dri-devel.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 1/9] dma-buf: make fence sequence numbers 64 bit v2
@ 2018-12-05 13:08 Christian König
  2018-12-05 13:08 ` [PATCH 6/9] drm/syncobj: add timeline payload query ioctl v4 Christian König
       [not found] ` <20181205130835.1595-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
  0 siblings, 2 replies; 16+ messages in thread
From: Christian König @ 2018-12-05 13:08 UTC (permalink / raw)
  To: dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW

For a lot of use cases we need 64bit sequence numbers. Currently drivers
overload the dma_fence structure to store the additional bits.

Stop doing that and make the sequence number in the dma_fence always
64bit.

For compatibility with hardware which can do only 32bit sequences the
comparisons in __dma_fence_is_later only takes the lower 32bits as significant
when the upper 32bits are all zero.

v2: change the logic in __dma_fence_is_later

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/dma-fence.c            |  2 +-
 drivers/dma-buf/sw_sync.c              |  2 +-
 drivers/dma-buf/sync_file.c            |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c |  2 +-
 drivers/gpu/drm/i915/i915_sw_fence.c   |  2 +-
 drivers/gpu/drm/i915/intel_engine_cs.c |  2 +-
 drivers/gpu/drm/vgem/vgem_fence.c      |  4 ++--
 include/linux/dma-fence.h              | 22 +++++++++++++++-------
 8 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 136ec04d683f..3aa8733f832a 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -649,7 +649,7 @@ EXPORT_SYMBOL(dma_fence_wait_any_timeout);
  */
 void
 dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
-	       spinlock_t *lock, u64 context, unsigned seqno)
+	       spinlock_t *lock, u64 context, u64 seqno)
 {
 	BUG_ON(!lock);
 	BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name);
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 53c1d6d36a64..32dcf7b4c935 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -172,7 +172,7 @@ static bool timeline_fence_enable_signaling(struct dma_fence *fence)
 static void timeline_fence_value_str(struct dma_fence *fence,
 				    char *str, int size)
 {
-	snprintf(str, size, "%d", fence->seqno);
+	snprintf(str, size, "%lld", fence->seqno);
 }
 
 static void timeline_fence_timeline_value_str(struct dma_fence *fence,
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 35dd06479867..4f6305ca52c8 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -144,7 +144,7 @@ char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len)
 	} else {
 		struct dma_fence *fence = sync_file->fence;
 
-		snprintf(buf, len, "%s-%s%llu-%d",
+		snprintf(buf, len, "%s-%s%llu-%lld",
 			 fence->ops->get_driver_name(fence),
 			 fence->ops->get_timeline_name(fence),
 			 fence->context,
@@ -258,7 +258,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a,
 
 			i_b++;
 		} else {
-			if (pt_a->seqno - pt_b->seqno <= INT_MAX)
+			if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno))
 				add_fence(fences, &i, pt_a);
 			else
 				add_fence(fences, &i, pt_b);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 12f2bf97611f..bfaf5c6323be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -388,7 +388,7 @@ void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 			   soffset, eoffset, eoffset - soffset);
 
 		if (i->fence)
-			seq_printf(m, " protected by 0x%08x on context %llu",
+			seq_printf(m, " protected by 0x%016llx on context %llu",
 				   i->fence->seqno, i->fence->context);
 
 		seq_printf(m, "\n");
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 6dbeed079ae5..11bcdabd5177 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -393,7 +393,7 @@ static void timer_i915_sw_fence_wake(struct timer_list *t)
 	if (!fence)
 		return;
 
-	pr_notice("Asynchronous wait on fence %s:%s:%x timed out (hint:%pS)\n",
+	pr_notice("Asynchronous wait on fence %s:%s:%llx timed out (hint:%pS)\n",
 		  cb->dma->ops->get_driver_name(cb->dma),
 		  cb->dma->ops->get_timeline_name(cb->dma),
 		  cb->dma->seqno,
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 217ed3ee1cab..f28a66c67d34 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1236,7 +1236,7 @@ static void print_request(struct drm_printer *m,
 
 	x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));
 
-	drm_printf(m, "%s%x%s [%llx:%x]%s @ %dms: %s\n",
+	drm_printf(m, "%s%x%s [%llx:%llx]%s @ %dms: %s\n",
 		   prefix,
 		   rq->global_seqno,
 		   i915_request_completed(rq) ? "!" : "",
diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c
index c1c420afe2dd..eb17c0cd3727 100644
--- a/drivers/gpu/drm/vgem/vgem_fence.c
+++ b/drivers/gpu/drm/vgem/vgem_fence.c
@@ -53,13 +53,13 @@ static void vgem_fence_release(struct dma_fence *base)
 
 static void vgem_fence_value_str(struct dma_fence *fence, char *str, int size)
 {
-	snprintf(str, size, "%u", fence->seqno);
+	snprintf(str, size, "%llu", fence->seqno);
 }
 
 static void vgem_fence_timeline_value_str(struct dma_fence *fence, char *str,
 					  int size)
 {
-	snprintf(str, size, "%u",
+	snprintf(str, size, "%llu",
 		 dma_fence_is_signaled(fence) ? fence->seqno : 0);
 }
 
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 999e4b104410..6b788467b2e3 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -77,7 +77,7 @@ struct dma_fence {
 	struct list_head cb_list;
 	spinlock_t *lock;
 	u64 context;
-	unsigned seqno;
+	u64 seqno;
 	unsigned long flags;
 	ktime_t timestamp;
 	int error;
@@ -244,7 +244,7 @@ struct dma_fence_ops {
 };
 
 void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
-		    spinlock_t *lock, u64 context, unsigned seqno);
+		    spinlock_t *lock, u64 context, u64 seqno);
 
 void dma_fence_release(struct kref *kref);
 void dma_fence_free(struct dma_fence *fence);
@@ -414,9 +414,17 @@ dma_fence_is_signaled(struct dma_fence *fence)
  * Returns true if f1 is chronologically later than f2. Both fences must be
  * from the same context, since a seqno is not common across contexts.
  */
-static inline bool __dma_fence_is_later(u32 f1, u32 f2)
+static inline bool __dma_fence_is_later(u64 f1, u64 f2)
 {
-	return (int)(f1 - f2) > 0;
+	/* This is for backward compatibility with drivers which can only handle
+	 * 32bit sequence numbers. Use a 64bit compare when any of the higher
+	 * bits are none zero, otherwise use a 32bit compare with wrap around
+	 * handling.
+	 */
+	if (upper_32_bits(f1) || upper_32_bits(f2))
+		return f1 > f2;
+
+	return (int)(lower_32_bits(f1) - lower_32_bits(f2)) > 0;
 }
 
 /**
@@ -548,21 +556,21 @@ u64 dma_fence_context_alloc(unsigned num);
 	do {								\
 		struct dma_fence *__ff = (f);				\
 		if (IS_ENABLED(CONFIG_DMA_FENCE_TRACE))			\
-			pr_info("f %llu#%u: " fmt,			\
+			pr_info("f %llu#%llu: " fmt,			\
 				__ff->context, __ff->seqno, ##args);	\
 	} while (0)
 
 #define DMA_FENCE_WARN(f, fmt, args...) \
 	do {								\
 		struct dma_fence *__ff = (f);				\
-		pr_warn("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\
 			 ##args);					\
 	} while (0)
 
 #define DMA_FENCE_ERR(f, fmt, args...) \
 	do {								\
 		struct dma_fence *__ff = (f);				\
-		pr_err("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_err("f %llu#%llu: " fmt, __ff->context, __ff->seqno,	\
 			##args);					\
 	} while (0)
 
-- 
2.14.1

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

^ permalink raw reply related	[flat|nested] 16+ messages in thread
* [PATCH 1/9] dma-buf: make fence sequence numbers 64 bit v2
@ 2018-12-06  9:37 Christian König
  2018-12-06  9:37 ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Christian König
  0 siblings, 1 reply; 16+ messages in thread
From: Christian König @ 2018-12-06  9:37 UTC (permalink / raw)
  To: dri-devel, amd-gfx

For a lot of use cases we need 64bit sequence numbers. Currently drivers
overload the dma_fence structure to store the additional bits.

Stop doing that and make the sequence number in the dma_fence always
64bit.

For compatibility with hardware which can do only 32bit sequences the
comparisons in __dma_fence_is_later only takes the lower 32bits as significant
when the upper 32bits are all zero.

v2: change the logic in __dma_fence_is_later

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/dma-fence.c            |  2 +-
 drivers/dma-buf/sw_sync.c              |  2 +-
 drivers/dma-buf/sync_file.c            |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c |  2 +-
 drivers/gpu/drm/i915/i915_sw_fence.c   |  2 +-
 drivers/gpu/drm/i915/intel_engine_cs.c |  2 +-
 drivers/gpu/drm/vgem/vgem_fence.c      |  4 ++--
 include/linux/dma-fence.h              | 22 +++++++++++++++-------
 8 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 136ec04d683f..3aa8733f832a 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -649,7 +649,7 @@ EXPORT_SYMBOL(dma_fence_wait_any_timeout);
  */
 void
 dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
-	       spinlock_t *lock, u64 context, unsigned seqno)
+	       spinlock_t *lock, u64 context, u64 seqno)
 {
 	BUG_ON(!lock);
 	BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name);
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 53c1d6d36a64..32dcf7b4c935 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -172,7 +172,7 @@ static bool timeline_fence_enable_signaling(struct dma_fence *fence)
 static void timeline_fence_value_str(struct dma_fence *fence,
 				    char *str, int size)
 {
-	snprintf(str, size, "%d", fence->seqno);
+	snprintf(str, size, "%lld", fence->seqno);
 }
 
 static void timeline_fence_timeline_value_str(struct dma_fence *fence,
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 35dd06479867..4f6305ca52c8 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -144,7 +144,7 @@ char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len)
 	} else {
 		struct dma_fence *fence = sync_file->fence;
 
-		snprintf(buf, len, "%s-%s%llu-%d",
+		snprintf(buf, len, "%s-%s%llu-%lld",
 			 fence->ops->get_driver_name(fence),
 			 fence->ops->get_timeline_name(fence),
 			 fence->context,
@@ -258,7 +258,7 @@ static struct sync_file *sync_file_merge(const char *name, struct sync_file *a,
 
 			i_b++;
 		} else {
-			if (pt_a->seqno - pt_b->seqno <= INT_MAX)
+			if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno))
 				add_fence(fences, &i, pt_a);
 			else
 				add_fence(fences, &i, pt_b);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 12f2bf97611f..bfaf5c6323be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -388,7 +388,7 @@ void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 			   soffset, eoffset, eoffset - soffset);
 
 		if (i->fence)
-			seq_printf(m, " protected by 0x%08x on context %llu",
+			seq_printf(m, " protected by 0x%016llx on context %llu",
 				   i->fence->seqno, i->fence->context);
 
 		seq_printf(m, "\n");
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 6dbeed079ae5..11bcdabd5177 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -393,7 +393,7 @@ static void timer_i915_sw_fence_wake(struct timer_list *t)
 	if (!fence)
 		return;
 
-	pr_notice("Asynchronous wait on fence %s:%s:%x timed out (hint:%pS)\n",
+	pr_notice("Asynchronous wait on fence %s:%s:%llx timed out (hint:%pS)\n",
 		  cb->dma->ops->get_driver_name(cb->dma),
 		  cb->dma->ops->get_timeline_name(cb->dma),
 		  cb->dma->seqno,
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 217ed3ee1cab..f28a66c67d34 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1236,7 +1236,7 @@ static void print_request(struct drm_printer *m,
 
 	x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));
 
-	drm_printf(m, "%s%x%s [%llx:%x]%s @ %dms: %s\n",
+	drm_printf(m, "%s%x%s [%llx:%llx]%s @ %dms: %s\n",
 		   prefix,
 		   rq->global_seqno,
 		   i915_request_completed(rq) ? "!" : "",
diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c
index c1c420afe2dd..eb17c0cd3727 100644
--- a/drivers/gpu/drm/vgem/vgem_fence.c
+++ b/drivers/gpu/drm/vgem/vgem_fence.c
@@ -53,13 +53,13 @@ static void vgem_fence_release(struct dma_fence *base)
 
 static void vgem_fence_value_str(struct dma_fence *fence, char *str, int size)
 {
-	snprintf(str, size, "%u", fence->seqno);
+	snprintf(str, size, "%llu", fence->seqno);
 }
 
 static void vgem_fence_timeline_value_str(struct dma_fence *fence, char *str,
 					  int size)
 {
-	snprintf(str, size, "%u",
+	snprintf(str, size, "%llu",
 		 dma_fence_is_signaled(fence) ? fence->seqno : 0);
 }
 
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 999e4b104410..6b788467b2e3 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -77,7 +77,7 @@ struct dma_fence {
 	struct list_head cb_list;
 	spinlock_t *lock;
 	u64 context;
-	unsigned seqno;
+	u64 seqno;
 	unsigned long flags;
 	ktime_t timestamp;
 	int error;
@@ -244,7 +244,7 @@ struct dma_fence_ops {
 };
 
 void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
-		    spinlock_t *lock, u64 context, unsigned seqno);
+		    spinlock_t *lock, u64 context, u64 seqno);
 
 void dma_fence_release(struct kref *kref);
 void dma_fence_free(struct dma_fence *fence);
@@ -414,9 +414,17 @@ dma_fence_is_signaled(struct dma_fence *fence)
  * Returns true if f1 is chronologically later than f2. Both fences must be
  * from the same context, since a seqno is not common across contexts.
  */
-static inline bool __dma_fence_is_later(u32 f1, u32 f2)
+static inline bool __dma_fence_is_later(u64 f1, u64 f2)
 {
-	return (int)(f1 - f2) > 0;
+	/* This is for backward compatibility with drivers which can only handle
+	 * 32bit sequence numbers. Use a 64bit compare when any of the higher
+	 * bits are none zero, otherwise use a 32bit compare with wrap around
+	 * handling.
+	 */
+	if (upper_32_bits(f1) || upper_32_bits(f2))
+		return f1 > f2;
+
+	return (int)(lower_32_bits(f1) - lower_32_bits(f2)) > 0;
 }
 
 /**
@@ -548,21 +556,21 @@ u64 dma_fence_context_alloc(unsigned num);
 	do {								\
 		struct dma_fence *__ff = (f);				\
 		if (IS_ENABLED(CONFIG_DMA_FENCE_TRACE))			\
-			pr_info("f %llu#%u: " fmt,			\
+			pr_info("f %llu#%llu: " fmt,			\
 				__ff->context, __ff->seqno, ##args);	\
 	} while (0)
 
 #define DMA_FENCE_WARN(f, fmt, args...) \
 	do {								\
 		struct dma_fence *__ff = (f);				\
-		pr_warn("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\
 			 ##args);					\
 	} while (0)
 
 #define DMA_FENCE_ERR(f, fmt, args...) \
 	do {								\
 		struct dma_fence *__ff = (f);				\
-		pr_err("f %llu#%u: " fmt, __ff->context, __ff->seqno,	\
+		pr_err("f %llu#%llu: " fmt, __ff->context, __ff->seqno,	\
 			##args);					\
 	} while (0)
 
-- 
2.14.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

^ permalink raw reply related	[flat|nested] 16+ messages in thread
* [PATCH 1/9] dma-buf: add new dma_fence_chain container v5
@ 2019-03-12  3:10 Chunming Zhou
       [not found] ` <20190312031049.23647-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
  0 siblings, 1 reply; 16+ messages in thread
From: Chunming Zhou @ 2019-03-12  3:10 UTC (permalink / raw)
  To: dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	lionel.g.landwerlin-ral2JQCrhuEAvxtiuMwx3w,
	jason-fQELhIk9awXprZlt/sZkLg, Christian.Koenig-5C7GfCeVMHo
  Cc: Christian König, Christian König

From: Christian König <ckoenig.leichtzumerken@gmail.com>

Lockless container implementation similar to a dma_fence_array, but with
only two elements per node and automatic garbage collection.

v2: properly document dma_fence_chain_for_each, add dma_fence_chain_find_seqno,
    drop prev reference during garbage collection if it's not a chain fence.
v3: use head and iterator for dma_fence_chain_for_each
v4: fix reference count in dma_fence_chain_enable_signaling
v5: fix iteration when walking each chain node

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/Makefile          |   3 +-
 drivers/dma-buf/dma-fence-chain.c | 241 ++++++++++++++++++++++++++++++
 include/linux/dma-fence-chain.h   |  81 ++++++++++
 3 files changed, 324 insertions(+), 1 deletion(-)
 create mode 100644 drivers/dma-buf/dma-fence-chain.c
 create mode 100644 include/linux/dma-fence-chain.h

diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 0913a6ccab5a..1f006e083eb9 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,4 +1,5 @@
-obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o
+obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
+	 reservation.o seqno-fence.o
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
new file mode 100644
index 000000000000..0c5e3c902fa0
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -0,0 +1,241 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/dma-fence-chain.h>
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence);
+
+/**
+ * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence
+ * @chain: chain node to get the previous node from
+ *
+ * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the
+ * chain node.
+ */
+static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain)
+{
+	struct dma_fence *prev;
+
+	rcu_read_lock();
+	prev = dma_fence_get_rcu_safe(&chain->prev);
+	rcu_read_unlock();
+	return prev;
+}
+
+/**
+ * dma_fence_chain_walk - chain walking function
+ * @fence: current chain node
+ *
+ * Walk the chain to the next node. Returns the next fence or NULL if we are at
+ * the end of the chain. Garbage collects chain nodes which are already
+ * signaled.
+ */
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain, *prev_chain;
+	struct dma_fence *prev, *replacement, *tmp;
+
+	chain = to_dma_fence_chain(fence);
+	if (!chain) {
+		dma_fence_put(fence);
+		return NULL;
+	}
+
+	while ((prev = dma_fence_chain_get_prev(chain))) {
+
+		prev_chain = to_dma_fence_chain(prev);
+		if (prev_chain) {
+			if (!dma_fence_is_signaled(prev_chain->fence))
+				break;
+
+			replacement = dma_fence_chain_get_prev(prev_chain);
+		} else {
+			if (!dma_fence_is_signaled(prev))
+				break;
+
+			replacement = NULL;
+		}
+
+		tmp = cmpxchg(&chain->prev, prev, replacement);
+		if (tmp == prev)
+			dma_fence_put(tmp);
+		else
+			dma_fence_put(replacement);
+		dma_fence_put(prev);
+	}
+
+	dma_fence_put(fence);
+	return prev;
+}
+EXPORT_SYMBOL(dma_fence_chain_walk);
+
+/**
+ * dma_fence_chain_find_seqno - find fence chain node by seqno
+ * @pfence: pointer to the chain node where to start
+ * @seqno: the sequence number to search for
+ *
+ * Advance the fence pointer to the chain node which will signal this sequence
+ * number. If no sequence number is provided then this is a no-op.
+ *
+ * Returns EINVAL if the fence is not a chain node or the sequence number has
+ * not yet advanced far enough.
+ */
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno)
+{
+	struct dma_fence_chain *chain;
+
+	if (!seqno)
+		return 0;
+
+	chain = to_dma_fence_chain(*pfence);
+	if (!chain || chain->base.seqno < seqno)
+		return -EINVAL;
+
+	dma_fence_chain_for_each(*pfence, &chain->base) {
+		if ((*pfence)->context != chain->base.context ||
+		    to_dma_fence_chain(*pfence)->prev_seqno < seqno)
+			break;
+	}
+	dma_fence_put(&chain->base);
+
+	return 0;
+}
+EXPORT_SYMBOL(dma_fence_chain_find_seqno);
+
+static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence)
+{
+        return "dma_fence_chain";
+}
+
+static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence)
+{
+        return "unbound";
+}
+
+static void dma_fence_chain_irq_work(struct irq_work *work)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(work, typeof(*chain), work);
+
+	/* Try to rearm the callback */
+	if (!dma_fence_chain_enable_signaling(&chain->base))
+		/* Ok, we are done. No more unsignaled fences left */
+		dma_fence_signal(&chain->base);
+	dma_fence_put(&chain->base);
+}
+
+static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(cb, typeof(*chain), cb);
+	irq_work_queue(&chain->work);
+	dma_fence_put(f);
+}
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence)
+{
+	struct dma_fence_chain *head = to_dma_fence_chain(fence);
+
+	dma_fence_get(&head->base);
+	dma_fence_chain_for_each(fence, &head->base) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		dma_fence_get(f);
+		if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) {
+			dma_fence_put(fence);
+			return true;
+		}
+		dma_fence_put(f);
+	}
+	dma_fence_put(&head->base);
+	return false;
+}
+
+static bool dma_fence_chain_signaled(struct dma_fence *fence)
+{
+	dma_fence_chain_for_each(fence, fence) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		if (!dma_fence_is_signaled(f)) {
+			dma_fence_put(fence);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void dma_fence_chain_release(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+
+	dma_fence_put(chain->prev);
+	dma_fence_put(chain->fence);
+	dma_fence_free(fence);
+}
+
+const struct dma_fence_ops dma_fence_chain_ops = {
+	.get_driver_name = dma_fence_chain_get_driver_name,
+	.get_timeline_name = dma_fence_chain_get_timeline_name,
+	.enable_signaling = dma_fence_chain_enable_signaling,
+	.signaled = dma_fence_chain_signaled,
+	.release = dma_fence_chain_release,
+};
+EXPORT_SYMBOL(dma_fence_chain_ops);
+
+/**
+ * dma_fence_chain_init - initialize a fence chain
+ * @chain: the chain node to initialize
+ * @prev: the previous fence
+ * @fence: the current fence
+ *
+ * Initialize a new chain node and either start a new chain or add the node to
+ * the existing chain of the previous fence.
+ */
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno)
+{
+	struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev);
+	uint64_t context;
+
+	spin_lock_init(&chain->lock);
+	chain->prev = prev;
+	chain->fence = fence;
+	chain->prev_seqno = 0;
+	init_irq_work(&chain->work, dma_fence_chain_irq_work);
+
+	/* Try to reuse the context of the previous chain node. */
+	if (prev_chain && __dma_fence_is_later(seqno, prev->seqno)) {
+		context = prev->context;
+		chain->prev_seqno = prev->seqno;
+	} else {
+		context = dma_fence_context_alloc(1);
+		/* Make sure that we always have a valid sequence number. */
+		if (prev_chain)
+			seqno = max(prev->seqno, seqno);
+	}
+
+	dma_fence_init(&chain->base, &dma_fence_chain_ops,
+		       &chain->lock, context, seqno);
+}
+EXPORT_SYMBOL(dma_fence_chain_init);
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
new file mode 100644
index 000000000000..09b038d3f5ef
--- /dev/null
+++ b/include/linux/dma-fence-chain.h
@@ -0,0 +1,81 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_DMA_FENCE_CHAIN_H
+#define __LINUX_DMA_FENCE_CHAIN_H
+
+#include <linux/dma-fence.h>
+#include <linux/irq_work.h>
+
+/**
+ * struct dma_fence_chain - fence to represent an node of a fence chain
+ * @base: fence base class
+ * @lock: spinlock for fence handling
+ * @prev: previous fence of the chain
+ * @prev_seqno: original previous seqno before garbage collection
+ * @fence: encapsulated fence
+ * @cb: callback structure for signaling
+ * @work: irq work item for signaling
+ */
+struct dma_fence_chain {
+	struct dma_fence base;
+	spinlock_t lock;
+	struct dma_fence *prev;
+	u64 prev_seqno;
+	struct dma_fence *fence;
+	struct dma_fence_cb cb;
+	struct irq_work work;
+};
+
+extern const struct dma_fence_ops dma_fence_chain_ops;
+
+/**
+ * to_dma_fence_chain - cast a fence to a dma_fence_chain
+ * @fence: fence to cast to a dma_fence_array
+ *
+ * Returns NULL if the fence is not a dma_fence_chain,
+ * or the dma_fence_chain otherwise.
+ */
+static inline struct dma_fence_chain *
+to_dma_fence_chain(struct dma_fence *fence)
+{
+	if (!fence || fence->ops != &dma_fence_chain_ops)
+		return NULL;
+
+	return container_of(fence, struct dma_fence_chain, base);
+}
+
+/**
+ * dma_fence_chain_for_each - iterate over all fences in chain
+ * @iter: current fence
+ * @head: starting point
+ *
+ * Iterate over all fences in the chain. We keep a reference to the current
+ * fence while inside the loop which must be dropped when breaking out.
+ */
+#define dma_fence_chain_for_each(iter, head)	\
+	for (iter = dma_fence_get(head); iter; \
+	     iter = dma_fence_chain_walk(iter))
+
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence);
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno);
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno);
+
+#endif /* __LINUX_DMA_FENCE_CHAIN_H */
-- 
2.17.1

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

^ permalink raw reply related	[flat|nested] 16+ messages in thread
* [PATCH 1/9] dma-buf: add new dma_fence_chain container v5
@ 2019-03-15 12:09 Chunming Zhou
       [not found] ` <20190315120959.25489-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
  0 siblings, 1 reply; 16+ messages in thread
From: Chunming Zhou @ 2019-03-15 12:09 UTC (permalink / raw)
  To: dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	lionel.g.landwerlin-ral2JQCrhuEAvxtiuMwx3w,
	jason-fQELhIk9awXprZlt/sZkLg, Christian.Koenig-5C7GfCeVMHo
  Cc: Christian König, Christian König

From: Christian König <ckoenig.leichtzumerken@gmail.com>

Lockless container implementation similar to a dma_fence_array, but with
only two elements per node and automatic garbage collection.

v2: properly document dma_fence_chain_for_each, add dma_fence_chain_find_seqno,
    drop prev reference during garbage collection if it's not a chain fence.
v3: use head and iterator for dma_fence_chain_for_each
v4: fix reference count in dma_fence_chain_enable_signaling
v5: fix iteration when walking each chain node

Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/Makefile          |   3 +-
 drivers/dma-buf/dma-fence-chain.c | 241 ++++++++++++++++++++++++++++++
 include/linux/dma-fence-chain.h   |  81 ++++++++++
 3 files changed, 324 insertions(+), 1 deletion(-)
 create mode 100644 drivers/dma-buf/dma-fence-chain.c
 create mode 100644 include/linux/dma-fence-chain.h

diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 0913a6ccab5a..1f006e083eb9 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,4 +1,5 @@
-obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o
+obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
+	 reservation.o seqno-fence.o
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
new file mode 100644
index 000000000000..0c5e3c902fa0
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -0,0 +1,241 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/dma-fence-chain.h>
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence);
+
+/**
+ * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence
+ * @chain: chain node to get the previous node from
+ *
+ * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the
+ * chain node.
+ */
+static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain)
+{
+	struct dma_fence *prev;
+
+	rcu_read_lock();
+	prev = dma_fence_get_rcu_safe(&chain->prev);
+	rcu_read_unlock();
+	return prev;
+}
+
+/**
+ * dma_fence_chain_walk - chain walking function
+ * @fence: current chain node
+ *
+ * Walk the chain to the next node. Returns the next fence or NULL if we are at
+ * the end of the chain. Garbage collects chain nodes which are already
+ * signaled.
+ */
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain, *prev_chain;
+	struct dma_fence *prev, *replacement, *tmp;
+
+	chain = to_dma_fence_chain(fence);
+	if (!chain) {
+		dma_fence_put(fence);
+		return NULL;
+	}
+
+	while ((prev = dma_fence_chain_get_prev(chain))) {
+
+		prev_chain = to_dma_fence_chain(prev);
+		if (prev_chain) {
+			if (!dma_fence_is_signaled(prev_chain->fence))
+				break;
+
+			replacement = dma_fence_chain_get_prev(prev_chain);
+		} else {
+			if (!dma_fence_is_signaled(prev))
+				break;
+
+			replacement = NULL;
+		}
+
+		tmp = cmpxchg(&chain->prev, prev, replacement);
+		if (tmp == prev)
+			dma_fence_put(tmp);
+		else
+			dma_fence_put(replacement);
+		dma_fence_put(prev);
+	}
+
+	dma_fence_put(fence);
+	return prev;
+}
+EXPORT_SYMBOL(dma_fence_chain_walk);
+
+/**
+ * dma_fence_chain_find_seqno - find fence chain node by seqno
+ * @pfence: pointer to the chain node where to start
+ * @seqno: the sequence number to search for
+ *
+ * Advance the fence pointer to the chain node which will signal this sequence
+ * number. If no sequence number is provided then this is a no-op.
+ *
+ * Returns EINVAL if the fence is not a chain node or the sequence number has
+ * not yet advanced far enough.
+ */
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno)
+{
+	struct dma_fence_chain *chain;
+
+	if (!seqno)
+		return 0;
+
+	chain = to_dma_fence_chain(*pfence);
+	if (!chain || chain->base.seqno < seqno)
+		return -EINVAL;
+
+	dma_fence_chain_for_each(*pfence, &chain->base) {
+		if ((*pfence)->context != chain->base.context ||
+		    to_dma_fence_chain(*pfence)->prev_seqno < seqno)
+			break;
+	}
+	dma_fence_put(&chain->base);
+
+	return 0;
+}
+EXPORT_SYMBOL(dma_fence_chain_find_seqno);
+
+static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence)
+{
+        return "dma_fence_chain";
+}
+
+static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence)
+{
+        return "unbound";
+}
+
+static void dma_fence_chain_irq_work(struct irq_work *work)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(work, typeof(*chain), work);
+
+	/* Try to rearm the callback */
+	if (!dma_fence_chain_enable_signaling(&chain->base))
+		/* Ok, we are done. No more unsignaled fences left */
+		dma_fence_signal(&chain->base);
+	dma_fence_put(&chain->base);
+}
+
+static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(cb, typeof(*chain), cb);
+	irq_work_queue(&chain->work);
+	dma_fence_put(f);
+}
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence)
+{
+	struct dma_fence_chain *head = to_dma_fence_chain(fence);
+
+	dma_fence_get(&head->base);
+	dma_fence_chain_for_each(fence, &head->base) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		dma_fence_get(f);
+		if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) {
+			dma_fence_put(fence);
+			return true;
+		}
+		dma_fence_put(f);
+	}
+	dma_fence_put(&head->base);
+	return false;
+}
+
+static bool dma_fence_chain_signaled(struct dma_fence *fence)
+{
+	dma_fence_chain_for_each(fence, fence) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		if (!dma_fence_is_signaled(f)) {
+			dma_fence_put(fence);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void dma_fence_chain_release(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+
+	dma_fence_put(chain->prev);
+	dma_fence_put(chain->fence);
+	dma_fence_free(fence);
+}
+
+const struct dma_fence_ops dma_fence_chain_ops = {
+	.get_driver_name = dma_fence_chain_get_driver_name,
+	.get_timeline_name = dma_fence_chain_get_timeline_name,
+	.enable_signaling = dma_fence_chain_enable_signaling,
+	.signaled = dma_fence_chain_signaled,
+	.release = dma_fence_chain_release,
+};
+EXPORT_SYMBOL(dma_fence_chain_ops);
+
+/**
+ * dma_fence_chain_init - initialize a fence chain
+ * @chain: the chain node to initialize
+ * @prev: the previous fence
+ * @fence: the current fence
+ *
+ * Initialize a new chain node and either start a new chain or add the node to
+ * the existing chain of the previous fence.
+ */
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno)
+{
+	struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev);
+	uint64_t context;
+
+	spin_lock_init(&chain->lock);
+	chain->prev = prev;
+	chain->fence = fence;
+	chain->prev_seqno = 0;
+	init_irq_work(&chain->work, dma_fence_chain_irq_work);
+
+	/* Try to reuse the context of the previous chain node. */
+	if (prev_chain && __dma_fence_is_later(seqno, prev->seqno)) {
+		context = prev->context;
+		chain->prev_seqno = prev->seqno;
+	} else {
+		context = dma_fence_context_alloc(1);
+		/* Make sure that we always have a valid sequence number. */
+		if (prev_chain)
+			seqno = max(prev->seqno, seqno);
+	}
+
+	dma_fence_init(&chain->base, &dma_fence_chain_ops,
+		       &chain->lock, context, seqno);
+}
+EXPORT_SYMBOL(dma_fence_chain_init);
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
new file mode 100644
index 000000000000..09b038d3f5ef
--- /dev/null
+++ b/include/linux/dma-fence-chain.h
@@ -0,0 +1,81 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_DMA_FENCE_CHAIN_H
+#define __LINUX_DMA_FENCE_CHAIN_H
+
+#include <linux/dma-fence.h>
+#include <linux/irq_work.h>
+
+/**
+ * struct dma_fence_chain - fence to represent an node of a fence chain
+ * @base: fence base class
+ * @lock: spinlock for fence handling
+ * @prev: previous fence of the chain
+ * @prev_seqno: original previous seqno before garbage collection
+ * @fence: encapsulated fence
+ * @cb: callback structure for signaling
+ * @work: irq work item for signaling
+ */
+struct dma_fence_chain {
+	struct dma_fence base;
+	spinlock_t lock;
+	struct dma_fence *prev;
+	u64 prev_seqno;
+	struct dma_fence *fence;
+	struct dma_fence_cb cb;
+	struct irq_work work;
+};
+
+extern const struct dma_fence_ops dma_fence_chain_ops;
+
+/**
+ * to_dma_fence_chain - cast a fence to a dma_fence_chain
+ * @fence: fence to cast to a dma_fence_array
+ *
+ * Returns NULL if the fence is not a dma_fence_chain,
+ * or the dma_fence_chain otherwise.
+ */
+static inline struct dma_fence_chain *
+to_dma_fence_chain(struct dma_fence *fence)
+{
+	if (!fence || fence->ops != &dma_fence_chain_ops)
+		return NULL;
+
+	return container_of(fence, struct dma_fence_chain, base);
+}
+
+/**
+ * dma_fence_chain_for_each - iterate over all fences in chain
+ * @iter: current fence
+ * @head: starting point
+ *
+ * Iterate over all fences in the chain. We keep a reference to the current
+ * fence while inside the loop which must be dropped when breaking out.
+ */
+#define dma_fence_chain_for_each(iter, head)	\
+	for (iter = dma_fence_get(head); iter; \
+	     iter = dma_fence_chain_walk(iter))
+
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence);
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno);
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno);
+
+#endif /* __LINUX_DMA_FENCE_CHAIN_H */
-- 
2.17.1

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

^ permalink raw reply related	[flat|nested] 16+ messages in thread
* [PATCH 1/9] dma-buf: add new dma_fence_chain container v6
@ 2019-03-20  5:47 Chunming Zhou
       [not found] ` <20190320054724.14636-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
  0 siblings, 1 reply; 16+ messages in thread
From: Chunming Zhou @ 2019-03-20  5:47 UTC (permalink / raw)
  To: dri-devel, amd-gfx, lionel.g.landwerlin, jason, Christian.Koenig,
	Tobias.Hector
  Cc: Christian König, Christian König

From: Christian König <ckoenig.leichtzumerken@gmail.com>

Lockless container implementation similar to a dma_fence_array, but with
only two elements per node and automatic garbage collection.

v2: properly document dma_fence_chain_for_each, add dma_fence_chain_find_seqno,
    drop prev reference during garbage collection if it's not a chain fence.
v3: use head and iterator for dma_fence_chain_for_each
v4: fix reference count in dma_fence_chain_enable_signaling
v5: fix iteration when walking each chain node
v6: add __rcu for member 'prev' of struct chain node

Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
---
 drivers/dma-buf/Makefile          |   3 +-
 drivers/dma-buf/dma-fence-chain.c | 241 ++++++++++++++++++++++++++++++
 include/linux/dma-fence-chain.h   |  81 ++++++++++
 3 files changed, 324 insertions(+), 1 deletion(-)
 create mode 100644 drivers/dma-buf/dma-fence-chain.c
 create mode 100644 include/linux/dma-fence-chain.h

diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 0913a6ccab5a..1f006e083eb9 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,4 +1,5 @@
-obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o
+obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
+	 reservation.o seqno-fence.o
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
new file mode 100644
index 000000000000..0c5e3c902fa0
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -0,0 +1,241 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/dma-fence-chain.h>
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence);
+
+/**
+ * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence
+ * @chain: chain node to get the previous node from
+ *
+ * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the
+ * chain node.
+ */
+static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain)
+{
+	struct dma_fence *prev;
+
+	rcu_read_lock();
+	prev = dma_fence_get_rcu_safe(&chain->prev);
+	rcu_read_unlock();
+	return prev;
+}
+
+/**
+ * dma_fence_chain_walk - chain walking function
+ * @fence: current chain node
+ *
+ * Walk the chain to the next node. Returns the next fence or NULL if we are at
+ * the end of the chain. Garbage collects chain nodes which are already
+ * signaled.
+ */
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain, *prev_chain;
+	struct dma_fence *prev, *replacement, *tmp;
+
+	chain = to_dma_fence_chain(fence);
+	if (!chain) {
+		dma_fence_put(fence);
+		return NULL;
+	}
+
+	while ((prev = dma_fence_chain_get_prev(chain))) {
+
+		prev_chain = to_dma_fence_chain(prev);
+		if (prev_chain) {
+			if (!dma_fence_is_signaled(prev_chain->fence))
+				break;
+
+			replacement = dma_fence_chain_get_prev(prev_chain);
+		} else {
+			if (!dma_fence_is_signaled(prev))
+				break;
+
+			replacement = NULL;
+		}
+
+		tmp = cmpxchg(&chain->prev, prev, replacement);
+		if (tmp == prev)
+			dma_fence_put(tmp);
+		else
+			dma_fence_put(replacement);
+		dma_fence_put(prev);
+	}
+
+	dma_fence_put(fence);
+	return prev;
+}
+EXPORT_SYMBOL(dma_fence_chain_walk);
+
+/**
+ * dma_fence_chain_find_seqno - find fence chain node by seqno
+ * @pfence: pointer to the chain node where to start
+ * @seqno: the sequence number to search for
+ *
+ * Advance the fence pointer to the chain node which will signal this sequence
+ * number. If no sequence number is provided then this is a no-op.
+ *
+ * Returns EINVAL if the fence is not a chain node or the sequence number has
+ * not yet advanced far enough.
+ */
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno)
+{
+	struct dma_fence_chain *chain;
+
+	if (!seqno)
+		return 0;
+
+	chain = to_dma_fence_chain(*pfence);
+	if (!chain || chain->base.seqno < seqno)
+		return -EINVAL;
+
+	dma_fence_chain_for_each(*pfence, &chain->base) {
+		if ((*pfence)->context != chain->base.context ||
+		    to_dma_fence_chain(*pfence)->prev_seqno < seqno)
+			break;
+	}
+	dma_fence_put(&chain->base);
+
+	return 0;
+}
+EXPORT_SYMBOL(dma_fence_chain_find_seqno);
+
+static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence)
+{
+        return "dma_fence_chain";
+}
+
+static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence)
+{
+        return "unbound";
+}
+
+static void dma_fence_chain_irq_work(struct irq_work *work)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(work, typeof(*chain), work);
+
+	/* Try to rearm the callback */
+	if (!dma_fence_chain_enable_signaling(&chain->base))
+		/* Ok, we are done. No more unsignaled fences left */
+		dma_fence_signal(&chain->base);
+	dma_fence_put(&chain->base);
+}
+
+static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(cb, typeof(*chain), cb);
+	irq_work_queue(&chain->work);
+	dma_fence_put(f);
+}
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence)
+{
+	struct dma_fence_chain *head = to_dma_fence_chain(fence);
+
+	dma_fence_get(&head->base);
+	dma_fence_chain_for_each(fence, &head->base) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		dma_fence_get(f);
+		if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) {
+			dma_fence_put(fence);
+			return true;
+		}
+		dma_fence_put(f);
+	}
+	dma_fence_put(&head->base);
+	return false;
+}
+
+static bool dma_fence_chain_signaled(struct dma_fence *fence)
+{
+	dma_fence_chain_for_each(fence, fence) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		if (!dma_fence_is_signaled(f)) {
+			dma_fence_put(fence);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void dma_fence_chain_release(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+
+	dma_fence_put(chain->prev);
+	dma_fence_put(chain->fence);
+	dma_fence_free(fence);
+}
+
+const struct dma_fence_ops dma_fence_chain_ops = {
+	.get_driver_name = dma_fence_chain_get_driver_name,
+	.get_timeline_name = dma_fence_chain_get_timeline_name,
+	.enable_signaling = dma_fence_chain_enable_signaling,
+	.signaled = dma_fence_chain_signaled,
+	.release = dma_fence_chain_release,
+};
+EXPORT_SYMBOL(dma_fence_chain_ops);
+
+/**
+ * dma_fence_chain_init - initialize a fence chain
+ * @chain: the chain node to initialize
+ * @prev: the previous fence
+ * @fence: the current fence
+ *
+ * Initialize a new chain node and either start a new chain or add the node to
+ * the existing chain of the previous fence.
+ */
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno)
+{
+	struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev);
+	uint64_t context;
+
+	spin_lock_init(&chain->lock);
+	chain->prev = prev;
+	chain->fence = fence;
+	chain->prev_seqno = 0;
+	init_irq_work(&chain->work, dma_fence_chain_irq_work);
+
+	/* Try to reuse the context of the previous chain node. */
+	if (prev_chain && __dma_fence_is_later(seqno, prev->seqno)) {
+		context = prev->context;
+		chain->prev_seqno = prev->seqno;
+	} else {
+		context = dma_fence_context_alloc(1);
+		/* Make sure that we always have a valid sequence number. */
+		if (prev_chain)
+			seqno = max(prev->seqno, seqno);
+	}
+
+	dma_fence_init(&chain->base, &dma_fence_chain_ops,
+		       &chain->lock, context, seqno);
+}
+EXPORT_SYMBOL(dma_fence_chain_init);
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
new file mode 100644
index 000000000000..934a442db8ac
--- /dev/null
+++ b/include/linux/dma-fence-chain.h
@@ -0,0 +1,81 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_DMA_FENCE_CHAIN_H
+#define __LINUX_DMA_FENCE_CHAIN_H
+
+#include <linux/dma-fence.h>
+#include <linux/irq_work.h>
+
+/**
+ * struct dma_fence_chain - fence to represent an node of a fence chain
+ * @base: fence base class
+ * @lock: spinlock for fence handling
+ * @prev: previous fence of the chain
+ * @prev_seqno: original previous seqno before garbage collection
+ * @fence: encapsulated fence
+ * @cb: callback structure for signaling
+ * @work: irq work item for signaling
+ */
+struct dma_fence_chain {
+	struct dma_fence base;
+	spinlock_t lock;
+	struct dma_fence __rcu *prev;
+	u64 prev_seqno;
+	struct dma_fence *fence;
+	struct dma_fence_cb cb;
+	struct irq_work work;
+};
+
+extern const struct dma_fence_ops dma_fence_chain_ops;
+
+/**
+ * to_dma_fence_chain - cast a fence to a dma_fence_chain
+ * @fence: fence to cast to a dma_fence_array
+ *
+ * Returns NULL if the fence is not a dma_fence_chain,
+ * or the dma_fence_chain otherwise.
+ */
+static inline struct dma_fence_chain *
+to_dma_fence_chain(struct dma_fence *fence)
+{
+	if (!fence || fence->ops != &dma_fence_chain_ops)
+		return NULL;
+
+	return container_of(fence, struct dma_fence_chain, base);
+}
+
+/**
+ * dma_fence_chain_for_each - iterate over all fences in chain
+ * @iter: current fence
+ * @head: starting point
+ *
+ * Iterate over all fences in the chain. We keep a reference to the current
+ * fence while inside the loop which must be dropped when breaking out.
+ */
+#define dma_fence_chain_for_each(iter, head)	\
+	for (iter = dma_fence_get(head); iter; \
+	     iter = dma_fence_chain_walk(iter))
+
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence);
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno);
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno);
+
+#endif /* __LINUX_DMA_FENCE_CHAIN_H */
-- 
2.17.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

^ permalink raw reply related	[flat|nested] 16+ messages in thread
* [PATCH 1/9] dma-buf: add new dma_fence_chain container v7
@ 2019-03-25  8:32 Chunming Zhou
  2019-03-25  8:32 ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Chunming Zhou
  0 siblings, 1 reply; 16+ messages in thread
From: Chunming Zhou @ 2019-03-25  8:32 UTC (permalink / raw)
  To: dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	lionel.g.landwerlin-ral2JQCrhuEAvxtiuMwx3w,
	jason-fQELhIk9awXprZlt/sZkLg, Christian.Koenig-5C7GfCeVMHo,
	Tobias.Hector-5C7GfCeVMHo
  Cc: Christian König, Christian König

From: Christian König <ckoenig.leichtzumerken@gmail.com>

Lockless container implementation similar to a dma_fence_array, but with
only two elements per node and automatic garbage collection.

v2: properly document dma_fence_chain_for_each, add dma_fence_chain_find_seqno,
    drop prev reference during garbage collection if it's not a chain fence.
v3: use head and iterator for dma_fence_chain_for_each
v4: fix reference count in dma_fence_chain_enable_signaling
v5: fix iteration when walking each chain node
v6: add __rcu for member 'prev' of struct chain node
v7: fix rcu warnings from kernel robot

Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
---
 drivers/dma-buf/Makefile          |   3 +-
 drivers/dma-buf/dma-fence-chain.c | 241 ++++++++++++++++++++++++++++++
 include/linux/dma-fence-chain.h   |  81 ++++++++++
 3 files changed, 324 insertions(+), 1 deletion(-)
 create mode 100644 drivers/dma-buf/dma-fence-chain.c
 create mode 100644 include/linux/dma-fence-chain.h

diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 0913a6ccab5a..1f006e083eb9 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,4 +1,5 @@
-obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o
+obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
+	 reservation.o seqno-fence.o
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c
new file mode 100644
index 000000000000..c729f98a7bd3
--- /dev/null
+++ b/drivers/dma-buf/dma-fence-chain.c
@@ -0,0 +1,241 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/dma-fence-chain.h>
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence);
+
+/**
+ * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence
+ * @chain: chain node to get the previous node from
+ *
+ * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the
+ * chain node.
+ */
+static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain)
+{
+	struct dma_fence *prev;
+
+	rcu_read_lock();
+	prev = dma_fence_get_rcu_safe(&chain->prev);
+	rcu_read_unlock();
+	return prev;
+}
+
+/**
+ * dma_fence_chain_walk - chain walking function
+ * @fence: current chain node
+ *
+ * Walk the chain to the next node. Returns the next fence or NULL if we are at
+ * the end of the chain. Garbage collects chain nodes which are already
+ * signaled.
+ */
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain, *prev_chain;
+	struct dma_fence *prev, *replacement, *tmp;
+
+	chain = to_dma_fence_chain(fence);
+	if (!chain) {
+		dma_fence_put(fence);
+		return NULL;
+	}
+
+	while ((prev = dma_fence_chain_get_prev(chain))) {
+
+		prev_chain = to_dma_fence_chain(prev);
+		if (prev_chain) {
+			if (!dma_fence_is_signaled(prev_chain->fence))
+				break;
+
+			replacement = dma_fence_chain_get_prev(prev_chain);
+		} else {
+			if (!dma_fence_is_signaled(prev))
+				break;
+
+			replacement = NULL;
+		}
+
+		tmp = cmpxchg((void **)&chain->prev, (void *)prev, (void *)replacement);
+		if (tmp == prev)
+			dma_fence_put(tmp);
+		else
+			dma_fence_put(replacement);
+		dma_fence_put(prev);
+	}
+
+	dma_fence_put(fence);
+	return prev;
+}
+EXPORT_SYMBOL(dma_fence_chain_walk);
+
+/**
+ * dma_fence_chain_find_seqno - find fence chain node by seqno
+ * @pfence: pointer to the chain node where to start
+ * @seqno: the sequence number to search for
+ *
+ * Advance the fence pointer to the chain node which will signal this sequence
+ * number. If no sequence number is provided then this is a no-op.
+ *
+ * Returns EINVAL if the fence is not a chain node or the sequence number has
+ * not yet advanced far enough.
+ */
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno)
+{
+	struct dma_fence_chain *chain;
+
+	if (!seqno)
+		return 0;
+
+	chain = to_dma_fence_chain(*pfence);
+	if (!chain || chain->base.seqno < seqno)
+		return -EINVAL;
+
+	dma_fence_chain_for_each(*pfence, &chain->base) {
+		if ((*pfence)->context != chain->base.context ||
+		    to_dma_fence_chain(*pfence)->prev_seqno < seqno)
+			break;
+	}
+	dma_fence_put(&chain->base);
+
+	return 0;
+}
+EXPORT_SYMBOL(dma_fence_chain_find_seqno);
+
+static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence)
+{
+        return "dma_fence_chain";
+}
+
+static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence)
+{
+        return "unbound";
+}
+
+static void dma_fence_chain_irq_work(struct irq_work *work)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(work, typeof(*chain), work);
+
+	/* Try to rearm the callback */
+	if (!dma_fence_chain_enable_signaling(&chain->base))
+		/* Ok, we are done. No more unsignaled fences left */
+		dma_fence_signal(&chain->base);
+	dma_fence_put(&chain->base);
+}
+
+static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	struct dma_fence_chain *chain;
+
+	chain = container_of(cb, typeof(*chain), cb);
+	irq_work_queue(&chain->work);
+	dma_fence_put(f);
+}
+
+static bool dma_fence_chain_enable_signaling(struct dma_fence *fence)
+{
+	struct dma_fence_chain *head = to_dma_fence_chain(fence);
+
+	dma_fence_get(&head->base);
+	dma_fence_chain_for_each(fence, &head->base) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		dma_fence_get(f);
+		if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) {
+			dma_fence_put(fence);
+			return true;
+		}
+		dma_fence_put(f);
+	}
+	dma_fence_put(&head->base);
+	return false;
+}
+
+static bool dma_fence_chain_signaled(struct dma_fence *fence)
+{
+	dma_fence_chain_for_each(fence, fence) {
+		struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+		struct dma_fence *f = chain ? chain->fence : fence;
+
+		if (!dma_fence_is_signaled(f)) {
+			dma_fence_put(fence);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void dma_fence_chain_release(struct dma_fence *fence)
+{
+	struct dma_fence_chain *chain = to_dma_fence_chain(fence);
+
+	dma_fence_put(rcu_dereference_protected(chain->prev, true));
+	dma_fence_put(chain->fence);
+	dma_fence_free(fence);
+}
+
+const struct dma_fence_ops dma_fence_chain_ops = {
+	.get_driver_name = dma_fence_chain_get_driver_name,
+	.get_timeline_name = dma_fence_chain_get_timeline_name,
+	.enable_signaling = dma_fence_chain_enable_signaling,
+	.signaled = dma_fence_chain_signaled,
+	.release = dma_fence_chain_release,
+};
+EXPORT_SYMBOL(dma_fence_chain_ops);
+
+/**
+ * dma_fence_chain_init - initialize a fence chain
+ * @chain: the chain node to initialize
+ * @prev: the previous fence
+ * @fence: the current fence
+ *
+ * Initialize a new chain node and either start a new chain or add the node to
+ * the existing chain of the previous fence.
+ */
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno)
+{
+	struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev);
+	uint64_t context;
+
+	spin_lock_init(&chain->lock);
+	rcu_assign_pointer(chain->prev, prev);
+	chain->fence = fence;
+	chain->prev_seqno = 0;
+	init_irq_work(&chain->work, dma_fence_chain_irq_work);
+
+	/* Try to reuse the context of the previous chain node. */
+	if (prev_chain && __dma_fence_is_later(seqno, prev->seqno)) {
+		context = prev->context;
+		chain->prev_seqno = prev->seqno;
+	} else {
+		context = dma_fence_context_alloc(1);
+		/* Make sure that we always have a valid sequence number. */
+		if (prev_chain)
+			seqno = max(prev->seqno, seqno);
+	}
+
+	dma_fence_init(&chain->base, &dma_fence_chain_ops,
+		       &chain->lock, context, seqno);
+}
+EXPORT_SYMBOL(dma_fence_chain_init);
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
new file mode 100644
index 000000000000..934a442db8ac
--- /dev/null
+++ b/include/linux/dma-fence-chain.h
@@ -0,0 +1,81 @@
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2018 Advanced Micro Devices, Inc.
+ * Authors:
+ *	Christian König <christian.koenig@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef __LINUX_DMA_FENCE_CHAIN_H
+#define __LINUX_DMA_FENCE_CHAIN_H
+
+#include <linux/dma-fence.h>
+#include <linux/irq_work.h>
+
+/**
+ * struct dma_fence_chain - fence to represent an node of a fence chain
+ * @base: fence base class
+ * @lock: spinlock for fence handling
+ * @prev: previous fence of the chain
+ * @prev_seqno: original previous seqno before garbage collection
+ * @fence: encapsulated fence
+ * @cb: callback structure for signaling
+ * @work: irq work item for signaling
+ */
+struct dma_fence_chain {
+	struct dma_fence base;
+	spinlock_t lock;
+	struct dma_fence __rcu *prev;
+	u64 prev_seqno;
+	struct dma_fence *fence;
+	struct dma_fence_cb cb;
+	struct irq_work work;
+};
+
+extern const struct dma_fence_ops dma_fence_chain_ops;
+
+/**
+ * to_dma_fence_chain - cast a fence to a dma_fence_chain
+ * @fence: fence to cast to a dma_fence_array
+ *
+ * Returns NULL if the fence is not a dma_fence_chain,
+ * or the dma_fence_chain otherwise.
+ */
+static inline struct dma_fence_chain *
+to_dma_fence_chain(struct dma_fence *fence)
+{
+	if (!fence || fence->ops != &dma_fence_chain_ops)
+		return NULL;
+
+	return container_of(fence, struct dma_fence_chain, base);
+}
+
+/**
+ * dma_fence_chain_for_each - iterate over all fences in chain
+ * @iter: current fence
+ * @head: starting point
+ *
+ * Iterate over all fences in the chain. We keep a reference to the current
+ * fence while inside the loop which must be dropped when breaking out.
+ */
+#define dma_fence_chain_for_each(iter, head)	\
+	for (iter = dma_fence_get(head); iter; \
+	     iter = dma_fence_chain_walk(iter))
+
+struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence);
+int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno);
+void dma_fence_chain_init(struct dma_fence_chain *chain,
+			  struct dma_fence *prev,
+			  struct dma_fence *fence,
+			  uint64_t seqno);
+
+#endif /* __LINUX_DMA_FENCE_CHAIN_H */
-- 
2.17.1

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

^ permalink raw reply related	[flat|nested] 16+ messages in thread
* [PATCH 0/9] *** timeline syncobj support ***
@ 2019-04-01  9:50 Chunming Zhou
       [not found] ` <20190401095103.9592-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
  0 siblings, 1 reply; 16+ messages in thread
From: Chunming Zhou @ 2019-04-01  9:50 UTC (permalink / raw)
  To: dri-devel-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW,
	lionel.g.landwerlin-ral2JQCrhuEAvxtiuMwx3w,
	jason-fQELhIk9awXprZlt/sZkLg, Christian.Koenig-5C7GfCeVMHo,
	Tobias.Hector-5C7GfCeVMHo
  Cc: Chunming Zhou

timeline syncobj gives user more flexibility and convenience to do sychronization.
Lionel has written cts and adapted ANV based on this patch set, and also reviewed
the patch set.
please someone from community helps to submit the patch set to drm-misc-next.

Christian König (3):
  dma-buf: add new dma_fence_chain container v7
  drm/syncobj: add new drm_syncobj_add_point interface v4
  drm/syncobj: use the timeline point in drm_syncobj_find_fence v4

Chunming Zhou (6):
  drm/syncobj: add support for timeline point wait v8
  drm/syncobj: add timeline payload query ioctl v6
  drm/amdgpu: add timeline support in amdgpu CS v3
  drm/syncobj: add transition iotcls between binary and timeline v2
  drm/syncobj: add timeline signal ioctl for syncobj v5
  drm/amdgpu: update version for timeline syncobj support in amdgpu

 drivers/dma-buf/Makefile                |   3 +-
 drivers/dma-buf/dma-fence-chain.c       | 241 +++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     |  10 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  | 152 ++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c |   3 +-
 drivers/gpu/drm/drm_internal.h          |   8 +
 drivers/gpu/drm/drm_ioctl.c             |   8 +
 drivers/gpu/drm/drm_syncobj.c           | 446 ++++++++++++++++++++++--
 include/drm/drm_syncobj.h               |   5 +
 include/linux/dma-fence-chain.h         |  81 +++++
 include/uapi/drm/amdgpu_drm.h           |   8 +
 include/uapi/drm/drm.h                  |  36 ++
 12 files changed, 944 insertions(+), 57 deletions(-)
 create mode 100644 drivers/dma-buf/dma-fence-chain.c
 create mode 100644 include/linux/dma-fence-chain.h

-- 
2.17.1

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

^ permalink raw reply	[flat|nested] 16+ messages in thread
end of thread, other threads:[~2019-04-01  9:51 UTC | newest]

Thread overview: 16+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-12-05 13:08 [PATCH 1/9] dma-buf: make fence sequence numbers 64 bit v2 Christian König
2018-12-05 13:08 ` [PATCH 6/9] drm/syncobj: add timeline payload query ioctl v4 Christian König
     [not found] ` <20181205130835.1595-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2018-12-05 13:08   ` [PATCH 2/9] dma-buf: add new dma_fence_chain container v3 Christian König
2018-12-05 13:08   ` [PATCH 3/9] drm/syncobj: remove drm_syncobj_cb and cleanup Christian König
2018-12-05 13:08   ` [PATCH 4/9] drm/syncobj: add new drm_syncobj_add_point interface v2 Christian König
2018-12-05 13:08   ` [PATCH 5/9] drm/syncobj: add support for timeline point wait v8 Christian König
2018-12-05 13:08   ` [PATCH 7/9] drm/syncobj: use the timeline point in drm_syncobj_find_fence v3 Christian König
2018-12-05 13:08   ` [PATCH 8/9] drm/amdgpu: add timeline support in amdgpu CS v2 Christian König
2018-12-05 13:08   ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Christian König
2018-12-05 13:09   ` [PATCH 1/9] dma-buf: make fence sequence numbers 64 bit v2 Christian König
2018-12-06  9:37 Christian König
2018-12-06  9:37 ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Christian König
2019-03-12  3:10 [PATCH 1/9] dma-buf: add new dma_fence_chain container v5 Chunming Zhou
     [not found] ` <20190312031049.23647-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2019-03-12  3:10   ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Chunming Zhou
2019-03-15 12:09 [PATCH 1/9] dma-buf: add new dma_fence_chain container v5 Chunming Zhou
     [not found] ` <20190315120959.25489-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2019-03-15 12:09   ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Chunming Zhou
2019-03-20  5:47 [PATCH 1/9] dma-buf: add new dma_fence_chain container v6 Chunming Zhou
     [not found] ` <20190320054724.14636-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2019-03-20  5:47   ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Chunming Zhou
2019-03-25  8:32 [PATCH 1/9] dma-buf: add new dma_fence_chain container v7 Chunming Zhou
2019-03-25  8:32 ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Chunming Zhou
2019-04-01  9:50 [PATCH 0/9] *** timeline syncobj support *** Chunming Zhou
     [not found] ` <20190401095103.9592-1-david1.zhou-5C7GfCeVMHo@public.gmane.org>
2019-04-01  9:51   ` [PATCH 9/9] drm/amdgpu: update version for timeline syncobj support in amdgpu Chunming Zhou

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).