kernel/linux
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ synced 2026-11-08 18:57:22 +00:00
Code Issues Releases Packages Activity
linux/drivers/base/devcoredump.c

473 lines
14 KiB
Raw Normal View History

driver core: add SPDX identifiers to all driver core files It's good to have SPDX identifiers in all files to make it easier to audit the kernel tree for correct licenses. Update the driver core files files with the correct SPDX license identifier based on the license text in the file itself. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This work is based on a script and data from Thomas Gleixner, Philippe Ombredanne, and Kate Stewart. Cc: Johannes Berg <johannes@sipsolutions.net> Cc: "Luis R. Rodriguez" <mcgrof@kernel.org> Cc: William Breathitt Gray <vilhelm.gray@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Philippe Ombredanne <pombredanne@nexb.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-07 17:30:07 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Constify 'struct bin_attribute' The sysfs core now allows instances of 'struct bin_attribute' to be moved into read-only memory. Make use of that to protect them against accidental or malicious modifications. Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Link: https://lore.kernel.org/r/20250114-sysfs-const-bin_attr-devcoredump-v1-2-fa93be30efae@weissschuh.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-01-14 22:44:59 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Constify 'struct bin_attribute' The sysfs core now allows instances of 'struct bin_attribute' to be moved into read-only memory. Make use of that to protect them against accidental or malicious modifications. Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Link: https://lore.kernel.org/r/20250114-sysfs-const-bin_attr-devcoredump-v1-2-fa93be30efae@weissschuh.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-01-14 22:44:59 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Constify 'struct bin_attribute' The sysfs core now allows instances of 'struct bin_attribute' to be moved into read-only memory. Make use of that to protect them against accidental or malicious modifications. Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Link: https://lore.kernel.org/r/20250114-sysfs-const-bin_attr-devcoredump-v1-2-fa93be30efae@weissschuh.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-01-14 22:44:59 +01:00
devcoredump: Define 'struct bin_attribute' through macro The macro saves some lines of code and simplifies the constification of the attribute. Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Link: https://lore.kernel.org/r/20250114-sysfs-const-bin_attr-devcoredump-v1-1-fa93be30efae@weissschuh.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-01-14 22:44:58 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Constify 'struct bin_attribute' The sysfs core now allows instances of 'struct bin_attribute' to be moved into read-only memory. Make use of that to protect them against accidental or malicious modifications. Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Link: https://lore.kernel.org/r/20250114-sysfs-const-bin_attr-devcoredump-v1-2-fa93be30efae@weissschuh.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-01-14 22:44:59 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
sysfs: treewide: switch back to attribute_group::bin_attrs The normal bin_attrs field can now handle const pointers. This makes the _new variant unnecessary. Switch all users back. Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Link: https://lore.kernel.org/r/20250530-sysfs-const-bin_attr-final-v3-4-724bfcf05b99@weissschuh.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-05-30 05:54:38 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
driver core: class: mark the struct class for sysfs callbacks as constant struct class should never be modified in a sysfs callback as there is nothing in the structure to modify, and frankly, the structure is almost never used in a sysfs callback, so mark it as constant to allow struct class to be moved to read-only memory. While we are touching all class sysfs callbacks also mark the attribute as constant as it can not be modified. The bonding code still uses this structure so it can not be removed from the function callbacks. Cc: "David S. Miller" <davem@davemloft.net> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Bartosz Golaszewski <brgl@bgdev.pl> Cc: Eric Dumazet <edumazet@google.com> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Linus Walleij <linus.walleij@linaro.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Miquel Raynal <miquel.raynal@bootlin.com> Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Russ Weight <russell.h.weight@intel.com> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steve French <sfrench@samba.org> Cc: Vignesh Raghavendra <vigneshr@ti.com> Cc: linux-cifs@vger.kernel.org Cc: linux-gpio@vger.kernel.org Cc: linux-mtd@lists.infradead.org Cc: linux-rdma@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: netdev@vger.kernel.org Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Link: https://lore.kernel.org/r/20230325084537.3622280-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-03-25 09:45:37 +01:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
drivers core: Miscellaneous changes for sysfs_emit Change additional instances that could use sysfs_emit and sysfs_emit_at that the coccinelle script could not convert. o macros creating show functions with ## concatenation o unbound sprintf uses with buf+len for start of output to sysfs_emit_at o returns with ?: tests and sprintf to sysfs_emit o sysfs output with struct class * not struct device * arguments Miscellanea: o remove unnecessary initializations around these changes o consistently use int len for return length of show functions o use octal permissions and not S_<FOO> o rename a few show function names so DEVICE_ATTR_<FOO> can be used o use DEVICE_ATTR_ADMIN_RO where appropriate o consistently use const char *output for strings o checkpatch/style neatening Signed-off-by: Joe Perches <joe@perches.com> Link: https://lore.kernel.org/r/8bc24444fe2049a9b2de6127389b57edfdfe324d.1600285923.git.joe@perches.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-16 13:40:42 -07:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: cleanup some comments Correct a spello, remove an extra space between words, and fix one kernel-doc warning: drivers/base/devcoredump.c:292: warning: No description found for return value of 'devcd_read_from_sgtable' Fixes: 522566376a3f ("devcoredump: add scatterlist support") Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Aviya Erenfeld <aviya.erenfeld@intel.com> Cc: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/20241130023554.538820-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-11-29 18:35:54 -08:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
driver core: class: mark the struct class for sysfs callbacks as constant struct class should never be modified in a sysfs callback as there is nothing in the structure to modify, and frankly, the structure is almost never used in a sysfs callback, so mark it as constant to allow struct class to be moved to read-only memory. While we are touching all class sysfs callbacks also mark the attribute as constant as it can not be modified. The bonding code still uses this structure so it can not be removed from the function callbacks. Cc: "David S. Miller" <davem@davemloft.net> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Bartosz Golaszewski <brgl@bgdev.pl> Cc: Eric Dumazet <edumazet@google.com> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Linus Walleij <linus.walleij@linaro.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Miquel Raynal <miquel.raynal@bootlin.com> Cc: Namjae Jeon <linkinjeon@kernel.org> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Russ Weight <russell.h.weight@intel.com> Cc: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Steve French <sfrench@samba.org> Cc: Vignesh Raghavendra <vigneshr@ti.com> Cc: linux-cifs@vger.kernel.org Cc: linux-gpio@vger.kernel.org Cc: linux-mtd@lists.infradead.org Cc: linux-rdma@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: netdev@vger.kernel.org Reviewed-by: Luis Chamberlain <mcgrof@kernel.org> Link: https://lore.kernel.org/r/20230325084537.3622280-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-03-25 09:45:37 +01:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
driver core: devcoredump: convert to use class_groups Convert devcoredump to use class_groups instead of class_attrs as that's the correct way to handle lists of class attribute files. Acked-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-11-28 16:41:58 +01:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
driver core: devcoredump: convert to use class_groups Convert devcoredump to use class_groups instead of class_attrs as that's the correct way to handle lists of class attribute files. Acked-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-11-28 16:41:58 +01:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
driver core: devcoredump: convert to use class_groups Convert devcoredump to use class_groups instead of class_attrs as that's the correct way to handle lists of class attribute files. Acked-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-11-28 16:41:58 +01:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
driver core: devcoredump: convert to use class_groups Convert devcoredump to use class_groups instead of class_attrs as that's the correct way to handle lists of class attribute files. Acked-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-11-28 16:41:58 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: use memory_read_from_buffer Use memory_read_from_buffer() to simplify devcd_readv(). Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Reviewed-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Link: https://lore.kernel.org/r/1564243146-5681-2-git-send-email-akinobu.mita@gmail.com Signed-off-by: Johannes Berg <johannes.berg@intel.com> Link: https://lore.kernel.org/r/20190731100007.32684-1-johannes@sipsolutions.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-07-31 12:00:06 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
devcoredump: fix kernel-doc warning remove make W=1 warnings drivers/base/devcoredump.c:208: warning: Function parameter or member 'data' not described in 'devcd_free_sgtable' drivers/base/devcoredump.c:208: warning: Excess function parameter 'table' description in 'devcd_free_sgtable' drivers/base/devcoredump.c:225: warning: expecting prototype for devcd_read_from_table(). Prototype was for devcd_read_from_sgtable() instead Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/20210331232614.304591-8-pierre-louis.bossart@linux.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-03-31 18:26:14 -05:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
devcoredump: fix kernel-doc warning remove make W=1 warnings drivers/base/devcoredump.c:208: warning: Function parameter or member 'data' not described in 'devcd_free_sgtable' drivers/base/devcoredump.c:208: warning: Excess function parameter 'table' description in 'devcd_free_sgtable' drivers/base/devcoredump.c:225: warning: expecting prototype for devcd_read_from_table(). Prototype was for devcd_read_from_sgtable() instead Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Link: https://lore.kernel.org/r/20210331232614.304591-8-pierre-louis.bossart@linux.intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-03-31 18:26:14 -05:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
devcoredump: cleanup some comments Correct a spello, remove an extra space between words, and fix one kernel-doc warning: drivers/base/devcoredump.c:292: warning: No description found for return value of 'devcd_read_from_sgtable' Fixes: 522566376a3f ("devcoredump: add scatterlist support") Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Aviya Erenfeld <aviya.erenfeld@intel.com> Cc: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/20241130023554.538820-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-11-29 18:35:54 -08:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
devcoredump: Add dev_coredump_put() It is useful for modules that do not want to keep coredump available after its unload. Otherwise, the coredump would only be removed after DEVCD_TIMEOUT seconds. v2: - dev_coredump_put() documentation updated (Mukesh) Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Jonathan Cavitt <jonathan.cavitt@intel.com> Reviewed-by: Johannes Berg <johannes@sipsolutions.net> Acked-by: Jonathan Cavitt <jonathan.cavitt@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Link: https://patchwork.freedesktop.org/patch/msgid/20240409200206.108452-1-jose.souza@intel.com Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2024-04-09 13:02:05 -07:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Add dev_coredumpm_timeout() Add function to set a custom coredump timeout. For Xe driver usage, current 5 minutes timeout may be too short for users to search and understand what needs to be done to capture coredump to report bugs. We have plans to automate(distribute a udev script) it but at the end will be up to distros and users to pack it so having a option to increase the timeout is a safer option. v2: - replace dev_coredump_timeout_set() by dev_coredumpm_timeout() (Mukesh) v3: - make dev_coredumpm() static inline (Johannes) v5: - rename DEVCOREDUMP_TIMEOUT -> DEVCD_TIMEOUT to avoid redefinition in include/net/bluetooth/coredump.h v6: - fix definition of dev_coredumpm_timeout() when CONFIG_DEV_COREDUMP is disabled Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Jonathan Cavitt <jonathan.cavitt@intel.com> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Johannes Berg <johannes@sipsolutions.net> Link: https://patchwork.freedesktop.org/patch/msgid/20240611174716.72660-1-jose.souza@intel.com Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2024-06-11 10:47:15 -07:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Add dev_coredumpm_timeout() Add function to set a custom coredump timeout. For Xe driver usage, current 5 minutes timeout may be too short for users to search and understand what needs to be done to capture coredump to report bugs. We have plans to automate(distribute a udev script) it but at the end will be up to distros and users to pack it so having a option to increase the timeout is a safer option. v2: - replace dev_coredump_timeout_set() by dev_coredumpm_timeout() (Mukesh) v3: - make dev_coredumpm() static inline (Johannes) v5: - rename DEVCOREDUMP_TIMEOUT -> DEVCD_TIMEOUT to avoid redefinition in include/net/bluetooth/coredump.h v6: - fix definition of dev_coredumpm_timeout() when CONFIG_DEV_COREDUMP is disabled Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Jonathan Cavitt <jonathan.cavitt@intel.com> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Johannes Berg <johannes@sipsolutions.net> Link: https://patchwork.freedesktop.org/patch/msgid/20240611174716.72660-1-jose.souza@intel.com Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2024-06-11 10:47:15 -07:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Add dev_coredumpm_timeout() Add function to set a custom coredump timeout. For Xe driver usage, current 5 minutes timeout may be too short for users to search and understand what needs to be done to capture coredump to report bugs. We have plans to automate(distribute a udev script) it but at the end will be up to distros and users to pack it so having a option to increase the timeout is a safer option. v2: - replace dev_coredump_timeout_set() by dev_coredumpm_timeout() (Mukesh) v3: - make dev_coredumpm() static inline (Johannes) v5: - rename DEVCOREDUMP_TIMEOUT -> DEVCD_TIMEOUT to avoid redefinition in include/net/bluetooth/coredump.h v6: - fix definition of dev_coredumpm_timeout() when CONFIG_DEV_COREDUMP is disabled Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Jonathan Cavitt <jonathan.cavitt@intel.com> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Johannes Berg <johannes@sipsolutions.net> Link: https://patchwork.freedesktop.org/patch/msgid/20240611174716.72660-1-jose.souza@intel.com Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2024-06-11 10:47:15 -07:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: provide a one-way disable function Since device/firmware coredumps can contain private data, it can be desirable to turn them off unconditionally to be certain that no such data will be collected by the system. To achieve this, provide a "disabled" sysfs class attribute that can only be changed from 0 to 1 and not back. Upon disabling, discard existing coredumps and stop storing new ones. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-11-13 22:16:29 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
treewide: Replace kmalloc with kmalloc_obj for non-scalar types This is the result of running the Coccinelle script from scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to avoid scalar types (which need careful case-by-case checking), and instead replace kmalloc-family calls that allocate struct or union object instances: Single allocations: kmalloc(sizeof(TYPE), ...) are replaced with: kmalloc_obj(TYPE, ...) Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...) are replaced with: kmalloc_objs(TYPE, COUNT, ...) Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...) are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...) (where TYPE may also be *VAR) The resulting allocations no longer return "void *", instead returning "TYPE *". Signed-off-by: Kees Cook <kees@kernel.org>
2026-02-20 23:49:23 -08:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Send uevent once devcd is ready dev_coredumpm() creates a devcoredump device and adds it to the core kernel framework which eventually end up sending uevent to the user space and later creates a symbolic link to the failed device. An application running in userspace may be interested in this symbolic link to get the name of the failed device. In a issue scenario, once uevent sent to the user space it start reading '/sys/class/devcoredump/devcdX/failing_device' to get the actual name of the device which might not been created and it is in its path of creation. To fix this, suppress sending uevent till the failing device symbolic link gets created and send uevent once symbolic link is created successfully. Fixes: 833c95456a70 ("device coredump: add new device coredump class") Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1700232572-25823-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-11-17 20:19:32 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: avoid -Wempty-body warnings Cleaning out the last -Wempty-body warnings found some interesting cases with empty macros, along with harmless warnings like this one: drivers/base/devcoredump.c: In function 'dev_coredumpm': drivers/base/devcoredump.c:297:56: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 297 | /* nothing - symlink will be missing */; | ^ drivers/base/devcoredump.c:301:56: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 301 | /* nothing - symlink will be missing */; | ^ Randy tried addressing this one before, and there were multiple other ideas in that thread. Add a runtime warning and code comment here. Link: https://lore.kernel.org/lkml/20200418184111.13401-8-rdunlap@infradead.org/ Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Link: https://lore.kernel.org/r/20210322114258.3420937-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-03-22 12:42:51 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: avoid -Wempty-body warnings Cleaning out the last -Wempty-body warnings found some interesting cases with empty macros, along with harmless warnings like this one: drivers/base/devcoredump.c: In function 'dev_coredumpm': drivers/base/devcoredump.c:297:56: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 297 | /* nothing - symlink will be missing */; | ^ drivers/base/devcoredump.c:301:56: error: suggest braces around empty body in an 'if' statement [-Werror=empty-body] 301 | /* nothing - symlink will be missing */; | ^ Randy tried addressing this one before, and there were multiple other ideas in that thread. Add a runtime warning and code comment here. Link: https://lore.kernel.org/lkml/20200418184111.13401-8-rdunlap@infradead.org/ Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Link: https://lore.kernel.org/r/20210322114258.3420937-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-03-22 12:42:51 +01:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Send uevent once devcd is ready dev_coredumpm() creates a devcoredump device and adds it to the core kernel framework which eventually end up sending uevent to the user space and later creates a symbolic link to the failed device. An application running in userspace may be interested in this symbolic link to get the name of the failed device. In a issue scenario, once uevent sent to the user space it start reading '/sys/class/devcoredump/devcdX/failing_device' to get the actual name of the device which might not been created and it is in its path of creation. To fix this, suppress sending uevent till the failing device symbolic link gets created and send uevent once symbolic link is created successfully. Fixes: 833c95456a70 ("device coredump: add new device coredump class") Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1700232572-25823-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-11-17 20:19:32 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump : Serialize devcd_del work In following scenario(diagram), when one thread X running dev_coredumpm() adds devcd device to the framework which sends uevent notification to userspace and another thread Y reads this uevent and call to devcd_data_write() which eventually try to delete the queued timer that is not initialized/queued yet. So, debug object reports some warning and in the meantime, timer is initialized and queued from X path. and from Y path, it gets reinitialized again and timer->entry.pprev=NULL and try_to_grab_pending() stucks. To fix this, introduce mutex and a boolean flag to serialize the behaviour. cpu0(X) cpu1(Y) dev_coredump() uevent sent to user space device_add() ======================> user space process Y reads the uevents writes to devcd fd which results into writes to devcd_data_write() mod_delayed_work() try_to_grab_pending() del_timer() debug_assert_init() INIT_DELAYED_WORK() schedule_delayed_work() debug_object_fixup() timer_fixup_assert_init() timer_setup() do_init_timer() /* Above call reinitializes the timer to timer->entry.pprev=NULL and this will be checked later in timer_pending() call. */ timer_pending() !hlist_unhashed_lockless(&timer->entry) !h->pprev /* del_timer() checks h->pprev and finds it to be NULL due to which try_to_grab_pending() stucks. */ Link: https://lore.kernel.org/lkml/2e1f81e2-428c-f11f-ce92-eb11048cb271@quicinc.com/ Signed-off-by: Mukesh Ojha <quic_mojha@quicinc.com> Link: https://lore.kernel.org/r/1663073424-13663-1-git-send-email-quic_mojha@quicinc.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-09-13 18:20:24 +05:30
devcoredump: Fix circular locking dependency with devcd->mutex. The original code causes a circular locking dependency found by lockdep. ====================================================== WARNING: possible circular locking dependency detected 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 Tainted: G S U ------------------------------------------------------ xe_fault_inject/5091 is trying to acquire lock: ffff888156815688 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}, at: __flush_work+0x25d/0x660 but task is already holding lock: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&devcd->mutex){+.+.}-{3:3}: mutex_lock_nested+0x4e/0xc0 devcd_data_write+0x27/0x90 sysfs_kf_bin_write+0x80/0xf0 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e -> #1 (kn->active#236){++++}-{0:0}: kernfs_drain+0x1e2/0x200 __kernfs_remove+0xae/0x400 kernfs_remove_by_name_ns+0x5d/0xc0 remove_files+0x54/0x70 sysfs_remove_group+0x3d/0xa0 sysfs_remove_groups+0x2e/0x60 device_remove_attrs+0xc7/0x100 device_del+0x15d/0x3b0 devcd_del+0x19/0x30 process_one_work+0x22b/0x6f0 worker_thread+0x1e8/0x3d0 kthread+0x11c/0x250 ret_from_fork+0x26c/0x2e0 ret_from_fork_asm+0x1a/0x30 -> #0 ((work_completion)(&(&devcd->del_wk)->work)){+.+.}-{0:0}: __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 __flush_work+0x27a/0x660 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 entry_SYSCALL_64_after_hwframe+0x76/0x7e other info that might help us debug this: Chain exists of: (work_completion)(&(&devcd->del_wk)->work) --> kn->active#236 --> &devcd->mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&devcd->mutex); lock(kn->active#236); lock(&devcd->mutex); lock((work_completion)(&(&devcd->del_wk)->work)); *** DEADLOCK *** 5 locks held by xe_fault_inject/5091: #0: ffff8881129f9488 (sb_writers#5){.+.+}-{0:0}, at: ksys_write+0x72/0xf0 #1: ffff88810c755078 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x123/0x220 #2: ffff8881054811a0 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x55/0x280 #3: ffff888156815620 (&devcd->mutex){+.+.}-{3:3}, at: dev_coredump_put+0x3f/0xa0 #4: ffffffff8359e020 (rcu_read_lock){....}-{1:2}, at: __flush_work+0x72/0x660 stack backtrace: CPU: 14 UID: 0 PID: 5091 Comm: xe_fault_inject Tainted: G S U 6.16.0-rc6-lgci-xe-xe-pw-151626v3+ #1 PREEMPT_{RT,(lazy)} Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER Hardware name: Micro-Star International Co., Ltd. MS-7D25/PRO Z690-A DDR4(MS-7D25), BIOS 1.10 12/13/2021 Call Trace: <TASK> dump_stack_lvl+0x91/0xf0 dump_stack+0x10/0x20 print_circular_bug+0x285/0x360 check_noncircular+0x135/0x150 ? register_lock_class+0x48/0x4a0 __lock_acquire+0x1661/0x2860 lock_acquire+0xc4/0x2f0 ? __flush_work+0x25d/0x660 ? mark_held_locks+0x46/0x90 ? __flush_work+0x25d/0x660 __flush_work+0x27a/0x660 ? __flush_work+0x25d/0x660 ? trace_hardirqs_on+0x1e/0xd0 ? __pfx_wq_barrier_func+0x10/0x10 flush_delayed_work+0x5d/0xa0 dev_coredump_put+0x63/0xa0 xe_driver_devcoredump_fini+0x12/0x20 [xe] devm_action_release+0x12/0x30 release_nodes+0x3a/0x120 devres_release_all+0x8a/0xd0 device_unbind_cleanup+0x12/0x80 device_release_driver_internal+0x23a/0x280 ? bus_find_device+0xa8/0xe0 device_driver_detach+0x14/0x20 unbind_store+0xaf/0xc0 drv_attr_store+0x21/0x50 sysfs_kf_write+0x4a/0x80 kernfs_fop_write_iter+0x169/0x220 vfs_write+0x293/0x560 ksys_write+0x72/0xf0 __x64_sys_write+0x19/0x30 x64_sys_call+0x2bf/0x2660 do_syscall_64+0x93/0xb60 ? __f_unlock_pos+0x15/0x20 ? __x64_sys_getdents64+0x9b/0x130 ? __pfx_filldir64+0x10/0x10 ? do_syscall_64+0x1a2/0xb60 ? clear_bhb_loop+0x30/0x80 ? clear_bhb_loop+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x76e292edd574 Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89 RSP: 002b:00007fffe247a828 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 000076e292edd574 RDX: 000000000000000c RSI: 00006267f6306063 RDI: 000000000000000b RBP: 000000000000000c R08: 000076e292fc4b20 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000202 R12: 00006267f6306063 R13: 000000000000000b R14: 00006267e6859c00 R15: 000076e29322a000 </TASK> xe 0000:03:00.0: [drm] Xe device coredump has been deleted. Fixes: 01daccf74832 ("devcoredump : Serialize devcd_del work") Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Rafael J. Wysocki <rafael@kernel.org> Cc: Danilo Krummrich <dakr@kernel.org> Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v6.1+ Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Cc: Matthew Brost <matthew.brost@intel.com> Acked-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250723142416.1020423-1-dev@lankhorst.se Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-07-23 16:24:16 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: Add dev_coredumpm_timeout() Add function to set a custom coredump timeout. For Xe driver usage, current 5 minutes timeout may be too short for users to search and understand what needs to be done to capture coredump to report bugs. We have plans to automate(distribute a udev script) it but at the end will be up to distros and users to pack it so having a option to increase the timeout is a safer option. v2: - replace dev_coredump_timeout_set() by dev_coredumpm_timeout() (Mukesh) v3: - make dev_coredumpm() static inline (Johannes) v5: - rename DEVCOREDUMP_TIMEOUT -> DEVCD_TIMEOUT to avoid redefinition in include/net/bluetooth/coredump.h v6: - fix definition of dev_coredumpm_timeout() when CONFIG_DEV_COREDUMP is disabled Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Mukesh Ojha <quic_mojha@quicinc.com> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Jonathan Cavitt <jonathan.cavitt@intel.com> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com> Signed-off-by: José Roberto de Souza <jose.souza@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Johannes Berg <johannes@sipsolutions.net> Link: https://patchwork.freedesktop.org/patch/msgid/20240611174716.72660-1-jose.souza@intel.com Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2024-06-11 10:47:15 -07:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
devcoredump: fix typo in comment s/dev_coredumpmsg/dev_coredumpsg/ in the kernel-doc Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Link: https://lore.kernel.org/r/1564243146-5681-3-git-send-email-akinobu.mita@gmail.com Signed-off-by: Johannes Berg <johannes.berg@intel.com> Link: https://lore.kernel.org/r/20190731100007.32684-2-johannes@sipsolutions.net Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-07-31 12:00:07 +02:00
devcoredump: add scatterlist support Add scatterlist support (dev_coredumpsg) to allow drivers to avoid vmalloc() like dev_coredumpm(), while also avoiding the module reference that the latter function requires. This internally uses dev_coredumpm() with function inside the devcoredump module, requiring removing the const (which touches the driver using it.) Signed-off-by: Aviya Erenfeld <aviya.erenfeld@intel.com> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2016-04-14 11:59:31 +02:00
device coredump: add new device coredump class Many devices run firmware and/or complex hardware, and most of that can have bugs. When it misbehaves, however, it is often much harder to debug than software running on the host. Introduce a "device coredump" mechanism to allow dumping internal device/firmware state through a generalized mechanism. As devices are different and information needed can vary accordingly, this doesn't prescribe a file format - it just provides mechanism to get data to be able to capture it in a generalized way (e.g. in distributions.) The dumped data will be readable in sysfs in the virtual device's data file under /sys/class/devcoredump/devcd*/. Writing to it will free the data and remove the device, as does a 5-minute timeout. Note that generalized capturing of such data may result in privacy issues, so users generally need to be involved. In order to allow certain users/system integrators/... to disable the feature at all, introduce a Kconfig option to override the drivers that would like to have the feature. For now, this provides two ways of dumping data: 1) with a vmalloc'ed area, that is then given to the subsystem and freed after retrieval or timeout 2) with a generalized reader/free function method We could/should add more options, e.g. a list of pages, since the vmalloc area is very limited on some architectures. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-09-12 09:01:56 +02:00