| Message ID | 20240722210648.80892-8-lucas.demarchi@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Fix i915 pmu on bind/unbind | expand |
Hello,
kernel test robot noticed "INFO:trying_to_register_non-static_key" on:
commit: a236f4d92e214998f7606430282249580f709423 ("[PATCH 7/7] drm/i915/pmu: Do not set event_init to NULL")
url: https://github.com/intel-lab-lkp/linux/commits/Lucas-De-Marchi/perf-core-Add-pmu-get-put/20240723-051755
base: https://git.kernel.org/cgit/linux/kernel/git/perf/perf-tools-next.git perf-tools-next
patch link: https://lore.kernel.org/all/20240722210648.80892-8-lucas.demarchi@intel.com/
patch subject: [PATCH 7/7] drm/i915/pmu: Do not set event_init to NULL
in testcase: kernel-selftests
version: kernel-selftests-x86_64-977d51cf-1_20240508
with following parameters:
group: locking
compiler: gcc-13
test machine: 4 threads Intel(R) Xeon(R) CPU E3-1225 v5 @ 3.30GHz (Skylake) with 16G memory
(please refer to attached dmesg/kmsg for entire log/backtrace)
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202408051423.839b16eb-oliver.sang@intel.com
[ 45.439542][ T194] INFO: trying to register non-static key.
[ 45.445246][ T194] The code is fine but needs lockdep annotation, or maybe
[ 45.452244][ T194] you didn't initialize this object before use?
[ 45.458370][ T194] turning off the locking correctness validator.
[ 45.464586][ T194] CPU: 3 PID: 194 Comm: (udev-worker) Tainted: G S 6.10.0-rc3-00133-ga236f4d92e21 #1
[ 45.475322][ T194] Hardware name: HP HP Z238 Microtower Workstation/8183, BIOS N51 Ver. 01.63 10/05/2017
[ 45.484923][ T194] Call Trace:
[ 45.488094][ T194] <TASK>
[ 45.490908][ T194] dump_stack_lvl (lib/dump_stack.c:118)
[ 45.495297][ T194] register_lock_class (kernel/locking/lockdep.c:1290)
[ 45.500377][ T194] ? lock_acquire (kernel/locking/lockdep.c:467 (discriminator 4) kernel/locking/lockdep.c:5756 (discriminator 4) kernel/locking/lockdep.c:5719 (discriminator 4))
[ 45.504938][ T194] ? intel_display_power_get (drivers/gpu/drm/i915/display/intel_display_power.c:504 drivers/gpu/drm/i915/display/intel_display_power.c:532) i915
[ 45.511333][ T194] ? __pfx_register_lock_class (kernel/locking/lockdep.c:1276)
[ 45.516848][ T194] ? __pfx_lock_acquire (kernel/locking/lockdep.c:5722)
[ 45.521748][ T194] ? lock_is_held_type (kernel/locking/lockdep.c:5495 (discriminator 1) kernel/locking/lockdep.c:5825 (discriminator 1))
[ 45.526654][ T194] ? find_held_lock (kernel/locking/lockdep.c:5244 (discriminator 1))
[ 45.531306][ T194] __lock_acquire (kernel/locking/lockdep.c:5015)
[ 45.535870][ T194] ? trace_contention_end (include/trace/events/lock.h:122 (discriminator 2))
[ 45.541042][ T194] ? __mutex_lock (arch/x86/include/asm/preempt.h:94 (discriminator 1) kernel/locking/mutex.c:618 (discriminator 1) kernel/locking/mutex.c:752 (discriminator 1))
[ 45.545688][ T194] lock_acquire (kernel/locking/lockdep.c:467 (discriminator 4) kernel/locking/lockdep.c:5756 (discriminator 4) kernel/locking/lockdep.c:5719 (discriminator 4))
[ 45.550069][ T194] ? i915_pmu_gt_unparked (drivers/gpu/drm/i915/i915_pmu.c:336) i915
[ 45.556233][ T194] ? __pfx_lock_acquire (kernel/locking/lockdep.c:5722)
[ 45.561162][ T194] ? __pfx___mutex_unlock_slowpath (kernel/locking/mutex.c:907)
[ 45.567023][ T194] ? __pfx_intel_display_power_grab_async_put_ref (drivers/gpu/drm/i915/display/intel_display_power.c:471) i915
[ 45.575181][ T194] _raw_spin_lock_irq (include/linux/spinlock_api_smp.h:120 kernel/locking/spinlock.c:170)
[ 45.579937][ T194] ? i915_pmu_gt_unparked (drivers/gpu/drm/i915/i915_pmu.c:336) i915
[ 45.586041][ T194] i915_pmu_gt_unparked (drivers/gpu/drm/i915/i915_pmu.c:336) i915
[ 45.591960][ T194] __gt_unpark (drivers/gpu/drm/i915/gt/intel_gt_pm.c:93) i915
[ 45.597075][ T194] __intel_wakeref_get_first (drivers/gpu/drm/i915/intel_wakeref.c:32) i915
[ 45.603498][ T194] intel_gt_resume (drivers/gpu/drm/i915/gt/intel_gt_pm.c:259) i915
[ 45.609021][ T194] ? __pfx_intel_execlists_submission_setup (drivers/gpu/drm/i915/gt/intel_execlists_submission.c:3541) i915
[ 45.616560][ T194] intel_gt_init (drivers/gpu/drm/i915/gt/intel_gt.c:740) i915
[ 45.621888][ T194] i915_gem_init (drivers/gpu/drm/i915/i915_gem.c:1193) i915
[ 45.627261][ T194] i915_driver_probe (drivers/gpu/drm/i915/i915_driver.c:798) i915
[ 45.632922][ T194] ? __pfx_i915_driver_probe (drivers/gpu/drm/i915/i915_driver.c:750) i915
[ 45.639091][ T194] ? drm_privacy_screen_get (drivers/gpu/drm/drm_privacy_screen.c:168) drm
[ 45.645110][ T194] ? intel_display_driver_probe_defer (drivers/gpu/drm/i915/display/intel_display_driver.c:81) i915
[ 45.652258][ T194] ? i915_pci_probe (drivers/gpu/drm/i915/i915_pci.c:998 (discriminator 1)) i915
[ 45.657875][ T194] ? __pfx_i915_pci_probe (drivers/gpu/drm/i915/i915_pci.c:959) i915
[ 45.663785][ T194] local_pci_probe (drivers/pci/pci-driver.c:324)
[ 45.668340][ T194] pci_call_probe (drivers/pci/pci-driver.c:392 (discriminator 1))
[ 45.672893][ T194] ? __pfx_do_raw_spin_lock (kernel/locking/spinlock_debug.c:114)
[ 45.678141][ T194] ? __pfx_pci_call_probe (drivers/pci/pci-driver.c:352)
[ 45.683232][ T194] ? pci_match_device (drivers/pci/pci-driver.c:159)
[ 45.688169][ T194] ? pci_match_device (drivers/pci/pci-driver.c:159 (discriminator 1))
[ 45.693077][ T194] ? kernfs_put (arch/x86/include/asm/atomic.h:67 (discriminator 1) include/linux/atomic/atomic-arch-fallback.h:2278 (discriminator 1) include/linux/atomic/atomic-instrumented.h:1384 (discriminator 1) fs/kernfs/dir.c:557 (discriminator 1))
[ 45.697294][ T194] pci_device_probe (drivers/pci/pci-driver.c:452)
[ 45.701942][ T194] ? pci_dma_configure (drivers/pci/pci-driver.c:1656)
[ 45.706941][ T194] really_probe (drivers/base/dd.c:578 drivers/base/dd.c:656)
[ 45.711328][ T194] __driver_probe_device (drivers/base/dd.c:798)
[ 45.716492][ T194] driver_probe_device (drivers/base/dd.c:828)
[ 45.721401][ T194] __driver_attach (drivers/base/dd.c:1215)
[ 45.726051][ T194] ? __pfx___driver_attach (drivers/base/dd.c:1155)
[ 45.731235][ T194] bus_for_each_dev (drivers/base/bus.c:367)
[ 45.735991][ T194] ? lockdep_init_map_type (kernel/locking/lockdep.c:4892 (discriminator 1))
[ 45.741332][ T194] ? __pfx_bus_for_each_dev (drivers/base/bus.c:356)
[ 45.746592][ T194] ? bus_add_driver (drivers/base/bus.c:672)
[ 45.751332][ T194] bus_add_driver (drivers/base/bus.c:673)
[ 45.755895][ T194] driver_register (drivers/base/driver.c:246)
[ 45.760539][ T194] i915_init (drivers/gpu/drm/i915/i915_driver.c:1436) i915
[ 45.765494][ T194] ? __pfx_i915_init (drivers/gpu/drm/i915/i915_config.c:13) i915
[ 45.770985][ T194] do_one_initcall (init/main.c:1267)
[ 45.775534][ T194] ? asm_sysvec_apic_timer_interrupt (arch/x86/include/asm/idtentry.h:702)
[ 45.781568][ T194] ? __pfx_do_one_initcall (init/main.c:1258)
[ 45.786741][ T194] ? kasan_unpoison (mm/kasan/shadow.c:156 mm/kasan/shadow.c:182)
[ 45.791304][ T194] do_init_module (kernel/module/main.c:2541)
[ 45.795868][ T194] init_module_from_file (kernel/module/main.c:3173)
[ 45.800951][ T194] ? __pfx_init_module_from_file (kernel/module/main.c:3149)
[ 45.806647][ T194] ? __lock_release+0x103/0x440
[ 45.811991][ T194] ? idempotent_init_module (kernel/module/main.c:3119 kernel/module/main.c:3184)
[ 45.817423][ T194] ? idempotent_init_module (kernel/module/main.c:3119 kernel/module/main.c:3184)
[ 45.822857][ T194] ? do_raw_spin_unlock (arch/x86/include/asm/atomic.h:23 include/linux/atomic/atomic-arch-fallback.h:457 include/linux/atomic/atomic-instrumented.h:33 include/asm-generic/qspinlock.h:57 kernel/locking/spinlock_debug.c:101 kernel/locking/spinlock_debug.c:141)
[ 45.827853][ T194] idempotent_init_module (kernel/module/main.c:3190)
[ 45.833104][ T194] ? __pfx_idempotent_init_module (kernel/module/main.c:3177)
[ 45.838879][ T194] ? __seccomp_filter (arch/x86/include/asm/bitops.h:227 arch/x86/include/asm/bitops.h:239 include/asm-generic/bitops/instrumented-non-atomic.h:142 kernel/seccomp.c:359 kernel/seccomp.c:386 kernel/seccomp.c:418 kernel/seccomp.c:1222)
[ 45.843791][ T194] ? security_capable (security/security.c:1036 (discriminator 13))
[ 45.848531][ T194] __x64_sys_finit_module (include/linux/file.h:47 kernel/module/main.c:3212 kernel/module/main.c:3194 kernel/module/main.c:3194)
[ 45.853704][ T194] do_syscall_64 (arch/x86/entry/common.c:52 (discriminator 1) arch/x86/entry/common.c:83 (discriminator 1))
[ 45.858092][ T194] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
[ 45.863871][ T194] RIP: 0033:0x7f5179545719
[ 45.868164][ T194] Code: 08 89 e8 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d b7 06 0d 00 f7 d8 64 89 01 48
All code
========
0: 08 89 e8 5b 5d c3 or %cl,-0x3ca2a418(%rcx)
6: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
d: 00 00 00
10: 90 nop
11: 48 89 f8 mov %rdi,%rax
14: 48 89 f7 mov %rsi,%rdi
17: 48 89 d6 mov %rdx,%rsi
1a: 48 89 ca mov %rcx,%rdx
1d: 4d 89 c2 mov %r8,%r10
20: 4d 89 c8 mov %r9,%r8
23: 4c 8b 4c 24 08 mov 0x8(%rsp),%r9
28: 0f 05 syscall
2a:* 48 3d 01 f0 ff ff cmp $0xfffffffffffff001,%rax <-- trapping instruction
30: 73 01 jae 0x33
32: c3 retq
33: 48 8b 0d b7 06 0d 00 mov 0xd06b7(%rip),%rcx # 0xd06f1
3a: f7 d8 neg %eax
3c: 64 89 01 mov %eax,%fs:(%rcx)
3f: 48 rex.W
Code starting with the faulting instruction
===========================================
0: 48 3d 01 f0 ff ff cmp $0xfffffffffffff001,%rax
6: 73 01 jae 0x9
8: c3 retq
9: 48 8b 0d b7 06 0d 00 mov 0xd06b7(%rip),%rcx # 0xd06c7
10: f7 d8 neg %eax
12: 64 89 01 mov %eax,%fs:(%rcx)
15: 48 rex.W
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240805/202408051423.839b16eb-oliver.sang@intel.com
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index df53a8fe53ec..c5738035bc2f 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -303,7 +303,7 @@ void i915_pmu_gt_parked(struct intel_gt *gt) { struct i915_pmu *pmu = >->i915->pmu; - if (!pmu->base.event_init) + if (pmu->closed) return; spin_lock_irq(&pmu->lock); @@ -325,7 +325,7 @@ void i915_pmu_gt_unparked(struct intel_gt *gt) { struct i915_pmu *pmu = >->i915->pmu; - if (!pmu->base.event_init) + if (pmu->closed) return; spin_lock_irq(&pmu->lock); @@ -1325,12 +1325,12 @@ void i915_pmu_register(struct drm_i915_private *i915) err_groups: kfree(pmu->base.attr_groups); err_attr: - pmu->base.event_init = NULL; free_event_attributes(pmu); err_name: if (IS_DGFX(i915)) kfree(pmu->name); err: + pmu->closed = true; drm_notice(&i915->drm, "Failed to register PMU!\n"); } @@ -1346,6 +1346,4 @@ void i915_pmu_unregister(struct drm_i915_private *i915) hrtimer_cancel(&pmu->timer); i915_pmu_unregister_cpuhp_state(pmu); - - pmu->base.event_init = NULL; }
event_init is not an optional function pointer from perf events. Now that pmu unregister happens only when freeing i915, setting it to NULL only protects other functions in i915. Replace that by checking pmu->closed. Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com> --- drivers/gpu/drm/i915/i915_pmu.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)