (error) { fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", error); @@ -758,7 +761,7 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who) break; } - error = gfs2_do_thaw(sdp); + error = gfs2_do_thaw(sdp, who, freeze_owner); if (error) goto out; @@ -796,10 +799,13 @@ static int gfs2_freeze_fs(struct super_block *sb) /** * gfs2_thaw_super - reallow writes to the filesystem * @sb: the VFS structure for the filesystem + * @who: freeze flags + * @freeze_owner: owner of the freeze * */ -static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who) +static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) { struct gfs2_sbd *sdp = sb->s_fs_info; int error; @@ -814,7 +820,7 @@ static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who) atomic_inc(&sb->s_active); gfs2_freeze_unlock(sdp); - error = gfs2_do_thaw(sdp); + error = gfs2_do_thaw(sdp, who, freeze_owner); if (!error) { clear_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index ecc699f8d9fc..748125653d6c 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -174,10 +174,10 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len) switch (n) { case 0: - error = thaw_super(sdp->sd_vfs, FREEZE_HOLDER_USERSPACE); + error = thaw_super(sdp->sd_vfs, FREEZE_HOLDER_USERSPACE, NULL); break; case 1: - error = freeze_super(sdp->sd_vfs, FREEZE_HOLDER_USERSPACE); + error = freeze_super(sdp->sd_vfs, FREEZE_HOLDER_USERSPACE, NULL); break; default: return -EINVAL; diff --git a/fs/internal.h b/fs/internal.h index b9b3e29a73fd..393f6c5c24f6 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -66,6 +66,7 @@ int do_linkat(int olddfd, struct filename *old, int newdfd, int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode); +struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); /* * namespace.c @@ -343,3 +344,9 @@ static inline bool path_mounted(const struct path *path) void file_f_owner_release(struct file *file); bool file_seek_cur_needs_f_lock(struct file *file); int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map); +struct dentry *find_next_child(struct dentry *parent, struct dentry *prev); +int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags); +int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr); diff --git a/fs/ioctl.c b/fs/ioctl.c index c91fd2b46a77..69107a245b4c 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -396,8 +396,8 @@ static int ioctl_fsfreeze(struct file *filp) /* Freeze */ if (sb->s_op->freeze_super) - return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE); - return freeze_super(sb, FREEZE_HOLDER_USERSPACE); + return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL); + return freeze_super(sb, FREEZE_HOLDER_USERSPACE, NULL); } static int ioctl_fsthaw(struct file *filp) @@ -409,8 +409,8 @@ static int ioctl_fsthaw(struct file *filp) /* Thaw */ if (sb->s_op->thaw_super) - return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE); - return thaw_super(sb, FREEZE_HOLDER_USERSPACE); + return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL); + return thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL); } static int ioctl_file_dedupe_range(struct file *file, @@ -821,7 +821,8 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd, return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: - if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || + if (S_ISDIR(inode->i_mode) || + (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode)) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? @@ -856,7 +857,7 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd, return ioctl_file_dedupe_range(filp, argp); case FIONREAD: - if (!S_ISREG(inode->i_mode)) + if (!S_ISREG(inode->i_mode) || IS_ANON_FILE(inode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, @@ -881,7 +882,7 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd, return ioctl_get_fs_sysfs_path(filp, argp); default: - if (S_ISREG(inode->i_mode)) + if (S_ISREG(inode->i_mode) && !IS_ANON_FILE(inode)) return file_ioctl(filp, cmd, argp); break; } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 5b08bd417b28..233abf598f65 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -679,11 +679,12 @@ static int iomap_read_folio_sync(loff_t block_start, struct folio *folio, return submit_bio_wait(&bio); } -static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, - size_t len, struct folio *folio) +static int __iomap_write_begin(const struct iomap_iter *iter, size_t len, + struct folio *folio) { const struct iomap *srcmap = iomap_iter_srcmap(iter); struct iomap_folio_state *ifs; + loff_t pos = iter->pos; loff_t block_size = i_blocksize(iter->inode); loff_t block_start = round_down(pos, block_size); loff_t block_end = round_up(pos + len, block_size); @@ -741,10 +742,13 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, return 0; } -static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos, - size_t len) +static struct folio *__iomap_get_folio(struct iomap_iter *iter, size_t len) { const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; + loff_t pos = iter->pos; + + if (!mapping_large_folio_support(iter->inode->i_mapping)) + len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); if (folio_ops && folio_ops->get_folio) return folio_ops->get_folio(iter, pos, len); @@ -752,10 +756,11 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos, return iomap_get_folio(iter, pos, len); } -static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret, +static void __iomap_put_folio(struct iomap_iter *iter, size_t ret, struct folio *folio) { const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; + loff_t pos = iter->pos; if (folio_ops && folio_ops->put_folio) { folio_ops->put_folio(iter->inode, pos, ret, folio); @@ -765,6 +770,22 @@ static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret, } } +/* trim pos and bytes to within a given folio */ +static loff_t iomap_trim_folio_range(struct iomap_iter *iter, + struct folio *folio, size_t *offset, u64 *bytes) +{ + loff_t pos = iter->pos; + size_t fsize = folio_size(folio); + + WARN_ON_ONCE(pos < folio_pos(folio)); + WARN_ON_ONCE(pos >= folio_pos(folio) + fsize); + + *offset = offset_in_folio(folio, pos); + *bytes = min(*bytes, fsize - *offset); + + return pos; +} + static int iomap_write_begin_inline(const struct iomap_iter *iter, struct folio *folio) { @@ -774,14 +795,22 @@ static int iomap_write_begin_inline(const struct iomap_iter *iter, return iomap_read_inline_data(iter, folio); } -static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, - size_t len, struct folio **foliop) +/* + * Grab and prepare a folio for write based on iter state. Returns the folio, + * offset, and length. Callers can optionally pass a max length *plen, + * otherwise init to zero. + */ +static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop, + size_t *poffset, u64 *plen) { const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops; const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + u64 len = min_t(u64, SIZE_MAX, iomap_length(iter)); struct folio *folio; int status = 0; + len = min_not_zero(len, *plen); BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length); if (srcmap != &iter->iomap) BUG_ON(pos + len > srcmap->offset + srcmap->length); @@ -789,10 +818,7 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, if (fatal_signal_pending(current)) return -EINTR; - if (!mapping_large_folio_support(iter->inode->i_mapping)) - len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); - - folio = __iomap_get_folio(iter, pos, len); + folio = __iomap_get_folio(iter, len); if (IS_ERR(folio)) return PTR_ERR(folio); @@ -816,24 +842,24 @@ static int iomap_write_begin(struct iomap_iter *iter, loff_t pos, } } - if (pos + len > folio_pos(folio) + folio_size(folio)) - len = folio_pos(folio) + folio_size(folio) - pos; + pos = iomap_trim_folio_range(iter, folio, poffset, &len); if (srcmap->type == IOMAP_INLINE) status = iomap_write_begin_inline(iter, folio); else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) status = __block_write_begin_int(folio, pos, len, NULL, srcmap); else - status = __iomap_write_begin(iter, pos, len, folio); + status = __iomap_write_begin(iter, len, folio); if (unlikely(status)) goto out_unlock; *foliop = folio; + *plen = len; return 0; out_unlock: - __iomap_put_folio(iter, pos, 0, folio); + __iomap_put_folio(iter, 0, folio); return status; } @@ -883,10 +909,11 @@ static void iomap_write_end_inline(const struct iomap_iter *iter, * Returns true if all copied bytes have been written to the pagecache, * otherwise return false. */ -static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, - size_t copied, struct folio *folio) +static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied, + struct folio *folio) { const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; if (srcmap->type == IOMAP_INLINE) { iomap_write_end_inline(iter, folio, pos, copied); @@ -917,14 +944,14 @@ static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) struct folio *folio; loff_t old_size; size_t offset; /* Offset into folio */ - size_t bytes; /* Bytes to write to folio */ + u64 bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ u64 written; /* Bytes have been written */ - loff_t pos = iter->pos; + loff_t pos; bytes = iov_iter_count(i); retry: - offset = pos & (chunk - 1); + offset = iter->pos & (chunk - 1); bytes = min(chunk - offset, bytes); status = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); @@ -949,23 +976,21 @@ retry: break; } - status = iomap_write_begin(iter, pos, bytes, &folio); + status = iomap_write_begin(iter, &folio, &offset, &bytes); if (unlikely(status)) { - iomap_write_failed(iter->inode, pos, bytes); + iomap_write_failed(iter->inode, iter->pos, bytes); break; } if (iter->iomap.flags & IOMAP_F_STALE) break; - offset = offset_in_folio(folio, pos); - if (bytes > folio_size(folio) - offset) - bytes = folio_size(folio) - offset; + pos = iter->pos; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); - written = iomap_write_end(iter, pos, bytes, copied, folio) ? + written = iomap_write_end(iter, bytes, copied, folio) ? copied : 0; /* @@ -980,7 +1005,7 @@ retry: i_size_write(iter->inode, pos + written); iter->iomap.flags |= IOMAP_F_SIZE_CHANGED; } - __iomap_put_folio(iter, pos, written, folio); + __iomap_put_folio(iter, written, folio); if (old_size < pos) pagecache_isize_extended(iter->inode, old_size, pos); @@ -1276,22 +1301,17 @@ static int iomap_unshare_iter(struct iomap_iter *iter) do { struct folio *folio; size_t offset; - loff_t pos = iter->pos; bool ret; bytes = min_t(u64, SIZE_MAX, bytes); - status = iomap_write_begin(iter, pos, bytes, &folio); + status = iomap_write_begin(iter, &folio, &offset, &bytes); if (unlikely(status)) return status; if (iomap->flags & IOMAP_F_STALE) break; - offset = offset_in_folio(folio, pos); - if (bytes > folio_size(folio) - offset) - bytes = folio_size(folio) - offset; - - ret = iomap_write_end(iter, pos, bytes, bytes, folio); - __iomap_put_folio(iter, pos, bytes, folio); + ret = iomap_write_end(iter, bytes, bytes, folio); + __iomap_put_folio(iter, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; @@ -1351,11 +1371,10 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) do { struct folio *folio; size_t offset; - loff_t pos = iter->pos; bool ret; bytes = min_t(u64, SIZE_MAX, bytes); - status = iomap_write_begin(iter, pos, bytes, &folio); + status = iomap_write_begin(iter, &folio, &offset, &bytes); if (status) return status; if (iter->iomap.flags & IOMAP_F_STALE) @@ -1363,15 +1382,12 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) /* warn about zeroing folios beyond eof that won't write back */ WARN_ON_ONCE(folio_pos(folio) > iter->inode->i_size); - offset = offset_in_folio(folio, pos); - if (bytes > folio_size(folio) - offset) - bytes = folio_size(folio) - offset; folio_zero_range(folio, offset, bytes); folio_mark_accessed(folio); - ret = iomap_write_end(iter, pos, bytes, bytes, folio); - __iomap_put_folio(iter, pos, bytes, folio); + ret = iomap_write_end(iter, bytes, bytes, folio); + __iomap_put_folio(iter, bytes, folio); if (WARN_ON_ONCE(!ret)) return -EIO; diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index 9eab2c8ac3c5..455cc6f90be0 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -99,7 +99,11 @@ DEFINE_RANGE_EVENT(iomap_dio_rw_queued); { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" }, \ - { IOMAP_ATOMIC, "ATOMIC" } + { IOMAP_OVERWRITE_ONLY, "OVERWRITE_ONLY" }, \ + { IOMAP_UNSHARE, "UNSHARE" }, \ + { IOMAP_DAX, "DAX" }, \ + { IOMAP_ATOMIC, "ATOMIC" }, \ + { IOMAP_DONTCACHE, "DONTCACHE" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ @@ -107,7 +111,14 @@ DEFINE_RANGE_EVENT(iomap_dio_rw_queued); { IOMAP_F_SHARED, "SHARED" }, \ { IOMAP_F_MERGED, "MERGED" }, \ { IOMAP_F_BUFFER_HEAD, "BH" }, \ - { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" } + { IOMAP_F_XATTR, "XATTR" }, \ + { IOMAP_F_BOUNDARY, "BOUNDARY" }, \ + { IOMAP_F_ANON_WRITE, "ANON_WRITE" }, \ + { IOMAP_F_ATOMIC_BIO, "ATOMIC_BIO" }, \ + { IOMAP_F_PRIVATE, "PRIVATE" }, \ + { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" }, \ + { IOMAP_F_STALE, "STALE" } + #define IOMAP_DIO_STRINGS \ {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ @@ -138,7 +149,7 @@ DECLARE_EVENT_CLASS(iomap_class, __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr 0x%llx offset 0x%llx " - "length 0x%llx type %s flags %s", + "length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), @@ -146,7 +157,9 @@ DECLARE_EVENT_CLASS(iomap_class, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), - __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS)) + __entry->type, + __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), + __entry->flags) ) #define DEFINE_IOMAP_EVENT(name) \ @@ -185,7 +198,7 @@ TRACE_EVENT(iomap_writepage_map, __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx " - "addr 0x%llx offset 0x%llx length 0x%llx type %s flags %s", + "addr 0x%llx offset 0x%llx length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), @@ -195,7 +208,9 @@ TRACE_EVENT(iomap_writepage_map, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), - __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS)) + __entry->type, + __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), + __entry->flags) ); TRACE_EVENT(iomap_iter, diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 5124e196c2bf..c1719b5778a1 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -62,6 +62,21 @@ const struct super_operations kernfs_sops = { .show_options = kernfs_sop_show_options, .show_path = kernfs_sop_show_path, + + /* + * sysfs is built on top of kernfs and sysfs provides the power + * management infrastructure to support suspend/hibernate by + * writing to various files in /sys/power/. As filesystems may + * be automatically frozen during suspend/hibernate implementing + * freeze/thaw support for kernfs generically will cause + * deadlocks as the suspending/hibernation initiating task will + * hold a VFS lock that it will then wait upon to be released. + * If freeze/thaw for kernfs is needed talk to the VFS. + */ + .freeze_fs = NULL, + .unfreeze_fs = NULL, + .freeze_super = NULL, + .thaw_super = NULL, }; static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len, @@ -255,7 +270,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, dput(dentry); return ERR_PTR(-ENOMEM); } - dtmp = lookup_positive_unlocked(name, dentry, strlen(name)); + dtmp = lookup_noperm_positive_unlocked(&QSTR(name), dentry); dput(dentry); kfree(name); if (IS_ERR(dtmp)) diff --git a/fs/libfs.c b/fs/libfs.c index 6393d7c49ee6..9ea0ecc325a8 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -583,7 +583,7 @@ const struct file_operations simple_offset_dir_operations = { .fsync = noop_fsync, }; -static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) +struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { struct dentry *child = NULL, *d; @@ -603,6 +603,7 @@ static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev dput(prev); return child; } +EXPORT_SYMBOL(find_next_child); void simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) @@ -1647,10 +1648,16 @@ struct inode *alloc_anon_inode(struct super_block *s) * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; - inode->i_mode = S_IRUSR | S_IWUSR; + /* + * Historically anonymous inodes didn't have a type at all and + * userspace has come to rely on this. Internally they're just + * regular files but S_IFREG is masked off when reporting + * information to userspace. + */ + inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_flags |= S_PRIVATE; + inode->i_flags |= S_PRIVATE | S_ANON_INODE; simple_inode_init_ts(inode); return inode; } diff --git a/fs/mpage.c b/fs/mpage.c index ad7844de87c3..c5fd821fd30e 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -445,10 +445,9 @@ static void clean_buffers(struct folio *folio, unsigned first_unmapped) try_to_free_buffers(folio); } -static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc, - void *data) +static int mpage_write_folio(struct writeback_control *wbc, struct folio *folio, + struct mpage_data *mpd) { - struct mpage_data *mpd = data; struct bio *bio = mpd->bio; struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; @@ -656,14 +655,16 @@ mpage_writepages(struct address_space *mapping, struct mpage_data mpd = { .get_block = get_block, }; + struct folio *folio = NULL; struct blk_plug plug; - int ret; + int error; blk_start_plug(&plug); - ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd); + while ((folio = writeback_iter(mapping, wbc, folio, &error))) + error = mpage_write_folio(wbc, folio, &mpd); if (mpd.bio) mpage_bio_submit_write(mpd.bio); blk_finish_plug(&plug); - return ret; + return error; } EXPORT_SYMBOL(mpage_writepages); diff --git a/fs/namei.c b/fs/namei.c index 84a0e0b0111c..4bb889fc980b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -571,14 +571,14 @@ int inode_permission(struct mnt_idmap *idmap, int retval; retval = sb_permission(inode->i_sb, inode, mask); - if (retval) + if (unlikely(retval)) return retval; if (unlikely(mask & MAY_WRITE)) { /* * Nobody gets write access to an immutable file. */ - if (IS_IMMUTABLE(inode)) + if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; /* @@ -586,16 +586,16 @@ int inode_permission(struct mnt_idmap *idmap, * written back improperly if their true value is unknown * to the vfs. */ - if (HAS_UNMAPPED_ID(idmap, inode)) + if (unlikely(HAS_UNMAPPED_ID(idmap, inode))) return -EACCES; } retval = do_inode_permission(idmap, inode, mask); - if (retval) + if (unlikely(retval)) return retval; retval = devcgroup_inode_permission(inode, mask); - if (retval) + if (unlikely(retval)) return retval; return security_inode_permission(inode, mask); @@ -1915,13 +1915,13 @@ static const char *pick_link(struct nameidata *nd, struct path *link, unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); - if (!(nd->flags & LOOKUP_RCU)) { + if (unlikely(atime_needs_update(&last->link, inode))) { + if (nd->flags & LOOKUP_RCU) { + if (!try_to_unlazy(nd)) + return ERR_PTR(-ECHILD); + } touch_atime(&last->link); cond_resched(); - } else if (atime_needs_update(&last->link, inode)) { - if (!try_to_unlazy(nd)) - return ERR_PTR(-ECHILD); - touch_atime(&last->link); } error = security_inode_follow_link(link->dentry, inode, @@ -2434,9 +2434,12 @@ static int link_path_walk(const char *name, struct nameidata *nd) nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); - while (*name=='/') - name++; - if (!*name) { + if (*name == '/') { + do { + name++; + } while (unlikely(*name == '/')); + } + if (unlikely(!*name)) { nd->dir_mode = 0; // short-circuit the 'hardening' idiocy return 0; } @@ -2449,7 +2452,7 @@ static int link_path_walk(const char *name, struct nameidata *nd) idmap = mnt_idmap(nd->path.mnt); err = may_lookup(idmap, nd); - if (err) + if (unlikely(err)) return err; nd->last.name = name; @@ -2869,13 +2872,12 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, } EXPORT_SYMBOL(vfs_path_lookup); -static int lookup_one_common(struct mnt_idmap *idmap, - const char *name, struct dentry *base, int len, - struct qstr *this) +static int lookup_noperm_common(struct qstr *qname, struct dentry *base) { - this->name = name; - this->len = len; - this->hash = full_name_hash(base, name, len); + const char *name = qname->name; + u32 len = qname->len; + + qname->hash = full_name_hash(base, name, len); if (!len) return -EACCES; @@ -2892,139 +2894,135 @@ static int lookup_one_common(struct mnt_idmap *idmap, * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { - int err = base->d_op->d_hash(base, this); + int err = base->d_op->d_hash(base, qname); if (err < 0) return err; } + return 0; +} +static int lookup_one_common(struct mnt_idmap *idmap, + struct qstr *qname, struct dentry *base) +{ + int err; + err = lookup_noperm_common(qname, base); + if (err < 0) + return err; return inode_permission(idmap, base->d_inode, MAY_EXEC); } /** - * try_lookup_one_len - filesystem helper to lookup single pathname component - * @name: pathname component to lookup + * try_lookup_noperm - filesystem helper to lookup single pathname component + * @name: qstr storing pathname component to lookup * @base: base directory to lookup from - * @len: maximum length @len should be interpreted to * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist. The function does not try to create a dentry. * * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. + * not be called by generic code. It does no permission checking. * * No locks need be held - only a counted reference to @base is needed. * */ -struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len) +struct dentry *try_lookup_noperm(struct qstr *name, struct dentry *base) { - struct qstr this; int err; - err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this); + err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); - return lookup_dcache(&this, base, 0); + return lookup_dcache(name, base, 0); } -EXPORT_SYMBOL(try_lookup_one_len); +EXPORT_SYMBOL(try_lookup_noperm); /** - * lookup_one_len - filesystem helper to lookup single pathname component - * @name: pathname component to lookup + * lookup_noperm - filesystem helper to lookup single pathname component + * @name: qstr storing pathname component to lookup * @base: base directory to lookup from - * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. + * not be called by generic code. It does no permission checking. * * The caller must hold base->i_mutex. */ -struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) +struct dentry *lookup_noperm(struct qstr *name, struct dentry *base) { struct dentry *dentry; - struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_common(&nop_mnt_idmap, name, base, len, &this); + err = lookup_noperm_common(name, base); if (err) return ERR_PTR(err); - dentry = lookup_dcache(&this, base, 0); - return dentry ? dentry : __lookup_slow(&this, base, 0); + dentry = lookup_dcache(name, base, 0); + return dentry ? dentry : __lookup_slow(name, base, 0); } -EXPORT_SYMBOL(lookup_one_len); +EXPORT_SYMBOL(lookup_noperm); /** - * lookup_one - filesystem helper to lookup single pathname component + * lookup_one - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from - * @name: pathname component to lookup + * @name: qstr holding pathname component to lookup * @base: base directory to lookup from - * @len: maximum length @len should be interpreted to * - * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. + * This can be used for in-kernel filesystem clients such as file servers. * * The caller must hold base->i_mutex. */ -struct dentry *lookup_one(struct mnt_idmap *idmap, const char *name, - struct dentry *base, int len) +struct dentry *lookup_one(struct mnt_idmap *idmap, struct qstr *name, + struct dentry *base) { struct dentry *dentry; - struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); - err = lookup_one_common(idmap, name, base, len, &this); + err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); - dentry = lookup_dcache(&this, base, 0); - return dentry ? dentry : __lookup_slow(&this, base, 0); + dentry = lookup_dcache(name, base, 0); + return dentry ? dentry : __lookup_slow(name, base, 0); } EXPORT_SYMBOL(lookup_one); /** - * lookup_one_unlocked - filesystem helper to lookup single pathname component + * lookup_one_unlocked - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from - * @name: pathname component to lookup + * @name: qstr olding pathname component to lookup * @base: base directory to lookup from - * @len: maximum length @len should be interpreted to * - * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. + * This can be used for in-kernel filesystem clients such as file servers. * - * Unlike lookup_one_len, it should be called without the parent - * i_mutex held, and will take the i_mutex itself if necessary. + * Unlike lookup_one, it should be called without the parent + * i_rwsem held, and will take the i_rwsem itself if necessary. */ -struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, - const char *name, struct dentry *base, - int len) +struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct qstr *name, + struct dentry *base) { - struct qstr this; int err; struct dentry *ret; - err = lookup_one_common(idmap, name, base, len, &this); + err = lookup_one_common(idmap, name, base); if (err) return ERR_PTR(err); - ret = lookup_dcache(&this, base, 0); + ret = lookup_dcache(name, base, 0); if (!ret) - ret = lookup_slow(&this, base, 0); + ret = lookup_slow(name, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_unlocked); /** - * lookup_one_positive_unlocked - filesystem helper to lookup single - * pathname component + * lookup_one_positive_unlocked - lookup single pathname component * @idmap: idmap of the mount the lookup is performed from - * @name: pathname component to lookup + * @name: qstr holding pathname component to lookup * @base: base directory to lookup from - * @len: maximum length @len should be interpreted to * * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns * known positive or ERR_PTR(). This is what most of the users want. @@ -3033,16 +3031,15 @@ EXPORT_SYMBOL(lookup_one_unlocked); * time, so callers of lookup_one_unlocked() need to be very careful; pinned * positives have >d_inode stable, so this one avoids such problems. * - * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. + * This can be used for in-kernel filesystem clients such as file servers. * - * The helper should be called without i_mutex held. + * The helper should be called without i_rwsem held. */ struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, - const char *name, - struct dentry *base, int len) + struct qstr *name, + struct dentry *base) { - struct dentry *ret = lookup_one_unlocked(idmap, name, base, len); + struct dentry *ret = lookup_one_unlocked(idmap, name, base); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); @@ -3053,38 +3050,48 @@ struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, EXPORT_SYMBOL(lookup_one_positive_unlocked); /** - * lookup_one_len_unlocked - filesystem helper to lookup single pathname component + * lookup_noperm_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from - * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should - * not be called by generic code. + * not be called by generic code. It does no permission checking. * - * Unlike lookup_one_len, it should be called without the parent - * i_mutex held, and will take the i_mutex itself if necessary. + * Unlike lookup_noperm, it should be called without the parent + * i_rwsem held, and will take the i_rwsem itself if necessary. */ -struct dentry *lookup_one_len_unlocked(const char *name, - struct dentry *base, int len) +struct dentry *lookup_noperm_unlocked(struct qstr *name, struct dentry *base) { - return lookup_one_unlocked(&nop_mnt_idmap, name, base, len); + struct dentry *ret; + + ret = try_lookup_noperm(name, base); + if (!ret) + ret = lookup_slow(name, base, 0); + return ret; } -EXPORT_SYMBOL(lookup_one_len_unlocked); +EXPORT_SYMBOL(lookup_noperm_unlocked); /* - * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) + * Like lookup_noperm_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent - * _can_ become positive at any time, so callers of lookup_one_len_unlocked() + * _can_ become positive at any time, so callers of lookup_noperm_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. */ -struct dentry *lookup_positive_unlocked(const char *name, - struct dentry *base, int len) +struct dentry *lookup_noperm_positive_unlocked(struct qstr *name, + struct dentry *base) { - return lookup_one_positive_unlocked(&nop_mnt_idmap, name, base, len); + struct dentry *ret; + + ret = lookup_noperm_unlocked(name, base); + if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { + dput(ret); + ret = ERR_PTR(-ENOENT); + } + return ret; } -EXPORT_SYMBOL(lookup_positive_unlocked); +EXPORT_SYMBOL(lookup_noperm_positive_unlocked); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) @@ -5403,25 +5410,25 @@ EXPORT_SYMBOL(vfs_get_link); static char *__page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { - struct page *page; + struct folio *folio; struct address_space *mapping = inode->i_mapping; if (!dentry) { - page = find_get_page(mapping, 0); - if (!page) + folio = filemap_get_folio(mapping, 0); + if (IS_ERR(folio)) return ERR_PTR(-ECHILD); - if (!PageUptodate(page)) { - put_page(page); + if (!folio_test_uptodate(folio)) { + folio_put(folio); return ERR_PTR(-ECHILD); } } else { - page = read_mapping_page(mapping, 0, NULL); - if (IS_ERR(page)) - return (char*)page; + folio = read_mapping_folio(mapping, 0, NULL); + if (IS_ERR(folio)) + return ERR_CAST(folio); } - set_delayed_call(callback, page_put_link, page); + set_delayed_call(callback, page_put_link, folio); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); - return page_address(page); + return folio_address(folio); } const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, @@ -5431,6 +5438,17 @@ const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, } EXPORT_SYMBOL_GPL(page_get_link_raw); +/** + * page_get_link() - An implementation of the get_link inode_operation. + * @dentry: The directory entry which is the symlink. + * @inode: The inode for the symlink. + * @callback: Used to drop the reference to the symlink. + * + * Filesystems which store their symlinks in the page cache should use + * this to implement the get_link() member of their inode_operations. + * + * Return: A pointer to the NUL-terminated symlink. + */ const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { @@ -5440,12 +5458,25 @@ const char *page_get_link(struct dentry *dentry, struct inode *inode, nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } - EXPORT_SYMBOL(page_get_link); +/** + * page_put_link() - Drop the reference to the symlink. + * @arg: The folio which contains the symlink. + * + * This is used internally by page_get_link(). It is exported for use + * by filesystems which need to implement a variant of page_get_link() + * themselves. Despite the apparent symmetry, filesystems which use + * page_get_link() do not need to call page_put_link(). + * + * The argument, while it has a void pointer type, must be a pointer to + * the folio which was retrieved from the page cache. The delayed_call + * infrastructure is used to drop the reference count once the caller + * is done with the symlink. + */ void page_put_link(void *arg) { - put_page(arg); + folio_put(arg); } EXPORT_SYMBOL(page_put_link); diff --git a/fs/namespace.c b/fs/namespace.c index 98a5cd756e9a..552ad7f4d18b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -355,12 +355,13 @@ static struct mount *alloc_vfsmnt(const char *name) if (err) goto out_free_cache; - if (name) { + if (name) mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL_ACCOUNT); - if (!mnt->mnt_devname) - goto out_free_id; - } + else + mnt->mnt_devname = "none"; + if (!mnt->mnt_devname) + goto out_free_id; #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); @@ -787,15 +788,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); - smp_mb(); // see mntput_no_expire() + smp_mb(); // see mntput_no_expire() and do_umount() if (likely(!read_seqretry(&mount_lock, seq))) return 0; - if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { - mnt_add_count(mnt, -1); - return 1; - } lock_mount_hash(); - if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { + if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; @@ -1268,7 +1265,7 @@ struct vfsmount *vfs_create_mount(struct fs_context *fc) if (!fc->root) return ERR_PTR(-EINVAL); - mnt = alloc_vfsmnt(fc->source ?: "none"); + mnt = alloc_vfsmnt(fc->source); if (!mnt) return ERR_PTR(-ENOMEM); @@ -2048,6 +2045,7 @@ static int do_umount(struct mount *mnt, int flags) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { + smp_mb(); // paired with __legitimize_mnt() shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { @@ -3560,7 +3558,8 @@ static int can_move_mount_beneath(const struct path *from, * @mnt_from itself. This defeats the whole purpose of mounting * @mnt_from beneath @mnt_to. */ - if (propagation_would_overmount(parent_mnt_to, mnt_from, mp)) + if (check_mnt(mnt_from) && + propagation_would_overmount(parent_mnt_to, mnt_from, mp)) return -EINVAL; return 0; @@ -3718,15 +3717,14 @@ static int do_move_mount(struct path *old_path, if (err) goto out; - if (is_anon_ns(ns)) - ns->mntns_flags &= ~MNTNS_PROPAGATING; - /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: + if (is_anon_ns(ns)) + ns->mntns_flags &= ~MNTNS_PROPAGATING; unlock_mount(mp); if (!err) { if (attached) { @@ -5494,7 +5492,7 @@ static int statmount_sb_source(struct kstatmount *s, struct seq_file *seq) seq->buf[seq->count] = '\0'; seq->count = start; seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL)); - } else if (r->mnt_devname) { + } else { seq_puts(seq, r->mnt_devname); } return 0; @@ -5807,7 +5805,9 @@ static int grab_requested_root(struct mnt_namespace *ns, struct path *root) STATMOUNT_SB_SOURCE | \ STATMOUNT_OPT_ARRAY | \ STATMOUNT_OPT_SEC_ARRAY | \ - STATMOUNT_SUPPORTED_MASK) + STATMOUNT_SUPPORTED_MASK | \ + STATMOUNT_MNT_UIDMAP | \ + STATMOUNT_MNT_GIDMAP) static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id, struct mnt_namespace *ns) @@ -5842,13 +5842,29 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id, return err; s->root = root; - s->idmap = mnt_idmap(s->mnt); - if (s->mask & STATMOUNT_SB_BASIC) - statmount_sb_basic(s); + /* + * Note that mount properties in mnt->mnt_flags, mnt->mnt_idmap + * can change concurrently as we only hold the read-side of the + * namespace semaphore and mount properties may change with only + * the mount lock held. + * + * We could sample the mount lock sequence counter to detect + * those changes and retry. But it's not worth it. Worst that + * happens is that the mnt->mnt_idmap pointer is already changed + * while mnt->mnt_flags isn't or vica versa. So what. + * + * Both mnt->mnt_flags and mnt->mnt_idmap are set and retrieved + * via READ_ONCE()/WRITE_ONCE() and guard against theoretical + * torn read/write. That's all we care about right now. + */ + s->idmap = mnt_idmap(s->mnt); if (s->mask & STATMOUNT_MNT_BASIC) statmount_mnt_basic(s); + if (s->mask & STATMOUNT_SB_BASIC) + statmount_sb_basic(s); + if (s->mask & STATMOUNT_PROPAGATE_FROM) statmount_propagate_from(s); @@ -6160,6 +6176,10 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) return -ENOENT; + /* + * We only need to guard against mount topology changes as + * listmount() doesn't care about any mount properties. + */ scoped_guard(rwsem_read, &namespace_sem) ret = do_listmount(ns, kreq.mnt_id, last_mnt_id, kmnt_ids, nr_mnt_ids, (flags & LISTMOUNT_REVERSE)); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 02c916a55020..6d63b958c4bb 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1105,6 +1105,8 @@ struct nfs_server *nfs_create_server(struct fs_context *fc) if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) server->namelen = NFS2_MAXNAMLEN; } + /* Linux 'subtree_check' borkenness mandates this setting */ + server->fh_expire_type = NFS_FH_VOL_RENAME; if (!(fattr->valid & NFS_ATTR_FATTR)) { error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh, @@ -1200,6 +1202,10 @@ void nfs_clients_init(struct net *net) #if IS_ENABLED(CONFIG_NFS_V4) idr_init(&nn->cb_ident_idr); #endif +#if IS_ENABLED(CONFIG_NFS_V4_1) + INIT_LIST_HEAD(&nn->nfs4_data_server_cache); + spin_lock_init(&nn->nfs4_data_server_lock); +#endif spin_lock_init(&nn->nfs_client_lock); nn->boot_time = ktime_get_real(); memset(&nn->rpcstats, 0, sizeof(nn->rpcstats)); @@ -1216,6 +1222,9 @@ void nfs_clients_exit(struct net *net) nfs_cleanup_cb_ident_idr(net); WARN_ON_ONCE(!list_empty(&nn->nfs_client_list)); WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list)); +#if IS_ENABLED(CONFIG_NFS_V4_1) + WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache)); +#endif } #ifdef CONFIG_PROC_FS diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bd23fc736b39..d0e0b435a843 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2676,6 +2676,18 @@ nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data) unblock_revalidate(new_dentry); } +static bool nfs_rename_is_unsafe_cross_dir(struct dentry *old_dentry, + struct dentry *new_dentry) +{ + struct nfs_server *server = NFS_SB(old_dentry->d_sb); + + if (old_dentry->d_parent != new_dentry->d_parent) + return false; + if (server->fh_expire_type & NFS_FH_RENAME_UNSAFE) + return !(server->fh_expire_type & NFS_FH_NOEXPIRE_WITH_OPEN); + return true; +} + /* * RENAME * FIXME: Some nfsds, like the Linux user space nfsd, may generate a @@ -2763,7 +2775,8 @@ int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } - if (S_ISREG(old_inode->i_mode)) + if (S_ISREG(old_inode->i_mode) && + nfs_rename_is_unsafe_cross_dir(old_dentry, new_dentry)) nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, must_unblock ? nfs_unblock_rename : NULL); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index f32f8d7c9122..48d89716193a 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -757,7 +757,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) { struct nfs_direct_req *dreq = hdr->dreq; struct nfs_commit_info cinfo; - struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct inode *inode = dreq->inode; int flags = NFS_ODIRECT_DONE; @@ -786,6 +785,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) spin_unlock(&inode->i_lock); while (!list_empty(&hdr->pages)) { + struct nfs_page *req; req = nfs_list_entry(hdr->pages.next); nfs_list_remove_request(req); diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 4fa304fa5bc4..29d9234d5c08 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -76,6 +76,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, struct page *scratch; struct list_head dsaddrs; struct nfs4_pnfs_ds_addr *da; + struct net *net = server->nfs_client->cl_net; /* set up xdr stream */ scratch = alloc_page(gfp_flags); @@ -159,8 +160,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, mp_count = be32_to_cpup(p); /* multipath count */ for (j = 0; j < mp_count; j++) { - da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, - &stream, gfp_flags); + da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); } @@ -170,7 +170,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_free_deviceid; } - dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + dsaddr->ds_list[i] = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags); if (!dsaddr->ds_list[i]) goto out_err_drain_dsaddrs; trace_fl_getdevinfo(server, &pdev->dev_id, dsaddr->ds_list[i]->ds_remotestr); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 61ad269c825f..e6909cafab68 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1329,7 +1329,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task, hdr->args.offset, hdr->args.count, &hdr->res.op_status, OP_READ, task->tk_status); - trace_ff_layout_read_error(hdr); + trace_ff_layout_read_error(hdr, task->tk_status); } err = ff_layout_async_handle_error(task, hdr->args.context->state, @@ -1502,7 +1502,7 @@ static int ff_layout_write_done_cb(struct rpc_task *task, hdr->args.offset, hdr->args.count, &hdr->res.op_status, OP_WRITE, task->tk_status); - trace_ff_layout_write_error(hdr); + trace_ff_layout_write_error(hdr, task->tk_status); } err = ff_layout_async_handle_error(task, hdr->args.context->state, @@ -1551,7 +1551,7 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, data->args.offset, data->args.count, &data->res.op_status, OP_COMMIT, task->tk_status); - trace_ff_layout_commit_error(data); + trace_ff_layout_commit_error(data, task->tk_status); } err = ff_layout_async_handle_error(task, NULL, data->ds_clp, diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index e58bedfb1dcc..4a304cf17c4b 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -49,6 +49,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, struct nfs4_pnfs_ds_addr *da; struct nfs4_ff_layout_ds *new_ds = NULL; struct nfs4_ff_ds_version *ds_versions = NULL; + struct net *net = server->nfs_client->cl_net; u32 mp_count; u32 version_count; __be32 *p; @@ -80,8 +81,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, for (i = 0; i < mp_count; i++) { /* multipath ds */ - da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net, - &stream, gfp_flags); + da = nfs4_decode_mp_ds_addr(net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); } @@ -149,7 +149,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, new_ds->ds_versions = ds_versions; new_ds->ds_versions_cnt = version_count; - new_ds->ds = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags); + new_ds->ds = nfs4_pnfs_ds_add(net, &dsaddrs, gfp_flags); if (!new_ds->ds) goto out_err_drain_dsaddrs; diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index 5c21caeae075..4ec952f9f47d 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -278,6 +278,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, new = __nfs_local_open_fh(clp, cred, fh, nfl, mode); if (IS_ERR(new)) return NULL; + rcu_read_lock(); /* try to swap in the pointer */ spin_lock(&clp->cl_uuid.lock); nf = rcu_dereference_protected(*pnf, 1); @@ -287,7 +288,6 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, rcu_assign_pointer(*pnf, nf); } spin_unlock(&clp->cl_uuid.lock); - rcu_read_lock(); } nf = nfs_local_file_get(nf); rcu_read_unlock(); diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index a68b21603ea9..6ba3ea39e928 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -31,7 +31,11 @@ struct nfs_net { unsigned short nfs_callback_tcpport; unsigned short nfs_callback_tcpport6; int cb_users[NFS4_MAX_MINOR_VERSION + 1]; -#endif +#endif /* CONFIG_NFS_V4 */ +#if IS_ENABLED(CONFIG_NFS_V4_1) + struct list_head nfs4_data_server_cache; + spinlock_t nfs4_data_server_lock; +#endif /* CONFIG_NFS_V4_1 */ struct nfs_netns_client *nfs_client; spinlock_t nfs_client_lock; ktime_t boot_time; diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 18d8f6529f61..a126eb31f62f 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -104,7 +104,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type, bool rcu) switch (status) { case 0: - status = nfs_refresh_inode(inode, res.fattr); + nfs_refresh_inode(inode, res.fattr); break; case -EPFNOSUPPORT: case -EPROTONOSUPPORT: diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 970f28dbf253..b1d2122bd5a7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -671,6 +671,15 @@ nfs4_async_handle_exception(struct rpc_task *task, struct nfs_server *server, struct nfs_client *clp = server->nfs_client; int ret; + if ((task->tk_rpc_status == -ENETDOWN || + task->tk_rpc_status == -ENETUNREACH) && + task->tk_flags & RPC_TASK_NETUNREACH_FATAL) { + exception->delay = 0; + exception->recovering = 0; + exception->retry = 0; + return -EIO; + } + ret = nfs4_do_handle_exception(server, errorcode, exception); if (exception->delay) { int ret2 = nfs4_exception_should_retrans(server, exception); @@ -7074,10 +7083,18 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, struct nfs4_unlockdata *p; struct nfs4_state *state = lsp->ls_state; struct inode *inode = state->inode; + struct nfs_lock_context *l_ctx; p = kzalloc(sizeof(*p), GFP_KERNEL); if (p == NULL) return NULL; + l_ctx = nfs_get_lock_context(ctx); + if (!IS_ERR(l_ctx)) { + p->l_ctx = l_ctx; + } else { + kfree(p); + return NULL; + } p->arg.fh = NFS_FH(inode); p->arg.fl = &p->fl; p->arg.seqid = seqid; @@ -7085,7 +7102,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->lsp = lsp; /* Ensure we don't close file until we're done freeing locks! */ p->ctx = get_nfs_open_context(ctx); - p->l_ctx = nfs_get_lock_context(ctx); locks_init_lock(&p->fl); locks_copy_lock(&p->fl, fl); p->server = NFS_SERVER(inode); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index bc67fe6801b1..deab4c0e21a0 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -2051,13 +2051,15 @@ TRACE_EVENT(fl_getdevinfo, DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, TP_PROTO( - const struct nfs_pgio_header *hdr + const struct nfs_pgio_header *hdr, + int error ), - TP_ARGS(hdr), + TP_ARGS(hdr, error), TP_STRUCT__entry( __field(unsigned long, error) + __field(unsigned long, nfs_error) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) @@ -2073,7 +2075,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, TP_fast_assign( const struct inode *inode = hdr->inode; - __entry->error = hdr->res.op_status; + __entry->error = -error; + __entry->nfs_error = hdr->res.op_status; __entry->fhandle = nfs_fhandle_hash(hdr->args.fh); __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; @@ -2088,7 +2091,8 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s", + "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s " + "nfs_error=%lu (%s)", -__entry->error, show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -2096,28 +2100,32 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, __entry->fhandle, __entry->offset, __entry->count, __entry->stateid_seq, __entry->stateid_hash, - __get_str(dstaddr) + __get_str(dstaddr), __entry->nfs_error, + show_nfs4_status(__entry->nfs_error) ) ); #define DEFINE_NFS4_FLEXFILES_IO_EVENT(name) \ DEFINE_EVENT(nfs4_flexfiles_io_event, name, \ TP_PROTO( \ - const struct nfs_pgio_header *hdr \ + const struct nfs_pgio_header *hdr, \ + int error \ ), \ - TP_ARGS(hdr)) + TP_ARGS(hdr, error)) DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_read_error); DEFINE_NFS4_FLEXFILES_IO_EVENT(ff_layout_write_error); TRACE_EVENT(ff_layout_commit_error, TP_PROTO( - const struct nfs_commit_data *data + const struct nfs_commit_data *data, + int error ), - TP_ARGS(data), + TP_ARGS(data, error), TP_STRUCT__entry( __field(unsigned long, error) + __field(unsigned long, nfs_error) __field(dev_t, dev) __field(u32, fhandle) __field(u64, fileid) @@ -2131,7 +2139,8 @@ TRACE_EVENT(ff_layout_commit_error, TP_fast_assign( const struct inode *inode = data->inode; - __entry->error = data->res.op_status; + __entry->error = -error; + __entry->nfs_error = data->res.op_status; __entry->fhandle = nfs_fhandle_hash(data->args.fh); __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; @@ -2142,14 +2151,15 @@ TRACE_EVENT(ff_layout_commit_error, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%llu count=%u dstaddr=%s", + "offset=%llu count=%u dstaddr=%s nfs_error=%lu (%s)", -__entry->error, show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, __entry->offset, __entry->count, - __get_str(dstaddr) + __get_str(dstaddr), __entry->nfs_error, + show_nfs4_status(__entry->nfs_error) ) ); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5f582713bf05..3adb7d0dbec7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -745,6 +745,14 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, return remaining; } +static void pnfs_reset_return_info(struct pnfs_layout_hdr *lo) +{ + struct pnfs_layout_segment *lseg; + + list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) + pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0); +} + static void pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo, struct list_head *free_me, @@ -1246,21 +1254,15 @@ static void pnfs_clear_layoutcommit(struct inode *inode, static void pnfs_layoutreturn_retry_later_locked(struct pnfs_layout_hdr *lo, const nfs4_stateid *arg_stateid, - const struct pnfs_layout_range *range) + const struct pnfs_layout_range *range, + struct list_head *freeme) { - const struct pnfs_layout_segment *lseg; - u32 seq = be32_to_cpu(arg_stateid->seqid); - if (pnfs_layout_is_valid(lo) && - nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) { - list_for_each_entry(lseg, &lo->plh_return_segs, pls_list) { - if (pnfs_seqid_is_newer(lseg->pls_seq, seq) || - !pnfs_should_free_range(&lseg->pls_range, range)) - continue; - pnfs_set_plh_return_info(lo, range->iomode, seq); - break; - } - } + nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid)) + pnfs_reset_return_info(lo); + else + pnfs_mark_layout_stateid_invalid(lo, freeme); + pnfs_clear_layoutreturn_waitbit(lo); } void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo, @@ -1268,11 +1270,12 @@ void pnfs_layoutreturn_retry_later(struct pnfs_layout_hdr *lo, const struct pnfs_layout_range *range) { struct inode *inode = lo->plh_inode; + LIST_HEAD(freeme); spin_lock(&inode->i_lock); - pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range); - pnfs_clear_layoutreturn_waitbit(lo); + pnfs_layoutreturn_retry_later_locked(lo, arg_stateid, range, &freeme); spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&freeme); } void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, @@ -1292,6 +1295,7 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq); pnfs_free_returned_lsegs(lo, &freeme, range, seq); pnfs_set_layout_stateid(lo, stateid, NULL, true); + pnfs_reset_return_info(lo); } else pnfs_mark_layout_stateid_invalid(lo, &freeme); out_unlock: @@ -1661,6 +1665,18 @@ int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, /* Was there an RPC level error? If not, retry */ if (task->tk_rpc_status == 0) break; + /* + * Is there a fatal network level error? + * If so release the layout, but flag the error. + */ + if ((task->tk_rpc_status == -ENETDOWN || + task->tk_rpc_status == -ENETUNREACH) && + task->tk_flags & RPC_TASK_NETUNREACH_FATAL) { + *ret = 0; + (*respp)->lrs_present = 0; + retval = -EIO; + break; + } /* If the call was not sent, let caller handle it */ if (!RPC_WAS_SENT(task)) return 0; @@ -1695,6 +1711,7 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, struct inode *inode = args->inode; const nfs4_stateid *res_stateid = NULL; struct nfs4_xdr_opaque_data *ld_private = args->ld_private; + LIST_HEAD(freeme); switch (ret) { case -NFS4ERR_BADSESSION: @@ -1703,9 +1720,9 @@ void pnfs_roc_release(struct nfs4_layoutreturn_args *args, case -NFS4ERR_NOMATCHING_LAYOUT: spin_lock(&inode->i_lock); pnfs_layoutreturn_retry_later_locked(lo, &args->stateid, - &args->range); - pnfs_clear_layoutreturn_waitbit(lo); + &args->range, &freeme); spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&freeme); break; case 0: if (res->lrs_present) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 30d2613e912b..91ff877185c8 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -60,6 +60,7 @@ struct nfs4_pnfs_ds { struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ char *ds_remotestr; /* comma sep list of addrs */ struct list_head ds_addrs; + const struct net *ds_net; struct nfs_client *ds_clp; refcount_t ds_count; unsigned long ds_state; @@ -415,7 +416,8 @@ int pnfs_generic_commit_pagelist(struct inode *inode, int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max); void pnfs_generic_write_commit_done(struct rpc_task *task, void *data); void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds); -struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs, +struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(const struct net *net, + struct list_head *dsaddrs, gfp_t gfp_flags); void nfs4_pnfs_v3_ds_connect_unload(void); int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index dbef837e871a..91ef486f40b9 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -16,6 +16,7 @@ #include "nfs4session.h" #include "internal.h" #include "pnfs.h" +#include "netns.h" #define NFSDBG_FACILITY NFSDBG_PNFS @@ -504,14 +505,14 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist); /* * Data server cache * - * Data servers can be mapped to different device ids. - * nfs4_pnfs_ds reference counting + * Data servers can be mapped to different device ids, but should + * never be shared between net namespaces. + * + * nfs4_pnfs_ds reference counting: * - set to 1 on allocation * - incremented when a device id maps a data server already in the cache. * - decremented when deviceid is removed from the cache. */ -static DEFINE_SPINLOCK(nfs4_ds_cache_lock); -static LIST_HEAD(nfs4_data_server_cache); /* Debug routines */ static void @@ -604,11 +605,11 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1, * Lookup DS by addresses. nfs4_ds_cache_lock is held */ static struct nfs4_pnfs_ds * -_data_server_lookup_locked(const struct list_head *dsaddrs) +_data_server_lookup_locked(const struct nfs_net *nn, const struct list_head *dsaddrs) { struct nfs4_pnfs_ds *ds; - list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) + list_for_each_entry(ds, &nn->nfs4_data_server_cache, ds_node) if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) return ds; return NULL; @@ -653,10 +654,11 @@ static void destroy_ds(struct nfs4_pnfs_ds *ds) void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds) { - if (refcount_dec_and_lock(&ds->ds_count, - &nfs4_ds_cache_lock)) { + struct nfs_net *nn = net_generic(ds->ds_net, nfs_net_id); + + if (refcount_dec_and_lock(&ds->ds_count, &nn->nfs4_data_server_lock)) { list_del_init(&ds->ds_node); - spin_unlock(&nfs4_ds_cache_lock); + spin_unlock(&nn->nfs4_data_server_lock); destroy_ds(ds); } } @@ -716,8 +718,9 @@ out_err: * uncached and return cached struct nfs4_pnfs_ds. */ struct nfs4_pnfs_ds * -nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) +nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, gfp_t gfp_flags) { + struct nfs_net *nn = net_generic(net, nfs_net_id); struct nfs4_pnfs_ds *tmp_ds, *ds = NULL; char *remotestr; @@ -733,16 +736,17 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) /* this is only used for debugging, so it's ok if its NULL */ remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags); - spin_lock(&nfs4_ds_cache_lock); - tmp_ds = _data_server_lookup_locked(dsaddrs); + spin_lock(&nn->nfs4_data_server_lock); + tmp_ds = _data_server_lookup_locked(nn, dsaddrs); if (tmp_ds == NULL) { INIT_LIST_HEAD(&ds->ds_addrs); list_splice_init(dsaddrs, &ds->ds_addrs); ds->ds_remotestr = remotestr; refcount_set(&ds->ds_count, 1); INIT_LIST_HEAD(&ds->ds_node); + ds->ds_net = net; ds->ds_clp = NULL; - list_add(&ds->ds_node, &nfs4_data_server_cache); + list_add(&ds->ds_node, &nn->nfs4_data_server_cache); dprintk("%s add new data server %s\n", __func__, ds->ds_remotestr); } else { @@ -754,7 +758,7 @@ nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags) refcount_read(&tmp_ds->ds_count)); ds = tmp_ds; } - spin_unlock(&nfs4_ds_cache_lock); + spin_unlock(&nn->nfs4_data_server_lock); out: return ds; } diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 1c62a5a9f51d..58146e935402 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -40,31 +40,31 @@ static const char *nfs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct page *page; + struct folio *folio; void *err; if (!dentry) { err = ERR_PTR(nfs_revalidate_mapping_rcu(inode)); if (err) return err; - page = find_get_page(inode->i_mapping, 0); - if (!page) + folio = filemap_get_folio(inode->i_mapping, 0); + if (IS_ERR(folio)) return ERR_PTR(-ECHILD); - if (!PageUptodate(page)) { - put_page(page); + if (!folio_test_uptodate(folio)) { + folio_put(folio); return ERR_PTR(-ECHILD); } } else { err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); if (err) return err; - page = read_cache_page(&inode->i_data, 0, nfs_symlink_filler, + folio = read_cache_folio(&inode->i_data, 0, nfs_symlink_filler, NULL); - if (IS_ERR(page)) - return ERR_CAST(page); + if (IS_ERR(folio)) + return ERR_CAST(folio); } - set_delayed_call(done, page_put_link, page); - return page_address(page); + set_delayed_call(done, page_put_link, folio); + return folio_address(folio); } /* diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index bf77399696a7..b55467911648 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -464,18 +464,17 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) sdentry = NULL; do { - int slen; dput(sdentry); sillycounter++; - slen = scnprintf(silly, sizeof(silly), - SILLYNAME_PREFIX "%0*llx%0*x", - SILLYNAME_FILEID_LEN, fileid, - SILLYNAME_COUNTER_LEN, sillycounter); + scnprintf(silly, sizeof(silly), + SILLYNAME_PREFIX "%0*llx%0*x", + SILLYNAME_FILEID_LEN, fileid, + SILLYNAME_COUNTER_LEN, sillycounter); dfprintk(VFS, "NFS: trying to rename %pd to %s\n", dentry, silly); - sdentry = lookup_one_len(silly, dentry->d_parent, slen); + sdentry = lookup_noperm(&QSTR(silly), dentry->d_parent); /* * N.B. Better to return EBUSY here ... it could be * dangerous to delete the file while it's in use. diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 372bdcf5e07a..ac1731eb34ab 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -284,7 +284,9 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, inode_lock_nested(inode, I_MUTEX_PARENT); - child = lookup_one_len(argp->name, parent, argp->len); + child = lookup_one(&nop_mnt_idmap, + &QSTR_LEN(argp->name, argp->len), + parent); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); goto out; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index a7a07470c1f8..ef4971d71ac4 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1001,7 +1001,9 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, } else dchild = dget(dparent); } else - dchild = lookup_positive_unlocked(name, dparent, namlen); + dchild = lookup_one_positive_unlocked(&nop_mnt_idmap, + &QSTR_LEN(name, namlen), + dparent); if (IS_ERR(dchild)) return rv; if (d_mountpoint(dchild)) diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index b397246dae7b..fd560dcf6059 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -266,7 +266,9 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, inode_lock_nested(inode, I_MUTEX_PARENT); - child = lookup_one_len(open->op_fname, parent, open->op_fnamelen); + child = lookup_one(&nop_mnt_idmap, + &QSTR_LEN(open->op_fname, open->op_fnamelen), + parent); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); goto out; diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index c1d9bd07285f..acde3edab733 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -218,7 +218,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) /* lock the parent */ inode_lock(d_inode(dir)); - dentry = lookup_one_len(dname, dir, HEXDIR_LEN-1); + dentry = lookup_one(&nop_mnt_idmap, &QSTR(dname), dir); if (IS_ERR(dentry)) { status = PTR_ERR(dentry); goto out_unlock; @@ -316,7 +316,8 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) list_for_each_entry_safe(entry, tmp, &ctx.names, list) { if (!status) { struct dentry *dentry; - dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1); + dentry = lookup_one(&nop_mnt_idmap, + &QSTR(entry->name), dir); if (IS_ERR(dentry)) { status = PTR_ERR(dentry); break; @@ -339,16 +340,16 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) } static int -nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn) +nfsd4_unlink_clid_dir(char *name, struct nfsd_net *nn) { struct dentry *dir, *dentry; int status; - dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name); + dprintk("NFSD: nfsd4_unlink_clid_dir. name %s\n", name); dir = nn->rec_file->f_path.dentry; inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - dentry = lookup_one_len(name, dir, namlen); + dentry = lookup_one(&nop_mnt_idmap, &QSTR(name), dir); if (IS_ERR(dentry)) { status = PTR_ERR(dentry); goto out_unlock; @@ -408,7 +409,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) if (status < 0) goto out_drop_write; - status = nfsd4_unlink_clid_dir(dname, HEXDIR_LEN-1, nn); + status = nfsd4_unlink_clid_dir(dname, nn); nfs4_reset_creds(original_cred); if (status == 0) { vfs_fsync(nn->rec_file, 0); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index e67420729ecd..fe876395985a 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3812,7 +3812,9 @@ nfsd4_encode_entry4_fattr(struct nfsd4_readdir *cd, const char *name, __be32 nfserr; int ignore_crossmnt = 0; - dentry = lookup_positive_unlocked(name, cd->rd_fhp->fh_dentry, namlen); + dentry = lookup_one_positive_unlocked(&nop_mnt_idmap, + &QSTR_LEN(name, namlen), + cd->rd_fhp->fh_dentry); if (IS_ERR(dentry)) return nfserrno(PTR_ERR(dentry)); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 6dda081eb24c..6370ac0a85fd 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -312,7 +312,8 @@ nfsd_proc_create(struct svc_rqst *rqstp) } inode_lock_nested(dirfhp->fh_dentry->d_inode, I_MUTEX_PARENT); - dchild = lookup_one_len(argp->name, dirfhp->fh_dentry, argp->len); + dchild = lookup_one(&nop_mnt_idmap, &QSTR_LEN(argp->name, argp->len), + dirfhp->fh_dentry); if (IS_ERR(dchild)) { resp->status = nfserrno(PTR_ERR(dchild)); goto out_unlock; @@ -331,7 +332,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) */ resp->status = nfserr_acces; if (!newfhp->fh_dentry) { - printk(KERN_WARNING + printk(KERN_WARNING "nfsd_proc_create: file handle not verified\n"); goto out_unlock; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9abdc4b75813..160a839af405 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -264,7 +264,8 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_nfserr; } } else { - dentry = lookup_one_len_unlocked(name, dparent, len); + dentry = lookup_one_unlocked(&nop_mnt_idmap, + &QSTR_LEN(name, len), dparent); host_err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_nfserr; @@ -922,7 +923,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, * directories, but we never have and it doesn't seem to have * caused anyone a problem. If we were to change this, note * also that our filldir callbacks would need a variant of - * lookup_one_len that doesn't check permissions. + * lookup_one_positive_unlocked() that doesn't check permissions. */ if (type == S_IFREG) may_flags |= NFSD_MAY_OWNER_OVERRIDE; @@ -1554,7 +1555,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, return nfserrno(host_err); inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); - dchild = lookup_one_len(fname, dentry, flen); + dchild = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry); host_err = PTR_ERR(dchild); if (IS_ERR(dchild)) { err = nfserrno(host_err); @@ -1659,7 +1660,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, dentry = fhp->fh_dentry; inode_lock_nested(dentry->d_inode, I_MUTEX_PARENT); - dnew = lookup_one_len(fname, dentry, flen); + dnew = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry); if (IS_ERR(dnew)) { err = nfserrno(PTR_ERR(dnew)); inode_unlock(dentry->d_inode); @@ -1734,7 +1735,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, dirp = d_inode(ddir); inode_lock_nested(dirp, I_MUTEX_PARENT); - dnew = lookup_one_len(name, ddir, len); + dnew = lookup_one(&nop_mnt_idmap, &QSTR_LEN(name, len), ddir); if (IS_ERR(dnew)) { host_err = PTR_ERR(dnew); goto out_unlock; @@ -1867,7 +1868,7 @@ retry: if (err != nfs_ok) goto out_unlock; - odentry = lookup_one_len(fname, fdentry, flen); + odentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), fdentry); host_err = PTR_ERR(odentry); if (IS_ERR(odentry)) goto out_nfserr; @@ -1880,7 +1881,7 @@ retry: goto out_dput_old; type = d_inode(odentry)->i_mode & S_IFMT; - ndentry = lookup_one_len(tname, tdentry, tlen); + ndentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(tname, tlen), tdentry); host_err = PTR_ERR(ndentry); if (IS_ERR(ndentry)) goto out_dput_old; @@ -1998,7 +1999,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, dirp = d_inode(dentry); inode_lock_nested(dirp, I_MUTEX_PARENT); - rdentry = lookup_one_len(fname, dentry, flen); + rdentry = lookup_one(&nop_mnt_idmap, &QSTR_LEN(fname, flen), dentry); host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) goto out_unlock; diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index cb01ea81724d..d0bcf744c553 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -705,8 +705,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb) int blocksize; int err; - down_write(&nilfs->ns_sem); - blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE); if (!blocksize) { nilfs_err(sb, "unable to set blocksize"); @@ -779,7 +777,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb) set_nilfs_init(nilfs); err = 0; out: - up_write(&nilfs->ns_sem); return err; failed_sbh: diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index b8ac85b548c7..821cb7874685 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end, if (IS_ERR(folios[numfolios])) { ret = PTR_ERR(folios[numfolios]); mlog_errno(ret); + folios[numfolios] = NULL; goto out; } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index c7a9729dc9d0..e5f58ff2175f 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) struct ocfs2_recovery_map *rm; mutex_init(&osb->recovery_lock); - osb->disable_recovery = 0; + osb->recovery_state = OCFS2_REC_ENABLED; osb->recovery_thread_task = NULL; init_waitqueue_head(&osb->recovery_event); @@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) return 0; } -/* we can't grab the goofy sem lock from inside wait_event, so we use - * memory barriers to make sure that we'll see the null task before - * being woken up */ static int ocfs2_recovery_thread_running(struct ocfs2_super *osb) { - mb(); return osb->recovery_thread_task != NULL; } -void ocfs2_recovery_exit(struct ocfs2_super *osb) +static void ocfs2_recovery_disable(struct ocfs2_super *osb, + enum ocfs2_recovery_state state) { - struct ocfs2_recovery_map *rm; - - /* disable any new recovery threads and wait for any currently - * running ones to exit. Do this before setting the vol_state. */ mutex_lock(&osb->recovery_lock); - osb->disable_recovery = 1; + /* + * If recovery thread is not running, we can directly transition to + * final state. + */ + if (!ocfs2_recovery_thread_running(osb)) { + osb->recovery_state = state + 1; + goto out_lock; + } + osb->recovery_state = state; + /* Wait for recovery thread to acknowledge state transition */ + wait_event_cmd(osb->recovery_event, + !ocfs2_recovery_thread_running(osb) || + osb->recovery_state >= state + 1, + mutex_unlock(&osb->recovery_lock), + mutex_lock(&osb->recovery_lock)); +out_lock: mutex_unlock(&osb->recovery_lock); - wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb)); - /* At this point, we know that no more recovery threads can be - * launched, so wait for any recovery completion work to - * complete. */ + /* + * At this point we know that no more recovery work can be queued so + * wait for any recovery completion work to complete. + */ if (osb->ocfs2_wq) flush_workqueue(osb->ocfs2_wq); +} + +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb) +{ + ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE); +} + +void ocfs2_recovery_exit(struct ocfs2_super *osb) +{ + struct ocfs2_recovery_map *rm; + + /* disable any new recovery threads and wait for any currently + * running ones to exit. Do this before setting the vol_state. */ + ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE); /* * Now that recovery is shut down, and the osb is about to be @@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg) } } restart: + if (quota_enabled) { + mutex_lock(&osb->recovery_lock); + /* Confirm that recovery thread will no longer recover quotas */ + if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) { + osb->recovery_state = OCFS2_REC_QUOTA_DISABLED; + wake_up(&osb->recovery_event); + } + if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED) + quota_enabled = 0; + mutex_unlock(&osb->recovery_lock); + } + status = ocfs2_super_lock(osb, 1); if (status < 0) { mlog_errno(status); @@ -1569,27 +1603,29 @@ bail: ocfs2_free_replay_slots(osb); osb->recovery_thread_task = NULL; - mb(); /* sync with ocfs2_recovery_thread_running */ + if (osb->recovery_state == OCFS2_REC_WANT_DISABLE) + osb->recovery_state = OCFS2_REC_DISABLED; wake_up(&osb->recovery_event); mutex_unlock(&osb->recovery_lock); - if (quota_enabled) - kfree(rm_quota); + kfree(rm_quota); return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) { + int was_set = -1; + mutex_lock(&osb->recovery_lock); + if (osb->recovery_state < OCFS2_REC_WANT_DISABLE) + was_set = ocfs2_recovery_map_set(osb, node_num); trace_ocfs2_recovery_thread(node_num, osb->node_num, - osb->disable_recovery, osb->recovery_thread_task, - osb->disable_recovery ? - -1 : ocfs2_recovery_map_set(osb, node_num)); + osb->recovery_state, osb->recovery_thread_task, was_set); - if (osb->disable_recovery) + if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE) goto out; if (osb->recovery_thread_task) diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index e3c3a35dc5e0..6397170f302f 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb); int ocfs2_recovery_init(struct ocfs2_super *osb); void ocfs2_recovery_exit(struct ocfs2_super *osb); +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb); int ocfs2_compute_replay_slots(struct ocfs2_super *osb); void ocfs2_free_replay_slots(struct ocfs2_super *osb); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 51c52768132d..6aaa94c554c1 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type { void ocfs2_initialize_journal_triggers(struct super_block *sb, struct ocfs2_triggers triggers[]); +enum ocfs2_recovery_state { + OCFS2_REC_ENABLED = 0, + OCFS2_REC_QUOTA_WANT_DISABLE, + /* + * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for + * ocfs2_recovery_disable_quota() to work. + */ + OCFS2_REC_QUOTA_DISABLED, + OCFS2_REC_WANT_DISABLE, + /* + * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work + */ + OCFS2_REC_DISABLED, +}; + struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; @@ -370,7 +385,7 @@ struct ocfs2_super struct ocfs2_recovery_map *recovery_map; struct ocfs2_replay_map *replay_map; struct task_struct *recovery_thread_task; - int disable_recovery; + enum ocfs2_recovery_state recovery_state; wait_queue_head_t checkpoint_event; struct ocfs2_journal *journal; unsigned long osb_commit_interval; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 2956d888c131..e272429da3db 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -453,8 +453,7 @@ out: /* Sync changes in local quota file into global quota file and * reinitialize local quota file. - * The function expects local quota file to be already locked and - * s_umount locked in shared mode. */ + * The function expects local quota file to be already locked. */ static int ocfs2_recover_local_quota_file(struct inode *lqinode, int type, struct ocfs2_quota_recovery *rec) @@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, { unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE, LOCAL_GROUP_QUOTA_SYSTEM_INODE }; - struct super_block *sb = osb->sb; struct ocfs2_local_disk_dqinfo *ldinfo; struct buffer_head *bh; handle_t *handle; @@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for " "slot %u\n", osb->dev_str, slot_num); - down_read(&sb->s_umount); for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (list_empty(&(rec->r_list[type]))) continue; @@ -677,7 +674,6 @@ out_put: break; } out: - up_read(&sb->s_umount); kfree(rec); return status; } @@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type) ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk); /* - * s_umount held in exclusive mode protects us against racing with - * recovery thread... + * ocfs2_dismount_volume() has already aborted quota recovery... */ if (oinfo->dqi_rec) { ocfs2_free_quota_recovery(oinfo->dqi_rec); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index f7b483f0de2a..6ac4dcd54588 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode, ac, cl); - if (PTR_ERR(bg_bh) == -ENOSPC) + if (PTR_ERR(bg_bh) == -ENOSPC) { + ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG; bg_bh = ocfs2_block_group_alloc_discontig(handle, alloc_inode, ac, cl); + } if (IS_ERR(bg_bh)) { status = PTR_ERR(bg_bh); bg_bh = NULL; @@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, { int status; u16 chain; + u32 contig_bits; u64 next_group; struct inode *alloc_inode = ac->ac_inode; struct buffer_head *group_bh = NULL; @@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, status = -ENOSPC; /* for now, the chain search is a bit simplistic. We just use * the 1st group with any empty bits. */ - while ((status = ac->ac_group_search(alloc_inode, group_bh, - bits_wanted, min_bits, - ac->ac_max_block, - res)) == -ENOSPC) { + while (1) { + if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) { + contig_bits = le16_to_cpu(bg->bg_contig_free_bits); + if (!contig_bits) + contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap, + le16_to_cpu(bg->bg_bits), 0); + if (bits_wanted > contig_bits && contig_bits >= min_bits) + bits_wanted = contig_bits; + } + + status = ac->ac_group_search(alloc_inode, group_bh, + bits_wanted, min_bits, + ac->ac_max_block, res); + if (status != -ENOSPC) + break; if (!bg->bg_next_group) break; @@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, victim = ocfs2_find_victim_chain(cl); ac->ac_chain = victim; +search: status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits, res, &bits_left); if (!status) { @@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, } } + /* Chains can't supply the bits_wanted contiguous space. + * We should switch to using every single bit when allocating + * from the global bitmap. */ + if (i == le16_to_cpu(cl->cl_next_free_rec) && + status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) { + ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG; + ac->ac_chain = victim; + goto search; + } + set_hint: if (status != -ENOSPC) { /* If the next search of this group is not likely to @@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle, BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted); BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL - && ac->ac_which != OCFS2_AC_USE_MAIN); + && ac->ac_which != OCFS2_AC_USE_MAIN + && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG); if (ac->ac_which == OCFS2_AC_USE_LOCAL) { WARN_ON(min_clusters > 1); diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index b481b834857d..bcf2ed4a8631 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -29,6 +29,7 @@ struct ocfs2_alloc_context { #define OCFS2_AC_USE_MAIN 2 #define OCFS2_AC_USE_INODE 3 #define OCFS2_AC_USE_META 4 +#define OCFS2_AC_USE_MAIN_DISCONTIG 5 u32 ac_which; /* these are used by the chain search */ diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8bb5022f3082..3d2533950bae 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) /* Orphan scan should be stopped as early as possible */ ocfs2_orphan_scan_stop(osb); + /* Stop quota recovery so that we can disable quotas */ + ocfs2_recovery_disable_quota(osb); + ocfs2_disable_quotas(osb); /* All dquots should be freed by now */ diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index d6cd81163030..135c49c5d848 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -9,12 +9,13 @@ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/cred.h> -#include <linux/parser.h> #include <linux/buffer_head.h> #include <linux/vmalloc.h> #include <linux/writeback.h> #include <linux/seq_file.h> #include <linux/crc-itu-t.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> #include "omfs.h" MODULE_AUTHOR("Bob Copeland <me@bobcopeland.com>"); @@ -384,79 +385,83 @@ nomem: return -ENOMEM; } +struct omfs_mount_options { + kuid_t s_uid; + kgid_t s_gid; + int s_dmask; + int s_fmask; +}; + enum { - Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_err + Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, }; -static const match_table_t tokens = { - {Opt_uid, "uid=%u"}, - {Opt_gid, "gid=%u"}, - {Opt_umask, "umask=%o"}, - {Opt_dmask, "dmask=%o"}, - {Opt_fmask, "fmask=%o"}, - {Opt_err, NULL}, +static const struct fs_parameter_spec omfs_param_spec[] = { + fsparam_uid ("uid", Opt_uid), + fsparam_gid ("gid", Opt_gid), + fsparam_u32oct ("umask", Opt_umask), + fsparam_u32oct ("dmask", Opt_dmask), + fsparam_u32oct ("fmask", Opt_fmask), + {} }; -static int parse_options(char *options, struct omfs_sb_info *sbi) +static int +omfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { - char *p; - substring_t args[MAX_OPT_ARGS]; - int option; - - if (!options) - return 1; - - while ((p = strsep(&options, ",")) != NULL) { - int token; - if (!*p) - continue; - - token = match_token(p, tokens, args); - switch (token) { - case Opt_uid: - if (match_int(&args[0], &option)) - return 0; - sbi->s_uid = make_kuid(current_user_ns(), option); - if (!uid_valid(sbi->s_uid)) - return 0; - break; - case Opt_gid: - if (match_int(&args[0], &option)) - return 0; - sbi->s_gid = make_kgid(current_user_ns(), option); - if (!gid_valid(sbi->s_gid)) - return 0; - break; - case Opt_umask: - if (match_octal(&args[0], &option)) - return 0; - sbi->s_fmask = sbi->s_dmask = option; - break; - case Opt_dmask: - if (match_octal(&args[0], &option)) - return 0; - sbi->s_dmask = option; - break; - case Opt_fmask: - if (match_octal(&args[0], &option)) - return 0; - sbi->s_fmask = option; - break; - default: - return 0; - } + struct omfs_mount_options *opts = fc->fs_private; + int token; + struct fs_parse_result result; + + /* All options are ignored on remount */ + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) + return 0; + + token = fs_parse(fc, omfs_param_spec, param, &result); + if (token < 0) + return token; + + switch (token) { + case Opt_uid: + opts->s_uid = result.uid; + break; + case Opt_gid: + opts->s_gid = result.gid; + break; + case Opt_umask: + opts->s_fmask = opts->s_dmask = result.uint_32; + break; + case Opt_dmask: + opts->s_dmask = result.uint_32; + break; + case Opt_fmask: + opts->s_fmask = result.uint_32; + break; + default: + return -EINVAL; } - return 1; + + return 0; } -static int omfs_fill_super(struct super_block *sb, void *data, int silent) +static void +omfs_set_options(struct omfs_sb_info *sbi, struct omfs_mount_options *opts) +{ + sbi->s_uid = opts->s_uid; + sbi->s_gid = opts->s_gid; + sbi->s_dmask = opts->s_dmask; + sbi->s_fmask = opts->s_fmask; +} + +static int omfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct buffer_head *bh, *bh2; struct omfs_super_block *omfs_sb; struct omfs_root_block *omfs_rb; struct omfs_sb_info *sbi; struct inode *root; + struct omfs_mount_options *parsed_opts = fc->fs_private; int ret = -EINVAL; + int silent = fc->sb_flags & SB_SILENT; sbi = kzalloc(sizeof(struct omfs_sb_info), GFP_KERNEL); if (!sbi) @@ -464,12 +469,7 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = sbi; - sbi->s_uid = current_uid(); - sbi->s_gid = current_gid(); - sbi->s_dmask = sbi->s_fmask = current_umask(); - - if (!parse_options((char *) data, sbi)) - goto end; + omfs_set_options(sbi, parsed_opts); sb->s_maxbytes = 0xffffffff; @@ -594,18 +594,50 @@ end: return ret; } -static struct dentry *omfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int omfs_get_tree(struct fs_context *fc) +{ + return get_tree_bdev(fc, omfs_fill_super); +} + +static void omfs_free_fc(struct fs_context *fc); + +static const struct fs_context_operations omfs_context_ops = { + .parse_param = omfs_parse_param, + .get_tree = omfs_get_tree, + .free = omfs_free_fc, +}; + +static int omfs_init_fs_context(struct fs_context *fc) +{ + struct omfs_mount_options *opts; + + opts = kzalloc(sizeof(*opts), GFP_KERNEL); + if (!opts) + return -ENOMEM; + + /* Set mount options defaults */ + opts->s_uid = current_uid(); + opts->s_gid = current_gid(); + opts->s_dmask = opts->s_fmask = current_umask(); + + fc->fs_private = opts; + fc->ops = &omfs_context_ops; + + return 0; +} + +static void omfs_free_fc(struct fs_context *fc) { - return mount_bdev(fs_type, flags, dev_name, data, omfs_fill_super); + kfree(fc->fs_private); } static struct file_system_type omfs_fs_type = { - .owner = THIS_MODULE, - .name = "omfs", - .mount = omfs_mount, - .kill_sb = kill_block_super, - .fs_flags = FS_REQUIRES_DEV, + .owner = THIS_MODULE, + .name = "omfs", + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, + .init_fs_context = omfs_init_fs_context, + .parameters = omfs_param_spec, }; MODULE_ALIAS_FS("omfs"); diff --git a/fs/open.c b/fs/open.c index a9063cca9911..7828234a7caa 100644 --- a/fs/open.c +++ b/fs/open.c @@ -60,7 +60,10 @@ int do_truncate(struct mnt_idmap *idmap, struct dentry *dentry, if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; - inode_lock(dentry->d_inode); + ret = inode_lock_killable(dentry->d_inode); + if (ret) + return ret; + /* Note any delegations or leases have already been broken: */ ret = notify_change(idmap, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); @@ -635,7 +638,9 @@ int chmod_common(const struct path *path, umode_t mode) if (error) return error; retry_deleg: - inode_lock(inode); + error = inode_lock_killable(inode); + if (error) + goto out_mnt_unlock; error = security_path_chmod(path, mode); if (error) goto out_unlock; @@ -650,6 +655,7 @@ out_unlock: if (!error) goto retry_deleg; } +out_mnt_unlock: mnt_drop_write(path->mnt); return error; } @@ -769,7 +775,9 @@ retry_deleg: return -EINVAL; if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid)) return -EINVAL; - inode_lock(inode); + error = inode_lock_killable(inode); + if (error) + return error; if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | setattr_should_drop_sgid(idmap, inode); diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 5ac743c6bc2e..08a6f372a352 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -32,12 +32,13 @@ static int orangefs_writepage_locked(struct folio *folio, len = i_size_read(inode); if (folio->private) { wr = folio->private; - WARN_ON(wr->pos >= len); off = wr->pos; - if (off + wr->len > len) + if ((off + wr->len > len) && (off <= len)) wlen = len - off; else wlen = wr->len; + if (wlen == 0) + wlen = wr->len; } else { WARN_ON(1); off = folio_pos(folio); @@ -46,8 +47,6 @@ static int orangefs_writepage_locked(struct folio *folio, if (wlen > len - off) wlen = len - off; } - /* Should've been handled in orangefs_invalidate_folio. */ - WARN_ON(off == len || off + wlen > len); WARN_ON(wlen == 0); bvec_set_folio(&bv, folio, wlen, offset_in_folio(folio, off)); @@ -320,6 +319,8 @@ static int orangefs_write_begin(struct file *file, wr->len += len; goto okay; } else { + wr->pos = pos; + wr->len = len; ret = orangefs_launder_folio(folio); if (ret) return ret; diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 444aeeccb6da..83f80fdb1567 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -385,11 +385,9 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected, */ take_dentry_name_snapshot(&name, real); /* - * No idmap handling here: it's an internal lookup. Could skip - * permission checking altogether, but for now just use non-idmap - * transformed ids. + * No idmap handling here: it's an internal lookup. */ - this = lookup_one_len(name.name.name, connected, name.name.len); + this = lookup_noperm(&name.name, connected); release_dentry_name_snapshot(&name); err = PTR_ERR(this); if (IS_ERR(this)) { diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index be5c65d6f848..bf722daf19a9 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -205,8 +205,8 @@ static struct dentry *ovl_lookup_positive_unlocked(struct ovl_lookup_data *d, struct dentry *base, int len, bool drop_negative) { - struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), name, - base, len); + struct dentry *ret = lookup_one_unlocked(mnt_idmap(d->layer->mnt), + &QSTR_LEN(name, len), base); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { if (drop_negative && ret->d_lockref.count == 1) { @@ -757,7 +757,7 @@ struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh) if (err) return ERR_PTR(err); - index = lookup_positive_unlocked(name.name, ofs->workdir, name.len); + index = lookup_noperm_positive_unlocked(&name, ofs->workdir); kfree(name.name); if (IS_ERR(index)) { if (PTR_ERR(index) == -ENOENT) @@ -789,8 +789,8 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, if (err) return ERR_PTR(err); - index = lookup_one_positive_unlocked(ovl_upper_mnt_idmap(ofs), name.name, - ofs->workdir, name.len); + index = lookup_one_positive_unlocked(ovl_upper_mnt_idmap(ofs), &name, + ofs->workdir); if (IS_ERR(index)) { err = PTR_ERR(index); if (err == -ENOENT) { @@ -1371,7 +1371,7 @@ out: bool ovl_lower_positive(struct dentry *dentry) { struct ovl_entry *poe = OVL_E(dentry->d_parent); - const struct qstr *name = &dentry->d_name; + struct qstr *name = &dentry->d_name; const struct cred *old_cred; unsigned int i; bool positive = false; @@ -1396,7 +1396,7 @@ bool ovl_lower_positive(struct dentry *dentry) this = lookup_one_positive_unlocked( mnt_idmap(parentpath->layer->mnt), - name->name, parentpath->dentry, name->len); + name, parentpath->dentry); if (IS_ERR(this)) { switch (PTR_ERR(this)) { case -ENOENT: diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index aef942a758ce..8baaba0a3fe5 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -402,7 +402,7 @@ static inline struct dentry *ovl_lookup_upper(struct ovl_fs *ofs, const char *name, struct dentry *base, int len) { - return lookup_one(ovl_upper_mnt_idmap(ofs), name, base, len); + return lookup_one(ovl_upper_mnt_idmap(ofs), &QSTR_LEN(name, len), base); } static inline bool ovl_open_flags_need_copy_up(int flags) diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 881ec5592da5..44e208da417c 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -271,7 +271,6 @@ static bool ovl_fill_merge(struct dir_context *ctx, const char *name, static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data *rdd) { int err; - struct ovl_cache_entry *p; struct dentry *dentry, *dir = path->dentry; const struct cred *old_cred; @@ -280,9 +279,11 @@ static int ovl_check_whiteouts(const struct path *path, struct ovl_readdir_data err = down_write_killable(&dir->d_inode->i_rwsem); if (!err) { while (rdd->first_maybe_whiteout) { - p = rdd->first_maybe_whiteout; + struct ovl_cache_entry *p = + rdd->first_maybe_whiteout; rdd->first_maybe_whiteout = p->next_maybe_whiteout; - dentry = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len); + dentry = lookup_one(mnt_idmap(path->mnt), + &QSTR_LEN(p->name, p->len), dir); if (!IS_ERR(dentry)) { p->is_whiteout = ovl_is_whiteout(dentry); dput(dentry); @@ -351,6 +352,7 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list, struct path realpath; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_merge, + .ctx.count = INT_MAX, .dentry = dentry, .list = list, .root = root, @@ -492,7 +494,7 @@ static int ovl_cache_update(const struct path *path, struct ovl_cache_entry *p, } } /* This checks also for xwhiteouts */ - this = lookup_one(mnt_idmap(path->mnt), p->name, dir, p->len); + this = lookup_one(mnt_idmap(path->mnt), &QSTR_LEN(p->name, p->len), dir); if (IS_ERR_OR_NULL(this) || !this->d_inode) { /* Mark a stale entry */ p->is_whiteout = true; @@ -571,6 +573,7 @@ static int ovl_dir_read_impure(const struct path *path, struct list_head *list, struct ovl_cache_entry *p, *n; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_plain, + .ctx.count = INT_MAX, .list = list, .root = root, }; @@ -672,6 +675,7 @@ static bool ovl_fill_real(struct dir_context *ctx, const char *name, struct ovl_readdir_translate *rdt = container_of(ctx, struct ovl_readdir_translate, ctx); struct dir_context *orig_ctx = rdt->orig_ctx; + bool res; if (rdt->parent_ino && strcmp(name, "..") == 0) { ino = rdt->parent_ino; @@ -686,7 +690,10 @@ static bool ovl_fill_real(struct dir_context *ctx, const char *name, name, namelen, rdt->xinowarn); } - return orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type); + res = orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type); + ctx->count = orig_ctx->count; + + return res; } static bool ovl_is_impure_dir(struct file *file) @@ -713,6 +720,7 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx) const struct ovl_layer *lower_layer = ovl_layer_lower(dir); struct ovl_readdir_translate rdt = { .ctx.actor = ovl_fill_real, + .ctx.count = ctx->count, .orig_ctx = ctx, .xinobits = ovl_xino_bits(ofs), .xinowarn = ovl_xino_warn(ofs), @@ -1073,6 +1081,7 @@ int ovl_check_d_type_supported(const struct path *realpath) int err; struct ovl_readdir_data rdd = { .ctx.actor = ovl_check_d_type, + .ctx.count = INT_MAX, .d_type_supported = false, }; @@ -1094,6 +1103,7 @@ static int ovl_workdir_cleanup_recurse(struct ovl_fs *ofs, const struct path *pa struct ovl_cache_entry *p; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_plain, + .ctx.count = INT_MAX, .list = &list, }; bool incompat = false; @@ -1178,6 +1188,7 @@ int ovl_indexdir_cleanup(struct ovl_fs *ofs) struct ovl_cache_entry *p; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_plain, + .ctx.count = INT_MAX, .list = &list, }; diff --git a/fs/pidfs.c b/fs/pidfs.c index d64a4cbeb0da..c1f0a067be40 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -20,6 +20,7 @@ #include <linux/time_namespace.h> #include <linux/utsname.h> #include <net/net_namespace.h> +#include <linux/coredump.h> #include "internal.h" #include "mount.h" @@ -33,6 +34,7 @@ static struct kmem_cache *pidfs_cachep __ro_after_init; struct pidfs_exit_info { __u64 cgroupid; __s32 exit_code; + __u32 coredump_mask; }; struct pidfs_inode { @@ -240,6 +242,22 @@ static inline bool pid_in_current_pidns(const struct pid *pid) return false; } +static __u32 pidfs_coredump_mask(unsigned long mm_flags) +{ + switch (__get_dumpable(mm_flags)) { + case SUID_DUMP_USER: + return PIDFD_COREDUMP_USER; + case SUID_DUMP_ROOT: + return PIDFD_COREDUMP_ROOT; + case SUID_DUMP_DISABLE: + return PIDFD_COREDUMP_SKIP; + default: + WARN_ON_ONCE(true); + } + + return 0; +} + static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) { struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg; @@ -280,6 +298,11 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) } } + if (mask & PIDFD_INFO_COREDUMP) { + kinfo.mask |= PIDFD_INFO_COREDUMP; + kinfo.coredump_mask = READ_ONCE(pidfs_i(inode)->__pei.coredump_mask); + } + task = get_pid_task(pid, PIDTYPE_PID); if (!task) { /* @@ -296,6 +319,13 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) if (!c) return -ESRCH; + if (!(kinfo.mask & PIDFD_INFO_COREDUMP)) { + task_lock(task); + if (task->mm) + kinfo.coredump_mask = pidfs_coredump_mask(task->mm->flags); + task_unlock(task); + } + /* Unconditionally return identifiers and credentials, the rest only on request */ user_ns = current_user_ns(); @@ -559,6 +589,31 @@ void pidfs_exit(struct task_struct *tsk) } } +#ifdef CONFIG_COREDUMP +void pidfs_coredump(const struct coredump_params *cprm) +{ + struct pid *pid = cprm->pid; + struct pidfs_exit_info *exit_info; + struct dentry *dentry; + struct inode *inode; + __u32 coredump_mask = 0; + + dentry = pid->stashed; + if (WARN_ON_ONCE(!dentry)) + return; + + inode = d_inode(dentry); + exit_info = &pidfs_i(inode)->__pei; + /* Note how we were coredumped. */ + coredump_mask = pidfs_coredump_mask(cprm->mm_flags); + /* Note that we actually did coredump. */ + coredump_mask |= PIDFD_COREDUMPED; + /* If coredumping is set to skip we should never end up here. */ + VFS_WARN_ON_ONCE(coredump_mask & PIDFD_COREDUMP_SKIP); + smp_store_release(&exit_info->coredump_mask, coredump_mask); +} +#endif + static struct vfsmount *pidfs_mnt __ro_after_init; /* @@ -569,36 +624,14 @@ static struct vfsmount *pidfs_mnt __ro_after_init; static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { - return -EOPNOTSUPP; + return anon_inode_setattr(idmap, dentry, attr); } - -/* - * User space expects pidfs inodes to have no file type in st_mode. - * - * In particular, 'lsof' has this legacy logic: - * - * type = s->st_mode & S_IFMT; - * switch (type) { - * ... - * case 0: - * if (!strcmp(p, "anon_inode")) - * Lf->ntype = Ntype = N_ANON_INODE; - * - * to detect our old anon_inode logic. - * - * Rather than mess with our internal sane inode data, just fix it - * up here in getattr() by masking off the format bits. - */ static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - struct inode *inode = d_inode(path->dentry); - - generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); - stat->mode &= ~S_IFMT; - return 0; + return anon_inode_getattr(idmap, path, stat, request_mask, query_flags); } static const struct inode_operations pidfs_inode_operations = { @@ -768,7 +801,7 @@ static inline bool pidfs_pid_valid(struct pid *pid, const struct path *path, { enum pid_type type; - if (flags & PIDFD_CLONE) + if (flags & PIDFD_STALE) return true; /* @@ -777,10 +810,14 @@ static inline bool pidfs_pid_valid(struct pid *pid, const struct path *path, * pidfd has been allocated perform another check that the pid * is still alive. If it is exit information is available even * if the task gets reaped before the pidfd is returned to - * userspace. The only exception is PIDFD_CLONE where no task - * linkage has been established for @pid yet and the kernel is - * in the middle of process creation so there's nothing for - * pidfs to miss. + * userspace. The only exception are indicated by PIDFD_STALE: + * + * (1) The kernel is in the middle of task creation and thus no + * task linkage has been established yet. + * (2) The caller knows @pid has been registered in pidfs at a + * time when the task was still alive. + * + * In both cases exit information will have been reported. */ if (flags & PIDFD_THREAD) type = PIDTYPE_PID; @@ -826,7 +863,7 @@ static int pidfs_init_inode(struct inode *inode, void *data) const struct pid *pid = data; inode->i_private = data; - inode->i_flags |= S_PRIVATE; + inode->i_flags |= S_PRIVATE | S_ANON_INODE; inode->i_mode |= S_IRWXU; inode->i_op = &pidfs_inode_operations; inode->i_fop = &pidfs_file_operations; @@ -874,11 +911,11 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) int ret; /* - * Ensure that PIDFD_CLONE can be passed as a flag without + * Ensure that PIDFD_STALE can be passed as a flag without * overloading other uapi pidfd flags. */ - BUILD_BUG_ON(PIDFD_CLONE == PIDFD_THREAD); - BUILD_BUG_ON(PIDFD_CLONE == PIDFD_NONBLOCK); + BUILD_BUG_ON(PIDFD_STALE == PIDFD_THREAD); + BUILD_BUG_ON(PIDFD_STALE == PIDFD_NONBLOCK); ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path); if (ret < 0) @@ -887,7 +924,8 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) if (!pidfs_pid_valid(pid, &path, flags)) return ERR_PTR(-ESRCH); - flags &= ~PIDFD_CLONE; + flags &= ~PIDFD_STALE; + flags |= O_RDWR; pidfd_file = dentry_open(&path, flags, current_cred()); /* Raise PIDFD_THREAD explicitly as do_dentry_open() strips it. */ if (!IS_ERR(pidfd_file)) @@ -896,6 +934,65 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) return pidfd_file; } +/** + * pidfs_register_pid - register a struct pid in pidfs + * @pid: pid to pin + * + * Register a struct pid in pidfs. Needs to be paired with + * pidfs_put_pid() to not risk leaking the pidfs dentry and inode. + * + * Return: On success zero, on error a negative error code is returned. + */ +int pidfs_register_pid(struct pid *pid) +{ + struct path path __free(path_put) = {}; + int ret; + + might_sleep(); + + if (!pid) + return 0; + + ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path); + if (unlikely(ret)) + return ret; + /* Keep the dentry and only put the reference to the mount. */ + path.dentry = NULL; + return 0; +} + +/** + * pidfs_get_pid - pin a struct pid through pidfs + * @pid: pid to pin + * + * Similar to pidfs_register_pid() but only valid if the caller knows + * there's a reference to the @pid through a dentry already that can't + * go away. + */ +void pidfs_get_pid(struct pid *pid) +{ + if (!pid) + return; + WARN_ON_ONCE(!stashed_dentry_get(&pid->stashed)); +} + +/** + * pidfs_put_pid - drop a pidfs reference + * @pid: pid to drop + * + * Drop a reference to @pid via pidfs. This is only safe if the + * reference has been taken via pidfs_get_pid(). + */ +void pidfs_put_pid(struct pid *pid) +{ + might_sleep(); + + if (!pid) + return; + VFS_WARN_ON_ONCE(!pid->stashed); + dput(pid->stashed); +} + static void pidfs_inode_init_once(void *data) { struct pidfs_inode *pi = data; diff --git a/fs/pnode.c b/fs/pnode.c index 7a062a5de10e..fb77427df39e 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -150,7 +150,7 @@ static struct mount *propagation_next(struct mount *m, struct mount *origin) { /* are there any slaves of this mount? */ - if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list)) + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) return first_slave(m); while (1) { @@ -174,7 +174,7 @@ static struct mount *skip_propagation_subtree(struct mount *m, * Advance m such that propagation_next will not return * the slaves of m. */ - if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list)) + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) m = last_slave(m); return m; @@ -185,7 +185,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin) while (1) { while (1) { struct mount *next; - if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list)) + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) return first_slave(m); next = next_peer(m); if (m->mnt_group_id == origin->mnt_group_id) { @@ -226,11 +226,15 @@ static int propagate_one(struct mount *m, struct mountpoint *dest_mp) struct mount *child; int type; /* skip ones added by this propagate_mnt() */ - if (IS_MNT_PROPAGATED(m)) + if (IS_MNT_NEW(m)) return 0; - /* skip if mountpoint isn't covered by it */ + /* skip if mountpoint isn't visible in m */ if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) return 0; + /* skip if m is in the anon_ns we are emptying */ + if (m->mnt_ns->mntns_flags & MNTNS_PROPAGATING) + return 0; + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { @@ -380,9 +384,6 @@ bool propagation_would_overmount(const struct mount *from, if (!IS_MNT_SHARED(from)) return false; - if (IS_MNT_PROPAGATED(to)) - return false; - if (to->mnt.mnt_root != mp->m_dentry) return false; diff --git a/fs/pnode.h b/fs/pnode.h index ddafe0d087ca..34b6247af01d 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -12,7 +12,7 @@ #define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED) #define IS_MNT_SLAVE(m) ((m)->mnt_master) -#define IS_MNT_PROPAGATED(m) (!(m)->mnt_ns || ((m)->mnt_ns->mntns_flags & MNTNS_PROPAGATING)) +#define IS_MNT_NEW(m) (!(m)->mnt_ns) #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED) #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE) #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED) diff --git a/fs/proc/base.c b/fs/proc/base.c index b0d4e1908b22..fe33a5843fbd 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2121,7 +2121,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, unsigned type = DT_UNKNOWN; ino_t ino = 1; - child = d_hash_and_lookup(dir, &qname); + child = try_lookup_noperm(&qname, dir); if (!child) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index e133b507ddf3..5c555db68aa2 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -111,7 +111,7 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) if (err) goto out; } else { - mangle(m, r->mnt_devname ? r->mnt_devname : "none"); + mangle(m, r->mnt_devname); } seq_putc(m, ' '); /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ @@ -177,7 +177,7 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) if (err) goto out; } else { - mangle(m, r->mnt_devname ? r->mnt_devname : "none"); + mangle(m, r->mnt_devname); } seq_puts(m, sb_rdonly(sb) ? " ro" : " rw"); err = show_sb_opts(m, sb); @@ -199,17 +199,13 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt) int err; /* device */ + seq_puts(m, "device "); if (sb->s_op->show_devname) { - seq_puts(m, "device "); err = sb->s_op->show_devname(m, mnt_path.dentry); if (err) goto out; } else { - if (r->mnt_devname) { - seq_puts(m, "device "); - mangle(m, r->mnt_devname); - } else - seq_puts(m, "no device"); + mangle(m, r->mnt_devname); } /* mount point */ diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 825c5c2e0962..df4a9b348769 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2560,7 +2560,7 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, struct dentry *dentry; int error; - dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name)); + dentry = lookup_noperm_positive_unlocked(&QSTR(qf_name), sb->s_root); if (IS_ERR(dentry)) return PTR_ERR(dentry); diff --git a/fs/read_write.c b/fs/read_write.c index bb0ed26a0b3a..0ef70e128c4a 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -332,7 +332,9 @@ loff_t default_llseek(struct file *file, loff_t offset, int whence) struct inode *inode = file_inode(file); loff_t retval; - inode_lock(inode); + retval = inode_lock_killable(inode); + if (retval) + return retval; switch (whence) { case SEEK_END: offset += i_size_read(inode); diff --git a/fs/readdir.c b/fs/readdir.c index 0038efda417b..7764b8638978 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -222,6 +222,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd, CLASS(fd_pos, f)(fd); struct readdir_callback buf = { .ctx.actor = fillonedir, + .ctx.count = 1, /* Hint to fs: just one entry. */ .dirent = dirent }; @@ -252,7 +253,6 @@ struct getdents_callback { struct dir_context ctx; struct linux_dirent __user * current_dir; int prev_reclen; - int count; int error; }; @@ -266,12 +266,16 @@ static bool filldir(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); int prev_reclen; + unsigned int flags = d_type; + + BUILD_BUG_ON(FILLDIR_FLAG_NOINTR & S_DT_MASK); + d_type &= S_DT_MASK; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ - if (reclen > buf->count) + if (reclen > ctx->count) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { @@ -279,7 +283,7 @@ static bool filldir(struct dir_context *ctx, const char *name, int namlen, return false; } prev_reclen = buf->prev_reclen; - if (prev_reclen && signal_pending(current)) + if (!(flags & FILLDIR_FLAG_NOINTR) && prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *) dirent - prev_reclen; @@ -296,7 +300,7 @@ static bool filldir(struct dir_context *ctx, const char *name, int namlen, buf->current_dir = (void __user *)dirent + reclen; buf->prev_reclen = reclen; - buf->count -= reclen; + ctx->count -= reclen; return true; efault_end: user_write_access_end(); @@ -311,7 +315,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, CLASS(fd_pos, f)(fd); struct getdents_callback buf = { .ctx.actor = filldir, - .count = count, + .ctx.count = count, .current_dir = dirent }; int error; @@ -329,7 +333,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else - error = count - buf.count; + error = count - buf.ctx.count; } return error; } @@ -338,7 +342,6 @@ struct getdents_callback64 { struct dir_context ctx; struct linux_dirent64 __user * current_dir; int prev_reclen; - int count; int error; }; @@ -351,15 +354,19 @@ static bool filldir64(struct dir_context *ctx, const char *name, int namlen, int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); int prev_reclen; + unsigned int flags = d_type; + + BUILD_BUG_ON(FILLDIR_FLAG_NOINTR & S_DT_MASK); + d_type &= S_DT_MASK; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ - if (reclen > buf->count) + if (reclen > ctx->count) return false; prev_reclen = buf->prev_reclen; - if (prev_reclen && signal_pending(current)) + if (!(flags & FILLDIR_FLAG_NOINTR) && prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *)dirent - prev_reclen; @@ -376,7 +383,7 @@ static bool filldir64(struct dir_context *ctx, const char *name, int namlen, buf->prev_reclen = reclen; buf->current_dir = (void __user *)dirent + reclen; - buf->count -= reclen; + ctx->count -= reclen; return true; efault_end: @@ -392,7 +399,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, CLASS(fd_pos, f)(fd); struct getdents_callback64 buf = { .ctx.actor = filldir64, - .count = count, + .ctx.count = count, .current_dir = dirent }; int error; @@ -411,7 +418,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, if (put_user(d_off, &lastdirent->d_off)) error = -EFAULT; else - error = count - buf.count; + error = count - buf.ctx.count; } return error; } @@ -475,6 +482,7 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, CLASS(fd_pos, f)(fd); struct compat_readdir_callback buf = { .ctx.actor = compat_fillonedir, + .ctx.count = 1, /* Hint to fs: just one entry. */ .dirent = dirent }; @@ -499,7 +507,6 @@ struct compat_getdents_callback { struct dir_context ctx; struct compat_linux_dirent __user *current_dir; int prev_reclen; - int count; int error; }; @@ -513,12 +520,16 @@ static bool compat_filldir(struct dir_context *ctx, const char *name, int namlen int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + namlen + 2, sizeof(compat_long_t)); int prev_reclen; + unsigned int flags = d_type; + + BUILD_BUG_ON(FILLDIR_FLAG_NOINTR & S_DT_MASK); + d_type &= S_DT_MASK; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) return false; buf->error = -EINVAL; /* only used if we fail.. */ - if (reclen > buf->count) + if (reclen > ctx->count) return false; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { @@ -526,7 +537,7 @@ static bool compat_filldir(struct dir_context *ctx, const char *name, int namlen return false; } prev_reclen = buf->prev_reclen; - if (prev_reclen && signal_pending(current)) + if (!(flags & FILLDIR_FLAG_NOINTR) && prev_reclen && signal_pending(current)) return false; dirent = buf->current_dir; prev = (void __user *) dirent - prev_reclen; @@ -542,7 +553,7 @@ static bool compat_filldir(struct dir_context *ctx, const char *name, int namlen buf->prev_reclen = reclen; buf->current_dir = (void __user *)dirent + reclen; - buf->count -= reclen; + ctx->count -= reclen; return true; efault_end: user_write_access_end(); @@ -557,8 +568,8 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, CLASS(fd_pos, f)(fd); struct compat_getdents_callback buf = { .ctx.actor = compat_filldir, + .ctx.count = count, .current_dir = dirent, - .count = count }; int error; @@ -575,7 +586,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else - error = count - buf.count; + error = count - buf.ctx.count; } return error; } diff --git a/fs/select.c b/fs/select.c index 7da531b1cf6b..9fb650d03d52 100644 --- a/fs/select.c +++ b/fs/select.c @@ -630,7 +630,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; ret = -EINVAL; - if (n < 0) + if (unlikely(n < 0)) goto out_nofds; /* max_fds can increase, so grab it once to avoid race */ @@ -857,7 +857,7 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait, int fd = pollfd->fd; __poll_t mask, filter; - if (fd < 0) + if (unlikely(fd < 0)) return 0; CLASS(fd, f)(fd); diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index fe738623cf1b..89d2dbbb742c 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -29,7 +29,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, { struct cached_fid *cfid; - spin_lock(&cfids->cfid_list_lock); list_for_each_entry(cfid, &cfids->entries, entry) { if (!strcmp(cfid->path, path)) { /* @@ -38,25 +37,20 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, * being deleted due to a lease break. */ if (!cfid->time || !cfid->has_lease) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } kref_get(&cfid->refcount); - spin_unlock(&cfids->cfid_list_lock); return cfid; } } if (lookup_only) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } if (cfids->num_entries >= max_cached_dirs) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } cfid = init_cached_dir(path); if (cfid == NULL) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } cfid->cfids = cfids; @@ -74,7 +68,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, */ cfid->has_lease = true; - spin_unlock(&cfids->cfid_list_lock); return cfid; } @@ -109,7 +102,8 @@ path_to_dentry(struct cifs_sb_info *cifs_sb, const char *path) while (*s && *s != sep) s++; - child = lookup_positive_unlocked(p, dentry, s - p); + child = lookup_noperm_positive_unlocked(&QSTR_LEN(p, s - p), + dentry); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); @@ -187,8 +181,10 @@ replay_again: if (!utf16_path) return -ENOMEM; + spin_lock(&cfids->cfid_list_lock); cfid = find_or_create_cached_dir(cfids, path, lookup_only, tcon->max_cached_dirs); if (cfid == NULL) { + spin_unlock(&cfids->cfid_list_lock); kfree(utf16_path); return -ENOENT; } @@ -197,7 +193,6 @@ replay_again: * Otherwise, it is either a new entry or laundromat worker removed it * from @cfids->entries. Caller will put last reference if the latter. */ - spin_lock(&cfids->cfid_list_lock); if (cfid->has_lease && cfid->time) { spin_unlock(&cfids->cfid_list_lock); *ret_cfid = cfid; @@ -207,7 +202,7 @@ replay_again: spin_unlock(&cfids->cfid_list_lock); /* - * Skip any prefix paths in @path as lookup_positive_unlocked() ends up + * Skip any prefix paths in @path as lookup_noperm_positive_unlocked() ends up * calling ->lookup() which already adds those through * build_path_from_dentry(). Also, do it earlier as we might reconnect * below when trying to send compounded request and then potentially diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index a08c42363ffc..fb04e263611c 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -929,7 +929,8 @@ cifs_get_root(struct smb3_fs_context *ctx, struct super_block *sb) while (*s && *s != sep) s++; - child = lookup_positive_unlocked(p, dentry, s - p); + child = lookup_noperm_positive_unlocked(&QSTR_LEN(p, s - p), + dentry); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 851b74f557c1..950aa4f912f5 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -160,8 +160,10 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq) server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); rdata->server = server; - cifs_negotiate_rsize(server, cifs_sb->ctx, - tlink_tcon(req->cfile->tlink)); + if (cifs_sb->ctx->rsize == 0) { + cifs_negotiate_rsize(server, cifs_sb->ctx, + tlink_tcon(req->cfile->tlink)); + } rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, &size, &rdata->credits); diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 50f96259d9ad..f9f11cbf89be 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -9,6 +9,7 @@ * */ #include <linux/fs.h> +#include <linux/namei.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/stat.h> @@ -78,7 +79,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); - dentry = d_hash_and_lookup(parent, name); + dentry = try_lookup_noperm(name, parent); if (!dentry) { /* * If we know that the inode will need to be revalidated @@ -733,7 +734,10 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, else cifs_buf_release(cfile->srch_inf. ntwrk_buf_start); + /* Reset all pointers to the network buffer to prevent stale references */ cfile->srch_inf.ntwrk_buf_start = NULL; + cfile->srch_inf.srch_entries_start = NULL; + cfile->srch_inf.last_entry = NULL; } rc = initiate_cifs_search(xid, file, full_path); if (rc) { @@ -756,11 +760,11 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, rc = server->ops->query_dir_next(xid, tcon, &cfile->fid, search_flags, &cfile->srch_inf); + if (rc) + return -ENOENT; /* FindFirst/Next set last_entry to NULL on malformed reply */ if (cfile->srch_inf.last_entry) cifs_save_resume_key(cfile->srch_inf.last_entry, cfile); - if (rc) - return -ENOENT; } if (index_to_find < cfile->srch_inf.index_of_last_entry) { /* we found the buffer that contains the entry */ diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 57d9bfbadd97..2a3e46b8e15a 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -666,6 +666,8 @@ finished: /* smb2_parse_contexts() fills idata->fi.IndexNumber */ rc = smb2_parse_contexts(server, &rsp_iov[0], &oparms->fid->epoch, oparms->fid->lease_key, &oplock, &idata->fi, NULL); + if (rc) + cifs_dbg(VFS, "rc: %d parsing context of compound op\n", rc); } for (i = 0; i < num_cmds; i++) { diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 0b35816d551f..4e28632b5fd6 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -2968,7 +2968,7 @@ replay_again: /* Eventually save off posix specific response info and timestamps */ err_free_rsp_buf: - free_rsp_buf(resp_buftype, rsp); + free_rsp_buf(resp_buftype, rsp_iov.iov_base); kfree(pc_buf); err_free_req: cifs_small_buf_release(req); diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 81a29857b1e3..d7a8a580d013 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -146,12 +146,9 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci) { struct oplock_info *opinfo; - if (list_empty(&ci->m_op_list)) - return NULL; - down_read(&ci->m_lock); - opinfo = list_first_entry(&ci->m_op_list, struct oplock_info, - op_entry); + opinfo = list_first_entry_or_null(&ci->m_op_list, struct oplock_info, + op_entry); if (opinfo) { if (opinfo->conn == NULL || !atomic_inc_not_zero(&opinfo->refcount)) @@ -1496,7 +1493,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req) if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) < sizeof(struct create_lease_v2) - 4) - return NULL; + goto err_out; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; @@ -1512,7 +1509,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req) if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) < sizeof(struct create_lease)) - return NULL; + goto err_out; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; @@ -1521,6 +1518,9 @@ struct lease_ctx_info *parse_lease_state(void *open_req) lreq->version = 1; } return lreq; +err_out: + kfree(lreq); + return NULL; } /** diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 46aa08245742..8d414239b3fe 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -633,6 +633,11 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls) return name; } + if (*name == '\0') { + kfree(name); + return ERR_PTR(-EINVAL); + } + if (*name == '\\') { pr_err("not allow directory name included leading slash\n"); kfree(name); @@ -4115,9 +4120,10 @@ static int process_query_dir_entries(struct smb2_query_dir_private *priv) return -EINVAL; lock_dir(priv->dir_fp); - dent = lookup_one(idmap, priv->d_info->name, - priv->dir_fp->filp->f_path.dentry, - priv->d_info->name_len); + dent = lookup_one(idmap, + &QSTR_LEN(priv->d_info->name, + priv->d_info->name_len), + priv->dir_fp->filp->f_path.dentry); unlock_dir(priv->dir_fp); if (IS_ERR(dent)) { diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 391d07da586c..baf0d3031a44 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -409,10 +409,15 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, ksmbd_debug(VFS, "write stream data pos : %llu, count : %zd\n", *pos, count); + if (*pos >= XATTR_SIZE_MAX) { + pr_err("stream write position %lld is out of bounds\n", *pos); + return -EINVAL; + } + size = *pos + count; if (size > XATTR_SIZE_MAX) { size = XATTR_SIZE_MAX; - count = (*pos + count) - XATTR_SIZE_MAX; + count = XATTR_SIZE_MAX - *pos; } v_len = ksmbd_vfs_getcasexattr(idmap, @@ -677,7 +682,7 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, struct ksmbd_file *parent_fp; int new_type; int err, lookup_flags = LOOKUP_NO_SYMLINKS; - int target_lookup_flags = LOOKUP_RENAME_TARGET; + int target_lookup_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE; if (ksmbd_override_fsids(work)) return -ENOMEM; diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 1f8fa3468173..dfed6fce8904 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -661,21 +661,40 @@ __close_file_table_ids(struct ksmbd_file_table *ft, bool (*skip)(struct ksmbd_tree_connect *tcon, struct ksmbd_file *fp)) { - unsigned int id; - struct ksmbd_file *fp; - int num = 0; + struct ksmbd_file *fp; + unsigned int id = 0; + int num = 0; + + while (1) { + write_lock(&ft->lock); + fp = idr_get_next(ft->idr, &id); + if (!fp) { + write_unlock(&ft->lock); + break; + } - idr_for_each_entry(ft->idr, fp, id) { - if (skip(tcon, fp)) + if (skip(tcon, fp) || + !atomic_dec_and_test(&fp->refcount)) { + id++; + write_unlock(&ft->lock); continue; + } set_close_state_blocked_works(fp); + idr_remove(ft->idr, fp->volatile_id); + fp->volatile_id = KSMBD_NO_FID; + write_unlock(&ft->lock); + + down_write(&fp->f_ci->m_lock); + list_del_init(&fp->node); + up_write(&fp->f_ci->m_lock); - if (!atomic_dec_and_test(&fp->refcount)) - continue; __ksmbd_close_fd(ft, fp); + num++; + id++; } + return num; } diff --git a/fs/stat.c b/fs/stat.c index 3d9222807214..52c604ebbff8 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -254,7 +254,7 @@ int vfs_getattr(const struct path *path, struct kstat *stat, int retval; retval = security_inode_getattr(path); - if (retval) + if (unlikely(retval)) return retval; return vfs_getattr_nosec(path, stat, request_mask, query_flags); } @@ -425,7 +425,7 @@ SYSCALL_DEFINE2(stat, const char __user *, filename, int error; error = vfs_stat(filename, &stat); - if (error) + if (unlikely(error)) return error; return cp_old_stat(&stat, statbuf); @@ -438,7 +438,7 @@ SYSCALL_DEFINE2(lstat, const char __user *, filename, int error; error = vfs_lstat(filename, &stat); - if (error) + if (unlikely(error)) return error; return cp_old_stat(&stat, statbuf); @@ -447,12 +447,13 @@ SYSCALL_DEFINE2(lstat, const char __user *, filename, SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, statbuf) { struct kstat stat; - int error = vfs_fstat(fd, &stat); + int error; - if (!error) - error = cp_old_stat(&stat, statbuf); + error = vfs_fstat(fd, &stat); + if (unlikely(error)) + return error; - return error; + return cp_old_stat(&stat, statbuf); } #endif /* __ARCH_WANT_OLD_STAT */ @@ -506,10 +507,12 @@ SYSCALL_DEFINE2(newstat, const char __user *, filename, struct stat __user *, statbuf) { struct kstat stat; - int error = vfs_stat(filename, &stat); + int error; - if (error) + error = vfs_stat(filename, &stat); + if (unlikely(error)) return error; + return cp_new_stat(&stat, statbuf); } @@ -520,7 +523,7 @@ SYSCALL_DEFINE2(newlstat, const char __user *, filename, int error; error = vfs_lstat(filename, &stat); - if (error) + if (unlikely(error)) return error; return cp_new_stat(&stat, statbuf); @@ -534,8 +537,9 @@ SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename, int error; error = vfs_fstatat(dfd, filename, &stat, flag); - if (error) + if (unlikely(error)) return error; + return cp_new_stat(&stat, statbuf); } #endif @@ -543,12 +547,13 @@ SYSCALL_DEFINE4(newfstatat, int, dfd, const char __user *, filename, SYSCALL_DEFINE2(newfstat, unsigned int, fd, struct stat __user *, statbuf) { struct kstat stat; - int error = vfs_fstat(fd, &stat); + int error; - if (!error) - error = cp_new_stat(&stat, statbuf); + error = vfs_fstat(fd, &stat); + if (unlikely(error)) + return error; - return error; + return cp_new_stat(&stat, statbuf); } #endif diff --git a/fs/super.c b/fs/super.c index 97a17f9d9023..bcc4e87123c8 100644 --- a/fs/super.c +++ b/fs/super.c @@ -39,7 +39,8 @@ #include <uapi/linux/mount.h> #include "internal.h" -static int thaw_super_locked(struct super_block *sb, enum freeze_holder who); +static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner); static LIST_HEAD(super_blocks); static DEFINE_SPINLOCK(sb_lock); @@ -201,7 +202,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink, inodes = list_lru_shrink_count(&sb->s_inode_lru, sc); dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc); - total_objects = dentries + inodes + fs_objects + 1; + total_objects = dentries + inodes + fs_objects; if (!total_objects) total_objects = 1; @@ -887,52 +888,48 @@ void drop_super_exclusive(struct super_block *sb) } EXPORT_SYMBOL(drop_super_exclusive); -static void __iterate_supers(void (*f)(struct super_block *)) -{ - struct super_block *sb, *p = NULL; - - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (super_flags(sb, SB_DYING)) - continue; - sb->s_count++; - spin_unlock(&sb_lock); +enum super_iter_flags_t { + SUPER_ITER_EXCL = (1U << 0), + SUPER_ITER_UNLOCKED = (1U << 1), + SUPER_ITER_REVERSE = (1U << 2), +}; - f(sb); +static inline struct super_block *first_super(enum super_iter_flags_t flags) +{ + if (flags & SUPER_ITER_REVERSE) + return list_last_entry(&super_blocks, struct super_block, s_list); + return list_first_entry(&super_blocks, struct super_block, s_list); +} - spin_lock(&sb_lock); - if (p) - __put_super(p); - p = sb; - } - if (p) - __put_super(p); - spin_unlock(&sb_lock); +static inline struct super_block *next_super(struct super_block *sb, + enum super_iter_flags_t flags) +{ + if (flags & SUPER_ITER_REVERSE) + return list_prev_entry(sb, s_list); + return list_next_entry(sb, s_list); } -/** - * iterate_supers - call function for all active superblocks - * @f: function to call - * @arg: argument to pass to it - * - * Scans the superblock list and calls given function, passing it - * locked superblock and given argument. - */ -void iterate_supers(void (*f)(struct super_block *, void *), void *arg) + +static void __iterate_supers(void (*f)(struct super_block *, void *), void *arg, + enum super_iter_flags_t flags) { struct super_block *sb, *p = NULL; + bool excl = flags & SUPER_ITER_EXCL; - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - bool locked; + guard(spinlock)(&sb_lock); + for (sb = first_super(flags); + !list_entry_is_head(sb, &super_blocks, s_list); + sb = next_super(sb, flags)) { + if (super_flags(sb, SB_DYING)) + continue; sb->s_count++; spin_unlock(&sb_lock); - locked = super_lock_shared(sb); - if (locked) { - if (sb->s_root) - f(sb, arg); - super_unlock_shared(sb); + if (flags & SUPER_ITER_UNLOCKED) { + f(sb, arg); + } else if (super_lock(sb, excl)) { + f(sb, arg); + super_unlock(sb, excl); } spin_lock(&sb_lock); @@ -942,7 +939,11 @@ void iterate_supers(void (*f)(struct super_block *, void *), void *arg) } if (p) __put_super(p); - spin_unlock(&sb_lock); +} + +void iterate_supers(void (*f)(struct super_block *, void *), void *arg) +{ + __iterate_supers(f, arg, 0); } /** @@ -963,15 +964,15 @@ void iterate_supers_type(struct file_system_type *type, hlist_for_each_entry(sb, &type->fs_supers, s_instances) { bool locked; + if (super_flags(sb, SB_DYING)) + continue; + sb->s_count++; spin_unlock(&sb_lock); locked = super_lock_shared(sb); - if (locked) { - if (sb->s_root) - f(sb, arg); - super_unlock_shared(sb); - } + if (locked) + f(sb, arg); spin_lock(&sb_lock); if (p) @@ -991,23 +992,21 @@ struct super_block *user_get_super(dev_t dev, bool excl) spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { - if (sb->s_dev == dev) { - bool locked; - - sb->s_count++; - spin_unlock(&sb_lock); - /* still alive? */ - locked = super_lock(sb, excl); - if (locked) { - if (sb->s_root) - return sb; - super_unlock(sb, excl); - } - /* nope, got unmounted */ - spin_lock(&sb_lock); - __put_super(sb); - break; - } + bool locked; + + if (sb->s_dev != dev) + continue; + + sb->s_count++; + spin_unlock(&sb_lock); + + locked = super_lock(sb, excl); + if (locked) + return sb; + + spin_lock(&sb_lock); + __put_super(sb); + break; } spin_unlock(&sb_lock); return NULL; @@ -1111,11 +1110,9 @@ cancel_readonly: return retval; } -static void do_emergency_remount_callback(struct super_block *sb) +static void do_emergency_remount_callback(struct super_block *sb, void *unused) { - bool locked = super_lock_excl(sb); - - if (locked && sb->s_root && sb->s_bdev && !sb_rdonly(sb)) { + if (sb->s_bdev && !sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, @@ -1126,13 +1123,12 @@ static void do_emergency_remount_callback(struct super_block *sb) put_fs_context(fc); } } - if (locked) - super_unlock_excl(sb); } static void do_emergency_remount(struct work_struct *work) { - __iterate_supers(do_emergency_remount_callback); + __iterate_supers(do_emergency_remount_callback, NULL, + SUPER_ITER_EXCL | SUPER_ITER_REVERSE); kfree(work); printk("Emergency Remount complete\n"); } @@ -1148,24 +1144,18 @@ void emergency_remount(void) } } -static void do_thaw_all_callback(struct super_block *sb) +static void do_thaw_all_callback(struct super_block *sb, void *unused) { - bool locked = super_lock_excl(sb); - - if (locked && sb->s_root) { - if (IS_ENABLED(CONFIG_BLOCK)) - while (sb->s_bdev && !bdev_thaw(sb->s_bdev)) - pr_warn("Emergency Thaw on %pg\n", sb->s_bdev); - thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE); - return; - } - if (locked) - super_unlock_excl(sb); + if (IS_ENABLED(CONFIG_BLOCK)) + while (sb->s_bdev && !bdev_thaw(sb->s_bdev)) + pr_warn("Emergency Thaw on %pg\n", sb->s_bdev); + thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE, NULL); + return; } static void do_thaw_all(struct work_struct *work) { - __iterate_supers(do_thaw_all_callback); + __iterate_supers(do_thaw_all_callback, NULL, SUPER_ITER_EXCL); kfree(work); printk(KERN_WARNING "Emergency Thaw complete\n"); } @@ -1186,6 +1176,66 @@ void emergency_thaw_all(void) } } +static inline bool get_active_super(struct super_block *sb) +{ + bool active = false; + + if (super_lock_excl(sb)) { + active = atomic_inc_not_zero(&sb->s_active); + super_unlock_excl(sb); + } + return active; +} + +static const char *filesystems_freeze_ptr = "filesystems_freeze"; + +static void filesystems_freeze_callback(struct super_block *sb, void *unused) +{ + if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) + return; + + if (!get_active_super(sb)) + return; + + if (sb->s_op->freeze_super) + sb->s_op->freeze_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + else + freeze_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + + deactivate_super(sb); +} + +void filesystems_freeze(void) +{ + __iterate_supers(filesystems_freeze_callback, NULL, + SUPER_ITER_UNLOCKED | SUPER_ITER_REVERSE); +} + +static void filesystems_thaw_callback(struct super_block *sb, void *unused) +{ + if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) + return; + + if (!get_active_super(sb)) + return; + + if (sb->s_op->thaw_super) + sb->s_op->thaw_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + else + thaw_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, + filesystems_freeze_ptr); + + deactivate_super(sb); +} + +void filesystems_thaw(void) +{ + __iterate_supers(filesystems_thaw_callback, NULL, SUPER_ITER_UNLOCKED); +} + static DEFINE_IDA(unnamed_dev_ida); /** @@ -1479,10 +1529,10 @@ static int fs_bdev_freeze(struct block_device *bdev) if (sb->s_op->freeze_super) error = sb->s_op->freeze_super(sb, - FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); else error = freeze_super(sb, - FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); if (!error) error = sync_blockdev(bdev); deactivate_super(sb); @@ -1528,10 +1578,10 @@ static int fs_bdev_thaw(struct block_device *bdev) if (sb->s_op->thaw_super) error = sb->s_op->thaw_super(sb, - FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); else error = thaw_super(sb, - FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); + FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); deactivate_super(sb); return error; } @@ -1903,7 +1953,7 @@ static int wait_for_partially_frozen(struct super_block *sb) } #define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE) -#define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST) +#define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST | FREEZE_EXCL) static inline int freeze_inc(struct super_block *sb, enum freeze_holder who) { @@ -1929,11 +1979,34 @@ static inline int freeze_dec(struct super_block *sb, enum freeze_holder who) return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; } -static inline bool may_freeze(struct super_block *sb, enum freeze_holder who) +static inline bool may_freeze(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) { + lockdep_assert_held(&sb->s_umount); + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + if (who & FREEZE_EXCL) { + if (WARN_ON_ONCE(!(who & FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(who & ~(FREEZE_EXCL | FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(!freeze_owner)) + return false; + /* This freeze already has a specific owner. */ + if (sb->s_writers.freeze_owner) + return false; + /* + * This is already frozen multiple times so we're just + * going to take a reference count and mark the freeze as + * being owned by the caller. + */ + if (sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount) + sb->s_writers.freeze_owner = freeze_owner; + return true; + } + if (who & FREEZE_HOLDER_KERNEL) return (who & FREEZE_MAY_NEST) || sb->s_writers.freeze_kcount == 0; @@ -1943,10 +2016,61 @@ static inline bool may_freeze(struct super_block *sb, enum freeze_holder who) return false; } +static inline bool may_unfreeze(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) +{ + lockdep_assert_held(&sb->s_umount); + + WARN_ON_ONCE((who & ~FREEZE_FLAGS)); + WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); + + if (who & FREEZE_EXCL) { + if (WARN_ON_ONCE(!(who & FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(who & ~(FREEZE_EXCL | FREEZE_HOLDER_KERNEL))) + return false; + if (WARN_ON_ONCE(!freeze_owner)) + return false; + if (WARN_ON_ONCE(sb->s_writers.freeze_kcount == 0)) + return false; + /* This isn't exclusively frozen. */ + if (!sb->s_writers.freeze_owner) + return false; + /* This isn't exclusively frozen by us. */ + if (sb->s_writers.freeze_owner != freeze_owner) + return false; + /* + * This is still frozen multiple times so we're just + * going to drop our reference count and undo our + * exclusive freeze. + */ + if ((sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount) > 1) + sb->s_writers.freeze_owner = NULL; + return true; + } + + if (who & FREEZE_HOLDER_KERNEL) { + /* + * Someone's trying to steal the reference belonging to + * @sb->s_writers.freeze_owner. + */ + if (sb->s_writers.freeze_kcount == 1 && + sb->s_writers.freeze_owner) + return false; + return sb->s_writers.freeze_kcount > 0; + } + + if (who & FREEZE_HOLDER_USERSPACE) + return sb->s_writers.freeze_ucount > 0; + + return false; +} + /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock * @who: context that wants to freeze + * @freeze_owner: owner of the freeze * * Syncs the super to make sure the filesystem is consistent and calls the fs's * freeze_fs. Subsequent calls to this without first thawing the fs may return @@ -1998,7 +2122,7 @@ static inline bool may_freeze(struct super_block *sb, enum freeze_holder who) * Return: If the freeze was successful zero is returned. If the freeze * failed a negative error code is returned. */ -int freeze_super(struct super_block *sb, enum freeze_holder who) +int freeze_super(struct super_block *sb, enum freeze_holder who, const void *freeze_owner) { int ret; @@ -2010,7 +2134,7 @@ int freeze_super(struct super_block *sb, enum freeze_holder who) retry: if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) { - if (may_freeze(sb, who)) + if (may_freeze(sb, who, freeze_owner)) ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1); else ret = -EBUSY; @@ -2032,6 +2156,7 @@ retry: if (sb_rdonly(sb)) { /* Nothing to do really... */ WARN_ON_ONCE(freeze_inc(sb, who) > 1); + sb->s_writers.freeze_owner = freeze_owner; sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); super_unlock_excl(sb); @@ -2079,6 +2204,7 @@ retry: * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super(). */ WARN_ON_ONCE(freeze_inc(sb, who) > 1); + sb->s_writers.freeze_owner = freeze_owner; sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); lockdep_sb_freeze_release(sb); @@ -2093,13 +2219,17 @@ EXPORT_SYMBOL(freeze_super); * removes that state without releasing the other state or unlocking the * filesystem. */ -static int thaw_super_locked(struct super_block *sb, enum freeze_holder who) +static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) { int error = -EINVAL; if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) goto out_unlock; + if (!may_unfreeze(sb, who, freeze_owner)) + goto out_unlock; + /* * All freezers share a single active reference. * So just unlock in case there are any left. @@ -2109,6 +2239,7 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who) if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; + sb->s_writers.freeze_owner = NULL; wake_up_var(&sb->s_writers.frozen); goto out_deactivate; } @@ -2126,6 +2257,7 @@ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who) } sb->s_writers.frozen = SB_UNFROZEN; + sb->s_writers.freeze_owner = NULL; wake_up_var(&sb->s_writers.frozen); sb_freeze_unlock(sb, SB_FREEZE_FS); out_deactivate: @@ -2141,6 +2273,7 @@ out_unlock: * thaw_super -- unlock filesystem * @sb: the super to thaw * @who: context that wants to freeze + * @freeze_owner: owner of the freeze * * Unlocks the filesystem and marks it writeable again after freeze_super() * if there are no remaining freezes on the filesystem. @@ -2154,13 +2287,14 @@ out_unlock: * have been frozen through the block layer via multiple block devices. * The filesystem remains frozen until all block devices are unfrozen. */ -int thaw_super(struct super_block *sb, enum freeze_holder who) +int thaw_super(struct super_block *sb, enum freeze_holder who, + const void *freeze_owner) { if (!super_lock_excl(sb)) { WARN_ON_ONCE("Dying superblock while thawing!"); return -EINVAL; } - return thaw_super_locked(sb, who); + return thaw_super_locked(sb, who, freeze_owner); } EXPORT_SYMBOL(thaw_super); diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index cb1af30b49f5..a3fd3cc591bd 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -555,7 +555,7 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent) if (unlikely(IS_DEADDIR(d_inode(parent)))) dentry = ERR_PTR(-ENOENT); else - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_noperm(&QSTR(name), parent); if (!IS_ERR(dentry) && d_inode(dentry)) { dput(dentry); dentry = ERR_PTR(-EEXIST); diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 4f33a4a48886..b4071c9cf8c9 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -115,7 +115,7 @@ void udf_truncate_tail_extent(struct inode *inode) } /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ - if (ret == 0) + if (ret >= 0) iinfo->i_lenExtents = inode->i_size; brelse(epos.bh); } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d80f94346199..22f4bf956ba1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, @@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, @@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, @@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_poison->updated))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, @@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, user_uffdio_move = (struct uffdio_move __user *) arg; - if (atomic_read(&ctx->mmap_changing)) - return -EAGAIN; + ret = -EAGAIN; + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + goto out; + } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */ diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c index b780deb81b02..b492794f8e9a 100644 --- a/fs/vboxsf/file.c +++ b/fs/vboxsf/file.c @@ -262,40 +262,42 @@ static struct vboxsf_handle *vboxsf_get_write_handle(struct vboxsf_inode *sf_i) return sf_handle; } -static int vboxsf_writepage(struct page *page, struct writeback_control *wbc) +static int vboxsf_writepages(struct address_space *mapping, + struct writeback_control *wbc) { - struct inode *inode = page->mapping->host; + struct inode *inode = mapping->host; + struct folio *folio = NULL; struct vboxsf_inode *sf_i = VBOXSF_I(inode); struct vboxsf_handle *sf_handle; - loff_t off = page_offset(page); loff_t size = i_size_read(inode); - u32 nwrite = PAGE_SIZE; - u8 *buf; - int err; - - if (off + PAGE_SIZE > size) - nwrite = size & ~PAGE_MASK; + int error; sf_handle = vboxsf_get_write_handle(sf_i); if (!sf_handle) return -EBADF; - buf = kmap(page); - err = vboxsf_write(sf_handle->root, sf_handle->handle, - off, &nwrite, buf); - kunmap(page); + while ((folio = writeback_iter(mapping, wbc, folio, &error))) { + loff_t off = folio_pos(folio); + u32 nwrite = folio_size(folio); + u8 *buf; - kref_put(&sf_handle->refcount, vboxsf_handle_release); + if (nwrite > size - off) + nwrite = size - off; - if (err == 0) { - /* mtime changed */ - sf_i->force_restat = 1; - } else { - ClearPageUptodate(page); + buf = kmap_local_folio(folio, 0); + error = vboxsf_write(sf_handle->root, sf_handle->handle, + off, &nwrite, buf); + kunmap_local(buf); + + folio_unlock(folio); } - unlock_page(page); - return err; + kref_put(&sf_handle->refcount, vboxsf_handle_release); + + /* mtime changed */ + if (error == 0) + sf_i->force_restat = 1; + return error; } static int vboxsf_write_end(struct file *file, struct address_space *mapping, @@ -347,10 +349,11 @@ out: */ const struct address_space_operations vboxsf_reg_aops = { .read_folio = vboxsf_read_folio, - .writepage = vboxsf_writepage, + .writepages = vboxsf_writepages, .dirty_folio = filemap_dirty_folio, .write_begin = simple_write_begin, .write_end = vboxsf_write_end, + .migrate_folio = filemap_migrate_folio, }; static const char *vboxsf_get_link(struct dentry *dentry, struct inode *inode, diff --git a/fs/xattr.c b/fs/xattr.c index fabb2a04501e..8ec5b0204bfd 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -1428,6 +1428,15 @@ static bool xattr_is_trusted(const char *name) return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } +static bool xattr_is_maclabel(const char *name) +{ + const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; + + return !strncmp(name, XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN) && + security_ismaclabel(suffix); +} + /** * simple_xattr_list - list all xattr objects * @inode: inode from which to get the xattrs @@ -1460,6 +1469,17 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, if (err) return err; + err = security_inode_listsecurity(inode, buffer, remaining_size); + if (err < 0) + return err; + + if (buffer) { + if (remaining_size < err) + return -ERANGE; + buffer += err; + } + remaining_size -= err; + read_lock(&xattrs->lock); for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) { xattr = rb_entry(rbp, struct simple_xattr, rb_node); @@ -1468,6 +1488,10 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, if (!trusted && xattr_is_trusted(xattr->name)) continue; + /* skip MAC labels; these are provided by LSM above */ + if (xattr_is_maclabel(xattr->name)) + continue; + err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) break; diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index e629663e460a..9b598c5790ad 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -123,7 +123,7 @@ xchk_fsfreeze( { int error; - error = freeze_super(sc->mp->m_super, FREEZE_HOLDER_KERNEL); + error = freeze_super(sc->mp->m_super, FREEZE_HOLDER_KERNEL, NULL); trace_xchk_fsfreeze(sc, error); return error; } @@ -135,7 +135,7 @@ xchk_fsthaw( int error; /* This should always succeed, we have a kernel freeze */ - error = thaw_super(sc->mp->m_super, FREEZE_HOLDER_KERNEL); + error = thaw_super(sc->mp->m_super, FREEZE_HOLDER_KERNEL, NULL); trace_xchk_fsthaw(sc, error); return error; } diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c index 3537f3cca6d5..9c12cb844231 100644 --- a/fs/xfs/scrub/orphanage.c +++ b/fs/xfs/scrub/orphanage.c @@ -153,8 +153,7 @@ xrep_orphanage_create( /* Try to find the orphanage directory. */ inode_lock_nested(root_inode, I_MUTEX_PARENT); - orphanage_dentry = lookup_one_len(ORPHANAGE, root_dentry, - strlen(ORPHANAGE)); + orphanage_dentry = lookup_noperm(&QSTR(ORPHANAGE), root_dentry); if (IS_ERR(orphanage_dentry)) { error = PTR_ERR(orphanage_dentry); goto out_unlock_root; @@ -445,7 +444,7 @@ xrep_adoption_check_dcache( if (!d_orphanage) return 0; - d_child = d_hash_and_lookup(d_orphanage, &qname); + d_child = try_lookup_noperm(&qname, d_orphanage); if (d_child) { trace_xrep_adoption_check_child(sc->mp, d_child); @@ -482,7 +481,7 @@ xrep_adoption_zap_dcache( if (!d_orphanage) return; - d_child = d_hash_and_lookup(d_orphanage, &qname); + d_child = try_lookup_noperm(&qname, d_orphanage); while (d_child != NULL) { trace_xrep_adoption_invalidate_child(sc->mp, d_child); diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index ed8d8ed42f0a..3545dc1d953c 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -127,7 +127,7 @@ xfs_dax_notify_failure_freeze( struct super_block *sb = mp->m_super; int error; - error = freeze_super(sb, FREEZE_HOLDER_KERNEL); + error = freeze_super(sb, FREEZE_HOLDER_KERNEL, NULL); if (error) xfs_emerg(mp, "already frozen by kernel, err=%d", error); @@ -143,7 +143,7 @@ xfs_dax_notify_failure_thaw( int error; if (kernel_frozen) { - error = thaw_super(sb, FREEZE_HOLDER_KERNEL); + error = thaw_super(sb, FREEZE_HOLDER_KERNEL, NULL); if (error) xfs_emerg(mp, "still frozen after notify failure, err=%d", error); @@ -153,7 +153,7 @@ xfs_dax_notify_failure_thaw( * Also thaw userspace call anyway because the device is about to be * removed immediately. */ - thaw_super(sb, FREEZE_HOLDER_USERSPACE); + thaw_super(sb, FREEZE_HOLDER_USERSPACE, NULL); } static int diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index b2dd0c0bf509..4a11ddccc563 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1149,7 +1149,7 @@ xfs_init_percpu_counters( return 0; free_freecounters: - while (--i > 0) + while (--i >= 0) percpu_counter_destroy(&mp->m_free[i].count); percpu_counter_destroy(&mp->m_delalloc_rtextents); free_delalloc: @@ -2114,6 +2114,21 @@ xfs_fs_reconfigure( if (error) return error; + /* attr2 -> noattr2 */ + if (xfs_has_noattr2(new_mp)) { + if (xfs_has_crc(mp)) { + xfs_warn(mp, + "attr2 is always enabled for a V5 filesystem - can't be changed."); + return -EINVAL; + } + mp->m_features &= ~XFS_FEAT_ATTR2; + mp->m_features |= XFS_FEAT_NOATTR2; + } else if (xfs_has_attr2(new_mp)) { + /* noattr2 -> attr2 */ + mp->m_features &= ~XFS_FEAT_NOATTR2; + mp->m_features |= XFS_FEAT_ATTR2; + } + /* inode32 -> inode64 */ if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) { mp->m_features &= ~XFS_FEAT_SMALL_INUMS; @@ -2126,6 +2141,17 @@ xfs_fs_reconfigure( mp->m_maxagi = xfs_set_inode_alloc(mp, mp->m_sb.sb_agcount); } + /* + * Now that mp has been modified according to the remount options, we + * do a final option validation with xfs_finish_flags() just like it is + * just like it is done during mount. We cannot use + * done during mount. We cannot use xfs_finish_flags() on new_mp as it + * contains only the user given options. + */ + error = xfs_finish_flags(mp); + if (error) + return error; + /* ro -> rw */ if (xfs_is_readonly(mp) && !(flags & SB_RDONLY)) { error = xfs_remount_rw(mp); diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 85a649fec6ac..67c328d23e4a 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -315,7 +315,7 @@ xfs_ail_splice( } /* - * Delete the given item from the AIL. Return a pointer to the item. + * Delete the given item from the AIL. */ static void xfs_ail_delete( @@ -777,26 +777,28 @@ xfs_ail_update_finish( } /* - * xfs_trans_ail_update - bulk AIL insertion operation. + * xfs_trans_ail_update_bulk - bulk AIL insertion operation. * - * @xfs_trans_ail_update takes an array of log items that all need to be + * @xfs_trans_ail_update_bulk takes an array of log items that all need to be * positioned at the same LSN in the AIL. If an item is not in the AIL, it will - * be added. Otherwise, it will be repositioned by removing it and re-adding - * it to the AIL. If we move the first item in the AIL, update the log tail to - * match the new minimum LSN in the AIL. + * be added. Otherwise, it will be repositioned by removing it and re-adding + * it to the AIL. * - * This function takes the AIL lock once to execute the update operations on - * all the items in the array, and as such should not be called with the AIL - * lock held. As a result, once we have the AIL lock, we need to check each log - * item LSN to confirm it needs to be moved forward in the AIL. + * If we move the first item in the AIL, update the log tail to match the new + * minimum LSN in the AIL. * - * To optimise the insert operation, we delete all the items from the AIL in - * the first pass, moving them into a temporary list, then splice the temporary - * list into the correct position in the AIL. This avoids needing to do an - * insert operation on every item. + * This function should be called with the AIL lock held. * - * This function must be called with the AIL lock held. The lock is dropped - * before returning. + * To optimise the insert operation, we add all items to a temporary list, then + * splice this list into the correct position in the AIL. + * + * Items that are already in the AIL are first deleted from their current + * location before being added to the temporary list. + * + * This avoids needing to do an insert operation on every item. + * + * The AIL lock is dropped by xfs_ail_update_finish() before returning to + * the caller. */ void xfs_trans_ail_update_bulk( diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index 81c94dd1d596..d613a4094db6 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -807,7 +807,8 @@ xfs_zone_gc_write_chunk( { struct xfs_zone_gc_data *data = chunk->data; struct xfs_mount *mp = chunk->ip->i_mount; - unsigned int folio_offset = chunk->bio.bi_io_vec->bv_offset; + phys_addr_t bvec_paddr = + bvec_phys(bio_first_bvec_all(&chunk->bio)); struct xfs_gc_bio *split_chunk; if (chunk->bio.bi_status) @@ -822,7 +823,7 @@ xfs_zone_gc_write_chunk( bio_reset(&chunk->bio, mp->m_rtdev_targp->bt_bdev, REQ_OP_WRITE); bio_add_folio_nofail(&chunk->bio, chunk->scratch->folio, chunk->len, - folio_offset); + offset_in_folio(chunk->scratch->folio, bvec_paddr)); while ((split_chunk = xfs_zone_gc_split_write(data, chunk))) xfs_zone_gc_submit_write(data, split_chunk); diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h index df120b4d1f83..eaf704d3d05e 100644 --- a/include/drm/drm_gpusvm.h +++ b/include/drm/drm_gpusvm.h @@ -89,6 +89,7 @@ struct drm_gpusvm_devmem_ops { * @ops: Pointer to the operations structure for GPU SVM device memory * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to. * @size: Size of device memory allocation + * @timeslice_expiration: Timeslice expiration in jiffies */ struct drm_gpusvm_devmem { struct device *dev; @@ -97,6 +98,7 @@ struct drm_gpusvm_devmem { const struct drm_gpusvm_devmem_ops *ops; struct drm_pagemap *dpagemap; size_t size; + u64 timeslice_expiration; }; /** @@ -186,6 +188,31 @@ struct drm_gpusvm_notifier { }; /** + * struct drm_gpusvm_range_flags - Structure representing a GPU SVM range flags + * + * @migrate_devmem: Flag indicating whether the range can be migrated to device memory + * @unmapped: Flag indicating if the range has been unmapped + * @partial_unmap: Flag indicating if the range has been partially unmapped + * @has_devmem_pages: Flag indicating if the range has devmem pages + * @has_dma_mapping: Flag indicating if the range has a DMA mapping + * @__flags: Flags for range in u16 form (used for READ_ONCE) + */ +struct drm_gpusvm_range_flags { + union { + struct { + /* All flags below must be set upon creation */ + u16 migrate_devmem : 1; + /* All flags below must be set / cleared under notifier lock */ + u16 unmapped : 1; + u16 partial_unmap : 1; + u16 has_devmem_pages : 1; + u16 has_dma_mapping : 1; + }; + u16 __flags; + }; +}; + +/** * struct drm_gpusvm_range - Structure representing a GPU SVM range * * @gpusvm: Pointer to the GPU SVM structure @@ -198,11 +225,6 @@ struct drm_gpusvm_notifier { * @dpagemap: The struct drm_pagemap of the device pages we're dma-mapping. * Note this is assuming only one drm_pagemap per range is allowed. * @flags: Flags for range - * @flags.migrate_devmem: Flag indicating whether the range can be migrated to device memory - * @flags.unmapped: Flag indicating if the range has been unmapped - * @flags.partial_unmap: Flag indicating if the range has been partially unmapped - * @flags.has_devmem_pages: Flag indicating if the range has devmem pages - * @flags.has_dma_mapping: Flag indicating if the range has a DMA mapping * * This structure represents a GPU SVM range used for tracking memory ranges * mapped in a DRM device. @@ -216,15 +238,7 @@ struct drm_gpusvm_range { unsigned long notifier_seq; struct drm_pagemap_device_addr *dma_addr; struct drm_pagemap *dpagemap; - struct { - /* All flags below must be set upon creation */ - u16 migrate_devmem : 1; - /* All flags below must be set / cleared under notifier lock */ - u16 unmapped : 1; - u16 partial_unmap : 1; - u16 has_devmem_pages : 1; - u16 has_dma_mapping : 1; - } flags; + struct drm_gpusvm_range_flags flags; }; /** @@ -283,17 +297,22 @@ struct drm_gpusvm { * @check_pages_threshold: Check CPU pages for present if chunk is less than or * equal to threshold. If not present, reduce chunk * size. + * @timeslice_ms: The timeslice MS which in minimum time a piece of memory + * remains with either exclusive GPU or CPU access. * @in_notifier: entering from a MMU notifier * @read_only: operating on read-only memory * @devmem_possible: possible to use device memory + * @devmem_only: use only device memory * * Context that is DRM GPUSVM is operating in (i.e. user arguments). */ struct drm_gpusvm_ctx { unsigned long check_pages_threshold; + unsigned long timeslice_ms; unsigned int in_notifier :1; unsigned int read_only :1; unsigned int devmem_possible :1; + unsigned int devmem_only :1; }; int drm_gpusvm_init(struct drm_gpusvm *gpusvm, diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h index d212848d07f3..a7ce9523c50d 100644 --- a/include/drm/intel/pciids.h +++ b/include/drm/intel/pciids.h @@ -861,6 +861,10 @@ MACRO__(0xB081, ## __VA_ARGS__), \ MACRO__(0xB082, ## __VA_ARGS__), \ MACRO__(0xB083, ## __VA_ARGS__), \ + MACRO__(0xB084, ## __VA_ARGS__), \ + MACRO__(0xB085, ## __VA_ARGS__), \ + MACRO__(0xB086, ## __VA_ARGS__), \ + MACRO__(0xB087, ## __VA_ARGS__), \ MACRO__(0xB08F, ## __VA_ARGS__), \ MACRO__(0xB090, ## __VA_ARGS__), \ MACRO__(0xB0A0, ## __VA_ARGS__), \ diff --git a/include/drm/ttm/ttm_backup.h b/include/drm/ttm/ttm_backup.h index 24ad120b8827..c33cba111171 100644 --- a/include/drm/ttm/ttm_backup.h +++ b/include/drm/ttm/ttm_backup.h @@ -9,14 +9,12 @@ #include <linux/mm_types.h> #include <linux/shmem_fs.h> -struct ttm_backup; - /** * ttm_backup_handle_to_page_ptr() - Convert handle to struct page pointer * @handle: The handle to convert. * * Converts an opaque handle received from the - * struct ttm_backoup_ops::backup_page() function to an (invalid) + * ttm_backup_backup_page() function to an (invalid) * struct page pointer suitable for a struct page array. * * Return: An (invalid) struct page pointer. @@ -45,8 +43,8 @@ static inline bool ttm_backup_page_ptr_is_handle(const struct page *page) * * Return: The handle that was previously used in * ttm_backup_handle_to_page_ptr() to obtain a struct page pointer, suitable - * for use as argument in the struct ttm_backup_ops drop() or - * copy_backed_up_page() functions. + * for use as argument in the struct ttm_backup_drop() or + * ttm_backup_copy_page() functions. */ static inline unsigned long ttm_backup_page_ptr_to_handle(const struct page *page) @@ -55,20 +53,20 @@ ttm_backup_page_ptr_to_handle(const struct page *page) return (unsigned long)page >> 1; } -void ttm_backup_drop(struct ttm_backup *backup, pgoff_t handle); +void ttm_backup_drop(struct file *backup, pgoff_t handle); -int ttm_backup_copy_page(struct ttm_backup *backup, struct page *dst, +int ttm_backup_copy_page(struct file *backup, struct page *dst, pgoff_t handle, bool intr); s64 -ttm_backup_backup_page(struct ttm_backup *backup, struct page *page, +ttm_backup_backup_page(struct file *backup, struct page *page, bool writeback, pgoff_t idx, gfp_t page_gfp, gfp_t alloc_gfp); -void ttm_backup_fini(struct ttm_backup *backup); +void ttm_backup_fini(struct file *backup); u64 ttm_backup_bytes_avail(void); -struct ttm_backup *ttm_backup_shmem_create(loff_t size); +struct file *ttm_backup_shmem_create(loff_t size); #endif diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 13cf47f3322f..406437ad674b 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -118,7 +118,7 @@ struct ttm_tt { * ttm_tt_create() callback is responsible for assigning * this field. */ - struct ttm_backup *backup; + struct file *backup; /** * @caching: The current caching state of the pages, see enum * ttm_caching. diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index a946e0203e6d..8f7931eb7d16 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -104,6 +104,16 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); #else /* ARCH_NEEDS_WEAK_PER_CPU */ +#ifdef MODULE + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section(ALLOC_TAG_SECTION_NAME) = { \ + .ct = CODE_TAG_INIT, \ + .counters = NULL }; + +#else /* MODULE */ + #define DEFINE_ALLOC_TAG(_alloc_tag) \ static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ static struct alloc_tag _alloc_tag __used __aligned(8) \ @@ -111,6 +121,8 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); .ct = CODE_TAG_INIT, \ .counters = &_alloc_tag_cntr }; +#endif /* MODULE */ + #endif /* ARCH_NEEDS_WEAK_PER_CPU */ DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 1625c8529e70..65abd5ab8836 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -90,7 +90,6 @@ struct linux_binfmt { struct list_head lh; struct module *module; int (*load_binary)(struct linux_binprm *); - int (*load_shlib)(struct file *); #ifdef CONFIG_COREDUMP int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ diff --git a/include/linux/bio.h b/include/linux/bio.h index cafc7c215de8..b786ec5bcc81 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -11,6 +11,7 @@ #include <linux/uio.h> #define BIO_MAX_VECS 256U +#define BIO_MAX_INLINE_VECS UIO_MAXIOV struct queue_limits; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e7da3c3b098b..166d6de50dbf 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -785,6 +785,17 @@ struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); +static inline void get_cgroup_ns(struct cgroup_namespace *ns) +{ + refcount_inc(&ns->ns.count); +} + +static inline void put_cgroup_ns(struct cgroup_namespace *ns) +{ + if (refcount_dec_and_test(&ns->ns.count)) + free_cgroup_ns(ns); +} + #else /* !CONFIG_CGROUPS */ static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } @@ -795,19 +806,10 @@ copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, return old_ns; } -#endif /* !CONFIG_CGROUPS */ +static inline void get_cgroup_ns(struct cgroup_namespace *ns) { } +static inline void put_cgroup_ns(struct cgroup_namespace *ns) { } -static inline void get_cgroup_ns(struct cgroup_namespace *ns) -{ - if (ns) - refcount_inc(&ns->ns.count); -} - -static inline void put_cgroup_ns(struct cgroup_namespace *ns) -{ - if (ns && refcount_dec_and_test(&ns->ns.count)) - free_cgroup_ns(ns); -} +#endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS diff --git a/include/linux/codetag.h b/include/linux/codetag.h index d14dbd26b370..0ee4c21c6dbc 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -36,10 +36,10 @@ union codetag_ref { struct codetag_type_desc { const char *section; size_t tag_size; - void (*module_load)(struct codetag_type *cttype, - struct codetag_module *cmod); - void (*module_unload)(struct codetag_type *cttype, - struct codetag_module *cmod); + void (*module_load)(struct module *mod, + struct codetag *start, struct codetag *end); + void (*module_unload)(struct module *mod, + struct codetag *start, struct codetag *end); #ifdef CONFIG_MODULES void (*module_replaced)(struct module *mod, struct module *new_mod); bool (*needs_section_mem)(struct module *mod, unsigned long size); diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 77e6e195d1d6..76e41805b92d 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -28,6 +28,7 @@ struct coredump_params { int vma_count; size_t vma_data_size; struct core_vma_metadata *vma_meta; + struct pid *pid; }; extern unsigned int core_file_note_size_limit; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e3049543008b..3aa955102b34 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -78,6 +78,8 @@ extern ssize_t cpu_show_gds(struct device *dev, extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_indirect_target_selection(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/dcache.h b/include/linux/dcache.h index e9f07e37dd6f..e29823c701ac 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -57,7 +57,8 @@ struct qstr { }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } -#define QSTR(n) (struct qstr)QSTR_INIT(n, strlen(n)) +#define QSTR_LEN(n,l) (struct qstr)QSTR_INIT(n,l) +#define QSTR(n) QSTR_LEN(n, strlen(n)) extern const struct qstr empty_name; extern const struct qstr slash_name; @@ -281,7 +282,6 @@ extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); -extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); static inline unsigned d_count(const struct dentry *dentry) { diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index d02f32b7514e..0864773a57e8 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -18,15 +18,16 @@ static inline int devcgroup_inode_permission(struct inode *inode, int mask) { short type, access = 0; + if (likely(!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))) + return 0; + if (likely(!inode->i_rdev)) return 0; if (S_ISBLK(inode->i_mode)) type = DEVCG_DEV_BLOCK; - else if (S_ISCHR(inode->i_mode)) + else /* S_ISCHR by the test above */ type = DEVCG_DEV_CHAR; - else - return 0; if (mask & MAY_WRITE) access |= DEVCG_ACC_WRITE; diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 65655a5d1be2..ca42d5e46ccc 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/moduleloader.h> +#include <linux/cleanup.h> #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -53,7 +54,7 @@ enum execmem_range_flags { EXECMEM_ROX_CACHE = (1 << 1), }; -#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM) /** * execmem_fill_trapping_insns - set memory to contain instructions that * will trap @@ -93,9 +94,15 @@ int execmem_make_temp_rw(void *ptr, size_t size); * Return: 0 on success or negative error code on failure. */ int execmem_restore_rox(void *ptr, size_t size); + +/* + * Called from mark_readonly(), where the system transitions to ROX. + */ +void execmem_cache_make_ro(void); #else static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; } static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; } +static inline void execmem_cache_make_ro(void) { } #endif /** @@ -170,6 +177,8 @@ void *execmem_alloc(enum execmem_type type, size_t size); */ void execmem_free(void *ptr); +DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T)); + #ifdef CONFIG_MMU /** * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory diff --git a/include/linux/file.h b/include/linux/file.h index 302f11355b10..af1768d934a0 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -59,7 +59,7 @@ static inline struct fd CLONED_FD(struct file *f) static inline void fdput(struct fd fd) { - if (fd.word & FDPUT_FPUT) + if (unlikely(fd.word & FDPUT_FPUT)) fput(fd_file(fd)); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 016b0fe1536e..81f8f0aec563 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -433,7 +433,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb) } struct address_space_operations { - int (*writepage)(struct page *page, struct writeback_control *wbc); int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ @@ -867,6 +866,11 @@ static inline void inode_lock(struct inode *inode) down_write(&inode->i_rwsem); } +static inline __must_check int inode_lock_killable(struct inode *inode) +{ + return down_write_killable(&inode->i_rwsem); +} + static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); @@ -877,6 +881,11 @@ static inline void inode_lock_shared(struct inode *inode) down_read(&inode->i_rwsem); } +static inline __must_check int inode_lock_shared_killable(struct inode *inode) +{ + return down_read_killable(&inode->i_rwsem); +} + static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); @@ -1307,6 +1316,7 @@ struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ + const void *freeze_owner; /* Owner of the freeze */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; @@ -1780,7 +1790,7 @@ static inline void __sb_end_write(struct super_block *sb, int level) static inline void __sb_start_write(struct super_block *sb, int level) { - percpu_down_read(sb->s_writers.rw_sem + level - 1); + percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) @@ -2071,8 +2081,18 @@ typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, struct dir_context { filldir_t actor; loff_t pos; + /* + * Filesystems MUST NOT MODIFY count, but may use as a hint: + * 0 unknown + * > 0 space in buffer (assume at least one entry) + * INT_MAX unlimited + */ + int count; }; +/* If OR-ed with d_type, pending signals are not checked */ +#define FILLDIR_FLAG_NOINTR 0x1000 + /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. @@ -2186,7 +2206,7 @@ struct file_operations { /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* File system supports uncached read/write buffered IO */ -#define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) +#define FOP_DONTCACHE 0 /* ((__force fop_flags_t)(1 << 7)) */ /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, @@ -2269,6 +2289,7 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed + * @FREEZE_EXCL: a freeze that can only be undone by the owner * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. @@ -2282,6 +2303,7 @@ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), + FREEZE_EXCL = (1U << 3), }; struct super_operations { @@ -2295,9 +2317,9 @@ struct super_operations { void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); - int (*freeze_super) (struct super_block *, enum freeze_holder who); + int (*freeze_super) (struct super_block *, enum freeze_holder who, const void *owner); int (*freeze_fs) (struct super_block *); - int (*thaw_super) (struct super_block *, enum freeze_holder who); + int (*thaw_super) (struct super_block *, enum freeze_holder who, const void *owner); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); @@ -2344,6 +2366,7 @@ struct super_operations { #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ +#define S_ANON_INODE (1 << 19) /* Inode is an anonymous inode */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -2400,6 +2423,7 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) +#define IS_ANON_FILE(inode) ((inode)->i_flags & S_ANON_INODE) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) @@ -2705,8 +2729,10 @@ extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); -int freeze_super(struct super_block *super, enum freeze_holder who); -int thaw_super(struct super_block *super, enum freeze_holder who); +int freeze_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); +int thaw_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); @@ -3515,9 +3541,11 @@ extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); -extern void iterate_supers(void (*)(struct super_block *, void *), void *); +extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); +void filesystems_freeze(void); +void filesystems_thaw(void); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 53e566efd5fd..5a0e897cae80 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -87,14 +87,9 @@ extern int lookup_constant(const struct constant_table tbl[], const char *name, extern const struct constant_table bool_names[]; #ifdef CONFIG_VALIDATE_FS_PARSER -extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, - int low, int high, int special); extern bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc); #else -static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, - int low, int high, int special) -{ return true; } static inline bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) { return true; } @@ -125,8 +120,6 @@ static inline bool fs_validate_description(const char *name, #define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0, NULL) #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) -#define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 5c6bea81a90e..c698f8415675 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -461,7 +461,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio, const char *from = kmap_local_folio(folio, offset); size_t chunk = len; - if (folio_test_highmem(folio) && + if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); @@ -489,7 +489,7 @@ static inline void memcpy_to_folio(struct folio *folio, size_t offset, char *to = kmap_local_folio(folio, offset); size_t chunk = len; - if (folio_test_highmem(folio) && + if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); @@ -522,7 +522,7 @@ static inline __must_check void *folio_zero_tail(struct folio *folio, { size_t len = folio_size(folio) - offset; - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { @@ -560,7 +560,7 @@ static inline void folio_fill_tail(struct folio *folio, size_t offset, VM_BUG_ON(offset + len > folio_size(folio)); - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { @@ -597,7 +597,7 @@ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8f3ac832ee7f..4861a7e304bb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -275,6 +275,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void fixup_hugetlb_reservations(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -468,6 +469,10 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 675959fb97ba..b52ac40d5830 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1002,6 +1002,12 @@ struct vmbus_channel { /* The max size of a packet on this channel */ u32 max_pkt_size; + + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + + /* boolean to control visibility of sysfs for ring buffer */ + bool ring_sysfs_visible; }; #define lock_requestor(channel, flags) \ @@ -1161,13 +1167,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, - void *buffer, - u32 bufferlen, - u64 requestid); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 508d466de1cc..457b4fba88bd 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1526,7 +1526,7 @@ struct ieee80211_mgmt { struct { u8 action_code; u8 dialog_token; - u8 status_code; + __le16 status_code; u8 variable[]; } __packed ttlm_res; struct { diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 591bf5b5e8dc..9af01bdd86d2 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -44,7 +44,6 @@ #define MICREL_PHY_50MHZ_CLK BIT(0) #define MICREL_PHY_FXEN BIT(1) #define MICREL_KSZ8_P1_ERRATA BIT(2) -#define MICREL_NO_EEE BIT(3) #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC diff --git a/include/linux/mm.h b/include/linux/mm.h index bf55206935c4..fdda6b16263b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -385,7 +385,7 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR -# define VM_UFFD_MINOR_BIT 38 +# define VM_UFFD_MINOR_BIT 41 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE diff --git a/include/linux/mman.h b/include/linux/mman.h index bce214fece16..f4c6346a8fcd 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -155,7 +155,9 @@ calc_vm_flag_bits(struct file *file, unsigned long flags) return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | +#ifdef CONFIG_TRANSPARENT_HUGEPAGE _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | +#endif arch_calc_vm_flag_bits(file, flags); } diff --git a/include/linux/module.h b/include/linux/module.h index b3329110d668..8050f77c3b64 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,6 +586,11 @@ struct module { atomic_t refcnt; #endif +#ifdef CONFIG_MITIGATION_ITS + int its_num_pages; + void **its_page_array; +#endif + #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; diff --git a/include/linux/mount.h b/include/linux/mount.h index dcc17ce8a959..6904ad33ee7a 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -22,48 +22,51 @@ struct fs_context; struct file; struct path; -#define MNT_NOSUID 0x01 -#define MNT_NODEV 0x02 -#define MNT_NOEXEC 0x04 -#define MNT_NOATIME 0x08 -#define MNT_NODIRATIME 0x10 -#define MNT_RELATIME 0x20 -#define MNT_READONLY 0x40 /* does the user want this to be r/o? */ -#define MNT_NOSYMFOLLOW 0x80 - -#define MNT_SHRINKABLE 0x100 -#define MNT_WRITE_HOLD 0x200 - -#define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */ -#define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */ -/* - * MNT_SHARED_MASK is the set of flags that should be cleared when a - * mount becomes shared. Currently, this is only the flag that says a - * mount cannot be bind mounted, since this is how we create a mount - * that shares events with another mount. If you add a new MNT_* - * flag, consider how it interacts with shared mounts. - */ -#define MNT_SHARED_MASK (MNT_UNBINDABLE) -#define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ - | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ - | MNT_READONLY | MNT_NOSYMFOLLOW) -#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) - -#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) - -#define MNT_INTERNAL 0x4000 - -#define MNT_LOCK_ATIME 0x040000 -#define MNT_LOCK_NOEXEC 0x080000 -#define MNT_LOCK_NOSUID 0x100000 -#define MNT_LOCK_NODEV 0x200000 -#define MNT_LOCK_READONLY 0x400000 -#define MNT_LOCKED 0x800000 -#define MNT_DOOMED 0x1000000 -#define MNT_SYNC_UMOUNT 0x2000000 -#define MNT_MARKED 0x4000000 -#define MNT_UMOUNT 0x8000000 +enum mount_flags { + MNT_NOSUID = 0x01, + MNT_NODEV = 0x02, + MNT_NOEXEC = 0x04, + MNT_NOATIME = 0x08, + MNT_NODIRATIME = 0x10, + MNT_RELATIME = 0x20, + MNT_READONLY = 0x40, /* does the user want this to be r/o? */ + MNT_NOSYMFOLLOW = 0x80, + + MNT_SHRINKABLE = 0x100, + MNT_WRITE_HOLD = 0x200, + + MNT_SHARED = 0x1000, /* if the vfsmount is a shared mount */ + MNT_UNBINDABLE = 0x2000, /* if the vfsmount is a unbindable mount */ + + MNT_INTERNAL = 0x4000, + + MNT_LOCK_ATIME = 0x040000, + MNT_LOCK_NOEXEC = 0x080000, + MNT_LOCK_NOSUID = 0x100000, + MNT_LOCK_NODEV = 0x200000, + MNT_LOCK_READONLY = 0x400000, + MNT_LOCKED = 0x800000, + MNT_DOOMED = 0x1000000, + MNT_SYNC_UMOUNT = 0x2000000, + MNT_MARKED = 0x4000000, + MNT_UMOUNT = 0x8000000, + + /* + * MNT_SHARED_MASK is the set of flags that should be cleared when a + * mount becomes shared. Currently, this is only the flag that says a + * mount cannot be bind mounted, since this is how we create a mount + * that shares events with another mount. If you add a new MNT_* + * flag, consider how it interacts with shared mounts. + */ + MNT_SHARED_MASK = MNT_UNBINDABLE, + MNT_USER_SETTABLE_MASK = MNT_NOSUID | MNT_NODEV | MNT_NOEXEC + | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME + | MNT_READONLY | MNT_NOSYMFOLLOW, + MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME, + + MNT_INTERNAL_FLAGS = MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED, +}; struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 58a2401e4b55..0075f6e5c3da 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -262,6 +262,11 @@ struct mr_table { int mroute_reg_vif_num; }; +static inline bool mr_can_free_table(struct net *net) +{ + return !check_net(net) || !net_initialized(net); +} + #ifdef CONFIG_IP_MROUTE_COMMON void vif_device_init(struct vif_device *v, struct net_device *dev, diff --git a/include/linux/namei.h b/include/linux/namei.h index bbaf55fb3101..5d085428e471 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -70,17 +70,16 @@ int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); -extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); -extern struct dentry *lookup_one_len(const char *, struct dentry *, int); -extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); -extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); -struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); +extern struct dentry *try_lookup_noperm(struct qstr *, struct dentry *); +extern struct dentry *lookup_noperm(struct qstr *, struct dentry *); +extern struct dentry *lookup_noperm_unlocked(struct qstr *, struct dentry *); +extern struct dentry *lookup_noperm_positive_unlocked(struct qstr *, struct dentry *); +struct dentry *lookup_one(struct mnt_idmap *, struct qstr *, struct dentry *); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, - const char *name, struct dentry *base, - int len); + struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, - const char *name, - struct dentry *base, int len); + struct qstr *name, + struct dentry *base); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); diff --git a/include/linux/net.h b/include/linux/net.h index 0ff950eecc6b..f60fff91e1df 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -70,6 +70,7 @@ enum sock_type { SOCK_DCCP = 6, SOCK_PACKET = 10, }; +#endif /* ARCH_HAS_SOCKET_TYPES */ #define SOCK_MAX (SOCK_PACKET + 1) /* Mask which covers at least up to SOCK_MASK-1. The @@ -81,8 +82,7 @@ enum sock_type { #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif - -#endif /* ARCH_HAS_SOCKET_TYPES */ +#define SOCK_COREDUMP O_NOCTTY /** * enum sock_shutdown_cmd - Shutdown types diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2d11d013cabe..7ea022750e4e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4972,6 +4972,7 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); +int netif_set_promiscuity(struct net_device *dev, int inc); int dev_set_promiscuity(struct net_device *dev, int inc); int netif_set_allmulti(struct net_device *dev, int inc, bool notify); int dev_set_allmulti(struct net_device *dev, int inc); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 71319637a84e..ee03f3cef30c 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -213,6 +213,15 @@ struct nfs_server { char *fscache_uniq; /* Uniquifier (or NULL) */ #endif + /* The following #defines numerically match the NFSv4 equivalents */ +#define NFS_FH_NOEXPIRE_WITH_OPEN (0x1) +#define NFS_FH_VOLATILE_ANY (0x2) +#define NFS_FH_VOL_MIGRATION (0x4) +#define NFS_FH_VOL_RENAME (0x8) +#define NFS_FH_RENAME_UNSAFE (NFS_FH_VOLATILE_ANY | NFS_FH_VOL_RENAME) + u32 fh_expire_type; /* V4 bitmask representing file + handle volatility type for + this filesystem */ u32 pnfs_blksize; /* layout_blksize attr */ #if IS_ENABLED(CONFIG_NFS_V4) u32 attr_bitmask[3];/* V4 bitmask representing the set @@ -236,9 +245,6 @@ struct nfs_server { u32 acl_bitmask; /* V4 bitmask representing the ACEs that are supported on this filesystem */ - u32 fh_expire_type; /* V4 bitmask representing file - handle volatility type for - this filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; void *pnfs_ld_data; /* per mount point data */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e6a21b62dcce..3b814ce08331 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -615,6 +615,13 @@ FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) PAGEFLAG_FALSE(HighMem, highmem) #endif +/* Does kmap_local_folio() only allow access to one page of the folio? */ +#ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP +#define folio_test_partial_kmap(f) true +#else +#define folio_test_partial_kmap(f) folio_test_highmem(f) +#endif + #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h index af7d75ede619..288f5235649a 100644 --- a/include/linux/percpu-rwsem.h +++ b/include/linux/percpu-rwsem.h @@ -43,9 +43,10 @@ is_static struct percpu_rw_semaphore name = { \ #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) -extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool); +extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool, bool); -static inline void percpu_down_read(struct percpu_rw_semaphore *sem) +static inline void percpu_down_read_internal(struct percpu_rw_semaphore *sem, + bool freezable) { might_sleep(); @@ -63,7 +64,7 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem) if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else - __percpu_down_read(sem, false); /* Unconditional memory barrier */ + __percpu_down_read(sem, false, freezable); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. @@ -71,6 +72,17 @@ static inline void percpu_down_read(struct percpu_rw_semaphore *sem) preempt_enable(); } +static inline void percpu_down_read(struct percpu_rw_semaphore *sem) +{ + percpu_down_read_internal(sem, false); +} + +static inline void percpu_down_read_freezable(struct percpu_rw_semaphore *sem, + bool freeze) +{ + percpu_down_read_internal(sem, freeze); +} + static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { bool ret = true; @@ -82,7 +94,7 @@ static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else - ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ + ret = __percpu_down_read(sem, true, false); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 52b5ea663b9f..85bf8dd9f087 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -15,11 +15,7 @@ /* enough to cover all DEFINE_PER_CPUs in modules */ #ifdef CONFIG_MODULES -#ifdef CONFIG_MEM_ALLOC_PROFILING -#define PERCPU_MODULE_RESERVE (8 << 13) -#else #define PERCPU_MODULE_RESERVE (8 << 10) -#endif #else #define PERCPU_MODULE_RESERVE 0 #endif diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index c74077977830..8a7f4f802c57 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -188,6 +188,13 @@ static inline struct alloc_tag *__pgalloc_tag_get(struct page *page) return tag; } +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) +{ + if (mem_alloc_profiling_enabled()) + return __pgalloc_tag_get(page); + return NULL; +} + void pgalloc_tag_split(struct folio *folio, int old_order, int new_order); void pgalloc_tag_swap(struct folio *new, struct folio *old); @@ -199,6 +206,7 @@ static inline void clear_page_tag_ref(struct page *page) {} static inline void alloc_tag_sec_init(void) {} static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {} static inline void pgalloc_tag_swap(struct folio *new, struct folio *old) {} +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } #endif /* CONFIG_MEM_ALLOC_PROFILING */ diff --git a/include/linux/pid.h b/include/linux/pid.h index 311ecebd7d56..453ae6d8a68d 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -77,7 +77,7 @@ struct file; struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); -int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file); void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 05e6f8f4a026..77e7db194914 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -2,11 +2,19 @@ #ifndef _LINUX_PID_FS_H #define _LINUX_PID_FS_H +struct coredump_params; + struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); void pidfs_add_pid(struct pid *pid); void pidfs_remove_pid(struct pid *pid); void pidfs_exit(struct task_struct *tsk); +#ifdef CONFIG_COREDUMP +void pidfs_coredump(const struct coredump_params *cprm); +#endif extern const struct dentry_operations pidfs_dentry_operations; +int pidfs_register_pid(struct pid *pid); +void pidfs_get_pid(struct pid *pid); +void pidfs_put_pid(struct pid *pid); #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 0b273a7b9f01..5f03a39a26f7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -104,10 +104,11 @@ static inline bool shmem_mapping(struct address_space *mapping) return false; } #endif /* CONFIG_SHMEM */ -extern void shmem_unlock_mapping(struct address_space *mapping); -extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, +void shmem_unlock_mapping(struct address_space *mapping); +struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); -extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); +int shmem_writeout(struct folio *folio, struct writeback_control *wbc); +void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 493d9de4e472..dc6ebaee3d18 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -365,7 +365,7 @@ struct sdw_intel_res { * on e.g. which machine driver to select (I2S mode, HDaudio or * SoundWire). */ -int sdw_intel_acpi_scan(acpi_handle *parent_handle, +int sdw_intel_acpi_scan(acpi_handle parent_handle, struct sdw_intel_acpi_info *info); void sdw_intel_process_wakeen_event(struct sdw_intel_ctx *ctx); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 0ba5e49bace4..6e64f0193777 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -249,10 +249,7 @@ struct spi_device { static_assert((SPI_MODE_KERNEL_MASK & SPI_MODE_USER_MASK) == 0, "SPI_MODE_USER_MASK & SPI_MODE_KERNEL_MASK must not overlap"); -static inline struct spi_device *to_spi_device(const struct device *dev) -{ - return dev ? container_of(dev, struct spi_device, dev) : NULL; -} +#define to_spi_device(__dev) container_of_const(__dev, struct spi_device, dev) /* Most drivers won't need to care about device refcounting */ static inline struct spi_device *spi_dev_get(struct spi_device *spi) diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e39d4d563b19..785048a3b3e6 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -51,7 +51,7 @@ struct tk_read_base { * @offs_real: Offset clock monotonic -> clock realtime * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai - * @tai_offset: The current UTC to TAI offset in seconds + * @coarse_nsec: The nanoseconds part for coarse time getters * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds * @clock_was_set_seq: The sequence number of clock was set events @@ -76,6 +76,7 @@ struct tk_read_base { * ntp shifted nano seconds. * @ntp_err_mult: Multiplication factor for scaled math conversion * @skip_second_overflow: Flag used to avoid updating NTP twice with same second + * @tai_offset: The current UTC to TAI offset in seconds * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffy times) @@ -100,7 +101,7 @@ struct tk_read_base { * which results in the following cacheline layout: * * 0: seqcount, tkr_mono - * 1: xtime_sec ... tai_offset + * 1: xtime_sec ... coarse_nsec * 2: tkr_raw, raw_sec * 3,4: Internal variables * @@ -121,7 +122,7 @@ struct timekeeper { ktime_t offs_real; ktime_t offs_boot; ktime_t offs_tai; - s32 tai_offset; + u32 coarse_nsec; /* Cacheline 2: */ struct tk_read_base tkr_raw; @@ -144,6 +145,7 @@ struct timekeeper { u32 ntp_error_shift; u32 ntp_err_mult; u32 skip_second_overflow; + s32 tai_offset; }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 6c3125300c00..a3d8305e88a5 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -224,7 +224,7 @@ enum tpm2_const { enum tpm2_timeouts { TPM2_TIMEOUT_A = 750, - TPM2_TIMEOUT_B = 2000, + TPM2_TIMEOUT_B = 4000, TPM2_TIMEOUT_C = 200, TPM2_TIMEOUT_D = 30, TPM2_DURATION_SHORT = 20, @@ -257,6 +257,7 @@ enum tpm2_return_codes { TPM2_RC_TESTING = 0x090A, /* RC_WARN */ TPM2_RC_REFERENCE_H0 = 0x0910, TPM2_RC_RETRY = 0x0922, + TPM2_RC_SESSION_MEMORY = 0x0903, }; enum tpm2_command_codes { @@ -437,6 +438,24 @@ static inline u32 tpm2_rc_value(u32 rc) return (rc & BIT(7)) ? rc & 0xbf : rc; } +/* + * Convert a return value from tpm_transmit_cmd() to POSIX error code. + */ +static inline ssize_t tpm_ret_to_err(ssize_t ret) +{ + if (ret < 0) + return ret; + + switch (tpm2_rc_value(ret)) { + case TPM2_RC_SUCCESS: + return 0; + case TPM2_RC_SESSION_MEMORY: + return -ENOMEM; + default: + return -EFAULT; + } +} + #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 31e9ffd936e3..5ca8d4dd149d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -61,6 +61,7 @@ struct vm_struct { unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; + unsigned long requested_size; }; struct vmap_area { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 522d837a23fa..54bfeeaa0995 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1798,6 +1798,7 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, void hci_uuids_clear(struct hci_dev *hdev); void hci_link_keys_clear(struct hci_dev *hdev); +u8 *hci_conn_key_enc_size(struct hci_conn *conn); struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr); struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h index c316b551df8d..0ee5bc766810 100644 --- a/include/net/netdev_lock.h +++ b/include/net/netdev_lock.h @@ -98,6 +98,9 @@ static inline int netdev_lock_cmp_fn(const struct lockdep_map *a, &qdisc_xmit_lock_key); \ } +#define netdev_lock_dereference(p, dev) \ + rcu_dereference_protected(p, lockdep_is_held(&(dev)->lock)) + int netdev_debug_event(struct notifier_block *nb, unsigned long event, void *ptr); diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 825141d675e5..d01c82983b4d 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -103,6 +103,12 @@ struct netdev_stat_ops { struct netdev_queue_stats_tx *tx); }; +void netdev_stat_queue_sum(struct net_device *netdev, + int rx_start, int rx_end, + struct netdev_queue_stats_rx *rx_sum, + int tx_start, int tx_end, + struct netdev_queue_stats_tx *tx_sum); + /** * struct netdev_queue_mgmt_ops - netdev ops for queue management * diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d48c657191cd..1c05fed05f2b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1031,6 +1031,21 @@ static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) return skb; } +static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct) +{ + struct sk_buff *skb; + + skb = __skb_dequeue(&sch->gso_skb); + if (skb) { + sch->q.qlen--; + return skb; + } + if (direct) + return __qdisc_dequeue_head(&sch->q); + else + return sch->dequeue(sch); +} + static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 39365fd2ea17..06ab2a3d2ebd 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -236,7 +236,6 @@ struct xfrm_state { /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; - struct sock __rcu *encap_sk; /* NAT keepalive */ u32 nat_keepalive_interval; /* seconds */ diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 8becb4504887..8582d22f3818 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1404,6 +1404,8 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s #define snd_pcm_lib_mmap_iomem NULL #endif +void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime); + /** * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer * @dma: DMA number diff --git a/include/sound/ump_msg.h b/include/sound/ump_msg.h index 72f60ddfea75..9556b4755a1e 100644 --- a/include/sound/ump_msg.h +++ b/include/sound/ump_msg.h @@ -604,7 +604,7 @@ struct snd_ump_stream_msg_ep_info { } __packed; /* UMP Stream Message: Device Info Notification (128bit) */ -struct snd_ump_stream_msg_devince_info { +struct snd_ump_stream_msg_device_info { #ifdef __BIG_ENDIAN_BITFIELD /* 0 */ u32 type:4; @@ -754,7 +754,7 @@ struct snd_ump_stream_msg_fb_name { union snd_ump_stream_msg { struct snd_ump_stream_msg_ep_discovery ep_discovery; struct snd_ump_stream_msg_ep_info ep_info; - struct snd_ump_stream_msg_devince_info device_info; + struct snd_ump_stream_msg_device_info device_info; struct snd_ump_stream_msg_stream_cfg stream_cfg; struct snd_ump_stream_msg_fb_discovery fb_discovery; struct snd_ump_stream_msg_fb_info fb_info; diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 549ab3b41961..3efc00cc1bcd 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1928,7 +1928,7 @@ DECLARE_EVENT_CLASS(btrfs__prelim_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct prelim_ref *oldref, const struct prelim_ref *newref, u64 tree_size), - TP_ARGS(fs_info, newref, oldref, tree_size), + TP_ARGS(fs_info, oldref, newref, tree_size), TP_STRUCT__entry_btrfs( __field( u64, root_id ) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 28705ae67784..fd404729b115 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4968,6 +4968,9 @@ union bpf_attr { * the netns switch takes place from ingress to ingress without * going through the CPU's backlog queue. * + * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during + * the netns switch. + * * The *flags* argument is reserved and must be 0. The helper is * currently only supported for tc BPF program types at the * ingress hook and for veth and netkit target device types. The diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 2970ef44655a..c27a4e238e4b 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -12,7 +12,7 @@ #define PIDFD_THREAD O_EXCL #ifdef __KERNEL__ #include <linux/sched.h> -#define PIDFD_CLONE CLONE_PIDFD +#define PIDFD_STALE CLONE_PIDFD #endif /* Flags for pidfd_send_signal(). */ @@ -25,10 +25,24 @@ #define PIDFD_INFO_CREDS (1UL << 1) /* Always returned, even if not requested */ #define PIDFD_INFO_CGROUPID (1UL << 2) /* Always returned if available, even if not requested */ #define PIDFD_INFO_EXIT (1UL << 3) /* Only returned if requested. */ +#define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ /* + * Values for @coredump_mask in pidfd_info. + * Only valid if PIDFD_INFO_COREDUMP is set in @mask. + * + * Note, the @PIDFD_COREDUMP_ROOT flag indicates that the generated + * coredump should be treated as sensitive and access should only be + * granted to privileged users. + */ +#define PIDFD_COREDUMPED (1U << 0) /* Did crash and... */ +#define PIDFD_COREDUMP_SKIP (1U << 1) /* coredumping generation was skipped. */ +#define PIDFD_COREDUMP_USER (1U << 2) /* coredump was done as the user. */ +#define PIDFD_COREDUMP_ROOT (1U << 3) /* coredump was done as root. */ + +/* * The concept of process and threads in userland and the kernel is a confusing * one - within the kernel every thread is a 'task' with its own individual PID, * however from userland's point of view threads are grouped by a single PID, @@ -92,6 +106,8 @@ struct pidfd_info { __u32 fsuid; __u32 fsgid; __s32 exit_code; + __u32 coredump_mask; + __u32 __spare1; }; #define PIDFS_IOCTL_MAGIC 0xFF diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 95762232e018..5929030d4e8b 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 15 +#define TASKSTATS_VERSION 16 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -72,8 +72,6 @@ struct taskstats { */ __u64 cpu_count __attribute__((aligned(8))); __u64 cpu_delay_total; - __u64 cpu_delay_max; - __u64 cpu_delay_min; /* Following four fields atomically updated using task->delays->lock */ @@ -82,14 +80,10 @@ struct taskstats { */ __u64 blkio_count; __u64 blkio_delay_total; - __u64 blkio_delay_max; - __u64 blkio_delay_min; /* Delay waiting for page fault I/O (swap in only) */ __u64 swapin_count; __u64 swapin_delay_total; - __u64 swapin_delay_max; - __u64 swapin_delay_min; /* cpu "wall-clock" running time * On some architectures, value will adjust for cpu time stolen @@ -172,14 +166,11 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; - __u64 freepages_delay_max; - __u64 freepages_delay_min; + /* Delay waiting for thrashing page */ __u64 thrashing_count; __u64 thrashing_delay_total; - __u64 thrashing_delay_max; - __u64 thrashing_delay_min; /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ @@ -187,8 +178,6 @@ struct taskstats { /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; - __u64 compact_delay_max; - __u64 compact_delay_min; /* v12 begin */ __u32 ac_tgid; /* thread group ID */ @@ -210,15 +199,37 @@ struct taskstats { /* v13: Delay waiting for write-protect copy */ __u64 wpcopy_count; __u64 wpcopy_delay_total; - __u64 wpcopy_delay_max; - __u64 wpcopy_delay_min; /* v14: Delay waiting for IRQ/SOFTIRQ */ __u64 irq_count; __u64 irq_delay_total; - __u64 irq_delay_max; - __u64 irq_delay_min; - /* v15: add Delay max */ + + /* v15: add Delay max and Delay min */ + + /* v16: move Delay max and Delay min to the end of taskstat */ + __u64 cpu_delay_max; + __u64 cpu_delay_min; + + __u64 blkio_delay_max; + __u64 blkio_delay_min; + + __u64 swapin_delay_max; + __u64 swapin_delay_min; + + __u64 freepages_delay_max; + __u64 freepages_delay_min; + + __u64 thrashing_delay_max; + __u64 thrashing_delay_min; + + __u64 compact_delay_max; + __u64 compact_delay_min; + + __u64 wpcopy_delay_max; + __u64 wpcopy_delay_min; + + __u64 irq_delay_max; + __u64 irq_delay_min; }; diff --git a/init/Kconfig b/init/Kconfig index 63f5974b9fa6..127c4a5f66b7 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -87,11 +87,6 @@ config CC_CAN_LINK default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag)) if 64BIT default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag)) -config CC_CAN_LINK_STATIC - bool - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag) -static) if 64BIT - default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m32-flag) -static) - # Fixed in GCC 14, 13.3, 12.4 and 11.5 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 config GCC_ASM_GOTO_OUTPUT_BROKEN @@ -140,6 +135,9 @@ config LD_CAN_USE_KEEP_IN_OVERLAY config RUSTC_HAS_COERCE_POINTEE def_bool RUSTC_VERSION >= 108400 +config RUSTC_HAS_UNNECESSARY_TRANSMUTES + def_bool RUSTC_VERSION >= 108800 + config PAHOLE_VERSION int default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE)) @@ -479,16 +477,6 @@ config CROSS_MEMORY_ATTACH to directly read from or write to another process' address space. See the man page for more details. -config USELIB - bool "uselib syscall (for libc5 and earlier)" - default ALPHA || M68K || SPARC - help - This option enables the uselib syscall, a system call used in the - dynamic linker from libc5 and earlier. glibc does not use this - system call. If you intend to run programs built on libc5 or - earlier, you may need to enable this syscall. Current systems - running glibc can safely disable this. - config AUDIT bool "Auditing support" depends on NET diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 9414ca6d101c..e0d6a59a89fa 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -86,13 +86,8 @@ static inline void napi_show_fdinfo(struct io_ring_ctx *ctx, } #endif -/* - * Caller holds a reference to the file already, we don't need to do - * anything else to get an extra reference. - */ -__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) +static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { - struct io_ring_ctx *ctx = file->private_data; struct io_overflow_cqe *ocqe; struct io_rings *r = ctx->rings; struct rusage sq_usage; @@ -106,7 +101,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) unsigned int sq_entries, cq_entries; int sq_pid = -1, sq_cpu = -1; u64 sq_total_time = 0, sq_work_time = 0; - bool has_lock; unsigned int i; if (ctx->flags & IORING_SETUP_CQE32) @@ -176,15 +170,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) seq_printf(m, "\n"); } - /* - * Avoid ABBA deadlock between the seq lock and the io_uring mutex, - * since fdinfo case grabs it in the opposite direction of normal use - * cases. If we fail to get the lock, we just don't iterate any - * structures that could be going away outside the io_uring mutex. - */ - has_lock = mutex_trylock(&ctx->uring_lock); - - if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { + if (ctx->flags & IORING_SETUP_SQPOLL) { struct io_sq_data *sq = ctx->sq_data; /* @@ -206,7 +192,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) seq_printf(m, "SqTotalTime:\t%llu\n", sq_total_time); seq_printf(m, "SqWorkTime:\t%llu\n", sq_work_time); seq_printf(m, "UserFiles:\t%u\n", ctx->file_table.data.nr); - for (i = 0; has_lock && i < ctx->file_table.data.nr; i++) { + for (i = 0; i < ctx->file_table.data.nr; i++) { struct file *f = NULL; if (ctx->file_table.data.nodes[i]) @@ -218,7 +204,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) } } seq_printf(m, "UserBufs:\t%u\n", ctx->buf_table.nr); - for (i = 0; has_lock && i < ctx->buf_table.nr; i++) { + for (i = 0; i < ctx->buf_table.nr; i++) { struct io_mapped_ubuf *buf = NULL; if (ctx->buf_table.nodes[i]) @@ -228,7 +214,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) else seq_printf(m, "%5u: <none>\n", i); } - if (has_lock && !xa_empty(&ctx->personalities)) { + if (!xa_empty(&ctx->personalities)) { unsigned long index; const struct cred *cred; @@ -238,7 +224,7 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) } seq_puts(m, "PollList:\n"); - for (i = 0; has_lock && i < (1U << ctx->cancel_table.hash_bits); i++) { + for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) { struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i]; struct io_kiocb *req; @@ -247,9 +233,6 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) task_work_pending(req->tctx->task)); } - if (has_lock) - mutex_unlock(&ctx->uring_lock); - seq_puts(m, "CqOverflowList:\n"); spin_lock(&ctx->completion_lock); list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) { @@ -262,4 +245,23 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) spin_unlock(&ctx->completion_lock); napi_show_fdinfo(ctx, m); } + +/* + * Caller holds a reference to the file already, we don't need to do + * anything else to get an extra reference. + */ +__cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file) +{ + struct io_ring_ctx *ctx = file->private_data; + + /* + * Avoid ABBA deadlock between the seq lock and the io_uring mutex, + * since fdinfo case grabs it in the opposite direction of normal use + * cases. + */ + if (mutex_trylock(&ctx->uring_lock)) { + __io_uring_show_fdinfo(ctx, m); + mutex_unlock(&ctx->uring_lock); + } +} #endif diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index a2b256e96d5d..edda31a15c6e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -448,24 +448,6 @@ static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) return req->link; } -static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req) -{ - if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT))) - return NULL; - return __io_prep_linked_timeout(req); -} - -static noinline void __io_arm_ltimeout(struct io_kiocb *req) -{ - io_queue_linked_timeout(__io_prep_linked_timeout(req)); -} - -static inline void io_arm_ltimeout(struct io_kiocb *req) -{ - if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT)) - __io_arm_ltimeout(req); -} - static void io_prep_async_work(struct io_kiocb *req) { const struct io_issue_def *def = &io_issue_defs[req->opcode]; @@ -518,7 +500,6 @@ static void io_prep_async_link(struct io_kiocb *req) static void io_queue_iowq(struct io_kiocb *req) { - struct io_kiocb *link = io_prep_linked_timeout(req); struct io_uring_task *tctx = req->tctx; BUG_ON(!tctx); @@ -543,8 +524,6 @@ static void io_queue_iowq(struct io_kiocb *req) trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work)); io_wq_enqueue(tctx->io_wq, &req->work); - if (link) - io_queue_linked_timeout(link); } static void io_req_queue_iowq_tw(struct io_kiocb *req, io_tw_token_t tw) @@ -657,6 +636,7 @@ static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool dying) * to care for a non-real case. */ if (need_resched()) { + ctx->cqe_sentinel = ctx->cqe_cached; io_cq_unlock_post(ctx); mutex_unlock(&ctx->uring_lock); cond_resched(); @@ -869,6 +849,14 @@ bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags) struct io_ring_ctx *ctx = req->ctx; bool posted; + /* + * If multishot has already posted deferred completions, ensure that + * those are flushed first before posting this one. If not, CQEs + * could get reordered. + */ + if (!wq_list_empty(&ctx->submit_state.compl_reqs)) + __io_submit_flush_completions(ctx); + lockdep_assert(!io_wq_current_is_worker()); lockdep_assert_held(&ctx->uring_lock); @@ -1724,15 +1712,22 @@ static bool io_assign_file(struct io_kiocb *req, const struct io_issue_def *def, return !!req->file; } +#define REQ_ISSUE_SLOW_FLAGS (REQ_F_CREDS | REQ_F_ARM_LTIMEOUT) + static inline int __io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags, const struct io_issue_def *def) { const struct cred *creds = NULL; + struct io_kiocb *link = NULL; int ret; - if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) - creds = override_creds(req->creds); + if (unlikely(req->flags & REQ_ISSUE_SLOW_FLAGS)) { + if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) + creds = override_creds(req->creds); + if (req->flags & REQ_F_ARM_LTIMEOUT) + link = __io_prep_linked_timeout(req); + } if (!def->audit_skip) audit_uring_entry(req->opcode); @@ -1742,8 +1737,12 @@ static inline int __io_issue_sqe(struct io_kiocb *req, if (!def->audit_skip) audit_uring_exit(!ret, ret); - if (creds) - revert_creds(creds); + if (unlikely(creds || link)) { + if (creds) + revert_creds(creds); + if (link) + io_queue_linked_timeout(link); + } return ret; } @@ -1769,7 +1768,6 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if (ret == IOU_ISSUE_SKIP_COMPLETE) { ret = 0; - io_arm_ltimeout(req); /* If the op doesn't have a file, we're not polling for it */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && def->iopoll_queue) @@ -1824,8 +1822,6 @@ void io_wq_submit_work(struct io_wq_work *work) else req_ref_get(req); - io_arm_ltimeout(req); - /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (atomic_read(&work->flags) & IO_WQ_WORK_CANCEL) { fail: @@ -1941,15 +1937,11 @@ struct file *io_file_get_normal(struct io_kiocb *req, int fd) static void io_queue_async(struct io_kiocb *req, int ret) __must_hold(&req->ctx->uring_lock) { - struct io_kiocb *linked_timeout; - if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) { io_req_defer_failed(req, ret); return; } - linked_timeout = io_prep_linked_timeout(req); - switch (io_arm_poll_handler(req, 0)) { case IO_APOLL_READY: io_kbuf_recycle(req, 0); @@ -1962,9 +1954,6 @@ static void io_queue_async(struct io_kiocb *req, int ret) case IO_APOLL_OK: break; } - - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); } static inline void io_queue_sqe(struct io_kiocb *req) diff --git a/io_uring/memmap.c b/io_uring/memmap.c index 76fcc79656b0..07f8a5cbd37e 100644 --- a/io_uring/memmap.c +++ b/io_uring/memmap.c @@ -116,7 +116,7 @@ static int io_region_init_ptr(struct io_mapped_region *mr) void *ptr; if (io_check_coalesce_buffer(mr->pages, mr->nr_pages, &ifd)) { - if (ifd.nr_folios == 1) { + if (ifd.nr_folios == 1 && !PageHighMem(mr->pages[0])) { mr->ptr = page_address(mr->pages[0]); return 0; } diff --git a/io_uring/net.c b/io_uring/net.c index 24040bc3916a..27f37fa2ef79 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -827,18 +827,24 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, cflags |= IORING_CQE_F_SOCK_NONEMPTY; if (sr->flags & IORING_RECVSEND_BUNDLE) { - cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, *ret), + size_t this_ret = *ret - sr->done_io; + + cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, this_ret), issue_flags); if (sr->retry) cflags = req->cqe.flags | (cflags & CQE_F_MASK); /* bundle with no more immediate buffers, we're done */ if (req->flags & REQ_F_BL_EMPTY) goto finish; - /* if more is available, retry and append to this one */ - if (!sr->retry && kmsg->msg.msg_inq > 0 && *ret > 0) { + /* + * If more is available AND it was a full transfer, retry and + * append to this one + */ + if (!sr->retry && kmsg->msg.msg_inq > 0 && this_ret > 0 && + !iov_iter_count(&kmsg->msg.msg_iter)) { req->cqe.flags = cflags & ~CQE_F_MASK; sr->len = kmsg->msg.msg_inq; - sr->done_io += *ret; + sr->done_io += this_ret; sr->retry = true; return false; } diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index d037cc68e9d3..03c699493b5a 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -20,7 +20,7 @@ #include "sqpoll.h" #define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 -#define IORING_TW_CAP_ENTRIES_VALUE 8 +#define IORING_TW_CAP_ENTRIES_VALUE 32 enum { IO_SQ_THREAD_SHOULD_STOP = 0, diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index a9ea7d29cdd9..430ed620ddfe 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -254,6 +254,11 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) return -EOPNOTSUPP; issue_flags |= IO_URING_F_IOPOLL; req->iopoll_completed = 0; + if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) { + /* make sure every req only blocks once */ + req->flags &= ~REQ_F_IOPOLL_STATE; + req->iopoll_start = ktime_get_ns(); + } } ret = file->f_op->uring_cmd(ioucmd, issue_flags); diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h index b04686b6b5d2..e6a5142c890e 100644 --- a/io_uring/uring_cmd.h +++ b/io_uring/uring_cmd.h @@ -17,9 +17,3 @@ bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, struct io_uring_task *tctx, bool cancel_all); void io_cmd_cache_free(const void *entry); - -int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd, - const struct iovec __user *uvec, - size_t uvec_segs, - int ddir, struct iov_iter *iter, - unsigned issue_flags); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 35b4f8659904..82ed2d3c9846 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -913,7 +913,7 @@ static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, ro = mnt_want_write(mnt); /* we'll drop it in any case */ inode_lock(d_inode(root)); - path.dentry = lookup_one_len(name->name, root, strlen(name->name)); + path.dentry = lookup_noperm(&QSTR(name->name), root); if (IS_ERR(path.dentry)) { error = PTR_ERR(path.dentry); goto out_putfd; @@ -969,8 +969,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) if (err) goto out_name; inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT); - dentry = lookup_one_len(name->name, mnt->mnt_root, - strlen(name->name)); + dentry = lookup_noperm(&QSTR(name->name), mnt->mnt_root); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out_unlock; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index dc3aa91a6ba0..5c2e96b19392 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -421,7 +421,7 @@ static int bpf_iter_link_pin_kernel(struct dentry *parent, int ret; inode_lock(parent->d_inode); - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_noperm(&QSTR(name), parent); if (IS_ERR(dentry)) { inode_unlock(parent->d_inode); return PTR_ERR(dentry); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 306b60430091..24b70ea3e6ce 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1116,9 +1116,11 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) if (top_cs) { /* - * Percpu kthreads in top_cpuset are ignored + * PF_NO_SETAFFINITY tasks are ignored. + * All per cpu kthreads should have PF_NO_SETAFFINITY + * flag set, see kthread_set_per_cpu(). */ - if (kthread_is_per_cpu(task)) + if (task->flags & PF_NO_SETAFFINITY) continue; cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus); } else { diff --git a/kernel/exit.c b/kernel/exit.c index 1b51dc099f1e..c33ecde016de 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -133,8 +133,13 @@ struct release_task_post { static void __unhash_process(struct release_task_post *post, struct task_struct *p, bool group_dead) { + struct pid *pid = task_pid(p); + nr_threads--; + detach_pid(post->pids, p, PIDTYPE_PID); + wake_up_all(&pid->wait_pidfd); + if (group_dead) { detach_pid(post->pids, p, PIDTYPE_TGID); detach_pid(post->pids, p, PIDTYPE_PGID); @@ -253,7 +258,8 @@ repeat: pidfs_exit(p); cgroup_release(p); - thread_pid = get_pid(p->thread_pid); + /* Retrieve @thread_pid before __unhash_process() may set it to NULL. */ + thread_pid = task_pid(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); @@ -282,8 +288,8 @@ repeat: } write_unlock_irq(&tasklist_lock); + /* @thread_pid can't go away until free_pids() below */ proc_flush_pid(thread_pid); - put_pid(thread_pid); add_device_randomness(&p->se.sum_exec_runtime, sizeof(p->se.sum_exec_runtime)); free_pids(post.pids); diff --git a/kernel/fork.c b/kernel/fork.c index c4b26cd8998b..aad55b0e103c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -498,10 +498,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) vma_numab_state_init(new); dup_anon_vma_name(orig, new); - /* track_pfn_copy() will later take care of copying internal state. */ - if (unlikely(new->vm_flags & VM_PFNMAP)) - untrack_pfn_clear(new); - return new; } @@ -672,6 +668,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; + + /* track_pfn_copy() will later take care of copying internal state. */ + if (unlikely(tmp->vm_flags & VM_PFNMAP)) + untrack_pfn_clear(tmp); + retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; @@ -2036,17 +2037,16 @@ static inline void rcu_copy_process(struct task_struct *p) } /** - * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd + * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd - * @ret: Where to return the file for the pidfd. + * @ret_file: return the new pidfs file * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * - * The helper doesn't perform checks on @pid which makes it useful for pidfds - * created via CLONE_PIDFD where @pid has no task attached when the pidfd and - * pidfd file are prepared. + * The helper verifies that @pid is still in use, without PIDFD_THREAD the + * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in @@ -2063,59 +2063,50 @@ static inline void rcu_copy_process(struct task_struct *p) * error, a negative error code is returned from the function and the * last argument remains unchanged. */ -static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) +int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file) { - struct file *pidfd_file; + struct file *pidfs_file; + + /* + * PIDFD_STALE is only allowed to be passed if the caller knows + * that @pid is already registered in pidfs and thus + * PIDFD_INFO_EXIT information is guaranteed to be available. + */ + if (!(flags & PIDFD_STALE)) { + /* + * While holding the pidfd waitqueue lock removing the + * task linkage for the thread-group leader pid + * (PIDTYPE_TGID) isn't possible. Thus, if there's still + * task linkage for PIDTYPE_PID not having thread-group + * leader linkage for the pid means it wasn't a + * thread-group leader in the first place. + */ + guard(spinlock_irq)(&pid->wait_pidfd.lock); + + /* Task has already been reaped. */ + if (!pid_has_task(pid, PIDTYPE_PID)) + return -ESRCH; + /* + * If this struct pid isn't used as a thread-group + * leader but the caller requested to create a + * thread-group leader pidfd then report ENOENT. + */ + if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID)) + return -ENOENT; + } CLASS(get_unused_fd, pidfd)(O_CLOEXEC); if (pidfd < 0) return pidfd; - pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); - if (IS_ERR(pidfd_file)) - return PTR_ERR(pidfd_file); + pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR); + if (IS_ERR(pidfs_file)) + return PTR_ERR(pidfs_file); - *ret = pidfd_file; + *ret_file = pidfs_file; return take_fd(pidfd); } -/** - * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd - * @pid: the struct pid for which to create a pidfd - * @flags: flags of the new @pidfd - * @ret: Where to return the pidfd. - * - * Allocate a new file that stashes @pid and reserve a new pidfd number in the - * caller's file descriptor table. The pidfd is reserved but not installed yet. - * - * The helper verifies that @pid is still in use, without PIDFD_THREAD the - * task identified by @pid must be a thread-group leader. - * - * If this function returns successfully the caller is responsible to either - * call fd_install() passing the returned pidfd and pidfd file as arguments in - * order to install the pidfd into its file descriptor table or they must use - * put_unused_fd() and fput() on the returned pidfd and pidfd file - * respectively. - * - * This function is useful when a pidfd must already be reserved but there - * might still be points of failure afterwards and the caller wants to ensure - * that no pidfd is leaked into its file descriptor table. - * - * Return: On success, a reserved pidfd is returned from the function and a new - * pidfd file is returned in the last argument to the function. On - * error, a negative error code is returned from the function and the - * last argument remains unchanged. - */ -int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) -{ - bool thread = flags & PIDFD_THREAD; - - if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) - return -EINVAL; - - return __pidfd_prepare(pid, flags, ret); -} - static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); @@ -2462,7 +2453,7 @@ __latent_entropy struct task_struct *copy_process( * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ - retval = __pidfd_prepare(pid, flags | PIDFD_CLONE, &pidfile); + retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index d6964fc29f51..ef234469baac 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -138,7 +138,8 @@ static int percpu_rwsem_wake_function(struct wait_queue_entry *wq_entry, return !reader; /* wake (readers until) 1 writer */ } -static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader) +static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader, + bool freeze) { DEFINE_WAIT_FUNC(wq_entry, percpu_rwsem_wake_function); bool wait; @@ -156,7 +157,8 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader) spin_unlock_irq(&sem->waiters.lock); while (wait) { - set_current_state(TASK_UNINTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE | + (freeze ? TASK_FREEZABLE : 0)); if (!smp_load_acquire(&wq_entry.private)) break; schedule(); @@ -164,7 +166,8 @@ static void percpu_rwsem_wait(struct percpu_rw_semaphore *sem, bool reader) __set_current_state(TASK_RUNNING); } -bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try) +bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try, + bool freeze) { if (__percpu_down_read_trylock(sem)) return true; @@ -174,7 +177,7 @@ bool __sched __percpu_down_read(struct percpu_rw_semaphore *sem, bool try) trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_READ); preempt_enable(); - percpu_rwsem_wait(sem, /* .reader = */ true); + percpu_rwsem_wait(sem, /* .reader = */ true, freeze); preempt_disable(); trace_contention_end(sem, 0); @@ -237,7 +240,7 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem) */ if (!__percpu_down_write_trylock(sem)) { trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE); - percpu_rwsem_wait(sem, /* .reader = */ false); + percpu_rwsem_wait(sem, /* .reader = */ false, false); contended = true; } diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index d7762ef5949a..39278737bb68 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -192,6 +192,11 @@ config GENDWARFKSYMS depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT # Requires ELF object files. depends on !LTO + # To avoid conflicts with the discarded __gendwarfksyms_ptr symbols on + # X86, requires pahole before commit 47dcb534e253 ("btf_encoder: Stop + # indexing symbols for VARs") or after commit 9810758003ce ("btf_encoder: + # Verify 0 address DWARF variables are in ELF section"). + depends on !X86 || !DEBUG_INFO_BTF || PAHOLE_VERSION < 128 || PAHOLE_VERSION > 129 help Calculate symbol versions from DWARF debugging information using gendwarfksyms. Requires DEBUG_INFO to be enabled. diff --git a/kernel/module/main.c b/kernel/module/main.c index a2859dc3eea6..5c6ab20240a6 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2829,6 +2829,7 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); + codetag_free_module_sections(mod); free_mod_mem(mod); } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index c9d97ed20122..5f31fdff8a38 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -128,17 +128,13 @@ out_time: out_net: put_cgroup_ns(new_nsp->cgroup_ns); out_cgroup: - if (new_nsp->pid_ns_for_children) - put_pid_ns(new_nsp->pid_ns_for_children); + put_pid_ns(new_nsp->pid_ns_for_children); out_pid: - if (new_nsp->ipc_ns) - put_ipc_ns(new_nsp->ipc_ns); + put_ipc_ns(new_nsp->ipc_ns); out_ipc: - if (new_nsp->uts_ns) - put_uts_ns(new_nsp->uts_ns); + put_uts_ns(new_nsp->uts_ns); out_uts: - if (new_nsp->mnt_ns) - put_mnt_ns(new_nsp->mnt_ns); + put_mnt_ns(new_nsp->mnt_ns); out_ns: kmem_cache_free(nsproxy_cachep, new_nsp); return ERR_PTR(err); @@ -189,18 +185,12 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) void free_nsproxy(struct nsproxy *ns) { - if (ns->mnt_ns) - put_mnt_ns(ns->mnt_ns); - if (ns->uts_ns) - put_uts_ns(ns->uts_ns); - if (ns->ipc_ns) - put_ipc_ns(ns->ipc_ns); - if (ns->pid_ns_for_children) - put_pid_ns(ns->pid_ns_for_children); - if (ns->time_ns) - put_time_ns(ns->time_ns); - if (ns->time_ns_for_children) - put_time_ns(ns->time_ns_for_children); + put_mnt_ns(ns->mnt_ns); + put_uts_ns(ns->uts_ns); + put_ipc_ns(ns->ipc_ns); + put_pid_ns(ns->pid_ns_for_children); + put_time_ns(ns->time_ns); + put_time_ns(ns->time_ns_for_children); put_cgroup_ns(ns->cgroup_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); diff --git a/kernel/padata.c b/kernel/padata.c index b3d4eacc4f5d..7eee94166357 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -358,7 +358,8 @@ static void padata_reorder(struct parallel_data *pd) * To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish. */ padata_get_pd(pd); - queue_work(pinst->serial_wq, &pd->reorder_work); + if (!queue_work(pinst->serial_wq, &pd->reorder_work)) + padata_put_pd(pd); } } diff --git a/kernel/params.c b/kernel/params.c index e668fc90b83e..b92d64161b75 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -943,7 +943,9 @@ struct kset *module_kset; static void module_kobj_release(struct kobject *kobj) { struct module_kobject *mk = to_module_kobject(kobj); - complete(mk->kobj_completion); + + if (mk->kobj_completion) + complete(mk->kobj_completion); } const struct kobj_type module_ktype = { diff --git a/kernel/pid.c b/kernel/pid.c index 4ac2ce46817f..8317bcbc7cf7 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -100,6 +100,7 @@ void put_pid(struct pid *pid) ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { + WARN_ON_ONCE(pid->stashed); kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } @@ -359,11 +360,6 @@ static void __change_pid(struct pid **pids, struct task_struct *task, hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; - if (type == PIDTYPE_PID) { - WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID)); - wake_up_all(&pid->wait_pidfd); - } - for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 23c0f4e6cb2f..338c9917d4ee 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -778,6 +778,8 @@ int hibernate(void) goto Restore; ksys_sync_helper(); + if (filesystem_freeze_enabled) + filesystems_freeze(); error = freeze_processes(); if (error) @@ -846,6 +848,7 @@ int hibernate(void) /* Don't bother checking whether freezer_test_done is true */ freezer_test_done = false; Exit: + filesystems_thaw(); pm_notifier_call_chain(PM_POST_HIBERNATION); Restore: pm_restore_console(); @@ -882,6 +885,9 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data) if (error) goto restore; + if (filesystem_freeze_enabled) + filesystems_freeze(); + error = freeze_processes(); if (error) goto exit; @@ -941,6 +947,7 @@ thaw: thaw_processes(); exit: + filesystems_thaw(); pm_notifier_call_chain(PM_POST_HIBERNATION); restore: @@ -1029,19 +1036,26 @@ static int software_resume(void) if (error) goto Restore; + if (filesystem_freeze_enabled) + filesystems_freeze(); + pm_pr_dbg("Preparing processes for hibernation restore.\n"); error = freeze_processes(); - if (error) + if (error) { + filesystems_thaw(); goto Close_Finish; + } error = freeze_kernel_threads(); if (error) { thaw_processes(); + filesystems_thaw(); goto Close_Finish; } error = load_image_and_restore(); thaw_processes(); + filesystems_thaw(); Finish: pm_notifier_call_chain(PM_POST_RESTORE); Restore: diff --git a/kernel/power/main.c b/kernel/power/main.c index 6254814d4817..0b0e76324c43 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -962,6 +962,34 @@ power_attr(pm_freeze_timeout); #endif /* CONFIG_FREEZER*/ +#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) +bool filesystem_freeze_enabled = false; + +static ssize_t freeze_filesystems_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%d\n", filesystem_freeze_enabled); +} + +static ssize_t freeze_filesystems_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val > 1) + return -EINVAL; + + filesystem_freeze_enabled = !!val; + return n; +} + +power_attr(freeze_filesystems); +#endif /* CONFIG_SUSPEND || CONFIG_HIBERNATION */ + static struct attribute * g[] = { &state_attr.attr, #ifdef CONFIG_PM_TRACE @@ -992,6 +1020,9 @@ static struct attribute * g[] = { #ifdef CONFIG_FREEZER &pm_freeze_timeout_attr.attr, #endif +#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) + &freeze_filesystems_attr.attr, +#endif NULL, }; diff --git a/kernel/power/power.h b/kernel/power/power.h index c352dea2f67b..2eb81662b8fa 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -18,6 +18,10 @@ struct swsusp_info { unsigned long size; } __aligned(PAGE_SIZE); +#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) +extern bool filesystem_freeze_enabled; +#endif + #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ extern void __init hibernate_reserved_size_init(void); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 8eaec4ab121d..76b141b9aac0 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -30,6 +30,7 @@ #include <trace/events/power.h> #include <linux/compiler.h> #include <linux/moduleparam.h> +#include <linux/fs.h> #include "power.h" @@ -374,6 +375,8 @@ static int suspend_prepare(suspend_state_t state) if (error) goto Restore; + if (filesystem_freeze_enabled) + filesystems_freeze(); trace_suspend_resume(TPS("freeze_processes"), 0, true); error = suspend_freeze_processes(); trace_suspend_resume(TPS("freeze_processes"), 0, false); @@ -550,6 +553,7 @@ int suspend_devices_and_enter(suspend_state_t state) static void suspend_finish(void) { suspend_thaw_processes(); + filesystems_thaw(); pm_notifier_call_chain(PM_POST_SUSPEND); pm_restore_console(); } @@ -588,6 +592,8 @@ static int enter_state(suspend_state_t state) ksys_sync_helper(); trace_suspend_resume(TPS("sync_filesystems"), 0, false); } + if (filesystem_freeze_enabled) + filesystems_freeze(); pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]); pm_suspend_clear_flags(); @@ -609,6 +615,7 @@ static int enter_state(suspend_state_t state) pm_pr_dbg("Finishing wakeup.\n"); suspend_finish(); Unlock: + filesystems_thaw(); mutex_unlock(&system_transition_mutex); return error; } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index fdbf249d1c68..f5133249fd4d 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1118,8 +1118,38 @@ static void scx_kf_disallow(u32 mask) current->scx.kf_mask &= ~mask; } -#define SCX_CALL_OP(mask, op, args...) \ +/* + * Track the rq currently locked. + * + * This allows kfuncs to safely operate on rq from any scx ops callback, + * knowing which rq is already locked. + */ +static DEFINE_PER_CPU(struct rq *, locked_rq); + +static inline void update_locked_rq(struct rq *rq) +{ + /* + * Check whether @rq is actually locked. This can help expose bugs + * or incorrect assumptions about the context in which a kfunc or + * callback is executed. + */ + if (rq) + lockdep_assert_rq_held(rq); + __this_cpu_write(locked_rq, rq); +} + +/* + * Return the rq currently locked from an scx callback, or NULL if no rq is + * locked. + */ +static inline struct rq *scx_locked_rq(void) +{ + return __this_cpu_read(locked_rq); +} + +#define SCX_CALL_OP(mask, op, rq, args...) \ do { \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ scx_ops.op(args); \ @@ -1127,11 +1157,14 @@ do { \ } else { \ scx_ops.op(args); \ } \ + update_locked_rq(NULL); \ } while (0) -#define SCX_CALL_OP_RET(mask, op, args...) \ +#define SCX_CALL_OP_RET(mask, op, rq, args...) \ ({ \ __typeof__(scx_ops.op(args)) __ret; \ + \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ __ret = scx_ops.op(args); \ @@ -1139,6 +1172,7 @@ do { \ } else { \ __ret = scx_ops.op(args); \ } \ + update_locked_rq(NULL); \ __ret; \ }) @@ -1153,31 +1187,31 @@ do { \ * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on * the specific task. */ -#define SCX_CALL_OP_TASK(mask, op, task, args...) \ +#define SCX_CALL_OP_TASK(mask, op, rq, task, args...) \ do { \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task; \ - SCX_CALL_OP(mask, op, task, ##args); \ + SCX_CALL_OP(mask, op, rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ } while (0) -#define SCX_CALL_OP_TASK_RET(mask, op, task, args...) \ +#define SCX_CALL_OP_TASK_RET(mask, op, rq, task, args...) \ ({ \ __typeof__(scx_ops.op(task, ##args)) __ret; \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task; \ - __ret = SCX_CALL_OP_RET(mask, op, task, ##args); \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ __ret; \ }) -#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...) \ +#define SCX_CALL_OP_2TASKS_RET(mask, op, rq, task0, task1, args...) \ ({ \ __typeof__(scx_ops.op(task0, task1, ##args)) __ret; \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task0; \ current->scx.kf_tasks[1] = task1; \ - __ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args); \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task0, task1, ##args); \ current->scx.kf_tasks[0] = NULL; \ current->scx.kf_tasks[1] = NULL; \ __ret; \ @@ -2172,7 +2206,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, WARN_ON_ONCE(*ddsp_taskp); *ddsp_taskp = p; - SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, rq, p, enq_flags); *ddsp_taskp = NULL; if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) @@ -2269,7 +2303,7 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags add_nr_running(rq, 1); if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p)) - SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, runnable, rq, p, enq_flags); if (enq_flags & SCX_ENQ_WAKEUP) touch_core_sched(rq, p); @@ -2283,7 +2317,7 @@ out: __scx_add_event(SCX_EV_SELECT_CPU_FALLBACK, 1); } -static void ops_dequeue(struct task_struct *p, u64 deq_flags) +static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags) { unsigned long opss; @@ -2304,7 +2338,7 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags) BUG(); case SCX_OPSS_QUEUED: if (SCX_HAS_OP(dequeue)) - SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, rq, p, deq_flags); if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, SCX_OPSS_NONE)) @@ -2337,7 +2371,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags return true; } - ops_dequeue(p, deq_flags); + ops_dequeue(rq, p, deq_flags); /* * A currently running task which is going off @rq first gets dequeued @@ -2353,11 +2387,11 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags */ if (SCX_HAS_OP(stopping) && task_current(rq, p)) { update_curr_scx(rq); - SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, false); } if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p)) - SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, rq, p, deq_flags); if (deq_flags & SCX_DEQ_SLEEP) p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP; @@ -2377,7 +2411,7 @@ static void yield_task_scx(struct rq *rq) struct task_struct *p = rq->curr; if (SCX_HAS_OP(yield)) - SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL); + SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, p, NULL); else p->scx.slice = 0; } @@ -2387,7 +2421,7 @@ static bool yield_to_task_scx(struct rq *rq, struct task_struct *to) struct task_struct *from = rq->curr; if (SCX_HAS_OP(yield)) - return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to); + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, from, to); else return false; } @@ -2945,7 +2979,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) * emitted in switch_class(). */ if (SCX_HAS_OP(cpu_acquire)) - SCX_CALL_OP(SCX_KF_REST, cpu_acquire, cpu_of(rq), NULL); + SCX_CALL_OP(SCX_KF_REST, cpu_acquire, rq, cpu_of(rq), NULL); rq->scx.cpu_released = false; } @@ -2990,7 +3024,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) do { dspc->nr_tasks = 0; - SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq), + SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, rq, cpu_of(rq), prev_on_scx ? prev : NULL); flush_dispatch_buf(rq); @@ -3104,7 +3138,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) * Core-sched might decide to execute @p before it is * dispatched. Call ops_dequeue() to notify the BPF scheduler. */ - ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC); + ops_dequeue(rq, p, SCX_DEQ_CORE_SCHED_EXEC); dispatch_dequeue(rq, p); } @@ -3112,7 +3146,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP_TASK(SCX_KF_REST, running, p); + SCX_CALL_OP_TASK(SCX_KF_REST, running, rq, p); clr_task_runnable(p, true); @@ -3193,8 +3227,7 @@ static void switch_class(struct rq *rq, struct task_struct *next) .task = next, }; - SCX_CALL_OP(SCX_KF_CPU_RELEASE, - cpu_release, cpu_of(rq), &args); + SCX_CALL_OP(SCX_KF_CPU_RELEASE, cpu_release, rq, cpu_of(rq), &args); } rq->scx.cpu_released = true; } @@ -3207,7 +3240,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, true); if (p->scx.flags & SCX_TASK_QUEUED) { set_task_runnable(rq, p); @@ -3348,7 +3381,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, * verifier. */ if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a))) - return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, NULL, (struct task_struct *)a, (struct task_struct *)b); else @@ -3385,7 +3418,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag *ddsp_taskp = p; cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU, - select_cpu, p, prev_cpu, wake_flags); + select_cpu, NULL, p, prev_cpu, wake_flags); p->scx.selected_cpu = cpu; *ddsp_taskp = NULL; if (ops_cpu_valid(cpu, "from ops.select_cpu()")) @@ -3430,8 +3463,8 @@ static void set_cpus_allowed_scx(struct task_struct *p, * designation pointless. Cast it away when calling the operation. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, NULL, + p, (struct cpumask *)p->cpus_ptr); } static void handle_hotplug(struct rq *rq, bool online) @@ -3444,9 +3477,9 @@ static void handle_hotplug(struct rq *rq, bool online) scx_idle_update_selcpu_topology(&scx_ops); if (online && SCX_HAS_OP(cpu_online)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, NULL, cpu); else if (!online && SCX_HAS_OP(cpu_offline)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, NULL, cpu); else scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG, "cpu %d going %s, exiting scheduler", cpu, @@ -3550,7 +3583,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) curr->scx.slice = 0; touch_core_sched(rq, curr); } else if (SCX_HAS_OP(tick)) { - SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr); + SCX_CALL_OP_TASK(SCX_KF_REST, tick, rq, curr); } if (!curr->scx.slice) @@ -3627,7 +3660,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool .fork = fork, }; - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, NULL, p, &args); if (unlikely(ret)) { ret = ops_sanitize_err("init_task", ret); return ret; @@ -3668,9 +3701,10 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool static void scx_ops_enable_task(struct task_struct *p) { + struct rq *rq = task_rq(p); u32 weight; - lockdep_assert_rq_held(task_rq(p)); + lockdep_assert_rq_held(rq); /* * Set the weight before calling ops.enable() so that the scheduler @@ -3684,20 +3718,22 @@ static void scx_ops_enable_task(struct task_struct *p) p->scx.weight = sched_weight_to_cgroup(weight); if (SCX_HAS_OP(enable)) - SCX_CALL_OP_TASK(SCX_KF_REST, enable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, enable, rq, p); scx_set_task_state(p, SCX_TASK_ENABLED); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); } static void scx_ops_disable_task(struct task_struct *p) { - lockdep_assert_rq_held(task_rq(p)); + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); if (SCX_HAS_OP(disable)) - SCX_CALL_OP_TASK(SCX_KF_REST, disable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, disable, rq, p); scx_set_task_state(p, SCX_TASK_READY); } @@ -3726,7 +3762,7 @@ static void scx_ops_exit_task(struct task_struct *p) } if (SCX_HAS_OP(exit_task)) - SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args); + SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, task_rq(p), p, &args); scx_set_task_state(p, SCX_TASK_NONE); } @@ -3835,7 +3871,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p, p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight)); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); } static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio) @@ -3851,8 +3887,8 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p) * different scheduler class. Keep the BPF scheduler up-to-date. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, rq, + p, (struct cpumask *)p->cpus_ptr); } static void switched_from_scx(struct rq *rq, struct task_struct *p) @@ -3913,7 +3949,7 @@ int scx_tg_online(struct task_group *tg) struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, tg->css.cgroup, &args); if (ret) ret = ops_sanitize_err("cgroup_init", ret); @@ -3935,7 +3971,7 @@ void scx_tg_offline(struct task_group *tg) percpu_down_read(&scx_cgroup_rwsem); if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, tg->css.cgroup); tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED); percpu_up_read(&scx_cgroup_rwsem); @@ -3968,7 +4004,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset) continue; if (SCX_HAS_OP(cgroup_prep_move)) { - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, NULL, p, from, css->cgroup); if (ret) goto err; @@ -3982,8 +4018,8 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset) err: cgroup_taskset_for_each(p, css, tset) { if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, - p->scx.cgrp_moving_from, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); p->scx.cgrp_moving_from = NULL; } @@ -4001,8 +4037,8 @@ void scx_cgroup_move_task(struct task_struct *p) * cgrp_moving_from set. */ if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) - SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p, - p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); + SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, NULL, + p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); p->scx.cgrp_moving_from = NULL; } @@ -4021,8 +4057,8 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_for_each(p, css, tset) { if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, - p->scx.cgrp_moving_from, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); p->scx.cgrp_moving_from = NULL; } out_unlock: @@ -4035,7 +4071,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) if (scx_cgroup_enabled && tg->scx_weight != weight) { if (SCX_HAS_OP(cgroup_set_weight)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, NULL, tg_cgrp(tg), weight); tg->scx_weight = weight; } @@ -4224,7 +4260,7 @@ static void scx_cgroup_exit(void) continue; rcu_read_unlock(); - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, css->cgroup); rcu_read_lock(); css_put(css); @@ -4261,7 +4297,7 @@ static int scx_cgroup_init(void) continue; rcu_read_unlock(); - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, css->cgroup, &args); if (ret) { css_put(css); @@ -4758,7 +4794,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) } if (scx_ops.exit) - SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei); + SCX_CALL_OP(SCX_KF_UNLOCKED, exit, NULL, ei); cancel_delayed_work_sync(&scx_watchdog_work); @@ -4965,7 +5001,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, if (SCX_HAS_OP(dump_task)) { ops_dump_init(s, " "); - SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p); + SCX_CALL_OP(SCX_KF_REST, dump_task, NULL, dctx, p); ops_dump_exit(); } @@ -5012,7 +5048,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) if (SCX_HAS_OP(dump)) { ops_dump_init(&s, ""); - SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx); + SCX_CALL_OP(SCX_KF_UNLOCKED, dump, NULL, &dctx); ops_dump_exit(); } @@ -5069,7 +5105,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) used = seq_buf_used(&ns); if (SCX_HAS_OP(dump_cpu)) { ops_dump_init(&ns, " "); - SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle); + SCX_CALL_OP(SCX_KF_REST, dump_cpu, NULL, &dctx, cpu, idle); ops_dump_exit(); } @@ -5328,7 +5364,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_idle_enable(ops); if (scx_ops.init) { - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init, NULL); if (ret) { ret = ops_sanitize_err("init", ret); cpus_read_unlock(); @@ -6791,6 +6827,12 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) != __alignof__(struct bpf_iter_scx_dsq)); + /* + * next() and destroy() will be called regardless of the return value. + * Always clear $kit->dsq. + */ + kit->dsq = NULL; + if (flags & ~__SCX_DSQ_ITER_USER_FLAGS) return -EINVAL; @@ -7077,13 +7119,32 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf) } if (ops_cpu_valid(cpu, NULL)) { - struct rq *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq(); + struct rq_flags rf; + + /* + * When called with an rq lock held, restrict the operation + * to the corresponding CPU to prevent ABBA deadlocks. + */ + if (locked_rq && rq != locked_rq) { + scx_ops_error("Invalid target CPU %d", cpu); + return; + } + + /* + * If no rq lock is held, allow to operate on any CPU by + * acquiring the corresponding rq lock. + */ + if (!locked_rq) { + rq_lock_irqsave(rq, &rf); + update_rq_clock(rq); + } rq->scx.cpuperf_target = perf; + cpufreq_update_util(rq, 0); - rcu_read_lock_sched_notrace(); - cpufreq_update_util(cpu_rq(cpu), 0); - rcu_read_unlock_sched_notrace(); + if (!locked_rq) + rq_unlock_irqrestore(rq, &rf); } } @@ -7314,12 +7375,6 @@ BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE) -BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE) -BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE) -BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE) -BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle) -BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU) -BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_cpu_rq) diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index cb343ca889e0..e67a19a071c1 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -674,7 +674,7 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify) * managed by put_prev_task_idle()/set_next_task_idle(). */ if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq)) - SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); + SCX_CALL_OP(SCX_KF_REST, update_idle, rq, cpu_of(rq), idle); /* * Update the idle masks: diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1e67d076f195..a009c91f7b05 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -164,10 +164,34 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk) return ts; } +static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk) +{ + struct timespec64 ts; + + ts.tv_sec = tk->xtime_sec; + ts.tv_nsec = tk->coarse_nsec; + return ts; +} + +/* + * Update the nanoseconds part for the coarse time keepers. They can't rely + * on xtime_nsec because xtime_nsec could be adjusted by a small negative + * amount when the multiplication factor of the clock is adjusted, which + * could cause the coarse clocks to go slightly backwards. See + * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse + * clockids which only is updated when the clock has been set or we have + * accumulated time. + */ +static inline void tk_update_coarse_nsecs(struct timekeeper *tk) +{ + tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; +} + static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; + tk_update_coarse_nsecs(tk); } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) @@ -175,6 +199,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); + tk_update_coarse_nsecs(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) @@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk_normalize_xtime(tk); delta -= incr; } + tk_update_coarse_nsecs(tk); } /** @@ -804,8 +830,8 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned int seq; ktime_t base, *offset = offsets[offs]; + unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); @@ -813,7 +839,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); - nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; + nsecs = tk->coarse_nsec; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; int shift = 0, maxshift; - u64 offset; + u64 offset, orig_offset; guard(raw_spinlock_irqsave)(&tk_core.lock); @@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); - + orig_offset = offset; /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; @@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) */ clock_set |= accumulate_nsecs_to_secs(tk); + /* + * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls + * making small negative adjustments to the base xtime_nsec + * value, only update the coarse clocks if we accumulated time + */ + if (orig_offset != offset) + tk_update_coarse_nsecs(tk); + timekeeping_update_from_shadow(&tk_core, clock_set); return !!clock_set; @@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - *ts = tk_xtime(tk); + *ts = tk_xtime_coarse(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); @@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - *ts = tk_xtime(tk); + *ts = tk_xtime_coarse(tk); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - now = tk_xtime(tk); + now = tk_xtime_coarse(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, - now.tv_nsec + mono.tv_nsec); + now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 01c2ab1e8971..32ef27c71b57 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk) /* CLOCK_REALTIME_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; - vdso_ts->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; + vdso_ts->nsec = tk->coarse_nsec; /* CLOCK_MONOTONIC_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; + nsec = tk->coarse_nsec; nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 95c6e3473a76..ba7ff14f5339 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -454,7 +454,8 @@ static void fprobe_remove_node_in_module(struct module *mod, struct hlist_head * struct fprobe_hlist_node *node; int ret = 0; - hlist_for_each_entry_rcu(node, head, hlist) { + hlist_for_each_entry_rcu(node, head, hlist, + lockdep_is_held(&fprobe_mutex)) { if (!within_module(node->addr, mod)) continue; if (delete_fprobe_node(node)) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c0f877d39a24..3f9bf562beea 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1887,10 +1887,12 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) head_page = cpu_buffer->head_page; - /* If both the head and commit are on the reader_page then we are done. */ - if (head_page == cpu_buffer->reader_page && - head_page == cpu_buffer->commit_page) + /* If the commit_buffer is the reader page, update the commit page */ + if (meta->commit_buffer == (unsigned long)cpu_buffer->reader_page->page) { + cpu_buffer->commit_page = cpu_buffer->reader_page; + /* Nothing more to do, the only page is the reader page */ goto done; + } /* Iterate until finding the commit page */ for (i = 0; i < meta->nr_subbufs + 1; i++, rb_inc_page(&head_page)) { diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index a322e4f249a5..5d64a18cacac 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -16,7 +16,7 @@ #include "trace_output.h" /* for trace_event_sem */ #include "trace_dynevent.h" -static DEFINE_MUTEX(dyn_event_ops_mutex); +DEFINE_MUTEX(dyn_event_ops_mutex); static LIST_HEAD(dyn_event_ops_list); bool trace_event_dyn_try_get_ref(struct trace_event_call *dyn_call) @@ -116,6 +116,20 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type return ret; } +/* + * Locked version of event creation. The event creation must be protected by + * dyn_event_ops_mutex because of protecting trace_probe_log. + */ +int dyn_event_create(const char *raw_command, struct dyn_event_operations *type) +{ + int ret; + + mutex_lock(&dyn_event_ops_mutex); + ret = type->create(raw_command); + mutex_unlock(&dyn_event_ops_mutex); + return ret; +} + static int create_dyn_event(const char *raw_command) { struct dyn_event_operations *ops; diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h index 936477a111d3..beee3f8d7544 100644 --- a/kernel/trace/trace_dynevent.h +++ b/kernel/trace/trace_dynevent.h @@ -100,6 +100,7 @@ void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos); void dyn_event_seq_stop(struct seq_file *m, void *v); int dyn_events_release_all(struct dyn_event_operations *type); int dyn_event_release(const char *raw_command, struct dyn_event_operations *type); +int dyn_event_create(const char *raw_command, struct dyn_event_operations *type); /* * for_each_dyn_event - iterate over the dyn_event list diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index c08355c3ef32..916555f0de81 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -969,10 +969,13 @@ static int __trace_eprobe_create(int argc, const char *argv[]) goto error; } } + trace_probe_log_clear(); return ret; + parse_error: ret = -EINVAL; error: + trace_probe_log_clear(); trace_event_probe_cleanup(ep); return ret; } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index b66b6d235d91..6e87ae2a1a66 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1560,7 +1560,7 @@ stacktrace_trigger(struct event_trigger_data *data, struct trace_event_file *file = data->private_data; if (file) - __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP); + __trace_stack(file->tr, tracing_gen_ctx_dec(), STACK_SKIP); else trace_dump_stack(STACK_SKIP); } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 98ccf3f00c51..4e37a0f6aaa3 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -633,11 +633,7 @@ ftrace_traceoff(unsigned long ip, unsigned long parent_ip, static __always_inline void trace_stack(struct trace_array *tr) { - unsigned int trace_ctx; - - trace_ctx = tracing_gen_ctx(); - - __trace_stack(tr, trace_ctx, FTRACE_STACK_SKIP); + __trace_stack(tr, tracing_gen_ctx_dec(), FTRACE_STACK_SKIP); } static void diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 2703b96d8990..3e5c47b6d7b2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1089,7 +1089,7 @@ static int create_or_delete_trace_kprobe(const char *raw_command) if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_kprobe_ops); - ret = trace_kprobe_create(raw_command); + ret = dyn_event_create(raw_command, &trace_kprobe_ops); return ret == -ECANCELED ? -EINVAL : ret; } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 2eeecb6c95ee..424751cdf31f 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -154,9 +154,12 @@ fail: } static struct trace_probe_log trace_probe_log; +extern struct mutex dyn_event_ops_mutex; void trace_probe_log_init(const char *subsystem, int argc, const char **argv) { + lockdep_assert_held(&dyn_event_ops_mutex); + trace_probe_log.subsystem = subsystem; trace_probe_log.argc = argc; trace_probe_log.argv = argv; @@ -165,11 +168,15 @@ void trace_probe_log_init(const char *subsystem, int argc, const char **argv) void trace_probe_log_clear(void) { + lockdep_assert_held(&dyn_event_ops_mutex); + memset(&trace_probe_log, 0, sizeof(trace_probe_log)); } void trace_probe_log_set_index(int index) { + lockdep_assert_held(&dyn_event_ops_mutex); + trace_probe_log.index = index; } @@ -178,6 +185,8 @@ void __trace_probe_log_err(int offset, int err_type) char *command, *p; int i, len = 0, pos = 0; + lockdep_assert_held(&dyn_event_ops_mutex); + if (!trace_probe_log.argv) return; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 3386439ec9f6..35cf76c75dd7 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -741,7 +741,7 @@ static int create_or_delete_trace_uprobe(const char *raw_command) if (raw_command[0] == '-') return dyn_event_release(raw_command, &trace_uprobe_ops); - ret = trace_uprobe_create(raw_command); + ret = dyn_event_create(raw_command, &trace_uprobe_ops); return ret == -ECANCELED ? -EINVAL : ret; } diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 25ecc1334b67..c7f602fa7b23 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -350,18 +350,28 @@ static bool needs_section_mem(struct module *mod, unsigned long size) return size >= sizeof(struct alloc_tag); } -static struct alloc_tag *find_used_tag(struct alloc_tag *from, struct alloc_tag *to) +static bool clean_unused_counters(struct alloc_tag *start_tag, + struct alloc_tag *end_tag) { - while (from <= to) { + struct alloc_tag *tag; + bool ret = true; + + for (tag = start_tag; tag <= end_tag; tag++) { struct alloc_tag_counters counter; - counter = alloc_tag_read(from); - if (counter.bytes) - return from; - from++; + if (!tag->counters) + continue; + + counter = alloc_tag_read(tag); + if (!counter.bytes) { + free_percpu(tag->counters); + tag->counters = NULL; + } else { + ret = false; + } } - return NULL; + return ret; } /* Called with mod_area_mt locked */ @@ -371,12 +381,16 @@ static void clean_unused_module_areas_locked(void) struct module *val; mas_for_each(&mas, val, module_tags.size) { + struct alloc_tag *start_tag; + struct alloc_tag *end_tag; + if (val != &unloaded_mod) continue; /* Release area if all tags are unused */ - if (!find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), - (struct alloc_tag *)(module_tags.start_addr + mas.last))) + start_tag = (struct alloc_tag *)(module_tags.start_addr + mas.index); + end_tag = (struct alloc_tag *)(module_tags.start_addr + mas.last); + if (clean_unused_counters(start_tag, end_tag)) mas_erase(&mas); } } @@ -561,7 +575,8 @@ unlock: static void release_module_tags(struct module *mod, bool used) { MA_STATE(mas, &mod_area_mt, module_tags.size, module_tags.size); - struct alloc_tag *tag; + struct alloc_tag *start_tag; + struct alloc_tag *end_tag; struct module *val; mas_lock(&mas); @@ -575,15 +590,22 @@ static void release_module_tags(struct module *mod, bool used) if (!used) goto release_area; - /* Find out if the area is used */ - tag = find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), - (struct alloc_tag *)(module_tags.start_addr + mas.last)); - if (tag) { - struct alloc_tag_counters counter = alloc_tag_read(tag); + start_tag = (struct alloc_tag *)(module_tags.start_addr + mas.index); + end_tag = (struct alloc_tag *)(module_tags.start_addr + mas.last); + if (!clean_unused_counters(start_tag, end_tag)) { + struct alloc_tag *tag; + + for (tag = start_tag; tag <= end_tag; tag++) { + struct alloc_tag_counters counter; + + if (!tag->counters) + continue; - pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n", - tag->ct.filename, tag->ct.lineno, tag->ct.modname, - tag->ct.function, counter.bytes); + counter = alloc_tag_read(tag); + pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n", + tag->ct.filename, tag->ct.lineno, tag->ct.modname, + tag->ct.function, counter.bytes); + } } else { used = false; } @@ -596,6 +618,34 @@ out: mas_unlock(&mas); } +static void load_module(struct module *mod, struct codetag *start, struct codetag *stop) +{ + /* Allocate module alloc_tag percpu counters */ + struct alloc_tag *start_tag; + struct alloc_tag *stop_tag; + struct alloc_tag *tag; + + if (!mod) + return; + + start_tag = ct_to_alloc_tag(start); + stop_tag = ct_to_alloc_tag(stop); + for (tag = start_tag; tag < stop_tag; tag++) { + WARN_ON(tag->counters); + tag->counters = alloc_percpu(struct alloc_tag_counters); + if (!tag->counters) { + while (--tag >= start_tag) { + free_percpu(tag->counters); + tag->counters = NULL; + } + shutdown_mem_profiling(true); + pr_err("Failed to allocate memory for allocation tag percpu counters in the module %s. Memory allocation profiling is disabled!\n", + mod->name); + break; + } + } +} + static void replace_module(struct module *mod, struct module *new_mod) { MA_STATE(mas, &mod_area_mt, 0, module_tags.size); @@ -757,6 +807,7 @@ static int __init alloc_tag_init(void) .needs_section_mem = needs_section_mem, .alloc_section_mem = reserve_module_tags, .free_section_mem = release_module_tags, + .module_load = load_module, .module_replaced = replace_module, #endif }; diff --git a/lib/codetag.c b/lib/codetag.c index 42aadd6c1454..de332e98d6f5 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -194,7 +194,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod) if (err >= 0) { cttype->count += range_size(cttype, &range); if (cttype->desc.module_load) - cttype->desc.module_load(cttype, cmod); + cttype->desc.module_load(mod, range.start, range.stop); } up_write(&cttype->mod_lock); @@ -333,7 +333,8 @@ void codetag_unload_module(struct module *mod) } if (found) { if (cttype->desc.module_unload) - cttype->desc.module_unload(cttype, cmod); + cttype->desc.module_unload(cmod->mod, + cmod->range.start, cmod->range.stop); cttype->count -= range_size(cttype, &cmod->range); idr_remove(&cttype->mod_idr, mod_id); @@ -608,7 +608,10 @@ static int __init __cma_declare_contiguous_nid(phys_addr_t *basep, * complain. Find the boundary by adding one to the last valid * address. */ - highmem_start = __pa(high_memory - 1) + 1; + if (IS_ENABLED(CONFIG_HIGHMEM)) + highmem_start = __pa(high_memory - 1) + 1; + else + highmem_start = memblock_end_of_DRAM(); pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n", __func__, &size, &base, &limit, &alignment); diff --git a/mm/execmem.c b/mm/execmem.c index e6c4f5076ca8..6f7a2653b280 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -254,6 +254,34 @@ out_unlock: return ptr; } +static bool execmem_cache_rox = false; + +void execmem_cache_make_ro(void) +{ + struct maple_tree *free_areas = &execmem_cache.free_areas; + struct maple_tree *busy_areas = &execmem_cache.busy_areas; + MA_STATE(mas_free, free_areas, 0, ULONG_MAX); + MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX); + struct mutex *mutex = &execmem_cache.mutex; + void *area; + + execmem_cache_rox = true; + + mutex_lock(mutex); + + mas_for_each(&mas_free, area, ULONG_MAX) { + unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT; + set_memory_ro(mas_free.index, pages); + } + + mas_for_each(&mas_busy, area, ULONG_MAX) { + unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT; + set_memory_ro(mas_busy.index, pages); + } + + mutex_unlock(mutex); +} + static int execmem_cache_populate(struct execmem_range *range, size_t size) { unsigned long vm_flags = VM_ALLOW_HUGE_VMAP; @@ -274,9 +302,15 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size) /* fill memory with instructions that will trap */ execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true); - err = set_memory_rox((unsigned long)p, vm->nr_pages); - if (err) - goto err_free_mem; + if (execmem_cache_rox) { + err = set_memory_rox((unsigned long)p, vm->nr_pages); + if (err) + goto err_free_mem; + } else { + err = set_memory_x((unsigned long)p, vm->nr_pages); + if (err) + goto err_free_mem; + } err = execmem_cache_add(p, alloc_size); if (err) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2a47682d1ab7..47d76d03ce30 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3075,6 +3075,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze, struct folio *folio) { + bool pmd_migration = is_pmd_migration_entry(*pmd); + VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio)); VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE)); VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); @@ -3085,9 +3087,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, * require a folio to check the PMD against. Otherwise, there * is a risk of replacing the wrong folio. */ - if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) { - if (folio && folio != pmd_folio(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) { + /* + * Do not apply pmd_folio() to a migration entry; and folio lock + * guarantees that it must be of the wrong folio anyway. + */ + if (folio && (pmd_migration || folio != pmd_folio(*pmd))) return; __split_huge_pmd_locked(vma, pmd, address, freeze); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e3e6ac991b9c..6a3cf7935c14 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. - * This function should be only used by move_vma() and operate on + * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ @@ -2949,12 +2949,20 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) while (start_pfn < end_pfn) { folio = pfn_folio(start_pfn); + + /* + * The folio might have been dissolved from under our feet, so make sure + * to carefully check the state under the lock. + */ + spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { h = folio_hstate(folio); } else { + spin_unlock_irq(&hugetlb_lock); start_pfn++; continue; } + spin_unlock_irq(&hugetlb_lock); if (!folio_ref_count(folio)) { ret = alloc_and_dissolve_hugetlb_folio(h, folio, @@ -3010,7 +3018,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; - long retval, gbl_chg; + long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; @@ -3163,8 +3171,16 @@ out_uncharge_cgroup_reservation: hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: - if (map_chg) - hugepage_subpool_put_pages(spool, 1); + /* + * put page to subpool iff the quota of subpool's rsv_hpages is used + * during hugepage_subpool_get_pages. + */ + if (map_chg && !gbl_chg) { + gbl_reserve = hugepage_subpool_put_pages(spool, 1); + hugetlb_acct_memory(h, -gbl_reserve); + } + + out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); @@ -4034,10 +4050,13 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, list_for_each_entry_safe(folio, next, src_list, lru) { int i; + bool cma; if (folio_test_hugetlb_vmemmap_optimized(folio)) continue; + cma = folio_test_hugetlb_cma(folio); + list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); @@ -4053,6 +4072,9 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, new_folio->mapping = NULL; init_new_hugetlb_folio(dst, new_folio); + /* Copy the CMA flag so that it is freed correctly */ + if (cma) + folio_set_hugetlb_cma(new_folio); list_add(&new_folio->lru, &dst_list); } } @@ -7233,7 +7255,7 @@ bool hugetlb_reserve_pages(struct inode *inode, struct vm_area_struct *vma, vm_flags_t vm_flags) { - long chg = -1, add = -1; + long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; @@ -7368,8 +7390,16 @@ bool hugetlb_reserve_pages(struct inode *inode, return true; out_put_pages: - /* put back original number of pages, chg */ - (void)hugepage_subpool_put_pages(spool, chg); + spool_resv = chg - gbl_reserve; + if (spool_resv) { + /* put sub pool's reservation back, chg - gbl_reserve */ + gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); + /* + * subpool's reserved pages can not be put back due to race, + * return to hstate. + */ + hugetlb_acct_memory(h, -gbl_resv); + } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); @@ -7909,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } + +/* + * For hugetlb, mremap() is an odd edge case - while the VMA copying is + * performed, we permit both the old and new VMAs to reference the same + * reservation. + * + * We fix this up after the operation succeeds, or if a newly allocated VMA + * is closed as a result of a failure to allocate memory. + */ +void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + clear_vma_resv_huge_pages(vma); +} diff --git a/mm/internal.h b/mm/internal.h index e9695baa5922..5c7a2b43ad76 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -248,11 +248,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { - unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); - const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; - int nr; + int nr, cur_nr; if (any_writable) *any_writable = false; @@ -265,11 +263,15 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); + /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */ + max_nr = min_t(unsigned long, max_nr, + folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte)); + nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; - while (ptep < end_ptep) { + while (nr < max_nr) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); @@ -282,14 +284,6 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (!pte_same(pte, expected_pte)) break; - /* - * Stop immediately once we reached the end of the folio. In - * corner cases the next PFN might fall into a different - * folio. - */ - if (pte_pfn(pte) >= folio_end_pfn) - break; - if (any_writable) *any_writable |= writable; if (any_young) @@ -297,12 +291,13 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (any_dirty) *any_dirty |= dirty; - nr = pte_batch_hint(ptep, pte); - expected_pte = pte_advance_pfn(expected_pte, nr); - ptep += nr; + cur_nr = pte_batch_hint(ptep, pte); + expected_pte = pte_advance_pfn(expected_pte, cur_nr); + ptep += cur_nr; + nr += cur_nr; } - return min(ptep - start_ptep, max_nr); + return min(nr, max_nr); } /** @@ -1595,7 +1590,6 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); -void unaccepted_cleanup_work(struct work_struct *work); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 88d1c9dcb507..d2c70cd2afb1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_vm_area_shadow(void *start, { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + + return 0; +} + +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + return 0; } +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret; diff --git a/mm/memblock.c b/mm/memblock.c index d3509414b8c3..0e9ebb8aa7fe 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -457,7 +457,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); - new_array = addr ? __va(addr) : NULL; + if (addr) { + /* The memory may not have been accepted, yet. */ + accept_memory(addr, new_alloc_size); + + new_array = __va(addr); + } else { + new_array = NULL; + } } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c96c1f2b9cf5..2d4d65f25fec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1168,7 +1168,6 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; - int i = 0; BUG_ON(mem_cgroup_is_root(memcg)); @@ -1178,10 +1177,9 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); while (!ret && (task = css_task_iter_next(&it))) { - /* Avoid potential softlockup warning */ - if ((++i & 1023) == 0) - cond_resched(); ret = fn(task, arg); + /* Avoid potential softlockup warning */ + cond_resched(); } css_task_iter_end(&it); if (ret) { diff --git a/mm/memory.c b/mm/memory.c index ba3ea0a82f7f..49199410805c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3751,7 +3751,7 @@ static bool __wp_can_reuse_large_anon_folio(struct folio *folio, /* Stabilize the mapcount vs. refcount and recheck. */ folio_lock_large_mapcount(folio); - VM_WARN_ON_ONCE(folio_large_mapcount(folio) < folio_ref_count(folio)); + VM_WARN_ON_ONCE_FOLIO(folio_large_mapcount(folio) > folio_ref_count(folio), folio); if (folio_test_large_maybe_mapped_shared(folio)) goto unlock; diff --git a/mm/migrate.c b/mm/migrate.c index 676d9cfc7059..c80591514e66 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -947,66 +947,20 @@ int filemap_migrate_folio(struct address_space *mapping, EXPORT_SYMBOL_GPL(filemap_migrate_folio); /* - * Writeback a folio to clean the dirty state - */ -static int writeout(struct address_space *mapping, struct folio *folio) -{ - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .nr_to_write = 1, - .range_start = 0, - .range_end = LLONG_MAX, - .for_reclaim = 1 - }; - int rc; - - if (!mapping->a_ops->writepage) - /* No write method for the address space */ - return -EINVAL; - - if (!folio_clear_dirty_for_io(folio)) - /* Someone else already triggered a write */ - return -EAGAIN; - - /* - * A dirty folio may imply that the underlying filesystem has - * the folio on some queue. So the folio must be clean for - * migration. Writeout may mean we lose the lock and the - * folio state is no longer what we checked for earlier. - * At this point we know that the migration attempt cannot - * be successful. - */ - remove_migration_ptes(folio, folio, 0); - - rc = mapping->a_ops->writepage(&folio->page, &wbc); - - if (rc != AOP_WRITEPAGE_ACTIVATE) - /* unlocked. Relock */ - folio_lock(folio); - - return (rc < 0) ? -EIO : -EAGAIN; -} - -/* * Default handling if a filesystem does not provide a migration function. */ static int fallback_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { - if (folio_test_dirty(src)) { - /* Only writeback folios in full synchronous migration */ - switch (mode) { - case MIGRATE_SYNC: - break; - default: - return -EBUSY; - } - return writeout(mapping, src); - } + WARN_ONCE(mapping->a_ops->writepages, + "%ps does not implement migrate_folio\n", + mapping->a_ops); + if (folio_test_dirty(src)) + return -EBUSY; /* - * Buffers may be managed in a filesystem specific way. - * We must have no buffers or drop them. + * Filesystem may have private data at folio->private that we + * can't migrate automatically. */ if (!filemap_release_folio(src, GFP_KERNEL)) return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY; diff --git a/mm/mm_init.c b/mm/mm_init.c index 9659689b8ace..eedce9321e13 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1441,7 +1441,6 @@ static void __meminit zone_init_free_lists(struct zone *zone) #ifdef CONFIG_UNACCEPTED_MEMORY INIT_LIST_HEAD(&zone->unaccepted_pages); - INIT_WORK(&zone->unaccepted_cleanup, unaccepted_cleanup_work); #endif } @@ -1786,7 +1785,7 @@ static bool arch_has_descending_max_zone_pfns(void) return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40); } -static void set_high_memory(void) +static void __init set_high_memory(void) { phys_addr_t highmem = memblock_end_of_DRAM(); diff --git a/mm/mremap.c b/mm/mremap.c index 7db9da609c84..0d4948b720e2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm, mremap_userfaultfd_prep(new_vma, vrm->uf); } - if (is_vm_hugetlb_page(vma)) - clear_vma_resv_huge_pages(vma); + fixup_hugetlb_reservations(vma); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index c81624bc3969..76200cd85fe7 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2621,27 +2621,6 @@ int write_cache_pages(struct address_space *mapping, } EXPORT_SYMBOL(write_cache_pages); -static int writeback_use_writepage(struct address_space *mapping, - struct writeback_control *wbc) -{ - struct folio *folio = NULL; - struct blk_plug plug; - int err; - - blk_start_plug(&plug); - while ((folio = writeback_iter(mapping, wbc, folio, &err))) { - err = mapping->a_ops->writepage(&folio->page, wbc); - if (err == AOP_WRITEPAGE_ACTIVATE) { - folio_unlock(folio); - err = 0; - } - mapping_set_error(mapping, err); - } - blk_finish_plug(&plug); - - return err; -} - int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; @@ -2652,14 +2631,11 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { - if (mapping->a_ops->writepages) { + if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); - } else if (mapping->a_ops->writepage) { - ret = writeback_use_writepage(mapping, wbc); - } else { + else /* deal with chardevs and other special files */ ret = 0; - } if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5669baf2a6fe..47fa713ccb4d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -290,7 +290,8 @@ EXPORT_SYMBOL(nr_online_nodes); #endif static bool page_contains_unaccepted(struct page *page, unsigned int order); -static bool cond_accept_memory(struct zone *zone, unsigned int order); +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags); static bool __free_unaccepted(struct page *page); int page_group_by_mobility_disabled __read_mostly; @@ -1151,14 +1152,9 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) __pgalloc_tag_sub(page, nr); } -static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) +/* When tag is not NULL, assuming mem_alloc_profiling_enabled */ +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) { - struct alloc_tag *tag; - - if (!mem_alloc_profiling_enabled()) - return; - - tag = __pgalloc_tag_get(page); if (tag) this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); } @@ -1168,7 +1164,7 @@ static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} -static inline void pgalloc_tag_sub_pages(struct page *page, unsigned int nr) {} +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} #endif /* CONFIG_MEM_ALLOC_PROFILING */ @@ -3616,7 +3612,7 @@ retry: } } - cond_accept_memory(zone, order); + cond_accept_memory(zone, order, alloc_flags); /* * Detect whether the number of free pages is below high @@ -3643,7 +3639,7 @@ check_alloc_wmark: gfp_mask)) { int ret; - if (cond_accept_memory(zone, order)) + if (cond_accept_memory(zone, order, alloc_flags)) goto try_this_zone; /* @@ -3696,7 +3692,7 @@ try_this_zone: return page; } else { - if (cond_accept_memory(zone, order)) + if (cond_accept_memory(zone, order, alloc_flags)) goto try_this_zone; /* Try again if zone has deferred pages */ @@ -4566,6 +4562,14 @@ restart: } retry: + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * infinite retries. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); @@ -4849,7 +4853,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, goto failed; } - cond_accept_memory(zone, 0); + cond_accept_memory(zone, 0, alloc_flags); retry_this_zone: mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages; if (zone_watermark_fast(zone, 0, mark, @@ -4858,7 +4862,7 @@ retry_this_zone: break; } - if (cond_accept_memory(zone, 0)) + if (cond_accept_memory(zone, 0, alloc_flags)) goto retry_this_zone; /* Try again if zone has deferred pages */ @@ -5065,11 +5069,13 @@ static void ___free_pages(struct page *page, unsigned int order, { /* get PageHead before we drop reference */ int head = PageHead(page); + /* get alloc tag in case the page is released by others */ + struct alloc_tag *tag = pgalloc_tag_get(page); if (put_page_testzero(page)) __free_frozen_pages(page, order, fpi_flags); else if (!head) { - pgalloc_tag_sub_pages(page, (1 << order) - 1); + pgalloc_tag_sub_pages(tag, (1 << order) - 1); while (order-- > 0) __free_frozen_pages(page + (1 << order), order, fpi_flags); @@ -7174,16 +7180,8 @@ bool has_managed_dma(void) #ifdef CONFIG_UNACCEPTED_MEMORY -/* Counts number of zones with unaccepted pages. */ -static DEFINE_STATIC_KEY_FALSE(zones_with_unaccepted_pages); - static bool lazy_accept = true; -void unaccepted_cleanup_work(struct work_struct *work) -{ - static_branch_dec(&zones_with_unaccepted_pages); -} - static int __init accept_memory_parse(char *p) { if (!strcmp(p, "lazy")) { @@ -7208,11 +7206,7 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order) static void __accept_page(struct zone *zone, unsigned long *flags, struct page *page) { - bool last; - list_del(&page->lru); - last = list_empty(&zone->unaccepted_pages); - account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); __ClearPageUnaccepted(page); @@ -7221,28 +7215,6 @@ static void __accept_page(struct zone *zone, unsigned long *flags, accept_memory(page_to_phys(page), PAGE_SIZE << MAX_PAGE_ORDER); __free_pages_ok(page, MAX_PAGE_ORDER, FPI_TO_TAIL); - - if (last) { - /* - * There are two corner cases: - * - * - If allocation occurs during the CPU bring up, - * static_branch_dec() cannot be used directly as - * it causes a deadlock on cpu_hotplug_lock. - * - * Instead, use schedule_work() to prevent deadlock. - * - * - If allocation occurs before workqueues are initialized, - * static_branch_dec() should be called directly. - * - * Workqueues are initialized before CPU bring up, so this - * will not conflict with the first scenario. - */ - if (system_wq) - schedule_work(&zone->unaccepted_cleanup); - else - unaccepted_cleanup_work(&zone->unaccepted_cleanup); - } } void accept_page(struct page *page) @@ -7279,20 +7251,17 @@ static bool try_to_accept_memory_one(struct zone *zone) return true; } -static inline bool has_unaccepted_memory(void) -{ - return static_branch_unlikely(&zones_with_unaccepted_pages); -} - -static bool cond_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags) { long to_accept, wmark; bool ret = false; - if (!has_unaccepted_memory()) + if (list_empty(&zone->unaccepted_pages)) return false; - if (list_empty(&zone->unaccepted_pages)) + /* Bailout, since try_to_accept_memory_one() needs to take a lock */ + if (alloc_flags & ALLOC_TRYLOCK) return false; wmark = promo_wmark_pages(zone); @@ -7325,22 +7294,17 @@ static bool __free_unaccepted(struct page *page) { struct zone *zone = page_zone(page); unsigned long flags; - bool first = false; if (!lazy_accept) return false; spin_lock_irqsave(&zone->lock, flags); - first = list_empty(&zone->unaccepted_pages); list_add_tail(&page->lru, &zone->unaccepted_pages); account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); __SetPageUnaccepted(page); spin_unlock_irqrestore(&zone->lock, flags); - if (first) - static_branch_inc(&zones_with_unaccepted_pages); - return true; } @@ -7351,7 +7315,8 @@ static bool page_contains_unaccepted(struct page *page, unsigned int order) return false; } -static bool cond_accept_memory(struct zone *zone, unsigned int order) +static bool cond_accept_memory(struct zone *zone, unsigned int order, + int alloc_flags) { return false; } @@ -7422,11 +7387,6 @@ struct page *try_alloc_pages_noprof(int nid, unsigned int order) if (!pcp_allowed_order(order)) return NULL; -#ifdef CONFIG_UNACCEPTED_MEMORY - /* Bailout, since try_to_accept_memory_one() needs to take a lock */ - if (has_unaccepted_memory()) - return NULL; -#endif /* Bailout, since _deferred_grow_zone() needs to take a lock */ if (deferred_pages_enabled()) return NULL; diff --git a/mm/page_io.c b/mm/page_io.c index 4bce19df557b..f7716b6569fa 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -237,9 +237,8 @@ static void swap_zeromap_folio_clear(struct folio *folio) * We may have stale swap cache pages in memory: notice * them here and get rid of the unnecessary final write. */ -int swap_writepage(struct page *page, struct writeback_control *wbc) +int swap_writeout(struct folio *folio, struct writeback_control *wbc) { - struct folio *folio = page_folio(page); int ret; if (folio_free_swap(folio)) { diff --git a/mm/readahead.c b/mm/readahead.c index 6a4e96b69702..20d36d6b055e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -690,9 +690,15 @@ EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { + struct file *file; + const struct inode *inode; + CLASS(fd, f)(fd); + if (fd_empty(f)) + return -EBADF; - if (fd_empty(f) || !(fd_file(f)->f_mode & FMODE_READ)) + file = fd_file(f); + if (!(file->f_mode & FMODE_READ)) return -EBADF; /* @@ -700,9 +706,15 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ - if (!fd_file(f)->f_mapping || !fd_file(f)->f_mapping->a_ops || - (!S_ISREG(file_inode(fd_file(f))->i_mode) && - !S_ISBLK(file_inode(fd_file(f))->i_mode))) + if (!file->f_mapping) + return -EINVAL; + if (!file->f_mapping->a_ops) + return -EINVAL; + + inode = file_inode(file); + if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) + return -EINVAL; + if (IS_ANON_FILE(inode)) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); diff --git a/mm/shmem.c b/mm/shmem.c index 99327c30507c..858cee02ca49 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -98,7 +98,7 @@ static struct vfsmount *shm_mnt __ro_after_init; #define SHORT_SYMLINK_LEN 128 /* - * shmem_fallocate communicates with shmem_fault or shmem_writepage via + * shmem_fallocate communicates with shmem_fault or shmem_writeout via * inode->i_private (with i_rwsem making sure that it has only one user at * a time): we would prefer not to enlarge the shmem inode just for that. */ @@ -107,7 +107,7 @@ struct shmem_falloc { pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ - pgoff_t nr_unswapped; /* how often writepage refused to swap out */ + pgoff_t nr_unswapped; /* how often writeout refused to swap out */ }; struct shmem_options { @@ -446,7 +446,7 @@ static void shmem_recalc_inode(struct inode *inode, long alloced, long swapped) /* * Special case: whereas normally shmem_recalc_inode() is called * after i_mapping->nrpages has already been adjusted (up or down), - * shmem_writepage() has to raise swapped before nrpages is lowered - + * shmem_writeout() has to raise swapped before nrpages is lowered - * to stop a racing shmem_recalc_inode() from thinking that a page has * been freed. Compensate here, to avoid the need for a followup call. */ @@ -1536,12 +1536,15 @@ int shmem_unuse(unsigned int type) return error; } -/* - * Move the page from the page cache to the swap cache. +/** + * shmem_writeout - Write the folio to swap + * @folio: The folio to write + * @wbc: How writeback is to be done + * + * Move the folio from the page cache to the swap cache. */ -static int shmem_writepage(struct page *page, struct writeback_control *wbc) +int shmem_writeout(struct folio *folio, struct writeback_control *wbc) { - struct folio *folio = page_folio(page); struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); @@ -1550,13 +1553,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) int nr_pages; bool split = false; - /* - * Our capabilities prevent regular writeback or sync from ever calling - * shmem_writepage; but a stacking filesystem might use ->writepage of - * its underlying filesystem, in which case tmpfs should write out to - * swap only in response to memory pressure, and not for the writeback - * threads or sync. - */ if (WARN_ON_ONCE(!wbc->for_reclaim)) goto redirty; @@ -1586,9 +1582,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) try_split: /* Ensure the subpages are still dirty */ folio_test_set_dirty(folio); - if (split_huge_page_to_list_to_order(page, wbc->list, 0)) + if (split_folio_to_list(folio, wbc->list)) goto redirty; - folio = page_folio(page); folio_clear_dirty(folio); } @@ -1646,7 +1641,7 @@ try_split: mutex_unlock(&shmem_swaplist_mutex); BUG_ON(folio_mapped(folio)); - return swap_writepage(&folio->page, wbc); + return swap_writeout(folio, wbc); } list_del_init(&info->swaplist); @@ -1660,6 +1655,7 @@ redirty: folio_unlock(folio); return 0; } +EXPORT_SYMBOL_GPL(shmem_writeout); #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) @@ -3768,7 +3764,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, index--; /* - * Inform shmem_writepage() how far we have reached. + * Inform shmem_writeout() how far we have reached. * No need for lock or barrier: we have the page lock. */ if (!folio_test_uptodate(folio)) @@ -5191,7 +5187,6 @@ static int shmem_error_remove_folio(struct address_space *mapping, } static const struct address_space_operations shmem_aops = { - .writepage = shmem_writepage, .dirty_folio = noop_dirty_folio, #ifdef CONFIG_TMPFS .write_begin = shmem_write_begin, diff --git a/mm/swap.h b/mm/swap.h index 6f4a3f927edb..aa62463976d5 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -20,7 +20,7 @@ static inline void swap_read_unplug(struct swap_iocb *plug) __swap_read_unplug(plug); } void swap_write_unplug(struct swap_iocb *sio); -int swap_writepage(struct page *page, struct writeback_control *wbc); +int swap_writeout(struct folio *folio, struct writeback_control *wbc); void __swap_writepage(struct folio *folio, struct writeback_control *wbc); /* linux/mm/swap_state.c */ @@ -141,7 +141,7 @@ static inline struct folio *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, return NULL; } -static inline int swap_writepage(struct page *p, struct writeback_control *wbc) +static inline int swap_writeout(struct folio *f, struct writeback_control *wbc) { return 0; } diff --git a/mm/swap_state.c b/mm/swap_state.c index 68fd981b514f..ec2b1c9c9926 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -30,7 +30,6 @@ * vmscan's shrink_folio_list. */ static const struct address_space_operations swap_aops = { - .writepage = swap_writepage, .dirty_folio = noop_dirty_folio, #ifdef CONFIG_MIGRATION .migrate_folio = migrate_folio, diff --git a/mm/swapfile.c b/mm/swapfile.c index 2eff8b51a945..86643b181098 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp) VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); - /* - * Should not even be attempting large allocations when huge - * page swap is disabled. Warn and fail the allocation. - */ - if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) { - VM_WARN_ON_ONCE(1); - return -EINVAL; + if (order) { + /* + * Reject large allocation when THP_SWAP is disabled, + * the caller should split the folio and try again. + */ + if (!IS_ENABLED(CONFIG_THP_SWAP)) + return -EAGAIN; + + /* + * Allocation size should never exceed cluster size + * (HPAGE_PMD_SIZE). + */ + if (size > SWAPFILE_CLUSTER) { + VM_WARN_ON_ONCE(1); + return -EINVAL; + } } local_lock(&percpu_swap_cluster.lock); @@ -2359,7 +2368,7 @@ retry: * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; - * and even shmem_writepage() could have been preempted after + * and even shmem_writeout() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ @@ -3323,6 +3332,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } /* + * The swap subsystem needs a major overhaul to support this. + * It doesn't work yet so just disable it for now. + */ + if (mapping_min_folio_order(mapping) > 0) { + error = -EINVAL; + goto bad_swap_unlock_inode; + } + + /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { diff --git a/mm/truncate.c b/mm/truncate.c index 5d98054094d1..f2aaf99f2990 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -191,6 +191,7 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio) bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { loff_t pos = folio_pos(folio); + size_t size = folio_size(folio); unsigned int offset, length; struct page *split_at, *split_at2; @@ -198,14 +199,13 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) offset = start - pos; else offset = 0; - length = folio_size(folio); - if (pos + length <= (u64)end) - length = length - offset; + if (pos + size <= (u64)end) + length = size - offset; else length = end + 1 - pos - offset; folio_wait_writeback(folio); - if (length == folio_size(folio)) { + if (length == size) { truncate_inode_folio(folio->mapping, folio); return true; } @@ -224,16 +224,20 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) return true; split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE); - split_at2 = folio_page(folio, - PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE); - if (!try_folio_split(folio, split_at, NULL)) { /* * try to split at offset + length to make sure folios within * the range can be dropped, especially to avoid memory waste * for shmem truncate */ - struct folio *folio2 = page_folio(split_at2); + struct folio *folio2; + + if (offset + length == size) + goto no_split; + + split_at2 = folio_page(folio, + PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE); + folio2 = page_folio(split_at2); if (!folio_try_get(folio2)) goto no_split; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 7d5d709cc838..e0db855c89b4 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1064,8 +1064,13 @@ static int move_present_pte(struct mm_struct *mm, src_folio->index = linear_page_index(dst_vma, dst_addr); orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot); - /* Follow mremap() behavior and treat the entry dirty after the move */ - orig_dst_pte = pte_mkwrite(pte_mkdirty(orig_dst_pte), dst_vma); + /* Set soft dirty bit so userspace can notice the pte was moved */ +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_dst_pte = pte_mksoft_dirty(orig_dst_pte); +#endif + if (pte_dirty(orig_src_pte)) + orig_dst_pte = pte_mkdirty(orig_dst_pte); + orig_dst_pte = pte_mkwrite(orig_dst_pte, dst_vma); set_pte_at(mm, dst_addr, dst_pte, orig_dst_pte); out: @@ -1100,6 +1105,9 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma, } orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte); +#ifdef CONFIG_MEM_SOFT_DIRTY + orig_src_pte = pte_swp_mksoft_dirty(orig_src_pte); +#endif set_pte_at(mm, dst_addr, dst_pte, orig_src_pte); double_pt_unlock(dst_ptl, src_ptl); @@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: + fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3ed720a787ec..00cf1b575c89 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm, { vm->flags = flags; vm->addr = (void *)va->va_start; - vm->size = va_size(va); + vm->size = vm->requested_size = va_size(va); vm->caller = caller; va->vm = vm; } @@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size, area->flags = flags; area->caller = caller; + area->requested_size = requested_size; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { @@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof); */ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) { + struct vm_struct *vm = NULL; + size_t alloced_size = 0; size_t old_size = 0; void *n; @@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) } if (p) { - struct vm_struct *vm; - vm = find_vm_area(p); if (unlikely(!vm)) { WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL; } - old_size = get_vm_area_size(vm); + alloced_size = get_vm_area_size(vm); + old_size = vm->requested_size; + if (WARN(alloced_size < old_size, + "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) + return NULL; } /* @@ -4088,11 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { - /* Zero out spare memory. */ - if (want_init_on_alloc(flags)) + /* Zero out "freed" memory, potentially for future realloc. */ + if (want_init_on_free() || want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); + vm->requested_size = size; kasan_poison_vmalloc(p + size, old_size - size); - kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL); + return (void *)p; + } + + /* + * We already have the bytes available in the allocation; use them. + */ + if (size <= alloced_size) { + kasan_unpoison_vmalloc(p + old_size, size - old_size, + KASAN_VMALLOC_PROT_NORMAL); + /* + * No need to zero memory here, as unused memory will have + * already been zeroed at initial allocation time or during + * realloc shrink time. + */ + vm->requested_size = size; return (void *)p; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 3783e45bfc92..b6f4db6c240f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -648,21 +648,20 @@ typedef enum { /* * pageout is called by shrink_folio_list() for each dirty folio. - * Calls ->writepage(). */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug, struct list_head *folio_list) { + int (*writeout)(struct folio *, struct writeback_control *); + /* - * If the folio is dirty, only perform writeback if that write - * will be non-blocking. To prevent this allocation from being - * stalled by pagecache activity. But note that there may be - * stalls if we need to run get_block(). We could test - * PagePrivate for that. - * - * If this process is currently in __generic_file_write_iter() against - * this folio's queue, we can perform writeback even if that - * will block. + * We no longer attempt to writeback filesystem folios here, other + * than tmpfs/shmem. That's taken care of in page-writeback. + * If we find a dirty filesystem folio at the end of the LRU list, + * typically that means the filesystem is saturating the storage + * with contiguous writes and telling it to write a folio here + * would only make the situation worse by injecting an element + * of random access. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because @@ -685,7 +684,11 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping, } return PAGE_KEEP; } - if (mapping->a_ops->writepage == NULL) + if (shmem_mapping(mapping)) + writeout = shmem_writeout; + else if (folio_test_anon(folio)) + writeout = swap_writeout; + else return PAGE_ACTIVATE; if (folio_clear_dirty_for_io(folio)) { @@ -708,7 +711,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping, wbc.list = folio_list; folio_set_reclaim(folio); - res = mapping->a_ops->writepage(&folio->page, &wbc); + res = writeout(folio, &wbc); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { @@ -717,7 +720,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping, } if (!folio_test_writeback(folio)) { - /* synchronous write or broken a_ops? */ + /* synchronous write? */ folio_clear_reclaim(folio); } trace_mm_vmscan_write_folio(folio); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 961b270f023c..d14a7e317ac8 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1243,19 +1243,19 @@ void zs_obj_write(struct zs_pool *pool, unsigned long handle, class = zspage_class(pool, zspage); off = offset_in_page(class->size * obj_idx); - if (off + class->size <= PAGE_SIZE) { + if (!ZsHugePage(zspage)) + off += ZS_HANDLE_SIZE; + + if (off + mem_len <= PAGE_SIZE) { /* this object is contained entirely within a page */ void *dst = kmap_local_zpdesc(zpdesc); - if (!ZsHugePage(zspage)) - off += ZS_HANDLE_SIZE; memcpy(dst + off, handle_mem, mem_len); kunmap_local(dst); } else { /* this object spans two pages */ size_t sizes[2]; - off += ZS_HANDLE_SIZE; sizes[0] = PAGE_SIZE - off; sizes[1] = mem_len - sizes[0]; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 7cd4bdcee439..558d39dffc23 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -506,28 +506,32 @@ batadv_hardif_is_iface_up(const struct batadv_hard_iface *hard_iface) return false; } -static void batadv_check_known_mac_addr(const struct net_device *net_dev) +static void batadv_check_known_mac_addr(const struct batadv_hard_iface *hard_iface) { - const struct batadv_hard_iface *hard_iface; + const struct net_device *mesh_iface = hard_iface->mesh_iface; + const struct batadv_hard_iface *tmp_hard_iface; - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->if_status != BATADV_IF_ACTIVE && - hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED) + if (!mesh_iface) + return; + + list_for_each_entry(tmp_hard_iface, &batadv_hardif_list, list) { + if (tmp_hard_iface == hard_iface) + continue; + + if (tmp_hard_iface->mesh_iface != mesh_iface) continue; - if (hard_iface->net_dev == net_dev) + if (tmp_hard_iface->if_status == BATADV_IF_NOT_IN_USE) continue; - if (!batadv_compare_eth(hard_iface->net_dev->dev_addr, - net_dev->dev_addr)) + if (!batadv_compare_eth(tmp_hard_iface->net_dev->dev_addr, + hard_iface->net_dev->dev_addr)) continue; pr_warn("The newly added mac address (%pM) already exists on: %s\n", - net_dev->dev_addr, hard_iface->net_dev->name); + hard_iface->net_dev->dev_addr, tmp_hard_iface->net_dev->name); pr_warn("It is strongly recommended to keep mac addresses unique to avoid problems!\n"); } - rcu_read_unlock(); } /** @@ -763,6 +767,8 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, hard_iface->net_dev->name, hardif_mtu, required_mtu); + batadv_check_known_mac_addr(hard_iface); + if (batadv_hardif_is_iface_up(hard_iface)) batadv_hardif_activate_interface(hard_iface); else @@ -901,7 +907,6 @@ batadv_hardif_add_interface(struct net_device *net_dev) batadv_v_hardif_init(hard_iface); - batadv_check_known_mac_addr(hard_iface->net_dev); kref_get(&hard_iface->refcount); list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list); batadv_hardif_generation++; @@ -988,7 +993,7 @@ static int batadv_hard_if_event(struct notifier_block *this, if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) goto hardif_put; - batadv_check_known_mac_addr(hard_iface->net_dev); + batadv_check_known_mac_addr(hard_iface); bat_priv = netdev_priv(hard_iface->mesh_iface); bat_priv->algo_ops->iface.update_mac(hard_iface); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 6533e281ada3..946d2ae551f8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -3023,3 +3023,27 @@ void hci_conn_tx_dequeue(struct hci_conn *conn) kfree_skb(skb); } + +u8 *hci_conn_key_enc_size(struct hci_conn *conn) +{ + if (conn->type == ACL_LINK) { + struct link_key *key; + + key = hci_find_link_key(conn->hdev, &conn->dst); + if (!key) + return NULL; + + return &key->pin_len; + } else if (conn->type == LE_LINK) { + struct smp_ltk *ltk; + + ltk = hci_find_ltk(conn->hdev, &conn->dst, conn->dst_type, + conn->role); + if (!ltk) + return NULL; + + return <k->enc_size; + } + + return NULL; +} diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 6d6061111ac5..c38ada69c3d7 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -739,10 +739,17 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data, handle); conn->enc_key_size = 0; } else { + u8 *key_enc_size = hci_conn_key_enc_size(conn); + conn->enc_key_size = rp->key_size; status = 0; - if (conn->enc_key_size < hdev->min_enc_key_size) { + /* Attempt to check if the key size is too small or if it has + * been downgraded from the last time it was stored as part of + * the link_key. + */ + if (conn->enc_key_size < hdev->min_enc_key_size || + (key_enc_size && conn->enc_key_size < *key_enc_size)) { /* As slave role, the conn->state has been set to * BT_CONNECTED and l2cap conn req might not be received * yet, at this moment the l2cap layer almost does @@ -755,6 +762,10 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data, clear_bit(HCI_CONN_ENCRYPT, &conn->flags); clear_bit(HCI_CONN_AES_CCM, &conn->flags); } + + /* Update the key encryption size with the connection one */ + if (key_enc_size && *key_enc_size != conn->enc_key_size) + *key_enc_size = conn->enc_key_size; } hci_encrypt_cfm(conn, status); @@ -3065,6 +3076,34 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, void *edata, hci_dev_unlock(hdev); } +static int hci_read_enc_key_size(struct hci_dev *hdev, struct hci_conn *conn) +{ + struct hci_cp_read_enc_key_size cp; + u8 *key_enc_size = hci_conn_key_enc_size(conn); + + if (!read_key_size_capable(hdev)) { + conn->enc_key_size = HCI_LINK_KEY_SIZE; + return -EOPNOTSUPP; + } + + bt_dev_dbg(hdev, "hcon %p", conn); + + memset(&cp, 0, sizeof(cp)); + cp.handle = cpu_to_le16(conn->handle); + + /* If the key enc_size is already known, use it as conn->enc_key_size, + * otherwise use hdev->min_enc_key_size so the likes of + * l2cap_check_enc_key_size don't fail while waiting for + * HCI_OP_READ_ENC_KEY_SIZE response. + */ + if (key_enc_size && *key_enc_size) + conn->enc_key_size = *key_enc_size; + else + conn->enc_key_size = hdev->min_enc_key_size; + + return hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, sizeof(cp), &cp); +} + static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -3157,23 +3196,11 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && ev->link_type == ACL_LINK) { struct link_key *key; - struct hci_cp_read_enc_key_size cp; key = hci_find_link_key(hdev, &ev->bdaddr); if (key) { set_bit(HCI_CONN_ENCRYPT, &conn->flags); - - if (!read_key_size_capable(hdev)) { - conn->enc_key_size = HCI_LINK_KEY_SIZE; - } else { - cp.handle = cpu_to_le16(conn->handle); - if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, - sizeof(cp), &cp)) { - bt_dev_err(hdev, "sending read key size failed"); - conn->enc_key_size = HCI_LINK_KEY_SIZE; - } - } - + hci_read_enc_key_size(hdev, conn); hci_encrypt_cfm(conn, ev->status); } } @@ -3612,24 +3639,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, /* Try reading the encryption key size for encrypted ACL links */ if (!ev->status && ev->encrypt && conn->type == ACL_LINK) { - struct hci_cp_read_enc_key_size cp; - - /* Only send HCI_Read_Encryption_Key_Size if the - * controller really supports it. If it doesn't, assume - * the default size (16). - */ - if (!read_key_size_capable(hdev)) { - conn->enc_key_size = HCI_LINK_KEY_SIZE; - goto notify; - } - - cp.handle = cpu_to_le16(conn->handle); - if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, - sizeof(cp), &cp)) { - bt_dev_err(hdev, "sending read key size failed"); - conn->enc_key_size = HCI_LINK_KEY_SIZE; + if (hci_read_enc_key_size(hdev, conn)) goto notify; - } goto unlock; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 73472756618a..042d3ac3b4a3 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1411,7 +1411,8 @@ static void l2cap_request_info(struct l2cap_conn *conn) sizeof(req), &req); } -static bool l2cap_check_enc_key_size(struct hci_conn *hcon) +static bool l2cap_check_enc_key_size(struct hci_conn *hcon, + struct l2cap_chan *chan) { /* The minimum encryption key size needs to be enforced by the * host stack before establishing any L2CAP connections. The @@ -1425,7 +1426,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon) int min_key_size = hcon->hdev->min_enc_key_size; /* On FIPS security level, key size must be 16 bytes */ - if (hcon->sec_level == BT_SECURITY_FIPS) + if (chan->sec_level == BT_SECURITY_FIPS) min_key_size = 16; return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) || @@ -1453,7 +1454,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) !__l2cap_no_conn_pending(chan)) return; - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -1528,7 +1529,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn) continue; } - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else l2cap_chan_close(chan, ECONNREFUSED); @@ -3992,7 +3993,7 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, /* Check if the ACL is secure enough (if not SDP) */ if (psm != cpu_to_le16(L2CAP_PSM_SDP) && (!hci_conn_check_link_mode(conn->hcon) || - !l2cap_check_enc_key_size(conn->hcon))) { + !l2cap_check_enc_key_size(conn->hcon, pchan))) { conn->disc_reason = HCI_ERROR_AUTH_FAILURE; result = L2CAP_CR_SEC_BLOCK; goto response; @@ -7352,7 +7353,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } if (chan->state == BT_CONNECT) { - if (!status && l2cap_check_enc_key_size(hcon)) + if (!status && l2cap_check_enc_key_size(hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -7362,7 +7363,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) struct l2cap_conn_rsp rsp; __u16 res, stat; - if (!status && l2cap_check_enc_key_size(hcon)) { + if (!status && l2cap_check_enc_key_size(hcon, chan)) { if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { res = L2CAP_CR_PEND; stat = L2CAP_CS_AUTHOR_PEND; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index c1e1e529e26c..46b22708dfbd 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -7506,11 +7506,16 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err) struct mgmt_cp_add_device *cp = cmd->param; if (!err) { + struct hci_conn_params *params; + + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, + le_addr_type(cp->addr.type)); + device_added(cmd->sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action); device_flags_changed(NULL, hdev, &cp->addr.bdaddr, cp->addr.type, hdev->conn_flags, - PTR_UINT(cmd->user_data)); + params ? params->flags : 0); } mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE, @@ -7613,8 +7618,6 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - cmd->user_data = UINT_PTR(current_flags); - err = hci_cmd_sync_queue(hdev, add_device_sync, cmd, add_device_complete); if (err < 0) { diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 98aea5485aae..a8c67035e23c 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -65,17 +65,14 @@ static struct dst_ops fake_dst_ops = { * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ -static const u32 br_dst_default_metrics[RTAX_MAX] = { - [RTAX_MTU - 1] = 1500, -}; - void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; rcuref_init(&rt->dst.__rcuref, 1); rt->dst.dev = br->dev; - dst_init_metrics(&rt->dst, br_dst_default_metrics, true); + dst_init_metrics(&rt->dst, br->metrics, false); + dst_metric_set(&rt->dst, RTAX_MTU, br->dev->mtu); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d5b3c5936a79..4715a8d6dc32 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -505,6 +505,7 @@ struct net_bridge { struct rtable fake_rtable; struct rt6_info fake_rt6_info; }; + u32 metrics[RTAX_MAX]; #endif u16 group_fwd_mask; u16 group_fwd_mask_required; diff --git a/net/can/bcm.c b/net/can/bcm.c index 0bca1b9b3f70..6bc1cc4c94c5 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -58,6 +58,7 @@ #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <net/sock.h> #include <net/net_namespace.h> @@ -122,6 +123,7 @@ struct bcm_op { struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; + spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ }; struct bcm_sock { @@ -217,7 +219,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex)); seq_printf(m, " <<<\n"); - list_for_each_entry(op, &bo->rx_ops, list) { + rcu_read_lock(); + + list_for_each_entry_rcu(op, &bo->rx_ops, list) { unsigned long reduction; @@ -273,6 +277,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, "# sent %ld\n", op->frames_abs); } seq_putc(m, '\n'); + + rcu_read_unlock(); + return 0; } #endif /* CONFIG_PROC_FS */ @@ -285,13 +292,18 @@ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct net_device *dev; - struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; + struct canfd_frame *cf; int err; /* no target device? => exit */ if (!op->ifindex) return; + /* read currframe under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + cf = op->frames + op->cfsiz * op->currframe; + spin_unlock_bh(&op->bcm_tx_lock); + dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ @@ -312,6 +324,10 @@ static void bcm_can_tx(struct bcm_op *op) skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); + + /* update currframe and count under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + if (!err) op->frames_abs++; @@ -320,6 +336,11 @@ static void bcm_can_tx(struct bcm_op *op) /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; + + if (op->count > 0) + op->count--; + + spin_unlock_bh(&op->bcm_tx_lock); out: dev_put(dev); } @@ -430,7 +451,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { - op->count--; + bcm_can_tx(op); if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ @@ -445,7 +466,6 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) bcm_send_to_user(op, &msg_head, NULL, 0); } - bcm_can_tx(op); } else if (op->kt_ival2) { bcm_can_tx(op); @@ -843,7 +863,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, REGMASK(op->can_id), bcm_rx_handler, op); - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -863,7 +883,7 @@ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh, list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -956,6 +976,27 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } op->flags = msg_head->flags; + /* only lock for unlikely count/nframes/currframe changes */ + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX || + op->flags & SETTIMER) { + + spin_lock_bh(&op->bcm_tx_lock); + + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX) { + /* potentially update changed nframes */ + op->nframes = msg_head->nframes; + /* restart multiple frame transmission */ + op->currframe = 0; + } + + if (op->flags & SETTIMER) + op->count = msg_head->count; + + spin_unlock_bh(&op->bcm_tx_lock); + } + } else { /* insert new BCM operation for the given can_id */ @@ -963,9 +1004,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; + op->nframes = msg_head->nframes; + + if (op->flags & SETTIMER) + op->count = msg_head->count; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { @@ -1023,22 +1069,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ - if (op->nframes != msg_head->nframes) { - op->nframes = msg_head->nframes; - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - - /* check flags */ - - if (op->flags & TX_RESET_MULTI_IDX) { - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - if (op->flags & SETTIMER) { /* set timer values */ - op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); @@ -1055,11 +1087,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->flags |= TX_ANNOUNCE; } - if (op->flags & TX_ANNOUNCE) { + if (op->flags & TX_ANNOUNCE) bcm_can_tx(op); - if (op->count) - op->count--; - } if (op->flags & STARTTIMER) bcm_tx_start_timer(op); @@ -1272,7 +1301,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return err; } diff --git a/net/can/gw.c b/net/can/gw.c index ef93293c1fae..55eccb1c7620 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -130,7 +130,7 @@ struct cgw_job { u32 handled_frames; u32 dropped_frames; u32 deleted_frames; - struct cf_mod mod; + struct cf_mod __rcu *cf_mod; union { /* CAN frame data source */ struct net_device *dev; @@ -459,6 +459,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) struct cgw_job *gwj = (struct cgw_job *)data; struct canfd_frame *cf; struct sk_buff *nskb; + struct cf_mod *mod; int modidx = 0; /* process strictly Classic CAN or CAN FD frames */ @@ -506,7 +507,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. */ - if (gwj->mod.modfunc[0]) + mod = rcu_dereference(gwj->cf_mod); + if (mod->modfunc[0]) nskb = skb_copy(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); @@ -529,8 +531,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ - while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) - (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); + while (modidx < MAX_MODFUNCTIONS && mod->modfunc[modidx]) + (*mod->modfunc[modidx++])(cf, mod); /* Has the CAN frame been modified? */ if (modidx) { @@ -546,11 +548,11 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) } /* check for checksum updates */ - if (gwj->mod.csumfunc.crc8) - (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + if (mod->csumfunc.crc8) + (*mod->csumfunc.crc8)(cf, &mod->csum.crc8); - if (gwj->mod.csumfunc.xor) - (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + if (mod->csumfunc.xor) + (*mod->csumfunc.xor)(cf, &mod->csum.xor); } /* clear the skb timestamp if not configured the other way */ @@ -581,9 +583,20 @@ static void cgw_job_free_rcu(struct rcu_head *rcu_head) { struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu); + /* cgw_job::cf_mod is always accessed from the same cgw_job object within + * the same RCU read section. Once cgw_job is scheduled for removal, + * cf_mod can also be removed without mandating an additional grace period. + */ + kfree(rcu_access_pointer(gwj->cf_mod)); kmem_cache_free(cgw_cache, gwj); } +/* Return cgw_job::cf_mod with RTNL protected section */ +static struct cf_mod *cgw_job_cf_mod(struct cgw_job *gwj) +{ + return rcu_dereference_protected(gwj->cf_mod, rtnl_is_locked()); +} + static int cgw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { @@ -616,6 +629,7 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, { struct rtcanmsg *rtcan; struct nlmsghdr *nlh; + struct cf_mod *mod; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) @@ -650,82 +664,83 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } + mod = cgw_job_cf_mod(gwj); if (gwj->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; - if (gwj->mod.modtype.and) { - memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.and; + if (mod->modtype.and) { + memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); + mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.or) { - memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.or; + if (mod->modtype.or) { + memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); + mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.xor) { - memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.xor; + if (mod->modtype.xor) { + memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); + mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.set) { - memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.set; + if (mod->modtype.set) { + memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); + mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } else { struct cgw_frame_mod mb; - if (gwj->mod.modtype.and) { - memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.and; + if (mod->modtype.and) { + memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); + mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.or) { - memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.or; + if (mod->modtype.or) { + memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); + mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.xor) { - memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.xor; + if (mod->modtype.xor) { + memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); + mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.set) { - memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.set; + if (mod->modtype.set) { + memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); + mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } - if (gwj->mod.uid) { - if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0) + if (mod->uid) { + if (nla_put_u32(skb, CGW_MOD_UID, mod->uid) < 0) goto cancel; } - if (gwj->mod.csumfunc.crc8) { + if (mod->csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, - &gwj->mod.csum.crc8) < 0) + &mod->csum.crc8) < 0) goto cancel; } - if (gwj->mod.csumfunc.xor) { + if (mod->csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, - &gwj->mod.csum.xor) < 0) + &mod->csum.xor) < 0) goto cancel; } @@ -1059,7 +1074,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct rtcanmsg *r; struct cgw_job *gwj; - struct cf_mod mod; + struct cf_mod *mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; @@ -1078,37 +1093,48 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; - err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); + mod = kmalloc(sizeof(*mod), GFP_KERNEL); + if (!mod) + return -ENOMEM; + + err = cgw_parse_attr(nlh, mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) - return err; + goto out_free_cf; - if (mod.uid) { + if (mod->uid) { ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { - if (gwj->mod.uid != mod.uid) + struct cf_mod *old_cf; + + old_cf = cgw_job_cf_mod(gwj); + if (old_cf->uid != mod->uid) continue; /* interfaces & filters must be identical */ - if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) - return -EINVAL; + if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) { + err = -EINVAL; + goto out_free_cf; + } - /* update modifications with disabled softirq & quit */ - local_bh_disable(); - memcpy(&gwj->mod, &mod, sizeof(mod)); - local_bh_enable(); + rcu_assign_pointer(gwj->cf_mod, mod); + kfree_rcu_mightsleep(old_cf); return 0; } } /* ifindex == 0 is not allowed for job creation */ - if (!ccgw.src_idx || !ccgw.dst_idx) - return -ENODEV; + if (!ccgw.src_idx || !ccgw.dst_idx) { + err = -ENODEV; + goto out_free_cf; + } gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); - if (!gwj) - return -ENOMEM; + if (!gwj) { + err = -ENOMEM; + goto out_free_cf; + } gwj->handled_frames = 0; gwj->dropped_frames = 0; @@ -1118,7 +1144,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, gwj->limit_hops = limhops; /* insert already parsed information */ - memcpy(&gwj->mod, &mod, sizeof(mod)); + RCU_INIT_POINTER(gwj->cf_mod, mod); memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw)); err = -ENODEV; @@ -1152,9 +1178,11 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (!err) hlist_add_head_rcu(&gwj->list, &net->can.cgw_list); out: - if (err) + if (err) { kmem_cache_free(cgw_cache, gwj); - +out_free_cf: + kfree(mod); + } return err; } @@ -1214,19 +1242,22 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { + struct cf_mod *cf_mod; + if (gwj->flags != r->flags) continue; if (gwj->limit_hops != limhops) continue; + cf_mod = cgw_job_cf_mod(gwj); /* we have a match when uid is enabled and identical */ - if (gwj->mod.uid || mod.uid) { - if (gwj->mod.uid != mod.uid) + if (cf_mod->uid || mod.uid) { + if (cf_mod->uid != mod.uid) continue; } else { /* no uid => check for identical modifications */ - if (memcmp(&gwj->mod, &mod, sizeof(mod))) + if (memcmp(cf_mod, &mod, sizeof(mod))) continue; } diff --git a/net/core/dev.c b/net/core/dev.c index 1be7cb73a602..0d891634c692 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9193,18 +9193,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) return 0; } -/** - * dev_set_promiscuity - update promiscuity count on a device - * @dev: device - * @inc: modifier - * - * Add or remove promiscuity from a device. While the count in the device - * remains above zero the interface remains promiscuous. Once it hits zero - * the device reverts back to normal filtering operation. A negative inc - * value is used to drop promiscuity on the device. - * Return 0 if successful or a negative errno code on error. - */ -int dev_set_promiscuity(struct net_device *dev, int inc) +int netif_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; int err; @@ -9216,7 +9205,6 @@ int dev_set_promiscuity(struct net_device *dev, int inc) dev_set_rx_mode(dev); return err; } -EXPORT_SYMBOL(dev_set_promiscuity); int netif_set_allmulti(struct net_device *dev, int inc, bool notify) { @@ -10453,6 +10441,7 @@ static void netdev_sync_lower_features(struct net_device *upper, if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); + netdev_lock_ops(lower); lower->wanted_features &= ~feature; __netdev_update_features(lower); @@ -10461,6 +10450,7 @@ static void netdev_sync_lower_features(struct net_device *upper, &feature, lower->name); else netdev_features_change(lower); + netdev_unlock_ops(lower); } } } @@ -11966,9 +11956,9 @@ void unregister_netdevice_many_notify(struct list_head *head, struct sk_buff *skb = NULL; /* Shutdown queueing discipline. */ + netdev_lock_ops(dev); dev_shutdown(dev); dev_tcx_uninstall(dev); - netdev_lock_ops(dev); dev_xdp_uninstall(dev); dev_memory_provider_uninstall(dev); netdev_unlock_ops(dev); @@ -12161,7 +12151,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, synchronize_net(); /* Shutdown queueing discipline. */ + netdev_lock_ops(dev); dev_shutdown(dev); + netdev_unlock_ops(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. diff --git a/net/core/dev_api.c b/net/core/dev_api.c index 90898cd540ce..f9a160ab596f 100644 --- a/net/core/dev_api.c +++ b/net/core/dev_api.c @@ -268,6 +268,29 @@ void dev_disable_lro(struct net_device *dev) EXPORT_SYMBOL(dev_disable_lro); /** + * dev_set_promiscuity() - update promiscuity count on a device + * @dev: device + * @inc: modifier + * + * Add or remove promiscuity from a device. While the count in the device + * remains above zero the interface remains promiscuous. Once it hits zero + * the device reverts back to normal filtering operation. A negative inc + * value is used to drop promiscuity on the device. + * Return 0 if successful or a negative errno code on error. + */ +int dev_set_promiscuity(struct net_device *dev, int inc) +{ + int ret; + + netdev_lock_ops(dev); + ret = netif_set_promiscuity(dev, inc); + netdev_unlock_ops(dev); + + return ret; +} +EXPORT_SYMBOL(dev_set_promiscuity); + +/** * dev_set_allmulti() - update allmulti count on a device * @dev: device * @inc: modifier diff --git a/net/core/devmem.c b/net/core/devmem.c index 6e27a47d0493..2db428ab6b8b 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -200,6 +200,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, refcount_set(&binding->ref, 1); + mutex_init(&binding->lock); + binding->dmabuf = dmabuf; binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent); @@ -379,6 +381,11 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv, xa_for_each(&binding->bound_rxqs, xa_idx, bound_rxq) { if (bound_rxq == rxq) { xa_erase(&binding->bound_rxqs, xa_idx); + if (xa_empty(&binding->bound_rxqs)) { + mutex_lock(&binding->lock); + binding->dev = NULL; + mutex_unlock(&binding->lock); + } break; } } diff --git a/net/core/devmem.h b/net/core/devmem.h index 7fc158d52729..a1aabc9685cc 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -20,6 +20,8 @@ struct net_devmem_dmabuf_binding { struct sg_table *sgt; struct net_device *dev; struct gen_pool *chunk_pool; + /* Protect dev */ + struct mutex lock; /* The user holds a ref (via the netlink API) for as long as they want * the binding to remain alive. Each page pool using this binding holds diff --git a/net/core/filter.c b/net/core/filter.c index 79cab4d78dc3..577a4504e26f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2509,6 +2509,7 @@ int skb_do_redirect(struct sk_buff *skb) goto out_drop; skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); + skb_scrub_packet(skb, false); return -EAGAIN; } return flags & BPF_F_NEIGH ? diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 230743bdbb14..a877693fecd6 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -708,25 +708,66 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, return 0; } +/** + * netdev_stat_queue_sum() - add up queue stats from range of queues + * @netdev: net_device + * @rx_start: index of the first Rx queue to query + * @rx_end: index after the last Rx queue (first *not* to query) + * @rx_sum: output Rx stats, should be already initialized + * @tx_start: index of the first Tx queue to query + * @tx_end: index after the last Tx queue (first *not* to query) + * @tx_sum: output Tx stats, should be already initialized + * + * Add stats from [start, end) range of queue IDs to *x_sum structs. + * The sum structs must be already initialized. Usually this + * helper is invoked from the .get_base_stats callbacks of drivers + * to account for stats of disabled queues. In that case the ranges + * are usually [netdev->real_num_*x_queues, netdev->num_*x_queues). + */ +void netdev_stat_queue_sum(struct net_device *netdev, + int rx_start, int rx_end, + struct netdev_queue_stats_rx *rx_sum, + int tx_start, int tx_end, + struct netdev_queue_stats_tx *tx_sum) +{ + const struct netdev_stat_ops *ops; + struct netdev_queue_stats_rx rx; + struct netdev_queue_stats_tx tx; + int i; + + ops = netdev->stat_ops; + + for (i = rx_start; i < rx_end; i++) { + memset(&rx, 0xff, sizeof(rx)); + if (ops->get_queue_stats_rx) + ops->get_queue_stats_rx(netdev, i, &rx); + netdev_nl_stats_add(rx_sum, &rx, sizeof(rx)); + } + for (i = tx_start; i < tx_end; i++) { + memset(&tx, 0xff, sizeof(tx)); + if (ops->get_queue_stats_tx) + ops->get_queue_stats_tx(netdev, i, &tx); + netdev_nl_stats_add(tx_sum, &tx, sizeof(tx)); + } +} +EXPORT_SYMBOL(netdev_stat_queue_sum); + static int netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, const struct genl_info *info) { - struct netdev_queue_stats_rx rx_sum, rx; - struct netdev_queue_stats_tx tx_sum, tx; - const struct netdev_stat_ops *ops; + struct netdev_queue_stats_rx rx_sum; + struct netdev_queue_stats_tx tx_sum; void *hdr; - int i; - ops = netdev->stat_ops; /* Netdev can't guarantee any complete counters */ - if (!ops->get_base_stats) + if (!netdev->stat_ops->get_base_stats) return 0; memset(&rx_sum, 0xff, sizeof(rx_sum)); memset(&tx_sum, 0xff, sizeof(tx_sum)); - ops->get_base_stats(netdev, &rx_sum, &tx_sum); + netdev->stat_ops->get_base_stats(netdev, &rx_sum, &tx_sum); /* The op was there, but nothing reported, don't bother */ if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && @@ -739,18 +780,8 @@ netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) goto nla_put_failure; - for (i = 0; i < netdev->real_num_rx_queues; i++) { - memset(&rx, 0xff, sizeof(rx)); - if (ops->get_queue_stats_rx) - ops->get_queue_stats_rx(netdev, i, &rx); - netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); - } - for (i = 0; i < netdev->real_num_tx_queues; i++) { - memset(&tx, 0xff, sizeof(tx)); - if (ops->get_queue_stats_tx) - ops->get_queue_stats_tx(netdev, i, &tx); - netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); - } + netdev_stat_queue_sum(netdev, 0, netdev->real_num_rx_queues, &rx_sum, + 0, netdev->real_num_tx_queues, &tx_sum); if (netdev_nl_stats_write_rx(rsp, &rx_sum) || netdev_nl_stats_write_tx(rsp, &tx_sum)) @@ -948,14 +979,25 @@ void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv) { struct net_devmem_dmabuf_binding *binding; struct net_devmem_dmabuf_binding *temp; + netdevice_tracker dev_tracker; struct net_device *dev; mutex_lock(&priv->lock); list_for_each_entry_safe(binding, temp, &priv->bindings, list) { + mutex_lock(&binding->lock); dev = binding->dev; + if (!dev) { + mutex_unlock(&binding->lock); + net_devmem_unbind_dmabuf(binding); + continue; + } + netdev_hold(dev, &dev_tracker, GFP_KERNEL); + mutex_unlock(&binding->lock); + netdev_lock(dev); net_devmem_unbind_dmabuf(binding); netdev_unlock(dev); + netdev_put(dev, &dev_tracker); } mutex_unlock(&priv->lock); } diff --git a/net/core/sock.c b/net/core/sock.c index e54449c9ab0b..1d9466a1f54e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -148,6 +148,8 @@ #include <linux/ethtool.h> +#include <uapi/linux/pidfd.h> + #include "dev.h" static DEFINE_MUTEX(proto_list_mutex); @@ -1879,6 +1881,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, { struct pid *peer_pid; struct file *pidfd_file = NULL; + unsigned int flags = 0; int pidfd; if (len > sizeof(pidfd)) @@ -1891,7 +1894,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, if (!peer_pid) return -ENODATA; - pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); + /* The use of PIDFD_STALE requires stashing of struct pid + * on pidfs with pidfs_register_pid() and only AF_UNIX + * were prepared for this. + */ + if (sk->sk_family == AF_UNIX) + flags = PIDFD_STALE; + + pidfd = pidfd_prepare(peer_pid, flags, &pidfd_file); put_pid(peer_pid); if (pidfd < 0) return pidfd; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index c33d4bf17929..0b7564b53790 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -140,7 +140,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + u8 *tag; + + if (skb_linearize(skb)) + return NULL; + + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M, KSZ_EGRESS_TAG_LEN); @@ -311,10 +316,16 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) { - /* Tag decoding */ - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; - unsigned int port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M; unsigned int len = KSZ_EGRESS_TAG_LEN; + unsigned int port; + u8 *tag; + + if (skb_linearize(skb)) + return NULL; + + /* Tag decoding */ + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M; /* Extra 4-bytes PTP timestamp */ if (tag[0] & KSZ9477_PTP_TAG_INDICATION) { diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 0e4076866c0a..f14a41ee4aa1 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -120,47 +120,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) } #ifdef CONFIG_INET_ESPINTCP -struct esp_tcp_sk { - struct sock *sk; - struct rcu_head rcu; -}; - -static void esp_free_tcp_sk(struct rcu_head *head) -{ - struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); - - sock_put(esk->sk); - kfree(esk); -} - static struct sock *esp_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); - struct esp_tcp_sk *esk; __be16 sport, dport; - struct sock *nsk; struct sock *sk; - sk = rcu_dereference(x->encap_sk); - if (sk && sk->sk_state == TCP_ESTABLISHED) - return sk; - spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (sk && sk == nsk) { - esk = kmalloc(sizeof(*esk), GFP_ATOMIC); - if (!esk) { - spin_unlock_bh(&x->lock); - return ERR_PTR(-ENOMEM); - } - RCU_INIT_POINTER(x->encap_sk, NULL); - esk->sk = sk; - call_rcu(&esk->rcu, esp_free_tcp_sk); - } spin_unlock_bh(&x->lock); sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4, @@ -173,20 +142,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x) return ERR_PTR(-EINVAL); } - spin_lock_bh(&x->lock); - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (encap->encap_sport != sport || - encap->encap_dport != dport) { - sock_put(sk); - sk = nsk ?: ERR_PTR(-EREMCHG); - } else if (sk == nsk) { - sock_put(sk); - } else { - rcu_assign_pointer(x->encap_sk, sk); - } - spin_unlock_bh(&x->lock); - return sk; } @@ -199,8 +154,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) sk = esp_find_tcp_sk(x); err = PTR_ERR_OR_ZERO(sk); - if (err) + if (err) { + kfree_skb(skb); goto out; + } bh_lock_sock(sk); if (sock_owned_by_user(sk)) @@ -209,6 +166,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); + sock_put(sk); + out: rcu_read_unlock(); return err; @@ -392,6 +351,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, if (IS_ERR(sk)) return ERR_CAST(sk); + sock_put(sk); + *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a8b04d4abcaa..85dc208f32e9 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -120,11 +120,6 @@ static void ipmr_expire_process(struct timer_list *t); lockdep_rtnl_is_held() || \ list_empty(&net->ipv4.mr_tables)) -static bool ipmr_can_free_table(struct net *net) -{ - return !check_net(net) || !net_initialized(net); -} - static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { @@ -317,11 +312,6 @@ EXPORT_SYMBOL(ipmr_rule_default); #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) -static bool ipmr_can_free_table(struct net *net) -{ - return !check_net(net); -} - static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { @@ -437,7 +427,7 @@ static void ipmr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); - WARN_ON_ONCE(!ipmr_can_free_table(net)); + WARN_ON_ONCE(!mr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index b5b06323cfd9..0d31a8c108d4 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -182,11 +182,15 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, int offset = skb_gro_offset(skb); const struct net_offload *ops; struct sk_buff *pp = NULL; - int ret; - - offset = offset - sizeof(struct udphdr); + int len, dlen; + __u8 *udpdata; + __be32 *udpdata32; - if (!pskb_pull(skb, offset)) + len = skb->len - offset; + dlen = offset + min(len, 8); + udpdata = skb_gro_header(skb, dlen, offset); + udpdata32 = (__be32 *)udpdata; + if (unlikely(!udpdata)) return NULL; rcu_read_lock(); @@ -194,11 +198,10 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (!ops || !ops->callbacks.gro_receive) goto out; - ret = __xfrm4_udp_encap_rcv(sk, skb, false); - if (ret) + /* check if it is a keepalive or IKE packet */ + if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out; - skb_push(skb, offset); NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); @@ -208,7 +211,6 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, out: rcu_read_unlock(); - skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 1; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9ba83f0c9928..c6b22170dc49 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3214,16 +3214,13 @@ static void add_v4_addrs(struct inet6_dev *idev) struct in6_addr addr; struct net_device *dev; struct net *net = dev_net(idev->dev); - int scope, plen, offset = 0; + int scope, plen; u32 pflags = 0; ASSERT_RTNL(); memset(&addr, 0, sizeof(struct in6_addr)); - /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */ - if (idev->dev->addr_len == sizeof(struct in6_addr)) - offset = sizeof(struct in6_addr) - 4; - memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); + memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4); if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { scope = IPV6_ADDR_COMPATv4; @@ -3534,7 +3531,13 @@ static void addrconf_gre_config(struct net_device *dev) return; } - if (dev->type == ARPHRD_ETHER) { + /* Generate the IPv6 link-local address using addrconf_addr_gen(), + * unless we have an IPv4 GRE device not bound to an IP address and + * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this + * case). Such devices fall back to add_v4_addrs() instead. + */ + if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 && + idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) { addrconf_addr_gen(idev, true); return; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 9e73944e3b53..72adfc107b55 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -137,47 +137,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) } #ifdef CONFIG_INET6_ESPINTCP -struct esp_tcp_sk { - struct sock *sk; - struct rcu_head rcu; -}; - -static void esp_free_tcp_sk(struct rcu_head *head) -{ - struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); - - sock_put(esk->sk); - kfree(esk); -} - static struct sock *esp6_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); - struct esp_tcp_sk *esk; __be16 sport, dport; - struct sock *nsk; struct sock *sk; - sk = rcu_dereference(x->encap_sk); - if (sk && sk->sk_state == TCP_ESTABLISHED) - return sk; - spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (sk && sk == nsk) { - esk = kmalloc(sizeof(*esk), GFP_ATOMIC); - if (!esk) { - spin_unlock_bh(&x->lock); - return ERR_PTR(-ENOMEM); - } - RCU_INIT_POINTER(x->encap_sk, NULL); - esk->sk = sk; - call_rcu(&esk->rcu, esp_free_tcp_sk); - } spin_unlock_bh(&x->lock); sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6, @@ -190,20 +159,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x) return ERR_PTR(-EINVAL); } - spin_lock_bh(&x->lock); - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (encap->encap_sport != sport || - encap->encap_dport != dport) { - sock_put(sk); - sk = nsk ?: ERR_PTR(-EREMCHG); - } else if (sk == nsk) { - sock_put(sk); - } else { - rcu_assign_pointer(x->encap_sk, sk); - } - spin_unlock_bh(&x->lock); - return sk; } @@ -216,8 +171,10 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) sk = esp6_find_tcp_sk(x); err = PTR_ERR_OR_ZERO(sk); - if (err) + if (err) { + kfree_skb(skb); goto out; + } bh_lock_sock(sk); if (sock_owned_by_user(sk)) @@ -226,6 +183,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); + sock_put(sk); + out: rcu_read_unlock(); return err; @@ -422,6 +381,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x, if (IS_ERR(sk)) return ERR_CAST(sk); + sock_put(sk); + *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index b413c9c8a21c..3276cde5ebd7 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -108,11 +108,6 @@ static void ipmr_expire_process(struct timer_list *t); lockdep_rtnl_is_held() || \ list_empty(&net->ipv6.mr6_tables)) -static bool ip6mr_can_free_table(struct net *net) -{ - return !check_net(net) || !net_initialized(net); -} - static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { @@ -306,11 +301,6 @@ EXPORT_SYMBOL(ip6mr_rule_default); #define ip6mr_for_each_table(mrt, net) \ for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) -static bool ip6mr_can_free_table(struct net *net) -{ - return !check_net(net); -} - static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) { @@ -416,7 +406,7 @@ static void ip6mr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); - WARN_ON_ONCE(!ip6mr_can_free_table(net)); + WARN_ON_ONCE(!mr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC | diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 4abc5e9d6322..841c81abaaf4 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -179,14 +179,18 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, int offset = skb_gro_offset(skb); const struct net_offload *ops; struct sk_buff *pp = NULL; - int ret; + int len, dlen; + __u8 *udpdata; + __be32 *udpdata32; if (skb->protocol == htons(ETH_P_IP)) return xfrm4_gro_udp_encap_rcv(sk, head, skb); - offset = offset - sizeof(struct udphdr); - - if (!pskb_pull(skb, offset)) + len = skb->len - offset; + dlen = offset + min(len, 8); + udpdata = skb_gro_header(skb, dlen, offset); + udpdata32 = (__be32 *)udpdata; + if (unlikely(!udpdata)) return NULL; rcu_read_lock(); @@ -194,11 +198,10 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (!ops || !ops->callbacks.gro_receive) goto out; - ret = __xfrm6_udp_encap_rcv(sk, skb, false); - if (ret) + /* check if it is a keepalive or IKE packet */ + if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out; - skb_push(skb, offset); NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); @@ -208,7 +211,6 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, out: rcu_read_unlock(); - skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 1; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 0259cde394ba..cc77ec5769d8 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -887,15 +887,15 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (sk->sk_type != SOCK_STREAM) goto copy_uaddr; + /* Partial read */ + if (used + offset < skb_len) + continue; + if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } - - /* Partial read */ - if (used + offset < skb_len) - continue; } while (len > 0); out: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 741e6c7edcb7..6b6de43d9420 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1354,10 +1354,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) hw->wiphy->software_iftypes |= BIT(NL80211_IFTYPE_MONITOR); - local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + - sizeof(void *) * channels, GFP_KERNEL); + local->int_scan_req = kzalloc(struct_size(local->int_scan_req, + channels, channels), + GFP_KERNEL); if (!local->int_scan_req) return -ENOMEM; + local->int_scan_req->n_channels = channels; eth_broadcast_addr(local->int_scan_req->bssid); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 5d1f2d6d09ad..35eaf0812c5b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -7675,6 +7675,7 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_res); int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 + 2 * 2 * IEEE80211_TTLM_NUM_TIDS; + u16 status_code; skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len); if (!skb) @@ -7697,19 +7698,18 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, WARN_ON(1); fallthrough; case NEG_TTLM_RES_REJECT: - mgmt->u.action.u.ttlm_res.status_code = - WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING; + status_code = WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING; break; case NEG_TTLM_RES_ACCEPT: - mgmt->u.action.u.ttlm_res.status_code = WLAN_STATUS_SUCCESS; + status_code = WLAN_STATUS_SUCCESS; break; case NEG_TTLM_RES_SUGGEST_PREFERRED: - mgmt->u.action.u.ttlm_res.status_code = - WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED; + status_code = WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED; ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm); break; } + mgmt->u.action.u.ttlm_res.status_code = cpu_to_le16(status_code); ieee80211_tx_skb(sdata, skb); } @@ -7875,7 +7875,7 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, * This can be better implemented in the future, to handle request * rejections. */ - if (mgmt->u.action.u.ttlm_res.status_code != WLAN_STATUS_SUCCESS) + if (le16_to_cpu(mgmt->u.action.u.ttlm_res.status_code) != WLAN_STATUS_SUCCESS) __ieee80211_disconnect(sdata); } diff --git a/net/mctp/device.c b/net/mctp/device.c index 8e0724c56723..7c0dcf3df319 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -117,11 +117,18 @@ static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct ifaddrmsg *hdr; struct mctp_dev *mdev; - int ifindex, rc; - - hdr = nlmsg_data(cb->nlh); - // filter by ifindex if requested - ifindex = hdr->ifa_index; + int ifindex = 0, rc; + + /* Filter by ifindex if a header is provided */ + if (cb->nlh->nlmsg_len >= nlmsg_msg_size(sizeof(*hdr))) { + hdr = nlmsg_data(cb->nlh); + ifindex = hdr->ifa_index; + } else { + if (cb->strict_check) { + NL_SET_ERR_MSG(cb->extack, "mctp: Invalid header for addr dump request"); + return -EINVAL; + } + } rcu_read_lock(); for_each_netdev_dump(net, dev, mcb->ifindex) { diff --git a/net/mctp/route.c b/net/mctp/route.c index 4c460160914f..d9c8e5a5f9ce 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -313,8 +313,10 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) key = flow->key; - if (WARN_ON(key->dev && key->dev != dev)) + if (key->dev) { + WARN_ON(key->dev != dev); return; + } mctp_dev_set_key(dev, key); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index cf3ce72c3de6..5251524b96af 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -64,7 +64,7 @@ struct hbucket { #define ahash_sizeof_regions(htable_bits) \ (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) #define ahash_region(n, htable_bits) \ - ((n) % ahash_numof_locks(htable_bits)) + ((n) / jhash_size(HTABLE_REGION_BITS)) #define ahash_bucket_start(h, htable_bits) \ ((htable_bits) < HTABLE_REGION_BITS ? 0 \ : (h) * jhash_size(HTABLE_REGION_BITS)) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3313bceb6cc9..014f07740369 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -119,13 +119,12 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) return false; } -/* Get route to daddr, update *saddr, optionally bind route to saddr */ +/* Get route to daddr, optionally bind route to saddr */ static struct rtable *do_output_route4(struct net *net, __be32 daddr, - int rt_mode, __be32 *saddr) + int rt_mode, __be32 *ret_saddr) { struct flowi4 fl4; struct rtable *rt; - bool loop = false; memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; @@ -135,23 +134,17 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, retry: rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { - /* Invalid saddr ? */ - if (PTR_ERR(rt) == -EINVAL && *saddr && - rt_mode & IP_VS_RT_MODE_CONNECT && !loop) { - *saddr = 0; - flowi4_update_output(&fl4, 0, daddr, 0); - goto retry; - } IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr); return NULL; - } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { + } + if (rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { ip_rt_put(rt); - *saddr = fl4.saddr; flowi4_update_output(&fl4, 0, daddr, fl4.saddr); - loop = true; + rt_mode = 0; goto retry; } - *saddr = fl4.saddr; + if (ret_saddr) + *ret_saddr = fl4.saddr; return rt; } @@ -344,19 +337,15 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, if (ret_saddr) *ret_saddr = dest_dst->dst_saddr.ip; } else { - __be32 saddr = htonl(INADDR_ANY); - noref = 0; /* For such unconfigured boxes avoid many route lookups * for performance reasons because we do not remember saddr */ rt_mode &= ~IP_VS_RT_MODE_CONNECT; - rt = do_output_route4(net, daddr, rt_mode, &saddr); + rt = do_output_route4(net, daddr, rt_mode, ret_saddr); if (!rt) goto err_unreach; - if (ret_saddr) - *ret_saddr = saddr; } local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 61fea7baae5d..2f22ca59586f 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -975,8 +975,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, upcall.cmd = OVS_PACKET_CMD_ACTION; upcall.mru = OVS_CB(skb)->mru; - for (a = nla_data(attr), rem = nla_len(attr); rem > 0; - a = nla_next(a, &rem)) { + nla_for_each_nested(a, attr, rem) { switch (nla_type(a)) { case OVS_USERSPACE_ATTR_USERDATA: upcall.userdata = a; diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 12dd71139da3..c93761040c6e 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -144,7 +144,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 2ca5332cfcc5..902ff5470607 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1136,7 +1136,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); } while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6c9029f71e88..2a0f3a513bfa 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -441,7 +441,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit || q->memory_usage > q->memory_limit) { - struct sk_buff *skb = fq_codel_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); q->cstats.drop_len += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index f3b8203d3e85..df7fac95ab15 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -366,7 +366,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_pie_qdisc_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); len_dropped += qdisc_pkt_len(skb); num_dropped += 1; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index cb8c525ea20e..7986145a527c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1569,6 +1569,9 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } + sch->qstats.backlog += len; + sch->q.qlen++; + if (first && !cl->cl_nactive) { if (cl->cl_flags & HFSC_RSC) init_ed(cl, len); @@ -1584,9 +1587,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } - sch->qstats.backlog += len; - sch->q.qlen++; - return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 44d9efe1a96a..5aa434b46707 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -564,7 +564,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = hhf_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); rtnl_kfree_skbs(skb, skb); } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 4b9a639b642e..14bf71f57057 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -348,7 +348,8 @@ static void htb_add_to_wait_tree(struct htb_sched *q, */ static inline void htb_next_rb_node(struct rb_node **n) { - *n = rb_next(*n); + if (*n) + *n = rb_next(*n); } /** @@ -609,8 +610,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) */ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(!cl->prio_activity); - + if (!cl->prio_activity) + return; htb_deactivate_prios(q, cl); cl->prio_activity = 0; } @@ -1485,8 +1486,6 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - if (!cl->prio_activity) - return; htb_deactivate(qdisc_priv(sch), cl); } @@ -1740,8 +1739,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, if (cl->parent) cl->parent->children--; - if (cl->prio_activity) - htb_deactivate(q, cl); + htb_deactivate(q, cl); if (cl->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&cl->pq_node, @@ -1949,8 +1947,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* turn parent into inner node */ qdisc_purge_queue(parent->leaf.q); parent_qdisc = parent->leaf.q; - if (parent->prio_activity) - htb_deactivate(q, parent); + htb_deactivate(q, parent); /* remove from evt list because of level change */ if (parent->cmode != HTB_CAN_SEND) { diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 3771d000b30d..ff49a6c97033 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -195,7 +195,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index eadc00410ebc..98f78cd55905 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -631,7 +631,7 @@ static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, const char *name) { struct qstr q = QSTR(name); - struct dentry *dentry = d_hash_and_lookup(parent, &q); + struct dentry *dentry = try_lookup_noperm(&q, parent); if (!dentry) { dentry = d_alloc(parent, &q); if (!dentry) @@ -658,7 +658,7 @@ static void __rpc_depopulate(struct dentry *parent, for (i = start; i < eof; i++) { name.name = files[i].name; name.len = strlen(files[i].name); - dentry = d_hash_and_lookup(parent, &name); + dentry = try_lookup_noperm(&name, parent); if (dentry == NULL) continue; @@ -1190,7 +1190,7 @@ static const struct rpc_filelist files[] = { struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name) { - return d_hash_and_lookup(sb->s_root, &QSTR(dir_name)); + return try_lookup_noperm(&QSTR(dir_name), sb->s_root); } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); @@ -1301,7 +1301,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) struct dentry *pipe_dentry = NULL; /* We should never get this far if "gssd" doesn't exist */ - gssd_dentry = d_hash_and_lookup(root, &QSTR(files[RPCAUTH_gssd].name)); + gssd_dentry = try_lookup_noperm(&QSTR(files[RPCAUTH_gssd].name), root); if (!gssd_dentry) return ERR_PTR(-ENOENT); @@ -1311,8 +1311,8 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) goto out; } - clnt_dentry = d_hash_and_lookup(gssd_dentry, - &QSTR(gssd_dummy_clnt_dir[0].name)); + clnt_dentry = try_lookup_noperm(&QSTR(gssd_dummy_clnt_dir[0].name), + gssd_dentry); if (!clnt_dentry) { __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index c524421ec652..8584893b4785 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -817,12 +817,16 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, goto exit; } + /* Get net to avoid freed tipc_crypto when delete namespace */ + get_net(aead->crypto->net); + /* Now, do encrypt */ rc = crypto_aead_encrypt(req); if (rc == -EINPROGRESS || rc == -EBUSY) return rc; tipc_bearer_put(b); + put_net(aead->crypto->net); exit: kfree(ctx); @@ -860,6 +864,7 @@ static void tipc_aead_encrypt_done(void *data, int err) kfree(tx_ctx); tipc_bearer_put(b); tipc_aead_put(aead); + put_net(net); } /** diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 77e33e1e340e..65b0da6fdf6a 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -396,7 +396,6 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; shinfo = skb_shinfo(strp->anchor); - shinfo->frag_list = NULL; /* If we don't know the length go max plus page for cipher overhead */ need_spc = strp->stm.full_len ?: TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; @@ -412,6 +411,8 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) page, 0, 0); } + shinfo->frag_list = NULL; + strp->copy_mode = 1; strp->stm.offset = 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f78a2492826f..59a64b2ced6e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -85,10 +85,13 @@ #include <linux/file.h> #include <linux/filter.h> #include <linux/fs.h> +#include <linux/fs_struct.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/mount.h> #include <linux/namei.h> +#include <linux/net.h> +#include <linux/pidfs.h> #include <linux/poll.h> #include <linux/proc_fs.h> #include <linux/sched/signal.h> @@ -643,6 +646,9 @@ static void unix_sock_destructor(struct sock *sk) return; } + if (sk->sk_peer_pid) + pidfs_put_pid(sk->sk_peer_pid); + if (u->addr) unix_release_addr(u->addr); @@ -734,13 +740,48 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_gc(); /* Garbage collect fds */ } -static void init_peercred(struct sock *sk) +struct unix_peercred { + struct pid *peer_pid; + const struct cred *peer_cred; +}; + +static inline int prepare_peercred(struct unix_peercred *peercred) { - sk->sk_peer_pid = get_pid(task_tgid(current)); - sk->sk_peer_cred = get_current_cred(); + struct pid *pid; + int err; + + pid = task_tgid(current); + err = pidfs_register_pid(pid); + if (likely(!err)) { + peercred->peer_pid = get_pid(pid); + peercred->peer_cred = get_current_cred(); + } + return err; } -static void update_peercred(struct sock *sk) +static void drop_peercred(struct unix_peercred *peercred) +{ + const struct cred *cred = NULL; + struct pid *pid = NULL; + + might_sleep(); + + swap(peercred->peer_pid, pid); + swap(peercred->peer_cred, cred); + + pidfs_put_pid(pid); + put_pid(pid); + put_cred(cred); +} + +static inline void init_peercred(struct sock *sk, + const struct unix_peercred *peercred) +{ + sk->sk_peer_pid = peercred->peer_pid; + sk->sk_peer_cred = peercred->peer_cred; +} + +static void update_peercred(struct sock *sk, struct unix_peercred *peercred) { const struct cred *old_cred; struct pid *old_pid; @@ -748,11 +789,11 @@ static void update_peercred(struct sock *sk) spin_lock(&sk->sk_peer_lock); old_pid = sk->sk_peer_pid; old_cred = sk->sk_peer_cred; - init_peercred(sk); + init_peercred(sk, peercred); spin_unlock(&sk->sk_peer_lock); - put_pid(old_pid); - put_cred(old_cred); + peercred->peer_pid = old_pid; + peercred->peer_cred = old_cred; } static void copy_peercred(struct sock *sk, struct sock *peersk) @@ -761,6 +802,7 @@ static void copy_peercred(struct sock *sk, struct sock *peersk) spin_lock(&sk->sk_peer_lock); sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); + pidfs_get_pid(sk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); spin_unlock(&sk->sk_peer_lock); } @@ -770,6 +812,7 @@ static int unix_listen(struct socket *sock, int backlog) int err; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); + struct unix_peercred peercred = {}; err = -EOPNOTSUPP; if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) @@ -777,6 +820,9 @@ static int unix_listen(struct socket *sock, int backlog) err = -EINVAL; if (!READ_ONCE(u->addr)) goto out; /* No listens on an unbound socket */ + err = prepare_peercred(&peercred); + if (err) + goto out; unix_state_lock(sk); if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN) goto out_unlock; @@ -786,11 +832,12 @@ static int unix_listen(struct socket *sock, int backlog) WRITE_ONCE(sk->sk_state, TCP_LISTEN); /* set credentials so connect can copy them */ - update_peercred(sk); + update_peercred(sk, &peercred); err = 0; out_unlock: unix_state_unlock(sk); + drop_peercred(&peercred); out: return err; } @@ -1101,7 +1148,7 @@ static int unix_release(struct socket *sock) } static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len, - int type) + int type, int flags) { struct inode *inode; struct path path; @@ -1109,13 +1156,39 @@ static struct sock *unix_find_bsd(struct sockaddr_un *sunaddr, int addr_len, int err; unix_mkname_bsd(sunaddr, addr_len); - err = kern_path(sunaddr->sun_path, LOOKUP_FOLLOW, &path); - if (err) - goto fail; - err = path_permission(&path, MAY_WRITE); - if (err) - goto path_put; + if (flags & SOCK_COREDUMP) { + const struct cred *cred; + struct cred *kcred; + struct path root; + + kcred = prepare_kernel_cred(&init_task); + if (!kcred) { + err = -ENOMEM; + goto fail; + } + + task_lock(&init_task); + get_fs_root(init_task.fs, &root); + task_unlock(&init_task); + + cred = override_creds(kcred); + err = vfs_path_lookup(root.dentry, root.mnt, sunaddr->sun_path, + LOOKUP_BENEATH | LOOKUP_NO_SYMLINKS | + LOOKUP_NO_MAGICLINKS, &path); + put_cred(revert_creds(cred)); + path_put(&root); + if (err) + goto fail; + } else { + err = kern_path(sunaddr->sun_path, LOOKUP_FOLLOW, &path); + if (err) + goto fail; + + err = path_permission(&path, MAY_WRITE); + if (err) + goto path_put; + } err = -ECONNREFUSED; inode = d_backing_inode(path.dentry); @@ -1165,12 +1238,12 @@ static struct sock *unix_find_abstract(struct net *net, static struct sock *unix_find_other(struct net *net, struct sockaddr_un *sunaddr, - int addr_len, int type) + int addr_len, int type, int flags) { struct sock *sk; if (sunaddr->sun_path[0]) - sk = unix_find_bsd(sunaddr, addr_len, type); + sk = unix_find_bsd(sunaddr, addr_len, type, flags); else sk = unix_find_abstract(net, sunaddr, addr_len, type); @@ -1428,7 +1501,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, } restart: - other = unix_find_other(sock_net(sk), sunaddr, alen, sock->type); + other = unix_find_other(sock_net(sk), sunaddr, alen, sock->type, 0); if (IS_ERR(other)) { err = PTR_ERR(other); goto out; @@ -1525,6 +1598,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; struct sock *sk = sock->sk, *newsk = NULL, *other = NULL; struct unix_sock *u = unix_sk(sk), *newu, *otheru; + struct unix_peercred peercred = {}; struct net *net = sock_net(sk); struct sk_buff *skb = NULL; unsigned char state; @@ -1561,6 +1635,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; } + err = prepare_peercred(&peercred); + if (err) + goto out; + /* Allocate skb for sending to listening sock */ skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL); if (!skb) { @@ -1570,7 +1648,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, restart: /* Find listening sock. */ - other = unix_find_other(net, sunaddr, addr_len, sk->sk_type); + other = unix_find_other(net, sunaddr, addr_len, sk->sk_type, flags); if (IS_ERR(other)) { err = PTR_ERR(other); goto out_free_skb; @@ -1636,7 +1714,7 @@ restart: unix_peer(newsk) = sk; newsk->sk_state = TCP_ESTABLISHED; newsk->sk_type = sk->sk_type; - init_peercred(newsk); + init_peercred(newsk, &peercred); newu = unix_sk(newsk); newu->listener = other; RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); @@ -1695,20 +1773,33 @@ out_free_skb: out_free_sk: unix_release_sock(newsk, 0); out: + drop_peercred(&peercred); return err; } static int unix_socketpair(struct socket *socka, struct socket *sockb) { + struct unix_peercred ska_peercred = {}, skb_peercred = {}; struct sock *ska = socka->sk, *skb = sockb->sk; + int err; + + err = prepare_peercred(&ska_peercred); + if (err) + return err; + + err = prepare_peercred(&skb_peercred); + if (err) { + drop_peercred(&ska_peercred); + return err; + } /* Join our sockets back to back */ sock_hold(ska); sock_hold(skb); unix_peer(ska) = skb; unix_peer(skb) = ska; - init_peercred(ska); - init_peercred(skb); + init_peercred(ska, &ska_peercred); + init_peercred(skb, &skb_peercred); ska->sk_state = TCP_ESTABLISHED; skb->sk_state = TCP_ESTABLISHED; @@ -2026,7 +2117,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_namelen) { lookup: other = unix_find_other(sock_net(sk), msg->msg_name, - msg->msg_namelen, sk->sk_type); + msg->msg_namelen, sk->sk_type, 0); if (IS_ERR(other)) { err = PTR_ERR(other); goto out_free; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 9865f305275d..ddd3a97f6609 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2681,7 +2681,7 @@ cfg80211_defrag_mle(const struct element *mle, const u8 *ie, size_t ielen, /* Required length for first defragmentation */ buf_len = mle->datalen - 1; for_each_element(elem, mle->data + mle->datalen, - ielen - sizeof(*mle) + mle->datalen) { + ie + ielen - mle->data - mle->datalen) { if (elem->id != WLAN_EID_FRAGMENT) break; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 4abc81f33d3e..72c000c0ae5f 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1304,7 +1304,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->queue_id = qid; xp_add_xsk(xs->pool, xs); - if (xs->zc && qid < dev->real_num_rx_queues) { + if (qid < dev->real_num_rx_queues) { struct netdev_rx_queue *rxq; rxq = __netif_get_rx_queue(dev, qid); diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index fe82e2d07300..fc7a603b04f1 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -171,8 +171,10 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) struct espintcp_ctx *ctx = espintcp_getctx(sk); if (skb_queue_len(&ctx->out_queue) >= - READ_ONCE(net_hotdata.max_backlog)) + READ_ONCE(net_hotdata.max_backlog)) { + kfree_skb(skb); return -ENOBUFS; + } __skb_queue_tail(&ctx->out_queue, skb); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 0c1420534394..907c3ccb440d 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -48,7 +48,6 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen) { struct acomp_req *req = ipcomp_cb(skb)->req; struct ipcomp_req_extra *extra; - const int plen = skb->data_len; struct scatterlist *dsg; int len, dlen; @@ -64,7 +63,7 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen) /* Only update truesize on input. */ if (!hlen) - skb->truesize += dlen - plen; + skb->truesize += dlen; skb->data_len = dlen; skb->len += dlen; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 143ac3aa7537..f4bad8c895d6 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1581,6 +1581,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *delpol; struct hlist_head *chain; + /* Sanitize mark before store */ + policy->mark.v &= policy->mark.m; + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 341d79ecb5c2..07fe8e5daa32 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -838,9 +838,6 @@ int __xfrm_state_delete(struct xfrm_state *x) xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); - if (x->encap_sk) - sock_put(rcu_dereference_raw(x->encap_sk)); - xfrm_dev_state_delete(x); /* All xfrm_state objects are created by xfrm_state_alloc. @@ -1721,6 +1718,9 @@ static void __xfrm_state_insert(struct xfrm_state *x) list_add(&x->km.all, &net->xfrm.state_all); + /* Sanitize mark before store */ + x->mark.v &= x->mark.m; + h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h, diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs index 014af0d1fc70..a08eb5518cac 100644 --- a/rust/bindings/lib.rs +++ b/rust/bindings/lib.rs @@ -26,6 +26,7 @@ #[allow(dead_code)] #[allow(clippy::undocumented_unsafe_blocks)] +#[cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))] mod bindings_raw { // Manual definition for blocklisted types. type __kernel_size_t = usize; diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs index ae9d072741ce..87a71fd40c3c 100644 --- a/rust/kernel/alloc/kvec.rs +++ b/rust/kernel/alloc/kvec.rs @@ -2,6 +2,9 @@ //! Implementation of [`Vec`]. +// May not be needed in Rust 1.87.0 (pending beta backport). +#![allow(clippy::ptr_eq)] + use super::{ allocator::{KVmalloc, Kmalloc, Vmalloc}, layout::ArrayLayout, diff --git a/rust/kernel/list.rs b/rust/kernel/list.rs index a335c3b1ff5e..2054682c5724 100644 --- a/rust/kernel/list.rs +++ b/rust/kernel/list.rs @@ -4,6 +4,9 @@ //! A linked list implementation. +// May not be needed in Rust 1.87.0 (pending beta backport). +#![allow(clippy::ptr_eq)] + use crate::sync::ArcBorrow; use crate::types::Opaque; use core::iter::{DoubleEndedIterator, FusedIterator}; diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index 878111cb77bc..fb61ce81ea28 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -73,7 +73,7 @@ impl fmt::Display for BStr { b'\r' => f.write_str("\\r")?, // Printable characters. 0x20..=0x7e => f.write_char(b as char)?, - _ => write!(f, "\\x{:02x}", b)?, + _ => write!(f, "\\x{b:02x}")?, } } Ok(()) @@ -109,7 +109,7 @@ impl fmt::Debug for BStr { b'\\' => f.write_str("\\\\")?, // Printable characters. 0x20..=0x7e => f.write_char(b as char)?, - _ => write!(f, "\\x{:02x}", b)?, + _ => write!(f, "\\x{b:02x}")?, } } f.write_char('"') @@ -447,7 +447,7 @@ impl fmt::Display for CStr { // Printable character. f.write_char(c as char)?; } else { - write!(f, "\\x{:02x}", c)?; + write!(f, "\\x{c:02x}")?; } } Ok(()) @@ -479,7 +479,7 @@ impl fmt::Debug for CStr { // Printable characters. b'\"' => f.write_str("\\\"")?, 0x20..=0x7e => f.write_char(c as char)?, - _ => write!(f, "\\x{:02x}", c)?, + _ => write!(f, "\\x{c:02x}")?, } } f.write_str("\"") @@ -641,13 +641,13 @@ mod tests { #[test] fn test_cstr_display() { let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap(); - assert_eq!(format!("{}", hello_world), "hello, world!"); + assert_eq!(format!("{hello_world}"), "hello, world!"); let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap(); - assert_eq!(format!("{}", non_printables), "\\x01\\x09\\x0a"); + assert_eq!(format!("{non_printables}"), "\\x01\\x09\\x0a"); let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap(); - assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu"); + assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu"); let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap(); - assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80"); + assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80"); } #[test] @@ -658,47 +658,47 @@ mod tests { bytes[i as usize] = i.wrapping_add(1); } let cstr = CStr::from_bytes_with_nul(&bytes).unwrap(); - assert_eq!(format!("{}", cstr), ALL_ASCII_CHARS); + assert_eq!(format!("{cstr}"), ALL_ASCII_CHARS); } #[test] fn test_cstr_debug() { let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap(); - assert_eq!(format!("{:?}", hello_world), "\"hello, world!\""); + assert_eq!(format!("{hello_world:?}"), "\"hello, world!\""); let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap(); - assert_eq!(format!("{:?}", non_printables), "\"\\x01\\x09\\x0a\""); + assert_eq!(format!("{non_printables:?}"), "\"\\x01\\x09\\x0a\""); let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap(); - assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\""); + assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\""); let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap(); - assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\""); + assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\""); } #[test] fn test_bstr_display() { let hello_world = BStr::from_bytes(b"hello, world!"); - assert_eq!(format!("{}", hello_world), "hello, world!"); + assert_eq!(format!("{hello_world}"), "hello, world!"); let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_"); - assert_eq!(format!("{}", escapes), "_\\t_\\n_\\r_\\_'_\"_"); + assert_eq!(format!("{escapes}"), "_\\t_\\n_\\r_\\_'_\"_"); let others = BStr::from_bytes(b"\x01"); - assert_eq!(format!("{}", others), "\\x01"); + assert_eq!(format!("{others}"), "\\x01"); let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu"); - assert_eq!(format!("{}", non_ascii), "d\\xe9j\\xe0 vu"); + assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu"); let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80"); - assert_eq!(format!("{}", good_bytes), "\\xf0\\x9f\\xa6\\x80"); + assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80"); } #[test] fn test_bstr_debug() { let hello_world = BStr::from_bytes(b"hello, world!"); - assert_eq!(format!("{:?}", hello_world), "\"hello, world!\""); + assert_eq!(format!("{hello_world:?}"), "\"hello, world!\""); let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_"); - assert_eq!(format!("{:?}", escapes), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\""); + assert_eq!(format!("{escapes:?}"), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\""); let others = BStr::from_bytes(b"\x01"); - assert_eq!(format!("{:?}", others), "\"\\x01\""); + assert_eq!(format!("{others:?}"), "\"\\x01\""); let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu"); - assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\""); + assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\""); let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80"); - assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\""); + assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\""); } } diff --git a/rust/macros/kunit.rs b/rust/macros/kunit.rs index 4f553ecf40c0..99ccac82edde 100644 --- a/rust/macros/kunit.rs +++ b/rust/macros/kunit.rs @@ -15,10 +15,7 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream { } if attr.len() > 255 { - panic!( - "The test suite name `{}` exceeds the maximum length of 255 bytes", - attr - ) + panic!("The test suite name `{attr}` exceeds the maximum length of 255 bytes") } let mut tokens: Vec<_> = ts.into_iter().collect(); @@ -102,16 +99,14 @@ pub(crate) fn kunit_tests(attr: TokenStream, ts: TokenStream) -> TokenStream { let mut kunit_macros = "".to_owned(); let mut test_cases = "".to_owned(); for test in &tests { - let kunit_wrapper_fn_name = format!("kunit_rust_wrapper_{}", test); + let kunit_wrapper_fn_name = format!("kunit_rust_wrapper_{test}"); let kunit_wrapper = format!( - "unsafe extern \"C\" fn {}(_test: *mut kernel::bindings::kunit) {{ {}(); }}", - kunit_wrapper_fn_name, test + "unsafe extern \"C\" fn {kunit_wrapper_fn_name}(_test: *mut kernel::bindings::kunit) {{ {test}(); }}" ); writeln!(kunit_macros, "{kunit_wrapper}").unwrap(); writeln!( test_cases, - " kernel::kunit::kunit_case(kernel::c_str!(\"{}\"), {}),", - test, kunit_wrapper_fn_name + " kernel::kunit::kunit_case(kernel::c_str!(\"{test}\"), {kunit_wrapper_fn_name})," ) .unwrap(); } diff --git a/rust/macros/module.rs b/rust/macros/module.rs index a9418fbc9b44..2f66107847f7 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -48,7 +48,7 @@ impl<'a> ModInfoBuilder<'a> { ) } else { // Loadable modules' modinfo strings go as-is. - format!("{field}={content}\0", field = field, content = content) + format!("{field}={content}\0") }; write!( @@ -126,10 +126,7 @@ impl ModuleInfo { }; if seen_keys.contains(&key) { - panic!( - "Duplicated key \"{}\". Keys can only be specified once.", - key - ); + panic!("Duplicated key \"{key}\". Keys can only be specified once."); } assert_eq!(expect_punct(it), ':'); @@ -143,10 +140,7 @@ impl ModuleInfo { "license" => info.license = expect_string_ascii(it), "alias" => info.alias = Some(expect_string_array(it)), "firmware" => info.firmware = Some(expect_string_array(it)), - _ => panic!( - "Unknown key \"{}\". Valid keys are: {:?}.", - key, EXPECTED_KEYS - ), + _ => panic!("Unknown key \"{key}\". Valid keys are: {EXPECTED_KEYS:?}."), } assert_eq!(expect_punct(it), ','); @@ -158,7 +152,7 @@ impl ModuleInfo { for key in REQUIRED_KEYS { if !seen_keys.iter().any(|e| e == key) { - panic!("Missing required key \"{}\".", key); + panic!("Missing required key \"{key}\"."); } } @@ -170,10 +164,7 @@ impl ModuleInfo { } if seen_keys != ordered_keys { - panic!( - "Keys are not ordered as expected. Order them like: {:?}.", - ordered_keys - ); + panic!("Keys are not ordered as expected. Order them like: {ordered_keys:?}."); } info diff --git a/rust/macros/paste.rs b/rust/macros/paste.rs index 6529a387673f..cce712d19855 100644 --- a/rust/macros/paste.rs +++ b/rust/macros/paste.rs @@ -50,7 +50,7 @@ fn concat_helper(tokens: &[TokenTree]) -> Vec<(String, Span)> { let tokens = group.stream().into_iter().collect::<Vec<TokenTree>>(); segments.append(&mut concat_helper(tokens.as_slice())); } - token => panic!("unexpected token in paste segments: {:?}", token), + token => panic!("unexpected token in paste segments: {token:?}"), }; } diff --git a/rust/pin-init/internal/src/pinned_drop.rs b/rust/pin-init/internal/src/pinned_drop.rs index c824dd8b436d..c4ca7a70b726 100644 --- a/rust/pin-init/internal/src/pinned_drop.rs +++ b/rust/pin-init/internal/src/pinned_drop.rs @@ -28,8 +28,7 @@ pub(crate) fn pinned_drop(_args: TokenStream, input: TokenStream) -> TokenStream // Found the end of the generics, this should be `PinnedDrop`. assert!( matches!(tt, TokenTree::Ident(i) if i.to_string() == "PinnedDrop"), - "expected 'PinnedDrop', found: '{:?}'", - tt + "expected 'PinnedDrop', found: '{tt:?}'" ); pinned_drop_idx = Some(i); break; diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs index 13495910271f..c98d7a8cde77 100644 --- a/rust/uapi/lib.rs +++ b/rust/uapi/lib.rs @@ -24,6 +24,7 @@ unreachable_pub, unsafe_op_in_unsafe_fn )] +#![cfg_attr(CONFIG_RUSTC_HAS_UNNECESSARY_TRANSMUTES, allow(unnecessary_transmutes))] // Manual definition of blocklisted types. type __kernel_size_t = usize; diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c index dac67c367457..4147616102f9 100644 --- a/samples/ftrace/sample-trace-array.c +++ b/samples/ftrace/sample-trace-array.c @@ -112,7 +112,7 @@ static int __init sample_trace_array_init(void) /* * If context specific per-cpu buffers havent already been allocated. */ - trace_printk_init_buffers(); + trace_array_init_printk(tr); simple_tsk = kthread_run(simple_thread, NULL, "sample-instance"); if (IS_ERR(simple_tsk)) { diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index d88acdf40855..fd649c68e198 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -37,6 +37,18 @@ KBUILD_CFLAGS += -Wno-gnu # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219 KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf) KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf) + +# Clang may emit a warning when a const variable, such as the dummy variables +# in typecheck(), or const member of an aggregate type are not initialized, +# which can result in unexpected behavior. However, in many audited cases of +# the "field" variant of the warning, this is intentional because the field is +# never used within a particular call path, the field is within a union with +# other non-const members, or the containing object is not const so the field +# can be modified via memcpy() / memset(). While the variable warning also gets +# disabled with this same switch, there should not be too much coverage lost +# because -Wuninitialized will still flag when an uninitialized const variable +# is used. +KBUILD_CFLAGS += $(call cc-disable-warning, default-const-init-unsafe) else # gcc inanely warns about local variables called 'main' diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index b0a6cd5b818c..b64862dc6f08 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -13,7 +13,7 @@ ifdef CONFIG_ARCH_VMLINUX_NEEDS_RELOCS vmlinux-final := vmlinux.unstripped quiet_cmd_strip_relocs = RSTRIP $@ - cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' $< $@ + cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' --remove-section=!'.rel*.dyn' $< $@ vmlinux: $(vmlinux-final) FORCE $(call if_changed,strip_relocs) @@ -94,10 +94,10 @@ $(vmlinux-final): $(RESOLVE_BTFIDS) endif ifdef CONFIG_BUILDTIME_TABLE_SORT -vmlinux: scripts/sorttable +$(vmlinux-final): scripts/sorttable endif -# module.builtin.ranges +# modules.builtin.ranges # --------------------------------------------------------------------------- ifdef CONFIG_BUILTIN_MODULE_RANGES __default: modules.builtin.ranges diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 938c7457717e..b024ffb3e201 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -73,7 +73,7 @@ vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE targets += vmlinux.o -# module.builtin.modinfo +# modules.builtin.modinfo # --------------------------------------------------------------------------- OBJCOPYFLAGS_modules.builtin.modinfo := -j .modinfo -O binary @@ -82,7 +82,7 @@ targets += modules.builtin.modinfo modules.builtin.modinfo: vmlinux.o FORCE $(call if_changed,objcopy) -# module.builtin +# modules.builtin # --------------------------------------------------------------------------- # The second line aids cases where multiple modules share the same object. diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec index 726f34e11960..98f206cb7c60 100644 --- a/scripts/package/kernel.spec +++ b/scripts/package/kernel.spec @@ -16,6 +16,7 @@ Source1: config Source2: diff.patch Provides: kernel-%{KERNELRELEASE} BuildRequires: bc binutils bison dwarves +BuildRequires: (elfutils-devel or libdw-devel) BuildRequires: (elfutils-libelf-devel or libelf-devel) flex BuildRequires: gcc make openssl openssl-devel perl python3 rsync diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 744ddba01d93..d4b007b38a47 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -210,7 +210,7 @@ Rules-Requires-Root: no Build-Depends: debhelper-compat (= 12) Build-Depends-Arch: bc, bison, flex, gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>, - kmod, libelf-dev:native, + kmod, libdw-dev:native, libelf-dev:native, libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>, python3:native, rsync Homepage: https://www.kernel.org/ diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 6039afae4bfc..0aef34b9609b 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -283,7 +283,7 @@ static struct dentry *aafs_create(const char *name, umode_t mode, dir = d_inode(parent); inode_lock(dir); - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_noperm(&QSTR(name), parent); if (IS_ERR(dentry)) { error = PTR_ERR(dentry); goto fail_lock; @@ -2551,7 +2551,7 @@ static int aa_mk_null_file(struct dentry *parent) return error; inode_lock(d_inode(parent)); - dentry = lookup_one_len(NULL_FILE_NAME, parent, strlen(NULL_FILE_NAME)); + dentry = lookup_noperm(&QSTR(NULL_FILE_NAME), parent); if (IS_ERR(dentry)) { error = PTR_ERR(dentry); goto out; diff --git a/security/inode.c b/security/inode.c index da3ab44c8e57..3913501621fa 100644 --- a/security/inode.c +++ b/security/inode.c @@ -128,7 +128,7 @@ static struct dentry *securityfs_create_dentry(const char *name, umode_t mode, dir = d_inode(parent); inode_lock(dir); - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_noperm(&QSTR(name), parent); if (IS_ERR(dentry)) goto out; diff --git a/security/landlock/audit.c b/security/landlock/audit.c index 7e5e0ed0e4e5..c52d079cdb77 100644 --- a/security/landlock/audit.c +++ b/security/landlock/audit.c @@ -175,7 +175,7 @@ static void test_get_hierarchy(struct kunit *const test) KUNIT_EXPECT_EQ(test, 10, get_hierarchy(&dom2, 0)->id); KUNIT_EXPECT_EQ(test, 20, get_hierarchy(&dom2, 1)->id); KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, 2)->id); - KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, -1)->id); + /* KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, -1)->id); */ } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ @@ -437,7 +437,7 @@ void landlock_log_denial(const struct landlock_cred_security *const subject, return; /* Checks if the current exec was restricting itself. */ - if (subject->domain_exec & (1 << youngest_layer)) { + if (subject->domain_exec & BIT(youngest_layer)) { /* Ignores denials for the same execution. */ if (!youngest_denied->log_same_exec) return; diff --git a/security/landlock/id.c b/security/landlock/id.c index 11fab9259c15..56f7cc0fc744 100644 --- a/security/landlock/id.c +++ b/security/landlock/id.c @@ -7,6 +7,7 @@ #include <kunit/test.h> #include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/random.h> #include <linux/spinlock.h> @@ -25,7 +26,7 @@ static void __init init_id(atomic64_t *const counter, const u32 random_32bits) * Ensures sure 64-bit values are always used by user space (or may * fail with -EOVERFLOW), and makes this testable. */ - init = 1ULL << 32; + init = BIT_ULL(32); /* * Makes a large (2^32) boot-time value to limit ID collision in logs @@ -105,7 +106,7 @@ static u64 get_id_range(size_t number_of_ids, atomic64_t *const counter, * to get a new ID (e.g. a full landlock_restrict_self() call), and the * cost of draining all available IDs during the system's uptime. */ - random_4bits = random_4bits % (1 << 4); + random_4bits &= 0b1111; step = number_of_ids + random_4bits; /* It is safe to cast a signed atomic to an unsigned value. */ @@ -144,6 +145,19 @@ static void test_range1_rand1(struct kunit *const test) init + 2); } +static void test_range1_rand15(struct kunit *const test) +{ + atomic64_t counter; + u64 init; + + init = get_random_u32(); + atomic64_set(&counter, init); + KUNIT_EXPECT_EQ(test, get_id_range(1, &counter, 15), init); + KUNIT_EXPECT_EQ( + test, get_id_range(get_random_u8(), &counter, get_random_u8()), + init + 16); +} + static void test_range1_rand16(struct kunit *const test) { atomic64_t counter; @@ -196,6 +210,19 @@ static void test_range2_rand2(struct kunit *const test) init + 4); } +static void test_range2_rand15(struct kunit *const test) +{ + atomic64_t counter; + u64 init; + + init = get_random_u32(); + atomic64_set(&counter, init); + KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 15), init); + KUNIT_EXPECT_EQ( + test, get_id_range(get_random_u8(), &counter, get_random_u8()), + init + 17); +} + static void test_range2_rand16(struct kunit *const test) { atomic64_t counter; @@ -232,10 +259,12 @@ static struct kunit_case __refdata test_cases[] = { KUNIT_CASE(test_init_once), KUNIT_CASE(test_range1_rand0), KUNIT_CASE(test_range1_rand1), + KUNIT_CASE(test_range1_rand15), KUNIT_CASE(test_range1_rand16), KUNIT_CASE(test_range2_rand0), KUNIT_CASE(test_range2_rand1), KUNIT_CASE(test_range2_rand2), + KUNIT_CASE(test_range2_rand15), KUNIT_CASE(test_range2_rand16), {} /* clang-format on */ diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index b9561e3417ae..33eafb71e4f3 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -9,6 +9,7 @@ #include <asm/current.h> #include <linux/anon_inodes.h> +#include <linux/bitops.h> #include <linux/build_bug.h> #include <linux/capability.h> #include <linux/cleanup.h> @@ -563,7 +564,7 @@ SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32, new_llcred->domain = new_dom; #ifdef CONFIG_AUDIT - new_llcred->domain_exec |= 1 << (new_dom->num_layers - 1); + new_llcred->domain_exec |= BIT(new_dom->num_layers - 1); #endif /* CONFIG_AUDIT */ return commit_creds(new_cred); diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 47480eb2189b..e67a8ce4b64c 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -2158,8 +2158,8 @@ static int __init init_sel_fs(void) return err; } - selinux_null.dentry = d_hash_and_lookup(selinux_null.mnt->mnt_root, - &null_name); + selinux_null.dentry = try_lookup_noperm(&null_name, + selinux_null.mnt->mnt_root); if (IS_ERR(selinux_null.dentry)) { pr_err("selinuxfs: could not lookup null!\n"); err = PTR_ERR(selinux_null.dentry); diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 4683b9139c56..4ecb17bd5436 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1074,8 +1074,7 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) runtime->oss.params = 0; runtime->oss.prepare = 1; runtime->oss.buffer_used = 0; - if (runtime->dma_area) - snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes)); + snd_pcm_runtime_buffer_set_silence(runtime); runtime->oss.period_frames = snd_pcm_alsa_frames(substream, oss_period_size); diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 6c2b6a62d9d2..853ac5bb33ff 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -723,6 +723,17 @@ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) atomic_inc(&runtime->buffer_accessing); } +/* fill the PCM buffer with the current silence format; called from pcm_oss.c */ +void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) +{ + snd_pcm_buffer_access_lock(runtime); + if (runtime->dma_area) + snd_pcm_format_set_silence(runtime->format, runtime->dma_area, + bytes_to_samples(runtime, runtime->dma_bytes)); + snd_pcm_buffer_access_unlock(runtime); +} +EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence); + #if IS_ENABLED(CONFIG_SND_PCM_OSS) #define is_oss_stream(substream) ((substream)->oss.oss) #else diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 198c598a5393..880240924bfd 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -732,15 +732,21 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client, */ static int __deliver_to_subscribers(struct snd_seq_client *client, struct snd_seq_event *event, - struct snd_seq_client_port *src_port, - int atomic, int hop) + int port, int atomic, int hop) { + struct snd_seq_client_port *src_port; struct snd_seq_subscribers *subs; int err, result = 0, num_ev = 0; union __snd_seq_event event_saved; size_t saved_size; struct snd_seq_port_subs_info *grp; + if (port < 0) + return 0; + src_port = snd_seq_port_use_ptr(client, port); + if (!src_port) + return 0; + /* save original event record */ saved_size = snd_seq_event_packet_size(event); memcpy(&event_saved, event, saved_size); @@ -775,6 +781,7 @@ static int __deliver_to_subscribers(struct snd_seq_client *client, read_unlock(&grp->list_lock); else up_read(&grp->list_mutex); + snd_seq_port_unlock(src_port); memcpy(event, &event_saved, saved_size); return (result < 0) ? result : num_ev; } @@ -783,25 +790,32 @@ static int deliver_to_subscribers(struct snd_seq_client *client, struct snd_seq_event *event, int atomic, int hop) { - struct snd_seq_client_port *src_port; - int ret = 0, ret2; - - src_port = snd_seq_port_use_ptr(client, event->source.port); - if (src_port) { - ret = __deliver_to_subscribers(client, event, src_port, atomic, hop); - snd_seq_port_unlock(src_port); - } - - if (client->ump_endpoint_port < 0 || - event->source.port == client->ump_endpoint_port) - return ret; + int ret; +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) + int ret2; +#endif - src_port = snd_seq_port_use_ptr(client, client->ump_endpoint_port); - if (!src_port) + ret = __deliver_to_subscribers(client, event, + event->source.port, atomic, hop); +#if IS_ENABLED(CONFIG_SND_SEQ_UMP) + if (!snd_seq_client_is_ump(client) || client->ump_endpoint_port < 0) return ret; - ret2 = __deliver_to_subscribers(client, event, src_port, atomic, hop); - snd_seq_port_unlock(src_port); - return ret2 < 0 ? ret2 : ret; + /* If it's an event from EP port (and with a UMP group), + * deliver to subscribers of the corresponding UMP group port, too. + * Or, if it's from non-EP port, deliver to subscribers of EP port, too. + */ + if (event->source.port == client->ump_endpoint_port) + ret2 = __deliver_to_subscribers(client, event, + snd_seq_ump_group_port(event), + atomic, hop); + else + ret2 = __deliver_to_subscribers(client, event, + client->ump_endpoint_port, + atomic, hop); + if (ret2 < 0) + return ret2; +#endif + return ret; } /* deliver an event to the destination port(s). diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index ff7e558b4d51..db2f169cae11 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -1285,3 +1285,21 @@ int snd_seq_deliver_to_ump(struct snd_seq_client *source, else return cvt_to_ump_midi1(dest, dest_port, event, atomic, hop); } + +/* return the UMP group-port number of the event; + * return -1 if groupless or non-UMP event + */ +int snd_seq_ump_group_port(const struct snd_seq_event *event) +{ + const struct snd_seq_ump_event *ump_ev = + (const struct snd_seq_ump_event *)event; + unsigned char type; + + if (!snd_seq_ev_is_ump(event)) + return -1; + type = ump_message_type(ump_ev->ump[0]); + if (ump_is_groupless_msg(type)) + return -1; + /* group-port number starts from 1 */ + return ump_message_group(ump_ev->ump[0]) + 1; +} diff --git a/sound/core/seq/seq_ump_convert.h b/sound/core/seq/seq_ump_convert.h index 6c146d803280..4abf0a7637d7 100644 --- a/sound/core/seq/seq_ump_convert.h +++ b/sound/core/seq/seq_ump_convert.h @@ -18,5 +18,6 @@ int snd_seq_deliver_to_ump(struct snd_seq_client *source, struct snd_seq_client_port *dest_port, struct snd_seq_event *event, int atomic, int hop); +int snd_seq_ump_group_port(const struct snd_seq_event *event); #endif /* __SEQ_UMP_CONVERT_H */ diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index 8686adaf4531..d3511135f7d3 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -177,7 +177,7 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level, * sdw_intel_startup() is required for creation of devices and bus * startup */ -int sdw_intel_acpi_scan(acpi_handle *parent_handle, +int sdw_intel_acpi_scan(acpi_handle parent_handle, struct sdw_intel_acpi_info *info) { acpi_status status; diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c index c6c018b40c69..4e0693f0ab0f 100644 --- a/sound/pci/es1968.c +++ b/sound/pci/es1968.c @@ -1561,7 +1561,7 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream) struct snd_pcm_runtime *runtime = substream->runtime; struct es1968 *chip = snd_pcm_substream_chip(substream); struct esschan *es; - int apu1, apu2; + int err, apu1, apu2; apu1 = snd_es1968_alloc_apu_pair(chip, ESM_APU_PCM_CAPTURE); if (apu1 < 0) @@ -1605,7 +1605,9 @@ static int snd_es1968_capture_open(struct snd_pcm_substream *substream) runtime->hw = snd_es1968_capture; runtime->hw.buffer_bytes_max = runtime->hw.period_bytes_max = calc_available_memory_size(chip) - 1024; /* keep MIXBUF size */ - snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES); + err = snd_pcm_hw_constraint_pow2(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES); + if (err < 0) + return err; spin_lock_irq(&chip->substream_lock); list_add(&es->list, &chip->substream_list); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8a2b09e4a7d5..20ab1fb2195f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6830,7 +6830,10 @@ static void alc256_fixup_chromebook(struct hda_codec *codec, switch (action) { case HDA_FIXUP_ACT_PRE_PROBE: - spec->gen.suppress_auto_mute = 1; + if (codec->core.subsystem_id == 0x10280d76) + spec->gen.suppress_auto_mute = 0; + else + spec->gen.suppress_auto_mute = 1; spec->gen.suppress_auto_mic = 1; spec->en_3kpull_low = false; break; @@ -10882,9 +10885,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8e1a, "HP ZBook Firefly 14 G12A", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A), SND_PCI_QUIRK(0x103c, 0x8e1b, "HP EliteBook G12", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A), SND_PCI_QUIRK(0x103c, 0x8e1c, "HP EliteBook G12", ALC245_FIXUP_HP_ZBOOK_FIREFLY_G12A), + SND_PCI_QUIRK(0x103c, 0x8e1d, "HP ZBook X Gli 16 G12", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8e2c, "HP EliteBook 16 G12", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8e36, "HP 14 Enstrom OmniBook X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e37, "HP 16 Piston OmniBook X", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8e3a, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8e3b, "HP Agusta", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), @@ -11300,6 +11306,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38fd, "ThinkBook plus Gen5 Hybrid", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), + SND_PCI_QUIRK(0x17aa, 0x390d, "Lenovo Yoga Pro 7 14ASP10", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC), SND_PCI_QUIRK(0x17aa, 0x391f, "Yoga S990-16 pro Quad YC Quad", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3920, "Yoga S990-16 pro Quad VECO Quad", ALC287_FIXUP_TAS2781_I2C), diff --git a/sound/sh/Kconfig b/sound/sh/Kconfig index b75fbb3236a7..f5fa09d740b4 100644 --- a/sound/sh/Kconfig +++ b/sound/sh/Kconfig @@ -14,7 +14,7 @@ if SND_SUPERH config SND_AICA tristate "Dreamcast Yamaha AICA sound" - depends on SH_DREAMCAST + depends on SH_DREAMCAST && SH_DMA_API select SND_PCM select G2_DMA help diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig index 3033e2d3fe16..90e367586493 100644 --- a/sound/soc/mediatek/Kconfig +++ b/sound/soc/mediatek/Kconfig @@ -228,6 +228,7 @@ config SND_SOC_MT8188 config SND_SOC_MT8188_MT6359 tristate "ASoC Audio driver for MT8188 with MT6359 and I2S codecs" depends on SND_SOC_MT8188 && MTK_PMIC_WRAP + depends on SND_SOC_MT6359_ACCDET || !SND_SOC_MT6359_ACCDET depends on I2C select SND_SOC_MT6359 select SND_SOC_HDMI_CODEC diff --git a/sound/soc/sof/intel/hda-bus.c b/sound/soc/sof/intel/hda-bus.c index b1be03011d7e..6492e1cefbfb 100644 --- a/sound/soc/sof/intel/hda-bus.c +++ b/sound/soc/sof/intel/hda-bus.c @@ -76,7 +76,7 @@ void sof_hda_bus_init(struct snd_sof_dev *sdev, struct device *dev) snd_hdac_ext_bus_init(bus, dev, &bus_core_ops, sof_hda_ext_ops); - if (chip && chip->hw_ip_version == SOF_INTEL_ACE_2_0) + if (chip && chip->hw_ip_version >= SOF_INTEL_ACE_2_0) bus->use_pio_for_commands = true; #else snd_hdac_ext_bus_init(bus, dev, NULL, NULL); diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index b34e5fdf10f1..6a3932d90b43 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -1049,7 +1049,21 @@ static void hda_generic_machine_select(struct snd_sof_dev *sdev, if (!*mach && codec_num <= 2) { bool tplg_fixup = false; - hda_mach = snd_soc_acpi_intel_hda_machines; + /* + * make a local copy of the match array since we might + * be modifying it + */ + hda_mach = devm_kmemdup_array(sdev->dev, + snd_soc_acpi_intel_hda_machines, + 2, /* we have one entry + sentinel in the array */ + sizeof(snd_soc_acpi_intel_hda_machines[0]), + GFP_KERNEL); + if (!hda_mach) { + dev_err(bus->dev, + "%s: failed to duplicate the HDA match table\n", + __func__); + return; + } dev_info(bus->dev, "using HDA machine driver %s now\n", hda_mach->drv_name); diff --git a/sound/soc/sof/ipc4-control.c b/sound/soc/sof/ipc4-control.c index 576f407cd456..976a4794d610 100644 --- a/sound/soc/sof/ipc4-control.c +++ b/sound/soc/sof/ipc4-control.c @@ -531,6 +531,14 @@ static int sof_ipc4_bytes_ext_put(struct snd_sof_control *scontrol, return -EINVAL; } + /* Check header id */ + if (header.numid != SOF_CTRL_CMD_BINARY) { + dev_err_ratelimited(scomp->dev, + "Incorrect numid for bytes put %d\n", + header.numid); + return -EINVAL; + } + /* Verify the ABI header first */ if (copy_from_user(&abi_hdr, tlvd->tlv, sizeof(abi_hdr))) return -EFAULT; @@ -613,7 +621,8 @@ static int _sof_ipc4_bytes_ext_get(struct snd_sof_control *scontrol, if (data_size > size) return -ENOSPC; - header.numid = scontrol->comp_id; + /* Set header id and length */ + header.numid = SOF_CTRL_CMD_BINARY; header.length = data_size; if (copy_to_user(tlvd, &header, sizeof(struct snd_ctl_tlv))) diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c index 1a2841899ff5..c09b424ab863 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -798,7 +798,8 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm spcm->stream[stream].private = stream_priv; - if (!support_info) + /* Delay reporting is only supported on playback */ + if (!support_info || stream == SNDRV_PCM_STREAM_CAPTURE) continue; time_info = kzalloc(sizeof(*time_info), GFP_KERNEL); diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index dc9cb8324067..14aa8ecc4bc4 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -1063,7 +1063,7 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp, struct snd_sof_dai *dai) { struct snd_soc_card *card = scomp->card; - struct snd_soc_pcm_runtime *rtd; + struct snd_soc_pcm_runtime *rtd, *full, *partial; struct snd_soc_dai *cpu_dai; int stream; int i; @@ -1080,12 +1080,22 @@ static int sof_connect_dai_widget(struct snd_soc_component *scomp, else goto end; + full = NULL; + partial = NULL; list_for_each_entry(rtd, &card->rtd_list, list) { /* does stream match DAI link ? */ - if (!rtd->dai_link->stream_name || - !strstr(rtd->dai_link->stream_name, w->sname)) - continue; + if (rtd->dai_link->stream_name) { + if (!strcmp(rtd->dai_link->stream_name, w->sname)) { + full = rtd; + break; + } else if (strstr(rtd->dai_link->stream_name, w->sname)) { + partial = rtd; + } + } + } + rtd = full ? full : partial; + if (rtd) { for_each_rtd_cpu_dais(rtd, i, cpu_dai) { /* * Please create DAI widget in the right order diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 9112313a9dbc..dbbc9eb935a4 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2242,6 +2242,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */ QUIRK_FLAG_GET_SAMPLE_RATE), + DEVICE_FLG(0x0c45, 0x636b, /* Microdia JP001 USB Camera */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x0d8c, 0x0014, /* USB Audio Device */ QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ @@ -2250,6 +2252,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x1101, 0x0003, /* Audioengine D1 */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */ QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16), DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 28705ae67784..fd404729b115 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4968,6 +4968,9 @@ union bpf_attr { * the netns switch takes place from ingress to ingress without * going through the CPU's backlog queue. * + * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during + * the netns switch. + * * The *flags* argument is reserved and must be 0. The helper is * currently only supported for tc BPF program types at the * ingress hook and for veth and netkit target device types. The diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index ce32cb35007d..c4da34048ef8 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -364,7 +364,7 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr) "Invalid attribute (binary %s)", policy->name); return -1; case YNL_PT_NUL_STR: - if ((!policy->len || len <= policy->len) && !data[len - 1]) + if (len && (!policy->len || len <= policy->len) && !data[len - 1]) break; yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, "Invalid attribute (string %s)", policy->name); diff --git a/tools/net/ynl/pyynl/ethtool.py b/tools/net/ynl/pyynl/ethtool.py index af7fddd7b085..cab6b576c876 100755 --- a/tools/net/ynl/pyynl/ethtool.py +++ b/tools/net/ynl/pyynl/ethtool.py @@ -338,16 +338,24 @@ def main(): print('Capabilities:') [print(f'\t{v}') for v in bits_to_dict(tsinfo['timestamping'])] - print(f'PTP Hardware Clock: {tsinfo["phc-index"]}') + print(f'PTP Hardware Clock: {tsinfo.get("phc-index", "none")}') - print('Hardware Transmit Timestamp Modes:') - [print(f'\t{v}') for v in bits_to_dict(tsinfo['tx-types'])] + if 'tx-types' in tsinfo: + print('Hardware Transmit Timestamp Modes:') + [print(f'\t{v}') for v in bits_to_dict(tsinfo['tx-types'])] + else: + print('Hardware Transmit Timestamp Modes: none') + + if 'rx-filters' in tsinfo: + print('Hardware Receive Filter Modes:') + [print(f'\t{v}') for v in bits_to_dict(tsinfo['rx-filters'])] + else: + print('Hardware Receive Filter Modes: none') - print('Hardware Receive Filter Modes:') - [print(f'\t{v}') for v in bits_to_dict(tsinfo['rx-filters'])] + if 'stats' in tsinfo and tsinfo['stats']: + print('Statistics:') + [print(f'\t{k}: {v}') for k, v in tsinfo['stats'].items()] - print('Statistics:') - [print(f'\t{k}: {v}') for k, v in tsinfo['stats'].items()] return print(f'Settings for {args.device}:') diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index 30c0a34b2784..a7f08edbc235 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -1143,10 +1143,9 @@ class Family(SpecFamily): self.pure_nested_structs[nested].request = True if attr in rs_members['reply']: self.pure_nested_structs[nested].reply = True - - if spec.is_multi_val(): - child = self.pure_nested_structs.get(nested) - child.in_multi_val = True + if spec.is_multi_val(): + child = self.pure_nested_structs.get(nested) + child.in_multi_val = True self._sort_pure_types() diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 3ce7b54003c2..687c5eafb49a 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -189,6 +189,15 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec op2 = ins.opcode.bytes[1]; op3 = ins.opcode.bytes[2]; + /* + * XXX hack, decoder is buggered and thinks 0xea is 7 bytes long. + */ + if (op1 == 0xea) { + insn->len = 1; + insn->type = INSN_BUG; + return 0; + } + if (ins.rex_prefix.nbytes) { rex = ins.rex_prefix.bytes[0]; rex_w = X86_REX_W(rex) >> 3; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 3a411064fa34..b21b12ec88d9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -227,6 +227,7 @@ static bool is_rust_noreturn(const struct symbol *func) str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference") || str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || + str_ends_with(func->name, "_7___rustc17rust_begin_unwind") || strstr(func->name, "_4core9panicking13assert_failed") || strstr(func->name, "_4core9panicking11panic_const24panic_const_") || (strstr(func->name, "_4core5slice5index24slice_") && diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c77c8c8e3d9b..80fb84fa3cfc 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -121,6 +121,7 @@ TARGETS += user_events TARGETS += vDSO TARGETS += mm TARGETS += x86 +TARGETS += x86/bugs TARGETS += zram #Please keep the TARGETS list alphabetically sorted # Run "make quicktest=1 run_tests" or diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64 index 3720b7611523..e1495a4bbc99 100644 --- a/tools/testing/selftests/bpf/config.aarch64 +++ b/tools/testing/selftests/bpf/config.aarch64 @@ -158,7 +158,6 @@ CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_TUN=y CONFIG_UNIX=y CONFIG_UPROBES=y -CONFIG_USELIB=y CONFIG_USER_NS=y CONFIG_VETH=y CONFIG_VLAN_8021Q=y diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x index 706931a8c2c6..26c3bc2ce11d 100644 --- a/tools/testing/selftests/bpf/config.s390x +++ b/tools/testing/selftests/bpf/config.s390x @@ -128,7 +128,6 @@ CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_TUN=y CONFIG_UNIX=y CONFIG_UPROBES=y -CONFIG_USELIB=y CONFIG_USER_NS=y CONFIG_VETH=y CONFIG_VLAN_8021Q=y diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c index 137b2364a082..9984413be9f0 100644 --- a/tools/testing/selftests/coredump/stackdump_test.c +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -1,14 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 #include <fcntl.h> +#include <inttypes.h> #include <libgen.h> #include <linux/limits.h> #include <pthread.h> #include <string.h> +#include <sys/mount.h> #include <sys/resource.h> +#include <sys/stat.h> +#include <sys/socket.h> +#include <sys/un.h> #include <unistd.h> #include "../kselftest_harness.h" +#include "../pidfd/pidfd.h" #define STACKDUMP_FILE "stack_values" #define STACKDUMP_SCRIPT "stackdump" @@ -35,6 +41,7 @@ static void crashing_child(void) FIXTURE(coredump) { char original_core_pattern[256]; + pid_t pid_coredump_server; }; FIXTURE_SETUP(coredump) @@ -44,6 +51,7 @@ FIXTURE_SETUP(coredump) char *dir; int ret; + self->pid_coredump_server = -ESRCH; file = fopen("/proc/sys/kernel/core_pattern", "r"); ASSERT_NE(NULL, file); @@ -61,10 +69,17 @@ FIXTURE_TEARDOWN(coredump) { const char *reason; FILE *file; - int ret; + int ret, status; unlink(STACKDUMP_FILE); + if (self->pid_coredump_server > 0) { + kill(self->pid_coredump_server, SIGTERM); + waitpid(self->pid_coredump_server, &status, 0); + } + unlink("/tmp/coredump.file"); + unlink("/tmp/coredump.socket"); + file = fopen("/proc/sys/kernel/core_pattern", "w"); if (!file) { reason = "Unable to open core_pattern"; @@ -89,14 +104,14 @@ fail: fprintf(stderr, "Failed to cleanup stackdump test: %s\n", reason); } -TEST_F(coredump, stackdump) +TEST_F_TIMEOUT(coredump, stackdump, 120) { struct sigaction action = {}; unsigned long long stack; char *test_dir, *line; size_t line_length; char buf[PATH_MAX]; - int ret, i; + int ret, i, status; FILE *file; pid_t pid; @@ -129,6 +144,10 @@ TEST_F(coredump, stackdump) /* * Step 3: Wait for the stackdump script to write the stack pointers to the stackdump file */ + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_TRUE(WCOREDUMP(status)); + for (i = 0; i < 10; ++i) { file = fopen(STACKDUMP_FILE, "r"); if (file) @@ -138,14 +157,466 @@ TEST_F(coredump, stackdump) ASSERT_NE(file, NULL); /* Step 4: Make sure all stack pointer values are non-zero */ + line = NULL; for (i = 0; -1 != getline(&line, &line_length, file); ++i) { stack = strtoull(line, NULL, 10); ASSERT_NE(stack, 0); } + free(line); ASSERT_EQ(i, 1 + NUM_THREAD_SPAWN); fclose(file); } +TEST_F(coredump, socket) +{ + int fd, pidfd, ret, status; + FILE *file; + pid_t pid, pid_coredump_server; + struct stat st; + char core_file[PATH_MAX]; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + const struct sockaddr_un coredump_sk = { + .sun_family = AF_UNIX, + .sun_path = "/tmp/coredump.socket", + }; + size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) + + sizeof("/tmp/coredump.socket"); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + ASSERT_NE(file, NULL); + + ret = fprintf(file, "@/tmp/coredump.socket"); + ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); + ASSERT_EQ(fclose(file), 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file; + socklen_t fd_peer_pidfd_len; + + close(ipc_sockets[0]); + + fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0); + if (fd_server < 0) + _exit(EXIT_FAILURE); + + ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len); + if (ret < 0) { + fprintf(stderr, "Failed to bind coredump socket\n"); + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + ret = listen(fd_server, 1); + if (ret < 0) { + fprintf(stderr, "Failed to listen on coredump socket\n"); + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) { + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) { + fprintf(stderr, "Failed to accept coredump socket connection\n"); + close(fd_server); + _exit(EXIT_FAILURE); + } + + fd_peer_pidfd_len = sizeof(fd_peer_pidfd); + ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD, + &fd_peer_pidfd, &fd_peer_pidfd_len); + if (ret < 0) { + fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n"); + close(fd_coredump); + close(fd_server); + _exit(EXIT_FAILURE); + } + + memset(&info, 0, sizeof(info)); + info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; + ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info); + if (ret < 0) { + fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n"); + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + _exit(EXIT_FAILURE); + } + + if (!(info.mask & PIDFD_INFO_COREDUMP)) { + fprintf(stderr, "Missing coredump information from coredumping task\n"); + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + _exit(EXIT_FAILURE); + } + + if (!(info.coredump_mask & PIDFD_COREDUMPED)) { + fprintf(stderr, "Received connection from non-coredumping task\n"); + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + _exit(EXIT_FAILURE); + } + + fd_core_file = creat("/tmp/coredump.file", 0644); + if (fd_core_file < 0) { + fprintf(stderr, "Failed to create coredump file\n"); + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + _exit(EXIT_FAILURE); + } + + for (;;) { + char buffer[4096]; + ssize_t bytes_read, bytes_write; + + bytes_read = read(fd_coredump, buffer, sizeof(buffer)); + if (bytes_read < 0) { + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + close(fd_core_file); + _exit(EXIT_FAILURE); + } + + if (bytes_read == 0) + break; + + bytes_write = write(fd_core_file, buffer, bytes_read); + if (bytes_read != bytes_write) { + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + close(fd_core_file); + _exit(EXIT_FAILURE); + } + } + + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + close(fd_core_file); + _exit(EXIT_SUCCESS); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_TRUE(WCOREDUMP(status)); + + info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; + ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0); + + waitpid(pid_coredump_server, &status, 0); + self->pid_coredump_server = -ESRCH; + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); + + ASSERT_EQ(stat("/tmp/coredump.file", &st), 0); + ASSERT_GT(st.st_size, 0); + /* + * We should somehow validate the produced core file. + * For now just allow for visual inspection + */ + system("file /tmp/coredump.file"); +} + +TEST_F(coredump, socket_detect_userspace_client) +{ + int fd, pidfd, ret, status; + FILE *file; + pid_t pid, pid_coredump_server; + struct stat st; + char core_file[PATH_MAX]; + struct pidfd_info info = {}; + int ipc_sockets[2]; + char c; + const struct sockaddr_un coredump_sk = { + .sun_family = AF_UNIX, + .sun_path = "/tmp/coredump.socket", + }; + size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) + + sizeof("/tmp/coredump.socket"); + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + ASSERT_NE(file, NULL); + + ret = fprintf(file, "@/tmp/coredump.socket"); + ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); + ASSERT_EQ(fclose(file), 0); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + int fd_server, fd_coredump, fd_peer_pidfd, fd_core_file; + socklen_t fd_peer_pidfd_len; + + close(ipc_sockets[0]); + + fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0); + if (fd_server < 0) + _exit(EXIT_FAILURE); + + ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len); + if (ret < 0) { + fprintf(stderr, "Failed to bind coredump socket\n"); + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + ret = listen(fd_server, 1); + if (ret < 0) { + fprintf(stderr, "Failed to listen on coredump socket\n"); + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) { + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + close(ipc_sockets[1]); + + fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC); + if (fd_coredump < 0) { + fprintf(stderr, "Failed to accept coredump socket connection\n"); + close(fd_server); + _exit(EXIT_FAILURE); + } + + fd_peer_pidfd_len = sizeof(fd_peer_pidfd); + ret = getsockopt(fd_coredump, SOL_SOCKET, SO_PEERPIDFD, + &fd_peer_pidfd, &fd_peer_pidfd_len); + if (ret < 0) { + fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n"); + close(fd_coredump); + close(fd_server); + _exit(EXIT_FAILURE); + } + + memset(&info, 0, sizeof(info)); + info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; + ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, &info); + if (ret < 0) { + fprintf(stderr, "Failed to retrieve pidfd info from peer pidfd for coredump socket connection\n"); + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + _exit(EXIT_FAILURE); + } + + if (!(info.mask & PIDFD_INFO_COREDUMP)) { + fprintf(stderr, "Missing coredump information from coredumping task\n"); + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + _exit(EXIT_FAILURE); + } + + if (info.coredump_mask & PIDFD_COREDUMPED) { + fprintf(stderr, "Received unexpected connection from coredumping task\n"); + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + _exit(EXIT_FAILURE); + } + + close(fd_coredump); + close(fd_server); + close(fd_peer_pidfd); + close(fd_core_file); + _exit(EXIT_SUCCESS); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + int fd_socket; + ssize_t ret; + + fd_socket = socket(AF_UNIX, SOCK_STREAM, 0); + if (fd_socket < 0) + _exit(EXIT_FAILURE); + + + ret = connect(fd_socket, (const struct sockaddr *)&coredump_sk, coredump_sk_len); + if (ret < 0) + _exit(EXIT_FAILURE); + + (void *)write(fd_socket, &(char){ 0 }, 1); + close(fd_socket); + _exit(EXIT_SUCCESS); + } + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); + + info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP; + ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0); + ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0); + ASSERT_EQ((info.coredump_mask & PIDFD_COREDUMPED), 0); + + waitpid(pid_coredump_server, &status, 0); + self->pid_coredump_server = -ESRCH; + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); + + ASSERT_NE(stat("/tmp/coredump.file", &st), 0); + ASSERT_EQ(errno, ENOENT); +} + +TEST_F(coredump, socket_enoent) +{ + int pidfd, ret, status; + FILE *file; + pid_t pid; + char core_file[PATH_MAX]; + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + ASSERT_NE(file, NULL); + + ret = fprintf(file, "@/tmp/coredump.socket"); + ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); + ASSERT_EQ(fclose(file), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_FALSE(WCOREDUMP(status)); +} + +TEST_F(coredump, socket_no_listener) +{ + int pidfd, ret, status; + FILE *file; + pid_t pid, pid_coredump_server; + int ipc_sockets[2]; + char c; + const struct sockaddr_un coredump_sk = { + .sun_family = AF_UNIX, + .sun_path = "/tmp/coredump.socket", + }; + size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) + + sizeof("/tmp/coredump.socket"); + + ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets); + ASSERT_EQ(ret, 0); + + file = fopen("/proc/sys/kernel/core_pattern", "w"); + ASSERT_NE(file, NULL); + + ret = fprintf(file, "@/tmp/coredump.socket"); + ASSERT_EQ(ret, strlen("@/tmp/coredump.socket")); + ASSERT_EQ(fclose(file), 0); + + pid_coredump_server = fork(); + ASSERT_GE(pid_coredump_server, 0); + if (pid_coredump_server == 0) { + int fd_server; + socklen_t fd_peer_pidfd_len; + + close(ipc_sockets[0]); + + fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0); + if (fd_server < 0) + _exit(EXIT_FAILURE); + + ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len); + if (ret < 0) { + fprintf(stderr, "Failed to bind coredump socket\n"); + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + if (write_nointr(ipc_sockets[1], "1", 1) < 0) { + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_FAILURE); + } + + close(fd_server); + close(ipc_sockets[1]); + _exit(EXIT_SUCCESS); + } + self->pid_coredump_server = pid_coredump_server; + + EXPECT_EQ(close(ipc_sockets[1]), 0); + ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1); + EXPECT_EQ(close(ipc_sockets[0]), 0); + + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) + crashing_child(); + + pidfd = sys_pidfd_open(pid, 0); + ASSERT_GE(pidfd, 0); + + waitpid(pid, &status, 0); + ASSERT_TRUE(WIFSIGNALED(status)); + ASSERT_FALSE(WCOREDUMP(status)); + + waitpid(pid_coredump_server, &status, 0); + self->pid_coredump_server = -ESRCH; + ASSERT_TRUE(WIFEXITED(status)); + ASSERT_EQ(WEXITSTATUS(status), 0); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index 2bf14ac2b8c6..9d48004ff1a1 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -431,6 +431,22 @@ static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6) return 0; } +static struct netdev_queue_id *create_queues(void) +{ + struct netdev_queue_id *queues; + size_t i = 0; + + queues = calloc(num_queues, sizeof(*queues)); + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.id = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].id = start_queue + i; + } + + return queues; +} + int do_server(struct memory_buffer *mem) { char ctrl_data[sizeof(int) * 20000]; @@ -448,7 +464,6 @@ int do_server(struct memory_buffer *mem) char buffer[256]; int socket_fd; int client_fd; - size_t i = 0; int ret; ret = parse_address(server_ip, atoi(port), &server_sin); @@ -471,16 +486,7 @@ int do_server(struct memory_buffer *mem) sleep(1); - queues = malloc(sizeof(*queues) * num_queues); - - for (i = 0; i < num_queues; i++) { - queues[i]._present.type = 1; - queues[i]._present.id = 1; - queues[i].type = NETDEV_QUEUE_TYPE_RX; - queues[i].id = start_queue + i; - } - - if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) error(1, 0, "Failed to bind\n"); tmp_mem = malloc(mem->size); @@ -545,7 +551,6 @@ int do_server(struct memory_buffer *mem) goto cleanup; } - i++; for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { if (cm->cmsg_level != SOL_SOCKET || (cm->cmsg_type != SCM_DEVMEM_DMABUF && @@ -630,10 +635,8 @@ cleanup: void run_devmem_tests(void) { - struct netdev_queue_id *queues; struct memory_buffer *mem; struct ynl_sock *ys; - size_t i = 0; mem = provider->alloc(getpagesize() * NUM_PAGES); @@ -641,38 +644,24 @@ void run_devmem_tests(void) if (configure_rss()) error(1, 0, "rss error\n"); - queues = calloc(num_queues, sizeof(*queues)); - if (configure_headersplit(1)) error(1, 0, "Failed to configure header split\n"); - if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + if (!bind_rx_queue(ifindex, mem->fd, + calloc(num_queues, sizeof(struct netdev_queue_id)), + num_queues, &ys)) error(1, 0, "Binding empty queues array should have failed\n"); - for (i = 0; i < num_queues; i++) { - queues[i]._present.type = 1; - queues[i]._present.id = 1; - queues[i].type = NETDEV_QUEUE_TYPE_RX; - queues[i].id = start_queue + i; - } - if (configure_headersplit(0)) error(1, 0, "Failed to configure header split\n"); - if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + if (!bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) error(1, 0, "Configure dmabuf with header split off should have failed\n"); if (configure_headersplit(1)) error(1, 0, "Failed to configure header split\n"); - for (i = 0; i < num_queues; i++) { - queues[i]._present.type = 1; - queues[i]._present.id = 1; - queues[i].type = NETDEV_QUEUE_TYPE_RX; - queues[i].id = start_queue + i; - } - - if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) error(1, 0, "Failed to bind\n"); /* Deactivating a bound queue should not be legal */ diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py index 4b6822866066..af8df2313a3b 100755 --- a/tools/testing/selftests/drivers/net/ping.py +++ b/tools/testing/selftests/drivers/net/ping.py @@ -9,11 +9,11 @@ from lib.py import EthtoolFamily, NetDrvEpEnv from lib.py import bkg, cmd, wait_port_listen, rand_port from lib.py import defer, ethtool, ip -remote_ifname="" no_sleep=False def _test_v4(cfg) -> None: - cfg.require_ipver("4") + if not cfg.addr_v["4"]: + return cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"]) cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote) @@ -21,7 +21,8 @@ def _test_v4(cfg) -> None: cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote) def _test_v6(cfg) -> None: - cfg.require_ipver("6") + if not cfg.addr_v["6"]: + return cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"]) cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote) @@ -57,7 +58,7 @@ def _set_offload_checksum(cfg, netnl, on) -> None: def _set_xdp_generic_sb_on(cfg) -> None: prog = cfg.net_lib_dir / "xdp_dummy.bpf.o" - cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) + cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote) cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True) defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off") @@ -66,8 +67,8 @@ def _set_xdp_generic_sb_on(cfg) -> None: def _set_xdp_generic_mb_on(cfg) -> None: prog = cfg.net_lib_dir / "xdp_dummy.bpf.o" - cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote) - defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote) + cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote) + defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote) ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog)) defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off") @@ -76,7 +77,7 @@ def _set_xdp_generic_mb_on(cfg) -> None: def _set_xdp_native_sb_on(cfg) -> None: prog = cfg.net_lib_dir / "xdp_dummy.bpf.o" - cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) + cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote) cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True) defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0] @@ -93,8 +94,8 @@ def _set_xdp_native_sb_on(cfg) -> None: def _set_xdp_native_mb_on(cfg) -> None: prog = cfg.net_lib_dir / "xdp_dummy.bpf.o" - cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote) - defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote) + cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote) + defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote) try: cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True) defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") @@ -112,18 +113,15 @@ def _set_xdp_offload_on(cfg) -> None: except Exception as e: raise KsftSkipEx('device does not support offloaded XDP') defer(ip, f"link set dev {cfg.ifname} xdpoffload off") - cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) + cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote) if no_sleep != True: time.sleep(10) def get_interface_info(cfg) -> None: - global remote_ifname global no_sleep - remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout - remote_ifname = remote_info.rstrip('\n') - if remote_ifname == "": + if cfg.remote_ifname == "": raise KsftFailEx('Can not get remote interface') local_info = ip("-d link show %s" % (cfg.ifname), json=True)[0] if 'parentbus' in local_info and local_info['parentbus'] == "netdevsim": @@ -136,15 +134,25 @@ def set_interface_init(cfg) -> None: cmd(f"ip link set dev {cfg.ifname} xdp off ", shell=True) cmd(f"ip link set dev {cfg.ifname} xdpgeneric off ", shell=True) cmd(f"ip link set dev {cfg.ifname} xdpoffload off", shell=True) - cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote) + cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote) + +def test_default_v4(cfg, netnl) -> None: + cfg.require_ipver("4") -def test_default(cfg, netnl) -> None: _set_offload_checksum(cfg, netnl, "off") _test_v4(cfg) - _test_v6(cfg) _test_tcp(cfg) _set_offload_checksum(cfg, netnl, "on") _test_v4(cfg) + _test_tcp(cfg) + +def test_default_v6(cfg, netnl) -> None: + cfg.require_ipver("6") + + _set_offload_checksum(cfg, netnl, "off") + _test_v6(cfg) + _test_tcp(cfg) + _set_offload_checksum(cfg, netnl, "on") _test_v6(cfg) _test_tcp(cfg) @@ -202,7 +210,8 @@ def main() -> None: with NetDrvEpEnv(__file__) as cfg: get_interface_info(cfg) set_interface_init(cfg) - ksft_run([test_default, + ksft_run([test_default_v4, + test_default_v6, test_xdp_generic_sb, test_xdp_generic_mb, test_xdp_native_sb, diff --git a/tools/testing/selftests/filesystems/.gitignore b/tools/testing/selftests/filesystems/.gitignore index 828b66a10c63..7afa58e2bb20 100644 --- a/tools/testing/selftests/filesystems/.gitignore +++ b/tools/testing/selftests/filesystems/.gitignore @@ -2,3 +2,4 @@ dnotify_test devpts_pts file_stressor +anon_inode_test diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile index 66305fc34c60..b02326193fee 100644 --- a/tools/testing/selftests/filesystems/Makefile +++ b/tools/testing/selftests/filesystems/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := devpts_pts file_stressor +TEST_GEN_PROGS := devpts_pts file_stressor anon_inode_test TEST_GEN_PROGS_EXTENDED := dnotify_test include ../lib.mk diff --git a/tools/testing/selftests/filesystems/anon_inode_test.c b/tools/testing/selftests/filesystems/anon_inode_test.c new file mode 100644 index 000000000000..e8e0ef1460d2 --- /dev/null +++ b/tools/testing/selftests/filesystems/anon_inode_test.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ + +#include <fcntl.h> +#include <stdio.h> +#include <sys/stat.h> + +#include "../kselftest_harness.h" +#include "overlayfs/wrappers.h" + +TEST(anon_inode_no_chown) +{ + int fd_context; + + fd_context = sys_fsopen("tmpfs", 0); + ASSERT_GE(fd_context, 0); + + ASSERT_LT(fchown(fd_context, 1234, 5678), 0); + ASSERT_EQ(errno, EOPNOTSUPP); + + EXPECT_EQ(close(fd_context), 0); +} + +TEST(anon_inode_no_chmod) +{ + int fd_context; + + fd_context = sys_fsopen("tmpfs", 0); + ASSERT_GE(fd_context, 0); + + ASSERT_LT(fchmod(fd_context, 0777), 0); + ASSERT_EQ(errno, EOPNOTSUPP); + + EXPECT_EQ(close(fd_context), 0); +} + +TEST(anon_inode_no_exec) +{ + int fd_context; + + fd_context = sys_fsopen("tmpfs", 0); + ASSERT_GE(fd_context, 0); + + ASSERT_LT(execveat(fd_context, "", NULL, NULL, AT_EMPTY_PATH), 0); + ASSERT_EQ(errno, EACCES); + + EXPECT_EQ(close(fd_context), 0); +} + +TEST(anon_inode_no_open) +{ + int fd_context; + + fd_context = sys_fsopen("tmpfs", 0); + ASSERT_GE(fd_context, 0); + + ASSERT_GE(dup2(fd_context, 500), 0); + ASSERT_EQ(close(fd_context), 0); + fd_context = 500; + + ASSERT_LT(open("/proc/self/fd/500", 0), 0); + ASSERT_EQ(errno, ENXIO); + + EXPECT_EQ(close(fd_context), 0); +} + +TEST_HARNESS_MAIN + diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 322b9d3b0125..57708de2075d 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -129,10 +129,10 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0), REG_FTR_BITS(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 1), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 1), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 1), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 1), REG_FTR_END, }; diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 2c3a0eb6b22d..9bc4591c7b16 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, int compaction_index = 0; char nr_hugepages[20] = {0}; char init_nr_hugepages[24] = {0}; + char target_nr_hugepages[24] = {0}; + int slen; snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), "%lu", initial_nr_hugepages); @@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, goto out; } - /* Request a large number of huge pages. The Kernel will allocate - as much as it can */ - if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + /* + * Request huge pages for about half of the free memory. The Kernel + * will allocate as much as it can, and we expect it will get at least 1/3 + */ + nr_hugepages_ul = mem_free / hugepage_size / 2; + snprintf(target_nr_hugepages, sizeof(target_nr_hugepages), + "%lu", nr_hugepages_ul); + + slen = strlen(target_nr_hugepages); + if (write(fd, target_nr_hugepages, slen) != slen) { + ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n", + nr_hugepages_ul, strerror(errno)); goto close_fd; } diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index b3d0e2771096..eba43ead13ae 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -271,12 +271,16 @@ FIXTURE_SETUP(guard_regions) self->page_size = (unsigned long)sysconf(_SC_PAGESIZE); setup_sighandler(); - if (variant->backing == ANON_BACKED) + switch (variant->backing) { + case ANON_BACKED: return; - - self->fd = open_file( - variant->backing == SHMEM_BACKED ? "/tmp/" : "", - self->path); + case LOCAL_FILE_BACKED: + self->fd = open_file("", self->path); + break; + case SHMEM_BACKED: + self->fd = memfd_create(self->path, 0); + break; + } /* We truncate file to at least 100 pages, tests can modify as needed. */ ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0); @@ -1696,7 +1700,7 @@ TEST_F(guard_regions, readonly_file) char *ptr; int i; - if (variant->backing == ANON_BACKED) + if (variant->backing != LOCAL_FILE_BACKED) SKIP(return, "Read-only test specific to file-backed"); /* Map shared so we can populate with pattern, populate it, unmap. */ diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 1bad310d282a..17bf2d1b0192 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -3,6 +3,8 @@ #ifndef _PKEYS_POWERPC_H #define _PKEYS_POWERPC_H +#include <sys/stat.h> + #ifndef SYS_pkey_alloc # define SYS_pkey_alloc 384 # define SYS_pkey_free 385 @@ -102,8 +104,18 @@ static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) return; } +#define REPEAT_8(s) s s s s s s s s +#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \ + REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) +#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \ + REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) +#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \ + REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) +#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \ + REPEAT_4096(s) REPEAT_4096(s) + /* 4-byte instructions * 16384 = 64K page */ -#define __page_o_noops() asm(".rept 16384 ; nop; .endr") +#define __page_o_noops() asm(REPEAT_16384("nop\n")) static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c index ca4ad0d44ab2..255b332f7a08 100644 --- a/tools/testing/selftests/mm/pkey_util.c +++ b/tools/testing/selftests/mm/pkey_util.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#define __SANE_USERSPACE_TYPES__ #include <sys/syscall.h> #include <unistd.h> diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 124078b56fa4..70a38f485d4d 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -31,6 +31,7 @@ TEST_PROGS += veth.sh TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh +TEST_PROGS += gre_ipv6_lladdr.sh TEST_PROGS += cmsg_so_mark.sh TEST_PROGS += cmsg_so_priority.sh TEST_PROGS += test_so_rcv.sh diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh new file mode 100755 index 000000000000..5b34f6e1f831 --- /dev/null +++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh @@ -0,0 +1,177 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source ./lib.sh + +PAUSE_ON_FAIL="no" + +# The trap function handler +# +exit_cleanup_all() +{ + cleanup_all_ns + + exit "${EXIT_STATUS}" +} + +# Add fake IPv4 and IPv6 networks on the loopback device, to be used as +# underlay by future GRE devices. +# +setup_basenet() +{ + ip -netns "${NS0}" link set dev lo up + ip -netns "${NS0}" address add dev lo 192.0.2.10/24 + ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad +} + +# Check if network device has an IPv6 link-local address assigned. +# +# Parameters: +# +# * $1: The network device to test +# * $2: An extra regular expression that should be matched (to verify the +# presence of extra attributes) +# * $3: The expected return code from grep (to allow checking the absence of +# a link-local address) +# * $4: The user visible name for the scenario being tested +# +check_ipv6_ll_addr() +{ + local DEV="$1" + local EXTRA_MATCH="$2" + local XRET="$3" + local MSG="$4" + + RET=0 + set +e + ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}" + check_err_fail "${XRET}" $? "" + log_test "${MSG}" + set -e +} + +# Create a GRE device and verify that it gets an IPv6 link-local address as +# expected. +# +# Parameters: +# +# * $1: The device type (gre, ip6gre, gretap or ip6gretap) +# * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any") +# * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any") +# * $4: The IPv6 interface identifier generation mode to use for the GRE +# device (eui64, none, stable-privacy or random). +# +test_gre_device() +{ + local GRE_TYPE="$1" + local LOCAL_IP="$2" + local REMOTE_IP="$3" + local MODE="$4" + local ADDR_GEN_MODE + local MATCH_REGEXP + local MSG + + ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}" + + case "${MODE}" in + "eui64") + ADDR_GEN_MODE=0 + MATCH_REGEXP="" + MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}" + XRET=0 + ;; + "none") + ADDR_GEN_MODE=1 + MATCH_REGEXP="" + MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}" + XRET=1 # No link-local address should be generated + ;; + "stable-privacy") + ADDR_GEN_MODE=2 + MATCH_REGEXP="stable-privacy" + MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}" + XRET=0 + # Initialise stable_secret (required for stable-privacy mode) + ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd" + ;; + "random") + ADDR_GEN_MODE=3 + MATCH_REGEXP="stable-privacy" + MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}" + XRET=0 + ;; + esac + + # Check that IPv6 link-local address is generated when device goes up + ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}" + ip -netns "${NS0}" link set dev gretest up + check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}" + + # Now disable link-local address generation + ip -netns "${NS0}" link set dev gretest down + ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1 + ip -netns "${NS0}" link set dev gretest up + + # Check that link-local address generation works when re-enabled while + # the device is already up + ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}" + check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}" + + ip -netns "${NS0}" link del dev gretest +} + +test_gre4() +{ + local GRE_TYPE + local MODE + + for GRE_TYPE in "gre" "gretap"; do + printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n" + + for MODE in "eui64" "none" "stable-privacy" "random"; do + test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}" + test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}" + test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}" + done + done +} + +test_gre6() +{ + local GRE_TYPE + local MODE + + for GRE_TYPE in "ip6gre" "ip6gretap"; do + printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n" + + for MODE in "eui64" "none" "stable-privacy" "random"; do + test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}" + test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}" + test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}" + done + done +} + +usage() +{ + echo "Usage: $0 [-p]" + exit 1 +} + +while getopts :p o +do + case $o in + p) PAUSE_ON_FAIL="yes";; + *) usage;; + esac +done + +setup_ns NS0 + +set -e +trap exit_cleanup_all EXIT + +setup_basenet + +test_gre4 +test_gre6 diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 55bcf81a2b9a..efd74063126e 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -131,6 +131,26 @@ #define PIDFD_INFO_EXIT (1UL << 3) /* Always returned if available, even if not requested */ #endif +#ifndef PIDFD_INFO_COREDUMP +#define PIDFD_INFO_COREDUMP (1UL << 4) +#endif + +#ifndef PIDFD_COREDUMPED +#define PIDFD_COREDUMPED (1U << 0) /* Did crash and... */ +#endif + +#ifndef PIDFD_COREDUMP_SKIP +#define PIDFD_COREDUMP_SKIP (1U << 1) /* coredumping generation was skipped. */ +#endif + +#ifndef PIDFD_COREDUMP_USER +#define PIDFD_COREDUMP_USER (1U << 2) /* coredump was done as the user. */ +#endif + +#ifndef PIDFD_COREDUMP_ROOT +#define PIDFD_COREDUMP_ROOT (1U << 3) /* coredump was done as root. */ +#endif + #ifndef PIDFD_THREAD #define PIDFD_THREAD O_EXCL #endif @@ -150,6 +170,8 @@ struct pidfd_info { __u32 fsuid; __u32 fsgid; __s32 exit_code; + __u32 coredump_mask; + __u32 __spare1; }; /* diff --git a/tools/testing/selftests/pidfd/pidfd_info_test.c b/tools/testing/selftests/pidfd/pidfd_info_test.c index 1758a1b0457b..a0eb6e81eaa2 100644 --- a/tools/testing/selftests/pidfd/pidfd_info_test.c +++ b/tools/testing/selftests/pidfd/pidfd_info_test.c @@ -299,6 +299,7 @@ TEST_F(pidfd_info, thread_group) /* Opening a thread as a thread-group leader must fail. */ pidfd_thread = sys_pidfd_open(pid_thread, 0); ASSERT_LT(pidfd_thread, 0); + ASSERT_EQ(errno, ENOENT); /* Opening a thread as a PIDFD_THREAD must succeed. */ pidfd_thread = sys_pidfd_open(pid_thread, PIDFD_THREAD); @@ -362,9 +363,9 @@ TEST_F(pidfd_info, thread_group) ASSERT_EQ(ioctl(pidfd_leader, PIDFD_GET_INFO, &info), 0); ASSERT_FALSE(!!(info.mask & PIDFD_INFO_CREDS)); ASSERT_TRUE(!!(info.mask & PIDFD_INFO_EXIT)); - /* The thread-group leader exited successfully. Only the specific thread was SIGKILLed. */ - ASSERT_TRUE(WIFEXITED(info.exit_code)); - ASSERT_EQ(WEXITSTATUS(info.exit_code), 0); + /* Even though the thread-group exited successfully it will still report the group exit code. */ + ASSERT_TRUE(WIFSIGNALED(info.exit_code)); + ASSERT_EQ(WTERMSIG(info.exit_code), SIGKILL); /* * Retrieve exit information for the thread-group leader via the @@ -375,9 +376,9 @@ TEST_F(pidfd_info, thread_group) ASSERT_FALSE(!!(info2.mask & PIDFD_INFO_CREDS)); ASSERT_TRUE(!!(info2.mask & PIDFD_INFO_EXIT)); - /* The thread-group leader exited successfully. Only the specific thread was SIGKILLed. */ - ASSERT_TRUE(WIFEXITED(info2.exit_code)); - ASSERT_EQ(WEXITSTATUS(info2.exit_code), 0); + /* Even though the thread-group exited successfully it will still report the group exit code. */ + ASSERT_TRUE(WIFSIGNALED(info2.exit_code)); + ASSERT_EQ(WTERMSIG(info2.exit_code), SIGKILL); /* Retrieve exit information for the thread. */ info.mask = PIDFD_INFO_CGROUPID | PIDFD_INFO_EXIT; diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 0843f6d37e9c..ddc97ecd8b39 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -538,5 +538,67 @@ "$TC qdisc del dev $DUMMY handle 1:0 root", "$IP addr del 10.10.10.10/24 dev $DUMMY || true" ] + }, + { + "id": "62c4", + "name": "Test HTB with FQ_CODEL - basic functionality", + "category": [ + "qdisc", + "htb", + "fq_codel" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + "$TC qdisc add dev $DEV1 root handle 1: htb default 11", + "$TC class add dev $DEV1 parent 1: classid 1:1 htb rate 10kbit", + "$TC class add dev $DEV1 parent 1:1 classid 1:11 htb rate 10kbit prio 0 quantum 1486", + "$TC qdisc add dev $DEV1 parent 1:11 fq_codel quantum 300 noecn", + "sleep 0.5" + ], + "scapy": { + "iface": "$DEV0", + "count": 5, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/TCP(sport=12345, dport=80)" + }, + "cmdUnderTest": "$TC -s qdisc show dev $DEV1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DEV1 | grep -A 5 'qdisc fq_codel'", + "matchPattern": "Sent [0-9]+ bytes [0-9]+ pkt", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 handle 1: root" + ] + }, + { + "id": "831d", + "name": "Test HFSC qlen accounting with DRR/NETEM/BLACKHOLE chain", + "category": ["qdisc", "hfsc", "drr", "netem", "blackhole"], + "plugins": { "requires": ["nsPlugin", "scapyPlugin"] }, + "setup": [ + "$IP link set dev $DEV1 up || true", + "$TC qdisc add dev $DEV1 root handle 1: drr", + "$TC filter add dev $DEV1 parent 1: basic classid 1:1", + "$TC class add dev $DEV1 parent 1: classid 1:1 drr", + "$TC qdisc add dev $DEV1 parent 1:1 handle 2: hfsc def 1", + "$TC class add dev $DEV1 parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0", + "$TC qdisc add dev $DEV1 parent 2:1 handle 3: netem", + "$TC qdisc add dev $DEV1 parent 3:1 handle 4: blackhole" + ], + "scapy": { + "iface": "$DEV0", + "count": 5, + "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/ICMP()" + }, + "cmdUnderTest": "$TC -s qdisc show dev $DEV1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DEV1", + "matchPattern": "qdisc hfsc", + "matchCount": "1", + "teardown": ["$TC qdisc del dev $DEV1 root handle 1: drr"] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json index e9469ee71e6f..6d515d0e5ed6 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/codel.json @@ -189,5 +189,29 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "deb1", + "name": "CODEL test qdisc limit trimming", + "category": ["qdisc", "codel"], + "plugins": { + "requires": ["nsPlugin", "scapyPlugin"] + }, + "setup": [ + "$TC qdisc add dev $DEV1 handle 1: root codel limit 10" + ], + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)" + } + ], + "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root codel limit 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc codel 1: root refcnt [0-9]+ limit 1p target 5ms interval 100ms", + "matchCount": "1", + "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json index 3a537b2ec4c9..24faf4e12dfa 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq.json @@ -377,5 +377,27 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "9479", + "name": "FQ test qdisc limit trimming", + "category": ["qdisc", "fq"], + "plugins": {"requires": ["nsPlugin", "scapyPlugin"]}, + "setup": [ + "$TC qdisc add dev $DEV1 handle 1: root fq limit 10" + ], + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)" + } + ], + "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq limit 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc fq 1: root refcnt [0-9]+ limit 1p", + "matchCount": "1", + "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json index 9774b1e8801b..4ce62b857fd7 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_codel.json @@ -294,5 +294,27 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "0436", + "name": "FQ_CODEL test qdisc limit trimming", + "category": ["qdisc", "fq_codel"], + "plugins": {"requires": ["nsPlugin", "scapyPlugin"]}, + "setup": [ + "$TC qdisc add dev $DEV1 handle 1: root fq_codel limit 10" + ], + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)" + } + ], + "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_codel limit 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc fq_codel 1: root refcnt [0-9]+ limit 1p flows 1024 quantum.*target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64", + "matchCount": "1", + "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json index d012d88d67fe..229fe1bf4a90 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fq_pie.json @@ -18,5 +18,27 @@ "matchCount": "1", "teardown": [ ] + }, + { + "id": "83bf", + "name": "FQ_PIE test qdisc limit trimming", + "category": ["qdisc", "fq_pie"], + "plugins": {"requires": ["nsPlugin", "scapyPlugin"]}, + "setup": [ + "$TC qdisc add dev $DEV1 handle 1: root fq_pie limit 10" + ], + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)" + } + ], + "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root fq_pie limit 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc fq_pie 1: root refcnt [0-9]+ limit 1p", + "matchCount": "1", + "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json index dbef5474b26b..0ca19fac54a5 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hhf.json @@ -188,5 +188,27 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "385f", + "name": "HHF test qdisc limit trimming", + "category": ["qdisc", "hhf"], + "plugins": {"requires": ["nsPlugin", "scapyPlugin"]}, + "setup": [ + "$TC qdisc add dev $DEV1 handle 1: root hhf limit 10" + ], + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)" + } + ], + "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root hhf limit 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc hhf 1: root refcnt [0-9]+ limit 1p.*hh_limit 2048 reset_timeout 40ms admit_bytes 128Kb evict_timeout 1s non_hh_weight 2", + "matchCount": "1", + "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json new file mode 100644 index 000000000000..1a98b66e8030 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/pie.json @@ -0,0 +1,24 @@ +[ + { + "id": "6158", + "name": "PIE test qdisc limit trimming", + "category": ["qdisc", "pie"], + "plugins": {"requires": ["nsPlugin", "scapyPlugin"]}, + "setup": [ + "$TC qdisc add dev $DEV1 handle 1: root pie limit 10" + ], + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)" + } + ], + "cmdUnderTest": "$TC qdisc change dev $DEV1 handle 1: root pie limit 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DEV1", + "matchPattern": "qdisc pie 1: root refcnt [0-9]+ limit 1p", + "matchCount": "1", + "teardown": ["$TC qdisc del dev $DEV1 handle 1: root"] + } +] diff --git a/tools/testing/selftests/x86/bugs/Makefile b/tools/testing/selftests/x86/bugs/Makefile new file mode 100644 index 000000000000..8ff2d7226c7f --- /dev/null +++ b/tools/testing/selftests/x86/bugs/Makefile @@ -0,0 +1,3 @@ +TEST_PROGS := its_sysfs.py its_permutations.py its_indirect_alignment.py its_ret_alignment.py +TEST_FILES := common.py +include ../../lib.mk diff --git a/tools/testing/selftests/x86/bugs/common.py b/tools/testing/selftests/x86/bugs/common.py new file mode 100755 index 000000000000..2f9664a80617 --- /dev/null +++ b/tools/testing/selftests/x86/bugs/common.py @@ -0,0 +1,164 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# This contains kselftest framework adapted common functions for testing +# mitigation for x86 bugs. + +import os, sys, re, shutil + +sys.path.insert(0, '../../kselftest') +import ksft + +def read_file(path): + if not os.path.exists(path): + return None + with open(path, 'r') as file: + return file.read().strip() + +def cpuinfo_has(arg): + cpuinfo = read_file('/proc/cpuinfo') + if arg in cpuinfo: + return True + return False + +def cmdline_has(arg): + cmdline = read_file('/proc/cmdline') + if arg in cmdline: + return True + return False + +def cmdline_has_either(args): + cmdline = read_file('/proc/cmdline') + for arg in args: + if arg in cmdline: + return True + return False + +def cmdline_has_none(args): + return not cmdline_has_either(args) + +def cmdline_has_all(args): + cmdline = read_file('/proc/cmdline') + for arg in args: + if arg not in cmdline: + return False + return True + +def get_sysfs(bug): + return read_file("/sys/devices/system/cpu/vulnerabilities/" + bug) + +def sysfs_has(bug, mitigation): + status = get_sysfs(bug) + if mitigation in status: + return True + return False + +def sysfs_has_either(bugs, mitigations): + for bug in bugs: + for mitigation in mitigations: + if sysfs_has(bug, mitigation): + return True + return False + +def sysfs_has_none(bugs, mitigations): + return not sysfs_has_either(bugs, mitigations) + +def sysfs_has_all(bugs, mitigations): + for bug in bugs: + for mitigation in mitigations: + if not sysfs_has(bug, mitigation): + return False + return True + +def bug_check_pass(bug, found): + ksft.print_msg(f"\nFound: {found}") + # ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}") + ksft.test_result_pass(f'{bug}: {found}') + +def bug_check_fail(bug, found, expected): + ksft.print_msg(f'\nFound:\t {found}') + ksft.print_msg(f'Expected:\t {expected}') + ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}") + ksft.test_result_fail(f'{bug}: {found}') + +def bug_status_unknown(bug, found): + ksft.print_msg(f'\nUnknown status: {found}') + ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}") + ksft.test_result_fail(f'{bug}: {found}') + +def basic_checks_sufficient(bug, mitigation): + if not mitigation: + bug_status_unknown(bug, "None") + return True + elif mitigation == "Not affected": + ksft.test_result_pass(bug) + return True + elif mitigation == "Vulnerable": + if cmdline_has_either([f'{bug}=off', 'mitigations=off']): + bug_check_pass(bug, mitigation) + return True + return False + +def get_section_info(vmlinux, section_name): + from elftools.elf.elffile import ELFFile + with open(vmlinux, 'rb') as f: + elffile = ELFFile(f) + section = elffile.get_section_by_name(section_name) + if section is None: + ksft.print_msg("Available sections in vmlinux:") + for sec in elffile.iter_sections(): + ksft.print_msg(sec.name) + raise ValueError(f"Section {section_name} not found in {vmlinux}") + return section['sh_addr'], section['sh_offset'], section['sh_size'] + +def get_patch_sites(vmlinux, offset, size): + import struct + output = [] + with open(vmlinux, 'rb') as f: + f.seek(offset) + i = 0 + while i < size: + data = f.read(4) # s32 + if not data: + break + sym_offset = struct.unpack('<i', data)[0] + i + i += 4 + output.append(sym_offset) + return output + +def get_instruction_from_vmlinux(elffile, section, virtual_address, target_address): + from capstone import Cs, CS_ARCH_X86, CS_MODE_64 + section_start = section['sh_addr'] + section_end = section_start + section['sh_size'] + + if not (section_start <= target_address < section_end): + return None + + offset = target_address - section_start + code = section.data()[offset:offset + 16] + + cap = init_capstone() + for instruction in cap.disasm(code, target_address): + if instruction.address == target_address: + return instruction + return None + +def init_capstone(): + from capstone import Cs, CS_ARCH_X86, CS_MODE_64, CS_OPT_SYNTAX_ATT + cap = Cs(CS_ARCH_X86, CS_MODE_64) + cap.syntax = CS_OPT_SYNTAX_ATT + return cap + +def get_runtime_kernel(): + import drgn + return drgn.program_from_kernel() + +def check_dependencies_or_skip(modules, script_name="unknown test"): + for mod in modules: + try: + __import__(mod) + except ImportError: + ksft.test_result_skip(f"Skipping {script_name}: missing module '{mod}'") + ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_indirect_alignment.py b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py new file mode 100755 index 000000000000..cdc33ae6a91c --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py @@ -0,0 +1,150 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for indirect target selection (ITS) mitigation. +# +# Test if indirect CALL/JMP are correctly patched by evaluating +# the vmlinux .retpoline_sites in /proc/kcore. + +# Install dependencies +# add-apt-repository ppa:michel-slm/kernel-utils +# apt update +# apt install -y python3-drgn python3-pyelftools python3-capstone +# +# Best to copy the vmlinux at a standard location: +# mkdir -p /usr/lib/debug/lib/modules/$(uname -r) +# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux +# +# Usage: ./its_indirect_alignment.py [vmlinux] + +import os, sys, argparse +from pathlib import Path + +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, this_dir + '/../../kselftest') +import ksft +import common as c + +bug = "indirect_target_selection" + +mitigation = c.get_sysfs(bug) +if not mitigation or "Aligned branch/return thunks" not in mitigation: + ksft.test_result_skip("Skipping its_indirect_alignment.py: Aligned branch/return thunks not enabled") + ksft.finished() + +if c.sysfs_has("spectre_v2", "Retpolines"): + ksft.test_result_skip("Skipping its_indirect_alignment.py: Retpolines deployed") + ksft.finished() + +c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_indirect_alignment.py") + +from elftools.elf.elffile import ELFFile +from drgn.helpers.common.memory import identify_address + +cap = c.init_capstone() + +if len(os.sys.argv) > 1: + arg_vmlinux = os.sys.argv[1] + if not os.path.exists(arg_vmlinux): + ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at argument path: {arg_vmlinux}") + ksft.exit_fail() + os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True) + os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux') + +vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux" +if not os.path.exists(vmlinux): + ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at {vmlinux}") + ksft.exit_fail() + +ksft.print_msg(f"Using vmlinux: {vmlinux}") + +retpolines_start_vmlinux, retpolines_sec_offset, size = c.get_section_info(vmlinux, '.retpoline_sites') +ksft.print_msg(f"vmlinux: Section .retpoline_sites (0x{retpolines_start_vmlinux:x}) found at 0x{retpolines_sec_offset:x} with size 0x{size:x}") + +sites_offset = c.get_patch_sites(vmlinux, retpolines_sec_offset, size) +total_retpoline_tests = len(sites_offset) +ksft.print_msg(f"Found {total_retpoline_tests} retpoline sites") + +prog = c.get_runtime_kernel() +retpolines_start_kcore = prog.symbol('__retpoline_sites').address +ksft.print_msg(f'kcore: __retpoline_sites: 0x{retpolines_start_kcore:x}') + +x86_indirect_its_thunk_r15 = prog.symbol('__x86_indirect_its_thunk_r15').address +ksft.print_msg(f'kcore: __x86_indirect_its_thunk_r15: 0x{x86_indirect_its_thunk_r15:x}') + +tests_passed = 0 +tests_failed = 0 +tests_unknown = 0 + +with open(vmlinux, 'rb') as f: + elffile = ELFFile(f) + text_section = elffile.get_section_by_name('.text') + + for i in range(0, len(sites_offset)): + site = retpolines_start_kcore + sites_offset[i] + vmlinux_site = retpolines_start_vmlinux + sites_offset[i] + passed = unknown = failed = False + try: + vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site) + kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0] + operand = kcore_insn.op_str + insn_end = site + kcore_insn.size - 1 # TODO handle Jcc.32 __x86_indirect_thunk_\reg + safe_site = insn_end & 0x20 + site_status = "" if safe_site else "(unsafe)" + + ksft.print_msg(f"\nSite {i}: {identify_address(prog, site)} <0x{site:x}> {site_status}") + ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}") + ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}") + + if (site & 0x20) ^ (insn_end & 0x20): + ksft.print_msg(f"\tSite at safe/unsafe boundary: {str(kcore_insn.bytes)} {kcore_insn.mnemonic} {operand}") + if safe_site: + tests_passed += 1 + passed = True + ksft.print_msg(f"\tPASSED: At safe address") + continue + + if operand.startswith('0xffffffff'): + thunk = int(operand, 16) + if thunk > x86_indirect_its_thunk_r15: + insn_at_thunk = list(cap.disasm(prog.read(thunk, 16), thunk))[0] + operand += ' -> ' + insn_at_thunk.mnemonic + ' ' + insn_at_thunk.op_str + ' <dynamic-thunk?>' + if 'jmp' in insn_at_thunk.mnemonic and thunk & 0x20: + ksft.print_msg(f"\tPASSED: Found {operand} at safe address") + passed = True + if not passed: + if kcore_insn.operands[0].type == capstone.CS_OP_IMM: + operand += ' <' + prog.symbol(int(operand, 16)) + '>' + if '__x86_indirect_its_thunk_' in operand: + ksft.print_msg(f"\tPASSED: Found {operand}") + else: + ksft.print_msg(f"\tPASSED: Found direct branch: {kcore_insn}, ITS thunk not required.") + passed = True + else: + unknown = True + if passed: + tests_passed += 1 + elif unknown: + ksft.print_msg(f"UNKNOWN: unexpected operand: {kcore_insn}") + tests_unknown += 1 + else: + ksft.print_msg(f'\t************* FAILED *************') + ksft.print_msg(f"\tFound {kcore_insn.bytes} {kcore_insn.mnemonic} {operand}") + ksft.print_msg(f'\t**********************************') + tests_failed += 1 + except Exception as e: + ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}") + tests_unknown += 1 + +ksft.print_msg(f"\n\nSummary:") +ksft.print_msg(f"PASS: \t{tests_passed} \t/ {total_retpoline_tests}") +ksft.print_msg(f"FAIL: \t{tests_failed} \t/ {total_retpoline_tests}") +ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_retpoline_tests}") + +if tests_failed == 0: + ksft.test_result_pass("All ITS return thunk sites passed") +else: + ksft.test_result_fail(f"{tests_failed} ITS return thunk sites failed") +ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_permutations.py b/tools/testing/selftests/x86/bugs/its_permutations.py new file mode 100755 index 000000000000..3204f4728c62 --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_permutations.py @@ -0,0 +1,109 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for indirect target selection (ITS) cmdline permutations with other bugs +# like spectre_v2 and retbleed. + +import os, sys, subprocess, itertools, re, shutil + +test_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, test_dir + '/../../kselftest') +import ksft +import common as c + +bug = "indirect_target_selection" +mitigation = c.get_sysfs(bug) + +if not mitigation or "Not affected" in mitigation: + ksft.test_result_skip("Skipping its_permutations.py: not applicable") + ksft.finished() + +if shutil.which('vng') is None: + ksft.test_result_skip("Skipping its_permutations.py: virtme-ng ('vng') not found in PATH.") + ksft.finished() + +TEST = f"{test_dir}/its_sysfs.py" +default_kparam = ['clearcpuid=hypervisor', 'panic=5', 'panic_on_warn=1', 'oops=panic', 'nmi_watchdog=1', 'hung_task_panic=1'] + +DEBUG = " -v " + +# Install dependencies +# https://github.com/arighi/virtme-ng +# apt install virtme-ng +BOOT_CMD = f"vng --run {test_dir}/../../../../../arch/x86/boot/bzImage " +#BOOT_CMD += DEBUG + +bug = "indirect_target_selection" + +input_options = { + 'indirect_target_selection' : ['off', 'on', 'stuff', 'vmexit'], + 'retbleed' : ['off', 'stuff', 'auto'], + 'spectre_v2' : ['off', 'on', 'eibrs', 'retpoline', 'ibrs', 'eibrs,retpoline'], +} + +def pretty_print(output): + OKBLUE = '\033[94m' + OKGREEN = '\033[92m' + WARNING = '\033[93m' + FAIL = '\033[91m' + ENDC = '\033[0m' + BOLD = '\033[1m' + + # Define patterns and their corresponding colors + patterns = { + r"^ok \d+": OKGREEN, + r"^not ok \d+": FAIL, + r"^# Testing .*": OKBLUE, + r"^# Found: .*": WARNING, + r"^# Totals: .*": BOLD, + r"pass:([1-9]\d*)": OKGREEN, + r"fail:([1-9]\d*)": FAIL, + r"skip:([1-9]\d*)": WARNING, + } + + # Apply colors based on patterns + for pattern, color in patterns.items(): + output = re.sub(pattern, lambda match: f"{color}{match.group(0)}{ENDC}", output, flags=re.MULTILINE) + + print(output) + +combinations = list(itertools.product(*input_options.values())) +ksft.print_header() +ksft.set_plan(len(combinations)) + +logs = "" + +for combination in combinations: + append = "" + log = "" + for p in default_kparam: + append += f' --append={p}' + command = BOOT_CMD + append + test_params = "" + for i, key in enumerate(input_options.keys()): + param = f'{key}={combination[i]}' + test_params += f' {param}' + command += f" --append={param}" + command += f" -- {TEST}" + test_name = f"{bug} {test_params}" + pretty_print(f'# Testing {test_name}') + t = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) + t.wait() + output, _ = t.communicate() + if t.returncode == 0: + ksft.test_result_pass(test_name) + else: + ksft.test_result_fail(test_name) + output = output.decode() + log += f" {output}" + pretty_print(log) + logs += output + "\n" + +# Optionally use tappy to parse the output +# apt install python3-tappy +with open("logs.txt", "w") as f: + f.write(logs) + +ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_ret_alignment.py b/tools/testing/selftests/x86/bugs/its_ret_alignment.py new file mode 100755 index 000000000000..f40078d9f6ff --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_ret_alignment.py @@ -0,0 +1,139 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for indirect target selection (ITS) mitigation. +# +# Tests if the RETs are correctly patched by evaluating the +# vmlinux .return_sites in /proc/kcore. +# +# Install dependencies +# add-apt-repository ppa:michel-slm/kernel-utils +# apt update +# apt install -y python3-drgn python3-pyelftools python3-capstone +# +# Run on target machine +# mkdir -p /usr/lib/debug/lib/modules/$(uname -r) +# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux +# +# Usage: ./its_ret_alignment.py + +import os, sys, argparse +from pathlib import Path + +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, this_dir + '/../../kselftest') +import ksft +import common as c + +bug = "indirect_target_selection" +mitigation = c.get_sysfs(bug) +if not mitigation or "Aligned branch/return thunks" not in mitigation: + ksft.test_result_skip("Skipping its_ret_alignment.py: Aligned branch/return thunks not enabled") + ksft.finished() + +c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_ret_alignment.py") + +from elftools.elf.elffile import ELFFile +from drgn.helpers.common.memory import identify_address + +cap = c.init_capstone() + +if len(os.sys.argv) > 1: + arg_vmlinux = os.sys.argv[1] + if not os.path.exists(arg_vmlinux): + ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at user-supplied path: {arg_vmlinux}") + ksft.exit_fail() + os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True) + os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux') + +vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux" +if not os.path.exists(vmlinux): + ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at {vmlinux}") + ksft.exit_fail() + +ksft.print_msg(f"Using vmlinux: {vmlinux}") + +rethunks_start_vmlinux, rethunks_sec_offset, size = c.get_section_info(vmlinux, '.return_sites') +ksft.print_msg(f"vmlinux: Section .return_sites (0x{rethunks_start_vmlinux:x}) found at 0x{rethunks_sec_offset:x} with size 0x{size:x}") + +sites_offset = c.get_patch_sites(vmlinux, rethunks_sec_offset, size) +total_rethunk_tests = len(sites_offset) +ksft.print_msg(f"Found {total_rethunk_tests} rethunk sites") + +prog = c.get_runtime_kernel() +rethunks_start_kcore = prog.symbol('__return_sites').address +ksft.print_msg(f'kcore: __rethunk_sites: 0x{rethunks_start_kcore:x}') + +its_return_thunk = prog.symbol('its_return_thunk').address +ksft.print_msg(f'kcore: its_return_thunk: 0x{its_return_thunk:x}') + +tests_passed = 0 +tests_failed = 0 +tests_unknown = 0 +tests_skipped = 0 + +with open(vmlinux, 'rb') as f: + elffile = ELFFile(f) + text_section = elffile.get_section_by_name('.text') + + for i in range(len(sites_offset)): + site = rethunks_start_kcore + sites_offset[i] + vmlinux_site = rethunks_start_vmlinux + sites_offset[i] + try: + passed = unknown = failed = skipped = False + + symbol = identify_address(prog, site) + vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site) + kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0] + + insn_end = site + kcore_insn.size - 1 + + safe_site = insn_end & 0x20 + site_status = "" if safe_site else "(unsafe)" + + ksft.print_msg(f"\nSite {i}: {symbol} <0x{site:x}> {site_status}") + ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}") + ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}") + + if safe_site: + tests_passed += 1 + passed = True + ksft.print_msg(f"\tPASSED: At safe address") + continue + + if "jmp" in kcore_insn.mnemonic: + passed = True + elif "ret" not in kcore_insn.mnemonic: + skipped = True + + if passed: + ksft.print_msg(f"\tPASSED: Found {kcore_insn.mnemonic} {kcore_insn.op_str}") + tests_passed += 1 + elif skipped: + ksft.print_msg(f"\tSKIPPED: Found '{kcore_insn.mnemonic}'") + tests_skipped += 1 + elif unknown: + ksft.print_msg(f"UNKNOWN: An unknown instruction: {kcore_insn}") + tests_unknown += 1 + else: + ksft.print_msg(f'\t************* FAILED *************') + ksft.print_msg(f"\tFound {kcore_insn.mnemonic} {kcore_insn.op_str}") + ksft.print_msg(f'\t**********************************') + tests_failed += 1 + except Exception as e: + ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}") + tests_unknown += 1 + +ksft.print_msg(f"\n\nSummary:") +ksft.print_msg(f"PASSED: \t{tests_passed} \t/ {total_rethunk_tests}") +ksft.print_msg(f"FAILED: \t{tests_failed} \t/ {total_rethunk_tests}") +ksft.print_msg(f"SKIPPED: \t{tests_skipped} \t/ {total_rethunk_tests}") +ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_rethunk_tests}") + +if tests_failed == 0: + ksft.test_result_pass("All ITS return thunk sites passed.") +else: + ksft.test_result_fail(f"{tests_failed} failed sites need ITS return thunks.") +ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_sysfs.py b/tools/testing/selftests/x86/bugs/its_sysfs.py new file mode 100755 index 000000000000..7bca81f2f606 --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_sysfs.py @@ -0,0 +1,65 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for Indirect Target Selection(ITS) mitigation sysfs status. + +import sys, os, re +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, this_dir + '/../../kselftest') +import ksft + +from common import * + +bug = "indirect_target_selection" +mitigation = get_sysfs(bug) + +ITS_MITIGATION_ALIGNED_THUNKS = "Mitigation: Aligned branch/return thunks" +ITS_MITIGATION_RETPOLINE_STUFF = "Mitigation: Retpolines, Stuffing RSB" +ITS_MITIGATION_VMEXIT_ONLY = "Mitigation: Vulnerable, KVM: Not affected" +ITS_MITIGATION_VULNERABLE = "Vulnerable" + +def check_mitigation(): + if mitigation == ITS_MITIGATION_ALIGNED_THUNKS: + if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"): + bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_RETPOLINE_STUFF) + return + if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'): + bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_VMEXIT_ONLY) + return + bug_check_pass(bug, ITS_MITIGATION_ALIGNED_THUNKS) + return + + if mitigation == ITS_MITIGATION_RETPOLINE_STUFF: + if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"): + bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF) + return + if sysfs_has('retbleed', 'Stuffing'): + bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF) + return + bug_check_fail(bug, ITS_MITIGATION_RETPOLINE_STUFF, ITS_MITIGATION_ALIGNED_THUNKS) + + if mitigation == ITS_MITIGATION_VMEXIT_ONLY: + if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'): + bug_check_pass(bug, ITS_MITIGATION_VMEXIT_ONLY) + return + bug_check_fail(bug, ITS_MITIGATION_VMEXIT_ONLY, ITS_MITIGATION_ALIGNED_THUNKS) + + if mitigation == ITS_MITIGATION_VULNERABLE: + if sysfs_has("spectre_v2", "Vulnerable"): + bug_check_pass(bug, ITS_MITIGATION_VULNERABLE) + else: + bug_check_fail(bug, "Mitigation", ITS_MITIGATION_VULNERABLE) + + bug_status_unknown(bug, mitigation) + return + +ksft.print_header() +ksft.set_plan(1) +ksft.print_msg(f'{bug}: {mitigation} ...') + +if not basic_checks_sufficient(bug, mitigation): + check_mitigation() + +ksft.finished() diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index d0f6d253ac72..613551132a96 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -1264,21 +1264,25 @@ static void test_unsent_bytes_client(const struct test_opts *opts, int type) send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); control_expectln("RECEIVED"); - ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent); - if (ret < 0) { - if (errno == EOPNOTSUPP) { - fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n"); - } else { + /* SIOCOUTQ isn't guaranteed to instantly track sent data. Even though + * the "RECEIVED" message means that the other side has received the + * data, there can be a delay in our kernel before updating the "unsent + * bytes" counter. Repeat SIOCOUTQ until it returns 0. + */ + timeout_begin(TIMEOUT); + do { + ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent); + if (ret < 0) { + if (errno == EOPNOTSUPP) { + fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n"); + break; + } perror("ioctl"); exit(EXIT_FAILURE); } - } else if (ret == 0 && sock_bytes_unsent != 0) { - fprintf(stderr, - "Unexpected 'SIOCOUTQ' value, expected 0, got %i\n", - sock_bytes_unsent); - exit(EXIT_FAILURE); - } - + timeout_check("SIOCOUTQ"); + } while (sock_bytes_unsent != 0); + timeout_end(); close(fd); } diff --git a/usr/include/Makefile b/usr/include/Makefile index e3d6b03527fe..f02f41941b60 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -59,6 +59,10 @@ ifeq ($(SRCARCH),arc) no-header-test += linux/bpf_perf_event.h endif +ifeq ($(SRCARCH),openrisc) +no-header-test += linux/bpf_perf_event.h +endif + ifeq ($(SRCARCH),powerpc) no-header-test += linux/bpf_perf_event.h endif |