All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH 07/14] drm/i915: Stop spinning for DROP_IDLE (debugfs/i915_drop_caches)
Date: Wed,  1 May 2019 12:45:34 +0100	[thread overview]
Message-ID: <20190501114541.10077-7-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20190501114541.10077-1-chris@chris-wilson.co.uk>

If the user is racing a call to debugfs/i915_drop_caches with ongoing
submission from another thread/process, we may never end up idling the
GPU and be uninterruptibly spinning in debugfs/i915_drop_caches trying
to catch an idle moment.

Just flush the work once, that should be enough to park the system under
correct conditions. Outside of those we either have a driver bug or the
user is racing themselves. Sadly, because the user may be provoking the
unwanted situation we can't put a warn here to attract attention to a
probable bug.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 7e8898d0b78b..2ecefacb1e66 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3933,9 +3933,7 @@ i915_drop_caches_set(void *data, u64 val)
 	fs_reclaim_release(GFP_KERNEL);
 
 	if (val & DROP_IDLE) {
-		do {
-			flush_delayed_work(&i915->gem.retire_work);
-		} while (READ_ONCE(i915->gt.awake));
+		flush_delayed_work(&i915->gem.retire_work);
 		flush_work(&i915->gem.idle_work);
 	}
 
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2019-05-01 11:52 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-01 11:45 [PATCH 01/14] drm/i915/hangcheck: Track context changes Chris Wilson
2019-05-01 11:45 ` [PATCH 02/14] drm/i915: Include fence signaled bit in print_request() Chris Wilson
2019-05-02 13:43   ` Tvrtko Ursulin
2019-05-01 11:45 ` [PATCH 03/14] drm/i915/execlists: Flush the tasklet on parking Chris Wilson
2019-05-02 13:48   ` Tvrtko Ursulin
2019-05-02 13:53     ` Chris Wilson
2019-05-02 14:14       ` Tvrtko Ursulin
2019-05-02 14:21         ` Chris Wilson
2019-05-02 14:24           ` Tvrtko Ursulin
2019-05-02 14:33             ` Chris Wilson
2019-05-01 11:45 ` [PATCH 04/14] drm/i915: Leave engine parking to the engines Chris Wilson
2019-05-02 14:18   ` Tvrtko Ursulin
2019-05-01 11:45 ` [PATCH 05/14] drm/i915: Remove delay for idle_work Chris Wilson
2019-05-02 13:19   ` Tvrtko Ursulin
2019-05-02 13:22     ` Chris Wilson
2019-05-02 13:51       ` Tvrtko Ursulin
2019-05-02 14:23         ` Chris Wilson
2019-05-01 11:45 ` [PATCH 06/14] drm/i915: Cancel retire_worker on parking Chris Wilson
2019-05-02 13:29   ` Tvrtko Ursulin
2019-05-02 13:33     ` Chris Wilson
2019-05-02 14:20       ` Tvrtko Ursulin
2019-05-02 14:26         ` Chris Wilson
2019-05-02 14:29   ` [PATCH v2] " Chris Wilson
2019-05-01 11:45 ` Chris Wilson [this message]
2019-05-02 13:34   ` [PATCH 07/14] drm/i915: Stop spinning for DROP_IDLE (debugfs/i915_drop_caches) Tvrtko Ursulin
2019-05-02 14:00     ` Chris Wilson
2019-05-02 14:16       ` Tvrtko Ursulin
2019-05-01 11:45 ` [PATCH 08/14] drm/i915: Only reschedule the submission tasklet if preemption is possible Chris Wilson
2019-05-03 10:53   ` Tvrtko Ursulin
2019-05-03 10:58     ` Chris Wilson
2019-05-01 11:45 ` [PATCH 09/14] drm/i915: Delay semaphore submission until the start of the signaler Chris Wilson
2019-05-03 11:03   ` Tvrtko Ursulin
2019-05-01 11:45 ` [PATCH 10/14] drm/i915/execlists: Don't apply priority boost for resets Chris Wilson
2019-05-01 11:45 ` [PATCH 11/14] drm/i915: Rearrange i915_scheduler.c Chris Wilson
2019-05-01 11:45 ` [PATCH 12/14] drm/i915: Pass i915_sched_node around internally Chris Wilson
2019-05-01 11:45 ` [PATCH 13/14] drm/i915: Bump signaler priority on adding a waiter Chris Wilson
2019-05-01 14:59   ` [PATCH] " Chris Wilson
2019-05-01 16:29   ` [PATCH v2] " Chris Wilson
2019-05-01 16:32   ` Chris Wilson
2019-05-01 11:45 ` [PATCH 14/14] drm/i915: Convert inconsistent static engine tables into an init error Chris Wilson
2019-05-01 12:29 ` ✗ Fi.CI.SPARSE: warning for series starting with [01/14] drm/i915/hangcheck: Track context changes Patchwork
2019-05-01 12:47 ` ✗ Fi.CI.BAT: failure " Patchwork
2019-05-01 15:22 ` ✗ Fi.CI.SPARSE: warning for series starting with [01/14] drm/i915/hangcheck: Track context changes (rev2) Patchwork
2019-05-01 15:35 ` ✓ Fi.CI.BAT: success " Patchwork
2019-05-01 16:42 ` ✗ Fi.CI.SPARSE: warning for series starting with [01/14] drm/i915/hangcheck: Track context changes (rev3) Patchwork
2019-05-01 16:52 ` ✓ Fi.CI.BAT: success " Patchwork
2019-05-01 17:01 ` ✗ Fi.CI.SPARSE: warning for series starting with [01/14] drm/i915/hangcheck: Track context changes (rev4) Patchwork
2019-05-01 17:37 ` ✓ Fi.CI.BAT: success " Patchwork
2019-05-02  9:35 ` ✗ Fi.CI.IGT: failure " Patchwork
2019-05-02 16:45 ` ✗ Fi.CI.BAT: failure for series starting with [01/14] drm/i915/hangcheck: Track context changes (rev5) Patchwork
2019-05-03 10:36 ` [PATCH 01/14] drm/i915/hangcheck: Track context changes Tvrtko Ursulin
2019-05-03 10:43   ` Chris Wilson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190501114541.10077-7-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.