drm/i915: Don't call synchronize_rcu_expedited under struct_mutex
Subsystems (2)
Joonas Lahtinen
maintainerPATCH 1/1 drm/i915: Don't call synchronize_rcu_expedited under struct_mutex
Only call synchronize_rcu_expedited after unlocking struct_mutex to avoid deadlock because the workqueues depend on struct_mutex.
From original patch by Andrea:
synchronize_rcu/synchronize_sched/synchronize_rcu_expedited() will hang until its own workqueues are run. The i915 gem workqueues will wait on the struct_mutex to be released. So we cannot wait for a quiescent state using those rcu primitives while holding the struct_mutex or it creates a circular lock dependency resulting in kernel hangs (which is reproducible but goes undetected by lockdep).
kswapd0 D 0 700 2 0x00000000
Call Trace: ? __schedule+0x1a5/0x660 ? schedule+0x36/0x80 ? _synchronize_rcu_expedited.constprop.65+0x2ef/0x300 ? wake_up_bit+0x20/0x20 ? rcu_stall_kick_kthreads.part.54+0xc0/0xc0 ? rcu_exp_wait_wake+0x530/0x530 ? i915_gem_shrink+0x34b/0x4b0 ? i915_gem_shrinker_scan+0x7c/0x90 ? i915_gem_shrinker_scan+0x7c/0x90 ? shrink_slab.part.61.constprop.72+0x1c1/0x3a0 ? shrink_zone+0x154/0x160 ? kswapd+0x40a/0x720 ? kthread+0xf4/0x130 ? try_to_free_pages+0x450/0x450 ? kthread_create_on_node+0x40/0x40 ? ret_from_fork+0x23/0x30 plasmashell D 0 4657 4614 0x00000000 Call Trace: ? __schedule+0x1a5/0x660 ? schedule+0x36/0x80 ? schedule_preempt_disabled+0xe/0x10 ? __mutex_lock.isra.4+0x1c9/0x790 ? i915_gem_close_object+0x26/0xc0 ? i915_gem_close_object+0x26/0xc0 ? drm_gem_object_release_handle+0x48/0x90 ? drm_gem_handle_delete+0x50/0x80 ? drm_ioctl+0x1fa/0x420 ? drm_gem_handle_create+0x40/0x40 ? pipe_write+0x391/0x410 ? __vfs_write+0xc6/0x120 ? do_vfs_ioctl+0x8b/0x5d0 ? SyS_ioctl+0x3b/0x70 ? entry_SYSCALL_64_fastpath+0x13/0x94 kworker/0:0 D 0 29186 2 0x00000000 Workqueue: events __i915_gem_free_work Call Trace: ? __schedule+0x1a5/0x660 ? schedule+0x36/0x80 ? schedule_preempt_disabled+0xe/0x10 ? __mutex_lock.isra.4+0x1c9/0x790 ? del_timer_sync+0x44/0x50 ? update_curr+0x57/0x110 ? __i915_gem_free_objects+0x31/0x300 ? __i915_gem_free_objects+0x31/0x300 ? __i915_gem_free_work+0x2d/0x40 ? process_one_work+0x13a/0x3b0 ? worker_thread+0x4a/0x460 ? kthread+0xf4/0x130 ? process_one_work+0x3b0/0x3b0 ? kthread_create_on_node+0x40/0x40 ? ret_from_fork+0x23/0x30
--- drivers/gpu/drm/i915/i915_gem_shrinker.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-)
drivers/gpu/drm/i915/i915_gem_shrinker.c +16 -10
@@ -53,6 +53,17 @@ static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)BUG (); } +static void i915_gem_shrinker_unlock (struct drm_device *dev,bool unlock) +{ +if (!unlock) +return ; + +mutex_unlock (&dev->struct_mutex); + +/* expedite the RCU grace period to free some request slabs */ +synchronize_rcu_expedited (); +} +static bool any_vma_pinned (struct drm_i915_gem_object *obj) {struct i915_vma *vma;
@@ -232,11 +243,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,intel_runtime_pm_put (dev_priv);i915_gem_retire_requests (dev_priv); -if (unlock) -mutex_unlock (&dev_priv->drm.struct_mutex); -/* expedite the RCU grace period to free some request slabs */ -synchronize_rcu_expedited (); +i915_gem_shrinker_unlock (&dev_priv->drm, unlock);return count; }
@@ -296,8 +304,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) count += obj->base.size >>PAGE_SHIFT ; } -if (unlock) -mutex_unlock (&dev->struct_mutex); +i915_gem_shrinker_unlock (dev, unlock);return count; }
@@ -324,8 +331,8 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) sc->nr_to_scan - freed,I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); -if (unlock) -mutex_unlock (&dev->struct_mutex); + +i915_gem_shrinker_unlock (dev, unlock);return freed; }
@@ -367,8 +374,7 @@ i915_gem_shrinker_unlock_uninterruptible(struct drm_i915_private *dev_priv, struct shrinker_lock_uninterruptible *slu) { dev_priv->mm.interruptible = slu->was_interruptible; -if (slu->unlock) -mutex_unlock (&dev_priv->drm.struct_mutex); +i915_gem_shrinker_unlock (&dev_priv->drm, slu->unlock); } static int
Signature · 6 lines
2.7.4 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI✓ Fi.CI.BAT: success for drm/i915: Don't call synchronize_rcu_expedited under struct_mutex
== Series Details ==
== Series Details ==
Series: drm/i915: Don't call synchronize_rcu_expedited under struct_mutex
URL : https://patchwork.freedesktop.org/series/22646/
State : success
== Summary ==
Series 22646v1 drm/i915: Don't call synchronize_rcu_expedited under struct_mutex
https://patchwork.freedesktop.org/api/1.0/series/22646/revisions/1/mbox/
Test gem_exec_flush:
Subgroup basic-batch-kernel-default-uc:
pass -> FAIL (fi-snb-2600) fdo#100007fdo#100007 https://bugs.freedesktop.org/show_bug.cgi?id=100007
fi-bdw-5557u total:278 pass:267 dwarn:0 dfail:0 fail:0 skip:11 time: 434s fi-bdw-gvtdvm total:278 pass:256 dwarn:8 dfail:0 fail:0 skip:14 time: 424s fi-bsw-n3050 total:278 pass:242 dwarn:0 dfail:0 fail:0 skip:36 time: 575s fi-bxt-j4205 total:278 pass:259 dwarn:0 dfail:0 fail:0 skip:19 time: 507s fi-bxt-t5700 total:278 pass:257 dwarn:1 dfail:0 fail:0 skip:20 time: 556s fi-byt-j1900 total:278 pass:254 dwarn:0 dfail:0 fail:0 skip:24 time: 485s fi-byt-n2820 total:278 pass:250 dwarn:0 dfail:0 fail:0 skip:28 time: 476s fi-hsw-4770 total:278 pass:262 dwarn:0 dfail:0 fail:0 skip:16 time: 411s fi-hsw-4770r total:278 pass:262 dwarn:0 dfail:0 fail:0 skip:16 time: 406s fi-ilk-650 total:278 pass:228 dwarn:0 dfail:0 fail:0 skip:50 time: 420s fi-ivb-3520m total:278 pass:260 dwarn:0 dfail:0 fail:0 skip:18 time: 493s fi-ivb-3770 total:278 pass:260 dwarn:0 dfail:0 fail:0 skip:18 time: 464s fi-kbl-7500u total:278 pass:260 dwarn:0 dfail:0 fail:0 skip:18 time: 458s fi-kbl-7560u total:278 pass:268 dwarn:0 dfail:0 fail:0 skip:10 time: 660s fi-skl-6260u total:278 pass:268 dwarn:0 dfail:0 fail:0 skip:10 time: 455s fi-skl-6700hq total:278 pass:261 dwarn:0 dfail:0 fail:0 skip:17 time: 570s fi-skl-6700k total:278 pass:256 dwarn:4 dfail:0 fail:0 skip:18 time: 454s fi-skl-6770hq total:278 pass:268 dwarn:0 dfail:0 fail:0 skip:10 time: 486s fi-skl-gvtdvm total:278 pass:265 dwarn:0 dfail:0 fail:0 skip:13 time: 429s fi-snb-2520m total:278 pass:250 dwarn:0 dfail:0 fail:0 skip:28 time: 530s fi-snb-2600 total:278 pass:248 dwarn:0 dfail:0 fail:1 skip:29 time: 396s
60e3f75dfa48d8943d4d4d57bbd7ef7c1d037d85 drm-tip: 2017y-04m-07d-07h-32m-05s UTC integration manifest 536e14a drm/i915: Don't call synchronize_rcu_expedited under struct_mutex
== Logs ==
For more details see: https://intel-gfx-ci.01.org/CI/Patchwork_4437/
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Chris Wilson
Reviewed-byRe: ✓ Fi.CI.BAT: success for drm/i915: Don't call synchronize_rcu_expedited under struct_mutex
Quoted 10 lines · Patchwork
== Series Details ==
Series: drm/i915: Don't call
synchronize_rcu_expeditedunderstruct_mutex
URL : https://patchwork.freedesktop.org/series/22646/
State : success== Summary ==
Series 22646v1 drm/i915: Don't call
synchronize_rcu_expeditedunderstruct_mutex
https://patchwork.freedesktop.org/api/1.0/series/22646/revisions/1/mbox/
Slow mbox. So reply here instead.
Hmm, so that fixes the immediate problem with struct_mutex, but there is still a danger that we are underneath some other mutex that is being waited upon. I think it is too dangerous to live and that kswapd should have the role of expediting the RCU cleanup.
Since the patch improves the situation,
But please do follow up with a
- synchronize_rcu_expedited();
+ /* We rely on the system flushing the RCU slabs to free our structs */ -Chris
Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx