This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1.... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.19.y and the diffstat can be found below.
thanks,
greg k-h
------------- Pseudo-Shortlog of commits:
Greg Kroah-Hartman gregkh@linuxfoundation.org Linux 5.19.9-rc1
Saaem Rizvi SyedSaaem.Rizvi@amd.com drm/amd/display: Removing assert statements for Linux
Saaem Rizvi SyedSaaem.Rizvi@amd.com drm/amd/display: Add SMU logging code
Jason Gunthorpe jgg@ziepe.ca iommu: Fix false ownership failure on AMD systems with PASID activated
Jean-Philippe Brucker jean-philippe@linaro.org iommu/virtio: Fix interaction with VFIO
Lu Baolu baolu.lu@linux.intel.com iommu/vt-d: Correctly calculate sagaw value of IOMMU
Mark Brown broonie@kernel.org arm64/bti: Disable in kernel BTI when cross section thunks are broken
Eugene Shalygin eugene.shalygin@gmail.com hwmon: (asus-ec-sensors) autoload module via DMI data
Urs Schroffenegger nabajour@lampshade.ch hwmon: (asus-ec-sensors) add definitions for ROG ZENITH II EXTREME
Eugene Shalygin eugene.shalygin@gmail.com hwmon: (asus-ec-sensors) add missing sensors for X570-I GAMING
Michael Carns mike@carns.com hwmon: (asus-ec-sensors) add support for Maximus XI Hero
Shady Nawara shady.nawara@outlook.com hwmon: (asus-ec-sensors) add support for Strix Z690-a D4
Sasha Levin sashal@kernel.org Revert "arm64: kasan: Revert "arm64: mte: reset the page tag in page->flags""
Zhengjun Xing zhengjun.xing@linux.intel.com perf stat: Fix L2 Topdown metrics disappear for raw events
Kan Liang kan.liang@linux.intel.com perf evlist: Always use arch_evlist__add_default_attrs()
Lu Baolu baolu.lu@linux.intel.com iommu/vt-d: Fix possible recursive locking in intel_iommu_init()
Eliav Farber farbere@amazon.com hwmon: (mr75203) enable polling for all VM channels
Eliav Farber farbere@amazon.com hwmon: (mr75203) fix multi-channel voltage reading
Eliav Farber farbere@amazon.com hwmon: (mr75203) fix voltage equation for negative source input
Eliav Farber farbere@amazon.com hwmon: (mr75203) update pvt->v_num and vm_num to the actual number of used sensors
Eliav Farber farbere@amazon.com hwmon: (mr75203) fix VM sensor allocation when "intel,vm-map" not defined
Vladimir Oltean vladimir.oltean@nxp.com net: dsa: felix: tc-taprio intervals smaller than MTU should send at least one packet
Vladimir Oltean vladimir.oltean@nxp.com time64.h: consolidate uses of PSEC_PER_NSEC
Alexander Gordeev agordeev@linux.ibm.com s390/boot: fix absolute zero lowcore corruption on boot
John Sperbeck jsperbeck@google.com iommu/amd: use full 64-bit value in build_completion_wait()
Chao Gao chao.gao@intel.com swiotlb: avoid potential left shift overflow
Hangbin Liu liuhangbin@gmail.com bonding: accept unsolicited NA message
Vladimir Oltean vladimir.oltean@nxp.com net: bonding: replace dev_trans_start() with the jiffies of the last ARP/NS
Przemyslaw Patynowski przemyslawx.patynowski@intel.com i40e: Fix ADQ rate limiting for PF
Przemyslaw Patynowski przemyslawx.patynowski@intel.com i40e: Refactor tc mqprio checks
Masahiro Yamada masahiroy@kernel.org kbuild: disable header exports for UML in a straightforward way
Yang Ling gnaygnil@gmail.com MIPS: loongson32: ls1c: Fix hang during startup
Casey Schaufler casey@schaufler-ca.com Smack: Provide read control for io_uring_cmd
Paul Moore paul@paul-moore.com selinux: implement the security_uring_cmd() LSM hook
Luis Chamberlain mcgrof@kernel.org lsm,io_uring: add LSM hooks for the new uring_cmd file op
Nathan Chancellor nathan@kernel.org ASoC: mchp-spdiftx: Fix clang -Wbitfield-constant-conversion
Claudiu Beznea claudiu.beznea@microchip.com ASoC: mchp-spdiftx: remove references to mchp_i2s_caps
Alexandru Gagniuc mr.nuke.me@gmail.com hwmon: (tps23861) fix byte order in resistance register
Adrian Hunter adrian.hunter@intel.com perf record: Fix synthesis failure warnings
Zhengjun Xing zhengjun.xing@linux.intel.com perf script: Fix Cannot print 'iregs' field for hybrid systems
Adrian Hunter adrian.hunter@intel.com perf dlfilter dlfilter-show-cycles: Fix types for print format
Adrian Hunter adrian.hunter@intel.com libperf evlist: Fix per-thread mmaps for multi-threaded targets
Toke Høiland-Jørgensen toke@toke.dk sch_sfb: Also store skb len before calling child enqueue
Arun Ramadoss arun.ramadoss@microchip.com net: phy: lan87xx: change interrupt src of link_up to comm_ready
Pavel Begunkov asml.silence@gmail.com io_uring: recycle kbuf recycle on tw requeue
Yacan Liu liuyacan@corp.netease.com net/smc: Fix possible access to freed memory in link clear
Lorenzo Bianconi lorenzo@kernel.org net: ethernet: mtk_eth_soc: check max allowed hash in mtk_ppe_check_skb
Lorenzo Bianconi lorenzo@kernel.org net: ethernet: mtk_eth_soc: fix typo in __mtk_foe_entry_clear
Vladimir Oltean vladimir.oltean@nxp.com net: dsa: felix: access QSYS_TAG_CONFIG under tas_lock in vsc9959_sched_speed_set
Vladimir Oltean vladimir.oltean@nxp.com net: dsa: felix: disable cut-through forwarding for frames oversized for tc-taprio
Sindhu-Devale sindhu.devale@intel.com RDMA/irdma: Report RNR NAK generation in device caps
Sindhu-Devale sindhu.devale@intel.com RDMA/irdma: Return correct WC error for bind operation failure
Sindhu-Devale sindhu.devale@intel.com RDMA/irdma: Return error on MR deregister CQP failure
Sindhu-Devale sindhu.devale@intel.com RDMA/irdma: Report the correct max cqes from query device
Dennis Maisenbacher dennis.maisenbacher@wdc.com nvmet: fix mar and mor off-by-one errors
Qu Wenruo wqu@suse.com btrfs: fix the max chunk size and stripe length calculation
Neal Cardwell ncardwell@google.com tcp: fix early ETIMEDOUT after spurious non-SACK RTO
Sagi Grimberg sagi@grimberg.me nvme-tcp: fix regression that causes sporadic requests to time out
Sagi Grimberg sagi@grimberg.me nvme-tcp: fix UAF when detecting digest errors
Gao Xiang xiang@kernel.org erofs: fix pcluster use-after-free on UP platforms
Sun Ke sunke32@huawei.com erofs: fix error return code in erofs_fscache_{meta_,}read_folio
Johannes Thumshirn johannes.thumshirn@wdc.com btrfs: zoned: fix mounting with conventional zones
Chris Mi cmi@nvidia.com RDMA/mlx5: Set local port to one when accessing counters
Yishai Hadas yishaih@nvidia.com IB/core: Fix a nested dead lock as part of ODP flow
David Lebrun dlebrun@google.com ipv6: sr: fix out-of-bounds read when setting HMAC data.
Hangbin Liu liuhangbin@gmail.com bonding: add all node mcast address when slave up
Hangbin Liu liuhangbin@gmail.com bonding: use unspecified address if no available link local address
Linus Walleij linus.walleij@linaro.org RDMA/siw: Pass a pointer to virt_to_page()
Ming Lei ming.lei@redhat.com block: don't add partitions if GD_SUPPRESS_PART_SCAN is set
Paul Durrant pdurrant@amazon.com xen-netback: only remove 'hotplug-status' when the vif is actually destroyed
Csókás Bence csokas.bence@prolan.hu net: fec: Use a spinlock to guard `fep->ptp_clk_on`
Ivan Vecera ivecera@redhat.com iavf: Detach device during reset task
Ivan Vecera ivecera@redhat.com i40e: Fix kernel crash during module removal
Michal Swiatkowski michal.swiatkowski@linux.intel.com ice: use bitmap_free instead of devm_kfree
Przemyslaw Patynowski przemyslawx.patynowski@intel.com ice: Fix DMA mappings leak
Eric Dumazet edumazet@google.com tcp: TX zerocopy should not sense pfmemalloc status
Pavel Begunkov asml.silence@gmail.com net: introduce __skb_fill_page_desc_noacc
Dan Carpenter dan.carpenter@oracle.com tipc: fix shift wrapping bug in map_get()
Toke Høiland-Jørgensen toke@toke.dk sch_sfb: Don't assume the skb is still around after enqueueing to child
Heiner Kallweit hkallweit1@gmail.com Revert "net: phy: meson-gxl: improve link-up behavior"
Sander Vanheule sander@svanheule.net kunit: fix assert_type for comparison macros
David Howells dhowells@redhat.com afs: Use the operation issue time instead of the reply time for callbacks
David Howells dhowells@redhat.com rxrpc: Fix an insufficiently large sglist in rxkad_verify_packet_2()
David Howells dhowells@redhat.com rxrpc: Fix ICMP/ICMP6 error handling
Takashi Iwai tiwai@suse.de ALSA: usb-audio: Register card again for iface over delayed_register option
Takashi Iwai tiwai@suse.de ALSA: usb-audio: Inform the delayed registration more properly
yangx.jy@fujitsu.com yangx.jy@fujitsu.com RDMA/srp: Set scmnd->result only when scmnd is not NULL
David Leadbeater dgl@dgl.cx netfilter: nf_conntrack_irc: Fix forged IP logic
Conor Dooley conor.dooley@microchip.com riscv: dts: microchip: use an mpfs specific l2 compatible
Pablo Neira Ayuso pablo@netfilter.org netfilter: nf_tables: clean up hook list when offload flags check fails
Harsh Modi harshmodi@google.com netfilter: br_netfilter: Drop dst references before setting.
Claudiu Beznea claudiu.beznea@microchip.com ARM: dts: at91: sama5d2_icp: don't keep vdd_other enabled all the time
Claudiu Beznea claudiu.beznea@microchip.com ARM: dts: at91: sama5d27_wlsom1: don't keep ldo2 enabled all the time
Claudiu Beznea claudiu.beznea@microchip.com ARM: dts: at91: sama7g5ek: specify proper regulator output ranges
Claudiu Beznea claudiu.beznea@microchip.com ARM: dts: at91: sama5d2_icp: specify proper regulator output ranges
Claudiu Beznea claudiu.beznea@microchip.com ARM: dts: at91: sama5d27_wlsom1: specify proper regulator output ranges
Claudiu Beznea claudiu.beznea@microchip.com ARM: at91: pm: fix DDR recalibration when resuming from backup and self-refresh
Claudiu Beznea claudiu.beznea@microchip.com ARM: at91: pm: fix self-refresh for sama7g5
Ajay.Kathat@microchip.com Ajay.Kathat@microchip.com wifi: wilc1000: fix DMA on stack objects
Yixing Liu liuyixing1@huawei.com RDMA/hns: Remove the num_qpc_timer variable
Wenpeng Liang liangwenpeng@huawei.com RDMA/hns: Fix wrong fixed value of qp->rq.wqe_shift
Chengchang Tang tangchengchang@huawei.com RDMA/hns: Fix supported page size
Liang He windhl@126.com soc: brcmstb: pm-arm: Fix refcount leak and __iomem leak bugs
Michael Guralnik michaelgur@nvidia.com RDMA/cma: Fix arguments order in net device validation
Geert Uytterhoeven geert+renesas@glider.be arm64: dts: renesas: r8a779g0: Fix HSCIF0 interrupt number
Shiraz Saleem shiraz.saleem@intel.com RDMA/irdma: Fix drain SQ hang with no completion
Jens Wiklander jens.wiklander@linaro.org tee: fix compiler warning in tee_shm_register()
Peter Ujfalusi peter.ujfalusi@linux.intel.com ASoC: SOF: Kconfig: Make IPC_MESSAGE_INJECTOR depend on SND_SOC_SOF
Peter Ujfalusi peter.ujfalusi@linux.intel.com ASoC: SOF: Kconfig: Make IPC_FLOOD_TEST depend on SND_SOC_SOF
Andrew Halaney ahalaney@redhat.com regulator: core: Clean up on enable failure
Marcel Ziswiler marcel.ziswiler@toradex.com arm64: dts: freescale: verdin-imx8mp: fix atmel_mxt_ts reset polarity
Marcel Ziswiler marcel.ziswiler@toradex.com arm64: dts: freescale: verdin-imx8mm: fix atmel_mxt_ts reset polarity
Tim Harvey tharvey@gateworks.com arm64: dts: imx8mm-venice-gw7901: fix port/phy validation
Philippe Schenker philippe.schenker@toradex.com arm64: dts: verdin-imx8mm: add otg2 pd to usbphy
Marek Vasut marex@denx.de soc: imx: gpcv2: Assert reset before ungating clock
Vladimir Oltean vladimir.oltean@nxp.com arm64: dts: ls1028a-qds-65bb: don't use in-band autoneg for 2500base-x
Marco Felsch m.felsch@pengutronix.de ARM: dts: imx6qdl-kontron-samx6i: fix spi-flash compatible
Marco Felsch m.felsch@pengutronix.de ARM: dts: imx6qdl-kontron-samx6i: remove duplicated node
David Jander david@protonic.nl ARM: dts: imx6qdl-vicut1.dtsi: Fix node name backlight_led
Jack Wang jinpu.wang@ionos.com RDMA/rtrs-srv: Pass the correct number of entries for dma mapped SGL
Jack Wang jinpu.wang@ionos.com RDMA/rtrs-clt: Use the right sg_cnt after ib_dma_map_sg
Alexander Stein alexander.stein@ew.tq-group.com arm64: dts: imx8mq-tqma8mq: Remove superfluous interrupt-names
Peng Fan peng.fan@nxp.com arm64: dts: imx8mp-venice-gw74xx: fix sai2 pin settings
Cristian Ciocaltea cristian.ciocaltea@collabora.com regmap: spi: Reserve space for register address/padding
Srinivas Kandagatla srinivas.kandagatla@linaro.org ASoC: qcom: sm8250: add missing module owner
Andrejs Cainikovs andrejs.cainikovs@toradex.com arm64: dts: imx8mm-verdin: use level interrupt for mcp251xfd
Andrejs Cainikovs andrejs.cainikovs@toradex.com arm64: dts: imx8mm-verdin: update CAN clock to 40MHz
Marco Felsch m.felsch@pengutronix.de Revert "soc: imx: imx8m-blk-ctrl: set power device name"
Richard Fitzgerald rf@opensource.cirrus.com ASoC: cs42l42: Only report button state if there was a button interrupt
Robin Murphy robin.murphy@arm.com spi: bitbang: Fix lsb-first Rx
David Howells dhowells@redhat.com smb3: missing inode locks in zero range
Enzo Matsumiya ematsumiya@suse.de cifs: remove useless parameter 'is_fsctl' from SMB2_ioctl()
Tejun Heo tj@kernel.org cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock
Tejun Heo tj@kernel.org cgroup: Elide write-locking threadgroup_rwsem when updating csses on an empty subtree
Yang Yingliang yangyingliang@huawei.com scsi: lpfc: Add missing destroy_workqueue() in error path
Sreekanth Reddy sreekanth.reddy@broadcom.com scsi: mpt3sas: Fix use-after-free warning
Ville Syrjälä ville.syrjala@linux.intel.com drm/i915: Implement WaEdpLinkRateDataReload
Rodrigo Vivi rodrigo.vivi@intel.com drm/i915/slpc: Let's fix the PCODE min freq table setup for SLPC
Ville Syrjälä ville.syrjala@linux.intel.com drm/i915/bios: Copy the whole MIPI sequence block
Bart Van Assche bvanassche@acm.org nvmet: fix a use-after-free
Greg Kroah-Hartman gregkh@linuxfoundation.org driver core: fix driver_set_override() issue with empty strings
Greg Kroah-Hartman gregkh@linuxfoundation.org drm/amd/display: fix memory leak when using debugfs_lookup()
Greg Kroah-Hartman gregkh@linuxfoundation.org sched/debug: fix dentry leak in update_sched_domain_debugfs
Greg Kroah-Hartman gregkh@linuxfoundation.org debugfs: add debugfs_lookup_and_remove()
Sergey Matyukevich sergey.matyukevich@syntacore.com perf: RISC-V: fix access beyond allocated array
Christian A. Ehrhardt lk@c--e.de kprobes: Prohibit probes in gate area
Alex Williamson alex.williamson@redhat.com vfio/type1: Unpin zero pages
Naohiro Aota naohiro.aota@wdc.com btrfs: zoned: fix API misuse of zone finish waiting
Shin'ichiro Kawasaki shinichiro.kawasaki@wdc.com btrfs: zoned: set pseudo max append zone limit in zone emulation mode
Masami Hiramatsu (Google) mhiramat@kernel.org tracing: Fix to check event_mutex is held while accessing trigger list
Yipeng Zou zouyipeng@huawei.com tracing: hold caller_addr to hardirq_{enable,disable}_ip
Brian Norris briannorris@chromium.org tracefs: Only clobber mode/uid/gid on remount if asked
Dongxiang Ke kdx.glider@gmail.com ALSA: usb-audio: Fix an out-of-bounds bug in __snd_usb_parse_audio_interface()
Takashi Iwai tiwai@suse.de ALSA: usb-audio: Clear fixed clock rate at closing EP
Takashi Iwai tiwai@suse.de ALSA: usb-audio: Split endpoint setups for hw_params and prepare
Pattara Teerapong pteerapong@chromium.org ALSA: aloop: Fix random zeros in capture data when using jiffies timer
Takashi Iwai tiwai@suse.de ALSA: hda: Once again fix regression of page allocations with IOMMU
Tasos Sahanidis tasos@tasossah.com ALSA: emu10k1: Fix out of bounds access in snd_emu10k1_pcm_channel_alloc()
Takashi Iwai tiwai@suse.de ALSA: pcm: oss: Fix race at SNDCTL_DSP_SYNC
Qu Huang jinsdb@126.com drm/amdgpu: mmVM_L2_CNTL3 register not initialized correctly
Tim Huang tim.huang@amd.com drm/amdgpu: add sdma instance check for gfx11 CGCG
Borislav Petkov bp@suse.de x86/sev: Mark snp_abort() noreturn
Yang Yingliang yangyingliang@huawei.com fbdev: chipsfb: Add missing pci_disable_device() in chipsfb_pci_init()
Shigeru Yoshida syoshida@redhat.com fbdev: fbcon: Destroy mutex on freeing struct fb_info
Yu Zhe yuzhe@nfschina.com fbdev: omapfb: Fix tests for platform_get_irq() failure
David Sloan david.sloan@eideticom.com md: Flush workqueue md_rdev_misc_wq in md_alloc()
lily floridsleeves@gmail.com net/core/skbuff: Check the return value of skb_copy_bits()
Lukasz Luba lukasz.luba@arm.com cpufreq: check only freq_table in __resolve_freq()
Lee, Chun-Yi joeyli.kernel@gmail.com thermal/int340x_thermal: handle data_vault when the value is ZERO_SIZE_PTR
Florian Westphal fw@strlen.de netfilter: conntrack: work around exceeded receive window
Mark Brown broonie@kernel.org arm64/signal: Raise limit on stack frames
Ionela Voinescu ionela.voinescu@arm.com arm64: errata: add detection for AMEVCNTR01 incrementing incorrectly
Helge Deller deller@gmx.de parisc: Add runtime check to prevent PA2.0 kernels on PA1.x machines
Li Qiong liqiong@nfschina.com parisc: ccio-dma: Handle kmalloc failure in ccio_init_resources()
Helge Deller deller@gmx.de Revert "parisc: Show error if wrong 32/64-bit compiler is being used"
Bart Van Assche bvanassche@acm.org scsi: ufs: core: Reduce the power mode change timeout
Zhenneng Li lizhenneng@kylinos.cn drm/radeon: add a force flush to delay work when radeon
shaoyunl shaoyun.liu@amd.com drm/amdgpu: Remove the additional kfd pre reset call for sriov
Candice Li candice.li@amd.com drm/amdgpu: Check num_gfx_rings for gfx v9_0 rb setup.
YiPeng Chai YiPeng.Chai@amd.com drm/amdgpu: fix hive reference leak when adding xgmi device
YiPeng Chai YiPeng.Chai@amd.com drm/amdgpu: Move psp_xgmi_terminate call from amdgpu_xgmi_remove_device to psp_hw_fini
Jeffy Chen jeffy.chen@rock-chips.com drm/gem: Fix GEM handle release errors
Guixin Liu kanie@linux.alibaba.com scsi: megaraid_sas: Fix double kfree()
Brian Bunker brian@purestorage.com scsi: core: Allow the ALUA transitioning state enough time
Tony Battersby tonyb@cybernetics.com scsi: qla2xxx: Disable ATIO interrupt coalesce for quad port ISP27XX
Yee Lee yee.lee@mediatek.com Revert "mm: kmemleak: take a full lowmem check in kmemleak_*_phys()"
Mathew McBride matt@traverse.com.au soc: fsl: select FSL_GUTS driver for DPIO
Linus Torvalds torvalds@linux-foundation.org fs: only do a memory barrier for the first set_buffer_uptodate()
Greg Kroah-Hartman gregkh@linuxfoundation.org net: mvpp2: debugfs: fix memory leak when using debugfs_lookup()
Stanislaw Gruszka stf_xl@wp.pl wifi: iwlegacy: 4965: corrected fix for potential off-by-one overflow in il4965_rs_fill_link_cmd()
Deren Wu deren.wu@mediatek.com wifi: mt76: mt7921e: fix crash in chip reset fail
Hyunwoo Kim imv4bel@gmail.com efi: capsule-loader: Fix use-after-free in efi_capsule_write
Ard Biesheuvel ardb@kernel.org efi: libstub: Disable struct randomization
-------------
Diffstat:
Documentation/arm64/silicon-errata.rst | 2 + Documentation/hwmon/asus_ec_sensors.rst | 4 + Makefile | 7 +- arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi | 21 +- arch/arm/boot/dts/at91-sama5d2_icp.dts | 21 +- arch/arm/boot/dts/at91-sama7g5ek.dts | 18 +- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 12 +- arch/arm/boot/dts/imx6qdl-vicut1.dtsi | 2 +- arch/arm/mach-at91/pm.c | 36 +- arch/arm/mach-at91/pm_suspend.S | 24 +- arch/arm64/Kconfig | 19 + .../boot/dts/freescale/fsl-ls1028a-qds-65bb.dts | 1 - .../boot/dts/freescale/imx8mm-venice-gw7901.dts | 4 + arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi | 11 +- .../boot/dts/freescale/imx8mp-venice-gw74xx.dts | 8 +- arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi | 4 +- arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi | 1 - arch/arm64/boot/dts/renesas/r8a779g0.dtsi | 2 +- arch/arm64/kernel/cpu_errata.c | 10 + arch/arm64/kernel/cpufeature.c | 5 +- arch/arm64/kernel/hibernate.c | 5 + arch/arm64/kernel/mte.c | 9 + arch/arm64/kernel/signal.c | 2 +- arch/arm64/kernel/topology.c | 32 +- arch/arm64/mm/copypage.c | 9 + arch/arm64/mm/mteswap.c | 9 + arch/arm64/tools/cpucaps | 1 + arch/mips/loongson32/ls1c/board.c | 1 - arch/parisc/include/asm/bitops.h | 8 - arch/parisc/kernel/head.S | 43 +- arch/riscv/boot/dts/microchip/mpfs.dtsi | 2 +- arch/s390/kernel/nmi.c | 2 +- arch/s390/kernel/setup.c | 1 + arch/x86/include/asm/sev.h | 2 +- arch/x86/kernel/sev.c | 2 +- block/partitions/core.c | 3 + drivers/base/driver.c | 6 + drivers/base/regmap/regmap-spi.c | 8 + drivers/cpufreq/cpufreq.c | 2 +- drivers/firmware/efi/capsule-loader.c | 31 +- drivers/firmware/efi/libstub/Makefile | 7 + drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 +- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 3 + drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 18 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 +- drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 + .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 2 +- .../dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c | 18 +- .../drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c | 17 + .../drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c | 14 +- .../drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c | 14 +- .../drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c | 14 +- drivers/gpu/drm/drm_gem.c | 17 +- drivers/gpu/drm/drm_internal.h | 4 +- drivers/gpu/drm/drm_prime.c | 20 +- drivers/gpu/drm/i915/display/intel_bios.c | 7 + .../gpu/drm/i915/display/intel_dp_link_training.c | 22 + drivers/gpu/drm/i915/gt/intel_llc.c | 19 +- drivers/gpu/drm/i915/gt/intel_rps.c | 50 +++ drivers/gpu/drm/i915/gt/intel_rps.h | 2 + drivers/gpu/drm/radeon/radeon_device.c | 3 + drivers/hwmon/asus-ec-sensors.c | 446 ++++++++++++++------- drivers/hwmon/mr75203.c | 72 +++- drivers/hwmon/tps23861.c | 10 +- drivers/infiniband/core/cma.c | 4 +- drivers/infiniband/core/umem_odp.c | 2 +- drivers/infiniband/hw/hns/hns_roce_device.h | 1 - drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 4 +- drivers/infiniband/hw/hns/hns_roce_main.c | 2 +- drivers/infiniband/hw/hns/hns_roce_qp.c | 7 +- drivers/infiniband/hw/irdma/uk.c | 4 +- drivers/infiniband/hw/irdma/utils.c | 15 +- drivers/infiniband/hw/irdma/verbs.c | 13 +- drivers/infiniband/hw/mlx5/mad.c | 6 + drivers/infiniband/sw/siw/siw_qp_tx.c | 18 +- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 9 +- drivers/infiniband/ulp/rtrs/rtrs-srv.c | 14 +- drivers/infiniband/ulp/srp/ib_srp.c | 3 +- drivers/iommu/amd/iommu.c | 3 +- drivers/iommu/amd/iommu_v2.c | 2 + drivers/iommu/intel/dmar.c | 7 + drivers/iommu/intel/iommu.c | 55 ++- drivers/iommu/iommu.c | 21 +- drivers/iommu/virtio-iommu.c | 11 + drivers/md/md.c | 1 + drivers/net/bonding/bond_main.c | 55 ++- drivers/net/dsa/ocelot/felix_vsc9959.c | 162 +++++--- drivers/net/ethernet/freescale/fec.h | 1 - drivers/net/ethernet/freescale/fec_main.c | 17 +- drivers/net/ethernet/freescale/fec_ptp.c | 28 +- drivers/net/ethernet/intel/i40e/i40e.h | 14 + drivers/net/ethernet/intel/i40e/i40e_client.c | 5 +- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 23 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 14 +- drivers/net/ethernet/intel/ice/ice_base.c | 17 - drivers/net/ethernet/intel/ice/ice_main.c | 10 +- drivers/net/ethernet/intel/ice/ice_xsk.c | 63 +++ drivers/net/ethernet/intel/ice/ice_xsk.h | 8 + drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 4 +- drivers/net/ethernet/mediatek/mtk_ppe.c | 2 +- drivers/net/ethernet/mediatek/mtk_ppe.h | 3 + drivers/net/phy/meson-gxl.c | 8 +- drivers/net/phy/microchip_t1.c | 58 ++- drivers/net/wireless/intel/iwlegacy/4965-rs.c | 5 +- .../net/wireless/mediatek/mt76/mt7921/pci_mac.c | 2 +- drivers/net/wireless/microchip/wilc1000/netdev.h | 1 + drivers/net/wireless/microchip/wilc1000/sdio.c | 39 +- drivers/net/wireless/microchip/wilc1000/wlan.c | 15 +- drivers/net/xen-netback/xenbus.c | 2 +- drivers/nvme/host/tcp.c | 7 +- drivers/nvme/target/core.c | 6 +- drivers/nvme/target/zns.c | 17 +- drivers/parisc/ccio-dma.c | 11 +- drivers/perf/riscv_pmu_sbi.c | 2 +- drivers/regulator/core.c | 9 +- drivers/scsi/lpfc/lpfc_init.c | 5 +- drivers/scsi/megaraid/megaraid_sas_fusion.c | 1 - drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- drivers/scsi/qla2xxx/qla_target.c | 10 +- drivers/scsi/scsi_lib.c | 44 +- drivers/soc/bcm/brcmstb/pm/pm-arm.c | 50 ++- drivers/soc/fsl/Kconfig | 1 + drivers/soc/imx/gpcv2.c | 5 +- drivers/soc/imx/imx8m-blk-ctrl.c | 1 - drivers/spi/spi-bitbang-txrx.h | 6 +- drivers/tee/tee_shm.c | 1 + .../intel/int340x_thermal/int3400_thermal.c | 9 +- drivers/ufs/core/ufshcd.c | 9 +- drivers/vfio/vfio_iommu_type1.c | 12 + drivers/video/fbdev/chipsfb.c | 1 + drivers/video/fbdev/core/fbsysfs.c | 4 + drivers/video/fbdev/omap/omapfb_main.c | 4 +- fs/afs/flock.c | 2 +- fs/afs/fsclient.c | 2 +- fs/afs/internal.h | 3 +- fs/afs/rxrpc.c | 7 +- fs/afs/yfsclient.c | 3 +- fs/btrfs/ctree.h | 2 - fs/btrfs/disk-io.c | 1 - fs/btrfs/inode.c | 7 +- fs/btrfs/space-info.c | 2 +- fs/btrfs/volumes.c | 3 + fs/btrfs/zoned.c | 99 ++--- fs/cifs/smb2file.c | 1 - fs/cifs/smb2ops.c | 88 ++-- fs/cifs/smb2pdu.c | 20 +- fs/cifs/smb2proto.h | 4 +- fs/debugfs/inode.c | 22 + fs/erofs/fscache.c | 8 +- fs/erofs/internal.h | 29 -- fs/tracefs/inode.c | 31 +- include/kunit/test.h | 6 +- include/linux/buffer_head.h | 11 + include/linux/debugfs.h | 6 + include/linux/dmar.h | 4 +- include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 3 + include/linux/security.h | 5 + include/linux/skbuff.h | 49 ++- include/linux/time64.h | 3 + include/linux/udp.h | 1 + include/net/bonding.h | 13 +- include/net/udp_tunnel.h | 4 + include/soc/at91/sama7-ddr.h | 8 + io_uring/io_uring.c | 5 + kernel/cgroup/cgroup.c | 85 +++- kernel/cgroup/cpuset.c | 3 +- kernel/dma/swiotlb.c | 5 +- kernel/fork.c | 1 + kernel/kprobes.c | 1 + kernel/sched/debug.c | 2 +- kernel/trace/trace_events_trigger.c | 3 +- kernel/trace/trace_preemptirq.c | 4 +- mm/kmemleak.c | 8 +- net/bridge/br_netfilter_hooks.c | 2 + net/bridge/br_netfilter_ipv6.c | 1 + net/core/datagram.c | 2 +- net/core/skbuff.c | 5 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_input.c | 25 +- net/ipv4/udp.c | 2 + net/ipv4/udp_tunnel_core.c | 1 + net/ipv6/addrconf.c | 8 +- net/ipv6/seg6.c | 5 + net/ipv6/udp.c | 5 +- net/netfilter/nf_conntrack_irc.c | 5 +- net/netfilter/nf_conntrack_proto_tcp.c | 31 ++ net/netfilter/nf_tables_api.c | 4 +- net/rxrpc/ar-internal.h | 1 + net/rxrpc/local_object.c | 1 + net/rxrpc/peer_event.c | 293 ++++++++++++-- net/rxrpc/rxkad.c | 2 +- net/sched/sch_sfb.c | 13 +- net/sched/sch_taprio.c | 5 +- net/smc/smc_core.c | 1 + net/smc/smc_core.h | 2 + net/smc/smc_wr.c | 5 + net/smc/smc_wr.h | 5 + net/tipc/monitor.c | 2 +- security/security.c | 4 + security/selinux/hooks.c | 24 ++ security/selinux/include/classmap.h | 2 +- security/smack/smack_lsm.c | 32 ++ sound/core/memalloc.c | 9 +- sound/core/oss/pcm_oss.c | 6 +- sound/drivers/aloop.c | 7 +- sound/pci/emu10k1/emupcm.c | 2 +- sound/pci/hda/hda_intel.c | 2 +- sound/soc/atmel/mchp-spdiftx.c | 10 +- sound/soc/codecs/cs42l42.c | 13 +- sound/soc/qcom/sm8250.c | 1 + sound/soc/sof/Kconfig | 2 + sound/usb/card.c | 2 +- sound/usb/endpoint.c | 25 +- sound/usb/endpoint.h | 6 +- sound/usb/pcm.c | 14 +- sound/usb/quirks.c | 2 +- sound/usb/stream.c | 9 +- tools/lib/perf/evlist.c | 50 +++ tools/objtool/check.c | 34 +- tools/perf/arch/x86/util/evlist.c | 7 +- tools/perf/builtin-record.c | 8 +- tools/perf/builtin-script.c | 3 + tools/perf/builtin-stat.c | 11 +- tools/perf/dlfilters/dlfilter-show-cycles.c | 4 +- tools/perf/util/evlist.c | 9 +- tools/perf/util/evlist.h | 7 +- 231 files changed, 2460 insertions(+), 1000 deletions(-)
From: Ard Biesheuvel ardb@kernel.org
commit 1a3887924a7e6edd331be76da7bf4c1e8eab4b1e upstream.
The EFI stub is a wrapper around the core kernel that makes it look like a EFI compatible PE/COFF application to the EFI firmware. EFI applications run on top of the EFI runtime, which is heavily based on so-called protocols, which are struct types consisting [mostly] of function pointer members that are instantiated and recorded in a protocol database.
These structs look like the ideal randomization candidates to the randstruct plugin (as they only carry function pointers), but of course, these protocols are contracts between the firmware that exposes them, and the EFI applications (including our stubbed kernel) that invoke them. This means that struct randomization for EFI protocols is not a great idea, and given that the stub shares very little data with the core kernel that is represented as a randomizable struct, we're better off just disabling it completely here.
Cc: stable@vger.kernel.org # v4.14+ Reported-by: Daniel Marth daniel.marth@inso.tuwien.ac.at Tested-by: Daniel Marth daniel.marth@inso.tuwien.ac.at Signed-off-by: Ard Biesheuvel ardb@kernel.org Acked-by: Kees Cook keescook@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/firmware/efi/libstub/Makefile | 7 +++++++ 1 file changed, 7 insertions(+)
--- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -37,6 +37,13 @@ KBUILD_CFLAGS := $(cflags-y) -Os -DDIS $(call cc-option,-fno-addrsig) \ -D__DISABLE_EXPORTS
+# +# struct randomization only makes sense for Linux internal types, which the EFI +# stub code never touches, so let's turn off struct randomization for the stub +# altogether +# +KBUILD_CFLAGS := $(filter-out $(RANDSTRUCT_CFLAGS), $(KBUILD_CFLAGS)) + # remove SCS flags from all objects in this directory KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS)) # disable LTO
From: Hyunwoo Kim imv4bel@gmail.com
commit 9cb636b5f6a8cc6d1b50809ec8f8d33ae0c84c95 upstream.
A race condition may occur if the user calls close() on another thread during a write() operation on the device node of the efi capsule.
This is a race condition that occurs between the efi_capsule_write() and efi_capsule_flush() functions of efi_capsule_fops, which ultimately results in UAF.
So, the page freeing process is modified to be done in efi_capsule_release() instead of efi_capsule_flush().
Cc: stable@vger.kernel.org # v4.9+ Signed-off-by: Hyunwoo Kim imv4bel@gmail.com Link: https://lore.kernel.org/all/20220907102920.GA88602@ubuntu/ Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/firmware/efi/capsule-loader.c | 31 +++++++------------------------ 1 file changed, 7 insertions(+), 24 deletions(-)
--- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -243,29 +243,6 @@ failed: }
/** - * efi_capsule_flush - called by file close or file flush - * @file: file pointer - * @id: not used - * - * If a capsule is being partially uploaded then calling this function - * will be treated as upload termination and will free those completed - * buffer pages and -ECANCELED will be returned. - **/ -static int efi_capsule_flush(struct file *file, fl_owner_t id) -{ - int ret = 0; - struct capsule_info *cap_info = file->private_data; - - if (cap_info->index > 0) { - pr_err("capsule upload not complete\n"); - efi_free_all_buff_pages(cap_info); - ret = -ECANCELED; - } - - return ret; -} - -/** * efi_capsule_release - called by file close * @inode: not used * @file: file pointer @@ -277,6 +254,13 @@ static int efi_capsule_release(struct in { struct capsule_info *cap_info = file->private_data;
+ if (cap_info->index > 0 && + (cap_info->header.headersize == 0 || + cap_info->count < cap_info->total_size)) { + pr_err("capsule upload not complete\n"); + efi_free_all_buff_pages(cap_info); + } + kfree(cap_info->pages); kfree(cap_info->phys); kfree(file->private_data); @@ -324,7 +308,6 @@ static const struct file_operations efi_ .owner = THIS_MODULE, .open = efi_capsule_open, .write = efi_capsule_write, - .flush = efi_capsule_flush, .release = efi_capsule_release, .llseek = no_llseek, };
From: Deren Wu deren.wu@mediatek.com
commit fa3fbe64037839f448dc569212bafc5a495d8219 upstream.
In case of drv own fail in reset, we may need to run mac_reset several times. The sequence would trigger system crash as the log below.
Because we do not re-enable/schedule "tx_napi" before disable it again, the process would keep waiting for state change in napi_diable(). To avoid the problem and keep status synchronize for each run, goto final resource handling if drv own failed.
[ 5857.353423] mt7921e 0000:3b:00.0: driver own failed [ 5858.433427] mt7921e 0000:3b:00.0: Timeout for driver own [ 5859.633430] mt7921e 0000:3b:00.0: driver own failed [ 5859.633444] ------------[ cut here ]------------ [ 5859.633446] WARNING: CPU: 6 at kernel/kthread.c:659 kthread_park+0x11d [ 5859.633717] Workqueue: mt76 mt7921_mac_reset_work [mt7921_common] [ 5859.633728] RIP: 0010:kthread_park+0x11d/0x150 [ 5859.633736] RSP: 0018:ffff8881b676fc68 EFLAGS: 00010202 ...... [ 5859.633766] Call Trace: [ 5859.633768] <TASK> [ 5859.633771] mt7921e_mac_reset+0x176/0x6f0 [mt7921e] [ 5859.633778] mt7921_mac_reset_work+0x184/0x3a0 [mt7921_common] [ 5859.633785] ? mt7921_mac_set_timing+0x520/0x520 [mt7921_common] [ 5859.633794] ? __kasan_check_read+0x11/0x20 [ 5859.633802] process_one_work+0x7ee/0x1320 [ 5859.633810] worker_thread+0x53c/0x1240 [ 5859.633818] kthread+0x2b8/0x370 [ 5859.633824] ? process_one_work+0x1320/0x1320 [ 5859.633828] ? kthread_complete_and_exit+0x30/0x30 [ 5859.633834] ret_from_fork+0x1f/0x30 [ 5859.633842] </TASK>
Cc: stable@vger.kernel.org Fixes: 0efaf31dec57 ("mt76: mt7921: fix MT7921E reset failure") Signed-off-by: Deren Wu deren.wu@mediatek.com Link: https://lore.kernel.org/r/727eb5ffd3c7c805245e512da150ecf0a7154020.165945290... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c @@ -345,7 +345,7 @@ int mt7921e_mac_reset(struct mt7921_dev
err = mt7921e_driver_own(dev); if (err) - return err; + goto out;
err = mt7921_run_firmware(dev); if (err)
From: Stanislaw Gruszka stf_xl@wp.pl
commit 6d0ef7241553f3553a0a2764c69b07892705924c upstream.
This reverts commit a8eb8e6f7159c7c20c0ddac428bde3d110890aa7 as it can cause invalid link quality command sent to the firmware and address the off-by-one issue by fixing condition of while loop.
Cc: stable@vger.kernel.org Fixes: a8eb8e6f7159 ("wifi: iwlegacy: 4965: fix potential off-by-one overflow in il4965_rs_fill_link_cmd()") Signed-off-by: Stanislaw Gruszka stf_xl@wp.pl Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20220815073737.GA999388@wp.pl Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/intel/iwlegacy/4965-rs.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c @@ -2403,7 +2403,7 @@ il4965_rs_fill_link_cmd(struct il_priv * /* Repeat initial/next rate. * For legacy IL_NUMBER_TRY == 1, this loop will not execute. * For HT IL_HT_NUMBER_TRY == 3, this executes twice. */ - while (repeat_rate > 0) { + while (repeat_rate > 0 && idx < (LINK_QUAL_MAX_RETRY_NUM - 1)) { if (is_legacy(tbl_type.lq_type)) { if (ant_toggle_cnt < NUM_TRY_BEFORE_ANT_TOGGLE) ant_toggle_cnt++; @@ -2422,8 +2422,6 @@ il4965_rs_fill_link_cmd(struct il_priv * cpu_to_le32(new_rate); repeat_rate--; idx++; - if (idx >= LINK_QUAL_MAX_RETRY_NUM) - goto out; }
il4965_rs_get_tbl_info_from_mcs(new_rate, lq_sta->band, @@ -2468,7 +2466,6 @@ il4965_rs_fill_link_cmd(struct il_priv * repeat_rate--; }
-out: lq_cmd->agg_params.agg_frame_cnt_limit = LINK_QUAL_AGG_FRAME_LIMIT_DEF; lq_cmd->agg_params.agg_dis_start_th = LINK_QUAL_AGG_DISABLE_START_DEF;
From: Greg Kroah-Hartman gregkh@linuxfoundation.org
commit fe2c9c61f668cde28dac2b188028c5299cedcc1e upstream.
When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. Fix this up to be much simpler logic and only create the root debugfs directory once when the driver is first accessed. That resolves the memory leak and makes things more obvious as to what the intent is.
Cc: Marcin Wojtas mw@semihalf.com Cc: Russell King linux@armlinux.org.uk Cc: "David S. Miller" davem@davemloft.net Cc: Eric Dumazet edumazet@google.com Cc: Jakub Kicinski kuba@kernel.org Cc: Paolo Abeni pabeni@redhat.com Cc: netdev@vger.kernel.org Cc: stable stable@kernel.org Fixes: 21da57a23125 ("net: mvpp2: add a debugfs interface for the Header Parser") Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -700,10 +700,10 @@ void mvpp2_dbgfs_cleanup(struct mvpp2 *p
void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) { - struct dentry *mvpp2_dir, *mvpp2_root; + static struct dentry *mvpp2_root; + struct dentry *mvpp2_dir; int ret, i;
- mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL);
On Tue, Sep 13, 2022 at 04:01:51PM +0200, Greg Kroah-Hartman wrote:
From: Greg Kroah-Hartman gregkh@linuxfoundation.org
commit fe2c9c61f668cde28dac2b188028c5299cedcc1e upstream.
When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. Fix this up to be much simpler logic and only create the root debugfs directory once when the driver is first accessed. That resolves the memory leak and makes things more obvious as to what the intent is.
Cc: Marcin Wojtas mw@semihalf.com Cc: Russell King linux@armlinux.org.uk Cc: "David S. Miller" davem@davemloft.net Cc: Eric Dumazet edumazet@google.com Cc: Jakub Kicinski kuba@kernel.org Cc: Paolo Abeni pabeni@redhat.com Cc: netdev@vger.kernel.org Cc: stable stable@kernel.org Fixes: 21da57a23125 ("net: mvpp2: add a debugfs interface for the Header Parser") Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -700,10 +700,10 @@ void mvpp2_dbgfs_cleanup(struct mvpp2 *p void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) {
- struct dentry *mvpp2_dir, *mvpp2_root;
- static struct dentry *mvpp2_root;
- struct dentry *mvpp2_dir; int ret, i;
- mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL);
This looks broken to me.
What happens if this is built as a module, and the module is loaded, binds (and creates the directory), then is removed, and then re- inserted? Nothing removes the old directory, so doesn't debugfs_create_dir() fail, resulting in subsequent failure to add any subsequent debugfs entries?
I don't think this patch should be backported to stable trees until this point is addressed.
On Tue, Sep 13, 2022 at 05:48:58PM +0100, Russell King (Oracle) wrote:
On Tue, Sep 13, 2022 at 04:01:51PM +0200, Greg Kroah-Hartman wrote:
From: Greg Kroah-Hartman gregkh@linuxfoundation.org
commit fe2c9c61f668cde28dac2b188028c5299cedcc1e upstream.
When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. Fix this up to be much simpler logic and only create the root debugfs directory once when the driver is first accessed. That resolves the memory leak and makes things more obvious as to what the intent is.
Cc: Marcin Wojtas mw@semihalf.com Cc: Russell King linux@armlinux.org.uk Cc: "David S. Miller" davem@davemloft.net Cc: Eric Dumazet edumazet@google.com Cc: Jakub Kicinski kuba@kernel.org Cc: Paolo Abeni pabeni@redhat.com Cc: netdev@vger.kernel.org Cc: stable stable@kernel.org Fixes: 21da57a23125 ("net: mvpp2: add a debugfs interface for the Header Parser") Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -700,10 +700,10 @@ void mvpp2_dbgfs_cleanup(struct mvpp2 *p void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) {
- struct dentry *mvpp2_dir, *mvpp2_root;
- static struct dentry *mvpp2_root;
- struct dentry *mvpp2_dir; int ret, i;
- mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL);
This looks broken to me.
What happens if this is built as a module, and the module is loaded, binds (and creates the directory), then is removed, and then re- inserted? Nothing removes the old directory, so doesn't debugfs_create_dir() fail, resulting in subsequent failure to add any subsequent debugfs entries?
I don't think this patch should be backported to stable trees until this point is addressed.
I'll drop this for now and get back to the fixup next week.
thanks,
greg k-h
From: Linus Torvalds torvalds@linux-foundation.org
commit 2f79cdfe58c13949bbbb65ba5926abfe9561d0ec upstream.
Commit d4252071b97d ("add barriers to buffer_uptodate and set_buffer_uptodate") added proper memory barriers to the buffer head BH_Uptodate bit, so that anybody who tests a buffer for being up-to-date will be guaranteed to actually see initialized state.
However, that commit didn't _just_ add the memory barrier, it also ended up dropping the "was it already set" logic that the BUFFER_FNS() macro had.
That's conceptually the right thing for a generic "this is a memory barrier" operation, but in the case of the buffer contents, we really only care about the memory barrier for the _first_ time we set the bit, in that the only memory ordering protection we need is to avoid anybody seeing uninitialized memory contents.
Any other access ordering wouldn't be about the BH_Uptodate bit anyway, and would require some other proper lock (typically BH_Lock or the folio lock). A reader that races with somebody invalidating the buffer head isn't an issue wrt the memory ordering, it's a serialization issue.
Now, you'd think that the buffer head operations don't matter in this day and age (and I certainly thought so), but apparently some loads still end up being heavy users of buffer heads. In particular, the kernel test robot reported that not having this bit access optimization in place caused a noticeable direct IO performance regression on ext4:
fxmark.ssd_ext4_no_jnl_DWTL_54_directio.works/sec -26.5% regression
although you presumably need a fast disk and a lot of cores to actually notice.
Link: https://lore.kernel.org/all/Yw8L7HTZ%2FdE2%2Fo9C@xsang-OptiPlex-9020/ Reported-by: kernel test robot oliver.sang@intel.com Tested-by: Fengwei Yin fengwei.yin@intel.com Cc: Mikulas Patocka mpatocka@redhat.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: stable@kernel.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/buffer_head.h | 11 +++++++++++ 1 file changed, 11 insertions(+)
--- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -137,6 +137,17 @@ BUFFER_FNS(Defer_Completion, defer_compl static __always_inline void set_buffer_uptodate(struct buffer_head *bh) { /* + * If somebody else already set this uptodate, they will + * have done the memory barrier, and a reader will thus + * see *some* valid buffer state. + * + * Any other serialization (with IO errors or whatever that + * might clear the bit) has to come from other state (eg BH_Lock). + */ + if (test_bit(BH_Uptodate, &bh->b_state)) + return; + + /* * make it consistent with folio_mark_uptodate * pairs with smp_load_acquire in buffer_uptodate */
From: Mathew McBride matt@traverse.com.au
commit 9a472613f5bccf1b36837423495ae592a9c5182f upstream.
The soc/fsl/dpio driver will perform a soc_device_match() to determine the optimal cache settings for a given CPU core.
If FSL_GUTS is not enabled, this search will fail and the driver will not configure cache stashing for the given DPIO, and a string of "unknown SoC" messages will appear:
fsl_mc_dpio dpio.7: unknown SoC version fsl_mc_dpio dpio.6: unknown SoC version fsl_mc_dpio dpio.5: unknown SoC version
Fixes: 51da14e96e9b ("soc: fsl: dpio: configure cache stashing destination") Signed-off-by: Mathew McBride matt@traverse.com.au Reviewed-by: Ioana Ciornei ioana.ciornei@nxp.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220901052149.23873-2-matt@traverse.com.au' Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/soc/fsl/Kconfig | 1 + 1 file changed, 1 insertion(+)
--- a/drivers/soc/fsl/Kconfig +++ b/drivers/soc/fsl/Kconfig @@ -24,6 +24,7 @@ config FSL_MC_DPIO tristate "QorIQ DPAA2 DPIO driver" depends on FSL_MC_BUS select SOC_BUS + select FSL_GUTS select DIMLIB help Driver for the DPAA2 DPIO object. A DPIO provides queue and
From: Yee Lee yee.lee@mediatek.com
This reverts commit 23c2d497de21f25898fbea70aeb292ab8acc8c94.
Commit 23c2d497de21 ("mm: kmemleak: take a full lowmem check in kmemleak_*_phys()") brought false leak alarms on some archs like arm64 that does not init pfn boundary in early booting. The final solution lands on linux-6.0: commit 0c24e061196c ("mm: kmemleak: add rbtree and store physical address for objects allocated with PA").
Revert this commit before linux-6.0. The original issue of invalid PA can be mitigated by additional check in devicetree.
The false alarm report is as following: Kmemleak output: (Qemu/arm64) unreferenced object 0xffff0000c0170a00 (size 128): comm "swapper/0", pid 1, jiffies 4294892404 (age 126.208s) hex dump (first 32 bytes): 62 61 73 65 00 00 00 00 00 00 00 00 00 00 00 00 base............ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<(____ptrval____)>] __kmalloc_track_caller+0x1b0/0x2e4 [<(____ptrval____)>] kstrdup_const+0x8c/0xc4 [<(____ptrval____)>] kvasprintf_const+0xbc/0xec [<(____ptrval____)>] kobject_set_name_vargs+0x58/0xe4 [<(____ptrval____)>] kobject_add+0x84/0x100 [<(____ptrval____)>] __of_attach_node_sysfs+0x78/0xec [<(____ptrval____)>] of_core_init+0x68/0x104 [<(____ptrval____)>] driver_init+0x28/0x48 [<(____ptrval____)>] do_basic_setup+0x14/0x28 [<(____ptrval____)>] kernel_init_freeable+0x110/0x178 [<(____ptrval____)>] kernel_init+0x20/0x1a0 [<(____ptrval____)>] ret_from_fork+0x10/0x20
This pacth is also applicable to linux-5.17.y/linux-5.18.y/linux-5.19.y
Cc: stable@vger.kernel.org Signed-off-by: Yee Lee yee.lee@mediatek.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/kmemleak.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
--- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1132,7 +1132,7 @@ EXPORT_SYMBOL(kmemleak_no_scan); void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, gfp_t gfp) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_alloc(__va(phys), size, min_count, gfp); } EXPORT_SYMBOL(kmemleak_alloc_phys); @@ -1146,7 +1146,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_free_part(__va(phys), size); } EXPORT_SYMBOL(kmemleak_free_part_phys); @@ -1158,7 +1158,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys); */ void __ref kmemleak_not_leak_phys(phys_addr_t phys) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_not_leak(__va(phys)); } EXPORT_SYMBOL(kmemleak_not_leak_phys); @@ -1170,7 +1170,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_ignore(__va(phys)); } EXPORT_SYMBOL(kmemleak_ignore_phys);
From: Tony Battersby tonyb@cybernetics.com
[ Upstream commit 53661ded2460b414644532de6b99bd87f71987e9 ]
This partially reverts commit d2b292c3f6fd ("scsi: qla2xxx: Enable ATIO interrupt handshake for ISP27XX")
For some workloads where the host sends a batch of commands and then pauses, ATIO interrupt coalesce can cause some incoming ATIO entries to be ignored for extended periods of time, resulting in slow performance, timeouts, and aborted commands.
Disable interrupt coalesce and re-enable the dedicated ATIO MSI-X interrupt.
Link: https://lore.kernel.org/r/97dcf365-89ff-014d-a3e5-1404c6af511c@cybernetics.c... Reviewed-by: Himanshu Madhani himanshu.madhani@oracle.com Reviewed-by: Nilesh Javali njavali@marvell.com Signed-off-by: Tony Battersby tonyb@cybernetics.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_target.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 2b2f682883752..62666df1a59eb 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -6935,14 +6935,8 @@ qlt_24xx_config_rings(struct scsi_qla_host *vha)
if (ha->flags.msix_enabled) { if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) { - if (IS_QLA2071(ha)) { - /* 4 ports Baker: Enable Interrupt Handshake */ - icb->msix_atio = 0; - icb->firmware_options_2 |= cpu_to_le32(BIT_26); - } else { - icb->msix_atio = cpu_to_le16(msix->entry); - icb->firmware_options_2 &= cpu_to_le32(~BIT_26); - } + icb->msix_atio = cpu_to_le16(msix->entry); + icb->firmware_options_2 &= cpu_to_le32(~BIT_26); ql_dbg(ql_dbg_init, vha, 0xf072, "Registering ICB vector 0x%x for atio que.\n", msix->entry);
From: Brian Bunker brian@purestorage.com
[ Upstream commit 54249306e2776774ccb827969e62d34570f991db ]
The error path for the SCSI check condition of not ready, target in ALUA state transition, will result in the failure of that path after the retries are exhausted. In most cases that is well ahead of the transition timeout established in the SCSI ALUA device handler.
Instead, reprep the command and re-add it to the queue after a 1 second delay. This will allow the handler to take care of the timeout and only fail the path if the target has exceeded the transition expiry timeout (default 60 seconds). If the expiry timeout is exceeded, the handler will change the path state from transitioning to standby leading to a path failure eliminating the potential of this re-prep to continue endlessly. In most cases the target will exit the transitioning state well before the expiry timeout but after the retries are exhausted as mentioned.
Additionally remove the scsi_io_completion_reprep() function which provides little value.
Link: https://lore.kernel.org/r/20220729214110.58576-1-brian@purestorage.com Reviewed-by: Martin Wilck mwilck@suse.com Acked-by: Krishna Kant krishna.kant@purestorage.com Acked-by: Seamus Connor sconnor@purestorage.com Signed-off-by: Brian Bunker brian@purestorage.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/scsi_lib.c | 44 +++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 19 deletions(-)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 78edb1ea4748d..f5c876d03c1ad 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -118,7 +118,7 @@ scsi_set_blocked(struct scsi_cmnd *cmd, int reason) } }
-static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd) +static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd, unsigned long msecs) { struct request *rq = scsi_cmd_to_rq(cmd);
@@ -128,7 +128,12 @@ static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd) } else { WARN_ON_ONCE(true); } - blk_mq_requeue_request(rq, true); + + if (msecs) { + blk_mq_requeue_request(rq, false); + blk_mq_delay_kick_requeue_list(rq->q, msecs); + } else + blk_mq_requeue_request(rq, true); }
/** @@ -658,14 +663,6 @@ static unsigned int scsi_rq_err_bytes(const struct request *rq) return bytes; }
-/* Helper for scsi_io_completion() when "reprep" action required. */ -static void scsi_io_completion_reprep(struct scsi_cmnd *cmd, - struct request_queue *q) -{ - /* A new command will be prepared and issued. */ - scsi_mq_requeue_cmd(cmd); -} - static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd) { struct request *req = scsi_cmd_to_rq(cmd); @@ -683,14 +680,21 @@ static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd) return false; }
+/* + * When ALUA transition state is returned, reprep the cmd to + * use the ALUA handler's transition timeout. Delay the reprep + * 1 sec to avoid aggressive retries of the target in that + * state. + */ +#define ALUA_TRANSITION_REPREP_DELAY 1000 + /* Helper for scsi_io_completion() when special action required. */ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) { - struct request_queue *q = cmd->device->request_queue; struct request *req = scsi_cmd_to_rq(cmd); int level = 0; - enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY, - ACTION_DELAYED_RETRY} action; + enum {ACTION_FAIL, ACTION_REPREP, ACTION_DELAYED_REPREP, + ACTION_RETRY, ACTION_DELAYED_RETRY} action; struct scsi_sense_hdr sshdr; bool sense_valid; bool sense_current = true; /* false implies "deferred sense" */ @@ -779,8 +783,8 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) action = ACTION_DELAYED_RETRY; break; case 0x0a: /* ALUA state transition */ - blk_stat = BLK_STS_TRANSPORT; - fallthrough; + action = ACTION_DELAYED_REPREP; + break; default: action = ACTION_FAIL; break; @@ -839,7 +843,10 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) return; fallthrough; case ACTION_REPREP: - scsi_io_completion_reprep(cmd, q); + scsi_mq_requeue_cmd(cmd, 0); + break; + case ACTION_DELAYED_REPREP: + scsi_mq_requeue_cmd(cmd, ALUA_TRANSITION_REPREP_DELAY); break; case ACTION_RETRY: /* Retry the same command immediately */ @@ -933,7 +940,7 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result, * command block will be released and the queue function will be goosed. If we * are not done then we have to figure out what to do next: * - * a) We can call scsi_io_completion_reprep(). The request will be + * a) We can call scsi_mq_requeue_cmd(). The request will be * unprepared and put back on the queue. Then a new command will * be created for it. This should be used if we made forward * progress, or if we want to switch from READ(10) to READ(6) for @@ -949,7 +956,6 @@ static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result, void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) { int result = cmd->result; - struct request_queue *q = cmd->device->request_queue; struct request *req = scsi_cmd_to_rq(cmd); blk_status_t blk_stat = BLK_STS_OK;
@@ -986,7 +992,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * request just queue the command up again. */ if (likely(result == 0)) - scsi_io_completion_reprep(cmd, q); + scsi_mq_requeue_cmd(cmd, 0); else scsi_io_completion_action(cmd, result); }
From: Guixin Liu kanie@linux.alibaba.com
[ Upstream commit 8c499e49240bd93628368c3588975cfb94169b8b ]
When allocating log_to_span fails, kfree(instance->ctrl_context) is called twice. Remove redundant call.
Link: https://lore.kernel.org/r/1659424729-46502-1-git-send-email-kanie@linux.alib... Acked-by: Sumit Saxena sumit.saxena@broadcom.com Signed-off-by: Guixin Liu kanie@linux.alibaba.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/megaraid/megaraid_sas_fusion.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 5b5885d9732b6..3e9b2b0099c7a 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -5311,7 +5311,6 @@ megasas_alloc_fusion_context(struct megasas_instance *instance) if (!fusion->log_to_span) { dev_err(&instance->pdev->dev, "Failed from %s %d\n", __func__, __LINE__); - kfree(instance->ctrl_context); return -ENOMEM; } }
From: Jeffy Chen jeffy.chen@rock-chips.com
[ Upstream commit ea2aa97ca37a9044ade001aef71dbc06318e8d44 ]
Currently we are assuming a one to one mapping between dmabuf and GEM handle when releasing GEM handles.
But that is not always true, since we would create extra handles for the GEM obj in cases like gem_open() and getfb{,2}().
A similar issue was reported at: https://lore.kernel.org/all/20211105083308.392156-1-jay.xu@rock-chips.com/
Another problem is that the imported dmabuf might not always have gem_obj->dma_buf set, which would cause leaks in drm_gem_remove_prime_handles().
Let's fix these for now by using handle to find the exact map to remove.
Signed-off-by: Jeffy Chen jeffy.chen@rock-chips.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Christian König christian.koenig@amd.com Link: https://patchwork.freedesktop.org/patch/msgid/20220819072834.17888-1-jeffy.c... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/drm_gem.c | 17 +---------------- drivers/gpu/drm/drm_internal.h | 4 ++-- drivers/gpu/drm/drm_prime.c | 20 ++++++++++++-------- 3 files changed, 15 insertions(+), 26 deletions(-)
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 86d670c712867..ad068865ba206 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -168,21 +168,6 @@ void drm_gem_private_object_init(struct drm_device *dev, } EXPORT_SYMBOL(drm_gem_private_object_init);
-static void -drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp) -{ - /* - * Note: obj->dma_buf can't disappear as long as we still hold a - * handle reference in obj->handle_count. - */ - mutex_lock(&filp->prime.lock); - if (obj->dma_buf) { - drm_prime_remove_buf_handle_locked(&filp->prime, - obj->dma_buf); - } - mutex_unlock(&filp->prime.lock); -} - /** * drm_gem_object_handle_free - release resources bound to userspace handles * @obj: GEM object to clean up. @@ -253,7 +238,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data) if (obj->funcs->close) obj->funcs->close(obj, file_priv);
- drm_gem_remove_prime_handles(obj, file_priv); + drm_prime_remove_buf_handle(&file_priv->prime, id); drm_vma_node_revoke(&obj->vma_node, file_priv);
drm_gem_object_handle_put_unlocked(obj); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 1fbbc19f1ac09..7bb98e6a446d0 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv); void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv); -void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, - struct dma_buf *dma_buf); +void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, + uint32_t handle);
/* drm_drv.c */ struct drm_minor *drm_minor_acquire(unsigned int minor_id); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index e3f09f18110c7..bd5366b16381b 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -190,29 +190,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri return -ENOENT; }
-void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, - struct dma_buf *dma_buf) +void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, + uint32_t handle) { struct rb_node *rb;
- rb = prime_fpriv->dmabufs.rb_node; + mutex_lock(&prime_fpriv->lock); + + rb = prime_fpriv->handles.rb_node; while (rb) { struct drm_prime_member *member;
- member = rb_entry(rb, struct drm_prime_member, dmabuf_rb); - if (member->dma_buf == dma_buf) { + member = rb_entry(rb, struct drm_prime_member, handle_rb); + if (member->handle == handle) { rb_erase(&member->handle_rb, &prime_fpriv->handles); rb_erase(&member->dmabuf_rb, &prime_fpriv->dmabufs);
- dma_buf_put(dma_buf); + dma_buf_put(member->dma_buf); kfree(member); - return; - } else if (member->dma_buf < dma_buf) { + break; + } else if (member->handle < handle) { rb = rb->rb_right; } else { rb = rb->rb_left; } } + + mutex_unlock(&prime_fpriv->lock); }
void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv)
From: YiPeng Chai YiPeng.Chai@amd.com
[ Upstream commit 9d705d7741ae70764f3d6d87e67fad3b5c30ffd0 ]
V1: The amdgpu_xgmi_remove_device function will send unload command to psp through psp ring to terminate xgmi, but psp ring has been destroyed in psp_hw_fini.
V2: 1. Change the commit title. 2. Restore amdgpu_xgmi_remove_device to its original calling location. Move psp_xgmi_terminate call from amdgpu_xgmi_remove_device to psp_hw_fini.
Signed-off-by: YiPeng Chai YiPeng.Chai@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index e9411c28d88ba..2b00f8fe15a89 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2612,6 +2612,9 @@ static int psp_hw_fini(void *handle) psp_rap_terminate(psp); psp_dtm_terminate(psp); psp_hdcp_terminate(psp); + + if (adev->gmc.xgmi.num_physical_nodes > 1) + psp_xgmi_terminate(psp); }
psp_asd_terminate(psp); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c index 1b108d03e7859..f2aebbf3fbe38 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c @@ -742,7 +742,7 @@ int amdgpu_xgmi_remove_device(struct amdgpu_device *adev) amdgpu_put_xgmi_hive(hive); }
- return psp_xgmi_terminate(&adev->psp); + return 0; }
static int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block)
From: YiPeng Chai YiPeng.Chai@amd.com
[ Upstream commit f5994da72ba124a3d0463672fdfbec073e3bb72f ]
Only amdgpu_get_xgmi_hive but no amdgpu_put_xgmi_hive which will leak the hive reference.
Signed-off-by: YiPeng Chai YiPeng.Chai@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3adebb63680e0..ea2b74c0fd229 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2482,12 +2482,14 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (!hive->reset_domain || !amdgpu_reset_get_reset_domain(hive->reset_domain)) { r = -ENOENT; + amdgpu_put_xgmi_hive(hive); goto init_failed; }
/* Drop the early temporary reset domain we created for device */ amdgpu_reset_put_reset_domain(adev->reset_domain); adev->reset_domain = hive->reset_domain; + amdgpu_put_xgmi_hive(hive); } }
From: Candice Li candice.li@amd.com
[ Upstream commit c351938350ab9b5e978dede2c321da43de7eb70c ]
No need to set up rb when no gfx rings.
Signed-off-by: Candice Li candice.li@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 5349ca4d19e38..6d8ff3b099422 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2587,7 +2587,8 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
gfx_v9_0_tiling_mode_table_init(adev);
- gfx_v9_0_setup_rb(adev); + if (adev->gfx.num_gfx_rings) + gfx_v9_0_setup_rb(adev); gfx_v9_0_get_cu_info(adev, &adev->gfx.cu_info); adev->gfx.config.db_debug2 = RREG32_SOC15(GC, 0, mmDB_DEBUG2);
From: shaoyunl shaoyun.liu@amd.com
[ Upstream commit 06671734881af2bcf7f453661b5f8616e32bb3fc ]
The additional call is caused by merge conflict
Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: shaoyunl shaoyun.liu@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 -- 1 file changed, 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index ea2b74c0fd229..67d4a3c13ed19 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4475,8 +4475,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, retry: amdgpu_amdkfd_pre_reset(adev);
- amdgpu_amdkfd_pre_reset(adev); - if (from_hypervisor) r = amdgpu_virt_request_full_gpu(adev, true); else
From: Zhenneng Li lizhenneng@kylinos.cn
[ Upstream commit f461950fdc374a3ada5a63c669d997de4600dffe ]
Although radeon card fence and wait for gpu to finish processing current batch rings, there is still a corner case that radeon lockup work queue may not be fully flushed, and meanwhile the radeon_suspend_kms() function has called pci_set_power_state() to put device in D3hot state. Per PCI spec rev 4.0 on 5.3.1.4.1 D3hot State.
Configuration and Message requests are the only TLPs accepted by a Function in the D3hot state. All other received Requests must be handled as Unsupported Requests, and all received Completions may optionally be handled as Unexpected Completions.
This issue will happen in following logs: Unable to handle kernel paging request at virtual address 00008800e0008010 CPU 0 kworker/0:3(131): Oops 0 pc = [<ffffffff811bea5c>] ra = [<ffffffff81240844>] ps = 0000 Tainted: G W pc is at si_gpu_check_soft_reset+0x3c/0x240 ra is at si_dma_is_lockup+0x34/0xd0 v0 = 0000000000000000 t0 = fff08800e0008010 t1 = 0000000000010000 t2 = 0000000000008010 t3 = fff00007e3c00000 t4 = fff00007e3c00258 t5 = 000000000000ffff t6 = 0000000000000001 t7 = fff00007ef078000 s0 = fff00007e3c016e8 s1 = fff00007e3c00000 s2 = fff00007e3c00018 s3 = fff00007e3c00000 s4 = fff00007fff59d80 s5 = 0000000000000000 s6 = fff00007ef07bd98 a0 = fff00007e3c00000 a1 = fff00007e3c016e8 a2 = 0000000000000008 a3 = 0000000000000001 a4 = 8f5c28f5c28f5c29 a5 = ffffffff810f4338 t8 = 0000000000000275 t9 = ffffffff809b66f8 t10 = ff6769c5d964b800 t11= 000000000000b886 pv = ffffffff811bea20 at = 0000000000000000 gp = ffffffff81d89690 sp = 00000000aa814126 Disabling lock debugging due to kernel taint Trace: [<ffffffff81240844>] si_dma_is_lockup+0x34/0xd0 [<ffffffff81119610>] radeon_fence_check_lockup+0xd0/0x290 [<ffffffff80977010>] process_one_work+0x280/0x550 [<ffffffff80977350>] worker_thread+0x70/0x7c0 [<ffffffff80977410>] worker_thread+0x130/0x7c0 [<ffffffff80982040>] kthread+0x200/0x210 [<ffffffff809772e0>] worker_thread+0x0/0x7c0 [<ffffffff80981f8c>] kthread+0x14c/0x210 [<ffffffff80911658>] ret_from_kernel_thread+0x18/0x20 [<ffffffff80981e40>] kthread+0x0/0x210 Code: ad3e0008 43f0074a ad7e0018 ad9e0020 8c3001e8 40230101 <88210000> 4821ed21 So force lockup work queue flush to fix this problem.
Acked-by: Christian König christian.koenig@amd.com Signed-off-by: Zhenneng Li lizhenneng@kylinos.cn Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/radeon/radeon_device.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 429644d5ddc69..9fba16cb3f1e7 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1604,6 +1604,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, if (r) { /* delay GPU reset to resume */ radeon_fence_driver_force_completion(rdev, i); + } else { + /* finish executing delayed work */ + flush_delayed_work(&rdev->fence_drv[i].lockup_work); } }
From: Bart Van Assche bvanassche@acm.org
[ Upstream commit 8f2c96420c6ec3dcb18c8be923e24c6feaa5ccf6 ]
The current power mode change timeout (180 s) is so large that it can cause a watchdog timer to fire. Reduce the power mode change timeout to 10 seconds.
Link: https://lore.kernel.org/r/20220811234401.1957911-1-bvanassche@acm.org Reviewed-by: Stanley Chu stanley.chu@mediatek.com Signed-off-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ufs/core/ufshcd.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index a51ca56a0ebe7..829da9cb14a86 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8723,6 +8723,8 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, struct scsi_device *sdp; unsigned long flags; int ret, retries; + unsigned long deadline; + int32_t remaining;
spin_lock_irqsave(hba->host->host_lock, flags); sdp = hba->ufs_device_wlun; @@ -8755,9 +8757,14 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, * callbacks hence set the RQF_PM flag so that it doesn't resume the * already suspended childs. */ + deadline = jiffies + 10 * HZ; for (retries = 3; retries > 0; --retries) { + ret = -ETIMEDOUT; + remaining = deadline - jiffies; + if (remaining <= 0) + break; ret = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr, - START_STOP_TIMEOUT, 0, 0, RQF_PM, NULL); + remaining / HZ, 0, 0, RQF_PM, NULL); if (!scsi_status_is_check_condition(ret) || !scsi_sense_valid(&sshdr) || sshdr.sense_key != UNIT_ATTENTION)
From: Helge Deller deller@gmx.de
[ Upstream commit b4b18f47f4f9682fbf5827682645da7c8dde8f80 ]
This reverts commit b160628e9ebcdc85d0db9d7f423c26b3c7c179d0.
There is no need any longer to have this sanity check, because the previous commit ("parisc: Make CONFIG_64BIT available for ARCH=parisc64 only") prevents that CONFIG_64BIT is set if ARCH==parisc.
Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/parisc/include/asm/bitops.h | 8 -------- 1 file changed, 8 deletions(-)
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index 56ffd260c669b..0ec9cfc5131fc 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -12,14 +12,6 @@ #include <asm/barrier.h> #include <linux/atomic.h>
-/* compiler build environment sanity checks: */ -#if !defined(CONFIG_64BIT) && defined(__LP64__) -#error "Please use 'ARCH=parisc' to build the 32-bit kernel." -#endif -#if defined(CONFIG_64BIT) && !defined(__LP64__) -#error "Please use 'ARCH=parisc64' to build the 64-bit kernel." -#endif - /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion * on use of volatile and __*_bit() (set/clear/change): * *_bit() want use of volatile.
From: Li Qiong liqiong@nfschina.com
[ Upstream commit d46c742f827fa2326ab1f4faa1cccadb56912341 ]
As the possible failure of the kmalloc(), it should be better to fix this error path, check and return '-ENOMEM' error code.
Signed-off-by: Li Qiong liqiong@nfschina.com Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/parisc/ccio-dma.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index 9be007c9420f9..f69ab90b5e22d 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -1380,15 +1380,17 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr) } }
-static void __init ccio_init_resources(struct ioc *ioc) +static int __init ccio_init_resources(struct ioc *ioc) { struct resource *res = ioc->mmio_region; char *name = kmalloc(14, GFP_KERNEL); - + if (unlikely(!name)) + return -ENOMEM; snprintf(name, 14, "GSC Bus [%d/]", ioc->hw_path);
ccio_init_resource(res, name, &ioc->ioc_regs->io_io_low); ccio_init_resource(res + 1, name, &ioc->ioc_regs->io_io_low_hv); + return 0; }
static int new_ioc_area(struct resource *res, unsigned long size, @@ -1543,7 +1545,10 @@ static int __init ccio_probe(struct parisc_device *dev) return -ENOMEM; } ccio_ioc_init(ioc); - ccio_init_resources(ioc); + if (ccio_init_resources(ioc)) { + kfree(ioc); + return -ENOMEM; + } hppa_dma_ops = &ccio_ops;
hba = kzalloc(sizeof(*hba), GFP_KERNEL);
From: Helge Deller deller@gmx.de
[ Upstream commit 591d2108f3abc4db9f9073cae37cf3591fd250d6 ]
If a 32-bit kernel was compiled for PA2.0 CPUs, it won't be able to run on machines with PA1.x CPUs. Add a check and bail out early if a PA1.x machine is detected.
Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/parisc/kernel/head.S | 43 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-)
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index e0a9e96576221..fd15fd4bbb61b 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -22,7 +22,7 @@ #include <linux/init.h> #include <linux/pgtable.h>
- .level PA_ASM_LEVEL + .level 1.1
__INITDATA ENTRY(boot_args) @@ -70,6 +70,47 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1)
+#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20) + /* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU + * and halt kernel if we detect a PA1.x CPU. */ + ldi 32,%r10 + mtctl %r10,%cr11 + .level 2.0 + mfctl,w %cr11,%r10 + .level 1.1 + comib,<>,n 0,%r10,$cpu_ok + + load32 PA(msg1),%arg0 + ldi msg1_end-msg1,%arg1 +$iodc_panic: + copy %arg0, %r10 + copy %arg1, %r11 + load32 PA(init_stack),%sp +#define MEM_CONS 0x3A0 + ldw MEM_CONS+32(%r0),%arg0 // HPA + ldi ENTRY_IO_COUT,%arg1 + ldw MEM_CONS+36(%r0),%arg2 // SPA + ldw MEM_CONS+8(%r0),%arg3 // layers + load32 PA(__bss_start),%r1 + stw %r1,-52(%sp) // arg4 + stw %r0,-56(%sp) // arg5 + stw %r10,-60(%sp) // arg6 = ptr to text + stw %r11,-64(%sp) // arg7 = len + stw %r0,-68(%sp) // arg8 + load32 PA(.iodc_panic_ret), %rp + ldw MEM_CONS+40(%r0),%r1 // ENTRY_IODC + bv,n (%r1) +.iodc_panic_ret: + b . /* wait endless with ... */ + or %r10,%r10,%r10 /* qemu idle sleep */ +msg1: .ascii "Can't boot kernel which was built for PA8x00 CPUs on this machine.\r\n" +msg1_end: + +$cpu_ok: +#endif + + .level PA_ASM_LEVEL + /* Initialize startup VM. Just map first 16/32 MB of memory */ load32 PA(swapper_pg_dir),%r4 mtctl %r4,%cr24 /* Initialize kernel root pointer */
From: Ionela Voinescu ionela.voinescu@arm.com
[ Upstream commit e89d120c4b720e232cc6a94f0fcbd59c15d41489 ]
The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate as the system counter. On affected Cortex-A510 cores, AMEVCNTR01 increments incorrectly giving a significantly higher output value. This results in inaccurate task scheduler utilization tracking and incorrect feedback on CPU frequency.
Work around this problem by returning 0 when reading the affected counter in key locations that results in disabling all users of this counter from using it either for frequency invariance or as FFH reference counter. This effect is the same to firmware disabling affected counters.
Details on how the two features are affected by this erratum:
- AMU counters will not be used for frequency invariance for affected CPUs and CPUs in the same cpufreq policy. AMUs can still be used for frequency invariance for unaffected CPUs in the system. Although unlikely, if no alternative method can be found to support frequency invariance for affected CPUs (cpufreq based or solution based on platform counters) frequency invariance will be disabled. Please check the chapter on frequency invariance at Documentation/scheduler/sched-capacity.rst for details of its effect.
- Given that FFH can be used to fetch either the core or constant counter values, restrictions are lifted regarding any of these counters returning a valid (!0) value. Therefore FFH is considered supported if there is a least one CPU that support AMUs, independent of any counters being disabled or affected by this erratum. Clarifying comments are now added to the cpc_ffh_supported(), cpu_read_constcnt() and cpu_read_corecnt() functions.
The above is achieved through adding a new erratum: ARM64_ERRATUM_2457168.
Signed-off-by: Ionela Voinescu ionela.voinescu@arm.com Reviewed-by: Catalin Marinas catalin.marinas@arm.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: Will Deacon will@kernel.org Cc: James Morse james.morse@arm.com Link: https://lore.kernel.org/r/20220819103050.24211-1-ionela.voinescu@arm.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 17 ++++++++++++++ arch/arm64/kernel/cpu_errata.c | 10 ++++++++ arch/arm64/kernel/cpufeature.c | 5 +++- arch/arm64/kernel/topology.c | 32 ++++++++++++++++++++++++-- arch/arm64/tools/cpucaps | 1 + 6 files changed, 64 insertions(+), 3 deletions(-)
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 33b04db8408f9..fda97b3fcf018 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -52,6 +52,8 @@ stable kernels. | Allwinner | A64/R18 | UNKNOWN1 | SUN50I_ERRATUM_UNKNOWN1 | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2064142 | ARM64_ERRATUM_2064142 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2038923 | ARM64_ERRATUM_2038923 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 001eaba5a6b4b..21f33d8d66685 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -914,6 +914,23 @@ config ARM64_ERRATUM_1902691
If unsure, say Y.
+config ARM64_ERRATUM_2457168 + bool "Cortex-A510: 2457168: workaround for AMEVCNTR01 incrementing incorrectly" + depends on ARM64_AMU_EXTN + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 2457168. + + The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate + as the system counter. On affected Cortex-A510 cores AMEVCNTR01 increments + incorrectly giving a significantly higher output value. + + Work around this problem by returning 0 when reading the affected counter in + key locations that results in disabling all users of this counter. This effect + is the same to firmware disabling affected counters. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5f4117dae8888..af137f91607da 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -656,6 +656,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2457168 + { + .desc = "ARM erratum 2457168", + .capability = ARM64_WORKAROUND_2457168, + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, + + /* Cortex-A510 r0p0-r1p1 */ + CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1) + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2038923 { .desc = "ARM erratum 2038923", diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index ebdfbd1cf207b..f34c9f8b9ee0a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1798,7 +1798,10 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n", smp_processor_id()); cpumask_set_cpu(smp_processor_id(), &amu_cpus); - update_freq_counters_refs(); + + /* 0 reference values signal broken/disabled counters */ + if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168)) + update_freq_counters_refs(); } }
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 9ab78ad826e2a..707b5451929d4 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -310,12 +310,25 @@ core_initcall(init_amu_fie);
static void cpu_read_corecnt(void *val) { + /* + * A value of 0 can be returned if the current CPU does not support AMUs + * or if the counter is disabled for this CPU. A return value of 0 at + * counter read is properly handled as an error case by the users of the + * counter. + */ *(u64 *)val = read_corecnt(); }
static void cpu_read_constcnt(void *val) { - *(u64 *)val = read_constcnt(); + /* + * Return 0 if the current CPU is affected by erratum 2457168. A value + * of 0 is also returned if the current CPU does not support AMUs or if + * the counter is disabled. A return value of 0 at counter read is + * properly handled as an error case by the users of the counter. + */ + *(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ? + 0UL : read_constcnt(); }
static inline @@ -342,7 +355,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val) */ bool cpc_ffh_supported(void) { - return freq_counters_valid(get_cpu_with_amu_feat()); + int cpu = get_cpu_with_amu_feat(); + + /* + * FFH is considered supported if there is at least one present CPU that + * supports AMUs. Using FFH to read core and reference counters for CPUs + * that do not support AMUs, have counters disabled or that are affected + * by errata, will result in a return value of 0. + * + * This is done to allow any enabled and valid counters to be read + * through FFH, knowing that potentially returning 0 as counter value is + * properly handled by the users of these counters. + */ + if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask)) + return false; + + return true; }
int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val) diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 8809e14cf86a2..18999f46df19f 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -66,6 +66,7 @@ WORKAROUND_1902691 WORKAROUND_2038923 WORKAROUND_2064142 WORKAROUND_2077057 +WORKAROUND_2457168 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
From: Mark Brown broonie@kernel.org
[ Upstream commit 7ddcaf78e93c9282b4d92184f511b4d5bee75355 ]
The signal code has a limit of 64K on the size of a stack frame that it will generate, if this limit is exceeded then a process will be killed if it receives a signal. Unfortunately with the advent of SME this limit is too small - the maximum possible size of the ZA register alone is 64K. This is not an issue for practical systems at present but is easily seen using virtual platforms.
Raise the limit to 256K, this is substantially more than could be used by any current architecture extension.
Signed-off-by: Mark Brown broonie@kernel.org Acked-by: Catalin Marinas catalin.marinas@arm.com Link: https://lore.kernel.org/r/20220817182324.638214-2-broonie@kernel.org Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 8bb631bf9464c..e8e1f46d383da 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -91,7 +91,7 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user) * not taken into account. This limit is not a guarantee and is * NOT ABI. */ -#define SIGFRAME_MAXSZ SZ_64K +#define SIGFRAME_MAXSZ SZ_256K
static int __sigframe_alloc(struct rt_sigframe_user_layout *user, unsigned long *offset, size_t size, bool extend)
From: Florian Westphal fw@strlen.de
[ Upstream commit cf97769c761abfeac8931b35fe0e1a8d5fabc9d8 ]
When a TCP sends more bytes than allowed by the receive window, all future packets can be marked as invalid. This can clog up the conntrack table because of 5-day default timeout.
Sequence of packets: 01 initiator > responder: [S], seq 171, win 5840, options [mss 1330,sackOK,TS val 63 ecr 0,nop,wscale 1] 02 responder > initiator: [S.], seq 33211, ack 172, win 65535, options [mss 1460,sackOK,TS val 010 ecr 63,nop,wscale 8] 03 initiator > responder: [.], ack 33212, win 2920, options [nop,nop,TS val 068 ecr 010], length 0 04 initiator > responder: [P.], seq 172:240, ack 33212, win 2920, options [nop,nop,TS val 279 ecr 010], length 68
Window is 5840 starting from 33212 -> 39052.
05 responder > initiator: [.], ack 240, win 256, options [nop,nop,TS val 872 ecr 279], length 0 06 responder > initiator: [.], seq 33212:34530, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
This is fine, conntrack will flag the connection as having outstanding data (UNACKED), which lowers the conntrack timeout to 300s.
07 responder > initiator: [.], seq 34530:35848, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318 08 responder > initiator: [.], seq 35848:37166, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318 09 responder > initiator: [.], seq 37166:38484, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318 10 responder > initiator: [.], seq 38484:39802, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 1318
Packet 10 is already sending more than permitted, but conntrack doesn't validate this (only seq is tested vs. maxend, not 'seq+len').
38484 is acceptable, but only up to 39052, so this packet should not have been sent (or only 568 bytes, not 1318).
At this point, connection is still in '300s' mode.
Next packet however will get flagged: 11 responder > initiator: [P.], seq 39802:40128, ack 240, win 256, options [nop,nop,TS val 892 ecr 279], length 326
nf_ct_proto_6: SEQ is over the upper bound (over the window of the receiver) .. LEN=378 .. SEQ=39802 ACK=240 ACK PSH ..
Now, a couple of replies/acks comes in:
12 initiator > responder: [.], ack 34530, win 4368, [.. irrelevant acks removed ] 16 initiator > responder: [.], ack 39802, win 8712, options [nop,nop,TS val 296201291 ecr 2982371892], length 0
This ack is significant -- this acks the last packet send by the responder that conntrack considered valid.
This means that ack == td_end. This will withdraw the 'unacked data' flag, the connection moves back to the 5-day timeout of established conntracks.
17 initiator > responder: ack 40128, win 10030, ...
This packet is also flagged as invalid.
Because conntrack only updates state based on packets that are considered valid, packet 11 'did not exist' and that gets us:
nf_ct_proto_6: ACK is over upper bound 39803 (ACKed data not seen yet) .. SEQ=240 ACK=40128 WINDOW=10030 RES=0x00 ACK URG
Because this received and processed by the endpoints, the conntrack entry remains in a bad state, no packets will ever be considered valid again:
30 responder > initiator: [F.], seq 40432, ack 2045, win 391, .. 31 initiator > responder: [.], ack 40433, win 11348, .. 32 initiator > responder: [F.], seq 2045, ack 40433, win 11348 ..
... all trigger 'ACK is over bound' test and we end up with non-early-evictable 5-day default timeout.
NB: This patch triggers a bunch of checkpatch warnings because of silly indent. I will resend the cleanup series linked below to reduce the indent level once this change has propagated to net-next.
I could route the cleanup via nf but that causes extra backport work for stable maintainers.
Link: https://lore.kernel.org/netfilter-devel/20220720175228.17880-1-fw@strlen.de/... Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_conntrack_proto_tcp.c | 31 ++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index a63b51dceaf2c..a634c72b1ffcf 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -655,6 +655,37 @@ static bool tcp_in_window(struct nf_conn *ct, tn->tcp_be_liberal) res = true; if (!res) { + bool seq_ok = before(seq, sender->td_maxend + 1); + + if (!seq_ok) { + u32 overshot = end - sender->td_maxend + 1; + bool ack_ok; + + ack_ok = after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1); + + if (in_recv_win && + ack_ok && + overshot <= receiver->td_maxwin && + before(sack, receiver->td_end + 1)) { + /* Work around TCPs that send more bytes than allowed by + * the receive window. + * + * If the (marked as invalid) packet is allowed to pass by + * the ruleset and the peer acks this data, then its possible + * all future packets will trigger 'ACK is over upper bound' check. + * + * Thus if only the sequence check fails then do update td_end so + * possible ACK for this data can update internal state. + */ + sender->td_end = end; + sender->flags |= IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED; + + nf_ct_l4proto_log_invalid(skb, ct, hook_state, + "%u bytes more than expected", overshot); + return res; + } + } + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", before(seq, sender->td_maxend + 1) ?
From: Lee, Chun-Yi joeyli.kernel@gmail.com
[ Upstream commit 7931e28098a4c1a2a6802510b0cbe57546d2049d ]
In some case, the GDDV returns a package with a buffer which has zero length. It causes that kmemdup() returns ZERO_SIZE_PTR (0x10).
Then the data_vault_read() got NULL point dereference problem when accessing the 0x10 value in data_vault.
[ 71.024560] BUG: kernel NULL pointer dereference, address: 0000000000000010
This patch uses ZERO_OR_NULL_PTR() for checking ZERO_SIZE_PTR or NULL value in data_vault.
Signed-off-by: "Lee, Chun-Yi" jlee@suse.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/thermal/intel/int340x_thermal/int3400_thermal.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 80d4e0676083a..365489bf4b8c1 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -527,7 +527,7 @@ static void int3400_setup_gddv(struct int3400_thermal_priv *priv) priv->data_vault = kmemdup(obj->package.elements[0].buffer.pointer, obj->package.elements[0].buffer.length, GFP_KERNEL); - if (!priv->data_vault) + if (ZERO_OR_NULL_PTR(priv->data_vault)) goto out_free;
bin_attr_data_vault.private = priv->data_vault; @@ -597,7 +597,7 @@ static int int3400_thermal_probe(struct platform_device *pdev) goto free_imok; }
- if (priv->data_vault) { + if (!ZERO_OR_NULL_PTR(priv->data_vault)) { result = sysfs_create_group(&pdev->dev.kobj, &data_attribute_group); if (result) @@ -615,7 +615,8 @@ static int int3400_thermal_probe(struct platform_device *pdev) free_sysfs: cleanup_odvp(priv); if (priv->data_vault) { - sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group); + if (!ZERO_OR_NULL_PTR(priv->data_vault)) + sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group); kfree(priv->data_vault); } free_uuid: @@ -647,7 +648,7 @@ static int int3400_thermal_remove(struct platform_device *pdev) if (!priv->rel_misc_dev_res) acpi_thermal_rel_misc_device_remove(priv->adev->handle);
- if (priv->data_vault) + if (!ZERO_OR_NULL_PTR(priv->data_vault)) sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group); sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group); sysfs_remove_group(&pdev->dev.kobj, &imok_attribute_group);
From: Lukasz Luba lukasz.luba@arm.com
[ Upstream commit 6ca7076fbfaeccce173aeab832d76b9e49e1034b ]
There is no need to check if the cpufreq driver implements callback cpufreq_driver::target_index. The logic in the __resolve_freq uses the frequency table available in the policy. It doesn't matter if the driver provides 'target_index' or 'target' callback. It just has to populate the 'policy->freq_table'.
Thus, check only frequency table during the frequency resolving call.
Acked-by: Viresh Kumar viresh.kumar@linaro.org Signed-off-by: Lukasz Luba lukasz.luba@arm.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/cpufreq/cpufreq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 2cad427741647..f9fd1b6c15d42 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -532,7 +532,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
target_freq = clamp_val(target_freq, policy->min, policy->max);
- if (!cpufreq_driver->target_index) + if (!policy->freq_table) return target_freq;
idx = cpufreq_frequency_table_target(policy, target_freq, relation);
From: lily floridsleeves@gmail.com
[ Upstream commit c624c58e08b15105662b9ab9be23d14a6b945a49 ]
skb_copy_bits() could fail, which requires a check on the return value.
Signed-off-by: Li Zhong floridsleeves@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/skbuff.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bebf58464d667..4b2b07a9422cf 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4179,9 +4179,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, SKB_GSO_CB(nskb)->csum_start = skb_headroom(nskb) + doffset; } else { - skb_copy_bits(head_skb, offset, - skb_put(nskb, len), - len); + if (skb_copy_bits(head_skb, offset, skb_put(nskb, len), len)) + goto err; } continue; }
From: David Sloan david.sloan@eideticom.com
[ Upstream commit 5e8daf906f890560df430d30617c692a794acb73 ]
A race condition still exists when removing and re-creating md devices in test cases. However, it is only seen on some setups.
The race condition was tracked down to a reference still being held to the kobject by the rdev in the md_rdev_misc_wq which will be released in rdev_delayed_delete().
md_alloc() waits for previous deletions by waiting on the md_misc_wq, but the md_rdev_misc_wq may still be holding a reference to a recently removed device.
To fix this, also flush the md_rdev_misc_wq in md_alloc().
Signed-off-by: David Sloan david.sloan@eideticom.com [logang@deltatee.com: rewrote commit message] Signed-off-by: Logan Gunthorpe logang@deltatee.com Signed-off-by: Song Liu song@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/md.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/md/md.c b/drivers/md/md.c index 91e7e80fce489..25d18b67a1620 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5647,6 +5647,7 @@ static int md_alloc(dev_t dev, char *name) * removed (mddev_delayed_delete). */ flush_workqueue(md_misc_wq); + flush_workqueue(md_rdev_misc_wq);
mutex_lock(&disks_mutex); mddev = mddev_alloc(dev);
From: Yu Zhe yuzhe@nfschina.com
[ Upstream commit acf4c6205e862304681234a6a4375b478af12552 ]
The platform_get_irq() returns negative error codes. It can't actually return zero.
Signed-off-by: Yu Zhe yuzhe@nfschina.com Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/omap/omapfb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c index 292fcb0a24fc9..6ff237cee7f87 100644 --- a/drivers/video/fbdev/omap/omapfb_main.c +++ b/drivers/video/fbdev/omap/omapfb_main.c @@ -1643,14 +1643,14 @@ static int omapfb_do_probe(struct platform_device *pdev, goto cleanup; } fbdev->int_irq = platform_get_irq(pdev, 0); - if (!fbdev->int_irq) { + if (fbdev->int_irq < 0) { dev_err(&pdev->dev, "unable to get irq\n"); r = ENXIO; goto cleanup; }
fbdev->ext_irq = platform_get_irq(pdev, 1); - if (!fbdev->ext_irq) { + if (fbdev->ext_irq < 0) { dev_err(&pdev->dev, "unable to get irq\n"); r = ENXIO; goto cleanup;
From: Shigeru Yoshida syoshida@redhat.com
[ Upstream commit 58559dfc1ebba2ae0c7627dc8f8991ae1984c6e3 ]
It's needed to destroy bl_curve_mutex on freeing struct fb_info since the mutex is embedded in the structure and initialized when it's allocated.
Signed-off-by: Shigeru Yoshida syoshida@redhat.com Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/core/fbsysfs.c | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index c2a60b187467e..4d7f63892dcc4 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -84,6 +84,10 @@ void framebuffer_release(struct fb_info *info) if (WARN_ON(refcount_read(&info->count))) return;
+#if IS_ENABLED(CONFIG_FB_BACKLIGHT) + mutex_destroy(&info->bl_curve_mutex); +#endif + kfree(info->apertures); kfree(info); }
From: Yang Yingliang yangyingliang@huawei.com
[ Upstream commit 07c55c9803dea748d17a054000cbf1913ce06399 ]
Add missing pci_disable_device() in error path in chipsfb_pci_init().
Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/chipsfb.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/video/fbdev/chipsfb.c b/drivers/video/fbdev/chipsfb.c index 393894af26f84..2b00a9d554fc0 100644 --- a/drivers/video/fbdev/chipsfb.c +++ b/drivers/video/fbdev/chipsfb.c @@ -430,6 +430,7 @@ static int chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent) err_release_fb: framebuffer_release(p); err_disable: + pci_disable_device(dp); err_out: return rc; }
From: Borislav Petkov bp@suse.de
[ Upstream commit c93c296fff6b369a7115916145047c8a3db6e27f ]
Mark both the function prototype and definition as noreturn in order to prevent the compiler from doing transformations which confuse objtool like so:
vmlinux.o: warning: objtool: sme_enable+0x71: unreachable instruction
This triggers with gcc-12.
Add it and sev_es_terminate() to the objtool noreturn tracking array too. Sort it while at it.
Suggested-by: Michael Matz matz@suse.de Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/r/20220824152420.20547-1-bp@alien8.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/sev.h | 2 +- arch/x86/kernel/sev.c | 2 +- tools/objtool/check.c | 34 ++++++++++++++++++---------------- 3 files changed, 20 insertions(+), 18 deletions(-)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 4a23e52fe0ee1..ebc271bb6d8ed 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -195,7 +195,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages); void snp_set_memory_private(unsigned long vaddr, unsigned int npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void snp_abort(void); +void __init __noreturn snp_abort(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned long *fw_err); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 4f84c3f11af5b..a428c62330d37 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -2112,7 +2112,7 @@ bool __init snp_init(struct boot_params *bp) return true; }
-void __init snp_abort(void) +void __init __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 31c719f99f66e..5d87e0b0d85f9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -162,32 +162,34 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
/* * Unfortunately these have to be hard coded because the noreturn - * attribute isn't provided in ELF data. + * attribute isn't provided in ELF data. Keep 'em sorted. */ static const char * const global_noreturns[] = { + "__invalid_creds", + "__module_put_and_kthread_exit", + "__reiserfs_panic", "__stack_chk_fail", - "panic", + "__ubsan_handle_builtin_unreachable", + "cpu_bringup_and_idle", + "cpu_startup_entry", "do_exit", + "do_group_exit", "do_task_dead", - "kthread_exit", - "make_task_dead", - "__module_put_and_kthread_exit", + "ex_handler_msr_mce", + "fortify_panic", "kthread_complete_and_exit", - "__reiserfs_panic", + "kthread_exit", + "kunit_try_catch_throw", "lbug_with_loc", - "fortify_panic", - "usercopy_abort", "machine_real_restart", + "make_task_dead", + "panic", "rewind_stack_and_make_dead", - "kunit_try_catch_throw", - "xen_start_kernel", - "cpu_bringup_and_idle", - "do_group_exit", + "sev_es_terminate", + "snp_abort", "stop_this_cpu", - "__invalid_creds", - "cpu_startup_entry", - "__ubsan_handle_builtin_unreachable", - "ex_handler_msr_mce", + "usercopy_abort", + "xen_start_kernel", };
if (!func)
From: Tim Huang tim.huang@amd.com
[ Upstream commit 00047c3d967d7ef8adf8bac3c3579294a3bc0bb1 ]
For some ASICs, like GFX IP v11.0.1, only have one SDMA instance, so not need to configure SDMA1_RLC_CGCG_CTRL for this case.
Signed-off-by: Tim Huang tim.huang@amd.com Reviewed-by: Yifan Zhang yifan1.zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index a4a6751b1e449..30998ac47707c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -5090,9 +5090,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade data = REG_SET_FIELD(data, SDMA0_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1); WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
- data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); - data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1); - WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */ + if (adev->sdma.num_instances > 1) { + data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); + data = REG_SET_FIELD(data, SDMA1_RLC_CGCG_CTRL, CGCG_INT_ENABLE, 1); + WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + } } else { /* Program RLC_CGCG_CGLS_CTRL */ def = data = RREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL); @@ -5121,9 +5124,12 @@ static void gfx_v11_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data);
- data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); - data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; - WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */ + if (adev->sdma.num_instances > 1) { + data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); + data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; + WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); + } } }
From: Qu Huang jinsdb@126.com
[ Upstream commit b8983d42524f10ac6bf35bbce6a7cc8e45f61e04 ]
The mmVM_L2_CNTL3 register is not assigned an initial value
Signed-off-by: Qu Huang jinsdb@126.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 3f44a099c52a4..3e51e773f92be 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -176,6 +176,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1); WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp);
+ tmp = mmVM_L2_CNTL3_DEFAULT; if (adev->gmc.translate_further) { tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12); tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
From: Takashi Iwai tiwai@suse.de
commit 8423f0b6d513b259fdab9c9bf4aaa6188d054c2d upstream.
There is a small race window at snd_pcm_oss_sync() that is called from OSS PCM SNDCTL_DSP_SYNC ioctl; namely the function calls snd_pcm_oss_make_ready() at first, then takes the params_lock mutex for the rest. When the stream is set up again by another thread between them, it leads to inconsistency, and may result in unexpected results such as NULL dereference of OSS buffer as a fuzzer spotted recently.
The fix is simply to cover snd_pcm_oss_make_ready() call into the same params_lock mutex with snd_pcm_oss_make_ready_locked() variant.
Reported-and-tested-by: butt3rflyh4ck butterflyhuangxx@gmail.com Reviewed-by: Jaroslav Kysela perex@perex.cz Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/CAFcO6XN7JDM4xSXGhtusQfS2mSBcx50VJKwQpCq=WeLt57aaZ... Link: https://lore.kernel.org/r/20220905060714.22549-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/core/oss/pcm_oss.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
--- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -1672,14 +1672,14 @@ static int snd_pcm_oss_sync(struct snd_p runtime = substream->runtime; if (atomic_read(&substream->mmap_count)) goto __direct; - err = snd_pcm_oss_make_ready(substream); - if (err < 0) - return err; atomic_inc(&runtime->oss.rw_ref); if (mutex_lock_interruptible(&runtime->oss.params_lock)) { atomic_dec(&runtime->oss.rw_ref); return -ERESTARTSYS; } + err = snd_pcm_oss_make_ready_locked(substream); + if (err < 0) + goto unlock; format = snd_pcm_oss_format_from(runtime->oss.format); width = snd_pcm_format_physical_width(format); if (runtime->oss.buffer_used > 0) {
From: Tasos Sahanidis tasos@tasossah.com
commit d29f59051d3a07b81281b2df2b8c9dfe4716067f upstream.
The voice allocator sometimes begins allocating from near the end of the array and then wraps around, however snd_emu10k1_pcm_channel_alloc() accesses the newly allocated voices as if it never wrapped around.
This results in out of bounds access if the first voice has a high enough index so that first_voice + requested_voice_count > NUM_G (64). The more voices are requested, the more likely it is for this to occur.
This was initially discovered using PipeWire, however it can be reproduced by calling aplay multiple times with 16 channels: aplay -r 48000 -D plughw:CARD=Live,DEV=3 -c 16 /dev/zero
UBSAN: array-index-out-of-bounds in sound/pci/emu10k1/emupcm.c:127:40 index 65 is out of range for type 'snd_emu10k1_voice [64]' CPU: 1 PID: 31977 Comm: aplay Tainted: G W IOE 6.0.0-rc2-emu10k1+ #7 Hardware name: ASUSTEK COMPUTER INC P5W DH Deluxe/P5W DH Deluxe, BIOS 3002 07/22/2010 Call Trace: <TASK> dump_stack_lvl+0x49/0x63 dump_stack+0x10/0x16 ubsan_epilogue+0x9/0x3f __ubsan_handle_out_of_bounds.cold+0x44/0x49 snd_emu10k1_playback_hw_params+0x3bc/0x420 [snd_emu10k1] snd_pcm_hw_params+0x29f/0x600 [snd_pcm] snd_pcm_common_ioctl+0x188/0x1410 [snd_pcm] ? exit_to_user_mode_prepare+0x35/0x170 ? do_syscall_64+0x69/0x90 ? syscall_exit_to_user_mode+0x26/0x50 ? do_syscall_64+0x69/0x90 ? exit_to_user_mode_prepare+0x35/0x170 snd_pcm_ioctl+0x27/0x40 [snd_pcm] __x64_sys_ioctl+0x95/0xd0 do_syscall_64+0x5c/0x90 ? do_syscall_64+0x69/0x90 ? do_syscall_64+0x69/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd
Signed-off-by: Tasos Sahanidis tasos@tasossah.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/3707dcab-320a-62ff-63c0-73fc201ef756@tasossah.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/emu10k1/emupcm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -124,7 +124,7 @@ static int snd_emu10k1_pcm_channel_alloc epcm->voices[0]->epcm = epcm; if (voices > 1) { for (i = 1; i < voices; i++) { - epcm->voices[i] = &epcm->emu->voices[epcm->voices[0]->number + i]; + epcm->voices[i] = &epcm->emu->voices[(epcm->voices[0]->number + i) % NUM_G]; epcm->voices[i]->epcm = epcm; } }
From: Takashi Iwai tiwai@suse.de
commit 37137ec26c2c03039d8064c00f6eae176841ee0d upstream.
The last fix for trying to recover the regression on AMD platforms, unfortunately, leaded to yet another regression: it turned out that IOMMUs don't like the usage of raw page allocations.
This is yet another attempt for addressing the log saga; at this time, we re-use the existing buffer allocation mechanism with SG-pages although we require only single pages. The SG buffer allocation itself was confirmed to work for stream buffers, so it's relatively easy to adapt for other places.
The only problem is: although the HD-audio code is accessing the address directly via dmab->address field, SG-pages don't set up it. For the ease of adaption, we now set up the dmab->addr field from the address of the first page as default, so that it can run with the HD-audio driver code as-is without the excessive call of snd_sgbuf_get_addr() multiple times; that's the only change in the memalloc helper side. The rest is nothing but a flip of the dma_type field in the HD-audio side.
Fixes: a8d302a0b770 ("ALSA: memalloc: Revive x86-specific WC page allocations again") Reported-by: Mikhail Gavrilov mikhail.v.gavrilov@gmail.com Tested-by: Mikhail Gavrilov mikhail.v.gavrilov@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/CABXGCsO+kB2t5QyHY-rUe76npr1m0-5JOtt8g8SiHUo34ur7W... Link: https://bugzilla.kernel.org/show_bug.cgi?id=216112 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216363 Link: https://lore.kernel.org/r/20220906090319.23358-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/core/memalloc.c | 9 +++++++-- sound/pci/hda/hda_intel.c | 2 +- 2 files changed, 8 insertions(+), 3 deletions(-)
--- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -535,10 +535,13 @@ static void *snd_dma_noncontig_alloc(str dmab->dev.need_sync = dma_need_sync(dmab->dev.dev, sg_dma_address(sgt->sgl)); p = dma_vmap_noncontiguous(dmab->dev.dev, size, sgt); - if (p) + if (p) { dmab->private_data = sgt; - else + /* store the first page address for convenience */ + dmab->addr = snd_sgbuf_get_addr(dmab, 0); + } else { dma_free_noncontiguous(dmab->dev.dev, size, sgt, dmab->dev.dir); + } return p; }
@@ -772,6 +775,8 @@ static void *snd_dma_sg_fallback_alloc(s if (!p) goto error; dmab->private_data = sgbuf; + /* store the first page address for convenience */ + dmab->addr = snd_sgbuf_get_addr(dmab, 0); return p;
error: --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1817,7 +1817,7 @@ static int azx_create(struct snd_card *c
/* use the non-cached pages in non-snoop mode */ if (!azx_snoop(chip)) - azx_bus(chip)->dma_type = SNDRV_DMA_TYPE_DEV_WC; + azx_bus(chip)->dma_type = SNDRV_DMA_TYPE_DEV_WC_SG;
if (chip->driver_type == AZX_DRIVER_NVIDIA) { dev_dbg(chip->card->dev, "Enable delay in RIRB handling\n");
From: Pattara Teerapong pteerapong@chromium.org
commit 3e48940abee88b8dbbeeaf8a07e7b2b6be1271b3 upstream.
In loopback_jiffies_timer_pos_update(), we are getting jiffies twice. First time for playback, second time for capture. Jiffies can be updated between these two calls and if the capture jiffies is larger, extra zeros will be filled in the capture buffer.
Change to get jiffies once and use it for both playback and capture.
Signed-off-by: Pattara Teerapong pteerapong@chromium.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220901144036.4049060-1-pteerapong@chromium.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/drivers/aloop.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
--- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -605,17 +605,18 @@ static unsigned int loopback_jiffies_tim cable->streams[SNDRV_PCM_STREAM_PLAYBACK]; struct loopback_pcm *dpcm_capt = cable->streams[SNDRV_PCM_STREAM_CAPTURE]; - unsigned long delta_play = 0, delta_capt = 0; + unsigned long delta_play = 0, delta_capt = 0, cur_jiffies; unsigned int running, count1, count2;
+ cur_jiffies = jiffies; running = cable->running ^ cable->pause; if (running & (1 << SNDRV_PCM_STREAM_PLAYBACK)) { - delta_play = jiffies - dpcm_play->last_jiffies; + delta_play = cur_jiffies - dpcm_play->last_jiffies; dpcm_play->last_jiffies += delta_play; }
if (running & (1 << SNDRV_PCM_STREAM_CAPTURE)) { - delta_capt = jiffies - dpcm_capt->last_jiffies; + delta_capt = cur_jiffies - dpcm_capt->last_jiffies; dpcm_capt->last_jiffies += delta_capt; }
From: Takashi Iwai tiwai@suse.de
commit ff878b408a03bef5d610b7e2302702e16a53636e upstream.
One of the former changes for the endpoint management was the more consistent setup of endpoints at hw_params. snd_usb_endpoint_configure() is a single function that does the full setup, and it's called from both PCM hw_params and prepare callbacks. Although the EP setup at the prepare phase is usually skipped (by checking need_setup flag), it may be still effective in some cases like suspend/resume that requires the interface setup again.
As it's a full and single setup, the invocation of snd_usb_endpoint_configure() includes not only the USB interface setup but also the buffer release and allocation. OTOH, doing the buffer release and re-allocation at PCM prepare phase is rather superfluous, and better to be done only in the hw_params phase.
For those optimizations, this patch splits the endpoint setup to two phases: snd_usb_endpoint_set_params() and snd_usb_endpoint_prepare(), to be called from hw_params and from prepare, respectively.
Note that this patch changes the driver operation slightly, effectively moving the USB interface setup again to PCM prepare stage instead of hw_params stage, while the buffer allocation and such initializations are still done at hw_params stage.
And, the change of the USB interface setup timing (moving to prepare) gave an interesting "fix", too: it was reported that the recent kernels caused silent output at the beginning on playbacks on some devices on Android, and this change casually fixed the regression. It seems that those devices are picky about the sample rate change (or the interface change?), and don't follow the too immediate rate changes.
Meanwhile, Android operates the PCM in the following order: - open, then hw_params with the possibly highest sample rate - close without prepare - re-open, hw_params with the normal sample rate - prepare, and start streaming This procedure ended up the hw_params twice with different rates, and because the recent kernel did set up the sample rate twice one and after, it screwed up the device. OTOH, the earlier kernels didn't set up the USB interface at hw_params, hence this problem didn't appear.
Now, with this patch, the USB interface setup is again back to the prepare phase, and it works around the problem automagically. Although we should address the sample rate problem in a more solid way in future, let's keep things working as before for now.
Fixes: bf6313a0ff76 ("ALSA: usb-audio: Refactor endpoint management") Cc: stable@vger.kernel.org Reported-by: chihhao chen chihhao.chen@mediatek.com Link: https://lore.kernel.org/r/87e6d6ae69d68dc588ac9acc8c0f24d6188375c3.camel@med... Link: https://lore.kernel.org/r/20220901124136.4984-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/endpoint.c | 23 +++++++++-------------- sound/usb/endpoint.h | 6 ++++-- sound/usb/pcm.c | 14 ++++++++++---- 3 files changed, 23 insertions(+), 20 deletions(-)
--- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -758,7 +758,8 @@ bool snd_usb_endpoint_compatible(struct * The endpoint needs to be closed via snd_usb_endpoint_close() later. * * Note that this function doesn't configure the endpoint. The substream - * needs to set it up later via snd_usb_endpoint_configure(). + * needs to set it up later via snd_usb_endpoint_set_params() and + * snd_usb_endpoint_prepare(). */ struct snd_usb_endpoint * snd_usb_endpoint_open(struct snd_usb_audio *chip, @@ -1290,12 +1291,13 @@ out_of_memory: /* * snd_usb_endpoint_set_params: configure an snd_usb_endpoint * + * It's called either from hw_params callback. * Determine the number of URBs to be used on this endpoint. * An endpoint must be configured before it can be started. * An endpoint that is already running can not be reconfigured. */ -static int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, - struct snd_usb_endpoint *ep) +int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, + struct snd_usb_endpoint *ep) { const struct audioformat *fmt = ep->cur_audiofmt; int err; @@ -1378,18 +1380,18 @@ static int init_sample_rate(struct snd_u }
/* - * snd_usb_endpoint_configure: Configure the endpoint + * snd_usb_endpoint_prepare: Prepare the endpoint * * This function sets up the EP to be fully usable state. - * It's called either from hw_params or prepare callback. + * It's called either from prepare callback. * The function checks need_setup flag, and performs nothing unless needed, * so it's safe to call this multiple times. * * This returns zero if unchanged, 1 if the configuration has changed, * or a negative error code. */ -int snd_usb_endpoint_configure(struct snd_usb_audio *chip, - struct snd_usb_endpoint *ep) +int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, + struct snd_usb_endpoint *ep) { bool iface_first; int err = 0; @@ -1410,9 +1412,6 @@ int snd_usb_endpoint_configure(struct sn if (err < 0) goto unlock; } - err = snd_usb_endpoint_set_params(chip, ep); - if (err < 0) - goto unlock; goto done; }
@@ -1440,10 +1439,6 @@ int snd_usb_endpoint_configure(struct sn if (err < 0) goto unlock;
- err = snd_usb_endpoint_set_params(chip, ep); - if (err < 0) - goto unlock; - err = snd_usb_select_mode_quirk(chip, ep->cur_audiofmt); if (err < 0) goto unlock; --- a/sound/usb/endpoint.h +++ b/sound/usb/endpoint.h @@ -17,8 +17,10 @@ snd_usb_endpoint_open(struct snd_usb_aud bool is_sync_ep); void snd_usb_endpoint_close(struct snd_usb_audio *chip, struct snd_usb_endpoint *ep); -int snd_usb_endpoint_configure(struct snd_usb_audio *chip, - struct snd_usb_endpoint *ep); +int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, + struct snd_usb_endpoint *ep); +int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, + struct snd_usb_endpoint *ep); int snd_usb_endpoint_get_clock_rate(struct snd_usb_audio *chip, int clock);
bool snd_usb_endpoint_compatible(struct snd_usb_audio *chip, --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -443,17 +443,17 @@ static int configure_endpoints(struct sn if (stop_endpoints(subs, false)) sync_pending_stops(subs); if (subs->sync_endpoint) { - err = snd_usb_endpoint_configure(chip, subs->sync_endpoint); + err = snd_usb_endpoint_prepare(chip, subs->sync_endpoint); if (err < 0) return err; } - err = snd_usb_endpoint_configure(chip, subs->data_endpoint); + err = snd_usb_endpoint_prepare(chip, subs->data_endpoint); if (err < 0) return err; snd_usb_set_format_quirk(subs, subs->cur_audiofmt); } else { if (subs->sync_endpoint) { - err = snd_usb_endpoint_configure(chip, subs->sync_endpoint); + err = snd_usb_endpoint_prepare(chip, subs->sync_endpoint); if (err < 0) return err; } @@ -551,7 +551,13 @@ static int snd_usb_hw_params(struct snd_ subs->cur_audiofmt = fmt; mutex_unlock(&chip->mutex);
- ret = configure_endpoints(chip, subs); + if (subs->sync_endpoint) { + ret = snd_usb_endpoint_set_params(chip, subs->sync_endpoint); + if (ret < 0) + goto unlock; + } + + ret = snd_usb_endpoint_set_params(chip, subs->data_endpoint);
unlock: if (ret < 0)
From: Takashi Iwai tiwai@suse.de
commit 809f44a0cc5ad4b1209467a6287f8ac0eb49d393 upstream.
The recent commit c11117b634f4 ("ALSA: usb-audio: Refcount multiple accesses on the single clock") tries to manage the clock rate shared by several endpoints. This was intended for avoiding the unmatched rate by a different endpoint, but unfortunately, it introduced a regression for PulseAudio and pipewire, too; those applications try to probe the multiple possible rates (44.1k and 48kHz) and setting up the normal rate fails but only the last rate is applied.
The cause is that the last sample rate is still left to the clock reference even after closing the endpoint, and this value is still used at the next open. It happens only when applications set up via PCM prepare but don't start/stop the stream; the rate is reset when the stream is stopped, but it's not cleared at close.
This patch addresses the issue above, simply by clearing the rate set in the clock reference at the last close of each endpoint.
Fixes: c11117b634f4 ("ALSA: usb-audio: Refcount multiple accesses on the single clock") Reported-by: Jason A. Donenfeld Jason@zx2c4.com Tested-by: Jason A. Donenfeld Jason@zx2c4.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/YxXIWv8dYmg1tnXP@zx2c4.com/ Link: https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/2620 Link: https://lore.kernel.org/r/20220907100421.6443-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/endpoint.c | 2 ++ 1 file changed, 2 insertions(+)
--- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -925,6 +925,8 @@ void snd_usb_endpoint_close(struct snd_u endpoint_set_interface(chip, ep, false);
if (!--ep->opened) { + if (ep->clock_ref && !atomic_read(&ep->clock_ref->locked)) + ep->clock_ref->rate = 0; ep->iface = 0; ep->altsetting = 0; ep->cur_audiofmt = NULL;
From: Dongxiang Ke kdx.glider@gmail.com
commit e53f47f6c1a56d2af728909f1cb894da6b43d9bf upstream.
There may be a bad USB audio device with a USB ID of (0x04fa, 0x4201) and the number of it's interfaces less than 4, an out-of-bounds read bug occurs when parsing the interface descriptor for this device.
Fix this by checking the number of interfaces.
Signed-off-by: Dongxiang Ke kdx.glider@gmail.com Link: https://lore.kernel.org/r/20220906024928.10951-1-kdx.glider@gmail.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/stream.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -1105,7 +1105,7 @@ static int __snd_usb_parse_audio_interfa * Dallas DS4201 workaround: It presents 5 altsettings, but the last * one misses syncpipe, and does not produce any sound. */ - if (chip->usb_id == USB_ID(0x04fa, 0x4201)) + if (chip->usb_id == USB_ID(0x04fa, 0x4201) && num >= 4) num = 4;
for (i = 0; i < num; i++) {
From: Brian Norris briannorris@chromium.org
commit 47311db8e8f33011d90dee76b39c8886120cdda4 upstream.
Users may have explicitly configured their tracefs permissions; we shouldn't overwrite those just because a second mount appeared.
Only clobber if the options were provided at mount time.
Note: the previous behavior was especially surprising in the presence of automounted /sys/kernel/debug/tracing/.
Existing behavior:
## Pre-existing status: tracefs is 0755. # stat -c '%A' /sys/kernel/tracing/ drwxr-xr-x
## (Re)trigger the automount. # umount /sys/kernel/debug/tracing # stat -c '%A' /sys/kernel/debug/tracing/. drwx------
## Unexpected: the automount changed mode for other mount instances. # stat -c '%A' /sys/kernel/tracing/ drwx------
New behavior (after this change):
## Pre-existing status: tracefs is 0755. # stat -c '%A' /sys/kernel/tracing/ drwxr-xr-x
## (Re)trigger the automount. # umount /sys/kernel/debug/tracing # stat -c '%A' /sys/kernel/debug/tracing/. drwxr-xr-x
## Expected: the automount does not change other mount instances. # stat -c '%A' /sys/kernel/tracing/ drwxr-xr-x
Link: https://lkml.kernel.org/r/20220826174353.2.Iab6e5ea57963d6deca5311b27fb72267...
Cc: stable@vger.kernel.org Fixes: 4282d60689d4f ("tracefs: Add new tracefs file system") Signed-off-by: Brian Norris briannorris@chromium.org Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/tracefs/inode.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-)
--- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -141,6 +141,8 @@ struct tracefs_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; + /* Opt_* bitfield. */ + unsigned int opts; };
enum { @@ -241,6 +243,7 @@ static int tracefs_parse_options(char *d kgid_t gid; char *p;
+ opts->opts = 0; opts->mode = TRACEFS_DEFAULT_MODE;
while ((p = strsep(&data, ",")) != NULL) { @@ -275,24 +278,36 @@ static int tracefs_parse_options(char *d * but traditionally tracefs has ignored all mount options */ } + + opts->opts |= BIT(token); }
return 0; }
-static int tracefs_apply_options(struct super_block *sb) +static int tracefs_apply_options(struct super_block *sb, bool remount) { struct tracefs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); struct tracefs_mount_opts *opts = &fsi->mount_opts;
- inode->i_mode &= ~S_IALLUGO; - inode->i_mode |= opts->mode; + /* + * On remount, only reset mode/uid/gid if they were provided as mount + * options. + */ + + if (!remount || opts->opts & BIT(Opt_mode)) { + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= opts->mode; + }
- inode->i_uid = opts->uid; + if (!remount || opts->opts & BIT(Opt_uid)) + inode->i_uid = opts->uid;
- /* Set all the group ids to the mount option */ - set_gid(sb->s_root, opts->gid); + if (!remount || opts->opts & BIT(Opt_gid)) { + /* Set all the group ids to the mount option */ + set_gid(sb->s_root, opts->gid); + }
return 0; } @@ -307,7 +322,7 @@ static int tracefs_remount(struct super_ if (err) goto fail;
- tracefs_apply_options(sb); + tracefs_apply_options(sb, true);
fail: return err; @@ -359,7 +374,7 @@ static int trace_fill_super(struct super
sb->s_op = &tracefs_super_operations;
- tracefs_apply_options(sb); + tracefs_apply_options(sb, false);
return 0;
From: Yipeng Zou zouyipeng@huawei.com
commit 54c3931957f6a6194d5972eccc36d052964b2abe upstream.
Currently, The arguments passing to lockdep_hardirqs_{on,off} was fixed in CALLER_ADDR0. The function trace_hardirqs_on_caller should have been intended to use caller_addr to represent the address that caller wants to be traced.
For example, lockdep log in riscv showing the last {enabled,disabled} at __trace_hardirqs_{on,off} all the time(if called by): [ 57.853175] hardirqs last enabled at (2519): __trace_hardirqs_on+0xc/0x14 [ 57.853848] hardirqs last disabled at (2520): __trace_hardirqs_off+0xc/0x14
After use trace_hardirqs_xx_caller, we can get more effective information: [ 53.781428] hardirqs last enabled at (2595): restore_all+0xe/0x66 [ 53.782185] hardirqs last disabled at (2596): ret_from_exception+0xa/0x10
Link: https://lkml.kernel.org/r/20220901104515.135162-2-zouyipeng@huawei.com
Cc: stable@vger.kernel.org Fixes: c3bc8fd637a96 ("tracing: Centralize preemptirq tracepoints and unify their usage") Signed-off-by: Yipeng Zou zouyipeng@huawei.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_preemptirq.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
--- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -95,14 +95,14 @@ __visible void trace_hardirqs_on_caller( }
lockdep_hardirqs_on_prepare(); - lockdep_hardirqs_on(CALLER_ADDR0); + lockdep_hardirqs_on(caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
__visible void trace_hardirqs_off_caller(unsigned long caller_addr) { - lockdep_hardirqs_off(CALLER_ADDR0); + lockdep_hardirqs_off(caller_addr);
if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1);
From: Masami Hiramatsu (Google) mhiramat@kernel.org
commit cecf8e128ec69149fe53c9a7bafa505a4bee25d9 upstream.
Since the check_user_trigger() is called outside of RCU read lock, this list_for_each_entry_rcu() caused a suspicious RCU usage warning.
# echo hist:keys=pid > events/sched/sched_stat_runtime/trigger # cat events/sched/sched_stat_runtime/trigger [ 43.167032] [ 43.167418] ============================= [ 43.167992] WARNING: suspicious RCU usage [ 43.168567] 5.19.0-rc5-00029-g19ebe4651abf #59 Not tainted [ 43.169283] ----------------------------- [ 43.169863] kernel/trace/trace_events_trigger.c:145 RCU-list traversed in non-reader section!! ...
However, this file->triggers list is safe when it is accessed under event_mutex is held. To fix this warning, adds a lockdep_is_held check to the list_for_each_entry_rcu().
Link: https://lkml.kernel.org/r/166226474977.223837.1992182913048377113.stgit@devn...
Cc: stable@vger.kernel.org Fixes: 7491e2c44278 ("tracing: Add a probe that attaches to trace events") Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_events_trigger.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
--- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -142,7 +142,8 @@ static bool check_user_trigger(struct tr { struct event_trigger_data *data;
- list_for_each_entry_rcu(data, &file->triggers, list) { + list_for_each_entry_rcu(data, &file->triggers, list, + lockdep_is_held(&event_mutex)) { if (data->flags & EVENT_TRIGGER_FL_PROBE) continue; return true;
From: Shin'ichiro Kawasaki shinichiro.kawasaki@wdc.com
commit cac5c44c48c9fb9cc31bea15ebd9ef0c6462314f upstream.
The commit 7d7672bc5d10 ("btrfs: convert count_max_extents() to use fs_info->max_extent_size") introduced a division by fs_info->max_extent_size. This max_extent_size is initialized with max zone append limit size of the device btrfs runs on. However, in zone emulation mode, the device is not zoned then its zone append limit is zero. This resulted in zero value of fs_info->max_extent_size and caused zero division error.
Fix the error by setting non-zero pseudo value to max append zone limit in zone emulation mode. Set the pseudo value based on max_segments as suggested in the commit c2ae7b772ef4 ("btrfs: zoned: revive max_zone_append_bytes").
Fixes: 7d7672bc5d10 ("btrfs: convert count_max_extents() to use fs_info->max_extent_size") CC: stable@vger.kernel.org # 5.12+ Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Reviewed-by: Naohiro Aota naohiro.aota@wdc.com Signed-off-by: Shin'ichiro Kawasaki shinichiro.kawasaki@wdc.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/zoned.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)
--- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -421,10 +421,19 @@ int btrfs_get_dev_zone_info(struct btrfs * since btrfs adds the pages one by one to a bio, and btrfs cannot * increase the metadata reservation even if it increases the number of * extents, it is safe to stick with the limit. + * + * With the zoned emulation, we can have non-zoned device on the zoned + * mode. In this case, we don't have a valid max zone append size. So, + * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size. */ - zone_info->max_zone_append_size = - min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, - (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + if (bdev_is_zoned(bdev)) { + zone_info->max_zone_append_size = min_t(u64, + (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, + (u64)bdev_max_segments(bdev) << PAGE_SHIFT); + } else { + zone_info->max_zone_append_size = + (u64)bdev_max_segments(bdev) << PAGE_SHIFT; + } if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++;
From: Naohiro Aota naohiro.aota@wdc.com
commit d5b81ced74afded85619ffbbe9c32ba9d82c9b1e upstream.
The commit 2ce543f47843 ("btrfs: zoned: wait until zone is finished when allocation didn't progress") implemented a zone finish waiting mechanism to the write path of zoned mode. However, using wait_var_event()/wake_up_all() on fs_info->zone_finish_wait is wrong and wait_var_event() just hangs because no one ever wakes it up once it goes into sleep.
Instead, we can simply use wait_on_bit_io() and clear_and_wake_up_bit() on fs_info->flags with a proper barrier installed.
Fixes: 2ce543f47843 ("btrfs: zoned: wait until zone is finished when allocation didn't progress") CC: stable@vger.kernel.org # 5.16+ Signed-off-by: Naohiro Aota naohiro.aota@wdc.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/ctree.h | 2 -- fs/btrfs/disk-io.c | 1 - fs/btrfs/inode.c | 7 +++---- fs/btrfs/zoned.c | 3 +-- 4 files changed, 4 insertions(+), 9 deletions(-)
--- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1065,8 +1065,6 @@ struct btrfs_fs_info {
spinlock_t zone_active_bgs_lock; struct list_head zone_active_bgs; - /* Waiters when BTRFS_FS_NEED_ZONE_FINISH is set */ - wait_queue_head_t zone_finish_wait;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY spinlock_t ref_verify_lock; --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3173,7 +3173,6 @@ void btrfs_init_fs_info(struct btrfs_fs_ init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); init_waitqueue_head(&fs_info->delayed_iputs_wait); - init_waitqueue_head(&fs_info->zone_finish_wait);
/* Usable values until the real ones are cached from the superblock */ fs_info->nodesize = 4096; --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1643,10 +1643,9 @@ static noinline int run_delalloc_zoned(s done_offset = end;
if (done_offset == start) { - struct btrfs_fs_info *info = inode->root->fs_info; - - wait_var_event(&info->zone_finish_wait, - !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags)); + wait_on_bit_io(&inode->root->fs_info->flags, + BTRFS_FS_NEED_ZONE_FINISH, + TASK_UNINTERRUPTIBLE); continue; }
--- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2016,8 +2016,7 @@ static int do_zone_finish(struct btrfs_b /* For active_bg_list */ btrfs_put_block_group(block_group);
- clear_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags); - wake_up_all(&fs_info->zone_finish_wait); + clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
return 0; }
From: Alex Williamson alex.williamson@redhat.com
commit 873aefb376bbc0ed1dd2381ea1d6ec88106fdbd4 upstream.
There's currently a reference count leak on the zero page. We increment the reference via pin_user_pages_remote(), but the page is later handled as an invalid/reserved page, therefore it's not accounted against the user and not unpinned by our put_pfn().
Introducing special zero page handling in put_pfn() would resolve the leak, but without accounting of the zero page, a single user could still create enough mappings to generate a reference count overflow.
The zero page is always resident, so for our purposes there's no reason to keep it pinned. Therefore, add a loop to walk pages returned from pin_user_pages_remote() and unpin any zero pages.
Cc: stable@vger.kernel.org Reported-by: Luboslav Pivarc lpivarc@redhat.com Reviewed-by: David Hildenbrand david@redhat.com Link: https://lore.kernel.org/r/166182871735.3518559.8884121293045337358.stgit@ome... Signed-off-by: Alex Williamson alex.williamson@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/vfio/vfio_iommu_type1.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
--- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -557,6 +557,18 @@ static int vaddr_get_pfns(struct mm_stru ret = pin_user_pages_remote(mm, vaddr, npages, flags | FOLL_LONGTERM, pages, NULL, NULL); if (ret > 0) { + int i; + + /* + * The zero page is always resident, we don't need to pin it + * and it falls into our invalid/reserved test so we don't + * unpin in put_pfn(). Unpin all zero pages in the batch here. + */ + for (i = 0 ; i < ret; i++) { + if (unlikely(is_zero_pfn(page_to_pfn(pages[i])))) + unpin_user_page(pages[i]); + } + *pfn = page_to_pfn(pages[0]); goto done; }
From: Christian A. Ehrhardt lk@c--e.de
commit 1efda38d6f9ba26ac88b359c6277f1172db03f1e upstream.
The system call gate area counts as kernel text but trying to install a kprobe in this area fails with an Oops later on. To fix this explicitly disallow the gate area for kprobes.
Found by syzkaller with the following reproducer: perf_event_open$cgroup(&(0x7f00000001c0)={0x6, 0x80, 0x0, 0x0, 0x0, 0x0, 0x80ffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, @perf_config_ext={0x0, 0xffffffffff600000}}, 0xffffffffffffffff, 0x0, 0xffffffffffffffff, 0x0)
Sample report: BUG: unable to handle page fault for address: fffffbfff3ac6000 PGD 6dfcb067 P4D 6dfcb067 PUD 6df8f067 PMD 6de4d067 PTE 0 Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 0 PID: 21978 Comm: syz-executor.2 Not tainted 6.0.0-rc3-00363-g7726d4c3e60b-dirty #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 RIP: 0010:__insn_get_emulate_prefix arch/x86/lib/insn.c:91 [inline] RIP: 0010:insn_get_emulate_prefix arch/x86/lib/insn.c:106 [inline] RIP: 0010:insn_get_prefixes.part.0+0xa8/0x1110 arch/x86/lib/insn.c:134 Code: 49 be 00 00 00 00 00 fc ff df 48 8b 40 60 48 89 44 24 08 e9 81 00 00 00 e8 e5 4b 39 ff 4c 89 fa 4c 89 f9 48 c1 ea 03 83 e1 07 <42> 0f b6 14 32 38 ca 7f 08 84 d2 0f 85 06 10 00 00 48 89 d8 48 89 RSP: 0018:ffffc900088bf860 EFLAGS: 00010246 RAX: 0000000000040000 RBX: ffffffff9b9bebc0 RCX: 0000000000000000 RDX: 1ffffffff3ac6000 RSI: ffffc90002d82000 RDI: ffffc900088bf9e8 RBP: ffffffff9d630001 R08: 0000000000000000 R09: ffffc900088bf9e8 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000001 R13: ffffffff9d630000 R14: dffffc0000000000 R15: ffffffff9d630000 FS: 00007f63eef63640(0000) GS:ffff88806d000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff3ac6000 CR3: 0000000029d90005 CR4: 0000000000770ef0 PKRU: 55555554 Call Trace: <TASK> insn_get_prefixes arch/x86/lib/insn.c:131 [inline] insn_get_opcode arch/x86/lib/insn.c:272 [inline] insn_get_modrm+0x64a/0x7b0 arch/x86/lib/insn.c:343 insn_get_sib+0x29a/0x330 arch/x86/lib/insn.c:421 insn_get_displacement+0x350/0x6b0 arch/x86/lib/insn.c:464 insn_get_immediate arch/x86/lib/insn.c:632 [inline] insn_get_length arch/x86/lib/insn.c:707 [inline] insn_decode+0x43a/0x490 arch/x86/lib/insn.c:747 can_probe+0xfc/0x1d0 arch/x86/kernel/kprobes/core.c:282 arch_prepare_kprobe+0x79/0x1c0 arch/x86/kernel/kprobes/core.c:739 prepare_kprobe kernel/kprobes.c:1160 [inline] register_kprobe kernel/kprobes.c:1641 [inline] register_kprobe+0xb6e/0x1690 kernel/kprobes.c:1603 __register_trace_kprobe kernel/trace/trace_kprobe.c:509 [inline] __register_trace_kprobe+0x26a/0x2d0 kernel/trace/trace_kprobe.c:477 create_local_trace_kprobe+0x1f7/0x350 kernel/trace/trace_kprobe.c:1833 perf_kprobe_init+0x18c/0x280 kernel/trace/trace_event_perf.c:271 perf_kprobe_event_init+0xf8/0x1c0 kernel/events/core.c:9888 perf_try_init_event+0x12d/0x570 kernel/events/core.c:11261 perf_init_event kernel/events/core.c:11325 [inline] perf_event_alloc.part.0+0xf7f/0x36a0 kernel/events/core.c:11619 perf_event_alloc kernel/events/core.c:12059 [inline] __do_sys_perf_event_open+0x4a8/0x2a00 kernel/events/core.c:12157 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f63ef7efaed Code: 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f63eef63028 EFLAGS: 00000246 ORIG_RAX: 000000000000012a RAX: ffffffffffffffda RBX: 00007f63ef90ff80 RCX: 00007f63ef7efaed RDX: 0000000000000000 RSI: ffffffffffffffff RDI: 00000000200001c0 RBP: 00007f63ef86019c R08: 0000000000000000 R09: 0000000000000000 R10: ffffffffffffffff R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000002 R14: 00007f63ef90ff80 R15: 00007f63eef43000 </TASK> Modules linked in: CR2: fffffbfff3ac6000 ---[ end trace 0000000000000000 ]--- RIP: 0010:__insn_get_emulate_prefix arch/x86/lib/insn.c:91 [inline] RIP: 0010:insn_get_emulate_prefix arch/x86/lib/insn.c:106 [inline] RIP: 0010:insn_get_prefixes.part.0+0xa8/0x1110 arch/x86/lib/insn.c:134 Code: 49 be 00 00 00 00 00 fc ff df 48 8b 40 60 48 89 44 24 08 e9 81 00 00 00 e8 e5 4b 39 ff 4c 89 fa 4c 89 f9 48 c1 ea 03 83 e1 07 <42> 0f b6 14 32 38 ca 7f 08 84 d2 0f 85 06 10 00 00 48 89 d8 48 89 RSP: 0018:ffffc900088bf860 EFLAGS: 00010246 RAX: 0000000000040000 RBX: ffffffff9b9bebc0 RCX: 0000000000000000 RDX: 1ffffffff3ac6000 RSI: ffffc90002d82000 RDI: ffffc900088bf9e8 RBP: ffffffff9d630001 R08: 0000000000000000 R09: ffffc900088bf9e8 R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000001 R13: ffffffff9d630000 R14: dffffc0000000000 R15: ffffffff9d630000 FS: 00007f63eef63640(0000) GS:ffff88806d000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff3ac6000 CR3: 0000000029d90005 CR4: 0000000000770ef0 PKRU: 55555554 ==================================================================
Link: https://lkml.kernel.org/r/20220907200917.654103-1-lk@c--e.de
cc: "Naveen N. Rao" naveen.n.rao@linux.ibm.com cc: Anil S Keshavamurthy anil.s.keshavamurthy@intel.com cc: "David S. Miller" davem@davemloft.net Cc: stable@vger.kernel.org Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Christian A. Ehrhardt lk@c--e.de Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/kprobes.c | 1 + 1 file changed, 1 insertion(+)
--- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1562,6 +1562,7 @@ static int check_kprobe_address_safe(str /* Ensure it is not in reserved area nor out of text */ if (!(core_kernel_text((unsigned long) p->addr) || is_module_text_address((unsigned long) p->addr)) || + in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) ||
From: Sergey Matyukevich sergey.matyukevich@syntacore.com
commit 20e0fbab16003ae23a9e86a64bcb93e3121587ca upstream.
SBI firmware should report total number of firmware and hardware counters including unused ones or special ones. In this case the kernel doesn't need to make any assumptions about gaps in reported counters, e.g. excluded timer counter. That was fixed in OpenSBI v1.1 by commit 3f66465fb6bf ("lib: pmu: allow to use the highest available counter"). This kernel patch has no effect if SBI firmware behaves correctly. However it eliminates access beyond the allocated pmu_ctr_list if the kernel is used with OpenSBI older than v1.1.
Fixes: e9991434596f ("RISC-V: Add perf platform driver based on SBI PMU extension") Signed-off-by: Sergey Matyukevich sergey.matyukevich@syntacore.com Reviewed-by: Atish Patra atishp@rivosinc.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220830155306.301714-2-geomatsi@gmail.com Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/perf/riscv_pmu_sbi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -467,7 +467,7 @@ static int pmu_sbi_get_ctrinfo(int nctr) if (!pmu_ctr_list) return -ENOMEM;
- for (i = 0; i <= nctr; i++) { + for (i = 0; i < nctr; i++) { ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_GET_INFO, i, 0, 0, 0, 0, 0); if (ret.error) /* The logical counter ids are not expected to be contiguous */
From: Greg Kroah-Hartman gregkh@linuxfoundation.org
commit dec9b2f1e0455a151a7293c367da22ab973f713e upstream.
There is a very common pattern of using debugfs_remove(debufs_lookup(..)) which results in a dentry leak of the dentry that was looked up. Instead of having to open-code the correct pattern of calling dput() on the dentry, create debugfs_lookup_and_remove() to handle this pattern automatically and properly without any memory leaks.
Cc: stable stable@kernel.org Reported-by: Kuyo Chang kuyo.chang@mediatek.com Tested-by: Kuyo Chang kuyo.chang@mediatek.com Link: https://lore.kernel.org/r/YxIaQ8cSinDR881k@kroah.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/debugfs/inode.c | 22 ++++++++++++++++++++++ include/linux/debugfs.h | 6 ++++++ 2 files changed, 28 insertions(+)
--- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -745,6 +745,28 @@ void debugfs_remove(struct dentry *dentr EXPORT_SYMBOL_GPL(debugfs_remove);
/** + * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it + * @name: a pointer to a string containing the name of the item to look up. + * @parent: a pointer to the parent dentry of the item. + * + * This is the equlivant of doing something like + * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting + * handled for the directory being looked up. + */ +void debugfs_lookup_and_remove(const char *name, struct dentry *parent) +{ + struct dentry *dentry; + + dentry = debugfs_lookup(name, parent); + if (!dentry) + return; + + debugfs_remove(dentry); + dput(dentry); +} +EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); + +/** * debugfs_rename - rename a file/directory in the debugfs filesystem * @old_dir: a pointer to the parent dentry for the renamed object. This * should be a directory dentry. --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -91,6 +91,8 @@ struct dentry *debugfs_create_automount( void debugfs_remove(struct dentry *dentry); #define debugfs_remove_recursive debugfs_remove
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent); + const struct file_operations *debugfs_real_fops(const struct file *filp);
int debugfs_file_get(struct dentry *dentry); @@ -225,6 +227,10 @@ static inline void debugfs_remove(struct static inline void debugfs_remove_recursive(struct dentry *dentry) { }
+static inline void debugfs_lookup_and_remove(const char *name, + struct dentry *parent) +{ } + const struct file_operations *debugfs_real_fops(const struct file *filp);
static inline int debugfs_file_get(struct dentry *dentry)
From: Greg Kroah-Hartman gregkh@linuxfoundation.org
commit c2e406596571659451f4b95e37ddfd5a8ef1d0dc upstream.
Kuyo reports that the pattern of using debugfs_remove(debugfs_lookup()) leaks a dentry and with a hotplug stress test, the machine eventually runs out of memory.
Fix this up by using the newly created debugfs_lookup_and_remove() call instead which properly handles the dentry reference counting logic.
Cc: Major Chen major.chen@samsung.com Cc: stable stable@kernel.org Cc: Ingo Molnar mingo@redhat.com Cc: Peter Zijlstra peterz@infradead.org Cc: Juri Lelli juri.lelli@redhat.com Cc: Vincent Guittot vincent.guittot@linaro.org Cc: Dietmar Eggemann dietmar.eggemann@arm.com Cc: Steven Rostedt rostedt@goodmis.org Cc: Ben Segall bsegall@google.com Cc: Mel Gorman mgorman@suse.de Cc: Daniel Bristot de Oliveira bristot@redhat.com Cc: Valentin Schneider vschneid@redhat.com Cc: Matthias Brugger matthias.bgg@gmail.com Reported-by: Kuyo Chang kuyo.chang@mediatek.com Tested-by: Kuyo Chang kuyo.chang@mediatek.com Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/r/20220902123107.109274-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/sched/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -416,7 +416,7 @@ void update_sched_domain_debugfs(void) char buf[32];
snprintf(buf, sizeof(buf), "cpu%d", cpu); - debugfs_remove(debugfs_lookup(buf, sd_dentry)); + debugfs_lookup_and_remove(buf, sd_dentry); d_cpu = debugfs_create_dir(buf, sd_dentry);
i = 0;
From: Greg Kroah-Hartman gregkh@linuxfoundation.org
commit cbfac7fa491651c57926c99edeb7495c6c1aeac2 upstream.
When calling debugfs_lookup() the result must have dput() called on it, otherwise the memory will leak over time. Fix this up by properly calling dput().
Cc: Harry Wentland harry.wentland@amd.com Cc: Leo Li sunpeng.li@amd.com Cc: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Cc: Alex Deucher alexander.deucher@amd.com Cc: "Christian König" christian.koenig@amd.com Cc: "Pan, Xinhui" Xinhui.Pan@amd.com Cc: David Airlie airlied@linux.ie Cc: Daniel Vetter daniel@ffwll.ch Cc: Wayne Lin Wayne.Lin@amd.com Cc: hersen wu hersenxs.wu@amd.com Cc: Wenjing Liu wenjing.liu@amd.com Cc: Patrik Jakobsson patrik.r.jakobsson@gmail.com Cc: Thelford Williams tdwilliamsiv@gmail.com Cc: Fangzhi Zuo Jerry.Zuo@amd.com Cc: Yongzhi Liu lyz_cs@pku.edu.cn Cc: Mikita Lipski mikita.lipski@amd.com Cc: Jiapeng Chong jiapeng.chong@linux.alibaba.com Cc: Bhanuprakash Modem bhanuprakash.modem@intel.com Cc: Sean Paul seanpaul@chromium.org Cc: amd-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Cc: stable@vger.kernel.org Reviewed-by: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -3188,7 +3188,7 @@ void crtc_debugfs_init(struct drm_crtc * &crc_win_y_end_fops); debugfs_create_file_unsafe("crc_win_update", 0644, dir, crtc, &crc_win_update_fops); - + dput(dir); } #endif /*
From: Greg Kroah-Hartman gregkh@linuxfoundation.org
commit 5666a274a6d54372d6b79b1f78682a9d827e679e upstream.
Python likes to send an empty string for some sysfs files, including the driver_override field. When commit 23d99baf9d72 ("PCI: Use driver_set_override() instead of open-coding") moved the PCI core to use the driver core function instead of hand-rolling their own handler, this showed up as a regression from some userspace tools, like DPDK.
Fix this up by actually looking at the length of the string first instead of trusting that userspace got it correct.
Fixes: 23d99baf9d72 ("PCI: Use driver_set_override() instead of open-coding") Cc: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Cc: Bjorn Helgaas bhelgaas@google.com Cc: "Rafael J. Wysocki" rafael@kernel.org Cc: Andy Shevchenko andy.shevchenko@gmail.com Cc: stable stable@kernel.org Reported-by: Stephen Hemminger stephen@networkplumber.org Tested-by: Huisong Li lihuisong@huawei.com Reviewed-by: Stephen Hemminger stephen@networkplumber.org Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Link: https://lore.kernel.org/r/20220901163734.3583106-1-gregkh@linuxfoundation.or... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/base/driver.c | 6 ++++++ 1 file changed, 6 insertions(+)
--- a/drivers/base/driver.c +++ b/drivers/base/driver.c @@ -63,6 +63,12 @@ int driver_set_override(struct device *d if (len >= (PAGE_SIZE - 1)) return -EINVAL;
+ /* + * Compute the real length of the string in case userspace sends us a + * bunch of \0 characters like python likes to do. + */ + len = strlen(s); + if (!len) { /* Empty string passed - clear override */ device_lock(dev);
From: Bart Van Assche bvanassche@acm.org
commit 6a02a61e81c231cc5c680c5dbf8665275147ac52 upstream.
Fix the following use-after-free complaint triggered by blktests nvme/004:
BUG: KASAN: user-memory-access in blk_mq_complete_request_remote+0xac/0x350 Read of size 4 at addr 0000607bd1835943 by task kworker/13:1/460 Workqueue: nvmet-wq nvme_loop_execute_work [nvme_loop] Call Trace: show_stack+0x52/0x58 dump_stack_lvl+0x49/0x5e print_report.cold+0x36/0x1e2 kasan_report+0xb9/0xf0 __asan_load4+0x6b/0x80 blk_mq_complete_request_remote+0xac/0x350 nvme_loop_queue_response+0x1df/0x275 [nvme_loop] __nvmet_req_complete+0x132/0x4f0 [nvmet] nvmet_req_complete+0x15/0x40 [nvmet] nvmet_execute_io_connect+0x18a/0x1f0 [nvmet] nvme_loop_execute_work+0x20/0x30 [nvme_loop] process_one_work+0x56e/0xa70 worker_thread+0x2d1/0x640 kthread+0x183/0x1c0 ret_from_fork+0x1f/0x30
Cc: stable@vger.kernel.org Fixes: a07b4970f464 ("nvmet: add a generic NVMe target") Signed-off-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvme/target/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
--- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -735,6 +735,8 @@ static void nvmet_set_error(struct nvmet
static void __nvmet_req_complete(struct nvmet_req *req, u16 status) { + struct nvmet_ns *ns = req->ns; + if (!req->sq->sqhd_disabled) nvmet_update_sq_head(req); req->cqe->sq_id = cpu_to_le16(req->sq->qid); @@ -745,9 +747,9 @@ static void __nvmet_req_complete(struct
trace_nvmet_req_complete(req);
- if (req->ns) - nvmet_put_namespace(req->ns); req->ops->queue_response(req); + if (ns) + nvmet_put_namespace(ns); }
void nvmet_req_complete(struct nvmet_req *req, u16 status)
From: Ville Syrjälä ville.syrjala@linux.intel.com
commit edca5a2c373db61efa959307c13ed9156b1c14d9 upstream.
Turns out the MIPI sequence block version number and new block size fields are considered part of the block header and are not included in the reported new block size field itself. Bump up the block size appropriately so that we'll copy over the last five bytes of the block as well.
For this particular machine those last five bytes included parts of the GPIO op for the backlight on sequence, causing the backlight no longer to turn back on:
Sequence 6 - MIPI_SEQ_BACKLIGHT_ON Delay: 20000 us - GPIO index 0, number 0, set 0 (0x00) + GPIO index 1, number 70, set 1 (0x01)
Cc: stable@vger.kernel.org Fixes: e163cfb4c96d ("drm/i915/bios: Make copies of VBT data blocks") Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6652 Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220829135834.8585-1-ville.sy... Reviewed-by: Jani Nikula jani.nikula@intel.com (cherry picked from commit a06289f3f72431f3777af95ea1226b5b0abdc426) Signed-off-by: Rodrigo Vivi rodrigo.vivi@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_bios.c | 7 +++++++ 1 file changed, 7 insertions(+)
--- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -478,6 +478,13 @@ init_bdb_block(struct drm_i915_private *
block_size = get_blocksize(block);
+ /* + * Version number and new block size are considered + * part of the header for MIPI sequenece block v3+. + */ + if (section_id == BDB_MIPI_SEQUENCE && *(const u8 *)block >= 3) + block_size += 5; + entry = kzalloc(struct_size(entry, data, max(min_size, block_size) + 3), GFP_KERNEL); if (!entry) {
From: Rodrigo Vivi rodrigo.vivi@intel.com
commit e1cab970574c001d83e59ca8388c474a57a1afb6 upstream.
We need to inform PCODE of a desired ring frequencies so PCODE update the memory frequencies to us. rps->min_freq and rps->max_freq are the frequencies used in that request. However they were unset when SLPC was enabled and PCODE never updated the memory freq.
v2 (as Suggested by Ashutosh): if SLPC is in use, let's pick the right frequencies from the get_ia_constants instead of the fake init of rps' min and max.
v3: don't forget the max <= min return
v4: Move all the freq conversion to intel_rps.c. And the max <= min check to where it belongs.
v5: (Ashutosh) Fix old comment s/50 HZ/50 MHz and add a doc explaining the "raw format"
Fixes: 7ba79a671568 ("drm/i915/guc/slpc: Gate Host RPS when SLPC is enabled") Cc: stable@vger.kernel.org # v5.15+ Cc: Ashutosh Dixit ashutosh.dixit@intel.com Tested-by: Sushma Venkatesh Reddy sushma.venkatesh.reddy@intel.com Signed-off-by: Rodrigo Vivi rodrigo.vivi@intel.com Reviewed-by: Ashutosh Dixit ashutosh.dixit@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220831214538.143950-1-rodrig... (cherry picked from commit 018a7bdbb090b9155a6509a0d1a684db4afaa5b1) Signed-off-by: Rodrigo Vivi rodrigo.vivi@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/gt/intel_llc.c | 19 ++++++------- drivers/gpu/drm/i915/gt/intel_rps.c | 50 ++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/gt/intel_rps.h | 2 + 3 files changed, 61 insertions(+), 10 deletions(-)
--- a/drivers/gpu/drm/i915/gt/intel_llc.c +++ b/drivers/gpu/drm/i915/gt/intel_llc.c @@ -12,6 +12,7 @@ #include "intel_llc.h" #include "intel_mchbar_regs.h" #include "intel_pcode.h" +#include "intel_rps.h"
struct ia_constants { unsigned int min_gpu_freq; @@ -55,9 +56,6 @@ static bool get_ia_constants(struct inte if (!HAS_LLC(i915) || IS_DGFX(i915)) return false;
- if (rps->max_freq <= rps->min_freq) - return false; - consts->max_ia_freq = cpu_max_MHz();
consts->min_ring_freq = @@ -65,13 +63,8 @@ static bool get_ia_constants(struct inte /* convert DDR frequency from units of 266.6MHz to bandwidth */ consts->min_ring_freq = mult_frac(consts->min_ring_freq, 8, 3);
- consts->min_gpu_freq = rps->min_freq; - consts->max_gpu_freq = rps->max_freq; - if (GRAPHICS_VER(i915) >= 9) { - /* Convert GT frequency to 50 HZ units */ - consts->min_gpu_freq /= GEN9_FREQ_SCALER; - consts->max_gpu_freq /= GEN9_FREQ_SCALER; - } + consts->min_gpu_freq = intel_rps_get_min_raw_freq(rps); + consts->max_gpu_freq = intel_rps_get_max_raw_freq(rps);
return true; } @@ -132,6 +125,12 @@ static void gen6_update_ring_freq(struct return;
/* + * Although this is unlikely on any platform during initialization, + * let's ensure we don't get accidentally into infinite loop + */ + if (consts.max_gpu_freq <= consts.min_gpu_freq) + return; + /* * For each potential GPU frequency, load a ring frequency we'd like * to use for memory access. We do this by specifying the IA frequency * the PCU should use as a reference to determine the ring frequency. --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -2123,6 +2123,31 @@ u32 intel_rps_get_max_frequency(struct i return intel_gpu_freq(rps, rps->max_freq_softlimit); }
+/** + * intel_rps_get_max_raw_freq - returns the max frequency in some raw format. + * @rps: the intel_rps structure + * + * Returns the max frequency in a raw format. In newer platforms raw is in + * units of 50 MHz. + */ +u32 intel_rps_get_max_raw_freq(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc = rps_to_slpc(rps); + u32 freq; + + if (rps_uses_slpc(rps)) { + return DIV_ROUND_CLOSEST(slpc->rp0_freq, + GT_FREQUENCY_MULTIPLIER); + } else { + freq = rps->max_freq; + if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) { + /* Convert GT frequency to 50 MHz units */ + freq /= GEN9_FREQ_SCALER; + } + return freq; + } +} + u32 intel_rps_get_rp0_frequency(struct intel_rps *rps) { struct intel_guc_slpc *slpc = rps_to_slpc(rps); @@ -2211,6 +2236,31 @@ u32 intel_rps_get_min_frequency(struct i return intel_gpu_freq(rps, rps->min_freq_softlimit); }
+/** + * intel_rps_get_min_raw_freq - returns the min frequency in some raw format. + * @rps: the intel_rps structure + * + * Returns the min frequency in a raw format. In newer platforms raw is in + * units of 50 MHz. + */ +u32 intel_rps_get_min_raw_freq(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc = rps_to_slpc(rps); + u32 freq; + + if (rps_uses_slpc(rps)) { + return DIV_ROUND_CLOSEST(slpc->min_freq, + GT_FREQUENCY_MULTIPLIER); + } else { + freq = rps->min_freq; + if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) { + /* Convert GT frequency to 50 MHz units */ + freq /= GEN9_FREQ_SCALER; + } + return freq; + } +} + static int set_min_freq(struct intel_rps *rps, u32 val) { int ret = 0; --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -37,8 +37,10 @@ u32 intel_rps_get_cagf(struct intel_rps u32 intel_rps_read_actual_frequency(struct intel_rps *rps); u32 intel_rps_get_requested_frequency(struct intel_rps *rps); u32 intel_rps_get_min_frequency(struct intel_rps *rps); +u32 intel_rps_get_min_raw_freq(struct intel_rps *rps); int intel_rps_set_min_frequency(struct intel_rps *rps, u32 val); u32 intel_rps_get_max_frequency(struct intel_rps *rps); +u32 intel_rps_get_max_raw_freq(struct intel_rps *rps); int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val); u32 intel_rps_get_rp0_frequency(struct intel_rps *rps); u32 intel_rps_get_rp1_frequency(struct intel_rps *rps);
From: Ville Syrjälä ville.syrjala@linux.intel.com
commit 672d6ca758651f0ec12cd0d59787067a5bde1c96 upstream.
A lot of modern laptops use the Parade PS8461E MUX for eDP switching. The MUX can operate in jitter cleaning mode or redriver mode, the first one resulting in higher link quality. The jitter cleaning mode needs to know the link rate used and the MUX achieves this by snooping the LINK_BW_SET, LINK_RATE_SELECT and SUPPORTED_LINK_RATES DPCD accesses.
When the MUX is powered down (seems this can happen whenever the display is turned off) it loses track of the snooped link rates so when we do the LINK_RATE_SELECT write it no longer knowns which link rate we're selecting, and thus it falls back to the lower quality redriver mode. This results in unstable high link rates (eg. usually 8.1Gbps link rate no longer works correctly).
In order to avoid all that let's re-snoop SUPPORTED_LINK_RATES from the sink at the start of every link training.
Unfortunately we don't have a way to detect the presence of the MUX. It looks like the set of laptops equipped with this MUX is fairly large and contains devices from multiple manufacturers. It may also still be growing with new models. So a quirk doesn't seem like a very easily maintainable option, thus we shall attempt to do this unconditionally on all machines that use LINK_RATE_SELECT. Hopefully this extra DPCD read doesn't cause issues for any unaffected machine. If that turns out to be the case we'll need to convert this into a quirk in the future.
Cc: stable@vger.kernel.org Cc: Jason A. Donenfeld Jason@zx2c4.com Cc: Ankit Nautiyal ankit.k.nautiyal@intel.com Cc: Jani Nikula jani.nikula@intel.com Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/6205 Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220902070319.15395-1-ville.s... Tested-by: Aaron Ma aaron.ma@canonical.com Tested-by: Jason A. Donenfeld Jason@zx2c4.com Reviewed-by: Jani Nikula jani.nikula@intel.com (cherry picked from commit 25899c590cb5ba9b9f284c6ca8e7e9086793d641) Signed-off-by: Rodrigo Vivi rodrigo.vivi@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_dp_link_training.c | 22 ++++++++++++++++++ 1 file changed, 22 insertions(+)
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -671,6 +671,28 @@ intel_dp_prepare_link_train(struct intel intel_dp_compute_rate(intel_dp, crtc_state->port_clock, &link_bw, &rate_select);
+ /* + * WaEdpLinkRateDataReload + * + * Parade PS8461E MUX (used on varius TGL+ laptops) needs + * to snoop the link rates reported by the sink when we + * use LINK_RATE_SET in order to operate in jitter cleaning + * mode (as opposed to redriver mode). Unfortunately it + * loses track of the snooped link rates when powered down, + * so we need to make it re-snoop often. Without this high + * link rates are not stable. + */ + if (!link_bw) { + struct intel_connector *connector = intel_dp->attached_connector; + __le16 sink_rates[DP_MAX_SUPPORTED_RATES]; + + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] Reloading eDP link rates\n", + connector->base.base.id, connector->base.name); + + drm_dp_dpcd_read(&intel_dp->aux, DP_SUPPORTED_LINK_RATES, + sink_rates, sizeof(sink_rates)); + } + if (link_bw) drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Using LINK_BW_SET value %02x\n",
From: Sreekanth Reddy sreekanth.reddy@broadcom.com
commit 991df3dd5144f2e6b1c38b8d20ed3d4d21e20b34 upstream.
Fix the following use-after-free warning which is observed during controller reset:
refcount_t: underflow; use-after-free. WARNING: CPU: 23 PID: 5399 at lib/refcount.c:28 refcount_warn_saturate+0xa6/0xf0
Link: https://lore.kernel.org/r/20220906134908.1039-2-sreekanth.reddy@broadcom.com Signed-off-by: Sreekanth Reddy sreekanth.reddy@broadcom.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -3670,6 +3670,7 @@ static struct fw_event_work *dequeue_nex fw_event = list_first_entry(&ioc->fw_event_list, struct fw_event_work, list); list_del_init(&fw_event->list); + fw_event_work_put(fw_event); } spin_unlock_irqrestore(&ioc->fw_event_lock, flags);
@@ -3751,7 +3752,6 @@ _scsih_fw_event_cleanup_queue(struct MPT if (cancel_work_sync(&fw_event->work)) fw_event_work_put(fw_event);
- fw_event_work_put(fw_event); } ioc->fw_events_cleanup = 0; }
From: Yang Yingliang yangyingliang@huawei.com
commit da6d507f5ff328f346b3c50e19e19993027b8ffd upstream.
Add the missing destroy_workqueue() before return from lpfc_sli4_driver_resource_setup() in the error path.
Link: https://lore.kernel.org/r/20220823044237.285643-1-yangyingliang@huawei.com Fixes: 3cee98db2610 ("scsi: lpfc: Fix crash on driver unload in wq free") Reviewed-by: James Smart jsmart2021@gmail.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/lpfc/lpfc_init.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
--- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -8061,7 +8061,7 @@ lpfc_sli4_driver_resource_setup(struct l /* Allocate device driver memory */ rc = lpfc_mem_alloc(phba, SGL_ALIGN_SZ); if (rc) - return -ENOMEM; + goto out_destroy_workqueue;
/* IF Type 2 ports get initialized now. */ if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) >= @@ -8489,6 +8489,9 @@ out_free_bsmbx: lpfc_destroy_bootstrap_mbox(phba); out_free_mem: lpfc_mem_free(phba); +out_destroy_workqueue: + destroy_workqueue(phba->wq); + phba->wq = NULL; return rc; }
From: Tejun Heo tj@kernel.org
[ Upstream commit 671c11f0619e5ccb380bcf0f062f69ba95fc974a ]
cgroup_update_dfl_csses() write-lock the threadgroup_rwsem as updating the csses can trigger process migrations. However, if the subtree doesn't contain any tasks, there aren't gonna be any cgroup migrations. This condition can be trivially detected by testing whether mgctx.preloaded_src_csets is empty. Elide write-locking threadgroup_rwsem if the subtree is empty.
After this optimization, the usage pattern of creating a cgroup, enabling the necessary controllers, and then seeding it with CLONE_INTO_CGROUP and then removing the cgroup after it becomes empty doesn't need to write-lock threadgroup_rwsem at all.
Signed-off-by: Tejun Heo tj@kernel.org Cc: Christian Brauner brauner@kernel.org Cc: Michal Koutný mkoutny@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/cgroup/cgroup.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ce95aee05e8ae..ed4d6bf85e725 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2950,12 +2950,11 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; + bool has_tasks; int ret;
lockdep_assert_held(&cgroup_mutex);
- percpu_down_write(&cgroup_threadgroup_rwsem); - /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { @@ -2966,6 +2965,16 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) } spin_unlock_irq(&css_set_lock);
+ /* + * We need to write-lock threadgroup_rwsem while migrating tasks. + * However, if there are no source csets for @cgrp, changing its + * controllers isn't gonna produce any task migrations and the + * write-locking can be skipped safely. + */ + has_tasks = !list_empty(&mgctx.preloaded_src_csets); + if (has_tasks) + percpu_down_write(&cgroup_threadgroup_rwsem); + /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) @@ -2985,7 +2994,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); - percpu_up_write(&cgroup_threadgroup_rwsem); + if (has_tasks) + percpu_up_write(&cgroup_threadgroup_rwsem); return ret; }
From: Tejun Heo tj@kernel.org
[ Upstream commit 4f7e7236435ca0abe005c674ebd6892c6e83aeb3 ]
Bringing up a CPU may involve creating and destroying tasks which requires read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside cpus_read_lock(). However, cpuset's ->attach(), which may be called with thredagroup_rwsem write-locked, also wants to disable CPU hotplug and acquires cpus_read_lock(), leading to a deadlock.
Fix it by guaranteeing that ->attach() is always called with CPU hotplug disabled and removing cpus_read_lock() call from cpuset_attach().
Signed-off-by: Tejun Heo tj@kernel.org Reviewed-and-tested-by: Imran Khan imran.f.khan@oracle.com Reported-and-tested-by: Xuewen Yan xuewen.yan@unisoc.com Fixes: 05c7b7a92cc8 ("cgroup/cpuset: Fix a race between cpuset_attach() and cpu hotplug") Cc: stable@vger.kernel.org # v5.17+ Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/cgroup/cgroup.c | 77 +++++++++++++++++++++++++++++------------- kernel/cgroup/cpuset.c | 3 +- 2 files changed, 55 insertions(+), 25 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ed4d6bf85e725..e702ca368539a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2346,6 +2346,47 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) } EXPORT_SYMBOL_GPL(task_cgroup_path);
+/** + * cgroup_attach_lock - Lock for ->attach() + * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem + * + * cgroup migration sometimes needs to stabilize threadgroups against forks and + * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() + * implementations (e.g. cpuset), also need to disable CPU hotplug. + * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can + * lead to deadlocks. + * + * Bringing up a CPU may involve creating and destroying tasks which requires + * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside + * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while + * write-locking threadgroup_rwsem, the locking order is reversed and we end up + * waiting for an on-going CPU hotplug operation which in turn is waiting for + * the threadgroup_rwsem to be released to create new tasks. For more details: + * + * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu + * + * Resolve the situation by always acquiring cpus_read_lock() before optionally + * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that + * CPU hotplug is disabled on entry. + */ +static void cgroup_attach_lock(bool lock_threadgroup) +{ + cpus_read_lock(); + if (lock_threadgroup) + percpu_down_write(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_attach_unlock - Undo cgroup_attach_lock() + * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem + */ +static void cgroup_attach_unlock(bool lock_threadgroup) +{ + if (lock_threadgroup) + percpu_up_write(&cgroup_threadgroup_rwsem); + cpus_read_unlock(); +} + /** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task @@ -2822,8 +2863,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, }
struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, - bool *locked) - __acquires(&cgroup_threadgroup_rwsem) + bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; @@ -2840,12 +2880,8 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); - if (pid || threadgroup) { - percpu_down_write(&cgroup_threadgroup_rwsem); - *locked = true; - } else { - *locked = false; - } + *threadgroup_locked = pid || threadgroup; + cgroup_attach_lock(*threadgroup_locked);
rcu_read_lock(); if (pid) { @@ -2876,17 +2912,14 @@ struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, goto out_unlock_rcu;
out_unlock_threadgroup: - if (*locked) { - percpu_up_write(&cgroup_threadgroup_rwsem); - *locked = false; - } + cgroup_attach_unlock(*threadgroup_locked); + *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; }
-void cgroup_procs_write_finish(struct task_struct *task, bool locked) - __releases(&cgroup_threadgroup_rwsem) +void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; @@ -2894,8 +2927,8 @@ void cgroup_procs_write_finish(struct task_struct *task, bool locked) /* release reference from cgroup_procs_write_start() */ put_task_struct(task);
- if (locked) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(threadgroup_locked); + for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); @@ -2972,8 +3005,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); - if (has_tasks) - percpu_down_write(&cgroup_threadgroup_rwsem); + cgroup_attach_lock(has_tasks);
/* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); @@ -2994,8 +3026,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); - if (has_tasks) - percpu_up_write(&cgroup_threadgroup_rwsem); + cgroup_attach_unlock(has_tasks); return ret; }
@@ -4943,13 +4974,13 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, struct task_struct *task; const struct cred *saved_cred; ssize_t ret; - bool locked; + bool threadgroup_locked;
dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV;
- task = cgroup_procs_write_start(buf, threadgroup, &locked); + task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; @@ -4975,7 +5006,7 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, ret = cgroup_attach_task(dst_cgrp, task, threadgroup);
out_finish: - cgroup_procs_write_finish(task, locked); + cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 58aadfda9b8b3..1f3a55297f39d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2289,7 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css);
- cpus_read_lock(); + lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ percpu_down_write(&cpuset_rwsem);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2343,7 +2343,6 @@ static void cpuset_attach(struct cgroup_taskset *tset) wake_up(&cpuset_attach_wq);
percpu_up_write(&cpuset_rwsem); - cpus_read_unlock(); }
/* The various types of files and directories in a cpuset file system */
From: Enzo Matsumiya ematsumiya@suse.de
[ Upstream commit 400d0ad63b190895e29f43bc75b1260111d3fd34 ]
SMB2_ioctl() is always called with is_fsctl = true, so doesn't make any sense to have it at all.
Thus, always set SMB2_0_IOCTL_IS_FSCTL flag on the request.
Also, as per MS-SMB2 3.3.5.15 "Receiving an SMB2 IOCTL Request", servers must fail the request if the request flags is zero anyway.
Signed-off-by: Enzo Matsumiya ematsumiya@suse.de Reviewed-by: Tom Talpey tom@talpey.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/smb2file.c | 1 - fs/cifs/smb2ops.c | 35 +++++++++++++---------------------- fs/cifs/smb2pdu.c | 20 +++++++++----------- fs/cifs/smb2proto.h | 4 ++-- 4 files changed, 24 insertions(+), 36 deletions(-)
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index f5dcc4940b6da..9dfd2dd612c25 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -61,7 +61,6 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, - true /* is_fsctl */, (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), CIFSMaxBufSize, NULL, NULL /* no return info */); if (rc == -EOPNOTSUPP) { diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 3898ec2632dc4..33357846a01b1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -680,7 +680,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) struct cifs_ses *ses = tcon->ses;
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, - FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, + FSCTL_QUERY_NETWORK_INTERFACE_INFO, NULL /* no data input */, 0 /* no data input */, CIFSMaxBufSize, (char **)&out_buf, &ret_data_len); if (rc == -EOPNOTSUPP) { @@ -1609,9 +1609,8 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon, struct resume_key_req *res_key;
rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, - FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */, - NULL, 0 /* no input */, CIFSMaxBufSize, - (char **)&res_key, &ret_data_len); + FSCTL_SRV_REQUEST_RESUME_KEY, NULL, 0 /* no input */, + CIFSMaxBufSize, (char **)&res_key, &ret_data_len);
if (rc == -EOPNOTSUPP) { pr_warn_once("Server share %s does not support copy range\n", tcon->treeName); @@ -1753,7 +1752,7 @@ smb2_ioctl_query_info(const unsigned int xid, rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE;
rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, COMPOUND_FID, - qi.info_type, true, buffer, qi.output_buffer_length, + qi.info_type, buffer, qi.output_buffer_length, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); free_req1_func = SMB2_ioctl_free; @@ -1929,9 +1928,8 @@ smb2_copychunk_range(const unsigned int xid, retbuf = NULL; rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, - true /* is_fsctl */, (char *)pcchunk, - sizeof(struct copychunk_ioctl), CIFSMaxBufSize, - (char **)&retbuf, &ret_data_len); + (char *)pcchunk, sizeof(struct copychunk_ioctl), + CIFSMaxBufSize, (char **)&retbuf, &ret_data_len); if (rc == 0) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) { @@ -2091,7 +2089,6 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon,
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_SPARSE, - true /* is_fctl */, &setsparse, 1, CIFSMaxBufSize, NULL, NULL); if (rc) { tcon->broken_sparse_sup = true; @@ -2174,7 +2171,6 @@ smb2_duplicate_extents(const unsigned int xid, rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_DUPLICATE_EXTENTS_TO_FILE, - true /* is_fsctl */, (char *)&dup_ext_buf, sizeof(struct duplicate_extents_to_file), CIFSMaxBufSize, NULL, @@ -2209,7 +2205,6 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_INTEGRITY_INFORMATION, - true /* is_fsctl */, (char *)&integr_info, sizeof(struct fsctl_set_integrity_information_req), CIFSMaxBufSize, NULL, @@ -2262,7 +2257,6 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SRV_ENUMERATE_SNAPSHOTS, - true /* is_fsctl */, NULL, 0 /* no input data */, max_response_size, (char **)&retbuf, &ret_data_len); @@ -2982,7 +2976,6 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, do { rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_DFS_GET_REFERRALS, - true /* is_fsctl */, (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); if (!is_retryable_error(rc)) @@ -3189,8 +3182,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
rc = SMB2_ioctl_init(tcon, server, &rqst[1], fid.persistent_fid, - fid.volatile_fid, FSCTL_GET_REPARSE_POINT, - true /* is_fctl */, NULL, 0, + fid.volatile_fid, FSCTL_GET_REPARSE_POINT, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); @@ -3370,8 +3362,7 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
rc = SMB2_ioctl_init(tcon, server, &rqst[1], COMPOUND_FID, - COMPOUND_FID, FSCTL_GET_REPARSE_POINT, - true /* is_fctl */, NULL, 0, + COMPOUND_FID, FSCTL_GET_REPARSE_POINT, NULL, 0, CIFSMaxBufSize - MAX_SMB2_CREATE_RESPONSE_SIZE - MAX_SMB2_CLOSE_RESPONSE_SIZE); @@ -3641,7 +3632,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len);
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, - cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true, + cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, (char *)&fsctl_buf, sizeof(struct file_zero_data_information), 0, NULL, NULL); @@ -3702,7 +3693,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, - true /* is_fctl */, (char *)&fsctl_buf, + (char *)&fsctl_buf, sizeof(struct file_zero_data_information), CIFSMaxBufSize, NULL, NULL); filemap_invalidate_unlock(inode->i_mapping); @@ -3764,7 +3755,7 @@ static int smb3_simple_fallocate_range(unsigned int xid, in_data.length = cpu_to_le64(len); rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), 1024 * sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); @@ -4085,7 +4076,7 @@ static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offs
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); @@ -4145,7 +4136,7 @@ static int smb3_fiemap(struct cifs_tcon *tcon,
rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, - FSCTL_QUERY_ALLOCATED_RANGES, true, + FSCTL_QUERY_ALLOCATED_RANGES, (char *)&in_data, sizeof(in_data), 1024 * sizeof(struct file_allocated_range_buffer), (char **)&out_data, &out_data_len); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index ba58d7fd54f9e..31d37afae741f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1174,7 +1174,7 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) }
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, - FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, + FSCTL_VALIDATE_NEGOTIATE_INFO, (char *)pneg_inbuf, inbuflen, CIFSMaxBufSize, (char **)&pneg_rsp, &rsplen); if (rc == -EOPNOTSUPP) { @@ -3053,7 +3053,7 @@ int SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + char *in_data, u32 indatalen, __u32 max_response_size) { struct smb2_ioctl_req *req; @@ -3128,10 +3128,8 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(max(indatalen, max_response_size), SMB2_MAX_BUFFER_SIZE)); - if (is_fsctl) - req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); - else - req->Flags = 0; + /* always an FSCTL (for now) */ + req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
/* validate negotiate request must be signed - see MS-SMB2 3.2.5.5 */ if (opcode == FSCTL_VALIDATE_NEGOTIATE_INFO) @@ -3158,9 +3156,9 @@ SMB2_ioctl_free(struct smb_rqst *rqst) */ int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, - u64 volatile_fid, u32 opcode, bool is_fsctl, - char *in_data, u32 indatalen, u32 max_out_data_len, - char **out_data, u32 *plen /* returned data len */) + u64 volatile_fid, u32 opcode, char *in_data, u32 indatalen, + u32 max_out_data_len, char **out_data, + u32 *plen /* returned data len */) { struct smb_rqst rqst; struct smb2_ioctl_rsp *rsp = NULL; @@ -3202,7 +3200,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
rc = SMB2_ioctl_init(tcon, server, &rqst, persistent_fid, volatile_fid, opcode, - is_fsctl, in_data, indatalen, max_out_data_len); + in_data, indatalen, max_out_data_len); if (rc) goto ioctl_exit;
@@ -3294,7 +3292,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, - FSCTL_SET_COMPRESSION, true /* is_fsctl */, + FSCTL_SET_COMPRESSION, (char *)&fsctl_input /* data input */, 2 /* in data len */, CIFSMaxBufSize /* max out data */, &ret_data /* out data */, NULL); diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index a69f1eed1cfe5..d57d7202dc367 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -147,13 +147,13 @@ extern int SMB2_open_init(struct cifs_tcon *tcon, extern void SMB2_open_free(struct smb_rqst *rqst); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen, + char *in_data, u32 indatalen, u32 maxoutlen, char **out_data, u32 *plen /* returned data len */); extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + char *in_data, u32 indatalen, __u32 max_response_size); extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
From: David Howells dhowells@redhat.com
[ Upstream commit c919c164fc87bcca8e80b3b9224492fa5b6455ba ]
smb3 fallocate zero range was not grabbing the inode or filemap_invalidate locks so could have race with pagemap reinstantiating the page.
Cc: stable@vger.kernel.org Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/smb2ops.c | 55 ++++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 25 deletions(-)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 33357846a01b1..e8a8daa82ed76 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -3590,26 +3590,43 @@ get_smb2_acl(struct cifs_sb_info *cifs_sb, return pntsd; }
+static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon, + loff_t offset, loff_t len, unsigned int xid) +{ + struct cifsFileInfo *cfile = file->private_data; + struct file_zero_data_information fsctl_buf; + + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); + + fsctl_buf.FileOffset = cpu_to_le64(offset); + fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + + return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, + (char *)&fsctl_buf, + sizeof(struct file_zero_data_information), + 0, NULL, NULL); +} + static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len, bool keep_size) { struct cifs_ses *ses = tcon->ses; - struct inode *inode; - struct cifsInodeInfo *cifsi; + struct inode *inode = file_inode(file); + struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct file_zero_data_information fsctl_buf; long rc; unsigned int xid; __le64 eof;
xid = get_xid();
- inode = d_inode(cfile->dentry); - cifsi = CIFS_I(inode); - trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len);
+ inode_lock(inode); + filemap_invalidate_lock(inode->i_mapping); + /* * We zero the range through ioctl, so we need remove the page caches * first, otherwise the data may be inconsistent with the server. @@ -3617,26 +3634,12 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, truncate_pagecache_range(inode, offset, offset + len - 1);
/* if file not oplocked can't be sure whether asking to extend size */ - if (!CIFS_CACHE_READ(cifsi)) - if (keep_size == false) { - rc = -EOPNOTSUPP; - trace_smb3_zero_err(xid, cfile->fid.persistent_fid, - tcon->tid, ses->Suid, offset, len, rc); - free_xid(xid); - return rc; - } - - cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); - - fsctl_buf.FileOffset = cpu_to_le64(offset); - fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); + rc = -EOPNOTSUPP; + if (keep_size == false && !CIFS_CACHE_READ(cifsi)) + goto zero_range_exit;
- rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, - cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, - (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), - 0, NULL, NULL); - if (rc) + rc = smb3_zero_data(file, tcon, offset, len, xid); + if (rc < 0) goto zero_range_exit;
/* @@ -3649,6 +3652,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, }
zero_range_exit: + filemap_invalidate_unlock(inode->i_mapping); + inode_unlock(inode); free_xid(xid); if (rc) trace_smb3_zero_err(xid, cfile->fid.persistent_fid, tcon->tid,
From: Robin Murphy robin.murphy@arm.com
[ Upstream commit 46f7ac3d7892e808c9ba01c39da6bb85cda26ecd ]
Shifting the recieved bit by "bits" inserts it at the top of the *currently remaining* Tx data, so we end up accumulating the whole transfer into bit 0 of the output word. Oops.
For the algorithm to work as intended, we need to remember where the top of the *original* word was, and shift Rx to there.
Fixes: 1847e3046c52 ("spi: gpio: Implement LSB First bitbang support") Signed-off-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/28324d8622da80461cce35a82859b003d6f6c4b0.165953873... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-bitbang-txrx.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/spi/spi-bitbang-txrx.h b/drivers/spi/spi-bitbang-txrx.h index 267342dfa7388..2dcbe166df63e 100644 --- a/drivers/spi/spi-bitbang-txrx.h +++ b/drivers/spi/spi-bitbang-txrx.h @@ -116,6 +116,7 @@ bitbang_txrx_le_cpha0(struct spi_device *spi, { /* if (cpol == 0) this is SPI_MODE_0; else this is SPI_MODE_2 */
+ u8 rxbit = bits - 1; u32 oldbit = !(word & 1); /* clock starts at inactive polarity */ for (; likely(bits); bits--) { @@ -135,7 +136,7 @@ bitbang_txrx_le_cpha0(struct spi_device *spi, /* sample LSB (from slave) on leading edge */ word >>= 1; if ((flags & SPI_MASTER_NO_RX) == 0) - word |= getmiso(spi) << (bits - 1); + word |= getmiso(spi) << rxbit; setsck(spi, cpol); } return word; @@ -148,6 +149,7 @@ bitbang_txrx_le_cpha1(struct spi_device *spi, { /* if (cpol == 0) this is SPI_MODE_1; else this is SPI_MODE_3 */
+ u8 rxbit = bits - 1; u32 oldbit = !(word & 1); /* clock starts at inactive polarity */ for (; likely(bits); bits--) { @@ -168,7 +170,7 @@ bitbang_txrx_le_cpha1(struct spi_device *spi, /* sample LSB (from slave) on trailing edge */ word >>= 1; if ((flags & SPI_MASTER_NO_RX) == 0) - word |= getmiso(spi) << (bits - 1); + word |= getmiso(spi) << rxbit; } return word; }
From: Richard Fitzgerald rf@opensource.cirrus.com
[ Upstream commit ea75deef1a738d25502cfbb2caa564270b271525 ]
Only report a button state change if the interrupt status shows that there was a button event.
Previously the code would always drop into the button reporting at the end of interrupt handling if the jack was present. If neither of the button report interrupts were pending it would report all buttons released. This could then lead to a button being reported as released while it is still pressed.
Fixes: c5b8ee0879bc ("ASoC: cs42l42: Report jack and button detection") Signed-off-by: Richard Fitzgerald rf@opensource.cirrus.com Link: https://lore.kernel.org/r/20220815123138.3810249-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/cs42l42.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 4fade23887972..8cba3015398b7 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -1618,7 +1618,6 @@ static irqreturn_t cs42l42_irq_thread(int irq, void *data) unsigned int current_plug_status; unsigned int current_button_status; unsigned int i; - int report = 0;
mutex_lock(&cs42l42->irq_lock); if (cs42l42->suspended) { @@ -1713,13 +1712,15 @@ static irqreturn_t cs42l42_irq_thread(int irq, void *data)
if (current_button_status & CS42L42_M_DETECT_TF_MASK) { dev_dbg(cs42l42->dev, "Button released\n"); - report = 0; + snd_soc_jack_report(cs42l42->jack, 0, + SND_JACK_BTN_0 | SND_JACK_BTN_1 | + SND_JACK_BTN_2 | SND_JACK_BTN_3); } else if (current_button_status & CS42L42_M_DETECT_FT_MASK) { - report = cs42l42_handle_button_press(cs42l42); - + snd_soc_jack_report(cs42l42->jack, + cs42l42_handle_button_press(cs42l42), + SND_JACK_BTN_0 | SND_JACK_BTN_1 | + SND_JACK_BTN_2 | SND_JACK_BTN_3); } - snd_soc_jack_report(cs42l42->jack, report, SND_JACK_BTN_0 | SND_JACK_BTN_1 | - SND_JACK_BTN_2 | SND_JACK_BTN_3); } }
From: Marco Felsch m.felsch@pengutronix.de
[ Upstream commit b64b46fbaa1da626324f304bcb5fe0662f28b6ce ]
This reverts commit 8239d67f59cf522dd4f7135392a2f9a3a25f9cff.
This change confuses the sysfs cleanup path since the rename is done after the device registration.
Fixes: 8239d67f59cf ("soc: imx: imx8m-blk-ctrl: set power device name") Signed-off-by: Marco Felsch m.felsch@pengutronix.de Reviewed-by: Lucas Stach l.stach@pengutronix.de Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/imx/imx8m-blk-ctrl.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c index 7ebc28709e945..2782a7e0a8719 100644 --- a/drivers/soc/imx/imx8m-blk-ctrl.c +++ b/drivers/soc/imx/imx8m-blk-ctrl.c @@ -242,7 +242,6 @@ static int imx8m_blk_ctrl_probe(struct platform_device *pdev) ret = PTR_ERR(domain->power_dev); goto cleanup_pds; } - dev_set_name(domain->power_dev, "%s", data->name);
domain->genpd.name = data->name; domain->genpd.power_on = imx8m_blk_ctrl_power_on;
From: Andrejs Cainikovs andrejs.cainikovs@toradex.com
[ Upstream commit be1e3dfecf7d2fbcb4a45b113da637983878246c ]
Update SPI CAN controller clock to match current hardware design.
Signed-off-by: Andrejs Cainikovs andrejs.cainikovs@toradex.com Acked-by: Marcel Ziswiler marcel.ziswiler@toradex.com Fixes: 6a57f224f734 ("arm64: dts: freescale: add initial support for verdin imx8m mini") Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index eafa88d980b32..2841c6bfe3a92 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -32,10 +32,10 @@ };
/* Fixed clock dedicated to SPI CAN controller */ - clk20m: oscillator { + clk40m: oscillator { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <20000000>; + clock-frequency = <40000000>; };
gpio-keys { @@ -194,7 +194,7 @@
can1: can@0 { compatible = "microchip,mcp251xfd"; - clocks = <&clk20m>; + clocks = <&clk40m>; interrupts-extended = <&gpio1 6 IRQ_TYPE_EDGE_FALLING>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_can1_int>;
From: Andrejs Cainikovs andrejs.cainikovs@toradex.com
[ Upstream commit e9f130e0775b5a2dad0a33440347d373ff69e631 ]
Switch to level interrupt for mcp251xfd. This will make sure no interrupts are lost.
Signed-off-by: Andrejs Cainikovs andrejs.cainikovs@toradex.com Reported-by: Marc Kleine-Budde mkl@pengutronix.de Acked-by: Marc Kleine-Budde mkl@pengutronix.de Fixes: 6a57f224f734 ("arm64: dts: freescale: add initial support for verdin imx8m mini") Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 2841c6bfe3a92..6491e745b3fa8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -195,7 +195,7 @@ can1: can@0 { compatible = "microchip,mcp251xfd"; clocks = <&clk40m>; - interrupts-extended = <&gpio1 6 IRQ_TYPE_EDGE_FALLING>; + interrupts-extended = <&gpio1 6 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_can1_int>; reg = <0>;
From: Srinivas Kandagatla srinivas.kandagatla@linaro.org
[ Upstream commit c6e14bb9f50df7126ca64405ae807d8bc7b39f9a ]
Add missing module owner to able to build and load this driver as module.
Fixes: aa2e2785545a ("ASoC: qcom: sm8250: add sound card qrb5165-rb5 support") Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20220816165229.7971-1-srinivas.kandagatla@linaro.o... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/qcom/sm8250.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c index 6e1184c8b672a..c48ac107810d4 100644 --- a/sound/soc/qcom/sm8250.c +++ b/sound/soc/qcom/sm8250.c @@ -270,6 +270,7 @@ static int sm8250_platform_probe(struct platform_device *pdev) if (!card) return -ENOMEM;
+ card->owner = THIS_MODULE; /* Allocate the private data */ data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data)
From: Cristian Ciocaltea cristian.ciocaltea@collabora.com
[ Upstream commit f5723cfc01932c7a8d5c78dbf7e067e537c91439 ]
Currently the max_raw_read and max_raw_write limits in regmap_spi struct do not take into account the additional size of the transmitted register address and padding. This may result in exceeding the maximum permitted SPI message size, which could cause undefined behaviour, e.g. data corruption.
Fix regmap_get_spi_bus() to properly adjust the above mentioned limits by reserving space for the register address/padding as set in the regmap configuration.
Fixes: f231ff38b7b2 ("regmap: spi: Set regmap max raw r/w from max_transfer_size")
Signed-off-by: Cristian Ciocaltea cristian.ciocaltea@collabora.com Reviewed-by: Lucas Tanure tanureal@opensource.cirrus.com Link: https://lore.kernel.org/r/20220818104851.429479-1-cristian.ciocaltea@collabo... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/regmap/regmap-spi.c | 8 ++++++++ 1 file changed, 8 insertions(+)
diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c index 719323bc6c7f1..37ab23a9d0345 100644 --- a/drivers/base/regmap/regmap-spi.c +++ b/drivers/base/regmap/regmap-spi.c @@ -113,6 +113,7 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi, const struct regmap_config *config) { size_t max_size = spi_max_transfer_size(spi); + size_t max_msg_size, reg_reserve_size; struct regmap_bus *bus;
if (max_size != SIZE_MAX) { @@ -120,9 +121,16 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi, if (!bus) return ERR_PTR(-ENOMEM);
+ max_msg_size = spi_max_message_size(spi); + reg_reserve_size = config->reg_bits / BITS_PER_BYTE + + config->pad_bits / BITS_PER_BYTE; + if (max_size + reg_reserve_size > max_msg_size) + max_size -= reg_reserve_size; + bus->free_on_exit = true; bus->max_raw_read = max_size; bus->max_raw_write = max_size; + return bus; }
From: Peng Fan peng.fan@nxp.com
[ Upstream commit 706dd9d30d3bda4e31d423af004c22d48e89fbc9 ]
The pad settings are missed, add them
Fixes: 7899eb6cb15d ("arm64: dts: imx: Add i.MX8M Plus Gateworks gw7400 dts support") Signed-off-by: Peng Fan peng.fan@nxp.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index 521215520a0f4..6630ec561dc25 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -770,10 +770,10 @@
pinctrl_sai2: sai2grp { fsl,pins = < - MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI2_TX_SYNC - MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI2_TX_DATA00 - MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI2_TX_BCLK - MX8MP_IOMUXC_SAI2_MCLK__AUDIOMIX_SAI2_MCLK + MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI2_TX_SYNC 0xd6 + MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI2_TX_DATA00 0xd6 + MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI2_TX_BCLK 0xd6 + MX8MP_IOMUXC_SAI2_MCLK__AUDIOMIX_SAI2_MCLK 0xd6 >; };
From: Alexander Stein alexander.stein@ew.tq-group.com
[ Upstream commit 8eaac789128a84e79c193e662959469e824423ee ]
This property was never needed, remove it. This also silences dtbs_check warnings.
Fixes: b186b8b6e770 ("arm64: dts: freescale: add initial device tree for TQMa8Mx with i.MX8M") Signed-off-by: Alexander Stein alexander.stein@ew.tq-group.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi | 1 - 1 file changed, 1 deletion(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi index 899e8e7dbc24f..802ad6e5cef61 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-tqma8mq.dtsi @@ -204,7 +204,6 @@ reg = <0x51>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_rtc>; - interrupt-names = "irq"; interrupt-parent = <&gpio1>; interrupts = <1 IRQ_TYPE_EDGE_FALLING>; quartz-load-femtofarads = <7000>;
From: Jack Wang jinpu.wang@ionos.com
[ Upstream commit b66905e04dc714825aa6cffb950e281b46bbeafe ]
When iommu is enabled, we hit warnings like this: WARNING: at rtrs/rtrs.c:178 rtrs_iu_post_rdma_write_imm+0x9b/0x110
rtrs warn on one sge entry length is 0, which is unexpected.
The problem is ib_dma_map_sg augments the SGL into a 'dma mapped SGL'. This process may change the number of entries and the lengths of each entry.
Code that touches dma_address is iterating over the 'dma mapped SGL' and must use dma_nents which returned from ib_dma_map_sg(). So pass the count return from ib_dma_map_sg.
Fixes: 6a98d71daea1 ("RDMA/rtrs: client: main functionality") Link: https://lore.kernel.org/r/20220818105355.110344-3-haris.iqbal@ionos.com Signed-off-by: Jack Wang jinpu.wang@ionos.com Reviewed-by: Aleksei Marov aleksei.marov@ionos.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 525f083fcaeb4..bf464400a4409 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -1004,7 +1004,8 @@ rtrs_clt_get_copy_req(struct rtrs_clt_path *alive_path, static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con, struct rtrs_clt_io_req *req, struct rtrs_rbuf *rbuf, bool fr_en, - u32 size, u32 imm, struct ib_send_wr *wr, + u32 count, u32 size, u32 imm, + struct ib_send_wr *wr, struct ib_send_wr *tail) { struct rtrs_clt_path *clt_path = to_clt_path(con->c.path); @@ -1024,12 +1025,12 @@ static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con, num_sge = 2; ptail = tail; } else { - for_each_sg(req->sglist, sg, req->sg_cnt, i) { + for_each_sg(req->sglist, sg, count, i) { sge[i].addr = sg_dma_address(sg); sge[i].length = sg_dma_len(sg); sge[i].lkey = clt_path->s.dev->ib_pd->local_dma_lkey; } - num_sge = 1 + req->sg_cnt; + num_sge = 1 + count; } sge[i].addr = req->iu->dma_addr; sge[i].length = size; @@ -1142,7 +1143,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req) */ rtrs_clt_update_all_stats(req, WRITE);
- ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en, + ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en, count, req->usr_len + sizeof(*msg), imm, wr, &inv_wr); if (ret) {
From: Jack Wang jinpu.wang@ionos.com
[ Upstream commit 56c310de0b4b3aca1c4fdd9c1093fc48372a7335 ]
ib_dma_map_sg() augments the SGL into a 'dma mapped SGL'. This process may change the number of entries and the lengths of each entry.
Code that touches dma_address is iterating over the 'dma mapped SGL' and must use dma_nents which returned from ib_dma_map_sg().
We should use the return count from ib_dma_map_sg for futher usage.
Fixes: 9cb837480424e ("RDMA/rtrs: server: main functionality") Link: https://lore.kernel.org/r/20220818105355.110344-4-haris.iqbal@ionos.com Signed-off-by: Jack Wang jinpu.wang@ionos.com Reviewed-by: Aleksei Marov aleksei.marov@ionos.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/ulp/rtrs/rtrs-srv.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index 24024bce25664..ee4876bdce4ac 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -600,7 +600,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) struct sg_table *sgt = &srv_mr->sgt; struct scatterlist *s; struct ib_mr *mr; - int nr, chunks; + int nr, nr_sgt, chunks;
chunks = chunks_per_mr * mri; if (!always_invalidate) @@ -615,19 +615,19 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) sg_set_page(s, srv->chunks[chunks + i], max_chunk_size, 0);
- nr = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl, + nr_sgt = ib_dma_map_sg(srv_path->s.dev->ib_dev, sgt->sgl, sgt->nents, DMA_BIDIRECTIONAL); - if (nr < sgt->nents) { - err = nr < 0 ? nr : -EINVAL; + if (!nr_sgt) { + err = -EINVAL; goto free_sg; } mr = ib_alloc_mr(srv_path->s.dev->ib_pd, IB_MR_TYPE_MEM_REG, - sgt->nents); + nr_sgt); if (IS_ERR(mr)) { err = PTR_ERR(mr); goto unmap_sg; } - nr = ib_map_mr_sg(mr, sgt->sgl, sgt->nents, + nr = ib_map_mr_sg(mr, sgt->sgl, nr_sgt, NULL, max_chunk_size); if (nr < 0 || nr < sgt->nents) { err = nr < 0 ? nr : -EINVAL; @@ -646,7 +646,7 @@ static int map_cont_bufs(struct rtrs_srv_path *srv_path) } } /* Eventually dma addr for each chunk can be cached */ - for_each_sg(sgt->sgl, s, sgt->orig_nents, i) + for_each_sg(sgt->sgl, s, nr_sgt, i) srv_path->dma_addr[chunks + i] = sg_dma_address(s);
ib_update_fast_reg_key(mr, ib_inc_rkey(mr->rkey));
From: David Jander david@protonic.nl
[ Upstream commit 83c75e1bc2b83b3f0c718833bde677ebfa736283 ]
This naming error slipped through, so now that a new backlight node has been added with correct spelling, fix this one also.
Fixes: 98efa526a0c4 ("ARM: dts: imx6qdl-vicut1/vicutgo: Add backlight_led node") Signed-off-by: David Jander david@protonic.nl Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx6qdl-vicut1.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm/boot/dts/imx6qdl-vicut1.dtsi b/arch/arm/boot/dts/imx6qdl-vicut1.dtsi index a1676b5d2980f..c5a98b0110dd3 100644 --- a/arch/arm/boot/dts/imx6qdl-vicut1.dtsi +++ b/arch/arm/boot/dts/imx6qdl-vicut1.dtsi @@ -28,7 +28,7 @@ enable-gpios = <&gpio4 28 GPIO_ACTIVE_HIGH>; };
- backlight_led: backlight_led { + backlight_led: backlight-led { compatible = "pwm-backlight"; pwms = <&pwm3 0 5000000 0>; brightness-levels = <0 16 64 255>;
From: Marco Felsch m.felsch@pengutronix.de
[ Upstream commit 204f67d86f55dd4fa757ed04757d7273f71a169c ]
The regulator node 'regulator-3p3v-s0' was dupplicated. Remove it to clean the DTS.
Fixes: 2a51f9dae13d ("ARM: dts: imx6qdl-kontron-samx6i: Add iMX6-based Kontron SMARC-sAMX6i module") Signed-off-by: Marco Felsch m.felsch@pengutronix.de Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 10 ---------- 1 file changed, 10 deletions(-)
diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 095c9143d99a3..f159c58b9edba 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -51,16 +51,6 @@ vin-supply = <®_3p3v_s5>; };
- reg_3p3v_s0: regulator-3p3v-s0 { - compatible = "regulator-fixed"; - regulator-name = "V_3V3_S0"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - regulator-boot-on; - vin-supply = <®_3p3v_s5>; - }; - reg_3p3v_s5: regulator-3p3v-s5 { compatible = "regulator-fixed"; regulator-name = "V_3V3_S5";
From: Marco Felsch m.felsch@pengutronix.de
[ Upstream commit af7d78c957017f8b3a0986769f6f18e57f9362ea ]
Drop the "winbond,w25q16dw" compatible since it causes to set the MODALIAS to w25q16dw which is not specified within spi-nor id table. Fix this by use the common "jedec,spi-nor" compatible.
Fixes: 2125212785c9 ("ARM: dts: imx6qdl-kontron-samx6i: add Kontron SMARC SoM Support") Signed-off-by: Marco Felsch m.felsch@pengutronix.de Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index f159c58b9edba..6b791d515e294 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -249,7 +249,7 @@
/* default boot source: workaround #1 for errata ERR006282 */ smarc_flash: flash@0 { - compatible = "winbond,w25q16dw", "jedec,spi-nor"; + compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <20000000>; };
From: Vladimir Oltean vladimir.oltean@nxp.com
[ Upstream commit e7406f864e765c564c5cf384464faff66114f97d ]
The Lynx PCS integrated with ENETC port 0 does not support in-band autoneg for the 2500base-x SERDES protocol, and prints errors from its phylink methods. Furthermore, the AQR112 card used for these boards does not expect in-band autoneg either. So delete the extraneous property.
Fixes: e426d63e752b ("arm64: dts: ls1028a-qds: add overlays for various serdes protocols") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts | 1 - 1 file changed, 1 deletion(-)
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts index 40d34c8384a5e..b949cac037427 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds-65bb.dts @@ -25,7 +25,6 @@ &enetc_port0 { phy-handle = <&slot1_sgmii>; phy-mode = "2500base-x"; - managed = "in-band-status"; status = "okay"; };
From: Marek Vasut marex@denx.de
[ Upstream commit df88005bd81b80c944d185554e264a4b0f993c37 ]
In case the power domain clock are ungated before the reset is asserted, the system might freeze completely. This is likely due to a device is an undefined state being attached to bus, which sporadically leads to a bus hang. Assert the reset before the clock are enabled to assure the device is in defined state before being attached to bus.
Fixes: fe58c887fb8ca ("soc: imx: gpcv2: add support for optional resets") Signed-off-by: Marek Vasut marex@denx.de Reviewed-by: Fabio Estevam festevam@denx.de Reviewed-by: Lucas Stach l.stach@pengutronix.de Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/imx/gpcv2.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/soc/imx/gpcv2.c b/drivers/soc/imx/gpcv2.c index 85aa86e1338af..5a3809f6a698f 100644 --- a/drivers/soc/imx/gpcv2.c +++ b/drivers/soc/imx/gpcv2.c @@ -333,6 +333,8 @@ static int imx_pgc_power_up(struct generic_pm_domain *genpd) } }
+ reset_control_assert(domain->reset); + /* Enable reset clocks for all devices in the domain */ ret = clk_bulk_prepare_enable(domain->num_clks, domain->clks); if (ret) { @@ -340,7 +342,8 @@ static int imx_pgc_power_up(struct generic_pm_domain *genpd) goto out_regulator_disable; }
- reset_control_assert(domain->reset); + /* delays for reset to propagate */ + udelay(5);
if (domain->bits.pxx) { /* request the domain to power up */
From: Philippe Schenker philippe.schenker@toradex.com
[ Upstream commit 2fa24aa721ebb3a83dd2093814ba9a5dcdaa3183 ]
The Verdin iMX8M Mini System on Module does not have USB-ID signal connected on Verdin USB_2 (usbotg2). On Verdin Development board this is no problem, as we have connected a USB-Hub that is always connected.
However, if Verdin USB_2 is desired to be used as a single USB-Host port the chipidea driver does not detect if a USB device is plugged into this port, due to runtime pm shutting down the PHY.
Add the power-domain &pgc_otg2 to &usbphynop2 in order to detect plugging events and enumerate the usb device.
Fixes: 6a57f224f734 ("arm64: dts: freescale: add initial support for verdin imx8m mini") Signed-off-by: Philippe Schenker philippe.schenker@toradex.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi | 1 + 1 file changed, 1 insertion(+)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 6491e745b3fa8..d6d31094be0af 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -737,6 +737,7 @@ };
&usbphynop2 { + power-domains = <&pgc_otg2>; vcc-supply = <®_vdd_3v3>; };
From: Tim Harvey tharvey@gateworks.com
[ Upstream commit 7f4dbc3f26e5cb1f056faaaf14277f48c4682fff ]
Since commit 65ac79e18120 ("net: dsa: microchip: add the phylink get_caps") the phy-mode must be set otherwise the switch driver will assume "NA" mode and invalidate the port.
Fixes: 65ac79e18120 ("net: dsa: microchip: add the phylink get_caps") Signed-off-by: Tim Harvey tharvey@gateworks.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts | 4 ++++ 1 file changed, 4 insertions(+)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts index 24737e89038a4..96cac0f969a77 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts @@ -626,24 +626,28 @@ lan1: port@0 { reg = <0>; label = "lan1"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; };
lan2: port@1 { reg = <1>; label = "lan2"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; };
lan3: port@2 { reg = <2>; label = "lan3"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; };
lan4: port@3 { reg = <3>; label = "lan4"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; };
From: Marcel Ziswiler marcel.ziswiler@toradex.com
[ Upstream commit 90974f655922219c0a0cdce7ae8de7f30c549cb5 ]
Fix reset GPIO polarity in-line with the following commit feedaacdadfc ("Input: atmel_mxt_ts - fix up inverted RESET handler").
Fixes: 6a57f224f734 ("arm64: dts: freescale: add initial support for verdin imx8m mini") Signed-off-by: Marcel Ziswiler marcel.ziswiler@toradex.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index d6d31094be0af..c2d4da25482ff 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -595,7 +595,7 @@ pinctrl-0 = <&pinctrl_gpio_9_dsi>, <&pinctrl_i2s_2_bclk_touch_reset>; reg = <0x4a>; /* Verdin I2S_2_BCLK (TOUCH_RESET#, SODIMM 42) */ - reset-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>; status = "disabled"; };
From: Marcel Ziswiler marcel.ziswiler@toradex.com
[ Upstream commit 8f143b9f3849828870bb2a7f28288095ad9a329d ]
Fix reset GPIO polarity in-line with the following commit feedaacdadfc ("Input: atmel_mxt_ts - fix up inverted RESET handler").
Fixes: a39ed23bdf6e ("arm64: dts: freescale: add initial support for verdin imx8m plus") Signed-off-by: Marcel Ziswiler marcel.ziswiler@toradex.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi index fb17e329cd370..f5323291a9b24 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi @@ -620,7 +620,7 @@ interrupts = <5 IRQ_TYPE_EDGE_FALLING>; reg = <0x4a>; /* Verdin GPIO_2 (SODIMM 208) */ - reset-gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; status = "disabled"; }; }; @@ -697,7 +697,7 @@ pinctrl-0 = <&pinctrl_gpio_9_dsi>, <&pinctrl_i2s_2_bclk_touch_reset>; reg = <0x4a>; /* Verdin I2S_2_BCLK (TOUCH_RESET#, SODIMM 42) */ - reset-gpios = <&gpio5 0 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; status = "disabled"; };
From: Andrew Halaney ahalaney@redhat.com
[ Upstream commit c32f1ebfd26bece77141257864ed7b4720da1557 ]
If regulator_enable() fails, enable_count is incremented still. A consumer, assuming no matching regulator_disable() is necessary on failure, will then get this error message upon regulator_put() since enable_count is non-zero:
[ 1.277418] WARNING: CPU: 3 PID: 1 at drivers/regulator/core.c:2304 _regulator_put.part.0+0x168/0x170
The consumer could try to fix this in their driver by cleaning up on error from regulator_enable() (i.e. call regulator_disable()), but that results in the following since regulator_enable() failed and didn't increment user_count:
[ 1.258112] unbalanced disables for vreg_l17c [ 1.262606] WARNING: CPU: 4 PID: 1 at drivers/regulator/core.c:2899 _regulator_disable+0xd4/0x190
Fix this by decrementing enable_count upon failure to enable.
With this in place, just the reason for failure to enable is printed as expected and developers can focus on the root cause of their issue instead of thinking their usage of the regulator consumer api is incorrect. For example, in my case:
[ 1.240426] vreg_l17c: invalid input voltage found
Fixes: 5451781dadf8 ("regulator: core: Only count load for enabled consumers") Signed-off-by: Andrew Halaney ahalaney@redhat.com Reviewed-by: Douglas Anderson dianders@chromium.org Reviewed-by: Brian Masney bmasney@redhat.com Link: https://lore.kernel.org/r/20220819194336.382740-1-ahalaney@redhat.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/regulator/core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 1e54a833f2cf0..a9daaf4d5aaab 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -2732,13 +2732,18 @@ static int _regulator_do_enable(struct regulator_dev *rdev) */ static int _regulator_handle_consumer_enable(struct regulator *regulator) { + int ret; struct regulator_dev *rdev = regulator->rdev;
lockdep_assert_held_once(&rdev->mutex.base);
regulator->enable_count++; - if (regulator->uA_load && regulator->enable_count == 1) - return drms_uA_update(rdev); + if (regulator->uA_load && regulator->enable_count == 1) { + ret = drms_uA_update(rdev); + if (ret) + regulator->enable_count--; + return ret; + }
return 0; }
From: Peter Ujfalusi peter.ujfalusi@linux.intel.com
[ Upstream commit 3942499fba11de048c3ac1390b808e9e6ae88de5 ]
Make sure that the IPC_FLOOD client can not be built in when SND_SOC_SOF is built as module.
Fixes: 6e9548cdb30e5 ("ASoC: SOF: Convert the generic IPC flood test into SOF client") Reported-by: kernel test robot lkp@intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Link: https://lore.kernel.org/r/20220823121554.4255-2-peter.ujfalusi@linux.intel.c... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sof/Kconfig | 1 + 1 file changed, 1 insertion(+)
diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig index 4542868cd730f..96c40542446db 100644 --- a/sound/soc/sof/Kconfig +++ b/sound/soc/sof/Kconfig @@ -196,6 +196,7 @@ config SND_SOC_SOF_DEBUG_ENABLE_FIRMWARE_TRACE
config SND_SOC_SOF_DEBUG_IPC_FLOOD_TEST tristate "SOF enable IPC flood test" + depends on SND_SOC_SOF select SND_SOC_SOF_CLIENT help This option enables a separate client device for IPC flood test
From: Peter Ujfalusi peter.ujfalusi@linux.intel.com
[ Upstream commit 2cf520ffbcbd55c0f2b4276065444d7526d9d197 ]
Make sure that the IPC_MESSAGE_INJECTOR client can not be built in when SND_SOC_SOF is built as module.
Fixes: cac0b0887e530 ("ASoC: SOF: Convert the generic IPC message injector into SOF client") Reported-by: kernel test robot lkp@intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Link: https://lore.kernel.org/r/20220823121554.4255-3-peter.ujfalusi@linux.intel.c... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sof/Kconfig | 1 + 1 file changed, 1 insertion(+)
diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig index 96c40542446db..39216c09f1597 100644 --- a/sound/soc/sof/Kconfig +++ b/sound/soc/sof/Kconfig @@ -215,6 +215,7 @@ config SND_SOC_SOF_DEBUG_IPC_FLOOD_TEST_NUM
config SND_SOC_SOF_DEBUG_IPC_MSG_INJECTOR tristate "SOF enable IPC message injector" + depends on SND_SOC_SOF select SND_SOC_SOF_CLIENT help This option enables the IPC message injector which can be used to send
From: Jens Wiklander jens.wiklander@linaro.org
[ Upstream commit eccd7439709810127563e7e3e49b8b44c7b2791d ]
Include <linux/uaccess.h> to avoid the warning: drivers/tee/tee_shm.c: In function 'tee_shm_register':
drivers/tee/tee_shm.c:242:14: error: implicit declaration of function 'access_ok' [-Werror=implicit-function-declaration]
242 | if (!access_ok((void __user *)addr, length)) | ^~~~~~~~~ cc1: some warnings being treated as errors
Fixes: 573ae4f13f63 ("tee: add overflow check in register_shm_helper()") Reviewed-by: Sumit Garg sumit.garg@linaro.org Reported-by: kernel test robot lkp@intel.com Signed-off-by: Jens Wiklander jens.wiklander@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tee/tee_shm.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 1175f3a46859f..27295bda3e0bd 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/tee_drv.h> +#include <linux/uaccess.h> #include <linux/uio.h> #include "tee_private.h"
From: Shiraz Saleem shiraz.saleem@intel.com
[ Upstream commit ead54ced6321099978d30d62dc49c282a6e70574 ]
SW generated completions for outstanding WRs posted on SQ after QP is in error target the wrong CQ. This causes the ib_drain_sq to hang with no completion.
Fix this to generate completions on the right CQ.
[ 863.969340] INFO: task kworker/u52:2:671 blocked for more than 122 seconds. [ 863.979224] Not tainted 5.14.0-130.el9.x86_64 #1 [ 863.986588] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 863.996997] task:kworker/u52:2 state:D stack: 0 pid: 671 ppid: 2 flags:0x00004000 [ 864.007272] Workqueue: xprtiod xprt_autoclose [sunrpc] [ 864.014056] Call Trace: [ 864.017575] __schedule+0x206/0x580 [ 864.022296] schedule+0x43/0xa0 [ 864.026736] schedule_timeout+0x115/0x150 [ 864.032185] __wait_for_common+0x93/0x1d0 [ 864.037717] ? usleep_range_state+0x90/0x90 [ 864.043368] __ib_drain_sq+0xf6/0x170 [ib_core] [ 864.049371] ? __rdma_block_iter_next+0x80/0x80 [ib_core] [ 864.056240] ib_drain_sq+0x66/0x70 [ib_core] [ 864.062003] rpcrdma_xprt_disconnect+0x82/0x3b0 [rpcrdma] [ 864.069365] ? xprt_prepare_transmit+0x5d/0xc0 [sunrpc] [ 864.076386] xprt_rdma_close+0xe/0x30 [rpcrdma] [ 864.082593] xprt_autoclose+0x52/0x100 [sunrpc] [ 864.088718] process_one_work+0x1e8/0x3c0 [ 864.094170] worker_thread+0x50/0x3b0 [ 864.099109] ? rescuer_thread+0x370/0x370 [ 864.104473] kthread+0x149/0x170 [ 864.109022] ? set_kthread_struct+0x40/0x40 [ 864.114713] ret_from_fork+0x22/0x30
Fixes: 81091d7696ae ("RDMA/irdma: Add SW mechanism to generate completions on error") Link: https://lore.kernel.org/r/20220824154358.117-1-shiraz.saleem@intel.com Reported-by: Kamal Heib kamalheib1@gmail.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/irdma/utils.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index ab3c5208a1231..7b15faadfef5c 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -2597,7 +2597,7 @@ void irdma_generate_flush_completions(struct irdma_qp *iwqp) spin_unlock_irqrestore(&iwqp->lock, flags2); spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1); if (compl_generated) - irdma_comp_handler(iwqp->iwrcq); + irdma_comp_handler(iwqp->iwscq); } else { spin_unlock_irqrestore(&iwqp->iwscq->lock, flags1); mod_delayed_work(iwqp->iwdev->cleanup_wq, &iwqp->dwork_flush,
From: Geert Uytterhoeven geert+renesas@glider.be
[ Upstream commit ab2866f12ca18747413ba41409231d44e0c6149b ]
The interrupt number for the HSCIF0 serial port, which serves as the serial console on the White Hawk board, is incorrect, causing userspace to hang immediately as soon as it tries to print something. Kernel output is unaffected, as it is printed using polling.
Fixes: 987da486d84a5643 ("arm64: dts: renesas: Add Renesas R8A779G0 SoC support") Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Reviewed-by: Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com Link: https://lore.kernel.org/r/751dcef40d4534e856ed49b1d5b3a3e8d365ec42.166141937... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/renesas/r8a779g0.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi index 7cbb0de060ddc..1c15726cff8bf 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi @@ -85,7 +85,7 @@ "renesas,rcar-gen4-hscif", "renesas,hscif"; reg = <0 0xe6540000 0 96>; - interrupts = <GIC_SPI 245 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 246 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cpg CPG_MOD 514>, <&cpg CPG_CORE R8A779G0_CLK_S0D3_PER>, <&scif_clk>;
From: Michael Guralnik michaelgur@nvidia.com
[ Upstream commit 27cfde795a96aef1e859a5480489944b95421e46 ]
Fix the order of source and destination addresses when resolving the route between server and client to validate use of correct net device.
The reverse order we had so far didn't actually validate the net device as the server would try to resolve the route to itself, thus always getting the server's net device.
The issue was discovered when running cm applications on a single host between 2 interfaces with same subnet and source based routing rules. When resolving the reverse route the source based route rules were ignored.
Fixes: f887f2ac87c2 ("IB/cma: Validate routing of incoming requests") Link: https://lore.kernel.org/r/1c1ec2277a131d277ebcceec987fd338d35b775f.166125187... Signed-off-by: Michael Guralnik michaelgur@nvidia.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index fabca5e51e3d4..4dd133eccfdfb 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1719,8 +1719,8 @@ cma_ib_id_from_event(struct ib_cm_id *cm_id, }
if (!validate_net_dev(*net_dev, - (struct sockaddr *)&req->listen_addr_storage, - (struct sockaddr *)&req->src_addr_storage)) { + (struct sockaddr *)&req->src_addr_storage, + (struct sockaddr *)&req->listen_addr_storage)) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; }
From: Liang He windhl@126.com
[ Upstream commit 1085f5080647f0c9f357c270a537869191f7f2a1 ]
In brcmstb_pm_probe(), there are two kinds of leak bugs:
(1) we need to add of_node_put() when for_each__matching_node() breaks (2) we need to add iounmap() for each iomap in fail path
Fixes: 0b741b8234c8 ("soc: bcm: brcmstb: Add support for S2/S3/S5 suspend states (ARM)") Signed-off-by: Liang He windhl@126.com Link: https://lore.kernel.org/r/20220707015620.306468-1-windhl@126.com Signed-off-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/soc/bcm/brcmstb/pm/pm-arm.c | 50 ++++++++++++++++++++++------- 1 file changed, 39 insertions(+), 11 deletions(-)
diff --git a/drivers/soc/bcm/brcmstb/pm/pm-arm.c b/drivers/soc/bcm/brcmstb/pm/pm-arm.c index 70ad0f3dce283..286f5d57c0cab 100644 --- a/drivers/soc/bcm/brcmstb/pm/pm-arm.c +++ b/drivers/soc/bcm/brcmstb/pm/pm-arm.c @@ -684,13 +684,14 @@ static int brcmstb_pm_probe(struct platform_device *pdev) const struct of_device_id *of_id = NULL; struct device_node *dn; void __iomem *base; - int ret, i; + int ret, i, s;
/* AON ctrl registers */ base = brcmstb_ioremap_match(aon_ctrl_dt_ids, 0, NULL); if (IS_ERR(base)) { pr_err("error mapping AON_CTRL\n"); - return PTR_ERR(base); + ret = PTR_ERR(base); + goto aon_err; } ctrl.aon_ctrl_base = base;
@@ -700,8 +701,10 @@ static int brcmstb_pm_probe(struct platform_device *pdev) /* Assume standard offset */ ctrl.aon_sram = ctrl.aon_ctrl_base + AON_CTRL_SYSTEM_DATA_RAM_OFS; + s = 0; } else { ctrl.aon_sram = base; + s = 1; }
writel_relaxed(0, ctrl.aon_sram + AON_REG_PANIC); @@ -711,7 +714,8 @@ static int brcmstb_pm_probe(struct platform_device *pdev) (const void **)&ddr_phy_data); if (IS_ERR(base)) { pr_err("error mapping DDR PHY\n"); - return PTR_ERR(base); + ret = PTR_ERR(base); + goto ddr_phy_err; } ctrl.support_warm_boot = ddr_phy_data->supports_warm_boot; ctrl.pll_status_offset = ddr_phy_data->pll_status_offset; @@ -731,17 +735,20 @@ static int brcmstb_pm_probe(struct platform_device *pdev) for_each_matching_node(dn, ddr_shimphy_dt_ids) { i = ctrl.num_memc; if (i >= MAX_NUM_MEMC) { + of_node_put(dn); pr_warn("too many MEMCs (max %d)\n", MAX_NUM_MEMC); break; }
base = of_io_request_and_map(dn, 0, dn->full_name); if (IS_ERR(base)) { + of_node_put(dn); if (!ctrl.support_warm_boot) break;
pr_err("error mapping DDR SHIMPHY %d\n", i); - return PTR_ERR(base); + ret = PTR_ERR(base); + goto ddr_shimphy_err; } ctrl.memcs[i].ddr_shimphy_base = base; ctrl.num_memc++; @@ -752,14 +759,18 @@ static int brcmstb_pm_probe(struct platform_device *pdev) for_each_matching_node(dn, brcmstb_memc_of_match) { base = of_iomap(dn, 0); if (!base) { + of_node_put(dn); pr_err("error mapping DDR Sequencer %d\n", i); - return -ENOMEM; + ret = -ENOMEM; + goto brcmstb_memc_err; }
of_id = of_match_node(brcmstb_memc_of_match, dn); if (!of_id) { iounmap(base); - return -EINVAL; + of_node_put(dn); + ret = -EINVAL; + goto brcmstb_memc_err; }
ddr_seq_data = of_id->data; @@ -779,21 +790,24 @@ static int brcmstb_pm_probe(struct platform_device *pdev) dn = of_find_matching_node(NULL, sram_dt_ids); if (!dn) { pr_err("SRAM not found\n"); - return -EINVAL; + ret = -EINVAL; + goto brcmstb_memc_err; }
ret = brcmstb_init_sram(dn); of_node_put(dn); if (ret) { pr_err("error setting up SRAM for PM\n"); - return ret; + goto brcmstb_memc_err; }
ctrl.pdev = pdev;
ctrl.s3_params = kmalloc(sizeof(*ctrl.s3_params), GFP_KERNEL); - if (!ctrl.s3_params) - return -ENOMEM; + if (!ctrl.s3_params) { + ret = -ENOMEM; + goto s3_params_err; + } ctrl.s3_params_pa = dma_map_single(&pdev->dev, ctrl.s3_params, sizeof(*ctrl.s3_params), DMA_TO_DEVICE); @@ -813,7 +827,21 @@ static int brcmstb_pm_probe(struct platform_device *pdev)
out: kfree(ctrl.s3_params); - +s3_params_err: + iounmap(ctrl.boot_sram); +brcmstb_memc_err: + for (i--; i >= 0; i--) + iounmap(ctrl.memcs[i].ddr_ctrl); +ddr_shimphy_err: + for (i = 0; i < ctrl.num_memc; i++) + iounmap(ctrl.memcs[i].ddr_shimphy_base); + + iounmap(ctrl.memcs[0].ddr_phy_base); +ddr_phy_err: + iounmap(ctrl.aon_ctrl_base); + if (s) + iounmap(ctrl.aon_sram); +aon_err: pr_warn("PM: initialization failed with code %d\n", ret);
return ret;
From: Chengchang Tang tangchengchang@huawei.com
[ Upstream commit 55af9d498556f0860eb89ffa7677e8d73f6f643f ]
The supported page size for hns is (4K, 128M), not (4K, 2G).
Fixes: cfc85f3e4b7f ("RDMA/hns: Add profile support for hip08 driver") Link: https://lore.kernel.org/r/20220829105021.1427804-2-liangwenpeng@huawei.com Signed-off-by: Chengchang Tang tangchengchang@huawei.com Signed-off-by: Wenpeng Liang liangwenpeng@huawei.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 7ffb7824d2689..2d7e91004e3c7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -83,7 +83,7 @@
#define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ PAGE_SIZE #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ PAGE_SIZE -#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000 +#define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFF000 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM 2 #define HNS_ROCE_INVALID_LKEY 0x0 #define HNS_ROCE_INVALID_SGE_LENGTH 0x80000000
From: Wenpeng Liang liangwenpeng@huawei.com
[ Upstream commit 0c8b5d6268d92d141bfd64d21c870d295a84dee1 ]
The value of qp->rq.wqe_shift of HIP08 is always determined by the number of sge. So delete the wrong branch.
Fixes: cfc85f3e4b7f ("RDMA/hns: Add profile support for hip08 driver") Fixes: 926a01dc000d ("RDMA/hns: Add QP operations support for hip08 SoC") Link: https://lore.kernel.org/r/20220829105021.1427804-3-liangwenpeng@huawei.com Signed-off-by: Wenpeng Liang liangwenpeng@huawei.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hns/hns_roce_qp.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 48d3616a6d71d..7bee7f6c5e702 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -462,11 +462,8 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) + hr_qp->rq.rsv_sge);
- if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE) - hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz); - else - hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz * - hr_qp->rq.max_gs); + hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz * + hr_qp->rq.max_gs);
hr_qp->rq.wqe_cnt = cnt; if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE &&
From: Yixing Liu liuyixing1@huawei.com
[ Upstream commit 45baad7dd98f4d83f67c86c28769d3184390e324 ]
The bt number of qpc_timer of HIP09 increases compared with that of HIP08. Therefore, qpc_timer_bt_num and num_qpc_timer do not match. As a result, the driver may fail to allocate qpc_timer. So the driver needs to uniquely uses qpc_timer_bt_num to represent the bt number of qpc_timer.
Fixes: 0e40dc2f70cd ("RDMA/hns: Add timer allocation support for hip08") Link: https://lore.kernel.org/r/20220829105021.1427804-4-liangwenpeng@huawei.com Signed-off-by: Yixing Liu liuyixing1@huawei.com Signed-off-by: Wenpeng Liang liangwenpeng@huawei.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hns/hns_roce_device.h | 1 - drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 3 +-- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 +- drivers/infiniband/hw/hns/hns_roce_main.c | 2 +- 4 files changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 2855e9ad4b328..1df076e70e293 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -730,7 +730,6 @@ struct hns_roce_caps { u32 num_qps; u32 num_pi_qps; u32 reserved_qps; - int num_qpc_timer; u32 num_srqs; u32 max_wqes; u32 max_srq_wrs; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index b354caeaa9b29..49edff989f1f1 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1941,7 +1941,7 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
caps->num_mtpts = HNS_ROCE_V2_MAX_MTPT_NUM; caps->num_pds = HNS_ROCE_V2_MAX_PD_NUM; - caps->num_qpc_timer = HNS_ROCE_V2_MAX_QPC_TIMER_NUM; + caps->qpc_timer_bt_num = HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM; caps->cqc_timer_bt_num = HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM;
caps->max_qp_init_rdma = HNS_ROCE_V2_MAX_QP_INIT_RDMA; @@ -2237,7 +2237,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) caps->max_rq_sg = le16_to_cpu(resp_a->max_rq_sg); caps->max_rq_sg = roundup_pow_of_two(caps->max_rq_sg); caps->max_extend_sg = le32_to_cpu(resp_a->max_extend_sg); - caps->num_qpc_timer = le16_to_cpu(resp_a->num_qpc_timer); caps->max_srq_sges = le16_to_cpu(resp_a->max_srq_sges); caps->max_srq_sges = roundup_pow_of_two(caps->max_srq_sges); caps->num_aeq_vectors = resp_a->num_aeq_vectors; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 2d7e91004e3c7..e4b640caee1b7 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -36,11 +36,11 @@ #include <linux/bitops.h>
#define HNS_ROCE_V2_MAX_QP_NUM 0x1000 -#define HNS_ROCE_V2_MAX_QPC_TIMER_NUM 0x200 #define HNS_ROCE_V2_MAX_WQE_NUM 0x8000 #define HNS_ROCE_V2_MAX_SRQ_WR 0x8000 #define HNS_ROCE_V2_MAX_SRQ_SGE 64 #define HNS_ROCE_V2_MAX_CQ_NUM 0x100000 +#define HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM 0x100 #define HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM 0x100 #define HNS_ROCE_V2_MAX_SRQ_NUM 0x100000 #define HNS_ROCE_V2_MAX_CQE_NUM 0x400000 diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index c8af4ebd7cbd3..4ccb217b2841d 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -725,7 +725,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev) ret = hns_roce_init_hem_table(hr_dev, &hr_dev->qpc_timer_table, HEM_TYPE_QPC_TIMER, hr_dev->caps.qpc_timer_entry_sz, - hr_dev->caps.num_qpc_timer, 1); + hr_dev->caps.qpc_timer_bt_num, 1); if (ret) { dev_err(dev, "Failed to init QPC timer memory, aborting.\n");
From: Ajay.Kathat@microchip.com Ajay.Kathat@microchip.com
[ Upstream commit 40b717bfcefab28a0656b8caa5e43d5449e5a671 ]
Sometimes 'wilc_sdio_cmd53' is called with addresses pointing to an object on the stack. Use dynamically allocated memory for cmd53 instead of stack address which is not DMA'able.
Fixes: 5625f965d764 ("wilc1000: move wilc driver out of staging") Reported-by: Michael Walle mwalle@kernel.org Suggested-by: Michael Walle mwalle@kernel.org Signed-off-by: Ajay Singh ajay.kathat@microchip.com Reviewed-by: Michael Walle mwalle@kernel.org Tested-by: Michael Walle mwalle@kernel.org Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20220809075749.62752-1-ajay.kathat@microchip.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/wireless/microchip/wilc1000/netdev.h | 1 + .../net/wireless/microchip/wilc1000/sdio.c | 39 ++++++++++++++++--- .../net/wireless/microchip/wilc1000/wlan.c | 15 ++++++- 3 files changed, 47 insertions(+), 8 deletions(-)
diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.h b/drivers/net/wireless/microchip/wilc1000/netdev.h index a067274c20144..bf001e9def6aa 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.h +++ b/drivers/net/wireless/microchip/wilc1000/netdev.h @@ -254,6 +254,7 @@ struct wilc { u8 *rx_buffer; u32 rx_buffer_offset; u8 *tx_buffer; + u32 *vmm_table;
struct txq_handle txq[NQUEUES]; int txq_entries; diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c index 7962c11cfe848..56f924a31bc66 100644 --- a/drivers/net/wireless/microchip/wilc1000/sdio.c +++ b/drivers/net/wireless/microchip/wilc1000/sdio.c @@ -27,6 +27,7 @@ struct wilc_sdio { bool irq_gpio; u32 block_size; int has_thrpt_enh3; + u8 *cmd53_buf; };
struct sdio_cmd52 { @@ -46,6 +47,7 @@ struct sdio_cmd53 { u32 count: 9; u8 *buffer; u32 block_size; + bool use_global_buf; };
static const struct wilc_hif_func wilc_hif_sdio; @@ -90,6 +92,8 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd) { struct sdio_func *func = container_of(wilc->dev, struct sdio_func, dev); int size, ret; + struct wilc_sdio *sdio_priv = wilc->bus_data; + u8 *buf = cmd->buffer;
sdio_claim_host(func);
@@ -100,12 +104,23 @@ static int wilc_sdio_cmd53(struct wilc *wilc, struct sdio_cmd53 *cmd) else size = cmd->count;
+ if (cmd->use_global_buf) { + if (size > sizeof(u32)) + return -EINVAL; + + buf = sdio_priv->cmd53_buf; + } + if (cmd->read_write) { /* write */ - ret = sdio_memcpy_toio(func, cmd->address, - (void *)cmd->buffer, size); + if (cmd->use_global_buf) + memcpy(buf, cmd->buffer, size); + + ret = sdio_memcpy_toio(func, cmd->address, buf, size); } else { /* read */ - ret = sdio_memcpy_fromio(func, (void *)cmd->buffer, - cmd->address, size); + ret = sdio_memcpy_fromio(func, buf, cmd->address, size); + + if (cmd->use_global_buf) + memcpy(cmd->buffer, buf, size); }
sdio_release_host(func); @@ -127,6 +142,12 @@ static int wilc_sdio_probe(struct sdio_func *func, if (!sdio_priv) return -ENOMEM;
+ sdio_priv->cmd53_buf = kzalloc(sizeof(u32), GFP_KERNEL); + if (!sdio_priv->cmd53_buf) { + ret = -ENOMEM; + goto free; + } + ret = wilc_cfg80211_init(&wilc, &func->dev, WILC_HIF_SDIO, &wilc_hif_sdio); if (ret) @@ -160,6 +181,7 @@ static int wilc_sdio_probe(struct sdio_func *func, irq_dispose_mapping(wilc->dev_irq_num); wilc_netdev_cleanup(wilc); free: + kfree(sdio_priv->cmd53_buf); kfree(sdio_priv); return ret; } @@ -171,6 +193,7 @@ static void wilc_sdio_remove(struct sdio_func *func)
clk_disable_unprepare(wilc->rtc_clk); wilc_netdev_cleanup(wilc); + kfree(sdio_priv->cmd53_buf); kfree(sdio_priv); }
@@ -367,8 +390,9 @@ static int wilc_sdio_write_reg(struct wilc *wilc, u32 addr, u32 data) cmd.address = WILC_SDIO_FBR_DATA_REG; cmd.block_mode = 0; cmd.increment = 1; - cmd.count = 4; + cmd.count = sizeof(u32); cmd.buffer = (u8 *)&data; + cmd.use_global_buf = true; cmd.block_size = sdio_priv->block_size; ret = wilc_sdio_cmd53(wilc, &cmd); if (ret) @@ -406,6 +430,7 @@ static int wilc_sdio_write(struct wilc *wilc, u32 addr, u8 *buf, u32 size) nblk = size / block_size; nleft = size % block_size;
+ cmd.use_global_buf = false; if (nblk > 0) { cmd.block_mode = 1; cmd.increment = 1; @@ -484,8 +509,9 @@ static int wilc_sdio_read_reg(struct wilc *wilc, u32 addr, u32 *data) cmd.address = WILC_SDIO_FBR_DATA_REG; cmd.block_mode = 0; cmd.increment = 1; - cmd.count = 4; + cmd.count = sizeof(u32); cmd.buffer = (u8 *)data; + cmd.use_global_buf = true;
cmd.block_size = sdio_priv->block_size; ret = wilc_sdio_cmd53(wilc, &cmd); @@ -527,6 +553,7 @@ static int wilc_sdio_read(struct wilc *wilc, u32 addr, u8 *buf, u32 size) nblk = size / block_size; nleft = size % block_size;
+ cmd.use_global_buf = false; if (nblk > 0) { cmd.block_mode = 1; cmd.increment = 1; diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c index 48441f0389ca1..0c8a571486d25 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan.c +++ b/drivers/net/wireless/microchip/wilc1000/wlan.c @@ -714,7 +714,7 @@ int wilc_wlan_handle_txq(struct wilc *wilc, u32 *txq_count) int ret = 0; int counter; int timeout; - u32 vmm_table[WILC_VMM_TBL_SIZE]; + u32 *vmm_table = wilc->vmm_table; u8 ac_pkt_num_to_chip[NQUEUES] = {0, 0, 0, 0}; const struct wilc_hif_func *func; int srcu_idx; @@ -1251,6 +1251,8 @@ void wilc_wlan_cleanup(struct net_device *dev) while ((rqe = wilc_wlan_rxq_remove(wilc))) kfree(rqe);
+ kfree(wilc->vmm_table); + wilc->vmm_table = NULL; kfree(wilc->rx_buffer); wilc->rx_buffer = NULL; kfree(wilc->tx_buffer); @@ -1485,6 +1487,14 @@ int wilc_wlan_init(struct net_device *dev) goto fail; }
+ if (!wilc->vmm_table) + wilc->vmm_table = kzalloc(WILC_VMM_TBL_SIZE, GFP_KERNEL); + + if (!wilc->vmm_table) { + ret = -ENOBUFS; + goto fail; + } + if (!wilc->tx_buffer) wilc->tx_buffer = kmalloc(WILC_TX_BUFF_SIZE, GFP_KERNEL);
@@ -1509,7 +1519,8 @@ int wilc_wlan_init(struct net_device *dev) return 0;
fail: - + kfree(wilc->vmm_table); + wilc->vmm_table = NULL; kfree(wilc->rx_buffer); wilc->rx_buffer = NULL; kfree(wilc->tx_buffer);
From: Claudiu Beznea claudiu.beznea@microchip.com
[ Upstream commit a02875c4cbd6f3d2f33d70cc158a19ef02d4b84f ]
It has been discovered that on some parts, from time to time, self-refresh procedure doesn't work as expected. Debugging and investigating it proved that disabling AC DLL introduce glitches in RAM controllers which leads to unexpected behavior. This is confirmed as a hardware bug. DLL bypass disables 3 DLLs: 2 DX DLLs and AC DLL. Thus, keep only DX DLLs disabled. This introduce 6mA extra current consumption on VDDCORE when switching to any ULP mode or standby mode but the self-refresh procedure still works.
Fixes: f0bbf17958e8 ("ARM: at91: pm: add self-refresh support for sama7g5") Suggested-by: Frederic Schumacher frederic.schumacher@microchip.com Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Tested-by: Cristian Birsan cristian.birsan@microchip.com Link: https://lore.kernel.org/r/20220826083927.3107272-3-claudiu.beznea@microchip.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-at91/pm_suspend.S | 24 +++++++++++++++++------- include/soc/at91/sama7-ddr.h | 4 ++++ 2 files changed, 21 insertions(+), 7 deletions(-)
diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S index abe4ced33edaf..ffed4d9490428 100644 --- a/arch/arm/mach-at91/pm_suspend.S +++ b/arch/arm/mach-at91/pm_suspend.S @@ -172,9 +172,15 @@ sr_ena_2: /* Put DDR PHY's DLL in bypass mode for non-backup modes. */ cmp r7, #AT91_PM_BACKUP beq sr_ena_3 - ldr tmp1, [r3, #DDR3PHY_PIR] - orr tmp1, tmp1, #DDR3PHY_PIR_DLLBYP - str tmp1, [r3, #DDR3PHY_PIR] + + /* Disable DX DLLs. */ + ldr tmp1, [r3, #DDR3PHY_DX0DLLCR] + orr tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS + str tmp1, [r3, #DDR3PHY_DX0DLLCR] + + ldr tmp1, [r3, #DDR3PHY_DX1DLLCR] + orr tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS + str tmp1, [r3, #DDR3PHY_DX1DLLCR]
sr_ena_3: /* Power down DDR PHY data receivers. */ @@ -221,10 +227,14 @@ sr_ena_3: bic tmp1, tmp1, #DDR3PHY_DSGCR_ODTPDD_ODT0 str tmp1, [r3, #DDR3PHY_DSGCR]
- /* Take DDR PHY's DLL out of bypass mode. */ - ldr tmp1, [r3, #DDR3PHY_PIR] - bic tmp1, tmp1, #DDR3PHY_PIR_DLLBYP - str tmp1, [r3, #DDR3PHY_PIR] + /* Enable DX DLLs. */ + ldr tmp1, [r3, #DDR3PHY_DX0DLLCR] + bic tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS + str tmp1, [r3, #DDR3PHY_DX0DLLCR] + + ldr tmp1, [r3, #DDR3PHY_DX1DLLCR] + bic tmp1, tmp1, #DDR3PHY_DXDLLCR_DLLDIS + str tmp1, [r3, #DDR3PHY_DX1DLLCR]
/* Enable quasi-dynamic programming. */ mov tmp1, #0 diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h index 9e17247474fa9..2706bc48c0764 100644 --- a/include/soc/at91/sama7-ddr.h +++ b/include/soc/at91/sama7-ddr.h @@ -39,6 +39,10 @@
#define DDR3PHY_ZQ0SR0 (0x188) /* ZQ status register 0 */
+#define DDR3PHY_DX0DLLCR (0x1CC) /* DDR3PHY DATX8 DLL Control Register */ +#define DDR3PHY_DX1DLLCR (0x20C) /* DDR3PHY DATX8 DLL Control Register */ +#define DDR3PHY_DXDLLCR_DLLDIS (1 << 31) /* DLL Disable */ + /* UDDRC */ #define UDDRC_STAT (0x04) /* UDDRC Operating Mode Status Register */ #define UDDRC_STAT_SELFREF_TYPE_DIS (0x0 << 4) /* SDRAM is not in Self-refresh */
From: Claudiu Beznea claudiu.beznea@microchip.com
[ Upstream commit 7a94b83a7dc551607b6c4400df29151e6a951f07 ]
On SAMA7G5, when resuming from backup and self-refresh, the bootloader performs DDR PHY recalibration by restoring the value of ZQ0SR0 (stored in RAM by Linux before going to backup and self-refresh). It has been discovered that the current procedure doesn't work for all possible values that might go to ZQ0SR0 due to hardware bug. The workaround to this is to avoid storing some values in ZQ0SR0. Thus Linux will read the ZQ0SR0 register and cache its value in RAM after processing it (using modified_gray_code array). The bootloader will restore the processed value.
Fixes: d2d4716d8384 ("ARM: at91: pm: save ddr phy calibration data to securam") Suggested-by: Frederic Schumacher frederic.schumacher@microchip.com Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220826083927.3107272-4-claudiu.beznea@microchip.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-at91/pm.c | 36 ++++++++++++++++++++++++++++++++---- include/soc/at91/sama7-ddr.h | 4 ++++ 2 files changed, 36 insertions(+), 4 deletions(-)
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index df6d673e83d56..f4501dea98b04 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -541,9 +541,41 @@ extern u32 at91_pm_suspend_in_sram_sz;
static int at91_suspend_finish(unsigned long val) { + unsigned char modified_gray_code[] = { + 0x00, 0x01, 0x02, 0x03, 0x06, 0x07, 0x04, 0x05, 0x0c, 0x0d, + 0x0e, 0x0f, 0x0a, 0x0b, 0x08, 0x09, 0x18, 0x19, 0x1a, 0x1b, + 0x1e, 0x1f, 0x1c, 0x1d, 0x14, 0x15, 0x16, 0x17, 0x12, 0x13, + 0x10, 0x11, + }; + unsigned int tmp, index; int i;
if (soc_pm.data.mode == AT91_PM_BACKUP && soc_pm.data.ramc_phy) { + /* + * Bootloader will perform DDR recalibration and will try to + * restore the ZQ0SR0 with the value saved here. But the + * calibration is buggy and restoring some values from ZQ0SR0 + * is forbidden and risky thus we need to provide processed + * values for these (modified gray code values). + */ + tmp = readl(soc_pm.data.ramc_phy + DDR3PHY_ZQ0SR0); + + /* Store pull-down output impedance select. */ + index = (tmp >> DDR3PHY_ZQ0SR0_PDO_OFF) & 0x1f; + soc_pm.bu->ddr_phy_calibration[0] = modified_gray_code[index]; + + /* Store pull-up output impedance select. */ + index = (tmp >> DDR3PHY_ZQ0SR0_PUO_OFF) & 0x1f; + soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index]; + + /* Store pull-down on-die termination impedance select. */ + index = (tmp >> DDR3PHY_ZQ0SR0_PDODT_OFF) & 0x1f; + soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index]; + + /* Store pull-up on-die termination impedance select. */ + index = (tmp >> DDR3PHY_ZQ0SRO_PUODT_OFF) & 0x1f; + soc_pm.bu->ddr_phy_calibration[0] |= modified_gray_code[index]; + /* * The 1st 8 words of memory might get corrupted in the process * of DDR PHY recalibration; it is saved here in securam and it @@ -1066,10 +1098,6 @@ static int __init at91_pm_backup_init(void) of_scan_flat_dt(at91_pm_backup_scan_memcs, &located); if (!located) goto securam_fail; - - /* DDR3PHY_ZQ0SR0 */ - soc_pm.bu->ddr_phy_calibration[0] = readl(soc_pm.data.ramc_phy + - 0x188); }
return 0; diff --git a/include/soc/at91/sama7-ddr.h b/include/soc/at91/sama7-ddr.h index 2706bc48c0764..6ce3bd22f6c69 100644 --- a/include/soc/at91/sama7-ddr.h +++ b/include/soc/at91/sama7-ddr.h @@ -38,6 +38,10 @@ #define DDR3PHY_DSGCR_ODTPDD_ODT0 (1 << 20) /* ODT[0] Power Down Driver */
#define DDR3PHY_ZQ0SR0 (0x188) /* ZQ status register 0 */ +#define DDR3PHY_ZQ0SR0_PDO_OFF (0) /* Pull-down output impedance select offset */ +#define DDR3PHY_ZQ0SR0_PUO_OFF (5) /* Pull-up output impedance select offset */ +#define DDR3PHY_ZQ0SR0_PDODT_OFF (10) /* Pull-down on-die termination impedance select offset */ +#define DDR3PHY_ZQ0SRO_PUODT_OFF (15) /* Pull-up on-die termination impedance select offset */
#define DDR3PHY_DX0DLLCR (0x1CC) /* DDR3PHY DATX8 DLL Control Register */ #define DDR3PHY_DX1DLLCR (0x20C) /* DDR3PHY DATX8 DLL Control Register */
From: Claudiu Beznea claudiu.beznea@microchip.com
[ Upstream commit addf7efec23af2b67547800aa232d551945e7de2 ]
Min and max output ranges of regulators need to satisfy board requirements not PMIC requirements. Thus adjust device tree to cope with this.
Fixes: 5d4c3cfb63fe ("ARM: dts: at91: sama5d27_wlsom1: add SAMA5D27 wlsom1 and wlsom1-ek") Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220826083927.3107272-5-claudiu.beznea@microchip.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi index ba621783acdbc..de0bef06af2c4 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi @@ -76,8 +76,8 @@ regulators { vdd_3v3: VDD_IO { regulator-name = "VDD_IO"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -95,8 +95,8 @@
vddio_ddr: VDD_DDR { regulator-name = "VDD_DDR"; - regulator-min-microvolt = <600000>; - regulator-max-microvolt = <1850000>; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -118,8 +118,8 @@
vdd_core: VDD_CORE { regulator-name = "VDD_CORE"; - regulator-min-microvolt = <600000>; - regulator-max-microvolt = <1850000>; + regulator-min-microvolt = <1250000>; + regulator-max-microvolt = <1250000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -160,8 +160,8 @@
LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on;
regulator-state-standby { @@ -175,8 +175,8 @@
LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; regulator-always-on;
regulator-state-standby {
From: Claudiu Beznea claudiu.beznea@microchip.com
[ Upstream commit 7737d93666eea282febf95e5fa3b3fde1f2549f3 ]
Min and max output ranges of regulators need to satisfy board requirements not PMIC requirements. Thus adjust device tree to cope with this.
Fixes: 68a95ef72cef ("ARM: dts: at91: sama5d2-icp: add SAMA5D2-ICP") Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220826083927.3107272-6-claudiu.beznea@microchip.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/at91-sama5d2_icp.dts | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts index 164201a8fbf2d..64d5ae179bec9 100644 --- a/arch/arm/boot/dts/at91-sama5d2_icp.dts +++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts @@ -197,8 +197,8 @@ regulators { vdd_io_reg: VDD_IO { regulator-name = "VDD_IO"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -216,8 +216,8 @@
VDD_DDR { regulator-name = "VDD_DDR"; - regulator-min-microvolt = <600000>; - regulator-max-microvolt = <1850000>; + regulator-min-microvolt = <1350000>; + regulator-max-microvolt = <1350000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -235,8 +235,8 @@
VDD_CORE { regulator-name = "VDD_CORE"; - regulator-min-microvolt = <600000>; - regulator-max-microvolt = <1850000>; + regulator-min-microvolt = <1250000>; + regulator-max-microvolt = <1250000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -273,8 +273,8 @@
LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; regulator-always-on;
regulator-state-standby { @@ -288,8 +288,8 @@
LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-always-on;
regulator-state-standby {
From: Claudiu Beznea claudiu.beznea@microchip.com
[ Upstream commit 7f41d52ced9e1b7ed4ff8e1ae9cacbf46b64e6db ]
Min and max output ranges of regulators need to satisfy board requirements not PMIC requirements. Thus adjust device tree to cope with this.
Fixes: 7540629e2fc7 ("ARM: dts: at91: add sama7g5 SoC DT and sama7g5-ek") Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220826083927.3107272-7-claudiu.beznea@microchip.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/at91-sama7g5ek.dts | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts index 103544620fd7c..b261b4da08502 100644 --- a/arch/arm/boot/dts/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/at91-sama7g5ek.dts @@ -244,8 +244,8 @@ regulators { vdd_3v3: VDD_IO { regulator-name = "VDD_IO"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -264,8 +264,8 @@
vddioddr: VDD_DDR { regulator-name = "VDD_DDR"; - regulator-min-microvolt = <1300000>; - regulator-max-microvolt = <1450000>; + regulator-min-microvolt = <1350000>; + regulator-max-microvolt = <1350000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -285,8 +285,8 @@
vddcore: VDD_CORE { regulator-name = "VDD_CORE"; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1850000>; + regulator-min-microvolt = <1150000>; + regulator-max-microvolt = <1150000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-always-on; @@ -306,7 +306,7 @@ vddcpu: VDD_OTHER { regulator-name = "VDD_OTHER"; regulator-min-microvolt = <1050000>; - regulator-max-microvolt = <1850000>; + regulator-max-microvolt = <1250000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; regulator-ramp-delay = <3125>; @@ -326,8 +326,8 @@
vldo1: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <3700000>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; regulator-always-on;
regulator-state-standby {
From: Claudiu Beznea claudiu.beznea@microchip.com
[ Upstream commit 617a0d9fe6867bf5b3b7272629cd780c27c877d9 ]
ldo2 is not used by any consumer on sama5d27_wlsom1 board, thus don't keep it enabled all the time.
Fixes: 5d4c3cfb63fe ("ARM: dts: at91: sama5d27_wlsom1: add SAMA5D27 wlsom1 and wlsom1-ek") Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220826083927.3107272-8-claudiu.beznea@microchip.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi | 1 - 1 file changed, 1 deletion(-)
diff --git a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi index de0bef06af2c4..d6f364c6be94b 100644 --- a/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_wlsom1.dtsi @@ -177,7 +177,6 @@ regulator-name = "LDO2"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; - regulator-always-on;
regulator-state-standby { regulator-on-in-suspend;
From: Claudiu Beznea claudiu.beznea@microchip.com
[ Upstream commit 3d074b750d2b4c91962f10ea1df1c289ce0d3ce8 ]
VDD_OTHER is not connected to any on board consumer thus it is not needed to keep it enabled all the time.
Fixes: 68a95ef72cef ("ARM: dts: at91: sama5d2-icp: add SAMA5D2-ICP") Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220826083927.3107272-9-claudiu.beznea@microchip.... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/at91-sama5d2_icp.dts | 1 - 1 file changed, 1 deletion(-)
diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts index 64d5ae179bec9..492456e195a37 100644 --- a/arch/arm/boot/dts/at91-sama5d2_icp.dts +++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts @@ -258,7 +258,6 @@ regulator-max-microvolt = <1850000>; regulator-initial-mode = <2>; regulator-allowed-modes = <2>, <4>; - regulator-always-on;
regulator-state-standby { regulator-on-in-suspend;
From: Harsh Modi harshmodi@google.com
[ Upstream commit d047283a7034140ea5da759a494fd2274affdd46 ]
The IPv6 path already drops dst in the daddr changed case, but the IPv4 path does not. This change makes the two code paths consistent.
Further, it is possible that there is already a metadata_dst allocated from ingress that might already be attached to skbuff->dst while following the bridge path. If it is not released before setting a new metadata_dst, it will be leaked. This is similar to what is done in bpf_set_tunnel_key() or ip6_route_input().
It is important to note that the memory being leaked is not the dst being set in the bridge code, but rather memory allocated from some other code path that is not being freed correctly before the skb dst is overwritten.
An example of the leakage fixed by this commit found using kmemleak:
unreferenced object 0xffff888010112b00 (size 256): comm "softirq", pid 0, jiffies 4294762496 (age 32.012s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 80 16 f1 83 ff ff ff ff ................ e1 4e f6 82 ff ff ff ff 00 00 00 00 00 00 00 00 .N.............. backtrace: [<00000000d79567ea>] metadata_dst_alloc+0x1b/0xe0 [<00000000be113e13>] udp_tun_rx_dst+0x174/0x1f0 [<00000000a36848f4>] geneve_udp_encap_recv+0x350/0x7b0 [<00000000d4afb476>] udp_queue_rcv_one_skb+0x380/0x560 [<00000000ac064aea>] udp_unicast_rcv_skb+0x75/0x90 [<000000009a8ee8c5>] ip_protocol_deliver_rcu+0xd8/0x230 [<00000000ef4980bb>] ip_local_deliver_finish+0x7a/0xa0 [<00000000d7533c8c>] __netif_receive_skb_one_core+0x89/0xa0 [<00000000a879497d>] process_backlog+0x93/0x190 [<00000000e41ade9f>] __napi_poll+0x28/0x170 [<00000000b4c0906b>] net_rx_action+0x14f/0x2a0 [<00000000b20dd5d4>] __do_softirq+0xf4/0x305 [<000000003a7d7e15>] __irq_exit_rcu+0xc3/0x140 [<00000000968d39a2>] sysvec_apic_timer_interrupt+0x9e/0xc0 [<000000009e920794>] asm_sysvec_apic_timer_interrupt+0x16/0x20 [<000000008942add0>] native_safe_halt+0x13/0x20
Florian Westphal says: "Original code was likely fine because nothing ever did set a skb->dst entry earlier than bridge in those days."
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Harsh Modi harshmodi@google.com Acked-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bridge/br_netfilter_hooks.c | 2 ++ net/bridge/br_netfilter_ipv6.c | 1 + 2 files changed, 3 insertions(+)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index ff47790366497..f20f4373ff408 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -384,6 +384,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ if (rt->dst.dev == dev) { + skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); goto bridged_dnat; } @@ -413,6 +414,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ kfree_skb(skb); return 0; } + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); }
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index e4e0c836c3f51..6b07f30675bb0 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -197,6 +197,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc kfree_skb(skb); return 0; } + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); }
From: Pablo Neira Ayuso pablo@netfilter.org
[ Upstream commit 77972a36ecc4db7fc7c68f0e80714263c5f03f65 ]
splice back the hook list so nft_chain_release_hook() has a chance to release the hooks.
BUG: memory leak unreferenced object 0xffff88810180b100 (size 96): comm "syz-executor133", pid 3619, jiffies 4294945714 (age 12.690s) hex dump (first 32 bytes): 28 64 23 02 81 88 ff ff 28 64 23 02 81 88 ff ff (d#.....(d#..... 90 a8 aa 83 ff ff ff ff 00 00 b5 0f 81 88 ff ff ................ backtrace: [<ffffffff83a8c59b>] kmalloc include/linux/slab.h:600 [inline] [<ffffffff83a8c59b>] nft_netdev_hook_alloc+0x3b/0xc0 net/netfilter/nf_tables_api.c:1901 [<ffffffff83a9239a>] nft_chain_parse_netdev net/netfilter/nf_tables_api.c:1998 [inline] [<ffffffff83a9239a>] nft_chain_parse_hook+0x33a/0x530 net/netfilter/nf_tables_api.c:2073 [<ffffffff83a9b14b>] nf_tables_addchain.constprop.0+0x10b/0x950 net/netfilter/nf_tables_api.c:2218 [<ffffffff83a9c41b>] nf_tables_newchain+0xa8b/0xc60 net/netfilter/nf_tables_api.c:2593 [<ffffffff83a3d6a6>] nfnetlink_rcv_batch+0xa46/0xd20 net/netfilter/nfnetlink.c:517 [<ffffffff83a3db79>] nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:638 [inline] [<ffffffff83a3db79>] nfnetlink_rcv+0x1f9/0x220 net/netfilter/nfnetlink.c:656 [<ffffffff83a13b17>] netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] [<ffffffff83a13b17>] netlink_unicast+0x397/0x4c0 net/netlink/af_netlink.c:1345 [<ffffffff83a13fd6>] netlink_sendmsg+0x396/0x710 net/netlink/af_netlink.c:1921 [<ffffffff83865ab6>] sock_sendmsg_nosec net/socket.c:714 [inline] [<ffffffff83865ab6>] sock_sendmsg+0x56/0x80 net/socket.c:734 [<ffffffff8386601c>] ____sys_sendmsg+0x36c/0x390 net/socket.c:2482 [<ffffffff8386a918>] ___sys_sendmsg+0xa8/0x110 net/socket.c:2536 [<ffffffff8386aaa8>] __sys_sendmsg+0x88/0x100 net/socket.c:2565 [<ffffffff845e5955>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<ffffffff845e5955>] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 [<ffffffff84800087>] entry_SYSCALL_64_after_hwframe+0x63/0xcd
Fixes: d54725cd11a5 ("netfilter: nf_tables: support for multiple devices per netdev hook") Reported-by: syzbot+5fcdbfab6d6744c57418@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index bc690238a3c56..848cc81d69926 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2166,8 +2166,10 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, chain->flags |= NFT_CHAIN_BASE | flags; basechain->policy = NF_ACCEPT; if (chain->flags & NFT_CHAIN_HW_OFFLOAD && - !nft_chain_offload_support(basechain)) + !nft_chain_offload_support(basechain)) { + list_splice_init(&basechain->hook_list, &hook->list); return -EOPNOTSUPP; + }
flow_block_init(&basechain->flow_block);
From: Conor Dooley conor.dooley@microchip.com
[ Upstream commit 0dec364ffeb6149aae572ded1e34d4b444c23be6 ]
PolarFire SoC does not have the same l2 cache controller as the fu540, featuring an extra interrupt. Appease the devicetree checker overlords by adding a PolarFire SoC specific compatible to fix the below sort of warnings:
mpfs-polarberry.dtb: cache-controller@2010000: interrupts: [[1], [3], [4], [2]] is too long
Fixes: 0fa6107eca41 ("RISC-V: Initial DTS for Microchip ICICLE board") Fixes: 34fc9cc3aebe ("riscv: dts: microchip: correct L2 cache interrupts") Reviewed-by: Heinrich Schuchardt heinrich.schuchardt@canonical.com Signed-off-by: Conor Dooley conor.dooley@microchip.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/riscv/boot/dts/microchip/mpfs.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 9f5bce1488d93..9bf37ef379509 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -161,7 +161,7 @@ ranges;
cctrllr: cache-controller@2010000 { - compatible = "sifive,fu540-c000-ccache", "cache"; + compatible = "microchip,mpfs-ccache", "sifive,fu540-c000-ccache", "cache"; reg = <0x0 0x2010000 0x0 0x1000>; cache-block-size = <64>; cache-level = <2>;
From: David Leadbeater dgl@dgl.cx
[ Upstream commit 0efe125cfb99e6773a7434f3463f7c2fa28f3a43 ]
Ensure the match happens in the right direction, previously the destination used was the server, not the NAT host, as the comment shows the code intended.
Additionally nf_nat_irc uses port 0 as a signal and there's no valid way it can appear in a DCC message, so consider port 0 also forged.
Fixes: 869f37d8e48f ("[NETFILTER]: nf_conntrack/nf_nat: add IRC helper port") Signed-off-by: David Leadbeater dgl@dgl.cx Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_conntrack_irc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 1796c456ac98b..992decbcaa5c1 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -194,8 +194,9 @@ static int help(struct sk_buff *skb, unsigned int protoff,
/* dcc_ip can be the internal OR external (NAT'ed) IP */ tuple = &ct->tuplehash[dir].tuple; - if (tuple->src.u3.ip != dcc_ip && - tuple->dst.u3.ip != dcc_ip) { + if ((tuple->src.u3.ip != dcc_ip && + ct->tuplehash[!dir].tuple.dst.u3.ip != dcc_ip) || + dcc_port == 0) { net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n", &tuple->src.u3.ip, &dcc_ip, dcc_port);
From: yangx.jy@fujitsu.com yangx.jy@fujitsu.com
[ Upstream commit 12f35199a2c0551187edbf8eb01379f0598659fa ]
This change fixes the following kernel NULL pointer dereference which is reproduced by blktests srp/007 occasionally.
BUG: kernel NULL pointer dereference, address: 0000000000000170 PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 9 Comm: kworker/0:1H Kdump: loaded Not tainted 6.0.0-rc1+ #37 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-29-g6a62e0cb0dfe-prebuilt.qemu.org 04/01/2014 Workqueue: 0x0 (kblockd) RIP: 0010:srp_recv_done+0x176/0x500 [ib_srp] Code: 00 4d 85 ff 0f 84 52 02 00 00 48 c7 82 80 02 00 00 00 00 00 00 4c 89 df 4c 89 14 24 e8 53 d3 4a f6 4c 8b 14 24 41 0f b6 42 13 <41> 89 87 70 01 00 00 41 0f b6 52 12 f6 c2 02 74 44 41 8b 42 1c b9 RSP: 0018:ffffaef7c0003e28 EFLAGS: 00000282 RAX: 0000000000000000 RBX: ffff9bc9486dea60 RCX: 0000000000000000 RDX: 0000000000000102 RSI: ffffffffb76bbd0e RDI: 00000000ffffffff RBP: ffff9bc980099a00 R08: 0000000000000001 R09: 0000000000000001 R10: ffff9bca53ef0000 R11: ffff9bc980099a10 R12: ffff9bc956e14000 R13: ffff9bc9836b9cb0 R14: ffff9bc9557b4480 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff9bc97ec00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000170 CR3: 0000000007e04000 CR4: 00000000000006f0 Call Trace: <IRQ> __ib_process_cq+0xb7/0x280 [ib_core] ib_poll_handler+0x2b/0x130 [ib_core] irq_poll_softirq+0x93/0x150 __do_softirq+0xee/0x4b8 irq_exit_rcu+0xf7/0x130 sysvec_apic_timer_interrupt+0x8e/0xc0 </IRQ>
Fixes: ad215aaea4f9 ("RDMA/srp: Make struct scsi_cmnd and struct srp_request adjacent") Link: https://lore.kernel.org/r/20220831081626.18712-1-yangx.jy@fujitsu.com Signed-off-by: Xiao Yang yangx.jy@fujitsu.com Acked-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/ulp/srp/ib_srp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 6058abf42ba74..3d9c108d73ad8 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1962,7 +1962,8 @@ static void srp_process_rsp(struct srp_rdma_ch *ch, struct srp_rsp *rsp) if (scmnd) { req = scsi_cmd_priv(scmnd); scmnd = srp_claim_req(ch, req, NULL, scmnd); - } else { + } + if (!scmnd) { shost_printk(KERN_ERR, target->scsi_host, "Null scmnd for RSP w/tag %#016llx received on ch %td / QP %#x\n", rsp->tag, ch - target->ch, ch->qp->qp_num);
From: Takashi Iwai tiwai@suse.de
[ Upstream commit 7e1afce5866e02b45bf88c27dd7de1b9dfade1cc ]
The info message that was added in the commit a4aad5636c72 ("ALSA: usb-audio: Inform devices that need delayed registration") is actually useful to know the need for the delayed registration. However, it turned out that this doesn't catch the all cases; namely, this warned only when a PCM stream is attached onto the existing PCM instance, but it doesn't count for a newly created PCM instance. This made confusion as if there were no further delayed registration.
This patch moves the check to the code path for either adding a stream or creating a PCM instance. Also, make it simpler by checking the card->registered flag instead of querying each snd_device state.
Fixes: a4aad5636c72 ("ALSA: usb-audio: Inform devices that need delayed registration") Link: https://bugzilla.kernel.org/show_bug.cgi?id=216082 Link: https://lore.kernel.org/r/20220831125901.4660-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/usb/stream.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/sound/usb/stream.c b/sound/usb/stream.c index 40ce8a1cb318a..f10f4e6d3fb85 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -495,6 +495,10 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, return 0; } } + + if (chip->card->registered) + chip->need_delayed_register = true; + /* look for an empty stream */ list_for_each_entry(as, &chip->pcm_list, list) { if (as->fmt_type != fp->fmt_type) @@ -502,9 +506,6 @@ static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip, subs = &as->substream[stream]; if (subs->ep_num) continue; - if (snd_device_get_state(chip->card, as->pcm) != - SNDRV_DEV_BUILD) - chip->need_delayed_register = true; err = snd_pcm_new_stream(as->pcm, stream, 1); if (err < 0) return err;
From: Takashi Iwai tiwai@suse.de
[ Upstream commit 2027f114686e0f3f1f39971964dfc618637c88c2 ]
When the delayed registration is specified via either delayed_register option or the quirk, we delay the invocation of snd_card_register() until the given interface. But if a wrong value has been set there and there are more interfaces over the given interface number, snd_card_register() call would be missing for those interfaces.
This patch catches up those missing calls by fixing the comparison of the interface number. Now the call is skipped only if the processed interface is less than the given interface, instead of the exact match.
Fixes: b70038ef4fea ("ALSA: usb-audio: Add delayed_register option") Link: https://bugzilla.kernel.org/show_bug.cgi?id=216082 Link: https://lore.kernel.org/r/20220831125901.4660-2-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/usb/card.c | 2 +- sound/usb/quirks.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/usb/card.c b/sound/usb/card.c index d356743de2ff9..706d249a9ad6b 100644 --- a/sound/usb/card.c +++ b/sound/usb/card.c @@ -699,7 +699,7 @@ static bool check_delayed_register_option(struct snd_usb_audio *chip, int iface) if (delayed_register[i] && sscanf(delayed_register[i], "%x:%x", &id, &inum) == 2 && id == chip->usb_id) - return inum != iface; + return iface < inum; }
return false; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 9bfead5efc4c1..5b4d8f5eade20 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1764,7 +1764,7 @@ bool snd_usb_registration_quirk(struct snd_usb_audio *chip, int iface)
for (q = registration_quirks; q->usb_id; q++) if (chip->usb_id == q->usb_id) - return iface != q->interface; + return iface < q->interface;
/* Register as normal */ return false;
From: David Howells dhowells@redhat.com
[ Upstream commit ac56a0b48da86fd1b4389632fb7c4c8a5d86eefa ]
Because rxrpc pretends to be a tunnel on top of a UDP/UDP6 socket, allowing it to siphon off UDP packets early in the handling of received UDP packets thereby avoiding the packet going through the UDP receive queue, it doesn't get ICMP packets through the UDP ->sk_error_report() callback. In fact, it doesn't appear that there's any usable option for getting hold of ICMP packets.
Fix this by adding a new UDP encap hook to distribute error messages for UDP tunnels. If the hook is set, then the tunnel driver will be able to see ICMP packets. The hook provides the offset into the packet of the UDP header of the original packet that caused the notification.
An alternative would be to call the ->error_handler() hook - but that requires that the skbuff be cloned (as ip_icmp_error() or ipv6_cmp_error() do, though isn't really necessary or desirable in rxrpc's case is we want to parse them there and then, not queue them).
Changes ======= ver #3) - Fixed an uninitialised variable.
ver #2) - Fixed some missing CONFIG_AF_RXRPC_IPV6 conditionals.
Fixes: 5271953cad31 ("rxrpc: Use the UDP encap_rcv hook") Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/udp.h | 1 + include/net/udp_tunnel.h | 4 + net/ipv4/udp.c | 2 + net/ipv4/udp_tunnel_core.c | 1 + net/ipv6/udp.c | 5 +- net/rxrpc/ar-internal.h | 1 + net/rxrpc/local_object.c | 1 + net/rxrpc/peer_event.c | 293 ++++++++++++++++++++++++++++++++----- 8 files changed, 270 insertions(+), 38 deletions(-)
diff --git a/include/linux/udp.h b/include/linux/udp.h index 254a2654400f8..e96da4157d04d 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -70,6 +70,7 @@ struct udp_sock { * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk);
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index afc7ce713657b..72394f441dad8 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -67,6 +67,9 @@ static inline int udp_sock_create(struct net *net, typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); +typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, + struct sk_buff *skb, + unsigned int udp_offset); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, @@ -80,6 +83,7 @@ struct udp_tunnel_sock_cfg { __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; + udp_tunnel_encap_err_rcv_t encap_err_rcv; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index aa9f2ec3dc468..01e1d36bdf135 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -781,6 +781,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) */ if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ + if (udp_sk(sk)->encap_err_rcv) + udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); goto out; } if (!inet->recverr) { diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 8efaf8c3fe2a9..8242c8947340e 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -72,6 +72,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
udp_sk(sk)->encap_type = cfg->encap_type; udp_sk(sk)->encap_rcv = cfg->encap_rcv; + udp_sk(sk)->encap_err_rcv = cfg->encap_err_rcv; udp_sk(sk)->encap_err_lookup = cfg->encap_err_lookup; udp_sk(sk)->encap_destroy = cfg->encap_destroy; udp_sk(sk)->gro_receive = cfg->gro_receive; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e2f2e087a7531..40074bc7274ea 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -616,8 +616,11 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, }
/* Tunnels don't have an application socket: don't pass errors back */ - if (tunnel) + if (tunnel) { + if (udp_sk(sk)->encap_err_rcv) + udp_sk(sk)->encap_err_rcv(sk, skb, offset); goto out; + }
if (!np->recverr) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 571436064cd6f..62c70709d7980 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -982,6 +982,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *); /* * peer_event.c */ +void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); void rxrpc_error_report(struct sock *); void rxrpc_peer_keepalive_worker(struct work_struct *);
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 96ecb7356c0fe..79bb02eb67b2b 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -137,6 +137,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
tuncfg.encap_type = UDP_ENCAP_RXRPC; tuncfg.encap_rcv = rxrpc_input_packet; + tuncfg.encap_err_rcv = rxrpc_encap_err_rcv; tuncfg.sk_user_data = local; setup_udp_tunnel_sock(net, local->socket, &tuncfg);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index be032850ae8ca..32561e9567fe3 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -16,22 +16,105 @@ #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> +#include <net/icmp.h> #include "ar-internal.h"
+static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int); static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); static void rxrpc_distribute_error(struct rxrpc_peer *, int, enum rxrpc_call_completion);
/* - * Find the peer associated with an ICMP packet. + * Find the peer associated with an ICMPv4 packet. */ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, - const struct sk_buff *skb, + struct sk_buff *skb, + unsigned int udp_offset, + unsigned int *info, struct sockaddr_rxrpc *srx) { - struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + struct iphdr *ip, *ip0 = ip_hdr(skb); + struct icmphdr *icmp = icmp_hdr(skb); + struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset);
- _enter(""); + _enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code); + + switch (icmp->type) { + case ICMP_DEST_UNREACH: + *info = ntohs(icmp->un.frag.mtu); + fallthrough; + case ICMP_TIME_EXCEEDED: + case ICMP_PARAMETERPROB: + ip = (struct iphdr *)((void *)icmp + 8); + break; + default: + return NULL; + } + + memset(srx, 0, sizeof(*srx)); + srx->transport_type = local->srx.transport_type; + srx->transport_len = local->srx.transport_len; + srx->transport.family = local->srx.transport.family; + + /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice + * versa? + */ + switch (srx->transport.family) { + case AF_INET: + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.family = AF_INET; + srx->transport.sin.sin_port = udp->dest; + memcpy(&srx->transport.sin.sin_addr, &ip->daddr, + sizeof(struct in_addr)); + break; + +#ifdef CONFIG_AF_RXRPC_IPV6 + case AF_INET6: + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.family = AF_INET; + srx->transport.sin.sin_port = udp->dest; + memcpy(&srx->transport.sin.sin_addr, &ip->daddr, + sizeof(struct in_addr)); + break; +#endif + + default: + WARN_ON_ONCE(1); + return NULL; + } + + _net("ICMP {%pISp}", &srx->transport); + return rxrpc_lookup_peer_rcu(local, srx); +} + +#ifdef CONFIG_AF_RXRPC_IPV6 +/* + * Find the peer associated with an ICMPv6 packet. + */ +static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local, + struct sk_buff *skb, + unsigned int udp_offset, + unsigned int *info, + struct sockaddr_rxrpc *srx) +{ + struct icmp6hdr *icmp = icmp6_hdr(skb); + struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb); + struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset); + + _enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code); + + switch (icmp->icmp6_type) { + case ICMPV6_DEST_UNREACH: + *info = ntohl(icmp->icmp6_mtu); + fallthrough; + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + case ICMPV6_PARAMPROB: + ip = (struct ipv6hdr *)((void *)icmp + 8); + break; + default: + return NULL; + }
memset(srx, 0, sizeof(*srx)); srx->transport_type = local->srx.transport_type; @@ -41,6 +124,165 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice * versa? */ + switch (srx->transport.family) { + case AF_INET: + _net("Rx ICMP6 on v4 sock"); + srx->transport_len = sizeof(srx->transport.sin); + srx->transport.family = AF_INET; + srx->transport.sin.sin_port = udp->dest; + memcpy(&srx->transport.sin.sin_addr, + &ip->daddr.s6_addr32[3], sizeof(struct in_addr)); + break; + case AF_INET6: + _net("Rx ICMP6"); + srx->transport.sin.sin_port = udp->dest; + memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr, + sizeof(struct in6_addr)); + break; + default: + WARN_ON_ONCE(1); + return NULL; + } + + _net("ICMP {%pISp}", &srx->transport); + return rxrpc_lookup_peer_rcu(local, srx); +} +#endif /* CONFIG_AF_RXRPC_IPV6 */ + +/* + * Handle an error received on the local endpoint as a tunnel. + */ +void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, + unsigned int udp_offset) +{ + struct sock_extended_err ee; + struct sockaddr_rxrpc srx; + struct rxrpc_local *local; + struct rxrpc_peer *peer; + unsigned int info = 0; + int err; + u8 version = ip_hdr(skb)->version; + u8 type = icmp_hdr(skb)->type; + u8 code = icmp_hdr(skb)->code; + + rcu_read_lock(); + local = rcu_dereference_sk_user_data(sk); + if (unlikely(!local)) { + rcu_read_unlock(); + return; + } + + rxrpc_new_skb(skb, rxrpc_skb_received); + + switch (ip_hdr(skb)->version) { + case IPVERSION: + peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset, + &info, &srx); + break; +#ifdef CONFIG_AF_RXRPC_IPV6 + case 6: + peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset, + &info, &srx); + break; +#endif + default: + rcu_read_unlock(); + return; + } + + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) { + rcu_read_unlock(); + return; + } + + memset(&ee, 0, sizeof(ee)); + + switch (version) { + case IPVERSION: + switch (type) { + case ICMP_DEST_UNREACH: + switch (code) { + case ICMP_FRAG_NEEDED: + rxrpc_adjust_mtu(peer, info); + rcu_read_unlock(); + rxrpc_put_peer(peer); + return; + default: + break; + } + + err = EHOSTUNREACH; + if (code <= NR_ICMP_UNREACH) { + /* Might want to do something different with + * non-fatal errors + */ + //harderr = icmp_err_convert[code].fatal; + err = icmp_err_convert[code].errno; + } + break; + + case ICMP_TIME_EXCEEDED: + err = EHOSTUNREACH; + break; + default: + err = EPROTO; + break; + } + + ee.ee_origin = SO_EE_ORIGIN_ICMP; + ee.ee_type = type; + ee.ee_code = code; + ee.ee_errno = err; + break; + +#ifdef CONFIG_AF_RXRPC_IPV6 + case 6: + switch (type) { + case ICMPV6_PKT_TOOBIG: + rxrpc_adjust_mtu(peer, info); + rcu_read_unlock(); + rxrpc_put_peer(peer); + return; + } + + icmpv6_err_convert(type, code, &err); + + if (err == EACCES) + err = EHOSTUNREACH; + + ee.ee_origin = SO_EE_ORIGIN_ICMP6; + ee.ee_type = type; + ee.ee_code = code; + ee.ee_errno = err; + break; +#endif + } + + trace_rxrpc_rx_icmp(peer, &ee, &srx); + + rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR); + rcu_read_unlock(); + rxrpc_put_peer(peer); +} + +/* + * Find the peer associated with a local error. + */ +static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local, + const struct sk_buff *skb, + struct sockaddr_rxrpc *srx) +{ + struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + + _enter(""); + + memset(srx, 0, sizeof(*srx)); + srx->transport_type = local->srx.transport_type; + srx->transport_len = local->srx.transport_len; + srx->transport.family = local->srx.transport.family; + switch (srx->transport.family) { case AF_INET: srx->transport_len = sizeof(srx->transport.sin); @@ -104,10 +346,8 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, /* * Handle an MTU/fragmentation problem. */ -static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr) +static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu) { - u32 mtu = serr->ee.ee_info; - _net("Rx ICMP Fragmentation Needed (%d)", mtu);
/* wind down the local interface MTU */ @@ -148,7 +388,7 @@ void rxrpc_error_report(struct sock *sk) struct sock_exterr_skb *serr; struct sockaddr_rxrpc srx; struct rxrpc_local *local; - struct rxrpc_peer *peer; + struct rxrpc_peer *peer = NULL; struct sk_buff *skb;
rcu_read_lock(); @@ -172,41 +412,20 @@ void rxrpc_error_report(struct sock *sk) } rxrpc_new_skb(skb, rxrpc_skb_received); serr = SKB_EXT_ERR(skb); - if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { - _leave("UDP empty message"); - rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); - return; - }
- peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx); - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (!peer) { - rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" [no peer]"); - return; - } - - trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); - - if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && - serr->ee.ee_type == ICMP_DEST_UNREACH && - serr->ee.ee_code == ICMP_FRAG_NEEDED)) { - rxrpc_adjust_mtu(peer, serr); - rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); - rxrpc_put_peer(peer); - _leave(" [MTU update]"); - return; + if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) { + peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx); + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (peer) { + trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); + rxrpc_store_error(peer, serr); + } }
- rxrpc_store_error(peer, serr); rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_freed); rxrpc_put_peer(peer); - _leave(""); }
From: David Howells dhowells@redhat.com
[ Upstream commit 0d40f728e28393a8817d1fcae923dfa3409e488c ]
rxkad_verify_packet_2() has a small stack-allocated sglist of 4 elements, but if that isn't sufficient for the number of fragments in the socket buffer, we try to allocate an sglist large enough to hold all the fragments.
However, for large packets with a lot of fragments, this isn't sufficient and we need at least one additional fragment.
The problem manifests as skb_to_sgvec() returning -EMSGSIZE and this then getting returned by userspace. Most of the time, this isn't a problem as rxrpc sets a limit of 5692, big enough for 4 jumbo subpackets to be glued together; occasionally, however, the server will ignore the reported limit and give a packet that's a lot bigger - say 19852 bytes with ->nr_frags being 7. skb_to_sgvec() then tries to return a "zeroth" fragment that seems to occur before the fragments counted by ->nr_frags and we hit the end of the sglist too early.
Note that __skb_to_sgvec() also has an skb_walk_frags() loop that is recursive up to 24 deep. I'm not sure if I need to take account of that too - or if there's an easy way of counting those frags too.
Fix this by counting an extra frag and allocating a larger sglist based on that.
Fixes: d0d5c0cd1e71 ("rxrpc: Use skb_unshare() rather than skb_cow_data()") Reported-by: Marc Dionne marc.dionne@auristor.com Signed-off-by: David Howells dhowells@redhat.com cc: linux-afs@lists.infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/rxkad.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 08aab5c01437d..db47844f4ac99 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -540,7 +540,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, * directly into the target buffer. */ sg = _sg; - nsg = skb_shinfo(skb)->nr_frags; + nsg = skb_shinfo(skb)->nr_frags + 1; if (nsg <= 4) { nsg = 4; } else {
From: David Howells dhowells@redhat.com
[ Upstream commit 7903192c4b4a82d792cb0dc5e2779a2efe60d45b ]
rxrpc and kafs between them try to use the receive timestamp on the first data packet (ie. the one with sequence number 1) as a base from which to calculate the time at which callback promise and lock expiration occurs.
However, we don't know how long it took for the server to send us the reply from it having completed the basic part of the operation - it might then, for instance, have to send a bunch of a callback breaks, depending on the particular operation.
Fix this by using the time at which the operation is issued on the client as a base instead. That should never be longer than the server's idea of the expiry time.
Fixes: 781070551c26 ("afs: Fix calculation of callback expiry time") Fixes: 2070a3e44962 ("rxrpc: Allow the reply time to be obtained on a client call") Suggested-by: Jeffrey E Altman jaltman@auristor.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/flock.c | 2 +- fs/afs/fsclient.c | 2 +- fs/afs/internal.h | 3 +-- fs/afs/rxrpc.c | 7 +------ fs/afs/yfsclient.c | 3 +-- 5 files changed, 5 insertions(+), 12 deletions(-)
diff --git a/fs/afs/flock.c b/fs/afs/flock.c index c4210a3964d8b..bbcc5afd15760 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call) if (call->error == 0) { spin_lock(&vnode->lock); trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0); - vnode->locked_at = call->reply_time; + vnode->locked_at = call->issue_time; afs_schedule_lock_extension(vnode); spin_unlock(&vnode->lock); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 4943413d9c5f7..7d37f63ef0f09 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -131,7 +131,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry) { - return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry; + return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry; }
static void xdr_decode_AFSCallBack(const __be32 **_bp, diff --git a/fs/afs/internal.h b/fs/afs/internal.h index a6f25d9e75b52..28bdd0387e5ea 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -137,7 +137,6 @@ struct afs_call { bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ bool upgrade; /* T to request service upgrade */ - bool have_reply_time; /* T if have got reply_time */ bool intr; /* T if interruptible */ bool unmarshalling_error; /* T if an unmarshalling error occurred */ u16 service_id; /* Actual service ID (after upgrade) */ @@ -151,7 +150,7 @@ struct afs_call { } __attribute__((packed)); __be64 tmp64; }; - ktime_t reply_time; /* Time of first reply packet */ + ktime_t issue_time; /* Time of issue of operation */ };
struct afs_call_type { diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a5434f3e57c68..e3de7fea36435 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -347,6 +347,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) if (call->max_lifespan) rxrpc_kernel_set_max_life(call->net->socket, rxcall, call->max_lifespan); + call->issue_time = ktime_get_real();
/* send the request */ iov[0].iov_base = call->request; @@ -497,12 +498,6 @@ static void afs_deliver_to_call(struct afs_call *call) return; }
- if (!call->have_reply_time && - rxrpc_kernel_get_reply_time(call->net->socket, - call->rxcall, - &call->reply_time)) - call->have_reply_time = true; - ret = call->type->deliver(call); state = READ_ONCE(call->state); if (ret == 0 && call->unmarshalling_error) diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index fdc7d675b4b0c..11571cca86c19 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -232,8 +232,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp, struct afs_callback *cb = &scb->callback; ktime_t cb_expiry;
- cb_expiry = call->reply_time; - cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100); + cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100); cb->expires_at = ktime_divns(cb_expiry, NSEC_PER_SEC); scb->have_cb = true; *_bp += xdr_size(x);
From: Sander Vanheule sander@svanheule.net
[ Upstream commit aded3cad909581c60335037112c4f86bbfe90f17 ]
When replacing KUNIT_BINARY_*_MSG_ASSERTION() macros with KUNIT_BINARY_INT_ASSERTION(), the assert_type parameter was not always correctly transferred. Specifically, the following errors were introduced: - KUNIT_EXPECT_LE_MSG() uses KUNIT_ASSERTION - KUNIT_ASSERT_LT_MSG() uses KUNIT_EXPECTATION - KUNIT_ASSERT_GT_MSG() uses KUNIT_EXPECTATION
A failing KUNIT_EXPECT_LE_MSG() test thus prevents further tests from running, while failing KUNIT_ASSERT_{LT,GT}_MSG() tests do not prevent further tests from running. This is contrary to the documentation, which states that failing KUNIT_EXPECT_* macros allow further tests to run, while failing KUNIT_ASSERT_* macros should prevent this.
Revert the KUNIT_{ASSERTION,EXPECTATION} switches to fix the behaviour for the affected macros.
Fixes: 40f39777ce4f ("kunit: decrease macro layering for integer asserts") Signed-off-by: Sander Vanheule sander@svanheule.net Reviewed-by: Daniel Latypov dlatypov@google.com Reviewed-by: Brendan Higgins brendanhiggins@google.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/kunit/test.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/include/kunit/test.h b/include/kunit/test.h index 8ffcd7de96070..648dbb00a3008 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -863,7 +863,7 @@ do { \
#define KUNIT_EXPECT_LE_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_INT_ASSERTION(test, \ - KUNIT_ASSERTION, \ + KUNIT_EXPECTATION, \ left, <=, right, \ fmt, \ ##__VA_ARGS__) @@ -1153,7 +1153,7 @@ do { \
#define KUNIT_ASSERT_LT_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_INT_ASSERTION(test, \ - KUNIT_EXPECTATION, \ + KUNIT_ASSERTION, \ left, <, right, \ fmt, \ ##__VA_ARGS__) @@ -1194,7 +1194,7 @@ do { \
#define KUNIT_ASSERT_GT_MSG(test, left, right, fmt, ...) \ KUNIT_BINARY_INT_ASSERTION(test, \ - KUNIT_EXPECTATION, \ + KUNIT_ASSERTION, \ left, >, right, \ fmt, \ ##__VA_ARGS__)
From: Heiner Kallweit hkallweit1@gmail.com
[ Upstream commit 7fdc77665f3d45c9da7c6edd4beadee9790f43aa ]
This reverts commit 2c87c6f9fbddc5b84d67b2fa3f432fcac6d99d93. Meanwhile it turned out that the following commit is the proper workaround for the issue that 2c87c6f9fbdd tries to address. a3a57bf07de2 ("net: stmmac: work around sporadic tx issue on link-up") It's nor clear why the to be reverted commit helped for one user, for others it didn't make a difference.
Fixes: 2c87c6f9fbdd ("net: phy: meson-gxl: improve link-up behavior") Signed-off-by: Heiner Kallweit hkallweit1@gmail.com Link: https://lore.kernel.org/r/8deeeddc-6b71-129b-1918-495a12dc11e3@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/meson-gxl.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)
diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index 73f7962a37d33..c49062ad72c6c 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -243,13 +243,7 @@ static irqreturn_t meson_gxl_handle_interrupt(struct phy_device *phydev) irq_status == INTSRC_ENERGY_DETECT) return IRQ_HANDLED;
- /* Give PHY some time before MAC starts sending data. This works - * around an issue where network doesn't come up properly. - */ - if (!(irq_status & INTSRC_LINK_DOWN)) - phy_queue_state_machine(phydev, msecs_to_jiffies(100)); - else - phy_trigger_machine(phydev); + phy_trigger_machine(phydev);
return IRQ_HANDLED; }
From: Toke Høiland-Jørgensen toke@toke.dk
[ Upstream commit 9efd23297cca530bb35e1848665805d3fcdd7889 ]
The sch_sfb enqueue() routine assumes the skb is still alive after it has been enqueued into a child qdisc, using the data in the skb cb field in the increment_qlen() routine after enqueue. However, the skb may in fact have been freed, causing a use-after-free in this case. In particular, this happens if sch_cake is used as a child of sfb, and the GSO splitting mode of CAKE is enabled (in which case the skb will be split into segments and the original skb freed).
Fix this by copying the sfb cb data to the stack before enqueueing the skb, and using this stack copy in increment_qlen() instead of the skb pointer itself.
Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-18231 Fixes: e13e02a3c68d ("net_sched: SFB flow scheduler") Signed-off-by: Toke Høiland-Jørgensen toke@toke.dk Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_sfb.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 3d061a13d7ed2..0d761f454ae8b 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -135,15 +135,15 @@ static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) } }
-static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) +static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q) { u32 sfbhash;
- sfbhash = sfb_hash(skb, 0); + sfbhash = cb->hashes[0]; if (sfbhash) increment_one_qlen(sfbhash, 0, q);
- sfbhash = sfb_hash(skb, 1); + sfbhash = cb->hashes[1]; if (sfbhash) increment_one_qlen(sfbhash, 1, q); } @@ -283,6 +283,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sfb_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; struct tcf_proto *fl; + struct sfb_skb_cb cb; int i; u32 p_min = ~0; u32 minqlen = ~0; @@ -399,11 +400,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, }
enqueue: + memcpy(&cb, sfb_skb_cb(skb), sizeof(cb)); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; - increment_qlen(skb, q); + increment_qlen(&cb, q); } else if (net_xmit_drop_count(ret)) { q->stats.childdrop++; qdisc_qstats_drop(sch);
From: Dan Carpenter dan.carpenter@oracle.com
[ Upstream commit e2b224abd9bf45dcb55750479fc35970725a430b ]
There is a shift wrapping bug in this code so anything thing above 31 will return false.
Fixes: 35c55c9877f8 ("tipc: add neighbor monitoring framework") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/tipc/monitor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 2f4d23238a7e3..9618e4429f0fe 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -160,7 +160,7 @@ static void map_set(u64 *up_map, int i, unsigned int v)
static int map_get(u64 up_map, int i) { - return (up_map & (1 << i)) >> i; + return (up_map & (1ULL << i)) >> i; }
static struct tipc_peer *peer_prev(struct tipc_peer *peer)
From: Pavel Begunkov asml.silence@gmail.com
[ Upstream commit 84ce071e38a6e25ea3ea91188e5482ac1f17b3af ]
Managed pages contain pinned userspace pages and controlled by upper layers, there is no need in tracking skb->pfmemalloc for them. Introduce a helper for filling frags but ignoring page tracking, it'll be needed later.
Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skbuff.h | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2f41364a6791e..b0a1374043f30 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2528,6 +2528,22 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) return skb_headlen(skb) + __skb_pagelen(skb); }
+static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, + int i, struct page *page, + int off, int size) +{ + skb_frag_t *frag = &shinfo->frags[i]; + + /* + * Propagate page pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page but rely + * on page_is_pfmemalloc doing the right thing(tm). + */ + frag->bv_page = page; + frag->bv_offset = off; + skb_frag_size_set(frag, size); +} + /** * __skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised @@ -2544,17 +2560,7 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb) static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - /* - * Propagate page pfmemalloc to the skb if we can. The problem is - * that not all callers have unique ownership of the page but rely - * on page_is_pfmemalloc doing the right thing(tm). - */ - frag->bv_page = page; - frag->bv_offset = off; - skb_frag_size_set(frag, size); - + __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true;
From: Eric Dumazet edumazet@google.com
[ Upstream commit 3261400639463a853ba2b3be8bd009c2a8089775 ]
We got a recent syzbot report [1] showing a possible misuse of pfmemalloc page status in TCP zerocopy paths.
Indeed, for pages coming from user space or other layers, using page_is_pfmemalloc() is moot, and possibly could give false positives.
There has been attempts to make page_is_pfmemalloc() more robust, but not using it in the first place in this context is probably better, removing cpu cycles.
Note to stable teams :
You need to backport 84ce071e38a6 ("net: introduce __skb_fill_page_desc_noacc") as a prereq.
Race is more probable after commit c07aea3ef4d4 ("mm: add a signature in struct page") because page_is_pfmemalloc() is now using low order bit from page->lru.next, which can change more often than page->index.
Low order bit should never be set for lru.next (when used as an anchor in LRU list), so KCSAN report is mostly a false positive.
Backporting to older kernel versions seems not necessary.
[1] BUG: KCSAN: data-race in lru_add_fn / tcp_build_frag
write to 0xffffea0004a1d2c8 of 8 bytes by task 18600 on cpu 0: __list_add include/linux/list.h:73 [inline] list_add include/linux/list.h:88 [inline] lruvec_add_folio include/linux/mm_inline.h:105 [inline] lru_add_fn+0x440/0x520 mm/swap.c:228 folio_batch_move_lru+0x1e1/0x2a0 mm/swap.c:246 folio_batch_add_and_move mm/swap.c:263 [inline] folio_add_lru+0xf1/0x140 mm/swap.c:490 filemap_add_folio+0xf8/0x150 mm/filemap.c:948 __filemap_get_folio+0x510/0x6d0 mm/filemap.c:1981 pagecache_get_page+0x26/0x190 mm/folio-compat.c:104 grab_cache_page_write_begin+0x2a/0x30 mm/folio-compat.c:116 ext4_da_write_begin+0x2dd/0x5f0 fs/ext4/inode.c:2988 generic_perform_write+0x1d4/0x3f0 mm/filemap.c:3738 ext4_buffered_write_iter+0x235/0x3e0 fs/ext4/file.c:270 ext4_file_write_iter+0x2e3/0x1210 call_write_iter include/linux/fs.h:2187 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x468/0x760 fs/read_write.c:578 ksys_write+0xe8/0x1a0 fs/read_write.c:631 __do_sys_write fs/read_write.c:643 [inline] __se_sys_write fs/read_write.c:640 [inline] __x64_sys_write+0x3e/0x50 fs/read_write.c:640 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd
read to 0xffffea0004a1d2c8 of 8 bytes by task 18611 on cpu 1: page_is_pfmemalloc include/linux/mm.h:1740 [inline] __skb_fill_page_desc include/linux/skbuff.h:2422 [inline] skb_fill_page_desc include/linux/skbuff.h:2443 [inline] tcp_build_frag+0x613/0xb20 net/ipv4/tcp.c:1018 do_tcp_sendpages+0x3e8/0xaf0 net/ipv4/tcp.c:1075 tcp_sendpage_locked net/ipv4/tcp.c:1140 [inline] tcp_sendpage+0x89/0xb0 net/ipv4/tcp.c:1150 inet_sendpage+0x7f/0xc0 net/ipv4/af_inet.c:833 kernel_sendpage+0x184/0x300 net/socket.c:3561 sock_sendpage+0x5a/0x70 net/socket.c:1054 pipe_to_sendpage+0x128/0x160 fs/splice.c:361 splice_from_pipe_feed fs/splice.c:415 [inline] __splice_from_pipe+0x222/0x4d0 fs/splice.c:559 splice_from_pipe fs/splice.c:594 [inline] generic_splice_sendpage+0x89/0xc0 fs/splice.c:743 do_splice_from fs/splice.c:764 [inline] direct_splice_actor+0x80/0xa0 fs/splice.c:931 splice_direct_to_actor+0x305/0x620 fs/splice.c:886 do_splice_direct+0xfb/0x180 fs/splice.c:974 do_sendfile+0x3bf/0x910 fs/read_write.c:1249 __do_sys_sendfile64 fs/read_write.c:1317 [inline] __se_sys_sendfile64 fs/read_write.c:1303 [inline] __x64_sys_sendfile64+0x10c/0x150 fs/read_write.c:1303 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd
value changed: 0x0000000000000000 -> 0xffffea0004a1d288
Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 18611 Comm: syz-executor.4 Not tainted 6.0.0-rc2-syzkaller-00248-ge022620b5d05-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/22/2022
Fixes: c07aea3ef4d4 ("mm: add a signature in struct page") Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Eric Dumazet edumazet@google.com Cc: Shakeel Butt shakeelb@google.com Reviewed-by: Shakeel Butt shakeelb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skbuff.h | 21 +++++++++++++++++++++ net/core/datagram.c | 2 +- net/ipv4/tcp.c | 2 +- 3 files changed, 23 insertions(+), 2 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b0a1374043f30..63d0a21b63162 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2587,6 +2587,27 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, skb_shinfo(skb)->nr_frags = i + 1; }
+/** + * skb_fill_page_desc_noacc - initialise a paged fragment in an skb + * @skb: buffer containing fragment to be initialised + * @i: paged fragment index to initialise + * @page: the page to use for this fragment + * @off: the offset to the data with @page + * @size: the length of the data + * + * Variant of skb_fill_page_desc() which does not deal with + * pfmemalloc, if page is not owned by us. + */ +static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, + struct page *page, int off, + int size) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + __skb_fill_page_desc_noacc(shinfo, i, page, off, size); + shinfo->nr_frags = i + 1; +} + void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize);
diff --git a/net/core/datagram.c b/net/core/datagram.c index 50f4faeea76cc..48e82438acb02 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -675,7 +675,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, page_ref_sub(last_head, refs); refs = 0; } - skb_fill_page_desc(skb, frag++, head, start, size); + skb_fill_page_desc_noacc(skb, frag++, head, start, size); } if (refs) page_ref_sub(last_head, refs); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3d446773ff2a5..ab03977b65781 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1015,7 +1015,7 @@ static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(page); - skb_fill_page_desc(skb, i, page, offset, copy); + skb_fill_page_desc_noacc(skb, i, page, offset, copy); }
if (!(flags & MSG_NO_SHARED_FRAGS))
From: Przemyslaw Patynowski przemyslawx.patynowski@intel.com
[ Upstream commit 7e753eb675f0523207b184558638ee2eed6c9ac2 ]
Fix leak, when user changes ring parameters. During reallocation of RX buffers, new DMA mappings are created for those buffers. New buffers with different RX ring count should substitute older ones, but those buffers were freed in ice_vsi_cfg_rxq and reallocated again with ice_alloc_rx_buf. kfree on rx_buf caused leak of already mapped DMA. Reallocate ZC with xdp_buf struct, when BPF program loads. Reallocate back to rx_buf, when BPF program unloads. If BPF program is loaded/unloaded and XSK pools are created, reallocate RX queues accordingly in XDP_SETUP_XSK_POOL handler.
Steps for reproduction: while : do for ((i=0; i<=8160; i=i+32)) do ethtool -G enp130s0f0 rx $i tx $i sleep 0.5 ethtool -g enp130s0f0 done done
Fixes: 617f3e1b588c ("ice: xsk: allocate separate memory for XDP SW ring") Signed-off-by: Przemyslaw Patynowski przemyslawx.patynowski@intel.com Signed-off-by: Mateusz Palczewski mateusz.palczewski@intel.com Tested-by: Chandan chandanx.rout@intel.com (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_base.c | 17 ------ drivers/net/ethernet/intel/ice/ice_main.c | 8 +++ drivers/net/ethernet/intel/ice/ice_xsk.c | 63 +++++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_xsk.h | 8 +++ 4 files changed, 79 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 136d7911adb48..1e32438081780 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -7,18 +7,6 @@ #include "ice_dcb_lib.h" #include "ice_sriov.h"
-static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring) -{ - rx_ring->xdp_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->xdp_buf), GFP_KERNEL); - return !!rx_ring->xdp_buf; -} - -static bool ice_alloc_rx_buf(struct ice_rx_ring *rx_ring) -{ - rx_ring->rx_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL); - return !!rx_ring->rx_buf; -} - /** * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI * @qs_cfg: gathered variables needed for PF->VSI queues assignment @@ -519,11 +507,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id);
- kfree(ring->rx_buf); ring->xsk_pool = ice_xsk_pool(ring); if (ring->xsk_pool) { - if (!ice_alloc_rx_buf_zc(ring)) - return -ENOMEM; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
ring->rx_buf_len = @@ -538,8 +523,6 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { - if (!ice_alloc_rx_buf(ring)) - return -ENOMEM; if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) /* coverity[check_return] */ xdp_rxq_info_reg(&ring->xdp_rxq, diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 3d45e075204e3..abc5d2b91f32b 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2898,10 +2898,18 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); } + /* reallocate Rx queues that are used for zero-copy */ + xdp_ring_err = ice_realloc_zc_buf(vsi, true); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_ring_err = ice_destroy_xdp_rings(vsi); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); + /* reallocate Rx queues that were used for zero-copy */ + xdp_ring_err = ice_realloc_zc_buf(vsi, false); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed"); } else { /* safe to call even when prog == vsi->xdp_prog as * dev_xdp_install in net/core/dev.c incremented prog's diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index e48e29258450f..03ce85f6e6df8 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -192,6 +192,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; + ice_clean_rx_ring(rx_ring);
ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); @@ -316,6 +317,62 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) return 0; }
+/** + * ice_realloc_rx_xdp_bufs - reallocate for either XSK or normal buffer + * @rx_ring: Rx ring + * @pool_present: is pool for XSK present + * + * Try allocating memory and return ENOMEM, if failed to allocate. + * If allocation was successful, substitute buffer with allocated one. + * Returns 0 on success, negative on failure + */ +static int +ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present) +{ + size_t elem_size = pool_present ? sizeof(*rx_ring->xdp_buf) : + sizeof(*rx_ring->rx_buf); + void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); + + if (!sw_ring) + return -ENOMEM; + + if (pool_present) { + kfree(rx_ring->rx_buf); + rx_ring->rx_buf = NULL; + rx_ring->xdp_buf = sw_ring; + } else { + kfree(rx_ring->xdp_buf); + rx_ring->xdp_buf = NULL; + rx_ring->rx_buf = sw_ring; + } + + return 0; +} + +/** + * ice_realloc_zc_buf - reallocate XDP ZC queue pairs + * @vsi: Current VSI + * @zc: is zero copy set + * + * Reallocate buffer for rx_rings that might be used by XSK. + * XDP requires more memory, than rx_buf provides. + * Returns 0 on success, negative on failure + */ +int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) +{ + struct ice_rx_ring *rx_ring; + unsigned long q; + + for_each_set_bit(q, vsi->af_xdp_zc_qps, + max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) { + rx_ring = vsi->rx_rings[q]; + if (ice_realloc_rx_xdp_bufs(rx_ring, zc)) + return -ENOMEM; + } + + return 0; +} + /** * ice_xsk_pool_setup - enable/disable a buffer pool region depending on its state * @vsi: Current VSI @@ -345,11 +402,17 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
if (if_running) { + struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; + ret = ice_qp_dis(vsi, qid); if (ret) { netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret); goto xsk_pool_if_up; } + + ret = ice_realloc_rx_xdp_bufs(rx_ring, pool_present); + if (ret) + goto xsk_pool_if_up; }
pool_failure = pool_present ? ice_xsk_pool_enable(vsi, pool, qid) : diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 21faec8e97db1..4edbe81eb6460 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -27,6 +27,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, u32 budget, int napi_budget); +int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); #else static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring, @@ -72,5 +73,12 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev,
static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { } static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { } + +static inline int +ice_realloc_zc_buf(struct ice_vsi __always_unused *vsi, + bool __always_unused zc) +{ + return 0; +} #endif /* CONFIG_XDP_SOCKETS */ #endif /* !_ICE_XSK_H_ */
From: Michal Swiatkowski michal.swiatkowski@linux.intel.com
[ Upstream commit 59ac325557b6c14f1f793b90d3946bc145ffa085 ]
pf->avail_txqs was allocated using bitmap_zalloc, bitmap_free should be used to free this memory.
Fixes: 78b5713ac1241 ("ice: Alloc queue management bitmaps and arrays dynamically") Signed-off-by: Michal Swiatkowski michal.swiatkowski@linux.intel.com Tested-by: Gurucharan gurucharanx.g@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index abc5d2b91f32b..4c6bb7482b362 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3912,7 +3912,7 @@ static int ice_init_pf(struct ice_pf *pf)
pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); if (!pf->avail_rxqs) { - devm_kfree(ice_pf_to_dev(pf), pf->avail_txqs); + bitmap_free(pf->avail_txqs); pf->avail_txqs = NULL; return -ENOMEM; }
From: Ivan Vecera ivecera@redhat.com
[ Upstream commit fb8396aeda5872369a8ed6d2301e2c86e303c520 ]
The driver incorrectly frees client instance and subsequent i40e module removal leads to kernel crash.
Reproducer: 1. Do ethtool offline test followed immediately by another one host# ethtool -t eth0 offline; ethtool -t eth0 offline 2. Remove recursively irdma module that also removes i40e module host# modprobe -r irdma
Result: [ 8675.035651] i40e 0000:3d:00.0 eno1: offline testing starting [ 8675.193774] i40e 0000:3d:00.0 eno1: testing finished [ 8675.201316] i40e 0000:3d:00.0 eno1: offline testing starting [ 8675.358921] i40e 0000:3d:00.0 eno1: testing finished [ 8675.496921] i40e 0000:3d:00.0: IRDMA hardware initialization FAILED init_state=2 status=-110 [ 8686.188955] i40e 0000:3d:00.1: i40e_ptp_stop: removed PHC on eno2 [ 8686.943890] i40e 0000:3d:00.1: Deleted LAN device PF1 bus=0x3d dev=0x00 func=0x01 [ 8686.952669] i40e 0000:3d:00.0: i40e_ptp_stop: removed PHC on eno1 [ 8687.761787] BUG: kernel NULL pointer dereference, address: 0000000000000030 [ 8687.768755] #PF: supervisor read access in kernel mode [ 8687.773895] #PF: error_code(0x0000) - not-present page [ 8687.779034] PGD 0 P4D 0 [ 8687.781575] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 8687.785935] CPU: 51 PID: 172891 Comm: rmmod Kdump: loaded Tainted: G W I 5.19.0+ #2 [ 8687.794800] Hardware name: Intel Corporation S2600WFD/S2600WFD, BIOS SE5C620.86B.0X.02.0001.051420190324 05/14/2019 [ 8687.805222] RIP: 0010:i40e_lan_del_device+0x13/0xb0 [i40e] [ 8687.810719] Code: d4 84 c0 0f 84 b8 25 01 00 e9 9c 25 01 00 41 bc f4 ff ff ff eb 91 90 0f 1f 44 00 00 41 54 55 53 48 8b 87 58 08 00 00 48 89 fb <48> 8b 68 30 48 89 ef e8 21 8a 0f d5 48 89 ef e8 a9 78 0f d5 48 8b [ 8687.829462] RSP: 0018:ffffa604072efce0 EFLAGS: 00010202 [ 8687.834689] RAX: 0000000000000000 RBX: ffff8f43833b2000 RCX: 0000000000000000 [ 8687.841821] RDX: 0000000000000000 RSI: ffff8f4b0545b298 RDI: ffff8f43833b2000 [ 8687.848955] RBP: ffff8f43833b2000 R08: 0000000000000001 R09: 0000000000000000 [ 8687.856086] R10: 0000000000000000 R11: 000ffffffffff000 R12: ffff8f43833b2ef0 [ 8687.863218] R13: ffff8f43833b2ef0 R14: ffff915103966000 R15: ffff8f43833b2008 [ 8687.870342] FS: 00007f79501c3740(0000) GS:ffff8f4adffc0000(0000) knlGS:0000000000000000 [ 8687.878427] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8687.884174] CR2: 0000000000000030 CR3: 000000014276e004 CR4: 00000000007706e0 [ 8687.891306] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 8687.898441] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 8687.905572] PKRU: 55555554 [ 8687.908286] Call Trace: [ 8687.910737] <TASK> [ 8687.912843] i40e_remove+0x2c0/0x330 [i40e] [ 8687.917040] pci_device_remove+0x33/0xa0 [ 8687.920962] device_release_driver_internal+0x1aa/0x230 [ 8687.926188] driver_detach+0x44/0x90 [ 8687.929770] bus_remove_driver+0x55/0xe0 [ 8687.933693] pci_unregister_driver+0x2a/0xb0 [ 8687.937967] i40e_exit_module+0xc/0xf48 [i40e]
Two offline tests cause IRDMA driver failure (ETIMEDOUT) and this failure is indicated back to i40e_client_subtask() that calls i40e_client_del_instance() to free client instance referenced by pf->cinst and sets this pointer to NULL. During the module removal i40e_remove() calls i40e_lan_del_device() that dereferences pf->cinst that is NULL -> crash. Do not remove client instance when client open callbacks fails and just clear __I40E_CLIENT_INSTANCE_OPENED bit. The driver also needs to take care about this situation (when netdev is up and client is NOT opened) in i40e_notify_client_of_netdev_close() and calls client close callback only when __I40E_CLIENT_INSTANCE_OPENED is set.
Fixes: 0ef2d5afb12d ("i40e: KISS the client interface") Signed-off-by: Ivan Vecera ivecera@redhat.com Tested-by: Helena Anna Dubel helena.anna.dubel@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_client.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index ea2bb0140a6eb..10d7a982a5b9b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -177,6 +177,10 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) "Cannot locate client instance close routine\n"); return; } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort close\n"); + return; + } cdev->client->ops->close(&cdev->lan_info, cdev->client, reset); clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); i40e_client_release_qvlist(&cdev->lan_info); @@ -429,7 +433,6 @@ void i40e_client_subtask(struct i40e_pf *pf) /* Remove failed client instance */ clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); - i40e_client_del_instance(pf); return; } }
From: Ivan Vecera ivecera@redhat.com
[ Upstream commit aa626da947e9cd30c4cf727493903e1adbb2c0a0 ]
iavf_reset_task() takes crit_lock at the beginning and holds it during whole call. The function subsequently calls iavf_init_interrupt_scheme() that grabs RTNL. Problem occurs when userspace initiates during the reset task any ndo callback that runs under RTNL like iavf_open() because some of that functions tries to take crit_lock. This leads to classic A-B B-A deadlock scenario.
To resolve this situation the device should be detached in iavf_reset_task() prior taking crit_lock to avoid subsequent ndos running under RTNL and reattach the device at the end.
Fixes: 62fe2a865e6d ("i40evf: add missing rtnl_lock() around i40evf_set_interrupt_capability") Cc: Jacob Keller jacob.e.keller@intel.com Cc: Patryk Piotrowski patryk.piotrowski@intel.com Cc: SlawomirX Laba slawomirx.laba@intel.com Tested-by: Vitaly Grinberg vgrinber@redhat.com Signed-off-by: Ivan Vecera ivecera@redhat.com Tested-by: Konrad Jankowski konrad0.jankowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/iavf/iavf_main.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 6d159334da9ec..981c43b204ff4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2789,6 +2789,11 @@ static void iavf_reset_task(struct work_struct *work) int i = 0, err; bool running;
+ /* Detach interface to avoid subsequent NDO callbacks */ + rtnl_lock(); + netif_device_detach(netdev); + rtnl_unlock(); + /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ @@ -2796,7 +2801,7 @@ static void iavf_reset_task(struct work_struct *work) if (adapter->state != __IAVF_REMOVE) queue_work(iavf_wq, &adapter->reset_task);
- return; + goto reset_finish; }
while (!mutex_trylock(&adapter->client_lock)) @@ -2866,7 +2871,6 @@ static void iavf_reset_task(struct work_struct *work)
if (running) { netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); adapter->link_up = false; iavf_napi_disable_all(adapter); } @@ -2996,7 +3000,7 @@ static void iavf_reset_task(struct work_struct *work) mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock);
- return; + goto reset_finish; reset_err: if (running) { set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); @@ -3007,6 +3011,10 @@ static void iavf_reset_task(struct work_struct *work) mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); +reset_finish: + rtnl_lock(); + netif_device_attach(netdev); + rtnl_unlock(); }
/**
From: Csókás Bence csokas.bence@prolan.hu
[ Upstream commit b353b241f1eb9b6265358ffbe2632fdcb563354f ]
Mutexes cannot be taken in a non-preemptible context, causing a panic in `fec_ptp_save_state()`. Replacing `ptp_clk_mutex` by `tmreg_lock` fixes this.
Fixes: 6a4d7234ae9a ("net: fec: ptp: avoid register access when ipg clock is disabled") Fixes: f79959220fa5 ("fec: Restart PPS after link state change") Reported-by: Marc Kleine-Budde mkl@pengutronix.de Link: https://lore.kernel.org/all/20220827160922.642zlcd5foopozru@pengutronix.de/ Signed-off-by: Csókás Bence csokas.bence@prolan.hu Tested-by: Francesco Dolcini francesco.dolcini@toradex.com # Toradex Apalis iMX6 Link: https://lore.kernel.org/r/20220901140402.64804-1-csokas.bence@prolan.hu Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/fec.h | 1 - drivers/net/ethernet/freescale/fec_main.c | 17 +++++++------- drivers/net/ethernet/freescale/fec_ptp.c | 28 ++++++++--------------- 3 files changed, 19 insertions(+), 27 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index ed7301b691694..939720a75f87c 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -557,7 +557,6 @@ struct fec_enet_private { struct clk *clk_2x_txclk;
bool ptp_clk_on; - struct mutex ptp_clk_mutex; unsigned int num_tx_queues; unsigned int num_rx_queues;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index a90275143d873..8538ea31ca803 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1994,6 +1994,7 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev) static int fec_enet_clk_enable(struct net_device *ndev, bool enable) { struct fec_enet_private *fep = netdev_priv(ndev); + unsigned long flags; int ret;
if (enable) { @@ -2002,15 +2003,15 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) return ret;
if (fep->clk_ptp) { - mutex_lock(&fep->ptp_clk_mutex); + spin_lock_irqsave(&fep->tmreg_lock, flags); ret = clk_prepare_enable(fep->clk_ptp); if (ret) { - mutex_unlock(&fep->ptp_clk_mutex); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); goto failed_clk_ptp; } else { fep->ptp_clk_on = true; } - mutex_unlock(&fep->ptp_clk_mutex); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); }
ret = clk_prepare_enable(fep->clk_ref); @@ -2025,10 +2026,10 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) } else { clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { - mutex_lock(&fep->ptp_clk_mutex); + spin_lock_irqsave(&fep->tmreg_lock, flags); clk_disable_unprepare(fep->clk_ptp); fep->ptp_clk_on = false; - mutex_unlock(&fep->ptp_clk_mutex); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); } clk_disable_unprepare(fep->clk_ref); clk_disable_unprepare(fep->clk_2x_txclk); @@ -2041,10 +2042,10 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) clk_disable_unprepare(fep->clk_ref); failed_clk_ref: if (fep->clk_ptp) { - mutex_lock(&fep->ptp_clk_mutex); + spin_lock_irqsave(&fep->tmreg_lock, flags); clk_disable_unprepare(fep->clk_ptp); fep->ptp_clk_on = false; - mutex_unlock(&fep->ptp_clk_mutex); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); } failed_clk_ptp: clk_disable_unprepare(fep->clk_enet_out); @@ -3873,7 +3874,7 @@ fec_probe(struct platform_device *pdev) }
fep->ptp_clk_on = false; - mutex_init(&fep->ptp_clk_mutex); + spin_lock_init(&fep->tmreg_lock);
/* clk_ref is optional, depends on board */ fep->clk_ref = devm_clk_get_optional(&pdev->dev, "enet_clk_ref"); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 3dc3c0b626c21..af20aa2379640 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -365,21 +365,19 @@ static int fec_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) */ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { - struct fec_enet_private *adapter = + struct fec_enet_private *fep = container_of(ptp, struct fec_enet_private, ptp_caps); u64 ns; unsigned long flags;
- mutex_lock(&adapter->ptp_clk_mutex); + spin_lock_irqsave(&fep->tmreg_lock, flags); /* Check the ptp clock */ - if (!adapter->ptp_clk_on) { - mutex_unlock(&adapter->ptp_clk_mutex); + if (!fep->ptp_clk_on) { + spin_unlock_irqrestore(&fep->tmreg_lock, flags); return -EINVAL; } - spin_lock_irqsave(&adapter->tmreg_lock, flags); - ns = timecounter_read(&adapter->tc); - spin_unlock_irqrestore(&adapter->tmreg_lock, flags); - mutex_unlock(&adapter->ptp_clk_mutex); + ns = timecounter_read(&fep->tc); + spin_unlock_irqrestore(&fep->tmreg_lock, flags);
*ts = ns_to_timespec64(ns);
@@ -404,10 +402,10 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp, unsigned long flags; u32 counter;
- mutex_lock(&fep->ptp_clk_mutex); + spin_lock_irqsave(&fep->tmreg_lock, flags); /* Check the ptp clock */ if (!fep->ptp_clk_on) { - mutex_unlock(&fep->ptp_clk_mutex); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); return -EINVAL; }
@@ -417,11 +415,9 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp, */ counter = ns & fep->cc.mask;
- spin_lock_irqsave(&fep->tmreg_lock, flags); writel(counter, fep->hwp + FEC_ATIME); timecounter_init(&fep->tc, &fep->cc, ns); spin_unlock_irqrestore(&fep->tmreg_lock, flags); - mutex_unlock(&fep->ptp_clk_mutex); return 0; }
@@ -518,13 +514,11 @@ static void fec_time_keep(struct work_struct *work) struct fec_enet_private *fep = container_of(dwork, struct fec_enet_private, time_keep); unsigned long flags;
- mutex_lock(&fep->ptp_clk_mutex); + spin_lock_irqsave(&fep->tmreg_lock, flags); if (fep->ptp_clk_on) { - spin_lock_irqsave(&fep->tmreg_lock, flags); timecounter_read(&fep->tc); - spin_unlock_irqrestore(&fep->tmreg_lock, flags); } - mutex_unlock(&fep->ptp_clk_mutex); + spin_unlock_irqrestore(&fep->tmreg_lock, flags);
schedule_delayed_work(&fep->time_keep, HZ); } @@ -599,8 +593,6 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) } fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed;
- spin_lock_init(&fep->tmreg_lock); - fec_ptp_start_cyclecounter(ndev);
INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep);
Hello Greg,
On 13.09.2022 16:03:49, Greg Kroah-Hartman wrote:
From: Csókás Bence csokas.bence@prolan.hu
[ Upstream commit b353b241f1eb9b6265358ffbe2632fdcb563354f ]
Mutexes cannot be taken in a non-preemptible context, causing a panic in `fec_ptp_save_state()`. Replacing `ptp_clk_mutex` by `tmreg_lock` fixes this.
Fixes: 6a4d7234ae9a ("net: fec: ptp: avoid register access when ipg clock is disabled") Fixes: f79959220fa5 ("fec: Restart PPS after link state change") Reported-by: Marc Kleine-Budde mkl@pengutronix.de Link: https://lore.kernel.org/all/20220827160922.642zlcd5foopozru@pengutronix.de/ Signed-off-by: Csókás Bence csokas.bence@prolan.hu Tested-by: Francesco Dolcini francesco.dolcini@toradex.com # Toradex Apalis iMX6 Link: https://lore.kernel.org/r/20220901140402.64804-1-csokas.bence@prolan.hu Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org
there's a revert pending for this patch:
| https://lore.kernel.org/all/20220912070143.98153-1-francesco.dolcini@toradex...
...as it causes troubles in 6.0-rc4:
| https://lore.kernel.org/all/20220907143915.5w65kainpykfobte@pengutronix.de/ | https://lore.kernel.org/all/CAHk-=wj1obPoTu1AHj9Bd_BGYjdjDyPP+vT5WMj8eheb3A9...
please drop this patch.
regards, Marc
On Tue, Sep 13, 2022 at 04:19:17PM +0200, Marc Kleine-Budde wrote:
Hello Greg,
On 13.09.2022 16:03:49, Greg Kroah-Hartman wrote:
From: Csókás Bence csokas.bence@prolan.hu
[ Upstream commit b353b241f1eb9b6265358ffbe2632fdcb563354f ]
Mutexes cannot be taken in a non-preemptible context, causing a panic in `fec_ptp_save_state()`. Replacing `ptp_clk_mutex` by `tmreg_lock` fixes this.
Fixes: 6a4d7234ae9a ("net: fec: ptp: avoid register access when ipg clock is disabled") Fixes: f79959220fa5 ("fec: Restart PPS after link state change") Reported-by: Marc Kleine-Budde mkl@pengutronix.de Link: https://lore.kernel.org/all/20220827160922.642zlcd5foopozru@pengutronix.de/ Signed-off-by: Csókás Bence csokas.bence@prolan.hu Tested-by: Francesco Dolcini francesco.dolcini@toradex.com # Toradex Apalis iMX6 Link: https://lore.kernel.org/r/20220901140402.64804-1-csokas.bence@prolan.hu Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org
there's a revert pending for this patch:
| https://lore.kernel.org/all/20220912070143.98153-1-francesco.dolcini@toradex...
...as it causes troubles in 6.0-rc4:
| https://lore.kernel.org/all/20220907143915.5w65kainpykfobte@pengutronix.de/ | https://lore.kernel.org/all/CAHk-=wj1obPoTu1AHj9Bd_BGYjdjDyPP+vT5WMj8eheb3A9...
please drop this patch.
Now dropped from all 3 queues, thanks.
greg k-h
From: Paul Durrant pdurrant@amazon.com
[ Upstream commit c55f34b6aec2a8cb47eadaffea773e83bf85de91 ]
Removing 'hotplug-status' in backend_disconnected() means that it will be removed even in the case that the frontend unilaterally disconnects (which it is free to do at any time). The consequence of this is that, when the frontend attempts to re-connect, the backend gets stuck in 'InitWait' rather than moving straight to 'Connected' (which it can do because the hotplug script has already run). Instead, the 'hotplug-status' mode should be removed in netback_remove() i.e. when the vif really is going away.
Fixes: 0f4558ae9187 ("Revert "xen-netback: remove 'hotplug-status' once it has served its purpose"") Signed-off-by: Paul Durrant pdurrant@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/xen-netback/xenbus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 990360d75cb64..e85b3c5d4acce 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -256,7 +256,6 @@ static void backend_disconnect(struct backend_info *be) unsigned int queue_index;
xen_unregister_watchers(vif); - xenbus_rm(XBT_NIL, be->dev->nodename, "hotplug-status"); #ifdef CONFIG_DEBUG_FS xenvif_debugfs_delif(vif); #endif /* CONFIG_DEBUG_FS */ @@ -984,6 +983,7 @@ static int netback_remove(struct xenbus_device *dev) struct backend_info *be = dev_get_drvdata(&dev->dev);
unregister_hotplug_status_watch(be); + xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); if (be->vif) { kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); backend_disconnect(be);
From: Ming Lei ming.lei@redhat.com
[ Upstream commit 748008e1da926a814cc0a054c81ca614408b1b0c ]
Commit b9684a71fca7 ("block, loop: support partitions without scanning") adds GD_SUPPRESS_PART_SCAN for replacing part function of GENHD_FL_NO_PART. But looks blk_add_partitions() is missed, since loop doesn't want to add partitions if GENHD_FL_NO_PART was set. And it causes regression on libblockdev (as called from udisks) which operates with the LO_FLAGS_PARTSCAN.
Fixes the issue by not adding partitions if GD_SUPPRESS_PART_SCAN is set.
Fixes: b9684a71fca7 ("block, loop: support partitions without scanning") Signed-off-by: Ming Lei ming.lei@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Link: https://lore.kernel.org/r/20220823103819.395776-1-ming.lei@redhat.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/partitions/core.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/block/partitions/core.c b/block/partitions/core.c index 8a0ec929023bc..76617b1d2d47f 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -597,6 +597,9 @@ static int blk_add_partitions(struct gendisk *disk) if (disk->flags & GENHD_FL_NO_PART) return 0;
+ if (test_bit(GD_SUPPRESS_PART_SCAN, &disk->state)) + return 0; + state = check_partition(disk); if (!state) return 0;
From: Linus Walleij linus.walleij@linaro.org
[ Upstream commit 0d1b756acf60da5004c1e20ca4462f0c257bf6e1 ]
Functions that work on a pointer to virtual memory such as virt_to_pfn() and users of that function such as virt_to_page() are supposed to pass a pointer to virtual memory, ideally a (void *) or other pointer. However since many architectures implement virt_to_pfn() as a macro, this function becomes polymorphic and accepts both a (unsigned long) and a (void *).
If we instead implement a proper virt_to_pfn(void *addr) function the following happens (occurred on arch/arm):
drivers/infiniband/sw/siw/siw_qp_tx.c:32:23: warning: incompatible integer to pointer conversion passing 'dma_addr_t' (aka 'unsigned int') to parameter of type 'const void *' [-Wint-conversion] drivers/infiniband/sw/siw/siw_qp_tx.c:32:37: warning: passing argument 1 of 'virt_to_pfn' makes pointer from integer without a cast [-Wint-conversion] drivers/infiniband/sw/siw/siw_qp_tx.c:538:36: warning: incompatible integer to pointer conversion passing 'unsigned long long' to parameter of type 'const void *' [-Wint-conversion]
Fix this with an explicit cast. In one case where the SIW SGE uses an unaligned u64 we need a double cast modifying the virtual address (va) to a platform-specific uintptr_t before casting to a (void *).
Fixes: b9be6f18cf9e ("rdma/siw: transmit path") Cc: linux-rdma@vger.kernel.org Signed-off-by: Linus Walleij linus.walleij@linaro.org Link: https://lore.kernel.org/r/20220902215918.603761-1-linus.walleij@linaro.org Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/sw/siw/siw_qp_tx.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 1f4e60257700e..7d47b521070b1 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -29,7 +29,7 @@ static struct page *siw_get_pblpage(struct siw_mem *mem, u64 addr, int *idx) dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx);
if (paddr) - return virt_to_page(paddr); + return virt_to_page((void *)paddr);
return NULL; } @@ -533,13 +533,23 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) kunmap_local(kaddr); } } else { - u64 va = sge->laddr + sge_off; + /* + * Cast to an uintptr_t to preserve all 64 bits + * in sge->laddr. + */ + uintptr_t va = (uintptr_t)(sge->laddr + sge_off);
- page_array[seg] = virt_to_page(va & PAGE_MASK); + /* + * virt_to_page() takes a (void *) pointer + * so cast to a (void *) meaning it will be 64 + * bits on a 64 bit platform and 32 bits on a + * 32 bit platform. + */ + page_array[seg] = virt_to_page((void *)(va & PAGE_MASK)); if (do_crc) crypto_shash_update( c_tx->mpa_crc_hd, - (void *)(uintptr_t)va, + (void *)va, plen); }
From: Hangbin Liu liuhangbin@gmail.com
[ Upstream commit b7f14132bf58256e841774ae07d3ffb7a841c2bc ]
When ns_ip6_target was set, the ipv6_dev_get_saddr() will be called to get available source address and send IPv6 neighbor solicit message.
If the target is global address, ipv6_dev_get_saddr() will get any available src address. But if the target is link local address, ipv6_dev_get_saddr() will only get available address from our interface, i.e. the corresponding bond interface.
But before bond interface up, all the address is tentative, while ipv6_dev_get_saddr() will ignore tentative address. This makes we can't find available link local src address, then bond_ns_send() will not be called and no NS message was sent. Finally bond interface will keep in down state.
Fix this by sending NS with unspecified address if there is no available source address.
Reported-by: LiLiang liali@redhat.com Fixes: 5e1eeef69c0f ("bonding: NS target should accept link local address") Signed-off-by: Hangbin Liu liuhangbin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 6ba4c83fe5fc0..0cf8c3a125d2e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3134,6 +3134,9 @@ static void bond_ns_send_all(struct bonding *bond, struct slave *slave) found: if (!ipv6_dev_get_saddr(dev_net(dst->dev), dst->dev, &targets[i], 0, &saddr)) bond_ns_send(slave, &targets[i], &saddr, tags); + else + bond_ns_send(slave, &targets[i], &in6addr_any, tags); + dst_release(dst); kfree(tags); }
From: Hangbin Liu liuhangbin@gmail.com
[ Upstream commit fd16eb948ea8b28afb03e11a5b11841e6ac2aa2b ]
When a link is enslave to bond, it need to set the interface down first. This makes the slave remove mac multicast address 33:33:00:00:00:01(The IPv6 multicast address ff02::1 is kept even when the interface down). When bond set the slave up, ipv6_mc_up() was not called due to commit c2edacf80e15 ("bonding / ipv6: no addrconf for slaves separately from master").
This is not an issue before we adding the lladdr target feature for bonding, as the mac multicast address will be added back when bond interface up and join group ff02::1.
But after adding lladdr target feature for bonding. When user set a lladdr target, the unsolicited NA message with all-nodes multicast dest will be dropped as the slave interface never add 33:33:00:00:00:01 back.
Fix this by calling ipv6_mc_up() to add 33:33:00:00:00:01 back when the slave interface up.
Reported-by: LiLiang liali@redhat.com Fixes: 5e1eeef69c0f ("bonding: NS target should accept link local address") Signed-off-by: Hangbin Liu liuhangbin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/addrconf.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b738eb7e1cae8..04cf06866e765 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3557,11 +3557,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, fallthrough; case NETDEV_UP: case NETDEV_CHANGE: - if (dev->flags & IFF_SLAVE) + if (idev && idev->cnf.disable_ipv6) break;
- if (idev && idev->cnf.disable_ipv6) + if (dev->flags & IFF_SLAVE) { + if (event == NETDEV_UP && !IS_ERR_OR_NULL(idev) && + dev->flags & IFF_UP && dev->flags & IFF_MULTICAST) + ipv6_mc_up(idev); break; + }
if (event == NETDEV_UP) { /* restore routes for permanent addresses */
From: David Lebrun dlebrun@google.com
[ Upstream commit 84a53580c5d2138c7361c7c3eea5b31827e63b35 ]
The SRv6 layer allows defining HMAC data that can later be used to sign IPv6 Segment Routing Headers. This configuration is realised via netlink through four attributes: SEG6_ATTR_HMACKEYID, SEG6_ATTR_SECRET, SEG6_ATTR_SECRETLEN and SEG6_ATTR_ALGID. Because the SECRETLEN attribute is decoupled from the actual length of the SECRET attribute, it is possible to provide invalid combinations (e.g., secret = "", secretlen = 64). This case is not checked in the code and with an appropriately crafted netlink message, an out-of-bounds read of up to 64 bytes (max secret length) can occur past the skb end pointer and into skb_shared_info:
Breakpoint 1, seg6_genl_sethmac (skb=<optimized out>, info=<optimized out>) at net/ipv6/seg6.c:208 208 memcpy(hinfo->secret, secret, slen); (gdb) bt #0 seg6_genl_sethmac (skb=<optimized out>, info=<optimized out>) at net/ipv6/seg6.c:208 #1 0xffffffff81e012e9 in genl_family_rcv_msg_doit (skb=skb@entry=0xffff88800b1f9f00, nlh=nlh@entry=0xffff88800b1b7600, extack=extack@entry=0xffffc90000ba7af0, ops=ops@entry=0xffffc90000ba7a80, hdrlen=4, net=0xffffffff84237580 <init_net>, family=<optimized out>, family=<optimized out>) at net/netlink/genetlink.c:731 #2 0xffffffff81e01435 in genl_family_rcv_msg (extack=0xffffc90000ba7af0, nlh=0xffff88800b1b7600, skb=0xffff88800b1f9f00, family=0xffffffff82fef6c0 <seg6_genl_family>) at net/netlink/genetlink.c:775 #3 genl_rcv_msg (skb=0xffff88800b1f9f00, nlh=0xffff88800b1b7600, extack=0xffffc90000ba7af0) at net/netlink/genetlink.c:792 #4 0xffffffff81dfffc3 in netlink_rcv_skb (skb=skb@entry=0xffff88800b1f9f00, cb=cb@entry=0xffffffff81e01350 <genl_rcv_msg>) at net/netlink/af_netlink.c:2501 #5 0xffffffff81e00919 in genl_rcv (skb=0xffff88800b1f9f00) at net/netlink/genetlink.c:803 #6 0xffffffff81dff6ae in netlink_unicast_kernel (ssk=0xffff888010eec800, skb=0xffff88800b1f9f00, sk=0xffff888004aed000) at net/netlink/af_netlink.c:1319 #7 netlink_unicast (ssk=ssk@entry=0xffff888010eec800, skb=skb@entry=0xffff88800b1f9f00, portid=portid@entry=0, nonblock=<optimized out>) at net/netlink/af_netlink.c:1345 #8 0xffffffff81dff9a4 in netlink_sendmsg (sock=<optimized out>, msg=0xffffc90000ba7e48, len=<optimized out>) at net/netlink/af_netlink.c:1921 ... (gdb) p/x ((struct sk_buff *)0xffff88800b1f9f00)->head + ((struct sk_buff *)0xffff88800b1f9f00)->end $1 = 0xffff88800b1b76c0 (gdb) p/x secret $2 = 0xffff88800b1b76c0 (gdb) p slen $3 = 64 '@'
The OOB data can then be read back from userspace by dumping HMAC state. This commit fixes this by ensuring SECRETLEN cannot exceed the actual length of SECRET.
Reported-by: Lucas Leong wmliang.tw@gmail.com Tested: verified that EINVAL is correctly returned when secretlen > len(secret) Fixes: 4f4853dc1c9c1 ("ipv6: sr: implement API to control SR HMAC structure") Signed-off-by: David Lebrun dlebrun@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/seg6.c | 5 +++++ 1 file changed, 5 insertions(+)
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 73aaabf0e9665..0b0e34ddc64e0 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -191,6 +191,11 @@ static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) goto out_unlock; }
+ if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) { + err = -EINVAL; + goto out_unlock; + } + if (hinfo) { err = seg6_hmac_info_del(net, hmackeyid); if (err)
From: Yishai Hadas yishaih@nvidia.com
[ Upstream commit 85eaeb5058f0f04dffb124c97c86b4f18db0b833 ]
Fix a nested dead lock as part of ODP flow by using mmput_async().
From the below call trace [1] can see that calling mmput() once we have
the umem_odp->umem_mutex locked as required by ib_umem_odp_map_dma_and_lock() might trigger in the same task the exit_mmap()->__mmu_notifier_release()->mlx5_ib_invalidate_range() which may dead lock when trying to lock the same mutex.
Moving to use mmput_async() will solve the problem as the above exit_mmap() flow will be called in other task and will be executed once the lock will be available.
[1] [64843.077665] task:kworker/u133:2 state:D stack: 0 pid:80906 ppid: 2 flags:0x00004000 [64843.077672] Workqueue: mlx5_ib_page_fault mlx5_ib_eqe_pf_action [mlx5_ib] [64843.077719] Call Trace: [64843.077722] <TASK> [64843.077724] __schedule+0x23d/0x590 [64843.077729] schedule+0x4e/0xb0 [64843.077735] schedule_preempt_disabled+0xe/0x10 [64843.077740] __mutex_lock.constprop.0+0x263/0x490 [64843.077747] __mutex_lock_slowpath+0x13/0x20 [64843.077752] mutex_lock+0x34/0x40 [64843.077758] mlx5_ib_invalidate_range+0x48/0x270 [mlx5_ib] [64843.077808] __mmu_notifier_release+0x1a4/0x200 [64843.077816] exit_mmap+0x1bc/0x200 [64843.077822] ? walk_page_range+0x9c/0x120 [64843.077828] ? __cond_resched+0x1a/0x50 [64843.077833] ? mutex_lock+0x13/0x40 [64843.077839] ? uprobe_clear_state+0xac/0x120 [64843.077860] mmput+0x5f/0x140 [64843.077867] ib_umem_odp_map_dma_and_lock+0x21b/0x580 [ib_core] [64843.077931] pagefault_real_mr+0x9a/0x140 [mlx5_ib] [64843.077962] pagefault_mr+0xb4/0x550 [mlx5_ib] [64843.077992] pagefault_single_data_segment.constprop.0+0x2ac/0x560 [mlx5_ib] [64843.078022] mlx5_ib_eqe_pf_action+0x528/0x780 [mlx5_ib] [64843.078051] process_one_work+0x22b/0x3d0 [64843.078059] worker_thread+0x53/0x410 [64843.078065] ? process_one_work+0x3d0/0x3d0 [64843.078073] kthread+0x12a/0x150 [64843.078079] ? set_kthread_struct+0x50/0x50 [64843.078085] ret_from_fork+0x22/0x30 [64843.078093] </TASK>
Fixes: 36f30e486dce ("IB/core: Improve ODP to use hmm_range_fault()") Reviewed-by: Maor Gottlieb maorg@nvidia.com Signed-off-by: Yishai Hadas yishaih@nvidia.com Link: https://lore.kernel.org/r/74d93541ea533ef7daec6f126deb1072500aeb16.166125184... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/umem_odp.c | 2 +- kernel/fork.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 186ed8859920c..d39e16c211e8a 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -462,7 +462,7 @@ int ib_umem_odp_map_dma_and_lock(struct ib_umem_odp *umem_odp, u64 user_virt, mutex_unlock(&umem_odp->umem_mutex);
out_put_mm: - mmput(owning_mm); + mmput_async(owning_mm); out_put_task: if (owning_process) put_task_struct(owning_process); diff --git a/kernel/fork.c b/kernel/fork.c index 9d44f2d46c696..d587c85f35b1e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1225,6 +1225,7 @@ void mmput_async(struct mm_struct *mm) schedule_work(&mm->async_put_work); } } +EXPORT_SYMBOL_GPL(mmput_async); #endif
/**
From: Chris Mi cmi@nvidia.com
[ Upstream commit 74b30b3ad5cec95d2647e796d10137438a098bc1 ]
When accessing Ports Performance Counters Register (PPCNT), local port must be one if it is Function-Per-Port HCA that HCA_CAP.num_ports is 1.
The offending patch can change the local port to other values when accessing PPCNT after enabling switchdev mode. The following syndrome will be printed:
# cat /sys/class/infiniband/rdmap4s0f0/ports/2/counters/* # dmesg mlx5_core 0000:04:00.0: mlx5_cmd_check:756:(pid 12450): ACCESS_REG(0x805) op_mod(0x1) failed, status bad parameter(0x3), syndrome (0x1e5585)
Fix it by setting local port to one for Function-Per-Port HCA.
Fixes: 210b1f78076f ("IB/mlx5: When not in dual port RoCE mode, use provided port as native") Reviewed-by: Mark Bloch mbloch@nvidia.com Signed-off-by: Chris Mi cmi@nvidia.com Link: https://lore.kernel.org/r/6c5086c295c76211169e58dbd610fb0402360bab.166176345... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/mlx5/mad.c | 6 ++++++ 1 file changed, 6 insertions(+)
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 293ed709e5ed5..b4dc52392275b 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -166,6 +166,12 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num, mdev = dev->mdev; mdev_port_num = 1; } + if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) { + /* set local port to one for Function-Per-Port HCA. */ + mdev = dev->mdev; + mdev_port_num = 1; + } + /* Declaring support of extended counters */ if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) { struct ib_class_port_info cpi = {};
From: Johannes Thumshirn johannes.thumshirn@wdc.com
[ Upstream commit 6ca64ac2763149fb66c0b4bf12f5e0977a88e51d ]
Since commit 6a921de58992 ("btrfs: zoned: introduce space_info->active_total_bytes"), we're only counting the bytes of a block group on an active zone as usable for metadata writes. But on a SMR drive, we don't have active zones and short circuit some of the logic.
This leads to an error on mount, because we cannot reserve space for metadata writes.
Fix this by also setting the BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE bit in the block-group's runtime flag if the zone is a conventional zone.
Fixes: 6a921de58992 ("btrfs: zoned: introduce space_info->active_total_bytes") Signed-off-by: Johannes Thumshirn johannes.thumshirn@wdc.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/zoned.c | 81 ++++++++++++++++++++++++------------------------ 1 file changed, 40 insertions(+), 41 deletions(-)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 4949e0d82923d..1386362fad3b8 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1187,7 +1187,7 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) * offset. */ static int calculate_alloc_pointer(struct btrfs_block_group *cache, - u64 *offset_ret) + u64 *offset_ret, bool new) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_root *root; @@ -1197,6 +1197,21 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache, int ret; u64 length;
+ /* + * Avoid tree lookups for a new block group, there's no use for it. + * It must always be 0. + * + * Also, we have a lock chain of extent buffer lock -> chunk mutex. + * For new a block group, this function is called from + * btrfs_make_block_group() which is already taking the chunk mutex. + * Thus, we cannot call calculate_alloc_pointer() which takes extent + * buffer locks to avoid deadlock. + */ + if (new) { + *offset_ret = 0; + return 0; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -1332,6 +1347,13 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) else num_conventional++;
+ /* + * Consider a zone as active if we can allow any number of + * active zones. + */ + if (!device->zone_info->max_active_zones) + __set_bit(i, active); + if (!is_sequential) { alloc_offsets[i] = WP_CONVENTIONAL; continue; @@ -1398,45 +1420,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) __set_bit(i, active); break; } - - /* - * Consider a zone as active if we can allow any number of - * active zones. - */ - if (!device->zone_info->max_active_zones) - __set_bit(i, active); }
if (num_sequential > 0) cache->seq_zone = true;
if (num_conventional > 0) { - /* - * Avoid calling calculate_alloc_pointer() for new BG. It - * is no use for new BG. It must be always 0. - * - * Also, we have a lock chain of extent buffer lock -> - * chunk mutex. For new BG, this function is called from - * btrfs_make_block_group() which is already taking the - * chunk mutex. Thus, we cannot call - * calculate_alloc_pointer() which takes extent buffer - * locks to avoid deadlock. - */ - /* Zone capacity is always zone size in emulation */ cache->zone_capacity = cache->length; - if (new) { - cache->alloc_offset = 0; - goto out; - } - ret = calculate_alloc_pointer(cache, &last_alloc); - if (ret || map->num_stripes == num_conventional) { - if (!ret) - cache->alloc_offset = last_alloc; - else - btrfs_err(fs_info, + ret = calculate_alloc_pointer(cache, &last_alloc, new); + if (ret) { + btrfs_err(fs_info, "zoned: failed to determine allocation offset of bg %llu", - cache->start); + cache->start); + goto out; + } else if (map->num_stripes == num_conventional) { + cache->alloc_offset = last_alloc; + cache->zone_is_active = 1; goto out; } } @@ -1504,13 +1504,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; }
- if (cache->zone_is_active) { - btrfs_get_block_group(cache); - spin_lock(&fs_info->zone_active_bgs_lock); - list_add_tail(&cache->active_bg_list, &fs_info->zone_active_bgs); - spin_unlock(&fs_info->zone_active_bgs_lock); - } - out: if (cache->alloc_offset > fs_info->zone_size) { btrfs_err(fs_info, @@ -1535,10 +1528,16 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) ret = -EIO; }
- if (!ret) + if (!ret) { cache->meta_write_pointer = cache->alloc_offset + cache->start; - - if (ret) { + if (cache->zone_is_active) { + btrfs_get_block_group(cache); + spin_lock(&fs_info->zone_active_bgs_lock); + list_add_tail(&cache->active_bg_list, + &fs_info->zone_active_bgs); + spin_unlock(&fs_info->zone_active_bgs_lock); + } + } else { kfree(cache->physical_map); cache->physical_map = NULL; }
From: Sun Ke sunke32@huawei.com
[ Upstream commit 5bd9628b784cc5e38e1c7ebb680bbd6ee741230e ]
If erofs_fscache_alloc_request fail and then goto out, it will return 0. it should return a negative error code instead of 0.
Fixes: d435d53228dd ("erofs: change to use asynchronous io for fscache readpage/readahead") Signed-off-by: Sun Ke sunke32@huawei.com Reviewed-by: Jingbo Xu jefflexu@linux.alibaba.com Reviewed-by: Gao Xiang hsiangkao@linux.alibaba.com Reviewed-by: Chao Yu chao@kernel.org Link: https://lore.kernel.org/r/20220815034829.3940803-1-sunke32@huawei.com Signed-off-by: Gao Xiang hsiangkao@linux.alibaba.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/erofs/fscache.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 8e01d89c3319e..b5fd9d71e67f1 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -222,8 +222,10 @@ static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out; + }
return erofs_fscache_read_folios_async(mdev.m_fscache->cookie, rreq, mdev.m_pa); @@ -301,8 +303,10 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
rreq = erofs_fscache_alloc_request(folio_mapping(folio), folio_pos(folio), folio_size(folio)); - if (IS_ERR(rreq)) + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); goto out_unlock; + }
pstart = mdev.m_pa + (pos - map.m_la); return erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
From: Gao Xiang hsiangkao@linux.alibaba.com
[ Upstream commit 2f44013e39984c127c6efedf70e6b5f4e9dcf315 ]
During stress testing with CONFIG_SMP disabled, KASAN reports as below:
================================================================== BUG: KASAN: use-after-free in __mutex_lock+0xe5/0xc30 Read of size 8 at addr ffff8881094223f8 by task stress/7789
CPU: 0 PID: 7789 Comm: stress Not tainted 6.0.0-rc1-00002-g0d53d2e882f9 #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Call Trace: <TASK> .. __mutex_lock+0xe5/0xc30 .. z_erofs_do_read_page+0x8ce/0x1560 .. z_erofs_readahead+0x31c/0x580 .. Freed by task 7787 kasan_save_stack+0x1e/0x40 kasan_set_track+0x20/0x30 kasan_set_free_info+0x20/0x40 __kasan_slab_free+0x10c/0x190 kmem_cache_free+0xed/0x380 rcu_core+0x3d5/0xc90 __do_softirq+0x12d/0x389
Last potentially related work creation: kasan_save_stack+0x1e/0x40 __kasan_record_aux_stack+0x97/0xb0 call_rcu+0x3d/0x3f0 erofs_shrink_workstation+0x11f/0x210 erofs_shrink_scan+0xdc/0x170 shrink_slab.constprop.0+0x296/0x530 drop_slab+0x1c/0x70 drop_caches_sysctl_handler+0x70/0x80 proc_sys_call_handler+0x20a/0x2f0 vfs_write+0x555/0x6c0 ksys_write+0xbe/0x160 do_syscall_64+0x3b/0x90
The root cause is that erofs_workgroup_unfreeze() doesn't reset to orig_val thus it causes a race that the pcluster reuses unexpectedly before freeing.
Since UP platforms are quite rare now, such path becomes unnecessary. Let's drop such specific-designed path directly instead.
Fixes: 73f5c66df3e2 ("staging: erofs: fix `erofs_workgroup_{try_to_freeze, unfreeze}'") Reviewed-by: Yue Hu huyue2@coolpad.com Reviewed-by: Chao Yu chao@kernel.org Link: https://lore.kernel.org/r/20220902045710.109530-1-hsiangkao@linux.alibaba.co... Signed-off-by: Gao Xiang hsiangkao@linux.alibaba.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/erofs/internal.h | 29 ----------------------------- 1 file changed, 29 deletions(-)
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index cfee49d33b95a..a01cc82795a25 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -195,7 +195,6 @@ struct erofs_workgroup { atomic_t refcount; };
-#if defined(CONFIG_SMP) static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, int val) { @@ -224,34 +223,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) return atomic_cond_read_relaxed(&grp->refcount, VAL != EROFS_LOCKED_MAGIC); } -#else -static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp, - int val) -{ - preempt_disable(); - /* no need to spin on UP platforms, let's just disable preemption. */ - if (val != atomic_read(&grp->refcount)) { - preempt_enable(); - return false; - } - return true; -} - -static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp, - int orig_val) -{ - preempt_enable(); -} - -static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) -{ - int v = atomic_read(&grp->refcount); - - /* workgroup is never freezed on uniprocessor systems */ - DBG_BUGON(v == EROFS_LOCKED_MAGIC); - return v; -} -#endif /* !CONFIG_SMP */ #endif /* !CONFIG_EROFS_FS_ZIP */
/* we strictly follow PAGE_SIZE and no buffer head yet */
From: Sagi Grimberg sagi@grimberg.me
[ Upstream commit 160f3549a907a50e51a8518678ba2dcf2541abea ]
We should also bail from the io_work loop when we set rd_enabled to true, so we don't attempt to read data from the socket when the TCP stream is already out-of-sync or corrupted.
Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver") Reported-by: Daniel Wagner dwagner@suse.de Signed-off-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Daniel Wagner dwagner@suse.de Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 7a9e6ffa23429..40bd68ba1040a 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1227,7 +1227,7 @@ static void nvme_tcp_io_work(struct work_struct *w) else if (unlikely(result < 0)) return;
- if (!pending) + if (!pending || !queue->rd_enabled) return;
} while (!time_after(jiffies, deadline)); /* quota is exhausted */
From: Sagi Grimberg sagi@grimberg.me
[ Upstream commit 3770a42bb8ceb856877699257a43c0585a5d2996 ]
When we queue requests, we strive to batch as much as possible and also signal the network stack that more data is about to be sent over a socket with MSG_SENDPAGE_NOTLAST. This flag looks at the pending requests queued as well as queue->more_requests that is derived from the block layer last-in-batch indication.
We set more_request=true when we flush the request directly from .queue_rq submission context (in nvme_tcp_send_all), however this is wrongly assuming that no other requests may be queued during the execution of nvme_tcp_send_all.
Due to this, a race condition may happen where:
1. request X is queued as !last-in-batch 2. request X submission context calls nvme_tcp_send_all directly 3. nvme_tcp_send_all is preempted and schedules to a different cpu 4. request Y is queued as last-in-batch 5. nvme_tcp_send_all context sends request X+Y, however signals for both MSG_SENDPAGE_NOTLAST because queue->more_requests=true.
==> none of the requests is pushed down to the wire as the network stack is waiting for more data, both requests timeout.
To fix this, we eliminate queue->more_requests and only rely on the queue req_list and send_list to be not-empty.
Fixes: 122e5b9f3d37 ("nvme-tcp: optimize network stack with setting msg flags according to batch size") Reported-by: Jonathan Nicklin jnicklin@blockbridge.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Tested-by: Jonathan Nicklin jnicklin@blockbridge.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/tcp.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 40bd68ba1040a..daa0e160e1212 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -121,7 +121,6 @@ struct nvme_tcp_queue { struct mutex send_mutex; struct llist_head req_list; struct list_head send_list; - bool more_requests;
/* recv state */ void *pdu; @@ -318,7 +317,7 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue) static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue) { return !list_empty(&queue->send_list) || - !llist_empty(&queue->req_list) || queue->more_requests; + !llist_empty(&queue->req_list); }
static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, @@ -337,9 +336,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, */ if (queue->io_cpu == raw_smp_processor_id() && sync && empty && mutex_trylock(&queue->send_mutex)) { - queue->more_requests = !last; nvme_tcp_send_all(queue); - queue->more_requests = false; mutex_unlock(&queue->send_mutex); }
From: Neal Cardwell ncardwell@google.com
[ Upstream commit 686dc2db2a0fdc1d34b424ec2c0a735becd8d62b ]
Fix a bug reported and analyzed by Nagaraj Arankal, where the handling of a spurious non-SACK RTO could cause a connection to fail to clear retrans_stamp, causing a later RTO to very prematurely time out the connection with ETIMEDOUT.
Here is the buggy scenario, expanding upon Nagaraj Arankal's excellent report:
(*1) Send one data packet on a non-SACK connection
(*2) Because no ACK packet is received, the packet is retransmitted and we enter CA_Loss; but this retransmission is spurious.
(*3) The ACK for the original data is received. The transmitted packet is acknowledged. The TCP timestamp is before the retrans_stamp, so tcp_may_undo() returns true, and tcp_try_undo_loss() returns true without changing state to Open (because tcp_is_sack() is false), and tcp_process_loss() returns without calling tcp_try_undo_recovery(). Normally after undoing a CA_Loss episode, tcp_fastretrans_alert() would see that the connection has returned to CA_Open and fall through and call tcp_try_to_open(), which would set retrans_stamp to 0. However, for non-SACK connections we hold the connection in CA_Loss, so do not fall through to call tcp_try_to_open() and do not set retrans_stamp to 0. So retrans_stamp is (erroneously) still non-zero.
At this point the first "retransmission event" has passed and been recovered from. Any future retransmission is a completely new "event". However, retrans_stamp is erroneously still set. (And we are still in CA_Loss, which is correct.)
(*4) After 16 minutes (to correspond with tcp_retries2=15), a new data packet is sent. Note: No data is transmitted between (*3) and (*4) and we disabled keep alives.
The socket's timeout SHOULD be calculated from this point in time, but instead it's calculated from the prior "event" 16 minutes ago (step (*2)).
(*5) Because no ACK packet is received, the packet is retransmitted.
(*6) At the time of the 2nd retransmission, the socket returns ETIMEDOUT, prematurely, because retrans_stamp is (erroneously) too far in the past (set at the time of (*2)).
This commit fixes this bug by ensuring that we reuse in tcp_try_undo_loss() the same careful logic for non-SACK connections that we have in tcp_try_undo_recovery(). To avoid duplicating logic, we factor out that logic into a new tcp_is_non_sack_preventing_reopen() helper and call that helper from both undo functions.
Fixes: da34ac7626b5 ("tcp: only undo on partial ACKs in CA_Loss") Reported-by: Nagaraj Arankal nagaraj.p.arankal@hpe.com Link: https://lore.kernel.org/all/SJ0PR84MB1847BE6C24D274C46A1B9B0EB27A9@SJ0PR84MB... Signed-off-by: Neal Cardwell ncardwell@google.com Signed-off-by: Yuchung Cheng ycheng@google.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20220903121023.866900-1-ncardwell.kernel@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e5435156e545d..c30696eafc361 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2514,6 +2514,21 @@ static inline bool tcp_may_undo(const struct tcp_sock *tp) return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp)); }
+static bool tcp_is_non_sack_preventing_reopen(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { + /* Hold old state until something *above* high_seq + * is ACKed. For Reno it is MUST to prevent false + * fast retransmits (RFC2582). SACK TCP is safe. */ + if (!tcp_any_retrans_done(sk)) + tp->retrans_stamp = 0; + return true; + } + return false; +} + /* People celebrate: "We love our President!" */ static bool tcp_try_undo_recovery(struct sock *sk) { @@ -2536,14 +2551,8 @@ static bool tcp_try_undo_recovery(struct sock *sk) } else if (tp->rack.reo_wnd_persist) { tp->rack.reo_wnd_persist--; } - if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { - /* Hold old state until something *above* high_seq - * is ACKed. For Reno it is MUST to prevent false - * fast retransmits (RFC2582). SACK TCP is safe. */ - if (!tcp_any_retrans_done(sk)) - tp->retrans_stamp = 0; + if (tcp_is_non_sack_preventing_reopen(sk)) return true; - } tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; return false; @@ -2579,6 +2588,8 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; + if (tcp_is_non_sack_preventing_reopen(sk)) + return true; if (frto_undo || tcp_is_sack(tp)) { tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0;
From: Qu Wenruo wqu@suse.com
[ Upstream commit 5da431b71d4b9be3c8cf6786eff9e2d41a5f9f65 ]
[BEHAVIOR CHANGE] Since commit f6fca3917b4d ("btrfs: store chunk size in space-info struct"), btrfs no longer can create larger data chunks than 1G:
mkfs.btrfs -f -m raid1 -d raid0 $dev1 $dev2 $dev3 $dev4 mount $dev1 $mnt
btrfs balance start --full $mnt btrfs balance start --full $mnt umount $mnt
btrfs ins dump-tree -t chunk $dev1 | grep "DATA|RAID0" -C 2
Before that offending commit, what we got is a 4G data chunk:
item 6 key (FIRST_CHUNK_TREE CHUNK_ITEM 9492758528) itemoff 15491 itemsize 176 length 4294967296 owner 2 stripe_len 65536 type DATA|RAID0 io_align 65536 io_width 65536 sector_size 4096 num_stripes 4 sub_stripes 1
Now what we got is only 1G data chunk:
item 6 key (FIRST_CHUNK_TREE CHUNK_ITEM 6271533056) itemoff 15491 itemsize 176 length 1073741824 owner 2 stripe_len 65536 type DATA|RAID0 io_align 65536 io_width 65536 sector_size 4096 num_stripes 4 sub_stripes 1
This will increase the number of data chunks by the number of devices, not only increase system chunk usage, but also greatly increase mount time.
Without a proper reason, we should not change the max chunk size.
[CAUSE] Previously, we set max data chunk size to 10G, while max data stripe length to 1G.
Commit f6fca3917b4d ("btrfs: store chunk size in space-info struct") completely ignored the 10G limit, but use 1G max stripe limit instead, causing above shrink in max data chunk size.
[FIX] Fix the max data chunk size to 10G, and in decide_stripe_size_regular() we limit stripe_size to 1G manually.
This should only affect data chunks, as for metadata chunks we always set the max stripe size the same as max chunk size (256M or 1G depending on fs size).
Now the same script result the same old result:
item 6 key (FIRST_CHUNK_TREE CHUNK_ITEM 9492758528) itemoff 15491 itemsize 176 length 4294967296 owner 2 stripe_len 65536 type DATA|RAID0 io_align 65536 io_width 65536 sector_size 4096 num_stripes 4 sub_stripes 1
Reported-by: Wang Yugui wangyugui@e16-tech.com Fixes: f6fca3917b4d ("btrfs: store chunk size in space-info struct") Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/space-info.c | 2 +- fs/btrfs/volumes.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index b0c5b4738b1f7..17623e6410c5d 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -199,7 +199,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags) ASSERT(flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
if (flags & BTRFS_BLOCK_GROUP_DATA) - return SZ_1G; + return BTRFS_MAX_DATA_CHUNK_SIZE; else if (flags & BTRFS_BLOCK_GROUP_SYSTEM) return SZ_32M;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3460fd6743807..16e01fbdcec83 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5266,6 +5266,9 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl, ctl->stripe_size); }
+ /* Stripe size should not go beyond 1G. */ + ctl->stripe_size = min_t(u64, ctl->stripe_size, SZ_1G); + /* Align to BTRFS_STRIPE_LEN */ ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN); ctl->chunk_size = ctl->stripe_size * data_stripes;
From: Dennis Maisenbacher dennis.maisenbacher@wdc.com
[ Upstream commit b7e97872a65e1d57b4451769610554c131f37a0a ]
Maximum Active Resources (MAR) and Maximum Open Resources (MOR) are 0's based vales where a value of 0xffffffff indicates that there is no limit.
Decrement the values that are returned by bdev_max_open_zones and bdev_max_active_zones as the block layer helpers are not 0's based. A 0 returned by the block layer helpers indicates no limit, thus convert it to 0xffffffff (U32_MAX).
Fixes: aaf2e048af27 ("nvmet: add ZBD over ZNS backend support") Suggested-by: Niklas Cassel niklas.cassel@wdc.com Signed-off-by: Dennis Maisenbacher dennis.maisenbacher@wdc.com Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/target/zns.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 82b61acf7a72b..1956be87ac5ff 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -100,6 +100,7 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req) struct nvme_id_ns_zns *id_zns; u64 zsze; u16 status; + u32 mar, mor;
if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) { req->error_loc = offsetof(struct nvme_identify, nsid); @@ -130,8 +131,20 @@ void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req) zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >> req->ns->blksize_shift; id_zns->lbafe[0].zsze = cpu_to_le64(zsze); - id_zns->mor = cpu_to_le32(bdev_max_open_zones(req->ns->bdev)); - id_zns->mar = cpu_to_le32(bdev_max_active_zones(req->ns->bdev)); + + mor = bdev_max_open_zones(req->ns->bdev); + if (!mor) + mor = U32_MAX; + else + mor--; + id_zns->mor = cpu_to_le32(mor); + + mar = bdev_max_active_zones(req->ns->bdev); + if (!mar) + mar = U32_MAX; + else + mar--; + id_zns->mar = cpu_to_le32(mar);
done: status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns));
From: Sindhu-Devale sindhu.devale@intel.com
[ Upstream commit 12faad5e5cf2372af2d51f348b697b5edf838daf ]
Report the correct max cqes available to an application taking into account a reserved entry to detect overflow.
Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Sindhu-Devale sindhu.devale@intel.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Link: https://lore.kernel.org/r/20220906223244.1119-2-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/irdma/verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 227a799385d1d..4835702871677 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -39,7 +39,7 @@ static int irdma_query_device(struct ib_device *ibdev, props->max_send_sge = hw_attrs->uk_attrs.max_hw_wq_frags; props->max_recv_sge = hw_attrs->uk_attrs.max_hw_wq_frags; props->max_cq = rf->max_cq - rf->used_cqs; - props->max_cqe = rf->max_cqe; + props->max_cqe = rf->max_cqe - 1; props->max_mr = rf->max_mr - rf->used_mrs; props->max_mw = props->max_mr; props->max_pd = rf->max_pd - rf->used_pds;
From: Sindhu-Devale sindhu.devale@intel.com
[ Upstream commit 6b227bd32db778eddc6f3b22cc72a28dda0f2272 ]
The MR deregister CQP can fail if an MW is bound to it. Return an appropriate error for this case.
Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Sindhu-Devale sindhu.devale@intel.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Link: https://lore.kernel.org/r/20220906223244.1119-3-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/irdma/utils.c | 13 ++++++++----- drivers/infiniband/hw/irdma/verbs.c | 6 +++++- 2 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 7b15faadfef5c..f4d774451160d 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -590,11 +590,14 @@ static int irdma_wait_event(struct irdma_pci_f *rf, cqp_error = cqp_request->compl_info.error; if (cqp_error) { err_code = -EIO; - if (cqp_request->compl_info.maj_err_code == 0xFFFF && - cqp_request->compl_info.min_err_code == 0x8029) { - if (!rf->reset) { - rf->reset = true; - rf->gen_ops.request_reset(rf); + if (cqp_request->compl_info.maj_err_code == 0xFFFF) { + if (cqp_request->compl_info.min_err_code == 0x8002) + err_code = -EBUSY; + else if (cqp_request->compl_info.min_err_code == 0x8029) { + if (!rf->reset) { + rf->reset = true; + rf->gen_ops.request_reset(rf); + } } } } diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 4835702871677..e7120d7a5b4c6 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -3001,6 +3001,7 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata) struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc; struct irdma_cqp_request *cqp_request; struct cqp_cmds_info *cqp_info; + int status;
if (iwmr->type != IRDMA_MEMREG_TYPE_MEM) { if (iwmr->region) { @@ -3031,8 +3032,11 @@ static int irdma_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata) cqp_info->post_sq = 1; cqp_info->in.u.dealloc_stag.dev = &iwdev->rf->sc_dev; cqp_info->in.u.dealloc_stag.scratch = (uintptr_t)cqp_request; - irdma_handle_cqp_op(iwdev->rf, cqp_request); + status = irdma_handle_cqp_op(iwdev->rf, cqp_request); irdma_put_cqp_request(&iwdev->rf->cqp, cqp_request); + if (status) + return status; + irdma_free_stag(iwdev, iwmr->stag); done: if (iwpbl->pbl_allocated)
From: Sindhu-Devale sindhu.devale@intel.com
[ Upstream commit dcb23bbb1de7e009875fdfac2b8a9808a9319cc6 ]
When a QP and a MR on a local host are in different PDs, the HW generates an asynchronous event (AE). The same AE is generated when a QP and a MW are in different PDs during a bind operation. Return the more appropriate IBV_WC_MW_BIND_ERR for the latter case by checking the OP type from the CQE in error.
Fixes: 551c46edc769 ("RDMA/irdma: Add user/kernel shared libraries") Signed-off-by: Sindhu-Devale sindhu.devale@intel.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Link: https://lore.kernel.org/r/20220906223244.1119-4-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/irdma/uk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c index daeab5daed5bc..d003ad864ee44 100644 --- a/drivers/infiniband/hw/irdma/uk.c +++ b/drivers/infiniband/hw/irdma/uk.c @@ -1005,6 +1005,7 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, int ret_code; bool move_cq_head = true; u8 polarity; + u8 op_type; bool ext_valid; __le64 *ext_cqe;
@@ -1187,7 +1188,6 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, do { __le64 *sw_wqe; u64 wqe_qword; - u8 op_type; u32 tail;
tail = qp->sq_ring.tail; @@ -1204,6 +1204,8 @@ int irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, break; } } while (1); + if (op_type == IRDMA_OP_TYPE_BIND_MW && info->minor_err == FLUSH_PROT_ERR) + info->minor_err = FLUSH_MW_BIND_ERR; qp->sq_flush_seen = true; if (!IRDMA_RING_MORE_WORK(qp->sq_ring)) qp->sq_flush_complete = true;
From: Sindhu-Devale sindhu.devale@intel.com
[ Upstream commit a261786fdc0a5bed2e5f994dcc0ffeeeb0d662c7 ]
Report RNR NAK generation when device capabilities are queried
Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Signed-off-by: Sindhu-Devale sindhu.devale@intel.com Signed-off-by: Shiraz Saleem shiraz.saleem@intel.com Link: https://lore.kernel.org/r/20220906223244.1119-6-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/irdma/verbs.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index e7120d7a5b4c6..ab73d1715f991 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -46,8 +46,11 @@ static int irdma_query_device(struct ib_device *ibdev, props->max_sge_rd = hw_attrs->uk_attrs.max_hw_read_sges; props->max_qp_rd_atom = hw_attrs->max_hw_ird; props->max_qp_init_rd_atom = hw_attrs->max_hw_ord; - if (rdma_protocol_roce(ibdev, 1)) + if (rdma_protocol_roce(ibdev, 1)) { + props->device_cap_flags |= IB_DEVICE_RC_RNR_NAK_GEN; props->max_pkeys = IRDMA_PKEY_TBL_SZ; + } + props->max_ah = rf->max_ah; props->max_mcast_grp = rf->max_mcg; props->max_mcast_qp_attach = IRDMA_MAX_MGS_PER_CTX;
From: Vladimir Oltean vladimir.oltean@nxp.com
[ Upstream commit 843794bbdef83955ae5b43dfafc355c3786e2145 ]
Experimentally, it looks like when QSYS_QMAXSDU_CFG_7 is set to 605, frames even way larger than 601 octets are transmitted even though these should be considered as oversized, according to the documentation, and dropped.
Since oversized frame dropping depends on frame size, which is only known at the EOF stage, and therefore not at SOF when cut-through forwarding begins, it means that the switch cannot take QSYS_QMAXSDU_CFG_* into consideration for traffic classes that are cut-through.
Since cut-through forwarding has no UAPI to control it, and the driver enables it based on the mantra "if we can, then why not", the strategy is to alter vsc9959_cut_through_fwd() to take into consideration which tc's have oversize frame dropping enabled, and disable cut-through for them. Then, from vsc9959_tas_guard_bands_update(), we re-trigger the cut-through determination process.
There are 2 strategies for vsc9959_cut_through_fwd() to determine whether a tc has oversized dropping enabled or not. One is to keep a bit mask of traffic classes per port, and the other is to read back from the hardware registers (a non-zero value of QSYS_QMAXSDU_CFG_* means the feature is enabled). We choose reading back from registers, because struct ocelot_port is shared with drivers (ocelot, seville) that don't support either cut-through nor tc-taprio, and we don't have a felix specific extension of struct ocelot_port. Furthermore, reading registers from the Felix hardware is quite cheap, since they are memory-mapped.
Fixes: 55a515b1f5a9 ("net: dsa: felix: drop oversized frames with tc-taprio instead of hanging the port") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/ocelot/felix_vsc9959.c | 122 ++++++++++++++++--------- 1 file changed, 79 insertions(+), 43 deletions(-)
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 6439b56f381f9..2a5822c619ef3 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1471,6 +1471,65 @@ static void vsc9959_tas_min_gate_lengths(struct tc_taprio_qopt_offload *taprio, min_gate_len[tc] = 0; }
+/* ocelot_write_rix is a macro that concatenates QSYS_MAXSDU_CFG_* with _RSZ, + * so we need to spell out the register access to each traffic class in helper + * functions, to simplify callers + */ +static void vsc9959_port_qmaxsdu_set(struct ocelot *ocelot, int port, int tc, + u32 max_sdu) +{ + switch (tc) { + case 0: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_0, + port); + break; + case 1: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_1, + port); + break; + case 2: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_2, + port); + break; + case 3: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_3, + port); + break; + case 4: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_4, + port); + break; + case 5: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_5, + port); + break; + case 6: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_6, + port); + break; + case 7: + ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_7, + port); + break; + } +} + +static u32 vsc9959_port_qmaxsdu_get(struct ocelot *ocelot, int port, int tc) +{ + switch (tc) { + case 0: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_0, port); + case 1: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_1, port); + case 2: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_2, port); + case 3: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_3, port); + case 4: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_4, port); + case 5: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_5, port); + case 6: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_6, port); + case 7: return ocelot_read_rix(ocelot, QSYS_QMAXSDU_CFG_7, port); + default: + return 0; + } +} + /* Update QSYS_PORT_MAX_SDU to make sure the static guard bands added by the * switch (see the ALWAYS_GUARD_BAND_SCH_Q comment) are correct at all MTU * values (the default value is 1518). Also, for traffic class windows smaller @@ -1527,6 +1586,8 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port)
vsc9959_tas_min_gate_lengths(ocelot_port->taprio, min_gate_len);
+ mutex_lock(&ocelot->fwd_domain_lock); + for (tc = 0; tc < OCELOT_NUM_TC; tc++) { u32 max_sdu;
@@ -1569,47 +1630,14 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) max_sdu); }
- /* ocelot_write_rix is a macro that concatenates - * QSYS_MAXSDU_CFG_* with _RSZ, so we need to spell out - * the writes to each traffic class - */ - switch (tc) { - case 0: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_0, - port); - break; - case 1: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_1, - port); - break; - case 2: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_2, - port); - break; - case 3: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_3, - port); - break; - case 4: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_4, - port); - break; - case 5: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_5, - port); - break; - case 6: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_6, - port); - break; - case 7: - ocelot_write_rix(ocelot, max_sdu, QSYS_QMAXSDU_CFG_7, - port); - break; - } + vsc9959_port_qmaxsdu_set(ocelot, port, tc, max_sdu); }
ocelot_write_rix(ocelot, maxlen, QSYS_PORT_MAX_SDU, port); + + ocelot->ops->cut_through_fwd(ocelot); + + mutex_unlock(&ocelot->fwd_domain_lock); }
static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, @@ -2709,7 +2737,7 @@ static void vsc9959_cut_through_fwd(struct ocelot *ocelot) { struct felix *felix = ocelot_to_felix(ocelot); struct dsa_switch *ds = felix->ds; - int port, other_port; + int tc, port, other_port;
lockdep_assert_held(&ocelot->fwd_domain_lock);
@@ -2753,19 +2781,27 @@ static void vsc9959_cut_through_fwd(struct ocelot *ocelot) min_speed = other_ocelot_port->speed; }
- /* Enable cut-through forwarding for all traffic classes. */ - if (ocelot_port->speed == min_speed) + /* Enable cut-through forwarding for all traffic classes that + * don't have oversized dropping enabled, since this check is + * bypassed in cut-through mode. + */ + if (ocelot_port->speed == min_speed) { val = GENMASK(7, 0);
+ for (tc = 0; tc < OCELOT_NUM_TC; tc++) + if (vsc9959_port_qmaxsdu_get(ocelot, port, tc)) + val &= ~BIT(tc); + } + set: tmp = ocelot_read_rix(ocelot, ANA_CUT_THRU_CFG, port); if (tmp == val) continue;
dev_dbg(ocelot->dev, - "port %d fwd mask 0x%lx speed %d min_speed %d, %s cut-through forwarding\n", + "port %d fwd mask 0x%lx speed %d min_speed %d, %s cut-through forwarding on TC mask 0x%x\n", port, mask, ocelot_port->speed, min_speed, - val ? "enabling" : "disabling"); + val ? "enabling" : "disabling", val);
ocelot_write_rix(ocelot, val, ANA_CUT_THRU_CFG, port); }
From: Vladimir Oltean vladimir.oltean@nxp.com
[ Upstream commit a4bb481aeb9d84cb53112a478e6db4705b794c34 ]
The read-modify-write of QSYS_TAG_CONFIG from vsc9959_sched_speed_set() runs unlocked with respect to the other functions that access it, which are vsc9959_tas_guard_bands_update(), vsc9959_qos_port_tas_set() and vsc9959_tas_clock_adjust(). All the others are under ocelot->tas_lock, so move the vsc9959_sched_speed_set() access under that lock as well, to resolve the concurrency.
Fixes: 55a515b1f5a9 ("net: dsa: felix: drop oversized frames with tc-taprio instead of hanging the port") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/ocelot/felix_vsc9959.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 2a5822c619ef3..f1767a6b9271c 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1664,13 +1664,13 @@ static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, break; }
+ mutex_lock(&ocelot->tas_lock); + ocelot_rmw_rix(ocelot, QSYS_TAG_CONFIG_LINK_SPEED(tas_speed), QSYS_TAG_CONFIG_LINK_SPEED_M, QSYS_TAG_CONFIG, port);
- mutex_lock(&ocelot->tas_lock); - if (ocelot_port->taprio) vsc9959_tas_guard_bands_update(ocelot, port);
From: Lorenzo Bianconi lorenzo@kernel.org
[ Upstream commit 0e80707d94e4c88f9879bdafcbaceb13432ec1f4 ]
Set ib1 state to MTK_FOE_STATE_UNBIND in __mtk_foe_entry_clear routine.
Fixes: 33fc42de33278 ("net: ethernet: mtk_eth_soc: support creating mac address based offload entries") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_ppe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index dab8f3f771f84..cfe804bc8d205 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -412,7 +412,7 @@ __mtk_foe_entry_clear(struct mtk_ppe *ppe, struct mtk_flow_entry *entry) if (entry->hash != 0xffff) { ppe->foe_table[entry->hash].ib1 &= ~MTK_FOE_IB1_STATE; ppe->foe_table[entry->hash].ib1 |= FIELD_PREP(MTK_FOE_IB1_STATE, - MTK_FOE_STATE_BIND); + MTK_FOE_STATE_UNBIND); dma_wmb(); } entry->hash = 0xffff;
From: Lorenzo Bianconi lorenzo@kernel.org
[ Upstream commit f27b405ef43319a3ceefc2123245201a63ed4e00 ]
Even if max hash configured in hw in mtk_ppe_hash_entry is MTK_PPE_ENTRIES - 1, check theoretical OOB accesses in mtk_ppe_check_skb routine
Fixes: c4f033d9e03e9 ("net: ethernet: mtk_eth_soc: rework hardware flow table management") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_ppe.h | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index 1f5cf1c9a9475..69ffce04d6306 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -293,6 +293,9 @@ mtk_ppe_check_skb(struct mtk_ppe *ppe, struct sk_buff *skb, u16 hash) if (!ppe) return;
+ if (hash > MTK_PPE_HASH_MASK) + return; + now = (u16)jiffies; diff = now - ppe->foe_check_time[hash]; if (diff < HZ / 10)
From: Yacan Liu liuyacan@corp.netease.com
[ Upstream commit e9b1a4f867ae9c1dbd1d71cd09cbdb3239fb4968 ]
After modifying the QP to the Error state, all RX WR would be completed with WC in IB_WC_WR_FLUSH_ERR status. Current implementation does not wait for it is done, but destroy the QP and free the link group directly. So there is a risk that accessing the freed memory in tasklet context.
Here is a crash example:
BUG: unable to handle page fault for address: ffffffff8f220860 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD f7300e067 P4D f7300e067 PUD f7300f063 PMD 8c4e45063 PTE 800ffff08c9df060 Oops: 0002 [#1] SMP PTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: G S OE 5.10.0-0607+ #23 Hardware name: Inspur NF5280M4/YZMB-00689-101, BIOS 4.1.20 07/09/2018 RIP: 0010:native_queued_spin_lock_slowpath+0x176/0x1b0 Code: f3 90 48 8b 32 48 85 f6 74 f6 eb d5 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 00 c8 02 00 48 03 04 f5 00 09 98 8e <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32 RSP: 0018:ffffb3b6c001ebd8 EFLAGS: 00010086 RAX: ffffffff8f220860 RBX: 0000000000000246 RCX: 0000000000080000 RDX: ffff91db1f86c800 RSI: 000000000000173c RDI: ffff91db62bace00 RBP: ffff91db62bacc00 R08: 0000000000000000 R09: c00000010000028b R10: 0000000000055198 R11: ffffb3b6c001ea58 R12: ffff91db80e05010 R13: 000000000000000a R14: 0000000000000006 R15: 0000000000000040 FS: 0000000000000000(0000) GS:ffff91db1f840000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff8f220860 CR3: 00000001f9580004 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> _raw_spin_lock_irqsave+0x30/0x40 mlx5_ib_poll_cq+0x4c/0xc50 [mlx5_ib] smc_wr_rx_tasklet_fn+0x56/0xa0 [smc] tasklet_action_common.isra.21+0x66/0x100 __do_softirq+0xd5/0x29c asm_call_irq_on_stack+0x12/0x20 </IRQ> do_softirq_own_stack+0x37/0x40 irq_exit_rcu+0x9d/0xa0 sysvec_call_function_single+0x34/0x80 asm_sysvec_call_function_single+0x12/0x20
Fixes: bd4ad57718cc ("smc: initialize IB transport incl. PD, MR, QP, CQ, event, WR") Signed-off-by: Yacan Liu liuyacan@corp.netease.com Reviewed-by: Tony Lu tonylu@linux.alibaba.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/smc/smc_core.c | 1 + net/smc/smc_core.h | 2 ++ net/smc/smc_wr.c | 5 +++++ net/smc/smc_wr.h | 5 +++++ 4 files changed, 13 insertions(+)
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f40f6ed0fbdb4..1f3bb1f6b1f7b 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -755,6 +755,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, lnk->lgr = lgr; smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */ lnk->link_idx = link_idx; + lnk->wr_rx_id_compl = 0; smc_ibdev_cnt_inc(lnk); smcr_copy_dev_info_to_link(lnk); atomic_set(&lnk->conn_cnt, 0); diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 4cb03e9423648..7b43a78c7f73a 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -115,8 +115,10 @@ struct smc_link { dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/ u64 wr_rx_id; /* seq # of last recv WR */ + u64 wr_rx_id_compl; /* seq # of last completed WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ + wait_queue_head_t wr_rx_empty_wait; /* wait for RQ empty */
struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 26f8f240d9e84..b0678a417e09d 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -454,6 +454,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
for (i = 0; i < num; i++) { link = wc[i].qp->qp_context; + link->wr_rx_id_compl = wc[i].wr_id; if (wc[i].status == IB_WC_SUCCESS) { link->wr_rx_tstamp = jiffies; smc_wr_rx_demultiplex(&wc[i]); @@ -465,6 +466,8 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num) case IB_WC_RNR_RETRY_EXC_ERR: case IB_WC_WR_FLUSH_ERR: smcr_link_down_cond_sched(link); + if (link->wr_rx_id_compl == link->wr_rx_id) + wake_up(&link->wr_rx_empty_wait); break; default: smc_wr_rx_post(link); /* refill WR RX */ @@ -639,6 +642,7 @@ void smc_wr_free_link(struct smc_link *lnk) return; ibdev = lnk->smcibdev->ibdev;
+ smc_wr_drain_cq(lnk); smc_wr_wakeup_reg_wait(lnk); smc_wr_wakeup_tx_wait(lnk);
@@ -889,6 +893,7 @@ int smc_wr_create_link(struct smc_link *lnk) atomic_set(&lnk->wr_tx_refcnt, 0); init_waitqueue_head(&lnk->wr_reg_wait); atomic_set(&lnk->wr_reg_refcnt, 0); + init_waitqueue_head(&lnk->wr_rx_empty_wait); return rc;
dma_unmap: diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index a54e90a1110fd..45e9b894d3f8a 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -73,6 +73,11 @@ static inline void smc_wr_tx_link_put(struct smc_link *link) wake_up_all(&link->wr_tx_wait); }
+static inline void smc_wr_drain_cq(struct smc_link *lnk) +{ + wait_event(lnk->wr_rx_empty_wait, lnk->wr_rx_id_compl == lnk->wr_rx_id); +} + static inline void smc_wr_wakeup_tx_wait(struct smc_link *lnk) { wake_up_all(&lnk->wr_tx_wait);
From: Pavel Begunkov asml.silence@gmail.com
[ Upstream commit 336d28a8f38013a069f2d46e73aaa1880ef17a47 ]
When we queue a request via tw for execution it's not going to be executed immediately, so when io_queue_async() hits IO_APOLL_READY and queues a tw but doesn't try to recycle/consume the buffer some other request may try to use the the buffer.
Fixes: c7fb19428d67 ("io_uring: add support for ring mapped supplied buffers") Signed-off-by: Pavel Begunkov asml.silence@gmail.com Link: https://lore.kernel.org/r/a19bc9e211e3184215a58e129b62f440180e9212.166248049... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- io_uring/io_uring.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index cd155b7e1346d..effe3570a051f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -8260,6 +8260,7 @@ static void io_queue_async(struct io_kiocb *req, int ret)
switch (io_arm_poll_handler(req, 0)) { case IO_APOLL_READY: + io_kbuf_recycle(req, 0); io_req_task_queue(req); break; case IO_APOLL_ABORTED:
From: Arun Ramadoss arun.ramadoss@microchip.com
[ Upstream commit 5382033a35227c57a349d74752ad2527780159a9 ]
Currently phy link up/down interrupt is enabled using the LAN87xx_INTERRUPT_MASK register. In the lan87xx_read_status function, phy link is determined using the T1_MODE_STAT_REG register comm_ready bit. comm_ready bit is set using the loc_rcvr_status & rem_rcvr_status. Whenever the phy link is up, LAN87xx_INTERRUPT_SOURCE link_up bit is set first but comm_ready bit takes some time to set based on local and remote receiver status. As per the current implementation, interrupt is triggered using link_up but the comm_ready bit is still cleared in the read_status function. So, link is always down. Initially tested with the shared interrupt mechanism with switch and internal phy which is working, but after implementing interrupt controller it is not working. It can fixed either by updating the read_status function to read from LAN87XX_INTERRUPT_SOURCE register or enable the interrupt mask for comm_ready bit. But the validation team recommends the use of comm_ready for link detection. This patch fixes by enabling the comm_ready bit for link_up in the LAN87XX_INTERRUPT_MASK_2 register (MISC Bank) and link_down in LAN87xx_INTERRUPT_MASK register.
Fixes: 8a1b415d70b7 ("net: phy: added ethtool master-slave configuration support") Signed-off-by: Arun Ramadoss arun.ramadoss@microchip.com Reviewed-by: Andrew Lunn andrew@lunn.ch Link: https://lore.kernel.org/r/20220905152750.5079-1-arun.ramadoss@microchip.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/microchip_t1.c | 58 +++++++++++++++++++++++++++++++--- 1 file changed, 54 insertions(+), 4 deletions(-)
diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index d4c93d59bc539..8569a545e0a3f 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -28,12 +28,16 @@
/* Interrupt Source Register */ #define LAN87XX_INTERRUPT_SOURCE (0x18) +#define LAN87XX_INTERRUPT_SOURCE_2 (0x08)
/* Interrupt Mask Register */ #define LAN87XX_INTERRUPT_MASK (0x19) #define LAN87XX_MASK_LINK_UP (0x0004) #define LAN87XX_MASK_LINK_DOWN (0x0002)
+#define LAN87XX_INTERRUPT_MASK_2 (0x09) +#define LAN87XX_MASK_COMM_RDY BIT(10) + /* MISC Control 1 Register */ #define LAN87XX_CTRL_1 (0x11) #define LAN87XX_MASK_RGMII_TXC_DLY_EN (0x4000) @@ -424,17 +428,55 @@ static int lan87xx_phy_config_intr(struct phy_device *phydev) int rc, val = 0;
if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { - /* unmask all source and clear them before enable */ - rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, 0x7FFF); + /* clear all interrupt */ + rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val); + if (rc < 0) + return rc; + rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE); - val = LAN87XX_MASK_LINK_UP | LAN87XX_MASK_LINK_DOWN; + if (rc < 0) + return rc; + + rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE, + PHYACC_ATTR_BANK_MISC, + LAN87XX_INTERRUPT_MASK_2, val); + if (rc < 0) + return rc; + + rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ, + PHYACC_ATTR_BANK_MISC, + LAN87XX_INTERRUPT_SOURCE_2, 0); + if (rc < 0) + return rc; + + /* enable link down and comm ready interrupt */ + val = LAN87XX_MASK_LINK_DOWN; rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val); + if (rc < 0) + return rc; + + val = LAN87XX_MASK_COMM_RDY; + rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE, + PHYACC_ATTR_BANK_MISC, + LAN87XX_INTERRUPT_MASK_2, val); } else { rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val); - if (rc) + if (rc < 0) return rc;
rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE); + if (rc < 0) + return rc; + + rc = access_ereg(phydev, PHYACC_ATTR_MODE_WRITE, + PHYACC_ATTR_BANK_MISC, + LAN87XX_INTERRUPT_MASK_2, val); + if (rc < 0) + return rc; + + rc = access_ereg(phydev, PHYACC_ATTR_MODE_READ, + PHYACC_ATTR_BANK_MISC, + LAN87XX_INTERRUPT_SOURCE_2, 0); }
return rc < 0 ? rc : 0; @@ -444,6 +486,14 @@ static irqreturn_t lan87xx_handle_interrupt(struct phy_device *phydev) { int irq_status;
+ irq_status = access_ereg(phydev, PHYACC_ATTR_MODE_READ, + PHYACC_ATTR_BANK_MISC, + LAN87XX_INTERRUPT_SOURCE_2, 0); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + irq_status = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE); if (irq_status < 0) { phy_error(phydev);
From: Toke Høiland-Jørgensen toke@toke.dk
[ Upstream commit 2f09707d0c972120bf794cfe0f0c67e2c2ddb252 ]
Cong Wang noticed that the previous fix for sch_sfb accessing the queued skb after enqueueing it to a child qdisc was incomplete: the SFB enqueue function was also calling qdisc_qstats_backlog_inc() after enqueue, which reads the pkt len from the skb cb field. Fix this by also storing the skb len, and using the stored value to increment the backlog after enqueueing.
Fixes: 9efd23297cca ("sch_sfb: Don't assume the skb is still around after enqueueing to child") Signed-off-by: Toke Høiland-Jørgensen toke@toke.dk Acked-by: Cong Wang cong.wang@bytedance.com Link: https://lore.kernel.org/r/20220905192137.965549-1-toke@toke.dk Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_sfb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0d761f454ae8b..2829455211f8c 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -281,6 +281,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, {
struct sfb_sched_data *q = qdisc_priv(sch); + unsigned int len = qdisc_pkt_len(skb); struct Qdisc *child = q->qdisc; struct tcf_proto *fl; struct sfb_skb_cb cb; @@ -403,7 +404,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, memcpy(&cb, sfb_skb_cb(skb), sizeof(cb)); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; increment_qlen(&cb, q); } else if (net_xmit_drop_count(ret)) {
From: Adrian Hunter adrian.hunter@intel.com
[ Upstream commit 7864d8f7c088aad988c44c631f1ceed9179cf2cf ]
The offending commit removed mmap_per_thread(), which did not consider the different set-output rules for per-thread mmaps i.e. in the per-thread case set-output is used for file descriptors of the same thread not the same cpu.
This was not immediately noticed because it only happens with multi-threaded targets and we do not have a test for that yet.
Reinstate mmap_per_thread() expanding it to cover also system-wide per-cpu events i.e. to continue to allow the mixing of per-thread and per-cpu mmaps.
Debug messages (with -vv) show the file descriptors that are opened with sys_perf_event_open. New debug messages are added (needs -vvv) that show also which file descriptors are mmapped and which are redirected with set-output.
In the per-cpu case (cpu != -1) file descriptors for the same CPU are set-output to the first file descriptor for that CPU.
In the per-thread case (cpu == -1) file descriptors for the same thread are set-output to the first file descriptor for that thread.
Example (process 17489 has 2 threads):
Before (but with new debug prints):
$ perf record --no-bpf-event -vvv --per-thread -p 17489 <SNIP> sys_perf_event_open: pid 17489 cpu -1 group_fd -1 flags 0x8 = 5 sys_perf_event_open: pid 17490 cpu -1 group_fd -1 flags 0x8 = 6 <SNIP> libperf: idx 0: mmapping fd 5 libperf: idx 0: set output fd 6 -> 5 failed to mmap with 22 (Invalid argument)
After:
$ perf record --no-bpf-event -vvv --per-thread -p 17489 <SNIP> sys_perf_event_open: pid 17489 cpu -1 group_fd -1 flags 0x8 = 5 sys_perf_event_open: pid 17490 cpu -1 group_fd -1 flags 0x8 = 6 <SNIP> libperf: mmap_per_thread: nr cpu values (may include -1) 1 nr threads 2 libperf: idx 0: mmapping fd 5 libperf: idx 1: mmapping fd 6 <SNIP> [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.018 MB perf.data (15 samples) ]
Per-cpu example (process 20341 has 2 threads, same as above):
$ perf record --no-bpf-event -vvv -p 20341 <SNIP> sys_perf_event_open: pid 20341 cpu 0 group_fd -1 flags 0x8 = 5 sys_perf_event_open: pid 20342 cpu 0 group_fd -1 flags 0x8 = 6 sys_perf_event_open: pid 20341 cpu 1 group_fd -1 flags 0x8 = 7 sys_perf_event_open: pid 20342 cpu 1 group_fd -1 flags 0x8 = 8 sys_perf_event_open: pid 20341 cpu 2 group_fd -1 flags 0x8 = 9 sys_perf_event_open: pid 20342 cpu 2 group_fd -1 flags 0x8 = 10 sys_perf_event_open: pid 20341 cpu 3 group_fd -1 flags 0x8 = 11 sys_perf_event_open: pid 20342 cpu 3 group_fd -1 flags 0x8 = 12 sys_perf_event_open: pid 20341 cpu 4 group_fd -1 flags 0x8 = 13 sys_perf_event_open: pid 20342 cpu 4 group_fd -1 flags 0x8 = 14 sys_perf_event_open: pid 20341 cpu 5 group_fd -1 flags 0x8 = 15 sys_perf_event_open: pid 20342 cpu 5 group_fd -1 flags 0x8 = 16 sys_perf_event_open: pid 20341 cpu 6 group_fd -1 flags 0x8 = 17 sys_perf_event_open: pid 20342 cpu 6 group_fd -1 flags 0x8 = 18 sys_perf_event_open: pid 20341 cpu 7 group_fd -1 flags 0x8 = 19 sys_perf_event_open: pid 20342 cpu 7 group_fd -1 flags 0x8 = 20 <SNIP> libperf: mmap_per_cpu: nr cpu values 8 nr threads 2 libperf: idx 0: mmapping fd 5 libperf: idx 0: set output fd 6 -> 5 libperf: idx 1: mmapping fd 7 libperf: idx 1: set output fd 8 -> 7 libperf: idx 2: mmapping fd 9 libperf: idx 2: set output fd 10 -> 9 libperf: idx 3: mmapping fd 11 libperf: idx 3: set output fd 12 -> 11 libperf: idx 4: mmapping fd 13 libperf: idx 4: set output fd 14 -> 13 libperf: idx 5: mmapping fd 15 libperf: idx 5: set output fd 16 -> 15 libperf: idx 6: mmapping fd 17 libperf: idx 6: set output fd 18 -> 17 libperf: idx 7: mmapping fd 19 libperf: idx 7: set output fd 20 -> 19 <SNIP> [ perf record: Woken up 7 times to write data ] [ perf record: Captured and wrote 0.020 MB perf.data (17 samples) ]
Fixes: ae4f8ae16a078964 ("libperf evlist: Allow mixing per-thread and per-cpu mmaps") Reported-by: Tomáš Trnka trnka@scm.com Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=216441 Signed-off-by: Adrian Hunter adrian.hunter@intel.com Acked-by: Jiri Olsa jolsa@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Ian Rogers irogers@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/r/20220905114209.8389-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/lib/perf/evlist.c | 50 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+)
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index e6c98a6e3908e..6b1bafe267a42 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -486,6 +486,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, if (ops->idx) ops->idx(evlist, evsel, mp, idx);
+ pr_debug("idx %d: mmapping fd %d\n", idx, *output); if (ops->mmap(map, mp, *output, evlist_cpu) < 0) return -1;
@@ -494,6 +495,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, if (!idx) perf_evlist__set_mmap_first(evlist, map, overwrite); } else { + pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output); if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) return -1;
@@ -519,6 +521,48 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, return 0; }
+static int +mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, + struct perf_mmap_param *mp) +{ + int nr_threads = perf_thread_map__nr(evlist->threads); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); + int cpu, thread, idx = 0; + int nr_mmaps = 0; + + pr_debug("%s: nr cpu values (may include -1) %d nr threads %d\n", + __func__, nr_cpus, nr_threads); + + /* per-thread mmaps */ + for (thread = 0; thread < nr_threads; thread++, idx++) { + int output = -1; + int output_overwrite = -1; + + if (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output, + &output_overwrite, &nr_mmaps)) + goto out_unmap; + } + + /* system-wide mmaps i.e. per-cpu */ + for (cpu = 1; cpu < nr_cpus; cpu++, idx++) { + int output = -1; + int output_overwrite = -1; + + if (mmap_per_evsel(evlist, ops, idx, mp, cpu, 0, &output, + &output_overwrite, &nr_mmaps)) + goto out_unmap; + } + + if (nr_mmaps != evlist->nr_mmaps) + pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps); + + return 0; + +out_unmap: + perf_evlist__munmap(evlist); + return -1; +} + static int mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) @@ -528,6 +572,8 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, int nr_mmaps = 0; int cpu, thread;
+ pr_debug("%s: nr cpu values %d nr threads %d\n", __func__, nr_cpus, nr_threads); + for (cpu = 0; cpu < nr_cpus; cpu++) { int output = -1; int output_overwrite = -1; @@ -569,6 +615,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) { + const struct perf_cpu_map *cpus = evlist->all_cpus; struct perf_evsel *evsel;
if (!ops || !ops->get || !ops->mmap) @@ -588,6 +635,9 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) return -ENOMEM;
+ if (perf_cpu_map__empty(cpus)) + return mmap_per_thread(evlist, ops, mp); + return mmap_per_cpu(evlist, ops, mp); }
From: Adrian Hunter adrian.hunter@intel.com
[ Upstream commit 1706623e940347ad23fdf77910eca4905dc37f91 ]
Avoid compiler warning about format %llu that expects long long unsigned int but argument has type __u64.
Reported-by: Arnaldo Carvalho de Melo acme@redhat.com Fixes: c3afd6e50fce824f ("perf dlfilter: Add dlfilter-show-cycles") Signed-off-by: Adrian Hunter adrian.hunter@intel.com Cc: Adrian Hunter adrian.hunter@intel.com Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Link: https://lore.kernel.org/r/20220905074735.4513-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/dlfilters/dlfilter-show-cycles.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/perf/dlfilters/dlfilter-show-cycles.c b/tools/perf/dlfilters/dlfilter-show-cycles.c index 9eccc97bff82f..6d47298ebe9f6 100644 --- a/tools/perf/dlfilters/dlfilter-show-cycles.c +++ b/tools/perf/dlfilters/dlfilter-show-cycles.c @@ -98,9 +98,9 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo static void print_vals(__u64 cycles, __u64 delta) { if (delta) - printf("%10llu %10llu ", cycles, delta); + printf("%10llu %10llu ", (unsigned long long)cycles, (unsigned long long)delta); else - printf("%10llu %10s ", cycles, ""); + printf("%10llu %10s ", (unsigned long long)cycles, ""); }
int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
From: Zhengjun Xing zhengjun.xing@linux.intel.com
[ Upstream commit 82b2425fad2dd47204b3da589b679220f8aacc0e ]
Commit b91e5492f9d7ca89 ("perf record: Add a dummy event on hybrid systems to collect metadata records") adds a dummy event on hybrid systems to fix the symbol "unknown" issue when the workload is created in a P-core but runs on an E-core. The added dummy event will cause "perf script -F iregs" to fail. Dummy events do not have "iregs" attribute set, so when we do evsel__check_attr, the "iregs" attribute check will fail, so the issue happened.
The following commit [1] has fixed a similar issue by skipping the attr check for the dummy event because it does not have any samples anyway. It works okay for the normal mode, but the issue still happened when running the test in the pipe mode. In the pipe mode, it calls process_attr() which still checks the attr for the dummy event. This commit fixed the issue by skipping the attr check for the dummy event in the API evsel__check_attr, Otherwise, we have to patch everywhere when evsel__check_attr() is called.
Before:
#./perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p -c 1000 --per-thread true 2>/dev/null|./perf script -F iregs |head -5 Samples for 'dummy:HG' event do not have IREGS attribute set. Cannot print 'iregs' field. 0x120 [0x90]: failed to process type: 64 #
After:
# ./perf record -o - --intr-regs=di,r8,dx,cx -e br_inst_retired.near_call:p -c 1000 --per-thread true 2>/dev/null|./perf script -F iregs |head -5 ABI:2 CX:0x55b8efa87000 DX:0x55b8efa7e000 DI:0xffffba5e625efbb0 R8:0xffff90e51f8ae100 ABI:2 CX:0x7f1dae1e4000 DX:0xd0 DI:0xffff90e18c675ac0 R8:0x71 ABI:2 CX:0xcc0 DX:0x1 DI:0xffff90e199880240 R8:0x0 ABI:2 CX:0xffff90e180dd7500 DX:0xffff90e180dd7500 DI:0xffff90e180043500 R8:0x1 ABI:2 CX:0x50 DX:0xffff90e18c583bd0 DI:0xffff90e1998803c0 R8:0x58 #
[1]https://lore.kernel.org/lkml/20220831124041.219925-1-jolsa@kernel.org/
Fixes: b91e5492f9d7ca89 ("perf record: Add a dummy event on hybrid systems to collect metadata records") Suggested-by: Namhyung Kim namhyung@kernel.org Signed-off-by: Xing Zhengjun zhengjun.xing@linux.intel.com Acked-by: Jiri Olsa jolsa@kernel.org Cc: Alexander Shishkin alexander.shishkin@intel.com Cc: Andi Kleen ak@linux.intel.com Cc: Ian Rogers irogers@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Kan Liang kan.liang@linux.intel.com Cc: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/r/20220908070030.3455164-1-zhengjun.xing@linux.intel... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-script.c | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index c689054002cca..26a572c160d6f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -441,6 +441,9 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) struct perf_event_attr *attr = &evsel->core.attr; bool allow_user_set;
+ if (evsel__is_dummy_event(evsel)) + return 0; + if (perf_header__has_feat(&session->header, HEADER_STAT)) return 0;
From: Adrian Hunter adrian.hunter@intel.com
[ Upstream commit faf59ec8c3c3708c64ff76b50e6f757c6b4a1054 ]
Some calls to synthesis functions set err < 0 but only warn about the failure and continue. However they do not set err back to zero, relying on subsequent code to do that.
That changed with the introduction of option --synth. When --synth=no subsequent functions that set err back to zero are not called.
Fix by setting err = 0 in those cases.
Example:
Before:
$ perf record --no-bpf-event --synth=all -o /tmp/huh uname Couldn't synthesize bpf events. Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB /tmp/huh (7 samples) ] $ perf record --no-bpf-event --synth=no -o /tmp/huh uname Couldn't synthesize bpf events.
After:
$ perf record --no-bpf-event --synth=no -o /tmp/huh uname Couldn't synthesize bpf events. Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.014 MB /tmp/huh (7 samples) ]
Fixes: 41b740b6e8a994e5 ("perf record: Add --synth option") Signed-off-by: Adrian Hunter adrian.hunter@intel.com Acked-by: Namhyung Kim namhyung@kernel.org Cc: Ian Rogers irogers@google.com Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Link: https://lore.kernel.org/r/20220907162458.72817-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-record.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 9a71f0330137e..68c878b4e5e4c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1892,14 +1892,18 @@ static int record__synthesize(struct record *rec, bool tail)
err = perf_event__synthesize_bpf_events(session, process_synthesized_event, machine, opts); - if (err < 0) + if (err < 0) { pr_warning("Couldn't synthesize bpf events.\n"); + err = 0; + }
if (rec->opts.synth & PERF_SYNTH_CGROUP) { err = perf_event__synthesize_cgroups(tool, process_synthesized_event, machine); - if (err < 0) + if (err < 0) { pr_warning("Couldn't synthesize cgroup events.\n"); + err = 0; + } }
if (rec->opts.nr_threads_synthesize > 1) {
From: Alexandru Gagniuc mr.nuke.me@gmail.com
commit 1f05f65bddd6958d25b133f886da49c1d4bff3fa upstream.
The tps23861 registers are little-endian, and regmap_read_bulk() does not do byte order conversion. On BE machines, the bytes were swapped, and the interpretation of the resistance value was incorrect.
To make it work on both big and little-endian machines, use le16_to_cpu() to convert the resitance register to host byte order.
Signed-off-by: Alexandru Gagniuc mr.nuke.me@gmail.com Fixes: fff7b8ab22554 ("hwmon: add Texas Instruments TPS23861 driver") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220905142806.110598-1-mr.nuke.me@gmail.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hwmon/tps23861.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
--- a/drivers/hwmon/tps23861.c +++ b/drivers/hwmon/tps23861.c @@ -489,18 +489,20 @@ static char *tps23861_port_poe_plus_stat
static int tps23861_port_resistance(struct tps23861_data *data, int port) { - u16 regval; + unsigned int raw_val; + __le16 regval;
regmap_bulk_read(data->regmap, PORT_1_RESISTANCE_LSB + PORT_N_RESISTANCE_LSB_OFFSET * (port - 1), ®val, 2);
- switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, regval)) { + raw_val = le16_to_cpu(regval); + switch (FIELD_GET(PORT_RESISTANCE_RSN_MASK, raw_val)) { case PORT_RESISTANCE_RSN_OTHER: - return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB) / 10000; + return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB) / 10000; case PORT_RESISTANCE_RSN_LOW: - return (FIELD_GET(PORT_RESISTANCE_MASK, regval) * RESISTANCE_LSB_LOW) / 10000; + return (FIELD_GET(PORT_RESISTANCE_MASK, raw_val) * RESISTANCE_LSB_LOW) / 10000; case PORT_RESISTANCE_RSN_SHORT: case PORT_RESISTANCE_RSN_OPEN: default:
From: Claudiu Beznea claudiu.beznea@microchip.com
commit 403fcb5118a0f4091001a537e76923031fb45eaf upstream.
Remove references to struct mchp_i2s_caps as they are not used.
Signed-off-by: Claudiu Beznea claudiu.beznea@microchip.com Link: https://lore.kernel.org/r/20220727090814.2446111-3-claudiu.beznea@microchip.... Signed-off-by: Mark Brown broonie@kernel.org Cc: Nathan Chancellor nathan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/atmel/mchp-spdiftx.c | 8 -------- 1 file changed, 8 deletions(-)
--- a/sound/soc/atmel/mchp-spdiftx.c +++ b/sound/soc/atmel/mchp-spdiftx.c @@ -196,7 +196,6 @@ struct mchp_spdiftx_dev { struct clk *pclk; struct clk *gclk; unsigned int fmt; - const struct mchp_i2s_caps *caps; int gclk_enabled:1; };
@@ -766,8 +765,6 @@ static const struct of_device_id mchp_sp MODULE_DEVICE_TABLE(of, mchp_spdiftx_dt_ids); static int mchp_spdiftx_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; - const struct of_device_id *match; struct mchp_spdiftx_dev *dev; struct resource *mem; struct regmap *regmap; @@ -781,11 +778,6 @@ static int mchp_spdiftx_probe(struct pla if (!dev) return -ENOMEM;
- /* Get hardware capabilities. */ - match = of_match_node(mchp_spdiftx_dt_ids, np); - if (match) - dev->caps = match->data; - /* Map I/O registers. */ base = devm_platform_get_and_ioremap_resource(pdev, 0, &mem); if (IS_ERR(base))
From: Nathan Chancellor nathan@kernel.org
commit 5c5c2baad2b55cc0a4b190266889959642298f79 upstream.
A recent change in clang strengthened its -Wbitfield-constant-conversion to warn when 1 is assigned to a 1-bit signed integer bitfield, as it can only be 0 or -1, not 1:
sound/soc/atmel/mchp-spdiftx.c:505:20: error: implicit truncation from 'int' to bit-field changes value from 1 to -1 [-Werror,-Wbitfield-constant-conversion] dev->gclk_enabled = 1; ^ ~ 1 error generated.
The actual value of the field is never checked, just that it is not zero, so there is not a real bug here. However, it is simple enough to silence the warning by making the bitfield unsigned, which matches the mchp-spdifrx driver.
Fixes: 06ca24e98e6b ("ASoC: mchp-spdiftx: add driver for S/PDIF TX Controller") Link: https://github.com/ClangBuiltLinux/linux/issues/1686 Link: https://github.com/llvm/llvm-project/commit/82afc9b169a67e8b8a1862fb9c41a2cd... Signed-off-by: Nathan Chancellor nathan@kernel.org Reviewed-by: Nick Desaulniers ndesaulniers@google.com Link: https://lore.kernel.org/r/20220810010809.2024482-1-nathan@kernel.org Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/atmel/mchp-spdiftx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- a/sound/soc/atmel/mchp-spdiftx.c +++ b/sound/soc/atmel/mchp-spdiftx.c @@ -196,7 +196,7 @@ struct mchp_spdiftx_dev { struct clk *pclk; struct clk *gclk; unsigned int fmt; - int gclk_enabled:1; + unsigned int gclk_enabled:1; };
static inline int mchp_spdiftx_is_running(struct mchp_spdiftx_dev *dev)
From: Luis Chamberlain mcgrof@kernel.org
commit 2a5840124009f133bd09fd855963551fb2cefe22 upstream.
io-uring cmd support was added through ee692a21e9bf ("fs,io_uring: add infrastructure for uring-cmd"), this extended the struct file_operations to allow a new command which each subsystem can use to enable command passthrough. Add an LSM specific for the command passthrough which enables LSMs to inspect the command details.
This was discussed long ago without no clear pointer for something conclusive, so this enables LSMs to at least reject this new file operation.
[0] https://lkml.kernel.org/r/8adf55db-7bab-f59d-d612-ed906b948d19@schaufler-ca....
Cc: stable@vger.kernel.org Fixes: ee692a21e9bf ("fs,io_uring: add infrastructure for uring-cmd") Signed-off-by: Luis Chamberlain mcgrof@kernel.org Acked-by: Jens Axboe axboe@kernel.dk Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/lsm_hook_defs.h | 1 + include/linux/lsm_hooks.h | 3 +++ include/linux/security.h | 5 +++++ io_uring/io_uring.c | 4 ++++ security/security.c | 4 ++++ 5 files changed, 17 insertions(+)
--- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -406,4 +406,5 @@ LSM_HOOK(int, 0, perf_event_write, struc #ifdef CONFIG_IO_URING LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) LSM_HOOK(int, 0, uring_sqpoll, void) +LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd) #endif /* CONFIG_IO_URING */ --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1575,6 +1575,9 @@ * Check whether the current task is allowed to spawn a io_uring polling * thread (IORING_SETUP_SQPOLL). * + * @uring_cmd: + * Check whether the file_operations uring_cmd is allowed to run. + * */ union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2051,6 +2051,7 @@ static inline int security_perf_event_wr #ifdef CONFIG_SECURITY extern int security_uring_override_creds(const struct cred *new); extern int security_uring_sqpoll(void); +extern int security_uring_cmd(struct io_uring_cmd *ioucmd); #else static inline int security_uring_override_creds(const struct cred *new) { @@ -2060,6 +2061,10 @@ static inline int security_uring_sqpoll( { return 0; } +static inline int security_uring_cmd(struct io_uring_cmd *ioucmd) +{ + return 0; +} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_IO_URING */
--- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -4878,6 +4878,10 @@ static int io_uring_cmd(struct io_kiocb if (!req->file->f_op->uring_cmd) return -EOPNOTSUPP;
+ ret = security_uring_cmd(ioucmd); + if (ret) + return ret; + if (ctx->flags & IORING_SETUP_SQE128) issue_flags |= IO_URING_F_SQE128; if (ctx->flags & IORING_SETUP_CQE32) --- a/security/security.c +++ b/security/security.c @@ -2654,4 +2654,8 @@ int security_uring_sqpoll(void) { return call_int_hook(uring_sqpoll, 0); } +int security_uring_cmd(struct io_uring_cmd *ioucmd) +{ + return call_int_hook(uring_cmd, 0, ioucmd); +} #endif /* CONFIG_IO_URING */
From: Paul Moore paul@paul-moore.com
commit f4d653dcaa4e4056e1630423e6a8ece4869b544f upstream.
Add a SELinux access control for the iouring IORING_OP_URING_CMD command. This includes the addition of a new permission in the existing "io_uring" object class: "cmd". The subject of the new permission check is the domain of the process requesting access, the object is the open file which points to the device/file that is the target of the IORING_OP_URING_CMD operation. A sample policy rule is shown below:
allow <domain> <file>:io_uring { cmd };
Cc: stable@vger.kernel.org Fixes: ee692a21e9bf ("fs,io_uring: add infrastructure for uring-cmd") Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/selinux/hooks.c | 24 ++++++++++++++++++++++++ security/selinux/include/classmap.h | 2 +- 2 files changed, 25 insertions(+), 1 deletion(-)
--- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -91,6 +91,7 @@ #include <uapi/linux/mount.h> #include <linux/fsnotify.h> #include <linux/fanotify.h> +#include <linux/io_uring.h>
#include "avc.h" #include "objsec.h" @@ -6990,6 +6991,28 @@ static int selinux_uring_sqpoll(void) return avc_has_perm(&selinux_state, sid, sid, SECCLASS_IO_URING, IO_URING__SQPOLL, NULL); } + +/** + * selinux_uring_cmd - check if IORING_OP_URING_CMD is allowed + * @ioucmd: the io_uring command structure + * + * Check to see if the current domain is allowed to execute an + * IORING_OP_URING_CMD against the device/file specified in @ioucmd. + * + */ +static int selinux_uring_cmd(struct io_uring_cmd *ioucmd) +{ + struct file *file = ioucmd->file; + struct inode *inode = file_inode(file); + struct inode_security_struct *isec = selinux_inode(inode); + struct common_audit_data ad; + + ad.type = LSM_AUDIT_DATA_FILE; + ad.u.file = file; + + return avc_has_perm(&selinux_state, current_sid(), isec->sid, + SECCLASS_IO_URING, IO_URING__CMD, &ad); +} #endif /* CONFIG_IO_URING */
/* @@ -7234,6 +7257,7 @@ static struct security_hook_list selinux #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, selinux_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, selinux_uring_sqpoll), + LSM_HOOK_INIT(uring_cmd, selinux_uring_cmd), #endif
/* --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -253,7 +253,7 @@ const struct security_class_mapping secc { "anon_inode", { COMMON_FILE_PERMS, NULL } }, { "io_uring", - { "override_creds", "sqpoll", NULL } }, + { "override_creds", "sqpoll", "cmd", NULL } }, { NULL } };
From: Casey Schaufler casey@schaufler-ca.com
commit dd9373402280cf4715fdc8fd5070f7d039e43511 upstream.
Limit io_uring "cmd" options to files for which the caller has Smack read access. There may be cases where the cmd option may be closer to a write access than a read, but there is no way to make that determination.
Cc: stable@vger.kernel.org Fixes: ee692a21e9bf ("fs,io_uring: add infrastructure for uring-cmd") Signed-off-by: Casey Schaufler casey@schaufler-ca.com Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/smack/smack_lsm.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+)
--- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -42,6 +42,7 @@ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/watch_queue.h> +#include <linux/io_uring.h> #include "smack.h"
#define TRANS_TRUE "TRUE" @@ -4739,6 +4740,36 @@ static int smack_uring_sqpoll(void) return -EPERM; }
+/** + * smack_uring_cmd - check on file operations for io_uring + * @ioucmd: the command in question + * + * Make a best guess about whether a io_uring "command" should + * be allowed. Use the same logic used for determining if the + * file could be opened for read in the absence of better criteria. + */ +static int smack_uring_cmd(struct io_uring_cmd *ioucmd) +{ + struct file *file = ioucmd->file; + struct smk_audit_info ad; + struct task_smack *tsp; + struct inode *inode; + int rc; + + if (!file) + return -EINVAL; + + tsp = smack_cred(file->f_cred); + inode = file_inode(file); + + smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH); + smk_ad_setfield_u_fs_path(&ad, file->f_path); + rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad); + rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc); + + return rc; +} + #endif /* CONFIG_IO_URING */
struct lsm_blob_sizes smack_blob_sizes __lsm_ro_after_init = { @@ -4896,6 +4927,7 @@ static struct security_hook_list smack_h #ifdef CONFIG_IO_URING LSM_HOOK_INIT(uring_override_creds, smack_uring_override_creds), LSM_HOOK_INIT(uring_sqpoll, smack_uring_sqpoll), + LSM_HOOK_INIT(uring_cmd, smack_uring_cmd), #endif };
From: Yang Ling gnaygnil@gmail.com
[ Upstream commit 35508d2424097f9b6a1a17aac94f702767035616 ]
The RTCCTRL reg of LS1C is obselete. Writing this reg will cause system hang.
Fixes: 60219c563c9b6 ("MIPS: Add RTC support for Loongson1C board") Signed-off-by: Yang Ling gnaygnil@gmail.com Tested-by: Keguang Zhang keguang.zhang@gmail.com Acked-by: Keguang Zhang keguang.zhang@gmail.com Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/loongson32/ls1c/board.c | 1 - 1 file changed, 1 deletion(-)
diff --git a/arch/mips/loongson32/ls1c/board.c b/arch/mips/loongson32/ls1c/board.c index e9de6da0ce51f..9dcfe9de55b0a 100644 --- a/arch/mips/loongson32/ls1c/board.c +++ b/arch/mips/loongson32/ls1c/board.c @@ -15,7 +15,6 @@ static struct platform_device *ls1c_platform_devices[] __initdata = { static int __init ls1c_platform_init(void) { ls1x_serial_set_uartclk(&ls1x_uart_pdev); - ls1x_rtc_set_extclk(&ls1x_rtc_pdev);
return platform_add_devices(ls1c_platform_devices, ARRAY_SIZE(ls1c_platform_devices));
From: Masahiro Yamada masahiroy@kernel.org
[ Upstream commit 1b620d539ccc18a1aca1613d9ff078115a7891a1 ]
Previously 'make ARCH=um headers' stopped because of missing arch/um/include/uapi/asm/Kbuild.
The error is not shown since commit ed102bf2afed ("um: Fix W=1 missing-include-dirs warnings") added arch/um/include/uapi/asm/Kbuild.
Hard-code the unsupported architecture, so it works like before.
Fixes: ed102bf2afed ("um: Fix W=1 missing-include-dirs warnings") Signed-off-by: Masahiro Yamada masahiroy@kernel.org Acked-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org --- Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/Makefile b/Makefile index e361c6230e9e5..2acd87dd62591 100644 --- a/Makefile +++ b/Makefile @@ -1286,8 +1286,7 @@ hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj
PHONY += headers headers: $(version_h) scripts_unifdef uapi-asm-generic archheaders archscripts - $(if $(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/Kbuild),, \ - $(error Headers not exportable for the $(SRCARCH) architecture)) + $(if $(filter um, $(SRCARCH)), $(error Headers not exportable for UML)) $(Q)$(MAKE) $(hdr-inst)=include/uapi $(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi
From: Przemyslaw Patynowski przemyslawx.patynowski@intel.com
[ Upstream commit 2313e69c84c024a85d017a60ae925085de47530a ]
Refactor bitwise checks for whether TC MQPRIO is enabled into one single method for improved readability.
Signed-off-by: Przemyslaw Patynowski przemyslawx.patynowski@intel.com Signed-off-by: Jan Sokolowski jan.sokolowski@intel.com Tested-by: Bharathi Sreenivas bharathi.sreenivas@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Stable-dep-of: 45bb006d3c92 ("i40e: Fix ADQ rate limiting for PF") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e.h | 14 +++++++++++++ .../net/ethernet/intel/i40e/i40e_ethtool.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_main.c | 20 +++++++++---------- 3 files changed, 25 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 407fe8f340a06..c5b61bc80f783 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1291,4 +1291,18 @@ int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi, struct i40e_cloud_filter *filter, bool add); + +/** + * i40e_is_tc_mqprio_enabled - check if TC MQPRIO is enabled on PF + * @pf: pointer to a pf. + * + * Check and return value of flag I40E_FLAG_TC_MQPRIO. + * + * Return: I40E_FLAG_TC_MQPRIO set state. + **/ +static inline u32 i40e_is_tc_mqprio_enabled(struct i40e_pf *pf) +{ + return pf->flags & I40E_FLAG_TC_MQPRIO; +} + #endif /* _I40E_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 22a61802a4027..ed9984f1e1b9f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -4931,7 +4931,7 @@ static int i40e_set_channels(struct net_device *dev, /* We do not support setting channels via ethtool when TCs are * configured through mqprio */ - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return -EINVAL;
/* verify they are not requesting separate vectors */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 71a8e1698ed48..45c56832c14fd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5339,7 +5339,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) u8 num_tc = 0; struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config;
- if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return pf->vsi[pf->lan_vsi]->mqprio_qopt.qopt.num_tc;
/* If neither MQPRIO nor DCB is enabled, then always use single TC */ @@ -5371,7 +5371,7 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) **/ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf) { - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return i40e_mqprio_get_enabled_tc(pf);
/* If neither MQPRIO nor DCB is enabled for this PF then just return @@ -5468,7 +5468,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, int i;
/* There is no need to reset BW when mqprio mode is on. */ - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return 0; if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { ret = i40e_set_bw_limit(vsi, vsi->seid, 0); @@ -5540,7 +5540,7 @@ static void i40e_vsi_config_netdev_tc(struct i40e_vsi *vsi, u8 enabled_tc) vsi->tc_config.tc_info[i].qoffset); }
- if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) return;
/* Assign UP2TC map for the VSI */ @@ -5701,7 +5701,7 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ctxt.vf_num = 0; ctxt.uplink_seid = vsi->uplink_seid; ctxt.info = vsi->info; - if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) { + if (i40e_is_tc_mqprio_enabled(pf)) { ret = i40e_vsi_setup_queue_map_mqprio(vsi, &ctxt, enabled_tc); if (ret) goto out; @@ -6425,7 +6425,7 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi, pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
if (vsi->type == I40E_VSI_MAIN) { - if (pf->flags & I40E_FLAG_TC_MQPRIO) + if (i40e_is_tc_mqprio_enabled(pf)) i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); else i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); @@ -7819,7 +7819,7 @@ static void *i40e_fwd_add(struct net_device *netdev, struct net_device *vdev) netdev_info(netdev, "Macvlans are not supported when DCB is enabled\n"); return ERR_PTR(-EINVAL); } - if ((pf->flags & I40E_FLAG_TC_MQPRIO)) { + if (i40e_is_tc_mqprio_enabled(pf)) { netdev_info(netdev, "Macvlans are not supported when HW TC offload is on\n"); return ERR_PTR(-EINVAL); } @@ -8072,7 +8072,7 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data) /* Quiesce VSI queues */ i40e_quiesce_vsi(vsi);
- if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO)) + if (!hw && !i40e_is_tc_mqprio_enabled(pf)) i40e_remove_queue_channels(vsi);
/* Configure VSI for enabled TCs */ @@ -8096,7 +8096,7 @@ static int i40e_setup_tc(struct net_device *netdev, void *type_data) "Setup channel (id:%u) utilizing num_queues %d\n", vsi->seid, vsi->tc_config.tc_info[0].qcount);
- if (pf->flags & I40E_FLAG_TC_MQPRIO) { + if (i40e_is_tc_mqprio_enabled(pf)) { if (vsi->mqprio_qopt.max_rate[0]) { u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
@@ -10750,7 +10750,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) * unless I40E_FLAG_TC_MQPRIO was enabled or DCB * is not supported with new link speed */ - if (pf->flags & I40E_FLAG_TC_MQPRIO) { + if (i40e_is_tc_mqprio_enabled(pf)) { i40e_aq_set_dcb_parameters(hw, false, NULL); } else { if (I40E_IS_X710TL_DEVICE(hw->device_id) &&
From: Przemyslaw Patynowski przemyslawx.patynowski@intel.com
[ Upstream commit 45bb006d3c924b1201ed43c87a96b437662dcaa8 ]
Fix HW rate limiting for ADQ. Fallback to kernel queue selection for ADQ, as it is network stack that decides which queue to use for transmit with ADQ configured. Reset PF after creation of VMDq2 VSIs required for ADQ, as to reprogram TX queue contexts in i40e_configure_tx_ring. Without this patch PF would limit TX rate only according to TC0.
Fixes: a9ce82f744dc ("i40e: Enable 'channel' mode in mqprio for TC configs") Signed-off-by: Przemyslaw Patynowski przemyslawx.patynowski@intel.com Signed-off-by: Jan Sokolowski jan.sokolowski@intel.com Tested-by: Bharathi Sreenivas bharathi.sreenivas@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 3 +++ drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 45c56832c14fd..1aaf0c5ddf6cf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6536,6 +6536,9 @@ static int i40e_configure_queue_channels(struct i40e_vsi *vsi) vsi->tc_seid_map[i] = ch->seid; } } + + /* reset to reconfigure TX queue contexts */ + i40e_do_reset(vsi->back, I40E_PF_RESET_FLAG, true); return ret;
err_free: diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index af69ccc6e8d2f..07f1e209d524d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3689,7 +3689,8 @@ u16 i40e_lan_select_queue(struct net_device *netdev, u8 prio;
/* is DCB enabled at all? */ - if (vsi->tc_config.numtc == 1) + if (vsi->tc_config.numtc == 1 || + i40e_is_tc_mqprio_enabled(vsi->back)) return netdev_pick_tx(netdev, skb, sb_dev);
prio = skb->priority;
From: Vladimir Oltean vladimir.oltean@nxp.com
[ Upstream commit 06799a9085e12a778fe2851db550ab5911ad28fe ]
The bonding driver piggybacks on time stamps kept by the network stack for the purpose of the netdev TX watchdog, and this is problematic because it does not work with NETIF_F_LLTX devices.
It is hard to say why the driver looks at dev_trans_start() of the slave->dev, considering that this is updated even by non-ARP/NS probes sent by us, and even by traffic not sent by us at all (for example PTP on physical slave devices). ARP monitoring in active-backup mode appears to still work even if we track only the last TX time of actual ARP probes.
Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Acked-by: Jay Vosburgh jay.vosburgh@canonical.com Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: 592335a4164c ("bonding: accept unsolicited NA message") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 35 +++++++++++++++++++-------------- include/net/bonding.h | 13 +++++++++++- 2 files changed, 32 insertions(+), 16 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0cf8c3a125d2e..01b58b7e7f165 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1974,6 +1974,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) new_slave->target_last_arp_rx[i] = new_slave->last_rx;
+ new_slave->last_tx = new_slave->last_rx; + if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1);
@@ -2857,8 +2859,11 @@ static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip, return; }
- if (bond_handle_vlan(slave, tags, skb)) + if (bond_handle_vlan(slave, tags, skb)) { + slave_update_last_tx(slave); arp_xmit(skb); + } + return; }
@@ -3047,8 +3052,7 @@ static int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) && - bond_time_in_interval(bond, - dev_trans_start(curr_arp_slave->dev), 1)) + bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_arp(bond, slave, sip, tip);
out_unlock: @@ -3076,8 +3080,10 @@ static void bond_ns_send(struct slave *slave, const struct in6_addr *daddr, }
addrconf_addr_solict_mult(daddr, &mcaddr); - if (bond_handle_vlan(slave, tags, skb)) + if (bond_handle_vlan(slave, tags, skb)) { + slave_update_last_tx(slave); ndisc_send_skb(skb, &mcaddr, saddr); + } }
static void bond_ns_send_all(struct bonding *bond, struct slave *slave) @@ -3222,8 +3228,7 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, curr_active_slave->last_link_up)) bond_validate_ns(bond, slave, saddr, daddr); else if (curr_arp_slave && - bond_time_in_interval(bond, - dev_trans_start(curr_arp_slave->dev), 1)) + bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_ns(bond, slave, saddr, daddr);
out: @@ -3311,12 +3316,12 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) * so it can wait */ bond_for_each_slave_rcu(bond, slave, iter) { - unsigned long trans_start = dev_trans_start(slave->dev); + unsigned long last_tx = slave_last_tx(slave);
bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
if (slave->link != BOND_LINK_UP) { - if (bond_time_in_interval(bond, trans_start, 1) && + if (bond_time_in_interval(bond, last_tx, 1) && bond_time_in_interval(bond, slave->last_rx, 1)) {
bond_propose_link_state(slave, BOND_LINK_UP); @@ -3341,7 +3346,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) || + if (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) {
bond_propose_link_state(slave, BOND_LINK_DOWN); @@ -3407,7 +3412,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) */ static int bond_ab_arp_inspect(struct bonding *bond) { - unsigned long trans_start, last_rx; + unsigned long last_tx, last_rx; struct list_head *iter; struct slave *slave; int commit = 0; @@ -3458,9 +3463,9 @@ static int bond_ab_arp_inspect(struct bonding *bond) * - (more than missed_max*delta since receive AND * the bond has an IP address) */ - trans_start = dev_trans_start(slave->dev); + last_tx = slave_last_tx(slave); if (bond_is_active_slave(slave) && - (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) || + (!bond_time_in_interval(bond, last_tx, bond->params.missed_max) || !bond_time_in_interval(bond, last_rx, bond->params.missed_max))) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; @@ -3477,8 +3482,8 @@ static int bond_ab_arp_inspect(struct bonding *bond) */ static void bond_ab_arp_commit(struct bonding *bond) { - unsigned long trans_start; struct list_head *iter; + unsigned long last_tx; struct slave *slave;
bond_for_each_slave(bond, slave, iter) { @@ -3487,10 +3492,10 @@ static void bond_ab_arp_commit(struct bonding *bond) continue;
case BOND_LINK_UP: - trans_start = dev_trans_start(slave->dev); + last_tx = slave_last_tx(slave); if (rtnl_dereference(bond->curr_active_slave) != slave || (!rtnl_dereference(bond->curr_active_slave) && - bond_time_in_interval(bond, trans_start, 1))) { + bond_time_in_interval(bond, last_tx, 1))) { struct slave *current_arp_slave;
current_arp_slave = rtnl_dereference(bond->current_arp_slave); diff --git a/include/net/bonding.h b/include/net/bonding.h index cb904d356e31e..3b816ae8b1f3b 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -161,8 +161,9 @@ struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ int delay; - /* all three in jiffies */ + /* all 4 in jiffies */ unsigned long last_link_up; + unsigned long last_tx; unsigned long last_rx; unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ @@ -539,6 +540,16 @@ static inline unsigned long slave_last_rx(struct bonding *bond, return slave->last_rx; }
+static inline void slave_update_last_tx(struct slave *slave) +{ + WRITE_ONCE(slave->last_tx, jiffies); +} + +static inline unsigned long slave_last_tx(struct slave *slave) +{ + return READ_ONCE(slave->last_tx); +} + #ifdef CONFIG_NET_POLL_CONTROLLER static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb)
From: Hangbin Liu liuhangbin@gmail.com
[ Upstream commit 592335a4164c3c41f57967223a1e1efe3a0c6eb3 ]
The unsolicited NA message with all-nodes multicast dest address should be valid, as this also means the link could reach the target.
Also rename bond_validate_ns() to bond_validate_na().
Reported-by: LiLiang liali@redhat.com Fixes: 5e1eeef69c0f ("bonding: NS target should accept link local address") Signed-off-by: Hangbin Liu liuhangbin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 01b58b7e7f165..bff0bfd10e235 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3174,12 +3174,19 @@ static bool bond_has_this_ip6(struct bonding *bond, struct in6_addr *addr) return ret; }
-static void bond_validate_ns(struct bonding *bond, struct slave *slave, +static void bond_validate_na(struct bonding *bond, struct slave *slave, struct in6_addr *saddr, struct in6_addr *daddr) { int i;
- if (ipv6_addr_any(saddr) || !bond_has_this_ip6(bond, daddr)) { + /* Ignore NAs that: + * 1. Source address is unspecified address. + * 2. Dest address is neither all-nodes multicast address nor + * exist on bond interface. + */ + if (ipv6_addr_any(saddr) || + (!ipv6_addr_equal(daddr, &in6addr_linklocal_allnodes) && + !bond_has_this_ip6(bond, daddr))) { slave_dbg(bond->dev, slave->dev, "%s: sip %pI6c tip %pI6c not found\n", __func__, saddr, daddr); return; @@ -3222,14 +3229,14 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, * see bond_arp_rcv(). */ if (bond_is_active_slave(slave)) - bond_validate_ns(bond, slave, saddr, daddr); + bond_validate_na(bond, slave, saddr, daddr); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) - bond_validate_ns(bond, slave, saddr, daddr); + bond_validate_na(bond, slave, saddr, daddr); else if (curr_arp_slave && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) - bond_validate_ns(bond, slave, saddr, daddr); + bond_validate_na(bond, slave, saddr, daddr);
out: return RX_HANDLER_ANOTHER;
From: Chao Gao chao.gao@intel.com
[ Upstream commit 3f0461613ebcdc8c4073e235053d06d5aa58750f ]
The second operand passed to slot_addr() is declared as int or unsigned int in all call sites. The left-shift to get the offset of a slot can overflow if swiotlb size is larger than 4G.
Convert the macro to an inline function and declare the second argument as phys_addr_t to avoid the potential overflow.
Fixes: 26a7e094783d ("swiotlb: refactor swiotlb_tbl_map_single") Signed-off-by: Chao Gao chao.gao@intel.com Reviewed-by: Dongli Zhang dongli.zhang@oracle.com Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/dma/swiotlb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 5830dce6081b3..ce34d50f7a9bb 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -464,7 +464,10 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size } }
-#define slot_addr(start, idx) ((start) + ((idx) << IO_TLB_SHIFT)) +static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx) +{ + return start + (idx << IO_TLB_SHIFT); +}
/* * Carefully handle integer overflow which can occur when boundary_mask == ~0UL.
From: John Sperbeck jsperbeck@google.com
[ Upstream commit 94a568ce32038d8ff9257004bb4632e60eb43a49 ]
We started using a 64 bit completion value. Unfortunately, we only stored the low 32-bits, so a very large completion value would never be matched in iommu_completion_wait().
Fixes: c69d89aff393 ("iommu/amd: Use 4K page for completion wait write-back semaphore") Signed-off-by: John Sperbeck jsperbeck@google.com Link: https://lore.kernel.org/r/20220801192229.3358786-1-jsperbeck@google.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/amd/iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 840831d5d2ad9..a0924144bac80 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -874,7 +874,8 @@ static void build_completion_wait(struct iommu_cmd *cmd, memset(cmd, 0, sizeof(*cmd)); cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK; cmd->data[1] = upper_32_bits(paddr); - cmd->data[2] = data; + cmd->data[2] = lower_32_bits(data); + cmd->data[3] = upper_32_bits(data); CMD_SET_TYPE(cmd, CMD_COMPL_WAIT); }
From: Alexander Gordeev agordeev@linux.ibm.com
[ Upstream commit 12dd19c159659ec9050f45dc8a2ff3c3917f4be3 ]
Crash dump always starts on CPU0. In case CPU0 is offline the prefix page is not installed and the absolute zero lowcore is used. However, struct lowcore::mcesad is never assigned and stays zero. That leads to __machine_kdump() -> save_vx_regs() call silently stores vector registers to the absolute lowcore at 0x11b0 offset.
Fixes: a62bc0739253 ("s390/kdump: add support for vector extension") Reviewed-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kernel/nmi.c | 2 +- arch/s390/kernel/setup.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 53ed3884fe644..5d66e3947070c 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -63,7 +63,7 @@ static inline unsigned long nmi_get_mcesa_size(void) * structure. The structure is required for machine check happening * early in the boot process. */ -static struct mcesa boot_mcesa __initdata __aligned(MCESA_MAX_SIZE); +static struct mcesa boot_mcesa __aligned(MCESA_MAX_SIZE);
void __init nmi_alloc_mcesa_early(u64 *mcesad) { diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 0a37f5de28631..3e0361db963ef 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -486,6 +486,7 @@ static void __init setup_lowcore_dat_off(void) put_abs_lowcore(restart_data, lc->restart_data); put_abs_lowcore(restart_source, lc->restart_source); put_abs_lowcore(restart_psw, lc->restart_psw); + put_abs_lowcore(mcesad, lc->mcesad);
lc->spinlock_lockval = arch_spin_lockval(0); lc->spinlock_index = 0;
From: Vladimir Oltean vladimir.oltean@nxp.com
[ Upstream commit 837ced3a1a5d8bb1a637dd584711f31ae6b54d93 ]
Time-sensitive networking code needs to work with PTP times expressed in nanoseconds, and with packet transmission times expressed in picoseconds, since those would be fractional at higher than gigabit speed when expressed in nanoseconds.
Convert the existing uses in tc-taprio and the ocelot/felix DSA driver to a PSEC_PER_NSEC macro. This macro is placed in include/linux/time64.h as opposed to its relatives (PSEC_PER_SEC etc) from include/vdso/time64.h because the vDSO library does not (yet) need/use it.
Cc: Andy Lutomirski luto@kernel.org Cc: Thomas Gleixner tglx@linutronix.de Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Reviewed-by: Vincenzo Frascino vincenzo.frascino@arm.com # for the vDSO parts Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: 11afdc6526de ("net: dsa: felix: tc-taprio intervals smaller than MTU should send at least one packet") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/ocelot/felix_vsc9959.c | 5 +++-- include/linux/time64.h | 3 +++ net/sched/sch_taprio.c | 5 +++-- 3 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index f1767a6b9271c..4cce71243080e 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -16,6 +16,7 @@ #include <linux/iopoll.h> #include <linux/mdio.h> #include <linux/pci.h> +#include <linux/time.h> #include "felix.h"
#define VSC9959_NUM_PORTS 6 @@ -1592,7 +1593,7 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) u32 max_sdu;
if (min_gate_len[tc] == U64_MAX /* Gate always open */ || - min_gate_len[tc] * 1000 > needed_bit_time_ps) { + min_gate_len[tc] * PSEC_PER_NSEC > needed_bit_time_ps) { /* Setting QMAXSDU_CFG to 0 disables oversized frame * dropping. */ @@ -1606,7 +1607,7 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) * frame, make sure to enable oversize frame dropping * for frames larger than the smallest that would fit. */ - max_sdu = div_u64(min_gate_len[tc] * 1000, + max_sdu = div_u64(min_gate_len[tc] * PSEC_PER_NSEC, picos_per_byte); /* A TC gate may be completely closed, which is a * special case where all packets are oversized. diff --git a/include/linux/time64.h b/include/linux/time64.h index 81b9686a20799..2fb8232cff1d5 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -20,6 +20,9 @@ struct itimerspec64 { struct timespec64 it_value; };
+/* Parameters used to convert the timespec values: */ +#define PSEC_PER_NSEC 1000L + /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index b9c71a304d399..0b941dd63d268 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <linux/time.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -176,7 +177,7 @@ static ktime_t get_interval_end_time(struct sched_gate_list *sched,
static int length_to_duration(struct taprio_sched *q, int len) { - return div_u64(len * atomic64_read(&q->picos_per_byte), 1000); + return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC); }
/* Returns the entry corresponding to next available interval. If @@ -551,7 +552,7 @@ static struct sk_buff *taprio_peek(struct Qdisc *sch) static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) { atomic_set(&entry->budget, - div64_u64((u64)entry->interval * 1000, + div64_u64((u64)entry->interval * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte))); }
From: Vladimir Oltean vladimir.oltean@nxp.com
[ Upstream commit 11afdc6526de0e0368c05da632a8c0d29fc60bb8 ]
The blamed commit broke tc-taprio schedules such as this one:
tc qdisc replace dev $swp1 root taprio \ num_tc 8 \ map 0 1 2 3 4 5 6 7 \ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 \ base-time 0 \ sched-entry S 0x7f 990000 \ sched-entry S 0x80 10000 \ flags 0x2
because the gate entry for TC 7 (S 0x80 10000 ns) now has a static guard band added earlier than its 'gate close' event, such that packet overruns won't occur in the worst case of the largest packet possible.
Since guard bands are statically determined based on the per-tc QSYS_QMAXSDU_CFG_* with a fallback on the port-based QSYS_PORT_MAX_SDU, we need to discuss what happens with TC 7 depending on kernel version, since the driver, prior to commit 55a515b1f5a9 ("net: dsa: felix: drop oversized frames with tc-taprio instead of hanging the port"), did not touch QSYS_QMAXSDU_CFG_*, and therefore relied on QSYS_PORT_MAX_SDU.
1 (before vsc9959_tas_guard_bands_update): QSYS_PORT_MAX_SDU defaults to 1518, and at gigabit this introduces a static guard band (independent of packet sizes) of 12144 ns, plus QSYS::HSCH_MISC_CFG.FRM_ADJ (bit time of 20 octets => 160 ns). But this is larger than the time window itself, of 10000 ns. So, the queue system never considers a frame with TC 7 as eligible for transmission, since the gate practically never opens, and these frames are forever stuck in the TX queues and hang the port.
2 (after vsc9959_tas_guard_bands_update): Under the sole goal of enabling oversized frame dropping, we make an effort to set QSYS_QMAXSDU_CFG_7 to 1230 bytes. But QSYS_QMAXSDU_CFG_7 plays one more role, which we did not take into account: per-tc static guard band, expressed in L2 byte time (auto-adjusted for FCS and L1 overhead). There is a discrepancy between what the driver thinks (that there is no guard band, and 100% of min_gate_len[tc] is available for egress scheduling) and what the hardware actually does (crops the equivalent of QSYS_QMAXSDU_CFG_7 ns out of min_gate_len[tc]). In practice, this means that the hardware thinks it has exactly 0 ns for scheduling tc 7.
In both cases, even minimum sized Ethernet frames are stuck on egress rather than being considered for scheduling on TC 7, even if they would fit given a proper configuration. Considering the current situation, with vsc9959_tas_guard_bands_update(), frames between 60 octets and 1230 octets in size are not eligible for oversized dropping (because they are smaller than QSYS_QMAXSDU_CFG_7), but won't be considered as eligible for scheduling either, because the min_gate_len[7] (10000 ns) minus the guard band determined by QSYS_QMAXSDU_CFG_7 (1230 octets * 8 ns per octet == 9840 ns) minus the guard band auto-added for L1 overhead by QSYS::HSCH_MISC_CFG.FRM_ADJ (20 octets * 8 ns per octet == 160 octets) leaves 0 ns for scheduling in the queue system proper.
Investigating the hardware behavior, it becomes apparent that the queue system needs precisely 33 ns of 'gate open' time in order to consider a frame as eligible for scheduling to a tc. So the solution to this problem is to amend vsc9959_tas_guard_bands_update(), by giving the per-tc guard bands less space by exactly 33 ns, just enough for one frame to be scheduled in that interval. This allows the queue system to make forward progress for that port-tc, and prevents it from hanging.
Fixes: 297c4de6f780 ("net: dsa: felix: re-enable TAS guard band mode") Reported-by: Xiaoliang Yang xiaoliang.yang_1@nxp.com Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/ocelot/felix_vsc9959.c | 35 +++++++++++++++++++++++--- 1 file changed, 31 insertions(+), 4 deletions(-)
diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 4cce71243080e..517bc3922ee24 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -22,6 +22,7 @@ #define VSC9959_NUM_PORTS 6
#define VSC9959_TAS_GCL_ENTRY_MAX 63 +#define VSC9959_TAS_MIN_GATE_LEN_NS 33 #define VSC9959_VCAP_POLICER_BASE 63 #define VSC9959_VCAP_POLICER_MAX 383 #define VSC9959_SWITCH_PCI_BAR 4 @@ -1411,6 +1412,23 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot) mdiobus_free(felix->imdio); }
+/* The switch considers any frame (regardless of size) as eligible for + * transmission if the traffic class gate is open for at least 33 ns. + * Overruns are prevented by cropping an interval at the end of the gate time + * slot for which egress scheduling is blocked, but we need to still keep 33 ns + * available for one packet to be transmitted, otherwise the port tc will hang. + * This function returns the size of a gate interval that remains available for + * setting the guard band, after reserving the space for one egress frame. + */ +static u64 vsc9959_tas_remaining_gate_len_ps(u64 gate_len_ns) +{ + /* Gate always open */ + if (gate_len_ns == U64_MAX) + return U64_MAX; + + return (gate_len_ns - VSC9959_TAS_MIN_GATE_LEN_NS) * PSEC_PER_NSEC; +} + /* Extract shortest continuous gate open intervals in ns for each traffic class * of a cyclic tc-taprio schedule. If a gate is always open, the duration is * considered U64_MAX. If the gate is always closed, it is considered 0. @@ -1590,10 +1608,13 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) mutex_lock(&ocelot->fwd_domain_lock);
for (tc = 0; tc < OCELOT_NUM_TC; tc++) { + u64 remaining_gate_len_ps; u32 max_sdu;
- if (min_gate_len[tc] == U64_MAX /* Gate always open */ || - min_gate_len[tc] * PSEC_PER_NSEC > needed_bit_time_ps) { + remaining_gate_len_ps = + vsc9959_tas_remaining_gate_len_ps(min_gate_len[tc]); + + if (remaining_gate_len_ps > needed_bit_time_ps) { /* Setting QMAXSDU_CFG to 0 disables oversized frame * dropping. */ @@ -1606,9 +1627,15 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) /* If traffic class doesn't support a full MTU sized * frame, make sure to enable oversize frame dropping * for frames larger than the smallest that would fit. + * + * However, the exact same register, QSYS_QMAXSDU_CFG_*, + * controls not only oversized frame dropping, but also + * per-tc static guard band lengths, so it reduces the + * useful gate interval length. Therefore, be careful + * to calculate a guard band (and therefore max_sdu) + * that still leaves 33 ns available in the time slot. */ - max_sdu = div_u64(min_gate_len[tc] * PSEC_PER_NSEC, - picos_per_byte); + max_sdu = div_u64(remaining_gate_len_ps, picos_per_byte); /* A TC gate may be completely closed, which is a * special case where all packets are oversized. * Any limit smaller than 64 octets accomplishes this
From: Eliav Farber farbere@amazon.com
[ Upstream commit 81114fc3d27bf5b06b2137d2fd2b63da656a8b90 ]
Bug - in case "intel,vm-map" is missing in device-tree ,'num' is set to 0, and no voltage channel infos are allocated.
The reason num is set to 0 when "intel,vm-map" is missing is to set the entire pvt->vm_idx[] with incremental channel numbers, but it didn't take into consideration that same num is used later in devm_kcalloc().
If "intel,vm-map" does exist there is no need to set the unspecified channels with incremental numbers, because the unspecified channels can't be accessed in pvt_read_in() which is the only other place besides the probe functions that uses pvt->vm_idx[].
This change fixes the bug by moving the incremental channel numbers setting to be done only if "intel,vm-map" property is defined (starting loop from 0), and removing 'num = 0'.
Fixes: 9d823351a337 ("hwmon: Add hardware monitoring driver for Moortec MR75203 PVT controller") Signed-off-by: Eliav Farber farbere@amazon.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20220908152449.35457-3-farbere@amazon.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/mr75203.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c index 26278b0f17a98..8b72e8fe34c1b 100644 --- a/drivers/hwmon/mr75203.c +++ b/drivers/hwmon/mr75203.c @@ -584,7 +584,12 @@ static int mr75203_probe(struct platform_device *pdev) ret = device_property_read_u8_array(dev, "intel,vm-map", pvt->vm_idx, vm_num); if (ret) { - num = 0; + /* + * Incase intel,vm-map property is not defined, we + * assume incremental channel numbers. + */ + for (i = 0; i < vm_num; i++) + pvt->vm_idx[i] = i; } else { for (i = 0; i < vm_num; i++) if (pvt->vm_idx[i] >= vm_num || @@ -594,13 +599,6 @@ static int mr75203_probe(struct platform_device *pdev) } }
- /* - * Incase intel,vm-map property is not defined, we assume - * incremental channel numbers. - */ - for (i = num; i < vm_num; i++) - pvt->vm_idx[i] = i; - in_config = devm_kcalloc(dev, num + 1, sizeof(*in_config), GFP_KERNEL); if (!in_config)
From: Eliav Farber farbere@amazon.com
[ Upstream commit bb9195bd6664d94d71647631593e09f705ff5edd ]
This issue is relevant when "intel,vm-map" is set in device-tree, and defines a lower number of VMs than actually supported.
This change is needed for all places that use pvt->v_num or vm_num later on in the code.
Fixes: 9d823351a337 ("hwmon: Add hardware monitoring driver for Moortec MR75203 PVT controller") Signed-off-by: Eliav Farber farbere@amazon.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20220908152449.35457-4-farbere@amazon.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/mr75203.c | 2 ++ 1 file changed, 2 insertions(+)
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c index 8b72e8fe34c1b..be02f32bf143d 100644 --- a/drivers/hwmon/mr75203.c +++ b/drivers/hwmon/mr75203.c @@ -595,6 +595,8 @@ static int mr75203_probe(struct platform_device *pdev) if (pvt->vm_idx[i] >= vm_num || pvt->vm_idx[i] == 0xff) { num = i; + pvt->v_num = i; + vm_num = i; break; } }
From: Eliav Farber farbere@amazon.com
[ Upstream commit 227a3a2fc31d8e4bb9c88d4804e19530af245b1b ]
According to Moortec Embedded Voltage Monitor (MEVM) series 3 data sheet, the minimum input signal is -100mv and maximum input signal is +1000mv.
The equation used to convert the digital word to voltage uses mixed types (*val signed and n unsigned), and on 64 bit machines also has different size, since sizeof(u32) = 4 and sizeof(long) = 8.
So when measuring a negative input, n will be small enough, such that PVT_N_CONST * n < PVT_R_CONST, and the result of (PVT_N_CONST * n - PVT_R_CONST) will overflow to a very big positive 32 bit number. Then when storing the result in *val it will be the same value just in 64 bit (instead of it representing a negative number which will what happen when sizeof(long) = 4).
When -1023 <= (PVT_N_CONST * n - PVT_R_CONST) <= -1 dividing the number by 1024 should result of in 0, but because ">> 10" is used, and the sign bit is used to fill the vacated bit positions, it results in -1 (0xf...fffff) which is wrong.
This change fixes the sign problem and supports negative values by casting n to long and replacing the shift right with div operation.
Fixes: 9d823351a337 ("hwmon: Add hardware monitoring driver for Moortec MR75203 PVT controller") Signed-off-by: Eliav Farber farbere@amazon.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20220908152449.35457-5-farbere@amazon.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/mr75203.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c index be02f32bf143d..6d3b3c499ed83 100644 --- a/drivers/hwmon/mr75203.c +++ b/drivers/hwmon/mr75203.c @@ -201,8 +201,18 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val) return ret;
n &= SAMPLE_DATA_MSK; - /* Convert the N bitstream count into voltage */ - *val = (PVT_N_CONST * n - PVT_R_CONST) >> PVT_CONV_BITS; + /* + * Convert the N bitstream count into voltage. + * To support negative voltage calculation for 64bit machines + * n must be cast to long, since n and *val differ both in + * signedness and in size. + * Division is used instead of right shift, because for signed + * numbers, the sign bit is used to fill the vacated bit + * positions, and if the number is negative, 1 is used. + * BIT(x) may not be used instead of (1 << x) because it's + * unsigned. + */ + *val = (PVT_N_CONST * (long)n - PVT_R_CONST) / (1 << PVT_CONV_BITS);
return 0; default:
From: Eliav Farber farbere@amazon.com
[ Upstream commit 91a9e063cdcfca8fe642b078d6fae4ce49187975 ]
Fix voltage allocation and reading to support all channels in all VMs. Prior to this change allocation and reading were done only for the first channel in each VM. This change counts the total number of channels for allocation, and takes into account the channel offset when reading the sample data register.
Fixes: 9d823351a337 ("hwmon: Add hardware monitoring driver for Moortec MR75203 PVT controller") Signed-off-by: Eliav Farber farbere@amazon.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20220908152449.35457-6-farbere@amazon.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/mr75203.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-)
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c index 6d3b3c499ed83..812ae40e7d74d 100644 --- a/drivers/hwmon/mr75203.c +++ b/drivers/hwmon/mr75203.c @@ -68,8 +68,9 @@
/* VM Individual Macro Register */ #define VM_COM_REG_SIZE 0x200 -#define VM_SDIF_DONE(n) (VM_COM_REG_SIZE + 0x34 + 0x200 * (n)) -#define VM_SDIF_DATA(n) (VM_COM_REG_SIZE + 0x40 + 0x200 * (n)) +#define VM_SDIF_DONE(vm) (VM_COM_REG_SIZE + 0x34 + 0x200 * (vm)) +#define VM_SDIF_DATA(vm, ch) \ + (VM_COM_REG_SIZE + 0x40 + 0x200 * (vm) + 0x4 * (ch))
/* SDA Slave Register */ #define IP_CTRL 0x00 @@ -115,6 +116,7 @@ struct pvt_device { u32 t_num; u32 p_num; u32 v_num; + u32 c_num; u32 ip_freq; u8 *vm_idx; }; @@ -178,14 +180,15 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val) { struct pvt_device *pvt = dev_get_drvdata(dev); struct regmap *v_map = pvt->v_map; + u8 vm_idx, ch_idx; u32 n, stat; - u8 vm_idx; int ret;
- if (channel >= pvt->v_num) + if (channel >= pvt->v_num * pvt->c_num) return -EINVAL;
- vm_idx = pvt->vm_idx[channel]; + vm_idx = pvt->vm_idx[channel / pvt->c_num]; + ch_idx = channel % pvt->c_num;
switch (attr) { case hwmon_in_input: @@ -196,7 +199,7 @@ static int pvt_read_in(struct device *dev, u32 attr, int channel, long *val) if (ret) return ret;
- ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx), &n); + ret = regmap_read(v_map, VM_SDIF_DATA(vm_idx, ch_idx), &n); if(ret < 0) return ret;
@@ -499,8 +502,8 @@ static int pvt_reset_control_deassert(struct device *dev, struct pvt_device *pvt
static int mr75203_probe(struct platform_device *pdev) { + u32 ts_num, vm_num, pd_num, ch_num, val, index, i; const struct hwmon_channel_info **pvt_info; - u32 ts_num, vm_num, pd_num, val, index, i; struct device *dev = &pdev->dev; u32 *temp_config, *in_config; struct device *hwmon_dev; @@ -541,9 +544,11 @@ static int mr75203_probe(struct platform_device *pdev) ts_num = (val & TS_NUM_MSK) >> TS_NUM_SFT; pd_num = (val & PD_NUM_MSK) >> PD_NUM_SFT; vm_num = (val & VM_NUM_MSK) >> VM_NUM_SFT; + ch_num = (val & CH_NUM_MSK) >> CH_NUM_SFT; pvt->t_num = ts_num; pvt->p_num = pd_num; pvt->v_num = vm_num; + pvt->c_num = ch_num; val = 0; if (ts_num) val++; @@ -580,7 +585,7 @@ static int mr75203_probe(struct platform_device *pdev) }
if (vm_num) { - u32 num = vm_num; + u32 total_ch;
ret = pvt_get_regmap(pdev, "vm", pvt); if (ret) @@ -604,20 +609,20 @@ static int mr75203_probe(struct platform_device *pdev) for (i = 0; i < vm_num; i++) if (pvt->vm_idx[i] >= vm_num || pvt->vm_idx[i] == 0xff) { - num = i; pvt->v_num = i; vm_num = i; break; } }
- in_config = devm_kcalloc(dev, num + 1, + total_ch = ch_num * vm_num; + in_config = devm_kcalloc(dev, total_ch + 1, sizeof(*in_config), GFP_KERNEL); if (!in_config) return -ENOMEM;
- memset32(in_config, HWMON_I_INPUT, num); - in_config[num] = 0; + memset32(in_config, HWMON_I_INPUT, total_ch); + in_config[total_ch] = 0; pvt_in.config = in_config;
pvt_info[index++] = &pvt_in;
From: Eliav Farber farbere@amazon.com
[ Upstream commit e43212e0f55dc2d6b15d6c174cc0a64b25fab5e7 ]
Configure ip-polling register to enable polling for all voltage monitor channels. This enables reading the voltage values for all inputs other than just input 0.
Fixes: 9d823351a337 ("hwmon: Add hardware monitoring driver for Moortec MR75203 PVT controller") Signed-off-by: Eliav Farber farbere@amazon.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://lore.kernel.org/r/20220908152449.35457-7-farbere@amazon.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/mr75203.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)
diff --git a/drivers/hwmon/mr75203.c b/drivers/hwmon/mr75203.c index 812ae40e7d74d..9259779cc2dff 100644 --- a/drivers/hwmon/mr75203.c +++ b/drivers/hwmon/mr75203.c @@ -388,6 +388,19 @@ static int pvt_init(struct pvt_device *pvt) if (ret) return ret;
+ val = (BIT(pvt->c_num) - 1) | VM_CH_INIT | + IP_POLL << SDIF_ADDR_SFT | SDIF_WRN_W | SDIF_PROG; + ret = regmap_write(v_map, SDIF_W, val); + if (ret < 0) + return ret; + + ret = regmap_read_poll_timeout(v_map, SDIF_STAT, + val, !(val & SDIF_BUSY), + PVT_POLL_DELAY_US, + PVT_POLL_TIMEOUT_US); + if (ret) + return ret; + val = CFG1_VOL_MEAS_MODE | CFG1_PARALLEL_OUT | CFG1_14_BIT | IP_CFG << SDIF_ADDR_SFT | SDIF_WRN_W | SDIF_PROG;
From: Lu Baolu baolu.lu@linux.intel.com
[ Upstream commit 9cd4f1434479f1ac25c440c421fbf52069079914 ]
The global rwsem dmar_global_lock was introduced by commit 3a5670e8ac932 ("iommu/vt-d: Introduce a rwsem to protect global data structures"). It is used to protect DMAR related global data from DMAR hotplug operations.
The dmar_global_lock used in the intel_iommu_init() might cause recursive locking issue, for example, intel_iommu_get_resv_regions() is taking the dmar_global_lock from within a section where intel_iommu_init() already holds it via probe_acpi_namespace_devices().
Using dmar_global_lock in intel_iommu_init() could be relaxed since it is unlikely that any IO board must be hot added before the IOMMU subsystem is initialized. This eliminates the possible recursive locking issue by moving down DMAR hotplug support after the IOMMU is initialized and removing the uses of dmar_global_lock in intel_iommu_init().
Fixes: d5692d4af08cd ("iommu/vt-d: Fix suspicious RCU usage in probe_acpi_namespace_devices()") Reported-by: Robin Murphy robin.murphy@arm.com Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Reviewed-by: Kevin Tian kevin.tian@intel.com Link: https://lore.kernel.org/r/894db0ccae854b35c73814485569b634237b5538.165703482... Link: https://lore.kernel.org/r/20220718235325.3952426-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iommu/intel/dmar.c | 7 +++++++ drivers/iommu/intel/iommu.c | 27 ++------------------------- include/linux/dmar.h | 4 +++- 3 files changed, 12 insertions(+), 26 deletions(-)
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 64b14ac4c7b02..fc8c1420c0b69 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -2368,6 +2368,13 @@ static int dmar_device_hotplug(acpi_handle handle, bool insert) if (!dmar_in_use()) return 0;
+ /* + * It's unlikely that any I/O board is hot added before the IOMMU + * subsystem is initialized. + */ + if (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled) + return -EOPNOTSUPP; + if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) { tmp = handle; } else { diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 5c0dce78586aa..936def2f416a2 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3123,13 +3123,7 @@ static int __init init_dmars(void)
#ifdef CONFIG_INTEL_IOMMU_SVM if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) { - /* - * Call dmar_alloc_hwirq() with dmar_global_lock held, - * could cause possible lock race condition. - */ - up_write(&dmar_global_lock); ret = intel_svm_enable_prq(iommu); - down_write(&dmar_global_lock); if (ret) goto free_iommu; } @@ -4035,7 +4029,6 @@ int __init intel_iommu_init(void) force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) || platform_optin_force_iommu();
- down_write(&dmar_global_lock); if (dmar_table_init()) { if (force_on) panic("tboot: Failed to initialize DMAR table\n"); @@ -4048,16 +4041,6 @@ int __init intel_iommu_init(void) goto out_free_dmar; }
- up_write(&dmar_global_lock); - - /* - * The bus notifier takes the dmar_global_lock, so lockdep will - * complain later when we register it under the lock. - */ - dmar_register_bus_notifier(); - - down_write(&dmar_global_lock); - if (!no_iommu) intel_iommu_debugfs_init();
@@ -4105,11 +4088,9 @@ int __init intel_iommu_init(void) pr_err("Initialization failed\n"); goto out_free_dmar; } - up_write(&dmar_global_lock);
init_iommu_pm_ops();
- down_read(&dmar_global_lock); for_each_active_iommu(iommu, drhd) { /* * The flush queue implementation does not perform @@ -4127,13 +4108,11 @@ int __init intel_iommu_init(void) "%s", iommu->name); iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL); } - up_read(&dmar_global_lock);
bus_set_iommu(&pci_bus_type, &intel_iommu_ops); if (si_domain && !hw_pass_through) register_memory_notifier(&intel_iommu_memory_nb);
- down_read(&dmar_global_lock); if (probe_acpi_namespace_devices()) pr_warn("ACPI name space devices didn't probe correctly\n");
@@ -4144,17 +4123,15 @@ int __init intel_iommu_init(void)
iommu_disable_protect_mem_regions(iommu); } - up_read(&dmar_global_lock); - - pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
intel_iommu_enabled = 1; + dmar_register_bus_notifier(); + pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
return 0;
out_free_dmar: intel_iommu_free_dmars(); - up_write(&dmar_global_lock); return ret; }
diff --git a/include/linux/dmar.h b/include/linux/dmar.h index cbd714a198a0a..f3a3d95df5325 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -69,6 +69,7 @@ struct dmar_pci_notify_info {
extern struct rw_semaphore dmar_global_lock; extern struct list_head dmar_drhd_units; +extern int intel_iommu_enabled;
#define for_each_drhd_unit(drhd) \ list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ @@ -92,7 +93,8 @@ extern struct list_head dmar_drhd_units; static inline bool dmar_rcu_check(void) { return rwsem_is_locked(&dmar_global_lock) || - system_state == SYSTEM_BOOTING; + system_state == SYSTEM_BOOTING || + (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled); }
#define dmar_rcu_dereference(p) rcu_dereference_check((p), dmar_rcu_check())
From: Kan Liang kan.liang@linux.intel.com
[ Upstream commit a9c1ecdabc4f2ef04ef5334b8deb3a5c5910136d ]
Current perf stat uses the evlist__add_default_attrs() to add the generic default attrs, and uses arch_evlist__add_default_attrs() to add the Arch specific default attrs, e.g., Topdown for x86.
It works well for the non-hybrid platforms. However, for a hybrid platform, the hard code generic default attrs don't work.
Uses arch_evlist__add_default_attrs() to replace the evlist__add_default_attrs(). The arch_evlist__add_default_attrs() is modified to invoke the same __evlist__add_default_attrs() for the generic default attrs. No functional change.
Add default_null_attrs[] to indicate the arch specific attrs. No functional change for the arch specific default attrs either.
Signed-off-by: Kan Liang kan.liang@linux.intel.com Acked-by: Ian Rogers irogers@google.com Acked-by: Namhyung Kim namhyung@kernel.org Cc: Alexander Shishkin alexander.shishkin@intel.com Cc: Andi Kleen ak@linux.intel.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/r/20220721065706.2886112-4-zhengjun.xing@linux.intel... Signed-off-by: Xing Zhengjun zhengjun.xing@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Stable-dep-of: f0c86a2bae4f ("perf stat: Fix L2 Topdown metrics disappear for raw events") Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/arch/x86/util/evlist.c | 7 ++++++- tools/perf/builtin-stat.c | 6 +++++- tools/perf/util/evlist.c | 9 +++++++-- tools/perf/util/evlist.h | 7 +++++-- 4 files changed, 23 insertions(+), 6 deletions(-)
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index 68f681ad54c1e..777bdf182a582 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -8,8 +8,13 @@ #define TOPDOWN_L1_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}" #define TOPDOWN_L2_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}"
-int arch_evlist__add_default_attrs(struct evlist *evlist) +int arch_evlist__add_default_attrs(struct evlist *evlist, + struct perf_event_attr *attrs, + size_t nr_attrs) { + if (nr_attrs) + return __evlist__add_default_attrs(evlist, attrs, nr_attrs); + if (!pmu_have_event("cpu", "slots")) return 0;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5f0333a8acd8a..5aacb7ed8c24a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1778,6 +1778,9 @@ static int add_default_attributes(void) (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) }, }; + + struct perf_event_attr default_null_attrs[] = {}; + /* Set attrs if no event is selected and !null_run: */ if (stat_config.null_run) return 0; @@ -1959,7 +1962,8 @@ static int add_default_attributes(void) return -1;
stat_config.topdown_level = TOPDOWN_MAX_LEVEL; - if (arch_evlist__add_default_attrs(evsel_list) < 0) + /* Platform specific attrs */ + if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) return -1; }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 48af7d379d822..efa5f006b5c61 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -342,9 +342,14 @@ int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *a return evlist__add_attrs(evlist, attrs, nr_attrs); }
-__weak int arch_evlist__add_default_attrs(struct evlist *evlist __maybe_unused) +__weak int arch_evlist__add_default_attrs(struct evlist *evlist, + struct perf_event_attr *attrs, + size_t nr_attrs) { - return 0; + if (!nr_attrs) + return 0; + + return __evlist__add_default_attrs(evlist, attrs, nr_attrs); }
struct evsel *evlist__find_tracepoint_by_id(struct evlist *evlist, int id) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 1bde9ccf4e7da..129095c0fe6d3 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -107,10 +107,13 @@ static inline int evlist__add_default(struct evlist *evlist) int __evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs);
+int arch_evlist__add_default_attrs(struct evlist *evlist, + struct perf_event_attr *attrs, + size_t nr_attrs); + #define evlist__add_default_attrs(evlist, array) \ - __evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) + arch_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
-int arch_evlist__add_default_attrs(struct evlist *evlist); struct evsel *arch_evlist__leader(struct list_head *list);
int evlist__add_dummy(struct evlist *evlist);
From: Zhengjun Xing zhengjun.xing@linux.intel.com
[ Upstream commit f0c86a2bae4fd12bfa8bad4d43fb59fb498cdd14 ]
In perf/Documentation/perf-stat.txt, for "--td-level" the default "0" means the max level that the current hardware support.
So we need initialize the stat_config.topdown_level to TOPDOWN_MAX_LEVEL when “--td-level=0” or no “--td-level” option. Otherwise, for the hardware with a max level is 2, the 2nd level metrics disappear for raw events in this case.
The issue cannot be observed for the perf stat default or "--topdown" options. This commit fixes the raw events issue and removes the duplicated code for the perf stat default.
Before:
# ./perf stat -e "cpu-clock,context-switches,cpu-migrations,page-faults,instructions,cycles,ref-cycles,branches,branch-misses,{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}" sleep 1
Performance counter stats for 'sleep 1':
1.03 msec cpu-clock # 0.001 CPUs utilized 1 context-switches # 966.216 /sec 0 cpu-migrations # 0.000 /sec 60 page-faults # 57.973 K/sec 1,132,112 instructions # 1.41 insn per cycle 803,872 cycles # 0.777 GHz 1,909,120 ref-cycles # 1.845 G/sec 236,634 branches # 228.640 M/sec 6,367 branch-misses # 2.69% of all branches 4,823,232 slots # 4.660 G/sec 1,210,536 topdown-retiring # 25.1% Retiring 699,841 topdown-bad-spec # 14.5% Bad Speculation 1,777,975 topdown-fe-bound # 36.9% Frontend Bound 1,134,878 topdown-be-bound # 23.5% Backend Bound 189,146 topdown-heavy-ops # 182.756 M/sec 662,012 topdown-br-mispredict # 639.647 M/sec 1,097,048 topdown-fetch-lat # 1.060 G/sec 416,121 topdown-mem-bound # 402.063 M/sec
1.002423690 seconds time elapsed
0.002494000 seconds user 0.000000000 seconds sys
After:
# ./perf stat -e "cpu-clock,context-switches,cpu-migrations,page-faults,instructions,cycles,ref-cycles,branches,branch-misses,{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}" sleep 1
Performance counter stats for 'sleep 1':
1.13 msec cpu-clock # 0.001 CPUs utilized 1 context-switches # 882.128 /sec 0 cpu-migrations # 0.000 /sec 61 page-faults # 53.810 K/sec 1,137,612 instructions # 1.29 insn per cycle 881,477 cycles # 0.778 GHz 2,093,496 ref-cycles # 1.847 G/sec 236,356 branches # 208.496 M/sec 7,090 branch-misses # 3.00% of all branches 5,288,862 slots # 4.665 G/sec 1,223,697 topdown-retiring # 23.1% Retiring 767,403 topdown-bad-spec # 14.5% Bad Speculation 2,053,322 topdown-fe-bound # 38.8% Frontend Bound 1,244,438 topdown-be-bound # 23.5% Backend Bound 186,665 topdown-heavy-ops # 3.5% Heavy Operations # 19.6% Light Operations 725,922 topdown-br-mispredict # 13.7% Branch Mispredict # 0.8% Machine Clears 1,327,400 topdown-fetch-lat # 25.1% Fetch Latency # 13.7% Fetch Bandwidth 497,775 topdown-mem-bound # 9.4% Memory Bound # 14.1% Core Bound
1.002701530 seconds time elapsed
0.002744000 seconds user 0.000000000 seconds sys
Fixes: 63e39aa6ae103451 ("perf stat: Support L2 Topdown events") Reviewed-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Xing Zhengjun zhengjun.xing@linux.intel.com Cc: Alexander Shishkin alexander.shishkin@intel.com Cc: Andi Kleen ak@linux.intel.com Cc: Ian Rogers irogers@google.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: Kan Liang kan.liang@linux.intel.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: https://lore.kernel.org/r/20220826140057.3289401-1-zhengjun.xing@linux.intel... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-stat.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5aacb7ed8c24a..82e14faecc3e4 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1944,6 +1944,9 @@ static int add_default_attributes(void) free(str); }
+ if (!stat_config.topdown_level) + stat_config.topdown_level = TOPDOWN_MAX_LEVEL; + if (!evsel_list->core.nr_entries) { if (target__has_cpu(&target)) default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK; @@ -1960,8 +1963,6 @@ static int add_default_attributes(void) } if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0) return -1; - - stat_config.topdown_level = TOPDOWN_MAX_LEVEL; /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) return -1;
This reverts commit add4bc9281e8704e5ab15616b429576c84f453a2.
On Mon, Sep 12, 2022 at 10:52:45AM +0100, Catalin Marinas wrote:
I missed this (holidays) and it looks like it's in stable already. On its own it will likely break kasan_hw if used together with user-space MTE as this change relies on two previous commits:
70c248aca9e7 ("mm: kasan: Skip unpoisoning of user pages") 6d05141a3930 ("mm: kasan: Skip page unpoisoning only if __GFP_SKIP_KASAN_UNPOISON")
The reason I did not cc stable is that there are other dependencies in this area. The potential issues without the above commits were rather theoretical, so take these patches rather as clean-ups/refactoring than fixes.
Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/hibernate.c | 5 +++++ arch/arm64/kernel/mte.c | 9 +++++++++ arch/arm64/mm/copypage.c | 9 +++++++++ arch/arm64/mm/mteswap.c | 9 +++++++++ 4 files changed, 32 insertions(+)
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index af5df48ba915b..2e248342476ea 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -300,6 +300,11 @@ static void swsusp_mte_restore_tags(void) unsigned long pfn = xa_state.xa_index; struct page *page = pfn_to_online_page(pfn);
+ /* + * It is not required to invoke page_kasan_tag_reset(page) + * at this point since the tags stored in page->flags are + * already restored. + */ mte_restore_page_tags(page_address(page), tags);
mte_free_tag_storage(tags); diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index b2b730233274b..f6b00743c3994 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -48,6 +48,15 @@ static void mte_sync_page_tags(struct page *page, pte_t old_pte, if (!pte_is_tagged) return;
+ page_kasan_tag_reset(page); + /* + * We need smp_wmb() in between setting the flags and clearing the + * tags because if another thread reads page->flags and builds a + * tagged address out of it, there is an actual dependency to the + * memory access, but on the current thread we do not guarantee that + * the new page->flags are visible before the tags were updated. + */ + smp_wmb(); mte_clear_page_tags(page_address(page)); }
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 24913271e898c..0dea80bf6de46 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -23,6 +23,15 @@ void copy_highpage(struct page *to, struct page *from)
if (system_supports_mte() && test_bit(PG_mte_tagged, &from->flags)) { set_bit(PG_mte_tagged, &to->flags); + page_kasan_tag_reset(to); + /* + * We need smp_wmb() in between setting the flags and clearing the + * tags because if another thread reads page->flags and builds a + * tagged address out of it, there is an actual dependency to the + * memory access, but on the current thread we do not guarantee that + * the new page->flags are visible before the tags were updated. + */ + smp_wmb(); mte_copy_page_tags(kto, kfrom); } } diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index 4334dec93bd44..a9e50e930484a 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -53,6 +53,15 @@ bool mte_restore_tags(swp_entry_t entry, struct page *page) if (!tags) return false;
+ page_kasan_tag_reset(page); + /* + * We need smp_wmb() in between setting the flags and clearing the + * tags because if another thread reads page->flags and builds a + * tagged address out of it, there is an actual dependency to the + * memory access, but on the current thread we do not guarantee that + * the new page->flags are visible before the tags were updated. + */ + smp_wmb(); mte_restore_page_tags(page_address(page), tags);
return true;
From: Shady Nawara shady.nawara@outlook.com
[ Upstream commit bae26b801f98bc902ab4a43c96947f3a0ce4f3a0 ]
adds T_Sensor and VRM Temp sensors for the Asus Strix z690-a D4 motherboard
Signed-off-by: Shady Nawara shady.nawara@outlook.com Signed-off-by: Eugene Shalygin eugene.shalygin@gmail.com Link: https://lore.kernel.org/r/20220603122758.1561064-1-eugene.shalygin@gmail.com Signed-off-by: Guenter Roeck linux@roeck-us.net Stable-dep-of: 88700d1396ba ("hwmon: (asus-ec-sensors) autoload module via DMI data") Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/hwmon/asus_ec_sensors.rst | 1 + drivers/hwmon/asus-ec-sensors.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+)
diff --git a/Documentation/hwmon/asus_ec_sensors.rst b/Documentation/hwmon/asus_ec_sensors.rst index 78ca69eda8778..00d8c46ef9e04 100644 --- a/Documentation/hwmon/asus_ec_sensors.rst +++ b/Documentation/hwmon/asus_ec_sensors.rst @@ -19,6 +19,7 @@ Supported boards: * ROG STRIX X570-E GAMING WIFI II * ROG STRIX X570-F GAMING * ROG STRIX X570-I GAMING + * ROG STRIX Z690-A GAMING WIFI D4
Authors: - Eugene Shalygin eugene.shalygin@gmail.com diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 3633ab691662b..19d3ca71b3609 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -54,6 +54,8 @@ static char *mutex_path_override; /* ACPI mutex for locking access to the EC for the firmware */ #define ASUS_HW_ACCESS_MUTEX_ASMX "\AMW0.ASMX"
+#define ASUS_HW_ACCESS_MUTEX_RMTW_ASMX "\RMTW.ASMX" + #define MAX_IDENTICAL_BOARD_VARIATIONS 3
/* Moniker for the ACPI global lock (':' is not allowed in ASL identifiers) */ @@ -139,6 +141,7 @@ enum board_family { family_unknown, family_amd_400_series, family_amd_500_series, + family_intel_600_series };
/* All the known sensors for ASUS EC controllers */ @@ -197,6 +200,12 @@ static const struct ec_sensor_info sensors_family_amd_500[] = { EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x01), };
+static const struct ec_sensor_info sensors_family_intel_600[] = { + [ec_sensor_temp_t_sensor] = + EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x3d), + [ec_sensor_temp_vrm] = EC_SENSOR("VRM", hwmon_temp, 1, 0x00, 0x3e), +}; + /* Shortcuts for common combinations */ #define SENSOR_SET_TEMP_CHIPSET_CPU_MB \ (SENSOR_TEMP_CHIPSET | SENSOR_TEMP_CPU | SENSOR_TEMP_MB) @@ -330,6 +339,12 @@ static const struct ec_board_info board_info[] = { .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, .family = family_amd_500_series, }, + { + .board_names = {"ROG STRIX Z690-A GAMING WIFI D4"}, + .sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM, + .mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX, + .family = family_intel_600_series, + }, {} };
@@ -799,6 +814,9 @@ static int __init asus_ec_probe(struct platform_device *pdev) case family_amd_500_series: ec_data->sensors_info = sensors_family_amd_500; break; + case family_intel_600_series: + ec_data->sensors_info = sensors_family_intel_600; + break; default: dev_err(dev, "Unknown board family: %d", ec_data->board_info->family);
From: Michael Carns mike@carns.com
[ Upstream commit 8f9eb10ff71d8e3beeee3f8d19050223600faf85 ]
Add definitions for ROG MAXIMUS XI HERO and ROG MAXIMUS XI HERO (WI-FI) boards.
Signed-off-by: Michael Carns mike@carns.com Signed-off-by: Eugene Shalygin eugene.shalygin@gmail.com Link: https://lore.kernel.org/r/20220627225437.87462-1-eugene.shalygin@gmail.com Signed-off-by: Guenter Roeck linux@roeck-us.net Stable-dep-of: 88700d1396ba ("hwmon: (asus-ec-sensors) autoload module via DMI data") Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/hwmon/asus_ec_sensors.rst | 2 ++ drivers/hwmon/asus-ec-sensors.c | 36 +++++++++++++++++++++++++ 2 files changed, 38 insertions(+)
diff --git a/Documentation/hwmon/asus_ec_sensors.rst b/Documentation/hwmon/asus_ec_sensors.rst index 00d8c46ef9e04..1e40c123db777 100644 --- a/Documentation/hwmon/asus_ec_sensors.rst +++ b/Documentation/hwmon/asus_ec_sensors.rst @@ -13,6 +13,8 @@ Supported boards: * ROG CROSSHAIR VIII FORMULA * ROG CROSSHAIR VIII HERO * ROG CROSSHAIR VIII IMPACT + * ROG MAXIMUS XI HERO + * ROG MAXIMUS XI HERO (WI-FI) * ROG STRIX B550-E GAMING * ROG STRIX B550-I GAMING * ROG STRIX X570-E GAMING diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 19d3ca71b3609..625c2baa35ec6 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -141,6 +141,7 @@ enum board_family { family_unknown, family_amd_400_series, family_amd_500_series, + family_intel_300_series, family_intel_600_series };
@@ -200,6 +201,26 @@ static const struct ec_sensor_info sensors_family_amd_500[] = { EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x01), };
+static const struct ec_sensor_info sensors_family_intel_300[] = { + [ec_sensor_temp_chipset] = + EC_SENSOR("Chipset", hwmon_temp, 1, 0x00, 0x3a), + [ec_sensor_temp_cpu] = EC_SENSOR("CPU", hwmon_temp, 1, 0x00, 0x3b), + [ec_sensor_temp_mb] = + EC_SENSOR("Motherboard", hwmon_temp, 1, 0x00, 0x3c), + [ec_sensor_temp_t_sensor] = + EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x3d), + [ec_sensor_temp_vrm] = EC_SENSOR("VRM", hwmon_temp, 1, 0x00, 0x3e), + [ec_sensor_fan_cpu_opt] = + EC_SENSOR("CPU_Opt", hwmon_fan, 2, 0x00, 0xb0), + [ec_sensor_fan_vrm_hs] = EC_SENSOR("VRM HS", hwmon_fan, 2, 0x00, 0xb2), + [ec_sensor_fan_water_flow] = + EC_SENSOR("Water_Flow", hwmon_fan, 2, 0x00, 0xbc), + [ec_sensor_temp_water_in] = + EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x00), + [ec_sensor_temp_water_out] = + EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x01), +}; + static const struct ec_sensor_info sensors_family_intel_600[] = { [ec_sensor_temp_t_sensor] = EC_SENSOR("T_Sensor", hwmon_temp, 1, 0x00, 0x3d), @@ -281,6 +302,18 @@ static const struct ec_board_info board_info[] = { .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, .family = family_amd_500_series, }, + { + .board_names = { + "ROG MAXIMUS XI HERO", + "ROG MAXIMUS XI HERO (WI-FI)", + }, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_intel_300_series, + }, { .board_names = {"ROG CROSSHAIR VIII IMPACT"}, .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | @@ -814,6 +847,9 @@ static int __init asus_ec_probe(struct platform_device *pdev) case family_amd_500_series: ec_data->sensors_info = sensors_family_amd_500; break; + case family_intel_300_series: + ec_data->sensors_info = sensors_family_intel_300; + break; case family_intel_600_series: ec_data->sensors_info = sensors_family_intel_600; break;
From: Eugene Shalygin eugene.shalygin@gmail.com
[ Upstream commit 1c4e4f4a0e8d9ebe8be1c838fec4fb7053a989d9 ]
VRM and chipset temperature for ROG STRIX X570-I GAMING were missing according to a user contribution to the LHM project [1].
[1] https://github.com/LibreHardwareMonitor/LibreHardwareMonitor/pull/767
Signed-off-by: Eugene Shalygin eugene.shalygin@gmail.com Link: https://lore.kernel.org/r/20220710085539.1682869-1-eugene.shalygin@gmail.com Signed-off-by: Guenter Roeck linux@roeck-us.net Stable-dep-of: 88700d1396ba ("hwmon: (asus-ec-sensors) autoload module via DMI data") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/asus-ec-sensors.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 625c2baa35ec6..0749cd023a323 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -366,9 +366,10 @@ static const struct ec_board_info board_info[] = { }, { .board_names = {"ROG STRIX X570-I GAMING"}, - .sensors = SENSOR_TEMP_T_SENSOR | SENSOR_FAN_VRM_HS | - SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, + .sensors = SENSOR_TEMP_CHIPSET | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | + SENSOR_FAN_VRM_HS | SENSOR_FAN_CHIPSET | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, .family = family_amd_500_series, },
From: Urs Schroffenegger nabajour@lampshade.ch
[ Upstream commit 9992b19d756ab8f0889fcaf3e71ff93852e74694 ]
Add definitions for ROG ZENITH II EXTREME and some unknown yet temperature sensors in the second EC bank. Details are available at [1, 2].
[1] https://github.com/zeule/asus-ec-sensors/pull/26 [2] https://github.com/zeule/asus-ec-sensors/issues/16
Signed-off-by: Urs Schroffenegger nabajour@lampshade.ch Signed-off-by: Eugene Shalygin eugene.shalygin@gmail.com Link: https://lore.kernel.org/r/20220710202639.1812058-2-eugene.shalygin@gmail.com Signed-off-by: Guenter Roeck linux@roeck-us.net Stable-dep-of: 88700d1396ba ("hwmon: (asus-ec-sensors) autoload module via DMI data") Signed-off-by: Sasha Levin sashal@kernel.org --- Documentation/hwmon/asus_ec_sensors.rst | 1 + drivers/hwmon/asus-ec-sensors.c | 47 +++++++++++++++++++++++++ 2 files changed, 48 insertions(+)
diff --git a/Documentation/hwmon/asus_ec_sensors.rst b/Documentation/hwmon/asus_ec_sensors.rst index 1e40c123db777..02f4ad314a1eb 100644 --- a/Documentation/hwmon/asus_ec_sensors.rst +++ b/Documentation/hwmon/asus_ec_sensors.rst @@ -22,6 +22,7 @@ Supported boards: * ROG STRIX X570-F GAMING * ROG STRIX X570-I GAMING * ROG STRIX Z690-A GAMING WIFI D4 + * ROG ZENITH II EXTREME
Authors: - Eugene Shalygin eugene.shalygin@gmail.com diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 0749cd023a323..61a4684fc020e 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -56,6 +56,8 @@ static char *mutex_path_override;
#define ASUS_HW_ACCESS_MUTEX_RMTW_ASMX "\RMTW.ASMX"
+#define ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0 "\_SB_.PCI0.SBRG.SIO1.MUT0" + #define MAX_IDENTICAL_BOARD_VARIATIONS 3
/* Moniker for the ACPI global lock (':' is not allowed in ASL identifiers) */ @@ -121,6 +123,18 @@ enum ec_sensors { ec_sensor_temp_water_in, /* "Water_Out" temperature sensor reading [℃] */ ec_sensor_temp_water_out, + /* "Water_Block_In" temperature sensor reading [℃] */ + ec_sensor_temp_water_block_in, + /* "Water_Block_Out" temperature sensor reading [℃] */ + ec_sensor_temp_water_block_out, + /* "T_sensor_2" temperature sensor reading [℃] */ + ec_sensor_temp_t_sensor_2, + /* "Extra_1" temperature sensor reading [℃] */ + ec_sensor_temp_sensor_extra_1, + /* "Extra_2" temperature sensor reading [℃] */ + ec_sensor_temp_sensor_extra_2, + /* "Extra_3" temperature sensor reading [℃] */ + ec_sensor_temp_sensor_extra_3, };
#define SENSOR_TEMP_CHIPSET BIT(ec_sensor_temp_chipset) @@ -136,6 +150,12 @@ enum ec_sensors { #define SENSOR_CURR_CPU BIT(ec_sensor_curr_cpu) #define SENSOR_TEMP_WATER_IN BIT(ec_sensor_temp_water_in) #define SENSOR_TEMP_WATER_OUT BIT(ec_sensor_temp_water_out) +#define SENSOR_TEMP_WATER_BLOCK_IN BIT(ec_sensor_temp_water_block_in) +#define SENSOR_TEMP_WATER_BLOCK_OUT BIT(ec_sensor_temp_water_block_out) +#define SENSOR_TEMP_T_SENSOR_2 BIT(ec_sensor_temp_t_sensor_2) +#define SENSOR_TEMP_SENSOR_EXTRA_1 BIT(ec_sensor_temp_sensor_extra_1) +#define SENSOR_TEMP_SENSOR_EXTRA_2 BIT(ec_sensor_temp_sensor_extra_2) +#define SENSOR_TEMP_SENSOR_EXTRA_3 BIT(ec_sensor_temp_sensor_extra_3)
enum board_family { family_unknown, @@ -199,6 +219,18 @@ static const struct ec_sensor_info sensors_family_amd_500[] = { EC_SENSOR("Water_In", hwmon_temp, 1, 0x01, 0x00), [ec_sensor_temp_water_out] = EC_SENSOR("Water_Out", hwmon_temp, 1, 0x01, 0x01), + [ec_sensor_temp_water_block_in] = + EC_SENSOR("Water_Block_In", hwmon_temp, 1, 0x01, 0x02), + [ec_sensor_temp_water_block_out] = + EC_SENSOR("Water_Block_Out", hwmon_temp, 1, 0x01, 0x03), + [ec_sensor_temp_sensor_extra_1] = + EC_SENSOR("Extra_1", hwmon_temp, 1, 0x01, 0x09), + [ec_sensor_temp_t_sensor_2] = + EC_SENSOR("T_sensor_2", hwmon_temp, 1, 0x01, 0x0a), + [ec_sensor_temp_sensor_extra_2] = + EC_SENSOR("Extra_2", hwmon_temp, 1, 0x01, 0x0b), + [ec_sensor_temp_sensor_extra_3] = + EC_SENSOR("Extra_3", hwmon_temp, 1, 0x01, 0x0c), };
static const struct ec_sensor_info sensors_family_intel_300[] = { @@ -231,6 +263,9 @@ static const struct ec_sensor_info sensors_family_intel_600[] = { #define SENSOR_SET_TEMP_CHIPSET_CPU_MB \ (SENSOR_TEMP_CHIPSET | SENSOR_TEMP_CPU | SENSOR_TEMP_MB) #define SENSOR_SET_TEMP_WATER (SENSOR_TEMP_WATER_IN | SENSOR_TEMP_WATER_OUT) +#define SENSOR_SET_WATER_BLOCK \ + (SENSOR_TEMP_WATER_BLOCK_IN | SENSOR_TEMP_WATER_BLOCK_OUT) +
struct ec_board_info { const char *board_names[MAX_IDENTICAL_BOARD_VARIATIONS]; @@ -379,6 +414,18 @@ static const struct ec_board_info board_info[] = { .mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX, .family = family_intel_600_series, }, + { + .board_names = {"ROG ZENITH II EXTREME"}, + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | SENSOR_FAN_VRM_HS | + SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE | + SENSOR_SET_WATER_BLOCK | + SENSOR_TEMP_T_SENSOR_2 | SENSOR_TEMP_SENSOR_EXTRA_1 | + SENSOR_TEMP_SENSOR_EXTRA_2 | SENSOR_TEMP_SENSOR_EXTRA_3, + .mutex_path = ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0, + .family = family_amd_500_series, + }, {} };
From: Eugene Shalygin eugene.shalygin@gmail.com
[ Upstream commit 88700d1396bae72d9a4c23a48bbd98c1c2f53f3d ]
Replace autoloading data based on the ACPI EC device with the DMI records for motherboards models. The ACPI method created a bug that when this driver returns error from the probe function because of the unsupported motherboard model, the ACPI subsystem concludes that the EC device does not work properly.
Fixes: 5cd29012028d ("hwmon: (asus-ec-sensors) introduce ec_board_info struct for board data") Bug: https://bugzilla.kernel.org/show_bug.cgi?id=216412 Bug: https://bugzilla.redhat.com/show_bug.cgi?id=2121844 Signed-off-by: Eugene Shalygin eugene.shalygin@gmail.com Link: https://lore.kernel.org/r/20220909155654.123398-2-eugene.shalygin@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hwmon/asus-ec-sensors.c | 408 +++++++++++++++++--------------- 1 file changed, 222 insertions(+), 186 deletions(-)
diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c index 61a4684fc020e..81e688975c6a7 100644 --- a/drivers/hwmon/asus-ec-sensors.c +++ b/drivers/hwmon/asus-ec-sensors.c @@ -266,9 +266,7 @@ static const struct ec_sensor_info sensors_family_intel_600[] = { #define SENSOR_SET_WATER_BLOCK \ (SENSOR_TEMP_WATER_BLOCK_IN | SENSOR_TEMP_WATER_BLOCK_OUT)
- struct ec_board_info { - const char *board_names[MAX_IDENTICAL_BOARD_VARIATIONS]; unsigned long sensors; /* * Defines which mutex to use for guarding access to the state and the @@ -281,152 +279,194 @@ struct ec_board_info { enum board_family family; };
-static const struct ec_board_info board_info[] = { - { - .board_names = {"PRIME X470-PRO"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CPU_OPT | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH, - .family = family_amd_400_series, - }, - { - .board_names = {"PRIME X570-PRO"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ProArt X570-CREATOR WIFI"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - }, - { - .board_names = {"Pro WS X570-ACE"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG CROSSHAIR VIII DARK HERO"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = { - "ROG CROSSHAIR VIII FORMULA", - "ROG CROSSHAIR VIII HERO", - "ROG CROSSHAIR VIII HERO (WI-FI)", - }, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | - SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = { - "ROG MAXIMUS XI HERO", - "ROG MAXIMUS XI HERO (WI-FI)", - }, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_intel_300_series, - }, - { - .board_names = {"ROG CROSSHAIR VIII IMPACT"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX B550-E GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CPU_OPT, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX B550-I GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_VRM_HS | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-E GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | - SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-E GAMING WIFI II"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_CURR_CPU | - SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-F GAMING"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | - SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX X570-I GAMING"}, - .sensors = SENSOR_TEMP_CHIPSET | SENSOR_TEMP_VRM | - SENSOR_TEMP_T_SENSOR | - SENSOR_FAN_VRM_HS | SENSOR_FAN_CHIPSET | - SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, - .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, - .family = family_amd_500_series, - }, - { - .board_names = {"ROG STRIX Z690-A GAMING WIFI D4"}, - .sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM, - .mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX, - .family = family_intel_600_series, - }, - { - .board_names = {"ROG ZENITH II EXTREME"}, - .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | - SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | - SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | SENSOR_FAN_VRM_HS | - SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE | - SENSOR_SET_WATER_BLOCK | - SENSOR_TEMP_T_SENSOR_2 | SENSOR_TEMP_SENSOR_EXTRA_1 | - SENSOR_TEMP_SENSOR_EXTRA_2 | SENSOR_TEMP_SENSOR_EXTRA_3, - .mutex_path = ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0, - .family = family_amd_500_series, - }, - {} +static const struct ec_board_info board_info_prime_x470_pro = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CPU_OPT | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ACPI_GLOBAL_LOCK_PSEUDO_PATH, + .family = family_amd_400_series, +}; + +static const struct ec_board_info board_info_prime_x570_pro = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_pro_art_x570_creator_wifi = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CPU_OPT | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_pro_ws_x570_ace = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_crosshair_viii_dark_hero = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_crosshair_viii_hero = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | + SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_maximus_xi_hero = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_WATER_FLOW, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_intel_300_series, +}; + +static const struct ec_board_info board_info_crosshair_viii_impact = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_b550_e_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CPU_OPT, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_b550_i_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_VRM_HS | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_e_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM | + SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_e_gaming_wifi_ii = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_CURR_CPU | + SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_f_gaming = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | + SENSOR_TEMP_T_SENSOR | SENSOR_FAN_CHIPSET, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_x570_i_gaming = { + .sensors = SENSOR_TEMP_CHIPSET | SENSOR_TEMP_VRM | + SENSOR_TEMP_T_SENSOR | + SENSOR_FAN_VRM_HS | SENSOR_FAN_CHIPSET | + SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE, + .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX, + .family = family_amd_500_series, +}; + +static const struct ec_board_info board_info_strix_z690_a_gaming_wifi_d4 = { + .sensors = SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM, + .mutex_path = ASUS_HW_ACCESS_MUTEX_RMTW_ASMX, + .family = family_intel_600_series, +}; + +static const struct ec_board_info board_info_zenith_ii_extreme = { + .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB | SENSOR_TEMP_T_SENSOR | + SENSOR_TEMP_VRM | SENSOR_SET_TEMP_WATER | + SENSOR_FAN_CPU_OPT | SENSOR_FAN_CHIPSET | SENSOR_FAN_VRM_HS | + SENSOR_FAN_WATER_FLOW | SENSOR_CURR_CPU | SENSOR_IN_CPU_CORE | + SENSOR_SET_WATER_BLOCK | + SENSOR_TEMP_T_SENSOR_2 | SENSOR_TEMP_SENSOR_EXTRA_1 | + SENSOR_TEMP_SENSOR_EXTRA_2 | SENSOR_TEMP_SENSOR_EXTRA_3, + .mutex_path = ASUS_HW_ACCESS_MUTEX_SB_PCI0_SBRG_SIO1_MUT0, + .family = family_amd_500_series, +}; + +#define DMI_EXACT_MATCH_ASUS_BOARD_NAME(name, board_info) \ + { \ + .matches = { \ + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, \ + "ASUSTeK COMPUTER INC."), \ + DMI_EXACT_MATCH(DMI_BOARD_NAME, name), \ + }, \ + .driver_data = (void *)board_info, \ + } + +static const struct dmi_system_id dmi_table[] = { + DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X470-PRO", + &board_info_prime_x470_pro), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X570-PRO", + &board_info_prime_x570_pro), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ProArt X570-CREATOR WIFI", + &board_info_pro_art_x570_creator_wifi), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("Pro WS X570-ACE", + &board_info_pro_ws_x570_ace), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII DARK HERO", + &board_info_crosshair_viii_dark_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII FORMULA", + &board_info_crosshair_viii_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII HERO", + &board_info_crosshair_viii_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII HERO (WI-FI)", + &board_info_crosshair_viii_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS XI HERO", + &board_info_maximus_xi_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG MAXIMUS XI HERO (WI-FI)", + &board_info_maximus_xi_hero), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VIII IMPACT", + &board_info_crosshair_viii_impact), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX B550-E GAMING", + &board_info_strix_b550_e_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX B550-I GAMING", + &board_info_strix_b550_i_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-E GAMING", + &board_info_strix_x570_e_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-E GAMING WIFI II", + &board_info_strix_x570_e_gaming_wifi_ii), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-F GAMING", + &board_info_strix_x570_f_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX X570-I GAMING", + &board_info_strix_x570_i_gaming), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG STRIX Z690-A GAMING WIFI D4", + &board_info_strix_z690_a_gaming_wifi_d4), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG ZENITH II EXTREME", + &board_info_zenith_ii_extreme), + {}, };
struct ec_sensor { @@ -537,12 +577,12 @@ static int find_ec_sensor_index(const struct ec_sensors_data *ec, return -ENOENT; }
-static int __init bank_compare(const void *a, const void *b) +static int bank_compare(const void *a, const void *b) { return *((const s8 *)a) - *((const s8 *)b); }
-static void __init setup_sensor_data(struct ec_sensors_data *ec) +static void setup_sensor_data(struct ec_sensors_data *ec) { struct ec_sensor *s = ec->sensors; bool bank_found; @@ -574,7 +614,7 @@ static void __init setup_sensor_data(struct ec_sensors_data *ec) sort(ec->banks, ec->nr_banks, 1, bank_compare, NULL); }
-static void __init fill_ec_registers(struct ec_sensors_data *ec) +static void fill_ec_registers(struct ec_sensors_data *ec) { const struct ec_sensor_info *si; unsigned int i, j, register_idx = 0; @@ -589,7 +629,7 @@ static void __init fill_ec_registers(struct ec_sensors_data *ec) } }
-static int __init setup_lock_data(struct device *dev) +static int setup_lock_data(struct device *dev) { const char *mutex_path; int status; @@ -812,7 +852,7 @@ static umode_t asus_ec_hwmon_is_visible(const void *drvdata, return find_ec_sensor_index(state, type, channel) >= 0 ? S_IRUGO : 0; }
-static int __init +static int asus_ec_hwmon_add_chan_info(struct hwmon_channel_info *asus_ec_hwmon_chan, struct device *dev, int num, enum hwmon_sensor_types type, u32 config) @@ -841,27 +881,15 @@ static struct hwmon_chip_info asus_ec_chip_info = { .ops = &asus_ec_hwmon_ops, };
-static const struct ec_board_info * __init get_board_info(void) +static const struct ec_board_info *get_board_info(void) { - const char *dmi_board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR); - const char *dmi_board_name = dmi_get_system_info(DMI_BOARD_NAME); - const struct ec_board_info *board; - - if (!dmi_board_vendor || !dmi_board_name || - strcasecmp(dmi_board_vendor, "ASUSTeK COMPUTER INC.")) - return NULL; - - for (board = board_info; board->sensors; board++) { - if (match_string(board->board_names, - MAX_IDENTICAL_BOARD_VARIATIONS, - dmi_board_name) >= 0) - return board; - } + const struct dmi_system_id *dmi_entry;
- return NULL; + dmi_entry = dmi_first_match(dmi_table); + return dmi_entry ? dmi_entry->driver_data : NULL; }
-static int __init asus_ec_probe(struct platform_device *pdev) +static int asus_ec_probe(struct platform_device *pdev) { const struct hwmon_channel_info **ptr_asus_ec_ci; int nr_count[hwmon_max] = { 0 }, nr_types = 0; @@ -970,29 +998,37 @@ static int __init asus_ec_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(hwdev); }
- -static const struct acpi_device_id acpi_ec_ids[] = { - /* Embedded Controller Device */ - { "PNP0C09", 0 }, - {} -}; +MODULE_DEVICE_TABLE(dmi, dmi_table);
static struct platform_driver asus_ec_sensors_platform_driver = { .driver = { .name = "asus-ec-sensors", - .acpi_match_table = acpi_ec_ids, }, + .probe = asus_ec_probe, };
-MODULE_DEVICE_TABLE(acpi, acpi_ec_ids); -/* - * we use module_platform_driver_probe() rather than module_platform_driver() - * because the probe function (and its dependants) are marked with __init, which - * means we can't put it into the .probe member of the platform_driver struct - * above, and we can't mark the asus_ec_sensors_platform_driver object as __init - * because the object is referenced from the module exit code. - */ -module_platform_driver_probe(asus_ec_sensors_platform_driver, asus_ec_probe); +static struct platform_device *asus_ec_sensors_platform_device; + +static int __init asus_ec_init(void) +{ + asus_ec_sensors_platform_device = + platform_create_bundle(&asus_ec_sensors_platform_driver, + asus_ec_probe, NULL, 0, NULL, 0); + + if (IS_ERR(asus_ec_sensors_platform_device)) + return PTR_ERR(asus_ec_sensors_platform_device); + + return 0; +} + +static void __exit asus_ec_exit(void) +{ + platform_device_unregister(asus_ec_sensors_platform_device); + platform_driver_unregister(&asus_ec_sensors_platform_driver); +} + +module_init(asus_ec_init); +module_exit(asus_ec_exit);
module_param_named(mutex_path, mutex_path_override, charp, 0); MODULE_PARM_DESC(mutex_path,
From: Mark Brown broonie@kernel.org
commit c0a454b9044fdc99486853aa424e5b3be2107078 upstream.
GCC does not insert a `bti c` instruction at the beginning of a function when it believes that all callers reach the function through a direct branch[1]. Unfortunately the logic it uses to determine this is not sufficiently robust, for example not taking account of functions being placed in different sections which may be loaded separately, so we may still see thunks being generated to these functions. If that happens, the first instruction in the callee function will result in a Branch Target Exception due to the missing landing pad.
While this has currently only been observed in the case of modules having their main code loaded sufficiently far from their init section to require thunks it could potentially happen for other cases so the safest thing is to disable BTI for the kernel when building with an affected toolchain.
[1]: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106671
Reported-by: D Scott Phillips scott@os.amperecomputing.com [Bits of the commit message are lifted from his report & workaround] Signed-off-by: Mark Brown broonie@kernel.org Link: https://lore.kernel.org/r/20220905142255.591990-1-broonie@kernel.org Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/Kconfig | 2 ++ 1 file changed, 2 insertions(+)
--- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1884,6 +1884,8 @@ config ARM64_BTI_KERNEL depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697 depends on !CC_IS_GCC || GCC_VERSION >= 100100 + # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106671 + depends on !CC_IS_GCC # https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc7... depends on !CC_IS_CLANG || CLANG_VERSION >= 120000 depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
From: Lu Baolu baolu.lu@linux.intel.com
commit 53fc7ad6edf210b497230ce74b61b322a202470c upstream.
The Intel IOMMU driver possibly selects between the first-level and the second-level translation tables for DMA address translation. However, the levels of page-table walks for the 4KB base page size are calculated from the SAGAW field of the capability register, which is only valid for the second-level page table. This causes the IOMMU driver to stop working if the hardware (or the emulated IOMMU) advertises only first-level translation capability and reports the SAGAW field as 0.
This solves the above problem by considering both the first level and the second level when calculating the supported page table levels.
Fixes: b802d070a52a1 ("iommu/vt-d: Use iova over first level") Cc: stable@vger.kernel.org Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220817023558.3253263-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iommu/intel/iommu.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-)
--- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -422,14 +422,36 @@ static inline int domain_pfn_supported(s return !(addr_width < BITS_PER_LONG && pfn >> addr_width); }
+/* + * Calculate the Supported Adjusted Guest Address Widths of an IOMMU. + * Refer to 11.4.2 of the VT-d spec for the encoding of each bit of + * the returned SAGAW. + */ +static unsigned long __iommu_calculate_sagaw(struct intel_iommu *iommu) +{ + unsigned long fl_sagaw, sl_sagaw; + + fl_sagaw = BIT(2) | (cap_fl1gp_support(iommu->cap) ? BIT(3) : 0); + sl_sagaw = cap_sagaw(iommu->cap); + + /* Second level only. */ + if (!sm_supported(iommu) || !ecap_flts(iommu->ecap)) + return sl_sagaw; + + /* First level only. */ + if (!ecap_slts(iommu->ecap)) + return fl_sagaw; + + return fl_sagaw & sl_sagaw; +} + static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw) { unsigned long sagaw; int agaw;
- sagaw = cap_sagaw(iommu->cap); - for (agaw = width_to_agaw(max_gaw); - agaw >= 0; agaw--) { + sagaw = __iommu_calculate_sagaw(iommu); + for (agaw = width_to_agaw(max_gaw); agaw >= 0; agaw--) { if (test_bit(agaw, &sagaw)) break; }
From: Jean-Philippe Brucker jean-philippe@linaro.org
commit 91c98fe7941499e4127cdc359c30841b873dd43a upstream.
Commit e8ae0e140c05 ("vfio: Require that devices support DMA cache coherence") requires IOMMU drivers to advertise IOMMU_CAP_CACHE_COHERENCY, in order to be used by VFIO. Since VFIO does not provide to userspace the ability to maintain coherency through cache invalidations, it requires hardware coherency. Advertise the capability in order to restore VFIO support.
The meaning of IOMMU_CAP_CACHE_COHERENCY also changed from "IOMMU can enforce cache coherent DMA transactions" to "IOMMU_CACHE is supported". While virtio-iommu cannot enforce coherency (of PCIe no-snoop transactions), it does support IOMMU_CACHE.
We can distinguish different cases of non-coherent DMA:
(1) When accesses from a hardware endpoint are not coherent. The host would describe such a device using firmware methods ('dma-coherent' in device-tree, '_CCA' in ACPI), since they are also needed without a vIOMMU. In this case mappings are created without IOMMU_CACHE. virtio-iommu doesn't need any additional support. It sends the same requests as for coherent devices.
(2) When the physical IOMMU supports non-cacheable mappings. Supporting those would require a new feature in virtio-iommu, new PROBE request property and MAP flags. Device drivers would use a new API to discover this since it depends on the architecture and the physical IOMMU.
(3) When the hardware supports PCIe no-snoop. It is possible for assigned PCIe devices to issue no-snoop transactions, and the virtio-iommu specification is lacking any mention of this.
Arm platforms don't necessarily support no-snoop, and those that do cannot enforce coherency of no-snoop transactions. Device drivers must be careful about assuming that no-snoop transactions won't end up cached; see commit e02f5c1bb228 ("drm: disable uncached DMA optimization for ARM and arm64"). On x86 platforms, the host may or may not enforce coherency of no-snoop transactions with the physical IOMMU. But according to the above commit, on x86 a driver which assumes that no-snoop DMA is compatible with uncached CPU mappings will also work if the host enforces coherency.
Although these issues are not specific to virtio-iommu, it could be used to facilitate discovery and configuration of no-snoop. This would require a new feature bit, PROBE property and ATTACH/MAP flags.
Cc: stable@vger.kernel.org Fixes: e8ae0e140c05 ("vfio: Require that devices support DMA cache coherence") Signed-off-by: Jean-Philippe Brucker jean-philippe@linaro.org Reviewed-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/20220825154622.86759-1-jean-philippe@linaro.org Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iommu/virtio-iommu.c | 11 +++++++++++ 1 file changed, 11 insertions(+)
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 08eeafc9529f..80151176ba12 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1006,7 +1006,18 @@ static int viommu_of_xlate(struct device *dev, struct of_phandle_args *args) return iommu_fwspec_add_ids(dev, args->args, 1); }
+static bool viommu_capable(enum iommu_cap cap) +{ + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return true; + default: + return false; + } +} + static struct iommu_ops viommu_ops = { + .capable = viommu_capable, .domain_alloc = viommu_domain_alloc, .probe_device = viommu_probe_device, .probe_finalize = viommu_probe_finalize,
From: Jason Gunthorpe jgg@nvidia.com
commit 2380f1e8195ef612deea1dc7a3d611c5d2b9b56a upstream.
The AMD IOMMU driver cannot activate PASID mode on a RID without the RID's translation being set to IDENTITY. Further it requires changing the RID's page table layout from the normal v1 IOMMU_DOMAIN_IDENTITY layout to a different v2 layout.
It does this by creating a new iommu_domain, configuring that domain for v2 identity operation and then attaching it to the group, from within the driver. This logic assumes the group is already set to the IDENTITY domain and is being used by the DMA API.
However, since the ownership logic is based on the group's domain pointer equaling the default domain to detect DMA API ownership, this causes it to look like the group is not attached to the DMA API any more. This blocks attaching drivers to any other devices in the group.
In a real system this manifests itself as the HD-audio devices on some AMD platforms losing their device drivers.
Work around this unique behavior of the AMD driver by checking for equality of IDENTITY domains based on their type, not their pointer value. This allows the AMD driver to have two IDENTITY domains for internal purposes without breaking the check.
Have the AMD driver properly declare that the special domain it created is actually an IDENTITY domain.
Cc: Robin Murphy robin.murphy@arm.com Cc: stable@vger.kernel.org Fixes: 512881eacfa7 ("bus: platform,amba,fsl-mc,PCI: Add device DMA ownership management") Reported-by: Takashi Iwai tiwai@suse.de Tested-by: Takashi Iwai tiwai@suse.de Signed-off-by: Jason Gunthorpe jgg@nvidia.com Reviewed-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/0-v1-ea566e16b06b+811-amd_owner_jgg@nvidia.com Signed-off-by: Joerg Roedel jroedel@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iommu/amd/iommu_v2.c | 2 ++ drivers/iommu/iommu.c | 21 +++++++++++++++++++-- 2 files changed, 21 insertions(+), 2 deletions(-)
--- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -786,6 +786,8 @@ int amd_iommu_init_device(struct pci_dev if (dev_state->domain == NULL) goto out_free_states;
+ /* See iommu_is_default_domain() */ + dev_state->domain->type = IOMMU_DOMAIN_IDENTITY; amd_iommu_domain_direct_map(dev_state->domain);
ret = amd_iommu_domain_enable_v2(dev_state->domain, pasids); --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3089,6 +3089,24 @@ out: return ret; }
+static bool iommu_is_default_domain(struct iommu_group *group) +{ + if (group->domain == group->default_domain) + return true; + + /* + * If the default domain was set to identity and it is still an identity + * domain then we consider this a pass. This happens because of + * amd_iommu_init_device() replacing the default idenytity domain with an + * identity domain that has a different configuration for AMDGPU. + */ + if (group->default_domain && + group->default_domain->type == IOMMU_DOMAIN_IDENTITY && + group->domain && group->domain->type == IOMMU_DOMAIN_IDENTITY) + return true; + return false; +} + /** * iommu_device_use_default_domain() - Device driver wants to handle device * DMA through the kernel DMA API. @@ -3107,8 +3125,7 @@ int iommu_device_use_default_domain(stru
mutex_lock(&group->mutex); if (group->owner_cnt) { - if (group->domain != group->default_domain || - group->owner) { + if (group->owner || !iommu_is_default_domain(group)) { ret = -EBUSY; goto unlock_out; }
From: Saaem Rizvi SyedSaaem.Rizvi@amd.com
commit 4b33b5ffcf68de3a43e7dddc91c5dc86e6ed8587 upstream.
[WHY] Logging for SMU response value after the wait allows us to know immediately what the response value was. Makes it easier to debug should the value be anything other than OK.
[HOW] Using the the already available DC SMU logging functions.
Tested-by: Daniel Wheeler daniel.wheeler@amd.com Reviewed-by: Charlene Liu Charlene.Liu@amd.com Acked-by: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Signed-off-by: Saaem Rizvi SyedSaaem.Rizvi@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c | 12 ++++++++++ drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c | 12 ++++++++++ drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c | 8 ++++++ drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c | 8 ++++++ drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c | 8 ++++++ 5 files changed, 48 insertions(+)
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c @@ -41,6 +41,12 @@ #define FN(reg_name, field) \ FD(reg_name##__##field)
+#include "logger_types.h" +#undef DC_LOGGER +#define DC_LOGGER \ + CTX->logger +#define smu_print(str, ...) {DC_LOG_SMU(str, ##__VA_ARGS__); } + #define VBIOSSMC_MSG_TestMessage 0x1 #define VBIOSSMC_MSG_GetSmuVersion 0x2 #define VBIOSSMC_MSG_PowerUpGfx 0x3 @@ -97,6 +103,12 @@ static int rn_vbios_smu_send_msg_with_pa result = rn_smu_wait_for_response(clk_mgr, 10, 200000); ASSERT(result == VBIOSSMC_Result_OK);
+ smu_print("SMU response after wait: %d\n", result); + + if (result == VBIOSSMC_Status_BUSY) { + return -1; + } + /* First clear response register */ REG_WRITE(MP1_SMN_C2PMSG_91, VBIOSSMC_Status_BUSY);
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c @@ -41,6 +41,12 @@ #define FN(reg_name, field) \ FD(reg_name##__##field)
+#include "logger_types.h" +#undef DC_LOGGER +#define DC_LOGGER \ + CTX->logger +#define smu_print(str, ...) {DC_LOG_SMU(str, ##__VA_ARGS__); } + #define VBIOSSMC_MSG_GetSmuVersion 0x2 #define VBIOSSMC_MSG_SetDispclkFreq 0x4 #define VBIOSSMC_MSG_SetDprefclkFreq 0x5 @@ -96,6 +102,12 @@ static int dcn301_smu_send_msg_with_para
result = dcn301_smu_wait_for_response(clk_mgr, 10, 200000);
+ smu_print("SMU response after wait: %d\n", result); + + if (result == VBIOSSMC_Status_BUSY) { + return -1; + } + /* First clear response register */ REG_WRITE(MP1_SMN_C2PMSG_91, VBIOSSMC_Status_BUSY);
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c @@ -40,6 +40,12 @@ #define FN(reg_name, field) \ FD(reg_name##__##field)
+#include "logger_types.h" +#undef DC_LOGGER +#define DC_LOGGER \ + CTX->logger +#define smu_print(str, ...) {DC_LOG_SMU(str, ##__VA_ARGS__); } + #define VBIOSSMC_MSG_TestMessage 0x1 #define VBIOSSMC_MSG_GetSmuVersion 0x2 #define VBIOSSMC_MSG_PowerUpGfx 0x3 @@ -104,6 +110,8 @@ static int dcn31_smu_send_msg_with_param result = dcn31_smu_wait_for_response(clk_mgr, 10, 200000); ASSERT(result == VBIOSSMC_Result_OK);
+ smu_print("SMU response after wait: %d\n", result); + if (result == VBIOSSMC_Status_BUSY) { return -1; } --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -70,6 +70,12 @@ static const struct IP_BASE NBIO_BASE = #define REG_NBIO(reg_name) \ (NBIO_BASE.instance[0].segment[regBIF_BX_PF2_ ## reg_name ## _BASE_IDX] + regBIF_BX_PF2_ ## reg_name)
+#include "logger_types.h" +#undef DC_LOGGER +#define DC_LOGGER \ + CTX->logger +#define smu_print(str, ...) {DC_LOG_SMU(str, ##__VA_ARGS__); } + #define mmMP1_C2PMSG_3 0x3B1050C
#define VBIOSSMC_MSG_TestMessage 0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team @@ -132,6 +138,8 @@ static int dcn315_smu_send_msg_with_para result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000); ASSERT(result == VBIOSSMC_Result_OK);
+ smu_print("SMU response after wait: %d\n", result); + if (result == VBIOSSMC_Status_BUSY) { return -1; } --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c @@ -58,6 +58,12 @@ static const struct IP_BASE MP0_BASE = { #define FN(reg_name, field) \ FD(reg_name##__##field)
+#include "logger_types.h" +#undef DC_LOGGER +#define DC_LOGGER \ + CTX->logger +#define smu_print(str, ...) {DC_LOG_SMU(str, ##__VA_ARGS__); } + #define VBIOSSMC_MSG_TestMessage 0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team #define VBIOSSMC_MSG_GetPmfwVersion 0x02 ///< Get PMFW version #define VBIOSSMC_MSG_Spare0 0x03 ///< Spare0 @@ -120,6 +126,8 @@ static int dcn316_smu_send_msg_with_para result = dcn316_smu_wait_for_response(clk_mgr, 10, 200000); ASSERT(result == VBIOSSMC_Result_OK);
+ smu_print("SMU response after wait: %d\n", result); + if (result == VBIOSSMC_Status_BUSY) { return -1; }
From: Saaem Rizvi SyedSaaem.Rizvi@amd.com
commit 149f6d1a6035a7aa6595ac6eeb9c8f566b2103cd upstream.
[WHY] Assert statements causing several bugs on Linux DM
[HOW] Removing assert statement for Linux DM (ASSERT(result == VBIOSSMC_Result_OK)). Also adding logging statements for setting dcfclk.
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=216092 Fixes: c1b972a18d05 ("drm/amd/display: Insert pulling smu busy status before sending another request") Reviewed-by: Gabe Teeger Gabe.Teeger@amd.com Acked-by: Solomon Chiu solomon.chiu@amd.com Signed-off-by: Saaem Rizvi SyedSaaem.Rizvi@amd.com Tested-by: Daniel Wheeler daniel.wheeler@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c | 8 ++++++-- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c | 7 ++++++- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c | 8 ++++++-- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c | 8 ++++++-- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c | 8 ++++++-- 5 files changed, 30 insertions(+), 9 deletions(-)
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c @@ -101,9 +101,9 @@ static int rn_vbios_smu_send_msg_with_pa uint32_t result;
result = rn_smu_wait_for_response(clk_mgr, 10, 200000); - ASSERT(result == VBIOSSMC_Result_OK);
- smu_print("SMU response after wait: %d\n", result); + if (result != VBIOSSMC_Result_OK) + smu_print("SMU Response was not OK. SMU response after wait received is: %d\n", result);
if (result == VBIOSSMC_Status_BUSY) { return -1; @@ -188,6 +188,10 @@ int rn_vbios_smu_set_hard_min_dcfclk(str VBIOSSMC_MSG_SetHardMinDcfclkByFreq, khz_to_mhz_ceil(requested_dcfclk_khz));
+#ifdef DBG + smu_print("actual_dcfclk_set_mhz %d is set to : %d\n", actual_dcfclk_set_mhz, actual_dcfclk_set_mhz * 1000); +#endif + return actual_dcfclk_set_mhz * 1000; }
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/dcn301_smu.c @@ -102,7 +102,8 @@ static int dcn301_smu_send_msg_with_para
result = dcn301_smu_wait_for_response(clk_mgr, 10, 200000);
- smu_print("SMU response after wait: %d\n", result); + if (result != VBIOSSMC_Result_OK) + smu_print("SMU Response was not OK. SMU response after wait received is: %d\n", result);
if (result == VBIOSSMC_Status_BUSY) { return -1; @@ -179,6 +180,10 @@ int dcn301_smu_set_hard_min_dcfclk(struc VBIOSSMC_MSG_SetHardMinDcfclkByFreq, khz_to_mhz_ceil(requested_dcfclk_khz));
+#ifdef DBG + smu_print("actual_dcfclk_set_mhz %d is set to : %d\n", actual_dcfclk_set_mhz, actual_dcfclk_set_mhz * 1000); +#endif + return actual_dcfclk_set_mhz * 1000; }
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c @@ -108,9 +108,9 @@ static int dcn31_smu_send_msg_with_param uint32_t result;
result = dcn31_smu_wait_for_response(clk_mgr, 10, 200000); - ASSERT(result == VBIOSSMC_Result_OK);
- smu_print("SMU response after wait: %d\n", result); + if (result != VBIOSSMC_Result_OK) + smu_print("SMU Response was not OK. SMU response after wait received is: %d\n", result);
if (result == VBIOSSMC_Status_BUSY) { return -1; @@ -202,6 +202,10 @@ int dcn31_smu_set_hard_min_dcfclk(struct VBIOSSMC_MSG_SetHardMinDcfclkByFreq, khz_to_mhz_ceil(requested_dcfclk_khz));
+#ifdef DBG + smu_print("actual_dcfclk_set_mhz %d is set to : %d\n", actual_dcfclk_set_mhz, actual_dcfclk_set_mhz * 1000); +#endif + return actual_dcfclk_set_mhz * 1000; }
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -136,9 +136,9 @@ static int dcn315_smu_send_msg_with_para uint32_t result;
result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000); - ASSERT(result == VBIOSSMC_Result_OK);
- smu_print("SMU response after wait: %d\n", result); + if (result != VBIOSSMC_Result_OK) + smu_print("SMU Response was not OK. SMU response after wait received is: %d\n", result);
if (result == VBIOSSMC_Status_BUSY) { return -1; @@ -205,6 +205,10 @@ int dcn315_smu_set_hard_min_dcfclk(struc VBIOSSMC_MSG_SetHardMinDcfclkByFreq, khz_to_mhz_ceil(requested_dcfclk_khz));
+#ifdef DBG + smu_print("actual_dcfclk_set_mhz %d is set to : %d\n", actual_dcfclk_set_mhz, actual_dcfclk_set_mhz * 1000); +#endif + return actual_dcfclk_set_mhz * 1000; }
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_smu.c @@ -124,9 +124,9 @@ static int dcn316_smu_send_msg_with_para uint32_t result;
result = dcn316_smu_wait_for_response(clk_mgr, 10, 200000); - ASSERT(result == VBIOSSMC_Result_OK);
- smu_print("SMU response after wait: %d\n", result); + if (result != VBIOSSMC_Result_OK) + smu_print("SMU Response was not OK. SMU response after wait received is: %d\n", result);
if (result == VBIOSSMC_Status_BUSY) { return -1; @@ -191,6 +191,10 @@ int dcn316_smu_set_hard_min_dcfclk(struc VBIOSSMC_MSG_SetHardMinDcfclkByFreq, khz_to_mhz_ceil(requested_dcfclk_khz));
+#ifdef DBG + smu_print("actual_dcfclk_set_mhz %d is set to : %d\n", actual_dcfclk_set_mhz, actual_dcfclk_set_mhz * 1000); +#endif + return actual_dcfclk_set_mhz * 1000; }
On 2022-09-13 16:01, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1....
404: no popcorn
Some of the others are available, some are not. Mirrors acting up again?
thanks, Holger
On Tue, Sep 13, 2022 at 05:20:04PM +0200, Holger Hoffstätte wrote:
On 2022-09-13 16:01, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1....
404: no popcorn
Some of the others are available, some are not. Mirrors acting up again?
Nope, my fault, sorry, new laptop, had to add another perl dependency that I had missed. I'll go upload them all again...
thanks,
greg k-h
On Tue, Sep 13, 2022 at 06:07:38PM +0200, Greg Kroah-Hartman wrote:
On Tue, Sep 13, 2022 at 05:20:04PM +0200, Holger Hoffstätte wrote:
On 2022-09-13 16:01, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1....
404: no popcorn
Some of the others are available, some are not. Mirrors acting up again?
Nope, my fault, sorry, new laptop, had to add another perl dependency that I had missed. I'll go upload them all again...
Ok, all uploaded again, should hit the mirrors in a bit, let me know if that didn't work in an hour or so.
thanks,
greg k-h
Hey Greg,
Ran tests and boot tested on my system, no regressions found
Tested-by: Fenil Jain fkjainco@gmail.com
On Tue, 13 Sept 2022 at 19:38, Greg Kroah-Hartman gregkh@linuxfoundation.org wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1.... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.19.y and the diffstat can be found below.
thanks,
greg k-h
Results from Linaro's test farm. No regressions on arm64, arm, x86_64, and i386.
Tested-by: Linux Kernel Functional Testing lkft@linaro.org
NOTE: Following Warning noticed on bcm2711-rpi-4-b while running LTP fs iogen01 tests and this kernel built with 64k Page size with NFS mounted file system. - CONFIG_ARM64_64K_PAGES=y
This warning is not always reproducible.
[ 1152.014544] ------------[ cut here ]------------ [ 1152.019249] WARNING: CPU: 3 PID: 56 at net/sunrpc/clnt.c:2521 call_decode+0x210/0x240 [ 1152.027211] Modules linked in: algif_hash aes_neon_bs aes_neon_blk xhci_pci xhci_pci_renesas snd_soc_hdmi_codec raspberrypi_cpufreq hci_uart brcmfmac btqca brcmutil btbcm bluetooth cfg80211 vc4 raspberrypi_hwmon rfkill cec reset_raspberrypi clk_raspberrypi bcm2711_thermal iproc_rng200 rng_core drm_display_helper i2c_bcm2835 drm_cma_helper pwm_bcm2835 drm_kms_helper pcie_brcmstb crct10dif_ce fuse drm [ 1152.063204] CPU: 3 PID: 56 Comm: kworker/u8:3 Not tainted 5.19.9-rc1 #1 [ 1152.069920] Hardware name: Raspberry Pi 4 Model B (DT) [ 1152.075131] Workqueue: rpciod rpc_async_schedule [ 1152.079826] pstate: 00000005 (nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 1152.086894] pc : call_decode+0x210/0x240 [ 1152.090874] lr : call_decode+0xd8/0x240 [ 1152.094766] sp : ffff80000bcefca0 [ 1152.098123] x29: ffff80000bcefca0 x28: ffff800009285500 x27: ffff80000aa78a70 [ 1152.105378] x26: 0000000004248160 x25: ffff80000a110008 x24: 0000000000000001 [ 1152.112630] x23: ffff80000a110008 x22: ffff80000aa78000 x21: ffff00004ca1c050 [ 1152.119880] x20: ffff00004ca1c000 x19: ffff00004d270f90 x18: 0000000000000000 [ 1152.127129] x17: 00d0070000000000 x16: 0000000000000000 x15: ffff0000fba2b000 [ 1152.134378] x14: 0000000000000000 x13: 0000000000000002 x12: 0000000000000000 [ 1152.141626] x11: 0000000000000000 x10: 0000000000000be0 x9 : ffff8000092a15ec [ 1152.148874] x8 : fefefefefefefeff x7 : 0000000000000018 x6 : ffff00004d271238 [ 1152.156123] x5 : 800aad4b0000ffff x4 : ffff00004d271238 x3 : 0000000000000000 [ 1152.163371] x2 : 0000000000000008 x1 : ffff00004ca1c160 x0 : 00000000ffffffff [ 1152.170620] Call trace: [ 1152.173098] call_decode+0x210/0x240 [ 1152.176725] __rpc_execute+0xac/0x6a4 [ 1152.180443] rpc_async_schedule+0x34/0x5c [ 1152.184512] process_one_work+0x1dc/0x450 [ 1152.188583] worker_thread+0x154/0x450 [ 1152.192385] kthread+0xfc/0x110 [ 1152.195578] ret_from_fork+0x10/0x20 [ 1152.199207] ---[ end trace 0000000000000000 ]---
https://lkft.validation.linaro.org/scheduler/job/5525031#L1343 https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.19.y/build/v5.19....
## Build * kernel: 5.19.9-rc1 * git: https://gitlab.com/Linaro/lkft/mirrors/stable/linux-stable-rc * git branch: linux-5.19.y * git commit: 318d4f28213a0b7494405e08920cdd5e649199eb * git describe: v5.19.8-193-g318d4f28213a * test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.19.y/build/v5.19....
## No test Regressions (compared to v5.19.8)
## No metric Regressions (compared to v5.19.8)
## No test Fixes (compared to v5.19.8)
## No metric Fixes (compared to v5.19.8)
## Test result summary total: 113663, pass: 100760, fail: 903, skip: 11686, xfail: 314
## Build Summary * arc: 10 total, 10 passed, 0 failed * arm: 333 total, 333 passed, 0 failed * arm64: 65 total, 63 passed, 2 failed * i386: 55 total, 53 passed, 2 failed * mips: 56 total, 56 passed, 0 failed * parisc: 12 total, 12 passed, 0 failed * powerpc: 69 total, 63 passed, 6 failed * riscv: 27 total, 22 passed, 5 failed * s390: 21 total, 21 passed, 0 failed * sh: 24 total, 24 passed, 0 failed * sparc: 12 total, 12 passed, 0 failed * x86_64: 58 total, 56 passed, 2 failed
## Test suites summary * fwts * igt-gpu-tools * kselftest-android * kselftest-arm64 * kselftest-arm64/arm64.btitest.bti_c_func * kselftest-arm64/arm64.btitest.bti_j_func * kselftest-arm64/arm64.btitest.bti_jc_func * kselftest-arm64/arm64.btitest.bti_none_func * kselftest-arm64/arm64.btitest.nohint_func * kselftest-arm64/arm64.btitest.paciasp_func * kselftest-arm64/arm64.nobtitest.bti_c_func * kselftest-arm64/arm64.nobtitest.bti_j_func * kselftest-arm64/arm64.nobtitest.bti_jc_func * kselftest-arm64/arm64.nobtitest.bti_none_func * kselftest-arm64/arm64.nobtitest.nohint_func * kselftest-arm64/arm64.nobtitest.paciasp_func * kselftest-breakpoints * kselftest-capabilities * kselftest-cgroup * kselftest-clone3 * kselftest-core * kselftest-cpu-hotplug * kselftest-cpufreq * kselftest-drivers-dma-buf * kselftest-efivarfs * kselftest-filesystems * kselftest-filesystems-binderfs * kselftest-firmware * kselftest-fpu * kselftest-futex * kselftest-gpio * kselftest-intel_pstate * kselftest-ipc * kselftest-ir * kselftest-kcmp * kselftest-kexec * kselftest-kvm * kselftest-lib * kselftest-livepatch * kselftest-membarrier * kselftest-memfd * kselftest-memory-hotplug * kselftest-mincore * kselftest-mount * kselftest-mqueue * kselftest-netfilter * kselftest-nsfs * kselftest-openat2 * kselftest-pid_namespace * kselftest-pidfd * kselftest-proc * kselftest-pstore * kselftest-ptrace * kselftest-rseq * kselftest-rtc * kselftest-seccomp * kselftest-sigaltstack * kselftest-size * kselftest-splice * kselftest-static_keys * kselftest-sync * kselftest-sysctl * kselftest-tc-testing * kselftest-timens * kselftest-timers * kselftest-tmpfs * kselftest-tpm2 * kselftest-user * kselftest-vm * kselftest-x86 * kselftest-zram * kunit * kvm-unit-tests * libgpiod * libhugetlbfs * log-parser-boot * log-parser-test * ltp-cap_bounds * ltp-commands * ltp-containers * ltp-controllers * ltp-cpuhotplug * ltp-crypto * ltp-cve * ltp-dio * ltp-fcntl-locktests * ltp-filecaps * ltp-fs * ltp-fs_bind * ltp-fs_perms_simple * ltp-fsx * ltp-hugetlb * ltp-io * ltp-ipc * ltp-math * ltp-mm * ltp-nptl * ltp-open-posix-tests * ltp-pty * ltp-sched * ltp-securebits * ltp-smoke * ltp-syscalls * ltp-tracing * network-basic-tests * packetdrill * perf * perf/Zstd-perf.data-compression * rcutorture * v4l2-compliance * vdso
-- Linaro LKFT https://lkft.linaro.org
Hi Greg,
On Tue, Sep 13, 2022 at 04:01:46PM +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
Build test (gcc version 12.2.1 20220819): mips: 59 configs -> no failure arm: 99 configs -> no failure arm64: 3 configs -> no failure x86_64: 4 configs -> no failure alpha allmodconfig -> no failure csky allmodconfig -> no failure powerpc allmodconfig -> no failure riscv allmodconfig -> no failure s390 allmodconfig -> no failure xtensa allmodconfig -> no failure
Boot test: x86_64: Booted on my test laptop. No regression. x86_64: Booted on qemu. No regression. [1] arm64: Booted on rpi4b (4GB model). No regression. [2] mips: Booted on ci20 board. No regression. [3]
[1]. https://openqa.qa.codethink.co.uk/tests/1821 [2]. https://openqa.qa.codethink.co.uk/tests/1826 [3]. https://openqa.qa.codethink.co.uk/tests/1828
Tested-by: Sudip Mukherjee sudip.mukherjee@codethink.co.uk
-- Regards Sudip
On Tue, Sep 13, 2022 at 04:01:46PM +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Successfully cross-compiled for arm64 (bcm2711_defconfig, GCC 10.2.0) and powerpc (ps3_defconfig, GCC 12.1.0).
Tested-by: Bagas Sanjaya bagasdotme@gmail.com
On 9/13/22 7:01 AM, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1.... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.19.y and the diffstat can be found below.
thanks,
greg k-h
Built and booted successfully on RISC-V RV64 (HiFive Unmatched).
Tested-by: Ron Economos re@w6rz.net
On Tue, Sep 13, 2022 at 04:01:46PM +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1.... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.19.y and the diffstat can be found below.
thanks,
greg k-h
Pseudo-Shortlog of commits:
[ ... ]
Csókás Bence csokas.bence@prolan.hu net: fec: Use a spinlock to guard `fep->ptp_clk_on`
This commit is broken, will be reverted upstream, and should not be applied to any stable releases.
Guenter
On Wed, Sep 14, 2022 at 07:28:43AM -0700, Guenter Roeck wrote:
On Tue, Sep 13, 2022 at 04:01:46PM +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1.... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.19.y and the diffstat can be found below.
thanks,
greg k-h
Pseudo-Shortlog of commits:
[ ... ]
Csókás Bence csokas.bence@prolan.hu net: fec: Use a spinlock to guard `fep->ptp_clk_on`
This commit is broken, will be reverted upstream, and should not be applied to any stable releases.
Already dropped from all queues, thanks.
greg k-h
On 9/13/22 07:01, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1.... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.19.y and the diffstat can be found below.
thanks,
greg k-h
On ARCH_BRCMSTB using 32-bit and 64-bit ARM kernels, build tested on BMIPS_GENERIC:
Tested-by: Florian Fainelli f.fainelli@gmail.com
On Tue, Sep 13, 2022 at 04:01:46PM +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
Build results: total: 150 pass: 150 fail: 0 Qemu test results: total: 490 pass: 490 fail: 0
New runtime warning
BUG: sleeping function called from invalid context at drivers/clk/imx/clk-pllv3.c:68
thanks to:
Csókás Bence csokas.bence@prolan.hu net: fec: Use a spinlock to guard `fep->ptp_clk_on`
In the assumption that this patch will be dropped
Tested-by: Guenter Roeck linux@roeck-us.net
Guenter
On 9/14/2022 5:09 PM, Guenter Roeck wrote:
On Tue, Sep 13, 2022 at 04:01:46PM +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
Build results: total: 150 pass: 150 fail: 0 Qemu test results: total: 490 pass: 490 fail: 0
New runtime warning
BUG: sleeping function called from invalid context at drivers/clk/imx/clk-pllv3.c:68
thanks to:
Csókás Bence csokas.bence@prolan.hu net: fec: Use a spinlock to guard `fep->ptp_clk_on`
In the assumption that this patch will be dropped
Tested-by: Guenter Roeck linux@roeck-us.net
It is being reverted upstream:
https://lore.kernel.org/netdev/20220912070143.98153-1-francesco.dolcini@tora...
So probably best to just drop that patch.
On Wed, Sep 14, 2022 at 07:24:42PM -0700, Florian Fainelli wrote:
On 9/14/2022 5:09 PM, Guenter Roeck wrote:
On Tue, Sep 13, 2022 at 04:01:46PM +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
Build results: total: 150 pass: 150 fail: 0 Qemu test results: total: 490 pass: 490 fail: 0
New runtime warning
BUG: sleeping function called from invalid context at drivers/clk/imx/clk-pllv3.c:68
thanks to:
Csókás Bence csokas.bence@prolan.hu net: fec: Use a spinlock to guard `fep->ptp_clk_on`
In the assumption that this patch will be dropped
Tested-by: Guenter Roeck linux@roeck-us.net
It is being reverted upstream:
https://lore.kernel.org/netdev/20220912070143.98153-1-francesco.dolcini@tora...
So probably best to just drop that patch.
It is already dropped, thanks.
greg k-h
On 13. 09. 22, 16:01, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.19.9 release. There are 192 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 15 Sep 2022 14:03:27 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.19.9-rc1.... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.19.y and the diffstat can be found below.
openSUSE configs¹⁾ all green.
Tested-by: Jiri Slaby jirislaby@kernel.org
¹⁾ armv6hl armv7hl arm64 i386 ppc64 ppc64le riscv64 s390x x86_64
linux-stable-mirror@lists.linaro.org