From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
To: intel-gfx@lists.freedesktop.org
Subject: [Intel-gfx] [PATCH 17/23] drm/i915: Convert i915_perf to ww locking as well
Date: Tue, 14 Jul 2020 13:45:10 +0200 [thread overview]
Message-ID: <20200714114516.3073222-17-maarten.lankhorst@linux.intel.com> (raw)
In-Reply-To: <20200714114516.3073222-1-maarten.lankhorst@linux.intel.com>
We have the ordering of timeline->mutex vs resv_lock wrong,
convert the i915_pin_vma and intel_context_pin as well to
future-proof this.
We may need to do future changes to do this more transaction-like,
and only get down to a single i915_gem_ww_ctx, but for now this
should work.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
drivers/gpu/drm/i915/i915_perf.c | 57 +++++++++++++++++++++++---------
1 file changed, 42 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index c6f6370283cf..e94976976571 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1195,24 +1195,39 @@ static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
struct i915_gem_engines_iter it;
struct i915_gem_context *ctx = stream->ctx;
struct intel_context *ce;
- int err;
+ struct i915_gem_ww_ctx ww;
+ int err = -ENODEV;
for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
if (ce->engine != stream->engine) /* first match! */
continue;
- /*
- * As the ID is the gtt offset of the context's vma we
- * pin the vma to ensure the ID remains fixed.
- */
- err = intel_context_pin(ce);
- if (err == 0) {
- stream->pinned_ctx = ce;
- break;
- }
+ err = 0;
+ break;
}
i915_gem_context_unlock_engines(ctx);
+ if (err)
+ return ERR_PTR(err);
+
+ i915_gem_ww_ctx_init(&ww, true);
+retry:
+ /*
+ * As the ID is the gtt offset of the context's vma we
+ * pin the vma to ensure the ID remains fixed.
+ */
+ err = intel_context_pin_ww(ce, &ww);
+ if (err == -EDEADLK) {
+ err = i915_gem_ww_ctx_backoff(&ww);
+ if (!err)
+ goto retry;
+ }
+ i915_gem_ww_ctx_fini(&ww);
+
+ if (err)
+ return ERR_PTR(err);
+
+ stream->pinned_ctx = ce;
return stream->pinned_ctx;
}
@@ -1923,15 +1938,22 @@ emit_oa_config(struct i915_perf_stream *stream,
{
struct i915_request *rq;
struct i915_vma *vma;
+ struct i915_gem_ww_ctx ww;
int err;
vma = get_oa_vma(stream, oa_config);
if (IS_ERR(vma))
return PTR_ERR(vma);
- err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
+ i915_gem_ww_ctx_init(&ww, true);
+retry:
+ err = i915_gem_object_lock(vma->obj, &ww);
+ if (err)
+ goto err;
+
+ err = i915_vma_pin_ww(vma, &ww, 0, 0, PIN_GLOBAL | PIN_HIGH);
if (err)
- goto err_vma_put;
+ goto err;
intel_engine_pm_get(ce->engine);
rq = i915_request_create(ce);
@@ -1953,11 +1975,9 @@ emit_oa_config(struct i915_perf_stream *stream,
goto err_add_request;
}
- i915_vma_lock(vma);
err = i915_request_await_object(rq, vma->obj, 0);
if (!err)
err = i915_vma_move_to_active(vma, rq, 0);
- i915_vma_unlock(vma);
if (err)
goto err_add_request;
@@ -1971,7 +1991,14 @@ emit_oa_config(struct i915_perf_stream *stream,
i915_request_add(rq);
err_vma_unpin:
i915_vma_unpin(vma);
-err_vma_put:
+err:
+ if (err == -EDEADLK) {
+ err = i915_gem_ww_ctx_backoff(&ww);
+ if (!err)
+ goto retry;
+ }
+
+ i915_gem_ww_ctx_fini(&ww);
i915_vma_put(vma);
return err;
}
--
2.27.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2020-07-14 11:46 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-14 11:44 [Intel-gfx] [PATCH 01/23] Revert "drm/i915/gem: Async GPU relocations only" Maarten Lankhorst
2020-07-14 11:44 ` [Intel-gfx] [PATCH 02/23] drm/i915: Revert relocation chaining commits Maarten Lankhorst
2020-07-14 11:44 ` [Intel-gfx] [PATCH 03/23] Revert "drm/i915/gem: Drop relocation slowpath" Maarten Lankhorst
2020-07-14 11:44 ` [Intel-gfx] [PATCH 04/23] drm/i915: Add an implementation for i915_gem_ww_ctx locking, v2 Maarten Lankhorst
2020-07-14 11:44 ` [Intel-gfx] [PATCH 05/23] drm/i915: Remove locking from i915_gem_object_prepare_read/write Maarten Lankhorst
2020-07-14 11:44 ` [Intel-gfx] [PATCH 06/23] drm/i915: Parse command buffer earlier in eb_relocate(slow) Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 07/23] Revert "drm/i915/gem: Split eb_vma into its own allocation" Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 08/23] drm/i915: Use per object locking in execbuf, v12 Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 09/23] drm/i915: Use ww locking in intel_renderstate Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 10/23] drm/i915: Add ww context handling to context_barrier_task Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 11/23] drm/i915: Nuke arguments to eb_pin_engine Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 12/23] drm/i915: Pin engine before pinning all objects, v5 Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 13/23] drm/i915: Rework intel_context pinning to do everything outside of pin_mutex Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 14/23] drm/i915: Make sure execbuffer always passes ww state to i915_vma_pin Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 15/23] drm/i915: Convert i915_gem_object/client_blt.c to use ww locking as well, v2 Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 16/23] drm/i915: Kill last user of intel_context_create_request outside of selftests Maarten Lankhorst
2020-07-14 11:45 ` Maarten Lankhorst [this message]
2020-07-14 11:45 ` [Intel-gfx] [PATCH 18/23] drm/i915: Dirty hack to fix selftests locking inversion Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 19/23] drm/i915/selftests: Fix locking inversion in lrc selftest Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 20/23] drm/i915: Use ww pinning for intel_context_create_request() Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 21/23] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v2 Maarten Lankhorst
2020-07-14 14:40 ` [Intel-gfx] [PATCH] " Maarten Lankhorst
2020-07-15 10:49 ` [Intel-gfx] [PATCH] drm/i915: Move i915_vma_lock in the selftests to avoid lock inversion, v3 Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 22/23] drm/i915: Add ww locking to vm_fault_gtt Maarten Lankhorst
2020-07-14 11:45 ` [Intel-gfx] [PATCH 23/23] drm/i915: Add ww locking to pin_to_display_plane Maarten Lankhorst
2020-07-14 13:14 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/23] Revert "drm/i915/gem: Async GPU relocations only" Patchwork
2020-07-14 13:15 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-07-14 13:36 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2020-07-14 15:22 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/23] Revert "drm/i915/gem: Async GPU relocations only" (rev2) Patchwork
2020-07-14 15:24 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-07-14 15:44 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2020-07-15 11:22 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/23] Revert "drm/i915/gem: Async GPU relocations only" (rev3) Patchwork
2020-07-15 11:22 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-07-15 11:42 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-07-15 14:06 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
-- strict thread matches above, loose matches on Subject: below --
2020-07-03 12:21 [Intel-gfx] [PATCH 00/23] drm/i915: Use ww locking in execbuf submission Maarten Lankhorst
2020-07-03 12:22 ` [Intel-gfx] [PATCH 17/23] drm/i915: Convert i915_perf to ww locking as well Maarten Lankhorst
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=20200714114516.3073222-17-maarten.lankhorst@linux.intel.com \
--to=maarten.lankhorst@linux.intel.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox