linux_dsm_epyc7002/drivers/gpu/drm/i915/gem
Chris Wilson 8b1c78e06e drm/i915: Avoid calling i915_gem_object_unbind holding object lock
In the extreme case, we may wish to wait on an rcu-barrier to reap stale
vm to purge the last of the object bindings. However, we are not allowed
to use rcu_barrier() beneath the dma_resv (i.e. object) lock and do not
take lightly the prospect of unlocking a mutex deep in the bowels of the
routine. i915_gem_object_unbind() itself does not need the object lock,
and it turns out the callers do not need to the unbind as part of a
locked sequence around set-cache-level, so rearrange the code to avoid
taking the object lock in the callers.

<4> [186.816311] ======================================================
<4> [186.816313] WARNING: possible circular locking dependency detected
<4> [186.816316] 5.4.0-rc8-CI-CI_DRM_7486+ #1 Tainted: G     U
<4> [186.816318] ------------------------------------------------------
<4> [186.816320] perf_pmu/1321 is trying to acquire lock:
<4> [186.816322] ffff88849487c4d8 (&mm->mmap_sem#2){++++}, at: __might_fault+0x39/0x90
<4> [186.816331]
but task is already holding lock:
<4> [186.816333] ffffe8ffffa05008 (&cpuctx_mutex){+.+.}, at: perf_event_ctx_lock_nested+0xa9/0x1b0
<4> [186.816339]
which lock already depends on the new lock.

<4> [186.816341]
the existing dependency chain (in reverse order) is:
<4> [186.816343]
-> #6 (&cpuctx_mutex){+.+.}:
<4> [186.816349]        __mutex_lock+0x9a/0x9d0
<4> [186.816352]        perf_event_init_cpu+0xa4/0x140
<4> [186.816357]        perf_event_init+0x19d/0x1cd
<4> [186.816362]        start_kernel+0x372/0x4f4
<4> [186.816365]        secondary_startup_64+0xa4/0xb0
<4> [186.816381]
-> #5 (pmus_lock){+.+.}:
<4> [186.816385]        __mutex_lock+0x9a/0x9d0
<4> [186.816387]        perf_event_init_cpu+0x6b/0x140
<4> [186.816404]        cpuhp_invoke_callback+0x9b/0x9d0
<4> [186.816406]        _cpu_up+0xa2/0x140
<4> [186.816409]        do_cpu_up+0x61/0xa0
<4> [186.816411]        smp_init+0x57/0x96
<4> [186.816413]        kernel_init_freeable+0xac/0x1c7
<4> [186.816416]        kernel_init+0x5/0x100
<4> [186.816419]        ret_from_fork+0x24/0x50
<4> [186.816421]
-> #4 (cpu_hotplug_lock.rw_sem){++++}:
<4> [186.816424]        cpus_read_lock+0x34/0xd0
<4> [186.816427]        rcu_barrier+0xaa/0x190
<4> [186.816429]        kernel_init+0x21/0x100
<4> [186.816431]        ret_from_fork+0x24/0x50
<4> [186.816433]
-> #3 (rcu_state.barrier_mutex){+.+.}:
<4> [186.816436]        __mutex_lock+0x9a/0x9d0
<4> [186.816438]        rcu_barrier+0x23/0x190
<4> [186.816502]        i915_gem_object_unbind+0x3a6/0x400 [i915]
<4> [186.816537]        i915_gem_object_set_cache_level+0x32/0x90 [i915]
<4> [186.816571]        i915_gem_object_pin_to_display_plane+0x5d/0x160 [i915]
<4> [186.816612]        intel_pin_and_fence_fb_obj+0x9e/0x200 [i915]
<4> [186.816679]        intel_plane_pin_fb+0x3f/0xd0 [i915]
<4> [186.816717]        intel_prepare_plane_fb+0x130/0x520 [i915]
<4> [186.816722]        drm_atomic_helper_prepare_planes+0x85/0x110
<4> [186.816761]        intel_atomic_commit+0xc6/0x350 [i915]
<4> [186.816764]        drm_atomic_helper_update_plane+0xed/0x110
<4> [186.816768]        setplane_internal+0x97/0x190
<4> [186.816770]        drm_mode_setplane+0xcd/0x190
<4> [186.816773]        drm_ioctl_kernel+0xa7/0xf0
<4> [186.816775]        drm_ioctl+0x2e1/0x390
<4> [186.816778]        do_vfs_ioctl+0xa0/0x6f0
<4> [186.816780]        ksys_ioctl+0x35/0x60
<4> [186.816782]        __x64_sys_ioctl+0x11/0x20
<4> [186.816785]        do_syscall_64+0x4f/0x210
<4> [186.816787]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4> [186.816789]
-> #2 (reservation_ww_class_mutex){+.+.}:
<4> [186.816793]        __ww_mutex_lock.constprop.15+0xc3/0x1090
<4> [186.816795]        ww_mutex_lock+0x39/0x70
<4> [186.816798]        dma_resv_lockdep+0x10e/0x1f7
<4> [186.816800]        do_one_initcall+0x58/0x2ff
<4> [186.816802]        kernel_init_freeable+0x137/0x1c7
<4> [186.816804]        kernel_init+0x5/0x100
<4> [186.816806]        ret_from_fork+0x24/0x50
<4> [186.816808]
-> #1 (reservation_ww_class_acquire){+.+.}:
<4> [186.816811]        dma_resv_lockdep+0xec/0x1f7
<4> [186.816813]        do_one_initcall+0x58/0x2ff
<4> [186.816815]        kernel_init_freeable+0x137/0x1c7
<4> [186.816817]        kernel_init+0x5/0x100
<4> [186.816819]        ret_from_fork+0x24/0x50
<4> [186.816820]
-> #0 (&mm->mmap_sem#2){++++}:
<4> [186.816824]        __lock_acquire+0x1328/0x15d0
<4> [186.816826]        lock_acquire+0xa7/0x1c0
<4> [186.816828]        __might_fault+0x63/0x90
<4> [186.816831]        _copy_to_user+0x1e/0x80
<4> [186.816834]        perf_read+0x200/0x2b0
<4> [186.816836]        vfs_read+0x96/0x160
<4> [186.816838]        ksys_read+0x9f/0xe0
<4> [186.816839]        do_syscall_64+0x4f/0x210
<4> [186.816841]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4> [186.816843]
other info that might help us debug this:

<4> [186.816846] Chain exists of:
  &mm->mmap_sem#2 --> pmus_lock --> &cpuctx_mutex

<4> [186.816849]  Possible unsafe locking scenario:

<4> [186.816851]        CPU0                    CPU1
<4> [186.816853]        ----                    ----
<4> [186.816854]   lock(&cpuctx_mutex);
<4> [186.816856]                                lock(pmus_lock);
<4> [186.816858]                                lock(&cpuctx_mutex);
<4> [186.816860]   lock(&mm->mmap_sem#2);
<4> [186.816861]
 *** DEADLOCK ***

Closes: https://gitlab.freedesktop.org/drm/intel/issues/728
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191206105527.1130413-5-chris@chris-wilson.co.uk
2019-12-07 19:27:36 +00:00
..
selftests drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_busy.c dma-buf: Restore seqlock around dma_resv updates 2019-08-16 12:40:58 +01:00
i915_gem_clflush.c drm/i915: Generalise the clflush dma-worker 2019-08-22 08:27:44 +01:00
i915_gem_clflush.h drm/i915: Move more GEM objects under gem/ 2019-05-28 12:45:29 +01:00
i915_gem_client_blt.c drm/i915: Drop struct_mutex from around i915_retire_requests() 2019-10-04 15:39:17 +01:00
i915_gem_client_blt.h drm/i915: add in-kernel blitter client 2019-05-30 12:01:44 +01:00
i915_gem_context_types.h drm/i915/gem: Excise the per-batch whitelist from the context 2019-11-28 11:39:50 +00:00
i915_gem_context.c drm/i915/gem: Pin gen6_ppgtt prior to constructing the request 2019-12-06 23:38:54 +00:00
i915_gem_context.h drm/i915/gem: Make context persistence optional 2019-10-29 21:02:52 +00:00
i915_gem_dmabuf.c drm/i915/gem: Distinguish each object type 2019-10-22 16:23:32 +01:00
i915_gem_domain.c drm/i915: Avoid calling i915_gem_object_unbind holding object lock 2019-12-07 19:27:36 +00:00
i915_gem_execbuffer.c drm/i915: Remove vestigal i915_gem_context locals from cmdparser 2019-12-05 10:27:29 +00:00
i915_gem_fence.c Merge drm/drm-next into drm-intel-next-queued 2019-08-22 00:10:36 -07:00
i915_gem_internal.c drm/i915/gem: Distinguish each object type 2019-10-22 16:23:32 +01:00
i915_gem_ioctls.h drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_lmem.c drm/i915/lmem: add the fake lmem region 2019-10-31 20:41:47 +00:00
i915_gem_lmem.h drm/i915/lmem: support kernel mapping 2019-10-25 22:55:43 +01:00
i915_gem_mman.c drm/i915/gem: Hook user-extensions upto MMAP_OFFSET_IOCTL 2019-12-04 18:06:28 +00:00
i915_gem_mman.h drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_object_blt.c drm/i915/blt: fixup block_size rounding 2019-10-29 06:57:20 +00:00
i915_gem_object_blt.h drm/i915/blt: support copying objects 2019-08-10 19:35:36 +01:00
i915_gem_object_types.h drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_object.c drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_object.h drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_pages.c drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_phys.c drm/i915: Switch obj->mm.lock lockdep annotations on its head 2019-11-07 09:58:11 +01:00
i915_gem_pm.c drm/i915: Defer rc6 shutdown to suspend_late 2019-11-05 16:05:42 +02:00
i915_gem_pm.h drm/i915: Teach record_defaults to operate on the intel_gt 2019-10-22 20:43:07 +01:00
i915_gem_region.c drm/i915: treat shmem as a region 2019-10-18 12:41:03 +01:00
i915_gem_region.h drm/i915/region: support contiguous allocations 2019-10-08 20:50:01 +01:00
i915_gem_shmem.c drm/i915/gem: Distinguish each object type 2019-10-22 16:23:32 +01:00
i915_gem_shrinker.c drm/i915: Switch obj->mm.lock lockdep annotations on its head 2019-11-07 09:58:11 +01:00
i915_gem_shrinker.h drm/i915: extract i915_gem_shrinker.h from i915_drv.h 2019-08-09 12:03:32 +03:00
i915_gem_stolen.c drm/i915/gem: Pass mem region to preallocated stolen 2019-11-11 19:22:18 +00:00
i915_gem_stolen.h drm/i915: treat stolen as a region 2019-10-18 12:41:05 +01:00
i915_gem_throttle.c drm/i915: Keep drm_i915_file_private around under RCU 2019-08-23 22:13:17 +01:00
i915_gem_tiling.c drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET 2019-12-04 15:11:44 +00:00
i915_gem_userptr.c drm/i915/userptr: Try to acquire the page lock around set_page_dirty() 2019-11-12 10:22:58 +02:00
i915_gem_wait.c dma-buf: rename reservation_object to dma_resv 2019-08-13 09:09:30 +02:00
i915_gemfs.c drm/i915: Stop reconfiguring our shmemfs mountpoint 2019-08-09 20:18:30 +01:00
i915_gemfs.h drm/i915: Move more GEM objects under gem/ 2019-05-28 12:45:29 +01:00
Makefile drm/i915: use upstream version of header tests 2019-07-30 12:11:57 +03:00