Nathan noticed that when HWSPINLOCK is disabled there's a Kconfig warning:
WARNING: unmet direct dependencies detected for QCOM_SMEM
Depends on [n]: (ARCH_QCOM [=y] || COMPILE_TEST [=n]) && HWSPINLOCK [=n]
Selected by [m]:
- ATH10K_SNOC [=m] && NETDEVICES [=y] && WLAN [=y] && WLAN_VENDOR_ATH [=y] && ATH10K [=m] && (ARCH_QCOM [=y] || COMPILE_TEST [=n])
The problem here is that QCOM_SMEM depends on HWSPINLOCK so we cannot select
QCOM_SMEM and instead we neeed to use 'depends on'.
Reported-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/all/Y4YsyaIW+CPdHWv3@dev-arch.thelio-3990X/
Fixes: 4d79f6f34b ("wifi: ath10k: Store WLAN firmware version in SMEM image table")
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20221202103027.25974-1-kvalo@kernel.org
In a SoC based solution, it would be useful to know the versions of the
various binary firmware blobs the system is running on. On a QCOM based
SoC, this info can be obtained from socinfo debugfs infrastructure. For
this to work, respective subsystem drivers have to export the firmware
version information to an SMEM based version information table.
Having firmware version information at one place will help quickly
figure out the firmware versions of various subsystems on the device
instead of going through builds/logs in an event of a system crash.
Fill WLAN firmware version information in SMEM version table to be
printed as part of socinfo debugfs infrastructure on a Qualcomm based
SoC.
This change is applicable only for SNOC/QMI based targets.
Example:
cat /sys/kernel/debug/qcom_socinfo/cnss/name
QC_IMAGE_VERSION_STRING=WLAN.HL.3.2.2.c10-00754-QCAHLSWMTPL-1
Tested-on: WCN3990 hw1.0 SNOC WLAN.HL.3.2.2.c10-00754-QCAHLSWMTPL-1
Signed-off-by: Youghandhar Chintala <quic_youghand@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221117180534.2267-1-quic_youghand@quicinc.com
Kalle Valo says:
====================
wireless-next patches for v6.2
Second set of patches for v6.2. Only driver patches this time, nothing
really special. Unused platform data support was removed from wl1251
and rtw89 got WoWLAN support.
Major changes:
ath11k
* support configuring channel dwell time during scan
rtw89
* new dynamic header firmware format support
* Wake-over-WLAN support
rtl8xxxu
* enable IEEE80211_HW_SUPPORT_FAST_XMIT
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently after the hardware restart triggered from the driver, the
station interface connection remains intact, since a disconnect trigger
is not sent to userspace. This can lead to a problem in targets where
the wifi mac sequence is added by the firmware.
After the target restart, its wifi mac sequence number gets reset to
zero. Hence AP to which our device is connected will receive frames with
a wifi mac sequence number jump to the past, thereby resulting in the
AP dropping all these frames, until the frame arrives with a wifi mac
sequence number which AP was expecting.
To avoid such frame drops, its better to trigger a station disconnect
upon target hardware restart which can be done with API
ieee80211_reconfig_disconnect exposed to mac80211.
The other targets are not affected by this change, since the hardware
params flag is not set.
Reported-by: kernel test robot <lkp@intel.com>
Tested-on: WCN6750 hw1.0 AHB WLAN.MSL.1.0.1-00887-QCAMSLSWPLZ-1
Signed-off-by: Youghandhar Chintala <quic_youghand@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221104085403.11025-1-quic_youghand@quicinc.com
(cherry picked from commit d99884ad9e in ath-next
as users are seeing this bug more now, also cc stable)
Running this test in a loop it is easy to reproduce an rtnl deadlock:
iw reg set FI
ifconfig wlan0 down
What happens is that thread A (workqueue) tries to update the regulatory:
try to acquire the rtnl_lock of ar->regd_update_work
rtnl_lock+0x17/0x20
ath11k_regd_update+0x15a/0x260 [ath11k]
ath11k_regd_update_work+0x15/0x20 [ath11k]
process_one_work+0x228/0x670
worker_thread+0x4d/0x440
kthread+0x16d/0x1b0
ret_from_fork+0x22/0x30
And thread B (ifconfig) tries to stop the interface:
try to cancel_work_sync(&ar->regd_update_work) in ath11k_mac_op_stop().
ifconfig 3109 [003] 2414.232506: probe:
ath11k_mac_op_stop: (ffffffffc14187a0)
drv_stop+0x30 ([mac80211])
ieee80211_do_stop+0x5d2 ([mac80211])
ieee80211_stop+0x3e ([mac80211])
__dev_close_many+0x9e ([kernel.kallsyms])
__dev_change_flags+0xbe ([kernel.kallsyms])
dev_change_flags+0x23 ([kernel.kallsyms])
devinet_ioctl+0x5e3 ([kernel.kallsyms])
inet_ioctl+0x197 ([kernel.kallsyms])
sock_do_ioctl+0x4d ([kernel.kallsyms])
sock_ioctl+0x264 ([kernel.kallsyms])
__x64_sys_ioctl+0x92 ([kernel.kallsyms])
do_syscall_64+0x3a ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe+0x63 ([kernel.kallsyms])
__GI___ioctl+0x7 (/lib/x86_64-linux-gnu/libc-2.23.so)
The sequence of deadlock is:
1. Thread B calls rtnl_lock().
2. Thread A starts to run and calls rtnl_lock() from within
ath11k_regd_update_work(), then enters wait state because the lock is owned by
thread B.
3. Thread B continues to run and tries to call
cancel_work_sync(&ar->regd_update_work), but thread A is in
ath11k_regd_update_work() waiting for rtnl_lock(). So cancel_work_sync()
forever waits for ath11k_regd_update_work() to finish and we have a deadlock.
Fix this by switching from using regulatory_set_wiphy_regd_sync() to
regulatory_set_wiphy_regd(). Now cfg80211 will schedule another workqueue which
handles the locking on it's own. So the ath11k workqueue can simply exit without
taking any locks, avoiding the deadlock.
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3
Cc: <stable@vger.kernel.org>
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
[kvalo: improve commit log]
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
The 2.7.0 series of QCN9074's firmware requests 5 segments
of memory instead of 3 (as in the 2.5.0 series).
The first segment (11M) is too large to be kalloc'd in one
go on x86 and requires piecemeal 1MB allocations, as was
the case with the prior public firmware (2.5.0, 15M).
Since f6f92968e1, ath11k will break the memory requests,
but only if there were fewer than 3 segments requested by
the firmware. It seems that 5 segments works fine and
allows QCN9074 to boot on x86 with firmware 2.7.0, so
change things accordingly.
Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.5.0.1-01208-QCAHKSWPL_SILICONZ-1
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.16
Signed-off-by: Tyler J. Stachecki <stachecki.tyler@gmail.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221022042728.43015-1-stachecki.tyler@gmail.com
qmi_msg_handler is required to be null terminated by QMI module.
There might be a case where a handler for a msg id is not present in the
handlers array which can lead to infinite loop while searching the handler
and therefore out of bound access in qmi_invoke_handler().
Hence update the initialization in qmi_msg_handler data structure.
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1
Signed-off-by: Rahul Bhattacharjee <quic_rbhattac@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221021090126.28626-1-quic_rbhattac@quicinc.com
====================
pull-request: wireless-next-2022-10-28
First set of patches v6.2. mac80211 refactoring continues for Wi-Fi 7.
All mac80211 driver are now converted to use internal TX queues, this
might cause some regressions so we wanted to do this early in the
cycle.
Note: wireless tree was merged[1] to wireless-next to avoid some
conflicts with mac80211 patches between the trees. Unfortunately there
are still two smaller conflicts in net/mac80211/util.c which Stephen
also reported[2]. In the first conflict initialise scratch_len to
"params->scratch_len ?: 3 * params->len" (note number 3, not 2!) and
in the second conflict take the version which uses elems->scratch_pos.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git/commit/?id=dfd2d876b3fda1790bc0239ba4c6967e25d16e91
[2] https://lore.kernel.org/all/20221020032340.5cf101c0@canb.auug.org.au/
mac80211
- preparation for Wi-Fi 7 Multi-Link Operation (MLO) continues
- add API to show the link STAs in debugfs
- all mac80211 drivers are now using mac80211 internal TX queues (iTXQs)
rtw89
- support 8852BE
rtl8xxxu
- support RTL8188FU
brmfmac
- support two station interfaces concurrently
bcma
- support SPROM rev 11
====================
Link: https://lore.kernel.org/r/20221028132943.304ECC433B5@smtp.kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
During firmware recovery, the monitor interface is not
getting created in the driver and firmware since
the respective flags are not updated properly.
So after firmware recovery is successful, when monitor
interface is brought down manually, firmware assertion
is observed, since we are trying to bring down the
interface which is not yet created in the firmware.
Fix this by updating the monitor flags properly per
phy#, during firmware recovery.
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
Signed-off-by: Nagarajan Maran <quic_nmaran@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221014155054.11471-1-quic_nmaran@quicinc.com
On WCN3990, we are seeing a rare scenario where copy engine hardware is
sending a copy complete interrupt to the host driver while still
processing the buffer that the driver has sent, this is leading into an
SMMU fault triggering kernel panic. This is happening on copy engine
channel 3 (CE3) where the driver normally enqueues WMI commands to the
firmware. Upon receiving a copy complete interrupt, host driver will
immediately unmap and frees the buffer presuming that hardware has
processed the buffer. In the issue case, upon receiving copy complete
interrupt, host driver will unmap and free the buffer but since hardware
is still accessing the buffer (which in this case got unmapped in
parallel), SMMU hardware will trigger an SMMU fault resulting in a
kernel panic.
In order to avoid this, as a work around, add a delay before unmapping
the copy engine source DMA buffer. This is conditionally done for
WCN3990 and only for the CE3 channel where issue is seen.
Below is the crash signature:
wifi smmu error: kernel: [ 10.120965] arm-smmu 15000000.iommu: Unhandled
context fault: fsr=0x402, iova=0x7fdfd8ac0,
fsynr=0x500003,cbfrsynra=0xc1, cb=6 arm-smmu 15000000.iommu: Unhandled
context fault:fsr=0x402, iova=0x7fe06fdc0, fsynr=0x710003,
cbfrsynra=0xc1, cb=6 qcom-q6v5-mss 4080000.remoteproc: fatal error
received: err_qdi.c:1040:EF:wlan_process:0x1:WLAN RT:0x2091:
cmnos_thread.c:3998:Asserted in copy_engine.c:AXI_ERROR_DETECTED:2149
remoteproc remoteproc0: crash detected in
4080000.remoteproc: type fatal error <3> remoteproc remoteproc0:
handling crash #1 in 4080000.remoteproc
pc : __arm_lpae_unmap+0x500/0x514
lr : __arm_lpae_unmap+0x4bc/0x514
sp : ffffffc011ffb530
x29: ffffffc011ffb590 x28: 0000000000000000
x27: 0000000000000000 x26: 0000000000000004
x25: 0000000000000003 x24: ffffffc011ffb890
x23: ffffffa762ef9be0 x22: ffffffa77244ef00
x21: 0000000000000009 x20: 00000007fff7c000
x19: 0000000000000003 x18: 0000000000000000
x17: 0000000000000004 x16: ffffffd7a357d9f0
x15: 0000000000000000 x14: 00fd5d4fa7ffffff
x13: 000000000000000e x12: 0000000000000000
x11: 00000000ffffffff x10: 00000000fffffe00
x9 : 000000000000017c x8 : 000000000000000c
x7 : 0000000000000000 x6 : ffffffa762ef9000
x5 : 0000000000000003 x4 : 0000000000000004
x3 : 0000000000001000 x2 : 00000007fff7c000
x1 : ffffffc011ffb890 x0 : 0000000000000000 Call trace:
__arm_lpae_unmap+0x500/0x514
__arm_lpae_unmap+0x4bc/0x514
__arm_lpae_unmap+0x4bc/0x514
arm_lpae_unmap_pages+0x78/0xa4
arm_smmu_unmap_pages+0x78/0x104
__iommu_unmap+0xc8/0x1e4
iommu_unmap_fast+0x38/0x48
__iommu_dma_unmap+0x84/0x104
iommu_dma_free+0x34/0x50
dma_free_attrs+0xa4/0xd0
ath10k_htt_rx_free+0xc4/0xf4 [ath10k_core] ath10k_core_stop+0x64/0x7c
[ath10k_core]
ath10k_halt+0x11c/0x180 [ath10k_core]
ath10k_stop+0x54/0x94 [ath10k_core]
drv_stop+0x48/0x1c8 [mac80211]
ieee80211_do_open+0x638/0x77c [mac80211] ieee80211_open+0x48/0x5c
[mac80211]
__dev_open+0xb4/0x174
__dev_change_flags+0xc4/0x1dc
dev_change_flags+0x3c/0x7c
devinet_ioctl+0x2b4/0x580
inet_ioctl+0xb0/0x1b4
sock_do_ioctl+0x4c/0x16c
compat_ifreq_ioctl+0x1cc/0x35c
compat_sock_ioctl+0x110/0x2ac
__arm64_compat_sys_ioctl+0xf4/0x3e0
el0_svc_common+0xb4/0x17c
el0_svc_compat_handler+0x2c/0x58
el0_svc_compat+0x8/0x2c
Tested-on: WCN3990 hw1.0 SNOC WLAN.HL.2.0-01387-QCAHLSWMTPLZ-1
Tested-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Youghandhar Chintala <quic_youghand@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221012142733.32420-1-quic_youghand@quicinc.com
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter, and wifi.
Current release - regressions:
- Revert "net/sched: taprio: make qdisc_leaf() see the
per-netdev-queue pfifo child qdiscs", it may cause crashes when the
qdisc is reconfigured
- inet: ping: fix splat due to packet allocation refactoring in inet
- tcp: clean up kernel listener's reqsk in inet_twsk_purge(), fix UAF
due to races when per-netns hash table is used
Current release - new code bugs:
- eth: adin1110: check in netdev_event that netdev belongs to driver
- fixes for PTR_ERR() vs NULL bugs in driver code, from Dan and co.
Previous releases - regressions:
- ipv4: handle attempt to delete multipath route when fib_info
contains an nh reference, avoid oob access
- wifi: fix handful of bugs in the new Multi-BSSID code
- wifi: mt76: fix rate reporting / throughput regression on mt7915
and newer, fix checksum offload
- wifi: iwlwifi: mvm: fix double list_add at
iwl_mvm_mac_wake_tx_queue (other cases)
- wifi: mac80211: do not drop packets smaller than the LLC-SNAP
header on fast-rx
Previous releases - always broken:
- ieee802154: don't warn zero-sized raw_sendmsg()
- ipv6: ping: fix wrong checksum for large frames
- mctp: prevent double key removal and unref
- tcp/udp: fix memory leaks and races around IPV6_ADDRFORM
- hv_netvsc: fix race between VF offering and VF association message
Misc:
- remove -Warray-bounds silencing in the drivers, compilers fixed"
* tag 'net-6.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (73 commits)
sunhme: fix an IS_ERR() vs NULL check in probe
net: marvell: prestera: fix a couple NULL vs IS_ERR() checks
kcm: avoid potential race in kcm_tx_work
tcp: Clean up kernel listener's reqsk in inet_twsk_purge()
net: phy: micrel: Fixes FIELD_GET assertion
openvswitch: add nf_ct_is_confirmed check before assigning the helper
tcp: Fix data races around icsk->icsk_af_ops.
ipv6: Fix data races around sk->sk_prot.
tcp/udp: Call inet6_destroy_sock() in IPv6 sk->sk_destruct().
udp: Call inet6_destroy_sock() in setsockopt(IPV6_ADDRFORM).
tcp/udp: Fix memory leak in ipv6_renew_options().
mctp: prevent double key removal and unref
selftests: netfilter: Fix nft_fib.sh for all.rp_filter=1
netfilter: rpfilter/fib: Populate flowic_l3mdev field
selftests: netfilter: Test reverse path filtering
net/mlx5: Make ASO poll CQ usable in atomic context
tcp: cdg: allow tcp_cdg_release() to be called multiple times
inet: ping: fix recent breakage
ipv6: ping: fix wrong checksum for large frames
net: ethernet: ti: am65-cpsw: set correct devlink flavour for unused ports
...
Return value of a function ath10k_get_arvif() is dereferenced without
checking for null in ath10k_wmi_event_tdls_peer(), but it is usually checked
for this function.
Make ath10k_wmi_event_tdls_peer() do check retval of ath10k_get_arvif().
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Signed-off-by: Peter Kosyh <pkosyh@yandex.ru>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221003091217.322598-1-pkosyh@yandex.ru
Current code does not wait for vdev delete completion on vdev create
failures and tries to send another vdev create followed by vdev set
param to firmware with same vdev id. This causes firmware crash.
Fix this crash by waiting for vdev delete completion on vdev
create failures.
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.6.0.1-00905-QCAHKSWPL_SILICONZ-1
Signed-off-by: Sowmiya Sree Elavalagan <quic_ssreeela@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221011095346.3901-1-quic_ssreeela@quicinc.com
Add support to configure channel dwell time during scan.
Dwell time help to stay on the channel for a specified duration
during scan and aid userspace in finding WiFi networks. Very
useful in passive scans where longer dwell times are needed
to find the WiFi networks.
Configure channel dwell time from duration of the scan request
received from mac80211 when the duration is non-zero. When the
scan request does not have duration value, use the default ones,
the current implementation.
Advertise corresponding feature flag NL80211_EXT_FEATURE_SET_SCAN_DWELL
to enable the feature.
Change is applicable for all ath11k hardware.
Tested-on: WCN6750 hw1.0 AHB WLAN.MSL.1.0.1-00887-QCAMSLSWPLZ-1
Signed-off-by: Manikanta Pubbisetty <quic_mpubbise@quicinc.com>
Reviewed-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221007051130.6067-1-quic_mpubbise@quicinc.com
In the VIF (other than monitor type) creation request, we should not
throw the error code when the monitor VIF creation fails, since the
actual VIF creation succeeds. If we throw the error code from driver
then the actual VIF creation get fail. So suppress the monitor VIF
creation error by throwing warning message instead of error code.
Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.6.0.1-00760-QCAHKSWPL_SILICONZ-1
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221006005842.8599-1-quic_periyasa@quicinc.com
Currently, ath11k sends peer assoc command for each peer to
firmware when bandwidth changes. Peer assoc command is a
bulky command and if many clients are connected, this could
lead to firmware buffer getting overflowed leading to a firmware
assert.
However, during bandwidth change, only phymode and bandwidth
also can be updated by WMI set peer param command. This makes
the overall command light when compared to peer assoc and for
multi-client cases, firmware buffer overflow also does not
occur.
Remove sending peer assoc command during sta bandwidth change
and instead add sending WMI set peer param command for phymode
and bandwidth.
Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1
Fixes: f187fe8e3b ("ath11k: fix firmware crash during channel switch")
Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221005095430.19890-1-quic_adisi@quicinc.com
Linaro reported stringop-overread warnings in ath11k (this is one of many):
drivers/net/wireless/ath/ath11k/mac.c:2238:29: error: 'ath11k_peer_assoc_h_he_limit' reading 16 bytes from a region of size 0 [-Werror=stringop-overread]
My further investigation showed that these warnings happen on GCC 11.3 but not
with GCC 12.2, and with only the kernel config Linaro provided:
https://builds.tuxbuild.com/2F4W7nZHNx3T88RB0gaCZ9hBX6c/config
I saw the same warnings both with arm64 and x86_64 builds and KASAN seems to be
the reason triggering these warnings with GCC 11. Nobody else has reported
this so this seems to be quite rare corner case. I don't know what specific
commit started emitting this warning so I can't provide a Fixes tag. The
function hasn't been touched for a year.
I decided to workaround this by converting the pointer to a new array in stack,
and then copying the data to the new array. It's only 16 bytes anyway and this
is executed during association, so not in a hotpath.
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.9
Reported-by: Linux Kernel Functional Testing <lkft@linaro.org>
Link: https://lore.kernel.org/all/CA+G9fYsZ_qypa=jHY_dJ=tqX4515+qrV9n2SWXVDHve826nF7Q@mail.gmail.com/
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20221010160638.20152-1-kvalo@kernel.org
The bug arises when a USB device claims to be an ATH9K but doesn't
have the expected endpoints. (In this case there was an interrupt
endpoint where the driver expected a bulk endpoint.) The kernel
needs to be able to handle such devices without getting an internal error.
usb 1-1: BOGUS urb xfer, pipe 3 != type 1
WARNING: CPU: 3 PID: 500 at drivers/usb/core/urb.c:493 usb_submit_urb+0xce2/0x1430 drivers/usb/core/urb.c:493
Modules linked in:
CPU: 3 PID: 500 Comm: kworker/3:2 Not tainted 5.10.135-syzkaller #0
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
Workqueue: events request_firmware_work_func
RIP: 0010:usb_submit_urb+0xce2/0x1430 drivers/usb/core/urb.c:493
Call Trace:
ath9k_hif_usb_alloc_rx_urbs drivers/net/wireless/ath/ath9k/hif_usb.c:908 [inline]
ath9k_hif_usb_alloc_urbs+0x75e/0x1010 drivers/net/wireless/ath/ath9k/hif_usb.c:1019
ath9k_hif_usb_dev_init drivers/net/wireless/ath/ath9k/hif_usb.c:1109 [inline]
ath9k_hif_usb_firmware_cb+0x142/0x530 drivers/net/wireless/ath/ath9k/hif_usb.c:1242
request_firmware_work_func+0x12e/0x240 drivers/base/firmware_loader/main.c:1097
process_one_work+0x9af/0x1600 kernel/workqueue.c:2279
worker_thread+0x61d/0x12f0 kernel/workqueue.c:2425
kthread+0x3b4/0x4a0 kernel/kthread.c:313
ret_from_fork+0x22/0x30 arch/x86/entry/entry_64.S:299
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221008211532.74583-1-pchelkin@ispras.ru
It is possible that skb is freed in ath9k_htc_rx_msg(), then
usb_submit_urb() fails and we try to free skb again. It causes
use-after-free bug. Moreover, if alloc_skb() fails, urb->context becomes
NULL but rx_buf is not freed and there can be a memory leak.
The patch removes unnecessary nskb and makes skb processing more clear: it
is supposed that ath9k_htc_rx_msg() either frees old skb or passes its
managing to another callback function.
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
Fixes: 3deff76095 ("ath9k_htc: Increase URB count for REG_IN pipe")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221008114917.21404-1-pchelkin@ispras.ru
Syzkaller reports a long-known leak of urbs in
ath9k_hif_usb_dealloc_tx_urbs().
The cause of the leak is that usb_get_urb() is called but usb_free_urb()
(or usb_put_urb()) is not called inside usb_kill_urb() as urb->dev or
urb->ep fields have not been initialized and usb_kill_urb() returns
immediately.
The patch removes trying to kill urbs located in hif_dev->tx.tx_buf
because hif_dev->tx.tx_buf is not supposed to contain urbs which are in
pending state (the pending urbs are stored in hif_dev->tx.tx_pending).
The tx.tx_lock is acquired so there should not be any changes in the list.
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
Fixes: 03fb92a432 ("ath9k: hif_usb: fix race condition between usb_get_urb() and usb_kill_anchored_urbs()")
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220725151359.283704-1-pchelkin@ispras.ru
Running this test in a loop it is easy to reproduce an rtnl deadlock:
iw reg set FI
ifconfig wlan0 down
What happens is that thread A (workqueue) tries to update the regulatory:
try to acquire the rtnl_lock of ar->regd_update_work
rtnl_lock+0x17/0x20
ath11k_regd_update+0x15a/0x260 [ath11k]
ath11k_regd_update_work+0x15/0x20 [ath11k]
process_one_work+0x228/0x670
worker_thread+0x4d/0x440
kthread+0x16d/0x1b0
ret_from_fork+0x22/0x30
And thread B (ifconfig) tries to stop the interface:
try to cancel_work_sync(&ar->regd_update_work) in ath11k_mac_op_stop().
ifconfig 3109 [003] 2414.232506: probe:
ath11k_mac_op_stop: (ffffffffc14187a0)
drv_stop+0x30 ([mac80211])
ieee80211_do_stop+0x5d2 ([mac80211])
ieee80211_stop+0x3e ([mac80211])
__dev_close_many+0x9e ([kernel.kallsyms])
__dev_change_flags+0xbe ([kernel.kallsyms])
dev_change_flags+0x23 ([kernel.kallsyms])
devinet_ioctl+0x5e3 ([kernel.kallsyms])
inet_ioctl+0x197 ([kernel.kallsyms])
sock_do_ioctl+0x4d ([kernel.kallsyms])
sock_ioctl+0x264 ([kernel.kallsyms])
__x64_sys_ioctl+0x92 ([kernel.kallsyms])
do_syscall_64+0x3a ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe+0x63 ([kernel.kallsyms])
__GI___ioctl+0x7 (/lib/x86_64-linux-gnu/libc-2.23.so)
The sequence of deadlock is:
1. Thread B calls rtnl_lock().
2. Thread A starts to run and calls rtnl_lock() from within
ath11k_regd_update_work(), then enters wait state because the lock is owned by
thread B.
3. Thread B continues to run and tries to call
cancel_work_sync(&ar->regd_update_work), but thread A is in
ath11k_regd_update_work() waiting for rtnl_lock(). So cancel_work_sync()
forever waits for ath11k_regd_update_work() to finish and we have a deadlock.
Fix this by switching from using regulatory_set_wiphy_regd_sync() to
regulatory_set_wiphy_regd(). Now cfg80211 will schedule another workqueue which
handles the locking on it's own. So the ath11k workqueue can simply exit without
taking any locks, avoiding the deadlock.
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
[kvalo: improve commit log]
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20221006151747.13757-1-kvalo@kernel.org
mac80211 is fully switching over to the internal TX queue (iTXQ)
implementation. Update all drivers not yet providing the now mandatory
wake_tx_queue() callback.
As an side effect the netdev interfaces of all updated drivers will
switch to the noqueue qdisc.
Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
[add staging drivers]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Kalle Valo says:
====================
wireless-next patches for v6.1
Few stack changes and lots of driver changes in this round. brcmfmac
has more activity as usual and it gets new hardware support. ath11k
improves WCN6750 support and also other smaller features. And of
course changes all over.
Note: in early September wireless tree was merged to wireless-next to
avoid some conflicts with mac80211 patches, this shouldn't cause any
problems but wanted to mention anyway.
Major changes:
mac80211
- refactoring and preparation for Wi-Fi 7 Multi-Link Operation (MLO)
feature continues
brcmfmac
- support CYW43439 SDIO chipset
- support BCM4378 on Apple platforms
- support CYW89459 PCIe chipset
rtw89
- more work to get rtw8852c supported
- P2P support
- support for enabling and disabling MSDU aggregation via nl80211
mt76
- tx status reporting improvements
ath11k
- cold boot calibration support on WCN6750
- Target Wake Time (TWT) debugfs support for STA interface
- support to connect to a non-transmit MBSSID AP profile
- enable remain-on-channel support on WCN6750
- implement SRAM dump debugfs interface
- enable threaded NAPI on all hardware
- WoW support for WCN6750
- support to provide transmit power from firmware via nl80211
- support to get power save duration for each client
- spectral scan support for 160 MHz
wcn36xx
- add SNR from a received frame as a source of system entropy
* tag 'wireless-next-2022-09-30' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next: (231 commits)
wifi: rtl8xxxu: Improve rtl8xxxu_queue_select
wifi: rtl8xxxu: Fix AIFS written to REG_EDCA_*_PARAM
wifi: rtl8xxxu: gen2: Enable 40 MHz channel width
wifi: rtw89: 8852b: configure DLE mem
wifi: rtw89: check DLE FIFO size with reserved size
wifi: rtw89: mac: correct register of report IMR
wifi: rtw89: pci: set power cut closed for 8852be
wifi: rtw89: pci: add to do PCI auto calibration
wifi: rtw89: 8852b: implement chip_ops::{enable,disable}_bb_rf
wifi: rtw89: add DMA busy checking bits to chip info
wifi: rtw89: mac: define DMA channel mask to avoid unsupported channels
wifi: rtw89: pci: mask out unsupported TX channels
iwlegacy: Replace zero-length arrays with DECLARE_FLEX_ARRAY() helper
ipw2x00: Replace zero-length array with DECLARE_FLEX_ARRAY() helper
wifi: iwlwifi: Track scan_cmd allocation size explicitly
brcmfmac: Remove the call to "dtim_assoc" IOVAR
brcmfmac: increase dcmd maximum buffer size
brcmfmac: Support 89459 pcie
brcmfmac: increase default max WOWL patterns to 16
cw1200: fix incorrect check to determine if no element is found in list
...
====================
Link: https://lore.kernel.org/r/20220930150413.A7984C433D6@smtp.kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 26f3a021b3 ("ath11k: allocate smaller chunks of memory for
firmware") and commit f6f92968e1 ("ath11k: qmi: try to allocate a
big block of DMA memory first") change ath11k to allocate the memory
chunks for target twice while wlan load. It fails for the 1st time
because of large memory and then changed to allocate many small chunks
for the 2nd time sometimes as below log.
1st time failed:
[10411.640620] ath11k_pci 0000:05:00.0: qmi firmware request memory request
[10411.640625] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 6881280
[10411.640630] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 3784704
[10411.640658] ath11k_pci 0000:05:00.0: qmi dma allocation failed (6881280 B type 1), will try later with small size
[10411.640671] ath11k_pci 0000:05:00.0: qmi delays mem_request 2
[10411.640677] ath11k_pci 0000:05:00.0: qmi respond memory request delayed 1
2nd time success:
[10411.642004] ath11k_pci 0000:05:00.0: qmi firmware request memory request
[10411.642008] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642012] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642014] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642016] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642018] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642020] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642022] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642024] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642027] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642029] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
[10411.642031] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 458752
[10411.642033] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 131072
[10411.642035] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642037] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642039] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642041] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642043] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642045] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 524288
[10411.642047] ath11k_pci 0000:05:00.0: qmi mem seg type 4 size 491520
[10411.642049] ath11k_pci 0000:05:00.0: qmi mem seg type 1 size 524288
And then commit 5962f370ce ("ath11k: Reuse the available memory after
firmware reload") skip the ath11k_qmi_free_resource() which frees the
memory chunks while recovery, after that, when run recovery test on
WCN6855, a warning happened every time as below and finally leads fail
for recovery.
[ 159.570318] BUG: Bad page state in process kworker/u16:5 pfn:33300
[ 159.570320] page:0000000096ffdbb9 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x33300
[ 159.570324] flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff)
[ 159.570329] raw: 000fffffc0000000 0000000000000000 dead000000000122 0000000000000000
[ 159.570332] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
[ 159.570334] page dumped because: nonzero _refcount
[ 159.570440] firewire_ohci syscopyarea sysfillrect psmouse sdhci_pci ahci sysimgblt firewire_core fb_sys_fops libahci crc_itu_t cqhci drm sdhci e1000e wmi video
[ 159.570460] CPU: 2 PID: 217 Comm: kworker/u16:5 Kdump: loaded Tainted: G B 5.19.0-rc1-wt-ath+ #3
[ 159.570465] Hardware name: LENOVO 418065C/418065C, BIOS 83ET63WW (1.33 ) 07/29/2011
[ 159.570467] Workqueue: qmi_msg_handler qmi_data_ready_work [qmi_helpers]
[ 159.570475] Call Trace:
[ 159.570476] <TASK>
[ 159.570478] dump_stack_lvl+0x49/0x5f
[ 159.570486] dump_stack+0x10/0x12
[ 159.570493] bad_page+0xab/0xf0
[ 159.570502] check_free_page_bad+0x66/0x70
[ 159.570511] __free_pages_ok+0x530/0x9a0
[ 159.570517] ? __dev_printk+0x58/0x6b
[ 159.570525] ? _dev_printk+0x56/0x72
[ 159.570534] ? qmi_decode+0x119/0x470 [qmi_helpers]
[ 159.570543] __free_pages+0x91/0xd0
[ 159.570548] dma_free_contiguous+0x50/0x60
[ 159.570556] dma_direct_free+0xe5/0x140
[ 159.570564] dma_free_attrs+0x35/0x50
[ 159.570570] ath11k_qmi_msg_mem_request_cb+0x2ae/0x3c0 [ath11k]
[ 159.570620] qmi_invoke_handler+0xac/0xe0 [qmi_helpers]
[ 159.570630] qmi_handle_message+0x6d/0x180 [qmi_helpers]
[ 159.570643] qmi_data_ready_work+0x2ca/0x440 [qmi_helpers]
[ 159.570656] process_one_work+0x227/0x440
[ 159.570667] worker_thread+0x31/0x3d0
[ 159.570676] ? process_one_work+0x440/0x440
[ 159.570685] kthread+0xfe/0x130
[ 159.570692] ? kthread_complete_and_exit+0x20/0x20
[ 159.570701] ret_from_fork+0x22/0x30
[ 159.570712] </TASK>
The reason is because when wlan start to recovery, the type, size and
count is not same for the 1st and 2nd QMI_WLFW_REQUEST_MEM_IND message,
Then it leads the parameter size is not correct for the dma_free_coherent().
For the chunk[1], the actual dma size is 524288 which allocate in the
2nd time of the initial wlan load phase, and the size which pass to
dma_free_coherent() is 3784704 which is got in the 1st time of recovery
phase, then warning above happened.
Change to use prev_size of struct target_mem_chunk for the paramter of
dma_free_coherent() since prev_size is the real size of last load/recovery.
Also change to check both type and size of struct target_mem_chunk to
reuse the memory to avoid mismatch buffer size for target. Then the
warning disappear and recovery success. When the 1st QMI_WLFW_REQUEST_MEM_IND
for recovery arrived, the trunk[0] is freed in ath11k_qmi_alloc_target_mem_chunk()
and then dma_alloc_coherent() failed caused by large size, and then
trunk[1] is freed in ath11k_qmi_free_target_mem_chunk(), the left 18
trunks will be reuse for the 2nd QMI_WLFW_REQUEST_MEM_IND message.
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3
Fixes: 5962f370ce ("ath11k: Reuse the available memory after firmware reload")
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220928073832.16251-1-quic_wgong@quicinc.com
Currently, ath11k_pcic_read() returns an error if wakeup()
fails, this makes firmware crash debug quite hard because we can
get nothing.
Change to go ahead on wakeup failure, in that case we still may
get something valid to check. There should be no mislead due
to incorrect content because we are aware of the failure with the
log printed.
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-01720.1-QCAHSPSWPL_V1_V2_SILICONZ_LITE-1
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220928015140.5431-1-quic_bqiang@quicinc.com
We tell driver developers to always pass NAPI_POLL_WEIGHT
as the weight to netif_napi_add(). This may be confusing
to newcomers, drop the weight argument, those who really
need to tweak the weight can use netif_napi_add_weight().
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de> # for CAN
Link: https://lore.kernel.org/r/20220927132753.750069-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, recovery flag is set immediately upon firmware
exit but tx queues are stopped once firmware arrives back
and is ready which is during ath11k_core_restart. Once
ieee80211 hw restart is completed, tx queues are resumed.
If during the time delta between firmware exit and firmware
ready, mac80211 send packets, currently ath11k will drop it
since recovery flag will be set. But warning prints will
come -
"ath11k c000000.wifi: failed to transmit frame -108"
If more tx packets are there, this could lead to flooding
of above print.
However, actually tx queues should be stopped immediately
when firmware leaves. This will prevent packets to get
dropped when firmware is recovering.
Add fix to stop tx queues immediately after firmware exit.
Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.5.0.1-01100-QCAHKSWPL_SILICONZ-1
Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://lore.kernel.org/r/20220923170235.18873-1-quic_adisi@quicinc.com
