5.15.11-rc1 review
Subsystems (5)
Greg Kroah-Hartman
maintainercover 5.15.11-rc1 review
This is the start of the stable review cycle for the 5.15.11 release. There are 177 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 Wed, 22 Dec 2021 14:30:09 +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-5.15.11-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <[email protected]>
Linux 5.15.11-rc1
Juergen Gross <[email protected]>
xen/netback: don't queue unlimited number of packages
Juergen Gross <[email protected]>
xen/netback: fix rx queue stall detection
Juergen Gross <[email protected]>
xen/console: harden hvc_xen against event channel storms
Juergen Gross <[email protected]>
xen/netfront: harden netfront against event channel storms
Juergen Gross <[email protected]>
xen/blkfront: harden blkfront against event channel storms
Magnus Karlsson <[email protected]>
Revert "xsk: Do not sleep in poll() when need_wakeup set"
SeongJae Park <[email protected]>
selftests/damon: test debugfs file reads/writes with huge count
Tony Lindgren <[email protected]>
bus: ti-sysc: Fix variable set but not used warning for reinit_modules
Jens Axboe <[email protected]>
io-wq: drop wqe lock before creating new worker
Paul E. McKenney <[email protected]>
rcu: Mark accesses to rcu_state.n_force_qs
Jens Axboe <[email protected]>
io-wq: check for wq exit after adding new worker task_work
Jens Axboe <[email protected]>
io-wq: remove spurious bit clear on task_work addition
George Kennedy <[email protected]>
scsi: scsi_debug: Sanity check block descriptor length in resp_mode_select()
George Kennedy <[email protected]>
scsi: scsi_debug: Fix type in min_t to avoid stack OOB
George Kennedy <[email protected]>
scsi: scsi_debug: Don't call kcalloc() if size arg is zero
Miklos Szeredi <[email protected]>
ovl: fix warning in ovl_create_real()
Miklos Szeredi <[email protected]>
fuse: annotate lock in fuse_reverse_inval_entry()
Pavel Skripkin <[email protected]>
media: mxl111sf: change mutex_init() location
Alan Stern <[email protected]>
USB: core: Make do_proc_control() and do_proc_bulk() killable
Alexei Starovoitov <[email protected]>
bpf: Fix extable address check.
Jie Meng <[email protected]>
bpf, x64: Factor out emission of REX byte in more cases
Matthieu Baerts <[email protected]>
mptcp: add missing documented NL params
Magnus Karlsson <[email protected]>
xsk: Do not sleep in poll() when need_wakeup set
Fabio Estevam <[email protected]>
ARM: dts: imx6ull-pinfunc: Fix CSI_DATA07__ESAI_TX0 pad name
Matthias Schiffer <[email protected]>
can: m_can: pci: use custom bit timings for Elkhart Lake
Matthias Schiffer <[email protected]>
can: m_can: make custom bittiming fields const
Matthias Schiffer <[email protected]>
Revert "can: m_can: remove support for custom bit timing"
Mario Limonciello <[email protected]>
drm/amd/pm: fix reading SMU FW version from amdgpu_firmware_info on YC
Hawking Zhang <[email protected]>
drm/amdgpu: don't override default ECO_BITs setting
Le Ma <[email protected]>
drm/amdgpu: correct register access for RLC_JUMP_TABLE_RESTORE
Russell Currey <[email protected]>
powerpc/module_64: Fix livepatching for RO modules
George Kennedy <[email protected]>
libata: if T_LENGTH is zero, dma direction should be DMA_NONE
Adrian Hunter <[email protected]>
perf inject: Fix segfault due to perf_data__fd() without open
Adrian Hunter <[email protected]>
perf inject: Fix segfault due to close without open
Bin Meng <[email protected]>
riscv: dts: unmatched: Add gpio card detect to mmc-spi-slot
Bin Meng <[email protected]>
riscv: dts: unleashed: Add gpio card detect to mmc-spi-slot
Zqiang <[email protected]>
locking/rtmutex: Fix incorrect condition in rtmutex_spin_on_owner()
Thiago Rafael Becker <[email protected]>
cifs: sanitize multiple delimiters in prepath
Yu Liao <[email protected]>
timekeeping: Really make sure wall_to_monotonic isn't positive
Ji-Ze Hong (Peter Hong) <[email protected]>
serial: 8250_fintek: Fix garbled text for console
Tejun Heo <[email protected]>
iocost: Fix divide-by-zero on donation from low hweight cgroup
Naohiro Aota <[email protected]>
zonefs: add MODULE_ALIAS_FS
Shin'ichiro Kawasaki <[email protected]>
btrfs: fix missing blkdev_put() call in btrfs_scan_one_device()
Josef Bacik <[email protected]>
btrfs: check WRITE_ERR when trying to read an extent buffer
Filipe Manana <[email protected]>
btrfs: fix double free of anon_dev after failure to create subvolume
Jianglei Nie <[email protected]>
btrfs: fix memory leak in __add_inode_ref()
Scott Mayhew <[email protected]>
selinux: fix sleeping function called from invalid context
Daniele Palmas <[email protected]>
USB: serial: option: add Telit FN990 compositions
Johan Hovold <[email protected]>
USB: serial: cp210x: fix CP2105 GPIO registration
Marian Postevca <[email protected]>
usb: gadget: u_ether: fix race in setting MAC address in setup phase
Xu Yang <[email protected]>
usb: typec: tcpm: fix tcpm unregister port but leave a pending timer
Pawel Laszczak <[email protected]>
usb: cdnsp: Fix lack of spin_lock_irqsave/spin_lock_restore
Pawel Laszczak <[email protected]>
usb: cdnsp: Fix issue in cdnsp_log_ep trace event
Pawel Laszczak <[email protected]>
usb: cdnsp: Fix incorrect calling of cdnsp_died function
Pawel Laszczak <[email protected]>
usb: cdnsp: Fix incorrect status for control request
Nehal Bakulchandra Shah <[email protected]>
usb: xhci: Extend support for runtime power management for AMD's Yellow carp.
Chunfeng Yun <[email protected]>
usb: xhci-mtk: fix list_del warning when enable list debug
Stefan Roese <[email protected]>
PCI/MSI: Mask MSI-X vectors only on success
Thomas Gleixner <[email protected]>
PCI/MSI: Clear PCI_MSIX_FLAGS_MASKALL on error
Amelie Delaunay <[email protected]>
usb: dwc2: fix STM ID/VBUS detection startup delay in dwc2_driver_probe
Jimmy Wang <[email protected]>
USB: NO_LPM quirk Lenovo USB-C to Ethernet Adapher(RTL8153-04)
Tetsuo Handa <[email protected]>
tty: n_hdlc: make n_hdlc_tty_wakeup() asynchronous
Vitaly Kuznetsov <[email protected]>
KVM: x86: Drop guest CPUID check for host initiated writes to MSR_IA32_PERF_CAPABILITIES
Greg Kroah-Hartman <[email protected]>
Revert "usb: early: convert to readl_poll_timeout_atomic()"
Greg Kroah-Hartman <[email protected]>
USB: gadget: bRequestType is a bitfield, not a enum
Xiaoming Ni <[email protected]>
powerpc/85xx: Fix oops when CONFIG_FSL_PMC=n
Martin KaFai Lau <[email protected]>
bpf, selftests: Fix racing issue in btf_skc_cls_ingress test
Alexei Starovoitov <[email protected]>
bpf: Fix extable fixup offset.
Lakshmi Ramasubramanian <[email protected]>
arm64: kexec: Fix missing error code 'ret' warning in load_other_segments()
David Howells <[email protected]>
afs: Fix mmap
Eric Dumazet <[email protected]>
sit: do not call ipip6_dev_free() from sit_init_net()
Florian Fainelli <[email protected]>
net: systemport: Add global locking for descriptor lifecycle
D. Wythe <[email protected]>
net/smc: Prevent smc_release() from long blocking
Gal Pressman <[email protected]>
net: Fix double 0x prefix print in SKB dump
Andrey Eremeev <[email protected]>
dsa: mv88e6xxx: fix debug print for SPEED_UNFORCED
Jiasheng Jiang <[email protected]>
sfc_ef100: potential dereference of null pointer
John Keeping <[email protected]>
net: stmmac: dwmac-rk: fix oob read in rk_gmac_setup
Willem de Bruijn <[email protected]>
net/packet: rx_owner_map depends on pg_vec
Haimin Zhang <[email protected]>
netdevsim: Zero-initialize memory for new map's value in function nsim_bpf_map_alloc
Cyril Novikov <[email protected]>
ixgbe: set X550 MDIO speed before talking to PHY
Robert Schlabbach <[email protected]>
ixgbe: Document how to enable NBASE-T support
Sasha Neftin <[email protected]>
igc: Fix typo in i225 LTR functions
Letu Ren <[email protected]>
igbvf: fix double free in igbvf_probe
Karen Sornek <[email protected]>
igb: Fix removal of unicast MAC filters of VFs
Nathan Chancellor <[email protected]>
soc/tegra: fuse: Fix bitwise vs. logical OR warning
Maxim Galaganov <[email protected]>
mptcp: fix deadlock in __mptcp_push_pending()
Florian Westphal <[email protected]>
mptcp: clear 'kern' flag from fallback sockets
Florian Westphal <[email protected]>
mptcp: remove tcp ulp setsockopt support
Lang Yu <[email protected]>
drm/amd/pm: fix a potential gpu_metrics_table memory leak
Nicholas Kazlauskas <[email protected]>
drm/amd/display: Set exit_optimized_pwr_state for DCN31
Karol Kolacinski <[email protected]>
ice: Don't put stale timestamps in the skb
Karol Kolacinski <[email protected]>
ice: Use div64_u64 instead of div_u64 in adjfine
Hangyu Hua <[email protected]>
rds: memory leak in __rds_conn_create()
Baowen Zheng <[email protected]>
flow_offload: return EOPNOTSUPP for the unsupported mpls action type
Ong Boon Leong <[email protected]>
net: stmmac: fix tc flower deletion for VLAN priority Rx steering
Johannes Berg <[email protected]>
mac80211: fix lookup when adding AddBA extension element
Ilan Peer <[email protected]>
cfg80211: Acquire wiphy mutex on regulatory work
Johannes Berg <[email protected]>
mac80211: agg-tx: don't schedule_and_wake_txq() under sta->lock
Harshit Mogalapalli <[email protected]>
drm/i915/display: Fix an unsigned subtraction which can never be negative.
Jiasheng Jiang <[email protected]>
drm/ast: potential dereference of null pointer
Paolo Abeni <[email protected]>
mptcp: never allow the PM to close a listener subflow
Hangbin Liu <[email protected]>
selftest/net/forwarding: declare NETIFS p9 p10
Marek Behún <[email protected]>
net: dsa: mv88e6xxx: Unforce speed & duplex in mac_link_down()
Willem de Bruijn <[email protected]>
selftests/net: toeplitz: fix udp option
Davide Caratti <[email protected]>
net/sched: sch_ets: don't remove idle classes from the round-robin list
Alejandro Concepcion-Rodriguez <[email protected]>
drm: simpledrm: fix wrong unit with pixel clock
Alyssa Ross <[email protected]>
dmaengine: st_fdma: fix MODULE_ALIAS
Dave Jiang <[email protected]>
dmaengine: idxd: fix missed completion on abort path
David Ahern <[email protected]>
selftests: Fix IPv6 address bind tests
David Ahern <[email protected]>
selftests: Fix raw socket bind tests with VRF
David Ahern <[email protected]>
selftests: Add duplicate config only for MD5 VRF tests
Yufeng Mo <[email protected]>
net: hns3: fix race condition in debugfs
Jie Wang <[email protected]>
net: hns3: fix use-after-free bug in hclgevf_send_mbx_msg
Po-Hsu Lin <[email protected]>
selftests: icmp_redirect: pass xfail=0 to log_test()
Filip Pokryvka <[email protected]>
netdevsim: don't overwrite read only ethtool parms
Eric Dumazet <[email protected]>
inet_diag: fix kernel-infoleak for UDP sockets
Eric Dumazet <[email protected]>
sch_cake: do not call cake_destroy() from cake_init()
Philipp Rudo <[email protected]>
s390/kexec_file: fix error handling when applying relocations
Jie2x Zhou <[email protected]>
selftests: net: Correct ping6 expected rc from 2 to 1
Javier Martinez Canillas <[email protected]>
Revert "drm/fb-helper: improve DRM fbdev emulation device names"
Parav Pandit <[email protected]>
vdpa: Consider device id larger than 31
Wei Wang <[email protected]>
virtio/vsock: fix the transport to work with VMADDR_CID_ANY
Arnd Bergmann <[email protected]>
virtio: always enter drivers/virtio/
Johannes Berg <[email protected]>
iwlwifi: mvm: don't crash on invalid rate w/o STA
Stephan Gerhold <[email protected]>
soc: imx: Register SoC device only on i.MX boards
Mike Tipton <[email protected]>
clk: Don't parent clks until the parent is fully registered
Martin Kepplinger <[email protected]>
arm64: dts: imx8mq: remove interconnect property from lcdif
Dinh Nguyen <[email protected]>
ARM: socfpga: dts: fix qspi node compatible
Xiubo Li <[email protected]>
ceph: initialize pathlen variable in reconnect_caps_cb
Hu Weiwen <[email protected]>
ceph: fix duplicate increment of opened_inodes metric
Dan Carpenter <[email protected]>
tee: amdtee: fix an IS_ERR() vs NULL bug
Randy Dunlap <[email protected]>
hv: utils: add PTP_1588_CLOCK to Kconfig to fix build
Johannes Berg <[email protected]>
mac80211: track only QoS data frames for admission control
Dave Jiang <[email protected]>
dmaengine: idxd: fix calling wq quiesce inside spinlock
Dave Jiang <[email protected]>
dmaengine: idxd: add halt interrupt support
Florian Klink <[email protected]>
arm64: dts: rockchip: fix poweroff on helios64
Alex Bee <[email protected]>
arm64: dts: rockchip: fix audio-supply for Rock Pi 4
John Keeping <[email protected]>
arm64: dts: rockchip: fix rk3399-leez-p710 vcc3v3-lan supply
John Keeping <[email protected]>
arm64: dts: rockchip: fix rk3308-roc-cc vcc-sd supply
Artem Lapkin <[email protected]>
arm64: dts: rockchip: remove mmc-hs400-enhanced-strobe from rk3399-khadas-edge
Mario Limonciello <[email protected]>
pinctrl: amd: Fix wakeups when IRQ is shared with SCI
Ville Syrjälä <[email protected]>
drm/i915/hdmi: Turn DP++ TMDS output buffers back on in encoder->shutdown()
Jani Nikula <[email protected]>
drm/i915/hdmi: convert intel_hdmi_to_dev to intel_hdmi_to_i915
Jaegeuk Kim <[email protected]>
scsi: ufs: core: Retry START_STOP on UNIT_ATTENTION
Anand Jain <[email protected]>
btrfs: remove stale comment about the btrfs_show_devname
Anand Jain <[email protected]>
btrfs: update latest_dev when we create a sprout device
Anand Jain <[email protected]>
btrfs: use latest_dev in btrfs_show_devname
Anand Jain <[email protected]>
btrfs: convert latest_bdev type to btrfs_device and rename
Paul Moore <[email protected]>
audit: improve robustness of the audit queue handling
Joe Thornber <[email protected]>
dm btree remove: fix use after free in rebalance_children()
Christian Brauner <[email protected]>
ceph: fix up non-directory creation in SGID directories
Mathew McBride <[email protected]>
arm64: dts: ten64: remove redundant interrupt declaration for gpio-keys
Jerome Marchand <[email protected]>
recordmcount.pl: look for jgnop instruction as well as bcrl on s390
Sven Schnelle <[email protected]>
s390/entry: fix duplicate tracking of irq nesting level
Dan Carpenter <[email protected]>
vdpa: check that offsets are within bounds
Will Deacon <[email protected]>
virtio_ring: Fix querying of maximum DMA mapping size for virtio device
Dan Carpenter <[email protected]>
vduse: check that offset is within bounds in get_config()
Dan Carpenter <[email protected]>
vduse: fix memory corruption in vduse_dev_ioctl()
Daniel Borkmann <[email protected]>
bpf, selftests: Update test case for atomic cmpxchg on r0 with pointer
Daniel Borkmann <[email protected]>
bpf: Fix kernel address leakage in atomic cmpxchg's r0 aux reg
Daniel Borkmann <[email protected]>
bpf, selftests: Add test case trying to taint map value pointer
Daniel Borkmann <[email protected]>
bpf: Make 32->64 bounds propagation slightly more robust
Daniel Borkmann <[email protected]>
bpf: Fix signed bounds propagation after mov32
Daniel Borkmann <[email protected]>
bpf, selftests: Add test case for atomic fetch on spilled pointer
Daniel Borkmann <[email protected]>
bpf: Fix kernel address leakage in atomic fetch
Sudeep Holla <[email protected]>
firmware: arm_scpi: Fix string overflow in SCPI genpd driver
Johannes Berg <[email protected]>
mac80211: validate extended element ID is present
Felix Fietkau <[email protected]>
mac80211: send ADDBA requests using the tid/queue of the aggregation session
Johannes Berg <[email protected]>
mac80211: mark TX-during-stop for TX in in_reconfig
Felix Fietkau <[email protected]>
mac80211: fix regression in SSN handling of addba tx
Felix Fietkau <[email protected]>
mac80211: fix rate control for retransmitted frames
Lai Jiangshan <[email protected]>
KVM: X86: Fix tlb flush for tdp in kvm_invalidate_pcid()
Juergen Gross <[email protected]>
x86/kvm: remove unused ack_notifier callbacks
Paolo Bonzini <[email protected]>
KVM: downgrade two BUG_ONs to WARN_ON_ONCE
Vitaly Kuznetsov <[email protected]>
KVM: selftests: Make sure kvm_create_max_vcpus test won't hit RLIMIT_NOFILE
Paolo Bonzini <[email protected]>
KVM: VMX: clear vmx_x86_ops.sync_pir_to_irr if APICv is disabled
Jon Hunter <[email protected]>
reset: tegra-bpmp: Revert Handle errors in BPMP response
-------------
Diffstat:
.../device_drivers/ethernet/intel/ixgbe.rst | 16 +++ Makefile | 4 +- arch/arm/boot/dts/imx6ull-pinfunc.h | 2 +- arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts | 2 +- arch/arm/boot/dts/socfpga_arria5_socdk.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_socdk.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_sockit.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_socrates.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_sodia.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts | 4 +- .../arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts | 2 - arch/arm64/boot/dts/freescale/imx8mq.dtsi | 2 - arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts | 2 +- .../boot/dts/rockchip/rk3399-khadas-edge.dtsi | 1 - .../boot/dts/rockchip/rk3399-kobol-helios64.dts | 1 + arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts | 2 +- arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi | 2 +- arch/arm64/kernel/machine_kexec_file.c | 1 + arch/powerpc/kernel/module_64.c | 42 ++++-- arch/powerpc/platforms/85xx/smp.c | 4 +- .../riscv/boot/dts/sifive/hifive-unleashed-a00.dts | 1 + .../riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 2 + arch/s390/kernel/irq.c | 9 +- arch/s390/kernel/machine_kexec_file.c | 7 +- arch/x86/kvm/ioapic.h | 1 - arch/x86/kvm/irq.h | 1 - arch/x86/kvm/vmx/vmx.c | 4 +- arch/x86/kvm/x86.c | 14 +- arch/x86/net/bpf_jit_comp.c | 101 ++++++++++----- block/blk-iocost.c | 9 +- drivers/Makefile | 3 +- drivers/ata/libata-scsi.c | 15 ++- drivers/block/xen-blkfront.c | 15 ++- drivers/bus/ti-sysc.c | 3 +- drivers/clk/clk.c | 15 ++- drivers/dma/idxd/irq.c | 7 +- drivers/dma/idxd/registers.h | 1 + drivers/dma/idxd/submit.c | 18 ++- drivers/dma/st_fdma.c | 2 +- drivers/firmware/scpi_pm_domain.c | 10 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 1 - drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c | 1 - drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 2 - drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c | 1 + drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c | 3 + drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 3 + drivers/gpu/drm/ast/ast_mode.c | 5 +- drivers/gpu/drm/drm_fb_helper.c | 8 +- drivers/gpu/drm/i915/display/g4x_hdmi.c | 1 + drivers/gpu/drm/i915/display/intel_ddi.c | 1 + drivers/gpu/drm/i915/display/intel_dmc.c | 2 +- drivers/gpu/drm/i915/display/intel_hdmi.c | 32 +++-- drivers/gpu/drm/i915/display/intel_hdmi.h | 1 + drivers/gpu/drm/tiny/simpledrm.c | 2 +- drivers/hv/Kconfig | 1 + drivers/md/persistent-data/dm-btree-remove.c | 2 +- drivers/media/usb/dvb-usb-v2/mxl111sf.c | 16 ++- drivers/net/can/m_can/m_can.c | 24 +++- drivers/net/can/m_can/m_can.h | 3 + drivers/net/can/m_can/m_can_pci.c | 48 ++++++- drivers/net/dsa/mv88e6xxx/chip.c | 4 + drivers/net/dsa/mv88e6xxx/port.c | 4 +- drivers/net/ethernet/broadcom/bcmsysport.c | 5 +- drivers/net/ethernet/broadcom/bcmsysport.h | 1 + drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 + drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 20 ++- .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 3 +- drivers/net/ethernet/intel/ice/ice_ptp.c | 13 +- drivers/net/ethernet/intel/ice/ice_ptp.h | 6 + drivers/net/ethernet/intel/igb/igb_main.c | 28 ++-- drivers/net/ethernet/intel/igbvf/netdev.c | 1 + drivers/net/ethernet/intel/igc/igc_i225.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 + drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 + drivers/net/ethernet/sfc/ef100_nic.c | 3 + drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 17 +++ drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 86 ++++++++++-- drivers/net/netdevsim/bpf.c | 1 + drivers/net/netdevsim/ethtool.c | 5 +- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 5 +- drivers/net/xen-netback/common.h | 1 + drivers/net/xen-netback/rx.c | 77 +++++++---- drivers/net/xen-netfront.c | 125 +++++++++++++----- drivers/pci/msi.c | 15 ++- drivers/pinctrl/pinctrl-amd.c | 29 ++++- drivers/reset/tegra/reset-bpmp.c | 9 +- drivers/scsi/scsi_debug.c | 42 +++--- drivers/scsi/ufs/ufshcd.c | 12 +- drivers/soc/imx/soc-imx.c | 4 + drivers/soc/tegra/fuse/fuse-tegra.c | 2 +- drivers/soc/tegra/fuse/fuse.h | 2 +- drivers/tee/amdtee/core.c | 5 +- drivers/tty/hvc/hvc_xen.c | 30 ++++- drivers/tty/n_hdlc.c | 23 +++- drivers/tty/serial/8250/8250_fintek.c | 20 --- drivers/usb/cdns3/cdnsp-gadget.c | 12 ++ drivers/usb/cdns3/cdnsp-ring.c | 11 +- drivers/usb/cdns3/cdnsp-trace.h | 4 +- drivers/usb/core/devio.c | 144 ++++++++++++++++----- drivers/usb/core/quirks.c | 3 + drivers/usb/dwc2/platform.c | 3 + drivers/usb/early/xhci-dbc.c | 15 ++- drivers/usb/gadget/composite.c | 6 +- drivers/usb/gadget/function/u_ether.c | 16 +-- drivers/usb/gadget/legacy/dbgp.c | 6 +- drivers/usb/gadget/legacy/inode.c | 6 +- drivers/usb/host/xhci-mtk-sch.c | 2 +- drivers/usb/host/xhci-pci.c | 6 +- drivers/usb/serial/cp210x.c | 6 +- drivers/usb/serial/option.c | 8 ++ drivers/usb/typec/tcpm/tcpm.c | 18 ++- drivers/vdpa/vdpa.c | 3 +- drivers/vdpa/vdpa_user/vduse_dev.c | 6 +- drivers/vhost/vdpa.c | 2 +- drivers/virtio/virtio_ring.c | 2 +- drivers/xen/events/events_base.c | 6 + fs/afs/file.c | 5 +- fs/afs/super.c | 1 + fs/btrfs/disk-io.c | 14 +- fs/btrfs/extent_io.c | 10 +- fs/btrfs/inode.c | 2 +- fs/btrfs/super.c | 26 +--- fs/btrfs/tree-log.c | 1 + fs/btrfs/volumes.c | 25 ++-- fs/btrfs/volumes.h | 6 +- fs/ceph/caps.c | 16 +-- fs/ceph/file.c | 18 ++- fs/ceph/mds_client.c | 3 +- fs/cifs/fs_context.c | 38 +++++- fs/fuse/dir.c | 2 +- fs/io-wq.c | 31 ++++- fs/overlayfs/dir.c | 3 +- fs/overlayfs/overlayfs.h | 1 + fs/overlayfs/super.c | 12 +- fs/zonefs/super.c | 1 + include/uapi/linux/mptcp.h | 18 +-- include/xen/events.h | 1 + kernel/audit.c | 21 ++- kernel/bpf/verifier.c | 49 +++++-- kernel/locking/rtmutex.c | 2 +- kernel/rcu/tree.c | 10 +- kernel/time/timekeeping.c | 3 +- net/core/skbuff.c | 2 +- net/ipv4/inet_diag.c | 4 +- net/ipv6/sit.c | 1 - net/mac80211/agg-rx.c | 5 +- net/mac80211/agg-tx.c | 16 ++- net/mac80211/driver-ops.h | 5 +- net/mac80211/mlme.c | 13 +- net/mac80211/sta_info.h | 1 + net/mac80211/tx.c | 6 +- net/mac80211/util.c | 7 +- net/mptcp/pm_netlink.c | 3 + net/mptcp/protocol.c | 6 +- net/mptcp/sockopt.c | 1 - net/packet/af_packet.c | 5 +- net/rds/connection.c | 1 + net/sched/cls_api.c | 1 + net/sched/sch_cake.c | 6 +- net/sched/sch_ets.c | 4 +- net/smc/af_smc.c | 4 +- net/vmw_vsock/virtio_transport_common.c | 3 +- net/wireless/reg.c | 7 +- scripts/recordmcount.pl | 2 +- security/selinux/hooks.c | 33 +++-- tools/perf/builtin-inject.c | 13 +- .../selftests/bpf/prog_tests/btf_skc_cls_ingress.c | 16 ++- .../selftests/bpf/verifier/atomic_cmpxchg.c | 86 ++++++++++++ .../selftests/bpf/verifier/value_ptr_arith.c | 23 ++++ tools/testing/selftests/damon/.gitignore | 2 + tools/testing/selftests/damon/Makefile | 2 + tools/testing/selftests/damon/debugfs_attrs.sh | 18 +++ .../selftests/damon/huge_count_read_write.c | 39 ++++++ tools/testing/selftests/kvm/kvm_create_max_vcpus.c | 30 +++++ tools/testing/selftests/net/fcnal-test.sh | 45 +++++-- .../net/forwarding/forwarding.config.sample | 2 + tools/testing/selftests/net/icmp_redirect.sh | 2 +- tools/testing/selftests/net/toeplitz.c | 2 +- virt/kvm/kvm_main.c | 6 +- 186 files changed, 1585 insertions(+), 555 deletions(-)
Greg Kroah-Hartman
maintainerPATCH 1/177 reset: tegra-bpmp: Revert Handle errors in BPMP response
From: Jon Hunter <[email protected]>
commit 69125b4b9440be015783312e1b8753ec96febde0 upstream.
Commit c045ceb5a145 ("reset: tegra-bpmp: Handle errors in BPMP response") fixed an issue in the Tegra BPMP error handling but has exposed an issue in the Tegra194 HDA driver and now resetting the Tegra194 HDA controller is failing. For now revert the commit c045ceb5a145 ("reset: tegra-bpmp: Handle errors in BPMP response") while a fix for the Tegra HDA driver is created.
--- drivers/reset/tegra/reset-bpmp.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-)
drivers/reset/tegra/reset-bpmp.c +1 -8
@@ -20,7 +20,6 @@ static int tegra_bpmp_reset_common(strucstruct tegra_bpmp *bpmp =to_tegra_bpmp (rstc);struct mrq_reset_request request;struct tegra_bpmp_message msg; -int err;memset (&request,0 ,sizeof (request)); request.cmd = command;
@@ -31,13 +30,7 @@ static int tegra_bpmp_reset_common(struc msg.tx.data = &request; msg.tx.size =sizeof (request); - err =tegra_bpmp_transfer (bpmp, &msg); -if (err) -return err; -if (msg.rx.ret) -return -EINVAL ; - -return 0 ; +return tegra_bpmp_transfer (bpmp, &msg); } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc,
Greg Kroah-Hartman
maintainerPATCH 2/177 KVM: VMX: clear vmx_x86_ops.sync_pir_to_irr if APICv is disabled
In reply to Greg Kroah-HartmanFrom: Paolo Bonzini <[email protected]>
[ Upstream commit e90e51d5f01d2baae5dcce280866bbb96816e978 ]
There is nothing to synchronize if APICv is disabled, since neither other vCPUs nor assigned devices can set PIR.ON.
--- arch/x86/kvm/vmx/vmx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/kvm/vmx/vmx.c +2 -2
@@ -7776,10 +7776,10 @@ static __init int hardware_setup(void) ple_window_shrink =0 ; } -if (!cpu_has_vmx_apicv ()) { +if (!cpu_has_vmx_apicv ()) enable_apicv =0 ; +if (!enable_apicv) vmx_x86_ops.sync_pir_to_irr =NULL ; - }if (cpu_has_vmx_tsc_scaling ()) { kvm_has_tsc_control = true;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 3/177 KVM: selftests: Make sure kvm_create_max_vcpus test wont hit RLIMIT_NOFILE
In reply to Greg Kroah-HartmanFrom: Vitaly Kuznetsov <[email protected]>
[ Upstream commit 908fa88e420f30dde6d80f092795a18ec72ca6d3 ]
With the elevated 'KVM_CAP_MAX_VCPUS' value kvm_create_max_vcpus test may hit RLIMIT_NOFILE limits:
# ./kvm_create_max_vcpus KVM_CAP_MAX_VCPU_ID: 4096 KVM_CAP_MAX_VCPUS: 1024 Testing creating 1024 vCPUs, with IDs 0...1023. /dev/kvm not available (errno: 24), skipping test
Adjust RLIMIT_NOFILE limits to make sure KVM_CAP_MAX_VCPUS fds can be opened. Note, raising hard limit ('rlim_max') requires CAP_SYS_RESOURCE capability which is generally not needed to run kvm selftests (but without raising the limit the test is doomed to fail anyway).
Message-Id: <[email protected]>
--- .../selftests/kvm/kvm_create_max_vcpus.c | 30 +++++++++++++++++++ 1 file changed, 30 insertions(+)
tools/testing/selftests/kvm/kvm_create_max_vcpus.c +30 -0
@@ -12,6 +12,7 @@#include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/resource.h> #include "test_util.h"
@@ -40,10 +41,39 @@ int main(int argc, char *argv[]) {int kvm_max_vcpu_id =kvm_check_cap (KVM_CAP_MAX_VCPU_ID );int kvm_max_vcpus =kvm_check_cap (KVM_CAP_MAX_VCPUS ); +/* +* Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds + +* an arbitrary number for everything else. +*/ +int nr_fds_wanted = kvm_max_vcpus +100 ; +struct rlimit rl;pr_info ("KVM_CAP_MAX_VCPU_ID: %d\n" , kvm_max_vcpu_id);pr_info ("KVM_CAP_MAX_VCPUS: %d\n" , kvm_max_vcpus); +/* +* Check that we're allowed to open nr_fds_wanted file descriptors and +* try raising the limits if needed. +*/ +TEST_ASSERT (!getrlimit (RLIMIT_NOFILE , &rl),"getrlimit() failed!" ); + +if (rl.rlim_cur < nr_fds_wanted) { + rl.rlim_cur = nr_fds_wanted; +if (rl.rlim_max < nr_fds_wanted) { +int old_rlim_max = rl.rlim_max; + rl.rlim_max = nr_fds_wanted; + +int r =setrlimit (RLIMIT_NOFILE , &rl); +if (r <0 ) { +printf ("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n" , + old_rlim_max, nr_fds_wanted); +exit (KSFT_SKIP ); + } + }else { +TEST_ASSERT (!setrlimit (RLIMIT_NOFILE , &rl),"setrlimit() failed!" ); + } + } +/* * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID. * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 4/177 KVM: downgrade two BUG_ONs to WARN_ON_ONCE
In reply to Greg Kroah-HartmanFrom: Paolo Bonzini <[email protected]>
[ Upstream commit 5f25e71e311478f9bb0a8ef49e7d8b95316491d7 ]
This is not an unrecoverable situation. Users of kvm_read_guest_offset_cached and kvm_write_guest_offset_cached must expect the read/write to fail, and therefore it is possible to just return early with an error value.
--- virt/kvm/kvm_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
virt/kvm/kvm_main.c +4 -2
@@ -3001,7 +3001,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,int r;gpa_t gpa = ghc->gpa + offset; -BUG_ON (len + offset > ghc->len); +if (WARN_ON_ONCE (len + offset > ghc->len)) +return -EINVAL ;if (slots->generation != ghc->generation) {if (__kvm_gfn_to_hva_cache_init (slots, ghc, ghc->gpa, ghc->len))
@@ -3038,7 +3039,8 @@ int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,int r;gpa_t gpa = ghc->gpa + offset; -BUG_ON (len + offset > ghc->len); +if (WARN_ON_ONCE (len + offset > ghc->len)) +return -EINVAL ;if (slots->generation != ghc->generation) {if (__kvm_gfn_to_hva_cache_init (slots, ghc, ghc->gpa, ghc->len))
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 5/177 x86/kvm: remove unused ack_notifier callbacks
In reply to Greg Kroah-HartmanFrom: Juergen Gross <[email protected]>
[ Upstream commit 9dba4d24cbb5524dd39ab1e08886373b17f07ff2 ]
Commit f52447261bc8c2 ("KVM: irq ack notification") introduced an ack_notifier() callback in struct kvm_pic and in struct kvm_ioapic without using them anywhere. Remove those callbacks again.
Message-Id: <[email protected]>
--- arch/x86/kvm/ioapic.h | 1 - arch/x86/kvm/irq.h | 1 - 2 files changed, 2 deletions(-)
arch/x86/kvm/ioapic.h +0 -1
@@ -81,7 +81,6 @@ struct kvm_ioapic {unsigned long irq_states[IOAPIC_NUM_PINS ];struct kvm_io_device dev;struct kvm *kvm; -void (*ack_notifier)(void *opaque,int irq);spinlock_t lock;struct rtc_status rtc_status;struct delayed_work eoi_inject;
arch/x86/kvm/irq.h +0 -1
@@ -56,7 +56,6 @@ struct kvm_pic {struct kvm_io_device dev_master;struct kvm_io_device dev_slave;struct kvm_io_device dev_elcr; -void (*ack_notifier)(void *opaque,int irq);unsigned long irq_states[PIC_NUM_PINS ]; };
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 6/177 KVM: X86: Fix tlb flush for tdp in kvm_invalidate_pcid()
In reply to Greg Kroah-HartmanFrom: Lai Jiangshan <[email protected]>
[ Upstream commit e45e9e3998f0001079b09555db5bb3b4257f6746 ]
The KVM doesn't know whether any TLB for a specific pcid is cached in the CPU when tdp is enabled. So it is better to flush all the guest TLB when invalidating any single PCID context.
The case is very rare or even impossible since KVM generally doesn't intercept CR3 write or INVPCID instructions when tdp is enabled, so the fix is mostly for the sake of overall robustness.
Message-Id: <[email protected]>
--- arch/x86/kvm/x86.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
arch/x86/kvm/x86.c +12 -0
@@ -1091,6 +1091,18 @@ static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid)unsigned long roots_to_free =0 ;int i; +/* +* MOV CR3 and INVPCID are usually not intercepted when using TDP, but +* this is reachable when running EPT=1 and unrestricted_guest=0, and +* also via the emulator. KVM's TDP page tables are not in the scope of +* the invalidation, but the guest's TLB entries need to be flushed as +* the CPU may have cached entries in its TLB for the target PCID. +*/ +if (unlikely (tdp_enabled)) { +kvm_make_request (KVM_REQ_TLB_FLUSH_GUEST , vcpu); +return ; + } +/* * If neither the current CR3 nor any of the prev_roots use the given * PCID, then nothing needs to be done here because a resync will
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 7/177 mac80211: fix rate control for retransmitted frames
In reply to Greg Kroah-HartmanFrom: Felix Fietkau <[email protected]>
commit 18688c80ad8a8dd50523dc9276e929932cac86d4 upstream.
Since retransmission clears info->control, rate control needs to be called again, otherwise the driver might crash due to invalid rates.
--- net/mac80211/tx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
net/mac80211/tx.c +3 -3
@@ -1821,15 +1821,15 @@ static int invoke_tx_handlers_late(strucstruct ieee80211_tx_info *info =IEEE80211_SKB_CB (tx->skb);ieee80211_tx_result res =TX_CONTINUE ; +if (!ieee80211_hw_check (&tx->local->hw,HAS_RATE_CONTROL )) +CALL_TXH (ieee80211_tx_h_rate_ctrl); +if (unlikely (info->flags &IEEE80211_TX_INTFL_RETRANSMISSION )) {__skb_queue_tail (&tx->skbs, tx->skb); tx->skb =NULL ; goto txh_done; } -if (!ieee80211_hw_check (&tx->local->hw,HAS_RATE_CONTROL )) -CALL_TXH (ieee80211_tx_h_rate_ctrl); -CALL_TXH (ieee80211_tx_h_michael_mic_add);CALL_TXH (ieee80211_tx_h_sequence);CALL_TXH (ieee80211_tx_h_fragment);
Greg Kroah-Hartman
maintainerPATCH 8/177 mac80211: fix regression in SSN handling of addba tx
In reply to Greg Kroah-HartmanFrom: Felix Fietkau <[email protected]>
commit 73111efacd3c6d9e644acca1d132566932be8af0 upstream.
Some drivers that do their own sequence number allocation (e.g. ath9k) rely on being able to modify params->ssn on starting tx ampdu sessions. This was broken by a change that modified it to use sta->tid_seq[tid] instead.
--- net/mac80211/agg-tx.c | 4 ++-- net/mac80211/sta_info.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-)
net/mac80211/agg-tx.c +2 -2
@@ -480,8 +480,7 @@ static void ieee80211_send_addba_with_ti/* send AddBA request */ ieee80211_send_addba_request (sdata, sta->sta.addr, tid, - tid_tx->dialog_token, - sta->tid_seq[tid] >>4 , + tid_tx->dialog_token, tid_tx->ssn, buf_size, tid_tx->timeout);WARN_ON (test_and_set_bit (HT_AGG_STATE_SENT_ADDBA , &tid_tx->state));
@@ -523,6 +522,7 @@ void ieee80211_tx_ba_session_handle_star params.ssn = sta->tid_seq[tid] >>4 ; ret =drv_ampdu_action (local, sdata, ¶ms); + tid_tx->ssn = params.ssn;if (ret ==IEEE80211_AMPDU_TX_START_DELAY_ADDBA ) {return ; }else if (ret ==IEEE80211_AMPDU_TX_START_IMMEDIATE ) {
net/mac80211/sta_info.h +1 -0
@@ -199,6 +199,7 @@ struct tid_ampdu_tx {u8 stop_initiator;bool tx_stop;u16 buf_size; +u16 ssn;u16 failed_bar_ssn;bool bar_pending;
Greg Kroah-Hartman
maintainerPATCH 9/177 mac80211: mark TX-during-stop for TX in in_reconfig
In reply to Greg Kroah-HartmanFrom: Johannes Berg <[email protected]>
commit db7205af049d230e7e0abf61c1e74c1aab40f390 upstream.
Mark TXQs as having seen transmit while they were stopped if we bail out of drv_wake_tx_queue() due to reconfig, so that the queue wake after this will make them catch up. This is particularly necessary for when TXQs are used for management packets since those TXQs won't see a lot of traffic that'd make them catch up later.
--- net/mac80211/driver-ops.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
net/mac80211/driver-ops.h +4 -1
@@ -1219,8 +1219,11 @@ static inline void drv_wake_tx_queue(str {struct ieee80211_sub_if_data *sdata =vif_to_sdata (txq->txq.vif); -if (local->in_reconfig) +/* In reconfig don't transmit now, but mark for waking later */ +if (local->in_reconfig) { +set_bit (IEEE80211_TXQ_STOP_NETIF_TX , &txq->flags);return ; + }if (!check_sdata_in_driver (sdata))return ;
Greg Kroah-Hartman
maintainerPATCH 10/177 mac80211: send ADDBA requests using the tid/queue of the aggregation session
In reply to Greg Kroah-HartmanFrom: Felix Fietkau <[email protected]>
commit 1fe98f5690c4219d419ea9cc190f94b3401cf324 upstream.
Sending them out on a different queue can cause a race condition where a number of packets in the queue may be discarded by the receiver, because the ADDBA request is sent too early.
This affects any driver with software A-MPDU setup which does not allocate packet seqno in hardware on tx, regardless of whether iTXQ is used or not. The only driver I've seen that explicitly deals with this issue internally is mwl8k.
--- net/mac80211/agg-tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/mac80211/agg-tx.c +1 -1
@@ -106,7 +106,7 @@ static void ieee80211_send_addba_request mgmt->u.action.u.addba_req.start_seq_num =cpu_to_le16 (start_seq_num <<4 ); -ieee80211_tx_skb (sdata, skb); +ieee80211_tx_skb_tid (sdata, skb, tid); }void ieee80211_send_bar (struct ieee80211_vif *vif,u8 *ra,u16 tid,u16 ssn)
Greg Kroah-Hartman
maintainerPATCH 11/177 mac80211: validate extended element ID is present
In reply to Greg Kroah-HartmanFrom: Johannes Berg <[email protected]>
commit 768c0b19b50665e337c96858aa2b7928d6dcf756 upstream.
Before attempting to parse an extended element, verify that the extended element ID is present.
--- net/mac80211/util.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
net/mac80211/util.c +6 -1
@@ -943,7 +943,12 @@ static void ieee80211_parse_extension_el struct ieee802_11_elems *elems) {const void *data = elem->data +1 ; -u8 len = elem->datalen -1 ; +u8 len; + +if (!elem->datalen) +return ; + + len = elem->datalen -1 ;switch (elem->data[0 ]) {case WLAN_EID_EXT_HE_MU_EDCA :
Greg Kroah-Hartman
maintainerPATCH 12/177 firmware: arm_scpi: Fix string overflow in SCPI genpd driver
In reply to Greg Kroah-HartmanFrom: Sudeep Holla <[email protected]>
commit 865ed67ab955428b9aa771d8b4f1e4fb7fd08945 upstream.
Without the bound checks for scpi_pd->name, it could result in the buffer overflow when copying the SCPI device name from the corresponding device tree node as the name string is set at maximum size of 30.
Let us fix it by using devm_kasprintf so that the string buffer is allocated dynamically.
--- drivers/firmware/scpi_pm_domain.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)
drivers/firmware/scpi_pm_domain.c +7 -3
@@ -16,7 +16,6 @@ struct scpi_pm_domain {struct generic_pm_domain genpd;struct scpi_ops *ops;u32 domain; -char name[30 ]; };/*
@@ -110,8 +109,13 @@ static int scpi_pm_domain_probe(struct p scpi_pd->domain = i; scpi_pd->ops = scpi_ops; -sprintf (scpi_pd->name,"%pOFn.%d" , np, i); - scpi_pd->genpd.name = scpi_pd->name; + scpi_pd->genpd.name =devm_kasprintf (dev,GFP_KERNEL , +"%pOFn.%d" , np, i); +if (!scpi_pd->genpd.name) { +dev_err (dev,"Failed to allocate genpd name:%pOFn.%d\n" , + np, i); +continue ; + } scpi_pd->genpd.power_off = scpi_pd_power_off; scpi_pd->genpd.power_on = scpi_pd_power_on;
Greg Kroah-Hartman
maintainerPATCH 13/177 bpf: Fix kernel address leakage in atomic fetch
In reply to Greg Kroah-HartmanFrom: Daniel Borkmann <[email protected]>
commit 7d3baf0afa3aa9102d6a521a8e4c41888bb79882 upstream.
The change in commit 37086bfdc737 ("bpf: Propagate stack bounds to registers in atomics w/ BPF_FETCH") around check_mem_access() handling is buggy since this would allow for unprivileged users to leak kernel pointers. For example, an atomic fetch/and with -1 on a stack destination which holds a spilled pointer will migrate the spilled register type into a scalar, which can then be exported out of the program (since scalar != pointer) by dumping it into a map value.
The original implementation of XADD was preventing this situation by using a double call to check_mem_access() one with BPF_READ and a subsequent one with BPF_WRITE, in both cases passing -1 as a placeholder value instead of register as per XADD semantics since it didn't contain a value fetch. The BPF_READ also included a check in check_stack_read_fixed_off() which rejects the program if the stack slot is of __is_pointer_value() if dst_regno < 0. The latter is to distinguish whether we're dealing with a regular stack spill/ fill or some arithmetical operation which is disallowed on non-scalars, see also 6e7e63cbb023 ("bpf: Forbid XADD on spilled pointers for unprivileged users") for more context on check_mem_access() and its handling of placeholder value -1.
One minimally intrusive option to fix the leak is for the BPF_FETCH case to initially check the BPF_READ case via check_mem_access() with -1 as register, followed by the actual load case with non-negative load_reg to propagate stack bounds to registers.
--- kernel/bpf/verifier.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)
kernel/bpf/verifier.c +9 -3
@@ -4417,13 +4417,19 @@ static int check_atomic(struct bpf_verif load_reg =-1 ; } -/* check whether we can read the memory */ +/* Check whether we can read the memory, with second call for fetch +* case to simulate the register fill. +*/ err =check_mem_access (env, insn_idx, insn->dst_reg, insn->off, -BPF_SIZE (insn->code),BPF_READ , load_reg, true); +BPF_SIZE (insn->code),BPF_READ ,-1 , true); +if (!err && load_reg >=0 ) + err =check_mem_access (env, insn_idx, insn->dst_reg, insn->off, +BPF_SIZE (insn->code),BPF_READ , load_reg, + true);if (err)return err; -/* check whether we can write into the same memory */ +/* Check whether we can write into the same memory. */ err =check_mem_access (env, insn_idx, insn->dst_reg, insn->off,BPF_SIZE (insn->code),BPF_WRITE ,-1 , true);if (err)
Greg Kroah-Hartman
maintainerPATCH 14/177 bpf, selftests: Add test case for atomic fetch on spilled pointer
In reply to Greg Kroah-HartmanFrom: Daniel Borkmann <[email protected]>
commit 180486b430f4e22cc00a478163d942804baae4b5 upstream.
Test whether unprivileged would be able to leak the spilled pointer either by exporting the returned value from the atomic{32,64} operation or by reading and exporting the value from the stack after the atomic operation took place.
Note that for unprivileged, the below atomic cmpxchg test case named "Dest pointer in r0 - succeed" is failing. The reason is that in the dst memory location (r10 -8) there is the spilled register r10:
0: R1=ctx(id=0,off=0,imm=0) R10=fp0
0: (bf) r0 = r10
1: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 1: (7b) *(u64 *)(r10 -8) = r0
2: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 fp-8_w=fp 2: (b7) r1 = 0
3: R0_w=fp0 R1_w=invP0 R10=fp0 fp-8_w=fp
3: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r1) 4: R0_w=fp0 R1_w=invP0 R10=fp0 fp-8_w=mmmmmmmm 4: (79) r1 = *(u64 *)(r0 -8)
5: R0_w=fp0 R1_w=invP(id=0) R10=fp0 fp-8_w=mmmmmmmm 5: (b7) r0 = 0
6: R0_w=invP0 R1_w=invP(id=0) R10=fp0 fp-8_w=mmmmmmmm 6: (95) exit
However, allowing this case for unprivileged is a bit useless given an update with a new pointer will fail anyway:
0: R1=ctx(id=0,off=0,imm=0) R10=fp0
0: (bf) r0 = r10
1: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 1: (7b) *(u64 *)(r10 -8) = r0
2: R0_w=fp0 R1=ctx(id=0,off=0,imm=0) R10=fp0 fp-8_w=fp 2: (db) r0 = atomic64_cmpxchg((u64 *)(r10 -8), r0, r10) R10 leaks addr into mem
--- tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c | 23 ++++++++++++++++++ 1 file changed, 23 insertions(+)
tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +23 -0
@@ -118,4 +118,27 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "leaking pointer from stack off -8", +}, +{ + "Dest pointer in r0 - succeed, check 2", + .insns = { +/* r0 = &val */ +BPF_MOV64_REG (BPF_REG_0 ,BPF_REG_10 ), +/* val = r0; */ +BPF_STX_MEM (BPF_DW ,BPF_REG_10 ,BPF_REG_0 ,-8 ), +/* r5 = &val */ +BPF_MOV64_REG (BPF_REG_5 ,BPF_REG_10 ), +/* r0 = atomic_cmpxchg(&val, r0, r5); */ +BPF_ATOMIC_OP (BPF_DW ,BPF_CMPXCHG ,BPF_REG_10 ,BPF_REG_5 ,-8 ), +/* r1 = *r0 */ +BPF_LDX_MEM (BPF_DW ,BPF_REG_1 ,BPF_REG_0 ,-8 ), +/* exit(0); */ +BPF_MOV64_IMM (BPF_REG_0 ,0 ), + BPF_EXIT_INSN(), + }, + .result =ACCEPT , + .result_unpriv = REJECT, + .errstr_unpriv = "R5 leaks addr into mem", },
Greg Kroah-Hartman
maintainerPATCH 15/177 bpf: Fix signed bounds propagation after mov32
In reply to Greg Kroah-HartmanFrom: Daniel Borkmann <[email protected]>
commit 3cf2b61eb06765e27fec6799292d9fb46d0b7e60 upstream.
For the case where both s32_{min,max}_value bounds are positive, the __reg_assign_32_into_64() directly propagates them to their 64 bit counterparts, otherwise it pessimises them into [0,u32_max] universe and tries to refine them later on by learning through the tnum as per comment in mentioned function. However, that does not always happen, for example, in mov32 operation we call zext_32_to_64(dst_reg) which invokes the __reg_assign_32_into_64() as is without subsequent bounds update as elsewhere thus no refinement based on tnum takes place.
Thus, not calling into the __update_reg_bounds() / __reg_deduce_bounds() / __reg_bound_offset() triplet as we do, for example, in case of ALU ops via adjust_scalar_min_max_vals(), will lead to more pessimistic bounds when dumping the full register state:
Before fix:
0: (b4) w0 = -1
1: R0_w=invP4294967295
(id=0,imm=ffffffff,
smin_value=4294967295,smax_value=4294967295,
umin_value=4294967295,umax_value=4294967295,
var_off=(0xffffffff; 0x0),
s32_min_value=-1,s32_max_value=-1,
u32_min_value=-1,u32_max_value=-1) 1: (bc) w0 = w0
2: R0_w=invP4294967295
(id=0,imm=ffffffff,
smin_value=0,smax_value=4294967295,
umin_value=4294967295,umax_value=4294967295,
var_off=(0xffffffff; 0x0),
s32_min_value=-1,s32_max_value=-1,
u32_min_value=-1,u32_max_value=-1)Technically, the smin_value=0 and smax_value=4294967295 bounds are not incorrect, but given the register is still a constant, they break assumptions about const scalars that smin_value == smax_value and umin_value == umax_value.
After fix:
0: (b4) w0 = -1
1: R0_w=invP4294967295
(id=0,imm=ffffffff,
smin_value=4294967295,smax_value=4294967295,
umin_value=4294967295,umax_value=4294967295,
var_off=(0xffffffff; 0x0),
s32_min_value=-1,s32_max_value=-1,
u32_min_value=-1,u32_max_value=-1) 1: (bc) w0 = w0
2: R0_w=invP4294967295
(id=0,imm=ffffffff,
smin_value=4294967295,smax_value=4294967295,
umin_value=4294967295,umax_value=4294967295,
var_off=(0xffffffff; 0x0),
s32_min_value=-1,s32_max_value=-1,
u32_min_value=-1,u32_max_value=-1)Without the smin_value == smax_value and umin_value == umax_value invariant being intact for const scalars, it is possible to leak out kernel pointers from unprivileged user space if the latter is enabled. For example, when such registers are involved in pointer arithmtics, then adjust_ptr_min_max_vals() will taint the destination register into an unknown scalar, and the latter can be exported and stored e.g. into a BPF map value.
--- kernel/bpf/verifier.c | 4 ++++ 1 file changed, 4 insertions(+)
kernel/bpf/verifier.c +4 -0
@@ -8120,6 +8120,10 @@ static int check_alu_op(struct bpf_verif insn->dst_reg); }zext_32_to_64 (dst_reg); + +__update_reg_bounds (dst_reg); +__reg_deduce_bounds (dst_reg); +__reg_bound_offset (dst_reg); } }else {/* case: R = imm
Greg Kroah-Hartman
maintainerPATCH 16/177 bpf: Make 32->64 bounds propagation slightly more robust
In reply to Greg Kroah-HartmanFrom: Daniel Borkmann <[email protected]>
commit e572ff80f05c33cd0cb4860f864f5c9c044280b6 upstream.
Make the bounds propagation in __reg_assign_32_into_64() slightly more robust and readable by aligning it similarly as we did back in the __reg_combine_64_into_32() counterpart. Meaning, only propagate or pessimize them as a smin/smax pair.
--- kernel/bpf/verifier.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-)
kernel/bpf/verifier.c +15 -9
@@ -1358,22 +1358,28 @@ static void __reg_bound_offset(struct bp reg->var_off =tnum_or (tnum_clear_subreg (var64_off), var32_off); } +static bool __reg32_bound_s64 (s32 a) +{ +return a >=0 && a <=S32_MAX ; +} +static void __reg_assign_32_into_64 (struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; -/* Attempt to pull 32-bit signed bounds into 64-bit bounds -* but must be positive otherwise set to worse case bounds -* and refine later from tnum. + +/* Attempt to pull 32-bit signed bounds into 64-bit bounds but must +* be positive otherwise set to worse case bounds and refine later +* from tnum. */ -if (reg->s32_min_value >=0 && reg->s32_max_value >=0 ) - reg->smax_value = reg->s32_max_value; -else - reg->smax_value =U32_MAX ; -if (reg->s32_min_value >=0 ) +if (__reg32_bound_s64 (reg->s32_min_value) && +__reg32_bound_s64 (reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; -else + reg->smax_value = reg->s32_max_value; + }else { reg->smin_value =0 ; + reg->smax_value =U32_MAX ; + } }static void __reg_combine_32_into_64 (struct bpf_reg_state *reg)
Greg Kroah-Hartman
maintainerPATCH 17/177 bpf, selftests: Add test case trying to taint map value pointer
In reply to Greg Kroah-HartmanFrom: Daniel Borkmann <[email protected]>
commit b1a7288dedc6caf9023f2676b4f5ed34cf0d4029 upstream.
Add a test case which tries to taint map value pointer arithmetic into a unknown scalar with subsequent export through the map.
Before fix:
# ./test_verifier 1186 #1186/u map access: trying to leak tained dst reg FAIL Unexpected success to load! verification time 24 usec stack depth 8 processed 15 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 1 #1186/p map access: trying to leak tained dst reg FAIL Unexpected success to load! verification time 8 usec stack depth 8 processed 15 insns (limit 1000000) max_states_per_insn 0 total_states 1 peak_states 1 mark_read 1 Summary: 0 PASSED, 0 SKIPPED, 2 FAILED
After fix:
# ./test_verifier 1186 #1186/u map access: trying to leak tained dst reg OK #1186/p map access: trying to leak tained dst reg OK Summary: 2 PASSED, 0 SKIPPED, 0 FAILED
--- tools/testing/selftests/bpf/verifier/value_ptr_arith.c | 23 +++++++++++++++++ 1 file changed, 23 insertions(+)
tools/testing/selftests/bpf/verifier/value_ptr_arith.c +23 -0
@@ -1078,6 +1078,29 @@ .errstr_unpriv = "R0 pointer -= pointer prohibited", }, { + "map access: trying to leak tained dst reg", + .insns = { +BPF_MOV64_IMM (BPF_REG_0 ,0 ), +BPF_ST_MEM (BPF_DW ,BPF_REG_10 ,-8 ,0 ), +BPF_MOV64_REG (BPF_REG_2 ,BPF_REG_10 ), +BPF_ALU64_IMM (BPF_ADD ,BPF_REG_2 ,-8 ), +BPF_LD_MAP_FD (BPF_REG_1 ,0 ), +BPF_RAW_INSN (BPF_JMP |BPF_CALL ,0 ,0 ,0 , BPF_FUNC_map_lookup_elem), +BPF_JMP_IMM (BPF_JNE ,BPF_REG_0 ,0 ,1 ), +BPF_EXIT_INSN (), +BPF_MOV64_REG (BPF_REG_2 ,BPF_REG_0 ), +BPF_MOV32_IMM (BPF_REG_1 ,0xFFFFFFFF ), +BPF_MOV32_REG (BPF_REG_1 ,BPF_REG_1 ), +BPF_ALU64_REG (BPF_SUB ,BPF_REG_2 ,BPF_REG_1 ), +BPF_STX_MEM (BPF_DW ,BPF_REG_0 ,BPF_REG_2 ,0 ), +BPF_MOV64_IMM (BPF_REG_0 ,0 ), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 4 }, + .result = REJECT, + .errstr = "math between map_value pointer and 4294967295 is not allowed", +}, +{"32bit pkt_ptr -= scalar" , .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
Greg Kroah-Hartman
maintainerPATCH 18/177 bpf: Fix kernel address leakage in atomic cmpxchgs r0 aux reg
In reply to Greg Kroah-HartmanFrom: Daniel Borkmann <[email protected]>
commit a82fe085f344ef20b452cd5f481010ff96b5c4cd upstream.
The implementation of BPF_CMPXCHG on a high level has the following parameters:
.-[old-val] .-[new-val]
BPF_R0 = cmpxchg{32,64}(DST_REG + insn->off, BPF_R0, SRC_REG)
`-[mem-loc] `-[old-val]
Given a BPF insn can only have two registers (dst, src), the R0 is fixed and used as an auxilliary register for input (old value) as well as output (returning old value from memory location). While the verifier performs a number of safety checks, it misses to reject unprivileged programs where R0 contains a pointer as old value.
Through brute-forcing it takes about ~16sec on my machine to leak a kernel pointer with BPF_CMPXCHG. The PoC is basically probing for kernel addresses by storing the guessed address into the map slot as a scalar, and using the map value pointer as R0 while SRC_REG has a canary value to detect a matching address.
Fix it by checking R0 for pointers, and reject if that's the case for unprivileged programs.
--- kernel/bpf/verifier.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
kernel/bpf/verifier.c +8 -1
@@ -4386,9 +4386,16 @@ static int check_atomic(struct bpf_verifif (insn->imm ==BPF_CMPXCHG ) {/* Check comparison of R0 with memory location */ - err =check_reg_arg (env,BPF_REG_0 ,SRC_OP ); +const u32 aux_reg =BPF_REG_0 ; + + err =check_reg_arg (env, aux_reg,SRC_OP );if (err)return err; + +if (is_pointer_value (env, aux_reg)) { +verbose (env,"R%d leaks addr into mem\n" , aux_reg); +return -EACCES ; + } }if (is_pointer_value (env, insn->src_reg)) {
Greg Kroah-Hartman
maintainerPATCH 19/177 bpf, selftests: Update test case for atomic cmpxchg on r0 with pointer
In reply to Greg Kroah-HartmanFrom: Daniel Borkmann <[email protected]>
commit e523102cb719cbad1673b6aa2a4d5c1fa6f13799 upstream.
Fix up unprivileged test case results for 'Dest pointer in r0' verifier tests given they now need to reject R0 containing a pointer value, and add a couple of new related ones with 32bit cmpxchg as well.
root@foo:~/bpf/tools/testing/selftests/bpf# ./test_verifier #0/u invalid and of negative number OK #0/p invalid and of negative number OK [...] #1268/p XDP pkt read, pkt_meta' <= pkt_data, bad access 1 OK #1269/p XDP pkt read, pkt_meta' <= pkt_data, bad access 2 OK #1270/p XDP pkt read, pkt_data <= pkt_meta', good access OK #1271/p XDP pkt read, pkt_data <= pkt_meta', bad access 1 OK #1272/p XDP pkt read, pkt_data <= pkt_meta', bad access 2 OK Summary: 1900 PASSED, 0 SKIPPED, 0 FAILED
--- tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c | 67 +++++++++++++++++- 1 file changed, 65 insertions(+), 2 deletions(-)
tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +65 -2
@@ -71,6 +71,8 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv ="R0 leaks addr into mem" , }, { "Can't use cmpxchg on uninit src reg",
@@ -119,7 +121,7 @@ }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "leaking pointer from stack off -8", + .errstr_unpriv = "R0 leaks addr into mem", }, { "Dest pointer in r0 - succeed, check 2",
@@ -140,5 +142,66 @@ }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R5 leaks addr into mem", + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ + "Dest pointer in r0 - succeed, check 3", + .insns = { +/* r0 = &val */ +BPF_MOV64_REG (BPF_REG_0 ,BPF_REG_10 ), +/* val = r0; */ +BPF_STX_MEM (BPF_DW ,BPF_REG_10 ,BPF_REG_0 ,-8 ), +/* r5 = &val */ +BPF_MOV64_REG (BPF_REG_5 ,BPF_REG_10 ), +/* r0 = atomic_cmpxchg(&val, r0, r5); */ +BPF_ATOMIC_OP (BPF_W ,BPF_CMPXCHG ,BPF_REG_10 ,BPF_REG_5 ,-8 ), +/* exit(0); */ +BPF_MOV64_IMM (BPF_REG_0 ,0 ), + BPF_EXIT_INSN(), + }, + .result =REJECT , + .errstr = "invalid size of register fill", + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ +"Dest pointer in r0 - succeed, check 4" , + .insns = { +/* r0 = &val */ +BPF_MOV32_REG (BPF_REG_0 ,BPF_REG_10 ), +/* val = r0; */ +BPF_STX_MEM (BPF_W ,BPF_REG_10 ,BPF_REG_0 ,-8 ), +/* r5 = &val */ +BPF_MOV32_REG (BPF_REG_5 ,BPF_REG_10 ), +/* r0 = atomic_cmpxchg(&val, r0, r5); */ +BPF_ATOMIC_OP (BPF_W ,BPF_CMPXCHG ,BPF_REG_10 ,BPF_REG_5 ,-8 ), +/* r1 = *r10 */ +BPF_LDX_MEM (BPF_W ,BPF_REG_1 ,BPF_REG_10 ,-8 ), +/* exit(0); */ +BPF_MOV64_IMM (BPF_REG_0 ,0 ), + BPF_EXIT_INSN(), + }, + .result =ACCEPT , + .result_unpriv = REJECT, + .errstr_unpriv = "R10 partial copy of pointer", +}, +{ +"Dest pointer in r0 - succeed, check 5" , + .insns = { +/* r0 = &val */ +BPF_MOV32_REG (BPF_REG_0 ,BPF_REG_10 ), +/* val = r0; */ +BPF_STX_MEM (BPF_W ,BPF_REG_10 ,BPF_REG_0 ,-8 ), +/* r5 = &val */ +BPF_MOV32_REG (BPF_REG_5 ,BPF_REG_10 ), +/* r0 = atomic_cmpxchg(&val, r0, r5); */ +BPF_ATOMIC_OP (BPF_W ,BPF_CMPXCHG ,BPF_REG_10 ,BPF_REG_5 ,-8 ), +/* r1 = *r0 */ +BPF_LDX_MEM (BPF_W ,BPF_REG_1 ,BPF_REG_0 ,-8 ), +/* exit(0); */ +BPF_MOV64_IMM (BPF_REG_0 ,0 ), + BPF_EXIT_INSN(), + }, + .result =REJECT , + .errstr = "R0 invalid mem access", + .errstr_unpriv = "R10 partial copy of pointer", },
Greg Kroah-Hartman
maintainerPATCH 20/177 vduse: fix memory corruption in vduse_dev_ioctl()
In reply to Greg Kroah-HartmanFrom: Dan Carpenter <[email protected]>
commit ff9f9c6e74848170fcb45c8403c80d661484c8c9 upstream.
The "config.offset" comes from the user. There needs to a check to prevent it being out of bounds. The "config.offset" and "dev->config_size" variables are both type u32. So if the offset if out of bounds then the "dev->config_size - config.offset" subtraction results in a very high u32 value. The out of bounds offset can result in memory corruption.
--- drivers/vdpa/vdpa_user/vduse_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/vdpa/vdpa_user/vduse_dev.c +2 -1
@@ -975,7 +975,8 @@ static long vduse_dev_ioctl(struct filebreak ; ret = -EINVAL ; -if (config.length ==0 || +if (config.offset > dev->config_size || + config.length ==0 || config.length > dev->config_size - config.offset)break ;
Greg Kroah-Hartman
maintainerPATCH 21/177 vduse: check that offset is within bounds in get_config()
In reply to Greg Kroah-HartmanFrom: Dan Carpenter <[email protected]>
commit dc1db0060c02d119fd4196924eff2d1129e9a442 upstream.
This condition checks "len" but it does not check "offset" and that could result in an out of bounds read if "offset > dev->config_size". The problem is that since both variables are unsigned the "dev->config_size - offset" subtraction would result in a very high unsigned value.
I think these checks might not be necessary because "len" and "offset" are supposed to already have been validated using the vhost_vdpa_config_validate() function. But I do not know the code perfectly, and I like to be safe.
--- drivers/vdpa/vdpa_user/vduse_dev.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/vdpa/vdpa_user/vduse_dev.c +2 -1
@@ -655,7 +655,8 @@ static void vduse_vdpa_get_config(struct {struct vduse_dev *dev =vdpa_to_vduse (vdpa); -if (len > dev->config_size - offset) +if (offset > dev->config_size || + len > dev->config_size - offset)return ;memcpy (buf, dev->config + offset, len);
Greg Kroah-Hartman
maintainerPATCH 22/177 virtio_ring: Fix querying of maximum DMA mapping size for virtio device
In reply to Greg Kroah-HartmanFrom: Will Deacon <[email protected]>
commit 817fc978b5a29b039db0418a91072b31c9aab152 upstream.
virtio_max_dma_size() returns the maximum DMA mapping size of the virtio device by querying dma_max_mapping_size() for the device when the DMA API is in use for the vring. Unfortunately, the device passed is initialised by register_virtio_device() and does not inherit the DMA configuration from its parent, resulting in SWIOTLB errors when bouncing is enabled and the default 256K mapping limit (IO_TLB_SEGSIZE) is not respected:
| virtio-pci 0000:00:01.0: swiotlb buffer is full (sz: 294912 bytes), total 1024 (slots), used 725 (slots)
Follow the pattern used elsewhere in the virtio_ring code when calling into the DMA layer and pass the parent device to dma_max_mapping_size() instead.
--- drivers/virtio/virtio_ring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/virtio/virtio_ring.c +1 -1
@@ -268,7 +268,7 @@ size_t virtio_max_dma_size(struct virtiosize_t max_segment_size =SIZE_MAX ;if (vring_use_dma_api (vdev)) - max_segment_size =dma_max_mapping_size (&vdev->dev); + max_segment_size =dma_max_mapping_size (vdev->dev.parent);return max_segment_size; }
Greg Kroah-Hartman
maintainerPATCH 23/177 vdpa: check that offsets are within bounds
In reply to Greg Kroah-HartmanFrom: Dan Carpenter <[email protected]>
commit 3ed21c1451a14d139e1ceb18f2fa70865ce3195a upstream.
In this function "c->off" is a u32 and "size" is a long. On 64bit systems if "c->off" is greater than "size" then "size - c->off" is a negative and we always return -E2BIG. But on 32bit systems the subtraction is type promoted to a high positive u32 value and basically any "c->len" is accepted.
--- drivers/vhost/vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/vhost/vdpa.c +1 -1
@@ -197,7 +197,7 @@ static int vhost_vdpa_config_validate(ststruct vdpa_device *vdpa = v->vdpa;long size = vdpa->config->get_config_size (vdpa); -if (c->len ==0 ) +if (c->len ==0 || c->off > size)return -EINVAL ;if (c->len > size - c->off)
Greg Kroah-Hartman
maintainerPATCH 24/177 s390/entry: fix duplicate tracking of irq nesting level
In reply to Greg Kroah-HartmanFrom: Sven Schnelle <[email protected]>
commit c9b12b59e2ea4c3c7cedec7efb071b649652f3a9 upstream.
In the current code, when exiting from idle, rcu_irq_enter() is called twice during irq entry:
irq_entry_enter()-> rcu_irq_enter()irq_enter() -> rcu_irq_enter()
This may lead to wrong results from rcu_is_cpu_rrupt_from_idle() because of a wrong dynticks nmi nesting count. Fix this by only calling irq_enter_rcu().
--- arch/s390/kernel/irq.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
arch/s390/kernel/irq.c +5 -4
@@ -138,7 +138,7 @@ void noinstr do_io_irq(struct pt_regs *rstruct pt_regs *old_regs =set_irq_regs (regs);int from_idle; -irq_enter (); +irq_enter_rcu ();if (user_mode (regs))update_timer_sys ();
@@ -155,7 +155,8 @@ void noinstr do_io_irq(struct pt_regs *rdo_irq_async (regs,IO_INTERRUPT ); }while (MACHINE_IS_LPAR &&irq_pending (regs)); -irq_exit (); +irq_exit_rcu (); +set_irq_regs (old_regs);irqentry_exit (regs, state);
@@ -169,7 +170,7 @@ void noinstr do_ext_irq(struct pt_regs *struct pt_regs *old_regs =set_irq_regs (regs);int from_idle; -irq_enter (); +irq_enter_rcu ();if (user_mode (regs))update_timer_sys ();
@@ -184,7 +185,7 @@ void noinstr do_ext_irq(struct pt_regs *do_irq_async (regs,EXT_INTERRUPT ); -irq_exit (); +irq_exit_rcu ();set_irq_regs (old_regs);irqentry_exit (regs, state);
Greg Kroah-Hartman
maintainerPATCH 25/177 recordmcount.pl: look for jgnop instruction as well as bcrl on s390
In reply to Greg Kroah-HartmanFrom: Jerome Marchand <[email protected]>
commit 85bf17b28f97ca2749968d8786dc423db320d9c2 upstream.
On s390, recordmcount.pl is looking for "bcrl 0,<xxx>" instructions in the objdump -d outpout. However since binutils 2.37, objdump -d display "jgnop <xxx>" for the same instruction. Update the mcount_regex so that it accepts both.
--- scripts/recordmcount.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
scripts/recordmcount.pl +1 -1
@@ -219,7 +219,7 @@ if ($arch eq "x86_64") { } elsif ($arch eq "s390" && $bits == 64) { if ($cc =~ /-DCC_USING_HOTPATCH/) { - $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*brcl\\s*0,[0-9a-f]+ <([^\+]*)>\$"; + $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(bcrl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$"; $mcount_adjust = 0; } $alignment = 8;
Greg Kroah-Hartman
maintainerPATCH 26/177 arm64: dts: ten64: remove redundant interrupt declaration for gpio-keys
In reply to Greg Kroah-HartmanFrom: Mathew McBride <[email protected]>
commit c88c5e461939a06ae769a01649d5c6b5a156f883 upstream.
gpio-keys already 'inherits' the interrupts from the controller of the specified GPIO, so having another declaration is redundant. On >=v5.15 this started causing an oops under gpio_keys_probe as the IRQ was already claimed.
--- arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts | 2 -- 1 file changed, 2 deletions(-)
arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts +0 -2
@@ -38,7 +38,6 @@ powerdn { label = "External Power Down"; gpios = <&gpio1 17 GPIO_ACTIVE_LOW>; - interrupts = <&gpio1 17 IRQ_TYPE_EDGE_FALLING>; linux,code = <KEY_POWER>; };
@@ -46,7 +45,6 @@ admin { label = "ADMIN button"; gpios = <&gpio3 8 GPIO_ACTIVE_HIGH>; - interrupts = <&gpio3 8 IRQ_TYPE_EDGE_RISING>; linux,code = <KEY_WPS_BUTTON>; }; };
Greg Kroah-Hartman
maintainerPATCH 27/177 ceph: fix up non-directory creation in SGID directories
In reply to Greg Kroah-HartmanFrom: Christian Brauner <[email protected]>
commit fd84bfdddd169c219c3a637889a8b87f70a072c2 upstream.
Ceph always inherits the SGID bit if it is set on the parent inode, while the generic inode_init_owner does not do this in a few cases where it can create a possible security problem (cf. [1]).
Update ceph to strip the SGID bit just as inode_init_owner would.
This bug was detected by the mapped mount testsuite in [3]. The testsuite tests all core VFS functionality and semantics with and without mapped mounts. That is to say it functions as a generic VFS testsuite in addition to a mapped mount testsuite. While working on mapped mount support for ceph, SIGD inheritance was the only failing test for ceph after the port.
The same bug was detected by the mapped mount testsuite in XFS in January 2021 (cf. [2]).
[1]: commit 0fa3ecd87848 ("Fix up non-directory creation in SGID directories") [2]: commit 01ea173e103e ("xfs: fix up non-directory creation in SGID directories") [3]: https://git.kernel.org/fs/xfs/xfstests-dev.git
--- fs/ceph/file.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-)
fs/ceph/file.c +15 -3
@@ -603,13 +603,25 @@ static int ceph_finish_async_create(stru in.cap.realm =cpu_to_le64 (ci->i_snap_realm->ino); in.cap.flags =CEPH_CAP_FLAG_AUTH ; in.ctime = in.mtime = in.atime = iinfo.btime; - in.mode =cpu_to_le32 ((u32 )mode); in.truncate_seq =cpu_to_le32 (1 ); in.truncate_size =cpu_to_le64 (-1ULL ); in.xattr_version =cpu_to_le64 (1 ); in.uid =cpu_to_le32 (from_kuid (&init_user_ns,current_fsuid ())); - in.gid =cpu_to_le32 (from_kgid (&init_user_ns, dir->i_mode &S_ISGID ? - dir->i_gid :current_fsgid ())); +if (dir->i_mode &S_ISGID ) { + in.gid =cpu_to_le32 (from_kgid (&init_user_ns, dir->i_gid)); + +/* Directories always inherit the setgid bit. */ +if (S_ISDIR (mode)) + mode |=S_ISGID ; +else if ((mode & (S_ISGID |S_IXGRP )) == (S_ISGID |S_IXGRP ) && + !in_group_p (dir->i_gid) && + !capable_wrt_inode_uidgid (&init_user_ns, dir,CAP_FSETID )) + mode &= ~S_ISGID ; + }else { + in.gid =cpu_to_le32 (from_kgid (&init_user_ns,current_fsgid ())); + } + in.mode =cpu_to_le32 ((u32 )mode); + in.nlink =cpu_to_le32 (1 ); in.max_size =cpu_to_le64 (lo->stripe_unit);
Greg Kroah-Hartman
maintainerPATCH 28/177 dm btree remove: fix use after free in rebalance_children()
In reply to Greg Kroah-HartmanFrom: Joe Thornber <[email protected]>
commit 1b8d2789dad0005fd5e7d35dab26a8e1203fb6da upstream.
Move dm_tm_unlock() after dm_tm_dec().
--- drivers/md/persistent-data/dm-btree-remove.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/md/persistent-data/dm-btree-remove.c +1 -1
@@ -423,9 +423,9 @@ static int rebalance_children(struct shamemcpy (n,dm_block_data (child),dm_bm_block_size (dm_tm_get_bm (info->tm))); -dm_tm_unlock (info->tm, child);dm_tm_dec (info->tm,dm_block_location (child)); +dm_tm_unlock (info->tm, child);return 0 ; }
Greg Kroah-Hartman
maintainerPATCH 29/177 audit: improve robustness of the audit queue handling
In reply to Greg Kroah-HartmanFrom: Paul Moore <[email protected]>
commit f4b3ee3c85551d2d343a3ba159304066523f730f upstream.
If the audit daemon were ever to get stuck in a stopped state the kernel's kauditd_thread() could get blocked attempting to send audit records to the userspace audit daemon. With the kernel thread blocked it is possible that the audit queue could grow unbounded as certain audit record generating events must be exempt from the queue limits else the system enter a deadlock state.
This patch resolves this problem by lowering the kernel thread's socket sending timeout from MAX_SCHEDULE_TIMEOUT to HZ/10 and tweaks the kauditd_send_queue() function to better manage the various audit queues when connection problems occur between the kernel and the audit daemon. With this patch, the backlog may temporarily grow beyond the defined limits when the audit daemon is stopped and the system is under heavy audit pressure, but kauditd_thread() will continue to make progress and drain the queues as it would for other connection problems. For example, with the audit daemon put into a stopped state and the system configured to audit every syscall it was still possible to shutdown the system without a kernel panic, deadlock, etc.; granted, the system was slow to shutdown but that is to be expected given the extreme pressure of recording every syscall.
The timeout value of HZ/10 was chosen primarily through experimentation and this developer's "gut feeling". There is likely no one perfect value, but as this scenario is limited in scope (root privileges would be needed to send SIGSTOP to the audit daemon), it is likely not worth exposing this as a tunable at present. This can always be done at a later date if it proves necessary.
--- kernel/audit.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-)
kernel/audit.c +10 -11
@@ -718,7 +718,7 @@ static int kauditd_send_queue(struct soc {int rc =0 ;struct sk_buff *skb; -static unsigned int failed =0 ; +unsigned int failed =0 ;/* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */
@@ -735,32 +735,30 @@ static int kauditd_send_queue(struct soccontinue ; } +retry:/* grab an extra skb reference in case of error */ skb_get (skb); rc =netlink_unicast (sk, skb, portid,0 );if (rc <0 ) { -/* fatal failure for our queue flush attempt? */ +/* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM ) { -/* yes - error processing for the queue */ sk =NULL ;if (err_hook) (*err_hook)(skb); -if (!skb_hook) - goto out; -/* keep processing with the skb_hook */ +if (rc == -EAGAIN ) + rc =0 ; +/* continue to drain the queue */ continue ; }else -/* no - requeue to preserve ordering */ -skb_queue_head (queue, skb); + goto retry; }else { -/* it worked - drop the extra reference and continue */ +/* skb sent - drop the extra reference and continue */ consume_skb (skb); failed =0 ; } } -out:return (rc >=0 ?0 : rc); }
@@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(straudit_panic ("cannot initialize netlink socket in namespace" );return -ENOMEM ; } - aunet->sk->sk_sndtimeo =MAX_SCHEDULE_TIMEOUT ; +/* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo =HZ /10 ;return 0 ; }
Greg Kroah-Hartman
maintainerPATCH 30/177 btrfs: convert latest_bdev type to btrfs_device and rename
In reply to Greg Kroah-HartmanFrom: Anand Jain <[email protected]>
Commit d24fa5c1da08026be9959baca309fa0adf8708bf upstream.
In preparation to fix a bug in btrfs_show_devname().
Convert fs_devices::latest_bdev type from struct block_device to struct btrfs_device and, rename the member to fs_devices::latest_dev. So that btrfs_show_devname() can use fs_devices::latest_dev::name.
--- fs/btrfs/disk-io.c | 6 +++--- fs/btrfs/extent_io.c | 2 +- fs/btrfs/inode.c | 2 +- fs/btrfs/super.c | 2 +- fs/btrfs/volumes.c | 10 +++++----- fs/btrfs/volumes.h | 6 +++++- 6 files changed, 16 insertions(+), 12 deletions(-)
fs/btrfs/disk-io.c +3 -3
@@ -3229,12 +3229,12 @@ int __cold open_ctree(struct super_blockmapping_set_gfp_mask (fs_info->btree_inode->i_mapping,GFP_NOFS );btrfs_init_btree_inode (fs_info); -invalidate_bdev (fs_devices->latest_bdev); +invalidate_bdev (fs_devices->latest_dev->bdev);/* * Read super block and check the signature bytes only */ - disk_super =btrfs_read_dev_super (fs_devices->latest_bdev); + disk_super =btrfs_read_dev_super (fs_devices->latest_dev->bdev);if (IS_ERR (disk_super)) { err =PTR_ERR (disk_super); goto fail_alloc;
@@ -3466,7 +3466,7 @@ int __cold open_ctree(struct super_block* below in btrfs_init_dev_replace(). */ btrfs_free_extra_devids (fs_devices); -if (!fs_devices->latest_bdev) { +if (!fs_devices->latest_dev->bdev) {btrfs_err (fs_info,"failed to read devices" ); goto fail_tree_roots; }
fs/btrfs/extent_io.c +1 -1
@@ -3327,7 +3327,7 @@ static int alloc_new_bio(struct btrfs_inif (wbc) {struct block_device *bdev; - bdev = fs_info->fs_devices->latest_bdev; + bdev = fs_info->fs_devices->latest_dev->bdev;bio_set_dev (bio, bdev);wbc_init_bio (wbc, bio); }
fs/btrfs/inode.c +1 -1
@@ -7967,7 +7967,7 @@ static int btrfs_dio_iomap_begin(struct iomap->type =IOMAP_MAPPED ; } iomap->offset = start; - iomap->bdev = fs_info->fs_devices->latest_bdev; + iomap->bdev = fs_info->fs_devices->latest_dev->bdev; iomap->length = len;if (write &&btrfs_use_zone_append (BTRFS_I (inode), em->block_start))
fs/btrfs/super.c +1 -1
@@ -1705,7 +1705,7 @@ static struct dentry *btrfs_mount_root(s goto error_close_devices; } - bdev = fs_devices->latest_bdev; + bdev = fs_devices->latest_dev->bdev; s =sget (fs_type, btrfs_test_super, btrfs_set_super, flags |SB_NOSEC , fs_info);if (IS_ERR (s)) {
fs/btrfs/volumes.c +5 -5
@@ -1092,7 +1092,7 @@ void btrfs_free_extra_devids(struct btrflist_for_each_entry (seed_dev, &fs_devices->seed_list, seed_list)__btrfs_free_extra_devids (seed_dev, &latest_dev); - fs_devices->latest_bdev = latest_dev->bdev; + fs_devices->latest_dev = latest_dev;mutex_unlock (&uuid_mutex); }
@@ -1225,7 +1225,7 @@ static int open_fs_devices(struct btrfs_return -EINVAL ; fs_devices->opened =1 ; - fs_devices->latest_bdev = latest_dev->bdev; + fs_devices->latest_dev = latest_dev; fs_devices->total_rw_bytes =0 ; fs_devices->chunk_alloc_policy =BTRFS_CHUNK_ALLOC_REGULAR ; fs_devices->read_policy =BTRFS_READ_POLICY_PID ;
@@ -1993,7 +1993,7 @@ static struct btrfs_device * btrfs_find_ }/* -* Helper function to check if the given device is part of s_bdev / latest_bdev +* Helper function to check if the given device is part of s_bdev / latest_dev * and replace it with the provided or the next active device, in the context * where this function called, there should be always be another device (or * this_dev) which is active.
@@ -2012,8 +2012,8 @@ void __cold btrfs_assign_next_active_dev (fs_info->sb->s_bdev == device->bdev)) fs_info->sb->s_bdev = next_device->bdev; -if (fs_info->fs_devices->latest_bdev == device->bdev) - fs_info->fs_devices->latest_bdev = next_device->bdev; +if (fs_info->fs_devices->latest_dev->bdev == device->bdev) + fs_info->fs_devices->latest_dev = next_device; }/*
fs/btrfs/volumes.h +5 -1
@@ -246,7 +246,11 @@ struct btrfs_fs_devices {/* Highest generation number of seen devices */ u64 latest_generation; -struct block_device *latest_bdev; +/* +* The mount device or a device with highest generation after removal +* or replace. +*/ +struct btrfs_device *latest_dev;/* all of the devices in the FS, protected by a mutex * so we can safely walk it to write out the supers without
Greg Kroah-Hartman
maintainerPATCH 31/177 btrfs: use latest_dev in btrfs_show_devname
In reply to Greg Kroah-HartmanFrom: Anand Jain <[email protected]>
Commit 6605fd2f394bba0a0059df2b6cfc87b0b6d393a2 upstream.
The test case btrfs/238 reports the warning below:
WARNING: CPU: 3 PID: 481 at fs/btrfs/super.c:2509 btrfs_show_devname+0x104/0x1e8 [btrfs] CPU: 2 PID: 1 Comm: systemd Tainted: G W O 5.14.0-rc1-custom #72 Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015 Call trace: btrfs_show_devname+0x108/0x1b4 [btrfs] show_mountinfo+0x234/0x2c4 m_show+0x28/0x34 seq_read_iter+0x12c/0x3c4 vfs_read+0x29c/0x2c8 ksys_read+0x80/0xec __arm64_sys_read+0x28/0x34 invoke_syscall+0x50/0xf8 do_el0_svc+0x88/0x138 el0_svc+0x2c/0x8c el0t_64_sync_handler+0x84/0xe4 el0t_64_sync+0x198/0x19c
Reason:
While btrfs_prepare_sprout() moves the fs_devices::devices into fs_devices::seed_list, the btrfs_show_devname() searches for the devices and found none, leading to the warning as in above.
Fix:latest_dev is updated according to the changes to the device list. That means we could use the latest_dev->name to show the device name in /proc/self/mounts, the pointer will be always valid as it's assigned before the device is deleted from the list in remove or replace. The RCU protection is sufficient as the device structure is freed after synchronization.
--- fs/btrfs/super.c | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-)
fs/btrfs/super.c +5 -19
@@ -2463,30 +2463,16 @@ static int btrfs_unfreeze(struct super_bstatic int btrfs_show_devname (struct seq_file *m,struct dentry *root) {struct btrfs_fs_info *fs_info =btrfs_sb (root->d_sb); -struct btrfs_device *dev, *first_dev =NULL ;/* -* Lightweight locking of the devices. We should not need -* device_list_mutex here as we only read the device data and the list -* is protected by RCU. Even if a device is deleted during the list -* traversals, we'll get valid data, the freeing callback will wait at -* least until the rcu_read_unlock. +* There should be always a valid pointer in latest_dev, it may be stale +* for a short moment in case it's being deleted but still valid until +* the end of RCU grace period. */ rcu_read_lock (); -list_for_each_entry_rcu (dev, &fs_info->fs_devices->devices, dev_list) { -if (test_bit (BTRFS_DEV_STATE_MISSING , &dev->dev_state)) -continue ; -if (!dev->name) -continue ; -if (!first_dev || dev->devid < first_dev->devid) - first_dev = dev; - } - -if (first_dev) -seq_escape (m,rcu_str_deref (first_dev->name)," \t\n\\" ); -else -WARN_ON (1 ); +seq_escape (m,rcu_str_deref (fs_info->fs_devices->latest_dev->name)," \t\n\\" );rcu_read_unlock (); +return 0 ; }
Greg Kroah-Hartman
maintainerPATCH 32/177 btrfs: update latest_dev when we create a sprout device
In reply to Greg Kroah-HartmanFrom: Anand Jain <[email protected]>
Commit b7cb29e666fe79dda5dbe5f57fb7c92413bf161c upstream.
When we add a device to the seed filesystem (sprouting) it is a new filesystem (and fsid) on the device added. Update the latest_dev so that /proc/self/mounts shows the correct device.
Example:
$ btrfstune -S1 /dev/vg/seed $ mount /dev/vg/seed /btrfs mount: /btrfs: WARNING: device write-protected, mounted read-only.
$ cat /proc/self/mounts | grep btrfs /dev/mapper/vg-seed /btrfs btrfs ro,relatime,space_cache,subvolid=5,subvol=/ 0 0
$ btrfs dev add -f /dev/vg/new /btrfs
Before:
$ cat /proc/self/mounts | grep btrfs /dev/mapper/vg-seed /btrfs btrfs ro,relatime,space_cache,subvolid=5,subvol=/ 0 0
After:
$ cat /proc/self/mounts | grep btrfs /dev/mapper/vg-new /btrfs btrfs ro,relatime,space_cache,subvolid=5,subvol=/ 0 0
--- fs/btrfs/volumes.c | 2 ++ 1 file changed, 2 insertions(+)
fs/btrfs/volumes.c +2 -0
@@ -2634,6 +2634,8 @@ int btrfs_init_new_device(struct btrfs_fbtrfs_abort_transaction (trans, ret); goto error_trans; } +btrfs_assign_next_active_device (fs_info->fs_devices->latest_dev, + device); } device->fs_devices = fs_devices;
Greg Kroah-Hartman
maintainerPATCH 33/177 btrfs: remove stale comment about the btrfs_show_devname
In reply to Greg Kroah-HartmanFrom: Anand Jain <[email protected]>
Commit cdccc03a8a369b59cff5e7ea3292511cfa551120 upstream.
There were few lockdep warnings because btrfs_show_devname() was using device_list_mutex as recorded in the commits:
0ccd05285e7f ("btrfs: fix a possible umount deadlock")
779bf3fefa83 ("btrfs: fix lock dep warning, move scratch dev out of device_list_mutex and uuid_mutex")
And finally, commit 88c14590cdd6 ("btrfs: use RCU in btrfs_show_devname for device list traversal") removed the device_list_mutex from btrfs_show_devname for performance reasons.
This patch removes a stale comment about the function btrfs_show_devname and device_list_mutex.
--- fs/btrfs/volumes.c | 7 ------- 1 file changed, 7 deletions(-)
fs/btrfs/volumes.c +0 -7
@@ -2312,13 +2312,6 @@ void btrfs_destroy_dev_replace_tgtdev(stmutex_unlock (&fs_devices->device_list_mutex); -/* -* The update_dev_time() with in btrfs_scratch_superblocks() -* may lead to a call to btrfs_show_devname() which will try -* to hold device_list_mutex. And here this device -* is already out of device list, so we don't have to hold -* the device_list_mutex lock. -*/ btrfs_scratch_superblocks (tgtdev->fs_info, tgtdev->bdev, tgtdev->name->str);
Greg Kroah-Hartman
maintainerPATCH 34/177 scsi: ufs: core: Retry START_STOP on UNIT_ATTENTION
In reply to Greg Kroah-HartmanFrom: Jaegeuk Kim <[email protected]>
commit af21c3fd5b3ec540a97b367a70b26616ff7e0c55 upstream.
Commit 57d104c153d3 ("ufs: add UFS power management support") made the UFS driver submit a REQUEST SENSE command before submitting a power management command to a WLUN to clear the POWER ON unit attention. Instead of submitting a REQUEST SENSE command before submitting a power management command, retry the power management command until it succeeds.
This is the preparation to get rid of all UNIT ATTENTION code which should be handled by users.
--- drivers/scsi/ufs/ufshcd.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)
drivers/scsi/ufs/ufshcd.c +9 -3
@@ -8477,7 +8477,7 @@ static int ufshcd_set_dev_pwr_mode(strucstruct scsi_sense_hdr sshdr;struct scsi_device *sdp;unsigned long flags; -int ret; +int ret, retries;spin_lock_irqsave (hba->host->host_lock, flags); sdp = hba->sdev_ufs_device;
@@ -8510,8 +8510,14 @@ static int ufshcd_set_dev_pwr_mode(struc* callbacks hence set the RQF_PM flag so that it doesn't resume the * already suspended childs. */ - ret =scsi_execute (sdp, cmd,DMA_NONE ,NULL ,0 ,NULL , &sshdr, -START_STOP_TIMEOUT ,0 ,0 ,RQF_PM ,NULL ); +for (retries =3 ; retries >0 ; --retries) { + ret =scsi_execute (sdp, cmd,DMA_NONE ,NULL ,0 ,NULL , &sshdr, +START_STOP_TIMEOUT ,0 ,0 ,RQF_PM ,NULL ); +if (!scsi_status_is_check_condition (ret) || + !scsi_sense_valid (&sshdr) || + sshdr.sense_key !=UNIT_ATTENTION ) +break ; + }if (ret) { sdev_printk(KERN_WARNING, sdp, "START_STOP failed for power mode: %d, result %x\n",
Greg Kroah-Hartman
maintainerPATCH 35/177 drm/i915/hdmi: convert intel_hdmi_to_dev to intel_hdmi_to_i915
In reply to Greg Kroah-HartmanFrom: Jani Nikula <[email protected]>
commit 7ceb751b615900086eed1d65955933923f127d99 upstream.
Prefer i915 over drm pointer.
--- drivers/gpu/drm/i915/display/intel_hdmi.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-)
drivers/gpu/drm/i915/display/intel_hdmi.c +7 -9
@@ -53,21 +53,20 @@#include "intel_panel.h" #include "intel_snps_phy.h" -static struct drm_device *intel_hdmi_to_dev (struct intel_hdmi *intel_hdmi) +static struct drm_i915_private *intel_hdmi_to_i915 (struct intel_hdmi *intel_hdmi) { -return hdmi_to_dig_port (intel_hdmi)->base.base.dev; +return to_i915 (hdmi_to_dig_port (intel_hdmi)->base.base.dev); }static void assert_hdmi_port_disabled (struct intel_hdmi *intel_hdmi) { -struct drm_device *dev =intel_hdmi_to_dev (intel_hdmi); -struct drm_i915_private *dev_priv =to_i915 (dev); +struct drm_i915_private *dev_priv =intel_hdmi_to_i915 (intel_hdmi);u32 enabled_bits; enabled_bits =HAS_DDI (dev_priv) ?DDI_BUF_CTL_ENABLE :SDVO_ENABLE ; -drm_WARN (dev, +drm_WARN (&dev_priv->drm,intel_de_read (dev_priv, intel_hdmi->hdmi_reg) & enabled_bits,"HDMI port enabled, expecting disabled\n" ); }
@@ -1246,7 +1245,7 @@ static void hsw_set_infoframes(struct invoid intel_dp_dual_mode_set_tmds_output (struct intel_hdmi *hdmi,bool enable) { -struct drm_i915_private *dev_priv =to_i915 (intel_hdmi_to_dev (hdmi)); +struct drm_i915_private *dev_priv =intel_hdmi_to_i915 (hdmi);struct i2c_adapter *adapter =intel_gmbus_get_adapter (dev_priv, hdmi->ddc_bus);
@@ -1830,7 +1829,7 @@ hdmi_port_clock_valid(struct intel_hdmi int clock, bool respect_downstream_limits, bool has_hdmi_sink) { - struct drm_i915_private *dev_priv = to_i915(intel_hdmi_to_dev(hdmi)); + struct drm_i915_private *dev_priv = intel_hdmi_to_i915(hdmi);if (clock <25000 )return MODE_CLOCK_LOW ;
@@ -1946,8 +1945,7 @@ intel_hdmi_mode_valid(struct drm_connect struct drm_display_mode *mode) {struct intel_hdmi *hdmi =intel_attached_hdmi (to_intel_connector (connector)); -struct drm_device *dev =intel_hdmi_to_dev (hdmi); -struct drm_i915_private *dev_priv =to_i915 (dev); +struct drm_i915_private *dev_priv =intel_hdmi_to_i915 (hdmi);enum drm_mode_status status;int clock = mode->clock;int max_dotclk =to_i915 (connector->dev)->max_dotclk_freq;
Greg Kroah-Hartman
maintainerPATCH 36/177 drm/i915/hdmi: Turn DP++ TMDS output buffers back on in encoder->shutdown()
In reply to Greg Kroah-HartmanFrom: Ville Syrjälä <[email protected]>
commit cecbc0c7eba7983965cac94f88d2db00b913253b upstream.
Looks like our VBIOS/GOP generally fail to turn the DP dual mode adater TMDS output buffers back on after a reboot. This leads to a black screen after reboot if we turned the TMDS output buffers off prior to reboot. And if i915 decides to do a fastboot the black screen will persist even after i915 takes over.
Apparently this has been a problem ever since commit b2ccb822d376 ("drm/i915:
Enable/disable TMDS output buffers in DP++ adaptor as needed") if one rebooted while the display was turned off. And things became worse with commit fe0f1e3bfdfe ("drm/i915: Shut down displays gracefully on reboot") since now we always turn the display off before a reboot.
This was reported on a RKL, but I confirmed the same behaviour on my SNB as well. So looks pretty universal.
Let's fix this by explicitly turning the TMDS output buffers back on in the encoder->shutdown() hook. Note that this gets called after irqs have been disabled, so the i2c communication with the DP dual mode adapter has to be performed via polling (which the gmbus code is perfectly happy to do for us).
We also need a bit of care in handling DDI encoders which may or may not be set up for HDMI output. Specifically ddc_pin will not be populated for a DP only DDI encoder, in which case we don't want to call intel_gmbus_get_adapter(). We can handle that by simply doing the dual mode adapter type check before calling intel_gmbus_get_adapter().
--- drivers/gpu/drm/i915/display/g4x_hdmi.c | 1 + drivers/gpu/drm/i915/display/intel_ddi.c | 1 + drivers/gpu/drm/i915/display/intel_hdmi.c | 16 ++++++++++++++-- drivers/gpu/drm/i915/display/intel_hdmi.h | 1 + 4 files changed, 17 insertions(+), 2 deletions(-)
drivers/gpu/drm/i915/display/g4x_hdmi.c +1 -0
@@ -584,6 +584,7 @@ void g4x_hdmi_init(struct drm_i915_privaelse intel_encoder->enable = g4x_enable_hdmi; } + intel_encoder->shutdown = intel_hdmi_encoder_shutdown; intel_encoder->type =INTEL_OUTPUT_HDMI ; intel_encoder->power_domain =intel_port_to_power_domain (port);
drivers/gpu/drm/i915/display/intel_ddi.c +1 -0
@@ -4432,6 +4432,7 @@ static void intel_ddi_encoder_shutdown(senum phy phy =intel_port_to_phy (i915, encoder->port);intel_dp_encoder_shutdown (encoder); +intel_hdmi_encoder_shutdown (encoder);if (!intel_phy_is_tc (i915, phy))return ;
drivers/gpu/drm/i915/display/intel_hdmi.c +14 -2
@@ -1246,12 +1246,13 @@ static void hsw_set_infoframes(struct invoid intel_dp_dual_mode_set_tmds_output (struct intel_hdmi *hdmi,bool enable) {struct drm_i915_private *dev_priv =intel_hdmi_to_i915 (hdmi); -struct i2c_adapter *adapter = -intel_gmbus_get_adapter (dev_priv, hdmi->ddc_bus); +struct i2c_adapter *adapter;if (hdmi->dp_dual_mode.type <DRM_DP_DUAL_MODE_TYPE2_DVI )return ; + adapter =intel_gmbus_get_adapter (dev_priv, hdmi->ddc_bus); +drm_dbg_kms (&dev_priv->drm,"%s DP dual mode adaptor TMDS output\n" , enable ?"Enabling" :"Disabling" );
@@ -2258,6 +2259,17 @@ int intel_hdmi_compute_config(struct intreturn 0 ; } +void intel_hdmi_encoder_shutdown (struct intel_encoder *encoder) +{ +struct intel_hdmi *intel_hdmi =enc_to_intel_hdmi (encoder); + +/* +* Give a hand to buggy BIOSen which forget to turn +* the TMDS output buffers back on after a reboot. +*/ +intel_dp_dual_mode_set_tmds_output (intel_hdmi, true); +} +static void intel_hdmi_unset_edid (struct drm_connector *connector) {
drivers/gpu/drm/i915/display/intel_hdmi.h +1 -0
@@ -28,6 +28,7 @@ void intel_hdmi_init_connector(struct inint intel_hdmi_compute_config (struct intel_encoder *encoder,struct intel_crtc_state *pipe_config,struct drm_connector_state *conn_state); +void intel_hdmi_encoder_shutdown (struct intel_encoder *encoder); bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder, struct drm_connector *connector, bool high_tmds_clock_ratio,
Greg Kroah-Hartman
maintainerPATCH 37/177 pinctrl: amd: Fix wakeups when IRQ is shared with SCI
In reply to Greg Kroah-HartmanFrom: Mario Limonciello <[email protected]>
commit 2d54067fcd23aae61e23508425ae5b29e973573d upstream.
On some Lenovo AMD Gen2 platforms the IRQ for the SCI and pinctrl drivers are shared. Due to how the s2idle loop handling works, this case needs an extra explicit check whether the interrupt was caused by SCI or by the GPIO controller.
To fix this rework the existing IRQ handler function to function as a checker and an IRQ handler depending on the calling arguments.
--- drivers/pinctrl/pinctrl-amd.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-)
drivers/pinctrl/pinctrl-amd.c +26 -3
@@ -598,14 +598,14 @@ static struct irq_chip amd_gpio_irqchip#define PIN_IRQ_PENDING (BIT(INTERRUPT_STS_OFF) | BIT(WAKE_STS_OFF)) -static irqreturn_t amd_gpio_irq_handler (int irq,void *dev_id) +static bool do_amd_gpio_irq_handler (int irq,void *dev_id) {struct amd_gpio *gpio_dev = dev_id;struct gpio_chip *gc = &gpio_dev->gc; -irqreturn_t ret =IRQ_NONE ;unsigned int i, irqnr;unsigned long flags;u32 __iomem *regs; +bool ret = false;u32 regval;u64 status, mask;
@@ -627,6 +627,14 @@ static irqreturn_t amd_gpio_irq_handler(/* Each status bit covers four pins */ for (i =0 ; i <4 ; i++) { regval =readl (regs + i); +/* caused wake on resume context for shared IRQ */ +if (irq <0 && (regval &BIT (WAKE_STS_OFF ))) { +dev_dbg (&gpio_dev->pdev->dev, +"Waking due to GPIO %d: 0x%x" , + irqnr + i, regval); +return true; + } +if (!(regval &PIN_IRQ_PENDING ) || !(regval &BIT (INTERRUPT_MASK_OFF )))continue ;
@@ -650,9 +658,12 @@ static irqreturn_t amd_gpio_irq_handler( }writel (regval, regs + i);raw_spin_unlock_irqrestore (&gpio_dev->lock, flags); - ret =IRQ_HANDLED ; + ret = true; } } +/* did not cause wake on resume context for shared IRQ */ +if (irq <0 ) +return false;/* Signal EOI to the GPIO unit */ raw_spin_lock_irqsave (&gpio_dev->lock, flags);
@@ -664,6 +675,16 @@ static irqreturn_t amd_gpio_irq_handler(return ret; } +static irqreturn_t amd_gpio_irq_handler (int irq,void *dev_id) +{ +return IRQ_RETVAL (do_amd_gpio_irq_handler (irq, dev_id)); +} + +static bool __maybe_unused amd_gpio_check_wake (void *dev_id) +{ +return do_amd_gpio_irq_handler (-1 , dev_id); +} +static int amd_get_groups_count (struct pinctrl_dev *pctldev) {struct amd_gpio *gpio_dev =pinctrl_dev_get_drvdata (pctldev);
@@ -1033,6 +1054,7 @@ static int amd_gpio_probe(struct platfor goto out2;platform_set_drvdata (pdev, gpio_dev); +acpi_register_wakeup_handler (gpio_dev->irq, amd_gpio_check_wake, gpio_dev);dev_dbg (&pdev->dev,"amd gpio driver loaded\n" );return ret;
@@ -1050,6 +1072,7 @@ static int amd_gpio_remove(struct platfo gpio_dev =platform_get_drvdata (pdev);gpiochip_remove (&gpio_dev->gc); +acpi_unregister_wakeup_handler (amd_gpio_check_wake, gpio_dev);return 0 ; }
Greg Kroah-Hartman
maintainerPATCH 38/177 arm64: dts: rockchip: remove mmc-hs400-enhanced-strobe from rk3399-khadas-edge
In reply to Greg Kroah-HartmanFrom: Artem Lapkin <[email protected]>
[ Upstream commit 6dd0053683804427529ef3523f7872f473440a19 ]
Remove mmc-hs400-enhanced-strobe from the rk3399-khadas-edge dts to improve compatibility with a wider range of eMMC chips.
Before (BJTD4R 29.1 GiB):
[ 7.001493] mmc2: CQHCI version 5.10 [ 7.027971] mmc2: SDHCI controller on fe330000.mmc [fe330000.mmc] using ADMA ....... [ 7.207086] mmc2: mmc_select_hs400es failed, error -110 [ 7.207129] mmc2: error -110 whilst initialising MMC card [ 7.308893] mmc2: mmc_select_hs400es failed, error -110 [ 7.308921] mmc2: error -110 whilst initialising MMC card [ 7.427524] mmc2: mmc_select_hs400es failed, error -110 [ 7.427546] mmc2: error -110 whilst initialising MMC card [ 7.590993] mmc2: mmc_select_hs400es failed, error -110 [ 7.591012] mmc2: error -110 whilst initialising MMC card
After:
[ 6.960785] mmc2: CQHCI version 5.10 [ 6.984672] mmc2: SDHCI controller on fe330000.mmc [fe330000.mmc] using ADMA [ 7.175021] mmc2: Command Queue Engine enabled [ 7.175053] mmc2: new HS400 MMC card at address 0001 [ 7.175808] mmcblk2: mmc2:0001 BJTD4R 29.1 GiB [ 7.176033] mmcblk2boot0: mmc2:0001 BJTD4R 4.00 MiB [ 7.176245] mmcblk2boot1: mmc2:0001 BJTD4R 4.00 MiB [ 7.176495] mmcblk2rpmb: mmc2:0001 BJTD4R 4.00 MiB, chardev (242:0)
--- arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi | 1 - 1 file changed, 1 deletion(-)
arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi +0 -1
@@ -705,7 +705,6 @@ &sdmmc { &sdhci { bus-width = <8>; mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; non-removable; status = "okay"; };
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 39/177 arm64: dts: rockchip: fix rk3308-roc-cc vcc-sd supply
In reply to Greg Kroah-HartmanFrom: John Keeping <[email protected]>
[ Upstream commit 772fb46109f635dd75db20c86b7eaf48efa46cef ]
Correct a typo in the vin-supply property. The input supply is always-on, so this mistake doesn't affect whether the supply is actually enabled correctly.
--- arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts +1 -1
@@ -97,7 +97,7 @@ vcc_sd: vcc-sd { regulator-max-microvolt = <3300000>; regulator-always-on; regulator-boot-on; - vim-supply = <&vcc_io>; + vin-supply = <&vcc_io>; }; vdd_core: vdd-core {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 40/177 arm64: dts: rockchip: fix rk3399-leez-p710 vcc3v3-lan supply
In reply to Greg Kroah-HartmanFrom: John Keeping <[email protected]>
[ Upstream commit 2b454a90e2ccdd6e03f88f930036da4df577be76 ]
Correct a typo in the vin-supply property. The input supply is always-on, so this mistake doesn't affect whether the supply is actually enabled correctly.
--- arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts +1 -1
@@ -55,7 +55,7 @@ vcc3v3_lan: vcc3v3-lan { regulator-boot-on; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - vim-supply = <&vcc3v3_sys>; + vin-supply = <&vcc3v3_sys>; }; vcc3v3_sys: vcc3v3-sys {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 41/177 arm64: dts: rockchip: fix audio-supply for Rock Pi 4
In reply to Greg Kroah-HartmanFrom: Alex Bee <[email protected]>
[ Upstream commit 8240e87f16d17a9592c9d67857a3dcdbcb98f10d ]
As stated in the schematics [1] and [2] P5 the APIO5 domain is supplied by RK808-D Buck4, which in our case vcc1v8_codec - i.e. a 1.8 V regulator.
Currently only white noise comes from the ES8316's output, which - for whatever reason - came up only after the the correct switch from i2s0_8ch_bus to i2s0_2ch_bus for i2s0's pinctrl was done.
Fix this by setting the correct regulator for audio-supply.
[1] https://dl.radxa.com/rockpi4/docs/hw/rockpi4/rockpi4_v13_sch_20181112.pdf
[2] https://dl.radxa.com/rockpi4/docs/hw/rockpi4/rockpi_4c_v12_sch_20200620.pdf
--- arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +1 -1
@@ -457,7 +457,7 @@ &io_domains { status = "okay"; bt656-supply = <&vcc_3v0>; - audio-supply = <&vcc_3v0>; + audio-supply = <&vcc1v8_codec>; sdmmc-supply = <&vcc_sdio>; gpio1830-supply = <&vcc_3v0>; };
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 42/177 arm64: dts: rockchip: fix poweroff on helios64
In reply to Greg Kroah-HartmanFrom: Florian Klink <[email protected]>
[ Upstream commit aef4b9a89a376a9cabe5e744729914e7766c59bb ]
Adding the rockchip,system-power-controller property here will use the rk808 to power off the system.
--- arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts | 1 + 1 file changed, 1 insertion(+)
arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts +1 -0
@@ -269,6 +269,7 @@ rk808: pmic@1b { clock-output-names = "xin32k", "rk808-clkout2"; pinctrl-names = "default"; pinctrl-0 = <&pmic_int_l>; + rockchip,system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; vcc3-supply = <&vcc5v0_sys>;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 43/177 dmaengine: idxd: add halt interrupt support
In reply to Greg Kroah-HartmanFrom: Dave Jiang <[email protected]>
[ Upstream commit 88d97ea82cbe352851a8654ee952d3a694c8c2c6 ]
Add halt interrupt support. Given that the misc interrupt handler already check halt state, the driver just need to run the halt handling code when receiving the halt interrupt.
--- drivers/dma/idxd/irq.c | 5 +++++ drivers/dma/idxd/registers.h | 1 + 2 files changed, 6 insertions(+)
drivers/dma/idxd/irq.c +5 -0
@@ -63,6 +63,9 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)int i;bool err = false; +if (cause &IDXD_INTC_HALT_STATE ) + goto halt; +if (cause &IDXD_INTC_ERR ) {spin_lock (&idxd->dev_lock);for (i =0 ; i <4 ; i++)
@@ -121,6 +124,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)if (!err)return 0 ; +halt: gensts.bits =ioread32 (idxd->reg_base +IDXD_GENSTATS_OFFSET );if (gensts.state ==IDXD_DEVICE_STATE_HALT ) { idxd->state =IDXD_DEV_HALTED ;
@@ -134,6 +138,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)queue_work (idxd->wq, &idxd->work); }else {spin_lock (&idxd->dev_lock); + idxd->state =IDXD_DEV_HALTED ;idxd_wqs_quiesce (idxd);idxd_wqs_unmap_portal (idxd);idxd_device_clear_state (idxd);
drivers/dma/idxd/registers.h +1 -0
@@ -158,6 +158,7 @@ enum idxd_device_reset_type {#define IDXD_INTC_CMD 0x02#define IDXD_INTC_OCCUPY 0x04#define IDXD_INTC_PERFMON_OVFL 0x08 +#define IDXD_INTC_HALT_STATE 0x10#define IDXD_CMD_OFFSET 0xa0union idxd_command_reg {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 44/177 dmaengine: idxd: fix calling wq quiesce inside spinlock
In reply to Greg Kroah-HartmanFrom: Dave Jiang <[email protected]>
[ Upstream commit fa51b16d05583c7aebbc06330afb50276243d198 ]
Dan reports that smatch has found idxd_wq_quiesce() is being called inside the idxd->dev_lock. idxd_wq_quiesce() calls wait_for_completion() and therefore it can sleep. Move the call outside of the spinlock as it does not need device lock.
--- drivers/dma/idxd/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/dma/idxd/irq.c +1 -1
@@ -137,10 +137,10 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)INIT_WORK (&idxd->work, idxd_device_reinit);queue_work (idxd->wq, &idxd->work); }else { -spin_lock (&idxd->dev_lock); idxd->state =IDXD_DEV_HALTED ;idxd_wqs_quiesce (idxd);idxd_wqs_unmap_portal (idxd); +spin_lock (&idxd->dev_lock);idxd_device_clear_state (idxd); dev_err(&idxd->pdev->dev, "idxd halted, need %s.\n",
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 45/177 mac80211: track only QoS data frames for admission control
In reply to Greg Kroah-HartmanFrom: Johannes Berg <[email protected]>
[ Upstream commit d5e568c3a4ec2ddd23e7dc5ad5b0c64e4f22981a ]
For admission control, obviously all of that only works for QoS data frames, otherwise we cannot even access the QoS field in the header.
Syzbot reported (see below) an uninitialized value here due to a status of a non-QoS nullfunc packet, which isn't even long enough to contain the QoS header.
Fix this to only do anything for QoS data packets.
--- net/mac80211/mlme.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
net/mac80211/mlme.c +10 -3
@@ -2446,11 +2446,18 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata, u16 tx_time) {struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; -u16 tid =ieee80211_get_tid (hdr); -int ac =ieee80211_ac_from_tid (tid); -struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; +u16 tid; +int ac; +struct ieee80211_sta_tx_tspec *tx_tspec;unsigned long now = jiffies; +if (!ieee80211_is_data_qos (hdr->frame_control)) +return ; + + tid =ieee80211_get_tid (hdr); + ac =ieee80211_ac_from_tid (tid); + tx_tspec = &ifmgd->tx_tspec[ac]; +if (likely (!tx_tspec->admitted_time))return ;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 46/177 hv: utils: add PTP_1588_CLOCK to Kconfig to fix build
In reply to Greg Kroah-HartmanFrom: Randy Dunlap <[email protected]>
[ Upstream commit 1dc2f2b81a6a9895da59f3915760f6c0c3074492 ]
The hyperv utilities use PTP clock interfaces and should depend a a kconfig symbol such that they will be built as a loadable module or builtin so that linker errors do not happen.
Prevents these build errors:
ld: drivers/hv/hv_util.o: in function `hv_timesync_deinit':
hv_util.c:(.text+0x37d): undefined reference to `ptp_clock_unregister'
ld: drivers/hv/hv_util.o: in function `hv_timesync_init':
hv_util.c:(.text+0x738): undefined reference to `ptp_clock_register'
--- drivers/hv/Kconfig | 1 + 1 file changed, 1 insertion(+)
drivers/hv/Kconfig +1 -0
@@ -18,6 +18,7 @@ config HYPERV_TIMER config HYPERV_UTILS tristate "Microsoft Hyper-V Utilities driver" depends on HYPERV && CONNECTOR && NLS + depends on PTP_1588_CLOCK_OPTIONAL help Select this option to enable the Hyper-V Utilities.
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 47/177 tee: amdtee: fix an IS_ERR() vs NULL bug
In reply to Greg Kroah-HartmanFrom: Dan Carpenter <[email protected]>
[ Upstream commit 9d7482771fac8d8e38e763263f2ca0ca12dd22c6 ]
The __get_free_pages() function does not return error pointers it returns NULL so fix this condition to avoid a NULL dereference.
--- drivers/tee/amdtee/core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/tee/amdtee/core.c +2 -3
@@ -203,9 +203,8 @@ static int copy_ta_binary(struct tee_context *ctx, void *ptr, void **ta, *ta_size =roundup (fw->size,PAGE_SIZE ); *ta = (void *)__get_free_pages (GFP_KERNEL ,get_order (*ta_size)); -if (IS_ERR (*ta)) { -pr_err ("%s: get_free_pages failed 0x%llx\n" , __func__, - (u64)*ta); +if (!*ta) { +pr_err ("%s: get_free_pages failed\n" , __func__); rc = -ENOMEM ; goto rel_fw; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 48/177 ceph: fix duplicate increment of opened_inodes metric
In reply to Greg Kroah-HartmanFrom: Hu Weiwen <[email protected]>
[ Upstream commit 973e5245637accc4002843f6b888495a6a7762bc ]
opened_inodes is incremented twice when the same inode is opened twice with O_RDONLY and O_WRONLY respectively.
To reproduce, run this python script, then check the metrics:
import os
for _ in range(10000):
fd_r = os.open('a', os.O_RDONLY)
fd_w = os.open('a', os.O_WRONLY)
os.close(fd_r)
os.close(fd_w)--- fs/ceph/caps.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)
fs/ceph/caps.c +8 -8
@@ -4349,7 +4349,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) {struct ceph_mds_client *mdsc =ceph_sb_to_mdsc (ci->vfs_inode.i_sb);int bits = (fmode <<1 ) |1 ; -bool is_opened = false; +bool already_opened = false;int i;if (count ==1 )
@@ -4357,19 +4357,19 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)spin_lock (&ci->i_ceph_lock);for (i =0 ; i <CEPH_FILE_MODE_BITS ; i++) { -if (bits & (1 << i)) - ci->i_nr_by_mode[i] += count; -/* -* If any of the mode ref is larger than 1, +* If any of the mode ref is larger than 0, * that means it has been already opened by * others. Just skip checking the PIN ref. */ -if (i && ci->i_nr_by_mode[i] >1 ) - is_opened = true; +if (i && ci->i_nr_by_mode[i]) + already_opened = true; + +if (bits & (1 << i)) + ci->i_nr_by_mode[i] += count; } -if (!is_opened) +if (!already_opened)percpu_counter_inc (&mdsc->metric.opened_inodes);spin_unlock (&ci->i_ceph_lock); }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 49/177 ceph: initialize pathlen variable in reconnect_caps_cb
In reply to Greg Kroah-HartmanFrom: Xiubo Li <[email protected]>
[ Upstream commit ee2a095d3b24f300a5e11944d208801e928f108c ]
The smatch static checker warned about an uninitialized symbol usage in this function, in the case where ceph_mdsc_build_path returns an error.
It turns out that that case is harmless, but it just looks sketchy. Initialize the variable at declaration time, and remove the unneeded setting of it later.
--- fs/ceph/mds_client.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
fs/ceph/mds_client.c +1 -2
@@ -3772,7 +3772,7 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap,struct ceph_pagelist *pagelist = recon_state->pagelist;struct dentry *dentry;char *path; -int pathlen, err; +int pathlen =0 , err;u64 pathbase;u64 snap_follows;
@@ -3792,7 +3792,6 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, } }else { path =NULL ; - pathlen =0 ; pathbase =0 ; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 50/177 ARM: socfpga: dts: fix qspi node compatible
In reply to Greg Kroah-HartmanFrom: Dinh Nguyen <[email protected]>
[ Upstream commit cb25b11943cbcc5a34531129952870420f8be858 ]
The QSPI flash node needs to have the required "jedec,spi-nor" in the compatible string.
--- arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts | 2 +- arch/arm/boot/dts/socfpga_arria5_socdk.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_socdk.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_sockit.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_socrates.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_sodia.dts | 2 +- arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts | 4 ++-- 7 files changed, 8 insertions(+), 8 deletions(-)
arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts +1 -1
@@ -12,7 +12,7 @@ &qspi { flash0: n25q00@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00aa"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>;
arch/arm/boot/dts/socfpga_arria5_socdk.dts +1 -1
@@ -119,7 +119,7 @@ &qspi { flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>;
arch/arm/boot/dts/socfpga_cyclone5_socdk.dts +1 -1
@@ -124,7 +124,7 @@ &qspi { flash0: n25q00@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; /* chip select */ spi-max-frequency = <100000000>;
arch/arm/boot/dts/socfpga_cyclone5_sockit.dts +1 -1
@@ -169,7 +169,7 @@ &qspi { flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>;
arch/arm/boot/dts/socfpga_cyclone5_socrates.dts +1 -1
@@ -80,7 +80,7 @@ &qspi { flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; m25p,fast-read;
arch/arm/boot/dts/socfpga_cyclone5_sodia.dts +1 -1
@@ -116,7 +116,7 @@ &qspi { flash0: n25q512a@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q512a"; + compatible = "micron,n25q512a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>;
arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts +2 -2
@@ -224,7 +224,7 @@ &qspi { n25q128@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q128"; + compatible = "micron,n25q128", "jedec,spi-nor"; reg = <0>; /* chip select */ spi-max-frequency = <100000000>; m25p,fast-read;
@@ -241,7 +241,7 @@ n25q128@0 { n25q00@1 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <1>; /* chip select */ spi-max-frequency = <100000000>; m25p,fast-read;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 51/177 arm64: dts: imx8mq: remove interconnect property from lcdif
In reply to Greg Kroah-HartmanFrom: Martin Kepplinger <[email protected]>
[ Upstream commit e5e6268f77badf18bd6ab435364cfe21c7396c31 ]
The mxsfb driver handling imx8mq lcdif doesn't yet request the interconnect bandwidth that's needed at runtime when the description is present in the DT node.
So remove that description and bring it back when it's supported.
--- arch/arm64/boot/dts/freescale/imx8mq.dtsi | 2 -- 1 file changed, 2 deletions(-)
arch/arm64/boot/dts/freescale/imx8mq.dtsi +0 -2
@@ -524,8 +524,6 @@ lcdif: lcd-controller@30320000 { <&clk IMX8MQ_VIDEO_PLL1>, <&clk IMX8MQ_VIDEO_PLL1_OUT>; assigned-clock-rates = <0>, <0>, <0>, <594000000>; - interconnects = <&noc IMX8MQ_ICM_LCDIF &noc IMX8MQ_ICS_DRAM>; - interconnect-names = "dram"; status = "disabled"; port@0 {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 52/177 clk: Dont parent clks until the parent is fully registered
In reply to Greg Kroah-HartmanFrom: Mike Tipton <[email protected]>
[ Upstream commit 54baf56eaa40aa5cdcd02b3c20d593e4e1211220 ]
Before commit fc0c209c147f ("clk: Allow parents to be specified without string names") child clks couldn't find their parent until the parent clk was added to a list in __clk_core_init(). After that commit, child clks can reference their parent clks directly via a clk_hw pointer, or they can lookup that clk_hw pointer via DT if the parent clk is registered with an OF clk provider.
The common clk framework treats hw->core being non-NULL as "the clk is registered" per the logic within clk_core_fill_parent_index():
parent = entry->hw->core; /* * We have a direct reference but it isn't registered yet? * Orphan it and let clk_reparent() update the orphan status * when the parent is registered. */ if (!parent)
Therefore we need to be extra careful to not set hw->core until the clk is fully registered with the clk framework. Otherwise we can get into a situation where a child finds a parent clk and we move the child clk off the orphan list when the parent isn't actually registered, wrecking our enable accounting and breaking critical clks.
Consider the following scenario:
CPU0 CPU1
---- ----
struct clk_hw clkBad;
struct clk_hw clkA;
clkA.init.parent_hws = { &clkBad }; clk_hw_register(&clkA) clk_hw_register(&clkBad)
... __clk_register()
hw->core = core
...
__clk_register()
__clk_core_init()
clk_prepare_lock()
__clk_init_parent()
clk_core_get_parent_by_index()
clk_core_fill_parent_index()
if (entry->hw) {
parent = entry->hw->core;At this point, 'parent' points to clkBad even though clkBad hasn't been fully registered yet. Ouch! A similar problem can happen if a clk controller registers orphan clks that are referenced in the DT node of another clk controller.
Let's fix all this by only setting the hw->core pointer underneath the clk prepare lock in __clk_core_init(). This way we know that clk_core_fill_parent_index() can't see hw->core be non-NULL until the clk is fully registered.
--- drivers/clk/clk.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)
drivers/clk/clk.c +12 -3
@@ -3415,6 +3415,14 @@ static int __clk_core_init(struct clk_core *core)clk_prepare_lock (); +/* +* Set hw->core after grabbing the prepare_lock to synchronize with +* callers of clk_core_fill_parent_index() where we treat hw->core +* being NULL as the clk not being registered yet. This is crucial so +* that clks aren't parented until their parent is fully registered. +*/ + core->hw->core = core; + ret =clk_pm_runtime_get (core);if (ret) goto unlock;
@@ -3579,8 +3587,10 @@ static int __clk_core_init(struct clk_core *core) out:clk_pm_runtime_put (core); unlock: -if (ret) +if (ret) {hlist_del_init (&core->child_node); + core->hw->core =NULL ; + }clk_prepare_unlock ();
@@ -3844,7 +3854,6 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) core->num_parents = init->num_parents; core->min_rate =0 ; core->max_rate =ULONG_MAX ; - hw->core = core; ret =clk_core_populate_parent_map (core, init);if (ret)
@@ -3862,7 +3871,7 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_create_clk; } -clk_core_link_consumer (hw->core, hw->clk); +clk_core_link_consumer (core, hw->clk); ret =__clk_core_init (core);if (!ret)
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 53/177 soc: imx: Register SoC device only on i.MX boards
In reply to Greg Kroah-HartmanFrom: Stephan Gerhold <[email protected]>
[ Upstream commit 4ebd29f91629e69da7d57390cdc953772eee03ab ]
At the moment, using the ARM32 multi_v7_defconfig always results in two SoCs being exposed in sysfs. This is wrong, as far as I'm aware the Qualcomm DragonBoard 410c does not actually make use of a i.MX SoC. :)
qcom-db410c:/sys/devices/soc0$ grep . * family:Freescale i.MX machine:Qualcomm Technologies, Inc. APQ 8016 SBC revision:0.0 serial_number:0000000000000000 soc_id:Unknown
qcom-db410c:/sys/devices/soc1$ grep . * family:Snapdragon machine:APQ8016 ...
This happens because imx_soc_device_init() registers the soc device unconditionally, even when running on devices that do not make use of i.MX. Arnd already reported this more than a year ago and even suggested a fix similar to this commit, but for some reason it was never submitted.
Fix it by checking if the "__mxc_cpu_type" variable was actually initialized by earlier platform code. On devices without i.MX it will simply stay 0.
--- drivers/soc/imx/soc-imx.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/soc/imx/soc-imx.c +4 -0
@@ -36,6 +36,10 @@ static int __init imx_soc_device_init(void)int ret;int i; +/* Return early if this is running on devices with different SoCs */ +if (!__mxc_cpu_type) +return 0 ; +if (of_machine_is_compatible ("fsl,ls1021a" ))return 0 ;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 54/177 iwlwifi: mvm: dont crash on invalid rate w/o STA
In reply to Greg Kroah-HartmanFrom: Johannes Berg <[email protected]>
[ Upstream commit d599f714b73e4177dfdfe64fce09175568288ee9 ]
If we get to the WARN_ONCE(..., "Got a HT rate (...)", ...) here with a NULL sta, then we crash because mvmsta is bad and we try to dereference it. Fix that by printing -1 as the state if no station was given.
--- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/wireless/intel/iwlwifi/mvm/tx.c +3 -2
@@ -268,17 +268,18 @@ static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm,int rate_idx =-1 ;u8 rate_plcp;u32 rate_flags =0 ; -struct iwl_mvm_sta *mvmsta =iwl_mvm_sta_from_mac80211 (sta);/* info->control is only relevant for non HW rate control */ if (!ieee80211_hw_check (mvm->hw,HAS_RATE_CONTROL )) { +struct iwl_mvm_sta *mvmsta =iwl_mvm_sta_from_mac80211 (sta); +/* HT rate doesn't make sense for a non data frame */ WARN_ONCE (info->control.rates[0 ].flags &IEEE80211_TX_RC_MCS && !ieee80211_is_data (fc),"Got a HT rate (flags:0x%x/mcs:%d/fc:0x%x/state:%d) for a non data frame\n" , info->control.rates[0 ].flags, info->control.rates[0 ].idx, -le16_to_cpu (fc), mvmsta->sta_state); +le16_to_cpu (fc), sta ? mvmsta->sta_state :-1 ); rate_idx = info->control.rates[0 ].idx; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 55/177 virtio: always enter drivers/virtio/
In reply to Greg Kroah-HartmanFrom: Arnd Bergmann <[email protected]>
[ Upstream commit 27d9839f17940e8edc475df616bbd9cf7ede8d05 ]
When neither VIRTIO_PCI_LIB nor VIRTIO are enabled, but the alibaba vdpa driver is, the kernel runs into a link error because the legacy virtio module never gets built:
x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_features':
eni_vdpa.c:(.text+0x23f): undefined reference to `vp_legacy_set_features'
x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_vq_state':
eni_vdpa.c:(.text+0x2fe): undefined reference to `vp_legacy_get_queue_enable'
x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_vq_address':
eni_vdpa.c:(.text+0x376): undefined reference to `vp_legacy_set_queue_address'
x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_set_vq_ready':
eni_vdpa.c:(.text+0x3b4): undefined reference to `vp_legacy_set_queue_address'
x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_free_irq':
eni_vdpa.c:(.text+0x460): undefined reference to `vp_legacy_queue_vector'
x86_64-linux-ld: eni_vdpa.c:(.text+0x4b7): undefined reference to `vp_legacy_config_vector'
x86_64-linux-ld: drivers/vdpa/alibaba/eni_vdpa.o: in function `eni_vdpa_reset':
When VIRTIO_PCI_LIB was added, it was correctly added to drivers/Makefile as well, but for the legacy module, this is missing. Solve this by always entering drivers/virtio during the build and letting its Makefile take care of the individual options, rather than having a separate line for each sub-option.
--- drivers/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/Makefile +1 -2
@@ -41,8 +41,7 @@ obj-$(CONFIG_DMADEVICES) += dma/ # SOC specific infrastructure drivers. obj-y += soc/ -obj-$(CONFIG_VIRTIO) += virtio/ -obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio/ +obj-y += virtio/ obj-$(CONFIG_VDPA) += vdpa/ obj-$(CONFIG_XEN) += xen/
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 56/177 virtio/vsock: fix the transport to work with VMADDR_CID_ANY
In reply to Greg Kroah-HartmanFrom: Wei Wang <[email protected]>
[ Upstream commit 1db8f5fc2e5c66a5c51e1f6488e0ba7d45c29ae4 ]
The VMADDR_CID_ANY flag used by a socket means that the socket isn't bound to any specific CID. For example, a host vsock server may want to be bound with VMADDR_CID_ANY, so that a guest vsock client can connect to the host server with CID=VMADDR_CID_HOST (i.e. 2), and meanwhile, a host vsock client can connect to the same local server with CID=VMADDR_CID_LOCAL (i.e. 1).
The current implementation sets the destination socket's svm_cid to a fixed CID value after the first client's connection, which isn't an expected operation. For example, if the guest client first connects to the host server, the server's svm_cid gets set to VMADDR_CID_HOST, then other host clients won't be able to connect to the server anymore.
Reproduce steps:
1. Run the host server:
socat VSOCK-LISTEN:1234,fork -
2. Run a guest client to connect to the host server:
socat - VSOCK-CONNECT:2:1234
3. Run a host client to connect to the host server:
socat - VSOCK-CONNECT:1:1234
Without this patch, step 3. above fails to connect, and socat complains "socat[1720] E connect(5, AF=40 cid:1 port:1234, 16): Connection reset by peer".
With this patch, the above works well.
--- net/vmw_vsock/virtio_transport_common.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/vmw_vsock/virtio_transport_common.c +2 -1
@@ -1299,7 +1299,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, space_available =virtio_transport_space_update (sk, pkt);/* Update CID in case it has changed after a transport reset event */ - vsk->local_addr.svm_cid = dst.svm_cid; +if (vsk->local_addr.svm_cid !=VMADDR_CID_ANY ) + vsk->local_addr.svm_cid = dst.svm_cid;if (space_available) sk->sk_write_space (sk);
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 57/177 vdpa: Consider device id larger than 31
In reply to Greg Kroah-HartmanFrom: Parav Pandit <[email protected]>
[ Upstream commit bb47620be322c5e9e372536cb6b54e17b3a00258 ]
virtio device id value can be more than 31. Hence, use BIT_ULL in assignment.
--- drivers/vdpa/vdpa.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/vdpa/vdpa.c +2 -1
@@ -353,7 +353,8 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m goto msg_err;while (mdev->id_table[i].device) { - supported_classes |=BIT (mdev->id_table[i].device); +if (mdev->id_table[i].device <=63 ) + supported_classes |=BIT_ULL (mdev->id_table[i].device); i++; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 58/177 Revert "drm/fb-helper: improve DRM fbdev emulation device names"
In reply to Greg Kroah-HartmanFrom: Javier Martinez Canillas <[email protected]>
[ Upstream commit 842470c4e211f284a224842849b1fa81b130c154 ]
This reverts commit b3484d2b03e4c940a9598aa841a52d69729c582a.
That change attempted to improve the DRM drivers fbdev emulation device names to avoid having confusing names like "simpledrmdrmfb" in /proc/fb.
But unfortunately, there are user-space programs such as pm-utils that match against the fbdev names and so broke after the mentioned commit.
Since the names in /proc/fb are used by tools that consider it an uAPI, let's restore the old names even when this lead to silly names like the one mentioned above.
--- drivers/gpu/drm/drm_fb_helper.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
drivers/gpu/drm/drm_fb_helper.c +7 -1
@@ -1743,7 +1743,13 @@ void drm_fb_helper_fill_info(struct fb_info *info, sizes->fb_width, sizes->fb_height); info->par = fb_helper; -snprintf (info->fix.id,sizeof (info->fix.id),"%s" , +/* +* The DRM drivers fbdev emulation device name can be confusing if the +* driver name also has a "drm" suffix on it. Leading to names such as +* "simpledrmdrmfb" in /proc/fb. Unfortunately, it's an uAPI and can't +* be changed due user-space tools (e.g: pm-utils) matching against it. +*/ +snprintf (info->fix.id,sizeof (info->fix.id),"%sdrmfb" , fb_helper->dev->driver->name); }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 59/177 selftests: net: Correct ping6 expected rc from 2 to 1
In reply to Greg Kroah-HartmanFrom: Jie2x Zhou <[email protected]>
[ Upstream commit 92816e2629808726af015c7f5b14adc8e4f8b147 ]
./fcnal-test.sh -v -t ipv6_ping
TEST: ping out, VRF bind - ns-B IPv6 LLA [FAIL]
TEST: ping out, VRF bind - multicast IP [FAIL]
ping6 is failing as it should.
COMMAND: ip netns exec ns-A /bin/ping6 -c1 -w1 fe80::7c4c:bcff:fe66:a63a%red strace of ping6 shows it is failing with '1',
so change the expected rc from 2 to 1.
--- tools/testing/selftests/net/fcnal-test.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/net/fcnal-test.sh +1 -1
@@ -2191,7 +2191,7 @@ ipv6_ping_vrf() log_start show_hint "Fails since VRF device does not support linklocal or multicast" run_cmd ${ping6} -c1 -w1 ${a} - log_test_addr ${a} $? 2 "ping out, VRF bind" + log_test_addr ${a} $? 1 "ping out, VRF bind" done for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV}
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 60/177 s390/kexec_file: fix error handling when applying relocations
In reply to Greg Kroah-HartmanFrom: Philipp Rudo <[email protected]>
[ Upstream commit 41967a37b8eedfee15b81406a9f3015be90d3980 ]
arch_kexec_apply_relocations_add currently ignores all errors returned by arch_kexec_do_relocs. This means that every unknown relocation is silently skipped causing unpredictable behavior while the relocated code runs. Fix this by checking for errors and fail kexec_file_load if an unknown relocation type is encountered.
The problem was found after gcc changed its behavior and used R_390_PLT32DBL relocations for brasl instruction and relied on ld to resolve the relocations in the final link in case direct calls are possible. As the purgatory code is only linked partially (option -r) ld didn't resolve the relocations leaving them for arch_kexec_do_relocs. But arch_kexec_do_relocs doesn't know how to handle R_390_PLT32DBL relocations so they were silently skipped. This ultimately caused an endless loop in the purgatory as the brasl instructions kept branching to itself.
--- arch/s390/kernel/machine_kexec_file.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
arch/s390/kernel/machine_kexec_file.c +6 -1
@@ -277,6 +277,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, {Elf_Rela *relas;int i, r_type; +int ret; relas = (void *)pi->ehdr + relsec->sh_offset;
@@ -311,7 +312,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, addr = section->sh_addr + relas[i].r_offset; r_type =ELF64_R_TYPE (relas[i].r_info); -arch_kexec_do_relocs (r_type, loc, val, addr); + ret =arch_kexec_do_relocs (r_type, loc, val, addr); +if (ret) { +pr_err ("Unknown rela relocation: %d\n" , r_type); +return -ENOEXEC ; + } }return 0 ; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 61/177 sch_cake: do not call cake_destroy() from cake_init()
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit ab443c53916730862cec202078d36fd4008bea79 ]
qdiscs are not supposed to call their own destroy() method from init(), because core stack already does that.
syzbot was able to trigger use after free:
DEBUG_LOCKS_WARN_ON(lock->magic != lock)
WARNING: CPU: 0 PID: 21902 at kernel/locking/mutex.c:586 __mutex_lock_common kernel/locking/mutex.c:586 [inline] WARNING: CPU: 0 PID: 21902 at kernel/locking/mutex.c:586 __mutex_lock+0x9ec/0x12f0 kernel/locking/mutex.c:740 Modules linked in: CPU: 0 PID: 21902 Comm: syz-executor189 Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__mutex_lock_common kernel/locking/mutex.c:586 [inline] RIP: 0010:__mutex_lock+0x9ec/0x12f0 kernel/locking/mutex.c:740 Code: 08 84 d2 0f 85 19 08 00 00 8b 05 97 38 4b 04 85 c0 0f 85 27 f7 ff ff 48 c7 c6 20 00 ac 89 48 c7 c7 a0 fe ab 89 e8 bf 76 ba ff <0f> 0b e9 0d f7 ff ff 48 8b 44 24 40 48 8d b8 c8 08 00 00 48 89 f8 RSP: 0018:ffffc9000627f290 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff88802315d700 RSI: ffffffff815f1db8 RDI: fffff52000c4fe44 RBP: ffff88818f28e000 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff815ebb5e R11: 0000000000000000 R12: 0000000000000000 R13: dffffc0000000000 R14: ffffc9000627f458 R15: 0000000093c30000 FS: 0000555556abc400(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fda689c3303 CR3: 000000001cfbb000 CR4: 0000000000350ef0 Call Trace: <TASK> tcf_chain0_head_change_cb_del+0x2e/0x3d0 net/sched/cls_api.c:810 tcf_block_put_ext net/sched/cls_api.c:1381 [inline] tcf_block_put_ext net/sched/cls_api.c:1376 [inline] tcf_block_put+0xbc/0x130 net/sched/cls_api.c:1394 cake_destroy+0x3f/0x80 net/sched/sch_cake.c:2695 qdisc_create.constprop.0+0x9da/0x10f0 net/sched/sch_api.c:1293 tc_modify_qdisc+0x4c5/0x1980 net/sched/sch_api.c:1660 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5571 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2496 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x904/0xdf0 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2409 ___sys_sendmsg+0xf3/0x170 net/socket.c:2463 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2492 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f1bb06badb9 Code: Unable to access opcode bytes at RIP 0x7f1bb06bad8f. RSP: 002b:00007fff3012a658 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f1bb06badb9 RDX: 0000000000000000 RSI: 00000000200007c0 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000003 R09: 0000000000000003 R10: 0000000000000003 R11: 0000000000000246 R12: 00007fff3012a688 R13: 00007fff3012a6a0 R14: 00007fff3012a6e0 R15: 00000000000013c2 </TASK>
--- net/sched/sch_cake.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)
net/sched/sch_cake.c +1 -5
@@ -2736,7 +2736,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->tins =kvcalloc (CAKE_MAX_TINS ,sizeof (struct cake_tin_data ),GFP_KERNEL );if (!q->tins) - goto nomem; +return -ENOMEM ;for (i =0 ; i <CAKE_MAX_TINS ; i++) {struct cake_tin_data *b = q->tins + i;
@@ -2766,10 +2766,6 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->min_netlen = ~0 ; q->min_adjlen = ~0 ;return 0 ; - -nomem: -cake_destroy (sch); -return -ENOMEM ; }static int cake_dump (struct Qdisc *sch,struct sk_buff *skb)
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 62/177 inet_diag: fix kernel-infoleak for UDP sockets
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit 71ddeac8cd1d217744a0e060ff520e147c9328d1 ]
KMSAN reported a kernel-infoleak [1], that can exploited by unpriv users.
After analysis it turned out UDP was not initializing r->idiag_expires. Other users of inet_sk_diag_fill() might make the same mistake in the future, so fix this in inet_sk_diag_fill().
[1]
BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in copyout lib/iov_iter.c:156 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 instrument_copy_to_user include/linux/instrumented.h:121 [inline] copyout lib/iov_iter.c:156 [inline] _copy_to_iter+0x69d/0x25c0 lib/iov_iter.c:670 copy_to_iter include/linux/uio.h:155 [inline] simple_copy_to_iter+0xf3/0x140 net/core/datagram.c:519 __skb_datagram_iter+0x2cb/0x1280 net/core/datagram.c:425 skb_copy_datagram_iter+0xdc/0x270 net/core/datagram.c:533 skb_copy_datagram_msg include/linux/skbuff.h:3657 [inline] netlink_recvmsg+0x660/0x1c60 net/netlink/af_netlink.c:1974 sock_recvmsg_nosec net/socket.c:944 [inline] sock_recvmsg net/socket.c:962 [inline] sock_read_iter+0x5a9/0x630 net/socket.c:1035 call_read_iter include/linux/fs.h:2156 [inline] new_sync_read fs/read_write.c:400 [inline] vfs_read+0x1631/0x1980 fs/read_write.c:481 ksys_read+0x28c/0x520 fs/read_write.c:619 __do_sys_read fs/read_write.c:629 [inline] __se_sys_read fs/read_write.c:627 [inline] __x64_sys_read+0xdb/0x120 fs/read_write.c:627 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae
Uninit was created at:
slab_post_alloc_hook mm/slab.h:524 [inline] slab_alloc_node mm/slub.c:3251 [inline] __kmalloc_node_track_caller+0xe0c/0x1510 mm/slub.c:4974 kmalloc_reserve net/core/skbuff.c:354 [inline] __alloc_skb+0x545/0xf90 net/core/skbuff.c:426 alloc_skb include/linux/skbuff.h:1126 [inline] netlink_dump+0x3d5/0x16a0 net/netlink/af_netlink.c:2245 __netlink_dump_start+0xd1c/0xee0 net/netlink/af_netlink.c:2370 netlink_dump_start include/linux/netlink.h:254 [inline] inet_diag_handler_cmd+0x2e7/0x400 net/ipv4/inet_diag.c:1343 sock_diag_rcv_msg+0x24a/0x620 netlink_rcv_skb+0x447/0x800 net/netlink/af_netlink.c:2491 sock_diag_rcv+0x63/0x80 net/core/sock_diag.c:276 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x1095/0x1360 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x16f3/0x1870 net/netlink/af_netlink.c:1916 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg net/socket.c:724 [inline] sock_write_iter+0x594/0x690 net/socket.c:1057 do_iter_readv_writev+0xa7f/0xc70 do_iter_write+0x52c/0x1500 fs/read_write.c:851 vfs_writev fs/read_write.c:924 [inline] do_writev+0x63f/0xe30 fs/read_write.c:967 __do_sys_writev fs/read_write.c:1040 [inline] __se_sys_writev fs/read_write.c:1037 [inline] __x64_sys_writev+0xe5/0x120 fs/read_write.c:1037 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae
Bytes 68-71 of 312 are uninitialized
Memory access of size 312 starts at ffff88812ab54000 Data copied to user address 0000000020001440
CPU: 1 PID: 6365 Comm: syz-executor801 Not tainted 5.16.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
--- net/ipv4/inet_diag.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
net/ipv4/inet_diag.c +1 -3
@@ -261,6 +261,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_state = sk->sk_state; r->idiag_timer =0 ; r->idiag_retrans =0 ; + r->idiag_expires =0 ; if (inet_diag_msg_attrs_fill(sk, skb, r, ext, sk_user_ns(NETLINK_CB(cb->skb).sk),
@@ -314,9 +315,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires =jiffies_delta_to_msecs (sk->sk_timer.expires - jiffies); - }else { - r->idiag_timer =0 ; - r->idiag_expires =0 ; }if ((ext & (1 << (INET_DIAG_INFO -1 ))) && handler->idiag_info_size) {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 63/177 netdevsim: dont overwrite read only ethtool parms
In reply to Greg Kroah-HartmanFrom: Filip Pokryvka <[email protected]>
[ Upstream commit ee60e626d536da4c710b3634afe68fe7c6d69b59 ]
Ethtool ring feature has _max_pending attributes read-only. Set only read-write attributes in nsim_set_ringparam.
This patch is useful, if netdevsim device is set-up using NetworkManager, because NetworkManager sends 0 as MAX values, as it is pointless to retrieve them in extra call, because they should be read-only. Then, the device is left in incosistent state (value > MAX).
--- drivers/net/netdevsim/ethtool.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/netdevsim/ethtool.c +4 -1
@@ -77,7 +77,10 @@ static int nsim_set_ringparam(struct net_device *dev, {struct netdevsim *ns =netdev_priv (dev); -memcpy (&ns->ethtool.ring, ring,sizeof (ns->ethtool.ring)); + ns->ethtool.ring.rx_pending = ring->rx_pending; + ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending; + ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending; + ns->ethtool.ring.tx_pending = ring->tx_pending;return 0 ; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 64/177 selftests: icmp_redirect: pass xfail=0 to log_test()
In reply to Greg Kroah-HartmanFrom: Po-Hsu Lin <[email protected]>
[ Upstream commit 3748939bce3fc7a15ef07161826507fbe410bb7a ]
If any sub-test in this icmp_redirect.sh is failing but not expected to fail. The script will complain:
./icmp_redirect.sh: line 72: [: 1: unary operator expected
This is because when the sub-test is not expected to fail, we won't pass any value for the xfail local variable in log_test() and thus it's empty. Fix this by passing 0 as the 4th variable to log_test() for non-xfail cases.
v2: added fixes tag
--- tools/testing/selftests/net/icmp_redirect.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/net/icmp_redirect.sh +1 -1
@@ -311,7 +311,7 @@ check_exception() ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \ grep -E -v 'mtu|redirected' | grep -q "cache" fi - log_test $? 0 "IPv4: ${desc}" + log_test $? 0 "IPv4: ${desc}" 0 # No PMTU info for test "redirect" and "mtu exception plus redirect" if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 65/177 net: hns3: fix use-after-free bug in hclgevf_send_mbx_msg
In reply to Greg Kroah-HartmanFrom: Jie Wang <[email protected]>
[ Upstream commit 27cbf64a766e86f068ce6214f04c00ceb4db1af4 ]
Currently, the hns3_remove function firstly uninstall client instance, and then uninstall acceletion engine device. The netdevice is freed in client instance uninstall process, but acceletion engine device uninstall process still use it to trace runtime information. This causes a use after free problem.
So fixes it by check the instance register state to avoid use after free.
--- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +2 -1
@@ -114,7 +114,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev,memcpy (&req->msg, send_msg,sizeof (struct hclge_vf_to_pf_msg )); -trace_hclge_vf_mbx_send (hdev, req); +if (test_bit (HCLGEVF_STATE_NIC_REGISTERED , &hdev->state)) +trace_hclge_vf_mbx_send (hdev, req);/* synchronous send */ if (need_resp) {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 66/177 net: hns3: fix race condition in debugfs
In reply to Greg Kroah-HartmanFrom: Yufeng Mo <[email protected]>
[ Upstream commit 6dde452bceca3f2ed2b33bc46a16ff5682a03a2e ]
When multiple threads concurrently access the debugfs content, data and pointer exceptions may occur. Therefore, mutex lock protection is added for debugfs.
--- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 ++ .../ethernet/hisilicon/hns3/hns3_debugfs.c | 20 +++++++++++++------ 2 files changed, 16 insertions(+), 6 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hnae3.h +2 -0
@@ -830,6 +830,8 @@ struct hnae3_handle {u8 netdev_flags;struct dentry *hnae3_dbgfs; +/* protects concurrent contention between debugfs commands */ +struct mutex dbgfs_lock;/* Network interface message level enabled bits */ u32 msg_enable;
drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +14 -6
@@ -1021,6 +1021,7 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,if (ret)return ret; +mutex_lock (&handle->dbgfs_lock); save_buf = &hns3_dbg_cmd[index].buf; if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
@@ -1033,15 +1034,15 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, read_buf = *save_buf; }else { read_buf =kvzalloc (hns3_dbg_cmd[index].buf_len,GFP_KERNEL ); -if (!read_buf) -return -ENOMEM ; +if (!read_buf) { + ret = -ENOMEM ; + goto out; + }/* save the buffer addr until the last read operation */ *save_buf = read_buf; - } -/* get data ready for the first time to read */ -if (!*ppos) { +/* get data ready for the first time to read */ ret =hns3_dbg_read_cmd (dbg_data, hns3_dbg_cmd[index].cmd, read_buf, hns3_dbg_cmd[index].buf_len);if (ret)
@@ -1050,8 +1051,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, size =simple_read_from_buffer (buffer, count, ppos, read_buf,strlen (read_buf)); -if (size >0 ) +if (size >0 ) { +mutex_unlock (&handle->dbgfs_lock);return size; + } out:/* free the buffer for the last read operation */
@@ -1060,6 +1063,7 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, *save_buf =NULL ; } +mutex_unlock (&handle->dbgfs_lock);return ret; }
@@ -1132,6 +1136,8 @@ int hns3_dbg_init(struct hnae3_handle *handle)debugfs_create_dir (hns3_dbg_dentry[i].name, handle->hnae3_dbgfs); +mutex_init (&handle->dbgfs_lock); +for (i =0 ; i <ARRAY_SIZE (hns3_dbg_cmd); i++) { if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) ||
@@ -1158,6 +1164,7 @@ int hns3_dbg_init(struct hnae3_handle *handle)return 0 ; out: +mutex_destroy (&handle->dbgfs_lock);debugfs_remove_recursive (handle->hnae3_dbgfs); handle->hnae3_dbgfs =NULL ;return ret;
@@ -1173,6 +1180,7 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) hns3_dbg_cmd[i].buf =NULL ; } +mutex_destroy (&handle->dbgfs_lock);debugfs_remove_recursive (handle->hnae3_dbgfs); handle->hnae3_dbgfs =NULL ; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 67/177 selftests: Add duplicate config only for MD5 VRF tests
In reply to Greg Kroah-HartmanFrom: David Ahern <[email protected]>
[ Upstream commit 7e0147592b5c4f9e2eb8c54a7857a56d4863f74e ]
Commit referenced below added configuration in the default VRF that duplicates a VRF to check MD5 passwords are properly used and fail when expected. That config should not be added all the time as it can cause tests to pass that should not (by matching on default VRF setup when it should not). Move the duplicate setup to a function that is only called for the MD5 tests and add a cleanup function to remove it after the MD5 tests.
--- tools/testing/selftests/net/fcnal-test.sh | 26 +++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-)
tools/testing/selftests/net/fcnal-test.sh +20 -6
@@ -455,6 +455,22 @@ cleanup() ip netns del ${NSC} >/dev/null 2>&1 } +cleanup_vrf_dup() +{ + ip link del ${NSA_DEV2} >/dev/null 2>&1 + ip netns pids ${NSC} | xargs kill 2>/dev/null + ip netns del ${NSC} >/dev/null 2>&1 +} + +setup_vrf_dup() +{ + # some VRF tests use ns-C which has the same config as + # ns-B but for a device NOT in the VRF + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 +} + setup() { local with_vrf=${1}
@@ -484,12 +500,6 @@ setup() ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} - - # some VRF tests use ns-C which has the same config as - # ns-B but for a device NOT in the VRF - create_ns ${NSC} "-" "-" - connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ - ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 else ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV}
@@ -1240,7 +1250,9 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests + setup_vrf_dup ipv4_tcp_md5 + cleanup_vrf_dup # # enable VRF global server
@@ -2719,7 +2731,9 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests + setup_vrf_dup ipv6_tcp_md5 + cleanup_vrf_dup # # enable VRF global server
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 68/177 selftests: Fix raw socket bind tests with VRF
In reply to Greg Kroah-HartmanFrom: David Ahern <[email protected]>
[ Upstream commit 0f108ae4452025fef529671998f6c7f1c4526790 ]
Commit referenced below added negative socket bind tests for VRF. The socket binds should fail since the address to bind to is in a VRF yet the socket is not bound to the VRF or a device within it. Update the expected return code to check for 1 (bind failure) so the test passes when the bind fails as expected. Add a 'show_hint' comment to explain why the bind is expected to fail.
--- tools/testing/selftests/net/fcnal-test.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
tools/testing/selftests/net/fcnal-test.sh +2 -1
@@ -1810,8 +1810,9 @@ ipv4_addr_bind_vrf() for a in ${NSA_IP} ${VRF_IP} do log_start + show_hint "Socket not bound to VRF, but address is in VRF" run_cmd nettest -s -R -P icmp -l ${a} -b - log_test_addr ${a} $? 0 "Raw socket bind to local address" + log_test_addr ${a} $? 1 "Raw socket bind to local address" log_start run_cmd nettest -s -R -P icmp -l ${a} -I ${NSA_DEV} -b
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 69/177 selftests: Fix IPv6 address bind tests
In reply to Greg Kroah-HartmanFrom: David Ahern <[email protected]>
[ Upstream commit 28a2686c185e84b6aa6a4d9c9a972360eb7ca266 ]
IPv6 allows binding a socket to a device then binding to an address not on the device (__inet6_bind -> ipv6_chk_addr with strict flag not set). Update the bind tests to reflect legacy behavior.
--- tools/testing/selftests/net/fcnal-test.sh | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)
tools/testing/selftests/net/fcnal-test.sh +11 -3
@@ -3429,11 +3429,14 @@ ipv6_addr_bind_novrf() run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. So this test passes + # when it really should not a=${NSA_LO_IP6} log_start - show_hint "Should fail with 'Cannot assign requested address'" + show_hint "Tecnically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b - log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" + log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address" } ipv6_addr_bind_vrf()
@@ -3474,10 +3477,15 @@ ipv6_addr_bind_vrf() run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind" + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. The only restriction + # is that the address is valid in the L3 domain. So this test + # passes when it really should not a=${VRF_IP6} log_start + show_hint "Tecnically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b - log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind" + log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind" a=${NSA_LO_IP6} log_start
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 70/177 dmaengine: idxd: fix missed completion on abort path
In reply to Greg Kroah-HartmanFrom: Dave Jiang <[email protected]>
[ Upstream commit 8affd8a4b5ce356c8900cfb037674f3a4a11fbdb ]
Ming reported that with the abort path of the descriptor submission, there can be a window where a completed descriptor can be missed to be completed by the irq completion thread:
CPU A CPU B
Submit (successful)
Submit (fail)
irq_process_work_list() // empty
llist_abort_desc()
// remove all descs from pending list
irq_process_pending_llist() // empty exit idxd_wq_thread() with no processing
Add opportunistic descriptor completion in the abort path in order to remove the missed completion.
--- drivers/dma/idxd/submit.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)
drivers/dma/idxd/submit.c +17 -1
@@ -106,6 +106,7 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, {struct idxd_desc *d, *t, *found =NULL ;struct llist_node *head; +LIST_HEAD (flist); desc->completion->status =IDXD_COMP_DESC_ABORT ;/*
@@ -120,7 +121,11 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, found = desc;continue ; } -list_add_tail (&desc->list, &ie->work_list); + +if (d->completion->status) +list_add_tail (&d->list, &flist); +else +list_add_tail (&d->list, &ie->work_list); } }
@@ -130,6 +135,17 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,if (found)complete_desc (found,IDXD_COMPLETE_ABORT ); + +/* +* complete_desc() will return desc to allocator and the desc can be +* acquired by a different process and the desc->list can be modified. +* Delete desc from list so the list trasversing does not get corrupted +* by the other process. +*/ +list_for_each_entry_safe (d, t, &flist, list) { +list_del_init (&d->list); +complete_desc (d,IDXD_COMPLETE_NORMAL ); + } }int idxd_submit_desc (struct idxd_wq *wq,struct idxd_desc *desc)
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 71/177 dmaengine: st_fdma: fix MODULE_ALIAS
In reply to Greg Kroah-HartmanFrom: Alyssa Ross <[email protected]>
[ Upstream commit 822c9f2b833c53fc67e8adf6f63ecc3ea24d502c ]
modprobe can't handle spaces in aliases.
--- drivers/dma/st_fdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/dma/st_fdma.c +1 -1
@@ -874,4 +874,4 @@ MODULE_LICENSE("GPL v2");MODULE_DESCRIPTION ("STMicroelectronics FDMA engine driver" );MODULE_AUTHOR ("Ludovic.barre <[email protected]>" );MODULE_AUTHOR ("Peter Griffin <[email protected]>" ); -MODULE_ALIAS ("platform: " DRIVER_NAME ); +MODULE_ALIAS ("platform:" DRIVER_NAME );
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 72/177 drm: simpledrm: fix wrong unit with pixel clock
In reply to Greg Kroah-HartmanFrom: Alejandro Concepcion-Rodriguez <[email protected]>
[ Upstream commit 5cf06065bd1f7b94fbb80e7eeb033899f77ab5ba ]
Pixel clock has to be set in kHz.
--- drivers/gpu/drm/tiny/simpledrm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/tiny/simpledrm.c +1 -1
@@ -458,7 +458,7 @@ static struct drm_display_mode simpledrm_mode(unsigned int width, {struct drm_display_mode mode = {SIMPLEDRM_MODE (width, height) }; - mode.clock =60 /* Hz */ * mode.hdisplay * mode.vdisplay; + mode.clock = mode.hdisplay * mode.vdisplay *60 /1000 /* kHz */ ;drm_mode_set_name (&mode);return mode;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 73/177 net/sched: sch_ets: dont remove idle classes from the round-robin list
In reply to Greg Kroah-HartmanFrom: Davide Caratti <[email protected]>
[ Upstream commit c062f2a0b04d86c5b8c9d973bea43493eaca3d32 ]
Shuang reported that the following script:
1) tc qdisc add dev ddd0 handle 10: parent 1: ets bands 8 strict 4 priomap 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7
2) mausezahn ddd0 -A 10.10.10.1 -B 10.10.10.2 -c 0 -a own -b 00:c1:a0:c1:a0:00 -t udp &
3) tc qdisc change dev ddd0 handle 10: ets bands 4 strict 2 quanta 2500 2500 priomap 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3
crashes systematically when line 2) is commented:
list_del corruption, ffff8e028404bd30->next is LIST_POISON1 (dead000000000100)
------------[ cut here ]------------ kernel BUG at lib/list_debug.c:47! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 0 PID: 954 Comm: tc Not tainted 5.16.0-rc4+ #478 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:__list_del_entry_valid.cold.1+0x12/0x47 Code: fe ff 0f 0b 48 89 c1 4c 89 c6 48 c7 c7 08 42 1b 87 e8 1d c5 fe ff 0f 0b 48 89 fe 48 89 c2 48 c7 c7 98 42 1b 87 e8 09 c5 fe ff <0f> 0b 48 c7 c7 48 43 1b 87 e8 fb c4 fe ff 0f 0b 48 89 f2 48 89 fe RSP: 0018:ffffae46807a3888 EFLAGS: 00010246 RAX: 000000000000004e RBX: 0000000000000007 RCX: 0000000000000202 RDX: 0000000000000000 RSI: ffffffff871ac536 RDI: 00000000ffffffff RBP: ffffae46807a3a10 R08: 0000000000000000 R09: c0000000ffff7fff R10: 0000000000000001 R11: ffffae46807a36a8 R12: ffff8e028404b800 R13: ffff8e028404bd30 R14: dead000000000100 R15: ffff8e02fafa2400 FS: 00007efdc92e4480(0000) GS:ffff8e02fb600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000682f48 CR3: 00000001058be000 CR4: 0000000000350ef0 Call Trace: <TASK> ets_qdisc_change+0x58b/0xa70 [sch_ets] tc_modify_qdisc+0x323/0x880 rtnetlink_rcv_msg+0x169/0x4a0 netlink_rcv_skb+0x50/0x100 netlink_unicast+0x1a5/0x280 netlink_sendmsg+0x257/0x4d0 sock_sendmsg+0x5b/0x60 ____sys_sendmsg+0x1f2/0x260 ___sys_sendmsg+0x7c/0xc0 __sys_sendmsg+0x57/0xa0 do_syscall_64+0x3a/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7efdc8031338 Code: 89 02 48 c7 c0 ff ff ff ff eb b5 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 25 43 2c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 41 54 41 89 d4 55 RSP: 002b:00007ffdf1ce9828 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000061b37a97 RCX: 00007efdc8031338 RDX: 0000000000000000 RSI: 00007ffdf1ce9890 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000078a940 R10: 000000000000000c R11: 0000000000000246 R12: 0000000000000001 R13: 0000000000688880 R14: 0000000000000000 R15: 0000000000000000 </TASK> Modules linked in: sch_ets sch_tbf dummy rfkill iTCO_wdt iTCO_vendor_support intel_rapl_msr intel_rapl_common joydev pcspkr i2c_i801 virtio_balloon i2c_smbus lpc_ich ip_tables xfs libcrc32c crct10dif_pclmul crc32_pclmul crc32c_intel serio_raw ghash_clmulni_intel ahci libahci libata virtio_blk virtio_console virtio_net net_failover failover sunrpc dm_mirror dm_region_hash dm_log dm_mod [last unloaded: sch_ets] ---[ end trace f35878d1912655c2 ]--- RIP: 0010:__list_del_entry_valid.cold.1+0x12/0x47 Code: fe ff 0f 0b 48 89 c1 4c 89 c6 48 c7 c7 08 42 1b 87 e8 1d c5 fe ff 0f 0b 48 89 fe 48 89 c2 48 c7 c7 98 42 1b 87 e8 09 c5 fe ff <0f> 0b 48 c7 c7 48 43 1b 87 e8 fb c4 fe ff 0f 0b 48 89 f2 48 89 fe RSP: 0018:ffffae46807a3888 EFLAGS: 00010246 RAX: 000000000000004e RBX: 0000000000000007 RCX: 0000000000000202 RDX: 0000000000000000 RSI: ffffffff871ac536 RDI: 00000000ffffffff RBP: ffffae46807a3a10 R08: 0000000000000000 R09: c0000000ffff7fff R10: 0000000000000001 R11: ffffae46807a36a8 R12: ffff8e028404b800 R13: ffff8e028404bd30 R14: dead000000000100 R15: ffff8e02fafa2400 FS: 00007efdc92e4480(0000) GS:ffff8e02fb600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000682f48 CR3: 00000001058be000 CR4: 0000000000350ef0 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: 0x4e00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---
we can remove 'q->classes[i].alist' only if DRR class 'i' was part of the active list. In the ETS scheduler DRR classes belong to that list only if the queue length is greater than zero: we need to test for non-zero value of 'q->classes[i].qdisc->q.qlen' before removing from the list, similarly to what has been done elsewhere in the ETS code.
--- net/sched/sch_ets.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/sched/sch_ets.c +2 -2
@@ -668,9 +668,9 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, } }for (i = q->nbands; i < oldbands; i++) { -qdisc_tree_flush_backlog (q->classes[i].qdisc); -if (i >= q->nstrict) +if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)list_del (&q->classes[i].alist); +qdisc_tree_flush_backlog (q->classes[i].qdisc); } q->nstrict = nstrict;memcpy (q->prio2band, priomap,sizeof (priomap));
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 74/177 selftests/net: toeplitz: fix udp option
In reply to Greg Kroah-HartmanFrom: Willem de Bruijn <[email protected]>
[ Upstream commit a8d13611b4a7b1b20d17bf2b9a89a3efcabde56c ]
Tiny fix. Option -u ("use udp") does not take an argument.
It can cause the next argument to silently be ignored.
--- tools/testing/selftests/net/toeplitz.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/net/toeplitz.c +1 -1
@@ -498,7 +498,7 @@ static void parse_opts(int argc, char **argv)bool have_toeplitz = false;int index, c; -while ((c =getopt_long (argc, argv,"46C:d:i:k:r:stT:u:v" , long_options, &index)) !=-1 ) { +while ((c =getopt_long (argc, argv,"46C:d:i:k:r:stT:uv" , long_options, &index)) !=-1 ) {switch (c) {case '4' : cfg_family =AF_INET ;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 75/177 net: dsa: mv88e6xxx: Unforce speed & duplex in mac_link_down()
In reply to Greg Kroah-HartmanFrom: Marek Behún <[email protected]>
[ Upstream commit 9d591fc028b6bddb38c6585874f331267cbdadae ]
Commit 64d47d50be7a ("net: dsa: mv88e6xxx: configure interface settings in mac_config") removed forcing of speed and duplex from mv88e6xxx_mac_config(), where the link is forced down, and left it only in mv88e6xxx_mac_link_up(), by which time link is unforced.
It seems that (at least on 88E6190) when changing cmode to 2500base-x, if the link is not forced down, but the speed or duplex are still forced, the forcing of new settings for speed & duplex doesn't take in mv88e6xxx_mac_link_up().
Fix this by unforcing speed & duplex in mv88e6xxx_mac_link_down().
--- drivers/net/dsa/mv88e6xxx/chip.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/net/dsa/mv88e6xxx/chip.c +4 -0
@@ -769,6 +769,10 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port,if ((!mv88e6xxx_port_ppu_updates (chip, port) || mode ==MLO_AN_FIXED ) && ops->port_sync_link) err = ops->port_sync_link (chip, port, mode, false); + +if (!err && ops->port_set_speed_duplex) + err = ops->port_set_speed_duplex (chip, port,SPEED_UNFORCED , +DUPLEX_UNFORCED );mv88e6xxx_reg_unlock (chip);if (err)
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 76/177 selftest/net/forwarding: declare NETIFS p9 p10
In reply to Greg Kroah-HartmanFrom: Hangbin Liu <[email protected]>
[ Upstream commit 71da1aec215290e249d09c44c768df859f3a3bba ]
The recent GRE selftests defined NUM_NETIFS=10. If the users copy forwarding.config.sample to forwarding.config directly, they will get error "Command line is not complete" when run the GRE tests, because create_netif_veth() failed with no interface name defined.
Fix it by extending the NETIFS with p9 and p10.
--- tools/testing/selftests/net/forwarding/forwarding.config.sample | 2 ++ 1 file changed, 2 insertions(+)
tools/testing/selftests/net/forwarding/forwarding.config.sample +2 -0
@@ -13,6 +13,8 @@ NETIFS[p5]=veth4 NETIFS[p6]=veth5 NETIFS[p7]=veth6 NETIFS[p8]=veth7 +NETIFS[p9]=veth8 +NETIFS[p10]=veth9 # Port that does not have a cable connected. NETIF_NO_CABLE=eth8
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 77/177 mptcp: never allow the PM to close a listener subflow
In reply to Greg Kroah-HartmanFrom: Paolo Abeni <[email protected]>
[ Upstream commit b0cdc5dbcf2ba0d99785da5aabf1b17943805b8a ]
Currently, when deleting an endpoint the netlink PM treverses all the local MPTCP sockets, regardless of their status.
If an MPTCP listener socket is bound to the IP matching the delete endpoint, the listener TCP socket will be closed. That is unexpected, the PM should only affect data subflows.
Additionally, syzbot was able to trigger a NULL ptr dereference due to the above:
general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] CPU: 1 PID: 6550 Comm: syz-executor122 Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__lock_acquire+0xd7d/0x54a0 kernel/locking/lockdep.c:4897 Code: 0f 0e 41 be 01 00 00 00 0f 86 c8 00 00 00 89 05 69 cc 0f 0e e9 bd 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 da 48 c1 ea 03 <80> 3c 02 00 0f 85 f3 2f 00 00 48 81 3b 20 75 17 8f 0f 84 52 f3 ff RSP: 0018:ffffc90001f2f818 EFLAGS: 00010016 RAX: dffffc0000000000 RBX: 0000000000000018 RCX: 0000000000000000 RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000001 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000000 R11: 000000000000000a R12: 0000000000000000 R13: ffff88801b98d700 R14: 0000000000000000 R15: 0000000000000001 FS: 00007f177cd3d700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f177cd1b268 CR3: 000000001dd55000 CR4: 0000000000350ee0 Call Trace: <TASK> lock_acquire kernel/locking/lockdep.c:5637 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5602 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0x39/0x50 kernel/locking/spinlock.c:162 finish_wait+0xc0/0x270 kernel/sched/wait.c:400 inet_csk_wait_for_connect net/ipv4/inet_connection_sock.c:464 [inline] inet_csk_accept+0x7de/0x9d0 net/ipv4/inet_connection_sock.c:497 mptcp_accept+0xe5/0x500 net/mptcp/protocol.c:2865 inet_accept+0xe4/0x7b0 net/ipv4/af_inet.c:739 mptcp_stream_accept+0x2e7/0x10e0 net/mptcp/protocol.c:3345 do_accept+0x382/0x510 net/socket.c:1773 __sys_accept4_file+0x7e/0xe0 net/socket.c:1816 __sys_accept4+0xb0/0x100 net/socket.c:1846 __do_sys_accept net/socket.c:1864 [inline] __se_sys_accept net/socket.c:1861 [inline] __x64_sys_accept+0x71/0xb0 net/socket.c:1861 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f177cd8b8e9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 b1 14 00 00 90 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 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f177cd3d308 EFLAGS: 00000246 ORIG_RAX: 000000000000002b RAX: ffffffffffffffda RBX: 00007f177ce13408 RCX: 00007f177cd8b8e9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 00007f177ce13400 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f177ce1340c R13: 00007f177cde1004 R14: 6d705f706374706d R15: 0000000000022000 </TASK>
Fix the issue explicitly skipping MPTCP socket in TCP_LISTEN status.
--- net/mptcp/pm_netlink.c | 3 +++ 1 file changed, 3 insertions(+)
net/mptcp/pm_netlink.c +3 -0
@@ -700,6 +700,9 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,msk_owned_by_me (msk); +if (sk->sk_state ==TCP_LISTEN ) +return ; +if (!rm_list->nr)return ;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 78/177 drm/ast: potential dereference of null pointer
In reply to Greg Kroah-HartmanFrom: Jiasheng Jiang <[email protected]>
[ Upstream commit fea3fdf975dd9f3e5248afaab8fe023db313f005 ]
The return value of kzalloc() needs to be checked. To avoid use of null pointer '&ast_state->base' in case of the failure of alloc.
--- drivers/gpu/drm/ast/ast_mode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/gpu/drm/ast/ast_mode.c +4 -1
@@ -1121,7 +1121,10 @@ static void ast_crtc_reset(struct drm_crtc *crtc)if (crtc->state) crtc->funcs->atomic_destroy_state (crtc, crtc->state); -__drm_atomic_helper_crtc_reset (crtc, &ast_state->base); +if (ast_state) +__drm_atomic_helper_crtc_reset (crtc, &ast_state->base); +else +__drm_atomic_helper_crtc_reset (crtc,NULL ); } static struct drm_crtc_state *
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 79/177 drm/i915/display: Fix an unsigned subtraction which can never be negative.
In reply to Greg Kroah-HartmanFrom: Harshit Mogalapalli <[email protected]>
[ Upstream commit 53b3495273282aa844c4613d19c3b30558c70c84 ]
smatch warning:drivers/gpu/drm/i915/display/intel_dmc.c:601 parse_dmc_fw() warn:
unsigned 'fw->size - offset' is never less than zero
Firmware size is size_t and offset is u32. So the subtraction is unsigned which can never be less than zero.
--- drivers/gpu/drm/i915/display/intel_dmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/i915/display/intel_dmc.c +1 -1
@@ -606,7 +606,7 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv,continue ; offset = readcount + dmc->dmc_info[id].dmc_offset *4 ; -if (fw->size - offset <0 ) { +if (offset > fw->size) {drm_err (&dev_priv->drm,"Reading beyond the fw_size\n" );continue ; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 80/177 mac80211: agg-tx: dont schedule_and_wake_txq() under sta->lock
In reply to Greg Kroah-HartmanFrom: Johannes Berg <[email protected]>
[ Upstream commit 06c41bda0ea14aa7fba932a9613c4ee239682cf0 ]
When we call ieee80211_agg_start_txq(), that will in turn call schedule_and_wake_txq(). Called from ieee80211_stop_tx_ba_cb() this is done under sta->lock, which leads to certain circular lock dependencies, as reported by Chris Murphy:
https://lore.kernel.org/r/CAJCQCtSXJ5qA4bqSPY=oLRMbv-irihVvP7A2uGutEbXQVkoNaw@mail.gmail.com
In general, ieee80211_agg_start_txq() is usually not called with sta->lock held, only in this one place. But it's always called with sta->ampdu_mlme.mtx held, and that's therefore clearly sufficient.
Change ieee80211_stop_tx_ba_cb() to also call it without the sta->lock held, by factoring it out of ieee80211_remove_tid_tx() (which is only called in this one place).
This breaks the locking chain and makes it less likely that we'll have similar locking chain problems in the future.
--- net/mac80211/agg-tx.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)
net/mac80211/agg-tx.c +8 -2
@@ -9,7 +9,7 @@* Copyright 2007, Michael Wu <[email protected]> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH -* Copyright (C) 2018 - 2020 Intel Corporation +* Copyright (C) 2018 - 2021 Intel Corporation */ #include <linux/ieee80211.h>
@@ -213,6 +213,8 @@ ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable)struct ieee80211_txq *txq = sta->sta.txq[tid];struct txq_info *txqi; +lockdep_assert_held (&sta->ampdu_mlme.mtx); +if (!txq)return ;
@@ -290,7 +292,6 @@ static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid)ieee80211_assign_tid_tx (sta, tid,NULL );ieee80211_agg_splice_finish (sta->sdata, tid); -ieee80211_agg_start_txq (sta, tid, false);kfree_rcu (tid_tx, rcu_head); }
@@ -889,6 +890,7 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, {struct ieee80211_sub_if_data *sdata = sta->sdata;bool send_delba = false; +bool start_txq = false;ht_dbg (sdata,"Stopping Tx BA session for %pM tid %d\n" , sta->sta.addr, tid);
@@ -906,10 +908,14 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, send_delba = true;ieee80211_remove_tid_tx (sta, tid); + start_txq = true; unlock_sta:spin_unlock_bh (&sta->lock); +if (start_txq) +ieee80211_agg_start_txq (sta, tid, false); +if (send_delba)ieee80211_send_delba (sdata, sta->sta.addr, tid,WLAN_BACK_INITIATOR ,WLAN_REASON_QSTA_NOT_USE );
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 81/177 cfg80211: Acquire wiphy mutex on regulatory work
In reply to Greg Kroah-HartmanFrom: Ilan Peer <[email protected]>
[ Upstream commit e08ebd6d7b90ae81f21425ca39136f5b2272580f ]
The function cfg80211_reg_can_beacon_relax() expects wiphy mutex to be held when it is being called. However, when reg_leave_invalid_chans() is called the mutex is not held. Fix it by acquiring the lock before calling the function.
--- net/wireless/reg.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
net/wireless/reg.c +6 -1
@@ -2338,6 +2338,7 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)struct cfg80211_chan_def chandef = {};struct cfg80211_registered_device *rdev =wiphy_to_rdev (wiphy);enum nl80211_iftype iftype; +bool ret;wdev_lock (wdev); iftype = wdev->iftype;
@@ -2387,7 +2388,11 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)case NL80211_IFTYPE_AP :case NL80211_IFTYPE_P2P_GO :case NL80211_IFTYPE_ADHOC : -return cfg80211_reg_can_beacon_relax (wiphy, &chandef, iftype); +wiphy_lock (wiphy); + ret =cfg80211_reg_can_beacon_relax (wiphy, &chandef, iftype); +wiphy_unlock (wiphy); + +return ret;case NL80211_IFTYPE_STATION :case NL80211_IFTYPE_P2P_CLIENT : return cfg80211_chandef_usable(wiphy, &chandef,
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 82/177 mac80211: fix lookup when adding AddBA extension element
In reply to Greg Kroah-HartmanFrom: Johannes Berg <[email protected]>
[ Upstream commit 511ab0c1dfb260a6b17b8771109e8d63474473a7 ]
We should be doing the HE capabilities lookup based on the full interface type so if P2P doesn't have HE but client has it doesn't get confused. Fix that.
--- net/mac80211/agg-rx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
net/mac80211/agg-rx.c +3 -2
@@ -9,7 +9,7 @@* Copyright 2007, Michael Wu <[email protected]> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH -* Copyright (C) 2018-2020 Intel Corporation +* Copyright (C) 2018-2021 Intel Corporation */ /**
@@ -191,7 +191,8 @@ static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, sband =ieee80211_get_sband (sdata);if (!sband)return ; - he_cap =ieee80211_get_he_iftype_cap (sband, sdata->vif.type); + he_cap =ieee80211_get_he_iftype_cap (sband, +ieee80211_vif_type_p2p (&sdata->vif));if (!he_cap)return ;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 83/177 net: stmmac: fix tc flower deletion for VLAN priority Rx steering
In reply to Greg Kroah-HartmanFrom: Ong Boon Leong <[email protected]>
[ Upstream commit aeb7c75cb77478fdbf821628e9c95c4baa9adc63 ]
To replicate the issue:-
1) Add 1 flower filter for VLAN Priority based frame steering:-
$ IFDEVNAME=eth0 $ tc qdisc add dev $IFDEVNAME ingress $ tc qdisc add dev $IFDEVNAME root mqprio num_tc 8 \ map 0 1 2 3 4 5 6 7 0 0 0 0 0 0 0 0 \ queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 hw 0 $ tc filter add dev $IFDEVNAME parent ffff: protocol 802.1Q \ flower vlan_prio 0 hw_tc 0
2) Get the 'pref' id
$ tc filter show dev $IFDEVNAME ingress
3) Delete a specific tc flower record (say pref 49151)
$ tc filter del dev $IFDEVNAME parent ffff: pref 49151
Quoted 1 line
From dmesg, we will observe kernel NULL pointer ooops
[ 197.170464] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 197.171367] #PF: supervisor read access in kernel mode [ 197.171367] #PF: error_code(0x0000) - not-present page [ 197.171367] PGD 0 P4D 0 [ 197.171367] Oops: 0000 [#1] PREEMPT SMP NOPTI
<snip>
[ 197.171367] RIP: 0010:tc_setup_cls+0x20b/0x4a0 [stmmac]
<snip>
[ 197.171367] Call Trace: [ 197.171367] <TASK> [ 197.171367] ? __stmmac_disable_all_queues+0xa8/0xe0 [stmmac] [ 197.171367] stmmac_setup_tc_block_cb+0x70/0x110 [stmmac] [ 197.171367] tc_setup_cb_destroy+0xb3/0x180 [ 197.171367] fl_hw_destroy_filter+0x94/0xc0 [cls_flower]
The above issue is due to previous incorrect implementation of tc_del_vlan_flow(), shown below, that uses flow_cls_offload_flow_rule() to get struct flow_rule *rule which is no longer valid for tc filter delete operation.
struct flow_rule *rule = flow_cls_offload_flow_rule(cls); struct flow_dissector *dissector = rule->match.dissector;
So, to ensure tc_del_vlan_flow() deletes the right VLAN cls record for earlier configured RX queue (configured by hw_tc) in tc_add_vlan_flow(), this patch introduces stmmac_rfs_entry as driver-side flow_cls_offload record for 'RX frame steering' tc flower, currently used for VLAN priority. The implementation has taken consideration for future extension to include other type RX frame steering such as EtherType based.
v2:
- Clean up overly extensive backtrace and rewrite git message to better explain the kernel NULL pointer issue.
--- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 17 ++++ .../net/ethernet/stmicro/stmmac/stmmac_tc.c | 86 ++++++++++++++++--- 2 files changed, 90 insertions(+), 13 deletions(-)
drivers/net/ethernet/stmicro/stmmac/stmmac.h +17 -0
@@ -172,6 +172,19 @@ struct stmmac_flow_entry {int is_l4; }; +/* Rx Frame Steering */ +enum stmmac_rfs_type { +STMMAC_RFS_T_VLAN , +STMMAC_RFS_T_MAX , +}; + +struct stmmac_rfs_entry { +unsigned long cookie; +int in_use; +int type; +int tc; +}; +struct stmmac_priv {/* Frequently used values are kept adjacent for cache effect */ u32 tx_coal_frames[MTL_MAX_TX_QUEUES ];
@@ -289,6 +302,10 @@ struct stmmac_priv {struct stmmac_tc_entry *tc_entries;unsigned int flow_entries_max;struct stmmac_flow_entry *flow_entries; +unsigned int rfs_entries_max[STMMAC_RFS_T_MAX ]; +unsigned int rfs_entries_cnt[STMMAC_RFS_T_MAX ]; +unsigned int rfs_entries_total; +struct stmmac_rfs_entry *rfs_entries;/* Pulse Per Second output */ struct stmmac_pps_cfg pps[STMMAC_PPS_MAX ];
drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +73 -13
136 lines not on this page · raw message
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 84/177 flow_offload: return EOPNOTSUPP for the unsupported mpls action type
In reply to Greg Kroah-HartmanFrom: Baowen Zheng <[email protected]>
[ Upstream commit 166b6a46b78bf8b9559a6620c3032f9fe492e082 ]
We need to return EOPNOTSUPP for the unsupported mpls action type when setup the flow action.
In the original implement, we will return 0 for the unsupported mpls action type, actually we do not setup it and the following actions to the flow action entry.
--- net/sched/cls_api.c | 1 + 1 file changed, 1 insertion(+)
net/sched/cls_api.c +1 -0
@@ -3687,6 +3687,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mpls_mangle.ttl =tcf_mpls_ttl (act);break ;default : + err = -EOPNOTSUPP ; goto err_out_locked; } }else if (is_tcf_skbedit_ptype (act)) {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 85/177 rds: memory leak in __rds_conn_create()
In reply to Greg Kroah-HartmanFrom: Hangyu Hua <[email protected]>
[ Upstream commit 5f9562ebe710c307adc5f666bf1a2162ee7977c0 ]
__rds_conn_create() did not release conn->c_path when loop_trans != 0 and trans->t_prefer_loopback != 0 and is_outgoing == 0.
--- net/rds/connection.c | 1 + 1 file changed, 1 insertion(+)
net/rds/connection.c +1 -0
@@ -253,6 +253,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,* should end up here, but if it * does, reset/destroy the connection. */ +kfree (conn->c_path);kmem_cache_free (rds_conn_slab, conn); conn =ERR_PTR (-EOPNOTSUPP ); goto out;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 86/177 ice: Use div64_u64 instead of div_u64 in adjfine
In reply to Greg Kroah-HartmanFrom: Karol Kolacinski <[email protected]>
[ Upstream commit 0013881c1145d36bf26165bb70fdd7560a5507a3 ]
Change the division in ice_ptp_adjfine from div_u64 to div64_u64. div_u64 is used when the divisor is 32 bit but in this case incval is 64 bit and it caused incorrect calculations and incval adjustments.
--- drivers/net/ethernet/intel/ice/ice_ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/ice/ice_ptp.c +1 -1
@@ -459,7 +459,7 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) scaled_ppm = -scaled_ppm; } -while ((u64 )scaled_ppm >div_u64 (U64_MAX , incval)) { +while ((u64 )scaled_ppm >div64_u64 (U64_MAX , incval)) {/* handle overflow by scaling down the scaled_ppm and * the divisor, losing some precision */
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 87/177 ice: Dont put stale timestamps in the skb
In reply to Greg Kroah-HartmanFrom: Karol Kolacinski <[email protected]>
[ Upstream commit 37e738b6fdb14529534dca441e0222313688fde3 ]
The driver has to check if it does not accidentally put the timestamp in the SKB before previous timestamp gets overwritten. Timestamp values in the PHY are read only and do not get cleared except at hardware reset or when a new timestamp value is captured. The cached_tstamp field is used to detect the case where a new timestamp has not yet been captured, ensuring that we avoid sending stale timestamp data to the stack.
--- drivers/net/ethernet/intel/ice/ice_ptp.c | 11 ++++------- drivers/net/ethernet/intel/ice/ice_ptp.h | 6 ++++++ 2 files changed, 10 insertions(+), 7 deletions(-)
drivers/net/ethernet/intel/ice/ice_ptp.c +4 -7
@@ -1182,19 +1182,16 @@ static void ice_ptp_tx_tstamp_work(struct kthread_work *work)if (err)continue ; -/* Check if the timestamp is valid */ -if (!(raw_tstamp &ICE_PTP_TS_VALID )) +/* Check if the timestamp is invalid or stale */ +if (!(raw_tstamp &ICE_PTP_TS_VALID ) || + raw_tstamp == tx->tstamps[idx].cached_tstamp)continue ; -/* clear the timestamp register, so that it won't show valid -* again when re-used. -*/ -ice_clear_phy_tstamp (hw, tx->quad, phy_idx); -/* The timestamp is valid, so we'll go ahead and clear this * index and then send the timestamp up to the stack. */ spin_lock (&tx->lock); + tx->tstamps[idx].cached_tstamp = raw_tstamp;clear_bit (idx, tx->in_use); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb =NULL ;
drivers/net/ethernet/intel/ice/ice_ptp.h +6 -0
@@ -46,15 +46,21 @@ struct ice_perout_channel {* struct ice_tx_tstamp - Tracking for a single Tx timestamp * @skb: pointer to the SKB for this timestamp request * @start: jiffies when the timestamp was first requested +* @cached_tstamp: last read timestamp * * This structure tracks a single timestamp request. The SKB pointer is * provided when initiating a request. The start time is used to ensure that * we discard old requests that were not fulfilled within a 2 second time * window. +* Timestamp values in the PHY are read only and do not get cleared except at +* hardware reset or when a new timestamp value is captured. The cached_tstamp +* field is used to detect the case where a new timestamp has not yet been +* captured, ensuring that we avoid sending stale timestamp data to the stack. */ struct ice_tx_tstamp {struct sk_buff *skb;unsigned long start; +u64 cached_tstamp; };/**
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 88/177 drm/amd/display: Set exit_optimized_pwr_state for DCN31
In reply to Greg Kroah-HartmanFrom: Nicholas Kazlauskas <[email protected]>
[ Upstream commit 7e4d2f30df3fb48f75ce9e96867d42bdddab83ac ]
[Why]
SMU now respects the PHY refclk disable request from driver.
This causes a hang during hotplug when PHY refclk was disabled because it's not being re-enabled and the transmitter control starts on dc_link_detect.
[How]
We normally would re-enable the clk with exit_optimized_pwr_state but this is only set on DCN21 and DCN301. Set it for dcn31 as well.
This fixes DMCUB timeouts in the PHY.
--- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +1 -0
@@ -100,6 +100,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = { .z10_save_init = dcn31_z10_save_init, .is_abm_supported = dcn31_is_abm_supported, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, + .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn20_update_visual_confirm_color, };
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 89/177 drm/amd/pm: fix a potential gpu_metrics_table memory leak
In reply to Greg Kroah-HartmanFrom: Lang Yu <[email protected]>
[ Upstream commit aa464957f7e660abd554f2546a588f6533720e21 ]
Memory is allocated for gpu_metrics_table in renoir_init_smc_tables(), but not freed in int smu_v12_0_fini_smc_tables(). Free it!
--- drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c +3 -0
@@ -191,6 +191,9 @@ int smu_v12_0_fini_smc_tables(struct smu_context *smu)kfree (smu_table->watermarks_table); smu_table->watermarks_table =NULL ; +kfree (smu_table->gpu_metrics_table); + smu_table->gpu_metrics_table =NULL ; +return 0 ; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 90/177 mptcp: remove tcp ulp setsockopt support
In reply to Greg Kroah-HartmanFrom: Florian Westphal <[email protected]>
[ Upstream commit 404cd9a22150f24acf23a8df2ad0c094ba379f57 ]
TCP_ULP setsockopt cannot be used for mptcp because its already used internally to plumb subflow (tcp) sockets to the mptcp layer.
syzbot managed to trigger a crash for mptcp connections that are in fallback mode:
KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027] CPU: 1 PID: 1083 Comm: syz-executor.3 Not tainted 5.16.0-rc2-syzkaller #0 RIP: 0010:tls_build_proto net/tls/tls_main.c:776 [inline] [..] __tcp_set_ulp net/ipv4/tcp_ulp.c:139 [inline] tcp_set_ulp+0x428/0x4c0 net/ipv4/tcp_ulp.c:160 do_tcp_setsockopt+0x455/0x37c0 net/ipv4/tcp.c:3391 mptcp_setsockopt+0x1b47/0x2400 net/mptcp/sockopt.c:638
Remove support for TCP_ULP setsockopt.
--- net/mptcp/sockopt.c | 1 - 1 file changed, 1 deletion(-)
net/mptcp/sockopt.c +0 -1
@@ -523,7 +523,6 @@ static bool mptcp_supported_sockopt(int level, int optname)case TCP_NODELAY :case TCP_THIN_LINEAR_TIMEOUTS :case TCP_CONGESTION : -case TCP_ULP :case TCP_CORK :case TCP_KEEPIDLE :case TCP_KEEPINTVL :
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 91/177 mptcp: clear kern flag from fallback sockets
In reply to Greg Kroah-HartmanFrom: Florian Westphal <[email protected]>
[ Upstream commit d6692b3b97bdc165d150f4c1505751a323a80717 ]
The mptcp ULP extension relies on sk->sk_sock_kern being set correctly:
It prevents setsockopt(fd, IPPROTO_TCP, TCP_ULP, "mptcp", 6); from working for plain tcp sockets (any userspace-exposed socket).
But in case of fallback, accept() can return a plain tcp sk. In such case, sk is still tagged as 'kernel' and setsockopt will work.
This will crash the kernel, The subflow extension has a NULL ctx->conn mptcp socket:
BUG: KASAN: null-ptr-deref in subflow_data_ready+0x181/0x2b0 Call Trace: tcp_data_ready+0xf8/0x370 [..]
--- net/mptcp/protocol.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/mptcp/protocol.c +3 -1
@@ -2901,7 +2901,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,*/ if (WARN_ON_ONCE (!new_mptcp_sock)) {tcp_sk (newsk)->is_mptcp =0 ; -return newsk; + goto out; }/* acquire the 2nd reference for the owning socket */
@@ -2913,6 +2913,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } +out: + newsk->sk_kern_sock = kern;return newsk; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 92/177 mptcp: fix deadlock in __mptcp_push_pending()
In reply to Greg Kroah-HartmanFrom: Maxim Galaganov <[email protected]>
[ Upstream commit 3d79e3756ca90f7a6087b77b62c1d9c0801e0820 ]
__mptcp_push_pending() may call mptcp_flush_join_list() with subflow socket lock held. If such call hits mptcp_sockopt_sync_all() then subsequently __mptcp_sockopt_sync() could try to lock the subflow socket for itself, causing a deadlock.
sysrq: Show Blocked State
task:ss-server state:D stack: 0 pid: 938 ppid: 1 flags:0x00000000
Call Trace: <TASK> __schedule+0x2d6/0x10c0 ? __mod_memcg_state+0x4d/0x70 ? csum_partial+0xd/0x20 ? _raw_spin_lock_irqsave+0x26/0x50 schedule+0x4e/0xc0 __lock_sock+0x69/0x90 ? do_wait_intr_irq+0xa0/0xa0 __lock_sock_fast+0x35/0x50 mptcp_sockopt_sync_all+0x38/0xc0 __mptcp_push_pending+0x105/0x200 mptcp_sendmsg+0x466/0x490 sock_sendmsg+0x57/0x60 __sys_sendto+0xf0/0x160 ? do_wait_intr_irq+0xa0/0xa0 ? fpregs_restore_userregs+0x12/0xd0 __x64_sys_sendto+0x20/0x30 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f9ba546c2d0 RSP: 002b:00007ffdc3b762d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007f9ba56c8060 RCX: 00007f9ba546c2d0 RDX: 000000000000077a RSI: 0000000000e5e180 RDI: 0000000000000234 RBP: 0000000000cc57f0 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007f9ba56c8060 R13: 0000000000b6ba60 R14: 0000000000cc7840 R15: 41d8685b1d7901b8 </TASK>
Fix the issue by using __mptcp_flush_join_list() instead of plain mptcp_flush_join_list() inside __mptcp_push_pending(), as suggested by Florian. The sockopt sync will be deferred to the workqueue.
--- net/mptcp/protocol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/mptcp/protocol.c +1 -1
@@ -1549,7 +1549,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)int ret =0 ; prev_ssk = ssk; -mptcp_flush_join_list (msk); +__mptcp_flush_join_list (msk); ssk =mptcp_subflow_get_send (msk);/* First check. If the ssk has changed since
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 93/177 soc/tegra: fuse: Fix bitwise vs. logical OR warning
In reply to Greg Kroah-HartmanFrom: Nathan Chancellor <[email protected]>
[ Upstream commit a7083763619f7485ccdade160deb81737cf2732f ]
A new warning in clang points out two instances where boolean expressions are being used with a bitwise OR instead of logical OR:
drivers/soc/tegra/fuse/speedo-tegra20.c:72:9: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical]
reg = tegra_fuse_read_spare(i) |
^~~~~~~~~~~~~~~~~~~~~~~~~~
||
drivers/soc/tegra/fuse/speedo-tegra20.c:72:9: note: cast one or both operands to int to silence this warning
drivers/soc/tegra/fuse/speedo-tegra20.c:87:9: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical]
reg = tegra_fuse_read_spare(i) |
^~~~~~~~~~~~~~~~~~~~~~~~~~
||drivers/soc/tegra/fuse/speedo-tegra20.c:87:9: note: cast one or both operands to int to silence this warning 2 warnings generated.
The motivation for the warning is that logical operations short circuit while bitwise operations do not.
In this instance, tegra_fuse_read_spare() is not semantically returning a boolean, it is returning a bit value. Use u32 for its return type so that it can be used with either bitwise or boolean operators without any warnings.
--- drivers/soc/tegra/fuse/fuse-tegra.c | 2 +- drivers/soc/tegra/fuse/fuse.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/soc/tegra/fuse/fuse-tegra.c +1 -1
@@ -320,7 +320,7 @@ static struct platform_driver tegra_fuse_driver = { };builtin_platform_driver (tegra_fuse_driver); -bool __init tegra_fuse_read_spare (unsigned int spare) +u32 __init tegra_fuse_read_spare (unsigned int spare) {unsigned int offset = fuse->soc->info->spare + spare *4 ;
drivers/soc/tegra/fuse/fuse.h +1 -1
@@ -65,7 +65,7 @@ struct tegra_fuse {void tegra_init_revision (void );void tegra_init_apbmisc (void ); -bool __init tegra_fuse_read_spare (unsigned int spare); +u32 __init tegra_fuse_read_spare (unsigned int spare);u32 __init tegra_fuse_read_early (unsigned int offset);u8 tegra_get_major_rev (void );
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 94/177 igb: Fix removal of unicast MAC filters of VFs
In reply to Greg Kroah-HartmanFrom: Karen Sornek <[email protected]>
[ Upstream commit 584af82154f56e6b2740160fcc84a2966d969e15 ]
Move checking condition of VF MAC filter before clearing or adding MAC filter to VF to prevent potential blackout caused by removal of necessary and working VF's MAC filter.
--- drivers/net/ethernet/intel/igb/igb_main.c | 28 +++++++++++------------ 1 file changed, 14 insertions(+), 14 deletions(-)
drivers/net/ethernet/intel/igb/igb_main.c +14 -14
@@ -7641,6 +7641,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,struct vf_mac_filter *entry =NULL ;int ret =0 ; +if ((vf_data->flags &IGB_VF_FLAG_PF_SET_MAC ) && + !vf_data->trusted) { +dev_warn (&pdev->dev, +"VF %d requested MAC filter but is administratively denied\n" , + vf); +return -EINVAL ; + } +if (!is_valid_ether_addr (addr)) { +dev_warn (&pdev->dev, +"VF %d attempted to set invalid MAC filter\n" , + vf); +return -EINVAL ; + } +switch (info) {case E1000_VF_MAC_FILTER_CLR :/* remove all unicast MAC filters related to the current VF */
@@ -7654,20 +7668,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, }break ;case E1000_VF_MAC_FILTER_ADD : -if ((vf_data->flags &IGB_VF_FLAG_PF_SET_MAC ) && - !vf_data->trusted) { -dev_warn (&pdev->dev, -"VF %d requested MAC filter but is administratively denied\n" , - vf); -return -EINVAL ; - } -if (!is_valid_ether_addr (addr)) { -dev_warn (&pdev->dev, -"VF %d attempted to set invalid MAC filter\n" , - vf); -return -EINVAL ; - } -/* try to find empty slot in the list */ list_for_each (pos, &adapter->vf_macs.l) { entry = list_entry(pos, struct vf_mac_filter, l);
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 95/177 igbvf: fix double free in `igbvf_probe`
In reply to Greg Kroah-HartmanFrom: Letu Ren <[email protected]>
[ Upstream commit b6d335a60dc624c0d279333b22c737faa765b028 ]
In igbvf_probe, if register_netdev() fails, the program will go to label err_hw_init, and then to label err_ioremap. In free_netdev() which is just below label err_ioremap, there is list_for_each_entry_safe and netif_napi_del which aims to delete all entries in dev->napi_list. The program has added an entry adapter->rx_ring->napi which is added by netif_napi_add in igbvf_alloc_queues(). However, adapter->rx_ring has been freed below label err_hw_init. So this a UAF.
In terms of how to patch the problem, we can refer to igbvf_remove() and delete the entry before adapter->rx_ring.
The KASAN logs are as follows:
[ 35.126075] BUG: KASAN: use-after-free in free_netdev+0x1fd/0x450 [ 35.127170] Read of size 8 at addr ffff88810126d990 by task modprobe/366 [ 35.128360] [ 35.128643] CPU: 1 PID: 366 Comm: modprobe Not tainted 5.15.0-rc2+ #14 [ 35.129789] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [ 35.131749] Call Trace: [ 35.132199] dump_stack_lvl+0x59/0x7b [ 35.132865] print_address_description+0x7c/0x3b0 [ 35.133707] ? free_netdev+0x1fd/0x450 [ 35.134378] __kasan_report+0x160/0x1c0 [ 35.135063] ? free_netdev+0x1fd/0x450 [ 35.135738] kasan_report+0x4b/0x70 [ 35.136367] free_netdev+0x1fd/0x450 [ 35.137006] igbvf_probe+0x121d/0x1a10 [igbvf] [ 35.137808] ? igbvf_vlan_rx_add_vid+0x100/0x100 [igbvf] [ 35.138751] local_pci_probe+0x13c/0x1f0 [ 35.139461] pci_device_probe+0x37e/0x6c0 [ 35.165526] [ 35.165806] Allocated by task 366: [ 35.166414] ____kasan_kmalloc+0xc4/0xf0 [ 35.167117] foo_kmem_cache_alloc_trace+0x3c/0x50 [igbvf] [ 35.168078] igbvf_probe+0x9c5/0x1a10 [igbvf] [ 35.168866] local_pci_probe+0x13c/0x1f0 [ 35.169565] pci_device_probe+0x37e/0x6c0 [ 35.179713] [ 35.179993] Freed by task 366: [ 35.180539] kasan_set_track+0x4c/0x80 [ 35.181211] kasan_set_free_info+0x1f/0x40 [ 35.181942] ____kasan_slab_free+0x103/0x140 [ 35.182703] kfree+0xe3/0x250 [ 35.183239] igbvf_probe+0x1173/0x1a10 [igbvf] [ 35.184040] local_pci_probe+0x13c/0x1f0
--- drivers/net/ethernet/intel/igbvf/netdev.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/ethernet/intel/igbvf/netdev.c +1 -0
@@ -2861,6 +2861,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)return 0 ; err_hw_init: +netif_napi_del (&adapter->rx_ring->napi);kfree (adapter->tx_ring);kfree (adapter->rx_ring); err_sw_init:
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 96/177 igc: Fix typo in i225 LTR functions
In reply to Greg Kroah-HartmanFrom: Sasha Neftin <[email protected]>
[ Upstream commit 0182d1f3fa640888a2ed7e3f6df2fdb10adee7c8 ]
The LTR maximum value was incorrectly written using the scale from the LTR minimum value. This would cause incorrect values to be sent, in cases where the initial calculation lead to different min/max scales.
--- drivers/net/ethernet/intel/igc/igc_i225.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/igc/igc_i225.c +1 -1
@@ -636,7 +636,7 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link) ltrv =rd32 (IGC_LTRMAXV );if (ltr_max != (ltrv &IGC_LTRMAXV_LTRV_MASK )) { ltrv =IGC_LTRMAXV_LSNP_REQ | ltr_max | - (scale_min <<IGC_LTRMAXV_SCALE_SHIFT ); + (scale_max <<IGC_LTRMAXV_SCALE_SHIFT );wr32 (IGC_LTRMAXV , ltrv); } }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 97/177 ixgbe: Document how to enable NBASE-T support
In reply to Greg Kroah-HartmanFrom: Robert Schlabbach <[email protected]>
[ Upstream commit 271225fd57c2f1e0b3f8826df51be6c634affefe ]
Commit a296d665eae1 ("ixgbe: Add ethtool support to enable 2.5 and 5.0 Gbps support") introduced suppression of the advertisement of NBASE-T speeds by default, according to Todd Fujinaka to accommodate customers with network switches which could not cope with advertised NBASE-T speeds, as posted in the E1000-devel mailing list:
https://sourceforge.net/p/e1000/mailman/message/37106269/
However, the suppression was not documented at all, nor was how to enable NBASE-T support.
Properly document the NBASE-T suppression and how to enable NBASE-T support.
--- .../device_drivers/ethernet/intel/ixgbe.rst | 16 ++++++++++++++++ drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++++ 2 files changed, 20 insertions(+)
Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst +16 -0
@@ -440,6 +440,22 @@ NOTE: For 82599-based network connections, if you are enabling jumbo frames in a virtual function (VF), jumbo frames must first be enabled in the physical function (PF). The VF MTU setting cannot be larger than the PF MTU. +NBASE-T Support +--------------- +The ixgbe driver supports NBASE-T on some devices. However, the advertisement +of NBASE-T speeds is suppressed by default, to accommodate broken network +switches which cannot cope with advertised NBASE-T speeds. Use the ethtool +command to enable advertising NBASE-T speeds on devices which support it:: + + ethtool -s eth? advertise 0x1800000001028 + +On Linux systems with INTERFACES(5), this can be specified as a pre-up command +in /etc/network/interfaces so that the interface is always brought up with +NBASE-T support, e.g.:: + + iface eth? inet dhcp + pre-up ethtool -s eth? advertise 0x1800000001028 || true + Generic Receive Offload, aka GRO -------------------------------- The driver supports the in-kernel software implementation of GRO. GRO has
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +4 -0
@@ -5526,6 +5526,10 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)if (!speed && hw->mac.ops.get_link_capabilities) { ret = hw->mac.ops.get_link_capabilities (hw, &speed, &autoneg); +/* remove NBASE-T speeds from default autonegotiation +* to accommodate broken network switches in the field +* which cannot cope with advertised NBASE-T speeds +*/ speed &= ~(IXGBE_LINK_SPEED_5GB_FULL |IXGBE_LINK_SPEED_2_5GB_FULL ); }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 98/177 ixgbe: set X550 MDIO speed before talking to PHY
In reply to Greg Kroah-HartmanFrom: Cyril Novikov <[email protected]>
[ Upstream commit bf0a375055bd1afbbf02a0ef45f7655da7b71317 ]
The MDIO bus speed must be initialized before talking to the PHY the first time in order to avoid talking to it using a speed that the PHY doesn't support.
This fixes HW initialization error -17 (IXGBE_ERR_PHY_ADDR_INVALID) on Denverton CPUs (a.k.a. the Atom C3000 family) on ports with a 10Gb network plugged in. On those devices, HLREG0[MDCSPD] resets to 1, which combined with the 10Gb network results in a 24MHz MDIO speed, which is apparently too fast for the connected PHY. PHY register reads over MDIO bus return garbage, leading to initialization failure.
Reproduced with Linux kernel 4.19 and 5.15-rc7. Can be reproduced using the following setup:
* Use an Atom C3000 family system with at least one X552 LAN on the SoC
* Disable PXE or other BIOS network initialization if possible (the interface must not be initialized before Linux boots)
* Connect a live 10Gb Ethernet cable to an X550 port
* Power cycle (not reset, doesn't always work) the system and boot Linux
* Observe: ixgbe interfaces w/ 10GbE cables plugged in fail with error -17
--- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +3 -0
@@ -3405,6 +3405,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)/* flush pending Tx transactions */ ixgbe_clear_tx_pending (hw); +/* set MDIO speed before talking to the PHY in case it's the 1st time */ +ixgbe_set_mdio_speed (hw); +/* PHY ops must be identified and initialized prior to reset */ status = hw->phy.ops.init (hw); if (status == IXGBE_ERR_SFP_NOT_SUPPORTED ||
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 99/177 netdevsim: Zero-initialize memory for new maps value in function nsim_bpf_map_alloc
In reply to Greg Kroah-HartmanFrom: Haimin Zhang <[email protected]>
[ Upstream commit 481221775d53d6215a6e5e9ce1cce6d2b4ab9a46 ]
Zero-initialize memory for new map's value in function nsim_bpf_map_alloc since it may cause a potential kernel information leak issue, as follows:
1. nsim_bpf_map_alloc calls nsim_map_alloc_elem to allocate elements for a new map.
2. nsim_map_alloc_elem uses kmalloc to allocate map's value, but doesn't zero it.
3. A user application can use IOCTL BPF_MAP_LOOKUP_ELEM to get specific element's information in the map.
4. The kernel function map_lookup_elem will call bpf_map_copy_value to get the information allocated at step-2, then use copy_to_user to copy to the user buffer.
This can only leak information for an array map.
--- drivers/net/netdevsim/bpf.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/netdevsim/bpf.c +1 -0
@@ -514,6 +514,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) goto err_free; key = nmap->entry[i].key; *key = i; +memset (nmap->entry[i].value,0 , offmap->map.value_size); } }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 100/177 net/packet: rx_owner_map depends on pg_vec
In reply to Greg Kroah-HartmanFrom: Willem de Bruijn <[email protected]>
[ Upstream commit ec6af094ea28f0f2dda1a6a33b14cd57e36a9755 ]
Packet sockets may switch ring versions. Avoid misinterpreting state between versions, whose fields share a union. rx_owner_map is only allocated with a packet ring (pg_vec) and both are swapped together. If pg_vec is NULL, meaning no packet ring was allocated, then neither was rx_owner_map. And the field may be old state from a tpacket_v3.
--- net/packet/af_packet.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
net/packet/af_packet.c +3 -2
@@ -4457,9 +4457,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } out_free_pg_vec: -bitmap_free (rx_owner_map); -if (pg_vec) +if (pg_vec) { +bitmap_free (rx_owner_map);free_pg_vec (pg_vec, order, req->tp_block_nr); + } out:return err; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 101/177 net: stmmac: dwmac-rk: fix oob read in rk_gmac_setup
In reply to Greg Kroah-HartmanFrom: John Keeping <[email protected]>
[ Upstream commit 0546b224cc7717cc8a2db076b0bb069a9c430794 ]
KASAN reports an out-of-bounds read in rk_gmac_setup on the line:
while (ops->regs[i]) {This happens for most platforms since the regs flexible array member is empty, so the memory after the ops structure is being read here. It seems that mostly this happens to contain zero anyway, so we get lucky and everything still works.
To avoid adding redundant data to nearly all the ops structures, add a new flag to indicate whether the regs field is valid and avoid this loop when it is not.
--- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +3 -1
@@ -33,6 +33,7 @@ struct rk_gmac_ops {void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv,int speed);void (*set_rmii_speed)(struct rk_priv_data *bsp_priv,int speed);void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv); +bool regs_valid;u32 regs[]; };
@@ -1092,6 +1093,7 @@ static const struct rk_gmac_ops rk3568_ops = { .set_to_rmii = rk3568_set_to_rmii, .set_rgmii_speed = rk3568_set_gmac_speed, .set_rmii_speed = rk3568_set_gmac_speed, + .regs_valid = true, .regs = {0xfe2a0000 ,/* gmac0 */ 0xfe010000, /* gmac1 */
@@ -1383,7 +1385,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,* to be distinguished. */ res =platform_get_resource (pdev,IORESOURCE_MEM ,0 ); -if (res) { +if (res && ops->regs_valid) {int i =0 ;while (ops->regs[i]) {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 102/177 sfc_ef100: potential dereference of null pointer
In reply to Greg Kroah-HartmanFrom: Jiasheng Jiang <[email protected]>
[ Upstream commit 407ecd1bd726f240123f704620d46e285ff30dd9 ]
The return value of kmalloc() needs to be checked.
To avoid use in efx_nic_update_stats() in case of the failure of alloc.
--- drivers/net/ethernet/sfc/ef100_nic.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/ethernet/sfc/ef100_nic.c +3 -0
@@ -609,6 +609,9 @@ static size_t ef100_update_stats(struct efx_nic *efx,ef100_common_stat_mask (mask);ef100_ethtool_stat_mask (mask); +if (!mc_stats) +return 0 ; +efx_nic_copy_stats (efx, mc_stats);efx_nic_update_stats (ef100_stat_desc,EF100_STAT_COUNT , mask, stats, mc_stats, false);
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 103/177 dsa: mv88e6xxx: fix debug print for SPEED_UNFORCED
In reply to Greg Kroah-HartmanFrom: Andrey Eremeev <[email protected]>
[ Upstream commit e08cdf63049b711099efff0811273449083bb958 ]
Debug print uses invalid check to detect if speed is unforced:
(speed != SPEED_UNFORCED) should be used instead of (!speed).
Found by Linux Verification Center (linuxtesting.org) with SVACE.
--- drivers/net/dsa/mv88e6xxx/port.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/dsa/mv88e6xxx/port.c +2 -2
@@ -283,7 +283,7 @@ static int mv88e6xxx_port_set_speed_duplex(struct mv88e6xxx_chip *chip,if (err)return err; -if (speed) +if (speed !=SPEED_UNFORCED )dev_dbg (chip->dev,"p%d: Speed set to %d Mbps\n" , port, speed);else dev_dbg (chip->dev,"p%d: Speed unforced\n" , port);
@@ -516,7 +516,7 @@ int mv88e6393x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port,if (err)return err; -if (speed) +if (speed !=SPEED_UNFORCED )dev_dbg (chip->dev,"p%d: Speed set to %d Mbps\n" , port, speed);else dev_dbg (chip->dev,"p%d: Speed unforced\n" , port);
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 104/177 net: Fix double 0x prefix print in SKB dump
In reply to Greg Kroah-HartmanFrom: Gal Pressman <[email protected]>
[ Upstream commit 8a03ef676ade55182f9b05115763aeda6dc08159 ]
When printing netdev features %pNF already takes care of the 0x prefix, remove the explicit one.
--- net/core/skbuff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/core/skbuff.c +1 -1
@@ -832,7 +832,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) ntohs(skb->protocol), skb->pkt_type, skb->skb_iif);if (dev) -printk ("%sdev name=%s feat=0x%pNF\n" , +printk ("%sdev name=%s feat=%pNF\n" , level, dev->name, &dev->features);if (sk) printk("%ssk family=%hu type=%u proto=%u\n",
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 105/177 net/smc: Prevent smc_release() from long blocking
In reply to Greg Kroah-HartmanFrom: D. Wythe <[email protected]>
[ Upstream commit 5c15b3123f65f8fbb1b445d9a7e8812e0e435df2 ]
In nginx/wrk benchmark, there's a hung problem with high probability on case likes that: (client will last several minutes to exit)
server: smc_run nginx
client: smc_run wrk -c 10000 -t 1 http://server
Client hangs with the following backtrace:
0 [ffffa7ce8Of3bbf8] __schedule at ffffffff9f9eOd5f
1 [ffffa7ce8Of3bc88] schedule at ffffffff9f9eløe6
2 [ffffa7ce8Of3bcaO] schedule_timeout at ffffffff9f9e3f3c
3 [ffffa7ce8Of3bd2O] wait_for_common at ffffffff9f9el9de
4 [ffffa7ce8Of3bd8O] __flush_work at ffffffff9fOfeOl3
5 [ffffa7ce8øf3bdfO] smc_release at ffffffffcO697d24 [smc]
6 [ffffa7ce8Of3be2O] __sock_release at ffffffff9f8O2e2d
7 [ffffa7ce8Of3be4ø] sock_close at ffffffff9f8ø2ebl
8 [ffffa7ce8øf3be48] __fput at ffffffff9f334f93
9 [ffffa7ce8Of3be78] task_work_run at ffffffff9flOlff5
10 [ffffa7ce8Of3beaO] do_exit at ffffffff9fOe5Ol2
11 [ffffa7ce8Of3bflO] do_group_exit at ffffffff9fOe592a
12 [ffffa7ce8Of3bf38] __x64_sys_exit_group at ffffffff9fOe5994 13 [ffffa7ce8Of3bf4O] do_syscall_64 at ffffffff9f9d4373
14 [ffffa7ce8Of3bfsO] entry_SYSCALL_64_after_hwframe at ffffffff9fa0007c
This issue dues to flush_work(), which is used to wait for smc_connect_work() to finish in smc_release(). Once lots of smc_connect_work() was pending or all executing work dangling, smc_release() has to block until one worker comes to free, which is equivalent to wait another smc_connnect_work() to finish.
In order to fix this, There are two changes:
1. For those idle smc_connect_work(), cancel it from the workqueue; for executing smc_connect_work(), waiting for it to finish. For that purpose, replace flush_work() with cancel_work_sync().
2. Since smc_connect() hold a reference for passive closing, if smc_connect_work() has been cancelled, release the reference.
--- net/smc/af_smc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/smc/af_smc.c +3 -1
@@ -193,7 +193,9 @@ static int smc_release(struct socket *sock)/* cleanup for a dangling non-blocking connect */ if (smc->connect_nonblock && sk->sk_state ==SMC_INIT )tcp_abort (smc->clcsock->sk,ECONNABORTED ); -flush_work (&smc->connect_work); + +if (cancel_work_sync (&smc->connect_work)) +sock_put (&smc->sk);/* sock_hold in smc_connect for passive closing */ if (sk->sk_state ==SMC_LISTEN )/* smc_close_non_accepted() is called and acquires
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 106/177 net: systemport: Add global locking for descriptor lifecycle
In reply to Greg Kroah-HartmanFrom: Florian Fainelli <[email protected]>
[ Upstream commit 8b8e6e782456f1ce02a7ae914bbd5b1053f0b034 ]
The descriptor list is a shared resource across all of the transmit queues, and the locking mechanism used today only protects concurrency across a given transmit queue between the transmit and reclaiming. This creates an opportunity for the SYSTEMPORT hardware to work on corrupted descriptors if we have multiple producers at once which is the case when using multiple transmit queues.
This was particularly noticeable when using multiple flows/transmit queues and it showed up in interesting ways in that UDP packets would get a correct UDP header checksum being calculated over an incorrect packet length. Similarly TCP packets would get an equally correct checksum computed by the hardware over an incorrect packet length.
The SYSTEMPORT hardware maintains an internal descriptor list that it re-arranges when the driver produces a new descriptor anytime it writes to the WRITE_PORT_{HI,LO} registers, there is however some delay in the hardware to re-organize its descriptors and it is possible that concurrent TX queues eventually break this internal allocation scheme to the point where the length/status part of the descriptor gets used for an incorrect data buffer.
The fix is to impose a global serialization for all TX queues in the short section where we are writing to the WRITE_PORT_{HI,LO} registers which solves the corruption even with multiple concurrent TX queues being used.
--- drivers/net/ethernet/broadcom/bcmsysport.c | 5 ++++- drivers/net/ethernet/broadcom/bcmsysport.h | 1 + 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/ethernet/broadcom/bcmsysport.c +4 -1
@@ -1309,11 +1309,11 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,struct bcm_sysport_priv *priv =netdev_priv (dev);struct device *kdev = &priv->pdev->dev;struct bcm_sysport_tx_ring *ring; +unsigned long flags, desc_flags;struct bcm_sysport_cb *cb;struct netdev_queue *txq;u32 len_status, addr_lo;unsigned int skb_len; -unsigned long flags;dma_addr_t mapping;u16 queue;int ret;
@@ -1373,8 +1373,10 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb, ring->desc_count--;/* Ports are latched, so write upper address first */ +spin_lock_irqsave (&priv->desc_lock, desc_flags);tdma_writel (priv, len_status,TDMA_WRITE_PORT_HI (ring->index));tdma_writel (priv, addr_lo,TDMA_WRITE_PORT_LO (ring->index)); +spin_unlock_irqrestore (&priv->desc_lock, desc_flags);/* Check ring space and update SW control flow */ if (ring->desc_count ==0 )
@@ -2013,6 +2015,7 @@ static int bcm_sysport_open(struct net_device *dev) }/* Initialize both hardware and software ring */ +spin_lock_init (&priv->desc_lock);for (i =0 ; i < dev->num_tx_queues; i++) { ret =bcm_sysport_init_tx_ring (priv, i);if (ret) {
drivers/net/ethernet/broadcom/bcmsysport.h +1 -0
@@ -711,6 +711,7 @@ struct bcm_sysport_priv {int wol_irq;/* Transmit rings */ +spinlock_t desc_lock;struct bcm_sysport_tx_ring *tx_rings;/* Receive queue */
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 107/177 sit: do not call ipip6_dev_free() from sit_init_net()
In reply to Greg Kroah-HartmanFrom: Eric Dumazet <[email protected]>
[ Upstream commit e28587cc491ef0f3c51258fdc87fbc386b1d4c59 ]
ipip6_dev_free is sit dev->priv_destructor, already called by register_netdevice() if something goes wrong.
Alternative would be to make ipip6_dev_free() robust against multiple invocations, but other drivers do not implement this strategy.
syzbot reported:
dst_release underflow
WARNING: CPU: 0 PID: 5059 at net/core/dst.c:173 dst_release+0xd8/0xe0 net/core/dst.c:173 Modules linked in: CPU: 1 PID: 5059 Comm: syz-executor.4 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:dst_release+0xd8/0xe0 net/core/dst.c:173 Code: 4c 89 f2 89 d9 31 c0 5b 41 5e 5d e9 da d5 44 f9 e8 1d 90 5f f9 c6 05 87 48 c6 05 01 48 c7 c7 80 44 99 8b 31 c0 e8 e8 67 29 f9 <0f> 0b eb 85 0f 1f 40 00 53 48 89 fb e8 f7 8f 5f f9 48 83 c3 a8 48 RSP: 0018:ffffc9000aa5faa0 EFLAGS: 00010246 RAX: d6894a925dd15a00 RBX: 00000000ffffffff RCX: 0000000000040000 RDX: ffffc90005e19000 RSI: 000000000003ffff RDI: 0000000000040000 RBP: 0000000000000000 R08: ffffffff816a1f42 R09: ffffed1017344f2c R10: ffffed1017344f2c R11: 0000000000000000 R12: 0000607f462b1358 R13: 1ffffffff1bfd305 R14: ffffe8ffffcb1358 R15: dffffc0000000000 FS: 00007f66c71a2700(0000) GS:ffff8880b9a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f88aaed5058 CR3: 0000000023e0f000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> dst_cache_destroy+0x107/0x1e0 net/core/dst_cache.c:160 ipip6_dev_free net/ipv6/sit.c:1414 [inline] sit_init_net+0x229/0x550 net/ipv6/sit.c:1936 ops_init+0x313/0x430 net/core/net_namespace.c:140 setup_net+0x35b/0x9d0 net/core/net_namespace.c:326 copy_net_ns+0x359/0x5c0 net/core/net_namespace.c:470 create_new_namespaces+0x4ce/0xa00 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0x11e/0x180 kernel/nsproxy.c:226 ksys_unshare+0x57d/0xb50 kernel/fork.c:3075 __do_sys_unshare kernel/fork.c:3146 [inline] __se_sys_unshare kernel/fork.c:3144 [inline] __x64_sys_unshare+0x34/0x40 kernel/fork.c:3144 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f66c882ce99 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 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 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f66c71a2168 EFLAGS: 00000246 ORIG_RAX: 0000000000000110 RAX: ffffffffffffffda RBX: 00007f66c893ff60 RCX: 00007f66c882ce99 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000048040200 RBP: 00007f66c8886ff1 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fff6634832f R14: 00007f66c71a2300 R15: 0000000000022000 </TASK>
--- net/ipv6/sit.c | 1 - 1 file changed, 1 deletion(-)
net/ipv6/sit.c +0 -1
@@ -1933,7 +1933,6 @@ static int __net_init sit_init_net(struct net *net)return 0 ; err_reg_dev: -ipip6_dev_free (sitn->fb_tunnel_dev);free_netdev (sitn->fb_tunnel_dev); err_alloc_dev:return err;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 108/177 afs: Fix mmap
In reply to Greg Kroah-HartmanFrom: David Howells <[email protected]>
[ Upstream commit 1744a22ae948799da7927b53ec97ccc877ff9d61 ]
Fix afs_add_open_map() to check that the vnode isn't already on the list when it adds it. It's possible that afs_drop_open_mmap() decremented the cb_nr_mmap counter, but hadn't yet got into the locked section to remove it.
Also vnode->cb_mmap_link should be initialised, so fix that too.
--- fs/afs/file.c | 5 +++-- fs/afs/super.c | 1 + 2 files changed, 4 insertions(+), 2 deletions(-)
fs/afs/file.c +3 -2
@@ -502,8 +502,9 @@ static void afs_add_open_mmap(struct afs_vnode *vnode)if (atomic_inc_return (&vnode->cb_nr_mmap) ==1 ) {down_write (&vnode->volume->cell->fs_open_mmaps_lock); -list_add_tail (&vnode->cb_mmap_link, - &vnode->volume->cell->fs_open_mmaps); +if (list_empty (&vnode->cb_mmap_link)) +list_add_tail (&vnode->cb_mmap_link, + &vnode->volume->cell->fs_open_mmaps);up_write (&vnode->volume->cell->fs_open_mmaps_lock); }
fs/afs/super.c +1 -0
@@ -667,6 +667,7 @@ static void afs_i_init_once(void *_vnode)INIT_LIST_HEAD (&vnode->pending_locks);INIT_LIST_HEAD (&vnode->granted_locks);INIT_DELAYED_WORK (&vnode->lock_work, afs_lock_work); +INIT_LIST_HEAD (&vnode->cb_mmap_link);seqlock_init (&vnode->cb_lock); }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 109/177 arm64: kexec: Fix missing error code ret warning in load_other_segments()
In reply to Greg Kroah-HartmanFrom: Lakshmi Ramasubramanian <[email protected]>
[ Upstream commit 9c5d89bc10551f1aecd768b00fca3339a7b8c8ee ]
Since commit ac10be5cdbfa ("arm64: Use common of_kexec_alloc_and_setup_fdt()"), smatch reports the following warning:
arch/arm64/kernel/machine_kexec_file.c:152 load_other_segments()
warn: missing error code 'ret'
Return code is not set to an error code in load_other_segments() when of_kexec_alloc_and_setup_fdt() call returns a NULL dtb. This results in status success (return code set to 0) being returned from load_other_segments().
Set return code to -EINVAL if of_kexec_alloc_and_setup_fdt() returns NULL dtb.
--- arch/arm64/kernel/machine_kexec_file.c | 1 + 1 file changed, 1 insertion(+)
arch/arm64/kernel/machine_kexec_file.c +1 -0
@@ -149,6 +149,7 @@ int load_other_segments(struct kimage *image, initrd_len, cmdline, 0);if (!dtb) {pr_err ("Preparing for new dtb failed\n" ); + ret = -EINVAL ; goto out_err; }
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 110/177 bpf: Fix extable fixup offset.
In reply to Greg Kroah-HartmanFrom: Alexei Starovoitov <[email protected]>
[ Upstream commit 433956e91200734d09958673a56df02d00a917c2 ]
The prog - start_of_ldx is the offset before the faulting ldx to the location after it, so this will be used to adjust pt_regs->ip for jumping over it and continuing, and with old temp it would have been fixed up to the wrong offset, causing crash.
--- arch/x86/net/bpf_jit_comp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/net/bpf_jit_comp.c +1 -1
@@ -1332,7 +1332,7 @@ st: if (is_imm8(insn->off))* End result: x86 insn "mov rbx, qword ptr [rax+0x14]" * of 4 bytes will be ignored and rbx will be zero inited. */ - ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] <<8 ); + ex->fixup = (prog - start_of_ldx) | (reg2pt_regs[dst_reg] <<8 ); }break ;
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 111/177 bpf, selftests: Fix racing issue in btf_skc_cls_ingress test
In reply to Greg Kroah-HartmanFrom: Martin KaFai Lau <[email protected]>
[ Upstream commit c2fcbf81c332b42382a0c439bfe2414a241e4f5b ]
The libbpf CI reported occasional failure in btf_skc_cls_ingress:
test_syncookie:FAIL:Unexpected syncookie states gen_cookie:80326634 recv_cookie:0 bpf prog error at line 97
"error at line 97" means the bpf prog cannot find the listening socket when the final ack is received. It then skipped processing the syncookie in the final ack which then led to "recv_cookie:0".
The problem is the userspace program did not do accept() and went ahead to close(listen_fd) before the kernel (and the bpf prog) had a chance to process the final ack.
The fix is to add accept() call so that the userspace will wait for the kernel to finish processing the final ack first before close()-ing everything.
--- .../bpf/prog_tests/btf_skc_cls_ingress.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c +14 -2
@@ -90,7 +90,7 @@ static void print_err_line(void)static void test_conn (void ) { -int listen_fd =-1 , cli_fd =-1 , err; +int listen_fd =-1 , cli_fd =-1 , srv_fd =-1 , err;socklen_t addrlen =sizeof (srv_sa6);int srv_port;
@@ -112,6 +112,10 @@ static void test_conn(void)if (CHECK_FAIL (cli_fd ==-1 )) goto done; + srv_fd =accept (listen_fd,NULL ,NULL ); +if (CHECK_FAIL (srv_fd ==-1 )) + goto done; + if (CHECK(skel->bss->listen_tp_sport != srv_port || skel->bss->req_sk_sport != srv_port, "Unexpected sk src port",
@@ -134,11 +138,13 @@ static void test_conn(void)close (listen_fd);if (cli_fd !=-1 )close (cli_fd); +if (srv_fd !=-1 ) +close (srv_fd); }static void test_syncookie (void ) { -int listen_fd =-1 , cli_fd =-1 , err; +int listen_fd =-1 , cli_fd =-1 , srv_fd =-1 , err;socklen_t addrlen =sizeof (srv_sa6);int srv_port;
@@ -161,6 +167,10 @@ static void test_syncookie(void)if (CHECK_FAIL (cli_fd ==-1 )) goto done; + srv_fd =accept (listen_fd,NULL ,NULL ); +if (CHECK_FAIL (srv_fd ==-1 )) + goto done; + if (CHECK(skel->bss->listen_tp_sport != srv_port, "Unexpected tp src port", "listen_tp_sport:%u expected:%u\n",
@@ -188,6 +198,8 @@ static void test_syncookie(void)close (listen_fd);if (cli_fd !=-1 )close (cli_fd); +if (srv_fd !=-1 ) +close (srv_fd); }struct test {
Signature · 1 line
2.33.0
Greg Kroah-Hartman
maintainerPATCH 112/177 powerpc/85xx: Fix oops when CONFIG_FSL_PMC=n
In reply to Greg Kroah-HartmanFrom: Xiaoming Ni <[email protected]>
[ Upstream commit 3dc709e518b47386e6af937eaec37bb36539edfd ]
When CONFIG_FSL_PMC is set to n, no value is assigned to cpu_up_prepare in the mpc85xx_pm_ops structure. As a result, oops is triggered in smp_85xx_start_cpu().
smp: Bringing up secondary CPUs ...
kernel tried to execute user page (0) - exploit attempt? (uid: 0)
BUG: Unable to handle kernel instruction fetch (NULL pointer?) Faulting instruction address: 0x00000000 Oops: Kernel access of bad area, sig: 11 [#1] ... NIP [00000000] 0x0 LR [c0021d2c] smp_85xx_kick_cpu+0xe8/0x568 Call Trace: [c1051da8] [c0021cb8] smp_85xx_kick_cpu+0x74/0x568 (unreliable) [c1051de8] [c0011460] __cpu_up+0xc0/0x228 [c1051e18] [c0031bbc] bringup_cpu+0x30/0x224 [c1051e48] [c0031f3c] cpu_up.constprop.0+0x180/0x33c [c1051e88] [c00322e8] bringup_nonboot_cpus+0x88/0xc8 [c1051eb8] [c07e67bc] smp_init+0x30/0x78 [c1051ed8] [c07d9e28] kernel_init_freeable+0x118/0x2a8 [c1051f18] [c00032d8] kernel_init+0x14/0x124 [c1051f38] [c0010278] ret_from_kernel_thread+0x14/0x1c
--- arch/powerpc/platforms/85xx/smp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/powerpc/platforms/85xx/smp.c +2 -2
@@ -220,7 +220,7 @@ static int smp_85xx_start_cpu(int cpu)local_irq_save (flags);hard_irq_disable (); -if (qoriq_pm_ops) +if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare) qoriq_pm_ops->cpu_up_prepare (cpu);/* if cpu is not spinning, reset it */
@@ -292,7 +292,7 @@ static int smp_85xx_kick_cpu(int nr) booting_thread_hwid =cpu_thread_in_core (nr); primary =cpu_first_thread_sibling (nr); -if (qoriq_pm_ops) +if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare) qoriq_pm_ops->cpu_up_prepare (nr);/*
Signature · 1 line
2.34.1
Greg Kroah-Hartman
maintainerPATCH 113/177 USB: gadget: bRequestType is a bitfield, not a enum
In reply to Greg Kroah-HartmanFrom: Greg Kroah-Hartman <[email protected]>
[ Upstream commit f08adf5add9a071160c68bb2a61d697f39ab0758 ]
Szymon rightly pointed out that the previous check for the endpoint direction in bRequestType was not looking at only the bit involved, but rather the whole value. Normally this is ok, but for some request types, bits other than bit 8 could be set and the check for the endpoint length could not stall correctly.
Fix that up by only checking the single bit.
--- drivers/usb/gadget/composite.c | 6 +++--- drivers/usb/gadget/legacy/dbgp.c | 6 +++--- drivers/usb/gadget/legacy/inode.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-)
drivers/usb/gadget/composite.c +3 -3
@@ -1680,14 +1680,14 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)u8 endp;if (w_length >USB_COMP_EP0_BUFSIZ ) { -if (ctrl->bRequestType ==USB_DIR_OUT ) { - goto done; - }else { +if (ctrl->bRequestType &USB_DIR_IN ) {/* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp =cpu_to_le16 (USB_COMP_EP0_BUFSIZ ); w_length =USB_COMP_EP0_BUFSIZ ; + }else { + goto done; } }
drivers/usb/gadget/legacy/dbgp.c +3 -3
@@ -346,14 +346,14 @@ static int dbgp_setup(struct usb_gadget *gadget,u16 len =0 ;if (length >DBGP_REQ_LEN ) { -if (ctrl->bRequestType ==USB_DIR_OUT ) { -return err; - }else { +if (ctrl->bRequestType &USB_DIR_IN ) {/* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp =cpu_to_le16 (DBGP_REQ_LEN ); length =DBGP_REQ_LEN ; + }else { +return err; } }
drivers/usb/gadget/legacy/inode.c +3 -3
@@ -1337,14 +1337,14 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)u16 w_length =le16_to_cpu (ctrl->wLength);if (w_length >RBUF_SIZE ) { -if (ctrl->bRequestType ==USB_DIR_OUT ) { -return value; - }else { +if (ctrl->bRequestType &USB_DIR_IN ) {/* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength; *temp =cpu_to_le16 (RBUF_SIZE ); w_length =RBUF_SIZE ; + }else { +return value; } }
Signature · 1 line
2.34.1
Greg Kroah-Hartman
maintainerPATCH 114/177 Revert "usb: early: convert to readl_poll_timeout_atomic()"
In reply to Greg Kroah-HartmanFrom: Greg Kroah-Hartman <[email protected]>
[ Upstream commit c4d936efa46d8ea183df16c0f3fa4423327da51d ]
This reverts commit 796eed4b2342c9d6b26c958e92af91253a2390e1.
This change causes boot lockups when using "arlyprintk=xdbc" because ktime can not be used at this point in time in the boot process. Also, it is not needed for very small delays like this.
--- drivers/usb/early/xhci-dbc.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-)
drivers/usb/early/xhci-dbc.c +11 -4
@@ -14,7 +14,6 @@#include <linux/pci_ids.h> #include <linux/memblock.h> #include <linux/io.h> -#include <linux/iopoll.h> #include <asm/pci-direct.h> #include <asm/fixmap.h> #include <linux/bcd.h>
@@ -136,9 +135,17 @@ static int handshake(void __iomem *ptr, u32 mask, u32 done, int wait, int delay) {u32 result; -return readl_poll_timeout_atomic (ptr, result, - ((result & mask) == done), - delay, wait); +/* Can not use readl_poll_timeout_atomic() for early boot things */ +do { + result =readl (ptr); + result &= mask; +if (result == done) +return 0 ; +udelay (delay); + wait -= delay; + }while (wait >0 ); + +return -ETIMEDOUT ; }static void __init xdbc_bios_handoff (void )
Signature · 1 line
2.34.1
Greg Kroah-Hartman
maintainerPATCH 115/177 KVM: x86: Drop guest CPUID check for host initiated writes to MSR_IA32_PERF_CAPABILITIES
In reply to Greg Kroah-HartmanFrom: Vitaly Kuznetsov <[email protected]>
[ Upstream commit 1aa2abb33a419090c7c87d4ae842a6347078ee12 ]
The ability to write to MSR_IA32_PERF_CAPABILITIES from the host should not depend on guest visible CPUID entries, even if just to allow creating/restoring guest MSRs and CPUIDs in any sequence.
Message-Id: <[email protected]>
--- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kvm/x86.c +1 -1
@@ -3359,7 +3359,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)if (!msr_info->host_initiated)return 1 ; -if (guest_cpuid_has (vcpu,X86_FEATURE_PDCM ) &&kvm_get_msr_feature (&msr_ent)) +if (kvm_get_msr_feature (&msr_ent))return 1 ;if (data & ~msr_ent.data)return 1 ;
Signature · 1 line
2.34.1
Greg Kroah-Hartman
maintainerPATCH 116/177 tty: n_hdlc: make n_hdlc_tty_wakeup() asynchronous
In reply to Greg Kroah-HartmanFrom: Tetsuo Handa <[email protected]>
commit 1ee33b1ca2b8dabfcc17198ffd049a6b55674a86 upstream.
syzbot is reporting that an unprivileged user who logged in from tty console can crash the system using a reproducer shown below [1], for n_hdlc_tty_wakeup() is synchronously calling n_hdlc_send_frames().
----------
#include <sys/ioctl.h>
#include <unistd.h>
int main(int argc, char *argv[])
{
const int disc = 0xd; ioctl(1, TIOCSETD, &disc);
while (1) {
ioctl(1, TCXONC, 0);
write(1, "", 1);
ioctl(1, TCXONC, 1); /* Kernel panic - not syncing: scheduling while atomic */
} }
----------
Linus suspected that "struct tty_ldisc"->ops->write_wakeup() must not sleep, and Jiri confirmed it from include/linux/tty_ldisc.h. Thus, defer n_hdlc_send_frames() from n_hdlc_tty_wakeup() to a WQ context like net/nfc/nci/uart.c does.
--- drivers/tty/n_hdlc.c | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-)
drivers/tty/n_hdlc.c +22 -1
@@ -140,6 +140,8 @@ struct n_hdlc {struct n_hdlc_buf_list rx_buf_list;struct n_hdlc_buf_list tx_free_buf_list;struct n_hdlc_buf_list rx_free_buf_list; +struct work_struct write_work; +struct tty_struct *tty_for_write_work; };/*
@@ -154,6 +156,7 @@ static struct n_hdlc_buf *n_hdlc_buf_get/* Local functions */ static struct n_hdlc *n_hdlc_alloc (void ); +static void n_hdlc_tty_write_work (struct work_struct *work);/* max frame size for memory allocations */ static int maxframe =4096 ;
@@ -210,6 +213,8 @@ static void n_hdlc_tty_close(struct tty_wake_up_interruptible (&tty->read_wait);wake_up_interruptible (&tty->write_wait); +cancel_work_sync (&n_hdlc->write_work); +n_hdlc_free_buf_list (&n_hdlc->rx_free_buf_list);n_hdlc_free_buf_list (&n_hdlc->tx_free_buf_list);n_hdlc_free_buf_list (&n_hdlc->rx_buf_list);
@@ -241,6 +246,8 @@ static int n_hdlc_tty_open(struct tty_streturn -ENFILE ; } +INIT_WORK (&n_hdlc->write_work, n_hdlc_tty_write_work); + n_hdlc->tty_for_write_work = tty; tty->disc_data = n_hdlc; tty->receive_room =65536 ;
@@ -335,6 +342,20 @@ check_again: }/* end of n_hdlc_send_frames() */ /** +* n_hdlc_tty_write_work - Asynchronous callback for transmit wakeup +* @work: pointer to work_struct +* +* Called when low level device driver can accept more send data. +*/ +static void n_hdlc_tty_write_work (struct work_struct *work) +{ + struct n_hdlc *n_hdlc = container_of(work, struct n_hdlc, write_work); +struct tty_struct *tty = n_hdlc->tty_for_write_work; + +n_hdlc_send_frames (n_hdlc, tty); +}/* end of n_hdlc_tty_write_work() */ + +/** * n_hdlc_tty_wakeup - Callback for transmit wakeup * @tty: pointer to associated tty instance data *
@@ -344,7 +365,7 @@ static void n_hdlc_tty_wakeup(struct tty {struct n_hdlc *n_hdlc = tty->disc_data; -n_hdlc_send_frames (n_hdlc, tty); +schedule_work (&n_hdlc->write_work); }/* end of n_hdlc_tty_wakeup() */ /**
Greg Kroah-Hartman
maintainerPATCH 117/177 USB: NO_LPM quirk Lenovo USB-C to Ethernet Adapher(RTL8153-04)
In reply to Greg Kroah-HartmanFrom: Jimmy Wang <[email protected]>
commit 0ad3bd562bb91853b9f42bda145b5db6255aee90 upstream.
This device doesn't work well with LPM, losing connectivity intermittently. Disable LPM to resolve the issue.
--- drivers/usb/core/quirks.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/usb/core/quirks.c +3 -0
@@ -434,6 +434,9 @@ static const struct usb_device_id usb_qu { USB_DEVICE(0x1532, 0x0116), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Lenovo USB-C to Ethernet Adapter RTL8153-04 */ + { USB_DEVICE(0x17ef, 0x720c), .driver_info = USB_QUIRK_NO_LPM }, + /* Lenovo Powered USB-C Travel Hub (4X90S92381, RTL8153 GigE) */ { USB_DEVICE(0x17ef, 0x721e), .driver_info = USB_QUIRK_NO_LPM },
Greg Kroah-Hartman
maintainerPATCH 118/177 usb: dwc2: fix STM ID/VBUS detection startup delay in dwc2_driver_probe
In reply to Greg Kroah-HartmanFrom: Amelie Delaunay <[email protected]>
commit fac6bf87c55f7f0733efb0375565fb6a50cf2caf upstream.
When activate_stm_id_vb_detection is enabled, ID and Vbus detection relies on sensing comparators. This detection needs time to stabilize. A delay was already applied in dwc2_resume() when reactivating the detection, but it wasn't done in dwc2_probe().
This patch adds delay after enabling STM ID/VBUS detection. Then, ID state is good when initializing gadget and host, and avoid to get a wrong Connector ID Status Change interrupt.
--- drivers/usb/dwc2/platform.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/usb/dwc2/platform.c +3 -0
@@ -575,6 +575,9 @@ static int dwc2_driver_probe(struct plat ggpio |=GGPIO_STM32_OTG_GCCFG_IDEN ; ggpio |=GGPIO_STM32_OTG_GCCFG_VBDEN ;dwc2_writel (hsotg, ggpio,GGPIO ); + +/* ID/VBUS detection startup time */ +usleep_range (5000 ,7000 ); } retval =dwc2_drd_init (hsotg);
Greg Kroah-Hartman
maintainerPATCH 119/177 PCI/MSI: Clear PCI_MSIX_FLAGS_MASKALL on error
In reply to Greg Kroah-HartmanFrom: Thomas Gleixner <[email protected]>
commit 94185adbfad56815c2c8401e16d81bdb74a79201 upstream.
PCI_MSIX_FLAGS_MASKALL is set in the MSI-X control register at MSI-X interrupt setup time. It's cleared on success, but the error handling path only clears the PCI_MSIX_FLAGS_ENABLE bit.
That's incorrect as the reset state of the PCI_MSIX_FLAGS_MASKALL bit is zero. That can be observed via lspci:
Capabilities: [b0] MSI-X: Enable- Count=67 Masked+
Clear the bit in the error path to restore the reset state.
--- drivers/pci/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/pci/msi.c +1 -1
@@ -776,7 +776,7 @@ out_free:free_msi_irqs (dev); out_disable: -pci_msix_clear_and_set_ctrl (dev,PCI_MSIX_FLAGS_ENABLE ,0 ); +pci_msix_clear_and_set_ctrl (dev,PCI_MSIX_FLAGS_MASKALL |PCI_MSIX_FLAGS_ENABLE ,0 );return ret; }
Greg Kroah-Hartman
maintainerPATCH 120/177 PCI/MSI: Mask MSI-X vectors only on success
In reply to Greg Kroah-HartmanFrom: Stefan Roese <[email protected]>
commit 83dbf898a2d45289be875deb580e93050ba67529 upstream.
Masking all unused MSI-X entries is done to ensure that a crash kernel starts from a clean slate, which correponds to the reset state of the device as defined in the PCI-E specificion 3.0 and later:
Vector Control for MSI-X Table Entries
--------------------------------------
"00: Mask bit: When this bit is set, the function is prohibited from
sending a message using this MSI-X Table entry.
...
This bit’s state after reset is 1 (entry is masked)."
A Marvell NVME device fails to deliver MSI interrupts after trying to enable MSI-X interrupts due to that masking. It seems to take the MSI-X mask bits into account even when MSI-X is disabled.
While not specification compliant, this can be cured by moving the masking into the success path, so that the MSI-X table entries stay in device reset state when the MSI-X setup fails.
[ tglx: Move it into the success path, add comment and amend changelog ]
--- drivers/pci/msi.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
drivers/pci/msi.c +10 -3
@@ -721,9 +721,6 @@ static int msix_capability_init(struct p goto out_disable; } -/* Ensure that all table entries are masked. */ -msix_mask_all (base, tsize); - ret =msix_setup_entries (dev, base, entries, nvec, affd);if (ret) goto out_disable;
@@ -750,6 +747,16 @@ static int msix_capability_init(struct p/* Set MSI-X enabled bits and unmask the function */ pci_intx_for_msi (dev,0 ); dev->msix_enabled =1 ; + +/* +* Ensure that all table entries are masked to prevent +* stale entries from firing in a crash kernel. +* +* Done late to deal with a broken Marvell NVME device +* which takes the MSI-X mask bits into account even +* when MSI-X is disabled, which prevents MSI delivery. +*/ +msix_mask_all (base, tsize);pci_msix_clear_and_set_ctrl (dev,PCI_MSIX_FLAGS_MASKALL ,0 );pcibios_free_irq (dev);
Greg Kroah-Hartman
maintainerPATCH 121/177 usb: xhci-mtk: fix list_del warning when enable list debug
In reply to Greg Kroah-HartmanFrom: Chunfeng Yun <[email protected]>
commit ccc14c6cfd346e85c3ecb970975afd5132763437 upstream.
There is warning of 'list_del corruption' when enable list debug (CONFIG_DEBUG_LIST=y), fix it by using list_del_init()
--- drivers/usb/host/xhci-mtk-sch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/usb/host/xhci-mtk-sch.c +1 -1
@@ -781,7 +781,7 @@ int xhci_mtk_check_bandwidth(struct usb_ ret =xhci_check_bandwidth (hcd, udev);if (!ret) -INIT_LIST_HEAD (&mtk->bw_ep_chk_list); +list_del_init (&mtk->bw_ep_chk_list);return ret; }
Greg Kroah-Hartman
maintainerPATCH 122/177 usb: xhci: Extend support for runtime power management for AMDs Yellow carp.
In reply to Greg Kroah-HartmanFrom: Nehal Bakulchandra Shah <[email protected]>
commit f886d4fbb7c97b8f5f447c92d2dab99c841803c0 upstream.
AMD's Yellow Carp platform has few more XHCI controllers, enable the runtime power management support for the same.
--- drivers/usb/host/xhci-pci.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/usb/host/xhci-pci.c +5 -1
@@ -71,6 +71,8 @@#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 0x161e#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 0x15d6#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 0x15d7 +#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 0x161c +#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8 0x161f#define PCI_DEVICE_ID_ASMEDIA_1042_XHCI 0x1042#define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142
@@ -330,7 +332,9 @@ static void xhci_pci_quirks(struct devic pdev->device ==PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 || pdev->device ==PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 || pdev->device ==PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 || - pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6)) + pdev->device ==PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 || + pdev->device ==PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 || + pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8)) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;if (xhci->quirks &XHCI_RESET_ON_RESUME )
Greg Kroah-Hartman
maintainerPATCH 123/177 usb: cdnsp: Fix incorrect status for control request
In reply to Greg Kroah-HartmanFrom: Pawel Laszczak <[email protected]>
commit 99ea221f2e2f2743314e348b25c1e2574b467528 upstream.
Patch fixes incorrect status for control request.
Without this fix all usb_request objects were returned to upper drivers with usb_reqest->status field set to -EINPROGRESS.
--- drivers/usb/cdns3/cdnsp-ring.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/usb/cdns3/cdnsp-ring.c +2 -0
@@ -1029,6 +1029,8 @@ static void cdnsp_process_ctrl_td(structreturn ; } + *status =0 ; +cdnsp_finish_td (pdev, td, event, pep, status); }
Greg Kroah-Hartman
maintainerPATCH 124/177 usb: cdnsp: Fix incorrect calling of cdnsp_died function
In reply to Greg Kroah-HartmanFrom: Pawel Laszczak <[email protected]>
commit 16f00d969afe60e233c1a91af7ac840df60d3536 upstream.
Patch restrict calling of cdnsp_died function during removing modules or software disconnect.
This function was called because after transition controller to HALT state the driver starts handling the deferred interrupt. In this case such interrupt can be simple ignored.
--- drivers/usb/cdns3/cdnsp-ring.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/usb/cdns3/cdnsp-ring.c +8 -1
@@ -1525,7 +1525,14 @@ irqreturn_t cdnsp_thread_irq_handler(intspin_lock_irqsave (&pdev->lock, flags);if (pdev->cdnsp_state & (CDNSP_STATE_HALTED |CDNSP_STATE_DYING )) { -cdnsp_died (pdev); +/* +* While removing or stopping driver there may still be deferred +* not handled interrupt which should not be treated as error. +* Driver should simply ignore it. +*/ +if (pdev->gadget_driver) +cdnsp_died (pdev); +spin_unlock_irqrestore (&pdev->lock, flags);return IRQ_HANDLED ; }
Greg Kroah-Hartman
maintainerPATCH 125/177 usb: cdnsp: Fix issue in cdnsp_log_ep trace event
In reply to Greg Kroah-HartmanFrom: Pawel Laszczak <[email protected]>
commit 50931ba27d1665c8b038cd1d16c5869301f32fd6 upstream.
Patch fixes incorrect order of __entry->stream_id and __entry->state parameters in TP_printk macro.
--- drivers/usb/cdns3/cdnsp-trace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/usb/cdns3/cdnsp-trace.h +2 -2
@@ -57,9 +57,9 @@ DECLARE_EVENT_CLASS(cdnsp_log_ep, __entry->first_prime_det = pep->stream_info.first_prime_det; __entry->drbls_count = pep->stream_info.drbls_count; ), -TP_printk ("%s: SID: %08x ep state: %x stream: enabled: %d num %d " +TP_printk ("%s: SID: %08x, ep state: %x, stream: enabled: %d num %d " "tds %d, first prime: %d drbls %d" , -__get_str (name), __entry->state, __entry->stream_id, +__get_str (name), __entry->stream_id, __entry->state, __entry->enabled, __entry->num_streams, __entry->td_count, __entry->first_prime_det, __entry->drbls_count) );
Greg Kroah-Hartman
maintainerPATCH 126/177 usb: cdnsp: Fix lack of spin_lock_irqsave/spin_lock_restore
In reply to Greg Kroah-HartmanFrom: Pawel Laszczak <[email protected]>
commit 4c4e162d9cf38528c4f13df09d5755cbc06f6c77 upstream.
Patch puts content of cdnsp_gadget_pullup function inside spin_lock_irqsave and spin_lock_restore section.
This construction is required here to keep the data consistency, otherwise some data can be changed e.g. from interrupt context.
--- drivers/usb/cdns3/cdnsp-gadget.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
drivers/usb/cdns3/cdnsp-gadget.c +12 -0
@@ -1541,15 +1541,27 @@ static int cdnsp_gadget_pullup(struct us {struct cdnsp_device *pdev =gadget_to_cdnsp (gadget);struct cdns *cdns =dev_get_drvdata (pdev->dev); +unsigned long flags;trace_cdnsp_pullup (is_on); +/* +* Disable events handling while controller is being +* enabled/disabled. +*/ +disable_irq (cdns->dev_irq); +spin_lock_irqsave (&pdev->lock, flags); +if (!is_on) {cdnsp_reset_device (pdev);cdns_clear_vbus (cdns); }else {cdns_set_vbus (cdns); } + +spin_unlock_irqrestore (&pdev->lock, flags); +enable_irq (cdns->dev_irq); +return 0 ; }
Greg Kroah-Hartman
maintainerPATCH 127/177 usb: typec: tcpm: fix tcpm unregister port but leave a pending timer
In reply to Greg Kroah-HartmanFrom: Xu Yang <[email protected]>
commit ca4d8344a72b91fb9d4c8bfbc22204b4c09c5d8f upstream.
In current design, when the tcpm port is unregisterd, the kthread_worker will be destroyed in the last step. Inside the kthread_destroy_worker(), the worker will flush all the works and wait for them to end. However, if one of the works calls hrtimer_start(), this hrtimer will be pending until timeout even though tcpm port is removed. Once the hrtimer timeout, many strange kernel dumps appear.
Thus, we can first complete kthread_destroy_worker(), then cancel all the hrtimers. This will guarantee that no hrtimer is pending at the end.
--- drivers/usb/typec/tcpm/tcpm.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-)
drivers/usb/typec/tcpm/tcpm.c +13 -5
@@ -324,6 +324,7 @@ struct tcpm_port {bool attached;bool connected; +bool registered;bool pd_supported;enum typec_port_type port_type;
@@ -6291,7 +6292,8 @@ static enum hrtimer_restart state_machin { struct tcpm_port *port = container_of(timer, struct tcpm_port, state_machine_timer); -kthread_queue_work (port->wq, &port->state_machine); +if (port->registered) +kthread_queue_work (port->wq, &port->state_machine);return HRTIMER_NORESTART ; }
@@ -6299,7 +6301,8 @@ static enum hrtimer_restart vdm_state_ma { struct tcpm_port *port = container_of(timer, struct tcpm_port, vdm_state_machine_timer); -kthread_queue_work (port->wq, &port->vdm_state_machine); +if (port->registered) +kthread_queue_work (port->wq, &port->vdm_state_machine);return HRTIMER_NORESTART ; }
@@ -6307,7 +6310,8 @@ static enum hrtimer_restart enable_frs_t { struct tcpm_port *port = container_of(timer, struct tcpm_port, enable_frs_timer); -kthread_queue_work (port->wq, &port->enable_frs); +if (port->registered) +kthread_queue_work (port->wq, &port->enable_frs);return HRTIMER_NORESTART ; }
@@ -6315,7 +6319,8 @@ static enum hrtimer_restart send_discove { struct tcpm_port *port = container_of(timer, struct tcpm_port, send_discover_timer); -kthread_queue_work (port->wq, &port->send_discover_work); +if (port->registered) +kthread_queue_work (port->wq, &port->send_discover_work);return HRTIMER_NORESTART ; }
@@ -6403,6 +6408,7 @@ struct tcpm_port *tcpm_register_port(strtypec_port_register_altmodes (port->typec_port, &tcpm_altmode_ops, port, port->port_altmode,ALTMODE_DISCOVERY_MAX ); + port->registered = true;mutex_lock (&port->lock);tcpm_init (port);
@@ -6424,6 +6430,9 @@ void tcpm_unregister_port(struct tcpm_po {int i; + port->registered = false; +kthread_destroy_worker (port->wq); +hrtimer_cancel (&port->send_discover_timer);hrtimer_cancel (&port->enable_frs_timer);hrtimer_cancel (&port->vdm_state_machine_timer);
@@ -6435,7 +6444,6 @@ void tcpm_unregister_port(struct tcpm_potypec_unregister_port (port->typec_port);usb_role_switch_put (port->role_sw);tcpm_debugfs_exit (port); -kthread_destroy_worker (port->wq); }EXPORT_SYMBOL_GPL (tcpm_unregister_port);
Greg Kroah-Hartman
maintainerPATCH 128/177 usb: gadget: u_ether: fix race in setting MAC address in setup phase
In reply to Greg Kroah-HartmanFrom: Marian Postevca <[email protected]>
commit 890d5b40908bfd1a79be018d2d297cf9df60f4ee upstream.
When listening for notifications through netlink of a new interface being registered, sporadically, it is possible for the MAC to be read as zero. The zero MAC address lasts a short period of time and then switches to a valid random MAC address.
This causes problems for netd in Android, which assumes that the interface is malfunctioning and will not use it.
In the good case we get this log:InterfaceController::getCfg() ifName usb0
hwAddr 92:a8:f0:73:79:5b ipv4Addr 0.0.0.0 flags 0x1002
In the error case we get these logs:InterfaceController::getCfg() ifName usb0
hwAddr 00:00:00:00:00:00 ipv4Addr 0.0.0.0 flags 0x1002
netd : interfaceGetCfg("usb0")
netd : interfaceSetCfg() -> ServiceSpecificException
(99, "[Cannot assign requested address] : ioctl() failed")
The reason for the issue is the order in which the interface is setup, it is first registered through register_netdev() and after the MAC address is set.
Fixed by first setting the MAC address of the net_device and after that calling register_netdev().
--- drivers/usb/gadget/function/u_ether.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-)
drivers/usb/gadget/function/u_ether.c +6 -10
@@ -17,6 +17,7 @@#include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> +#include <linux/etherdevice.h> #include "u_ether.h"
@@ -861,19 +862,23 @@ int gether_register_netdev(struct net_de {struct eth_dev *dev;struct usb_gadget *g; -struct sockaddr sa;int status;if (!net->dev.parent)return -EINVAL ; dev =netdev_priv (net); g = dev->gadget; + + net->addr_assign_type =NET_ADDR_RANDOM ; +eth_hw_addr_set (net, dev->dev_mac); + status =register_netdev (net);if (status <0 ) {dev_dbg (&g->dev,"register_netdev failed, %d\n" , status);return status; }else {INFO (dev,"HOST MAC %pM\n" , dev->host_mac); +INFO (dev,"MAC %pM\n" , dev->dev_mac);/* two kinds of host-initiated state changes: * - iff DATA transfer is active, carrier is "on"
@@ -881,15 +886,6 @@ int gether_register_netdev(struct net_de*/ netif_carrier_off (net); } - sa.sa_family = net->type; -memcpy (sa.sa_data, dev->dev_mac,ETH_ALEN ); -rtnl_lock (); - status =dev_set_mac_address (net, &sa,NULL ); -rtnl_unlock (); -if (status) -pr_warn ("cannot set self ethernet address: %d\n" , status); -else -INFO (dev,"MAC %pM\n" , dev->dev_mac);return status; }
Greg Kroah-Hartman
maintainerPATCH 129/177 USB: serial: cp210x: fix CP2105 GPIO registration
In reply to Greg Kroah-HartmanFrom: Johan Hovold <[email protected]>
commit 83b67041f3eaf33f98a075249aa7f4c7617c2f85 upstream.
When generalising GPIO support and adding support for CP2102N, the GPIO registration for some CP2105 devices accidentally broke. Specifically, when all the pins of a port are in "modem" mode, and thus unavailable for GPIO use, the GPIO chip would now be registered without having initialised the number of GPIO lines. This would in turn be rejected by gpiolib and some errors messages would be printed (but importantly probe would still succeed).
Fix this by initialising the number of GPIO lines before registering the GPIO chip.
Note that as for the other device types, and as when all CP2105 pins are muxed for LED function, the GPIO chip is registered also when no pins are available for GPIO use.
--- drivers/usb/serial/cp210x.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/usb/serial/cp210x.c +4 -2
@@ -1682,6 +1682,8 @@ static int cp2105_gpioconf_init(struct u/* 2 banks of GPIO - One for the pins taken from each serial port */ if (intf_num ==0 ) { + priv->gc.ngpio =2 ; +if (mode.eci ==CP210X_PIN_MODE_MODEM ) {/* mark all GPIOs of this interface as reserved */ priv->gpio_altfunc =0xff ;
@@ -1692,8 +1694,9 @@ static int cp2105_gpioconf_init(struct u priv->gpio_pushpull = (u8)((le16_to_cpu (config.gpio_mode) &CP210X_ECI_GPIO_MODE_MASK ) >>CP210X_ECI_GPIO_MODE_OFFSET ); - priv->gc.ngpio =2 ; }else if (intf_num ==1 ) { + priv->gc.ngpio =3 ; +if (mode.sci ==CP210X_PIN_MODE_MODEM ) {/* mark all GPIOs of this interface as reserved */ priv->gpio_altfunc =0xff ;
@@ -1704,7 +1707,6 @@ static int cp2105_gpioconf_init(struct u priv->gpio_pushpull = (u8)((le16_to_cpu (config.gpio_mode) &CP210X_SCI_GPIO_MODE_MASK ) >>CP210X_SCI_GPIO_MODE_OFFSET ); - priv->gc.ngpio =3 ; }else {return -ENODEV ; }
Greg Kroah-Hartman
maintainerPATCH 130/177 USB: serial: option: add Telit FN990 compositions
In reply to Greg Kroah-HartmanFrom: Daniele Palmas <[email protected]>
commit 2b503c8598d1b232e7fc7526bce9326d92331541 upstream.
Add the following Telit FN990 compositions:
0x1070: tty, adb, rmnet, tty, tty, tty, tty 0x1071: tty, adb, mbim, tty, tty, tty, tty 0x1072: rndis, tty, adb, tty, tty, tty, tty 0x1073: tty, adb, ecm, tty, tty, tty, tty
--- drivers/usb/serial/option.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/usb/serial/option.c +8 -0
@@ -1219,6 +1219,14 @@ static const struct usb_device_id option .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff), /* Telit LN920 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff), /* Telit FN990 (rmnet) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff), /* Telit FN990 (MBIM) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff), /* Telit FN990 (RNDIS) */ + .driver_info = NCTRL(2) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */ + .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
Greg Kroah-Hartman
maintainerPATCH 131/177 selinux: fix sleeping function called from invalid context
In reply to Greg Kroah-HartmanFrom: Scott Mayhew <[email protected]>
commit cc274ae7763d9700a56659f3228641d7069e7a3f upstream.
selinux_sb_mnt_opts_compat() is called via sget_fc() under the sb_lock spinlock, so it can't use GFP_KERNEL allocations:
[ 868.565200] BUG: sleeping function called from invalid context at
include/linux/sched/mm.h:230
[ 868.568246] in_atomic(): 1, irqs_disabled(): 0,
non_block: 0, pid: 4914, name: mount.nfs
[ 868.569626] preempt_count: 1, expected: 0
[ 868.570215] RCU nest depth: 0, expected: 0
[ 868.570809] Preemption disabled at:
[ 868.570810] [<0000000000000000>] 0x0
[ 868.571848] CPU: 1 PID: 4914 Comm: mount.nfs Kdump: loaded
Tainted: G W 5.16.0-rc5.2585cf9dfa #1
[ 868.573273] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009),
BIOS 1.14.0-4.fc34 04/01/2014
[ 868.574478] Call Trace:
[ 868.574844] <TASK>
[ 868.575156] dump_stack_lvl+0x34/0x44
[ 868.575692] __might_resched.cold+0xd6/0x10f
[ 868.576308] slab_pre_alloc_hook.constprop.0+0x89/0xf0
[ 868.577046] __kmalloc_track_caller+0x72/0x420
[ 868.577684] ? security_context_to_sid_core+0x48/0x2b0
[ 868.578569] kmemdup_nul+0x22/0x50
[ 868.579108] security_context_to_sid_core+0x48/0x2b0
[ 868.579854] ? _nfs4_proc_pathconf+0xff/0x110 [nfsv4]
[ 868.580742] ? nfs_reconfigure+0x80/0x80 [nfs]
[ 868.581355] security_context_str_to_sid+0x36/0x40
[ 868.581960] selinux_sb_mnt_opts_compat+0xb5/0x1e0
[ 868.582550] ? nfs_reconfigure+0x80/0x80 [nfs]
[ 868.583098] security_sb_mnt_opts_compat+0x2a/0x40
[ 868.583676] nfs_compare_super+0x113/0x220 [nfs]
[ 868.584249] ? nfs_try_mount_request+0x210/0x210 [nfs]
[ 868.584879] sget_fc+0xb5/0x2f0
[ 868.585267] nfs_get_tree_common+0x91/0x4a0 [nfs]
[ 868.585834] vfs_get_tree+0x25/0xb0
[ 868.586241] fc_mount+0xe/0x30
[ 868.586605] do_nfs4_mount+0x130/0x380 [nfsv4]
[ 868.587160] nfs4_try_get_tree+0x47/0xb0 [nfsv4]
[ 868.587724] vfs_get_tree+0x25/0xb0
[ 868.588193] do_new_mount+0x176/0x310
[ 868.588782] __x64_sys_mount+0x103/0x140
[ 868.589388] do_syscall_64+0x3b/0x90
[ 868.589935] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 868.590699] RIP: 0033:0x7f2b371c6c4e
[ 868.591239] Code: 48 8b 0d dd 71 0e 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e
0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 49 89 ca b8 a5 00
00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d aa 71
0e 00 f7 d8 64 89 01 48
[ 868.593810] RSP: 002b:00007ffc83775d88 EFLAGS: 00000246
ORIG_RAX: 00000000000000a5
[ 868.594691] RAX: ffffffffffffffda RBX: 00007ffc83775f10 RCX: 00007f2b371c6c4e
[ 868.595504] RDX: 0000555d517247a0 RSI: 0000555d51724700 RDI: 0000555d51724540
[ 868.596317] RBP: 00007ffc83775f10 R08: 0000555d51726890 R09: 0000555d51726890
[ 868.597162] R10: 0000000000000000 R11: 0000000000000246 R12: 0000555d51726890
[ 868.598005] R13: 0000000000000003 R14: 0000555d517246e0 R15: 0000555d511ac925
[ 868.598826] </TASK>--- security/selinux/hooks.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-)
security/selinux/hooks.c +19 -14
@@ -611,10 +611,11 @@ static int bad_option(struct superblock_return 0 ; } -static int parse_sid (struct super_block *sb,const char *s,u32 *sid) +static int parse_sid (struct super_block *sb,const char *s,u32 *sid, +gfp_t gfp) {int rc =security_context_str_to_sid (&selinux_state, s, - sid,GFP_KERNEL ); + sid, gfp);if (rc) pr_warn("SELinux: security_context_str_to_sid" "(%s) failed for (dev %s, type %s) errno=%d\n",
@@ -685,7 +686,8 @@ static int selinux_set_mnt_opts(struct s*/ if (opts) {if (opts->fscontext) { - rc =parse_sid (sb, opts->fscontext, &fscontext_sid); + rc =parse_sid (sb, opts->fscontext, &fscontext_sid, +GFP_KERNEL );if (rc) goto out; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
@@ -694,7 +696,8 @@ static int selinux_set_mnt_opts(struct s sbsec->flags |=FSCONTEXT_MNT ; }if (opts->context) { - rc =parse_sid (sb, opts->context, &context_sid); + rc =parse_sid (sb, opts->context, &context_sid, +GFP_KERNEL );if (rc) goto out; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
@@ -703,7 +706,8 @@ static int selinux_set_mnt_opts(struct s sbsec->flags |=CONTEXT_MNT ; }if (opts->rootcontext) { - rc =parse_sid (sb, opts->rootcontext, &rootcontext_sid); + rc =parse_sid (sb, opts->rootcontext, &rootcontext_sid, +GFP_KERNEL );if (rc) goto out; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
@@ -712,7 +716,8 @@ static int selinux_set_mnt_opts(struct s sbsec->flags |=ROOTCONTEXT_MNT ; }if (opts->defcontext) { - rc =parse_sid (sb, opts->defcontext, &defcontext_sid); + rc =parse_sid (sb, opts->defcontext, &defcontext_sid, +GFP_KERNEL );if (rc) goto out; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
@@ -2701,14 +2706,14 @@ static int selinux_sb_mnt_opts_compat(streturn (sbsec->flags &SE_MNTMASK ) ?1 :0 ;if (opts->fscontext) { - rc =parse_sid (sb, opts->fscontext, &sid); + rc =parse_sid (sb, opts->fscontext, &sid,GFP_NOWAIT );if (rc)return 1 ;if (bad_option (sbsec,FSCONTEXT_MNT , sbsec->sid, sid))return 1 ; }if (opts->context) { - rc =parse_sid (sb, opts->context, &sid); + rc =parse_sid (sb, opts->context, &sid,GFP_NOWAIT );if (rc)return 1 ;if (bad_option (sbsec,CONTEXT_MNT , sbsec->mntpoint_sid, sid))
@@ -2718,14 +2723,14 @@ static int selinux_sb_mnt_opts_compat(ststruct inode_security_struct *root_isec; root_isec =backing_inode_security (sb->s_root); - rc =parse_sid (sb, opts->rootcontext, &sid); + rc =parse_sid (sb, opts->rootcontext, &sid,GFP_NOWAIT );if (rc)return 1 ;if (bad_option (sbsec,ROOTCONTEXT_MNT , root_isec->sid, sid))return 1 ; }if (opts->defcontext) { - rc =parse_sid (sb, opts->defcontext, &sid); + rc =parse_sid (sb, opts->defcontext, &sid,GFP_NOWAIT );if (rc)return 1 ;if (bad_option (sbsec,DEFCONTEXT_MNT , sbsec->def_sid, sid))
@@ -2748,14 +2753,14 @@ static int selinux_sb_remount(struct supreturn 0 ;if (opts->fscontext) { - rc =parse_sid (sb, opts->fscontext, &sid); + rc =parse_sid (sb, opts->fscontext, &sid,GFP_KERNEL );if (rc)return rc;if (bad_option (sbsec,FSCONTEXT_MNT , sbsec->sid, sid)) goto out_bad_option; }if (opts->context) { - rc =parse_sid (sb, opts->context, &sid); + rc =parse_sid (sb, opts->context, &sid,GFP_KERNEL );if (rc)return rc;if (bad_option (sbsec,CONTEXT_MNT , sbsec->mntpoint_sid, sid))
@@ -2764,14 +2769,14 @@ static int selinux_sb_remount(struct supif (opts->rootcontext) {struct inode_security_struct *root_isec; root_isec =backing_inode_security (sb->s_root); - rc =parse_sid (sb, opts->rootcontext, &sid); + rc =parse_sid (sb, opts->rootcontext, &sid,GFP_KERNEL );if (rc)return rc;if (bad_option (sbsec,ROOTCONTEXT_MNT , root_isec->sid, sid)) goto out_bad_option; }if (opts->defcontext) { - rc =parse_sid (sb, opts->defcontext, &sid); + rc =parse_sid (sb, opts->defcontext, &sid,GFP_KERNEL );if (rc)return rc;if (bad_option (sbsec,DEFCONTEXT_MNT , sbsec->def_sid, sid))
Greg Kroah-Hartman
maintainerPATCH 132/177 btrfs: fix memory leak in __add_inode_ref()
In reply to Greg Kroah-HartmanFrom: Jianglei Nie <[email protected]>
commit f35838a6930296fc1988764cfa54cb3f705c0665 upstream.
Line 1169 (#3) allocates a memory chunk for victim_name by kmalloc(), but when the function returns in line 1184 (#4) victim_name allocated by line 1169 (#3) is not freed, which will lead to a memory leak. There is a similar snippet of code in this function as allocating a memory chunk for victim_name in line 1104 (#1) as well as releasing the memory in line 1116 (#2).
We should kfree() victim_name when the return value of backref_in_log() is less than zero and before the function returns in line 1184 (#4).
1057 static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
1058 struct btrfs_root *root, 1059 struct btrfs_path *path, 1060 struct btrfs_root *log_root, 1061 struct btrfs_inode *dir, 1062 struct btrfs_inode *inode, 1063 u64 inode_objectid, u64 parent_objectid, 1064 u64 ref_index, char *name, int namelen, 1065 int *search_done)
1066 {
1104 victim_name = kmalloc(victim_name_len, GFP_NOFS); // #1: kmalloc (victim_name-1)
1105 if (!victim_name)
1106 return -ENOMEM;
1112 ret = backref_in_log(log_root, &search_key,
1113 parent_objectid, victim_name,
1114 victim_name_len);
1115 if (ret < 0) {
1116 kfree(victim_name); // #2: kfree (victim_name-1)
1117 return ret;
1118 } else if (!ret) {
1169 victim_name = kmalloc(victim_name_len, GFP_NOFS); // #3: kmalloc (victim_name-2)
1170 if (!victim_name)
1171 return -ENOMEM;
1180 ret = backref_in_log(log_root, &search_key,
1181 parent_objectid, victim_name,
1182 victim_name_len);
1183 if (ret < 0) {
1184 return ret; // #4: missing kfree (victim_name-2)
1185 } else if (!ret) {
1241 return 0;
1242 }
--- fs/btrfs/tree-log.c | 1 + 1 file changed, 1 insertion(+)
fs/btrfs/tree-log.c +1 -0
@@ -1153,6 +1153,7 @@ again: parent_objectid, victim_name, victim_name_len);if (ret <0 ) { +kfree (victim_name);return ret; }else if (!ret) { ret = -ENOENT ;
Greg Kroah-Hartman
maintainerPATCH 133/177 btrfs: fix double free of anon_dev after failure to create subvolume
In reply to Greg Kroah-HartmanFrom: Filipe Manana <[email protected]>
commit 33fab972497ae66822c0b6846d4f9382938575b6 upstream.
When creating a subvolume, at create_subvol(), we allocate an anonymous device and later call btrfs_get_new_fs_root(), which in turn just calls btrfs_get_root_ref(). There we call btrfs_init_fs_root() which assigns the anonymous device to the root, but if after that call there's an error, when we jump to 'fail' label, we call btrfs_put_root(), which frees the anonymous device and then returns an error that is propagated back to create_subvol(). Than create_subvol() frees the anonymous device again.
When this happens, if the anonymous device was not reallocated after the first time it was freed with btrfs_put_root(), we get a kernel message like the following:
(...)
[13950.282466] BTRFS: error (device dm-0) in create_subvol:663: errno=-5 IO failure [13950.283027] ida_free called for id=65 which is not allocated. [13950.285974] BTRFS info (device dm-0): forced readonly (...)
If the anonymous device gets reallocated by another btrfs filesystem or any other kernel subsystem, then bad things can happen.
So fix this by setting the root's anonymous device to 0 at btrfs_get_root_ref(), before we call btrfs_put_root(), if an error happened.
--- fs/btrfs/disk-io.c | 8 ++++++++ 1 file changed, 8 insertions(+)
fs/btrfs/disk-io.c +8 -0
@@ -1731,6 +1731,14 @@ again: }return root; fail: +/* +* If our caller provided us an anonymous device, then it's his +* responsability to free it in case we fail. So we have to set our +* root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() +* and once again by our caller. +*/ +if (anon_dev) + root->anon_dev =0 ;btrfs_put_root (root);return ERR_PTR (ret); }
Greg Kroah-Hartman
maintainerPATCH 134/177 btrfs: check WRITE_ERR when trying to read an extent buffer
In reply to Greg Kroah-HartmanFrom: Josef Bacik <[email protected]>
commit 651740a502411793327e2f0741104749c4eedcd1 upstream.
Filipe reported a hang when we have errors on btrfs. This turned out to be a side-effect of my fix c2e39305299f01 ("btrfs: clear extent buffer uptodate when we fail to write it") which made it so we clear EXTENT_BUFFER_UPTODATE on an eb when we fail to write it out.
Below is a paste of Filipe's analysis he got from using drgn to debug the hang
"""
btree readahead code calls read_extent_buffer_pages(), sets ->io_pages to a value while writeback of all pages has not yet completed:
--> writeback for the first 3 pages finishes, we clear
EXTENT_BUFFER_UPTODATE from eb on the first page when we get an error.
--> at this point eb->io_pages is 1 and we cleared Uptodate bit from the
first 3 pages
--> read_extent_buffer_pages() does not see EXTENT_BUFFER_UPTODATE() so
it continues, it's able to lock the pages since we obviously don't hold the pages locked during writeback
--> read_extent_buffer_pages() then computes 'num_reads' as 3, and sets
eb->io_pages to 3, since only the first page does not have Uptodate bit set at this point
--> writeback for the remaining page completes, we ended decrementing
eb->io_pages by 1, resulting in eb->io_pages == 2, and therefore never calling end_extent_buffer_writeback(), so EXTENT_BUFFER_WRITEBACK remains in the eb's flags
--> of course, when the read bio completes, it doesn't and shouldn't
call end_extent_buffer_writeback()
--> we should clear EXTENT_BUFFER_UPTODATE only after all pages of
the eb finished writeback? or maybe make the read pages code wait for writeback of all pages of the eb to complete before checking which pages need to be read, touch ->io_pages, submit read bio, etc
writeback bit never cleared means we can hang when aborting a transaction, at:
btrfs_cleanup_one_transaction()
btrfs_destroy_marked_extents()
wait_on_extent_buffer_writeback()
"""
This is a problem because our writes are not synchronized with reads in any way. We clear the UPTODATE flag and then we can easily come in and try to read the EB while we're still waiting on other bio's to complete.
We have two options here, we could lock all the pages, and then check to see if eb->io_pages != 0 to know if we've already got an outstanding write on the eb.
Or we can simply check to see if we have WRITE_ERR set on this extent buffer. We set this bit _before_ we clear UPTODATE, so if the read gets triggered because we aren't UPTODATE because of a write error we're guaranteed to have WRITE_ERR set, and in this case we can simply return -EIO. This will fix the reported hang.
--- fs/btrfs/extent_io.c | 8 ++++++++ 1 file changed, 8 insertions(+)
fs/btrfs/extent_io.c +8 -0
@@ -6547,6 +6547,14 @@ int read_extent_buffer_pages(struct exteif (test_bit (EXTENT_BUFFER_UPTODATE , &eb->bflags))return 0 ; +/* +* We could have had EXTENT_BUFFER_UPTODATE cleared by the write +* operation, which could potentially still be in flight. In this case +* we simply want to return an error. +*/ +if (unlikely (test_bit (EXTENT_BUFFER_WRITE_ERR , &eb->bflags))) +return -EIO ; +if (eb->fs_info->sectorsize <PAGE_SIZE )return read_extent_buffer_subpage (eb, wait, mirror_num);
Greg Kroah-Hartman
maintainerPATCH 135/177 btrfs: fix missing blkdev_put() call in btrfs_scan_one_device()
In reply to Greg Kroah-HartmanFrom: Shin'ichiro Kawasaki <[email protected]>
commit 4989d4a0aed3fb30f5b48787a689d7090de6f86d upstream.
The function btrfs_scan_one_device() calls blkdev_get_by_path() and blkdev_put() to get and release its target block device. However, when btrfs_sb_log_location_bdev() fails, blkdev_put() is not called and the block device is left without clean up. This triggered failure of fstests generic/085. Fix the failure path of btrfs_sb_log_location_bdev() to call blkdev_put().
--- fs/btrfs/volumes.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
fs/btrfs/volumes.c +4 -2
@@ -1366,8 +1366,10 @@ struct btrfs_device *btrfs_scan_one_devi bytenr_orig =btrfs_sb_offset (0 ); ret =btrfs_sb_log_location_bdev (bdev,0 ,READ , &bytenr); -if (ret) -return ERR_PTR (ret); +if (ret) { + device =ERR_PTR (ret); + goto error_bdev_put; + } disk_super =btrfs_read_disk_super (bdev, bytenr, bytenr_orig);if (IS_ERR (disk_super)) {
Greg Kroah-Hartman
maintainerPATCH 136/177 zonefs: add MODULE_ALIAS_FS
In reply to Greg Kroah-HartmanFrom: Naohiro Aota <[email protected]>
commit 8ffea2599f63fdbee968b894eab78170abf3ec2c upstream.
Add MODULE_ALIAS_FS() to load the module automatically when you do "mount -t zonefs".
--- fs/zonefs/super.c | 1 + 1 file changed, 1 insertion(+)
fs/zonefs/super.c +1 -0
@@ -1787,5 +1787,6 @@ static void __exit zonefs_exit(void)MODULE_AUTHOR ("Damien Le Moal" );MODULE_DESCRIPTION ("Zone file system for zoned block devices" );MODULE_LICENSE ("GPL" ); +MODULE_ALIAS_FS ("zonefs" );module_init (zonefs_init);module_exit (zonefs_exit);
Greg Kroah-Hartman
maintainerPATCH 137/177 iocost: Fix divide-by-zero on donation from low hweight cgroup
In reply to Greg Kroah-HartmanFrom: Tejun Heo <[email protected]>
commit edaa26334c117a584add6053f48d63a988d25a6e upstream.
The donation calculation logic assumes that the donor has non-zero after-donation hweight, so the lowest active hweight a donating cgroup can have is 2 so that it can donate 1 while keeping the other 1 for itself. Earlier, we only donated from cgroups with sizable surpluses so this condition was always true. However, with the precise donation algorithm implemented, f1de2439ec43 ("blk-iocost: revamp donation amount determination") made the donation amount calculation exact enabling even low hweight cgroups to donate.
This means that in rare occasions, a cgroup with active hweight of 1 can enter donation calculation triggering the following warning and then a divide-by-zero oops.
WARNING: CPU: 4 PID: 0 at block/blk-iocost.c:1928 transfer_surpluses.cold+0x0/0x53 [884/94867] ... RIP: 0010:transfer_surpluses.cold+0x0/0x53 Code: 92 ff 48 c7 c7 28 d1 ab b5 65 48 8b 34 25 00 ae 01 00 48 81 c6 90 06 00 00 e8 8b 3f fe ff 48 c7 c0 ea ff ff ff e9 95 ff 92 ff <0f> 0b 48 c7 c7 30 da ab b5 e8 71 3f fe ff 4c 89 e8 4d 85 ed 74 0 4 ... Call Trace: <IRQ> ioc_timer_fn+0x1043/0x1390 call_timer_fn+0xa1/0x2c0 __run_timers.part.0+0x1ec/0x2e0 run_timer_softirq+0x35/0x70 ... iocg: invalid donation weights in /a/b: active=1 donating=1 after=0
Fix it by excluding cgroups w/ active hweight < 2 from donating. Excluding these extreme low hweight donations shouldn't affect work conservation in any meaningful way.
--- block/blk-iocost.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
block/blk-iocost.c +8 -1
@@ -2311,7 +2311,14 @@ static void ioc_timer_fn(struct timer_li hwm =current_hweight_max (iocg); new_hwi =hweight_after_donation (iocg, old_hwi, hwm, usage, &now); -if (new_hwi < hwm) { +/* +* Donation calculation assumes hweight_after_donation +* to be positive, a condition that a donor w/ hwa < 2 +* can't meet. Don't bother with donation if hwa is +* below 2. It's not gonna make a meaningful difference +* anyway. +*/ +if (new_hwi < hwm && hwa >=2 ) { iocg->hweight_donating = hwa; iocg->hweight_after_donation = new_hwi;list_add (&iocg->surplus_list, &surpluses);
Greg Kroah-Hartman
maintainerPATCH 138/177 serial: 8250_fintek: Fix garbled text for console
In reply to Greg Kroah-HartmanFrom: Ji-Ze Hong (Peter Hong) <[email protected]>
commit 6c33ff728812aa18792afffaf2c9873b898e7512 upstream.
Commit fab8a02b73eb ("serial: 8250_fintek: Enable high speed mode on Fintek F81866") introduced support to use high baudrate with Fintek SuperIO UARTs. It'll change clocksources when the UART probed.
But when user add kernel parameter "console=ttyS0,115200 console=tty0" to make the UART as console output, the console will output garbled text after the following kernel message.
[ 3.681188] Serial: 8250/16550 driver, 32 ports, IRQ sharing enabled
The issue is occurs in following step:
probe_setup_port() -> fintek_8250_goto_highspeed()
It change clocksource from 115200 to 921600 with wrong time, it should change clocksource in set_termios() not in probed. The following 3 patches are implemented change clocksource in fintek_8250_set_termios().
Commit 58178914ae5b ("serial: 8250_fintek: UART dynamic clocksource on Fintek F81216H") Commit 195638b6d44f ("serial: 8250_fintek: UART dynamic clocksource on Fintek F81866") Commit 423d9118c624 ("serial: 8250_fintek: Add F81966 Support")
Due to the high baud rate had implemented above 3 patches and the patch Commit fab8a02b73eb ("serial: 8250_fintek: Enable high speed mode on Fintek F81866") is bugged, So this patch will remove it.
--- drivers/tty/serial/8250/8250_fintek.c | 20 -------------------- 1 file changed, 20 deletions(-)
drivers/tty/serial/8250/8250_fintek.c +0 -20
@@ -290,25 +290,6 @@ static void fintek_8250_set_max_fifo(str } } -static void fintek_8250_goto_highspeed (struct uart_8250_port *uart, -struct fintek_8250 *pdata) -{ -sio_write_reg (pdata,LDN , pdata->index); - -switch (pdata->pid) { -case CHIP_ID_F81966 : -case CHIP_ID_F81866 :/* set uart clock for high speed serial mode */ -sio_write_mask_reg (pdata,F81866_UART_CLK , -F81866_UART_CLK_MASK , -F81866_UART_CLK_14_769MHZ ); - - uart->port.uartclk =921600 *16 ; -break ; -default :/* leave clock speed untouched */ -break ; - } -} -static void fintek_8250_set_termios (struct uart_port *port,struct ktermios *termios,struct ktermios *old)
@@ -430,7 +411,6 @@ static int probe_setup_port(struct fintefintek_8250_set_irq_mode (pdata, level_mode);fintek_8250_set_max_fifo (pdata); -fintek_8250_goto_highspeed (uart, pdata);fintek_8250_exit_key (addr[i]);
Greg Kroah-Hartman
maintainerPATCH 139/177 timekeeping: Really make sure wall_to_monotonic isnt positive
In reply to Greg Kroah-HartmanFrom: Yu Liao <[email protected]>
commit 4e8c11b6b3f0b6a283e898344f154641eda94266 upstream.
Even after commit e1d7ba873555 ("time: Always make sure wall_to_monotonic isn't positive") it is still possible to make wall_to_monotonic positive by running the following code:
int main(void)
{
struct timespec time;
clock_gettime(CLOCK_MONOTONIC, &time);
time.tv_nsec = 0;
clock_settime(CLOCK_REALTIME, &time);
return 0;
}The reason is that the second parameter of timespec64_compare(), ts_delta, may be unnormalized because the delta is calculated with an open coded substraction which causes the comparison of tv_sec to yield the wrong result:
wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 }
ts_delta = { .tv_sec = -9, .tv_nsec = -900000000 }
That makes timespec64_compare() claim that wall_to_monotonic < ts_delta, but actually the result should be wall_to_monotonic > ts_delta.
After normalization, the result of timespec64_compare() is correct because the tv_sec comparison is not longer misleading:
wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 }
ts_delta = { .tv_sec = -10, .tv_nsec = 100000000 }
Use timespec64_sub() to ensure that ts_delta is normalized, which fixes the issue.
--- kernel/time/timekeeping.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
kernel/time/timekeeping.c +1 -2
@@ -1306,8 +1306,7 @@ int do_settimeofday64(const struct timestimekeeping_forward_now (tk); xt =tk_xtime (tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta =timespec64_sub (*ts, xt);if (timespec64_compare (&tk->wall_to_monotonic, &ts_delta) >0 ) { ret = -EINVAL ;
Greg Kroah-Hartman
maintainerPATCH 140/177 cifs: sanitize multiple delimiters in prepath
In reply to Greg Kroah-HartmanFrom: Thiago Rafael Becker <[email protected]>
commit a31080899d5fdafcccf7f39dd214a814a2c82626 upstream.
mount.cifs can pass a device with multiple delimiters in it. This will cause rename(2) to fail with ENOENT.
V2:
- Make sanitize_path more readable.
- Fix multiple delimiters between UNC and prepath.
- Avoid a memory leak if a bad user starts putting a lot of delimiters in the path on purpose.
--- fs/cifs/fs_context.c | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-)
fs/cifs/fs_context.c +37 -1
@@ -432,6 +432,42 @@ out: }/* +* Remove duplicate path delimiters. Windows is supposed to do that +* but there are some bugs that prevent rename from working if there are +* multiple delimiters. +* +* Returns a sanitized duplicate of @path. The caller is responsible for +* cleaning up the original. +*/ +#define IS_DELIM (c) ((c) == '/' || (c) == '\\') +static char *sanitize_path (char *path) +{ +char *cursor1 = path, *cursor2 = path; + +/* skip all prepended delimiters */ +while (IS_DELIM (*cursor1)) + cursor1++; + +/* copy the first letter */ + *cursor2 = *cursor1; + +/* copy the remainder... */ +while (*(cursor1++)) { +/* ... skipping all duplicated delimiters */ +if (IS_DELIM (*cursor1) &&IS_DELIM (*cursor2)) +continue ; + *(++cursor2) = *cursor1; + } + +/* if the last character is a delimiter, skip it */ +if (IS_DELIM (*(cursor2 -1 ))) + cursor2--; + + *(cursor2) ='\0' ; +return kstrdup (path,GFP_KERNEL ); +} + +/* * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath * fields with the result. Returns 0 on success and an error otherwise * (e.g. ENOMEM or EINVAL)
@@ -490,7 +526,7 @@ smb3_parse_devname(const char *devname,if (!*pos)return 0 ; - ctx->prepath =kstrdup (pos,GFP_KERNEL ); + ctx->prepath =sanitize_path (pos);if (!ctx->prepath)return -ENOMEM ;
Greg Kroah-Hartman
maintainerPATCH 141/177 locking/rtmutex: Fix incorrect condition in rtmutex_spin_on_owner()
In reply to Greg Kroah-HartmanFrom: Zqiang <[email protected]>
commit 8f556a326c93213927e683fc32bbf5be1b62540a upstream.
Optimistic spinning needs to be terminated when the spinning waiter is not longer the top waiter on the lock, but the condition is negated. It terminates if the waiter is the top waiter, which is defeating the whole purpose.
--- kernel/locking/rtmutex.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/locking/rtmutex.c +1 -1
@@ -1373,7 +1373,7 @@ static bool rtmutex_spin_on_owner(struct* - the VCPU on which owner runs is preempted */ if (!owner->on_cpu ||need_resched () || -rt_mutex_waiter_is_top_waiter (lock, waiter) || + !rt_mutex_waiter_is_top_waiter (lock, waiter) ||vcpu_is_preempted (task_cpu (owner))) { res = false;break ;
Greg Kroah-Hartman
maintainerPATCH 142/177 riscv: dts: unleashed: Add gpio card detect to mmc-spi-slot
In reply to Greg Kroah-HartmanFrom: Bin Meng <[email protected]>
commit 6331b8765cd0634a4e4cdcc1a6f1a74196616b94 upstream.
Per HiFive Unleashed schematics, the card detect signal of the micro SD card is connected to gpio pin #11, which should be reflected in the DT via the <gpios> property, as described in Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt.
--- arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts | 1 + 1 file changed, 1 insertion(+)
arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +1 -0
@@ -80,6 +80,7 @@ spi-max-frequency = <20000000>; voltage-ranges = <3300 3300>; disable-wp; + gpios = <&gpio 11 GPIO_ACTIVE_LOW>; }; };
Greg Kroah-Hartman
maintainerPATCH 143/177 riscv: dts: unmatched: Add gpio card detect to mmc-spi-slot
In reply to Greg Kroah-HartmanFrom: Bin Meng <[email protected]>
commit 298d03c2d7f1b5daacb6d4f4053fd3d677d67087 upstream.
Per HiFive Unmatched schematics, the card detect signal of the micro SD card is connected to gpio pin #15, which should be reflected in the DT via the <gpios> property, as described in Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt.
--- arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 2 ++ 1 file changed, 2 insertions(+)
arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +2 -0
@@ -2,6 +2,7 @@ /* Copyright (c) 2020 SiFive, Inc */ #include "fu740-c000.dtsi" +#include <dt-bindings/gpio/gpio.h> #include <dt-bindings/interrupt-controller/irq.h> /* Clock frequency (in Hz) of the PCB crystal for rtcclk */
@@ -228,6 +229,7 @@ spi-max-frequency = <20000000>; voltage-ranges = <3300 3300>; disable-wp; + gpios = <&gpio 15 GPIO_ACTIVE_LOW>; }; };
Greg Kroah-Hartman
maintainerPATCH 144/177 perf inject: Fix segfault due to close without open
In reply to Greg Kroah-HartmanFrom: Adrian Hunter <[email protected]>
commit 0c8e32fe48f549eef27c8c6b0a63530f83c3a643 upstream.
The fixed commit attempts to close inject.output even if it was never opened e.g.
$ perf record uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (7 samples) ] $ perf inject -i perf.data --vm-time-correlation=dry-run Segmentation fault (core dumped) $ gdb --quiet perf Reading symbols from perf... (gdb) r inject -i perf.data --vm-time-correlation=dry-run Starting program: /home/ahunter/bin/perf inject -i perf.data --vm-time-correlation=dry-run [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib/x86_64-linux-gnu/libthread_db.so.1".
Program received signal SIGSEGV, Segmentation fault. 0x00007eff8afeef5b in _IO_new_fclose (fp=0x0) at iofclose.c:48
48 iofclose.c: No such file or directory.
(gdb) bt
#0 0x00007eff8afeef5b in _IO_new_fclose (fp=0x0) at iofclose.c:48 #1 0x0000557fc7b74f92 in perf_data__close (data=data@entry=0x7ffcdafa6578) at util/data.c:376 #2 0x0000557fc7a6b807 in cmd_inject (argc=<optimized out>, argv=<optimized out>) at builtin-inject.c:1085 #3 0x0000557fc7ac4783 in run_builtin (p=0x557fc8074878 <commands+600>, argc=4, argv=0x7ffcdafb6a60) at perf.c:313 #4 0x0000557fc7a25d5c in handle_internal_command (argv=<optimized out>, argc=<optimized out>) at perf.c:365 #5 run_argv (argcp=<optimized out>, argv=<optimized out>) at perf.c:409 #6 main (argc=4, argv=0x7ffcdafb6a60) at perf.c:539
(gdb)
--- tools/perf/builtin-inject.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
tools/perf/builtin-inject.c +2 -1
@@ -1069,7 +1069,8 @@ out_delete:zstd_fini (&(inject.session->zstd_data));perf_session__delete (inject.session); out_close_output: -perf_data__close (&inject.output); +if (!inject.in_place_update) +perf_data__close (&inject.output);free (inject.itrace_synth_opts.vm_tm_corr_args);return ret; }
Greg Kroah-Hartman
maintainerPATCH 145/177 perf inject: Fix segfault due to perf_data__fd() without open
In reply to Greg Kroah-HartmanFrom: Adrian Hunter <[email protected]>
commit c271a55b0c6029fed0cac909fa57999a11467132 upstream.
The fixed commit attempts to get the output file descriptor even if the file was never opened e.g.
$ perf record uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.002 MB perf.data (7 samples) ] $ perf inject -i perf.data --vm-time-correlation=dry-run Segmentation fault (core dumped) $ gdb --quiet perf Reading symbols from perf... (gdb) r inject -i perf.data --vm-time-correlation=dry-run Starting program: /home/ahunter/bin/perf inject -i perf.data --vm-time-correlation=dry-run [Thread debugging using libthread_db enabled] Using host libthread_db library "/lib/x86_64-linux-gnu/libthread_db.so.1".
Program received signal SIGSEGV, Segmentation fault. __GI___fileno (fp=0x0) at fileno.c:35
35 fileno.c: No such file or directory.
(gdb) bt
#0 __GI___fileno (fp=0x0) at fileno.c:35 #1 0x00005621e48dd987 in perf_data__fd (data=0x7fff4c68bd08) at util/data.h:72 #2 perf_data__fd (data=0x7fff4c68bd08) at util/data.h:69 #3 cmd_inject (argc=<optimized out>, argv=0x7fff4c69c1f0) at builtin-inject.c:1017 #4 0x00005621e4936783 in run_builtin (p=0x5621e4ee6878 <commands+600>, argc=4, argv=0x7fff4c69c1f0) at perf.c:313 #5 0x00005621e4897d5c in handle_internal_command (argv=<optimized out>, argc=<optimized out>) at perf.c:365 #6 run_argv (argcp=<optimized out>, argv=<optimized out>) at perf.c:409 #7 main (argc=4, argv=0x7fff4c69c1f0) at perf.c:539
(gdb)
--- tools/perf/builtin-inject.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)
tools/perf/builtin-inject.c +7 -3
@@ -755,12 +755,16 @@ static int parse_vm_time_correlation(conreturn inject->itrace_synth_opts.vm_tm_corr_args ?0 : -ENOMEM ; } +static int output_fd (struct perf_inject *inject) +{ +return inject->in_place_update ?-1 :perf_data__fd (&inject->output); +} +static int __cmd_inject (struct perf_inject *inject) {int ret = -EINVAL ;struct perf_session *session = inject->session; -struct perf_data *data_out = &inject->output; -int fd = inject->in_place_update ?-1 :perf_data__fd (data_out); +int fd =output_fd (inject);u64 output_data_offset;signal (SIGINT , sig_handler);
@@ -1006,7 +1010,7 @@ int cmd_inject(int argc, const char **ar } inject.session =__perf_session__new (&data, repipe, -perf_data__fd (&inject.output), +output_fd (&inject), &inject.tool);if (IS_ERR (inject.session)) { ret =PTR_ERR (inject.session);
Greg Kroah-Hartman
maintainerPATCH 146/177 libata: if T_LENGTH is zero, dma direction should be DMA_NONE
In reply to Greg Kroah-HartmanFrom: George Kennedy <[email protected]>
commit 5da5231bb47864e5dd6c6731151e98b6ee498827 upstream.
Avoid data corruption by rejecting pass-through commands where T_LENGTH is zero (No data is transferred) and the dma direction is not DMA_NONE.
--- drivers/ata/libata-scsi.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-)
drivers/ata/libata-scsi.c +13 -2
@@ -2826,8 +2826,19 @@ static unsigned int ata_scsi_pass_thru(s goto invalid_fld; } -if (ata_is_ncq (tf->protocol) && (cdb[2 + cdb_offset] &0x3 ) ==0 ) - tf->protocol =ATA_PROT_NCQ_NODATA ; +if ((cdb[2 + cdb_offset] &0x3 ) ==0 ) { +/* +* When T_LENGTH is zero (No data is transferred), dir should +* be DMA_NONE. +*/ +if (scmd->sc_data_direction !=DMA_NONE ) { + fp =2 + cdb_offset; + goto invalid_fld; + } + +if (ata_is_ncq (tf->protocol)) + tf->protocol =ATA_PROT_NCQ_NODATA ; + }/* enable LBA */ tf->flags |=ATA_TFLAG_LBA ;
Greg Kroah-Hartman
maintainerPATCH 147/177 powerpc/module_64: Fix livepatching for RO modules
In reply to Greg Kroah-HartmanFrom: Russell Currey <[email protected]>
commit 8734b41b3efe0fc6082c1937b0e88556c396dc96 upstream.
Livepatching a loaded module involves applying relocations through apply_relocate_add(), which attempts to write to read-only memory when CONFIG_STRICT_MODULE_RWX=y. Work around this by performing these writes through the text poke area by using patch_instruction().
R_PPC_REL24 is the only relocation type generated by the kpatch-build userspace tool or klp-convert kernel tree that I observed applying a relocation to a post-init module.
A more comprehensive solution is planned, but using patch_instruction() for R_PPC_REL24 on should serve as a sufficient fix.
This does have a performance impact, I observed ~15% overhead in module_load() on POWER8 bare metal with checksum verification off.
--- arch/powerpc/kernel/module_64.c | 42 ++++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-)
arch/powerpc/kernel/module_64.c +34 -8
@@ -422,11 +422,17 @@ static inline int create_stub(const Elf6 const char *name) {long reladdr; +func_desc_t desc; +int i;if (is_mprofile_ftrace_call (name))return create_ftrace_stub (entry, addr, me); -memcpy (entry->jump, ppc64_stub_insns,sizeof (ppc64_stub_insns)); +for (i =0 ; i <sizeof (ppc64_stub_insns) /sizeof (u32); i++) { +if (patch_instruction (&entry->jump[i], +ppc_inst (ppc64_stub_insns[i]))) +return 0 ; + }/* Stub uses address relative to r2. */ reladdr = (unsigned long )entry -my_r2 (sechdrs, me);
@@ -437,10 +443,24 @@ static inline int create_stub(const Elf6 }pr_debug ("Stub %p get data from reladdr %li\n" , entry, reladdr); - entry->jump[0 ] |=PPC_HA (reladdr); - entry->jump[1 ] |=PPC_LO (reladdr); - entry->funcdata =func_desc (addr); - entry->magic =STUB_MAGIC ; +if (patch_instruction (&entry->jump[0 ], +ppc_inst (entry->jump[0 ] |PPC_HA (reladdr)))) +return 0 ; + +if (patch_instruction (&entry->jump[1 ], +ppc_inst (entry->jump[1 ] |PPC_LO (reladdr)))) +return 0 ; + +// func_desc_t is 8 bytes if ABIv2, else 16 bytes + desc =func_desc (addr); +for (i =0 ; i <sizeof (func_desc_t) /sizeof (u32); i++) { +if (patch_instruction (((u32 *)&entry->funcdata) + i, +ppc_inst (((u32 *)(&desc))[i]))) +return 0 ; + } + +if (patch_instruction (&entry->magic,ppc_inst (STUB_MAGIC ))) +return 0 ;return 1 ; }
@@ -495,8 +515,11 @@ static int restore_r2(const char *name, me->name, *instruction, instruction);return 0 ; } +/* ld r2,R2_STACK_OFFSET(r1) */ - *instruction =PPC_INST_LD_TOC ; +if (patch_instruction (instruction,ppc_inst (PPC_INST_LD_TOC ))) +return 0 ; +return 1 ; }
@@ -636,9 +659,12 @@ int apply_relocate_add(Elf64_Shdr *sechd }/* Only replace bits 2 through 26 */ - *(uint32_t *)location - = (*(uint32_t *)location & ~0x03fffffc ) + value = (*(uint32_t *)location & ~0x03fffffc ) | (value &0x03fffffc ); + +if (patch_instruction ((u32 *)location,ppc_inst (value))) +return -EFAULT ; +break ;case R_PPC64_REL64 :
Greg Kroah-Hartman
maintainerPATCH 148/177 drm/amdgpu: correct register access for RLC_JUMP_TABLE_RESTORE
In reply to Greg Kroah-HartmanFrom: Le Ma <[email protected]>
commit f3a8076eb28cae1553958c629aecec479394bbe2 upstream.
should count on GC IP base address
--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +2 -2
@@ -3061,8 +3061,8 @@ static void gfx_v9_0_init_pg(struct amdg AMD_PG_SUPPORT_CP | AMD_PG_SUPPORT_GDS | AMD_PG_SUPPORT_RLC_SMU_HS)) { -WREG32 (mmRLC_JUMP_TABLE_RESTORE, - adev->gfx.rlc.cp_table_gpu_addr >>8 ); +WREG32_SOC15 (GC ,0 , mmRLC_JUMP_TABLE_RESTORE, + adev->gfx.rlc.cp_table_gpu_addr >>8 );gfx_v9_0_init_gfx_power_gating (adev); } }
Greg Kroah-Hartman
maintainerPATCH 149/177 drm/amdgpu: dont override default ECO_BITs setting
In reply to Greg Kroah-HartmanFrom: Hawking Zhang <[email protected]>
commit 841933d5b8aa853abe68e63827f68f50fab37226 upstream.
Leave this bit as hardware default setting
--- drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 1 - drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c | 1 - drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c | 1 - drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 2 -- 8 files changed, 9 deletions(-)
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +0 -1
@@ -162,7 +162,6 @@ static void gfxhub_v1_0_init_tlb_regs(st ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); - tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,ECO_BITS ,0 ); tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* XXX for emulation. */ tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,ATC_EN ,1 );
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c +0 -1
@@ -196,7 +196,6 @@ static void gfxhub_v2_0_init_tlb_regs(st ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp =REG_SET_FIELD (tmp,GCMC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); - tmp =REG_SET_FIELD (tmp,GCMC_VM_MX_L1_TLB_CNTL ,ECO_BITS ,0 ); tmp =REG_SET_FIELD (tmp,GCMC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* UC, uncached */
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +0 -1
@@ -197,7 +197,6 @@ static void gfxhub_v2_1_init_tlb_regs(st ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp =REG_SET_FIELD (tmp,GCMC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); - tmp =REG_SET_FIELD (tmp,GCMC_VM_MX_L1_TLB_CNTL ,ECO_BITS ,0 ); tmp =REG_SET_FIELD (tmp,GCMC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* UC, uncached */
drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +0 -1
@@ -145,7 +145,6 @@ static void mmhub_v1_0_init_tlb_regs(str ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); - tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,ECO_BITS ,0 ); tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* XXX for emulation. */ tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,ATC_EN ,1 );
drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c +0 -1
@@ -165,7 +165,6 @@ static void mmhub_v1_7_init_tlb_regs(str ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); - tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,ECO_BITS ,0 ); tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* XXX for emulation. */ tmp =REG_SET_FIELD (tmp,MC_VM_MX_L1_TLB_CNTL ,ATC_EN ,1 );
drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +0 -1
@@ -269,7 +269,6 @@ static void mmhub_v2_0_init_tlb_regs(str ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp =REG_SET_FIELD (tmp,MMMC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); - tmp =REG_SET_FIELD (tmp,MMMC_VM_MX_L1_TLB_CNTL ,ECO_BITS ,0 ); tmp =REG_SET_FIELD (tmp,MMMC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* UC, uncached */
drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c +0 -1
@@ -194,7 +194,6 @@ static void mmhub_v2_3_init_tlb_regs(str ENABLE_ADVANCED_DRIVER_MODEL, 1); tmp =REG_SET_FIELD (tmp,MMMC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); - tmp =REG_SET_FIELD (tmp,MMMC_VM_MX_L1_TLB_CNTL ,ECO_BITS ,0 ); tmp =REG_SET_FIELD (tmp,MMMC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* UC, uncached */
drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c +0 -2
@@ -190,8 +190,6 @@ static void mmhub_v9_4_init_tlb_regs(str tmp =REG_SET_FIELD (tmp,VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL ,SYSTEM_APERTURE_UNMAPPED_ACCESS ,0 ); tmp =REG_SET_FIELD (tmp,VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL , -ECO_BITS ,0 ); - tmp =REG_SET_FIELD (tmp,VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL ,MTYPE ,MTYPE_UC );/* XXX for emulation. */ tmp =REG_SET_FIELD (tmp,VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL ,ATC_EN ,1 );
Greg Kroah-Hartman
maintainerPATCH 150/177 drm/amd/pm: fix reading SMU FW version from amdgpu_firmware_info on YC
In reply to Greg Kroah-HartmanFrom: Mario Limonciello <[email protected]>
commit dcd10d879a9d1d4e929d374c2f24aba8fac3252b upstream.
This value does not get cached into adev->pm.fw_version during startup for smu13 like it does for other SMU like smu12.
--- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +3 -0
@@ -197,6 +197,7 @@ int smu_v13_0_check_fw_status(struct smuint smu_v13_0_check_fw_version (struct smu_context *smu) { +struct amdgpu_device *adev = smu->adev;uint32_t if_version =0xff , smu_version =0xff ;uint16_t smu_major;uint8_t smu_minor, smu_debug;
@@ -209,6 +210,8 @@ int smu_v13_0_check_fw_version(struct sm smu_major = (smu_version >>16 ) &0xffff ; smu_minor = (smu_version >>8 ) &0xff ; smu_debug = (smu_version >>0 ) &0xff ; +if (smu->is_apu) + adev->pm.fw_version = smu_version;switch (smu->adev->asic_type) {case CHIP_ALDEBARAN :
Greg Kroah-Hartman
maintainerPATCH 151/177 Revert "can: m_can: remove support for custom bit timing"
In reply to Greg Kroah-HartmanFrom: Matthias Schiffer <[email protected]>
commit ea768b2ffec6cc9c3e17c37ef75d0539b8f89ff5 upstream.
The timing limits specified by the Elkhart Lake CPU datasheets do not match the defaults. Let's reintroduce the support for custom bit timings.
This reverts commit 0ddd83fbebbc5537f9d180d31f659db3564be708.
--- drivers/net/can/m_can/m_can.c | 24 ++++++++++++++++++------ drivers/net/can/m_can/m_can.h | 3 +++ 2 files changed, 21 insertions(+), 6 deletions(-)
drivers/net/can/m_can/m_can.c +18 -6
@@ -1494,20 +1494,32 @@ static int m_can_dev_setup(struct m_can_case 30 :/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */ can_set_static_ctrlmode (dev,CAN_CTRLMODE_FD_NON_ISO ); - cdev->can.bittiming_const = &m_can_bittiming_const_30X; - cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X; + cdev->can.bittiming_const = cdev->bit_timing ? + cdev->bit_timing : &m_can_bittiming_const_30X; + + cdev->can.data_bittiming_const = cdev->data_timing ? + cdev->data_timing : + &m_can_data_bittiming_const_30X;break ;case 31 :/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */ can_set_static_ctrlmode (dev,CAN_CTRLMODE_FD_NON_ISO ); - cdev->can.bittiming_const = &m_can_bittiming_const_31X; - cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = cdev->bit_timing ? + cdev->bit_timing : &m_can_bittiming_const_31X; + + cdev->can.data_bittiming_const = cdev->data_timing ? + cdev->data_timing : + &m_can_data_bittiming_const_31X;break ;case 32 :case 33 :/* Support both MCAN version v3.2.x and v3.3.0 */ - cdev->can.bittiming_const = &m_can_bittiming_const_31X; - cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = cdev->bit_timing ? + cdev->bit_timing : &m_can_bittiming_const_31X; + + cdev->can.data_bittiming_const = cdev->data_timing ? + cdev->data_timing : + &m_can_data_bittiming_const_31X; cdev->can.ctrlmode_supported |= (m_can_niso_supported(cdev) ?
drivers/net/can/m_can/m_can.h +3 -0
@@ -85,6 +85,9 @@ struct m_can_classdev {struct sk_buff *tx_skb;struct phy *transceiver; +struct can_bittiming_const *bit_timing; +struct can_bittiming_const *data_timing; +struct m_can_ops *ops;int version;
Greg Kroah-Hartman
maintainerPATCH 152/177 can: m_can: make custom bittiming fields const
In reply to Greg Kroah-HartmanFrom: Matthias Schiffer <[email protected]>
commit ea22ba40debee29ee7257c42002409899e9311c1 upstream.
The assigned timing structs will be defined a const anyway, so we can avoid a few casts by declaring the struct fields as const as well.
--- drivers/net/can/m_can/m_can.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/can/m_can/m_can.h +2 -2
@@ -85,8 +85,8 @@ struct m_can_classdev {struct sk_buff *tx_skb;struct phy *transceiver; -struct can_bittiming_const *bit_timing; -struct can_bittiming_const *data_timing; +const struct can_bittiming_const *bit_timing; +const struct can_bittiming_const *data_timing;struct m_can_ops *ops;
Greg Kroah-Hartman
maintainerPATCH 153/177 can: m_can: pci: use custom bit timings for Elkhart Lake
In reply to Greg Kroah-HartmanFrom: Matthias Schiffer <[email protected]>
commit ea4c1787685dbf9842046f05b6390b6901ee6ba2 upstream.
The relevant datasheet [1] specifies nonstandard limits for the bit timing parameters. While it is unclear what the exact effect of violating these limits is, it seems like a good idea to adhere to the documentation.
[1] Intel Atom® x6000E Series, and Intel® Pentium® and Celeron® N and J Series Processors for IoT Applications Datasheet,
Volume 2 (Book 3 of 3), July 2021, Revision 001
--- drivers/net/can/m_can/m_can_pci.c | 48 ++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-)
drivers/net/can/m_can/m_can_pci.c +44 -4
@@ -18,9 +18,14 @@#define M_CAN_PCI_MMIO_BAR 0 -#define M_CAN_CLOCK_FREQ_EHL 200000000#define CTL_CSR_INT_CTL_OFFSET 0x508 +struct m_can_pci_config { +const struct can_bittiming_const *bit_timing; +const struct can_bittiming_const *data_timing; +unsigned int clock_freq; +}; +struct m_can_pci_priv {struct m_can_classdev cdev;
@@ -84,9 +89,40 @@ static struct m_can_ops m_can_pci_ops = .read_fifo = iomap_read_fifo, }; +static const struct can_bittiming_const m_can_bittiming_const_ehl = { + .name =KBUILD_MODNAME , + .tseg1_min =2 ,/* Time segment 1 = prop_seg + phase_seg1 */ + .tseg1_max =64 , + .tseg2_min =1 ,/* Time segment 2 = phase_seg2 */ + .tseg2_max =128 , + .sjw_max =128 , + .brp_min =1 , + .brp_max =512 , + .brp_inc =1 , +}; + +static const struct can_bittiming_const m_can_data_bittiming_const_ehl = { + .name =KBUILD_MODNAME , + .tseg1_min =2 ,/* Time segment 1 = prop_seg + phase_seg1 */ + .tseg1_max =16 , + .tseg2_min =1 ,/* Time segment 2 = phase_seg2 */ + .tseg2_max =8 , + .sjw_max =4 , + .brp_min =1 , + .brp_max =32 , + .brp_inc =1 , +}; + +static const struct m_can_pci_config m_can_pci_ehl = { + .bit_timing = &m_can_bittiming_const_ehl, + .data_timing = &m_can_data_bittiming_const_ehl, + .clock_freq =200000000 , +}; +static int m_can_pci_probe (struct pci_dev *pci,const struct pci_device_id *id) {struct device *dev = &pci->dev; +const struct m_can_pci_config *cfg;struct m_can_classdev *mcan_class;struct m_can_pci_priv *priv;void __iomem *base;
@@ -114,6 +150,8 @@ static int m_can_pci_probe(struct pci_deif (!mcan_class)return -ENOMEM ; + cfg = (const struct m_can_pci_config *)id->driver_data; + priv =cdev_to_priv (mcan_class); priv->base = base;
@@ -125,7 +163,9 @@ static int m_can_pci_probe(struct pci_de mcan_class->dev = &pci->dev; mcan_class->net->irq =pci_irq_vector (pci,0 ); mcan_class->pm_clock_support =1 ; - mcan_class->can.clock.freq = id->driver_data; + mcan_class->bit_timing = cfg->bit_timing; + mcan_class->data_timing = cfg->data_timing; + mcan_class->can.clock.freq = cfg->clock_freq; mcan_class->ops = &m_can_pci_ops;pci_set_drvdata (pci, mcan_class);
@@ -178,8 +218,8 @@ static SIMPLE_DEV_PM_OPS(m_can_pci_pm_op m_can_pci_suspend, m_can_pci_resume);static const struct pci_device_id m_can_pci_id_table[] = { - {PCI_VDEVICE (INTEL ,0x4bc1 ),M_CAN_CLOCK_FREQ_EHL , }, - {PCI_VDEVICE (INTEL ,0x4bc2 ),M_CAN_CLOCK_FREQ_EHL , }, + {PCI_VDEVICE (INTEL ,0x4bc1 ), (kernel_ulong_t)&m_can_pci_ehl, }, + {PCI_VDEVICE (INTEL ,0x4bc2 ), (kernel_ulong_t)&m_can_pci_ehl, }, { }/* Terminating Entry */ };MODULE_DEVICE_TABLE (pci, m_can_pci_id_table);
Greg Kroah-Hartman
maintainerPATCH 154/177 ARM: dts: imx6ull-pinfunc: Fix CSI_DATA07__ESAI_TX0 pad name
In reply to Greg Kroah-HartmanFrom: Fabio Estevam <[email protected]>
commit 737e65c7956795b3553781fb7bc82fce1c39503f upstream.
According to the i.MX6ULL Reference Manual, pad CSI_DATA07 may have the ESAI_TX0 functionality, not ESAI_T0.
Also, NXP's i.MX Config Tools 10.0 generates dtsi with the MX6ULL_PAD_CSI_DATA07__ESAI_TX0 naming, so fix it accordingly.
There are no devicetree users in mainline that use the old name, so just remove the old entry.
--- arch/arm/boot/dts/imx6ull-pinfunc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm/boot/dts/imx6ull-pinfunc.h +1 -1
@@ -82,6 +82,6 @@#define MX6ULL_PAD_CSI_DATA04__ESAI_TX_FS 0x01F4 0x0480 0x0000 0x9 0x0#define MX6ULL_PAD_CSI_DATA05__ESAI_TX_CLK 0x01F8 0x0484 0x0000 0x9 0x0#define MX6ULL_PAD_CSI_DATA06__ESAI_TX5_RX0 0x01FC 0x0488 0x0000 0x9 0x0 -#define MX6ULL_PAD_CSI_DATA07__ESAI_T0 0x0200 0x048C 0x0000 0x9 0x0 +#define MX6ULL_PAD_CSI_DATA07__ESAI_TX0 0x0200 0x048C 0x0000 0x9 0x0#endif /* __DTS_IMX6ULL_PINFUNC_H */
Greg Kroah-Hartman
maintainerPATCH 155/177 xsk: Do not sleep in poll() when need_wakeup set
In reply to Greg Kroah-HartmanFrom: Magnus Karlsson <[email protected]>
commit bd0687c18e635b63233dc87f38058cd728802ab4 upstream.
Do not sleep in poll() when the need_wakeup flag is set. When this flag is set, the application needs to explicitly wake up the driver with a syscall (poll, recvmsg, sendmsg, etc.) to guarantee that Rx and/or Tx processing will be processed promptly. But the current code in poll(), sleeps first then wakes up the driver. This means that no driver processing will occur (baring any interrupts) until the timeout has expired.
Fix this by checking the need_wakeup flag first and if set, wake the driver and return to the application. Only if need_wakeup is not set should the process sleep if there is a timeout set in the poll() call.
--- net/xdp/xsk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/xdp/xsk.c +2 -2
@@ -692,8 +692,6 @@ static __poll_t xsk_poll(struct file *fistruct xdp_sock *xs =xdp_sk (sk);struct xsk_buff_pool *pool; -sock_poll_wait (file, sock, wait); -if (unlikely (!xsk_is_bound (xs)))return mask;
@@ -705,6 +703,8 @@ static __poll_t xsk_poll(struct file *fielse /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg (sk); + }else { +sock_poll_wait (file, sock, wait); }if (xs->rx && !xskq_prod_is_empty (xs->rx))
Greg Kroah-Hartman
maintainerPATCH 156/177 mptcp: add missing documented NL params
In reply to Greg Kroah-HartmanFrom: Matthieu Baerts <[email protected]>
commit 6813b1928758ce64fabbb8ef157f994b7c2235fa upstream.
'loc_id' and 'rem_id' are set in all events linked to subflows but those were missing in the events description in the comments.
--- include/uapi/linux/mptcp.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)
include/uapi/linux/mptcp.h +10 -8
@@ -129,19 +129,21 @@ struct mptcp_info {* MPTCP_EVENT_REMOVED: token, rem_id * An address has been lost by the peer. * -* MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, -* daddr4 | daddr6, sport, dport, backup, -* if_idx [, error] +* MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, +* saddr4 | saddr6, daddr4 | daddr6, sport, +* dport, backup, if_idx [, error] * A new subflow has been established. 'error' should not be set. * -* MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, -* sport, dport, backup, if_idx [, error] +* MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, +* daddr4 | daddr6, sport, dport, backup, if_idx +* [, error] * A subflow has been closed. An error (copy of sk_err) could be set if an * error has been detected for this subflow. * -* MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, -* sport, dport, backup, if_idx [, error] -* The priority of a subflow has changed. 'error' should not be set. +* MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, +* daddr4 | daddr6, sport, dport, backup, if_idx +* [, error] +* The priority of a subflow has changed. 'error' should not be set. */ enum mptcp_event_type {MPTCP_EVENT_UNSPEC =0 ,
Greg Kroah-Hartman
maintainerPATCH 157/177 bpf, x64: Factor out emission of REX byte in more cases
In reply to Greg Kroah-HartmanFrom: Jie Meng <[email protected]>
commit 6364d7d75a0e015a405d1f8a07f267f076c36ca6 upstream.
Introduce a single reg version of maybe_emit_mod() and factor out common code in more cases.
--- arch/x86/net/bpf_jit_comp.c | 50 ++++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 24 deletions(-)
arch/x86/net/bpf_jit_comp.c +26 -24
@@ -721,6 +721,20 @@ static void maybe_emit_mod(u8 **pprog, u *pprog = prog; } +/* +* Similar version of maybe_emit_mod() for a single register +*/ +static void maybe_emit_1mod (u8 **pprog,u32 reg,bool is64) +{ +u8 *prog = *pprog; + +if (is64) +EMIT1 (add_1mod (0x48 , reg)); +else if (is_ereg (reg)) +EMIT1 (add_1mod (0x40 , reg)); + *pprog = prog; +} +/* LDX: dst_reg = *(u8*)(src_reg + off) */ static void emit_ldx (u8 **pprog,u32 size,u32 dst_reg,u32 src_reg,int off) {
@@ -951,10 +965,8 @@ static int do_jit(struct bpf_prog *bpf_p/* neg dst */ case BPF_ALU |BPF_NEG :case BPF_ALU64 |BPF_NEG : -if (BPF_CLASS (insn->code) ==BPF_ALU64 ) -EMIT1 (add_1mod (0x48 , dst_reg)); -else if (is_ereg (dst_reg)) -EMIT1 (add_1mod (0x40 , dst_reg)); +maybe_emit_1mod (&prog, dst_reg, +BPF_CLASS (insn->code) ==BPF_ALU64 );EMIT2 (0xF7 ,add_1reg (0xD8 , dst_reg));break ;
@@ -968,10 +980,8 @@ static int do_jit(struct bpf_prog *bpf_pcase BPF_ALU64 |BPF_AND |BPF_K :case BPF_ALU64 |BPF_OR |BPF_K :case BPF_ALU64 |BPF_XOR |BPF_K : -if (BPF_CLASS (insn->code) ==BPF_ALU64 ) -EMIT1 (add_1mod (0x48 , dst_reg)); -else if (is_ereg (dst_reg)) -EMIT1 (add_1mod (0x40 , dst_reg)); +maybe_emit_1mod (&prog, dst_reg, +BPF_CLASS (insn->code) ==BPF_ALU64 );/* * b3 holds 'normal' opcode, b2 short form only valid
@@ -1112,10 +1122,8 @@ static int do_jit(struct bpf_prog *bpf_pcase BPF_ALU64 |BPF_LSH |BPF_K :case BPF_ALU64 |BPF_RSH |BPF_K :case BPF_ALU64 |BPF_ARSH |BPF_K : -if (BPF_CLASS (insn->code) ==BPF_ALU64 ) -EMIT1 (add_1mod (0x48 , dst_reg)); -else if (is_ereg (dst_reg)) -EMIT1 (add_1mod (0x40 , dst_reg)); +maybe_emit_1mod (&prog, dst_reg, +BPF_CLASS (insn->code) ==BPF_ALU64 ); b3 = simple_alu_opcodes[BPF_OP (insn->code)];if (imm32 ==1 )
@@ -1146,10 +1154,8 @@ static int do_jit(struct bpf_prog *bpf_p }/* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */ -if (BPF_CLASS (insn->code) ==BPF_ALU64 ) -EMIT1 (add_1mod (0x48 , dst_reg)); -else if (is_ereg (dst_reg)) -EMIT1 (add_1mod (0x40 , dst_reg)); +maybe_emit_1mod (&prog, dst_reg, +BPF_CLASS (insn->code) ==BPF_ALU64 ); b3 = simple_alu_opcodes[BPF_OP (insn->code)];EMIT2 (0xD3 ,add_1reg (b3, dst_reg));
@@ -1459,10 +1465,8 @@ st: if (is_imm8(insn->off))case BPF_JMP |BPF_JSET |BPF_K :case BPF_JMP32 |BPF_JSET |BPF_K :/* test dst_reg, imm32 */ -if (BPF_CLASS (insn->code) ==BPF_JMP ) -EMIT1 (add_1mod (0x48 , dst_reg)); -else if (is_ereg (dst_reg)) -EMIT1 (add_1mod (0x40 , dst_reg)); +maybe_emit_1mod (&prog, dst_reg, +BPF_CLASS (insn->code) ==BPF_JMP );EMIT2_off32 (0xF7 ,add_1reg (0xC0 , dst_reg), imm32); goto emit_cond_jmp;
@@ -1495,10 +1499,8 @@ st: if (is_imm8(insn->off)) }/* cmp dst_reg, imm8/32 */ -if (BPF_CLASS (insn->code) ==BPF_JMP ) -EMIT1 (add_1mod (0x48 , dst_reg)); -else if (is_ereg (dst_reg)) -EMIT1 (add_1mod (0x40 , dst_reg)); +maybe_emit_1mod (&prog, dst_reg, +BPF_CLASS (insn->code) ==BPF_JMP );if (is_imm8 (imm32))EMIT3 (0x83 ,add_1reg (0xF8 , dst_reg), imm32);
Greg Kroah-Hartman
maintainerPATCH 158/177 bpf: Fix extable address check.
In reply to Greg Kroah-HartmanFrom: Alexei Starovoitov <[email protected]>
commit 588a25e92458c6efeb7a261d5ca5726f5de89184 upstream.
The verifier checks that PTR_TO_BTF_ID pointer is either valid or NULL, but it cannot distinguish IS_ERR pointer from valid one.
When offset is added to IS_ERR pointer it may become small positive value which is a user address that is not handled by extable logic and has to be checked for at the runtime.
Tighten BPF_PROBE_MEM pointer check code to prevent this case.
--- arch/x86/net/bpf_jit_comp.c | 49 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 7 deletions(-)
arch/x86/net/bpf_jit_comp.c +42 -7
@@ -1280,19 +1280,54 @@ st: if (is_imm8(insn->off))case BPF_LDX |BPF_MEM |BPF_DW :case BPF_LDX |BPF_PROBE_MEM |BPF_DW :if (BPF_MODE (insn->code) ==BPF_PROBE_MEM ) { -/* test src_reg, src_reg */ -maybe_emit_mod (&prog, src_reg, src_reg, true);/* always 1 byte */ -EMIT2 (0x85 ,add_2reg (0xC0 , src_reg, src_reg)); -/* jne start_of_ldx */ -EMIT2 (X86_JNE ,0 ); +/* Though the verifier prevents negative insn->off in BPF_PROBE_MEM +* add abs(insn->off) to the limit to make sure that negative +* offset won't be an issue. +* insn->off is s16, so it won't affect valid pointers. +*/ +u64 limit =TASK_SIZE_MAX +PAGE_SIZE +abs (insn->off); +u8 *end_of_jmp1, *end_of_jmp2; + +/* Conservatively check that src_reg + insn->off is a kernel address: +* 1. src_reg + insn->off >= limit +* 2. src_reg + insn->off doesn't become small positive. +* Cannot do src_reg + insn->off >= limit in one branch, +* since it needs two spare registers, but JIT has only one. +*/ + +/* movabsq r11, limit */ +EMIT2 (add_1mod (0x48 ,AUX_REG ),add_1reg (0xB8 ,AUX_REG )); +EMIT ((u32 )limit,4 ); +EMIT (limit >>32 ,4 ); +/* cmp src_reg, r11 */ +maybe_emit_mod (&prog, src_reg,AUX_REG , true); +EMIT2 (0x39 ,add_2reg (0xC0 , src_reg,AUX_REG )); +/* if unsigned '<' goto end_of_jmp2 */ +EMIT2 (X86_JB ,0 ); + end_of_jmp1 = prog; + +/* mov r11, src_reg */ +emit_mov_reg (&prog, true,AUX_REG , src_reg); +/* add r11, insn->off */ +maybe_emit_1mod (&prog,AUX_REG , true); +EMIT2_off32 (0x81 ,add_1reg (0xC0 ,AUX_REG ), insn->off); +/* jmp if not carry to start_of_ldx +* Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr +* that has to be rejected. +*/ +EMIT2 (0x73 /* JNC */ ,0 ); + end_of_jmp2 = prog; +/* xor dst_reg, dst_reg */ emit_mov_imm32 (&prog, false, dst_reg,0 );/* jmp byte_after_ldx */ EMIT2 (0xEB ,0 ); -/* populate jmp_offset for JNE above */ - temp[4 ] = prog - temp -5 /* sizeof(test + jne) */ ; +/* populate jmp_offset for JB above to jump to xor dst_reg */ + end_of_jmp1[-1 ] = end_of_jmp2 - end_of_jmp1; +/* populate jmp_offset for JNC above to jump to start_of_ldx */ start_of_ldx = prog; + end_of_jmp2[-1 ] = start_of_ldx - end_of_jmp2; }emit_ldx (&prog,BPF_SIZE (insn->code), dst_reg, src_reg, insn->off);if (BPF_MODE (insn->code) ==BPF_PROBE_MEM ) {
Greg Kroah-Hartman
maintainerPATCH 159/177 USB: core: Make do_proc_control() and do_proc_bulk() killable
In reply to Greg Kroah-HartmanFrom: Alan Stern <[email protected]>
commit ae8709b296d80c7f45aa1f35c0e7659ad69edce1 upstream.
The USBDEVFS_CONTROL and USBDEVFS_BULK ioctls invoke usb_start_wait_urb(), which contains an uninterruptible wait with a user-specified timeout value. If timeout value is very large and the device being accessed does not respond in a reasonable amount of time, the kernel will complain about "Task X blocked for more than N seconds", as found in testing by syzbot:
INFO: task syz-executor.0:8700 blocked for more than 143 seconds.
Not tainted 5.14.0-rc7-syzkaller #0
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:syz-executor.0 state:D stack:23192 pid: 8700 ppid: 8455 flags:0x00004004
Call Trace:
context_switch kernel/sched/core.c:4681 [inline]
__schedule+0xc07/0x11f0 kernel/sched/core.c:5938
schedule+0x14b/0x210 kernel/sched/core.c:6017
schedule_timeout+0x98/0x2f0 kernel/time/timer.c:1857
do_wait_for_common+0x2da/0x480 kernel/sched/completion.c:85
__wait_for_common kernel/sched/completion.c:106 [inline]
wait_for_common kernel/sched/completion.c:117 [inline]
wait_for_completion_timeout+0x46/0x60 kernel/sched/completion.c:157
usb_start_wait_urb+0x167/0x550 drivers/usb/core/message.c:63
do_proc_bulk+0x978/0x1080 drivers/usb/core/devio.c:1236
proc_bulk drivers/usb/core/devio.c:1273 [inline]
usbdev_do_ioctl drivers/usb/core/devio.c:2547 [inline]
usbdev_ioctl+0x3441/0x6b10 drivers/usb/core/devio.c:2713...
To fix this problem, this patch replaces usbfs's calls to usb_control_msg() and usb_bulk_msg() with special-purpose code that does essentially the same thing (as recommended in the comment for usb_start_wait_urb()), except that it always uses a killable wait and it uses GFP_KERNEL rather than GFP_NOIO.
--- drivers/usb/core/devio.c | 144 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 111 insertions(+), 33 deletions(-)
drivers/usb/core/devio.c +111 -33
@@ -32,6 +32,7 @@#include <linux/usb.h> #include <linux/usbdevice_fs.h> #include <linux/usb/hcd.h> /* for usbcore internals */ +#include <linux/usb/quirks.h> #include <linux/cdev.h> #include <linux/notifier.h> #include <linux/security.h>
@@ -1102,14 +1103,55 @@ static int usbdev_release(struct inode *return 0 ; } +static void usbfs_blocking_completion (struct urb *urb) +{ +complete ((struct completion *) urb->context); +} + +/* +* Much like usb_start_wait_urb, but returns status separately from +* actual_length and uses a killable wait. +*/ +static int usbfs_start_wait_urb (struct urb *urb,int timeout, +unsigned int *actlen) +{ +DECLARE_COMPLETION_ONSTACK (ctx); +unsigned long expire; +int rc; + + urb->context = &ctx; + urb->complete = usbfs_blocking_completion; + *actlen =0 ; + rc =usb_submit_urb (urb,GFP_KERNEL ); +if (unlikely (rc)) +return rc; + + expire = (timeout ?msecs_to_jiffies (timeout) :MAX_SCHEDULE_TIMEOUT ); + rc =wait_for_completion_killable_timeout (&ctx, expire); +if (rc <=0 ) { +usb_kill_urb (urb); + *actlen = urb->actual_length; +if (urb->status != -ENOENT ) + ;/* Completed before it was killed */ +else if (rc <0 ) +return -EINTR ; +else +return -ETIMEDOUT ; + } + *actlen = urb->actual_length; +return urb->status; +} +static int do_proc_control (struct usb_dev_state *ps,struct usbdevfs_ctrltransfer *ctrl) {struct usb_device *dev = ps->dev;unsigned int tmo;unsigned char *tbuf; -unsigned wLength; +unsigned int wLength, actlen;int i, pipe, ret; +struct urb *urb =NULL ; +struct usb_ctrlrequest *dr =NULL ; ret =check_ctrlrecip (ps, ctrl->bRequestType, ctrl->bRequest, ctrl->wIndex);
@@ -1122,51 +1164,63 @@ static int do_proc_control(struct usb_de sizeof(struct usb_ctrlrequest));if (ret)return ret; + + ret = -ENOMEM ; tbuf = (unsigned char *)__get_free_page (GFP_KERNEL ); -if (!tbuf) { - ret = -ENOMEM ; +if (!tbuf) goto done; - } + urb =usb_alloc_urb (0 ,GFP_NOIO ); +if (!urb) + goto done; + dr =kmalloc (sizeof (struct usb_ctrlrequest ),GFP_NOIO ); +if (!dr) + goto done; + + dr->bRequestType = ctrl->bRequestType; + dr->bRequest = ctrl->bRequest; + dr->wValue =cpu_to_le16 (ctrl->wValue); + dr->wIndex =cpu_to_le16 (ctrl->wIndex); + dr->wLength =cpu_to_le16 (ctrl->wLength); + tmo = ctrl->timeout;snoop (&dev->dev,"control urb: bRequestType=%02x " "bRequest=%02x wValue=%04x " "wIndex=%04x wLength=%04x\n" , ctrl->bRequestType, ctrl->bRequest, ctrl->wValue, ctrl->wIndex, ctrl->wLength); -if ((ctrl->bRequestType &USB_DIR_IN ) && ctrl->wLength) { + +if ((ctrl->bRequestType &USB_DIR_IN ) && wLength) { pipe =usb_rcvctrlpipe (dev,0 ); -snoop_urb (dev,NULL , pipe, ctrl->wLength, tmo,SUBMIT ,NULL ,0 ); +usb_fill_control_urb (urb, dev, pipe, (unsigned char *) dr, tbuf, + wLength,NULL ,NULL ); +snoop_urb (dev,NULL , pipe, wLength, tmo,SUBMIT ,NULL ,0 );usb_unlock_device (dev); - i =usb_control_msg (dev, pipe, ctrl->bRequest, - ctrl->bRequestType, ctrl->wValue, ctrl->wIndex, - tbuf, ctrl->wLength, tmo); + i =usbfs_start_wait_urb (urb, tmo, &actlen);usb_lock_device (dev); -snoop_urb (dev,NULL , pipe,max (i,0 ),min (i,0 ),COMPLETE , - tbuf,max (i,0 )); -if ((i >0 ) && ctrl->wLength) { -if (copy_to_user (ctrl->data, tbuf, i)) { +snoop_urb (dev,NULL , pipe, actlen, i,COMPLETE , tbuf, actlen); +if (!i && actlen) { +if (copy_to_user (ctrl->data, tbuf, actlen)) { ret = -EFAULT ; - goto done; + goto recv_fault; } } }else { -if (ctrl->wLength) { -if (copy_from_user (tbuf, ctrl->data, ctrl->wLength)) { +if (wLength) { +if (copy_from_user (tbuf, ctrl->data, wLength)) { ret = -EFAULT ; goto done; } } pipe =usb_sndctrlpipe (dev,0 ); -snoop_urb (dev,NULL , pipe, ctrl->wLength, tmo,SUBMIT , - tbuf, ctrl->wLength); +usb_fill_control_urb (urb, dev, pipe, (unsigned char *) dr, tbuf, + wLength,NULL ,NULL ); +snoop_urb (dev,NULL , pipe, wLength, tmo,SUBMIT , tbuf, wLength);usb_unlock_device (dev); - i =usb_control_msg (dev, pipe, ctrl->bRequest, - ctrl->bRequestType, ctrl->wValue, ctrl->wIndex, - tbuf, ctrl->wLength, tmo); + i =usbfs_start_wait_urb (urb, tmo, &actlen);usb_lock_device (dev); -snoop_urb (dev,NULL , pipe,max (i,0 ),min (i,0 ),COMPLETE ,NULL ,0 ); +snoop_urb (dev,NULL , pipe, actlen, i,COMPLETE ,NULL ,0 ); }if (i <0 && i != -EPIPE ) { dev_printk(KERN_DEBUG, &dev->dev, "usbfs: USBDEVFS_CONTROL "
@@ -1174,8 +1228,15 @@ static int do_proc_control(struct usb_de current->comm, ctrl->bRequestType, ctrl->bRequest, ctrl->wLength, i); } - ret = i; + ret = (i <0 ? i : actlen); + + recv_fault: +/* Linger a bit, prior to the next control message. */ +if (dev->quirks &USB_QUIRK_DELAY_CTRL_MSG ) +msleep (200 ); done: +kfree (dr); +usb_free_urb (urb);free_page ((unsigned long ) tbuf);usbfs_decrease_memory_usage (PAGE_SIZE +sizeof (struct urb ) +sizeof (struct usb_ctrlrequest ));
@@ -1195,10 +1256,11 @@ static int do_proc_bulk(struct usb_dev_s struct usbdevfs_bulktransfer *bulk) {struct usb_device *dev = ps->dev; -unsigned int tmo, len1, pipe; -int len2; +unsigned int tmo, len1, len2, pipe;unsigned char *tbuf;int i, ret; +struct urb *urb =NULL ; +struct usb_host_endpoint *ep; ret =findintfep (ps->dev, bulk->ep);if (ret <0 )
@@ -1206,14 +1268,17 @@ static int do_proc_bulk(struct usb_dev_s ret =checkintf (ps, ret);if (ret)return ret; + + len1 = bulk->len; +if (len1 <0 || len1 >= (INT_MAX -sizeof (struct urb ))) +return -EINVAL ; +if (bulk->ep &USB_DIR_IN ) pipe =usb_rcvbulkpipe (dev, bulk->ep &0x7f );else pipe =usb_sndbulkpipe (dev, bulk->ep &0x7f ); -if (!usb_maxpacket (dev, pipe, !(bulk->ep &USB_DIR_IN ))) -return -EINVAL ; - len1 = bulk->len; -if (len1 >= (INT_MAX -sizeof (struct urb ))) + ep =usb_pipe_endpoint (dev, pipe); +if (!ep || !usb_endpoint_maxp (&ep->desc))return -EINVAL ; ret =usbfs_increase_memory_usage (len1 +sizeof (struct urb ));if (ret)
@@ -1223,17 +1288,29 @@ static int do_proc_bulk(struct usb_dev_s* len1 can be almost arbitrarily large. Don't WARN if it's * too big, just fail the request. */ + ret = -ENOMEM ; tbuf =kmalloc (len1,GFP_KERNEL | __GFP_NOWARN); -if (!tbuf) { - ret = -ENOMEM ; +if (!tbuf) goto done; + urb =usb_alloc_urb (0 ,GFP_KERNEL ); +if (!urb) + goto done; + +if ((ep->desc.bmAttributes &USB_ENDPOINT_XFERTYPE_MASK ) == +USB_ENDPOINT_XFER_INT ) { + pipe = (pipe & ~(3 <<30 )) | (PIPE_INTERRUPT <<30 ); +usb_fill_int_urb (urb, dev, pipe, tbuf, len1, +NULL ,NULL , ep->desc.bInterval); + }else { +usb_fill_bulk_urb (urb, dev, pipe, tbuf, len1,NULL ,NULL ); } + tmo = bulk->timeout;if (bulk->ep &0x80 ) {snoop_urb (dev,NULL , pipe, len1, tmo,SUBMIT ,NULL ,0 );usb_unlock_device (dev); - i =usb_bulk_msg (dev, pipe, tbuf, len1, &len2, tmo); + i =usbfs_start_wait_urb (urb, tmo, &len2);usb_lock_device (dev);snoop_urb (dev,NULL , pipe, len2, i,COMPLETE , tbuf, len2);
@@ -1253,12 +1330,13 @@ static int do_proc_bulk(struct usb_dev_ssnoop_urb (dev,NULL , pipe, len1, tmo,SUBMIT , tbuf, len1);usb_unlock_device (dev); - i =usb_bulk_msg (dev, pipe, tbuf, len1, &len2, tmo); + i =usbfs_start_wait_urb (urb, tmo, &len2);usb_lock_device (dev);snoop_urb (dev,NULL , pipe, len2, i,COMPLETE ,NULL ,0 ); } ret = (i <0 ? i : len2); done: +usb_free_urb (urb);kfree (tbuf);usbfs_decrease_memory_usage (len1 +sizeof (struct urb ));return ret;
Greg Kroah-Hartman
maintainerPATCH 160/177 media: mxl111sf: change mutex_init() location
In reply to Greg Kroah-HartmanFrom: Pavel Skripkin <[email protected]>
commit 44870a9e7a3c24acbb3f888b2a7cc22c9bdf7e7f upstream.
Syzbot reported, that mxl111sf_ctrl_msg() uses uninitialized mutex. The problem was in wrong mutex_init() location.
Previous mutex_init(&state->msg_lock) call was in ->init() function, but dvb_usbv2_init() has this order of calls:
dvb_usbv2_init() dvb_usbv2_adapter_init() dvb_usbv2_adapter_frontend_init() props->frontend_attach() props->init()
Since mxl111sf_* devices call mxl111sf_ctrl_msg() in ->frontend_attach() internally we need to initialize state->msg_lock before frontend_attach(). To achieve it, ->probe() call added to all mxl111sf_* devices, which will simply initiaize mutex.
--- drivers/media/usb/dvb-usb-v2/mxl111sf.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
drivers/media/usb/dvb-usb-v2/mxl111sf.c +14 -2
@@ -931,8 +931,6 @@ static int mxl111sf_init(struct dvb_usb_ .len = sizeof(eeprom), .buf = eeprom }, }; -mutex_init (&state->msg_lock); - ret =get_chip_info (state);if (mxl_fail (ret))pr_err ("failed to get chip info during probe" );
@@ -1074,6 +1072,14 @@ static int mxl111sf_get_stream_config_dvreturn 0 ; } +static int mxl111sf_probe (struct dvb_usb_device *dev) +{ +struct mxl111sf_state *state =d_to_priv (dev); + +mutex_init (&state->msg_lock); +return 0 ; +} +static struct dvb_usb_device_properties mxl111sf_props_dvbt = { .driver_name =KBUILD_MODNAME , .owner =THIS_MODULE ,
@@ -1083,6 +1089,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81, + .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_dvbt, .tuner_attach = mxl111sf_attach_tuner,
@@ -1124,6 +1131,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81, + .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_atsc, .tuner_attach = mxl111sf_attach_tuner,
@@ -1165,6 +1173,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81, + .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_mh, .tuner_attach = mxl111sf_attach_tuner,
@@ -1233,6 +1242,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81, + .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_atsc_mh, .tuner_attach = mxl111sf_attach_tuner,
@@ -1311,6 +1321,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81, + .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_mercury, .tuner_attach = mxl111sf_attach_tuner,
@@ -1381,6 +1392,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81, + .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_mercury_mh, .tuner_attach = mxl111sf_attach_tuner,
Greg Kroah-Hartman
maintainerPATCH 161/177 fuse: annotate lock in fuse_reverse_inval_entry()
In reply to Greg Kroah-HartmanFrom: Miklos Szeredi <[email protected]>
commit bda9a71980e083699a0360963c0135657b73f47a upstream.
Add missing inode lock annotatation; found by syzbot.
--- fs/fuse/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/fuse/dir.c +1 -1
@@ -1079,7 +1079,7 @@ int fuse_reverse_inval_entry(struct fuseif (!parent)return -ENOENT ; -inode_lock (parent); +inode_lock_nested (parent,I_MUTEX_PARENT );if (!S_ISDIR (parent->i_mode)) goto unlock;
Greg Kroah-Hartman
maintainerPATCH 162/177 ovl: fix warning in ovl_create_real()
In reply to Greg Kroah-HartmanFrom: Miklos Szeredi <[email protected]>
commit 1f5573cfe7a7056e80a92c7a037a3e69f3a13d1c upstream.
Syzbot triggered the following warning in ovl_workdir_create() -> ovl_create_real():
if (!err && WARN_ON(!newdentry->d_inode)) {The reason is that the cgroup2 filesystem returns from mkdir without instantiating the new dentry.
Weird filesystems such as this will be rejected by overlayfs at a later stage during setup, but to prevent such a warning, call ovl_mkdir_real() directly from ovl_workdir_create() and reject this case early.
--- fs/overlayfs/dir.c | 3 +-- fs/overlayfs/overlayfs.h | 1 + fs/overlayfs/super.c | 12 ++++++++---- 3 files changed, 10 insertions(+), 6 deletions(-)
fs/overlayfs/dir.c +1 -2
@@ -137,8 +137,7 @@ kill_whiteout: goto out; } -static int ovl_mkdir_real (struct inode *dir,struct dentry **newdentry, -umode_t mode) +int ovl_mkdir_real (struct inode *dir,struct dentry **newdentry,umode_t mode) {int err;struct dentry *d, *dentry = *newdentry;
fs/overlayfs/overlayfs.h +1 -0
@@ -570,6 +570,7 @@ struct ovl_cattr {#define OVL_CATTR (m) (&(struct ovl_cattr) { .mode = (m) }) +int ovl_mkdir_real (struct inode *dir,struct dentry **newdentry,umode_t mode);struct dentry *ovl_create_real (struct inode *dir,struct dentry *newdentry,struct ovl_cattr *attr);int ovl_cleanup (struct inode *dir,struct dentry *dentry);
fs/overlayfs/super.c +8 -4
@@ -787,10 +787,14 @@ retry: goto retry; } - work =ovl_create_real (dir, work,OVL_CATTR (attr.ia_mode)); - err =PTR_ERR (work); -if (IS_ERR (work)) - goto out_err; + err =ovl_mkdir_real (dir, &work, attr.ia_mode); +if (err) + goto out_dput; + +/* Weird filesystem returning with hashed negative (kernfs)? */ + err = -EINVAL ; +if (d_really_is_negative (work)) + goto out_dput;/* * Try to remove POSIX ACL xattrs from workdir. We are good if:
Greg Kroah-Hartman
maintainerPATCH 163/177 scsi: scsi_debug: Dont call kcalloc() if size arg is zero
In reply to Greg Kroah-HartmanFrom: George Kennedy <[email protected]>
commit 3344b58b53a76199dae48faa396e9fc37bf86992 upstream.
If the size arg to kcalloc() is zero, it returns ZERO_SIZE_PTR. Because of that, for a following NULL pointer check to work on the returned pointer, kcalloc() must not be called with the size arg equal to zero. Return early without error before the kcalloc() call if size arg is zero.
BUG: KASAN: null-ptr-deref in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: null-ptr-deref in sg_copy_buffer+0x138/0x240 lib/scatterlist.c:974 Write of size 4 at addr 0000000000000010 by task syz-executor.1/22789 CPU: 1 PID: 22789 Comm: syz-executor.1 Not tainted 5.15.0-syzk #1 Hardware name: Red Hat KVM, BIOS 1.13.0-2 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 __kasan_report mm/kasan/report.c:446 [inline] kasan_report.cold.14+0x112/0x117 mm/kasan/report.c:459 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x1a3/0x210 mm/kasan/generic.c:189 memcpy+0x3b/0x60 mm/kasan/shadow.c:66 memcpy include/linux/fortify-string.h:191 [inline] sg_copy_buffer+0x138/0x240 lib/scatterlist.c:974 do_dout_fetch drivers/scsi/scsi_debug.c:2954 [inline] do_dout_fetch drivers/scsi/scsi_debug.c:2946 [inline] resp_verify+0x49e/0x930 drivers/scsi/scsi_debug.c:4276 schedule_resp+0x4d8/0x1a70 drivers/scsi/scsi_debug.c:5478 scsi_debug_queuecommand+0x8c9/0x1ec0 drivers/scsi/scsi_debug.c:7533 scsi_dispatch_cmd drivers/scsi/scsi_lib.c:1520 [inline] scsi_queue_rq+0x16b0/0x2d40 drivers/scsi/scsi_lib.c:1699 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1639 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1761 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1838 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:62 blk_execute_rq+0xdb/0x360 block/blk-exec.c:102 sg_scsi_ioctl drivers/scsi/scsi_ioctl.c:621 [inline] scsi_ioctl+0x8bb/0x15c0 drivers/scsi/scsi_ioctl.c:930 sg_ioctl_common+0x172d/0x2710 drivers/scsi/sg.c:1112 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1165 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
--- drivers/scsi/scsi_debug.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/scsi/scsi_debug.c +4 -0
@@ -4259,6 +4259,8 @@ static int resp_verify(struct scsi_cmndmk_sense_invalid_opcode (scp);return check_condition_result; } +if (vnum ==0 ) +return 0 ;/* not an error */ a_num = is_bytchk3 ?1 : vnum;/* Treat following check like one for read (i.e. no write) access */ ret =check_device_access_params (scp, lba, a_num, false);
@@ -4322,6 +4324,8 @@ static int resp_report_zones(struct scsi } zs_lba =get_unaligned_be64 (cmd +2 ); alloc_len =get_unaligned_be32 (cmd +10 ); +if (alloc_len ==0 ) +return 0 ;/* not an error */ rep_opts = cmd[14 ] &0x3f ; partial = cmd[14 ] &0x80 ;
Greg Kroah-Hartman
maintainerPATCH 164/177 scsi: scsi_debug: Fix type in min_t to avoid stack OOB
In reply to Greg Kroah-HartmanFrom: George Kennedy <[email protected]>
commit 36e07d7ede88a1f1ef8f0f209af5b7612324ac2c upstream.
Change min_t() to use type "u32" instead of type "int" to avoid stack out of bounds. With min_t() type "int" the values get sign extended and the larger value gets used causing stack out of bounds.
BUG: KASAN: stack-out-of-bounds in memcpy include/linux/fortify-string.h:191 [inline] BUG: KASAN: stack-out-of-bounds in sg_copy_buffer+0x1de/0x240 lib/scatterlist.c:976 Read of size 127 at addr ffff888072607128 by task syz-executor.7/18707 CPU: 1 PID: 18707 Comm: syz-executor.7 Not tainted 5.15.0-syzk #1 Hardware name: Red Hat KVM, BIOS 1.13.0-2 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold.14+0x7d/0x117 mm/kasan/report.c:459 check_region_inline mm/kasan/generic.c:183 [inline] kasan_check_range+0x1a3/0x210 mm/kasan/generic.c:189 memcpy+0x23/0x60 mm/kasan/shadow.c:65 memcpy include/linux/fortify-string.h:191 [inline] sg_copy_buffer+0x1de/0x240 lib/scatterlist.c:976 sg_copy_from_buffer+0x33/0x40 lib/scatterlist.c:1000 fill_from_dev_buffer.part.34+0x82/0x130 drivers/scsi/scsi_debug.c:1162 fill_from_dev_buffer drivers/scsi/scsi_debug.c:1888 [inline] resp_readcap16+0x365/0x3b0 drivers/scsi/scsi_debug.c:1887 schedule_resp+0x4d8/0x1a70 drivers/scsi/scsi_debug.c:5478 scsi_debug_queuecommand+0x8c9/0x1ec0 drivers/scsi/scsi_debug.c:7533 scsi_dispatch_cmd drivers/scsi/scsi_lib.c:1520 [inline] scsi_queue_rq+0x16b0/0x2d40 drivers/scsi/scsi_lib.c:1699 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1639 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1761 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1838 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:62 sg_common_write.isra.18+0xeb3/0x2000 drivers/scsi/sg.c:836 sg_new_write.isra.19+0x570/0x8c0 drivers/scsi/sg.c:774 sg_ioctl_common+0x14d6/0x2710 drivers/scsi/sg.c:939 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1165 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae
--- drivers/scsi/scsi_debug.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-)
drivers/scsi/scsi_debug.c +19 -15
@@ -1189,7 +1189,7 @@ static int p_fill_from_dev_buffer(struct __func__, off_dst,scsi_bufflen (scp), act_len, scsi_get_resid(scp)); n =scsi_bufflen (scp) - (off_dst + act_len); -scsi_set_resid (scp,min_t (int,scsi_get_resid (scp), n)); +scsi_set_resid (scp,min_t (u32,scsi_get_resid (scp), n));return 0 ; }
@@ -1562,7 +1562,8 @@ static int resp_inquiry(struct scsi_cmndunsigned char pq_pdt;unsigned char *arr;unsigned char *cmd = scp->cmnd; -int alloc_len, n, ret; +u32 alloc_len, n; +int ret;bool have_wlun, is_disk, is_zbc, is_disk_zbc; alloc_len =get_unaligned_be16 (cmd +3 );
@@ -1585,7 +1586,8 @@ static int resp_inquiry(struct scsi_cmndkfree (arr);return check_condition_result; }else if (0x1 & cmd[1 ]) {/* EVPD bit set */ -int lu_id_num, port_group_id, target_dev_id, len; +int lu_id_num, port_group_id, target_dev_id; +u32 len;char lu_id_str[6 ];int host_no = devip->sdbg_host->shost->host_no;
@@ -1676,9 +1678,9 @@ static int resp_inquiry(struct scsi_cmndkfree (arr);return check_condition_result; } - len =min (get_unaligned_be16 (arr +2 ) +4 , alloc_len); + len =min_t (u32,get_unaligned_be16 (arr +2 ) +4 , alloc_len); ret =fill_from_dev_buffer (scp, arr, -min (len,SDEBUG_MAX_INQ_ARR_SZ )); +min_t (u32, len,SDEBUG_MAX_INQ_ARR_SZ ));kfree (arr);return ret; }
@@ -1714,7 +1716,7 @@ static int resp_inquiry(struct scsi_cmnd }put_unaligned_be16 (0x2100 , arr + n);/* SPL-4 no version claimed */ ret =fill_from_dev_buffer (scp, arr, -min_t (int, alloc_len,SDEBUG_LONG_INQ_SZ )); +min_t (u32, alloc_len,SDEBUG_LONG_INQ_SZ ));kfree (arr);return ret; }
@@ -1729,8 +1731,8 @@ static int resp_requests(struct scsi_cmnunsigned char *cmd = scp->cmnd;unsigned char arr[SCSI_SENSE_BUFFERSIZE ];/* assume >= 18 bytes */ bool dsense = !!(cmd[1 ] &1 ); -int alloc_len = cmd[4 ]; -int len =18 ; +u32 alloc_len = cmd[4 ]; +u32 len =18 ;int stopped_state =atomic_read (&devip->stopped);memset (arr,0 ,sizeof (arr));
@@ -1774,7 +1776,7 @@ static int resp_requests(struct scsi_cmn arr[7 ] =0xa ; } } -return fill_from_dev_buffer (scp, arr,min_t (int, len, alloc_len)); +return fill_from_dev_buffer (scp, arr,min_t (u32, len, alloc_len)); }static int resp_start_stop (struct scsi_cmnd *scp,struct sdebug_dev_info *devip)
@@ -2312,7 +2314,8 @@ static int resp_mode_sense(struct scsi_c {int pcontrol, pcode, subpcode, bd_len;unsigned char dev_spec; -int alloc_len, offset, len, target_dev_id; +u32 alloc_len, offset, len; +int target_dev_id;int target = scp->device->id;unsigned char *ap;unsigned char arr[SDEBUG_MAX_MSENSE_SZ ];
@@ -2468,7 +2471,7 @@ static int resp_mode_sense(struct scsi_c arr[0 ] = offset -1 ; else put_unaligned_be16((offset - 2), arr + 0); -return fill_from_dev_buffer (scp, arr,min_t (int, alloc_len, offset)); +return fill_from_dev_buffer (scp, arr,min_t (u32, alloc_len, offset)); }#define SDEBUG_MAX_MSELECT_SZ 512
@@ -2583,7 +2586,8 @@ static int resp_ie_l_pg(unsigned char *astatic int resp_log_sense (struct scsi_cmnd *scp,struct sdebug_dev_info *devip) { -int ppc, sp, pcode, subpcode, alloc_len, len, n; +int ppc, sp, pcode, subpcode; +u32 alloc_len, len, n;unsigned char arr[SDEBUG_MAX_LSENSE_SZ ];unsigned char *cmd = scp->cmnd;
@@ -2653,9 +2657,9 @@ static int resp_log_sense(struct scsi_cmmk_sense_invalid_fld (scp,SDEB_IN_CDB ,3 ,-1 );return check_condition_result; } - len =min_t (int,get_unaligned_be16 (arr +2 ) +4 , alloc_len); + len =min_t (u32,get_unaligned_be16 (arr +2 ) +4 , alloc_len);return fill_from_dev_buffer (scp, arr, -min_t (int, len,SDEBUG_MAX_INQ_ARR_SZ )); +min_t (u32, len,SDEBUG_MAX_INQ_ARR_SZ )); }static inline bool sdebug_dev_is_zoned (struct sdebug_dev_info *devip)
@@ -4430,7 +4434,7 @@ static int resp_report_zones(struct scsiput_unaligned_be64 (sdebug_capacity -1 , arr +8 ); rep_len = (unsigned long )desc - (unsigned long )arr; - ret =fill_from_dev_buffer (scp, arr,min_t (int, alloc_len, rep_len)); + ret =fill_from_dev_buffer (scp, arr,min_t (u32, alloc_len, rep_len)); fini:read_unlock (macc_lckp);
Greg Kroah-Hartman
maintainerPATCH 165/177 scsi: scsi_debug: Sanity check block descriptor length in resp_mode_select()
In reply to Greg Kroah-HartmanFrom: George Kennedy <[email protected]>
commit e0a2c28da11e2c2b963fc01d50acbf03045ac732 upstream.
In resp_mode_select() sanity check the block descriptor len to avoid UAF.
BUG: KASAN: use-after-free in resp_mode_select+0xa4c/0xb40 drivers/scsi/scsi_debug.c:2509 Read of size 1 at addr ffff888026670f50 by task scsicmd/15032 CPU: 1 PID: 15032 Comm: scsicmd Not tainted 5.15.0-01d0625 #15 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Call Trace: <TASK> dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:107 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:257 kasan_report.cold.14+0x7d/0x117 mm/kasan/report.c:443 __asan_report_load1_noabort+0x14/0x20 mm/kasan/report_generic.c:306 resp_mode_select+0xa4c/0xb40 drivers/scsi/scsi_debug.c:2509 schedule_resp+0x4af/0x1a10 drivers/scsi/scsi_debug.c:5483 scsi_debug_queuecommand+0x8c9/0x1e70 drivers/scsi/scsi_debug.c:7537 scsi_queue_rq+0x16b4/0x2d10 drivers/scsi/scsi_lib.c:1521 blk_mq_dispatch_rq_list+0xb9b/0x2700 block/blk-mq.c:1640 __blk_mq_sched_dispatch_requests+0x28f/0x590 block/blk-mq-sched.c:325 blk_mq_sched_dispatch_requests+0x105/0x190 block/blk-mq-sched.c:358 __blk_mq_run_hw_queue+0xe5/0x150 block/blk-mq.c:1762 __blk_mq_delay_run_hw_queue+0x4f8/0x5c0 block/blk-mq.c:1839 blk_mq_run_hw_queue+0x18d/0x350 block/blk-mq.c:1891 blk_mq_sched_insert_request+0x3db/0x4e0 block/blk-mq-sched.c:474 blk_execute_rq_nowait+0x16b/0x1c0 block/blk-exec.c:63 sg_common_write.isra.18+0xeb3/0x2000 drivers/scsi/sg.c:837 sg_new_write.isra.19+0x570/0x8c0 drivers/scsi/sg.c:775 sg_ioctl_common+0x14d6/0x2710 drivers/scsi/sg.c:941 sg_ioctl+0xa2/0x180 drivers/scsi/sg.c:1166 __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:52 do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:50 entry_SYSCALL_64_after_hwframe+0x44/0xae arch/x86/entry/entry_64.S:113
--- drivers/scsi/scsi_debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/scsi/scsi_debug.c +2 -2
@@ -2502,11 +2502,11 @@ static int resp_mode_select(struct scsi_ __func__, param_len, res); md_len = mselect6 ? (arr[0 ] +1 ) : (get_unaligned_be16 (arr +0 ) +2 ); bd_len = mselect6 ? arr[3 ] :get_unaligned_be16 (arr +6 ); -if (md_len >2 ) { + off = bd_len + (mselect6 ?4 :8 ); +if (md_len >2 || off >= res) {mk_sense_invalid_fld (scp,SDEB_IN_DATA ,0 ,-1 );return check_condition_result; } - off = bd_len + (mselect6 ?4 :8 ); mpage = arr[off] &0x3f ; ps = !!(arr[off] &0x80 );if (ps) {
Greg Kroah-Hartman
maintainerPATCH 166/177 io-wq: remove spurious bit clear on task_work addition
In reply to Greg Kroah-HartmanFrom: Jens Axboe <[email protected]>
commit e47498afeca9a0c6d07eeeacc46d563555a3f677 upstream.
There's a small race here where the task_work could finish and drop the worker itself, so that by the time that task_work_add() returns with a successful addition we've already put the worker.
The worker callbacks clear this bit themselves, so we don't actually need to manually clear it in the caller. Get rid of it.
--- fs/io-wq.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
fs/io-wq.c +1 -3
@@ -359,10 +359,8 @@ static bool io_queue_worker_create(strucinit_task_work (&worker->create_work, func); worker->create_index = acct->index; -if (!task_work_add (wq->task, &worker->create_work,TWA_SIGNAL )) { -clear_bit_unlock (0 , &worker->create_state); +if (!task_work_add (wq->task, &worker->create_work,TWA_SIGNAL ))return true; - }clear_bit_unlock (0 , &worker->create_state); fail_release:io_worker_release (worker);
Greg Kroah-Hartman
maintainerPATCH 167/177 io-wq: check for wq exit after adding new worker task_work
In reply to Greg Kroah-HartmanFrom: Jens Axboe <[email protected]>
commit 71a85387546e50b1a37b0fa45dadcae3bfb35cf6 upstream.
We check IO_WQ_BIT_EXIT before attempting to create a new worker, and wq exit cancels pending work if we have any. But it's possible to have a race between the two, where creation checks exit finding it not set, but we're in the process of exiting. The exit side will cancel pending creation task_work, but there's a gap where we add task_work after we've canceled existing creations at exit time.
Fix this by checking the EXIT bit post adding the creation task_work. If it's set, run the same cancelation that exit does.
--- fs/io-wq.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-)
fs/io-wq.c +25 -6
@@ -141,6 +141,7 @@ static bool io_acct_cancel_pending_work(struct io_wqe_acct *acct, struct io_cb_cancel_data *match);static void create_worker_cb (struct callback_head *cb); +static void io_wq_cancel_tw_create (struct io_wq *wq);static bool io_worker_get (struct io_worker *worker) {
@@ -357,10 +358,22 @@ static bool io_queue_worker_create(struc test_and_set_bit_lock(0, &worker->create_state)) goto fail_release; +atomic_inc (&wq->worker_refs);init_task_work (&worker->create_work, func); worker->create_index = acct->index; -if (!task_work_add (wq->task, &worker->create_work,TWA_SIGNAL )) +if (!task_work_add (wq->task, &worker->create_work,TWA_SIGNAL )) { +/* +* EXIT may have been set after checking it above, check after +* adding the task_work and remove any creation item if it is +* now set. wq exit does that too, but we can have added this +* work item after we canceled in io_wq_exit_workers(). +*/ +if (test_bit (IO_WQ_BIT_EXIT , &wq->state)) +io_wq_cancel_tw_create (wq); +io_worker_ref_put (wq);return true; + } +io_worker_ref_put (wq);clear_bit_unlock (0 , &worker->create_state); fail_release:io_worker_release (worker);
@@ -1193,13 +1206,9 @@ void io_wq_exit_start(struct io_wq *wq)set_bit (IO_WQ_BIT_EXIT , &wq->state); } -static void io_wq_exit_workers (struct io_wq *wq) +static void io_wq_cancel_tw_create (struct io_wq *wq) {struct callback_head *cb; -int node; - -if (!wq->task) -return ;while ((cb =task_work_cancel_match (wq->task, io_task_work_match, wq)) !=NULL ) {struct io_worker *worker;
@@ -1207,6 +1216,16 @@ static void io_wq_exit_workers(struct io worker = container_of(cb, struct io_worker, create_work);io_worker_cancel_cb (worker); } +} + +static void io_wq_exit_workers (struct io_wq *wq) +{ +int node; + +if (!wq->task) +return ; + +io_wq_cancel_tw_create (wq);rcu_read_lock ();for_each_node (node) {
Greg Kroah-Hartman
maintainerPATCH 168/177 rcu: Mark accesses to rcu_state.n_force_qs
In reply to Greg Kroah-HartmanFrom: Paul E. McKenney <[email protected]>
commit 2431774f04d1050292054c763070021bade7b151 upstream.
This commit marks accesses to the rcu_state.n_force_qs. These data races are hard to make happen, but syzkaller was equal to the task.
--- kernel/rcu/tree.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
kernel/rcu/tree.c +5 -5
@@ -1907,7 +1907,7 @@ static void rcu_gp_fqs(bool first_time)struct rcu_node *rnp =rcu_get_root ();WRITE_ONCE (rcu_state.gp_activity, jiffies); - rcu_state.n_force_qs++; +WRITE_ONCE (rcu_state.n_force_qs, rcu_state.n_force_qs +1 );if (first_time) {/* Collect dyntick-idle snapshots. */ force_qs_rnp (dyntick_save_progress_counter);
@@ -2550,7 +2550,7 @@ static void rcu_do_batch(struct rcu_data/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */ if (count ==0 && rdp->qlen_last_fqs_check !=0 ) { rdp->qlen_last_fqs_check =0 ; - rdp->n_force_qs_snap = rcu_state.n_force_qs; + rdp->n_force_qs_snap =READ_ONCE (rcu_state.n_force_qs); }else if (count < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = count;
@@ -2898,10 +2898,10 @@ static void __call_rcu_core(struct rcu_d }else {/* Give the grace period a kick. */ rdp->blimit =DEFAULT_MAX_RCU_BLIMIT ; -if (rcu_state.n_force_qs == rdp->n_force_qs_snap && +if (READ_ONCE (rcu_state.n_force_qs) == rdp->n_force_qs_snap &&rcu_segcblist_first_pend_cb (&rdp->cblist) != head)rcu_force_quiescent_state (); - rdp->n_force_qs_snap = rcu_state.n_force_qs; + rdp->n_force_qs_snap =READ_ONCE (rcu_state.n_force_qs); rdp->qlen_last_fqs_check =rcu_segcblist_n_cbs (&rdp->cblist); } }
@@ -4128,7 +4128,7 @@ int rcutree_prepare_cpu(unsigned int cpu/* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave_rcu_node (rnp, flags); rdp->qlen_last_fqs_check =0 ; - rdp->n_force_qs_snap = rcu_state.n_force_qs; + rdp->n_force_qs_snap =READ_ONCE (rcu_state.n_force_qs); rdp->blimit = blimit; rdp->dynticks_nesting =1 ;/* CPU not up, no tearing. */ rcu_dynticks_eqs_online ();
Greg Kroah-Hartman
maintainerPATCH 169/177 io-wq: drop wqe lock before creating new worker
In reply to Greg Kroah-HartmanFrom: Jens Axboe <[email protected]>
commit d800c65c2d4eccebb27ffb7808e842d5b533823c upstream.
We have two io-wq creation paths:
- On queue enqueue
- When a worker goes to sleep
The latter invokes worker creation with the wqe->lock held, but that can run into problems if we end up exiting and need to cancel the queued work. syzbot caught this:
============================================
WARNING: possible recursive locking detected
5.16.0-rc4-syzkaller #0 Not tainted
--------------------------------------------
iou-wrk-6468/6471 is trying to acquire lock:ffff88801aa98018 (&wqe->lock){+.+.}-{2:2}, at: io_worker_cancel_cb+0xb7/0x210 fs/io-wq.c:187
but task is already holding lock:ffff88801aa98018 (&wqe->lock){+.+.}-{2:2}, at: io_wq_worker_sleeping+0xb6/0x140 fs/io-wq.c:700
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
---- lock(&wqe->lock);
lock(&wqe->lock);
*** DEADLOCK ***
May be due to missing lock nesting notation
1 lock held by iou-wrk-6468/6471:
#0: ffff88801aa98018 (&wqe->lock){+.+.}-{2:2}, at: io_wq_worker_sleeping+0xb6/0x140 fs/io-wq.c:700
stack backtrace: CPU: 1 PID: 6471 Comm: iou-wrk-6468 Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1dc/0x2d8 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2956 [inline] check_deadlock kernel/locking/lockdep.c:2999 [inline] validate_chain+0x5984/0x8240 kernel/locking/lockdep.c:3788 __lock_acquire+0x1382/0x2b00 kernel/locking/lockdep.c:5027 lock_acquire+0x19f/0x4d0 kernel/locking/lockdep.c:5637 __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline] _raw_spin_lock+0x2a/0x40 kernel/locking/spinlock.c:154 io_worker_cancel_cb+0xb7/0x210 fs/io-wq.c:187 io_wq_cancel_tw_create fs/io-wq.c:1220 [inline] io_queue_worker_create+0x3cf/0x4c0 fs/io-wq.c:372 io_wq_worker_sleeping+0xbe/0x140 fs/io-wq.c:701 sched_submit_work kernel/sched/core.c:6295 [inline] schedule+0x67/0x1f0 kernel/sched/core.c:6323 schedule_timeout+0xac/0x300 kernel/time/timer.c:1857 wait_woken+0xca/0x1b0 kernel/sched/wait.c:460 unix_msg_wait_data net/unix/unix_bpf.c:32 [inline] unix_bpf_recvmsg+0x7f9/0xe20 net/unix/unix_bpf.c:77 unix_stream_recvmsg+0x214/0x2c0 net/unix/af_unix.c:2832 sock_recvmsg_nosec net/socket.c:944 [inline] sock_recvmsg net/socket.c:962 [inline] sock_read_iter+0x3a7/0x4d0 net/socket.c:1035 call_read_iter include/linux/fs.h:2156 [inline] io_iter_do_read fs/io_uring.c:3501 [inline] io_read fs/io_uring.c:3558 [inline] io_issue_sqe+0x144c/0x9590 fs/io_uring.c:6671 io_wq_submit_work+0x2d8/0x790 fs/io_uring.c:6836 io_worker_handle_work+0x808/0xdd0 fs/io-wq.c:574 io_wqe_worker+0x395/0x870 fs/io-wq.c:630 ret_from_fork+0x1f/0x30
We can safely drop the lock before doing work creation, making the two contexts the same in that regard.
--- fs/io-wq.c | 2 ++ 1 file changed, 2 insertions(+)
fs/io-wq.c +2 -0
@@ -395,7 +395,9 @@ static void io_wqe_dec_running(struct ioif (atomic_dec_and_test (&acct->nr_running) &&io_acct_run_queue (acct)) {atomic_inc (&acct->nr_running);atomic_inc (&wqe->wq->worker_refs); +raw_spin_unlock (&wqe->lock);io_queue_worker_create (worker, acct, create_worker_cb); +raw_spin_lock (&wqe->lock); } }
Greg Kroah-Hartman
maintainerPATCH 170/177 bus: ti-sysc: Fix variable set but not used warning for reinit_modules
In reply to Greg Kroah-HartmanFrom: Tony Lindgren <[email protected]>
commit 1b1da99b845337362a3dafe0f7b49927ab4ae041 upstream.
Fix drivers/bus/ti-sysc.c:2494:13: error: variable 'error' set but not used introduced by commit 9d881361206e ("bus: ti-sysc: Add quirk handling for reinit on context lost").
--- drivers/bus/ti-sysc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/bus/ti-sysc.c +1 -2
@@ -2456,12 +2456,11 @@ static void sysc_reinit_modules(struct sstruct sysc_module *module;struct list_head *pos;struct sysc *ddata; -int error =0 ;list_for_each (pos, &sysc_soc->restored_modules) { module = list_entry(pos, struct sysc_module, node); ddata = module->ddata; - error =sysc_reinit_module (ddata, ddata->enabled); +sysc_reinit_module (ddata, ddata->enabled); } }