From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 06/42] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock
Date: Sun, 2 Aug 2020 17:43:36 +0100 [thread overview]
Message-ID: <20200802164412.2738-7-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200802164412.2738-1-chris@chris-wilson.co.uk>
Make b->signaled_requests a lockless-list so that we can manipulate it
outside of the b->irq_lock.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 53 ++++++++++++++-----
.../gpu/drm/i915/gt/intel_breadcrumbs_types.h | 2 +-
drivers/gpu/drm/i915/i915_request.h | 6 ++-
3 files changed, 46 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index d8b206e53660..9e7ac612fabb 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -174,16 +174,13 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
intel_engine_add_retire(b->irq_engine, tl);
}
-static bool __signal_request(struct i915_request *rq, struct list_head *signals)
+static bool __signal_request(struct i915_request *rq)
{
- clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
-
if (!__dma_fence_signal(&rq->fence)) {
i915_request_put(rq);
return false;
}
- list_add_tail(&rq->signal_link, signals);
return true;
}
@@ -191,17 +188,42 @@ static void signal_irq_work(struct irq_work *work)
{
struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work);
const ktime_t timestamp = ktime_get();
+ struct llist_node *signal, *sn;
struct intel_context *ce, *cn;
struct list_head *pos, *next;
- LIST_HEAD(signal);
+
+ signal = NULL;
+ if (unlikely(!llist_empty(&b->signaled_requests)))
+ signal = llist_del_all(&b->signaled_requests);
spin_lock(&b->irq_lock);
- if (list_empty(&b->signalers))
+ /*
+ * Keep the irq armed until the interrupt after all listeners are gone.
+ *
+ * Enabling/disabling the interrupt is rather costly, roughly a couple
+ * of hundred microseconds. If we are proactive and enable/disable
+ * the interrupt around every request that wants a breadcrumb, we
+ * quickly drown in the extra orders of magnitude of latency imposed
+ * on request submission.
+ *
+ * So we try to be lazy, and keep the interrupts enabled until no
+ * more listeners appear within a breadcrumb interrupt interval (that
+ * is until a request completes that no one cares about). The
+ * observation is that listeners come in batches, and will often
+ * listen to a bunch of requests in succession.
+ *
+ * We also try to avoid raising too many interrupts, as they may
+ * be generated by userspace batches and it is unfortunately rather
+ * too easy to drown the CPU under a flood of GPU interrupts. Thus
+ * whenever no one appears to be listening, we turn off the interrupts.
+ * Fewer interrupts should conserve power -- at the very least, fewer
+ * interrupt draw less ire from other users of the system and tools
+ * like powertop.
+ */
+ if (!signal && list_empty(&b->signalers))
__intel_breadcrumbs_disarm_irq(b);
- list_splice_init(&b->signaled_requests, &signal);
-
list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) {
GEM_BUG_ON(list_empty(&ce->signals));
@@ -218,7 +240,11 @@ static void signal_irq_work(struct irq_work *work)
* spinlock as the callback chain may end up adding
* more signalers to the same context or engine.
*/
- __signal_request(rq, &signal);
+ clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+ if (__signal_request(rq)) {
+ rq->signal_node.next = signal;
+ signal = &rq->signal_node;
+ }
}
/*
@@ -238,9 +264,9 @@ static void signal_irq_work(struct irq_work *work)
spin_unlock(&b->irq_lock);
- list_for_each_safe(pos, next, &signal) {
+ llist_for_each_safe(signal, sn, signal) {
struct i915_request *rq =
- list_entry(pos, typeof(*rq), signal_link);
+ llist_entry(signal, typeof(*rq), signal_node);
struct list_head cb_list;
spin_lock(&rq->lock);
@@ -264,7 +290,7 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine)
spin_lock_init(&b->irq_lock);
INIT_LIST_HEAD(&b->signalers);
- INIT_LIST_HEAD(&b->signaled_requests);
+ init_llist_head(&b->signaled_requests);
init_irq_work(&b->irq_work, signal_irq_work);
@@ -327,7 +353,8 @@ static void insert_breadcrumb(struct i915_request *rq,
* its signal completion.
*/
if (__request_completed(rq)) {
- if (__signal_request(rq, &b->signaled_requests))
+ if (__signal_request(rq) &&
+ llist_add(&rq->signal_node, &b->signaled_requests))
irq_work_queue(&b->irq_work);
return;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
index 8e53b9942695..3fa19820b37a 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h
@@ -35,7 +35,7 @@ struct intel_breadcrumbs {
struct intel_engine_cs *irq_engine;
struct list_head signalers;
- struct list_head signaled_requests;
+ struct llist_head signaled_requests;
struct irq_work irq_work; /* for use from inside irq_lock */
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 16b721080195..874af6db6103 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -176,7 +176,11 @@ struct i915_request {
struct intel_context *context;
struct intel_ring *ring;
struct intel_timeline __rcu *timeline;
- struct list_head signal_link;
+
+ union {
+ struct list_head signal_link;
+ struct llist_node signal_node;
+ };
/*
* The rcu epoch of when this request was allocated. Used to judiciously
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2020-08-02 16:44 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-08-02 16:43 [Intel-gfx] Time, where did it go? Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 01/42] drm/i915: Fix wrong return value Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 02/42] drm/i915/gem: Don't drop the timeline lock during execbuf Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 03/42] drm/i915/gem: Reduce context termination list iteration guard to RCU Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 04/42] drm/i915/gt: Protect context lifetime with RCU Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 05/42] drm/i915/gt: Free stale request on destroying the virtual engine Chris Wilson
2020-08-02 16:43 ` Chris Wilson [this message]
2020-08-02 16:43 ` [Intel-gfx] [PATCH 07/42] drm/i915/gt: Split the breadcrumb spinlock between global and contexts Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 08/42] drm/i915: Drop i915_request.lock serialisation around await_start Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 09/42] drm/i915: Drop i915_request.lock requirement for intel_rps_boost() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 10/42] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 11/42] drm/i915/gem: Reduce ctx->engines_mutex for get_engines() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 12/42] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 13/42] drm/i915/gt: Decouple completed requests on unwind Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 14/42] drm/i915/gt: Check for a completed last request once Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 15/42] drm/i915/gt: Refactor heartbeat request construction and submission Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 16/42] drm/i915/gt: Replace direct submit with direct call to tasklet Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 17/42] drm/i915/gt: Use virtual_engine during execlists_dequeue Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 18/42] drm/i915/gt: Decouple inflight virtual engines Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 19/42] drm/i915/gt: Defer schedule_out until after the next dequeue Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 20/42] drm/i915/gt: Resubmit the virtual engine on schedule-out Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 21/42] drm/i915/gt: Simplify virtual engine handling for execlists_hold() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 22/42] drm/i915/gt: ce->inflight updates are now serialised Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 23/42] drm/i915/gt: Drop atomic for engine->fw_active tracking Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 24/42] drm/i915/gt: Extract busy-stats for ring-scheduler Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 25/42] drm/i915/gt: Convert stats.active to plain unsigned int Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 26/42] drm/i915: Lift waiter/signaler iterators Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 27/42] drm/i915: Strip out internal priorities Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 28/42] drm/i915: Remove I915_USER_PRIORITY_SHIFT Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 29/42] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 30/42] drm/i915: Prune empty priolists Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 31/42] drm/i915: Replace engine->schedule() with a known request operation Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 32/42] drm/i915/gt: Do not suspend bonded requests if one hangs Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 33/42] drm/i915: Teach the i915_dependency to use a double-lock Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 34/42] drm/i915: Restructure priority inheritance Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 35/42] drm/i915/selftests: Measure set-priority duration Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 36/42] drm/i915: Improve DFS for priority inheritance Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 37/42] drm/i915/gt: Remove timeslice suppression Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 38/42] drm/i915: Fair low-latency scheduling Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 39/42] drm/i915/gt: Specify a deadline for the heartbeat Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 40/42] drm/i915: Replace the priority boosting for the display with a deadline Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 41/42] drm/i915: Move saturated workload detection back to the context Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 42/42] drm/i915/gt: Another tweak for flushing the tasklets Chris Wilson
2020-08-02 17:14 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/42] drm/i915: Fix wrong return value Patchwork
2020-08-02 17:14 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-08-02 17:34 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-08-02 17:56 ` [Intel-gfx] Time, where did it go? Dave Airlie
2020-08-02 19:36 ` Chris Wilson
2020-08-04 21:45 ` Dave Airlie
2020-08-07 7:12 ` Chris Wilson
2020-08-09 20:01 ` Dave Airlie
2020-08-02 21:03 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for series starting with [01/42] drm/i915: Fix wrong return value Patchwork
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=20200802164412.2738-7-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).