Intel-GFX Archive on lore.kernel.org
 help / color / Atom feed
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 04/42] drm/i915/gt: Protect context lifetime with RCU
Date: Sun,  2 Aug 2020 17:43:34 +0100
Message-ID: <20200802164412.2738-5-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200802164412.2738-1-chris@chris-wilson.co.uk>

Allow a brief period for continued access to a dead intel_context by
deferring the release of the struct until after an RCU grace period.
As we are using a dedicated slab cache for the contexts, we can defer
the release of the slab pages via RCU, with the caveat that individual
structs may be reused from the freelist within an RCU grace period. To
handle that, we have to avoid clearing members of the zombie struct.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_context.c | 330 +++++++++++++-----------
 drivers/gpu/drm/i915/i915_active.c      |  10 +
 drivers/gpu/drm/i915/i915_active.h      |   2 +
 drivers/gpu/drm/i915/i915_utils.h       |   7 +
 4 files changed, 202 insertions(+), 147 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 52db2bde44a3..4e7924640ffa 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -22,7 +22,7 @@ static struct i915_global_context {
 
 static struct intel_context *intel_context_alloc(void)
 {
-	return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL);
+	return kmem_cache_alloc(global.slab_ce, GFP_KERNEL);
 }
 
 void intel_context_free(struct intel_context *ce)
@@ -30,6 +30,177 @@ void intel_context_free(struct intel_context *ce)
 	kmem_cache_free(global.slab_ce, ce);
 }
 
+static int __context_pin_state(struct i915_vma *vma)
+{
+	unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
+	int err;
+
+	err = i915_ggtt_pin(vma, 0, bias | PIN_HIGH);
+	if (err)
+		return err;
+
+	err = i915_active_acquire(&vma->active);
+	if (err)
+		goto err_unpin;
+
+	/*
+	 * And mark it as a globally pinned object to let the shrinker know
+	 * it cannot reclaim the object until we release it.
+	 */
+	i915_vma_make_unshrinkable(vma);
+	vma->obj->mm.dirty = true;
+
+	return 0;
+
+err_unpin:
+	i915_vma_unpin(vma);
+	return err;
+}
+
+static void __context_unpin_state(struct i915_vma *vma)
+{
+	i915_vma_make_shrinkable(vma);
+	i915_active_release(&vma->active);
+	__i915_vma_unpin(vma);
+}
+
+static int __ring_active(struct intel_ring *ring)
+{
+	int err;
+
+	err = intel_ring_pin(ring);
+	if (err)
+		return err;
+
+	err = i915_active_acquire(&ring->vma->active);
+	if (err)
+		goto err_pin;
+
+	return 0;
+
+err_pin:
+	intel_ring_unpin(ring);
+	return err;
+}
+
+static void __ring_retire(struct intel_ring *ring)
+{
+	i915_active_release(&ring->vma->active);
+	intel_ring_unpin(ring);
+}
+
+__i915_active_call
+static void __intel_context_retire(struct i915_active *active)
+{
+	struct intel_context *ce = container_of(active, typeof(*ce), active);
+
+	CE_TRACE(ce, "retire runtime: { total:%lluns, avg:%lluns }\n",
+		 intel_context_get_total_runtime_ns(ce),
+		 intel_context_get_avg_runtime_ns(ce));
+
+	set_bit(CONTEXT_VALID_BIT, &ce->flags);
+	if (ce->state)
+		__context_unpin_state(ce->state);
+
+	intel_timeline_unpin(ce->timeline);
+	__ring_retire(ce->ring);
+
+	intel_context_put(ce);
+}
+
+static int __intel_context_active(struct i915_active *active)
+{
+	struct intel_context *ce = container_of(active, typeof(*ce), active);
+	int err;
+
+	CE_TRACE(ce, "active\n");
+
+	intel_context_get(ce);
+
+	err = __ring_active(ce->ring);
+	if (err)
+		goto err_put;
+
+	err = intel_timeline_pin(ce->timeline);
+	if (err)
+		goto err_ring;
+
+	if (!ce->state)
+		return 0;
+
+	err = __context_pin_state(ce->state);
+	if (err)
+		goto err_timeline;
+
+	return 0;
+
+err_timeline:
+	intel_timeline_unpin(ce->timeline);
+err_ring:
+	__ring_retire(ce->ring);
+err_put:
+	intel_context_put(ce);
+	return err;
+}
+
+static void __intel_context_ctor(void *arg)
+{
+	struct intel_context *ce = arg;
+
+	INIT_LIST_HEAD(&ce->signal_link);
+	INIT_LIST_HEAD(&ce->signals);
+
+	atomic_set(&ce->pin_count, 0);
+	mutex_init(&ce->pin_mutex);
+
+	ce->active_count = 0;
+	i915_active_init(&ce->active,
+			 __intel_context_active, __intel_context_retire);
+
+	ce->inflight = NULL;
+	ce->lrc_reg_state = NULL;
+	ce->lrc.desc = 0;
+}
+
+static void
+__intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
+{
+	GEM_BUG_ON(!engine->cops);
+	GEM_BUG_ON(!engine->gt->vm);
+
+	kref_init(&ce->ref);
+	i915_active_reinit(&ce->active);
+	mutex_reinit(&ce->pin_mutex);
+
+	ce->engine = engine;
+	ce->ops = engine->cops;
+	ce->sseu = engine->sseu;
+
+	ce->wa_bb_page = 0;
+	ce->flags = 0;
+	ce->tag = 0;
+
+	memset(&ce->runtime, 0, sizeof(ce->runtime));
+
+	ce->vm = i915_vm_get(engine->gt->vm);
+	ce->gem_context = NULL;
+
+	ce->ring = __intel_context_ring_size(SZ_4K);
+	ce->timeline = NULL;
+	ce->state = NULL;
+
+	GEM_BUG_ON(atomic_read(&ce->pin_count));
+	GEM_BUG_ON(ce->active_count);
+	GEM_BUG_ON(ce->inflight);
+}
+
+void
+intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)
+{
+	__intel_context_ctor(ce);
+	__intel_context_init(ce, engine);
+}
+
 struct intel_context *
 intel_context_create(struct intel_engine_cs *engine)
 {
@@ -39,7 +210,7 @@ intel_context_create(struct intel_engine_cs *engine)
 	if (!ce)
 		return ERR_PTR(-ENOMEM);
 
-	intel_context_init(ce, engine);
+	__intel_context_init(ce, engine);
 	return ce;
 }
 
@@ -158,154 +329,13 @@ void intel_context_unpin(struct intel_context *ce)
 	/*
 	 * Once released, we may asynchronously drop the active reference.
 	 * As that may be the only reference keeping the context alive,
-	 * take an extra now so that it is not freed before we finish
+	 * hold onto RCU so that it is not freed before we finish
 	 * dereferencing it.
 	 */
-	intel_context_get(ce);
+	rcu_read_lock();
 	intel_context_active_release(ce);
-	intel_context_put(ce);
-}
-
-static int __context_pin_state(struct i915_vma *vma)
-{
-	unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
-	int err;
-
-	err = i915_ggtt_pin(vma, 0, bias | PIN_HIGH);
-	if (err)
-		return err;
-
-	err = i915_active_acquire(&vma->active);
-	if (err)
-		goto err_unpin;
-
-	/*
-	 * And mark it as a globally pinned object to let the shrinker know
-	 * it cannot reclaim the object until we release it.
-	 */
-	i915_vma_make_unshrinkable(vma);
-	vma->obj->mm.dirty = true;
-
-	return 0;
-
-err_unpin:
-	i915_vma_unpin(vma);
-	return err;
-}
-
-static void __context_unpin_state(struct i915_vma *vma)
-{
-	i915_vma_make_shrinkable(vma);
-	i915_active_release(&vma->active);
-	__i915_vma_unpin(vma);
-}
-
-static int __ring_active(struct intel_ring *ring)
-{
-	int err;
-
-	err = intel_ring_pin(ring);
-	if (err)
-		return err;
-
-	err = i915_active_acquire(&ring->vma->active);
-	if (err)
-		goto err_pin;
-
-	return 0;
-
-err_pin:
-	intel_ring_unpin(ring);
-	return err;
-}
-
-static void __ring_retire(struct intel_ring *ring)
-{
-	i915_active_release(&ring->vma->active);
-	intel_ring_unpin(ring);
+	rcu_read_unlock();
 }
-
-__i915_active_call
-static void __intel_context_retire(struct i915_active *active)
-{
-	struct intel_context *ce = container_of(active, typeof(*ce), active);
-
-	CE_TRACE(ce, "retire runtime: { total:%lluns, avg:%lluns }\n",
-		 intel_context_get_total_runtime_ns(ce),
-		 intel_context_get_avg_runtime_ns(ce));
-
-	set_bit(CONTEXT_VALID_BIT, &ce->flags);
-	if (ce->state)
-		__context_unpin_state(ce->state);
-
-	intel_timeline_unpin(ce->timeline);
-	__ring_retire(ce->ring);
-
-	intel_context_put(ce);
-}
-
-static int __intel_context_active(struct i915_active *active)
-{
-	struct intel_context *ce = container_of(active, typeof(*ce), active);
-	int err;
-
-	CE_TRACE(ce, "active\n");
-
-	intel_context_get(ce);
-
-	err = __ring_active(ce->ring);
-	if (err)
-		goto err_put;
-
-	err = intel_timeline_pin(ce->timeline);
-	if (err)
-		goto err_ring;
-
-	if (!ce->state)
-		return 0;
-
-	err = __context_pin_state(ce->state);
-	if (err)
-		goto err_timeline;
-
-	return 0;
-
-err_timeline:
-	intel_timeline_unpin(ce->timeline);
-err_ring:
-	__ring_retire(ce->ring);
-err_put:
-	intel_context_put(ce);
-	return err;
-}
-
-void
-intel_context_init(struct intel_context *ce,
-		   struct intel_engine_cs *engine)
-{
-	GEM_BUG_ON(!engine->cops);
-	GEM_BUG_ON(!engine->gt->vm);
-
-	kref_init(&ce->ref);
-
-	ce->engine = engine;
-	ce->ops = engine->cops;
-	ce->sseu = engine->sseu;
-	ce->ring = __intel_context_ring_size(SZ_4K);
-
-	ewma_runtime_init(&ce->runtime.avg);
-
-	ce->vm = i915_vm_get(engine->gt->vm);
-
-	INIT_LIST_HEAD(&ce->signal_link);
-	INIT_LIST_HEAD(&ce->signals);
-
-	mutex_init(&ce->pin_mutex);
-
-	i915_active_init(&ce->active,
-			 __intel_context_active, __intel_context_retire);
-}
-
 void intel_context_fini(struct intel_context *ce)
 {
 	if (ce->timeline)
@@ -333,7 +363,13 @@ static struct i915_global_context global = { {
 
 int __init i915_global_context_init(void)
 {
-	global.slab_ce = KMEM_CACHE(intel_context, SLAB_HWCACHE_ALIGN);
+	global.slab_ce =
+		kmem_cache_create("intel_context",
+				  sizeof(struct intel_context),
+				  __alignof__(struct intel_context),
+				  SLAB_HWCACHE_ALIGN |
+				  SLAB_TYPESAFE_BY_RCU,
+				  __intel_context_ctor);
 	if (!global.slab_ce)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index b0a6522be3d1..6a3bb10e3bb2 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -795,6 +795,16 @@ void i915_active_fini(struct i915_active *ref)
 		kmem_cache_free(global.slab_cache, ref->cache);
 }
 
+void i915_active_reinit(struct i915_active *ref)
+{
+	GEM_BUG_ON(!i915_active_is_idle(ref));
+	debug_active_init(ref);
+	mutex_reinit(&ref->mutex);
+
+	ref->cache = NULL;
+	ref->tree = RB_ROOT;
+}
+
 static inline bool is_idle_barrier(struct active_node *node, u64 idx)
 {
 	return node->timeline == idx && !i915_active_fence_isset(&node->base);
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index fb165d3f01cf..6df7e721616d 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -219,6 +219,8 @@ i915_active_is_idle(const struct i915_active *ref)
 
 void i915_active_fini(struct i915_active *ref);
 
+void i915_active_reinit(struct i915_active *ref);
+
 int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					    struct intel_engine_cs *engine);
 void i915_active_acquire_barrier(struct i915_active *ref);
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 54773371e6bd..ef8db3aa75c7 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -443,6 +443,13 @@ static inline bool timer_expired(const struct timer_list *t)
 	return READ_ONCE(t->expires) && !timer_pending(t);
 }
 
+static inline void mutex_reinit(struct mutex *lock)
+{
+#if IS_ENABLED(CONFIG_DEBUG_MUTEXES)
+	lock->magic = lock;
+#endif
+}
+
 /*
  * This is a lookalike for IS_ENABLED() that takes a kconfig value,
  * e.g. CONFIG_DRM_I915_SPIN_REQUEST, and evaluates whether it is non-zero
-- 
2.20.1

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

  parent reply index

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 ` Chris Wilson [this message]
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 ` [Intel-gfx] [PATCH 06/42] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock Chris Wilson
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=20200802164412.2738-5-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

Intel-GFX Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/intel-gfx/0 intel-gfx/git/0.git
	git clone --mirror https://lore.kernel.org/intel-gfx/1 intel-gfx/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 intel-gfx intel-gfx/ https://lore.kernel.org/intel-gfx \
		intel-gfx@lists.freedesktop.org
	public-inbox-index intel-gfx

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.freedesktop.lists.intel-gfx


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git