From: Matthew Brost <matthew.brost@intel.com>
To: <intel-gfx@lists.freedesktop.org>, <dri-devel@lists.freedesktop.org>
Cc: <john.c.harrison@intel.com>
Subject: [Intel-gfx] [PATCH 14/25] drm/i915/guc: Implement multi-lrc reset
Date: Thu, 14 Oct 2021 10:19:54 -0700 [thread overview]
Message-ID: <20211014172005.27155-15-matthew.brost@intel.com> (raw)
In-Reply-To: <20211014172005.27155-1-matthew.brost@intel.com>
Update context and full GPU reset to work with multi-lrc. The idea is
parent context tracks all the active requests inflight for itself and
its children. The parent context owns the reset replaying / canceling
requests as needed.
v2:
(John Harrison)
- Simply loop in find active request
- Add comments to find ative request / reset loop
v3:
(John Harrison)
- s/its'/its/g
- Fix comment when searching for active request
- Reorder if state in __guc_reset_context
v4:
(Kernel test robot)
- Delete ununsed is_multi_lrc function
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/i915/gt/intel_context.c | 15 ++++-
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 64 +++++++++++++------
2 files changed, 58 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 79f321c6c008..6aab60584ee5 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -529,20 +529,29 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
struct i915_request *intel_context_find_active_request(struct intel_context *ce)
{
+ struct intel_context *parent = intel_context_to_parent(ce);
struct i915_request *rq, *active = NULL;
unsigned long flags;
GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));
- spin_lock_irqsave(&ce->guc_state.lock, flags);
- list_for_each_entry_reverse(rq, &ce->guc_state.requests,
+ /*
+ * We search the parent list to find an active request on the submitted
+ * context. The parent list contains the requests for all the contexts
+ * in the relationship so we have to do a compare of each request's
+ * context.
+ */
+ spin_lock_irqsave(&parent->guc_state.lock, flags);
+ list_for_each_entry_reverse(rq, &parent->guc_state.requests,
sched.link) {
+ if (rq->context != ce)
+ continue;
if (i915_request_completed(rq))
break;
active = rq;
}
- spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+ spin_unlock_irqrestore(&parent->guc_state.lock, flags);
return active;
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index ebb64fb50396..112b5e6fe39d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1217,10 +1217,15 @@ __unwind_incomplete_requests(struct intel_context *ce)
static void __guc_reset_context(struct intel_context *ce, bool stalled)
{
+ bool local_stalled;
struct i915_request *rq;
unsigned long flags;
u32 head;
+ int i, number_children = ce->parallel.number_children;
bool skip = false;
+ struct intel_context *parent = ce;
+
+ GEM_BUG_ON(intel_context_is_child(ce));
intel_context_get(ce);
@@ -1246,25 +1251,38 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
if (unlikely(skip))
goto out_put;
- rq = intel_context_find_active_request(ce);
- if (!rq) {
- head = ce->ring->tail;
- stalled = false;
- goto out_replay;
- }
+ /*
+ * For each context in the relationship find the hanging request
+ * resetting each context / request as needed
+ */
+ for (i = 0; i < number_children + 1; ++i) {
+ if (!intel_context_is_pinned(ce))
+ goto next_context;
+
+ local_stalled = false;
+ rq = intel_context_find_active_request(ce);
+ if (!rq) {
+ head = ce->ring->tail;
+ goto out_replay;
+ }
- if (!i915_request_started(rq))
- stalled = false;
+ if (i915_request_started(rq))
+ local_stalled = true;
- GEM_BUG_ON(i915_active_is_idle(&ce->active));
- head = intel_ring_wrap(ce->ring, rq->head);
- __i915_request_reset(rq, stalled);
+ GEM_BUG_ON(i915_active_is_idle(&ce->active));
+ head = intel_ring_wrap(ce->ring, rq->head);
+ __i915_request_reset(rq, local_stalled && stalled);
out_replay:
- guc_reset_state(ce, head, stalled);
- __unwind_incomplete_requests(ce);
+ guc_reset_state(ce, head, local_stalled && stalled);
+next_context:
+ if (i != number_children)
+ ce = list_next_entry(ce, parallel.child_link);
+ }
+
+ __unwind_incomplete_requests(parent);
out_put:
- intel_context_put(ce);
+ intel_context_put(parent);
}
void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
@@ -1285,7 +1303,8 @@ void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
xa_unlock(&guc->context_lookup);
- if (intel_context_is_pinned(ce))
+ if (intel_context_is_pinned(ce) &&
+ !intel_context_is_child(ce))
__guc_reset_context(ce, stalled);
intel_context_put(ce);
@@ -1377,7 +1396,8 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
xa_unlock(&guc->context_lookup);
- if (intel_context_is_pinned(ce))
+ if (intel_context_is_pinned(ce) &&
+ !intel_context_is_child(ce))
guc_cancel_context_requests(ce);
intel_context_put(ce);
@@ -2070,6 +2090,8 @@ static struct i915_sw_fence *guc_context_block(struct intel_context *ce)
u16 guc_id;
bool enabled;
+ GEM_BUG_ON(intel_context_is_child(ce));
+
spin_lock_irqsave(&ce->guc_state.lock, flags);
incr_context_blocked(ce);
@@ -2124,6 +2146,7 @@ static void guc_context_unblock(struct intel_context *ce)
bool enable;
GEM_BUG_ON(context_enabled(ce));
+ GEM_BUG_ON(intel_context_is_child(ce));
spin_lock_irqsave(&ce->guc_state.lock, flags);
@@ -2150,11 +2173,14 @@ static void guc_context_unblock(struct intel_context *ce)
static void guc_context_cancel_request(struct intel_context *ce,
struct i915_request *rq)
{
+ struct intel_context *block_context =
+ request_to_scheduling_context(rq);
+
if (i915_sw_fence_signaled(&rq->submit)) {
struct i915_sw_fence *fence;
intel_context_get(ce);
- fence = guc_context_block(ce);
+ fence = guc_context_block(block_context);
i915_sw_fence_wait(fence);
if (!i915_request_completed(rq)) {
__i915_request_skip(rq);
@@ -2168,7 +2194,7 @@ static void guc_context_cancel_request(struct intel_context *ce,
*/
flush_work(&ce_to_guc(ce)->ct.requests.worker);
- guc_context_unblock(ce);
+ guc_context_unblock(block_context);
intel_context_put(ce);
}
}
@@ -2194,6 +2220,8 @@ static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
intel_wakeref_t wakeref;
unsigned long flags;
+ GEM_BUG_ON(intel_context_is_child(ce));
+
guc_flush_submissions(guc);
spin_lock_irqsave(&ce->guc_state.lock, flags);
--
2.32.0
next prev parent reply other threads:[~2021-10-14 17:49 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-14 17:19 [Intel-gfx] [PATCH 00/25] Parallel submission aka multi-bb execbuf Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 01/25] drm/i915/guc: Move GuC guc_id allocation under submission state sub-struct Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 02/25] drm/i915/guc: Take GT PM ref when deregistering context Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 03/25] drm/i915/guc: Take engine PM when a context is pinned with GuC submission Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 04/25] drm/i915/guc: Don't call switch_to_kernel_context " Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 05/25] drm/i915: Add logical engine mapping Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 06/25] drm/i915: Expose logical engine instance to user Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 07/25] drm/i915/guc: Introduce context parent-child relationship Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 08/25] drm/i915/guc: Add multi-lrc context registration Matthew Brost
2021-10-14 18:18 ` John Harrison
2021-10-14 17:19 ` [Intel-gfx] [PATCH 09/25] drm/i915/guc: Ensure GuC schedule operations do not operate on child contexts Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 10/25] drm/i915/guc: Assign contexts in parent-child relationship consecutive guc_ids Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 11/25] drm/i915/guc: Implement parallel context pin / unpin functions Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 12/25] drm/i915/guc: Implement multi-lrc submission Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 13/25] drm/i915/guc: Insert submit fences between requests in parent-child relationship Matthew Brost
2021-10-14 17:19 ` Matthew Brost [this message]
2021-10-14 17:19 ` [Intel-gfx] [PATCH 15/25] drm/i915/guc: Update debugfs for GuC multi-lrc Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 16/25] drm/i915/guc: Connect UAPI to GuC multi-lrc interface Matthew Brost
2021-10-14 18:24 ` John Harrison
2021-10-14 17:19 ` [Intel-gfx] [PATCH 17/25] drm/i915/doc: Update parallel submit doc to point to i915_drm.h Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 18/25] drm/i915/guc: Add basic GuC multi-lrc selftest Matthew Brost
2021-10-14 17:19 ` [Intel-gfx] [PATCH 19/25] drm/i915/guc: Implement no mid batch preemption for multi-lrc Matthew Brost
2021-10-14 17:20 ` [Intel-gfx] [PATCH 20/25] drm/i915: Multi-BB execbuf Matthew Brost
2021-10-14 18:27 ` John Harrison
2021-10-14 17:20 ` [Intel-gfx] [PATCH 21/25] drm/i915/guc: Handle errors in multi-lrc requests Matthew Brost
2021-10-14 17:20 ` [Intel-gfx] [PATCH 22/25] drm/i915: Make request conflict tracking understand parallel submits Matthew Brost
2021-10-14 17:20 ` [Intel-gfx] [PATCH 23/25] drm/i915: Update I915_GEM_BUSY IOCTL to understand composite fences Matthew Brost
2021-10-14 17:20 ` [Intel-gfx] [PATCH 24/25] drm/i915: Enable multi-bb execbuf Matthew Brost
2021-10-14 18:29 ` John Harrison
2021-10-14 17:20 ` [Intel-gfx] [PATCH 25/25] drm/i915/execlists: Weak parallel submission support for execlists Matthew Brost
2021-10-14 18:42 ` John Harrison
2021-10-14 18:55 ` Matthew Brost
2021-10-14 23:50 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Parallel submission aka multi-bb execbuf (rev7) Patchwork
2021-10-14 23:51 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-10-15 0:25 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-10-15 6:12 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
-- strict thread matches above, loose matches on Subject: below --
2021-10-13 20:42 [Intel-gfx] [PATCH 00/25] Parallel submission aka multi-bb execbuf Matthew Brost
2021-10-13 20:42 ` [Intel-gfx] [PATCH 14/25] drm/i915/guc: Implement multi-lrc reset Matthew Brost
2021-10-14 0:28 ` John Harrison
2021-10-14 16:26 ` kernel test robot
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=20211014172005.27155-15-matthew.brost@intel.com \
--to=matthew.brost@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=john.c.harrison@intel.com \
/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