[Intel-gfx] [PATCH 1/7] drm/i915/gem: Remove redundant exec_fence

[Intel-gfx] [PATCH 1/7] drm/i915/gem: Remove redundant exec_fence

[Chris Wilson]

Since there can only be one of in_fence/exec_fence, just use the single
in_fence local.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 24 ++++++++-----------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index d54a4933cc05..824a2b76947a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2622,7 +2622,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
-	struct dma_fence *exec_fence = NULL;
 	struct sync_file *out_fence = NULL;
 	struct i915_vma *batch;
 	int out_fence_fd = -1;
@@ -2677,8 +2676,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_in_fence;
 		}
 
-		exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!exec_fence) {
+		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
+		if (!in_fence) {
 			err = -EINVAL;
 			goto err_in_fence;
 		}
@@ -2688,7 +2687,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
 		if (out_fence_fd < 0) {
 			err = out_fence_fd;
-			goto err_exec_fence;
+			goto err_in_fence;
 		}
 	}
 
@@ -2779,14 +2778,13 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	}
 
 	if (in_fence) {
-		err = i915_request_await_dma_fence(eb.request, in_fence);
-		if (err < 0)
-			goto err_request;
-	}
-
-	if (exec_fence) {
-		err = i915_request_await_execution(eb.request, exec_fence,
-						   eb.engine->bond_execute);
+		if (args->flags & I915_EXEC_FENCE_SUBMIT)
+			err = i915_request_await_execution(eb.request,
+							   in_fence,
+							   eb.engine->bond_execute);
+		else
+			err = i915_request_await_dma_fence(eb.request,
+							   in_fence);
 		if (err < 0)
 			goto err_request;
 	}
@@ -2855,8 +2853,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
-err_exec_fence:
-	dma_fence_put(exec_fence);
 err_in_fence:
 	dma_fence_put(in_fence);
 	return err;
-- 
2.20.1

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

[Intel-gfx] [PATCH 2/7] drm/i915: Mark the addition of the initial-breadcrumb in the request

[Chris Wilson]

The initial-breadcrumb is used to mark the end of the awaiting and the
beginning of the user payload. We verify that we do not start the user
payload before all signaler are completed, checking our semaphore setup
by looking for the initial breadcrumb being written too early. We also
want to ensure that we do not add semaphore waits after we have already
closed the semaphore section, an issue for later deferred waits.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c |  5 ++++-
 drivers/gpu/drm/i915/i915_request.c |  7 ++++++-
 drivers/gpu/drm/i915/i915_request.h | 27 ++++++++++++++++++++-------
 3 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 32feb2a27dfc..51470e96cdd4 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1886,7 +1886,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 				continue;
 
 			/* No waiter should start before its signaler */
-			GEM_BUG_ON(w->context->timeline->has_initial_breadcrumb &&
+			GEM_BUG_ON(i915_request_has_initial_breadcrumb(w) &&
 				   i915_request_started(w) &&
 				   !i915_request_completed(rq));
 
@@ -3493,6 +3493,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 {
 	u32 *cs;
 
+	GEM_BUG_ON(i915_request_has_initial_breadcrumb(rq));
 	if (!i915_request_timeline(rq)->has_initial_breadcrumb)
 		return 0;
 
@@ -3519,6 +3520,8 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	/* Record the updated position of the request's payload */
 	rq->infix = intel_ring_offset(rq, cs);
 
+	__set_bit(I915_FENCE_FLAG_INITIAL_BREADCRUMB, &rq->fence.flags);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 2d5b98549ddc..00b7c4eb3f32 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -951,6 +951,7 @@ __emit_semaphore_wait(struct i915_request *to,
 	u32 *cs;
 
 	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
+	GEM_BUG_ON(i915_request_has_initial_breadcrumb(to));
 
 	/* We need to pin the signaler's HWSP until we are finished reading. */
 	err = intel_timeline_read_hwsp(from, to, &hwsp_offset);
@@ -1000,6 +1001,9 @@ emit_semaphore_wait(struct i915_request *to,
 	if (!intel_context_use_semaphores(to->context))
 		goto await_fence;
 
+	if (i915_request_has_initial_breadcrumb(to))
+		goto await_fence;
+
 	if (!rcu_access_pointer(from->hwsp_cacheline))
 		goto await_fence;
 
@@ -1256,7 +1260,8 @@ __i915_request_await_execution(struct i915_request *to,
 	 * immediate execution, and so we must wait until it reaches the
 	 * active slot.
 	 */
-	if (intel_engine_has_semaphores(to->engine)) {
+	if (intel_engine_has_semaphores(to->engine) &&
+	    !i915_request_has_initial_breadcrumb(to)) {
 		err = __emit_semaphore_wait(to, from, from->fence.seqno - 1);
 		if (err < 0)
 			return err;
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index d8ce908e1346..98ae2dc82371 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -84,19 +84,26 @@ enum {
 	I915_FENCE_FLAG_PQUEUE,
 
 	/*
-	 * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list
+	 * I915_FENCE_FLAG_HOLD - this request is currently on hold
 	 *
-	 * Internal bookkeeping used by the breadcrumb code to track when
-	 * a request is on the various signal_list.
+	 * This request has been suspended, pending an ongoing investigation.
 	 */
-	I915_FENCE_FLAG_SIGNAL,
+	I915_FENCE_FLAG_HOLD,
 
 	/*
-	 * I915_FENCE_FLAG_HOLD - this request is currently on hold
+	 * I915_FENCE_FLAG_INITIAL_BREADCRUMB - this request has the initial
+	 * breadcrumb that marks the end of semaphore waits and start of the
+	 * user payload.
+	 */
+	I915_FENCE_FLAG_INITIAL_BREADCRUMB,
+
+	/*
+	 * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list
 	 *
-	 * This request has been suspended, pending an ongoing investigation.
+	 * Internal bookkeeping used by the breadcrumb code to track when
+	 * a request is on the various signal_list.
 	 */
-	I915_FENCE_FLAG_HOLD,
+	I915_FENCE_FLAG_SIGNAL,
 
 	/*
 	 * I915_FENCE_FLAG_NOPREEMPT - this request should not be preempted
@@ -390,6 +397,12 @@ static inline bool i915_request_in_priority_queue(const struct i915_request *rq)
 	return test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
 }
 
+static inline bool
+i915_request_has_initial_breadcrumb(const struct i915_request *rq)
+{
+	return test_bit(I915_FENCE_FLAG_INITIAL_BREADCRUMB, &rq->fence.flags);
+}
+
 /**
  * Returns true if seq1 is later than seq2.
  */
-- 
2.20.1

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

[Intel-gfx] [PATCH 3/7] dma-buf: Proxy fence, an unsignaled fence placeholder

[Chris Wilson]

Often we need to create a fence for a future event that has not yet been
associated with a fence. We can store a proxy fence, a placeholder, in
the timeline and replace it later when the real fence is known. Any
listeners that attach to the proxy fence will automatically be signaled
when the real fence completes, and any future listeners will instead be
attach directly to the real fence avoiding any indirection overhead.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
---
 drivers/dma-buf/Makefile             |  13 +-
 drivers/dma-buf/dma-fence-private.h  |  20 +
 drivers/dma-buf/dma-fence-proxy.c    | 248 ++++++++++
 drivers/dma-buf/dma-fence.c          |   4 +-
 drivers/dma-buf/selftests.h          |   1 +
 drivers/dma-buf/st-dma-fence-proxy.c | 699 +++++++++++++++++++++++++++
 include/linux/dma-fence-proxy.h      |  34 ++
 7 files changed, 1015 insertions(+), 4 deletions(-)
 create mode 100644 drivers/dma-buf/dma-fence-private.h
 create mode 100644 drivers/dma-buf/dma-fence-proxy.c
 create mode 100644 drivers/dma-buf/st-dma-fence-proxy.c
 create mode 100644 include/linux/dma-fence-proxy.h

diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 995e05f609ff..afaf6dadd9a3 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,6 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
-	 dma-resv.o seqno-fence.o
+obj-y := \
+	dma-buf.o \
+	dma-fence.o \
+	dma-fence-array.o \
+	dma-fence-chain.o \
+	dma-fence-proxy.o \
+	dma-resv.o \
+	seqno-fence.o
 obj-$(CONFIG_DMABUF_HEAPS)	+= dma-heap.o
 obj-$(CONFIG_DMABUF_HEAPS)	+= heaps/
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
@@ -10,6 +16,7 @@ obj-$(CONFIG_UDMABUF)		+= udmabuf.o
 dmabuf_selftests-y := \
 	selftest.o \
 	st-dma-fence.o \
-	st-dma-fence-chain.o
+	st-dma-fence-chain.o \
+	st-dma-fence-proxy.o
 
 obj-$(CONFIG_DMABUF_SELFTESTS)	+= dmabuf_selftests.o
diff --git a/drivers/dma-buf/dma-fence-private.h b/drivers/dma-buf/dma-fence-private.h
new file mode 100644
index 000000000000..6924d28af0fa
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-private.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Fence mechanism for dma-buf and to allow for asynchronous dma access
+ *
+ * Copyright (C) 2012 Canonical Ltd
+ * Copyright (C) 2012 Texas Instruments
+ *
+ * Authors:
+ * Rob Clark <robdclark@gmail.com>
+ * Maarten Lankhorst <maarten.lankhorst@canonical.com>
+ */
+
+#ifndef DMA_FENCE_PRIVATE_H
+#define DMA_FENCE_PRIAVTE_H
+
+struct dma_fence;
+
+bool __dma_fence_enable_signaling(struct dma_fence *fence);
+
+#endif /* DMA_FENCE_PRIAVTE_H */
diff --git a/drivers/dma-buf/dma-fence-proxy.c b/drivers/dma-buf/dma-fence-proxy.c
new file mode 100644
index 000000000000..f0cd89b966e0
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-proxy.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * dma-fence-proxy: placeholder unsignaled fence
+ *
+ * Copyright (C) 2017-2019 Intel Corporation
+ */
+
+#include <linux/dma-fence.h>
+#include <linux/dma-fence-proxy.h>
+#include <linux/export.h>
+#include <linux/irq_work.h>
+#include <linux/slab.h>
+
+#include "dma-fence-private.h"
+
+struct dma_fence_proxy {
+	struct dma_fence base;
+
+	struct dma_fence *real;
+	struct dma_fence_cb cb;
+	struct irq_work work;
+
+	wait_queue_head_t wq;
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#define same_lockclass(A, B) (A)->dep_map.key == (B)->dep_map.key
+#else
+#define same_lockclass(A, B) 0
+#endif
+
+static const char *proxy_get_driver_name(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	struct dma_fence *real = READ_ONCE(p->real);
+
+	return real ? real->ops->get_driver_name(real) : "proxy";
+}
+
+static const char *proxy_get_timeline_name(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	struct dma_fence *real = READ_ONCE(p->real);
+
+	return real ? real->ops->get_timeline_name(real) : "unset";
+}
+
+static void proxy_irq_work(struct irq_work *work)
+{
+	struct dma_fence_proxy *p = container_of(work, typeof(*p), work);
+
+	dma_fence_signal(&p->base);
+	dma_fence_put(&p->base);
+}
+
+static void proxy_callback(struct dma_fence *real, struct dma_fence_cb *cb)
+{
+	struct dma_fence_proxy *p = container_of(cb, typeof(*p), cb);
+
+	if (real->error)
+		dma_fence_set_error(&p->base, real->error);
+
+	/* Lower the height of the proxy chain -> single stack frame */
+	irq_work_queue(&p->work);
+}
+
+static bool proxy_enable_signaling(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	struct dma_fence *real = READ_ONCE(p->real);
+	bool ret = true;
+
+	if (real) {
+		spin_lock_nested(real->lock,
+				 same_lockclass(&p->wq.lock, real->lock));
+		ret = __dma_fence_enable_signaling(real);
+		spin_unlock(real->lock);
+	}
+
+	return ret;
+}
+
+static void proxy_release(struct dma_fence *fence)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+
+	dma_fence_put(p->real);
+	dma_fence_free(&p->base);
+}
+
+const struct dma_fence_ops dma_fence_proxy_ops = {
+	.get_driver_name = proxy_get_driver_name,
+	.get_timeline_name = proxy_get_timeline_name,
+	.enable_signaling = proxy_enable_signaling,
+	.wait = dma_fence_default_wait,
+	.release = proxy_release,
+};
+EXPORT_SYMBOL_GPL(dma_fence_proxy_ops);
+
+/**
+ * dma_fence_create_proxy - Create an unset dma-fence
+ *
+ * dma_fence_create_proxy() creates a new dma_fence stub that is initially
+ * unsignaled and may later be replaced with a real fence. Any listeners
+ * to the proxy fence will be signaled when the target fence signals its
+ * completion.
+ */
+struct dma_fence *dma_fence_create_proxy(void)
+{
+	struct dma_fence_proxy *p;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return NULL;
+
+	init_waitqueue_head(&p->wq);
+	dma_fence_init(&p->base, &dma_fence_proxy_ops, &p->wq.lock,
+		       dma_fence_context_alloc(1), 0);
+	init_irq_work(&p->work, proxy_irq_work);
+
+	return &p->base;
+}
+EXPORT_SYMBOL(dma_fence_create_proxy);
+
+static void __wake_up_listeners(struct dma_fence_proxy *p)
+{
+	struct wait_queue_entry *wait, *next;
+
+	list_for_each_entry_safe(wait, next, &p->wq.head, entry) {
+		INIT_LIST_HEAD(&wait->entry);
+		wait->func(wait, TASK_NORMAL, 0, p->real);
+	}
+}
+
+static void proxy_assign(struct dma_fence *fence, struct dma_fence *real)
+{
+	struct dma_fence_proxy *p = container_of(fence, typeof(*p), base);
+	unsigned long flags;
+
+	if (WARN_ON(fence == real))
+		return;
+
+	if (WARN_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)))
+		return;
+
+	if (WARN_ON(p->real))
+		return;
+
+	spin_lock_irqsave(&p->wq.lock, flags);
+
+	if (unlikely(!real)) {
+		dma_fence_signal_locked(&p->base);
+		goto unlock;
+	}
+
+	p->real = dma_fence_get(real);
+
+	dma_fence_get(&p->base);
+	spin_lock_nested(real->lock, same_lockclass(&p->wq.lock, real->lock));
+	if (dma_fence_is_signaled_locked(real)) {
+		proxy_callback(real, &p->cb);
+	} else if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
+			    &p->base.flags) &&
+		   !__dma_fence_enable_signaling(real)) {
+		proxy_callback(real, &p->cb);
+	} else {
+		p->cb.func = proxy_callback;
+		list_add_tail(&p->cb.node, &real->cb_list);
+	}
+	spin_unlock(real->lock);
+
+unlock:
+	__wake_up_listeners(p);
+	spin_unlock_irqrestore(&p->wq.lock, flags);
+}
+
+/**
+ * dma_fence_replace_proxy - Replace the proxy fence with the real target
+ * @slot: pointer to location of fence to update
+ * @fence: the new fence to store in @slot
+ *
+ * Once the real dma_fence is known, we can replace the proxy fence holder
+ * with a pointer to the real dma fence. Future listeners will attach to
+ * the real fence, avoiding any indirection overhead. Previous listeners
+ * will remain attached to the proxy fence, and be signaled in turn when
+ * the target fence completes.
+ */
+struct dma_fence *
+dma_fence_replace_proxy(struct dma_fence __rcu **slot, struct dma_fence *fence)
+{
+	struct dma_fence *old;
+
+	if (fence)
+		dma_fence_get(fence);
+
+	old = rcu_replace_pointer(*slot, fence, true);
+	if (old && dma_fence_is_proxy(old))
+		proxy_assign(old, fence);
+
+	return old;
+}
+EXPORT_SYMBOL(dma_fence_replace_proxy);
+
+void dma_fence_add_proxy_listener(struct dma_fence *fence,
+				  struct wait_queue_entry *wait)
+{
+	if (dma_fence_is_proxy(fence)) {
+		struct dma_fence_proxy *p =
+			container_of(fence, typeof(*p), base);
+		unsigned long flags;
+
+		spin_lock_irqsave(&p->wq.lock, flags);
+		if (!p->real) {
+			list_add_tail(&wait->entry, &p->wq.head);
+			wait = NULL;
+		}
+		fence = p->real;
+		spin_unlock_irqrestore(&p->wq.lock, flags);
+	}
+
+	if (wait) {
+		INIT_LIST_HEAD(&wait->entry);
+		wait->func(wait, TASK_NORMAL, 0, fence);
+	}
+}
+EXPORT_SYMBOL(dma_fence_add_proxy_listener);
+
+bool dma_fence_remove_proxy_listener(struct dma_fence *fence,
+				     struct wait_queue_entry *wait)
+{
+	bool ret = false;
+
+	if (dma_fence_is_proxy(fence)) {
+		struct dma_fence_proxy *p =
+			container_of(fence, typeof(*p), base);
+		unsigned long flags;
+
+		spin_lock_irqsave(&p->wq.lock, flags);
+		if (!list_empty(&wait->entry)) {
+			list_del_init(&wait->entry);
+			ret = true;
+		}
+		spin_unlock_irqrestore(&p->wq.lock, flags);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(dma_fence_remove_proxy_listener);
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 90edf2b281b0..5a9ff241e39e 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -19,6 +19,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/dma_fence.h>
 
+#include "dma-fence-private.h"
+
 EXPORT_TRACEPOINT_SYMBOL(dma_fence_emit);
 EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal);
 EXPORT_TRACEPOINT_SYMBOL(dma_fence_signaled);
@@ -273,7 +275,7 @@ void dma_fence_free(struct dma_fence *fence)
 }
 EXPORT_SYMBOL(dma_fence_free);
 
-static bool __dma_fence_enable_signaling(struct dma_fence *fence)
+bool __dma_fence_enable_signaling(struct dma_fence *fence)
 {
 	bool was_set;
 
diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h
index 55918ef9adab..616eca70e2d8 100644
--- a/drivers/dma-buf/selftests.h
+++ b/drivers/dma-buf/selftests.h
@@ -12,3 +12,4 @@
 selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */
 selftest(dma_fence, dma_fence)
 selftest(dma_fence_chain, dma_fence_chain)
+selftest(dma_fence_proxy, dma_fence_proxy)
diff --git a/drivers/dma-buf/st-dma-fence-proxy.c b/drivers/dma-buf/st-dma-fence-proxy.c
new file mode 100644
index 000000000000..c95811199c16
--- /dev/null
+++ b/drivers/dma-buf/st-dma-fence-proxy.c
@@ -0,0 +1,699 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/delay.h>
+#include <linux/dma-fence.h>
+#include <linux/dma-fence-proxy.h>
+#include <linux/kernel.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "selftest.h"
+
+static struct kmem_cache *slab_fences;
+
+static struct mock_fence {
+	struct dma_fence base;
+	spinlock_t lock;
+} *to_mock_fence(struct dma_fence *f) {
+	return container_of(f, struct mock_fence, base);
+}
+
+static const char *mock_name(struct dma_fence *f)
+{
+	return "mock";
+}
+
+static void mock_fence_release(struct dma_fence *f)
+{
+	kmem_cache_free(slab_fences, to_mock_fence(f));
+}
+
+static const struct dma_fence_ops mock_ops = {
+	.get_driver_name = mock_name,
+	.get_timeline_name = mock_name,
+	.release = mock_fence_release,
+};
+
+static struct dma_fence *mock_fence(void)
+{
+	struct mock_fence *f;
+
+	f = kmem_cache_alloc(slab_fences, GFP_KERNEL);
+	if (!f)
+		return NULL;
+
+	spin_lock_init(&f->lock);
+	dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0);
+
+	return &f->base;
+}
+
+static int sanitycheck(void *arg)
+{
+	struct dma_fence *f;
+
+	f = dma_fence_create_proxy();
+	if (!f)
+		return -ENOMEM;
+
+	dma_fence_signal(f);
+	dma_fence_put(f);
+
+	return 0;
+}
+
+struct fences {
+	struct dma_fence *real;
+	struct dma_fence *proxy;
+	struct dma_fence __rcu *slot;
+};
+
+static int create_fences(struct fences *f, bool attach)
+{
+	f->proxy = dma_fence_create_proxy();
+	if (!f->proxy)
+		return -ENOMEM;
+
+	RCU_INIT_POINTER(f->slot, f->proxy);
+
+	f->real = mock_fence();
+	if (!f->real) {
+		dma_fence_put(f->proxy);
+		return -ENOMEM;
+	}
+
+	if (attach)
+		dma_fence_replace_proxy(&f->slot, f->real);
+
+	return 0;
+}
+
+static void free_fences(struct fences *f)
+{
+	dma_fence_put(dma_fence_replace_proxy(&f->slot, NULL));
+	dma_fence_put(f->real);
+	dma_fence_put(f->proxy);
+}
+
+static int wrap_signaling(void *arg)
+{
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	if (dma_fence_is_signaled(f.proxy)) {
+		pr_err("Fence unexpectedly signaled on creation\n");
+		goto err_free;
+	}
+
+	if (dma_fence_signal(f.real)) {
+		pr_err("Fence reported being already signaled\n");
+		goto err_free;
+	}
+
+	if (!dma_fence_is_signaled(f.proxy)) {
+		pr_err("Fence not reporting signaled\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_signaling_recurse(void *arg)
+{
+	struct fences f;
+	struct dma_fence *chain;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	chain = dma_fence_create_proxy();
+	if (!chain) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	dma_fence_replace_proxy(&f.slot, chain);
+	dma_fence_put(dma_fence_replace_proxy(&f.slot, f.real));
+	dma_fence_put(chain);
+
+	/* f.real <- chain <- f.proxy */
+
+	if (dma_fence_is_signaled(f.proxy)) {
+		pr_err("Fence unexpectedly signaled on creation\n");
+		goto err_free;
+	}
+
+	if (dma_fence_signal(f.real)) {
+		pr_err("Fence reported being already signaled\n");
+		goto err_free;
+	}
+
+	if (!dma_fence_is_signaled(f.proxy)) {
+		pr_err("Fence not reporting signaled\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+struct simple_cb {
+	struct dma_fence_cb cb;
+	bool seen;
+};
+
+static void simple_callback(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	smp_store_mb(container_of(cb, struct simple_cb, cb)->seen, true);
+}
+
+static int wrap_add_callback(void *arg)
+{
+	struct simple_cb cb = {};
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	if (dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Failed to add callback, fence already signaled!\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+	if (!cb.seen) {
+		pr_err("Callback failed!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_add_callback_recurse(void *arg)
+{
+	struct simple_cb cb = {};
+	struct dma_fence *chain;
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	chain = dma_fence_create_proxy();
+	if (!chain) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	dma_fence_replace_proxy(&f.slot, chain);
+	dma_fence_put(dma_fence_replace_proxy(&f.slot, f.real));
+	dma_fence_put(chain);
+
+	/* f.real <- chain <- f.proxy */
+
+	if (dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Failed to add callback, fence already signaled!\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+	if (!cb.seen) {
+		pr_err("Callback failed!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_late_add_callback(void *arg)
+{
+	struct simple_cb cb = {};
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	dma_fence_signal(f.real);
+
+	if (!dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Added callback, but fence was already signaled!\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+	if (cb.seen) {
+		pr_err("Callback called after failed attachment!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_early_add_callback(void *arg)
+{
+	struct simple_cb cb = {};
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	if (dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Failed to add callback, fence already signaled!\n");
+		goto err_free;
+	}
+
+	dma_fence_replace_proxy(&f.slot, f.real);
+	dma_fence_signal(f.real);
+	if (!cb.seen) {
+		pr_err("Callback failed!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_early_add_callback_late(void *arg)
+{
+	struct simple_cb cb = {};
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	dma_fence_signal(f.real);
+
+	if (dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Failed to add callback, fence already signaled!\n");
+		goto err_free;
+	}
+
+	dma_fence_replace_proxy(&f.slot, f.real);
+	dma_fence_signal(f.real);
+	if (!cb.seen) {
+		pr_err("Callback failed!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_early_add_callback_early(void *arg)
+{
+	struct simple_cb cb = {};
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	if (dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Failed to add callback, fence already signaled!\n");
+		goto err_free;
+	}
+
+	dma_fence_replace_proxy(&f.slot, f.real);
+	dma_fence_signal(f.real);
+	if (!cb.seen) {
+		pr_err("Callback failed!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_rm_callback(void *arg)
+{
+	struct simple_cb cb = {};
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	if (dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Failed to add callback, fence already signaled!\n");
+		goto err_free;
+	}
+
+	if (!dma_fence_remove_callback(f.proxy, &cb.cb)) {
+		pr_err("Failed to remove callback!\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+	if (cb.seen) {
+		pr_err("Callback still signaled after removal!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_late_rm_callback(void *arg)
+{
+	struct simple_cb cb = {};
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	if (dma_fence_add_callback(f.proxy, &cb.cb, simple_callback)) {
+		pr_err("Failed to add callback, fence already signaled!\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+	if (!cb.seen) {
+		pr_err("Callback failed!\n");
+		goto err_free;
+	}
+
+	if (dma_fence_remove_callback(f.proxy, &cb.cb)) {
+		pr_err("Callback removal succeed after being executed!\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_status(void *arg)
+{
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	if (dma_fence_get_status(f.proxy)) {
+		pr_err("Fence unexpectedly has signaled status on creation\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+	if (!dma_fence_get_status(f.proxy)) {
+		pr_err("Fence not reporting signaled status\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_error(void *arg)
+{
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	dma_fence_set_error(f.real, -EIO);
+
+	if (dma_fence_get_status(f.proxy)) {
+		pr_err("Fence unexpectedly has error status before signal\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+	if (dma_fence_get_status(f.proxy) != -EIO) {
+		pr_err("Fence not reporting error status, got %d\n",
+		       dma_fence_get_status(f.proxy));
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_wait(void *arg)
+{
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, true))
+		return -ENOMEM;
+
+	if (dma_fence_wait_timeout(f.proxy, false, 0) != 0) {
+		pr_err("Wait reported complete before being signaled\n");
+		goto err_free;
+	}
+
+	dma_fence_signal(f.real);
+
+	if (dma_fence_wait_timeout(f.proxy, false, 0) == 0) {
+		pr_err("Wait reported incomplete after being signaled\n");
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	dma_fence_signal(f.real);
+	free_fences(&f);
+	return err;
+}
+
+struct wait_timer {
+	struct timer_list timer;
+	struct fences f;
+};
+
+static void wait_timer(struct timer_list *timer)
+{
+	struct wait_timer *wt = from_timer(wt, timer, timer);
+
+	dma_fence_signal(wt->f.real);
+}
+
+static int wrap_wait_timeout(void *arg)
+{
+	struct wait_timer wt;
+	int err = -EINVAL;
+
+	if (create_fences(&wt.f, true))
+		return -ENOMEM;
+
+	timer_setup_on_stack(&wt.timer, wait_timer, 0);
+
+	if (dma_fence_wait_timeout(wt.f.proxy, false, 1) != 0) {
+		pr_err("Wait reported complete before being signaled\n");
+		goto err_free;
+	}
+
+	mod_timer(&wt.timer, jiffies + 1);
+
+	if (dma_fence_wait_timeout(wt.f.proxy, false, 2) != 0) {
+		if (timer_pending(&wt.timer)) {
+			pr_notice("Timer did not fire within the jiffie!\n");
+			err = 0; /* not our fault! */
+		} else {
+			pr_err("Wait reported incomplete after timeout\n");
+		}
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	del_timer_sync(&wt.timer);
+	destroy_timer_on_stack(&wt.timer);
+	dma_fence_signal(wt.f.real);
+	free_fences(&wt.f);
+	return err;
+}
+
+struct proxy_wait {
+	struct wait_queue_entry base;
+	struct dma_fence *fence;
+	bool seen;
+};
+
+static int proxy_wait_cb(struct wait_queue_entry *entry,
+			 unsigned int mode, int flags, void *key)
+{
+	struct proxy_wait *p = container_of(entry, typeof(*p), base);
+
+	p->fence = key;
+	p->seen = true;
+
+	return 0;
+}
+
+static int wrap_listen_early(void *arg)
+{
+	struct proxy_wait wait = { .base.func = proxy_wait_cb };
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	dma_fence_replace_proxy(&f.slot, f.real);
+	dma_fence_add_proxy_listener(f.proxy, &wait.base);
+
+	if (!wait.seen) {
+		pr_err("Proxy listener was not called after replace!\n");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	if (wait.fence != f.real) {
+		pr_err("Proxy listener was not passed the real fence!\n");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	dma_fence_signal(f.real);
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_listen_late(void *arg)
+{
+	struct proxy_wait wait = { .base.func = proxy_wait_cb };
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	dma_fence_add_proxy_listener(f.proxy, &wait.base);
+	dma_fence_replace_proxy(&f.slot, f.real);
+
+	if (!wait.seen) {
+		pr_err("Proxy listener was not called on replace!\n");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	if (wait.fence != f.real) {
+		pr_err("Proxy listener was not passed the real fence!\n");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	dma_fence_signal(f.real);
+	free_fences(&f);
+	return err;
+}
+
+static int wrap_listen_cancel(void *arg)
+{
+	struct proxy_wait wait = { .base.func = proxy_wait_cb };
+	struct fences f;
+	int err = -EINVAL;
+
+	if (create_fences(&f, false))
+		return -ENOMEM;
+
+	dma_fence_add_proxy_listener(f.proxy, &wait.base);
+	if (!dma_fence_remove_proxy_listener(f.proxy, &wait.base)) {
+		pr_err("Cancelling listener, already detached?\n");
+		err = -EINVAL;
+		goto err_free;
+	}
+	dma_fence_replace_proxy(&f.slot, f.real);
+
+	if (wait.seen) {
+		pr_err("Proxy listener was called after being removed!\n");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	if (dma_fence_remove_proxy_listener(f.proxy, &wait.base)) {
+		pr_err("Double listener cancellation!\n");
+		err = -EINVAL;
+		goto err_free;
+	}
+
+	err = 0;
+err_free:
+	dma_fence_signal(f.real);
+	free_fences(&f);
+	return err;
+}
+
+int dma_fence_proxy(void)
+{
+	static const struct subtest tests[] = {
+		SUBTEST(sanitycheck),
+		SUBTEST(wrap_signaling),
+		SUBTEST(wrap_signaling_recurse),
+		SUBTEST(wrap_add_callback),
+		SUBTEST(wrap_add_callback_recurse),
+		SUBTEST(wrap_late_add_callback),
+		SUBTEST(wrap_early_add_callback),
+		SUBTEST(wrap_early_add_callback_late),
+		SUBTEST(wrap_early_add_callback_early),
+		SUBTEST(wrap_rm_callback),
+		SUBTEST(wrap_late_rm_callback),
+		SUBTEST(wrap_status),
+		SUBTEST(wrap_error),
+		SUBTEST(wrap_wait),
+		SUBTEST(wrap_wait_timeout),
+		SUBTEST(wrap_listen_early),
+		SUBTEST(wrap_listen_late),
+		SUBTEST(wrap_listen_cancel),
+	};
+	int ret;
+
+	slab_fences = KMEM_CACHE(mock_fence,
+				 SLAB_TYPESAFE_BY_RCU |
+				 SLAB_HWCACHE_ALIGN);
+	if (!slab_fences)
+		return -ENOMEM;
+
+	ret = subtests(tests, NULL);
+
+	kmem_cache_destroy(slab_fences);
+
+	return ret;
+}
diff --git a/include/linux/dma-fence-proxy.h b/include/linux/dma-fence-proxy.h
new file mode 100644
index 000000000000..063cde6b42c4
--- /dev/null
+++ b/include/linux/dma-fence-proxy.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * dma-fence-proxy: allows waiting upon unset and future fences
+ *
+ * Copyright (C) 2017 Intel Corporation
+ */
+
+#ifndef __LINUX_DMA_FENCE_PROXY_H
+#define __LINUX_DMA_FENCE_PROXY_H
+
+#include <linux/kernel.h>
+#include <linux/dma-fence.h>
+
+struct wait_queue_entry;
+
+extern const struct dma_fence_ops dma_fence_proxy_ops;
+
+struct dma_fence *dma_fence_create_proxy(void);
+
+static inline bool dma_fence_is_proxy(struct dma_fence *fence)
+{
+	return fence->ops == &dma_fence_proxy_ops;
+}
+
+struct dma_fence *
+dma_fence_replace_proxy(struct dma_fence __rcu **slot,
+			struct dma_fence *fence);
+
+void dma_fence_add_proxy_listener(struct dma_fence *fence,
+				  struct wait_queue_entry *wait);
+bool dma_fence_remove_proxy_listener(struct dma_fence *fence,
+				     struct wait_queue_entry *wait);
+
+#endif /* __LINUX_DMA_FENCE_PROXY_H */
-- 
2.20.1

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

[Intel-gfx] [PATCH 4/7] drm/syncobj: Allow use of dma-fence-proxy

[Chris Wilson]

Allow the callers to supply a dma-fence-proxy for asynchronous waiting on
future fences.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/drm_syncobj.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 42d46414f767..e141db0e1eb6 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -184,6 +184,7 @@
  */
 
 #include <linux/anon_inodes.h>
+#include <linux/dma-fence-proxy.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/sched/signal.h>
@@ -324,14 +325,9 @@ void drm_syncobj_replace_fence(struct drm_syncobj *syncobj,
 	struct dma_fence *old_fence;
 	struct syncobj_wait_entry *cur, *tmp;
 
-	if (fence)
-		dma_fence_get(fence);
-
 	spin_lock(&syncobj->lock);
 
-	old_fence = rcu_dereference_protected(syncobj->fence,
-					      lockdep_is_held(&syncobj->lock));
-	rcu_assign_pointer(syncobj->fence, fence);
+	old_fence = dma_fence_replace_proxy(&syncobj->fence, fence);
 
 	if (fence != old_fence) {
 		list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node)
-- 
2.20.1

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

[Intel-gfx] [PATCH 5/7] drm/i915/gem: Teach execbuf how to wait on future syncobj

[Chris Wilson]

If a syncobj has not yet been assigned, treat it as a future fence and
install and wait upon a dma-fence-proxy. The proxy will be replace by
the real fence later, and that fence will be responsible for signaling
our waiter.

Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4854
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    |  21 ++-
 drivers/gpu/drm/i915/i915_request.c           | 153 ++++++++++++++++++
 drivers/gpu/drm/i915/i915_scheduler.c         |  41 +++++
 drivers/gpu/drm/i915/i915_scheduler.h         |   3 +
 4 files changed, 216 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 824a2b76947a..5a9578514423 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/intel-iommu.h>
+#include <linux/dma-fence-proxy.h>
 #include <linux/dma-resv.h>
 #include <linux/sync_file.h>
 #include <linux/uaccess.h>
@@ -2524,8 +2525,24 @@ await_fence_array(struct i915_execbuffer *eb,
 			continue;
 
 		fence = drm_syncobj_fence_get(syncobj);
-		if (!fence)
-			return -EINVAL;
+		if (!fence) {
+			struct dma_fence *old;
+
+			fence = dma_fence_create_proxy();
+			if (!fence)
+				return -ENOMEM;
+
+			spin_lock(&syncobj->lock);
+			old = rcu_dereference_protected(syncobj->fence, true);
+			if (unlikely(old)) {
+				dma_fence_put(fence);
+				fence = dma_fence_get(old);
+			} else {
+				rcu_assign_pointer(syncobj->fence,
+						   dma_fence_get(fence));
+			}
+			spin_unlock(&syncobj->lock);
+		}
 
 		err = i915_request_await_dma_fence(eb->request, fence);
 		dma_fence_put(fence);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 00b7c4eb3f32..945494b06bce 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -24,6 +24,7 @@
 
 #include <linux/dma-fence-array.h>
 #include <linux/dma-fence-chain.h>
+#include <linux/dma-fence-proxy.h>
 #include <linux/irq_work.h>
 #include <linux/prefetch.h>
 #include <linux/sched.h>
@@ -379,6 +380,7 @@ static bool fatal_error(int error)
 	case 0: /* not an error! */
 	case -EAGAIN: /* innocent victim of a GT reset (__i915_request_reset) */
 	case -ETIMEDOUT: /* waiting for Godot (timer_i915_sw_fence_wake) */
+	case -EDEADLK: /* cyclic fence lockup (await_proxy)  */
 		return false;
 	default:
 		return true;
@@ -1133,6 +1135,155 @@ i915_request_await_external(struct i915_request *rq, struct dma_fence *fence)
 	return err;
 }
 
+struct await_proxy {
+	struct wait_queue_entry base;
+	struct i915_request *request;
+	struct dma_fence *fence;
+	struct timer_list timer;
+	struct work_struct work;
+	int (*attach)(struct await_proxy *ap);
+	void *data;
+};
+
+static void await_proxy_work(struct work_struct *work)
+{
+	struct await_proxy *ap = container_of(work, typeof(*ap), work);
+	struct i915_request *rq = ap->request;
+
+	del_timer_sync(&ap->timer);
+
+	if (ap->fence) {
+		int err = 0;
+
+		/*
+		 * If the fence is external, we impose a 10s timeout.
+		 * However, if the fence is internal, we skip a timeout in
+		 * the belief that all fences are in-order (DAG, no cycles)
+		 * and we can enforce forward progress by reset the GPU if
+		 * necessary. A future fence, provided userspace, can trivially
+		 * generate a cycle in the dependency graph, and so cause
+		 * that entire cycle to become deadlocked and for no forward
+		 * progress to either be made, and the driver being kept
+		 * eternally awake.
+		 */
+		if (dma_fence_is_i915(ap->fence) &&
+		    !i915_sched_node_verify_dag(&rq->sched,
+						&to_request(ap->fence)->sched))
+			err = -EDEADLK;
+
+		if (!err) {
+			mutex_lock(&rq->context->timeline->mutex);
+			err = ap->attach(ap);
+			mutex_unlock(&rq->context->timeline->mutex);
+		}
+
+		/* Don't flag an error for co-dependent scheduling */
+		if (err == -EDEADLK) {
+			struct i915_sched_node *waiter =
+				&to_request(ap->fence)->sched;
+			struct i915_dependency *p;
+
+			list_for_each_entry_lockless(p,
+						     &rq->sched.waiters_list,
+						     wait_link) {
+				if (p->waiter == waiter &&
+				    p->flags & I915_DEPENDENCY_WEAK) {
+					err = 0;
+					break;
+				}
+			}
+		}
+
+		if (err < 0)
+			i915_sw_fence_set_error_once(&rq->submit, err);
+	}
+
+	i915_sw_fence_complete(&rq->submit);
+
+	dma_fence_put(ap->fence);
+	kfree(ap);
+}
+
+static int
+await_proxy_wake(struct wait_queue_entry *entry,
+		 unsigned int mode,
+		 int flags,
+		 void *fence)
+{
+	struct await_proxy *ap = container_of(entry, typeof(*ap), base);
+
+	ap->fence = dma_fence_get(fence);
+	schedule_work(&ap->work);
+
+	return 0;
+}
+
+static void
+await_proxy_timer(struct timer_list *t)
+{
+	struct await_proxy *ap = container_of(t, typeof(*ap), timer);
+
+	if (dma_fence_remove_proxy_listener(ap->base.private, &ap->base)) {
+		struct i915_request *rq = ap->request;
+
+		pr_notice("Asynchronous wait on unset proxy fence by %s:%s:%llx timed out\n",
+			  rq->fence.ops->get_driver_name(&rq->fence),
+			  rq->fence.ops->get_timeline_name(&rq->fence),
+			  rq->fence.seqno);
+		i915_sw_fence_set_error_once(&rq->submit, -ETIMEDOUT);
+
+		schedule_work(&ap->work);
+	}
+}
+
+static int
+__i915_request_await_proxy(struct i915_request *rq,
+			   struct dma_fence *fence,
+			   unsigned long timeout,
+			   int (*attach)(struct await_proxy *ap),
+			   void *data)
+{
+	struct await_proxy *ap;
+
+	ap = kzalloc(sizeof(*ap), I915_FENCE_GFP);
+	if (!ap)
+		return -ENOMEM;
+
+	i915_sw_fence_await(&rq->submit);
+	mark_external(rq);
+
+	ap->base.private = fence;
+	ap->base.func = await_proxy_wake;
+	ap->request = rq;
+	INIT_WORK(&ap->work, await_proxy_work);
+	ap->attach = attach;
+	ap->data = data;
+
+	timer_setup(&ap->timer, await_proxy_timer, 0);
+	if (timeout)
+		mod_timer(&ap->timer, round_jiffies_up(jiffies + timeout));
+
+	dma_fence_add_proxy_listener(fence, &ap->base);
+	return 0;
+}
+
+static int await_proxy(struct await_proxy *ap)
+{
+	return i915_request_await_dma_fence(ap->request, ap->fence);
+}
+
+static int
+i915_request_await_proxy(struct i915_request *rq, struct dma_fence *fence)
+{
+	/*
+	 * Wait until we know the real fence so that can optimise the
+	 * inter-fence synchronisation.
+	 */
+	return __i915_request_await_proxy(rq, fence,
+					  i915_fence_timeout(rq->i915),
+					  await_proxy, NULL);
+}
+
 int
 i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 {
@@ -1179,6 +1330,8 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 		if (dma_fence_is_i915(fence))
 			ret = i915_request_await_request(rq, to_request(fence));
+		else if (dma_fence_is_proxy(fence))
+			ret = i915_request_await_proxy(rq, fence);
 		else
 			ret = i915_request_await_external(rq, fence);
 		if (ret < 0)
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index bec2a9c25425..f8e797a7eee9 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -472,6 +472,47 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 	return 0;
 }
 
+bool i915_sched_node_verify_dag(struct i915_sched_node *waiter,
+				struct i915_sched_node *signaler)
+{
+	struct i915_dependency *dep, *p;
+	struct i915_dependency stack;
+	bool result = false;
+	LIST_HEAD(dfs);
+
+	if (list_empty(&waiter->waiters_list))
+		return true;
+
+	spin_lock_irq(&schedule_lock);
+
+	stack.signaler = signaler;
+	list_add(&stack.dfs_link, &dfs);
+
+	list_for_each_entry(dep, &dfs, dfs_link) {
+		struct i915_sched_node *node = dep->signaler;
+
+		if (node_signaled(node))
+			continue;
+
+		list_for_each_entry(p, &node->signalers_list, signal_link) {
+			if (p->signaler == waiter)
+				goto out;
+
+			if (list_empty(&p->dfs_link))
+				list_add_tail(&p->dfs_link, &dfs);
+		}
+	}
+
+	result = true;
+out:
+	list_for_each_entry_safe(dep, p, &dfs, dfs_link)
+		INIT_LIST_HEAD(&dep->dfs_link);
+
+	spin_unlock_irq(&schedule_lock);
+
+	return result;
+}
+
 void i915_sched_node_fini(struct i915_sched_node *node)
 {
 	struct i915_dependency *dep, *tmp;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 6f0bf00fc569..13432add8929 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -28,6 +28,9 @@
 void i915_sched_node_init(struct i915_sched_node *node);
 void i915_sched_node_reinit(struct i915_sched_node *node);
 
+bool i915_sched_node_verify_dag(struct i915_sched_node *waiter,
+				struct i915_sched_node *signal);
+
 bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 				      struct i915_sched_node *signal,
 				      struct i915_dependency *dep,
-- 
2.20.1

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

[Intel-gfx] [PATCH 6/7] drm/i915/gem: Allow combining submit-fences with syncobj

[Chris Wilson]

We allow exported sync_file fences to be used as submit fences, but they
are not the only source of user fences. We also accept an array of
syncobj, and as with sync_file these are dma_fences underneath and so
feature the same set of controls. The submit-fence allows for a request
to be scheduled at the same time as the signaler, rather than as normal
after. Userspace can combine submit-fence with its own semaphores for
intra-batch scheduling.

Not exposing submit-fences to syncobj was at the time just a matter of
pragmatic expediency.

Fixes: a88b6e4cbafd ("drm/i915: Allow specification of parallel execbuf")
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4854
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 14 +++++++----
 drivers/gpu/drm/i915/i915_request.c           | 25 +++++++++++++++++++
 include/uapi/drm/i915_drm.h                   |  7 +++---
 3 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 5a9578514423..2067557e277b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2432,7 +2432,7 @@ static void
 __free_fence_array(struct drm_syncobj **fences, unsigned int n)
 {
 	while (n--)
-		drm_syncobj_put(ptr_mask_bits(fences[n], 2));
+		drm_syncobj_put(ptr_mask_bits(fences[n], 3));
 	kvfree(fences);
 }
 
@@ -2489,7 +2489,7 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args,
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
+		fences[n] = ptr_pack_bits(syncobj, fence.flags, 3);
 	}
 
 	return fences;
@@ -2520,7 +2520,7 @@ await_fence_array(struct i915_execbuffer *eb,
 		struct dma_fence *fence;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(fences[n], &flags, 3);
 		if (!(flags & I915_EXEC_FENCE_WAIT))
 			continue;
 
@@ -2544,7 +2544,11 @@ await_fence_array(struct i915_execbuffer *eb,
 			spin_unlock(&syncobj->lock);
 		}
 
-		err = i915_request_await_dma_fence(eb->request, fence);
+		if (flags & I915_EXEC_FENCE_WAIT_SUBMIT)
+			err = i915_request_await_execution(eb->request, fence,
+							   eb->engine->bond_execute);
+		else
+			err = i915_request_await_dma_fence(eb->request, fence);
 		dma_fence_put(fence);
 		if (err < 0)
 			return err;
@@ -2565,7 +2569,7 @@ signal_fence_array(struct i915_execbuffer *eb,
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(fences[n], &flags, 3);
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 945494b06bce..9ad1e6761492 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1433,6 +1433,27 @@ __i915_request_await_execution(struct i915_request *to,
 					     &from->fence);
 }
 
+static int execution_proxy(struct await_proxy *ap)
+{
+	return i915_request_await_execution(ap->request, ap->fence, ap->data);
+}
+
+static int
+i915_request_await_proxy_execution(struct i915_request *rq,
+				   struct dma_fence *fence,
+				   void (*hook)(struct i915_request *rq,
+						struct dma_fence *signal))
+{
+	/*
+	 * We have to wait until the real request is known in order to
+	 * be able to hook into its execution, as opposed to waiting for
+	 * its completion.
+	 */
+	return __i915_request_await_proxy(rq, fence,
+					  i915_fence_timeout(rq->i915),
+					  execution_proxy, hook);
+}
+
 int
 i915_request_await_execution(struct i915_request *rq,
 			     struct dma_fence *fence,
@@ -1472,6 +1493,10 @@ i915_request_await_execution(struct i915_request *rq,
 			ret = __i915_request_await_execution(rq,
 							     to_request(fence),
 							     hook);
+		else if (dma_fence_is_proxy(fence))
+			ret = i915_request_await_proxy_execution(rq,
+								 fence,
+								 hook);
 		else
 			ret = i915_request_await_external(rq, fence);
 		if (ret < 0)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 14b67cd6b54b..704dd0e3bc1d 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1040,9 +1040,10 @@ struct drm_i915_gem_exec_fence {
 	 */
 	__u32 handle;
 
-#define I915_EXEC_FENCE_WAIT            (1<<0)
-#define I915_EXEC_FENCE_SIGNAL          (1<<1)
-#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
+#define I915_EXEC_FENCE_WAIT            (1u << 0)
+#define I915_EXEC_FENCE_SIGNAL          (1u << 1)
+#define I915_EXEC_FENCE_WAIT_SUBMIT     (1u << 2)
+#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_WAIT_SUBMIT << 1))
 	__u32 flags;
 };
 
-- 
2.20.1

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

[Intel-gfx] [PATCH 7/7] drm/i915/gt: Declare when we enabled timeslicing

[Chris Wilson]

Let userspace know if they can trust timeslicing by including it as part
of the I915_PARAM_HAS_SCHEDULER::I915_SCHEDULER_CAP_TIMESLICING

v2: Only declare timeslicing if we can safely preempt userspace.

Fixes: 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing")
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3802
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4854
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine_user.c | 1 +
 include/uapi/drm/i915_drm.h                 | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 848decee9066..8415511f1465 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -98,6 +98,7 @@ static void set_scheduler_caps(struct drm_i915_private *i915)
 		MAP(HAS_PREEMPTION, PREEMPTION),
 		MAP(HAS_SEMAPHORES, SEMAPHORES),
 		MAP(SUPPORTS_STATS, ENGINE_BUSY_STATS),
+		MAP(HAS_TIMESLICES, TIMESLICING),
 #undef MAP
 	};
 	struct intel_engine_cs *engine;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 704dd0e3bc1d..1ee227b5131a 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -523,6 +523,7 @@ typedef struct drm_i915_irq_wait {
 #define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
 #define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
 #define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
+#define   I915_SCHEDULER_CAP_TIMESLICING	(1ul << 5)
 
 #define I915_PARAM_HUC_STATUS		 42
 
-- 
2.20.1

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

Re: [Intel-gfx] [PATCH 1/7] drm/i915/gem: Remove redundant exec_fence

[Mika Kuoppala]

Chris Wilson <chris@chris-wilson.co.uk> writes:

> Since there can only be one of in_fence/exec_fence, just use the single
> in_fence local.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
>  .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 24 ++++++++-----------
>  1 file changed, 10 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> index d54a4933cc05..824a2b76947a 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> @@ -2622,7 +2622,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  	struct drm_i915_private *i915 = to_i915(dev);
>  	struct i915_execbuffer eb;
>  	struct dma_fence *in_fence = NULL;
> -	struct dma_fence *exec_fence = NULL;
>  	struct sync_file *out_fence = NULL;
>  	struct i915_vma *batch;
>  	int out_fence_fd = -1;
> @@ -2677,8 +2676,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  			goto err_in_fence;
>  		}
>  
> -		exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
> -		if (!exec_fence) {
> +		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
> +		if (!in_fence) {

This looks wrong. Seems you can return straight from here.
-Mika


>  			err = -EINVAL;
>  			goto err_in_fence;
>  		}
> @@ -2688,7 +2687,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
>  		if (out_fence_fd < 0) {
>  			err = out_fence_fd;
> -			goto err_exec_fence;
> +			goto err_in_fence;
>  		}
>  	}
>  
> @@ -2779,14 +2778,13 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  	}
>  
>  	if (in_fence) {
> -		err = i915_request_await_dma_fence(eb.request, in_fence);
> -		if (err < 0)
> -			goto err_request;
> -	}
> -
> -	if (exec_fence) {
> -		err = i915_request_await_execution(eb.request, exec_fence,
> -						   eb.engine->bond_execute);
> +		if (args->flags & I915_EXEC_FENCE_SUBMIT)
> +			err = i915_request_await_execution(eb.request,
> +							   in_fence,
> +							   eb.engine->bond_execute);
> +		else
> +			err = i915_request_await_dma_fence(eb.request,
> +							   in_fence);
>  		if (err < 0)
>  			goto err_request;
>  	}
> @@ -2855,8 +2853,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  err_out_fence:
>  	if (out_fence_fd != -1)
>  		put_unused_fd(out_fence_fd);
> -err_exec_fence:
> -	dma_fence_put(exec_fence);
>  err_in_fence:
>  	dma_fence_put(in_fence);
>  	return err;
> -- 
> 2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] [PATCH v2] drm/i915/gem: Remove redundant exec_fence

[Chris Wilson]

Since there can only be one of in_fence/exec_fence, just use the single
in_fence local.

v2: Considate lookup

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 40 +++++++------------
 1 file changed, 14 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index d54a4933cc05..3c98aaaa8d11 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2622,7 +2622,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
-	struct dma_fence *exec_fence = NULL;
 	struct sync_file *out_fence = NULL;
 	struct i915_vma *batch;
 	int out_fence_fd = -1;
@@ -2665,30 +2664,22 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
-	if (args->flags & I915_EXEC_FENCE_IN) {
+#define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
+	if (args->flags & IN_FENCES) {
+		if ((args->flags & IN_FENCES) == IN_FENCES)
+			return -EINVAL;
+
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
 		if (!in_fence)
 			return -EINVAL;
 	}
-
-	if (args->flags & I915_EXEC_FENCE_SUBMIT) {
-		if (in_fence) {
-			err = -EINVAL;
-			goto err_in_fence;
-		}
-
-		exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!exec_fence) {
-			err = -EINVAL;
-			goto err_in_fence;
-		}
-	}
+#undef IN_FENCES
 
 	if (args->flags & I915_EXEC_FENCE_OUT) {
 		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
 		if (out_fence_fd < 0) {
 			err = out_fence_fd;
-			goto err_exec_fence;
+			goto err_in_fence;
 		}
 	}
 
@@ -2779,14 +2770,13 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	}
 
 	if (in_fence) {
-		err = i915_request_await_dma_fence(eb.request, in_fence);
-		if (err < 0)
-			goto err_request;
-	}
-
-	if (exec_fence) {
-		err = i915_request_await_execution(eb.request, exec_fence,
-						   eb.engine->bond_execute);
+		if (args->flags & I915_EXEC_FENCE_SUBMIT)
+			err = i915_request_await_execution(eb.request,
+							   in_fence,
+							   eb.engine->bond_execute);
+		else
+			err = i915_request_await_dma_fence(eb.request,
+							   in_fence);
 		if (err < 0)
 			goto err_request;
 	}
@@ -2855,8 +2845,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
-err_exec_fence:
-	dma_fence_put(exec_fence);
 err_in_fence:
 	dma_fence_put(in_fence);
 	return err;
-- 
2.20.1

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

[Intel-gfx] [PATCH v2] drm/i915/gem: Remove redundant exec_fence

[Chris Wilson]

Since there can only be one of in_fence/exec_fence, just use the single
in_fence local.

v2: Consolidate lookup

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 40 +++++++------------
 1 file changed, 14 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index d54a4933cc05..3c98aaaa8d11 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2622,7 +2622,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
-	struct dma_fence *exec_fence = NULL;
 	struct sync_file *out_fence = NULL;
 	struct i915_vma *batch;
 	int out_fence_fd = -1;
@@ -2665,30 +2664,22 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
-	if (args->flags & I915_EXEC_FENCE_IN) {
+#define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
+	if (args->flags & IN_FENCES) {
+		if ((args->flags & IN_FENCES) == IN_FENCES)
+			return -EINVAL;
+
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
 		if (!in_fence)
 			return -EINVAL;
 	}
-
-	if (args->flags & I915_EXEC_FENCE_SUBMIT) {
-		if (in_fence) {
-			err = -EINVAL;
-			goto err_in_fence;
-		}
-
-		exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!exec_fence) {
-			err = -EINVAL;
-			goto err_in_fence;
-		}
-	}
+#undef IN_FENCES
 
 	if (args->flags & I915_EXEC_FENCE_OUT) {
 		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
 		if (out_fence_fd < 0) {
 			err = out_fence_fd;
-			goto err_exec_fence;
+			goto err_in_fence;
 		}
 	}
 
@@ -2779,14 +2770,13 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	}
 
 	if (in_fence) {
-		err = i915_request_await_dma_fence(eb.request, in_fence);
-		if (err < 0)
-			goto err_request;
-	}
-
-	if (exec_fence) {
-		err = i915_request_await_execution(eb.request, exec_fence,
-						   eb.engine->bond_execute);
+		if (args->flags & I915_EXEC_FENCE_SUBMIT)
+			err = i915_request_await_execution(eb.request,
+							   in_fence,
+							   eb.engine->bond_execute);
+		else
+			err = i915_request_await_dma_fence(eb.request,
+							   in_fence);
 		if (err < 0)
 			goto err_request;
 	}
@@ -2855,8 +2845,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
-err_exec_fence:
-	dma_fence_put(exec_fence);
 err_in_fence:
 	dma_fence_put(in_fence);
 	return err;
-- 
2.20.1

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

Re: [Intel-gfx] [PATCH v2] drm/i915/gem: Remove redundant exec_fence

[Mika Kuoppala]

Chris Wilson <chris@chris-wilson.co.uk> writes:

> Since there can only be one of in_fence/exec_fence, just use the single
> in_fence local.
>
> v2: Considate lookup
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>

Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

> ---
>  .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 40 +++++++------------
>  1 file changed, 14 insertions(+), 26 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> index d54a4933cc05..3c98aaaa8d11 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
> @@ -2622,7 +2622,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  	struct drm_i915_private *i915 = to_i915(dev);
>  	struct i915_execbuffer eb;
>  	struct dma_fence *in_fence = NULL;
> -	struct dma_fence *exec_fence = NULL;
>  	struct sync_file *out_fence = NULL;
>  	struct i915_vma *batch;
>  	int out_fence_fd = -1;
> @@ -2665,30 +2664,22 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  	if (args->flags & I915_EXEC_IS_PINNED)
>  		eb.batch_flags |= I915_DISPATCH_PINNED;
>  
> -	if (args->flags & I915_EXEC_FENCE_IN) {
> +#define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
> +	if (args->flags & IN_FENCES) {
> +		if ((args->flags & IN_FENCES) == IN_FENCES)
> +			return -EINVAL;
> +
>  		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
>  		if (!in_fence)
>  			return -EINVAL;
>  	}
> -
> -	if (args->flags & I915_EXEC_FENCE_SUBMIT) {
> -		if (in_fence) {
> -			err = -EINVAL;
> -			goto err_in_fence;
> -		}
> -
> -		exec_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
> -		if (!exec_fence) {
> -			err = -EINVAL;
> -			goto err_in_fence;
> -		}
> -	}
> +#undef IN_FENCES
>  
>  	if (args->flags & I915_EXEC_FENCE_OUT) {
>  		out_fence_fd = get_unused_fd_flags(O_CLOEXEC);
>  		if (out_fence_fd < 0) {
>  			err = out_fence_fd;
> -			goto err_exec_fence;
> +			goto err_in_fence;
>  		}
>  	}
>  
> @@ -2779,14 +2770,13 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  	}
>  
>  	if (in_fence) {
> -		err = i915_request_await_dma_fence(eb.request, in_fence);
> -		if (err < 0)
> -			goto err_request;
> -	}
> -
> -	if (exec_fence) {
> -		err = i915_request_await_execution(eb.request, exec_fence,
> -						   eb.engine->bond_execute);
> +		if (args->flags & I915_EXEC_FENCE_SUBMIT)
> +			err = i915_request_await_execution(eb.request,
> +							   in_fence,
> +							   eb.engine->bond_execute);
> +		else
> +			err = i915_request_await_dma_fence(eb.request,
> +							   in_fence);
>  		if (err < 0)
>  			goto err_request;
>  	}
> @@ -2855,8 +2845,6 @@ i915_gem_do_execbuffer(struct drm_device *dev,
>  err_out_fence:
>  	if (out_fence_fd != -1)
>  		put_unused_fd(out_fence_fd);
> -err_exec_fence:
> -	dma_fence_put(exec_fence);
>  err_in_fence:
>  	dma_fence_put(in_fence);
>  	return err;
> -- 
> 2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [Intel-gfx] [PATCH 2/7] drm/i915: Mark the addition of the initial-breadcrumb in the request

[Mika Kuoppala]

Chris Wilson <chris@chris-wilson.co.uk> writes:

> The initial-breadcrumb is used to mark the end of the awaiting and the
> beginning of the user payload. We verify that we do not start the user
> payload before all signaler are completed, checking our semaphore setup
> by looking for the initial breadcrumb being written too early. We also
> want to ensure that we do not add semaphore waits after we have already
> closed the semaphore section, an issue for later deferred waits.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/gt/intel_lrc.c |  5 ++++-
>  drivers/gpu/drm/i915/i915_request.c |  7 ++++++-
>  drivers/gpu/drm/i915/i915_request.h | 27 ++++++++++++++++++++-------
>  3 files changed, 30 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
> index 32feb2a27dfc..51470e96cdd4 100644
> --- a/drivers/gpu/drm/i915/gt/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
> @@ -1886,7 +1886,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
>  				continue;
>  
>  			/* No waiter should start before its signaler */
> -			GEM_BUG_ON(w->context->timeline->has_initial_breadcrumb &&
> +			GEM_BUG_ON(i915_request_has_initial_breadcrumb(w) &&
>  				   i915_request_started(w) &&
>  				   !i915_request_completed(rq));
>  
> @@ -3493,6 +3493,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
>  {
>  	u32 *cs;
>  
> +	GEM_BUG_ON(i915_request_has_initial_breadcrumb(rq));
>  	if (!i915_request_timeline(rq)->has_initial_breadcrumb)
>  		return 0;
>  
> @@ -3519,6 +3520,8 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
>  	/* Record the updated position of the request's payload */
>  	rq->infix = intel_ring_offset(rq, cs);
>  
> +	__set_bit(I915_FENCE_FLAG_INITIAL_BREADCRUMB, &rq->fence.flags);
> +
>  	return 0;
>  }
>  
> diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
> index 2d5b98549ddc..00b7c4eb3f32 100644
> --- a/drivers/gpu/drm/i915/i915_request.c
> +++ b/drivers/gpu/drm/i915/i915_request.c
> @@ -951,6 +951,7 @@ __emit_semaphore_wait(struct i915_request *to,
>  	u32 *cs;
>  
>  	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
> +	GEM_BUG_ON(i915_request_has_initial_breadcrumb(to));
>  
>  	/* We need to pin the signaler's HWSP until we are finished reading. */
>  	err = intel_timeline_read_hwsp(from, to, &hwsp_offset);
> @@ -1000,6 +1001,9 @@ emit_semaphore_wait(struct i915_request *to,
>  	if (!intel_context_use_semaphores(to->context))
>  		goto await_fence;
>  
> +	if (i915_request_has_initial_breadcrumb(to))
> +		goto await_fence;
> +
>  	if (!rcu_access_pointer(from->hwsp_cacheline))
>  		goto await_fence;
>  
> @@ -1256,7 +1260,8 @@ __i915_request_await_execution(struct i915_request *to,
>  	 * immediate execution, and so we must wait until it reaches the
>  	 * active slot.
>  	 */
> -	if (intel_engine_has_semaphores(to->engine)) {
> +	if (intel_engine_has_semaphores(to->engine) &&
> +	    !i915_request_has_initial_breadcrumb(to)) {
>  		err = __emit_semaphore_wait(to, from, from->fence.seqno - 1);
>  		if (err < 0)
>  			return err;
> diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
> index d8ce908e1346..98ae2dc82371 100644
> --- a/drivers/gpu/drm/i915/i915_request.h
> +++ b/drivers/gpu/drm/i915/i915_request.h
> @@ -84,19 +84,26 @@ enum {
>  	I915_FENCE_FLAG_PQUEUE,
>  
>  	/*
> -	 * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list
> +	 * I915_FENCE_FLAG_HOLD - this request is currently on hold
>  	 *
> -	 * Internal bookkeeping used by the breadcrumb code to track when
> -	 * a request is on the various signal_list.
> +	 * This request has been suspended, pending an ongoing investigation.
>  	 */
> -	I915_FENCE_FLAG_SIGNAL,
> +	I915_FENCE_FLAG_HOLD,
>  
>  	/*
> -	 * I915_FENCE_FLAG_HOLD - this request is currently on hold
> +	 * I915_FENCE_FLAG_INITIAL_BREADCRUMB - this request has the initial
> +	 * breadcrumb that marks the end of semaphore waits and start of the
> +	 * user payload.
> +	 */
> +	I915_FENCE_FLAG_INITIAL_BREADCRUMB,
> +
> +	/*
> +	 * I915_FENCE_FLAG_SIGNAL - this request is currently on signal_list
>  	 *
> -	 * This request has been suspended, pending an ongoing investigation.
> +	 * Internal bookkeeping used by the breadcrumb code to track when
> +	 * a request is on the various signal_list.
>  	 */
> -	I915_FENCE_FLAG_HOLD,
> +	I915_FENCE_FLAG_SIGNAL,
>  
>  	/*
>  	 * I915_FENCE_FLAG_NOPREEMPT - this request should not be preempted
> @@ -390,6 +397,12 @@ static inline bool i915_request_in_priority_queue(const struct i915_request *rq)
>  	return test_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags);
>  }
>  
> +static inline bool
> +i915_request_has_initial_breadcrumb(const struct i915_request *rq)
> +{
> +	return test_bit(I915_FENCE_FLAG_INITIAL_BREADCRUMB, &rq->fence.flags);
> +}
> +
>  /**
>   * Returns true if seq1 is later than seq2.
>   */
> -- 
> 2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [v2] drm/i915/gem: Remove redundant exec_fence (rev3)

[Patchwork]

== Series Details ==

Series: series starting with [v2] drm/i915/gem: Remove redundant exec_fence (rev3)
URL   : https://patchwork.freedesktop.org/series/77235/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
c5d36cb78d92 drm/i915/gem: Remove redundant exec_fence
56b752269be2 drm/i915: Mark the addition of the initial-breadcrumb in the request
6df249b03f5f dma-buf: Proxy fence, an unsignaled fence placeholder
-:45: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#45: 
new file mode 100644

-:380: CHECK:UNCOMMENTED_DEFINITION: spinlock_t definition without comment
#380: FILE: drivers/dma-buf/st-dma-fence-proxy.c:20:
+	spinlock_t lock;

-:540: WARNING:MEMORY_BARRIER: memory barrier without comment
#540: FILE: drivers/dma-buf/st-dma-fence-proxy.c:180:
+	smp_store_mb(container_of(cb, struct simple_cb, cb)->seen, true);

total: 0 errors, 2 warnings, 1 checks, 1043 lines checked
5581ddb7dd99 drm/syncobj: Allow use of dma-fence-proxy
80e21224756c drm/i915/gem: Teach execbuf how to wait on future syncobj
186fef4cf0c2 drm/i915/gem: Allow combining submit-fences with syncobj
b67343cec0c9 drm/i915/gt: Declare when we enabled timeslicing

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

[Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [v2] drm/i915/gem: Remove redundant exec_fence (rev3)

[Patchwork]

== Series Details ==

Series: series starting with [v2] drm/i915/gem: Remove redundant exec_fence (rev3)
URL   : https://patchwork.freedesktop.org/series/77235/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_8475 -> Patchwork_17650
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/index.html

New tests
---------

  New tests have been introduced between CI_DRM_8475 and Patchwork_17650:

### New IGT tests (1) ###

  * igt@dmabuf@all@dma_fence_proxy:
    - Statuses : 41 pass(s)
    - Exec time: [0.03, 0.10] s

  

Known issues
------------

  Here are the changes found in Patchwork_17650 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@i915_selftest@live@gt_engines:
    - fi-bwr-2160:        [PASS][1] -> [INCOMPLETE][2] ([i915#489])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/fi-bwr-2160/igt@i915_selftest@live@gt_engines.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/fi-bwr-2160/igt@i915_selftest@live@gt_engines.html

  
  [i915#489]: https://gitlab.freedesktop.org/drm/intel/issues/489


Participating hosts (48 -> 45)
------------------------------

  Additional (2): fi-kbl-7560u fi-tgl-u 
  Missing    (5): fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-byt-clapper fi-bdw-samus 


Build changes
-------------

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_8475 -> Patchwork_17650

  CI-20190529: 20190529
  CI_DRM_8475: fdb67b76a2d3b315585813539269dac22e2305f4 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5651: e54e2642f1967ca3c488db32264607df670d1dfb @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_17650: b67343cec0c9c6f9e2ee43eaefacd1613be851f7 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

b67343cec0c9 drm/i915/gt: Declare when we enabled timeslicing
186fef4cf0c2 drm/i915/gem: Allow combining submit-fences with syncobj
80e21224756c drm/i915/gem: Teach execbuf how to wait on future syncobj
5581ddb7dd99 drm/syncobj: Allow use of dma-fence-proxy
6df249b03f5f dma-buf: Proxy fence, an unsignaled fence placeholder
56b752269be2 drm/i915: Mark the addition of the initial-breadcrumb in the request
c5d36cb78d92 drm/i915/gem: Remove redundant exec_fence

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✓ Fi.CI.IGT: success for series starting with [v2] drm/i915/gem: Remove redundant exec_fence (rev3)

[Patchwork]

== Series Details ==

Series: series starting with [v2] drm/i915/gem: Remove redundant exec_fence (rev3)
URL   : https://patchwork.freedesktop.org/series/77235/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_8475_full -> Patchwork_17650_full
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_17650_full:

### IGT changes ###

#### Suppressed ####

  The following results come from untrusted machines, tests, or statuses.
  They do not affect the overall result.

  * {igt@gem_exec_fence@syncobj-invalid-wait}:
    - shard-snb:          [PASS][1] -> [FAIL][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-snb1/igt@gem_exec_fence@syncobj-invalid-wait.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-snb4/igt@gem_exec_fence@syncobj-invalid-wait.html
    - shard-tglb:         [PASS][3] -> [FAIL][4]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-tglb3/igt@gem_exec_fence@syncobj-invalid-wait.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-tglb2/igt@gem_exec_fence@syncobj-invalid-wait.html
    - shard-skl:          NOTRUN -> [FAIL][5]
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl6/igt@gem_exec_fence@syncobj-invalid-wait.html
    - shard-glk:          [PASS][6] -> [FAIL][7]
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-glk4/igt@gem_exec_fence@syncobj-invalid-wait.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-glk2/igt@gem_exec_fence@syncobj-invalid-wait.html
    - shard-apl:          [PASS][8] -> [FAIL][9]
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-apl4/igt@gem_exec_fence@syncobj-invalid-wait.html
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-apl4/igt@gem_exec_fence@syncobj-invalid-wait.html
    - shard-kbl:          [PASS][10] -> [FAIL][11]
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-kbl1/igt@gem_exec_fence@syncobj-invalid-wait.html
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-kbl2/igt@gem_exec_fence@syncobj-invalid-wait.html
    - shard-iclb:         [PASS][12] -> [FAIL][13]
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-iclb2/igt@gem_exec_fence@syncobj-invalid-wait.html
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-iclb6/igt@gem_exec_fence@syncobj-invalid-wait.html
    - shard-hsw:          [PASS][14] -> [FAIL][15]
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-hsw4/igt@gem_exec_fence@syncobj-invalid-wait.html
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-hsw2/igt@gem_exec_fence@syncobj-invalid-wait.html

  
New tests
---------

  New tests have been introduced between CI_DRM_8475_full and Patchwork_17650_full:

### New IGT tests (1) ###

  * igt@dmabuf@all@dma_fence_proxy:
    - Statuses : 8 pass(s)
    - Exec time: [0.03, 0.09] s

  

Known issues
------------

  Here are the changes found in Patchwork_17650_full that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gen9_exec_parse@allowed-all:
    - shard-skl:          [PASS][16] -> [DMESG-WARN][17] ([i915#1436] / [i915#716])
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-skl1/igt@gen9_exec_parse@allowed-all.html
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl10/igt@gen9_exec_parse@allowed-all.html

  * igt@i915_pm_rpm@system-suspend:
    - shard-skl:          [PASS][18] -> [INCOMPLETE][19] ([i915#151] / [i915#69])
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-skl9/igt@i915_pm_rpm@system-suspend.html
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl4/igt@i915_pm_rpm@system-suspend.html

  * igt@kms_cursor_legacy@2x-long-flip-vs-cursor-legacy:
    - shard-glk:          [PASS][20] -> [FAIL][21] ([i915#72])
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-glk2/igt@kms_cursor_legacy@2x-long-flip-vs-cursor-legacy.html
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-glk9/igt@kms_cursor_legacy@2x-long-flip-vs-cursor-legacy.html

  * igt@kms_cursor_legacy@flip-vs-cursor-atomic:
    - shard-skl:          [PASS][22] -> [FAIL][23] ([IGT#5])
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-skl7/igt@kms_cursor_legacy@flip-vs-cursor-atomic.html
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl5/igt@kms_cursor_legacy@flip-vs-cursor-atomic.html

  * igt@kms_dp_dsc@basic-dsc-enable-edp:
    - shard-iclb:         [PASS][24] -> [SKIP][25] ([fdo#109349])
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-iclb2/igt@kms_dp_dsc@basic-dsc-enable-edp.html
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-iclb6/igt@kms_dp_dsc@basic-dsc-enable-edp.html

  * igt@kms_hdr@bpc-switch:
    - shard-skl:          [PASS][26] -> [FAIL][27] ([i915#1188])
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-skl4/igt@kms_hdr@bpc-switch.html
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl9/igt@kms_hdr@bpc-switch.html

  * igt@kms_psr@psr2_sprite_render:
    - shard-iclb:         [PASS][28] -> [SKIP][29] ([fdo#109441]) +1 similar issue
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-iclb2/igt@kms_psr@psr2_sprite_render.html
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-iclb6/igt@kms_psr@psr2_sprite_render.html

  * igt@kms_setmode@basic:
    - shard-hsw:          [PASS][30] -> [FAIL][31] ([i915#31])
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-hsw4/igt@kms_setmode@basic.html
   [31]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-hsw1/igt@kms_setmode@basic.html

  * igt@kms_vblank@pipe-a-ts-continuation-suspend:
    - shard-kbl:          [PASS][32] -> [DMESG-WARN][33] ([i915#180]) +1 similar issue
   [32]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-kbl6/igt@kms_vblank@pipe-a-ts-continuation-suspend.html
   [33]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-kbl4/igt@kms_vblank@pipe-a-ts-continuation-suspend.html

  
#### Possible fixes ####

  * igt@kms_cursor_crc@pipe-c-cursor-128x128-random:
    - shard-skl:          [FAIL][34] ([i915#54]) -> [PASS][35]
   [34]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-skl10/igt@kms_cursor_crc@pipe-c-cursor-128x128-random.html
   [35]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl9/igt@kms_cursor_crc@pipe-c-cursor-128x128-random.html

  * igt@kms_cursor_crc@pipe-c-cursor-suspend:
    - shard-apl:          [DMESG-WARN][36] ([i915#180]) -> [PASS][37] +1 similar issue
   [36]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-apl1/igt@kms_cursor_crc@pipe-c-cursor-suspend.html
   [37]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-apl7/igt@kms_cursor_crc@pipe-c-cursor-suspend.html

  * igt@kms_cursor_legacy@cursora-vs-flipa-atomic-transitions:
    - shard-snb:          [SKIP][38] ([fdo#109271]) -> [PASS][39]
   [38]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-snb2/igt@kms_cursor_legacy@cursora-vs-flipa-atomic-transitions.html
   [39]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-snb5/igt@kms_cursor_legacy@cursora-vs-flipa-atomic-transitions.html

  * igt@kms_cursor_legacy@pipe-d-torture-move:
    - shard-tglb:         [DMESG-WARN][40] ([i915#128]) -> [PASS][41]
   [40]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-tglb2/igt@kms_cursor_legacy@pipe-d-torture-move.html
   [41]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-tglb2/igt@kms_cursor_legacy@pipe-d-torture-move.html

  * {igt@kms_flip@2x-flip-vs-expired-vblank@bc-hdmi-a1-hdmi-a2}:
    - shard-glk:          [FAIL][42] ([i915#79]) -> [PASS][43]
   [42]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-glk1/igt@kms_flip@2x-flip-vs-expired-vblank@bc-hdmi-a1-hdmi-a2.html
   [43]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-glk6/igt@kms_flip@2x-flip-vs-expired-vblank@bc-hdmi-a1-hdmi-a2.html

  * {igt@kms_flip@flip-vs-suspend-interruptible@c-dp1}:
    - shard-kbl:          [DMESG-WARN][44] ([i915#180]) -> [PASS][45] +1 similar issue
   [44]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-kbl4/igt@kms_flip@flip-vs-suspend-interruptible@c-dp1.html
   [45]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-kbl1/igt@kms_flip@flip-vs-suspend-interruptible@c-dp1.html

  * igt@kms_plane_alpha_blend@pipe-a-coverage-7efc:
    - shard-skl:          [FAIL][46] ([fdo#108145] / [i915#265]) -> [PASS][47] +1 similar issue
   [46]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-skl2/igt@kms_plane_alpha_blend@pipe-a-coverage-7efc.html
   [47]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl7/igt@kms_plane_alpha_blend@pipe-a-coverage-7efc.html

  * igt@kms_psr@no_drrs:
    - shard-iclb:         [FAIL][48] ([i915#173]) -> [PASS][49]
   [48]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-iclb1/igt@kms_psr@no_drrs.html
   [49]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-iclb5/igt@kms_psr@no_drrs.html

  * igt@kms_psr@psr2_suspend:
    - shard-iclb:         [SKIP][50] ([fdo#109441]) -> [PASS][51] +2 similar issues
   [50]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-iclb4/igt@kms_psr@psr2_suspend.html
   [51]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-iclb2/igt@kms_psr@psr2_suspend.html

  * igt@kms_vblank@pipe-c-ts-continuation-suspend:
    - shard-skl:          [INCOMPLETE][52] ([i915#69]) -> [PASS][53]
   [52]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-skl6/igt@kms_vblank@pipe-c-ts-continuation-suspend.html
   [53]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-skl3/igt@kms_vblank@pipe-c-ts-continuation-suspend.html

  * {igt@perf@polling-parameterized}:
    - shard-hsw:          [FAIL][54] ([i915#1542]) -> [PASS][55]
   [54]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-hsw6/igt@perf@polling-parameterized.html
   [55]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-hsw7/igt@perf@polling-parameterized.html

  
#### Warnings ####

  * igt@i915_pm_dc@dc6-psr:
    - shard-tglb:         [FAIL][56] ([i915#454]) -> [SKIP][57] ([i915#468])
   [56]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-tglb3/igt@i915_pm_dc@dc6-psr.html
   [57]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-tglb2/igt@i915_pm_dc@dc6-psr.html

  * igt@kms_content_protection@atomic-dpms:
    - shard-apl:          [DMESG-FAIL][58] ([fdo#110321] / [i915#95]) -> [TIMEOUT][59] ([i915#1319])
   [58]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-apl8/igt@kms_content_protection@atomic-dpms.html
   [59]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-apl4/igt@kms_content_protection@atomic-dpms.html

  * igt@kms_content_protection@legacy:
    - shard-apl:          [TIMEOUT][60] ([i915#1319]) -> [FAIL][61] ([fdo#110321] / [fdo#110336])
   [60]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8475/shard-apl3/igt@kms_content_protection@legacy.html
   [61]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/shard-apl2/igt@kms_content_protection@legacy.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [IGT#5]: https://gitlab.freedesktop.org/drm/igt-gpu-tools/issues/5
  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109349]: https://bugs.freedesktop.org/show_bug.cgi?id=109349
  [fdo#109441]: https://bugs.freedesktop.org/show_bug.cgi?id=109441
  [fdo#110321]: https://bugs.freedesktop.org/show_bug.cgi?id=110321
  [fdo#110336]: https://bugs.freedesktop.org/show_bug.cgi?id=110336
  [i915#1188]: https://gitlab.freedesktop.org/drm/intel/issues/1188
  [i915#128]: https://gitlab.freedesktop.org/drm/intel/issues/128
  [i915#1319]: https://gitlab.freedesktop.org/drm/intel/issues/1319
  [i915#1436]: https://gitlab.freedesktop.org/drm/intel/issues/1436
  [i915#151]: https://gitlab.freedesktop.org/drm/intel/issues/151
  [i915#1542]: https://gitlab.freedesktop.org/drm/intel/issues/1542
  [i915#173]: https://gitlab.freedesktop.org/drm/intel/issues/173
  [i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
  [i915#265]: https://gitlab.freedesktop.org/drm/intel/issues/265
  [i915#31]: https://gitlab.freedesktop.org/drm/intel/issues/31
  [i915#34]: https://gitlab.freedesktop.org/drm/intel/issues/34
  [i915#454]: https://gitlab.freedesktop.org/drm/intel/issues/454
  [i915#468]: https://gitlab.freedesktop.org/drm/intel/issues/468
  [i915#54]: https://gitlab.freedesktop.org/drm/intel/issues/54
  [i915#69]: https://gitlab.freedesktop.org/drm/intel/issues/69
  [i915#716]: https://gitlab.freedesktop.org/drm/intel/issues/716
  [i915#72]: https://gitlab.freedesktop.org/drm/intel/issues/72
  [i915#79]: https://gitlab.freedesktop.org/drm/intel/issues/79
  [i915#95]: https://gitlab.freedesktop.org/drm/intel/issues/95


Participating hosts (11 -> 11)
------------------------------

  No changes in participating hosts


Build changes
-------------

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_8475 -> Patchwork_17650

  CI-20190529: 20190529
  CI_DRM_8475: fdb67b76a2d3b315585813539269dac22e2305f4 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5651: e54e2642f1967ca3c488db32264607df670d1dfb @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_17650: b67343cec0c9c6f9e2ee43eaefacd1613be851f7 @ git://anongit.freedesktop.org/gfx-ci/linux
  piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17650/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx