summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2024-12-11riscv: Fix IPIs usage in kfence_protect_page()Alexandre Ghiti
flush_tlb_kernel_range() may use IPIs to flush the TLBs of all the cores, which triggers the following warning when the irqs are disabled: [ 3.455330] WARNING: CPU: 1 PID: 0 at kernel/smp.c:815 smp_call_function_many_cond+0x452/0x520 [ 3.456647] Modules linked in: [ 3.457218] CPU: 1 UID: 0 PID: 0 Comm: swapper/1 Not tainted 6.12.0-rc7-00010-g91d3de7240b8 #1 [ 3.457416] Hardware name: QEMU QEMU Virtual Machine, BIOS [ 3.457633] epc : smp_call_function_many_cond+0x452/0x520 [ 3.457736] ra : on_each_cpu_cond_mask+0x1e/0x30 [ 3.457786] epc : ffffffff800b669a ra : ffffffff800b67c2 sp : ff2000000000bb50 [ 3.457824] gp : ffffffff815212b8 tp : ff6000008014f080 t0 : 000000000000003f [ 3.457859] t1 : ffffffff815221e0 t2 : 000000000000000f s0 : ff2000000000bc10 [ 3.457920] s1 : 0000000000000040 a0 : ffffffff815221e0 a1 : 0000000000000001 [ 3.457953] a2 : 0000000000010000 a3 : 0000000000000003 a4 : 0000000000000000 [ 3.458006] a5 : 0000000000000000 a6 : ffffffffffffffff a7 : 0000000000000000 [ 3.458042] s2 : ffffffff815223be s3 : 00fffffffffff000 s4 : ff600001ffe38fc0 [ 3.458076] s5 : ff600001ff950d00 s6 : 0000000200000120 s7 : 0000000000000001 [ 3.458109] s8 : 0000000000000001 s9 : ff60000080841ef0 s10: 0000000000000001 [ 3.458141] s11: ffffffff81524812 t3 : 0000000000000001 t4 : ff60000080092bc0 [ 3.458172] t5 : 0000000000000000 t6 : ff200000000236d0 [ 3.458203] status: 0000000200000100 badaddr: ffffffff800b669a cause: 0000000000000003 [ 3.458373] [<ffffffff800b669a>] smp_call_function_many_cond+0x452/0x520 [ 3.458593] [<ffffffff800b67c2>] on_each_cpu_cond_mask+0x1e/0x30 [ 3.458625] [<ffffffff8000e4ca>] __flush_tlb_range+0x118/0x1ca [ 3.458656] [<ffffffff8000e6b2>] flush_tlb_kernel_range+0x1e/0x26 [ 3.458683] [<ffffffff801ea56a>] kfence_protect+0xc0/0xce [ 3.458717] [<ffffffff801e9456>] kfence_guarded_free+0xc6/0x1c0 [ 3.458742] [<ffffffff801e9d6c>] __kfence_free+0x62/0xc6 [ 3.458764] [<ffffffff801c57d8>] kfree+0x106/0x32c [ 3.458786] [<ffffffff80588cf2>] detach_buf_split+0x188/0x1a8 [ 3.458816] [<ffffffff8058708c>] virtqueue_get_buf_ctx+0xb6/0x1f6 [ 3.458839] [<ffffffff805871da>] virtqueue_get_buf+0xe/0x16 [ 3.458880] [<ffffffff80613d6a>] virtblk_done+0x5c/0xe2 [ 3.458908] [<ffffffff8058766e>] vring_interrupt+0x6a/0x74 [ 3.458930] [<ffffffff800747d8>] __handle_irq_event_percpu+0x7c/0xe2 [ 3.458956] [<ffffffff800748f0>] handle_irq_event+0x3c/0x86 [ 3.458978] [<ffffffff800786cc>] handle_simple_irq+0x9e/0xbe [ 3.459004] [<ffffffff80073934>] generic_handle_domain_irq+0x1c/0x2a [ 3.459027] [<ffffffff804bf87c>] imsic_handle_irq+0xba/0x120 [ 3.459056] [<ffffffff80073934>] generic_handle_domain_irq+0x1c/0x2a [ 3.459080] [<ffffffff804bdb76>] riscv_intc_aia_irq+0x24/0x34 [ 3.459103] [<ffffffff809d0452>] handle_riscv_irq+0x2e/0x4c [ 3.459133] [<ffffffff809d923e>] call_on_irq_stack+0x32/0x40 So only flush the local TLB and let the lazy kfence page fault handling deal with the faults which could happen when a core has an old protected pte version cached in its TLB. That leads to potential inaccuracies which can be tolerated when using kfence. Fixes: 47513f243b45 ("riscv: Enable KFENCE for riscv64") Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20241209074125.52322-1-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-12-11riscv: Fix wrong usage of __pa() on a fixmap addressAlexandre Ghiti
riscv uses fixmap addresses to map the dtb so we can't use __pa() which is reserved for linear mapping addresses. Fixes: b2473a359763 ("of/fdt: add dt_phys arg to early_init_dt_scan and early_init_dt_verify") Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com> Link: https://lore.kernel.org/r/20241209074508.53037-1-alexghiti@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-12-11riscv: Fixup boot failure when CONFIG_DEBUG_RT_MUTEXES=yGuo Ren
When CONFIG_DEBUG_RT_MUTEXES=y, mutex_lock->rt_mutex_try_acquire would change from rt_mutex_cmpxchg_acquire to rt_mutex_slowtrylock(): raw_spin_lock_irqsave(&lock->wait_lock, flags); ret = __rt_mutex_slowtrylock(lock); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); Because queued_spin_#ops to ticket_#ops is changed one by one by jump_label, raw_spin_lock/unlock would cause a deadlock during the changing. That means in arch/riscv/kernel/jump_label.c: 1. arch_jump_label_transform_queue() -> mutex_lock(&text_mutex); +-> raw_spin_lock -> queued_spin_lock |-> raw_spin_unlock -> queued_spin_unlock patch_insn_write -> change the raw_spin_lock to ticket_lock mutex_unlock(&text_mutex); ... 2. /* Dirty the lock value */ arch_jump_label_transform_queue() -> mutex_lock(&text_mutex); +-> raw_spin_lock -> *ticket_lock* |-> raw_spin_unlock -> *queued_spin_unlock* /* BUG: ticket_lock with queued_spin_unlock */ patch_insn_write -> change the raw_spin_unlock to ticket_unlock mutex_unlock(&text_mutex); ... 3. /* Dead lock */ arch_jump_label_transform_queue() -> mutex_lock(&text_mutex); +-> raw_spin_lock -> ticket_lock /* deadlock! */ |-> raw_spin_unlock -> ticket_unlock patch_insn_write -> change other raw_spin_#op -> ticket_#op mutex_unlock(&text_mutex); So, the solution is to disable mutex usage of arch_jump_label_transform_queue() during early_boot_irqs_disabled, just like we have done for stop_machine. Reported-by: Conor Dooley <conor@kernel.org> Signed-off-by: Guo Ren <guoren@linux.alibaba.com> Signed-off-by: Guo Ren <guoren@kernel.org> Fixes: ab83647fadae ("riscv: Add qspinlock support") Link: https://lore.kernel.org/linux-riscv/CAJF2gTQwYTGinBmCSgVUoPv0_q4EPt_+WiyfUA1HViAKgUzxAg@mail.gmail.com/T/#mf488e6347817fca03bb93a7d34df33d8615b3775 Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Alexandre Ghiti <alexghiti@rivosinc.com> Tested-by: Conor Dooley <conor.dooley@microchip.com> Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com> Tested-by: Nam Cao <namcao@linutronix.de> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20241130153310.3349484-1-guoren@kernel.org Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2024-12-11ASoC: fsl_spdif: change IFACE_PCM to IFACE_MIXERShengjiu Wang
As the snd_soc_card_get_kcontrol() is updated to use snd_ctl_find_id_mixer() in commit 897cc72b0837 ("ASoC: soc-card: Use snd_ctl_find_id_mixer() instead of open-coding") which make the iface fix to be IFACE_MIXER. Fixes: 897cc72b0837 ("ASoC: soc-card: Use snd_ctl_find_id_mixer() instead of open-coding") Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com> Link: https://patch.msgid.link/20241126053254.3657344-3-shengjiu.wang@nxp.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: fsl_xcvr: change IFACE_PCM to IFACE_MIXERShengjiu Wang
As the snd_soc_card_get_kcontrol() is updated to use snd_ctl_find_id_mixer() in commit 897cc72b0837 ("ASoC: soc-card: Use snd_ctl_find_id_mixer() instead of open-coding") which make the iface fix to be IFACE_MIXER. Fixes: 897cc72b0837 ("ASoC: soc-card: Use snd_ctl_find_id_mixer() instead of open-coding") Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com> Link: https://patch.msgid.link/20241126053254.3657344-2-shengjiu.wang@nxp.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11libperf: evlist: Fix --cpu argument on hybrid platformJames Clark
Since the linked fixes: commit, specifying a CPU on hybrid platforms results in an error because Perf tries to open an extended type event on "any" CPU which isn't valid. Extended type events can only be opened on CPUs that match the type. Before (working): $ perf record --cpu 1 -- true [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 2.385 MB perf.data (7 samples) ] After (not working): $ perf record -C 1 -- true WARNING: A requested CPU in '1' is not supported by PMU 'cpu_atom' (CPUs 16-27) for event 'cycles:P' Error: The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cpu_atom/cycles:P/). /bin/dmesg | grep -i perf may provide additional information. (Ignore the warning message, that's expected and not particularly relevant to this issue). This is because perf_cpu_map__intersect() of the user specified CPU (1) and one of the PMU's CPUs (16-27) correctly results in an empty (NULL) CPU map. However for the purposes of opening an event, libperf converts empty CPU maps into an any CPU (-1) which the kernel rejects. Fix it by deleting evsels with empty CPU maps in the specific case where user requested CPU maps are evaluated. Fixes: 251aa040244a ("perf parse-events: Wildcard most "numeric" events") Reviewed-by: Ian Rogers <irogers@google.com> Tested-by: Thomas Falcon <thomas.falcon@intel.com> Signed-off-by: James Clark <james.clark@linaro.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/r/20241114160450.295844-2-james.clark@linaro.org Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-12-11perf test expr: Fix system_tsc_freq for only x86Ian Rogers
The refactoring of tool PMU events to have a PMU then adding the expr literals to the tool PMU made it so that the literal system_tsc_freq was only supported on x86. Update the test expectations to match - namely the parsing is x86 specific and only yields a non-zero value on Intel. Fixes: 609aa2667f67 ("perf tool_pmu: Switch to standard pmu functions and json descriptions") Reported-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Closes: https://lore.kernel.org/linux-perf-users/20241022140156.98854-1-atrajeev@linux.vnet.ibm.com/ Co-developed-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Tested-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Ian Rogers <irogers@google.com> Cc: James Clark <james.clark@linaro.org> Cc: akanksha@linux.ibm.com Cc: hbathini@linux.ibm.com Cc: kjain@linux.ibm.com Cc: maddy@linux.ibm.com Cc: disgoel@linux.vnet.ibm.com Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20241205022305.158202-1-irogers@google.com Signed-off-by: Namhyung Kim <namhyung@kernel.org>
2024-12-11selftests/ftrace: adjust offset for kprobe syntax error testHari Bathini
In 'NOFENTRY_ARGS' test case for syntax check, any offset X of `vfs_read+X` except function entry offset (0) fits the criterion, even if that offset is not at instruction boundary, as the parser comes before probing. But with "ENDBR64" instruction on x86, offset 4 is treated as function entry. So, X can't be 4 as well. Thus, 8 was used as offset for the test case. On 64-bit powerpc though, any offset <= 16 can be considered function entry depending on build configuration (see arch_kprobe_on_func_entry() for implementation details). So, use `vfs_read+20` to accommodate that scenario too. Link: https://lore.kernel.org/r/20241129202621.721159-1-hbathini@linux.ibm.com Fixes: 4231f30fcc34a ("selftests/ftrace: Add BTF arguments test cases") Suggested-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com> Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org> Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
2024-12-11Bluetooth: Improve setsockopt() handling of malformed user inputMichal Luczaj
The bt_copy_from_sockptr() return value is being misinterpreted by most users: a non-zero result is mistakenly assumed to represent an error code, but actually indicates the number of bytes that could not be copied. Remove bt_copy_from_sockptr() and adapt callers to use copy_safe_from_sockptr(). For sco_sock_setsockopt() (case BT_CODEC) use copy_struct_from_sockptr() to scrub parts of uninitialized buffer. Opportunistically, rename `len` to `optlen` in hci_sock_setsockopt_old() and hci_sock_setsockopt(). Fixes: 51eda36d33e4 ("Bluetooth: SCO: Fix not validating setsockopt user input") Fixes: a97de7bff13b ("Bluetooth: RFCOMM: Fix not validating setsockopt user input") Fixes: 4f3951242ace ("Bluetooth: L2CAP: Fix not validating setsockopt user input") Fixes: 9e8742cdfc4b ("Bluetooth: ISO: Fix not validating setsockopt user input") Fixes: b2186061d604 ("Bluetooth: hci_sock: Fix not validating setsockopt user input") Reviewed-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com> Reviewed-by: David Wei <dw@davidwei.uk> Signed-off-by: Michal Luczaj <mhal@rbox.co> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
2024-12-11scripts/kernel-doc: Get -export option working againAkira Yokosawa
Since commit cdd30ebb1b9f ("module: Convert symbol namespace to string literal"), exported symbols marked by EXPORT_SYMBOL_NS(_GPL) are ignored by "kernel-doc -export" in fresh build of "make htmldocs". This is because regex in the perl script for those markers fails to match the new signatures: - EXPORT_SYMBOL_NS(symbol, "ns"); - EXPORT_SYMBOL_NS_GPL(symbol, "ns"); Update the regex so that it matches quoted string. Note: Escape sequence of \w is good for C identifiers, but can be too strict for quoted strings. Instead, use \S, which matches any non-whitespace character, for compatibility with possible extension of namespace convention in the future [1]. Fixes: cdd30ebb1b9f ("module: Convert symbol namespace to string literal") Link: https://lore.kernel.org/CAK7LNATMufXP0EA6QUE9hBkZMa6vJO6ZiaYuak2AhOrd2nSVKQ@mail.gmail.com/ [1] Signed-off-by: Akira Yokosawa <akiyks@gmail.com> Cc: Masahiro Yamada <masahiroy@kernel.org> Tested-by: Randy Dunlap <rdunlap@infradead.org> Acked-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Jonathan Corbet <corbet@lwn.net> Link: https://lore.kernel.org/r/e5c43f36-45cd-49f4-b7b8-ff342df3c7a4@gmail.com
2024-12-11ASoC: tas2781: Fix calibration issue in stress testShenghao Ding
One specific test condition: the default registers of p[j].reg ~ p[j+3].reg are 0, TASDEVICE_REG(0x00, 0x14, 0x38)(PLT_FLAG_REG), TASDEVICE_REG(0x00, 0x14, 0x40)(SINEGAIN_REG), and TASDEVICE_REG(0x00, 0x14, 0x44)(SINEGAIN2_REG). After first calibration, they are freshed to TASDEVICE_REG(0x00, 0x1a, 0x20), TASDEVICE_REG(0x00, 0x16, 0x58)(PLT_FLAG_REG), TASDEVICE_REG(0x00, 0x14, 0x44)(SINEGAIN_REG), and TASDEVICE_REG(0x00, 0x16, 0x64)(SINEGAIN2_REG) via "Calibration Start" kcontrol. In second calibration, the p[j].reg ~ p[j+3].reg have already become tas2781_cali_start_reg. However, p[j+2].reg, TASDEVICE_REG(0x00, 0x14, 0x44)(SINEGAIN_REG), will be freshed to TASDEVICE_REG(0x00, 0x16, 0x64), which is the third register in the input params of the kcontrol. This is why only first calibration can work, the second-time, third-time or more-time calibration always failed without reboot. Of course, if no p[j].reg is in the list of tas2781_cali_start_reg, this stress test can work well. Fixes: 49e2e353fb0d ("ASoC: tas2781: Add Calibration Kcontrols for Chromebook") Signed-off-by: Shenghao Ding <shenghao-ding@ti.com> Link: https://patch.msgid.link/20241211043859.1328-1-shenghao-ding@ti.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-10net: renesas: rswitch: handle stop vs interrupt raceNikita Yushchenko
Currently the stop routine of rswitch driver does not immediately prevent hardware from continuing to update descriptors and requesting interrupts. It can happen that when rswitch_stop() executes the masking of interrupts from the queues of the port being closed, napi poll for that port is already scheduled or running on a different CPU. When execution of this napi poll completes, it will unmask the interrupts. And unmasked interrupt can fire after rswitch_stop() returns from napi_disable() call. Then, the handler won't mask it, because napi_schedule_prep() will return false, and interrupt storm will happen. This can't be fixed by making rswitch_stop() call napi_disable() before masking interrupts. In this case, the interrupt storm will happen if interrupt fires between napi_disable() and masking. Fix this by checking for priv->opened_ports bit when unmasking interrupts after napi poll. For that to be consistent, move priv->opened_ports changes into spinlock-protected areas, and reorder other operations in rswitch_open() and rswitch_stop() accordingly. Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com> Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com> Fixes: 3590918b5d07 ("net: ethernet: renesas: Add support for "Ethernet Switch"") Link: https://patch.msgid.link/20241209113204.175015-1-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10Merge branch 'net-renesas-rswitch-several-fixes'Jakub Kicinski
Nikita Yushchenko says: ==================== net: renesas: rswitch: several fixes This series fixes several glitches found in the rswitch driver. Repost of https://lore.kernel.org/20241206190015.4194153-1-nikita.yoush@cogentembedded.com ==================== Link: https://patch.msgid.link/20241208095004.69468-1-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10net: renesas: rswitch: avoid use-after-put for a device tree nodeNikita Yushchenko
The device tree node saved in the rswitch_device structure is used at several driver locations. So passing this node to of_node_put() after the first use is wrong. Move of_node_put() for this node to exit paths. Fixes: b46f1e579329 ("net: renesas: rswitch: Simplify struct phy * handling") Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com> Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com> Link: https://patch.msgid.link/20241208095004.69468-5-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10net: renesas: rswitch: fix leaked pointer on error pathNikita Yushchenko
If error path is taken while filling descriptor for a frame, skb pointer is left in the entry. Later, on the ring entry reuse, the same entry could be used as a part of a multi-descriptor frame, and skb for that new frame could be stored in a different entry. Then, the stale pointer will reach the completion routine, and passed to the release operation. Fix that by clearing the saved skb pointer at the error path. Fixes: d2c96b9d5f83 ("net: rswitch: Add jumbo frames handling for TX") Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com> Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com> Link: https://patch.msgid.link/20241208095004.69468-4-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10net: renesas: rswitch: fix race window between tx start and completeNikita Yushchenko
If hardware is already transmitting, it can start handling the descriptor being written to immediately after it observes updated DT field, before the queue is kicked by a write to GWTRC. If the start_xmit() execution is preempted at unfortunate moment, this transmission can complete, and interrupt handled, before gq->cur gets updated. With the current implementation of completion, this will cause the last entry not completed. Fix that by changing completion loop to check DT values directly, instead of depending on gq->cur. Fixes: 3590918b5d07 ("net: ethernet: renesas: Add support for "Ethernet Switch"") Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com> Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com> Link: https://patch.msgid.link/20241208095004.69468-3-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10net: renesas: rswitch: fix possible early skb releaseNikita Yushchenko
When sending frame split into multiple descriptors, hardware processes descriptors one by one, including writing back DT values. The first descriptor could be already marked as completed when processing of next descriptors for the same frame is still in progress. Although only the last descriptor is configured to generate interrupt, completion of the first descriptor could be noticed by the driver when handling interrupt for the previous frame. Currently, driver stores skb in the entry that corresponds to the first descriptor. This results into skb could be unmapped and freed when hardware did not complete the send yet. This opens a window for corrupting the data being sent. Fix this by saving skb in the entry that corresponds to the last descriptor used to send the frame. Fixes: d2c96b9d5f83 ("net: rswitch: Add jumbo frames handling for TX") Signed-off-by: Nikita Yushchenko <nikita.yoush@cogentembedded.com> Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com> Link: https://patch.msgid.link/20241208095004.69468-2-nikita.yoush@cogentembedded.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10smb: client: destroy cfid_put_wq on module exitEnzo Matsumiya
Fix potential problem in rmmod Signed-off-by: Enzo Matsumiya <ematsumiya@suse.de> Signed-off-by: Steve French <stfrench@microsoft.com>
2024-12-10cifs: Use str_yes_no() helper in cifs_ses_add_channel()Thorsten Blum
Remove hard-coded strings by using the str_yes_no() helper function. Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev> Signed-off-by: Steve French <stfrench@microsoft.com>
2024-12-10cifs: Fix rmdir failure due to ongoing I/O on deleted fileDavid Howells
The cifs_io_request struct (a wrapper around netfs_io_request) holds open the file on the server, even beyond the local Linux file being closed. This can cause problems with Windows-based filesystems as the file's name still exists after deletion until the file is closed, preventing the parent directory from being removed and causing spurious test failures in xfstests due to inability to remove a directory. The symptom looks something like this in the test output: rm: cannot remove '/mnt/scratch/test/p0/d3': Directory not empty rm: cannot remove '/mnt/scratch/test/p1/dc/dae': Directory not empty Fix this by waiting in unlink and rename for any outstanding I/O requests to be completed on the target file before removing that file. Note that this doesn't prevent Linux from trying to start new requests after deletion if it still has the file open locally - something that's perfectly acceptable on a UNIX system. Note also that whilst I've marked this as fixing the commit to make cifs use netfslib, I don't know that it won't occur before that. Fixes: 3ee1a1fc3981 ("cifs: Cut over to using netfslib") Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.com> cc: Jeff Layton <jlayton@kernel.org> cc: linux-cifs@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org Signed-off-by: Steve French <stfrench@microsoft.com>
2024-12-10Merge tag 'wireless-2024-12-10' of ↵Jakub Kicinski
https://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless Johannes Berg says: ==================== A small set of fixes: - avoid CSA warnings during link removal (by changing link bitmap after remove) - fix # of spatial streams initialisation - fix queues getting stuck in some CSA cases and resume failures - fix interface address when switching monitor mode - fix MBSS change flags 32-bit stack corruption - more UBSAN __counted_by "fixes" ... - fix link ID netlink validation * tag 'wireless-2024-12-10' of https://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless: wifi: cfg80211: sme: init n_channels before channels[] access wifi: mac80211: fix station NSS capability initialization order wifi: mac80211: fix vif addr when switching from monitor to station wifi: mac80211: fix a queue stall in certain cases of CSA wifi: mac80211: wake the queues in case of failure in resume wifi: cfg80211: clear link ID from bitmap during link delete after clean up wifi: mac80211: init cnt before accessing elem in ieee80211_copy_mbssid_beacon wifi: mac80211: fix mbss changed flags corruption on 32 bit systems wifi: nl80211: fix NL80211_ATTR_MLO_LINK_ID off-by-one ==================== Link: https://patch.msgid.link/20241210130145.28618-3-johannes@sipsolutions.net Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10tcp: check space before adding MPTCP SYN optionsMoYuanhao
Ensure there is enough space before adding MPTCP options in tcp_syn_options(). Without this check, 'remaining' could underflow, and causes issues. If there is not enough space, MPTCP should not be used. Signed-off-by: MoYuanhao <moyuanhao3676@163.com> Fixes: cec37a6e41aa ("mptcp: Handle MP_CAPABLE options for outgoing connections") Cc: stable@vger.kernel.org Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org> [ Matt: Add Fixes, cc Stable, update Description ] Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org> Reviewed-by: Eric Dumazet <edumazet@google.com> Link: https://patch.msgid.link/20241209-net-mptcp-check-space-syn-v1-1-2da992bb6f74@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10Documentation: networking: Add a caveat to nexthop_compat_mode sysctlPetr Machata
net.ipv4.nexthop_compat_mode was added when nexthop objects were added to provide the view of nexthop objects through the usual lens of the route UAPI. As nexthop objects evolved, the information provided through this lens became incomplete. For example, details of resilient nexthop groups are obviously omitted. Now that 16-bit nexthop group weights are a thing, the 8-bit UAPI cannot convey the >8-bit weight accurately. Instead of inventing workarounds for an obsolete interface, just document the expectations of inaccuracy. Fixes: b72a6a7ab957 ("net: nexthop: Increase weight to u16") Signed-off-by: Petr Machata <petrm@nvidia.com> Reviewed-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://patch.msgid.link/b575e32399ccacd09079b2a218255164535123bd.1733740749.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10bnxt_en: Fix aggregation ID mask to prevent oops on 5760X chipsMichael Chan
The 5760X (P7) chip's HW GRO/LRO interface is very similar to that of the previous generation (5750X or P5). However, the aggregation ID fields in the completion structures on P7 have been redefined from 16 bits to 12 bits. The freed up 4 bits are redefined for part of the metadata such as the VLAN ID. The aggregation ID mask was not modified when adding support for P7 chips. Including the extra 4 bits for the aggregation ID can potentially cause the driver to store or fetch the packet header of GRO/LRO packets in the wrong TPA buffer. It may hit the BUG() condition in __skb_pull() because the SKB contains no valid packet header: kernel BUG at include/linux/skbuff.h:2766! Oops: invalid opcode: 0000 1 PREEMPT SMP NOPTI CPU: 4 UID: 0 PID: 0 Comm: swapper/4 Kdump: loaded Tainted: G OE 6.12.0-rc2+ #7 Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE Hardware name: Dell Inc. PowerEdge R760/0VRV9X, BIOS 1.0.1 12/27/2022 RIP: 0010:eth_type_trans+0xda/0x140 Code: 80 00 00 00 eb c1 8b 47 70 2b 47 74 48 8b 97 d0 00 00 00 83 f8 01 7e 1b 48 85 d2 74 06 66 83 3a ff 74 09 b8 00 04 00 00 eb a5 <0f> 0b b8 00 01 00 00 eb 9c 48 85 ff 74 eb 31 f6 b9 02 00 00 00 48 RSP: 0018:ff615003803fcc28 EFLAGS: 00010283 RAX: 00000000000022d2 RBX: 0000000000000003 RCX: ff2e8c25da334040 RDX: 0000000000000040 RSI: ff2e8c25c1ce8000 RDI: ff2e8c25869f9000 RBP: ff2e8c258c31c000 R08: ff2e8c25da334000 R09: 0000000000000001 R10: ff2e8c25da3342c0 R11: ff2e8c25c1ce89c0 R12: ff2e8c258e0990b0 R13: ff2e8c25bb120000 R14: ff2e8c25c1ce89c0 R15: ff2e8c25869f9000 FS: 0000000000000000(0000) GS:ff2e8c34be300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f05317e4c8 CR3: 000000108bac6006 CR4: 0000000000773ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: <IRQ> ? die+0x33/0x90 ? do_trap+0xd9/0x100 ? eth_type_trans+0xda/0x140 ? do_error_trap+0x65/0x80 ? eth_type_trans+0xda/0x140 ? exc_invalid_op+0x4e/0x70 ? eth_type_trans+0xda/0x140 ? asm_exc_invalid_op+0x16/0x20 ? eth_type_trans+0xda/0x140 bnxt_tpa_end+0x10b/0x6b0 [bnxt_en] ? bnxt_tpa_start+0x195/0x320 [bnxt_en] bnxt_rx_pkt+0x902/0xd90 [bnxt_en] ? __bnxt_tx_int.constprop.0+0x89/0x300 [bnxt_en] ? kmem_cache_free+0x343/0x440 ? __bnxt_tx_int.constprop.0+0x24f/0x300 [bnxt_en] __bnxt_poll_work+0x193/0x370 [bnxt_en] bnxt_poll_p5+0x9a/0x300 [bnxt_en] ? try_to_wake_up+0x209/0x670 __napi_poll+0x29/0x1b0 Fix it by redefining the aggregation ID mask for P5_PLUS chips to be 12 bits. This will work because the maximum aggregation ID is less than 4096 on all P5_PLUS chips. Fixes: 13d2d3d381ee ("bnxt_en: Add new P7 hardware interface definitions") Reviewed-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com> Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com> Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com> Signed-off-by: Michael Chan <michael.chan@broadcom.com> Reviewed-by: Simon Horman <horms@kernel.org> Link: https://patch.msgid.link/20241209015448.1937766-1-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-10Merge tag 'clk-fixes-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux Pull clk fixes from Stephen Boyd: "Two reverts and two EN7581 driver fixes: - Revert the attempt to make CLK_GET_RATE_NOCACHE flag work in clk_set_rate() because it led to problems with the Qualcomm CPUFreq driver - Revert Amlogic reset driver back to the initial implementation. This broke probe of the audio subsystem on axg based platforms and also had compilation problems. We'll try again next time. - Fix a clk frequency and fix array bounds runtime checks in the Airoha EN7581 driver" * tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux: clk: en7523: Initialize num before accessing hws in en7523_register_clocks() clk: en7523: Fix wrong BUS clock for EN7581 clk: amlogic: axg-audio: revert reset implementation Revert "clk: Fix invalid execution of clk_set_rate"
2024-12-10Merge tag 'for-6.13-rc2-tag' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux Pull btrfs fixes from David Sterba: "A few more fixes. Apart from the one liners and updated bio splitting error handling there's a fix for subvolume mount with different flags. This was known and fixed for some time but I've delayed it to give it more testing. - fix unbalanced locking when swapfile activation fails when the subvolume gets deleted in the meantime - add btrfs error handling after bio_split() calls that got error handling recently - during unmount, flush delalloc workers at the right time before the cleaner thread is shut down - fix regression in buffered write folio conversion, explicitly wait for writeback as FGP_STABLE flag is currently a no-op on btrfs - handle race in subvolume mount with different flags, the conversion to the new mount API did not handle the case where multiple subvolumes get mounted in parallel, which is a distro use case" * tag 'for-6.13-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: btrfs: flush delalloc workers queue before stopping cleaner kthread during unmount btrfs: handle bio_split() errors btrfs: properly wait for writeback before buffered write btrfs: fix missing snapshot drew unlock when root is dead during swap activation btrfs: fix mount failure due to remount races
2024-12-10Merge tag 'probes-fixes-v6.13-rc1' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull eprobes fix from Masami Hiramatsu: - release eprobe when failing to add dyn_event. This unregisters event call and release eprobe when it fails to add a dynamic event. Found in cleaning up. * tag 'probes-fixes-v6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: tracing/eprobe: Fix to release eprobe when failed to add dyn_event
2024-12-10ksmbd: set ATTR_CTIME flags when setting mtimeNamjae Jeon
David reported that the new warning from setattr_copy_mgtime is coming like the following. [ 113.215316] ------------[ cut here ]------------ [ 113.215974] WARNING: CPU: 1 PID: 31 at fs/attr.c:300 setattr_copy+0x1ee/0x200 [ 113.219192] CPU: 1 UID: 0 PID: 31 Comm: kworker/1:1 Not tainted 6.13.0-rc1+ #234 [ 113.220127] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-rebuilt.opensuse.org 04/01/2014 [ 113.221530] Workqueue: ksmbd-io handle_ksmbd_work [ksmbd] [ 113.222220] RIP: 0010:setattr_copy+0x1ee/0x200 [ 113.222833] Code: 24 28 49 8b 44 24 30 48 89 53 58 89 43 6c 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc 48 89 df e8 77 d6 ff ff e9 cd fe ff ff <0f> 0b e9 be fe ff ff 66 0 [ 113.225110] RSP: 0018:ffffaf218010fb68 EFLAGS: 00010202 [ 113.225765] RAX: 0000000000000120 RBX: ffffa446815f8568 RCX: 0000000000000003 [ 113.226667] RDX: ffffaf218010fd38 RSI: ffffa446815f8568 RDI: ffffffff94eb03a0 [ 113.227531] RBP: ffffaf218010fb90 R08: 0000001a251e217d R09: 00000000675259fa [ 113.228426] R10: 0000000002ba8a6d R11: ffffa4468196c7a8 R12: ffffaf218010fd38 [ 113.229304] R13: 0000000000000120 R14: ffffffff94eb03a0 R15: 0000000000000000 [ 113.230210] FS: 0000000000000000(0000) GS:ffffa44739d00000(0000) knlGS:0000000000000000 [ 113.231215] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 113.232055] CR2: 00007efe0053d27e CR3: 000000000331a000 CR4: 00000000000006b0 [ 113.232926] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 113.233812] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 113.234797] Call Trace: [ 113.235116] <TASK> [ 113.235393] ? __warn+0x73/0xd0 [ 113.235802] ? setattr_copy+0x1ee/0x200 [ 113.236299] ? report_bug+0xf3/0x1e0 [ 113.236757] ? handle_bug+0x4d/0x90 [ 113.237202] ? exc_invalid_op+0x13/0x60 [ 113.237689] ? asm_exc_invalid_op+0x16/0x20 [ 113.238185] ? setattr_copy+0x1ee/0x200 [ 113.238692] btrfs_setattr+0x80/0x820 [btrfs] [ 113.239285] ? get_stack_info_noinstr+0x12/0xf0 [ 113.239857] ? __module_address+0x22/0xa0 [ 113.240368] ? handle_ksmbd_work+0x6e/0x460 [ksmbd] [ 113.240993] ? __module_text_address+0x9/0x50 [ 113.241545] ? __module_address+0x22/0xa0 [ 113.242033] ? unwind_next_frame+0x10e/0x920 [ 113.242600] ? __pfx_stack_trace_consume_entry+0x10/0x10 [ 113.243268] notify_change+0x2c2/0x4e0 [ 113.243746] ? stack_depot_save_flags+0x27/0x730 [ 113.244339] ? set_file_basic_info+0x130/0x2b0 [ksmbd] [ 113.244993] set_file_basic_info+0x130/0x2b0 [ksmbd] [ 113.245613] ? process_scheduled_works+0xbe/0x310 [ 113.246181] ? worker_thread+0x100/0x240 [ 113.246696] ? kthread+0xc8/0x100 [ 113.247126] ? ret_from_fork+0x2b/0x40 [ 113.247606] ? ret_from_fork_asm+0x1a/0x30 [ 113.248132] smb2_set_info+0x63f/0xa70 [ksmbd] ksmbd is trying to set the atime and mtime via notify_change without also setting the ctime. so This patch add ATTR_CTIME flags when setting mtime to avoid a warning. Reported-by: David Disseldorp <ddiss@suse.de> Signed-off-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
2024-12-10ksmbd: fix racy issue from session lookup and expireNamjae Jeon
Increment the session reference count within the lock for lookup to avoid racy issue with session expire. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-25737 Signed-off-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
2024-12-10ksmbd: retry iterate_dir in smb2_query_dirHobin Woo
Some file systems do not ensure that the single call of iterate_dir reaches the end of the directory. For example, FUSE fetches entries from a daemon using 4KB buffer and stops fetching if entries exceed the buffer. And then an actor of caller, KSMBD, is used to fill the entries from the buffer. Thus, pattern searching on FUSE, files located after the 4KB could not be found and STATUS_NO_SUCH_FILE was returned. Signed-off-by: Hobin Woo <hobin.woo@samsung.com> Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com> Reviewed-by: Namjae Jeon <linkinjeon@kernel.org> Tested-by: Yoonho Shin <yoonho.shin@samsung.com> Acked-by: Namjae Jeon <linkinjeon@kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
2024-12-10bpf: Fix theoretical prog_array UAF in __uprobe_perf_func()Jann Horn
Currently, the pointer stored in call->prog_array is loaded in __uprobe_perf_func(), with no RCU annotation and no immediately visible RCU protection, so it looks as if the loaded pointer can immediately be dangling. Later, bpf_prog_run_array_uprobe() starts a RCU-trace read-side critical section, but this is too late. It then uses rcu_dereference_check(), but this use of rcu_dereference_check() does not actually dereference anything. Fix it by aligning the semantics to bpf_prog_run_array(): Let the caller provide rcu_read_lock_trace() protection and then load call->prog_array with rcu_dereference_check(). This issue seems to be theoretical: I don't know of any way to reach this code without having handle_swbp() further up the stack, which is already holding a rcu_read_lock_trace() lock, so where we take rcu_read_lock_trace() in __uprobe_perf_func()/bpf_prog_run_array_uprobe() doesn't actually have any effect. Fixes: 8c7dcb84e3b7 ("bpf: implement sleepable uprobes by chaining gps") Suggested-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Jann Horn <jannh@google.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20241210-bpf-fix-uprobe-uaf-v4-1-5fc8959b2b74@google.com
2024-12-10block: get wp_offset by bdev_offset_from_zone_startLongPing Wei
Call bdev_offset_from_zone_start() instead of open-coding it. Fixes: dd291d77cc90 ("block: Introduce zone write plugging") Signed-off-by: LongPing Wei <weilongping@oppo.com> Reviewed-by: Damien Le Moal <dlemoal@kernel.org> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Link: https://lore.kernel.org/r/20241107020439.1644577-1-weilongping@oppo.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-12-10bpf: fix potential error returnAnton Protopopov
The bpf_remove_insns() function returns WARN_ON_ONCE(error), where error is a result of bpf_adj_branches(), and thus should be always 0 However, if for any reason it is not 0, then it will be converted to boolean by WARN_ON_ONCE and returned to user space as 1, not an actual error value. Fix this by returning the original err after the WARN check. Signed-off-by: Anton Protopopov <aspsk@isovalent.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20241210114245.836164-1-aspsk@isovalent.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10Documentation: PM: Clarify pm_runtime_resume_and_get() return valuePaul Barker
Update the documentation to match the behaviour of the code. pm_runtime_resume_and_get() always returns 0 on success, even if __pm_runtime_resume() returns 1. Fixes: 2c412337cfe6 ("PM: runtime: Add documentation for pm_runtime_resume_and_get()") Signed-off-by: Paul Barker <paul.barker.ct@bp.renesas.com> Link: https://patch.msgid.link/20241203143729.478-1-paul.barker.ct@bp.renesas.com [ rjw: Subject and changelog edits, adjusted new comment formatting ] Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2024-12-10Merge branch 'bpf-track-changes_pkt_data-property-for-global-functions'Alexei Starovoitov
Eduard Zingerman says: ==================== bpf: track changes_pkt_data property for global functions Nick Zavaritsky reported [0] a bug in verifier, where the following unsafe program is not rejected: __attribute__((__noinline__)) long skb_pull_data(struct __sk_buff *sk, __u32 len) { return bpf_skb_pull_data(sk, len); } SEC("tc") int test_invalidate_checks(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; if ((void *)(p + 1) > (void *)(long)sk->data_end) return TCX_DROP; skb_pull_data(sk, 0); /* not safe, p is invalid after bpf_skb_pull_data call */ *p = 42; return TCX_PASS; } This happens because verifier does not track package invalidation effect of global sub-programs. This patch-set fixes the issue by modifying check_cfg() to compute whether or not each sub-program calls (directly or indirectly) helper invalidating packet pointers. As global functions could be replaced with extension programs, a new field 'changes_pkt_data' is added to struct bpf_prog_aux. Verifier only allows replacing functions that do not change packet data with functions that do not change packet data. In case if there is a need to a have a global function that does not change packet data, but allow replacing it with function that does, the recommendation is to add a noop call to a helper, e.g.: - for skb do 'bpf_skb_change_proto(skb, 0, 0)'; - for xdp do 'bpf_xdp_adjust_meta(xdp, 0)'. Functions also can do tail calls. Effects of the tail call cannot be analyzed before-hand, thus verifier assumes that tail calls always change packet data. Changes v1 [1] -> v2: - added handling of extension programs and tail calls (thanks, Alexei, for all the input). [0] https://lore.kernel.org/bpf/0498CA22-5779-4767-9C0C-A9515CEA711F@gmail.com/ [1] https://lore.kernel.org/bpf/20241206040307.568065-1-eddyz87@gmail.com/ ==================== Link: https://patch.msgid.link/20241210041100.1898468-1-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10selftests/bpf: validate that tail call invalidates packet pointersEduard Zingerman
Add a test case with a tail call done from a global sub-program. Such tails calls should be considered as invalidating packet pointers. Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-9-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10bpf: consider that tail calls invalidate packet pointersEduard Zingerman
Tail-called programs could execute any of the helpers that invalidate packet pointers. Hence, conservatively assume that each tail call invalidates packet pointers. Making the change in bpf_helper_changes_pkt_data() automatically makes use of check_cfg() logic that computes 'changes_pkt_data' effect for global sub-programs, such that the following program could be rejected: int tail_call(struct __sk_buff *sk) { bpf_tail_call_static(sk, &jmp_table, 0); return 0; } SEC("tc") int not_safe(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; ... make p valid ... tail_call(sk); *p = 42; /* this is unsafe */ ... } The tc_bpf2bpf.c:subprog_tc() needs change: mark it as a function that can invalidate packet pointers. Otherwise, it can't be freplaced with tailcall_freplace.c:entry_freplace() that does a tail call. Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-8-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10selftests/bpf: freplace tests for tracking of changes_packet_dataEduard Zingerman
Try different combinations of global functions replacement: - replace function that changes packet data with one that doesn't; - replace function that changes packet data with one that does; - replace function that doesn't change packet data with one that does; - replace function that doesn't change packet data with one that doesn't; Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-7-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10bpf: check changes_pkt_data property for extension programsEduard Zingerman
When processing calls to global sub-programs, verifier decides whether to invalidate all packet pointers in current state depending on the changes_pkt_data property of the global sub-program. Because of this, an extension program replacing a global sub-program must be compatible with changes_pkt_data property of the sub-program being replaced. This commit: - adds changes_pkt_data flag to struct bpf_prog_aux: - this flag is set in check_cfg() for main sub-program; - in jit_subprogs() for other sub-programs; - modifies bpf_check_attach_btf_id() to check changes_pkt_data flag; - moves call to check_attach_btf_id() after the call to check_cfg(), because it needs changes_pkt_data flag to be set: bpf_check: ... ... - check_attach_btf_id resolve_pseudo_ldimm64 resolve_pseudo_ldimm64 --> bpf_prog_is_offloaded bpf_prog_is_offloaded check_cfg check_cfg + check_attach_btf_id ... ... The following fields are set by check_attach_btf_id(): - env->ops - prog->aux->attach_btf_trace - prog->aux->attach_func_name - prog->aux->attach_func_proto - prog->aux->dst_trampoline - prog->aux->mod - prog->aux->saved_dst_attach_type - prog->aux->saved_dst_prog_type - prog->expected_attach_type Neither of these fields are used by resolve_pseudo_ldimm64() or bpf_prog_offload_verifier_prep() (for netronome and netdevsim drivers), so the reordering is safe. Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com> Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-6-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10selftests/bpf: test for changing packet data from global functionsEduard Zingerman
Check if verifier is aware of packet pointers invalidation done in global functions. Based on a test shared by Nick Zavaritsky in [0]. [0] https://lore.kernel.org/bpf/0498CA22-5779-4767-9C0C-A9515CEA711F@gmail.com/ Suggested-by: Nick Zavaritsky <mejedi@gmail.com> Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-5-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10bpf: track changes_pkt_data property for global functionsEduard Zingerman
When processing calls to certain helpers, verifier invalidates all packet pointers in a current state. For example, consider the following program: __attribute__((__noinline__)) long skb_pull_data(struct __sk_buff *sk, __u32 len) { return bpf_skb_pull_data(sk, len); } SEC("tc") int test_invalidate_checks(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; if ((void *)(p + 1) > (void *)(long)sk->data_end) return TCX_DROP; skb_pull_data(sk, 0); *p = 42; return TCX_PASS; } After a call to bpf_skb_pull_data() the pointer 'p' can't be used safely. See function filter.c:bpf_helper_changes_pkt_data() for a list of such helpers. At the moment verifier invalidates packet pointers when processing helper function calls, and does not traverse global sub-programs when processing calls to global sub-programs. This means that calls to helpers done from global sub-programs do not invalidate pointers in the caller state. E.g. the program above is unsafe, but is not rejected by verifier. This commit fixes the omission by computing field bpf_subprog_info->changes_pkt_data for each sub-program before main verification pass. changes_pkt_data should be set if: - subprogram calls helper for which bpf_helper_changes_pkt_data returns true; - subprogram calls a global function, for which bpf_subprog_info->changes_pkt_data should be set. The verifier.c:check_cfg() pass is modified to compute this information. The commit relies on depth first instruction traversal done by check_cfg() and absence of recursive function calls: - check_cfg() would eventually visit every call to subprogram S in a state when S is fully explored; - when S is fully explored: - every direct helper call within S is explored (and thus changes_pkt_data is set if needed); - every call to subprogram S1 called by S was visited with S1 fully explored (and thus S inherits changes_pkt_data from S1). The downside of such approach is that dead code elimination is not taken into account: if a helper call inside global function is dead because of current configuration, verifier would conservatively assume that the call occurs for the purpose of the changes_pkt_data computation. Reported-by: Nick Zavaritsky <mejedi@gmail.com> Closes: https://lore.kernel.org/bpf/0498CA22-5779-4767-9C0C-A9515CEA711F@gmail.com/ Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-4-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10bpf: refactor bpf_helper_changes_pkt_data to use helper numberEduard Zingerman
Use BPF helper number instead of function pointer in bpf_helper_changes_pkt_data(). This would simplify usage of this function in verifier.c:check_cfg() (in a follow-up patch), where only helper number is easily available and there is no real need to lookup helper proto. Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-3-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10bpf: add find_containing_subprog() utility functionEduard Zingerman
Add a utility function, looking for a subprogram containing a given instruction index, rewrite find_subprog() to use this function. Signed-off-by: Eduard Zingerman <eddyz87@gmail.com> Link: https://lore.kernel.org/r/20241210041100.1898468-2-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-12-10bpf,perf: Fix invalid prog_array access in perf_event_detach_bpf_progJiri Olsa
Syzbot reported [1] crash that happens for following tracing scenario: - create tracepoint perf event with attr.inherit=1, attach it to the process and set bpf program to it - attached process forks -> chid creates inherited event the new child event shares the parent's bpf program and tp_event (hence prog_array) which is global for tracepoint - exit both process and its child -> release both events - first perf_event_detach_bpf_prog call will release tp_event->prog_array and second perf_event_detach_bpf_prog will crash, because tp_event->prog_array is NULL The fix makes sure the perf_event_detach_bpf_prog checks prog_array is valid before it tries to remove the bpf program from it. [1] https://lore.kernel.org/bpf/Z1MR6dCIKajNS6nU@krava/T/#m91dbf0688221ec7a7fc95e896a7ef9ff93b0b8ad Fixes: 0ee288e69d03 ("bpf,perf: Fix perf_event_detach_bpf_prog error handling") Reported-by: syzbot+2e0d2840414ce817aaac@syzkaller.appspotmail.com Signed-off-by: Jiri Olsa <jolsa@kernel.org> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20241208142507.1207698-1-jolsa@kernel.org
2024-12-10bpf: Fix UAF via mismatching bpf_prog/attachment RCU flavorsJann Horn
Uprobes always use bpf_prog_run_array_uprobe() under tasks-trace-RCU protection. But it is possible to attach a non-sleepable BPF program to a uprobe, and non-sleepable BPF programs are freed via normal RCU (see __bpf_prog_put_noref()). This leads to UAF of the bpf_prog because a normal RCU grace period does not imply a tasks-trace-RCU grace period. Fix it by explicitly waiting for a tasks-trace-RCU grace period after removing the attachment of a bpf_prog to a perf_event. Fixes: 8c7dcb84e3b7 ("bpf: implement sleepable uprobes by chaining gps") Suggested-by: Andrii Nakryiko <andrii@kernel.org> Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Jann Horn <jannh@google.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20241210-bpf-fix-actual-uprobe-uaf-v1-1-19439849dd44@google.com
2024-12-10ARC: bpf: Correct conditional check in 'check_jmp_32'Hardevsinh Palaniya
The original code checks 'if (ARC_CC_AL)', which is always true since ARC_CC_AL is a constant. This makes the check redundant and likely obscures the intention of verifying whether the jump is conditional. Updates the code to check cond == ARC_CC_AL instead, reflecting the intent to differentiate conditional from unconditional jumps. Suggested-by: Vadim Fedorenko <vadim.fedorenko@linux.dev> Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev> Acked-by: Shahab Vahedi <list+bpf@vahedi.org> Signed-off-by: Hardevsinh Palaniya <hardevsinh.palaniya@siliconsignals.io> Signed-off-by: Vineet Gupta <vgupta@kernel.org>
2024-12-10ARC: dts: Replace deprecated snps,nr-gpios property for ↵Uwe Kleine-König
snps,dw-apb-gpio-port devices snps,dw-apb-gpio-port is deprecated since commit ef42a8da3cf3 ("dt-bindings: gpio: dwapb: Add ngpios property support"). The respective driver supports this since commit 7569486d79ae ("gpio: dwapb: Add ngpios DT-property support") which is included in Linux v5.10-rc1. This change was created using git grep -l snps,nr-gpios arch/arc/boot/dts | xargs perl -p -i -e 's/\bsnps,nr-gpios\b/ngpios/ . Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com> Signed-off-by: Vineet Gupta <vgupta@kernel.org>
2024-12-10ARC: build: Use __force to suppress per-CPU cmpxchg warningsPaul E. McKenney
Currently, the cast of the first argument to cmpxchg_emu_u8() drops the __percpu address-space designator, which results in sparse complaints when applying cmpxchg() to per-CPU variables in ARC. Therefore, use __force to suppress these complaints, given that this does not pertain to cmpxchg() semantics, which are plently well-defined on variables in general, whether per-CPU or otherwise. Reported-by: kernel test robot <lkp@intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202409251336.ToC0TvWB-lkp@intel.com/ Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Cc: <linux-snps-arc@lists.infradead.org> Signed-off-by: Vineet Gupta <vgupta@kernel.org>
2024-12-10ARC: fix reference of dependency for PAE40 configLukas Bulwahn
Commit d71e629bed5b ("ARC: build: disallow invalid PAE40 + 4K page config") reworks the build dependencies for ARC_HAS_PAE40, and accidentally refers to the non-existing config option MMU_V4 rather than the intended option ARC_MMU_V4. Note the missing prefix in the name here. Refer to the intended config option in the dependency of the ARC_HAS_PAE40 config. Fixes: d71e629bed5b ("ARC: build: disallow invalid PAE40 + 4K page config") Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com> Signed-off-by: Vineet Gupta <vgupta@kernel.org>
2024-12-10ARC: build: disallow invalid PAE40 + 4K page configVineet Gupta
The config option being built was | CONFIG_ARC_MMU_V4=y | CONFIG_ARC_PAGE_SIZE_4K=y | CONFIG_HIGHMEM=y | CONFIG_ARC_HAS_PAE40=y This was hitting a BUILD_BUG_ON() since a 4K page can't hoist 1k, 8-byte PTE entries (8 byte due to PAE40). BUILD_BUG_ON() is a good last ditch resort, but such a config needs to be disallowed explicitly in Kconfig. Side-note: the actual fix is single liner dependency, but while at it cleaned out a few things: - 4K dependency on MMU v3 or v4 is always true, since 288ff7de62af09 ("ARC: retire MMUv1 and MMUv2 support") - PAE40 dependency in on MMU ver not really ISA, although that follows eventually. Reported-by: kernel test robot <lkp@intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202409160223.xydgucbY-lkp@intel.com/ Signed-off-by: Vineet Gupta <vgupta@kernel.org>
generated by cgit v1.2.3 (git 2.39.1) at 2025-07-29 22:19:51 +0000