[Intel-gfx] Support for iris PIPE_FLUSH_DEFERRED

[Intel-gfx] Support for iris PIPE_FLUSH_DEFERRED

[Chris Wilson]

To correctly implement PIPE_FLUSH_DEFERRED iris needs to combine
I915_EXEC_FENCE_SUBMIT with a syncobj so that it can use semaphores
without running afoul of priority-inversion and use efficient scheduling
with timeslicing.
-Chris


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

[Intel-gfx] [PATCH 1/6] 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    | 188 ++++++++++
 drivers/dma-buf/dma-fence.c          |   4 +-
 drivers/dma-buf/selftests.h          |   1 +
 drivers/dma-buf/st-dma-fence-proxy.c | 541 +++++++++++++++++++++++++++
 include/linux/dma-fence-proxy.h      |  20 +
 7 files changed, 783 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 9c190026bfab..af743bf0720f 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-$(CONFIG_SYNC_FILE)		+= sync_file.o
@@ -9,6 +15,7 @@ obj-$(CONFIG_UDMABUF)		+= udmabuf.o
 
 dmabuf_selftests-y := \
 	selftest.o \
-	st-dma-fence.o
+	st-dma-fence.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..2cc0002dc47f
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-proxy.c
@@ -0,0 +1,188 @@
+// 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;
+	spinlock_t lock;
+
+	struct dma_fence *real;
+	struct dma_fence_cb cb;
+	struct irq_work work;
+};
+
+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);
+
+	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, SINGLE_DEPTH_NESTING);
+		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);
+}
+
+static 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,
+};
+
+/**
+ * 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;
+
+	spin_lock_init(&p->lock);
+	dma_fence_init(&p->base, &dma_fence_proxy_ops, &p->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 wrap_signal_locked(struct dma_fence *fence, struct dma_fence *real)
+{
+	if (real->error)
+		dma_fence_set_error(fence, real->error);
+	dma_fence_signal_locked(fence);
+}
+
+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->base.lock, flags);
+
+	if (unlikely(!real)) {
+		dma_fence_signal_locked(&p->base);
+		goto unlock;
+	}
+
+	p->real = dma_fence_get(real);
+
+	spin_lock_nested(real->lock, SINGLE_DEPTH_NESTING);
+	if (dma_fence_is_signaled(real)) {
+		wrap_signal_locked(&p->base, real);
+	} else if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
+			    &p->base.flags) &&
+		   !__dma_fence_enable_signaling(real)) {
+		wrap_signal_locked(&p->base, real);
+	} else {
+		dma_fence_get(&p->base);
+		p->cb.func = proxy_callback;
+		list_add_tail(&p->cb.node, &real->cb_list);
+	}
+	spin_unlock(real->lock);
+
+unlock:
+	spin_unlock_irqrestore(p->base.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 && old->ops == &dma_fence_proxy_ops)
+		proxy_assign(old, fence);
+
+	return old;
+}
+EXPORT_SYMBOL(dma_fence_replace_proxy);
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 052a41e2451c..fa7bedc6703d 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 5320386f02e5..070a157de553 100644
--- a/drivers/dma-buf/selftests.h
+++ b/drivers/dma-buf/selftests.h
@@ -11,3 +11,4 @@
  */
 selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */
 selftest(dma_fence, dma_fence)
+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..4e066b8e5a7f
--- /dev/null
+++ b/drivers/dma-buf/st-dma-fence-proxy.c
@@ -0,0 +1,541 @@
+// 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_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;
+}
+
+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_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),
+	};
+	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..587d5044f0bf
--- /dev/null
+++ b/include/linux/dma-fence-proxy.h
@@ -0,0 +1,20 @@
+/* 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>
+
+struct dma_fence;
+
+struct dma_fence *dma_fence_create_proxy(void);
+
+struct dma_fence *
+dma_fence_replace_proxy(struct dma_fence __rcu **slot, struct dma_fence *fence);
+
+#endif /* __LINUX_DMA_FENCE_PROXY_H */
-- 
2.25.1

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

[Intel-gfx] [PATCH 2/6] 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)
-- 
2.25.1

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

[Intel-gfx] [PATCH 3/6] 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.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 17 +++++++++++++++--
 1 file changed, 15 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 87fa5f42c39a..ff797a83eda2 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>
@@ -2528,8 +2529,20 @@ await_fence_array(struct i915_execbuffer *eb,
 			continue;
 
 		fence = drm_syncobj_fence_get(syncobj);
-		if (!fence)
-			return -EINVAL;
+		if (!fence) {
+			fence = dma_fence_create_proxy();
+			if (!fence)
+				return -ENOMEM;
+
+			spin_lock(&syncobj->lock);
+			if (syncobj->fence) {
+				dma_fence_put(fence);
+				fence = dma_fence_get(syncobj->fence);
+			} else {
+				syncobj->fence = dma_fence_get(fence);
+			}
+			spin_unlock(&syncobj->lock);
+		}
 
 		err = i915_request_await_dma_fence(eb->request, fence);
 		dma_fence_put(fence);
-- 
2.25.1

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

[Intel-gfx] [PATCH 4/6] drm/i915/gem: Allow combining submit-fences with syncobj

[Chris Wilson]

Fixes: a88b6e4cbafd ("drm/i915: Allow specification of parallel execbuf")
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>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 10 +++++++---
 include/uapi/drm/i915_drm.h                    |  7 ++++---
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index ff797a83eda2..f9595acfbb96 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2493,7 +2493,7 @@ 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;
@@ -2524,7 +2524,7 @@ 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;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 829c0a48577f..92e2773a7c77 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;
 };
 
-- 
2.25.1

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

[Intel-gfx] [PATCH 5/6] 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")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Kenneth Graunke <kenneth@whitecape.org>
---
 drivers/gpu/drm/i915/gt/intel_engine.h      | 3 ++-
 drivers/gpu/drm/i915/gt/intel_engine_user.c | 5 +++++
 include/uapi/drm/i915_drm.h                 | 1 +
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 29c8c03c5caa..a32dc82a90d4 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -326,7 +326,8 @@ intel_engine_has_timeslices(const struct intel_engine_cs *engine)
 	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
 		return false;
 
-	return intel_engine_has_semaphores(engine);
+	return (intel_engine_has_semaphores(engine) &&
+		intel_engine_has_preemption(engine));
 }
 
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 848decee9066..b84fdd722781 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -121,6 +121,11 @@ static void set_scheduler_caps(struct drm_i915_private *i915)
 			else
 				disabled |= BIT(map[i].sched);
 		}
+
+		if (intel_engine_has_timeslices(engine))
+			enabled |= I915_SCHEDULER_CAP_TIMESLICING;
+		else
+			disabled |= I915_SCHEDULER_CAP_TIMESLICING;
 	}
 
 	i915->caps.scheduler = enabled & ~disabled;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 92e2773a7c77..4b2be4d446a1 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
 
-- 
2.25.1

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

[Intel-gfx] [PATCH 6/6] drm/i915/gt: Yield the timeslice if caught waiting on a user semaphore

[Chris Wilson]

If we find ourselves waiting on a MI_SEMAPHORE_WAIT, either within the
user batch or in our own preamble, the engine raises a
GT_WAIT_ON_SEMAPHORE interrupt. We can unmask that interrupt and so
respond to a semaphore wait by yielding the timeslice, if we have
another context to yield to!

The only real complication is that the interrupt is only generated for
the start of the semaphore wait, and is asynchronous to our
process_csb() -- that is, we may not have registered the timeslice before
we see the interrupt. To ensure we don't miss a potential semaphore
blocking forward progress (e.g. selftests/live_timeslice_preempt) we mark
the interrupt and apply it to the next timeslice regardless of whether it
was active at the time.

v2: We use semaphores in preempt-to-busy, within the timeslicing
implementation itself! Ergo, when we do insert a preemption due to an
expired timeslice, the new context may start with the missed semaphore
flagged by the retired context and be yielded, ad infinitum. To avoid
this, read the context id at the time of the semaphore interrupt and
only yield if that context is still active.

Fixes: 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Kenneth Graunke <kenneth@whitecape.org>
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |  6 +++
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  9 +++++
 drivers/gpu/drm/i915/gt/intel_gt_irq.c       | 13 ++++++-
 drivers/gpu/drm/i915/gt/intel_lrc.c          | 40 +++++++++++++++++---
 drivers/gpu/drm/i915/i915_reg.h              |  1 +
 5 files changed, 61 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 119c9cb24fd4..eec6e3245a97 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1288,6 +1288,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
 		drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID));
+	if (HAS_EXECLISTS(dev_priv)) {
+		drm_printf(m, "\tEL_STAT_HI: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI));
+		drm_printf(m, "\tEL_STAT_LO: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO));
+	}
 	drm_printf(m, "\tRING_START: 0x%08x\n",
 		   ENGINE_READ(engine, RING_START));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index b23366a81048..24cff658e6e5 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -156,6 +156,15 @@ struct intel_engine_execlists {
 	 */
 	struct i915_priolist default_priolist;
 
+	/**
+	 * @yield: CCID at the time of the last semaphore-wait interrupt.
+	 *
+	 * Instead of leaving a semaphore busy-spinning on an engine, we would
+	 * like to switch to another ready context, i.e. yielding the semaphore
+	 * timeslice.
+	 */
+	u32 yield;
+
 	/**
 	 * @error_interrupt: CS Master EIR
 	 *
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index f0e7fd95165a..875bd0392ffc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -39,6 +39,13 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 		}
 	}
 
+	if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) {
+		WRITE_ONCE(engine->execlists.yield,
+			   ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI));
+		if (del_timer(&engine->execlists.timer))
+			tasklet = true;
+	}
+
 	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
 		tasklet = true;
 
@@ -228,7 +235,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	struct intel_uncore *uncore = gt->uncore;
 	const u32 dmask = irqs << 16 | irqs;
 	const u32 smask = irqs << 16;
@@ -366,7 +374,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	const u32 gt_interrupts[] = {
 		irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT,
 		irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 47561dc29304..fc6c3a922a22 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1728,7 +1728,8 @@ static void defer_active(struct intel_engine_cs *engine)
 }
 
 static bool
-need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
+need_timeslice(const struct intel_engine_cs *engine,
+	       const struct i915_request *rq)
 {
 	int hint;
 
@@ -1744,6 +1745,31 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
 	return hint >= effective_prio(rq);
 }
 
+static bool
+timeslice_yield(const struct intel_engine_execlists *el,
+		const struct i915_request *rq)
+{
+	/*
+	 * Once bitten, forever smitten!
+	 *
+	 * If the active context ever busy-waited on a semaphore,
+	 * it will be treated as a hog until the end of its timeslice.
+	 * The HW only sends an interrupt on the first miss, and we
+	 * do know if that semaphore has been signaled, or even if it
+	 * is now stuck on another semaphore. Play safe, yield if it
+	 * might be stuck -- it will be given a fresh timeslice in
+	 * the near future.
+	 */
+	return upper_32_bits(rq->context->lrc_desc) == READ_ONCE(el->yield);
+}
+
+static bool
+timeslice_expired(const struct intel_engine_execlists *el,
+		  const struct i915_request *rq)
+{
+	return timer_expired(&el->timer) || timeslice_yield(el, rq);
+}
+
 static int
 switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq)
 {
@@ -1759,8 +1785,7 @@ timeslice(const struct intel_engine_cs *engine)
 	return READ_ONCE(engine->props.timeslice_duration_ms);
 }
 
-static unsigned long
-active_timeslice(const struct intel_engine_cs *engine)
+static unsigned long active_timeslice(const struct intel_engine_cs *engine)
 {
 	const struct i915_request *rq = *engine->execlists.active;
 
@@ -1903,13 +1928,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
-			   timer_expired(&engine->execlists.timer)) {
+			   timeslice_expired(execlists, last)) {
 			ENGINE_TRACE(engine,
-				     "expired last=%llx:%lld, prio=%d, hint=%d\n",
+				     "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
 				     last->fence.context,
 				     last->fence.seqno,
 				     last->sched.attr.priority,
-				     execlists->queue_priority_hint);
+				     execlists->queue_priority_hint,
+				     yesno(timeslice_yield(execlists, last)));
 
 			ring_set_paused(engine, 1);
 			defer_active(engine);
@@ -2169,6 +2195,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		}
 		clear_ports(port + 1, last_port - port);
 
+		WRITE_ONCE(execlists->yield, -1);
 		execlists_submit_ports(engine);
 		set_preempt_timeout(engine);
 	} else {
@@ -4413,6 +4440,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift;
 	engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift;
 	engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift;
+	engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift;
 }
 
 static void rcs_submission_override(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f45b5e86ec63..0b5e669c4867 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3092,6 +3092,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
+#define GT_WAIT_SEMAPHORE_INTERRUPT		REG_BIT(11) /* bdw+ */
 #define GT_CONTEXT_SWITCH_INTERRUPT		(1 <<  8)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
-- 
2.25.1

_______________________________________________
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 [1/6] dma-buf: Proxy fence, an unsignaled fence placeholder

[Patchwork]

== Series Details ==

Series: series starting with [1/6] dma-buf: Proxy fence, an unsignaled fence placeholder
URL   : https://patchwork.freedesktop.org/series/73824/
State : warning

== Summary ==

$ dim checkpatch origin/drm-tip
09c82611f40a 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

-:93: CHECK:UNCOMMENTED_DEFINITION: spinlock_t definition without comment
#93: FILE: drivers/dma-buf/dma-fence-proxy.c:18:
+	spinlock_t lock;

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

-:480: WARNING:MEMORY_BARRIER: memory barrier without comment
#480: 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, 2 checks, 811 lines checked
998583c37f1c drm/syncobj: Allow use of dma-fence-proxy
fa7ab03ef010 drm/i915/gem: Teach execbuf how to wait on future syncobj
4599f7d30c99 drm/i915/gem: Allow combining submit-fences with syncobj
b6df913b7c4d drm/i915/gt: Declare when we enabled timeslicing
997bcef70cfe drm/i915/gt: Yield the timeslice if caught waiting on a user semaphore

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

[Intel-gfx] ✗ Fi.CI.SPARSE: warning for series starting with [1/6] dma-buf: Proxy fence, an unsignaled fence placeholder

[Patchwork]

== Series Details ==

Series: series starting with [1/6] dma-buf: Proxy fence, an unsignaled fence placeholder
URL   : https://patchwork.freedesktop.org/series/73824/
State : warning

== Summary ==

$ dim sparse origin/drm-tip
Sparse version: v0.6.0
Commit: dma-buf: Proxy fence, an unsignaled fence placeholder
Okay!

Commit: drm/syncobj: Allow use of dma-fence-proxy
Okay!

Commit: drm/i915/gem: Teach execbuf how to wait on future syncobj
-
+drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c:2540:62:    expected struct dma_fence *fence
+drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c:2540:62:    got struct dma_fence [noderef] <asn:4> *fence
+drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c:2540:62: warning: incorrect type in argument 1 (different address spaces)
+drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c:2542:48:    expected struct dma_fence [noderef] <asn:4> *fence
+drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c:2542:48:    got struct dma_fence *
+drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c:2542:48: warning: incorrect type in assignment (different address spaces)

Commit: drm/i915/gem: Allow combining submit-fences with syncobj
Okay!

Commit: drm/i915/gt: Declare when we enabled timeslicing
Okay!

Commit: drm/i915/gt: Yield the timeslice if caught waiting on a user semaphore
Okay!

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

[Intel-gfx] ✗ Fi.CI.BAT: failure for series starting with [1/6] dma-buf: Proxy fence, an unsignaled fence placeholder

[Patchwork]

== Series Details ==

Series: series starting with [1/6] dma-buf: Proxy fence, an unsignaled fence placeholder
URL   : https://patchwork.freedesktop.org/series/73824/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_7991 -> Patchwork_16679
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_16679 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_16679, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/index.html

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

  Here are the unknown changes that may have been introduced in Patchwork_16679:

### IGT changes ###

#### Possible regressions ####

  * igt@i915_selftest@live_gt_lrc:
    - fi-cfl-8700k:       [PASS][1] -> [DMESG-FAIL][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7991/fi-cfl-8700k/igt@i915_selftest@live_gt_lrc.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/fi-cfl-8700k/igt@i915_selftest@live_gt_lrc.html

  
New tests
---------

  New tests have been introduced between CI_DRM_7991 and Patchwork_16679:

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

  * igt@dmabuf@dma_fence_proxy:
    - Statuses : 36 pass(s)
    - Exec time: [0.03, 0.11] s

  

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

  Here are the changes found in Patchwork_16679 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@gem_close_race@basic-threads:
    - fi-hsw-peppy:       [PASS][3] -> [TIMEOUT][4] ([fdo#112271] / [i915#1084])
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7991/fi-hsw-peppy/igt@gem_close_race@basic-threads.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/fi-hsw-peppy/igt@gem_close_race@basic-threads.html

  * igt@i915_selftest@live_gem_contexts:
    - fi-cml-s:           [PASS][5] -> [DMESG-FAIL][6] ([i915#877])
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7991/fi-cml-s/igt@i915_selftest@live_gem_contexts.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/fi-cml-s/igt@i915_selftest@live_gem_contexts.html

  
#### Possible fixes ####

  * igt@gem_close_race@basic-threads:
    - fi-hsw-4770r:       [TIMEOUT][7] ([fdo#112271] / [i915#1084]) -> [PASS][8]
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7991/fi-hsw-4770r/igt@gem_close_race@basic-threads.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/fi-hsw-4770r/igt@gem_close_race@basic-threads.html

  * igt@kms_frontbuffer_tracking@basic:
    - fi-hsw-peppy:       [DMESG-WARN][9] ([i915#44]) -> [PASS][10]
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7991/fi-hsw-peppy/igt@kms_frontbuffer_tracking@basic.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/fi-hsw-peppy/igt@kms_frontbuffer_tracking@basic.html

  
#### Warnings ####

  * igt@kms_chamelium@hdmi-hpd-fast:
    - fi-kbl-7500u:       [FAIL][11] ([fdo#111096] / [i915#323]) -> [FAIL][12] ([fdo#111407])
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_7991/fi-kbl-7500u/igt@kms_chamelium@hdmi-hpd-fast.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/fi-kbl-7500u/igt@kms_chamelium@hdmi-hpd-fast.html

  
  [fdo#111096]: https://bugs.freedesktop.org/show_bug.cgi?id=111096
  [fdo#111407]: https://bugs.freedesktop.org/show_bug.cgi?id=111407
  [fdo#112271]: https://bugs.freedesktop.org/show_bug.cgi?id=112271
  [i915#1084]: https://gitlab.freedesktop.org/drm/intel/issues/1084
  [i915#323]: https://gitlab.freedesktop.org/drm/intel/issues/323
  [i915#44]: https://gitlab.freedesktop.org/drm/intel/issues/44
  [i915#877]: https://gitlab.freedesktop.org/drm/intel/issues/877


Participating hosts (49 -> 44)
------------------------------

  Additional (2): fi-tgl-y fi-bwr-2160 
  Missing    (7): fi-ilk-m540 fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-ctg-p8600 fi-byt-clapper fi-bdw-samus 


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

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_7991 -> Patchwork_16679

  CI-20190529: 20190529
  CI_DRM_7991: 56b4b8720717a562ebf4657c8624fb63a6c9d195 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5458: 5f7e4ae6a91ed2c104593b8abd5b71a6cc96fc10 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_16679: 997bcef70cfea1b212dc9b9fe55cfc9bc1f7090f @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

997bcef70cfe drm/i915/gt: Yield the timeslice if caught waiting on a user semaphore
b6df913b7c4d drm/i915/gt: Declare when we enabled timeslicing
4599f7d30c99 drm/i915/gem: Allow combining submit-fences with syncobj
fa7ab03ef010 drm/i915/gem: Teach execbuf how to wait on future syncobj
998583c37f1c drm/syncobj: Allow use of dma-fence-proxy
09c82611f40a dma-buf: Proxy fence, an unsignaled fence placeholder

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_16679/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx