[PATCH 01/37] drm/i915: Record the position of the start of the request

[PATCH 01/37] drm/i915: Record the position of the start of the request

[Chris Wilson]

Not only does it make for good documentation and debugging aide, but it is
also vital for when we want to unwind requests - such as when throwing away
an incomplete request.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1470414607-32453-2-git-send-email-arun.siluvery@linux.intel.com
---
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem_request.c | 13 +++++++++----
 drivers/gpu/drm/i915/i915_gpu_error.c   |  6 ++++--
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7971c76852df..1eda64d5100f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -557,6 +557,7 @@ struct drm_i915_error_state {
 		struct drm_i915_error_request {
 			long jiffies;
 			u32 seqno;
+			u32 head;
 			u32 tail;
 		} *requests;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index b764c1d440c8..8a9e9bfeea09 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -426,6 +426,13 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 	if (ret)
 		goto err_ctx;
 
+	/* Record the position of the start of the request so that
+	 * should we detect the updated seqno part-way through the
+	 * GPU processing the request, we never over-estimate the
+	 * position of the head.
+	 */
+	req->head = req->ring->tail;
+
 	return req;
 
 err_ctx:
@@ -500,8 +507,6 @@ void __i915_add_request(struct drm_i915_gem_request *request, bool flush_caches)
 
 	trace_i915_gem_request_add(request);
 
-	request->head = request_start;
-
 	/* Seal the request and mark it as pending execution. Note that
 	 * we may inspect this state, without holding any locks, during
 	 * hangcheck. Hence we apply the barrier to ensure that we do not
@@ -514,10 +519,10 @@ void __i915_add_request(struct drm_i915_gem_request *request, bool flush_caches)
 	list_add_tail(&request->link, &engine->request_list);
 	list_add_tail(&request->ring_link, &ring->request_list);
 
-	/* Record the position of the start of the request so that
+	/* Record the position of the start of the breadcrumb so that
 	 * should we detect the updated seqno part-way through the
 	 * GPU processing the request, we never over-estimate the
-	 * position of the head.
+	 * position of the ring's HEAD.
 	 */
 	request->postfix = ring->tail;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index eecb87063c88..c9e1246ecd36 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -455,9 +455,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				   dev_priv->engine[i].name,
 				   ee->num_requests);
 			for (j = 0; j < ee->num_requests; j++) {
-				err_printf(m, "  seqno 0x%08x, emitted %ld, tail 0x%08x\n",
+				err_printf(m, "  seqno 0x%08x, emitted %ld, head 0x%08x tail 0x%08x\n",
 					   ee->requests[j].seqno,
 					   ee->requests[j].jiffies,
+					   ee->requests[j].head,
 					   ee->requests[j].tail);
 			}
 		}
@@ -1205,7 +1206,8 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			erq = &ee->requests[count++];
 			erq->seqno = request->fence.seqno;
 			erq->jiffies = request->emitted_jiffies;
-			erq->tail = request->postfix;
+			erq->head = request->head;
+			erq->tail = request->tail;
 		}
 	}
 }
-- 
2.8.1

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

[PATCH 02/37] drm/i915: Reduce amount of duplicate buffer information captured on error

[Chris Wilson]

When capturing the error state, we do not need to know about every
address space - just those that are related to the error. We know which
context is active at the time, therefore we know which VM are implicated
in the error. We can then restrict the VM which we report to the
relevant subset.

v2: s/i/count_active/ (and similar)
    Rewrite label generation for "Buffers"

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h       |   9 +-
 drivers/gpu/drm/i915/i915_gpu_error.c | 224 +++++++++++++++-------------------
 2 files changed, 105 insertions(+), 128 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1eda64d5100f..2bb4d568667b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -517,6 +517,7 @@ struct drm_i915_error_state {
 		int num_waiters;
 		int hangcheck_score;
 		enum intel_engine_hangcheck_action hangcheck_action;
+		struct i915_address_space *vm;
 		int num_requests;
 
 		/* our own tracking of ring head and tail */
@@ -587,17 +588,15 @@ struct drm_i915_error_state {
 		u32 read_domains;
 		u32 write_domain;
 		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
-		s32 pinned:2;
 		u32 tiling:2;
 		u32 dirty:1;
 		u32 purgeable:1;
 		u32 userptr:1;
 		s32 engine:4;
 		u32 cache_level:3;
-	} **active_bo, **pinned_bo;
-
-	u32 *active_bo_count, *pinned_bo_count;
-	u32 vm_count;
+	} *active_bo[I915_NUM_ENGINES], *pinned_bo;
+	u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count;
+	struct i915_address_space *active_vm[I915_NUM_ENGINES];
 };
 
 struct intel_connector;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index c9e1246ecd36..17681fa3b7d4 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -42,16 +42,6 @@ static const char *engine_str(int engine)
 	}
 }
 
-static const char *pin_flag(int pinned)
-{
-	if (pinned > 0)
-		return " P";
-	else if (pinned < 0)
-		return " p";
-	else
-		return "";
-}
-
 static const char *tiling_flag(int tiling)
 {
 	switch (tiling) {
@@ -189,7 +179,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 {
 	int i;
 
-	err_printf(m, "  %s [%d]:\n", name, count);
+	err_printf(m, "%s [%d]:\n", name, count);
 
 	while (count--) {
 		err_printf(m, "    %08x_%08x %8u %02x %02x [ ",
@@ -202,7 +192,6 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 			err_printf(m, "%02x ", err->rseqno[i]);
 
 		err_printf(m, "] %02x", err->wseqno);
-		err_puts(m, pin_flag(err->pinned));
 		err_puts(m, tiling_flag(err->tiling));
 		err_puts(m, dirty_flag(err->dirty));
 		err_puts(m, purgeable_flag(err->purgeable));
@@ -414,18 +403,33 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			error_print_engine(m, &error->engine[i]);
 	}
 
-	for (i = 0; i < error->vm_count; i++) {
-		err_printf(m, "vm[%d]\n", i);
+	for (i = 0; i < ARRAY_SIZE(error->active_vm); i++) {
+		char buf[128];
+		int len, first = 1;
 
-		print_error_buffers(m, "Active",
+		if (!error->active_vm[i])
+			break;
+
+		len = scnprintf(buf, sizeof(buf), "Active[%d] (", i);
+		for (j = 0; j < ARRAY_SIZE(error->engine); j++) {
+			if (error->engine[j].vm != error->active_vm[i])
+				continue;
+
+			len += scnprintf(buf + len, sizeof(buf), "%s%s",
+					 first ? "" : ", ",
+					 dev_priv->engine[j].name);
+			first = 0;
+		}
+		scnprintf(buf + len, sizeof(buf), ")");
+		print_error_buffers(m, buf,
 				    error->active_bo[i],
 				    error->active_bo_count[i]);
-
-		print_error_buffers(m, "Pinned",
-				    error->pinned_bo[i],
-				    error->pinned_bo_count[i]);
 	}
 
+	print_error_buffers(m, "Pinned (global)",
+			    error->pinned_bo,
+			    error->pinned_bo_count);
+
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		struct drm_i915_error_engine *ee = &error->engine[i];
 
@@ -627,13 +631,10 @@ static void i915_error_state_free(struct kref *error_ref)
 
 	i915_error_object_free(error->semaphore_obj);
 
-	for (i = 0; i < error->vm_count; i++)
+	for (i = 0; i < ARRAY_SIZE(error->active_bo); i++)
 		kfree(error->active_bo[i]);
-
-	kfree(error->active_bo);
-	kfree(error->active_bo_count);
 	kfree(error->pinned_bo);
-	kfree(error->pinned_bo_count);
+
 	kfree(error->overlay);
 	kfree(error->display);
 	kfree(error);
@@ -779,9 +780,6 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 	err->read_domains = obj->base.read_domains;
 	err->write_domain = obj->base.write_domain;
 	err->fence_reg = obj->fence_reg;
-	err->pinned = 0;
-	if (i915_gem_obj_is_pinned(obj))
-		err->pinned = 1;
 	err->tiling = i915_gem_object_get_tiling(obj);
 	err->dirty = obj->dirty;
 	err->purgeable = obj->madv != I915_MADV_WILLNEED;
@@ -789,13 +787,17 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 	err->cache_level = obj->cache_level;
 }
 
-static u32 capture_active_bo(struct drm_i915_error_buffer *err,
-			     int count, struct list_head *head)
+static u32 capture_error_bo(struct drm_i915_error_buffer *err,
+			    int count, struct list_head *head,
+			    bool pinned_only)
 {
 	struct i915_vma *vma;
 	int i = 0;
 
 	list_for_each_entry(vma, head, vm_link) {
+		if (pinned_only && !i915_vma_is_pinned(vma))
+			continue;
+
 		capture_bo(err++, vma);
 		if (++i == count)
 			break;
@@ -804,28 +806,6 @@ static u32 capture_active_bo(struct drm_i915_error_buffer *err,
 	return i;
 }
 
-static u32 capture_pinned_bo(struct drm_i915_error_buffer *err,
-			     int count, struct list_head *head,
-			     struct i915_address_space *vm)
-{
-	struct drm_i915_gem_object *obj;
-	struct drm_i915_error_buffer * const first = err;
-	struct drm_i915_error_buffer * const last = err + count;
-
-	list_for_each_entry(obj, head, global_list) {
-		struct i915_vma *vma;
-
-		if (err == last)
-			break;
-
-		list_for_each_entry(vma, &obj->vma_list, obj_link)
-			if (vma->vm == vm && i915_vma_is_pinned(vma))
-				capture_bo(err++, vma);
-	}
-
-	return err - first;
-}
-
 /* Generate a semi-unique error code. The code is not meant to have meaning, The
  * code's only purpose is to try to prevent false duplicated bug reports by
  * grossly estimating a GPU error state.
@@ -1063,7 +1043,6 @@ static void error_record_engine_registers(struct drm_i915_error_state *error,
 	}
 }
 
-
 static void i915_gem_record_active_context(struct intel_engine_cs *engine,
 					   struct drm_i915_error_state *error,
 					   struct drm_i915_error_engine *ee)
@@ -1116,10 +1095,9 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 
 		request = i915_gem_find_active_request(engine);
 		if (request) {
-			struct i915_address_space *vm;
 			struct intel_ring *ring;
 
-			vm = request->ctx->ppgtt ?
+			ee->vm = request->ctx->ppgtt ?
 				&request->ctx->ppgtt->base : &ggtt->base;
 
 			/* We need to copy these to an anonymous buffer
@@ -1129,7 +1107,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			ee->batchbuffer =
 				i915_error_object_create(dev_priv,
 							 request->batch_obj,
-							 vm);
+							 ee->vm);
 
 			if (HAS_BROKEN_CS_TLB(dev_priv))
 				ee->wa_batchbuffer =
@@ -1212,89 +1190,88 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 	}
 }
 
-/* FIXME: Since pin count/bound list is global, we duplicate what we capture per
- * VM.
- */
 static void i915_gem_capture_vm(struct drm_i915_private *dev_priv,
 				struct drm_i915_error_state *error,
 				struct i915_address_space *vm,
-				const int ndx)
+				int idx)
 {
-	struct drm_i915_error_buffer *active_bo = NULL, *pinned_bo = NULL;
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_error_buffer *active_bo;
 	struct i915_vma *vma;
-	int i;
+	int count;
 
-	i = 0;
+	count = 0;
 	list_for_each_entry(vma, &vm->active_list, vm_link)
-		i++;
-	error->active_bo_count[ndx] = i;
-
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		list_for_each_entry(vma, &obj->vma_list, obj_link)
-			if (vma->vm == vm && i915_vma_is_pinned(vma))
-				i++;
-	}
-	error->pinned_bo_count[ndx] = i - error->active_bo_count[ndx];
-
-	if (i) {
-		active_bo = kcalloc(i, sizeof(*active_bo), GFP_ATOMIC);
-		if (active_bo)
-			pinned_bo = active_bo + error->active_bo_count[ndx];
-	}
+		count++;
 
+	active_bo = NULL;
+	if (count)
+		active_bo = kcalloc(count, sizeof(*active_bo), GFP_ATOMIC);
 	if (active_bo)
-		error->active_bo_count[ndx] =
-			capture_active_bo(active_bo,
-					  error->active_bo_count[ndx],
-					  &vm->active_list);
-
-	if (pinned_bo)
-		error->pinned_bo_count[ndx] =
-			capture_pinned_bo(pinned_bo,
-					  error->pinned_bo_count[ndx],
-					  &dev_priv->mm.bound_list, vm);
-	error->active_bo[ndx] = active_bo;
-	error->pinned_bo[ndx] = pinned_bo;
+		count = capture_error_bo(active_bo, count, &vm->active_list, false);
+	else
+		count = 0;
+
+	error->active_vm[idx] = vm;
+	error->active_bo[idx] = active_bo;
+	error->active_bo_count[idx] = count;
 }
 
-static void i915_gem_capture_buffers(struct drm_i915_private *dev_priv,
-				     struct drm_i915_error_state *error)
+static void i915_capture_active_buffers(struct drm_i915_private *dev_priv,
+					struct drm_i915_error_state *error)
 {
-	struct i915_address_space *vm;
-	int cnt = 0, i = 0;
-
-	list_for_each_entry(vm, &dev_priv->vm_list, global_link)
-		cnt++;
-
-	error->active_bo = kcalloc(cnt, sizeof(*error->active_bo), GFP_ATOMIC);
-	error->pinned_bo = kcalloc(cnt, sizeof(*error->pinned_bo), GFP_ATOMIC);
-	error->active_bo_count = kcalloc(cnt, sizeof(*error->active_bo_count),
-					 GFP_ATOMIC);
-	error->pinned_bo_count = kcalloc(cnt, sizeof(*error->pinned_bo_count),
-					 GFP_ATOMIC);
-
-	if (error->active_bo == NULL ||
-	    error->pinned_bo == NULL ||
-	    error->active_bo_count == NULL ||
-	    error->pinned_bo_count == NULL) {
-		kfree(error->active_bo);
-		kfree(error->active_bo_count);
-		kfree(error->pinned_bo);
-		kfree(error->pinned_bo_count);
-
-		error->active_bo = NULL;
-		error->active_bo_count = NULL;
-		error->pinned_bo = NULL;
-		error->pinned_bo_count = NULL;
-	} else {
-		list_for_each_entry(vm, &dev_priv->vm_list, global_link)
-			i915_gem_capture_vm(dev_priv, error, vm, i++);
+	int cnt = 0, i, j;
+
+	BUILD_BUG_ON(ARRAY_SIZE(error->engine) > ARRAY_SIZE(error->active_bo));
+	BUILD_BUG_ON(ARRAY_SIZE(error->active_bo) != ARRAY_SIZE(error->active_vm));
+	BUILD_BUG_ON(ARRAY_SIZE(error->active_bo) != ARRAY_SIZE(error->active_bo_count));
+
+	/* Scan each engine looking for unique active contexts/vm */
+	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
+		struct drm_i915_error_engine *ee = &error->engine[i];
+		bool found;
+
+		if (!ee->vm)
+			continue;
 
-		error->vm_count = cnt;
+		found = false;
+		for (j = 0; j < i && !found; j++)
+			found = error->engine[j].vm == ee->vm;
+		if (!found)
+			i915_gem_capture_vm(dev_priv, error, ee->vm, cnt++);
 	}
 }
 
+static void i915_capture_pinned_buffers(struct drm_i915_private *dev_priv,
+					struct drm_i915_error_state *error)
+{
+	struct i915_address_space *vm = &dev_priv->ggtt.base;
+	struct drm_i915_error_buffer *bo;
+	struct i915_vma *vma;
+	int count_inactive, count_active;
+
+	count_inactive = 0;
+	list_for_each_entry(vma, &vm->active_list, vm_link)
+		count_inactive++;
+
+	count_active = 0;
+	list_for_each_entry(vma, &vm->inactive_list, vm_link)
+		count_active++;
+
+	bo = NULL;
+	if (count_inactive + count_active)
+		bo = kcalloc(count_inactive + count_active,
+			     sizeof(*bo), GFP_ATOMIC);
+	if (!bo)
+		return;
+
+	count_inactive = capture_error_bo(bo, count_inactive,
+					  &vm->active_list, true);
+	count_active = capture_error_bo(bo + count_inactive, count_active,
+					&vm->inactive_list, true);
+	error->pinned_bo_count = count_inactive + count_active;
+	error->pinned_bo = bo;
+}
+
 /* Capture all registers which don't fit into another category. */
 static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 				   struct drm_i915_error_state *error)
@@ -1438,9 +1415,10 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
 
 	i915_capture_gen_state(dev_priv, error);
 	i915_capture_reg_state(dev_priv, error);
-	i915_gem_capture_buffers(dev_priv, error);
 	i915_gem_record_fences(dev_priv, error);
 	i915_gem_record_rings(dev_priv, error);
+	i915_capture_active_buffers(dev_priv, error);
+	i915_capture_pinned_buffers(dev_priv, error);
 
 	do_gettimeofday(&error->time);
 
-- 
2.8.1

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

[PATCH 03/37] drm/i915: Stop the machine whilst capturing the GPU crash dump

[Chris Wilson]

The error state is purposefully racy as we expect it to be called at any
time and so have avoided any locking whilst capturing the crash dump.
However, with multi-engine GPUs and multiple CPUs, those races can
manifest into OOPSes as we attempt to chase dangling pointers freed on
other CPUs. Under discussion are lots of ways to slow down normal
operation in order to protect the post-mortem error capture, but what it
we take the opposite approach and freeze the machine whilst the error
capture runs (note the GPU may still running, but as long as we don't
process any of the results the driver's bookkeeping will be static).

Note that by of itself, this is not a complete fix. It also depends on
the compiler barriers in list_add/list_del to prevent traversing the
lists into the void. We also depend that we only require state from
carefully controlled sources - i.e. all the state we require for
post-mortem debugging should be reachable from the request itself so
that we only have to worry about retrieving the request carefully. Once
we have the request, we know that all pointers from it are intact.

v2: Avoid drm_clflush_pages() inside stop_machine() as it may use
stop_machine() itself for its wbinvd fallback.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig          |  1 +
 drivers/gpu/drm/i915/i915_drv.h       |  2 ++
 drivers/gpu/drm/i915/i915_gpu_error.c | 46 +++++++++++++++++++++--------------
 3 files changed, 31 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 7769e469118f..7badcee88ebf 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -4,6 +4,7 @@ config DRM_I915
 	depends on X86 && PCI
 	select INTEL_GTT
 	select INTERVAL_TREE
+	select STOP_MACHINE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
 	select SHMEM
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2bb4d568667b..2664612bce3f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -481,6 +481,8 @@ struct drm_i915_error_state {
 	struct kref ref;
 	struct timeval time;
 
+	struct drm_i915_private *i915;
+
 	char error_msg[128];
 	bool simulated;
 	int iommu;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 17681fa3b7d4..89a82b10c032 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -28,6 +28,7 @@
  */
 
 #include <generated/utsrelease.h>
+#include <linux/stop_machine.h>
 #include "i915_drv.h"
 
 static const char *engine_str(int engine)
@@ -693,14 +694,12 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
 
 	dst->page_count = num_pages;
 	while (num_pages--) {
-		unsigned long flags;
 		void *d;
 
 		d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
 		if (d == NULL)
 			goto unwind;
 
-		local_irq_save(flags);
 		if (use_ggtt) {
 			void __iomem *s;
 
@@ -719,15 +718,10 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
 
 			page = i915_gem_object_get_page(src, i);
 
-			drm_clflush_pages(&page, 1);
-
 			s = kmap_atomic(page);
 			memcpy(d, s, PAGE_SIZE);
 			kunmap_atomic(s);
-
-			drm_clflush_pages(&page, 1);
 		}
-		local_irq_restore(flags);
 
 		dst->pages[i++] = d;
 		reloc_offset += PAGE_SIZE;
@@ -1384,6 +1378,31 @@ static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
 	error->suspend_count = dev_priv->suspend_count;
 }
 
+static int capture(void *data)
+{
+	struct drm_i915_error_state *error = data;
+
+	/* Ensure that what we readback from memory matches what the GPU sees */
+	wbinvd();
+
+	i915_capture_gen_state(error->i915, error);
+	i915_capture_reg_state(error->i915, error);
+	i915_gem_record_fences(error->i915, error);
+	i915_gem_record_rings(error->i915, error);
+	i915_capture_active_buffers(error->i915, error);
+	i915_capture_pinned_buffers(error->i915, error);
+
+	do_gettimeofday(&error->time);
+
+	error->overlay = intel_overlay_capture_error_state(error->i915);
+	error->display = intel_display_capture_error_state(error->i915);
+
+	/* And make sure we don't leave trash in the CPU cache */
+	wbinvd();
+
+	return 0;
+}
+
 /**
  * i915_capture_error_state - capture an error record for later analysis
  * @dev: drm device
@@ -1412,18 +1431,9 @@ void i915_capture_error_state(struct drm_i915_private *dev_priv,
 	}
 
 	kref_init(&error->ref);
+	error->i915 = dev_priv;
 
-	i915_capture_gen_state(dev_priv, error);
-	i915_capture_reg_state(dev_priv, error);
-	i915_gem_record_fences(dev_priv, error);
-	i915_gem_record_rings(dev_priv, error);
-	i915_capture_active_buffers(dev_priv, error);
-	i915_capture_pinned_buffers(dev_priv, error);
-
-	do_gettimeofday(&error->time);
-
-	error->overlay = intel_overlay_capture_error_state(dev_priv);
-	error->display = intel_display_capture_error_state(dev_priv);
+	stop_machine(capture, error, NULL);
 
 	i915_error_capture_msg(dev_priv, error, engine_mask, error_msg);
 	DRM_INFO("%s\n", error->error_msg);
-- 
2.8.1

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

[PATCH 04/37] drm/i915: Store the active context object on all engines upon error

[Chris Wilson]

With execlists, we have context objects everywhere, not just RCS. So
store them for post-mortem debugging. This also has a secondary effect
of removing one more unsafe list iteration with using preserved state
from the hanging request. And now we can cross-reference the request's
context state with that loaded by the GPU.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 28 ++++------------------------
 1 file changed, 4 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 89a82b10c032..983488da742a 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1037,28 +1037,6 @@ static void error_record_engine_registers(struct drm_i915_error_state *error,
 	}
 }
 
-static void i915_gem_record_active_context(struct intel_engine_cs *engine,
-					   struct drm_i915_error_state *error,
-					   struct drm_i915_error_engine *ee)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	struct drm_i915_gem_object *obj;
-
-	/* Currently render ring is the only HW context user */
-	if (engine->id != RCS || !error->ccid)
-		return;
-
-	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (!i915_gem_obj_ggtt_bound(obj))
-			continue;
-
-		if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) {
-			ee->ctx = i915_error_ggtt_object_create(dev_priv, obj);
-			break;
-		}
-	}
-}
-
 static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 				  struct drm_i915_error_state *error)
 {
@@ -1108,6 +1086,10 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 					i915_error_ggtt_object_create(dev_priv,
 								      engine->scratch.obj);
 
+			ee->ctx =
+				i915_error_ggtt_object_create(dev_priv,
+							      request->ctx->engine[i].state);
+
 			if (request->pid) {
 				struct task_struct *task;
 
@@ -1138,8 +1120,6 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 		ee->wa_ctx = i915_error_ggtt_object_create(dev_priv,
 							   engine->wa_ctx.obj);
 
-		i915_gem_record_active_context(engine, error, ee);
-
 		count = 0;
 		list_for_each_entry(request, &engine->request_list, link)
 			count++;
-- 
2.8.1

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

[PATCH 05/37] drm/i915: Remove inactive/active list from debugfs

[Chris Wilson]

These two files (i915_gem_active, i915_gem_inactive) no longer give
pertinent information since active/inactive tracking is per-vm and so we
need the information per-vm. They are obsolete so remove them.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 49 -------------------------------------
 1 file changed, 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c461072da142..4c08e2d23002 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -210,53 +210,6 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (frontbuffer: 0x%03x)", frontbuffer_bits);
 }
 
-static int i915_gem_object_list_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = m->private;
-	uintptr_t list = (uintptr_t) node->info_ent->data;
-	struct list_head *head;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct i915_vma *vma;
-	u64 total_obj_size, total_gtt_size;
-	int count, ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
-
-	/* FIXME: the user of this interface might want more than just GGTT */
-	switch (list) {
-	case ACTIVE_LIST:
-		seq_puts(m, "Active:\n");
-		head = &ggtt->base.active_list;
-		break;
-	case INACTIVE_LIST:
-		seq_puts(m, "Inactive:\n");
-		head = &ggtt->base.inactive_list;
-		break;
-	default:
-		mutex_unlock(&dev->struct_mutex);
-		return -EINVAL;
-	}
-
-	total_obj_size = total_gtt_size = count = 0;
-	list_for_each_entry(vma, head, vm_link) {
-		seq_printf(m, "   ");
-		describe_obj(m, vma->obj);
-		seq_printf(m, "\n");
-		total_obj_size += vma->obj->base.size;
-		total_gtt_size += vma->node.size;
-		count++;
-	}
-	mutex_unlock(&dev->struct_mutex);
-
-	seq_printf(m, "Total %d objects, %llu bytes, %llu GTT size\n",
-		   count, total_obj_size, total_gtt_size);
-	return 0;
-}
-
 static int obj_rank_by_stolen(void *priv,
 			      struct list_head *A, struct list_head *B)
 {
@@ -5376,8 +5329,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gem_objects", i915_gem_object_info, 0},
 	{"i915_gem_gtt", i915_gem_gtt_info, 0},
 	{"i915_gem_pinned", i915_gem_gtt_info, 0, (void *) PINNED_LIST},
-	{"i915_gem_active", i915_gem_object_list_info, 0, (void *) ACTIVE_LIST},
-	{"i915_gem_inactive", i915_gem_object_list_info, 0, (void *) INACTIVE_LIST},
 	{"i915_gem_stolen", i915_gem_stolen_list_info },
 	{"i915_gem_pageflip", i915_gem_pageflip_info, 0},
 	{"i915_gem_request", i915_gem_request_info, 0},
-- 
2.8.1

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

[PATCH 06/37] drm/i915: Focus debugfs/i915_gem_pinned to show only display pins

[Chris Wilson]

Only those objects pinned to the display have semi-permanent pins of a
global nature (other pins are transient within their local vm). Simplify
i915_gem_pinned to only show the pertinent information about the pinned
objects within the GGTT.

v2: i915_gem_gtt_info is still shared with debugfs/i915_gem_gtt,
rename i915_gem_pinned to i915_gem_pin_display to better reflect its
contents

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 4c08e2d23002..c535c4c2f7af 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -40,12 +40,6 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
-enum {
-	ACTIVE_LIST,
-	INACTIVE_LIST,
-	PINNED_LIST,
-};
-
 /* As the drm_debugfs_init() routines are called before dev->dev_private is
  * allocated we need to hook into the minor for release. */
 static int
@@ -537,8 +531,8 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
-	uintptr_t list = (uintptr_t) node->info_ent->data;
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	bool show_pin_display_only = !!data;
 	struct drm_i915_gem_object *obj;
 	u64 total_obj_size, total_gtt_size;
 	int count, ret;
@@ -549,7 +543,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data)
 
 	total_obj_size = total_gtt_size = count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (list == PINNED_LIST && !i915_gem_obj_is_pinned(obj))
+		if (show_pin_display_only && !obj->pin_display)
 			continue;
 
 		seq_puts(m, "   ");
@@ -5328,7 +5322,7 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_capabilities", i915_capabilities, 0},
 	{"i915_gem_objects", i915_gem_object_info, 0},
 	{"i915_gem_gtt", i915_gem_gtt_info, 0},
-	{"i915_gem_pinned", i915_gem_gtt_info, 0, (void *) PINNED_LIST},
+	{"i915_gem_pin_display", i915_gem_gtt_info, 0, (void *)1},
 	{"i915_gem_stolen", i915_gem_stolen_list_info },
 	{"i915_gem_pageflip", i915_gem_pageflip_info, 0},
 	{"i915_gem_request", i915_gem_request_info, 0},
-- 
2.8.1

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

[PATCH 07/37] drm/i915: Reduce i915_gem_objects to only show object information

[Chris Wilson]

No longer is knowing how much of the GTT (both mappable aperture and
beyond) relevant, and the output clutters the real information - that is
how many objects are allocated and bound (and by who) so that we can
quickly grasp if there is a leak.

v2: Relent, and rename pinned to indicate display only. Since the
display objects are semi-static and are of variable size, they are the
interesting objects to watch over time for aperture leaking. The other
pins are either static (such as the scratch page) or very short lived
(such as execbuf) and not part of the precious GGTT.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 100 ++++++++++--------------------------
 1 file changed, 28 insertions(+), 72 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c535c4c2f7af..fd028953453d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -269,17 +269,6 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-#define count_objects(list, member) do { \
-	list_for_each_entry(obj, list, member) { \
-		size += i915_gem_obj_total_ggtt_size(obj); \
-		++count; \
-		if (obj->map_and_fenceable) { \
-			mappable_size += i915_gem_obj_ggtt_size(obj); \
-			++mappable_count; \
-		} \
-	} \
-} while (0)
-
 struct file_stats {
 	struct drm_i915_file_private *file_priv;
 	unsigned long count;
@@ -394,30 +383,16 @@ static void print_context_stats(struct seq_file *m,
 	print_file_stats(m, "[k]contexts", stats);
 }
 
-#define count_vmas(list, member) do { \
-	list_for_each_entry(vma, list, member) { \
-		size += i915_gem_obj_total_ggtt_size(vma->obj); \
-		++count; \
-		if (vma->obj->map_and_fenceable) { \
-			mappable_size += i915_gem_obj_ggtt_size(vma->obj); \
-			++mappable_count; \
-		} \
-	} \
-} while (0)
-
 static int i915_gem_object_info(struct seq_file *m, void* data)
 {
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	u32 count, mappable_count, purgeable_count;
-	u64 size, mappable_size, purgeable_size;
-	unsigned long pin_mapped_count = 0, pin_mapped_purgeable_count = 0;
-	u64 pin_mapped_size = 0, pin_mapped_purgeable_size = 0;
+	u32 count, mapped_count, purgeable_count, dpy_count;
+	u64 size, mapped_size, purgeable_size, dpy_size;
 	struct drm_i915_gem_object *obj;
 	struct drm_file *file;
-	struct i915_vma *vma;
 	int ret;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -428,70 +403,51 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		   dev_priv->mm.object_count,
 		   dev_priv->mm.object_memory);
 
-	size = count = mappable_size = mappable_count = 0;
-	count_objects(&dev_priv->mm.bound_list, global_list);
-	seq_printf(m, "%u [%u] objects, %llu [%llu] bytes in gtt\n",
-		   count, mappable_count, size, mappable_size);
-
-	size = count = mappable_size = mappable_count = 0;
-	count_vmas(&ggtt->base.active_list, vm_link);
-	seq_printf(m, "  %u [%u] active objects, %llu [%llu] bytes\n",
-		   count, mappable_count, size, mappable_size);
-
-	size = count = mappable_size = mappable_count = 0;
-	count_vmas(&ggtt->base.inactive_list, vm_link);
-	seq_printf(m, "  %u [%u] inactive objects, %llu [%llu] bytes\n",
-		   count, mappable_count, size, mappable_size);
-
 	size = count = purgeable_size = purgeable_count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
-		size += obj->base.size, ++count;
-		if (obj->madv == I915_MADV_DONTNEED)
-			purgeable_size += obj->base.size, ++purgeable_count;
+		size += obj->base.size;
+		++count;
+
+		if (obj->madv == I915_MADV_DONTNEED) {
+			purgeable_size += obj->base.size;
+			++purgeable_count;
+		}
+
 		if (obj->mapping) {
-			pin_mapped_count++;
-			pin_mapped_size += obj->base.size;
-			if (obj->pages_pin_count == 0) {
-				pin_mapped_purgeable_count++;
-				pin_mapped_purgeable_size += obj->base.size;
-			}
+			mapped_count++;
+			mapped_size += obj->base.size;
 		}
 	}
 	seq_printf(m, "%u unbound objects, %llu bytes\n", count, size);
 
-	size = count = mappable_size = mappable_count = 0;
+	size = count = dpy_size = dpy_count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (obj->fault_mappable) {
-			size += i915_gem_obj_ggtt_size(obj);
-			++count;
-		}
+		size += obj->base.size;
+		++count;
+
 		if (obj->pin_display) {
-			mappable_size += i915_gem_obj_ggtt_size(obj);
-			++mappable_count;
+			dpy_size += obj->base.size;
+			++dpy_count;
 		}
+
 		if (obj->madv == I915_MADV_DONTNEED) {
 			purgeable_size += obj->base.size;
 			++purgeable_count;
 		}
+
 		if (obj->mapping) {
-			pin_mapped_count++;
-			pin_mapped_size += obj->base.size;
-			if (obj->pages_pin_count == 0) {
-				pin_mapped_purgeable_count++;
-				pin_mapped_purgeable_size += obj->base.size;
-			}
+			mapped_count++;
+			mapped_size += obj->base.size;
 		}
 	}
+	seq_printf(m, "%u bound objects, %llu bytes\n",
+		   count, size);
 	seq_printf(m, "%u purgeable objects, %llu bytes\n",
 		   purgeable_count, purgeable_size);
-	seq_printf(m, "%u pinned mappable objects, %llu bytes\n",
-		   mappable_count, mappable_size);
-	seq_printf(m, "%u fault mappable objects, %llu bytes\n",
-		   count, size);
-	seq_printf(m,
-		   "%lu [%lu] pin mapped objects, %llu [%llu] bytes [purgeable]\n",
-		   pin_mapped_count, pin_mapped_purgeable_count,
-		   pin_mapped_size, pin_mapped_purgeable_size);
+	seq_printf(m, "%u mapped objects, %llu bytes\n",
+		   mapped_count, mapped_size);
+	seq_printf(m, "%u display objects (pinned), %llu bytes\n",
+		   dpy_count, dpy_size);
 
 	seq_printf(m, "%llu [%llu] gtt total\n",
 		   ggtt->base.total, ggtt->mappable_end - ggtt->base.start);
-- 
2.8.1

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

[PATCH 08/37] drm/i915: Record the device capabilities at the time of a hang

[Chris Wilson]

When the machine hangs, capture the intel_device_info. This should be a
good indication of what is active, and is very useful when looking at
historic bug reports to remind oneself of the machine's capabilities.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h       | 254 +++++++++++++++++-----------------
 drivers/gpu/drm/i915/i915_gpu_error.c |  15 ++
 2 files changed, 143 insertions(+), 126 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2664612bce3f..a4203ff0cf7f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -475,132 +475,6 @@ struct sdvo_device_mapping {
 	u8 ddc_pin;
 };
 
-struct intel_display_error_state;
-
-struct drm_i915_error_state {
-	struct kref ref;
-	struct timeval time;
-
-	struct drm_i915_private *i915;
-
-	char error_msg[128];
-	bool simulated;
-	int iommu;
-	u32 reset_count;
-	u32 suspend_count;
-
-	/* Generic register state */
-	u32 eir;
-	u32 pgtbl_er;
-	u32 ier;
-	u32 gtier[4];
-	u32 ccid;
-	u32 derrmr;
-	u32 forcewake;
-	u32 error; /* gen6+ */
-	u32 err_int; /* gen7 */
-	u32 fault_data0; /* gen8, gen9 */
-	u32 fault_data1; /* gen8, gen9 */
-	u32 done_reg;
-	u32 gac_eco;
-	u32 gam_ecochk;
-	u32 gab_ctl;
-	u32 gfx_mode;
-	u32 extra_instdone[I915_NUM_INSTDONE_REG];
-	u64 fence[I915_MAX_NUM_FENCES];
-	struct intel_overlay_error_state *overlay;
-	struct intel_display_error_state *display;
-	struct drm_i915_error_object *semaphore_obj;
-
-	struct drm_i915_error_engine {
-		int engine_id;
-		/* Software tracked state */
-		bool waiting;
-		int num_waiters;
-		int hangcheck_score;
-		enum intel_engine_hangcheck_action hangcheck_action;
-		struct i915_address_space *vm;
-		int num_requests;
-
-		/* our own tracking of ring head and tail */
-		u32 cpu_ring_head;
-		u32 cpu_ring_tail;
-
-		u32 last_seqno;
-		u32 semaphore_seqno[I915_NUM_ENGINES - 1];
-
-		/* Register state */
-		u32 start;
-		u32 tail;
-		u32 head;
-		u32 ctl;
-		u32 hws;
-		u32 ipeir;
-		u32 ipehr;
-		u32 instdone;
-		u32 bbstate;
-		u32 instpm;
-		u32 instps;
-		u32 seqno;
-		u64 bbaddr;
-		u64 acthd;
-		u32 fault_reg;
-		u64 faddr;
-		u32 rc_psmi; /* sleep state */
-		u32 semaphore_mboxes[I915_NUM_ENGINES - 1];
-
-		struct drm_i915_error_object {
-			int page_count;
-			u64 gtt_offset;
-			u32 *pages[0];
-		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
-
-		struct drm_i915_error_object *wa_ctx;
-
-		struct drm_i915_error_request {
-			long jiffies;
-			u32 seqno;
-			u32 head;
-			u32 tail;
-		} *requests;
-
-		struct drm_i915_error_waiter {
-			char comm[TASK_COMM_LEN];
-			pid_t pid;
-			u32 seqno;
-		} *waiters;
-
-		struct {
-			u32 gfx_mode;
-			union {
-				u64 pdp[4];
-				u32 pp_dir_base;
-			};
-		} vm_info;
-
-		pid_t pid;
-		char comm[TASK_COMM_LEN];
-	} engine[I915_NUM_ENGINES];
-
-	struct drm_i915_error_buffer {
-		u32 size;
-		u32 name;
-		u32 rseqno[I915_NUM_ENGINES], wseqno;
-		u64 gtt_offset;
-		u32 read_domains;
-		u32 write_domain;
-		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
-		u32 tiling:2;
-		u32 dirty:1;
-		u32 purgeable:1;
-		u32 userptr:1;
-		s32 engine:4;
-		u32 cache_level:3;
-	} *active_bo[I915_NUM_ENGINES], *pinned_bo;
-	u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count;
-	struct i915_address_space *active_vm[I915_NUM_ENGINES];
-};
-
 struct intel_connector;
 struct intel_encoder;
 struct intel_crtc_state;
@@ -825,6 +699,134 @@ struct intel_device_info {
 #undef DEFINE_FLAG
 #undef SEP_SEMICOLON
 
+struct intel_display_error_state;
+
+struct drm_i915_error_state {
+	struct kref ref;
+	struct timeval time;
+
+	struct drm_i915_private *i915;
+
+	char error_msg[128];
+	bool simulated;
+	int iommu;
+	u32 reset_count;
+	u32 suspend_count;
+	struct intel_device_info device_info;
+
+	/* Generic register state */
+	u32 eir;
+	u32 pgtbl_er;
+	u32 ier;
+	u32 gtier[4];
+	u32 ccid;
+	u32 derrmr;
+	u32 forcewake;
+	u32 error; /* gen6+ */
+	u32 err_int; /* gen7 */
+	u32 fault_data0; /* gen8, gen9 */
+	u32 fault_data1; /* gen8, gen9 */
+	u32 done_reg;
+	u32 gac_eco;
+	u32 gam_ecochk;
+	u32 gab_ctl;
+	u32 gfx_mode;
+	u32 extra_instdone[I915_NUM_INSTDONE_REG];
+	u64 fence[I915_MAX_NUM_FENCES];
+	struct intel_overlay_error_state *overlay;
+	struct intel_display_error_state *display;
+	struct drm_i915_error_object *semaphore_obj;
+
+	struct drm_i915_error_engine {
+		int engine_id;
+		/* Software tracked state */
+		bool waiting;
+		int num_waiters;
+		int hangcheck_score;
+		enum intel_engine_hangcheck_action hangcheck_action;
+		struct i915_address_space *vm;
+		int num_requests;
+
+		/* our own tracking of ring head and tail */
+		u32 cpu_ring_head;
+		u32 cpu_ring_tail;
+
+		u32 last_seqno;
+		u32 semaphore_seqno[I915_NUM_ENGINES - 1];
+
+		/* Register state */
+		u32 start;
+		u32 tail;
+		u32 head;
+		u32 ctl;
+		u32 hws;
+		u32 ipeir;
+		u32 ipehr;
+		u32 instdone;
+		u32 bbstate;
+		u32 instpm;
+		u32 instps;
+		u32 seqno;
+		u64 bbaddr;
+		u64 acthd;
+		u32 fault_reg;
+		u64 faddr;
+		u32 rc_psmi; /* sleep state */
+		u32 semaphore_mboxes[I915_NUM_ENGINES - 1];
+
+		struct drm_i915_error_object {
+			int page_count;
+			u64 gtt_offset;
+			u32 *pages[0];
+		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
+
+		struct drm_i915_error_object *wa_ctx;
+
+		struct drm_i915_error_request {
+			long jiffies;
+			u32 seqno;
+			u32 head;
+			u32 tail;
+		} *requests;
+
+		struct drm_i915_error_waiter {
+			char comm[TASK_COMM_LEN];
+			pid_t pid;
+			u32 seqno;
+		} *waiters;
+
+		struct {
+			u32 gfx_mode;
+			union {
+				u64 pdp[4];
+				u32 pp_dir_base;
+			};
+		} vm_info;
+
+		pid_t pid;
+		char comm[TASK_COMM_LEN];
+	} engine[I915_NUM_ENGINES];
+
+	struct drm_i915_error_buffer {
+		u32 size;
+		u32 name;
+		u32 rseqno[I915_NUM_ENGINES], wseqno;
+		u64 gtt_offset;
+		u32 read_domains;
+		u32 write_domain;
+		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
+		u32 tiling:2;
+		u32 dirty:1;
+		u32 purgeable:1;
+		u32 userptr:1;
+		s32 engine:4;
+		u32 cache_level:3;
+	} *active_bo[I915_NUM_ENGINES], *pinned_bo;
+	u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count;
+	struct i915_address_space *active_vm[I915_NUM_ENGINES];
+};
+
+
 enum i915_cache_level {
 	I915_CACHE_NONE = 0,
 	I915_CACHE_LLC, /* also used for snoopable memory on non-LLC */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 983488da742a..a87a5c489e2e 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -313,6 +313,16 @@ static void print_error_obj(struct drm_i915_error_state_buf *m,
 	}
 }
 
+static void err_print_capabilities(struct drm_i915_error_state_buf *m,
+				   const struct intel_device_info *info)
+{
+#define PRINT_FLAG(x)  err_printf(m, #x ": %s\n", yesno(info->x))
+#define SEP_SEMICOLON ;
+	DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_SEMICOLON);
+#undef PRINT_FLAG
+#undef SEP_SEMICOLON
+}
+
 int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			    const struct i915_error_state_file_priv *error_priv)
 {
@@ -332,6 +342,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	err_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec,
 		   error->time.tv_usec);
 	err_printf(m, "Kernel: " UTS_RELEASE "\n");
+	err_print_capabilities(m, &error->device_info);
 	max_hangcheck_score = 0;
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].hangcheck_score > max_hangcheck_score)
@@ -1356,6 +1367,10 @@ static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
 #endif
 	error->reset_count = i915_reset_count(&dev_priv->gpu_error);
 	error->suspend_count = dev_priv->suspend_count;
+
+	memcpy(&error->device_info,
+	       INTEL_INFO(dev_priv),
+	       sizeof(error->device_info));
 }
 
 static int capture(void *data)
-- 
2.8.1

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

[PATCH 09/37] drm/i915: Remove redundant WARN_ON from __i915_add_request()

[Chris Wilson]

It's an outright programming error, so explode if it is ever hit.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_request.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 8a9e9bfeea09..4c5b7e104f2f 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -470,18 +470,12 @@ static void i915_gem_mark_busy(const struct intel_engine_cs *engine)
  */
 void __i915_add_request(struct drm_i915_gem_request *request, bool flush_caches)
 {
-	struct intel_engine_cs *engine;
-	struct intel_ring *ring;
+	struct intel_engine_cs *engine = request->engine;
+	struct intel_ring *ring = request->ring;
 	u32 request_start;
 	u32 reserved_tail;
 	int ret;
 
-	if (WARN_ON(!request))
-		return;
-
-	engine = request->engine;
-	ring = request->ring;
-
 	/*
 	 * To ensure that this call will not fail, space for its emissions
 	 * should already have been reserved in the ring buffer. Let the ring
-- 
2.8.1

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

[PATCH 10/37] drm/i915: Always set the vma->pages

[Chris Wilson]

Previously, we would only set the vma->pages pointer for GGTT entries.
However, if we always set it, we can use it to prettify some code that
may want to access the backing store associated with the VMA (as
assigned to the VMA).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem.c     |  8 ++++----
 drivers/gpu/drm/i915/i915_gem_gtt.c | 30 ++++++++++++++----------------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  3 +--
 3 files changed, 19 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 03548db54e6b..b427969325ec 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2821,12 +2821,12 @@ int i915_vma_unbind(struct i915_vma *vma)
 	if (i915_vma_is_ggtt(vma)) {
 		if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL) {
 			obj->map_and_fenceable = false;
-		} else if (vma->ggtt_view.pages) {
-			sg_free_table(vma->ggtt_view.pages);
-			kfree(vma->ggtt_view.pages);
+		} else if (vma->pages) {
+			sg_free_table(vma->pages);
+			kfree(vma->pages);
 		}
-		vma->ggtt_view.pages = NULL;
 	}
+	vma->pages = NULL;
 
 	/* Since the unbound list is global, only move to that list if
 	 * no more VMAs exist. */
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d876501694c6..9c178b0c40b5 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -170,11 +170,13 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 {
 	u32 pte_flags = 0;
 
+	vma->pages = vma->obj->pages;
+
 	/* Currently applicable only to VLV */
 	if (vma->obj->gt_ro)
 		pte_flags |= PTE_READ_ONLY;
 
-	vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
+	vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
 				cache_level, pte_flags);
 
 	return 0;
@@ -2618,8 +2620,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	if (obj->gt_ro)
 		pte_flags |= PTE_READ_ONLY;
 
-	vma->vm->insert_entries(vma->vm, vma->ggtt_view.pages,
-				vma->node.start,
+	vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
 				cache_level, pte_flags);
 
 	/*
@@ -2651,8 +2652,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 
 	if (flags & I915_VMA_GLOBAL_BIND) {
 		vma->vm->insert_entries(vma->vm,
-					vma->ggtt_view.pages,
-					vma->node.start,
+					vma->pages, vma->node.start,
 					cache_level, pte_flags);
 	}
 
@@ -2660,8 +2660,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 		struct i915_hw_ppgtt *appgtt =
 			to_i915(vma->vm->dev)->mm.aliasing_ppgtt;
 		appgtt->base.insert_entries(&appgtt->base,
-					    vma->ggtt_view.pages,
-					    vma->node.start,
+					    vma->pages, vma->node.start,
 					    cache_level, pte_flags);
 	}
 
@@ -3557,28 +3556,27 @@ i915_get_ggtt_vma_pages(struct i915_vma *vma)
 {
 	int ret = 0;
 
-	if (vma->ggtt_view.pages)
+	if (vma->pages)
 		return 0;
 
 	if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL)
-		vma->ggtt_view.pages = vma->obj->pages;
+		vma->pages = vma->obj->pages;
 	else if (vma->ggtt_view.type == I915_GGTT_VIEW_ROTATED)
-		vma->ggtt_view.pages =
+		vma->pages =
 			intel_rotate_fb_obj_pages(&vma->ggtt_view.params.rotated, vma->obj);
 	else if (vma->ggtt_view.type == I915_GGTT_VIEW_PARTIAL)
-		vma->ggtt_view.pages =
-			intel_partial_pages(&vma->ggtt_view, vma->obj);
+		vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj);
 	else
 		WARN_ONCE(1, "GGTT view %u not implemented!\n",
 			  vma->ggtt_view.type);
 
-	if (!vma->ggtt_view.pages) {
+	if (!vma->pages) {
 		DRM_ERROR("Failed to get pages for GGTT view type %u!\n",
 			  vma->ggtt_view.type);
 		ret = -EINVAL;
-	} else if (IS_ERR(vma->ggtt_view.pages)) {
-		ret = PTR_ERR(vma->ggtt_view.pages);
-		vma->ggtt_view.pages = NULL;
+	} else if (IS_ERR(vma->pages)) {
+		ret = PTR_ERR(vma->pages);
+		vma->pages = NULL;
 		DRM_ERROR("Failed to get pages for VMA view type %u (%d)!\n",
 			  vma->ggtt_view.type, ret);
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 56e64a5355e8..b580e8a013ce 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -155,8 +155,6 @@ struct i915_ggtt_view {
 		} partial;
 		struct intel_rotation_info rotated;
 	} params;
-
-	struct sg_table *pages;
 };
 
 extern const struct i915_ggtt_view i915_ggtt_view_normal;
@@ -176,6 +174,7 @@ struct i915_vma {
 	struct drm_mm_node node;
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm;
+	struct sg_table *pages;
 	void __iomem *iomap;
 	u64 size;
 
-- 
2.8.1

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

[PATCH 11/37] drm/i915: Create a VMA for an object

[Chris Wilson]

In many places, we wish to store the VMA in preference to the object
itself and so being able to create the persistent VMA is useful.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 11 +++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.h |  5 +++++
 2 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9c178b0c40b5..1bec50bd651b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3387,6 +3387,17 @@ __i915_gem_vma_create(struct drm_i915_gem_object *obj,
 }
 
 struct i915_vma *
+i915_vma_create(struct drm_i915_gem_object *obj,
+		struct i915_address_space *vm,
+		const struct i915_ggtt_view *view)
+{
+	GEM_BUG_ON(view && !i915_is_ggtt(vm));
+	GEM_BUG_ON(view ? i915_gem_obj_to_ggtt_view(obj, view) : i915_gem_obj_to_vma(obj, vm));
+
+	return __i915_gem_vma_create(obj, vm, view ?: &i915_ggtt_view_normal);
+}
+
+struct i915_vma *
 i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
 				  struct i915_address_space *vm)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index b580e8a013ce..f2769e01cc8c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -228,6 +228,11 @@ struct i915_vma {
 	struct drm_i915_gem_exec_object2 *exec_entry;
 };
 
+struct i915_vma *
+i915_vma_create(struct drm_i915_gem_object *obj,
+		struct i915_address_space *vm,
+		const struct i915_ggtt_view *view);
+
 static inline bool i915_vma_is_ggtt(const struct i915_vma *vma)
 {
 	return vma->flags & I915_VMA_GGTT;
-- 
2.8.1

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

[PATCH 12/37] drm/i915: Add fetch_and_zero() macro

[Chris Wilson]

A simple little macro to clear a pointer and return the old value. This
is useful for writing

	value = *ptr;
	if (!value)
		return;

	*ptr = 0;
	...
	free(value);

in a slightly more concise form:

	value = fetch_and_zero(ptr);
	if (!value)
		return;

	...
	free(value);

with the idea that this establishes a pattern that may be extended for
atomic use (using xchg or cmpxchg) i.e. atomic_fetch_and_zero() and
similar to llist.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_drv.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a4203ff0cf7f..731c67fc9796 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3903,4 +3903,10 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req)
 	return false;
 }
 
+#define fetch_and_zero(ptr) ({						\
+	typeof(*ptr) T__ = *(ptr);					\
+	*(ptr) = (typeof(*ptr))0;					\
+	T__;								\
+})
+
 #endif
-- 
2.8.1

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

[PATCH 13/37] drm/i915: Add convenience wrappers for vma's object get/put

[Chris Wilson]

The VMA are unreferenced, they belong to the object and live until they
are closed. However, if we want to use the VMA as a cookie and use it to
keep the object alive, we want to hold onto a reference to the object
for the lifetime of the VMA cookie. To facilitate this, add a couple of
simple wrappers for managing the reference count on the object owning the
VMA.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h            | 12 ++++++++++++
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  4 ++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 731c67fc9796..873ffe8bfe89 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2376,6 +2376,18 @@ i915_gem_object_get_stride(struct drm_i915_gem_object *obj)
 	return obj->tiling_and_stride & STRIDE_MASK;
 }
 
+static inline struct i915_vma *i915_vma_get(struct i915_vma *vma)
+{
+	i915_gem_object_get(vma->obj);
+	return vma;
+}
+
+static inline void i915_vma_put(struct i915_vma *vma)
+{
+	lockdep_assert_held(&vma->vm->dev->struct_mutex);
+	i915_gem_object_put(vma->obj);
+}
+
 /*
  * Optimised SGL iterator for GEM objects
  */
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index c8d13fea4b25..ced05878b405 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -271,7 +271,7 @@ static void eb_destroy(struct eb_vmas *eb)
 				       exec_list);
 		list_del_init(&vma->exec_list);
 		i915_gem_execbuffer_unreserve_vma(vma);
-		i915_gem_object_put(vma->obj);
+		i915_vma_put(vma);
 	}
 	kfree(eb);
 }
@@ -900,7 +900,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 		vma = list_first_entry(&eb->vmas, struct i915_vma, exec_list);
 		list_del_init(&vma->exec_list);
 		i915_gem_execbuffer_unreserve_vma(vma);
-		i915_gem_object_put(vma->obj);
+		i915_vma_put(vma);
 	}
 
 	mutex_unlock(&dev->struct_mutex);
-- 
2.8.1

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

[PATCH 14/37] drm/i915: Track pinned vma inside guc

[Chris Wilson]

Since the guc allocates and pins and object into the GGTT for its usage,
it is more natural to use that pinned VMA as our resource cookie.

v2: Embrace naming tautology

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c        |  10 +--
 drivers/gpu/drm/i915/i915_gem_gtt.h        |   6 ++
 drivers/gpu/drm/i915/i915_guc_submission.c | 132 ++++++++++++++---------------
 drivers/gpu/drm/i915/intel_guc.h           |   9 +-
 drivers/gpu/drm/i915/intel_guc_loader.c    |   7 +-
 5 files changed, 83 insertions(+), 81 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fd028953453d..32d26b6c4bca 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2526,15 +2526,15 @@ static int i915_guc_log_dump(struct seq_file *m, void *data)
 	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_i915_gem_object *log_obj = dev_priv->guc.log_obj;
-	u32 *log;
+	struct drm_i915_gem_object *obj;
 	int i = 0, pg;
 
-	if (!log_obj)
+	if (!dev_priv->guc.log_vma)
 		return 0;
 
-	for (pg = 0; pg < log_obj->base.size / PAGE_SIZE; pg++) {
-		log = kmap_atomic(i915_gem_object_get_page(log_obj, pg));
+	obj = dev_priv->guc.log_vma->obj;
+	for (pg = 0; pg < obj->base.size / PAGE_SIZE; pg++) {
+		u32 *log = kmap_atomic(i915_gem_object_get_page(obj, pg));
 
 		for (i = 0; i < PAGE_SIZE / sizeof(u32); i += 4)
 			seq_printf(m, "0x%08x 0x%08x 0x%08x 0x%08x\n",
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index f2769e01cc8c..a2691943a404 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -716,4 +716,10 @@ static inline void i915_vma_unpin_iomap(struct i915_vma *vma)
 	i915_vma_unpin(vma);
 }
 
+static inline struct page *i915_vma_first_page(struct i915_vma *vma)
+{
+	GEM_BUG_ON(!vma->pages);
+	return sg_page(vma->pages->sgl);
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 6831321a9c8c..4b20263e45d0 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -183,7 +183,7 @@ static int guc_update_doorbell_id(struct intel_guc *guc,
 				  struct i915_guc_client *client,
 				  u16 new_id)
 {
-	struct sg_table *sg = guc->ctx_pool_obj->pages;
+	struct sg_table *sg = guc->ctx_pool_vma->pages;
 	void *doorbell_bitmap = guc->doorbell_bitmap;
 	struct guc_doorbell_info *doorbell;
 	struct guc_context_desc desc;
@@ -325,7 +325,6 @@ static void guc_init_proc_desc(struct intel_guc *guc,
 static void guc_init_ctx_desc(struct intel_guc *guc,
 			      struct i915_guc_client *client)
 {
-	struct drm_i915_gem_object *client_obj = client->client_obj;
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx = client->owner;
@@ -383,8 +382,8 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	 * The doorbell, process descriptor, and workqueue are all parts
 	 * of the client object, which the GuC will reference via the GGTT
 	 */
-	gfx_addr = i915_gem_obj_ggtt_offset(client_obj);
-	desc.db_trigger_phy = sg_dma_address(client_obj->pages->sgl) +
+	gfx_addr = client->vma->node.start;
+	desc.db_trigger_phy = sg_dma_address(client->vma->pages->sgl) +
 				client->doorbell_offset;
 	desc.db_trigger_cpu = (uintptr_t)client->client_base +
 				client->doorbell_offset;
@@ -400,7 +399,7 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	desc.desc_private = (uintptr_t)client;
 
 	/* Pool context is pinned already */
-	sg = guc->ctx_pool_obj->pages;
+	sg = guc->ctx_pool_vma->pages;
 	sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
 			     sizeof(desc) * client->ctx_index);
 }
@@ -413,7 +412,7 @@ static void guc_fini_ctx_desc(struct intel_guc *guc,
 
 	memset(&desc, 0, sizeof(desc));
 
-	sg = guc->ctx_pool_obj->pages;
+	sg = guc->ctx_pool_vma->pages;
 	sg_pcopy_from_buffer(sg->sgl, sg->nents, &desc, sizeof(desc),
 			     sizeof(desc) * client->ctx_index);
 }
@@ -496,7 +495,7 @@ static void guc_add_workqueue_item(struct i915_guc_client *gc,
 	/* WQ starts from the page after doorbell / process_desc */
 	wq_page = (wq_off + GUC_DB_SIZE) >> PAGE_SHIFT;
 	wq_off &= PAGE_SIZE - 1;
-	base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, wq_page));
+	base = kmap_atomic(i915_gem_object_get_page(gc->vma->obj, wq_page));
 	wqi = (struct guc_wq_item *)((char *)base + wq_off);
 
 	/* Now fill in the 4-word work queue item */
@@ -614,8 +613,8 @@ static void i915_guc_submit(struct drm_i915_gem_request *rq)
  */
 
 /**
- * gem_allocate_guc_obj() - Allocate gem object for GuC usage
- * @dev_priv:	driver private data structure
+ * guc_allocate_vma() - Allocate a GGTT VMA for GuC usage
+ * @guc:	the guc
  * @size:	size of object
  *
  * This is a wrapper to create a gem obj. In order to use it inside GuC, the
@@ -624,45 +623,49 @@ static void i915_guc_submit(struct drm_i915_gem_request *rq)
  *
  * Return:	A drm_i915_gem_object if successful, otherwise NULL.
  */
-static struct drm_i915_gem_object *
-gem_allocate_guc_obj(struct drm_i915_private *dev_priv, u32 size)
+static struct i915_vma *guc_allocate_vma(struct intel_guc *guc, u32 size)
 {
+	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int ret;
 
 	obj = i915_gem_object_create(&dev_priv->drm, size);
 	if (IS_ERR(obj))
-		return NULL;
+		return ERR_CAST(obj);
 
-	if (i915_gem_object_get_pages(obj)) {
-		i915_gem_object_put(obj);
-		return NULL;
-	}
+	vma = i915_vma_create(obj, &dev_priv->ggtt.base, NULL);
+	if (IS_ERR(vma))
+		goto err;
 
-	if (i915_gem_object_ggtt_pin(obj, NULL, 0, PAGE_SIZE,
-				     PIN_OFFSET_BIAS | GUC_WOPCM_TOP)) {
-		i915_gem_object_put(obj);
-		return NULL;
+	ret = i915_vma_pin(vma, 0, PAGE_SIZE,
+			   PIN_GLOBAL | PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+	if (ret) {
+		vma = ERR_PTR(ret);
+		goto err;
 	}
 
 	/* Invalidate GuC TLB to let GuC take the latest updates to GTT. */
 	I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
 
-	return obj;
+	return vma;
+
+err:
+	i915_gem_object_put(obj);
+	return vma;
 }
 
 /**
- * gem_release_guc_obj() - Release gem object allocated for GuC usage
- * @obj:	gem obj to be released
+ * guc_release_vma() - Release gem object allocated for GuC usage
+ * @vma:	gem obj to be released
  */
-static void gem_release_guc_obj(struct drm_i915_gem_object *obj)
+static void guc_release_vma(struct i915_vma *vma)
 {
-	if (!obj)
+	if (!vma)
 		return;
 
-	if (i915_gem_obj_is_pinned(obj))
-		i915_gem_object_ggtt_unpin(obj);
-
-	i915_gem_object_put(obj);
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
 }
 
 static void
@@ -689,7 +692,7 @@ guc_client_free(struct drm_i915_private *dev_priv,
 		kunmap(kmap_to_page(client->client_base));
 	}
 
-	gem_release_guc_obj(client->client_obj);
+	guc_release_vma(client->vma);
 
 	if (client->ctx_index != GUC_INVALID_CTX_ID) {
 		guc_fini_ctx_desc(guc, client);
@@ -773,7 +776,7 @@ guc_client_alloc(struct drm_i915_private *dev_priv,
 {
 	struct i915_guc_client *client;
 	struct intel_guc *guc = &dev_priv->guc;
-	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 	uint16_t db_id;
 
 	client = kzalloc(sizeof(*client), GFP_KERNEL);
@@ -794,13 +797,13 @@ guc_client_alloc(struct drm_i915_private *dev_priv,
 	}
 
 	/* The first page is doorbell/proc_desc. Two followed pages are wq. */
-	obj = gem_allocate_guc_obj(dev_priv, GUC_DB_SIZE + GUC_WQ_SIZE);
-	if (!obj)
+	vma = guc_allocate_vma(guc, GUC_DB_SIZE + GUC_WQ_SIZE);
+	if (IS_ERR(vma))
 		goto err;
 
 	/* We'll keep just the first (doorbell/proc) page permanently kmap'd. */
-	client->client_obj = obj;
-	client->client_base = kmap(i915_gem_object_get_page(obj, 0));
+	client->vma = vma;
+	client->client_base = kmap(i915_vma_first_page(vma));
 	client->wq_offset = GUC_DB_SIZE;
 	client->wq_size = GUC_WQ_SIZE;
 
@@ -842,8 +845,7 @@ err:
 
 static void guc_create_log(struct intel_guc *guc)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 	unsigned long offset;
 	uint32_t size, flags;
 
@@ -859,16 +861,16 @@ static void guc_create_log(struct intel_guc *guc)
 		GUC_LOG_ISR_PAGES + 1 +
 		GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT;
 
-	obj = guc->log_obj;
-	if (!obj) {
-		obj = gem_allocate_guc_obj(dev_priv, size);
-		if (!obj) {
+	vma = guc->log_vma;
+	if (!vma) {
+		vma = guc_allocate_vma(guc, size);
+		if (IS_ERR(vma)) {
 			/* logging will be off */
 			i915.guc_log_level = -1;
 			return;
 		}
 
-		guc->log_obj = obj;
+		guc->log_vma = vma;
 	}
 
 	/* each allocated unit is a page */
@@ -877,7 +879,7 @@ static void guc_create_log(struct intel_guc *guc)
 		(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
 		(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
 
-	offset = i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT; /* in pages */
+	offset = vma->node.start >> PAGE_SHIFT; /* in pages */
 	guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
 }
 
@@ -906,7 +908,7 @@ static void init_guc_policies(struct guc_policies *policies)
 static void guc_create_ads(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
-	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 	struct guc_ads *ads;
 	struct guc_policies *policies;
 	struct guc_mmio_reg_state *reg_state;
@@ -919,16 +921,16 @@ static void guc_create_ads(struct intel_guc *guc)
 			sizeof(struct guc_mmio_reg_state) +
 			GUC_S3_SAVE_SPACE_PAGES * PAGE_SIZE;
 
-	obj = guc->ads_obj;
-	if (!obj) {
-		obj = gem_allocate_guc_obj(dev_priv, PAGE_ALIGN(size));
-		if (!obj)
+	vma = guc->ads_vma;
+	if (!vma) {
+		vma = guc_allocate_vma(guc, PAGE_ALIGN(size));
+		if (IS_ERR(vma))
 			return;
 
-		guc->ads_obj = obj;
+		guc->ads_vma = vma;
 	}
 
-	page = i915_gem_object_get_page(obj, 0);
+	page = i915_vma_first_page(vma);
 	ads = kmap(page);
 
 	/*
@@ -948,8 +950,7 @@ static void guc_create_ads(struct intel_guc *guc)
 	policies = (void *)ads + sizeof(struct guc_ads);
 	init_guc_policies(policies);
 
-	ads->scheduler_policies = i915_gem_obj_ggtt_offset(obj) +
-			sizeof(struct guc_ads);
+	ads->scheduler_policies = vma->node.start + sizeof(struct guc_ads);
 
 	/* MMIO reg state */
 	reg_state = (void *)policies + sizeof(struct guc_policies);
@@ -977,10 +978,9 @@ static void guc_create_ads(struct intel_guc *guc)
  */
 int i915_guc_submission_init(struct drm_i915_private *dev_priv)
 {
-	const size_t ctxsize = sizeof(struct guc_context_desc);
-	const size_t poolsize = GUC_MAX_GPU_CONTEXTS * ctxsize;
-	const size_t gemsize = round_up(poolsize, PAGE_SIZE);
 	struct intel_guc *guc = &dev_priv->guc;
+	struct i915_vma *vma;
+	u32 size;
 
 	/* Wipe bitmap & delete client in case of reinitialisation */
 	bitmap_clear(guc->doorbell_bitmap, 0, GUC_MAX_DOORBELLS);
@@ -989,13 +989,15 @@ int i915_guc_submission_init(struct drm_i915_private *dev_priv)
 	if (!i915.enable_guc_submission)
 		return 0; /* not enabled  */
 
-	if (guc->ctx_pool_obj)
+	if (guc->ctx_pool_vma)
 		return 0; /* already allocated */
 
-	guc->ctx_pool_obj = gem_allocate_guc_obj(dev_priv, gemsize);
-	if (!guc->ctx_pool_obj)
-		return -ENOMEM;
+	size = PAGE_ALIGN(GUC_MAX_GPU_CONTEXTS*sizeof(struct guc_context_desc));
+	vma = guc_allocate_vma(guc, size);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
 
+	guc->ctx_pool_vma = vma;
 	ida_init(&guc->ctx_ids);
 	guc_create_log(guc);
 	guc_create_ads(guc);
@@ -1048,16 +1050,12 @@ void i915_guc_submission_fini(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
 
-	gem_release_guc_obj(dev_priv->guc.ads_obj);
-	guc->ads_obj = NULL;
-
-	gem_release_guc_obj(dev_priv->guc.log_obj);
-	guc->log_obj = NULL;
+	guc_release_vma(fetch_and_zero(&guc->ads_vma));
+	guc_release_vma(fetch_and_zero(&guc->log_vma));
 
-	if (guc->ctx_pool_obj)
+	if (guc->ctx_pool_vma)
 		ida_destroy(&guc->ctx_ids);
-	gem_release_guc_obj(guc->ctx_pool_obj);
-	guc->ctx_pool_obj = NULL;
+	guc_release_vma(fetch_and_zero(&guc->ctx_pool_vma));
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index 26f3d9c08120..c97326269588 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -63,7 +63,7 @@ struct drm_i915_gem_request;
  *   retcode: errno from last guc_submit()
  */
 struct i915_guc_client {
-	struct drm_i915_gem_object *client_obj;
+	struct i915_vma *vma;
 	void *client_base;		/* first page (only) of above	*/
 	struct i915_gem_context *owner;
 	struct intel_guc *guc;
@@ -124,11 +124,10 @@ struct intel_guc_fw {
 struct intel_guc {
 	struct intel_guc_fw guc_fw;
 	uint32_t log_flags;
-	struct drm_i915_gem_object *log_obj;
+	struct i915_vma *log_vma;
 
-	struct drm_i915_gem_object *ads_obj;
-
-	struct drm_i915_gem_object *ctx_pool_obj;
+	struct i915_vma *ads_vma;
+	struct i915_vma *ctx_pool_vma;
 	struct ida ctx_ids;
 
 	struct i915_guc_client *execbuf_client;
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index bfcf6b5d29ad..1e2d9f2ad4f6 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -193,16 +193,15 @@ static void set_guc_init_params(struct drm_i915_private *dev_priv)
 			i915.guc_log_level << GUC_LOG_VERBOSITY_SHIFT;
 	}
 
-	if (guc->ads_obj) {
-		u32 ads = (u32)i915_gem_obj_ggtt_offset(guc->ads_obj)
-				>> PAGE_SHIFT;
+	if (guc->ads_vma) {
+		u32 ads = (u32)guc->ads_vma->node.start >> PAGE_SHIFT;
 		params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
 		params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED;
 	}
 
 	/* If GuC submission is enabled, set up additional parameters here */
 	if (i915.enable_guc_submission) {
-		u32 pgs = i915_gem_obj_ggtt_offset(dev_priv->guc.ctx_pool_obj);
+		u32 pgs = dev_priv->guc.ctx_pool_vma->node.start;
 		u32 ctx_in_16 = GUC_MAX_GPU_CONTEXTS / 16;
 
 		pgs >>= PAGE_SHIFT;
-- 
2.8.1

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

[PATCH 15/37] drm/i915: Convert fence computations to use vma directly

[Chris Wilson]

Lookup the GGTT vma once for the object assigned to the fence, and then
derive everything from that vma.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_fence.c | 55 +++++++++++++++++------------------
 1 file changed, 26 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 9e8173fe2a09..1d0f975c61f8 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -85,22 +85,19 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 	POSTING_READ(fence_reg_lo);
 
 	if (obj) {
-		u32 size = i915_gem_obj_ggtt_size(obj);
+		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
 		unsigned int tiling = i915_gem_object_get_tiling(obj);
 		unsigned int stride = i915_gem_object_get_stride(obj);
-		uint64_t val;
+		u64 size = vma->node.size;
+		u32 row_size = stride * (tiling == I915_TILING_Y ? 32 : 8);
+		u64 val;
 
 		/* Adjust fence size to match tiled area */
-		if (tiling != I915_TILING_NONE) {
-			uint32_t row_size = stride *
-				(tiling == I915_TILING_Y ? 32 : 8);
-			size = (size / row_size) * row_size;
-		}
+		size = rounddown(size, row_size);
 
-		val = (uint64_t)((i915_gem_obj_ggtt_offset(obj) + size - 4096) &
-				 0xfffff000) << 32;
-		val |= i915_gem_obj_ggtt_offset(obj) & 0xfffff000;
-		val |= (uint64_t)((stride / 128) - 1) << fence_pitch_shift;
+		val = ((vma->node.start + size - 4096) & 0xfffff000) << 32;
+		val |= vma->node.start & 0xfffff000;
+		val |= (u64)((stride / 128) - 1) << fence_pitch_shift;
 		if (tiling == I915_TILING_Y)
 			val |= 1 << I965_FENCE_TILING_Y_SHIFT;
 		val |= I965_FENCE_REG_VALID;
@@ -123,17 +120,17 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 	u32 val;
 
 	if (obj) {
-		u32 size = i915_gem_obj_ggtt_size(obj);
+		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
 		unsigned int tiling = i915_gem_object_get_tiling(obj);
 		unsigned int stride = i915_gem_object_get_stride(obj);
 		int pitch_val;
 		int tile_width;
 
-		WARN((i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK) ||
-		     (size & -size) != size ||
-		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
-		     "object 0x%08llx [fenceable? %d] not 1M or pot-size (0x%08x) aligned\n",
-		     i915_gem_obj_ggtt_offset(obj), obj->map_and_fenceable, size);
+		WARN((vma->node.start & ~I915_FENCE_START_MASK) ||
+		     !is_power_of_2(vma->node.size) ||
+		     (vma->node.start & (vma->node.size - 1)),
+		     "object 0x%08llx [fenceable? %d] not 1M or pot-size (0x%08llx) aligned\n",
+		     vma->node.start, obj->map_and_fenceable, vma->node.size);
 
 		if (tiling == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
 			tile_width = 128;
@@ -144,10 +141,10 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 		pitch_val = stride / tile_width;
 		pitch_val = ffs(pitch_val) - 1;
 
-		val = i915_gem_obj_ggtt_offset(obj);
+		val = vma->node.start;
 		if (tiling == I915_TILING_Y)
 			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
-		val |= I915_FENCE_SIZE_BITS(size);
+		val |= I915_FENCE_SIZE_BITS(vma->node.size);
 		val |= pitch_val << I830_FENCE_PITCH_SHIFT;
 		val |= I830_FENCE_REG_VALID;
 	} else
@@ -161,27 +158,27 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg,
 				struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t val;
+	u32 val;
 
 	if (obj) {
-		u32 size = i915_gem_obj_ggtt_size(obj);
+		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
 		unsigned int tiling = i915_gem_object_get_tiling(obj);
 		unsigned int stride = i915_gem_object_get_stride(obj);
-		uint32_t pitch_val;
+		u32 pitch_val;
 
-		WARN((i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK) ||
-		     (size & -size) != size ||
-		     (i915_gem_obj_ggtt_offset(obj) & (size - 1)),
-		     "object 0x%08llx not 512K or pot-size 0x%08x aligned\n",
-		     i915_gem_obj_ggtt_offset(obj), size);
+		WARN((vma->node.start & ~I830_FENCE_START_MASK) ||
+		     !is_power_of_2(vma->node.size) ||
+		     (vma->node.start & (vma->node.size - 1)),
+		     "object 0x%08llx not 512K or pot-size 0x%08llx aligned\n",
+		     vma->node.start, vma->node.size);
 
 		pitch_val = stride / 128;
 		pitch_val = ffs(pitch_val) - 1;
 
-		val = i915_gem_obj_ggtt_offset(obj);
+		val = vma->node.start;
 		if (tiling == I915_TILING_Y)
 			val |= 1 << I830_FENCE_TILING_Y_SHIFT;
-		val |= I830_FENCE_SIZE_BITS(size);
+		val |= I830_FENCE_SIZE_BITS(vma->node.size);
 		val |= pitch_val << I830_FENCE_PITCH_SHIFT;
 		val |= I830_FENCE_REG_VALID;
 	} else
-- 
2.8.1

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

[PATCH 16/37] drm/i915: Use VMA directly for checking tiling parameters

[Chris Wilson]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_tiling.c | 47 ++++++++++++++++++++--------------
 1 file changed, 28 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index f4b984de83b5..2ceaddc959d3 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -117,34 +117,45 @@ i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 }
 
 /* Is the current GTT allocation valid for the change in tiling? */
-static bool
+static int
 i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct i915_vma *vma;
 	u32 size;
 
 	if (tiling_mode == I915_TILING_NONE)
-		return true;
+		return 0;
 
 	if (INTEL_GEN(dev_priv) >= 4)
-		return true;
+		return 0;
+
+	vma = i915_gem_obj_to_ggtt(obj);
+	if (!vma)
+		return 0;
+
+	if (!obj->map_and_fenceable)
+		return 0;
 
 	if (IS_GEN3(dev_priv)) {
-		if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK)
-			return false;
+		if (vma->node.start & ~I915_FENCE_START_MASK)
+			goto bad;
 	} else {
-		if (i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK)
-			return false;
+		if (vma->node.start & ~I830_FENCE_START_MASK)
+			goto bad;
 	}
 
 	size = i915_gem_get_ggtt_size(dev_priv, obj->base.size, tiling_mode);
-	if (i915_gem_obj_ggtt_size(obj) != size)
-		return false;
+	if (vma->node.size < size)
+		goto bad;
 
-	if (i915_gem_obj_ggtt_offset(obj) & (size - 1))
-		return false;
+	if (vma->node.start & (size - 1))
+		goto bad;
 
-	return true;
+	return 0;
+
+bad:
+	return i915_vma_unbind(vma);
 }
 
 /**
@@ -168,7 +179,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 	struct drm_i915_gem_set_tiling *args = data;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
-	int ret = 0;
+	int err = 0;
 
 	/* Make sure we don't cross-contaminate obj->tiling_and_stride */
 	BUILD_BUG_ON(I915_TILING_LAST & STRIDE_MASK);
@@ -187,7 +198,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 
 	mutex_lock(&dev->struct_mutex);
 	if (obj->pin_display || obj->framebuffer_references) {
-		ret = -EBUSY;
+		err = -EBUSY;
 		goto err;
 	}
 
@@ -234,11 +245,9 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 * has to also include the unfenced register the GPU uses
 		 * whilst executing a fenced command for an untiled object.
 		 */
-		if (obj->map_and_fenceable &&
-		    !i915_gem_object_fence_ok(obj, args->tiling_mode))
-			ret = i915_vma_unbind(i915_gem_obj_to_ggtt(obj));
 
-		if (ret == 0) {
+		err = i915_gem_object_fence_ok(obj, args->tiling_mode);
+		if (!err) {
 			if (obj->pages &&
 			    obj->madv == I915_MADV_WILLNEED &&
 			    dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES) {
@@ -281,7 +290,7 @@ err:
 
 	intel_runtime_pm_put(dev_priv);
 
-	return ret;
+	return err;
 }
 
 /**
-- 
2.8.1

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

[PATCH 17/37] drm/i915: Use VMA as the primary object for context state

[Chris Wilson]

When working with contexts, we most frequently want the GGTT VMA for the
context state, first and foremost. Since the object is available via the
VMA, we need only then store the VMA.

v2: Formatting tweaks to debugfs output, restored some comments removed
in the next patch

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c        | 34 ++++++++--------
 drivers/gpu/drm/i915/i915_drv.h            |  3 +-
 drivers/gpu/drm/i915/i915_gem_context.c    | 51 +++++++++++++-----------
 drivers/gpu/drm/i915/i915_gpu_error.c      |  7 ++--
 drivers/gpu/drm/i915/i915_guc_submission.c |  6 +--
 drivers/gpu/drm/i915/intel_lrc.c           | 64 +++++++++++++++---------------
 drivers/gpu/drm/i915/intel_ringbuffer.c    |  6 +--
 7 files changed, 86 insertions(+), 85 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 32d26b6c4bca..fcda4e7da127 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -354,7 +354,7 @@ static int per_file_ctx_stats(int id, void *ptr, void *data)
 
 	for (n = 0; n < ARRAY_SIZE(ctx->engine); n++) {
 		if (ctx->engine[n].state)
-			per_file_stats(0, ctx->engine[n].state, data);
+			per_file_stats(0, ctx->engine[n].state->obj, data);
 		if (ctx->engine[n].ring)
 			per_file_stats(0, ctx->engine[n].ring->obj, data);
 	}
@@ -1977,7 +1977,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 			seq_printf(m, "%s: ", engine->name);
 			seq_putc(m, ce->initialised ? 'I' : 'i');
 			if (ce->state)
-				describe_obj(m, ce->state);
+				describe_obj(m, ce->state->obj);
 			if (ce->ring)
 				describe_ctx_ring(m, ce->ring);
 			seq_putc(m, '\n');
@@ -1995,36 +1995,34 @@ static void i915_dump_lrc_obj(struct seq_file *m,
 			      struct i915_gem_context *ctx,
 			      struct intel_engine_cs *engine)
 {
-	struct drm_i915_gem_object *ctx_obj = ctx->engine[engine->id].state;
+	struct i915_vma *vma = ctx->engine[engine->id].state;
 	struct page *page;
-	uint32_t *reg_state;
 	int j;
-	unsigned long ggtt_offset = 0;
 
 	seq_printf(m, "CONTEXT: %s %u\n", engine->name, ctx->hw_id);
 
-	if (ctx_obj == NULL) {
-		seq_puts(m, "\tNot allocated\n");
+	if (!vma) {
+		seq_puts(m, "\tFake context\n");
 		return;
 	}
 
-	if (!i915_gem_obj_ggtt_bound(ctx_obj))
-		seq_puts(m, "\tNot bound in GGTT\n");
-	else
-		ggtt_offset = i915_gem_obj_ggtt_offset(ctx_obj);
+	if (vma->flags & I915_VMA_GLOBAL_BIND)
+		seq_printf(m, "\tBound in GGTT at 0x%08x\n",
+			   lower_32_bits(vma->node.start));
 
-	if (i915_gem_object_get_pages(ctx_obj)) {
-		seq_puts(m, "\tFailed to get pages for context object\n");
+	if (i915_gem_object_get_pages(vma->obj)) {
+		seq_puts(m, "\tFailed to get pages for context object\n\n");
 		return;
 	}
 
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	if (!WARN_ON(page == NULL)) {
-		reg_state = kmap_atomic(page);
+	page = i915_gem_object_get_page(vma->obj, LRC_STATE_PN);
+	if (page) {
+		u32 *reg_state = kmap_atomic(page);
 
 		for (j = 0; j < 0x600 / sizeof(u32) / 4; j += 4) {
-			seq_printf(m, "\t[0x%08lx] 0x%08x 0x%08x 0x%08x 0x%08x\n",
-				   ggtt_offset + 4096 + (j * 4),
+			seq_printf(m,
+				   "\t[0x%04x] 0x%08x 0x%08x 0x%08x 0x%08x\n",
+				   j * 4,
 				   reg_state[j], reg_state[j + 1],
 				   reg_state[j + 2], reg_state[j + 3]);
 		}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 873ffe8bfe89..310eaab21c15 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -896,9 +896,8 @@ struct i915_gem_context {
 	u32 ggtt_alignment;
 
 	struct intel_context {
-		struct drm_i915_gem_object *state;
+		struct i915_vma *state;
 		struct intel_ring *ring;
-		struct i915_vma *lrc_vma;
 		uint32_t *lrc_reg_state;
 		u64 lrc_desc;
 		int pin_count;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 547caf26a6b9..3857ce097c84 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -155,7 +155,7 @@ void i915_gem_context_free(struct kref *ctx_ref)
 		if (ce->ring)
 			intel_ring_free(ce->ring);
 
-		i915_gem_object_put(ce->state);
+		i915_vma_put(ce->state);
 	}
 
 	list_del(&ctx->link);
@@ -281,13 +281,24 @@ __create_hw_context(struct drm_device *dev,
 	ctx->ggtt_alignment = get_context_alignment(dev_priv);
 
 	if (dev_priv->hw_context_size) {
-		struct drm_i915_gem_object *obj =
-				i915_gem_alloc_context_obj(dev, dev_priv->hw_context_size);
+		struct drm_i915_gem_object *obj;
+		struct i915_vma *vma;
+
+		obj = i915_gem_alloc_context_obj(dev,
+						 dev_priv->hw_context_size);
 		if (IS_ERR(obj)) {
 			ret = PTR_ERR(obj);
 			goto err_out;
 		}
-		ctx->engine[RCS].state = obj;
+
+		vma = i915_vma_create(obj, &dev_priv->ggtt.base, NULL);
+		if (IS_ERR(vma)) {
+			i915_gem_object_put(obj);
+			ret = PTR_ERR(vma);
+			goto err_out;
+		}
+
+		ctx->engine[RCS].state = vma;
 	}
 
 	/* Default context will never have a file_priv */
@@ -399,7 +410,7 @@ static void i915_gem_context_unpin(struct i915_gem_context *ctx,
 		struct intel_context *ce = &ctx->engine[engine->id];
 
 		if (ce->state)
-			i915_gem_object_ggtt_unpin(ce->state);
+			i915_vma_unpin(ce->state);
 
 		i915_gem_context_put(ctx);
 	}
@@ -620,9 +631,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring,
-			i915_gem_obj_ggtt_offset(req->ctx->engine[RCS].state) |
-			flags);
+	intel_ring_emit(ring, req->ctx->engine[RCS].state->node.start | flags);
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -755,6 +764,7 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	struct i915_gem_context *to = req->ctx;
 	struct intel_engine_cs *engine = req->engine;
 	struct i915_hw_ppgtt *ppgtt = to->ppgtt ?: req->i915->mm.aliasing_ppgtt;
+	struct i915_vma *vma = to->engine[RCS].state;
 	struct i915_gem_context *from;
 	u32 hw_flags;
 	int ret, i;
@@ -763,8 +773,7 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 		return 0;
 
 	/* Trying to pin first makes error handling easier. */
-	ret = i915_gem_object_ggtt_pin(to->engine[RCS].state, NULL, 0,
-				       to->ggtt_alignment, 0);
+	ret = i915_vma_pin(vma, 0, to->ggtt_alignment, PIN_GLOBAL);
 	if (ret)
 		return ret;
 
@@ -785,9 +794,9 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	 *
 	 * XXX: We need a real interface to do this instead of trickery.
 	 */
-	ret = i915_gem_object_set_to_gtt_domain(to->engine[RCS].state, false);
+	ret = i915_gem_object_set_to_gtt_domain(vma->obj, false);
 	if (ret)
-		goto unpin_out;
+		goto err;
 
 	if (needs_pd_load_pre(ppgtt, engine, to)) {
 		/* Older GENs and non render rings still want the load first,
@@ -797,7 +806,7 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 		trace_switch_mm(engine, to);
 		ret = ppgtt->switch_mm(ppgtt, req);
 		if (ret)
-			goto unpin_out;
+			goto err;
 	}
 
 	if (!to->engine[RCS].initialised || i915_gem_context_is_default(to))
@@ -814,7 +823,7 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	if (to != from || (hw_flags & MI_FORCE_RESTORE)) {
 		ret = mi_set_context(req, hw_flags);
 		if (ret)
-			goto unpin_out;
+			goto err;
 	}
 
 	/* The backing object for the context is done after switching to the
@@ -824,8 +833,6 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	 * MI_SET_CONTEXT instead of when the next seqno has completed.
 	 */
 	if (from != NULL) {
-		struct drm_i915_gem_object *obj = from->engine[RCS].state;
-
 		/* As long as MI_SET_CONTEXT is serializing, ie. it flushes the
 		 * whole damn pipeline, we don't need to explicitly mark the
 		 * object dirty. The only exception is that the context must be
@@ -833,11 +840,9 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 		 * able to defer doing this until we know the object would be
 		 * swapped, but there is no way to do that yet.
 		 */
-		obj->base.read_domains = I915_GEM_DOMAIN_INSTRUCTION;
-		i915_vma_move_to_active(i915_gem_obj_to_ggtt(obj), req, 0);
-
-		/* obj is kept alive until the next request by its active ref */
-		i915_gem_object_ggtt_unpin(obj);
+		i915_vma_move_to_active(from->engine[RCS].state, req, 0);
+		/* state is kept alive until the next request */
+		i915_vma_unpin(from->engine[RCS].state);
 		i915_gem_context_put(from);
 	}
 	engine->last_context = i915_gem_context_get(to);
@@ -882,8 +887,8 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 
 	return 0;
 
-unpin_out:
-	i915_gem_object_ggtt_unpin(to->engine[RCS].state);
+err:
+	i915_vma_unpin(vma);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index a87a5c489e2e..eebce0427296 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1097,9 +1097,10 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 					i915_error_ggtt_object_create(dev_priv,
 								      engine->scratch.obj);
 
-			ee->ctx =
-				i915_error_ggtt_object_create(dev_priv,
-							      request->ctx->engine[i].state);
+			if (request->ctx->engine[i].state) {
+				ee->ctx = i915_error_ggtt_object_create(dev_priv,
+									request->ctx->engine[i].state->obj);
+			}
 
 			if (request->pid) {
 				struct task_struct *task;
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 4b20263e45d0..def13037a8be 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -358,7 +358,7 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 		lrc->context_desc = lower_32_bits(ce->lrc_desc);
 
 		/* The state page is after PPHWSP */
-		gfx_addr = i915_gem_obj_ggtt_offset(ce->state);
+		gfx_addr = ce->state->node.start;
 		lrc->ring_lcra = gfx_addr + LRC_STATE_PN * PAGE_SIZE;
 		lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
 				(guc_engine_id << GUC_ELC_ENGINE_OFFSET);
@@ -1078,7 +1078,7 @@ int intel_guc_suspend(struct drm_device *dev)
 	/* any value greater than GUC_POWER_D0 */
 	data[1] = GUC_POWER_D1;
 	/* first page is shared data with GuC */
-	data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state);
+	data[2] = ctx->engine[RCS].state->node.start;
 
 	return host2guc_action(guc, data, ARRAY_SIZE(data));
 }
@@ -1103,7 +1103,7 @@ int intel_guc_resume(struct drm_device *dev)
 	data[0] = HOST2GUC_ACTION_EXIT_S_STATE;
 	data[1] = GUC_POWER_D0;
 	/* first page is shared data with GuC */
-	data[2] = i915_gem_obj_ggtt_offset(ctx->engine[RCS].state);
+	data[2] = ctx->engine[RCS].state->node.start;
 
 	return host2guc_action(guc, data, ARRAY_SIZE(data));
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c7f4b64b16f6..74c08bf5d136 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -315,7 +315,7 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 
 	desc = ctx->desc_template;				/* bits  3-4  */
 	desc |= engine->ctx_desc_template;			/* bits  0-11 */
-	desc |= ce->lrc_vma->node.start + LRC_PPHWSP_PN * PAGE_SIZE;
+	desc |= ce->state->node.start + LRC_PPHWSP_PN * PAGE_SIZE;
 								/* bits 12-31 */
 	desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT;		/* bits 32-52 */
 
@@ -763,7 +763,6 @@ void intel_execlists_cancel_requests(struct intel_engine_cs *engine)
 static int intel_lr_context_pin(struct i915_gem_context *ctx,
 				struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = ctx->i915;
 	struct intel_context *ce = &ctx->engine[engine->id];
 	void *vaddr;
 	u32 *lrc_reg_state;
@@ -774,16 +773,15 @@ static int intel_lr_context_pin(struct i915_gem_context *ctx,
 	if (ce->pin_count++)
 		return 0;
 
-	ret = i915_gem_object_ggtt_pin(ce->state, NULL,
-				       0, GEN8_LR_CONTEXT_ALIGN,
-				       PIN_OFFSET_BIAS | GUC_WOPCM_TOP);
+	ret = i915_vma_pin(ce->state, 0, GEN8_LR_CONTEXT_ALIGN,
+			   PIN_OFFSET_BIAS | GUC_WOPCM_TOP | PIN_GLOBAL);
 	if (ret)
 		goto err;
 
-	vaddr = i915_gem_object_pin_map(ce->state);
+	vaddr = i915_gem_object_pin_map(ce->state->obj);
 	if (IS_ERR(vaddr)) {
 		ret = PTR_ERR(vaddr);
-		goto unpin_ctx_obj;
+		goto unpin_vma;
 	}
 
 	lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
@@ -792,24 +790,25 @@ static int intel_lr_context_pin(struct i915_gem_context *ctx,
 	if (ret)
 		goto unpin_map;
 
-	ce->lrc_vma = i915_gem_obj_to_ggtt(ce->state);
 	intel_lr_context_descriptor_update(ctx, engine);
 
 	lrc_reg_state[CTX_RING_BUFFER_START+1] = ce->ring->vma->node.start;
 	ce->lrc_reg_state = lrc_reg_state;
-	ce->state->dirty = true;
+	ce->state->obj->dirty = true;
 
 	/* Invalidate GuC TLB. */
-	if (i915.enable_guc_submission)
+	if (i915.enable_guc_submission) {
+		struct drm_i915_private *dev_priv = ctx->i915;
 		I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+	}
 
 	i915_gem_context_get(ctx);
 	return 0;
 
 unpin_map:
-	i915_gem_object_unpin_map(ce->state);
-unpin_ctx_obj:
-	i915_gem_object_ggtt_unpin(ce->state);
+	i915_gem_object_unpin_map(ce->state->obj);
+unpin_vma:
+	__i915_vma_unpin(ce->state);
 err:
 	ce->pin_count = 0;
 	return ret;
@@ -828,12 +827,8 @@ void intel_lr_context_unpin(struct i915_gem_context *ctx,
 
 	intel_ring_unpin(ce->ring);
 
-	i915_gem_object_unpin_map(ce->state);
-	i915_gem_object_ggtt_unpin(ce->state);
-
-	ce->lrc_vma = NULL;
-	ce->lrc_desc = 0;
-	ce->lrc_reg_state = NULL;
+	i915_gem_object_unpin_map(ce->state->obj);
+	i915_vma_unpin(ce->state);
 
 	i915_gem_context_put(ctx);
 }
@@ -1747,19 +1742,18 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 }
 
 static int
-lrc_setup_hws(struct intel_engine_cs *engine,
-	      struct drm_i915_gem_object *dctx_obj)
+lrc_setup_hws(struct intel_engine_cs *engine, struct i915_vma *vma)
 {
 	void *hws;
 
 	/* The HWSP is part of the default context object in LRC mode. */
-	engine->status_page.gfx_addr = i915_gem_obj_ggtt_offset(dctx_obj) +
-				       LRC_PPHWSP_PN * PAGE_SIZE;
-	hws = i915_gem_object_pin_map(dctx_obj);
+	engine->status_page.gfx_addr =
+		vma->node.start + LRC_PPHWSP_PN * PAGE_SIZE;
+	hws = i915_gem_object_pin_map(vma->obj);
 	if (IS_ERR(hws))
 		return PTR_ERR(hws);
 	engine->status_page.page_addr = hws + LRC_PPHWSP_PN * PAGE_SIZE;
-	engine->status_page.obj = dctx_obj;
+	engine->status_page.obj = vma->obj;
 
 	return 0;
 }
@@ -2131,6 +2125,7 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 {
 	struct drm_i915_gem_object *ctx_obj;
 	struct intel_context *ce = &ctx->engine[engine->id];
+	struct i915_vma *vma;
 	uint32_t context_size;
 	struct intel_ring *ring;
 	int ret;
@@ -2148,6 +2143,12 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 		return PTR_ERR(ctx_obj);
 	}
 
+	vma = i915_vma_create(ctx_obj, &ctx->i915->ggtt.base, NULL);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto error_deref_obj;
+	}
+
 	ring = intel_engine_create_ring(engine, ctx->ring_size);
 	if (IS_ERR(ring)) {
 		ret = PTR_ERR(ring);
@@ -2161,7 +2162,7 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 	}
 
 	ce->ring = ring;
-	ce->state = ctx_obj;
+	ce->state = vma;
 	ce->initialised = engine->init_context == NULL;
 
 	return 0;
@@ -2170,8 +2171,6 @@ error_ring_free:
 	intel_ring_free(ring);
 error_deref_obj:
 	i915_gem_object_put(ctx_obj);
-	ce->ring = NULL;
-	ce->state = NULL;
 	return ret;
 }
 
@@ -2182,24 +2181,23 @@ void intel_lr_context_reset(struct drm_i915_private *dev_priv,
 
 	for_each_engine(engine, dev_priv) {
 		struct intel_context *ce = &ctx->engine[engine->id];
-		struct drm_i915_gem_object *ctx_obj = ce->state;
 		void *vaddr;
 		uint32_t *reg_state;
 
-		if (!ctx_obj)
+		if (!ce->state)
 			continue;
 
-		vaddr = i915_gem_object_pin_map(ctx_obj);
+		vaddr = i915_gem_object_pin_map(ce->state->obj);
 		if (WARN_ON(IS_ERR(vaddr)))
 			continue;
 
 		reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
-		ctx_obj->dirty = true;
 
 		reg_state[CTX_RING_HEAD+1] = 0;
 		reg_state[CTX_RING_TAIL+1] = 0;
 
-		i915_gem_object_unpin_map(ctx_obj);
+		ce->state->obj->dirty = true;
+		i915_gem_object_unpin_map(ce->state->obj);
 
 		ce->ring->head = 0;
 		ce->ring->tail = 0;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ed19868df9c6..0bbf8500c174 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2092,8 +2092,8 @@ static int intel_ring_context_pin(struct i915_gem_context *ctx,
 		return 0;
 
 	if (ce->state) {
-		ret = i915_gem_object_ggtt_pin(ce->state, NULL, 0,
-					       ctx->ggtt_alignment, PIN_HIGH);
+		ret = i915_vma_pin(ce->state, 0, ctx->ggtt_alignment,
+				   PIN_GLOBAL | PIN_HIGH);
 		if (ret)
 			goto error;
 	}
@@ -2127,7 +2127,7 @@ static void intel_ring_context_unpin(struct i915_gem_context *ctx,
 		return;
 
 	if (ce->state)
-		i915_gem_object_ggtt_unpin(ce->state);
+		i915_vma_unpin(ce->state);
 
 	i915_gem_context_put(ctx);
 }
-- 
2.8.1

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

[PATCH 18/37] drm/i915: Only clflush the context object when binding

[Chris Wilson]

We know that the only access to the context object is via the GPU, and
the only time when it can be out of the GPU domain is when it is swapped
out and unbound. Therefore we only need to clflush the object when
binding.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_context.c | 19 +++++++------------
 drivers/gpu/drm/i915/intel_ringbuffer.c |  4 ++++
 2 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 3857ce097c84..824dfe14bcd0 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -772,6 +772,13 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	if (skip_rcs_switch(ppgtt, engine, to))
 		return 0;
 
+	/* Clear this page out of any CPU caches for coherent swap-in/out. */
+	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
+		ret = i915_gem_object_set_to_gtt_domain(vma->obj, false);
+		if (ret)
+			return ret;
+	}
+
 	/* Trying to pin first makes error handling easier. */
 	ret = i915_vma_pin(vma, 0, to->ggtt_alignment, PIN_GLOBAL);
 	if (ret)
@@ -786,18 +793,6 @@ static int do_rcs_switch(struct drm_i915_gem_request *req)
 	 */
 	from = engine->last_context;
 
-	/*
-	 * Clear this page out of any CPU caches for coherent swap-in/out. Note
-	 * that thanks to write = false in this call and us not setting any gpu
-	 * write domains when putting a context object onto the active list
-	 * (when switching away from it), this won't block.
-	 *
-	 * XXX: We need a real interface to do this instead of trickery.
-	 */
-	ret = i915_gem_object_set_to_gtt_domain(vma->obj, false);
-	if (ret)
-		goto err;
-
 	if (needs_pd_load_pre(ppgtt, engine, to)) {
 		/* Older GENs and non render rings still want the load first,
 		 * "PP_DCLV followed by PP_DIR_BASE register through Load
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 0bbf8500c174..27a284619a27 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2092,6 +2092,10 @@ static int intel_ring_context_pin(struct i915_gem_context *ctx,
 		return 0;
 
 	if (ce->state) {
+		ret = i915_gem_object_set_to_gtt_domain(ce->state->obj, false);
+		if (ret)
+			goto error;
+
 		ret = i915_vma_pin(ce->state, 0, ctx->ggtt_alignment,
 				   PIN_GLOBAL | PIN_HIGH);
 		if (ret)
-- 
2.8.1

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

[PATCH 19/37] drm/i915: Move assertion for iomap access to i915_vma_pin_iomap

[Chris Wilson]

Access through the GTT requires the device to be awake. Ideally
i915_vma_pin_iomap() is short-lived and the pinning demarcates the
access through the iomap. This is not entirely true, we have a mixture
of long lived pins that exceed the wakelock (such as legacy ringbuffers)
and short lived pin that do live within the wakelock (such as execlist
ringbuffers).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c     | 3 +++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 3 ---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 1bec50bd651b..738a474c5afa 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3650,6 +3650,9 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 {
 	void __iomem *ptr;
 
+	/* Access through the GTT requires the device to be awake. */
+	assert_rpm_wakelock_held(to_i915(vma->vm->dev));
+
 	lockdep_assert_held(&vma->vm->dev->struct_mutex);
 	if (WARN_ON(!vma->obj->map_and_fenceable))
 		return IO_ERR_PTR(-ENODEV);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 27a284619a27..d2c84bb998e6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1966,9 +1966,6 @@ int intel_ring_pin(struct intel_ring *ring)
 		if (ret)
 			goto err_unpin;
 
-		/* Access through the GTT requires the device to be awake. */
-		assert_rpm_wakelock_held(dev_priv);
-
 		addr = (void __force *)
 			i915_vma_pin_iomap(i915_gem_obj_to_ggtt(obj));
 		if (IS_ERR(addr)) {
-- 
2.8.1

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

[PATCH 20/37] drm/i915: Use VMA for ringbuffer tracking

[Chris Wilson]

Use the GGTT VMA as the primary cookie for handing ring objects as
the most common action upon the ring is mapping and unmapping which act
upon the VMA itself. By restructuring the code to work with the ring
VMA, we can shrink the code and remove a few cycles from context pinning.

v2: Move the flush of the object back to before the first pin. We use
the am-I-bound? query to only have to check the flush on the first
bind and so avoid stalling on active rings.
Lots of little renames and small hoops.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c        |   2 +-
 drivers/gpu/drm/i915/i915_gpu_error.c      |   4 +-
 drivers/gpu/drm/i915/i915_guc_submission.c |  16 +-
 drivers/gpu/drm/i915/intel_lrc.c           |  17 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 242 ++++++++++++++---------------
 drivers/gpu/drm/i915/intel_ringbuffer.h    |  14 +-
 6 files changed, 138 insertions(+), 157 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fcda4e7da127..2da37c196ef0 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -356,7 +356,7 @@ static int per_file_ctx_stats(int id, void *ptr, void *data)
 		if (ctx->engine[n].state)
 			per_file_stats(0, ctx->engine[n].state->obj, data);
 		if (ctx->engine[n].ring)
-			per_file_stats(0, ctx->engine[n].ring->obj, data);
+			per_file_stats(0, ctx->engine[n].ring->vma->obj, data);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index eebce0427296..2f6bf6391036 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1122,12 +1122,12 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			ee->cpu_ring_tail = ring->tail;
 			ee->ringbuffer =
 				i915_error_ggtt_object_create(dev_priv,
-							      ring->obj);
+							      ring->vma->obj);
 		}
 
 		ee->hws_page =
 			i915_error_ggtt_object_create(dev_priv,
-						      engine->status_page.obj);
+						      engine->status_page.vma->obj);
 
 		ee->wa_ctx = i915_error_ggtt_object_create(dev_priv,
 							   engine->wa_ctx.obj);
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index def13037a8be..7227f97d8040 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -343,7 +343,6 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 		struct intel_context *ce = &ctx->engine[engine->id];
 		uint32_t guc_engine_id = engine->guc_id;
 		struct guc_execlist_context *lrc = &desc.lrc[guc_engine_id];
-		struct drm_i915_gem_object *obj;
 
 		/* TODO: We have a design issue to be solved here. Only when we
 		 * receive the first batch, we know which engine is used by the
@@ -358,17 +357,14 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 		lrc->context_desc = lower_32_bits(ce->lrc_desc);
 
 		/* The state page is after PPHWSP */
-		gfx_addr = ce->state->node.start;
-		lrc->ring_lcra = gfx_addr + LRC_STATE_PN * PAGE_SIZE;
+		lrc->ring_lcra =
+			ce->state->node.start + LRC_STATE_PN * PAGE_SIZE;
 		lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
 				(guc_engine_id << GUC_ELC_ENGINE_OFFSET);
 
-		obj = ce->ring->obj;
-		gfx_addr = i915_gem_obj_ggtt_offset(obj);
-
-		lrc->ring_begin = gfx_addr;
-		lrc->ring_end = gfx_addr + obj->base.size - 1;
-		lrc->ring_next_free_location = gfx_addr;
+		lrc->ring_begin = ce->ring->vma->node.start;
+		lrc->ring_end = lrc->ring_begin + ce->ring->size - 1;
+		lrc->ring_next_free_location = lrc->ring_begin;
 		lrc->ring_current_tail_pointer_value = 0;
 
 		desc.engines_used |= (1 << guc_engine_id);
@@ -941,7 +937,7 @@ static void guc_create_ads(struct intel_guc *guc)
 	 * to find it.
 	 */
 	engine = &dev_priv->engine[RCS];
-	ads->golden_context_lrca = engine->status_page.gfx_addr;
+	ads->golden_context_lrca = engine->status_page.ggtt_offset;
 
 	for_each_engine(engine, dev_priv)
 		ads->eng_state_size[engine->guc_id] = intel_lr_context_size(engine);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 74c08bf5d136..3c5137d9c3b9 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1273,7 +1273,7 @@ static void lrc_init_hws(struct intel_engine_cs *engine)
 	struct drm_i915_private *dev_priv = engine->i915;
 
 	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
-		   (u32)engine->status_page.gfx_addr);
+		   engine->status_page.ggtt_offset);
 	POSTING_READ(RING_HWS_PGA(engine->mmio_base));
 }
 
@@ -1695,9 +1695,9 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 
 	intel_engine_cleanup_common(engine);
 
-	if (engine->status_page.obj) {
-		i915_gem_object_unpin_map(engine->status_page.obj);
-		engine->status_page.obj = NULL;
+	if (engine->status_page.vma) {
+		i915_gem_object_unpin_map(engine->status_page.vma->obj);
+		engine->status_page.vma = NULL;
 	}
 	intel_lr_context_unpin(dev_priv->kernel_context, engine);
 
@@ -1744,16 +1744,17 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 static int
 lrc_setup_hws(struct intel_engine_cs *engine, struct i915_vma *vma)
 {
+	const int hws_offset = LRC_PPHWSP_PN * PAGE_SIZE;
 	void *hws;
 
 	/* The HWSP is part of the default context object in LRC mode. */
-	engine->status_page.gfx_addr =
-		vma->node.start + LRC_PPHWSP_PN * PAGE_SIZE;
 	hws = i915_gem_object_pin_map(vma->obj);
 	if (IS_ERR(hws))
 		return PTR_ERR(hws);
-	engine->status_page.page_addr = hws + LRC_PPHWSP_PN * PAGE_SIZE;
-	engine->status_page.obj = vma->obj;
+
+	engine->status_page.page_addr = hws + hws_offset;
+	engine->status_page.ggtt_offset = vma->node.start + hws_offset;
+	engine->status_page.vma = vma;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d2c84bb998e6..3f1ef8edd405 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -466,7 +466,7 @@ static void intel_ring_setup_status_page(struct intel_engine_cs *engine)
 		mmio = RING_HWS_PGA(engine->mmio_base);
 	}
 
-	I915_WRITE(mmio, (u32)engine->status_page.gfx_addr);
+	I915_WRITE(mmio, engine->status_page.ggtt_offset);
 	POSTING_READ(mmio);
 
 	/*
@@ -531,7 +531,6 @@ static int init_ring_common(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 	struct intel_ring *ring = engine->buffer;
-	struct drm_i915_gem_object *obj = ring->obj;
 	int ret = 0;
 
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
@@ -571,7 +570,7 @@ static int init_ring_common(struct intel_engine_cs *engine)
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
 	 * register values. */
-	I915_WRITE_START(engine, i915_gem_obj_ggtt_offset(obj));
+	I915_WRITE_START(engine, ring->vma->node.start);
 
 	/* WaClearRingBufHeadRegAtInit:ctg,elk */
 	if (I915_READ_HEAD(engine))
@@ -586,16 +585,16 @@ static int init_ring_common(struct intel_engine_cs *engine)
 
 	/* If the head is still not zero, the ring is dead */
 	if (wait_for((I915_READ_CTL(engine) & RING_VALID) != 0 &&
-		     I915_READ_START(engine) == i915_gem_obj_ggtt_offset(obj) &&
+		     I915_READ_START(engine) == ring->vma->node.start &&
 		     (I915_READ_HEAD(engine) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
-			  "ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08lx]\n",
+			  "ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08llx]\n",
 			  engine->name,
 			  I915_READ_CTL(engine),
 			  I915_READ_CTL(engine) & RING_VALID,
 			  I915_READ_HEAD(engine), I915_READ_TAIL(engine),
 			  I915_READ_START(engine),
-			  (unsigned long)i915_gem_obj_ggtt_offset(obj));
+			  ring->vma->node.start);
 		ret = -EIO;
 		goto out;
 	}
@@ -1853,79 +1852,78 @@ static void cleanup_phys_status_page(struct intel_engine_cs *engine)
 
 static void cleanup_status_page(struct intel_engine_cs *engine)
 {
-	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 
-	obj = engine->status_page.obj;
-	if (obj == NULL)
+	vma = fetch_and_zero(&engine->status_page.vma);
+	if (!vma)
 		return;
 
-	kunmap(sg_page(obj->pages->sgl));
-	i915_gem_object_ggtt_unpin(obj);
-	i915_gem_object_put(obj);
-	engine->status_page.obj = NULL;
+	i915_vma_unpin(vma);
+	i915_gem_object_unpin_map(vma->obj);
+	i915_vma_put(vma);
 }
 
 static int init_status_page(struct intel_engine_cs *engine)
 {
-	struct drm_i915_gem_object *obj = engine->status_page.obj;
-
-	if (obj == NULL) {
-		unsigned flags;
-		int ret;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	unsigned int flags;
+	int ret;
 
-		obj = i915_gem_object_create(&engine->i915->drm, 4096);
-		if (IS_ERR(obj)) {
-			DRM_ERROR("Failed to allocate status page\n");
-			return PTR_ERR(obj);
-		}
+	obj = i915_gem_object_create(&engine->i915->drm, 4096);
+	if (IS_ERR(obj)) {
+		DRM_ERROR("Failed to allocate status page\n");
+		return PTR_ERR(obj);
+	}
 
-		ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
-		if (ret)
-			goto err_unref;
-
-		flags = 0;
-		if (!HAS_LLC(engine->i915))
-			/* On g33, we cannot place HWS above 256MiB, so
-			 * restrict its pinning to the low mappable arena.
-			 * Though this restriction is not documented for
-			 * gen4, gen5, or byt, they also behave similarly
-			 * and hang if the HWS is placed at the top of the
-			 * GTT. To generalise, it appears that all !llc
-			 * platforms have issues with us placing the HWS
-			 * above the mappable region (even though we never
-			 * actualy map it).
-			 */
-			flags |= PIN_MAPPABLE;
-		ret = i915_gem_object_ggtt_pin(obj, NULL, 0, 4096, flags);
-		if (ret) {
-err_unref:
-			i915_gem_object_put(obj);
-			return ret;
-		}
+	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
+	if (ret)
+		goto err;
 
-		engine->status_page.obj = obj;
+	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err;
 	}
 
-	engine->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
-	engine->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
-	memset(engine->status_page.page_addr, 0, PAGE_SIZE);
+	flags = PIN_GLOBAL;
+	if (!HAS_LLC(engine->i915))
+		/* On g33, we cannot place HWS above 256MiB, so
+		 * restrict its pinning to the low mappable arena.
+		 * Though this restriction is not documented for
+		 * gen4, gen5, or byt, they also behave similarly
+		 * and hang if the HWS is placed at the top of the
+		 * GTT. To generalise, it appears that all !llc
+		 * platforms have issues with us placing the HWS
+		 * above the mappable region (even though we never
+		 * actualy map it).
+		 */
+		flags |= PIN_MAPPABLE;
+	ret = i915_vma_pin(vma, 0, 4096, flags);
+	if (ret)
+		goto err;
 
-	DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
-			engine->name, engine->status_page.gfx_addr);
+	engine->status_page.vma = vma;
+	engine->status_page.ggtt_offset = vma->node.start;
+	engine->status_page.page_addr = i915_gem_object_pin_map(obj);
 
+	DRM_DEBUG_DRIVER("%s hws offset: 0x%08llx\n",
+			 engine->name, vma->node.start);
 	return 0;
+
+err:
+	i915_gem_object_put(obj);
+	return ret;
 }
 
 static int init_phys_status_page(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 
-	if (!dev_priv->status_page_dmah) {
-		dev_priv->status_page_dmah =
-			drm_pci_alloc(&dev_priv->drm, PAGE_SIZE, PAGE_SIZE);
-		if (!dev_priv->status_page_dmah)
-			return -ENOMEM;
-	}
+	dev_priv->status_page_dmah =
+		drm_pci_alloc(&dev_priv->drm, PAGE_SIZE, PAGE_SIZE);
+	if (!dev_priv->status_page_dmah)
+		return -ENOMEM;
 
 	engine->status_page.page_addr = dev_priv->status_page_dmah->vaddr;
 	memset(engine->status_page.page_addr, 0, PAGE_SIZE);
@@ -1935,52 +1933,43 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
 
 int intel_ring_pin(struct intel_ring *ring)
 {
-	struct drm_i915_private *dev_priv = ring->engine->i915;
-	struct drm_i915_gem_object *obj = ring->obj;
 	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
-	unsigned flags = PIN_OFFSET_BIAS | 4096;
+	unsigned int flags = PIN_GLOBAL | PIN_OFFSET_BIAS | 4096;
+	struct i915_vma *vma = ring->vma;
 	void *addr;
 	int ret;
 
-	if (HAS_LLC(dev_priv) && !obj->stolen) {
-		ret = i915_gem_object_ggtt_pin(obj, NULL, 0, PAGE_SIZE, flags);
-		if (ret)
-			return ret;
+	GEM_BUG_ON(ring->vaddr);
 
-		ret = i915_gem_object_set_to_cpu_domain(obj, true);
-		if (ret)
-			goto err_unpin;
+	if (ring->needs_iomap)
+		flags |= PIN_MAPPABLE;
 
-		addr = i915_gem_object_pin_map(obj);
-		if (IS_ERR(addr)) {
-			ret = PTR_ERR(addr);
-			goto err_unpin;
-		}
-	} else {
-		ret = i915_gem_object_ggtt_pin(obj, NULL, 0, PAGE_SIZE,
-					       flags | PIN_MAPPABLE);
-		if (ret)
+	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
+		if (flags & PIN_MAPPABLE)
+			ret = i915_gem_object_set_to_gtt_domain(vma->obj, true);
+		else
+			ret = i915_gem_object_set_to_cpu_domain(vma->obj, true);
+		if (unlikely(ret))
 			return ret;
+	}
 
-		ret = i915_gem_object_set_to_gtt_domain(obj, true);
-		if (ret)
-			goto err_unpin;
+	ret = i915_vma_pin(vma, 0, PAGE_SIZE, flags);
+	if (unlikely(ret))
+		return ret;
 
-		addr = (void __force *)
-			i915_vma_pin_iomap(i915_gem_obj_to_ggtt(obj));
-		if (IS_ERR(addr)) {
-			ret = PTR_ERR(addr);
-			goto err_unpin;
-		}
-	}
+	if (flags & PIN_MAPPABLE)
+		addr = (void __force *)i915_vma_pin_iomap(vma);
+	else
+		addr = i915_gem_object_pin_map(vma->obj);
+	if (IS_ERR(addr))
+		goto err;
 
 	ring->vaddr = addr;
-	ring->vma = i915_gem_obj_to_ggtt(obj);
 	return 0;
 
-err_unpin:
-	i915_gem_object_ggtt_unpin(obj);
-	return ret;
+err:
+	i915_vma_unpin(vma);
+	return PTR_ERR(addr);
 }
 
 void intel_ring_unpin(struct intel_ring *ring)
@@ -1988,60 +1977,56 @@ void intel_ring_unpin(struct intel_ring *ring)
 	GEM_BUG_ON(!ring->vma);
 	GEM_BUG_ON(!ring->vaddr);
 
-	if (HAS_LLC(ring->engine->i915) && !ring->obj->stolen)
-		i915_gem_object_unpin_map(ring->obj);
-	else
+	if (ring->needs_iomap)
 		i915_vma_unpin_iomap(ring->vma);
+	else
+		i915_gem_object_unpin_map(ring->vma->obj);
 	ring->vaddr = NULL;
 
-	i915_gem_object_ggtt_unpin(ring->obj);
-	ring->vma = NULL;
-}
-
-static void intel_destroy_ringbuffer_obj(struct intel_ring *ring)
-{
-	i915_gem_object_put(ring->obj);
-	ring->obj = NULL;
+	i915_vma_unpin(ring->vma);
 }
 
-static int intel_alloc_ringbuffer_obj(struct drm_device *dev,
-				      struct intel_ring *ring)
+static struct i915_vma *
+intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 {
 	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 
-	obj = NULL;
-	if (!HAS_LLC(dev))
-		obj = i915_gem_object_create_stolen(dev, ring->size);
-	if (obj == NULL)
-		obj = i915_gem_object_create(dev, ring->size);
+	obj = ERR_PTR(-ENODEV);
+	if (!HAS_LLC(dev_priv))
+		obj = i915_gem_object_create_stolen(&dev_priv->drm, size);
 	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+		obj = i915_gem_object_create(&dev_priv->drm, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
 
 	/* mark ring buffers as read-only from GPU side by default */
 	obj->gt_ro = 1;
 
-	ring->obj = obj;
+	vma = i915_vma_create(obj, &dev_priv->ggtt.base, NULL);
+	if (IS_ERR(vma))
+		goto err;
 
-	return 0;
+	return vma;
+
+err:
+	i915_gem_object_put(obj);
+	return vma;
 }
 
 struct intel_ring *
 intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 {
 	struct intel_ring *ring;
-	int ret;
+	struct i915_vma *vma;
 
 	GEM_BUG_ON(!is_power_of_2(size));
 
 	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
-	if (ring == NULL) {
-		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n",
-				 engine->name);
+	if (!ring)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	ring->engine = engine;
-	list_add(&ring->link, &engine->buffers);
 
 	INIT_LIST_HEAD(&ring->request_list);
 
@@ -2057,22 +2042,23 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 	ring->last_retired_head = -1;
 	intel_ring_update_space(ring);
 
-	ret = intel_alloc_ringbuffer_obj(&engine->i915->drm, ring);
-	if (ret) {
-		DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s: %d\n",
-				 engine->name, ret);
-		list_del(&ring->link);
+	vma = intel_ring_create_vma(engine->i915, size);
+	if (IS_ERR(vma)) {
 		kfree(ring);
-		return ERR_PTR(ret);
+		return ERR_CAST(vma);
 	}
+	ring->vma = vma;
+	if (!HAS_LLC(engine->i915) || vma->obj->stolen)
+		ring->needs_iomap = true;
 
+	list_add(&ring->link, &engine->buffers);
 	return ring;
 }
 
 void
 intel_ring_free(struct intel_ring *ring)
 {
-	intel_destroy_ringbuffer_obj(ring);
+	i915_vma_put(ring->vma);
 	list_del(&ring->link);
 	kfree(ring);
 }
@@ -2166,7 +2152,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 		ret = PTR_ERR(ring);
 		goto error;
 	}
-	engine->buffer = ring;
 
 	if (I915_NEED_GFX_HWS(dev_priv)) {
 		ret = init_status_page(engine);
@@ -2181,11 +2166,10 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 
 	ret = intel_ring_pin(ring);
 	if (ret) {
-		DRM_ERROR("Failed to pin and map ringbuffer %s: %d\n",
-				engine->name, ret);
-		intel_destroy_ringbuffer_obj(ring);
+		intel_ring_free(ring);
 		goto error;
 	}
+	engine->buffer = ring;
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ea2735144b2a..bc692d519a72 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -26,10 +26,10 @@
  */
 #define I915_RING_FREE_SPACE 64
 
-struct  intel_hw_status_page {
-	u32		*page_addr;
-	unsigned int	gfx_addr;
-	struct		drm_i915_gem_object *obj;
+struct intel_hw_status_page {
+	struct i915_vma *vma;
+	u32 *page_addr;
+	u32 ggtt_offset;
 };
 
 #define I915_READ_TAIL(engine) I915_READ(RING_TAIL((engine)->mmio_base))
@@ -83,9 +83,8 @@ struct intel_engine_hangcheck {
 };
 
 struct intel_ring {
-	struct drm_i915_gem_object *obj;
-	void *vaddr;
 	struct i915_vma *vma;
+	void *vaddr;
 
 	struct intel_engine_cs *engine;
 	struct list_head link;
@@ -97,6 +96,7 @@ struct intel_ring {
 	int space;
 	int size;
 	int effective_size;
+	bool needs_iomap;
 
 	/** We track the position of the requests in the ring buffer, and
 	 * when each is retired we increment last_retired_head as the GPU
@@ -516,7 +516,7 @@ int init_workarounds_ring(struct intel_engine_cs *engine);
 
 static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
 {
-	return engine->status_page.gfx_addr + I915_GEM_HWS_INDEX_ADDR;
+	return engine->status_page.ggtt_offset + I915_GEM_HWS_INDEX_ADDR;
 }
 
 /* intel_breadcrumbs.c -- user interrupt bottom-half for waiters */
-- 
2.8.1

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

[PATCH 21/37] drm/i915: Use VMA for scratch page tracking

[Chris Wilson]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_context.c |  2 +-
 drivers/gpu/drm/i915/i915_gpu_error.c   |  2 +-
 drivers/gpu/drm/i915/intel_display.c    |  2 +-
 drivers/gpu/drm/i915/intel_lrc.c        | 18 +++++------
 drivers/gpu/drm/i915/intel_ringbuffer.c | 55 +++++++++++++++++++--------------
 drivers/gpu/drm/i915/intel_ringbuffer.h | 10 ++----
 6 files changed, 46 insertions(+), 43 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 824dfe14bcd0..e566167d9441 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -660,7 +660,7 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 					MI_STORE_REGISTER_MEM |
 					MI_SRM_LRM_GLOBAL_GTT);
 			intel_ring_emit_reg(ring, last_reg);
-			intel_ring_emit(ring, engine->scratch.gtt_offset);
+			intel_ring_emit(ring, engine->scratch->node.start);
 			intel_ring_emit(ring, MI_NOOP);
 		}
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 2f6bf6391036..dd60a417a6bc 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1095,7 +1095,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			if (HAS_BROKEN_CS_TLB(dev_priv))
 				ee->wa_batchbuffer =
 					i915_error_ggtt_object_create(dev_priv,
-								      engine->scratch.obj);
+								      engine->scratch->obj);
 
 			if (request->ctx->engine[i].state) {
 				ee->ctx = i915_error_ggtt_object_create(dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index c5c0c35d4f6e..2e7d03c5bf5c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -11795,7 +11795,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 			intel_ring_emit(ring, MI_STORE_REGISTER_MEM |
 					      MI_SRM_LRM_GLOBAL_GTT);
 		intel_ring_emit_reg(ring, DERRMR);
-		intel_ring_emit(ring, req->engine->scratch.gtt_offset + 256);
+		intel_ring_emit(ring, req->engine->scratch->node.start + 256);
 		if (IS_GEN8(dev)) {
 			intel_ring_emit(ring, 0);
 			intel_ring_emit(ring, MI_NOOP);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3c5137d9c3b9..cdcdec83d640 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -914,7 +914,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
-	wa_ctx_emit(batch, index, engine->scratch.gtt_offset + 256);
+	wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
 	wa_ctx_emit(batch, index, 0);
 
 	wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
@@ -932,7 +932,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 	wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
-	wa_ctx_emit(batch, index, engine->scratch.gtt_offset + 256);
+	wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
 	wa_ctx_emit(batch, index, 0);
 
 	return index;
@@ -993,7 +993,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *engine,
 
 	/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
 	/* Actual scratch location is at 128 bytes offset */
-	scratch_addr = engine->scratch.gtt_offset + 2*CACHELINE_BYTES;
+	scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
 
 	wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
 	wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
@@ -1072,8 +1072,8 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
 	/* WaClearSlmSpaceAtContextSwitch:kbl */
 	/* Actual scratch location is at 128 bytes offset */
 	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
-		uint32_t scratch_addr
-			= engine->scratch.gtt_offset + 2*CACHELINE_BYTES;
+		u32 scratch_addr =
+			engine->scratch->node.start + 2 * CACHELINE_BYTES;
 
 		wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
 		wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
@@ -1215,7 +1215,7 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 	}
 
 	/* some WA perform writes to scratch page, ensure it is valid */
-	if (engine->scratch.obj == NULL) {
+	if (!engine->scratch) {
 		DRM_ERROR("scratch page not allocated for %s\n", engine->name);
 		return -EINVAL;
 	}
@@ -1483,7 +1483,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 {
 	struct intel_ring *ring = request->ring;
 	struct intel_engine_cs *engine = request->engine;
-	u32 scratch_addr = engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	u32 scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 flags = 0;
 	int ret;
@@ -1844,11 +1844,11 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
 	else
 		engine->init_hw = gen8_init_render_ring;
 	engine->init_context = gen8_init_rcs_context;
-	engine->cleanup = intel_fini_pipe_control;
+	engine->cleanup = intel_engine_cleanup_scratch;
 	engine->emit_flush = gen8_emit_flush_render;
 	engine->emit_request = gen8_emit_request_render;
 
-	ret = intel_init_pipe_control(engine, 4096);
+	ret = intel_engine_create_scratch(engine, 4096);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 3f1ef8edd405..939632229320 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -176,7 +176,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	int ret;
 
 	ret = intel_ring_begin(req, 6);
@@ -212,7 +212,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -286,7 +286,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -370,7 +370,8 @@ gen8_emit_pipe_control(struct drm_i915_gem_request *req,
 static int
 gen8_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
-	u32 scratch_addr = req->engine->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+	u32 scratch_addr =
+		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -612,45 +613,51 @@ out:
 	return ret;
 }
 
-void intel_fini_pipe_control(struct intel_engine_cs *engine)
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
 {
-	if (engine->scratch.obj == NULL)
+	struct i915_vma *vma;
+
+	vma = fetch_and_zero(&engine->scratch);
+	if (!vma)
 		return;
 
-	i915_gem_object_ggtt_unpin(engine->scratch.obj);
-	i915_gem_object_put(engine->scratch.obj);
-	engine->scratch.obj = NULL;
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
 }
 
-int intel_init_pipe_control(struct intel_engine_cs *engine, int size)
+int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
 {
 	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 	int ret;
 
-	WARN_ON(engine->scratch.obj);
+	WARN_ON(engine->scratch);
 
 	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
 	if (!obj)
 		obj = i915_gem_object_create(&engine->i915->drm, size);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("Failed to allocate scratch page\n");
-		ret = PTR_ERR(obj);
-		goto err;
+		return PTR_ERR(obj);
 	}
 
-	ret = i915_gem_object_ggtt_pin(obj, NULL, 0, 4096, PIN_HIGH);
+	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_unref;
+	}
+
+	ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
 	if (ret)
 		goto err_unref;
 
-	engine->scratch.obj = obj;
-	engine->scratch.gtt_offset = i915_gem_obj_ggtt_offset(obj);
-	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
-			 engine->name, engine->scratch.gtt_offset);
+	engine->scratch = vma;
+	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
+			 engine->name, vma->node.start);
 	return 0;
 
 err_unref:
-	i915_gem_object_put(engine->scratch.obj);
-err:
+	i915_gem_object_put(obj);
 	return ret;
 }
 
@@ -1305,7 +1312,7 @@ static void render_ring_cleanup(struct intel_engine_cs *engine)
 		dev_priv->semaphore_obj = NULL;
 	}
 
-	intel_fini_pipe_control(engine);
+	intel_engine_cleanup_scratch(engine);
 }
 
 static int gen8_rcs_signal(struct drm_i915_gem_request *req)
@@ -1763,7 +1770,7 @@ i830_emit_bb_start(struct drm_i915_gem_request *req,
 		   unsigned int dispatch_flags)
 {
 	struct intel_ring *ring = req->ring;
-	u32 cs_offset = req->engine->scratch.gtt_offset;
+	u32 cs_offset = req->engine->scratch->node.start;
 	int ret;
 
 	ret = intel_ring_begin(req, 6);
@@ -2792,11 +2799,11 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine)
 		return ret;
 
 	if (INTEL_GEN(dev_priv) >= 6) {
-		ret = intel_init_pipe_control(engine, 4096);
+		ret = intel_engine_create_scratch(engine, 4096);
 		if (ret)
 			return ret;
 	} else if (HAS_BROKEN_CS_TLB(dev_priv)) {
-		ret = intel_init_pipe_control(engine, I830_WA_SIZE);
+		ret = intel_engine_create_scratch(engine, I830_WA_SIZE);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index bc692d519a72..c6024db75f93 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -198,6 +198,7 @@ struct intel_engine_cs {
 
 	struct intel_hw_status_page status_page;
 	struct i915_ctx_workarounds wa_ctx;
+	struct i915_vma *scratch;
 
 	u32             irq_keep_mask; /* always keep these interrupts */
 	u32		irq_enable_mask; /* bitmask to enable ring interrupt */
@@ -320,11 +321,6 @@ struct intel_engine_cs {
 
 	struct intel_engine_hangcheck hangcheck;
 
-	struct {
-		struct drm_i915_gem_object *obj;
-		u32 gtt_offset;
-	} scratch;
-
 	bool needs_cmd_parser;
 
 	/*
@@ -476,8 +472,8 @@ void intel_ring_update_space(struct intel_ring *ring);
 
 void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno);
 
-int intel_init_pipe_control(struct intel_engine_cs *engine, int size);
-void intel_fini_pipe_control(struct intel_engine_cs *engine);
+int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine);
 
 void intel_engine_setup_common(struct intel_engine_cs *engine);
 int intel_engine_init_common(struct intel_engine_cs *engine);
-- 
2.8.1

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

[PATCH 22/37] drm/i915: Move common scratch allocation/destroy to intel_engine_cs.c

[Chris Wilson]

Since the scratch allocation and cleanup is shared by all engine
submission backends, move it out of the legacy intel_ringbuffer.c and
into the new home for common routines, intel_engine_cs.c

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
---
 drivers/gpu/drm/i915/intel_engine_cs.c  | 50 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c        |  1 -
 drivers/gpu/drm/i915/intel_ringbuffer.c | 50 ---------------------------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 +--
 4 files changed, 51 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 186c12d07f99..7104dec5e893 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -195,6 +195,54 @@ void intel_engine_setup_common(struct intel_engine_cs *engine)
 	i915_gem_batch_pool_init(engine, &engine->batch_pool);
 }
 
+int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int ret;
+
+	WARN_ON(engine->scratch);
+
+	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
+	if (!obj)
+		obj = i915_gem_object_create(&engine->i915->drm, size);
+	if (IS_ERR(obj)) {
+		DRM_ERROR("Failed to allocate scratch page\n");
+		return PTR_ERR(obj);
+	}
+
+	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_unref;
+	}
+
+	ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
+	if (ret)
+		goto err_unref;
+
+	engine->scratch = vma;
+	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
+			 engine->name, vma->node.start);
+	return 0;
+
+err_unref:
+	i915_gem_object_put(obj);
+	return ret;
+}
+
+static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
+{
+	struct i915_vma *vma;
+
+	vma = fetch_and_zero(&engine->scratch);
+	if (!vma)
+		return;
+
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -226,6 +274,8 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
+	intel_engine_cleanup_scratch(engine);
+
 	intel_engine_cleanup_cmd_parser(engine);
 	intel_engine_fini_breadcrumbs(engine);
 	i915_gem_batch_pool_fini(&engine->batch_pool);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index cdcdec83d640..88bc5d4ce243 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1844,7 +1844,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
 	else
 		engine->init_hw = gen8_init_render_ring;
 	engine->init_context = gen8_init_rcs_context;
-	engine->cleanup = intel_engine_cleanup_scratch;
 	engine->emit_flush = gen8_emit_flush_render;
 	engine->emit_request = gen8_emit_request_render;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 939632229320..0ecdd452a7f7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -613,54 +613,6 @@ out:
 	return ret;
 }
 
-void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
-{
-	struct i915_vma *vma;
-
-	vma = fetch_and_zero(&engine->scratch);
-	if (!vma)
-		return;
-
-	i915_vma_unpin(vma);
-	i915_vma_put(vma);
-}
-
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
-{
-	struct drm_i915_gem_object *obj;
-	struct i915_vma *vma;
-	int ret;
-
-	WARN_ON(engine->scratch);
-
-	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
-	if (!obj)
-		obj = i915_gem_object_create(&engine->i915->drm, size);
-	if (IS_ERR(obj)) {
-		DRM_ERROR("Failed to allocate scratch page\n");
-		return PTR_ERR(obj);
-	}
-
-	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
-	if (IS_ERR(vma)) {
-		ret = PTR_ERR(vma);
-		goto err_unref;
-	}
-
-	ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
-	if (ret)
-		goto err_unref;
-
-	engine->scratch = vma;
-	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
-			 engine->name, vma->node.start);
-	return 0;
-
-err_unref:
-	i915_gem_object_put(obj);
-	return ret;
-}
-
 static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
 {
 	struct intel_ring *ring = req->ring;
@@ -1311,8 +1263,6 @@ static void render_ring_cleanup(struct intel_engine_cs *engine)
 		i915_gem_object_put(dev_priv->semaphore_obj);
 		dev_priv->semaphore_obj = NULL;
 	}
-
-	intel_engine_cleanup_scratch(engine);
 }
 
 static int gen8_rcs_signal(struct drm_i915_gem_request *req)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c6024db75f93..dca84258be16 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -472,11 +472,9 @@ void intel_ring_update_space(struct intel_ring *ring);
 
 void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno);
 
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
-void intel_engine_cleanup_scratch(struct intel_engine_cs *engine);
-
 void intel_engine_setup_common(struct intel_engine_cs *engine);
 int intel_engine_init_common(struct intel_engine_cs *engine);
+int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 
 static inline int intel_engine_idle(struct intel_engine_cs *engine,
-- 
2.8.1

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

[PATCH 23/37] drm/i915: Move common seqno reset to intel_engine_cs.c

[Chris Wilson]

Since the intel_engine_init_seqno() is shared by all engine submission
backends, move it out of the legacy intel_ringbuffer.c and
into the new home for common routines, intel_engine_cs.c

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
---
 drivers/gpu/drm/i915/intel_engine_cs.c  | 42 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 42 ---------------------------------
 2 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 7104dec5e893..829624571ca4 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -161,6 +161,48 @@ cleanup:
 	return ret;
 }
 
+void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+
+	/* Our semaphore implementation is strictly monotonic (i.e. we proceed
+	 * so long as the semaphore value in the register/page is greater
+	 * than the sync value), so whenever we reset the seqno,
+	 * so long as we reset the tracking semaphore value to 0, it will
+	 * always be before the next request's seqno. If we don't reset
+	 * the semaphore value, then when the seqno moves backwards all
+	 * future waits will complete instantly (causing rendering corruption).
+	 */
+	if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
+		I915_WRITE(RING_SYNC_0(engine->mmio_base), 0);
+		I915_WRITE(RING_SYNC_1(engine->mmio_base), 0);
+		if (HAS_VEBOX(dev_priv))
+			I915_WRITE(RING_SYNC_2(engine->mmio_base), 0);
+	}
+	if (dev_priv->semaphore_obj) {
+		struct drm_i915_gem_object *obj = dev_priv->semaphore_obj;
+		struct page *page = i915_gem_object_get_dirty_page(obj, 0);
+		void *semaphores = kmap(page);
+		memset(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
+		       0, I915_NUM_ENGINES * gen8_semaphore_seqno_size);
+		kunmap(page);
+	}
+	memset(engine->semaphore.sync_seqno, 0,
+	       sizeof(engine->semaphore.sync_seqno));
+
+	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
+	if (engine->irq_seqno_barrier)
+		engine->irq_seqno_barrier(engine);
+	engine->last_submitted_seqno = seqno;
+
+	engine->hangcheck.seqno = seqno;
+
+	/* After manually advancing the seqno, fake the interrupt in case
+	 * there are any waiters for that seqno.
+	 */
+	intel_engine_wakeup(engine);
+}
+
 void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
 {
 	memset(&engine->hangcheck, 0, sizeof(engine->hangcheck));
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 0ecdd452a7f7..469059fc9f15 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2313,48 +2313,6 @@ int intel_ring_cacheline_align(struct drm_i915_gem_request *req)
 	return 0;
 }
 
-void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-
-	/* Our semaphore implementation is strictly monotonic (i.e. we proceed
-	 * so long as the semaphore value in the register/page is greater
-	 * than the sync value), so whenever we reset the seqno,
-	 * so long as we reset the tracking semaphore value to 0, it will
-	 * always be before the next request's seqno. If we don't reset
-	 * the semaphore value, then when the seqno moves backwards all
-	 * future waits will complete instantly (causing rendering corruption).
-	 */
-	if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
-		I915_WRITE(RING_SYNC_0(engine->mmio_base), 0);
-		I915_WRITE(RING_SYNC_1(engine->mmio_base), 0);
-		if (HAS_VEBOX(dev_priv))
-			I915_WRITE(RING_SYNC_2(engine->mmio_base), 0);
-	}
-	if (dev_priv->semaphore_obj) {
-		struct drm_i915_gem_object *obj = dev_priv->semaphore_obj;
-		struct page *page = i915_gem_object_get_dirty_page(obj, 0);
-		void *semaphores = kmap(page);
-		memset(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
-		       0, I915_NUM_ENGINES * gen8_semaphore_seqno_size);
-		kunmap(page);
-	}
-	memset(engine->semaphore.sync_seqno, 0,
-	       sizeof(engine->semaphore.sync_seqno));
-
-	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
-	if (engine->irq_seqno_barrier)
-		engine->irq_seqno_barrier(engine);
-	engine->last_submitted_seqno = seqno;
-
-	engine->hangcheck.seqno = seqno;
-
-	/* After manually advancing the seqno, fake the interrupt in case
-	 * there are any waiters for that seqno.
-	 */
-	intel_engine_wakeup(engine);
-}
-
 static void gen6_bsd_submit_request(struct drm_i915_gem_request *request)
 {
 	struct drm_i915_private *dev_priv = request->i915;
-- 
2.8.1

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

[PATCH 24/37] drm/i915/overlay: Use VMA as the primary tracker for images

[Chris Wilson]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_overlay.c | 39 ++++++++++++++++++++----------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 90f3ab424e01..d930e3a4a9cd 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -171,8 +171,8 @@ struct overlay_registers {
 struct intel_overlay {
 	struct drm_i915_private *i915;
 	struct intel_crtc *crtc;
-	struct drm_i915_gem_object *vid_bo;
-	struct drm_i915_gem_object *old_vid_bo;
+	struct i915_vma *vma;
+	struct i915_vma *old_vma;
 	bool active;
 	bool pfit_active;
 	u32 pfit_vscale_ratio; /* shifted-point number, (1<<12) == 1.0 */
@@ -317,15 +317,17 @@ static void intel_overlay_release_old_vid_tail(struct i915_gem_active *active,
 {
 	struct intel_overlay *overlay =
 		container_of(active, typeof(*overlay), last_flip);
-	struct drm_i915_gem_object *obj = overlay->old_vid_bo;
+	struct i915_vma *vma;
 
-	i915_gem_track_fb(obj, NULL,
-			  INTEL_FRONTBUFFER_OVERLAY(overlay->crtc->pipe));
+	vma = fetch_and_zero(&overlay->old_vma);
+	if (WARN_ON(!vma))
+		return;
 
-	i915_gem_object_ggtt_unpin(obj);
-	i915_gem_object_put(obj);
+	i915_gem_track_fb(vma->obj, NULL,
+			  INTEL_FRONTBUFFER_OVERLAY(overlay->crtc->pipe));
 
-	overlay->old_vid_bo = NULL;
+	i915_gem_object_unpin_from_display_plane(vma->obj, &i915_ggtt_view_normal);
+	i915_vma_put(vma);
 }
 
 static void intel_overlay_off_tail(struct i915_gem_active *active,
@@ -333,15 +335,15 @@ static void intel_overlay_off_tail(struct i915_gem_active *active,
 {
 	struct intel_overlay *overlay =
 		container_of(active, typeof(*overlay), last_flip);
-	struct drm_i915_gem_object *obj = overlay->vid_bo;
+	struct i915_vma *vma;
 
 	/* never have the overlay hw on without showing a frame */
-	if (WARN_ON(!obj))
+	vma = fetch_and_zero(&overlay->vma);
+	if (WARN_ON(!vma))
 		return;
 
-	i915_gem_object_ggtt_unpin(obj);
-	i915_gem_object_put(obj);
-	overlay->vid_bo = NULL;
+	i915_gem_object_unpin_from_display_plane(vma->obj, &i915_ggtt_view_normal);
+	i915_vma_put(vma);
 
 	overlay->crtc->overlay = NULL;
 	overlay->crtc = NULL;
@@ -421,7 +423,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 	/* Only wait if there is actually an old frame to release to
 	 * guarantee forward progress.
 	 */
-	if (!overlay->old_vid_bo)
+	if (!overlay->old_vma)
 		return 0;
 
 	if (I915_READ(ISR) & I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT) {
@@ -744,6 +746,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	struct drm_i915_private *dev_priv = overlay->i915;
 	u32 swidth, swidthsw, sheight, ostride;
 	enum pipe pipe = overlay->crtc->pipe;
+	struct i915_vma *vma;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 	WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex));
@@ -757,6 +760,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	if (ret != 0)
 		return ret;
 
+	vma = i915_gem_obj_to_ggtt_view(new_bo, &i915_ggtt_view_normal);
+
 	ret = i915_gem_object_put_fence(new_bo);
 	if (ret)
 		goto out_unpin;
@@ -834,11 +839,11 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	if (ret)
 		goto out_unpin;
 
-	i915_gem_track_fb(overlay->vid_bo, new_bo,
+	i915_gem_track_fb(overlay->vma->obj, new_bo,
 			  INTEL_FRONTBUFFER_OVERLAY(pipe));
 
-	overlay->old_vid_bo = overlay->vid_bo;
-	overlay->vid_bo = new_bo;
+	overlay->old_vma = overlay->vma;
+	overlay->vma = vma;
 
 	intel_frontbuffer_flip(dev_priv, INTEL_FRONTBUFFER_OVERLAY(pipe));
 
-- 
2.8.1

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

[PATCH 25/37] drm/i915: Use VMA as the primary tracker for semaphore page

[Chris Wilson]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c     |  2 +-
 drivers/gpu/drm/i915/i915_drv.h         |  5 ++-
 drivers/gpu/drm/i915/i915_gpu_error.c   | 16 ++++-----
 drivers/gpu/drm/i915/intel_engine_cs.c  | 12 ++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 60 +++++++++++++++++++--------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 +--
 6 files changed, 55 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2da37c196ef0..fb483df1afd6 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3145,7 +3145,7 @@ static int i915_semaphore_status(struct seq_file *m, void *unused)
 		struct page *page;
 		uint64_t *seqno;
 
-		page = i915_gem_object_get_page(dev_priv->semaphore_obj, 0);
+		page = i915_gem_object_get_page(dev_priv->semaphore->obj, 0);
 
 		seqno = (uint64_t *)kmap_atomic(page);
 		for_each_engine_id(engine, dev_priv, id) {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 310eaab21c15..dcad703070c6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -735,7 +735,7 @@ struct drm_i915_error_state {
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
-	struct drm_i915_error_object *semaphore_obj;
+	struct drm_i915_error_object *semaphore;
 
 	struct drm_i915_error_engine {
 		int engine_id;
@@ -826,7 +826,6 @@ struct drm_i915_error_state {
 	struct i915_address_space *active_vm[I915_NUM_ENGINES];
 };
 
-
 enum i915_cache_level {
 	I915_CACHE_NONE = 0,
 	I915_CACHE_LLC, /* also used for snoopable memory on non-LLC */
@@ -1753,7 +1752,7 @@ struct drm_i915_private {
 	struct pci_dev *bridge_dev;
 	struct i915_gem_context *kernel_context;
 	struct intel_engine_cs engine[I915_NUM_ENGINES];
-	struct drm_i915_gem_object *semaphore_obj;
+	struct i915_vma *semaphore;
 	u32 next_seqno;
 
 	struct drm_dma_handle *status_page_dmah;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index dd60a417a6bc..d45b21a01efc 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -550,7 +550,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		}
 	}
 
-	if ((obj = error->semaphore_obj)) {
+	if ((obj = error->semaphore)) {
 		err_printf(m, "Semaphore page = 0x%08x\n",
 			   lower_32_bits(obj->gtt_offset));
 		for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
@@ -641,7 +641,7 @@ static void i915_error_state_free(struct kref *error_ref)
 		kfree(ee->waiters);
 	}
 
-	i915_error_object_free(error->semaphore_obj);
+	i915_error_object_free(error->semaphore);
 
 	for (i = 0; i < ARRAY_SIZE(error->active_bo); i++)
 		kfree(error->active_bo[i]);
@@ -870,7 +870,7 @@ static void gen8_record_semaphore_state(struct drm_i915_error_state *error,
 	struct intel_engine_cs *to;
 	enum intel_engine_id id;
 
-	if (!error->semaphore_obj)
+	if (!error->semaphore)
 		return;
 
 	for_each_engine_id(to, dev_priv, id) {
@@ -883,7 +883,7 @@ static void gen8_record_semaphore_state(struct drm_i915_error_state *error,
 
 		signal_offset =
 			(GEN8_SIGNAL_OFFSET(engine, id) & (PAGE_SIZE - 1)) / 4;
-		tmp = error->semaphore_obj->pages[0];
+		tmp = error->semaphore->pages[0];
 		idx = intel_engine_sync_index(engine, to);
 
 		ee->semaphore_mboxes[idx] = tmp[signal_offset];
@@ -1055,11 +1055,9 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 	struct drm_i915_gem_request *request;
 	int i, count;
 
-	if (dev_priv->semaphore_obj) {
-		error->semaphore_obj =
-			i915_error_ggtt_object_create(dev_priv,
-						      dev_priv->semaphore_obj);
-	}
+	error->semaphore =
+		i915_error_ggtt_object_create(dev_priv,
+					      dev_priv->semaphore->obj);
 
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
 		struct intel_engine_cs *engine = &dev_priv->engine[i];
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 829624571ca4..573f642a74f8 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -179,12 +179,16 @@ void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno)
 		if (HAS_VEBOX(dev_priv))
 			I915_WRITE(RING_SYNC_2(engine->mmio_base), 0);
 	}
-	if (dev_priv->semaphore_obj) {
-		struct drm_i915_gem_object *obj = dev_priv->semaphore_obj;
-		struct page *page = i915_gem_object_get_dirty_page(obj, 0);
-		void *semaphores = kmap(page);
+	if (dev_priv->semaphore) {
+		struct page *page = i915_vma_first_page(dev_priv->semaphore);
+		void *semaphores;
+
+		/* Semaphores are in noncoherent memory, flush to be safe */
+		semaphores = kmap(page);
 		memset(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
 		       0, I915_NUM_ENGINES * gen8_semaphore_seqno_size);
+		drm_clflush_virt_range(semaphores + GEN8_SEMAPHORE_OFFSET(engine->id, 0),
+				       I915_NUM_ENGINES * gen8_semaphore_seqno_size);
 		kunmap(page);
 	}
 	memset(engine->semaphore.sync_seqno, 0,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 469059fc9f15..a5619a81d284 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1257,12 +1257,14 @@ static int init_render_ring(struct intel_engine_cs *engine)
 static void render_ring_cleanup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	struct i915_vma *vma;
 
-	if (dev_priv->semaphore_obj) {
-		i915_gem_object_ggtt_unpin(dev_priv->semaphore_obj);
-		i915_gem_object_put(dev_priv->semaphore_obj);
-		dev_priv->semaphore_obj = NULL;
-	}
+	vma = fetch_and_zero(&dev_priv->semaphore);
+	if (!vma)
+		return;
+
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
 }
 
 static int gen8_rcs_signal(struct drm_i915_gem_request *req)
@@ -2522,30 +2524,30 @@ static void intel_ring_init_semaphores(struct drm_i915_private *dev_priv,
 	if (!i915.semaphores)
 		return;
 
-	if (INTEL_GEN(dev_priv) >= 8 && !dev_priv->semaphore_obj) {
+	if (INTEL_GEN(dev_priv) >= 8 && !dev_priv->semaphore) {
+		struct i915_vma *vma;
+
 		obj = i915_gem_object_create(&dev_priv->drm, 4096);
-		if (IS_ERR(obj)) {
-			DRM_ERROR("Failed to allocate semaphore bo. Disabling semaphores\n");
-			i915.semaphores = 0;
-		} else {
-			i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
-			ret = i915_gem_object_ggtt_pin(obj, NULL,
-						       0, 0, PIN_HIGH);
-			if (ret != 0) {
-				i915_gem_object_put(obj);
-				DRM_ERROR("Failed to pin semaphore bo. Disabling semaphores\n");
-				i915.semaphores = 0;
-			} else {
-				dev_priv->semaphore_obj = obj;
-			}
-		}
-	}
+		if (IS_ERR(obj))
+			goto err;
 
-	if (!i915.semaphores)
-		return;
+		vma = i915_vma_create(obj, &dev_priv->ggtt.base, NULL);
+		if (IS_ERR(vma))
+			goto err_obj;
+
+		ret = i915_gem_object_set_to_gtt_domain(obj, false);
+		if (ret)
+			goto err_obj;
+
+		ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
+		if (ret)
+			goto err_obj;
+
+		dev_priv->semaphore = vma;
+	}
 
 	if (INTEL_GEN(dev_priv) >= 8) {
-		u64 offset = i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj);
+		u64 offset = dev_priv->semaphore->node.start;
 
 		engine->semaphore.sync_to = gen8_ring_sync_to;
 		engine->semaphore.signal = gen8_xcs_signal;
@@ -2612,6 +2614,14 @@ static void intel_ring_init_semaphores(struct drm_i915_private *dev_priv,
 			engine->semaphore.mbox.signal[i] = mbox_reg;
 		}
 	}
+
+	return;
+
+err_obj:
+	i915_gem_object_put(obj);
+err:
+	DRM_DEBUG_DRIVER("Failed to allocate space for semaphores, disabling\n");
+	i915.semaphores = 0;
 }
 
 static void intel_ring_init_irq(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index dca84258be16..cb40785e7677 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -57,10 +57,10 @@ struct intel_hw_status_page {
 #define GEN8_SEMAPHORE_OFFSET(__from, __to)			     \
 	(((__from) * I915_NUM_ENGINES  + (__to)) * gen8_semaphore_seqno_size)
 #define GEN8_SIGNAL_OFFSET(__ring, to)			     \
-	(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
+	(dev_priv->semaphore->node.start + \
 	 GEN8_SEMAPHORE_OFFSET((__ring)->id, (to)))
 #define GEN8_WAIT_OFFSET(__ring, from)			     \
-	(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
+	(dev_priv->semaphore->node.start + \
 	 GEN8_SEMAPHORE_OFFSET(from, (__ring)->id))
 
 enum intel_engine_hangcheck_action {
-- 
2.8.1

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

[PATCH 26/37] drm/i915: Use VMA for render state page tracking

[Chris Wilson]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_render_state.c | 40 +++++++++++++++-------------
 drivers/gpu/drm/i915/i915_gem_render_state.h |  2 +-
 2 files changed, 23 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 57fd767a2d79..95b7e9afd5f8 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -30,8 +30,7 @@
 
 struct render_state {
 	const struct intel_renderstate_rodata *rodata;
-	struct drm_i915_gem_object *obj;
-	u64 ggtt_offset;
+	struct i915_vma *vma;
 	u32 aux_batch_size;
 	u32 aux_batch_offset;
 };
@@ -73,7 +72,7 @@ render_state_get_rodata(const struct drm_i915_gem_request *req)
 
 static int render_state_setup(struct render_state *so)
 {
-	struct drm_device *dev = so->obj->base.dev;
+	struct drm_device *dev = so->vma->vm->dev;
 	const struct intel_renderstate_rodata *rodata = so->rodata;
 	const bool has_64bit_reloc = INTEL_GEN(dev) >= 8;
 	unsigned int i = 0, reloc_index = 0;
@@ -81,18 +80,18 @@ static int render_state_setup(struct render_state *so)
 	u32 *d;
 	int ret;
 
-	ret = i915_gem_object_set_to_cpu_domain(so->obj, true);
+	ret = i915_gem_object_set_to_cpu_domain(so->vma->obj, true);
 	if (ret)
 		return ret;
 
-	page = i915_gem_object_get_dirty_page(so->obj, 0);
+	page = i915_gem_object_get_dirty_page(so->vma->obj, 0);
 	d = kmap(page);
 
 	while (i < rodata->batch_items) {
 		u32 s = rodata->batch[i];
 
 		if (i * 4  == rodata->reloc[reloc_index]) {
-			u64 r = s + so->ggtt_offset;
+			u64 r = s + so->vma->node.start;
 			s = lower_32_bits(r);
 			if (has_64bit_reloc) {
 				if (i + 1 >= rodata->batch_items ||
@@ -154,7 +153,7 @@ static int render_state_setup(struct render_state *so)
 
 	kunmap(page);
 
-	ret = i915_gem_object_set_to_gtt_domain(so->obj, false);
+	ret = i915_gem_object_set_to_gtt_domain(so->vma->obj, false);
 	if (ret)
 		return ret;
 
@@ -175,6 +174,7 @@ err_out:
 int i915_gem_render_state_init(struct drm_i915_gem_request *req)
 {
 	struct render_state so;
+	struct drm_i915_gem_object *obj;
 	int ret;
 
 	if (WARN_ON(req->engine->id != RCS))
@@ -187,21 +187,25 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
 	if (so.rodata->batch_items * 4 > 4096)
 		return -EINVAL;
 
-	so.obj = i915_gem_object_create(&req->i915->drm, 4096);
-	if (IS_ERR(so.obj))
-		return PTR_ERR(so.obj);
+	obj = i915_gem_object_create(&req->i915->drm, 4096);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
-	ret = i915_gem_object_ggtt_pin(so.obj, NULL, 0, 0, 0);
-	if (ret)
+	so.vma = i915_vma_create(obj, &req->i915->ggtt.base, NULL);
+	if (IS_ERR(so.vma)) {
+		ret = PTR_ERR(so.vma);
 		goto err_obj;
+	}
 
-	so.ggtt_offset = i915_gem_obj_ggtt_offset(so.obj);
+	ret = i915_vma_pin(so.vma, 0, 0, PIN_GLOBAL);
+	if (ret)
+		goto err_obj;
 
 	ret = render_state_setup(&so);
 	if (ret)
 		goto err_unpin;
 
-	ret = req->engine->emit_bb_start(req, so.ggtt_offset,
+	ret = req->engine->emit_bb_start(req, so.vma->node.start,
 					 so.rodata->batch_items * 4,
 					 I915_DISPATCH_SECURE);
 	if (ret)
@@ -209,7 +213,7 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
 
 	if (so.aux_batch_size > 8) {
 		ret = req->engine->emit_bb_start(req,
-						 (so.ggtt_offset +
+						 (so.vma->node.start +
 						  so.aux_batch_offset),
 						 so.aux_batch_size,
 						 I915_DISPATCH_SECURE);
@@ -217,10 +221,10 @@ int i915_gem_render_state_init(struct drm_i915_gem_request *req)
 			goto err_unpin;
 	}
 
-	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), req, 0);
+	i915_vma_move_to_active(so.vma, req, 0);
 err_unpin:
-	i915_gem_object_ggtt_unpin(so.obj);
+	i915_vma_unpin(so.vma);
 err_obj:
-	i915_gem_object_put(so.obj);
+	i915_gem_object_put(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.h b/drivers/gpu/drm/i915/i915_gem_render_state.h
index c44fca8599bb..18cce3f06e9c 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.h
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.h
@@ -24,7 +24,7 @@
 #ifndef _I915_GEM_RENDER_STATE_H_
 #define _I915_GEM_RENDER_STATE_H_
 
-#include <linux/types.h>
+struct drm_i915_gem_request;
 
 int i915_gem_render_state_init(struct drm_i915_gem_request *req);
 
-- 
2.8.1

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

[PATCH 27/37] drm/i915: Use VMA for wa_ctx tracking

[Chris Wilson]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c   |  2 +-
 drivers/gpu/drm/i915/intel_lrc.c        | 58 ++++++++++++++++++---------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  4 +--
 3 files changed, 35 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index d45b21a01efc..54c04eddf313 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1128,7 +1128,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 						      engine->status_page.vma->obj);
 
 		ee->wa_ctx = i915_error_ggtt_object_create(dev_priv,
-							   engine->wa_ctx.obj);
+							   engine->wa_ctx.vma->obj);
 
 		count = 0;
 		list_for_each_entry(request, &engine->request_list, link)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 88bc5d4ce243..ae39ae771ad9 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1165,45 +1165,51 @@ static int gen9_init_perctx_bb(struct intel_engine_cs *engine,
 
 static int lrc_setup_wa_ctx_obj(struct intel_engine_cs *engine, u32 size)
 {
-	int ret;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int err;
 
-	engine->wa_ctx.obj = i915_gem_object_create(&engine->i915->drm,
-						    PAGE_ALIGN(size));
-	if (IS_ERR(engine->wa_ctx.obj)) {
-		DRM_DEBUG_DRIVER("alloc LRC WA ctx backing obj failed.\n");
-		ret = PTR_ERR(engine->wa_ctx.obj);
-		engine->wa_ctx.obj = NULL;
-		return ret;
-	}
+	obj = i915_gem_object_create(&engine->i915->drm, PAGE_ALIGN(size));
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
-	ret = i915_gem_object_ggtt_pin(engine->wa_ctx.obj, NULL,
-				       0, PAGE_SIZE, PIN_HIGH);
-	if (ret) {
-		DRM_DEBUG_DRIVER("pin LRC WA ctx backing obj failed: %d\n",
-				 ret);
-		i915_gem_object_put(engine->wa_ctx.obj);
-		return ret;
+	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err;
 	}
 
+	err = i915_vma_pin(vma, 0, PAGE_SIZE, PIN_GLOBAL | PIN_HIGH);
+	if (err)
+		goto err;
+
+	engine->wa_ctx.vma = vma;
 	return 0;
+
+err:
+	i915_gem_object_put(obj);
+	return err;
 }
 
 static void lrc_destroy_wa_ctx_obj(struct intel_engine_cs *engine)
 {
-	if (engine->wa_ctx.obj) {
-		i915_gem_object_ggtt_unpin(engine->wa_ctx.obj);
-		i915_gem_object_put(engine->wa_ctx.obj);
-		engine->wa_ctx.obj = NULL;
-	}
+	struct i915_vma *vma;
+
+	vma = fetch_and_zero(&engine->wa_ctx.vma);
+	if (!vma)
+		return;
+
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
 }
 
 static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 {
-	int ret;
+	struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
 	uint32_t *batch;
 	uint32_t offset;
 	struct page *page;
-	struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
+	int ret;
 
 	WARN_ON(engine->id != RCS);
 
@@ -1226,7 +1232,7 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
 		return ret;
 	}
 
-	page = i915_gem_object_get_dirty_page(wa_ctx->obj, 0);
+	page = i915_gem_object_get_dirty_page(wa_ctx->vma->obj, 0);
 	batch = kmap_atomic(page);
 	offset = 0;
 
@@ -2019,9 +2025,9 @@ populate_lr_context(struct i915_gem_context *ctx,
 			       RING_INDIRECT_CTX(engine->mmio_base), 0);
 		ASSIGN_CTX_REG(reg_state, CTX_RCS_INDIRECT_CTX_OFFSET,
 			       RING_INDIRECT_CTX_OFFSET(engine->mmio_base), 0);
-		if (engine->wa_ctx.obj) {
+		if (engine->wa_ctx.vma) {
 			struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
-			uint32_t ggtt_offset = i915_gem_obj_ggtt_offset(wa_ctx->obj);
+			u32 ggtt_offset = wa_ctx->vma->node.start;
 
 			reg_state[CTX_RCS_INDIRECT_CTX+1] =
 				(ggtt_offset + wa_ctx->indirect_ctx.offset * sizeof(uint32_t)) |
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index cb40785e7677..e3777572c70e 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -123,12 +123,12 @@ struct drm_i915_reg_table;
  *    an option for future use.
  *  size: size of the batch in DWORDS
  */
-struct  i915_ctx_workarounds {
+struct i915_ctx_workarounds {
 	struct i915_wa_ctx_bb {
 		u32 offset;
 		u32 size;
 	} indirect_ctx, per_ctx;
-	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
 };
 
 struct drm_i915_gem_request;
-- 
2.8.1

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

[PATCH 28/37] drm/i915: Consolidate i915_vma_unpin_and_release()

[Chris Wilson]

In a few places, we repeat a call to clear a pointer to a vma whilst
unpinning and releasing a reference to its owner. Refactor those into a
common function.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 12 ++++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.h        |  1 +
 drivers/gpu/drm/i915/i915_guc_submission.c | 21 ++++-----------------
 drivers/gpu/drm/i915/intel_engine_cs.c     |  9 +--------
 drivers/gpu/drm/i915/intel_lrc.c           |  9 +--------
 drivers/gpu/drm/i915/intel_ringbuffer.c    |  8 +-------
 6 files changed, 20 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 738a474c5afa..d15eb1d71341 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3674,3 +3674,15 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	__i915_vma_pin(vma);
 	return ptr;
 }
+
+void i915_vma_unpin_and_release(struct i915_vma **p_vma)
+{
+	struct i915_vma *vma;
+
+	vma = fetch_and_zero(p_vma);
+	if (!vma)
+		return;
+
+	i915_vma_unpin(vma);
+	i915_vma_put(vma);
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index a2691943a404..ec538fcc9c20 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -232,6 +232,7 @@ struct i915_vma *
 i915_vma_create(struct drm_i915_gem_object *obj,
 		struct i915_address_space *vm,
 		const struct i915_ggtt_view *view);
+void i915_vma_unpin_and_release(struct i915_vma **p_vma);
 
 static inline bool i915_vma_is_ggtt(const struct i915_vma *vma)
 {
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 7227f97d8040..75db2da76b41 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -651,19 +651,6 @@ err:
 	return vma;
 }
 
-/**
- * guc_release_vma() - Release gem object allocated for GuC usage
- * @vma:	gem obj to be released
- */
-static void guc_release_vma(struct i915_vma *vma)
-{
-	if (!vma)
-		return;
-
-	i915_vma_unpin(vma);
-	i915_vma_put(vma);
-}
-
 static void
 guc_client_free(struct drm_i915_private *dev_priv,
 		struct i915_guc_client *client)
@@ -688,7 +675,7 @@ guc_client_free(struct drm_i915_private *dev_priv,
 		kunmap(kmap_to_page(client->client_base));
 	}
 
-	guc_release_vma(client->vma);
+	i915_vma_unpin_and_release(&client->vma);
 
 	if (client->ctx_index != GUC_INVALID_CTX_ID) {
 		guc_fini_ctx_desc(guc, client);
@@ -1046,12 +1033,12 @@ void i915_guc_submission_fini(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc *guc = &dev_priv->guc;
 
-	guc_release_vma(fetch_and_zero(&guc->ads_vma));
-	guc_release_vma(fetch_and_zero(&guc->log_vma));
+	i915_vma_unpin_and_release(&guc->ads_vma);
+	i915_vma_unpin_and_release(&guc->log_vma);
 
 	if (guc->ctx_pool_vma)
 		ida_destroy(&guc->ctx_ids);
-	guc_release_vma(fetch_and_zero(&guc->ctx_pool_vma));
+	i915_vma_unpin_and_release(&guc->ctx_pool_vma);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 573f642a74f8..f02d66bbec4b 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -279,14 +279,7 @@ err_unref:
 
 static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
 {
-	struct i915_vma *vma;
-
-	vma = fetch_and_zero(&engine->scratch);
-	if (!vma)
-		return;
-
-	i915_vma_unpin(vma);
-	i915_vma_put(vma);
+	i915_vma_unpin_and_release(&engine->scratch);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ae39ae771ad9..4b9beaa30023 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1193,14 +1193,7 @@ err:
 
 static void lrc_destroy_wa_ctx_obj(struct intel_engine_cs *engine)
 {
-	struct i915_vma *vma;
-
-	vma = fetch_and_zero(&engine->wa_ctx.vma);
-	if (!vma)
-		return;
-
-	i915_vma_unpin(vma);
-	i915_vma_put(vma);
+	i915_vma_unpin_and_release(&engine->wa_ctx.vma);
 }
 
 static int intel_init_workaround_bb(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index a5619a81d284..d618d05249f3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1257,14 +1257,8 @@ static int init_render_ring(struct intel_engine_cs *engine)
 static void render_ring_cleanup(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
-	struct i915_vma *vma;
-
-	vma = fetch_and_zero(&dev_priv->semaphore);
-	if (!vma)
-		return;
 
-	i915_vma_unpin(vma);
-	i915_vma_put(vma);
+	i915_vma_unpin_and_release(&dev_priv->semaphore);
 }
 
 static int gen8_rcs_signal(struct drm_i915_gem_request *req)
-- 
2.8.1

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

[PATCH 29/37] drm/i915: Track pinned VMA

[Chris Wilson]

Treat the VMA as the primary struct responsible for tracking bindings
into the GPU's VM. That is we want to treat the VMA returned after we
pin an object into the VM as the cookie we hold and eventually release
when unpinning. Doing so eliminates the ambiguity in pinning the object
and then searching for the relevant pin later.

v2: Joonas' stylistic nitpicks, a fun rebase.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c        |   2 +-
 drivers/gpu/drm/i915/i915_drv.h            |  60 ++------
 drivers/gpu/drm/i915/i915_gem.c            | 233 ++++++++---------------------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  59 ++++----
 drivers/gpu/drm/i915/i915_gem_fence.c      |  14 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c        |  74 +++++----
 drivers/gpu/drm/i915/i915_gem_gtt.h        |  14 --
 drivers/gpu/drm/i915/i915_gem_request.c    |   2 +-
 drivers/gpu/drm/i915/i915_gem_request.h    |   2 +-
 drivers/gpu/drm/i915/i915_gem_stolen.c     |   2 +-
 drivers/gpu/drm/i915/i915_gem_tiling.c     |   2 +-
 drivers/gpu/drm/i915/i915_gpu_error.c      |  58 +++----
 drivers/gpu/drm/i915/intel_display.c       |  57 ++++---
 drivers/gpu/drm/i915/intel_drv.h           |   5 +-
 drivers/gpu/drm/i915/intel_fbc.c           |   2 +-
 drivers/gpu/drm/i915/intel_fbdev.c         |  19 +--
 drivers/gpu/drm/i915/intel_guc_loader.c    |  21 +--
 drivers/gpu/drm/i915/intel_overlay.c       |  32 ++--
 18 files changed, 264 insertions(+), 394 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fb483df1afd6..21961304284e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -105,7 +105,7 @@ static char get_tiling_flag(struct drm_i915_gem_object *obj)
 
 static char get_global_flag(struct drm_i915_gem_object *obj)
 {
-	return i915_gem_obj_to_ggtt(obj) ? 'g' : ' ';
+	return i915_gem_object_to_ggtt(obj, NULL) ?  'g' : ' ';
 }
 
 static char get_pin_mapped_flag(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index dcad703070c6..e22445e0b004 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3077,7 +3077,7 @@ struct drm_i915_gem_object *i915_gem_object_create_from_data(
 void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file);
 void i915_gem_free_object(struct drm_gem_object *obj);
 
-int __must_check
+struct i915_vma * __must_check
 i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 const struct i915_ggtt_view *view,
 			 u64 size,
@@ -3273,12 +3273,11 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj,
 				  bool write);
 int __must_check
 i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write);
-int __must_check
+struct i915_vma * __must_check
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
 				     const struct i915_ggtt_view *view);
-void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj,
-					      const struct i915_ggtt_view *view);
+void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma);
 int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj,
 				int align);
 int i915_gem_open(struct drm_device *dev, struct drm_file *file);
@@ -3298,63 +3297,34 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 				struct drm_gem_object *gem_obj, int flags);
 
-u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
-				  const struct i915_ggtt_view *view);
-u64 i915_gem_obj_offset(struct drm_i915_gem_object *o,
-			struct i915_address_space *vm);
-static inline u64
-i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
-{
-	return i915_gem_obj_ggtt_offset_view(o, &i915_ggtt_view_normal);
-}
-
-bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o,
-				  const struct i915_ggtt_view *view);
-bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
-			struct i915_address_space *vm);
-
 struct i915_vma *
 i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
-		    struct i915_address_space *vm);
-struct i915_vma *
-i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj,
-			  const struct i915_ggtt_view *view);
+		     struct i915_address_space *vm,
+		     const struct i915_ggtt_view *view);
 
 struct i915_vma *
 i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
-				  struct i915_address_space *vm);
-struct i915_vma *
-i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj,
-				       const struct i915_ggtt_view *view);
-
-static inline struct i915_vma *
-i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj)
-{
-	return i915_gem_obj_to_ggtt_view(obj, &i915_ggtt_view_normal);
-}
-bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj);
+				  struct i915_address_space *vm,
+				  const struct i915_ggtt_view *view);
 
-/* Some GGTT VM helpers */
 static inline struct i915_hw_ppgtt *
 i915_vm_to_ppgtt(struct i915_address_space *vm)
 {
 	return container_of(vm, struct i915_hw_ppgtt, base);
 }
 
-static inline bool i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *obj)
+static inline struct i915_vma *
+i915_gem_object_to_ggtt(struct drm_i915_gem_object *obj,
+			const struct i915_ggtt_view *view)
 {
-	return i915_gem_obj_ggtt_bound_view(obj, &i915_ggtt_view_normal);
+	return i915_gem_obj_to_vma(obj, &to_i915(obj->base.dev)->ggtt.base, view);
 }
 
-unsigned long
-i915_gem_obj_ggtt_size(struct drm_i915_gem_object *obj);
-
-void i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj,
-				     const struct i915_ggtt_view *view);
-static inline void
-i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj)
+static inline unsigned long
+i915_gem_object_ggtt_offset(struct drm_i915_gem_object *o,
+			    const struct i915_ggtt_view *view)
 {
-	i915_gem_object_ggtt_unpin_view(obj, &i915_ggtt_view_normal);
+	return i915_gem_object_to_ggtt(o, view)->node.start;
 }
 
 /* i915_gem_fence.c */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b427969325ec..d4938c4fd9c6 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -737,14 +737,15 @@ i915_gem_gtt_pread(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct i915_vma *vma;
 	struct drm_mm_node node;
 	char __user *user_data;
 	uint64_t remain;
 	uint64_t offset;
 	int ret;
 
-	ret = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
-	if (ret) {
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma)) {
 		ret = insert_mappable_node(dev_priv, &node, PAGE_SIZE);
 		if (ret)
 			goto out;
@@ -757,7 +758,7 @@ i915_gem_gtt_pread(struct drm_device *dev,
 
 		i915_gem_object_pin_pages(obj);
 	} else {
-		node.start = i915_gem_obj_ggtt_offset(obj);
+		node.start = vma->node.start;
 		node.allocated = false;
 		ret = i915_gem_object_put_fence(obj);
 		if (ret)
@@ -838,7 +839,7 @@ out_unpin:
 		i915_gem_object_unpin_pages(obj);
 		remove_mappable_node(&node);
 	} else {
-		i915_gem_object_ggtt_unpin(obj);
+		i915_vma_unpin(vma);
 	}
 out:
 	return ret;
@@ -1036,6 +1037,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915,
 {
 	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct drm_device *dev = obj->base.dev;
+	struct i915_vma *vma;
 	struct drm_mm_node node;
 	uint64_t remain, offset;
 	char __user *user_data;
@@ -1045,9 +1047,9 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915,
 	if (i915_gem_object_is_tiled(obj))
 		return -EFAULT;
 
-	ret = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
 				       PIN_MAPPABLE | PIN_NONBLOCK);
-	if (ret) {
+	if (IS_ERR(vma)) {
 		ret = insert_mappable_node(i915, &node, PAGE_SIZE);
 		if (ret)
 			goto out;
@@ -1060,7 +1062,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915,
 
 		i915_gem_object_pin_pages(obj);
 	} else {
-		node.start = i915_gem_obj_ggtt_offset(obj);
+		node.start = vma->node.start;
 		node.allocated = false;
 		ret = i915_gem_object_put_fence(obj);
 		if (ret)
@@ -1148,7 +1150,7 @@ out_unpin:
 		i915_gem_object_unpin_pages(obj);
 		remove_mappable_node(&node);
 	} else {
-		i915_gem_object_ggtt_unpin(obj);
+		i915_vma_unpin(vma);
 	}
 out:
 	return ret;
@@ -1616,7 +1618,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 
 /**
  * i915_gem_fault - fault a page into the GTT
- * @vma: VMA in question
+ * @area: CPU VMA in question
  * @vmf: fault info
  *
  * The fault handler is set up by drm_gem_mmap() when a object is GTT mapped
@@ -1630,20 +1632,21 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
  * suffer if the GTT working set is large or there are few fence registers
  * left.
  */
-int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf)
 {
-	struct drm_i915_gem_object *obj = to_intel_bo(vma->vm_private_data);
+	struct drm_i915_gem_object *obj = to_intel_bo(area->vm_private_data);
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	struct i915_ggtt_view view = i915_ggtt_view_normal;
 	bool write = !!(vmf->flags & FAULT_FLAG_WRITE);
+	struct i915_vma *vma;
 	pgoff_t page_offset;
 	unsigned long pfn;
 	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset */
-	page_offset = ((unsigned long)vmf->virtual_address - vma->vm_start) >>
+	page_offset = ((unsigned long)vmf->virtual_address - area->vm_start) >>
 		PAGE_SHIFT;
 
 	trace_i915_gem_object_fault(obj, page_offset, true, write);
@@ -1680,14 +1683,16 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		view.params.partial.size =
 			min_t(unsigned int,
 			      chunk_size,
-			      (vma->vm_end - vma->vm_start)/PAGE_SIZE -
+			      (area->vm_end - area->vm_start) / PAGE_SIZE -
 			      view.params.partial.offset);
 	}
 
 	/* Now pin it into the GTT if needed */
-	ret = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
-	if (ret)
+	vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
 		goto err_unlock;
+	}
 
 	ret = i915_gem_object_set_to_gtt_domain(obj, write);
 	if (ret)
@@ -1698,8 +1703,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		goto err_unpin;
 
 	/* Finally, remap it using the new GTT offset */
-	pfn = ggtt->mappable_base +
-		i915_gem_obj_ggtt_offset_view(obj, &view);
+	pfn = ggtt->mappable_base + vma->node.start;
 	pfn >>= PAGE_SHIFT;
 
 	if (unlikely(view.type == I915_GGTT_VIEW_PARTIAL)) {
@@ -1708,12 +1712,14 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		 * is due to userspace losing part of the mapping or never
 		 * having accessed it before (at this partials' range).
 		 */
-		unsigned long base = vma->vm_start +
+		unsigned long base = area->vm_start +
 				     (view.params.partial.offset << PAGE_SHIFT);
 		unsigned int i;
 
 		for (i = 0; i < view.params.partial.size; i++) {
-			ret = vm_insert_pfn(vma, base + i * PAGE_SIZE, pfn + i);
+			ret = vm_insert_pfn(area,
+					    base + i * PAGE_SIZE,
+					    pfn + i);
 			if (ret)
 				break;
 		}
@@ -1721,14 +1727,16 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		obj->fault_mappable = true;
 	} else {
 		if (!obj->fault_mappable) {
-			unsigned long size = min_t(unsigned long,
-						   vma->vm_end - vma->vm_start,
-						   obj->base.size);
+			unsigned long size =
+				min_t(unsigned long,
+				      area->vm_end - area->vm_start,
+				      obj->base.size) >> PAGE_SHIFT;
+			unsigned long base = area->vm_start;
 			int i;
 
-			for (i = 0; i < size >> PAGE_SHIFT; i++) {
-				ret = vm_insert_pfn(vma,
-						    (unsigned long)vma->vm_start + i * PAGE_SIZE,
+			for (i = 0; i < size; i++) {
+				ret = vm_insert_pfn(area,
+						    base + i * PAGE_SIZE,
 						    pfn + i);
 				if (ret)
 					break;
@@ -1736,12 +1744,12 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 			obj->fault_mappable = true;
 		} else
-			ret = vm_insert_pfn(vma,
+			ret = vm_insert_pfn(area,
 					    (unsigned long)vmf->virtual_address,
 					    pfn + page_offset);
 	}
 err_unpin:
-	i915_gem_object_ggtt_unpin_view(obj, &view);
+	__i915_vma_unpin(vma);
 err_unlock:
 	mutex_unlock(&dev->struct_mutex);
 err_rpm:
@@ -3188,7 +3196,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 					    old_write_domain);
 
 	/* And bump the LRU for this access */
-	vma = i915_gem_obj_to_ggtt(obj);
+	vma = i915_gem_object_to_ggtt(obj, NULL);
 	if (vma &&
 	    drm_mm_node_allocated(&vma->node) &&
 	    !i915_vma_is_active(vma))
@@ -3412,11 +3420,12 @@ rpm_put:
  * Can be called from an uninterruptible phase (modesetting) and allows
  * any flushes to be pipelined (for pageflips).
  */
-int
+struct i915_vma *
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
 				     const struct i915_ggtt_view *view)
 {
+	struct i915_vma *vma;
 	u32 old_read_domains, old_write_domain;
 	int ret;
 
@@ -3436,19 +3445,23 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 */
 	ret = i915_gem_object_set_cache_level(obj,
 					      HAS_WT(obj->base.dev) ? I915_CACHE_WT : I915_CACHE_NONE);
-	if (ret)
+	if (ret) {
+		vma = ERR_PTR(ret);
 		goto err_unpin_display;
+	}
 
 	/* As the user may map the buffer once pinned in the display plane
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers.
 	 */
-	ret = i915_gem_object_ggtt_pin(obj, view, 0, alignment,
+	vma = i915_gem_object_ggtt_pin(obj, view, 0, alignment,
 				       view->type == I915_GGTT_VIEW_NORMAL ?
 				       PIN_MAPPABLE : 0);
-	if (ret)
+	if (IS_ERR(vma))
 		goto err_unpin_display;
 
+	WARN_ON(obj->pin_display > i915_vma_pin_count(vma));
+
 	i915_gem_object_flush_cpu_write_domain(obj);
 
 	old_write_domain = obj->base.write_domain;
@@ -3464,23 +3477,23 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 					    old_read_domains,
 					    old_write_domain);
 
-	return 0;
+	return vma;
 
 err_unpin_display:
 	obj->pin_display--;
-	return ret;
+	return vma;
 }
 
 void
-i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj,
-					 const struct i915_ggtt_view *view)
+i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
 {
-	if (WARN_ON(obj->pin_display == 0))
+	if (WARN_ON(vma->obj->pin_display == 0))
 		return;
 
-	i915_gem_object_ggtt_unpin_view(obj, view);
+	vma->obj->pin_display--;
 
-	obj->pin_display--;
+	i915_vma_unpin(vma);
+	WARN_ON(vma->obj->pin_display > i915_vma_pin_count(vma));
 }
 
 /**
@@ -3677,27 +3690,25 @@ err:
 	return ret;
 }
 
-int
+struct i915_vma *
 i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 const struct i915_ggtt_view *view,
 			 u64 size,
 			 u64 alignment,
 			 u64 flags)
 {
+	struct i915_address_space *vm = &to_i915(obj->base.dev)->ggtt.base;
 	struct i915_vma *vma;
 	int ret;
 
-	if (!view)
-		view = &i915_ggtt_view_normal;
-
-	vma = i915_gem_obj_lookup_or_create_ggtt_vma(obj, view);
+	vma = i915_gem_obj_lookup_or_create_vma(obj, vm, view);
 	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+		return vma;
 
 	if (i915_vma_misplaced(vma, size, alignment, flags)) {
 		if (flags & PIN_NONBLOCK &&
 		    (i915_vma_is_pinned(vma) || i915_vma_is_active(vma)))
-			return -ENOSPC;
+			return ERR_PTR(-ENOSPC);
 
 		WARN(i915_vma_is_pinned(vma),
 		     "bo is already pinned in ggtt with incorrect alignment:"
@@ -3710,17 +3721,14 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 		     obj->map_and_fenceable);
 		ret = i915_vma_unbind(vma);
 		if (ret)
-			return ret;
+			return ERR_PTR(ret);
 	}
 
-	return i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
-}
+	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
+	if (ret)
+		return ERR_PTR(ret);
 
-void
-i915_gem_object_ggtt_unpin_view(struct drm_i915_gem_object *obj,
-				const struct i915_ggtt_view *view)
-{
-	i915_vma_unpin(i915_gem_obj_to_ggtt_view(obj, view));
+	return vma;
 }
 
 static __always_inline unsigned int __busy_read_flag(unsigned int id)
@@ -4106,32 +4114,6 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	intel_runtime_pm_put(dev_priv);
 }
 
-struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
-				     struct i915_address_space *vm)
-{
-	struct i915_vma *vma;
-	list_for_each_entry(vma, &obj->vma_list, obj_link) {
-		if (vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL &&
-		    vma->vm == vm)
-			return vma;
-	}
-	return NULL;
-}
-
-struct i915_vma *i915_gem_obj_to_ggtt_view(struct drm_i915_gem_object *obj,
-					   const struct i915_ggtt_view *view)
-{
-	struct i915_vma *vma;
-
-	GEM_BUG_ON(!view);
-
-	list_for_each_entry(vma, &obj->vma_list, obj_link)
-		if (i915_vma_is_ggtt(vma) &&
-		    i915_ggtt_view_equal(&vma->ggtt_view, view))
-			return vma;
-	return NULL;
-}
-
 int i915_gem_suspend(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -4599,97 +4581,6 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old,
 	}
 }
 
-/* All the new VM stuff */
-u64 i915_gem_obj_offset(struct drm_i915_gem_object *o,
-			struct i915_address_space *vm)
-{
-	struct drm_i915_private *dev_priv = to_i915(o->base.dev);
-	struct i915_vma *vma;
-
-	WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base);
-
-	list_for_each_entry(vma, &o->vma_list, obj_link) {
-		if (i915_vma_is_ggtt(vma) &&
-		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
-			continue;
-		if (vma->vm == vm)
-			return vma->node.start;
-	}
-
-	WARN(1, "%s vma for this object not found.\n",
-	     i915_is_ggtt(vm) ? "global" : "ppgtt");
-	return -1;
-}
-
-u64 i915_gem_obj_ggtt_offset_view(struct drm_i915_gem_object *o,
-				  const struct i915_ggtt_view *view)
-{
-	struct i915_vma *vma;
-
-	list_for_each_entry(vma, &o->vma_list, obj_link)
-		if (i915_vma_is_ggtt(vma) &&
-		    i915_ggtt_view_equal(&vma->ggtt_view, view))
-			return vma->node.start;
-
-	WARN(1, "global vma for this object not found. (view=%u)\n", view->type);
-	return -1;
-}
-
-bool i915_gem_obj_bound(struct drm_i915_gem_object *o,
-			struct i915_address_space *vm)
-{
-	struct i915_vma *vma;
-
-	list_for_each_entry(vma, &o->vma_list, obj_link) {
-		if (i915_vma_is_ggtt(vma) &&
-		    vma->ggtt_view.type != I915_GGTT_VIEW_NORMAL)
-			continue;
-		if (vma->vm == vm && drm_mm_node_allocated(&vma->node))
-			return true;
-	}
-
-	return false;
-}
-
-bool i915_gem_obj_ggtt_bound_view(struct drm_i915_gem_object *o,
-				  const struct i915_ggtt_view *view)
-{
-	struct i915_vma *vma;
-
-	list_for_each_entry(vma, &o->vma_list, obj_link)
-		if (i915_vma_is_ggtt(vma) &&
-		    i915_ggtt_view_equal(&vma->ggtt_view, view) &&
-		    drm_mm_node_allocated(&vma->node))
-			return true;
-
-	return false;
-}
-
-unsigned long i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o)
-{
-	struct i915_vma *vma;
-
-	GEM_BUG_ON(list_empty(&o->vma_list));
-
-	list_for_each_entry(vma, &o->vma_list, obj_link) {
-		if (i915_vma_is_ggtt(vma) &&
-		    vma->ggtt_view.type == I915_GGTT_VIEW_NORMAL)
-			return vma->node.size;
-	}
-
-	return 0;
-}
-
-bool i915_gem_obj_is_pinned(struct drm_i915_gem_object *obj)
-{
-	struct i915_vma *vma;
-	list_for_each_entry(vma, &obj->vma_list, obj_link)
-		if (i915_vma_is_pinned(vma))
-			return true;
-
-	return false;
-}
-
 /* Like i915_gem_object_get_page(), but mark the returned page dirty */
 struct page *
 i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, int n)
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index ced05878b405..58c49625a51d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -180,8 +180,8 @@ eb_lookup_vmas(struct eb_vmas *eb,
 		 * from the (obj, vm) we don't run the risk of creating
 		 * duplicated vmas for the same vm.
 		 */
-		vma = i915_gem_obj_lookup_or_create_vma(obj, vm);
-		if (IS_ERR(vma)) {
+		vma = i915_gem_obj_lookup_or_create_vma(obj, vm, NULL);
+		if (unlikely(IS_ERR(vma))) {
 			DRM_DEBUG("Failed to lookup VMA\n");
 			ret = PTR_ERR(vma);
 			goto err;
@@ -349,30 +349,33 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 		   struct drm_i915_gem_relocation_entry *reloc,
 		   uint64_t target_offset)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct i915_vma *vma;
 	uint64_t delta = relocation_target(reloc, target_offset);
 	uint64_t offset;
 	void __iomem *reloc_page;
 	int ret;
 
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
 	ret = i915_gem_object_set_to_gtt_domain(obj, true);
 	if (ret)
-		return ret;
+		goto unpin;
 
 	ret = i915_gem_object_put_fence(obj);
 	if (ret)
-		return ret;
+		goto unpin;
 
 	/* Map the page containing the relocation we're going to perform.  */
-	offset = i915_gem_obj_ggtt_offset(obj);
-	offset += reloc->offset;
+	offset = vma->node.start + reloc->offset;
 	reloc_page = io_mapping_map_atomic_wc(ggtt->mappable,
 					      offset & PAGE_MASK);
 	iowrite32(lower_32_bits(delta), reloc_page + offset_in_page(offset));
 
-	if (INTEL_INFO(dev)->gen >= 8) {
+	if (INTEL_GEN(dev_priv) >= 8) {
 		offset += sizeof(uint32_t);
 
 		if (offset_in_page(offset) == 0) {
@@ -388,7 +391,9 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 
 	io_mapping_unmap_atomic(reloc_page);
 
-	return 0;
+unpin:
+	i915_vma_unpin(vma);
+	return ret;
 }
 
 static void
@@ -1281,7 +1286,7 @@ i915_reset_gen7_sol_offsets(struct drm_i915_gem_request *req)
 	return 0;
 }
 
-static struct i915_vma*
+static struct i915_vma *
 i915_gem_execbuffer_parse(struct intel_engine_cs *engine,
 			  struct drm_i915_gem_exec_object2 *shadow_exec_entry,
 			  struct drm_i915_gem_object *batch_obj,
@@ -1305,31 +1310,28 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *engine,
 				      batch_start_offset,
 				      batch_len,
 				      is_master);
-	if (ret)
+	if (ret) {
+		if (ret == -EACCES) /* unhandled chained batch */
+			vma = NULL;
+		else
+			vma = ERR_PTR(ret);
 		goto err;
+	}
 
-	ret = i915_gem_object_ggtt_pin(shadow_batch_obj, NULL, 0, 0, 0);
-	if (ret)
+	vma = i915_gem_object_ggtt_pin(shadow_batch_obj, NULL, 0, 0, 0);
+	if (IS_ERR(vma))
 		goto err;
 
-	i915_gem_object_unpin_pages(shadow_batch_obj);
-
 	memset(shadow_exec_entry, 0, sizeof(*shadow_exec_entry));
 
-	vma = i915_gem_obj_to_ggtt(shadow_batch_obj);
 	vma->exec_entry = shadow_exec_entry;
 	vma->exec_entry->flags = __EXEC_OBJECT_HAS_PIN;
 	i915_gem_object_get(shadow_batch_obj);
 	list_add_tail(&vma->exec_list, &eb->vmas);
 
-	return vma;
-
 err:
 	i915_gem_object_unpin_pages(shadow_batch_obj);
-	if (ret == -EACCES) /* unhandled chained batch */
-		return NULL;
-	else
-		return ERR_PTR(ret);
+	return vma;
 }
 
 static int
@@ -1677,6 +1679,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	 * hsw should have this fixed, but bdw mucks it up again. */
 	if (dispatch_flags & I915_DISPATCH_SECURE) {
 		struct drm_i915_gem_object *obj = params->batch->obj;
+		struct i915_vma *vma;
 
 		/*
 		 * So on first glance it looks freaky that we pin the batch here
@@ -1688,11 +1691,13 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		 *   fitting due to fragmentation.
 		 * So this is actually safe.
 		 */
-		ret = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
-		if (ret)
+		vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
+		if (IS_ERR(vma)) {
+			ret = PTR_ERR(vma);
 			goto err;
+		}
 
-		params->batch = i915_gem_obj_to_ggtt(obj);
+		params->batch = vma;
 	}
 
 	/* Allocate a request for this batch buffer nice and early. */
@@ -1708,7 +1713,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	 * inactive_list and lose its active reference. Hence we do not need
 	 * to explicitly hold another reference here.
 	 */
-	params->request->batch_obj = params->batch->obj;
+	params->request->batch = params->batch;
 
 	ret = i915_gem_request_add_to_client(params->request, file);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 1d0f975c61f8..911cea719e79 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -85,7 +85,7 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 	POSTING_READ(fence_reg_lo);
 
 	if (obj) {
-		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
+		struct i915_vma *vma = i915_gem_object_to_ggtt(obj, NULL);
 		unsigned int tiling = i915_gem_object_get_tiling(obj);
 		unsigned int stride = i915_gem_object_get_stride(obj);
 		u64 size = vma->node.size;
@@ -120,7 +120,7 @@ static void i915_write_fence_reg(struct drm_device *dev, int reg,
 	u32 val;
 
 	if (obj) {
-		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
+		struct i915_vma *vma = i915_gem_object_to_ggtt(obj, NULL);
 		unsigned int tiling = i915_gem_object_get_tiling(obj);
 		unsigned int stride = i915_gem_object_get_stride(obj);
 		int pitch_val;
@@ -161,7 +161,7 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg,
 	u32 val;
 
 	if (obj) {
-		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
+		struct i915_vma *vma = i915_gem_object_to_ggtt(obj, NULL);
 		unsigned int tiling = i915_gem_object_get_tiling(obj);
 		unsigned int stride = i915_gem_object_get_stride(obj);
 		u32 pitch_val;
@@ -432,13 +432,7 @@ bool
 i915_gem_object_pin_fence(struct drm_i915_gem_object *obj)
 {
 	if (obj->fence_reg != I915_FENCE_REG_NONE) {
-		struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-		struct i915_vma *ggtt_vma = i915_gem_obj_to_ggtt(obj);
-
-		WARN_ON(!ggtt_vma ||
-			dev_priv->fence_regs[obj->fence_reg].pin_count >
-			i915_vma_pin_count(ggtt_vma));
-		dev_priv->fence_regs[obj->fence_reg].pin_count++;
+		to_i915(obj->base.dev)->fence_regs[obj->fence_reg].pin_count++;
 		return true;
 	} else
 		return false;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d15eb1d71341..47159ba649b8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3341,23 +3341,20 @@ void i915_vma_close(struct i915_vma *vma)
 }
 
 static struct i915_vma *
-__i915_gem_vma_create(struct drm_i915_gem_object *obj,
-		      struct i915_address_space *vm,
-		      const struct i915_ggtt_view *view)
+__i915_vma_create(struct drm_i915_gem_object *obj,
+		  struct i915_address_space *vm,
+		  const struct i915_ggtt_view *view)
 {
 	struct i915_vma *vma;
 	int i;
 
 	GEM_BUG_ON(vm->closed);
-
-	if (WARN_ON(i915_is_ggtt(vm) != !!view))
-		return ERR_PTR(-EINVAL);
+	GEM_BUG_ON((i915_is_ggtt(vm) != !!view));
 
 	vma = kmem_cache_zalloc(to_i915(obj->base.dev)->vmas, GFP_KERNEL);
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	INIT_LIST_HEAD(&vma->obj_link);
 	INIT_LIST_HEAD(&vma->exec_list);
 	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
 		init_request_active(&vma->last_read[i], i915_vma_retire);
@@ -3366,8 +3363,7 @@ __i915_gem_vma_create(struct drm_i915_gem_object *obj,
 	vma->obj = obj;
 	vma->size = obj->base.size;
 
-	if (i915_is_ggtt(vm)) {
-		vma->flags |= I915_VMA_GGTT;
+	if (view) {
 		vma->ggtt_view = *view;
 		if (view->type == I915_GGTT_VIEW_PARTIAL) {
 			vma->size = view->params.partial.size;
@@ -3377,57 +3373,79 @@ __i915_gem_vma_create(struct drm_i915_gem_object *obj,
 				intel_rotation_info_size(&view->params.rotated);
 			vma->size <<= PAGE_SHIFT;
 		}
+	}
+
+	if (i915_is_ggtt(vm)) {
+		vma->flags |= I915_VMA_GGTT;
 	} else {
 		i915_ppgtt_get(i915_vm_to_ppgtt(vm));
 	}
 
 	list_add_tail(&vma->obj_link, &obj->vma_list);
-
 	return vma;
 }
 
+static inline bool vma_matches(struct i915_vma *vma,
+			       struct i915_address_space *vm,
+			       const struct i915_ggtt_view *view)
+{
+	if (vma->vm != vm)
+		return false;
+
+	if (!i915_vma_is_ggtt(vma))
+		return true;
+
+	if (!view)
+		return vma->ggtt_view.type == 0;
+
+	if (vma->ggtt_view.type != view->type)
+		return false;
+
+	return memcmp(&vma->ggtt_view.params,
+		      &view->params,
+		      sizeof(view->params)) == 0;
+}
+
 struct i915_vma *
 i915_vma_create(struct drm_i915_gem_object *obj,
 		struct i915_address_space *vm,
 		const struct i915_ggtt_view *view)
 {
 	GEM_BUG_ON(view && !i915_is_ggtt(vm));
-	GEM_BUG_ON(view ? i915_gem_obj_to_ggtt_view(obj, view) : i915_gem_obj_to_vma(obj, vm));
+	GEM_BUG_ON(i915_gem_obj_to_vma(obj, vm, view));
 
-	return __i915_gem_vma_create(obj, vm, view ?: &i915_ggtt_view_normal);
+	return __i915_vma_create(obj, vm, view);
 }
 
 struct i915_vma *
-i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
-				  struct i915_address_space *vm)
+i915_gem_obj_to_vma(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    const struct i915_ggtt_view *view)
 {
 	struct i915_vma *vma;
 
-	vma = i915_gem_obj_to_vma(obj, vm);
-	if (!vma)
-		vma = __i915_gem_vma_create(obj, vm,
-					    i915_is_ggtt(vm) ? &i915_ggtt_view_normal : NULL);
+	list_for_each_entry_reverse(vma, &obj->vma_list, obj_link)
+		if (vma_matches(vma, vm, view))
+			return vma;
 
-	return vma;
+	return NULL;
 }
 
 struct i915_vma *
-i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj,
-				       const struct i915_ggtt_view *view)
+i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj,
+				  struct i915_address_space *vm,
+				  const struct i915_ggtt_view *view)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct i915_vma *vma = i915_gem_obj_to_ggtt_view(obj, view);
+	struct i915_vma *vma;
 
-	GEM_BUG_ON(!view);
+	GEM_BUG_ON(view && !i915_is_ggtt(vm));
 
+	vma = i915_gem_obj_to_vma(obj, vm, view);
 	if (!vma)
-		vma = __i915_gem_vma_create(obj, &ggtt->base, view);
+		vma = __i915_vma_create(obj, vm, view);
 
 	GEM_BUG_ON(i915_vma_is_closed(vma));
 	return vma;
-
 }
 
 static struct scatterlist *
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index ec538fcc9c20..71513b13ca94 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -610,20 +610,6 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev);
 int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj);
 void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj);
 
-static inline bool
-i915_ggtt_view_equal(const struct i915_ggtt_view *a,
-                     const struct i915_ggtt_view *b)
-{
-	if (WARN_ON(!a || !b))
-		return false;
-
-	if (a->type != b->type)
-		return false;
-	if (a->type != I915_GGTT_VIEW_NORMAL)
-		return !memcmp(&a->params, &b->params, sizeof(a->params));
-	return true;
-}
-
 /* Flags used by pin/bind&friends. */
 #define PIN_NONBLOCK		BIT(0)
 #define PIN_MAPPABLE		BIT(1)
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 4c5b7e104f2f..a0756b553a19 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -406,7 +406,7 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 	/* No zalloc, must clear what we need by hand */
 	req->previous_context = NULL;
 	req->file_priv = NULL;
-	req->batch_obj = NULL;
+	req->batch = NULL;
 	req->pid = NULL;
 	req->elsp_submitted = 0;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index 85393be09c27..a66243a6f791 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -118,7 +118,7 @@ struct drm_i915_gem_request {
 	/** Batch buffer related to this request if any (used for
 	 * error state dump only).
 	 */
-	struct drm_i915_gem_object *batch_obj;
+	struct i915_vma *batch;
 	struct list_head active_list;
 
 	/** Time at which this request was emitted, in jiffies. */
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index f7633585ea38..9a9b3cfbac7f 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -696,7 +696,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	if (gtt_offset == I915_GTT_OFFSET_NONE)
 		return obj;
 
-	vma = i915_gem_obj_lookup_or_create_vma(obj, &ggtt->base);
+	vma = i915_gem_obj_lookup_or_create_vma(obj, &ggtt->base, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err;
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 2ceaddc959d3..265e4123e678 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -130,7 +130,7 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
 	if (INTEL_GEN(dev_priv) >= 4)
 		return 0;
 
-	vma = i915_gem_obj_to_ggtt(obj);
+	vma = i915_gem_object_to_ggtt(obj, NULL);
 	if (!vma)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 54c04eddf313..5b4b0f4dea4f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -654,46 +654,42 @@ static void i915_error_state_free(struct kref *error_ref)
 
 static struct drm_i915_error_object *
 i915_error_object_create(struct drm_i915_private *dev_priv,
-			 struct drm_i915_gem_object *src,
-			 struct i915_address_space *vm)
+			 struct i915_vma *vma)
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct drm_i915_gem_object *src;
 	struct drm_i915_error_object *dst;
-	struct i915_vma *vma = NULL;
 	int num_pages;
 	bool use_ggtt;
 	int i = 0;
 	u64 reloc_offset;
 
-	if (src == NULL || src->pages == NULL)
+	if (!vma)
+		return NULL;
+
+	src = vma->obj;
+	if (!src->pages)
 		return NULL;
 
 	num_pages = src->base.size >> PAGE_SHIFT;
 
 	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC);
-	if (dst == NULL)
+	if (!dst)
 		return NULL;
 
-	if (i915_gem_obj_bound(src, vm))
-		dst->gtt_offset = i915_gem_obj_offset(src, vm);
-	else
-		dst->gtt_offset = -1;
-
-	reloc_offset = dst->gtt_offset;
-	if (i915_is_ggtt(vm))
-		vma = i915_gem_obj_to_ggtt(src);
+	reloc_offset = dst->gtt_offset = vma->node.start;
 	use_ggtt = (src->cache_level == I915_CACHE_NONE &&
-		   vma && (vma->flags & I915_VMA_GLOBAL_BIND) &&
+		   (vma->flags & I915_VMA_GLOBAL_BIND) &&
 		   reloc_offset + num_pages * PAGE_SIZE <= ggtt->mappable_end);
 
 	/* Cannot access stolen address directly, try to use the aperture */
 	if (src->stolen) {
 		use_ggtt = true;
 
-		if (!(vma && vma->flags & I915_VMA_GLOBAL_BIND))
+		if (!(vma->flags & I915_VMA_GLOBAL_BIND))
 			goto unwind;
 
-		reloc_offset = i915_gem_obj_ggtt_offset(src);
+		reloc_offset = vma->node.start;
 		if (reloc_offset + num_pages * PAGE_SIZE > ggtt->mappable_end)
 			goto unwind;
 	}
@@ -746,8 +742,6 @@ unwind:
 	kfree(dst);
 	return NULL;
 }
-#define i915_error_ggtt_object_create(dev_priv, src) \
-	i915_error_object_create((dev_priv), (src), &(dev_priv)->ggtt.base)
 
 /* The error capture is special as tries to run underneath the normal
  * locking rules - so we use the raw version of the i915_gem_active lookup.
@@ -1056,8 +1050,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 	int i, count;
 
 	error->semaphore =
-		i915_error_ggtt_object_create(dev_priv,
-					      dev_priv->semaphore->obj);
+		i915_error_object_create(dev_priv, dev_priv->semaphore);
 
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
 		struct intel_engine_cs *engine = &dev_priv->engine[i];
@@ -1087,18 +1080,16 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			 */
 			ee->batchbuffer =
 				i915_error_object_create(dev_priv,
-							 request->batch_obj,
-							 ee->vm);
+							 request->batch);
 
 			if (HAS_BROKEN_CS_TLB(dev_priv))
 				ee->wa_batchbuffer =
-					i915_error_ggtt_object_create(dev_priv,
-								      engine->scratch->obj);
+					i915_error_object_create(dev_priv,
+								 engine->scratch);
 
-			if (request->ctx->engine[i].state) {
-				ee->ctx = i915_error_ggtt_object_create(dev_priv,
-									request->ctx->engine[i].state->obj);
-			}
+			ee->ctx =
+				i915_error_object_create(dev_priv,
+							 request->ctx->engine[i].state);
 
 			if (request->pid) {
 				struct task_struct *task;
@@ -1119,16 +1110,15 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			ee->cpu_ring_head = ring->head;
 			ee->cpu_ring_tail = ring->tail;
 			ee->ringbuffer =
-				i915_error_ggtt_object_create(dev_priv,
-							      ring->vma->obj);
+				i915_error_object_create(dev_priv, ring->vma);
 		}
 
 		ee->hws_page =
-			i915_error_ggtt_object_create(dev_priv,
-						      engine->status_page.vma->obj);
+			i915_error_object_create(dev_priv,
+						 engine->status_page.vma);
 
-		ee->wa_ctx = i915_error_ggtt_object_create(dev_priv,
-							   engine->wa_ctx.vma->obj);
+		ee->wa_ctx =
+			i915_error_object_create(dev_priv, engine->wa_ctx.vma);
 
 		count = 0;
 		list_for_each_entry(request, &engine->request_list, link)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2e7d03c5bf5c..e582b4267036 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2179,14 +2179,14 @@ static unsigned int intel_surf_alignment(const struct drm_i915_private *dev_priv
 	}
 }
 
-int
-intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
-			   unsigned int rotation)
+struct i915_vma *
+intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
 {
 	struct drm_device *dev = fb->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct i915_ggtt_view view;
+	struct i915_vma *vma;
 	u32 alignment;
 	int ret;
 
@@ -2213,10 +2213,11 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	 */
 	intel_runtime_pm_get(dev_priv);
 
-	ret = i915_gem_object_pin_to_display_plane(obj, alignment,
-						   &view);
-	if (ret)
+	vma = i915_gem_object_pin_to_display_plane(obj, alignment, &view);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
 		goto err_pm;
+	}
 
 	/* Install a fence for tiled scan-out. Pre-i965 always needs a
 	 * fence, whereas 965+ only requires a fence if using
@@ -2243,19 +2244,20 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	}
 
 	intel_runtime_pm_put(dev_priv);
-	return 0;
+	return vma;
 
 err_unpin:
-	i915_gem_object_unpin_from_display_plane(obj, &view);
+	i915_gem_object_unpin_from_display_plane(vma);
 err_pm:
 	intel_runtime_pm_put(dev_priv);
-	return ret;
+	return ERR_PTR(ret);
 }
 
 void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
 {
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct i915_ggtt_view view;
+	struct i915_vma *vma;
 
 	WARN_ON(!mutex_is_locked(&obj->base.dev->struct_mutex));
 
@@ -2264,7 +2266,8 @@ void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
 	if (view.type == I915_GGTT_VIEW_NORMAL)
 		i915_gem_object_unpin_fence(obj);
 
-	i915_gem_object_unpin_from_display_plane(obj, &view);
+	vma = i915_gem_object_to_ggtt(obj, &view);
+	i915_gem_object_unpin_from_display_plane(vma);
 }
 
 static int intel_fb_pitch(const struct drm_framebuffer *fb, int plane,
@@ -2796,7 +2799,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 			continue;
 
 		obj = intel_fb_obj(fb);
-		if (i915_gem_obj_ggtt_offset(obj) == plane_config->base) {
+		if (i915_gem_object_ggtt_offset(obj, NULL) == plane_config->base) {
 			drm_framebuffer_reference(fb);
 			goto valid_fb;
 		}
@@ -3115,7 +3118,7 @@ static void i9xx_update_primary_plane(struct drm_plane *primary,
 		I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	} else
-		I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset);
+		I915_WRITE(DSPADDR(plane), i915_gem_object_ggtt_offset(obj, NULL) + linear_offset);
 	POSTING_READ(reg);
 }
 
@@ -3237,11 +3240,17 @@ u32 intel_fb_gtt_offset(struct drm_framebuffer *fb,
 {
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct i915_ggtt_view view;
+	struct i915_vma *vma;
 	u64 offset;
 
 	intel_fill_fb_ggtt_view(&view, fb, rotation);
 
-	offset = i915_gem_obj_ggtt_offset_view(obj, &view);
+	vma = i915_gem_object_to_ggtt(obj, &view);
+	if (WARN(!vma, "ggtt vma for display object not found! (view=%u)\n",
+		 view.type))
+		return -1;
+
+	offset = vma->node.start;
 
 	WARN_ON(upper_32_bits(offset));
 
@@ -12032,6 +12041,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	struct intel_engine_cs *engine;
 	bool mmio_flip;
 	struct drm_i915_gem_request *request;
+	struct i915_vma *vma;
 	int ret;
 
 	/*
@@ -12139,9 +12149,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	mmio_flip = use_mmio_flip(engine, obj);
 
-	ret = intel_pin_and_fence_fb_obj(fb, primary->state->rotation);
-	if (ret)
+	vma = intel_pin_and_fence_fb_obj(fb, primary->state->rotation);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
 		goto cleanup_pending;
+	}
 
 	work->gtt_offset = intel_fb_gtt_offset(fb, primary->state->rotation);
 	work->gtt_offset += intel_crtc->dspaddr_offset;
@@ -14484,7 +14496,11 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		if (ret)
 			DRM_DEBUG_KMS("failed to attach phys object\n");
 	} else {
-		ret = intel_pin_and_fence_fb_obj(fb, new_state->rotation);
+		struct i915_vma *vma;
+
+		vma = intel_pin_and_fence_fb_obj(fb, new_state->rotation);
+		if (IS_ERR(vma))
+			ret = PTR_ERR(vma);
 	}
 
 	if (ret == 0) {
@@ -14850,7 +14866,7 @@ intel_update_cursor_plane(struct drm_plane *plane,
 	if (!obj)
 		addr = 0;
 	else if (!INTEL_INFO(dev)->cursor_needs_physical)
-		addr = i915_gem_obj_ggtt_offset(obj);
+		addr = i915_gem_object_ggtt_offset(obj, NULL);
 	else
 		addr = obj->phys_handle->busaddr;
 
@@ -16723,7 +16739,6 @@ void intel_modeset_gem_init(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *c;
 	struct drm_i915_gem_object *obj;
-	int ret;
 
 	intel_init_gt_powersave(dev_priv);
 
@@ -16737,15 +16752,17 @@ void intel_modeset_gem_init(struct drm_device *dev)
 	 * for this.
 	 */
 	for_each_crtc(dev, c) {
+		struct i915_vma *vma;
+
 		obj = intel_fb_obj(c->primary->fb);
 		if (obj == NULL)
 			continue;
 
 		mutex_lock(&dev->struct_mutex);
-		ret = intel_pin_and_fence_fb_obj(c->primary->fb,
+		vma = intel_pin_and_fence_fb_obj(c->primary->fb,
 						 c->primary->state->rotation);
 		mutex_unlock(&dev->struct_mutex);
-		if (ret) {
+		if (IS_ERR(vma)) {
 			DRM_ERROR("failed to pin boot fb on pipe %d\n",
 				  to_intel_crtc(c)->pipe);
 			drm_framebuffer_unreference(c->primary->fb);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9539f0e63fa5..1c700b0c3cea 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -193,6 +193,7 @@ struct intel_framebuffer {
 struct intel_fbdev {
 	struct drm_fb_helper helper;
 	struct intel_framebuffer *fb;
+	struct i915_vma *vma;
 	async_cookie_t cookie;
 	int preferred_bpp;
 };
@@ -1239,8 +1240,8 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 void intel_release_load_detect_pipe(struct drm_connector *connector,
 				    struct intel_load_detect_pipe *old,
 				    struct drm_modeset_acquire_ctx *ctx);
-int intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
-			       unsigned int rotation);
+struct i915_vma *
+intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation);
 void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation);
 struct drm_framebuffer *
 __intel_framebuffer_create(struct drm_device *dev,
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index e67b09a3328c..e122052c4081 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -737,7 +737,7 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 	/* FIXME: We lack the proper locking here, so only run this on the
 	 * platforms that need. */
 	if (IS_GEN(dev_priv, 5, 6))
-		cache->fb.ilk_ggtt_offset = i915_gem_obj_ggtt_offset(obj);
+		cache->fb.ilk_ggtt_offset = i915_gem_object_ggtt_offset(obj, NULL);
 	cache->fb.pixel_format = fb->pixel_format;
 	cache->fb.stride = fb->pitches[0];
 	cache->fb.fence_reg = obj->fence_reg;
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 82bf282a4ff4..863e7a91ece0 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -188,7 +188,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	struct fb_info *info;
 	struct drm_framebuffer *fb;
 	struct i915_vma *vma;
-	struct drm_i915_gem_object *obj;
 	bool prealloc = false;
 	void __iomem *vaddr;
 	int ret;
@@ -216,17 +215,17 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		sizes->fb_height = intel_fb->base.height;
 	}
 
-	obj = intel_fb->obj;
-
 	mutex_lock(&dev->struct_mutex);
 
 	/* Pin the GGTT vma for our access via info->screen_base.
 	 * This also validates that any existing fb inherited from the
 	 * BIOS is suitable for own access.
 	 */
-	ret = intel_pin_and_fence_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0);
-	if (ret)
+	vma = intel_pin_and_fence_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
 		goto out_unlock;
+	}
 
 	info = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(info)) {
@@ -246,8 +245,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->flags = FBINFO_DEFAULT | FBINFO_CAN_FORCE_OUTPUT;
 	info->fbops = &intelfb_ops;
 
-	vma = i915_gem_obj_to_ggtt(obj);
-
 	/* setup aperture base/size for vesafb takeover */
 	info->apertures->ranges[0].base = dev->mode_config.fb_base;
 	info->apertures->ranges[0].size = ggtt->mappable_end;
@@ -274,14 +271,14 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	 * If the object is stolen however, it will be full of whatever
 	 * garbage was left in there.
 	 */
-	if (ifbdev->fb->obj->stolen && !prealloc)
+	if (intel_fb->obj->stolen && !prealloc)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08llx, bo %p\n",
-		      fb->width, fb->height,
-		      i915_gem_obj_ggtt_offset(obj), obj);
+	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08llx\n",
+		      fb->width, fb->height, vma->node.start);
+	ifbdev->vma = vma;
 
 	mutex_unlock(&dev->struct_mutex);
 	vga_switcheroo_client_fb_set(dev->pdev, info);
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index 1e2d9f2ad4f6..7dd745dfeffb 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -249,12 +249,12 @@ static inline bool guc_ucode_response(struct drm_i915_private *dev_priv,
  * Note that GuC needs the CSS header plus uKernel code to be copied by the
  * DMA engine in one operation, whereas the RSA signature is loaded via MMIO.
  */
-static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv)
+static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv,
+			      struct i915_vma *vma)
 {
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
-	struct drm_i915_gem_object *fw_obj = guc_fw->guc_fw_obj;
 	unsigned long offset;
-	struct sg_table *sg = fw_obj->pages;
+	struct sg_table *sg = vma->pages;
 	u32 status, rsa[UOS_RSA_SCRATCH_MAX_COUNT];
 	int i, ret = 0;
 
@@ -271,7 +271,7 @@ static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv)
 	I915_WRITE(DMA_COPY_SIZE, guc_fw->header_size + guc_fw->ucode_size);
 
 	/* Set the source address for the new blob */
-	offset = i915_gem_obj_ggtt_offset(fw_obj) + guc_fw->header_offset;
+	offset = vma->node.start + guc_fw->header_offset;
 	I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset));
 	I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF);
 
@@ -326,6 +326,7 @@ static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
 {
 	struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
 	struct drm_device *dev = &dev_priv->drm;
+	struct i915_vma *vma;
 	int ret;
 
 	ret = i915_gem_object_set_to_gtt_domain(guc_fw->guc_fw_obj, false);
@@ -334,10 +335,10 @@ static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
 		return ret;
 	}
 
-	ret = i915_gem_object_ggtt_pin(guc_fw->guc_fw_obj, NULL, 0, 0, 0);
-	if (ret) {
-		DRM_DEBUG_DRIVER("pin failed %d\n", ret);
-		return ret;
+	vma = i915_gem_object_ggtt_pin(guc_fw->guc_fw_obj, NULL, 0, 0, 0);
+	if (IS_ERR(vma)) {
+		DRM_DEBUG_DRIVER("pin failed %d\n", (int)PTR_ERR(vma));
+		return PTR_ERR(vma);
 	}
 
 	/* Invalidate GuC TLB to let GuC take the latest updates to GTT. */
@@ -380,7 +381,7 @@ static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
 
 	set_guc_init_params(dev_priv);
 
-	ret = guc_ucode_xfer_dma(dev_priv);
+	ret = guc_ucode_xfer_dma(dev_priv, vma);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
@@ -388,7 +389,7 @@ static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
 	 * We keep the object pages for reuse during resume. But we can unpin it
 	 * now that DMA has completed, so it doesn't continue to take up space.
 	 */
-	i915_gem_object_ggtt_unpin(guc_fw->guc_fw_obj);
+	i915_vma_unpin(vma);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index d930e3a4a9cd..402e05f2f1de 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -326,7 +326,7 @@ static void intel_overlay_release_old_vid_tail(struct i915_gem_active *active,
 	i915_gem_track_fb(vma->obj, NULL,
 			  INTEL_FRONTBUFFER_OVERLAY(overlay->crtc->pipe));
 
-	i915_gem_object_unpin_from_display_plane(vma->obj, &i915_ggtt_view_normal);
+	i915_gem_object_unpin_from_display_plane(vma);
 	i915_vma_put(vma);
 }
 
@@ -342,7 +342,7 @@ static void intel_overlay_off_tail(struct i915_gem_active *active,
 	if (WARN_ON(!vma))
 		return;
 
-	i915_gem_object_unpin_from_display_plane(vma->obj, &i915_ggtt_view_normal);
+	i915_gem_object_unpin_from_display_plane(vma);
 	i915_vma_put(vma);
 
 	overlay->crtc->overlay = NULL;
@@ -755,12 +755,10 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	if (ret != 0)
 		return ret;
 
-	ret = i915_gem_object_pin_to_display_plane(new_bo, 0,
+	vma = i915_gem_object_pin_to_display_plane(new_bo, 0,
 						   &i915_ggtt_view_normal);
-	if (ret != 0)
-		return ret;
-
-	vma = i915_gem_obj_to_ggtt_view(new_bo, &i915_ggtt_view_normal);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
 
 	ret = i915_gem_object_put_fence(new_bo);
 	if (ret)
@@ -803,7 +801,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	swidth = params->src_w;
 	swidthsw = calc_swidthsw(dev_priv, params->offset_Y, tmp_width);
 	sheight = params->src_h;
-	iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, &regs->OBUF_0Y);
+	iowrite32(vma->node.start + params->offset_Y, &regs->OBUF_0Y);
 	ostride = params->stride_Y;
 
 	if (params->format & I915_OVERLAY_YUV_PLANAR) {
@@ -817,8 +815,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 				      params->src_w/uv_hscale);
 		swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
 		sheight |= (params->src_h/uv_vscale) << 16;
-		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_U, &regs->OBUF_0U);
-		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_V, &regs->OBUF_0V);
+		iowrite32(vma->node.start + params->offset_U, &regs->OBUF_0U);
+		iowrite32(vma->node.start + params->offset_V, &regs->OBUF_0V);
 		ostride |= params->stride_UV << 16;
 	}
 
@@ -850,7 +848,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	return 0;
 
 out_unpin:
-	i915_gem_object_ggtt_unpin(new_bo);
+	i915_gem_object_unpin_from_display_plane(vma);
 	return ret;
 }
 
@@ -1373,6 +1371,7 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv)
 	struct intel_overlay *overlay;
 	struct drm_i915_gem_object *reg_bo;
 	struct overlay_registers __iomem *regs;
+	struct i915_vma *vma = NULL;
 	int ret;
 
 	if (!HAS_OVERLAY(dev_priv))
@@ -1406,13 +1405,14 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv)
 		}
 		overlay->flip_addr = reg_bo->phys_handle->busaddr;
 	} else {
-		ret = i915_gem_object_ggtt_pin(reg_bo, NULL,
+		vma = i915_gem_object_ggtt_pin(reg_bo, NULL,
 					       0, PAGE_SIZE, PIN_MAPPABLE);
-		if (ret) {
+		if (IS_ERR(vma)) {
 			DRM_ERROR("failed to pin overlay register bo\n");
+			ret = PTR_ERR(vma);
 			goto out_free_bo;
 		}
-		overlay->flip_addr = i915_gem_obj_ggtt_offset(reg_bo);
+		overlay->flip_addr = vma->node.start;
 
 		ret = i915_gem_object_set_to_gtt_domain(reg_bo, true);
 		if (ret) {
@@ -1444,8 +1444,8 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv)
 	return;
 
 out_unpin_bo:
-	if (!OVERLAY_NEEDS_PHYSICAL(dev_priv))
-		i915_gem_object_ggtt_unpin(reg_bo);
+	if (vma)
+		i915_vma_unpin(vma);
 out_free_bo:
 	i915_gem_object_put(reg_bo);
 out_free:
-- 
2.8.1

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

[PATCH 30/37] drm/i915: Introduce i915_ggtt_offset()

[Chris Wilson]

This little helper only exists to safely discard the upper unused 32bits
of the general 64-bit VMA address - as we know that all Global GTT
currently are less than 4GiB in size and so that the upper bits must be
zero. In many places, we use a u32 for the global GTT offset and we want
to document where we are discarding the full VMA offset.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c        |  2 +-
 drivers/gpu/drm/i915/i915_drv.h            |  2 +-
 drivers/gpu/drm/i915/i915_gem.c            | 11 +++++------
 drivers/gpu/drm/i915/i915_gem_context.c    |  6 ++++--
 drivers/gpu/drm/i915/i915_gem_gtt.h        |  9 +++++++++
 drivers/gpu/drm/i915/i915_guc_submission.c | 15 ++++++++-------
 drivers/gpu/drm/i915/intel_display.c       | 10 +++-------
 drivers/gpu/drm/i915/intel_engine_cs.c     |  4 ++--
 drivers/gpu/drm/i915/intel_fbdev.c         |  6 +++---
 drivers/gpu/drm/i915/intel_guc_loader.c    |  6 +++---
 drivers/gpu/drm/i915/intel_lrc.c           | 20 +++++++++++---------
 drivers/gpu/drm/i915/intel_overlay.c       | 10 ++++++----
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 28 ++++++++++++++--------------
 13 files changed, 70 insertions(+), 59 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 21961304284e..82652ad28cd4 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2008,7 +2008,7 @@ static void i915_dump_lrc_obj(struct seq_file *m,
 
 	if (vma->flags & I915_VMA_GLOBAL_BIND)
 		seq_printf(m, "\tBound in GGTT at 0x%08x\n",
-			   lower_32_bits(vma->node.start));
+			   i915_ggtt_offset(vma));
 
 	if (i915_gem_object_get_pages(vma->obj)) {
 		seq_puts(m, "\tFailed to get pages for context object\n\n");
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e22445e0b004..9414f3d4c2b3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3324,7 +3324,7 @@ static inline unsigned long
 i915_gem_object_ggtt_offset(struct drm_i915_gem_object *o,
 			    const struct i915_ggtt_view *view)
 {
-	return i915_gem_object_to_ggtt(o, view)->node.start;
+	return i915_ggtt_offset(i915_gem_object_to_ggtt(o, view));
 }
 
 /* i915_gem_fence.c */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d4938c4fd9c6..eaf85bbbf997 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -758,7 +758,7 @@ i915_gem_gtt_pread(struct drm_device *dev,
 
 		i915_gem_object_pin_pages(obj);
 	} else {
-		node.start = vma->node.start;
+		node.start = i915_ggtt_offset(vma);
 		node.allocated = false;
 		ret = i915_gem_object_put_fence(obj);
 		if (ret)
@@ -1062,7 +1062,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_private *i915,
 
 		i915_gem_object_pin_pages(obj);
 	} else {
-		node.start = vma->node.start;
+		node.start = i915_ggtt_offset(vma);
 		node.allocated = false;
 		ret = i915_gem_object_put_fence(obj);
 		if (ret)
@@ -1703,7 +1703,7 @@ int i915_gem_fault(struct vm_area_struct *area, struct vm_fault *vmf)
 		goto err_unpin;
 
 	/* Finally, remap it using the new GTT offset */
-	pfn = ggtt->mappable_base + vma->node.start;
+	pfn = ggtt->mappable_base + i915_ggtt_offset(vma);
 	pfn >>= PAGE_SHIFT;
 
 	if (unlikely(view.type == I915_GGTT_VIEW_PARTIAL)) {
@@ -3712,10 +3712,9 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 
 		WARN(i915_vma_is_pinned(vma),
 		     "bo is already pinned in ggtt with incorrect alignment:"
-		     " offset=%08x %08x, req.alignment=%llx, req.map_and_fenceable=%d,"
+		     " offset=%08x, req.alignment=%llx, req.map_and_fenceable=%d,"
 		     " obj->map_and_fenceable=%d\n",
-		     upper_32_bits(vma->node.start),
-		     lower_32_bits(vma->node.start),
+		     i915_ggtt_offset(vma),
 		     alignment,
 		     !!(flags & PIN_MAPPABLE),
 		     obj->map_and_fenceable);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index e566167d9441..98d2956f91f4 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -631,7 +631,8 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, req->ctx->engine[RCS].state->node.start | flags);
+	intel_ring_emit(ring,
+			i915_ggtt_offset(req->ctx->engine[RCS].state) | flags);
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -660,7 +661,8 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 					MI_STORE_REGISTER_MEM |
 					MI_SRM_LRM_GLOBAL_GTT);
 			intel_ring_emit_reg(ring, last_reg);
-			intel_ring_emit(ring, engine->scratch->node.start);
+			intel_ring_emit(ring,
+					i915_ggtt_offset(engine->scratch));
 			intel_ring_emit(ring, MI_NOOP);
 		}
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 71513b13ca94..d6e4b6529196 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -272,6 +272,15 @@ static inline bool i915_vma_has_active_engine(const struct i915_vma *vma,
 	return vma->active & BIT(engine);
 }
 
+static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
+{
+	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
+	GEM_BUG_ON(!vma->node.allocated);
+	GEM_BUG_ON(upper_32_bits(vma->node.start));
+	GEM_BUG_ON(upper_32_bits(vma->node.start + vma->node.size - 1));
+	return lower_32_bits(vma->node.start);
+}
+
 struct i915_page_dma {
 	struct page *page;
 	union {
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 75db2da76b41..ee77305f351b 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -358,11 +358,11 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 
 		/* The state page is after PPHWSP */
 		lrc->ring_lcra =
-			ce->state->node.start + LRC_STATE_PN * PAGE_SIZE;
+			i915_ggtt_offset(ce->state) + LRC_STATE_PN * PAGE_SIZE;
 		lrc->context_id = (client->ctx_index << GUC_ELC_CTXID_OFFSET) |
 				(guc_engine_id << GUC_ELC_ENGINE_OFFSET);
 
-		lrc->ring_begin = ce->ring->vma->node.start;
+		lrc->ring_begin = i915_ggtt_offset(ce->ring->vma);
 		lrc->ring_end = lrc->ring_begin + ce->ring->size - 1;
 		lrc->ring_next_free_location = lrc->ring_begin;
 		lrc->ring_current_tail_pointer_value = 0;
@@ -378,7 +378,7 @@ static void guc_init_ctx_desc(struct intel_guc *guc,
 	 * The doorbell, process descriptor, and workqueue are all parts
 	 * of the client object, which the GuC will reference via the GGTT
 	 */
-	gfx_addr = client->vma->node.start;
+	gfx_addr = i915_ggtt_offset(client->vma);
 	desc.db_trigger_phy = sg_dma_address(client->vma->pages->sgl) +
 				client->doorbell_offset;
 	desc.db_trigger_cpu = (uintptr_t)client->client_base +
@@ -862,7 +862,7 @@ static void guc_create_log(struct intel_guc *guc)
 		(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
 		(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
 
-	offset = vma->node.start >> PAGE_SHIFT; /* in pages */
+	offset = i915_ggtt_offset(vma) >> PAGE_SHIFT; /* in pages */
 	guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
 }
 
@@ -933,7 +933,8 @@ static void guc_create_ads(struct intel_guc *guc)
 	policies = (void *)ads + sizeof(struct guc_ads);
 	init_guc_policies(policies);
 
-	ads->scheduler_policies = vma->node.start + sizeof(struct guc_ads);
+	ads->scheduler_policies =
+		i915_ggtt_offset(vma) + sizeof(struct guc_ads);
 
 	/* MMIO reg state */
 	reg_state = (void *)policies + sizeof(struct guc_policies);
@@ -1061,7 +1062,7 @@ int intel_guc_suspend(struct drm_device *dev)
 	/* any value greater than GUC_POWER_D0 */
 	data[1] = GUC_POWER_D1;
 	/* first page is shared data with GuC */
-	data[2] = ctx->engine[RCS].state->node.start;
+	data[2] = i915_ggtt_offset(ctx->engine[RCS].state);
 
 	return host2guc_action(guc, data, ARRAY_SIZE(data));
 }
@@ -1086,7 +1087,7 @@ int intel_guc_resume(struct drm_device *dev)
 	data[0] = HOST2GUC_ACTION_EXIT_S_STATE;
 	data[1] = GUC_POWER_D0;
 	/* first page is shared data with GuC */
-	data[2] = ctx->engine[RCS].state->node.start;
+	data[2] = i915_ggtt_offset(ctx->engine[RCS].state);
 
 	return host2guc_action(guc, data, ARRAY_SIZE(data));
 }
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e582b4267036..31eaeedfad30 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3241,7 +3241,6 @@ u32 intel_fb_gtt_offset(struct drm_framebuffer *fb,
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct i915_ggtt_view view;
 	struct i915_vma *vma;
-	u64 offset;
 
 	intel_fill_fb_ggtt_view(&view, fb, rotation);
 
@@ -3250,11 +3249,7 @@ u32 intel_fb_gtt_offset(struct drm_framebuffer *fb,
 		 view.type))
 		return -1;
 
-	offset = vma->node.start;
-
-	WARN_ON(upper_32_bits(offset));
-
-	return lower_32_bits(offset);
+	return i915_ggtt_offset(vma);
 }
 
 static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
@@ -11804,7 +11799,8 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 			intel_ring_emit(ring, MI_STORE_REGISTER_MEM |
 					      MI_SRM_LRM_GLOBAL_GTT);
 		intel_ring_emit_reg(ring, DERRMR);
-		intel_ring_emit(ring, req->engine->scratch->node.start + 256);
+		intel_ring_emit(ring,
+				i915_ggtt_offset(req->engine->scratch) + 256);
 		if (IS_GEN8(dev)) {
 			intel_ring_emit(ring, 0);
 			intel_ring_emit(ring, MI_NOOP);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index f02d66bbec4b..5ec8a10fd18b 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -268,8 +268,8 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
 		goto err_unref;
 
 	engine->scratch = vma;
-	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
-			 engine->name, vma->node.start);
+	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n",
+			 engine->name, i915_ggtt_offset(vma));
 	return 0;
 
 err_unref:
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index 863e7a91ece0..cfe28d19ad68 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -249,7 +249,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->apertures->ranges[0].base = dev->mode_config.fb_base;
 	info->apertures->ranges[0].size = ggtt->mappable_end;
 
-	info->fix.smem_start = dev->mode_config.fb_base + vma->node.start;
+	info->fix.smem_start = dev->mode_config.fb_base + i915_ggtt_offset(vma);
 	info->fix.smem_len = vma->node.size;
 
 	vaddr = i915_vma_pin_iomap(vma);
@@ -276,8 +276,8 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08llx\n",
-		      fb->width, fb->height, vma->node.start);
+	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x\n",
+		      fb->width, fb->height, i915_ggtt_offset(vma));
 	ifbdev->vma = vma;
 
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c
index 7dd745dfeffb..324812d69b70 100644
--- a/drivers/gpu/drm/i915/intel_guc_loader.c
+++ b/drivers/gpu/drm/i915/intel_guc_loader.c
@@ -194,14 +194,14 @@ static void set_guc_init_params(struct drm_i915_private *dev_priv)
 	}
 
 	if (guc->ads_vma) {
-		u32 ads = (u32)guc->ads_vma->node.start >> PAGE_SHIFT;
+		u32 ads = i915_ggtt_offset(guc->ads_vma) >> PAGE_SHIFT;
 		params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
 		params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED;
 	}
 
 	/* If GuC submission is enabled, set up additional parameters here */
 	if (i915.enable_guc_submission) {
-		u32 pgs = dev_priv->guc.ctx_pool_vma->node.start;
+		u32 pgs = i915_ggtt_offset(dev_priv->guc.ctx_pool_vma);
 		u32 ctx_in_16 = GUC_MAX_GPU_CONTEXTS / 16;
 
 		pgs >>= PAGE_SHIFT;
@@ -271,7 +271,7 @@ static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv,
 	I915_WRITE(DMA_COPY_SIZE, guc_fw->header_size + guc_fw->ucode_size);
 
 	/* Set the source address for the new blob */
-	offset = vma->node.start + guc_fw->header_offset;
+	offset = i915_ggtt_offset(vma) + guc_fw->header_offset;
 	I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset));
 	I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF);
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4b9beaa30023..33682f66b37b 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -315,7 +315,7 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 
 	desc = ctx->desc_template;				/* bits  3-4  */
 	desc |= engine->ctx_desc_template;			/* bits  0-11 */
-	desc |= ce->state->node.start + LRC_PPHWSP_PN * PAGE_SIZE;
+	desc |= i915_ggtt_offset(ce->state) + LRC_PPHWSP_PN * PAGE_SIZE;
 								/* bits 12-31 */
 	desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT;		/* bits 32-52 */
 
@@ -792,7 +792,8 @@ static int intel_lr_context_pin(struct i915_gem_context *ctx,
 
 	intel_lr_context_descriptor_update(ctx, engine);
 
-	lrc_reg_state[CTX_RING_BUFFER_START+1] = ce->ring->vma->node.start;
+	lrc_reg_state[CTX_RING_BUFFER_START+1] =
+		i915_ggtt_offset(ce->ring->vma);
 	ce->lrc_reg_state = lrc_reg_state;
 	ce->state->obj->dirty = true;
 
@@ -914,7 +915,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
-	wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
+	wa_ctx_emit(batch, index, i915_ggtt_offset(engine->scratch) + 256);
 	wa_ctx_emit(batch, index, 0);
 
 	wa_ctx_emit(batch, index, MI_LOAD_REGISTER_IMM(1));
@@ -932,7 +933,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 	wa_ctx_emit(batch, index, (MI_LOAD_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
-	wa_ctx_emit(batch, index, engine->scratch->node.start + 256);
+	wa_ctx_emit(batch, index, i915_ggtt_offset(engine->scratch) + 256);
 	wa_ctx_emit(batch, index, 0);
 
 	return index;
@@ -993,7 +994,7 @@ static int gen8_init_indirectctx_bb(struct intel_engine_cs *engine,
 
 	/* WaClearSlmSpaceAtContextSwitch:bdw,chv */
 	/* Actual scratch location is at 128 bytes offset */
-	scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
+	scratch_addr = i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
 
 	wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
 	wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
@@ -1073,7 +1074,7 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine,
 	/* Actual scratch location is at 128 bytes offset */
 	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
 		u32 scratch_addr =
-			engine->scratch->node.start + 2 * CACHELINE_BYTES;
+			i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
 
 		wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
 		wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
@@ -1482,7 +1483,8 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
 {
 	struct intel_ring *ring = request->ring;
 	struct intel_engine_cs *engine = request->engine;
-	u32 scratch_addr = engine->scratch->node.start + 2 * CACHELINE_BYTES;
+	u32 scratch_addr =
+		i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES;
 	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 flags = 0;
 	int ret;
@@ -1752,7 +1754,7 @@ lrc_setup_hws(struct intel_engine_cs *engine, struct i915_vma *vma)
 		return PTR_ERR(hws);
 
 	engine->status_page.page_addr = hws + hws_offset;
-	engine->status_page.ggtt_offset = vma->node.start + hws_offset;
+	engine->status_page.ggtt_offset = i915_ggtt_offset(vma) + hws_offset;
 	engine->status_page.vma = vma;
 
 	return 0;
@@ -2020,7 +2022,7 @@ populate_lr_context(struct i915_gem_context *ctx,
 			       RING_INDIRECT_CTX_OFFSET(engine->mmio_base), 0);
 		if (engine->wa_ctx.vma) {
 			struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
-			u32 ggtt_offset = wa_ctx->vma->node.start;
+			u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
 
 			reg_state[CTX_RCS_INDIRECT_CTX+1] =
 				(ggtt_offset + wa_ctx->indirect_ctx.offset * sizeof(uint32_t)) |
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 402e05f2f1de..72f8990a13d2 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -801,7 +801,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	swidth = params->src_w;
 	swidthsw = calc_swidthsw(dev_priv, params->offset_Y, tmp_width);
 	sheight = params->src_h;
-	iowrite32(vma->node.start + params->offset_Y, &regs->OBUF_0Y);
+	iowrite32(i915_ggtt_offset(vma) + params->offset_Y, &regs->OBUF_0Y);
 	ostride = params->stride_Y;
 
 	if (params->format & I915_OVERLAY_YUV_PLANAR) {
@@ -815,8 +815,10 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 				      params->src_w/uv_hscale);
 		swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
 		sheight |= (params->src_h/uv_vscale) << 16;
-		iowrite32(vma->node.start + params->offset_U, &regs->OBUF_0U);
-		iowrite32(vma->node.start + params->offset_V, &regs->OBUF_0V);
+		iowrite32(i915_ggtt_offset(vma) + params->offset_U,
+			  &regs->OBUF_0U);
+		iowrite32(i915_ggtt_offset(vma) + params->offset_V,
+			  &regs->OBUF_0V);
 		ostride |= params->stride_UV << 16;
 	}
 
@@ -1412,7 +1414,7 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv)
 			ret = PTR_ERR(vma);
 			goto out_free_bo;
 		}
-		overlay->flip_addr = vma->node.start;
+		overlay->flip_addr = i915_ggtt_offset(vma);
 
 		ret = i915_gem_object_set_to_gtt_domain(reg_bo, true);
 		if (ret) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d618d05249f3..26bd2a1f8c86 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -176,7 +176,7 @@ intel_emit_post_sync_nonzero_flush(struct drm_i915_gem_request *req)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
+		i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
 	int ret;
 
 	ret = intel_ring_begin(req, 6);
@@ -212,7 +212,7 @@ gen6_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
+		i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -286,7 +286,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
 	struct intel_ring *ring = req->ring;
 	u32 scratch_addr =
-		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
+		i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -371,7 +371,7 @@ static int
 gen8_render_ring_flush(struct drm_i915_gem_request *req, u32 mode)
 {
 	u32 scratch_addr =
-		req->engine->scratch->node.start + 2 * CACHELINE_BYTES;
+		i915_ggtt_offset(req->engine->scratch) + 2 * CACHELINE_BYTES;
 	u32 flags = 0;
 	int ret;
 
@@ -571,7 +571,7 @@ static int init_ring_common(struct intel_engine_cs *engine)
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
 	 * register values. */
-	I915_WRITE_START(engine, ring->vma->node.start);
+	I915_WRITE_START(engine, i915_ggtt_offset(ring->vma));
 
 	/* WaClearRingBufHeadRegAtInit:ctg,elk */
 	if (I915_READ_HEAD(engine))
@@ -586,16 +586,16 @@ static int init_ring_common(struct intel_engine_cs *engine)
 
 	/* If the head is still not zero, the ring is dead */
 	if (wait_for((I915_READ_CTL(engine) & RING_VALID) != 0 &&
-		     I915_READ_START(engine) == ring->vma->node.start &&
+		     I915_READ_START(engine) == i915_ggtt_offset(ring->vma) &&
 		     (I915_READ_HEAD(engine) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
-			  "ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08llx]\n",
+			  "ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08x]\n",
 			  engine->name,
 			  I915_READ_CTL(engine),
 			  I915_READ_CTL(engine) & RING_VALID,
 			  I915_READ_HEAD(engine), I915_READ_TAIL(engine),
 			  I915_READ_START(engine),
-			  ring->vma->node.start);
+			  i915_ggtt_offset(ring->vma));
 		ret = -EIO;
 		goto out;
 	}
@@ -1716,7 +1716,7 @@ i830_emit_bb_start(struct drm_i915_gem_request *req,
 		   unsigned int dispatch_flags)
 {
 	struct intel_ring *ring = req->ring;
-	u32 cs_offset = req->engine->scratch->node.start;
+	u32 cs_offset = i915_ggtt_offset(req->engine->scratch);
 	int ret;
 
 	ret = intel_ring_begin(req, 6);
@@ -1857,11 +1857,11 @@ static int init_status_page(struct intel_engine_cs *engine)
 		goto err;
 
 	engine->status_page.vma = vma;
-	engine->status_page.ggtt_offset = vma->node.start;
+	engine->status_page.ggtt_offset = i915_ggtt_offset(vma);
 	engine->status_page.page_addr = i915_gem_object_pin_map(obj);
 
-	DRM_DEBUG_DRIVER("%s hws offset: 0x%08llx\n",
-			 engine->name, vma->node.start);
+	DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
+			 engine->name, i915_ggtt_offset(vma));
 	return 0;
 
 err:
@@ -2541,13 +2541,13 @@ static void intel_ring_init_semaphores(struct drm_i915_private *dev_priv,
 	}
 
 	if (INTEL_GEN(dev_priv) >= 8) {
-		u64 offset = dev_priv->semaphore->node.start;
+		u32 offset = i915_ggtt_offset(dev_priv->semaphore);
 
 		engine->semaphore.sync_to = gen8_ring_sync_to;
 		engine->semaphore.signal = gen8_xcs_signal;
 
 		for (i = 0; i < I915_NUM_ENGINES; i++) {
-			u64 ring_offset;
+			u32 ring_offset;
 
 			if (i != engine->id)
 				ring_offset = offset + GEN8_SEMAPHORE_OFFSET(engine->id, i);
-- 
2.8.1

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

[PATCH 31/37] drm/i915: Print the batchbuffer offset next to BBADDR in error state

[Chris Wilson]

It is useful when looking at captured error states to check the recorded
BBADDR register (the address of the last batchbuffer instruction loaded)
against the expected offset of the batch buffer, and so do a quick check
that (a) the capture is true or (b) HEAD hasn't wandered off into the
badlands.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h       |  1 +
 drivers/gpu/drm/i915/i915_gpu_error.c | 15 +++++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9414f3d4c2b3..c11704e6c382 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -777,6 +777,7 @@ struct drm_i915_error_state {
 		struct drm_i915_error_object {
 			int page_count;
 			u64 gtt_offset;
+			u64 gtt_size;
 			u32 *pages[0];
 		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 5b4b0f4dea4f..4f936a574200 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -243,8 +243,16 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 	err_printf(m, "  IPEIR: 0x%08x\n", ee->ipeir);
 	err_printf(m, "  IPEHR: 0x%08x\n", ee->ipehr);
 	err_printf(m, "  INSTDONE: 0x%08x\n", ee->instdone);
+	if (ee->batchbuffer) {
+		u64 start = ee->batchbuffer->gtt_offset;
+		u64 end = start + ee->batchbuffer->gtt_size;
+
+		err_printf(m, "  batch: [0x%08x_%08x, 0x%08x_%08x]\n",
+			   upper_32_bits(start), lower_32_bits(start),
+			   upper_32_bits(end), lower_32_bits(end));
+	}
 	if (INTEL_GEN(m->i915) >= 4) {
-		err_printf(m, "  BBADDR: 0x%08x %08x\n",
+		err_printf(m, "  BBADDR: 0x%08x_%08x\n",
 			   (u32)(ee->bbaddr>>32), (u32)ee->bbaddr);
 		err_printf(m, "  BB_STATE: 0x%08x\n", ee->bbstate);
 		err_printf(m, "  INSTPS: 0x%08x\n", ee->instps);
@@ -677,7 +685,10 @@ i915_error_object_create(struct drm_i915_private *dev_priv,
 	if (!dst)
 		return NULL;
 
-	reloc_offset = dst->gtt_offset = vma->node.start;
+	dst->gtt_offset = vma->node.start;
+	dst->gtt_size = vma->node.size;
+
+	reloc_offset = dst->gtt_offset;
 	use_ggtt = (src->cache_level == I915_CACHE_NONE &&
 		   (vma->flags & I915_VMA_GLOBAL_BIND) &&
 		   reloc_offset + num_pages * PAGE_SIZE <= ggtt->mappable_end);
-- 
2.8.1

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

[PATCH 32/37] drm/i915: Move debug only per-request pid tracking from request to ctx

[Chris Wilson]

Since contexts are not currently shared between userspace processes, we
have an exact correspondence between context creator and guilty batch
submitter. Therefore we can save some per-batch work by inspecting the
context->pid upon error instead. Note that we take the context's
creator's pid rather than the file's pid in order to better track fd
passed over sockets.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c     | 25 ++++++++++++++++---------
 drivers/gpu/drm/i915/i915_drv.h         |  2 ++
 drivers/gpu/drm/i915/i915_gem_context.c |  4 ++++
 drivers/gpu/drm/i915/i915_gem_request.c |  6 ------
 drivers/gpu/drm/i915/i915_gem_request.h |  3 ---
 drivers/gpu/drm/i915/i915_gpu_error.c   | 13 ++++++++++---
 6 files changed, 32 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 82652ad28cd4..61e12a0f08d4 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -460,6 +460,8 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 	print_context_stats(m, dev_priv);
 	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
 		struct file_stats stats;
+		struct drm_i915_file_private *file_priv = file->driver_priv;
+		struct drm_i915_gem_request *request;
 		struct task_struct *task;
 
 		memset(&stats, 0, sizeof(stats));
@@ -473,10 +475,17 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		 * still alive (e.g. get_pid(current) => fork() => exit()).
 		 * Therefore, we need to protect this ->comm access using RCU.
 		 */
+		mutex_lock(&dev->struct_mutex);
+		request = list_first_entry_or_null(&file_priv->mm.request_list,
+						   struct drm_i915_gem_request,
+						   client_list);
 		rcu_read_lock();
-		task = pid_task(file->pid, PIDTYPE_PID);
+		task = pid_task(request && request->ctx->pid ?
+				request->ctx->pid : file->pid,
+				PIDTYPE_PID);
 		print_file_stats(m, task ? task->comm : "<unknown>", stats);
 		rcu_read_unlock();
+		mutex_unlock(&dev->struct_mutex);
 	}
 	mutex_unlock(&dev->filelist_mutex);
 
@@ -658,12 +667,11 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 
 		seq_printf(m, "%s requests: %d\n", engine->name, count);
 		list_for_each_entry(req, &engine->request_list, link) {
+			struct pid *pid = req->ctx->pid;
 			struct task_struct *task;
 
 			rcu_read_lock();
-			task = NULL;
-			if (req->pid)
-				task = pid_task(req->pid, PIDTYPE_PID);
+			task = pid ? pid_task(pid, PIDTYPE_PID) : NULL;
 			seq_printf(m, "    %x @ %d: %s [%d]\n",
 				   req->fence.seqno,
 				   (int) (jiffies - req->emitted_jiffies),
@@ -1952,18 +1960,17 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
 		seq_printf(m, "HW context %u ", ctx->hw_id);
-		if (IS_ERR(ctx->file_priv)) {
-			seq_puts(m, "(deleted) ");
-		} else if (ctx->file_priv) {
-			struct pid *pid = ctx->file_priv->file->pid;
+		if (ctx->pid) {
 			struct task_struct *task;
 
-			task = get_pid_task(pid, PIDTYPE_PID);
+			task = get_pid_task(ctx->pid, PIDTYPE_PID);
 			if (task) {
 				seq_printf(m, "(%s [%d]) ",
 					   task->comm, task->pid);
 				put_task_struct(task);
 			}
+		} else if (IS_ERR(ctx->file_priv)) {
+			seq_puts(m, "(deleted) ");
 		} else {
 			seq_puts(m, "(kernel) ");
 		}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c11704e6c382..84a0c4c71af6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -785,6 +785,7 @@ struct drm_i915_error_state {
 
 		struct drm_i915_error_request {
 			long jiffies;
+			pid_t pid;
 			u32 seqno;
 			u32 head;
 			u32 tail;
@@ -883,6 +884,7 @@ struct i915_gem_context {
 	struct drm_i915_private *i915;
 	struct drm_i915_file_private *file_priv;
 	struct i915_hw_ppgtt *ppgtt;
+	struct pid *pid;
 
 	struct i915_ctx_hang_stats hang_stats;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 98d2956f91f4..35950ee46a1d 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -158,6 +158,7 @@ void i915_gem_context_free(struct kref *ctx_ref)
 		i915_vma_put(ce->state);
 	}
 
+	put_pid(ctx->pid);
 	list_del(&ctx->link);
 
 	ida_simple_remove(&ctx->i915->context_hw_ida, ctx->hw_id);
@@ -311,6 +312,9 @@ __create_hw_context(struct drm_device *dev,
 		ret = DEFAULT_CONTEXT_HANDLE;
 
 	ctx->file_priv = file_priv;
+	if (file_priv)
+		ctx->pid = get_task_pid(current, PIDTYPE_PID);
+
 	ctx->user_handle = ret;
 	/* NB: Mark all slices as needing a remap so that when the context first
 	 * loads it will restore whatever remap state already exists. If there
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index a0756b553a19..1a215320cefb 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -137,8 +137,6 @@ int i915_gem_request_add_to_client(struct drm_i915_gem_request *req,
 	list_add_tail(&req->client_list, &file_priv->mm.request_list);
 	spin_unlock(&file_priv->mm.lock);
 
-	req->pid = get_pid(task_pid(current));
-
 	return 0;
 }
 
@@ -154,9 +152,6 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
 	list_del(&request->client_list);
 	request->file_priv = NULL;
 	spin_unlock(&file_priv->mm.lock);
-
-	put_pid(request->pid);
-	request->pid = NULL;
 }
 
 void i915_gem_retire_noop(struct i915_gem_active *active,
@@ -407,7 +402,6 @@ i915_gem_request_alloc(struct intel_engine_cs *engine,
 	req->previous_context = NULL;
 	req->file_priv = NULL;
 	req->batch = NULL;
-	req->pid = NULL;
 	req->elsp_submitted = 0;
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index a66243a6f791..6c72bd8d9423 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -134,9 +134,6 @@ struct drm_i915_gem_request {
 	/** file_priv list entry for this request */
 	struct list_head client_list;
 
-	/** process identifier submitting this request */
-	struct pid *pid;
-
 	/**
 	 * The ELSP only accepts two elements at a time, so we queue
 	 * context/tail pairs on a given queue (ring->execlist_queue) until the
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 4f936a574200..9517d83cc3ad 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -479,7 +479,8 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				   dev_priv->engine[i].name,
 				   ee->num_requests);
 			for (j = 0; j < ee->num_requests; j++) {
-				err_printf(m, "  seqno 0x%08x, emitted %ld, head 0x%08x tail 0x%08x\n",
+				err_printf(m, "  pid %d, seqno 0x%08x, emitted %ld, head 0x%08x tail 0x%08x\n",
+					   ee->requests[j].pid,
 					   ee->requests[j].seqno,
 					   ee->requests[j].jiffies,
 					   ee->requests[j].head,
@@ -1081,6 +1082,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 		request = i915_gem_find_active_request(engine);
 		if (request) {
 			struct intel_ring *ring;
+			struct pid *pid;
 
 			ee->vm = request->ctx->ppgtt ?
 				&request->ctx->ppgtt->base : &ggtt->base;
@@ -1102,11 +1104,12 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 				i915_error_object_create(dev_priv,
 							 request->ctx->engine[i].state);
 
-			if (request->pid) {
+			pid = request->ctx->pid;
+			if (pid) {
 				struct task_struct *task;
 
 				rcu_read_lock();
-				task = pid_task(request->pid, PIDTYPE_PID);
+				task = pid_task(pid, PIDTYPE_PID);
 				if (task) {
 					strcpy(ee->comm, task->comm);
 					ee->pid = task->pid;
@@ -1171,6 +1174,10 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			erq->jiffies = request->emitted_jiffies;
 			erq->head = request->head;
 			erq->tail = request->tail;
+
+			rcu_read_lock();
+			erq->pid = request->ctx->pid ? pid_nr(request->ctx->pid) : 0;
+			rcu_read_unlock();
 		}
 	}
 }
-- 
2.8.1

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

[PATCH 33/37] drm/i915: Only record active and pending requests upon a GPU hang

[Chris Wilson]

There is no other state pertaining to the completed requests in the
hang, other than gleamed through the ringbuffer, so including the
expired requests in the list of outstanding requests simply adds noise.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 110 +++++++++++++++++++---------------
 1 file changed, 62 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9517d83cc3ad..ff8430f27d9a 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1054,12 +1054,69 @@ static void error_record_engine_registers(struct drm_i915_error_state *error,
 	}
 }
 
+static void engine_record_requests(struct intel_engine_cs *engine,
+				   struct drm_i915_gem_request *first,
+				   struct drm_i915_error_engine *ee)
+{
+	struct drm_i915_gem_request *request;
+	int count;
+
+	count = 0;
+	request = first;
+	list_for_each_entry_from(request, &engine->request_list, link)
+		count += !!request->batch;
+
+	ee->requests = NULL;
+	kcalloc(count, sizeof(*ee->requests),
+		GFP_ATOMIC);
+	if (!ee->requests)
+		return;
+	ee->num_requests = count;
+
+	count = 0;
+	request = first;
+	list_for_each_entry_from(request, &engine->request_list, link) {
+		struct drm_i915_error_request *erq;
+
+		if (!request->batch)
+			continue;
+
+		if (count >= ee->num_requests) {
+			/*
+			 * If the ring request list was changed in
+			 * between the point where the error request
+			 * list was created and dimensioned and this
+			 * point then just exit early to avoid crashes.
+			 *
+			 * We don't need to communicate that the
+			 * request list changed state during error
+			 * state capture and that the error state is
+			 * slightly incorrect as a consequence since we
+			 * are typically only interested in the request
+			 * list state at the point of error state
+			 * capture, not in any changes happening during
+			 * the capture.
+			 */
+			break;
+		}
+
+		erq = &ee->requests[count++];
+		erq->seqno = request->fence.seqno;
+		erq->jiffies = request->emitted_jiffies;
+		erq->head = request->head;
+		erq->tail = request->tail;
+
+		rcu_read_lock();
+		erq->pid = request->ctx->pid ? pid_nr(request->ctx->pid) : 0;
+		rcu_read_unlock();
+	}
+}
+
 static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 				  struct drm_i915_error_state *error)
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct drm_i915_gem_request *request;
-	int i, count;
+	int i;
 
 	error->semaphore =
 		i915_error_object_create(dev_priv, dev_priv->semaphore);
@@ -1067,6 +1124,7 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
 		struct intel_engine_cs *engine = &dev_priv->engine[i];
 		struct drm_i915_error_engine *ee = &error->engine[i];
+		struct drm_i915_gem_request *request;
 
 		ee->pid = -1;
 		ee->engine_id = -1;
@@ -1125,6 +1183,8 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 			ee->cpu_ring_tail = ring->tail;
 			ee->ringbuffer =
 				i915_error_object_create(dev_priv, ring->vma);
+
+			engine_record_requests(engine, request, ee);
 		}
 
 		ee->hws_page =
@@ -1133,52 +1193,6 @@ static void i915_gem_record_rings(struct drm_i915_private *dev_priv,
 
 		ee->wa_ctx =
 			i915_error_object_create(dev_priv, engine->wa_ctx.vma);
-
-		count = 0;
-		list_for_each_entry(request, &engine->request_list, link)
-			count++;
-
-		ee->num_requests = count;
-		ee->requests =
-			kcalloc(count, sizeof(*ee->requests), GFP_ATOMIC);
-		if (!ee->requests) {
-			ee->num_requests = 0;
-			continue;
-		}
-
-		count = 0;
-		list_for_each_entry(request, &engine->request_list, link) {
-			struct drm_i915_error_request *erq;
-
-			if (count >= ee->num_requests) {
-				/*
-				 * If the ring request list was changed in
-				 * between the point where the error request
-				 * list was created and dimensioned and this
-				 * point then just exit early to avoid crashes.
-				 *
-				 * We don't need to communicate that the
-				 * request list changed state during error
-				 * state capture and that the error state is
-				 * slightly incorrect as a consequence since we
-				 * are typically only interested in the request
-				 * list state at the point of error state
-				 * capture, not in any changes happening during
-				 * the capture.
-				 */
-				break;
-			}
-
-			erq = &ee->requests[count++];
-			erq->seqno = request->fence.seqno;
-			erq->jiffies = request->emitted_jiffies;
-			erq->head = request->head;
-			erq->tail = request->tail;
-
-			rcu_read_lock();
-			erq->pid = request->ctx->pid ? pid_nr(request->ctx->pid) : 0;
-			rcu_read_unlock();
-		}
 	}
 }
 
-- 
2.8.1

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

[PATCH 34/37] drm/i915: Record the RING_MODE register for post-mortem debugging

[Chris Wilson]

Just another useful register to inspect following a GPU hang.

v2: Remove partial decoding of RING_MODE to userspace, be consistent and
use GEN > 2 guards around RING_MODE everywhere.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h         | 1 +
 drivers/gpu/drm/i915/i915_gpu_error.c   | 3 +++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 7 ++++---
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 84a0c4c71af6..25d3cf204a2b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -759,6 +759,7 @@ struct drm_i915_error_state {
 		u32 tail;
 		u32 head;
 		u32 ctl;
+		u32 mode;
 		u32 hws;
 		u32 ipeir;
 		u32 ipehr;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index ff8430f27d9a..d3a364b61225 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -237,6 +237,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 	err_printf(m, "  HEAD:  0x%08x\n", ee->head);
 	err_printf(m, "  TAIL:  0x%08x\n", ee->tail);
 	err_printf(m, "  CTL:   0x%08x\n", ee->ctl);
+	err_printf(m, "  MODE:  0x%08x\n", ee->mode);
 	err_printf(m, "  HWS:   0x%08x\n", ee->hws);
 	err_printf(m, "  ACTHD: 0x%08x %08x\n",
 		   (u32)(ee->acthd>>32), (u32)ee->acthd);
@@ -999,6 +1000,8 @@ static void error_record_engine_registers(struct drm_i915_error_state *error,
 	ee->head = I915_READ_HEAD(engine);
 	ee->tail = I915_READ_TAIL(engine);
 	ee->ctl = I915_READ_CTL(engine);
+	if (INTEL_GEN(dev_priv) > 2)
+		ee->mode = I915_READ_MODE(engine);
 
 	if (I915_NEED_GFX_HWS(dev_priv)) {
 		i915_reg_t mmio;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 26bd2a1f8c86..5a49a4e760be 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -498,7 +498,7 @@ static bool stop_ring(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 
-	if (!IS_GEN2(dev_priv)) {
+	if (INTEL_GEN(dev_priv) > 2) {
 		I915_WRITE_MODE(engine, _MASKED_BIT_ENABLE(STOP_RING));
 		if (intel_wait_for_register(dev_priv,
 					    RING_MI_MODE(engine->mmio_base),
@@ -520,7 +520,7 @@ static bool stop_ring(struct intel_engine_cs *engine)
 	I915_WRITE_HEAD(engine, 0);
 	I915_WRITE_TAIL(engine, 0);
 
-	if (!IS_GEN2(dev_priv)) {
+	if (INTEL_GEN(dev_priv) > 2) {
 		(void)I915_READ_CTL(engine);
 		I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING));
 	}
@@ -2141,7 +2141,8 @@ void intel_engine_cleanup(struct intel_engine_cs *engine)
 	dev_priv = engine->i915;
 
 	if (engine->buffer) {
-		WARN_ON(!IS_GEN2(dev_priv) && (I915_READ_MODE(engine) & MODE_IDLE) == 0);
+		WARN_ON(INTEL_GEN(dev_priv) > 2 &&
+			(I915_READ_MODE(engine) & MODE_IDLE) == 0);
 
 		intel_ring_unpin(engine->buffer);
 		intel_ring_free(engine->buffer);
-- 
2.8.1

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

[PATCH 35/37] drm/i915: Always use the GTT for error capture

[Chris Wilson]

Since the GTT provides universal access to any GPU page, we can use it
to reduce our plethora of read methods to just one. It also has the
important characteristic of being exactly what the GPU sees - if there
are incoherency problems, seeing the batch as executed (rather than as
trapped inside the cpu cache) is important.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c   |  43 ++++++++----
 drivers/gpu/drm/i915/i915_gem_gtt.h   |   2 +
 drivers/gpu/drm/i915/i915_gpu_error.c | 122 ++++++++++++----------------------
 3 files changed, 75 insertions(+), 92 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 47159ba649b8..e173ccdebdc6 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2729,6 +2729,7 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 	 */
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	unsigned long hole_start, hole_end;
+	struct i915_hw_ppgtt *ppgtt;
 	struct drm_mm_node *entry;
 	int ret;
 
@@ -2736,6 +2737,15 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
+	/* Reserve a mappable slot for our lockless error capture */
+	ret = drm_mm_insert_node_in_range_generic(&ggtt->base.mm,
+						  &ggtt->gpu_error,
+						  4096, 0, -1,
+						  0, ggtt->mappable_end,
+						  0, 0);
+	if (ret)
+		return ret;
+
 	/* Clear any non-preallocated blocks */
 	drm_mm_for_each_hole(entry, &ggtt->base.mm, hole_start, hole_end) {
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
@@ -2750,25 +2760,21 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 			       true);
 
 	if (USES_PPGTT(dev_priv) && !USES_FULL_PPGTT(dev_priv)) {
-		struct i915_hw_ppgtt *ppgtt;
-
 		ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-		if (!ppgtt)
-			return -ENOMEM;
+		if (!ppgtt) {
+			ret = -ENOMEM;
+			goto err;
+		}
 
 		ret = __hw_ppgtt_init(ppgtt, dev_priv);
-		if (ret) {
-			kfree(ppgtt);
-			return ret;
-		}
+		if (ret)
+			goto err_ppgtt;
 
-		if (ppgtt->base.allocate_va_range)
+		if (ppgtt->base.allocate_va_range) {
 			ret = ppgtt->base.allocate_va_range(&ppgtt->base, 0,
 							    ppgtt->base.total);
-		if (ret) {
-			ppgtt->base.cleanup(&ppgtt->base);
-			kfree(ppgtt);
-			return ret;
+			if (ret)
+				goto err_ppgtt_cleanup;
 		}
 
 		ppgtt->base.clear_range(&ppgtt->base,
@@ -2782,6 +2788,14 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 	}
 
 	return 0;
+
+err_ppgtt_cleanup:
+	ppgtt->base.cleanup(&ppgtt->base);
+err_ppgtt:
+	kfree(ppgtt);
+err:
+	drm_mm_remove_node(&ggtt->gpu_error);
+	return ret;
 }
 
 /**
@@ -2801,6 +2815,9 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 
 	i915_gem_cleanup_stolen(&dev_priv->drm);
 
+	if (drm_mm_node_allocated(&ggtt->gpu_error))
+		drm_mm_remove_node(&ggtt->gpu_error);
+
 	if (drm_mm_initialized(&ggtt->base.mm)) {
 		intel_vgt_deballoon(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index d6e4b6529196..79a08a050487 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -439,6 +439,8 @@ struct i915_ggtt {
 	bool do_idle_maps;
 
 	int mtrr;
+
+	struct drm_mm_node gpu_error;
 };
 
 struct i915_hw_ppgtt {
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index d3a364b61225..f212ac3d7a5b 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -626,7 +626,7 @@ static void i915_error_object_free(struct drm_i915_error_object *obj)
 		return;
 
 	for (page = 0; page < obj->page_count; page++)
-		kfree(obj->pages[page]);
+		free_page((unsigned long)obj->pages[page]);
 
 	kfree(obj);
 }
@@ -662,98 +662,69 @@ static void i915_error_state_free(struct kref *error_ref)
 	kfree(error);
 }
 
+static int compress_page(void *src, struct drm_i915_error_object *dst)
+{
+	unsigned long page;
+
+	page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+	if (!page)
+		return -ENOMEM;
+
+	dst->pages[dst->page_count++] = (void *)page;
+
+	memcpy((void *)page, src, PAGE_SIZE);
+	return 0;
+}
+
 static struct drm_i915_error_object *
-i915_error_object_create(struct drm_i915_private *dev_priv,
+i915_error_object_create(struct drm_i915_private *i915,
 			 struct i915_vma *vma)
 {
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct drm_i915_gem_object *src;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	const u64 slot = ggtt->gpu_error.start;
 	struct drm_i915_error_object *dst;
-	int num_pages;
-	bool use_ggtt;
-	int i = 0;
-	u64 reloc_offset;
+	unsigned long num_pages;
+	struct sgt_iter iter;
+	dma_addr_t dma;
 
 	if (!vma)
 		return NULL;
 
-	src = vma->obj;
-	if (!src->pages)
-		return NULL;
-
-	num_pages = src->base.size >> PAGE_SHIFT;
-
-	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *), GFP_ATOMIC);
+	num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
+	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *),
+		      GFP_ATOMIC | __GFP_NOWARN);
 	if (!dst)
 		return NULL;
 
 	dst->gtt_offset = vma->node.start;
-	dst->gtt_size = vma->node.size;
-
-	reloc_offset = dst->gtt_offset;
-	use_ggtt = (src->cache_level == I915_CACHE_NONE &&
-		   (vma->flags & I915_VMA_GLOBAL_BIND) &&
-		   reloc_offset + num_pages * PAGE_SIZE <= ggtt->mappable_end);
+	dst->page_count = 0;
 
-	/* Cannot access stolen address directly, try to use the aperture */
-	if (src->stolen) {
-		use_ggtt = true;
-
-		if (!(vma->flags & I915_VMA_GLOBAL_BIND))
-			goto unwind;
-
-		reloc_offset = vma->node.start;
-		if (reloc_offset + num_pages * PAGE_SIZE > ggtt->mappable_end)
-			goto unwind;
-	}
+	for_each_sgt_dma(dma, iter, vma->pages) {
+		int ret;
+		void *s;
 
-	/* Cannot access snooped pages through the aperture */
-	if (use_ggtt && src->cache_level != I915_CACHE_NONE &&
-	    !HAS_LLC(dev_priv))
-		goto unwind;
+		ggtt->base.insert_page(&ggtt->base, dma, slot,
+				       I915_CACHE_NONE, 0);
 
-	dst->page_count = num_pages;
-	while (num_pages--) {
-		void *d;
+		s = (void *__force)
+			io_mapping_map_atomic_wc(ggtt->mappable, slot);
+		ret = compress_page(s, dst);
+		io_mapping_unmap_atomic(s);
 
-		d = kmalloc(PAGE_SIZE, GFP_ATOMIC);
-		if (d == NULL)
+		if (ret)
 			goto unwind;
-
-		if (use_ggtt) {
-			void __iomem *s;
-
-			/* Simply ignore tiling or any overlapping fence.
-			 * It's part of the error state, and this hopefully
-			 * captures what the GPU read.
-			 */
-
-			s = io_mapping_map_atomic_wc(ggtt->mappable,
-						     reloc_offset);
-			memcpy_fromio(d, s, PAGE_SIZE);
-			io_mapping_unmap_atomic(s);
-		} else {
-			struct page *page;
-			void *s;
-
-			page = i915_gem_object_get_page(src, i);
-
-			s = kmap_atomic(page);
-			memcpy(d, s, PAGE_SIZE);
-			kunmap_atomic(s);
-		}
-
-		dst->pages[i++] = d;
-		reloc_offset += PAGE_SIZE;
 	}
-
-	return dst;
+	goto out;
 
 unwind:
-	while (i--)
-		kfree(dst->pages[i]);
+	while (dst->page_count--)
+		free_page((unsigned long)dst->pages[dst->page_count]);
 	kfree(dst);
-	return NULL;
+	dst = NULL;
+
+out:
+	ggtt->base.clear_range(&ggtt->base, slot, PAGE_SIZE, true);
+	return dst;
 }
 
 /* The error capture is special as tries to run underneath the normal
@@ -1401,9 +1372,6 @@ static int capture(void *data)
 {
 	struct drm_i915_error_state *error = data;
 
-	/* Ensure that what we readback from memory matches what the GPU sees */
-	wbinvd();
-
 	i915_capture_gen_state(error->i915, error);
 	i915_capture_reg_state(error->i915, error);
 	i915_gem_record_fences(error->i915, error);
@@ -1416,9 +1384,6 @@ static int capture(void *data)
 	error->overlay = intel_overlay_capture_error_state(error->i915);
 	error->display = intel_display_capture_error_state(error->i915);
 
-	/* And make sure we don't leave trash in the CPU cache */
-	wbinvd();
-
 	return 0;
 }
 
@@ -1492,7 +1457,6 @@ void i915_error_state_get(struct drm_device *dev,
 	if (error_priv->error)
 		kref_get(&error_priv->error->ref);
 	spin_unlock_irq(&dev_priv->gpu_error.lock);
-
 }
 
 void i915_error_state_put(struct i915_error_state_file_priv *error_priv)
-- 
2.8.1

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

[PATCH 36/37] drm/i915: Consolidate error object printing

[Chris Wilson]

Leave all the pretty printing to userspace and simplify the error
capture to only have a single common object printer. It makes the kernel
code more compact, and the refactoring allows us to apply more complex
transformations like compressing the output.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 100 +++++++++-------------------------
 1 file changed, 25 insertions(+), 75 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index f212ac3d7a5b..e87a0e5351d2 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -309,10 +309,22 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 }
 
 static void print_error_obj(struct drm_i915_error_state_buf *m,
+			    struct intel_engine_cs *engine,
+			    const char *name,
 			    struct drm_i915_error_object *obj)
 {
 	int page, offset, elt;
 
+	if (!obj)
+		return;
+
+	if (name) {
+		err_printf(m, "%s --- %s = 0x%08x %08x\n",
+			   engine ? engine->name : "global", name,
+			   upper_32_bits(obj->gtt_offset),
+			   lower_32_bits(obj->gtt_offset));
+	}
+
 	for (page = offset = 0; page < obj->page_count; page++) {
 		for (elt = 0; elt < PAGE_SIZE/4; elt++) {
 			err_printf(m, "%08x :  %08x\n", offset,
@@ -339,8 +351,8 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_error_state *error = error_priv->error;
 	struct drm_i915_error_object *obj;
-	int i, j, offset, elt;
 	int max_hangcheck_score;
+	int i, j;
 
 	if (!error) {
 		err_printf(m, "no error state collected\n");
@@ -464,15 +476,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
 				   upper_32_bits(obj->gtt_offset),
 				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
-		}
-
-		obj = ee->wa_batchbuffer;
-		if (obj) {
-			err_printf(m, "%s (w/a) --- gtt_offset = 0x%08x\n",
-				   dev_priv->engine[i].name,
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
+			print_error_obj(m, &dev_priv->engine[i], NULL, obj);
 		}
 
 		if (ee->num_requests) {
@@ -501,77 +505,23 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			}
 		}
 
-		if ((obj = ee->ringbuffer)) {
-			err_printf(m, "%s --- ringbuffer = 0x%08x\n",
-				   dev_priv->engine[i].name,
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"ringbuffer", ee->ringbuffer);
 
-		if ((obj = ee->hws_page)) {
-			u64 hws_offset = obj->gtt_offset;
-			u32 *hws_page = &obj->pages[0][0];
+		print_error_obj(m, &dev_priv->engine[i],
+				"HW Status", ee->hws_page);
 
-			if (i915.enable_execlists) {
-				hws_offset += LRC_PPHWSP_PN * PAGE_SIZE;
-				hws_page = &obj->pages[LRC_PPHWSP_PN][0];
-			}
-			err_printf(m, "%s --- HW Status = 0x%08llx\n",
-				   dev_priv->engine[i].name, hws_offset);
-			offset = 0;
-			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
-				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-					   offset,
-					   hws_page[elt],
-					   hws_page[elt+1],
-					   hws_page[elt+2],
-					   hws_page[elt+3]);
-				offset += 16;
-			}
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"HW context", ee->ctx);
 
-		obj = ee->wa_ctx;
-		if (obj) {
-			u64 wa_ctx_offset = obj->gtt_offset;
-			u32 *wa_ctx_page = &obj->pages[0][0];
-			struct intel_engine_cs *engine = &dev_priv->engine[RCS];
-			u32 wa_ctx_size = (engine->wa_ctx.indirect_ctx.size +
-					   engine->wa_ctx.per_ctx.size);
-
-			err_printf(m, "%s --- WA ctx batch buffer = 0x%08llx\n",
-				   dev_priv->engine[i].name, wa_ctx_offset);
-			offset = 0;
-			for (elt = 0; elt < wa_ctx_size; elt += 4) {
-				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-					   offset,
-					   wa_ctx_page[elt + 0],
-					   wa_ctx_page[elt + 1],
-					   wa_ctx_page[elt + 2],
-					   wa_ctx_page[elt + 3]);
-				offset += 16;
-			}
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"WA context", ee->wa_ctx);
 
-		if ((obj = ee->ctx)) {
-			err_printf(m, "%s --- HW Context = 0x%08x\n",
-				   dev_priv->engine[i].name,
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, obj);
-		}
+		print_error_obj(m, &dev_priv->engine[i],
+				"WA batchbuffer", ee->wa_batchbuffer);
 	}
 
-	if ((obj = error->semaphore)) {
-		err_printf(m, "Semaphore page = 0x%08x\n",
-			   lower_32_bits(obj->gtt_offset));
-		for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
-			err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-				   elt * 4,
-				   obj->pages[0][elt],
-				   obj->pages[0][elt+1],
-				   obj->pages[0][elt+2],
-				   obj->pages[0][elt+3]);
-		}
-	}
+	print_error_obj(m, NULL, "Semaphores", error->semaphore);
 
 	if (error->overlay)
 		intel_overlay_print_error_state(m, error->overlay);
-- 
2.8.1

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

[PATCH 37/37] drm/i915: Compress GPU objects in error state

[Chris Wilson]

Our error states are quickly growing, pinning kernel memory with them.
The majority of the space is taken up by the error objects. These
compress well using zlib and without decode are mostly meaningless, so
encoding them does not hinder quickly parsing the error state for
familiarity.

v2: Make the zlib dependency optional

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/Kconfig          |  12 +++
 drivers/gpu/drm/i915/i915_drv.h       |   3 +-
 drivers/gpu/drm/i915/i915_gpu_error.c | 170 +++++++++++++++++++++++++++++-----
 3 files changed, 163 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 7badcee88ebf..62a71eb126f2 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -58,6 +58,18 @@ config DRM_I915_USERPTR
 
 	  If in doubt, say "Y".
 
+config DRM_I915_DEFLATE_ERROR
+	bool "Compress GPU error state"
+	depends on DRM_I915
+	select ZLIB_DEFLATE
+	default y
+	help
+	  This option selects ZLIB_DEFLATE if it isn't already
+	  selected and causes any error state captured upon a GPU hang
+	  to be compressed using zlib.
+
+	  If in doubt, say "Y".
+
 config DRM_I915_GVT
         bool "Enable Intel GVT-g graphics virtualization host support"
         depends on DRM_I915
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 25d3cf204a2b..a85e22cd8962 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -776,9 +776,10 @@ struct drm_i915_error_state {
 		u32 semaphore_mboxes[I915_NUM_ENGINES - 1];
 
 		struct drm_i915_error_object {
-			int page_count;
 			u64 gtt_offset;
 			u64 gtt_size;
+			int page_count;
+			int unused;
 			u32 *pages[0];
 		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index e87a0e5351d2..e25b4474e954 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -29,6 +29,7 @@
 
 #include <generated/utsrelease.h>
 #include <linux/stop_machine.h>
+#include <linux/zlib.h>
 #include "i915_drv.h"
 
 static const char *engine_str(int engine)
@@ -173,6 +174,110 @@ static void i915_error_puts(struct drm_i915_error_state_buf *e,
 #define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__)
 #define err_puts(e, s) i915_error_puts(e, s)
 
+#ifdef CONFIG_DRM_I915_DEFLATE_ERROR
+
+static bool compress_init(struct z_stream_s *zstream)
+{
+	memset(zstream, 0, sizeof(*zstream));
+
+	zstream->workspace =
+		kmalloc(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
+			GFP_ATOMIC | __GFP_NOWARN);
+	if (!zstream->workspace)
+		return NULL;
+
+	if (zlib_deflateInit(zstream, Z_DEFAULT_COMPRESSION) != Z_OK) {
+		kfree(zstream->workspace);
+		return false;
+	}
+
+	return true;
+}
+
+static int compress_page(struct z_stream_s *zstream,
+			 void *src,
+			 struct drm_i915_error_object *dst)
+{
+	zstream->next_in = src;
+	zstream->avail_in = PAGE_SIZE;
+
+	do {
+		if (zstream->avail_out == 0) {
+			unsigned long page;
+
+			page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+			if (!page)
+				return -ENOMEM;
+
+			dst->pages[dst->page_count++] = (void *)page;
+
+			zstream->next_out = (void *)page;
+			zstream->avail_out = PAGE_SIZE;
+		}
+
+		if (zlib_deflate(zstream, Z_SYNC_FLUSH) != Z_OK)
+			return -EIO;
+
+		/* Fallback to uncompressed if we increase size? */
+		if (0 && zstream->total_out > zstream->total_in)
+			return -E2BIG;
+	} while (zstream->avail_in);
+
+	return 0;
+}
+
+static void compress_fini(struct z_stream_s *zstream,
+			  struct drm_i915_error_object *dst)
+{
+	if (dst) {
+		zlib_deflate(zstream, Z_FINISH);
+		dst->unused = zstream->avail_out;
+	}
+
+	zlib_deflateEnd(zstream);
+	kfree(zstream->workspace);
+}
+
+static void err_compression_marker(struct drm_i915_error_state_buf *m)
+{
+	err_puts(m, ":");
+}
+
+#else
+
+static bool compress_init(struct z_stream_s *zstream)
+{
+	return true;
+}
+
+static int compress_page(struct z_stream_s *zstream,
+			 void *src,
+			 struct drm_i915_error_object *dst)
+{
+	unsigned long page;
+
+	page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+	if (!page)
+		return -ENOMEM;
+
+	dst->pages[dst->page_count++] =
+		memcpy((void *)page, src, PAGE_SIZE);
+
+	return 0;
+}
+
+static void compress_fini(struct z_stream_s *zstream,
+			  struct drm_i915_error_object *dst)
+{
+}
+
+static void err_compression_marker(struct drm_i915_error_state_buf *m)
+{
+	err_puts(m, "~");
+}
+
+#endif
+
 static void print_error_buffers(struct drm_i915_error_state_buf *m,
 				const char *name,
 				struct drm_i915_error_buffer *err,
@@ -308,12 +413,30 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
+static bool
+ascii85_encode(u32 in, char *out)
+{
+	int i;
+
+	if (in == 0)
+		return false;
+
+	out[5] = '\0';
+	for (i = 5; i--; ) {
+		out[i] = '!' + in % 85;
+		in /= 85;
+	}
+
+	return true;
+}
+
 static void print_error_obj(struct drm_i915_error_state_buf *m,
 			    struct intel_engine_cs *engine,
 			    const char *name,
 			    struct drm_i915_error_object *obj)
 {
-	int page, offset, elt;
+	char out[6];
+	int page;
 
 	if (!obj)
 		return;
@@ -325,13 +448,23 @@ static void print_error_obj(struct drm_i915_error_state_buf *m,
 			   lower_32_bits(obj->gtt_offset));
 	}
 
-	for (page = offset = 0; page < obj->page_count; page++) {
-		for (elt = 0; elt < PAGE_SIZE/4; elt++) {
-			err_printf(m, "%08x :  %08x\n", offset,
-				   obj->pages[page][elt]);
-			offset += 4;
+	err_compression_marker(m);
+	for (page = 0; page < obj->page_count; page++) {
+		int i, len;
+
+		len = PAGE_SIZE;
+		if (page == obj->page_count - 1)
+			len -= obj->unused;
+		len = (len + 3) / 4;
+
+		for (i = 0; i < len; i++) {
+			if (ascii85_encode(obj->pages[page][i], out))
+				err_puts(m, out);
+			else
+				err_puts(m, "z");
 		}
 	}
+	err_puts(m, "\n");
 }
 
 static void err_print_capabilities(struct drm_i915_error_state_buf *m,
@@ -612,20 +745,6 @@ static void i915_error_state_free(struct kref *error_ref)
 	kfree(error);
 }
 
-static int compress_page(void *src, struct drm_i915_error_object *dst)
-{
-	unsigned long page;
-
-	page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
-	if (!page)
-		return -ENOMEM;
-
-	dst->pages[dst->page_count++] = (void *)page;
-
-	memcpy((void *)page, src, PAGE_SIZE);
-	return 0;
-}
-
 static struct drm_i915_error_object *
 i915_error_object_create(struct drm_i915_private *i915,
 			 struct i915_vma *vma)
@@ -633,6 +752,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 	struct i915_ggtt *ggtt = &i915->ggtt;
 	const u64 slot = ggtt->gpu_error.start;
 	struct drm_i915_error_object *dst;
+	struct z_stream_s zstream;
 	unsigned long num_pages;
 	struct sgt_iter iter;
 	dma_addr_t dma;
@@ -641,6 +761,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 		return NULL;
 
 	num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
+	num_pages = DIV_ROUND_UP(10 * num_pages, 8); /* worstcase zlib growth */
 	dst = kmalloc(sizeof(*dst) + num_pages * sizeof(u32 *),
 		      GFP_ATOMIC | __GFP_NOWARN);
 	if (!dst)
@@ -648,6 +769,12 @@ i915_error_object_create(struct drm_i915_private *i915,
 
 	dst->gtt_offset = vma->node.start;
 	dst->page_count = 0;
+	dst->unused = 0;
+
+	if (!compress_init(&zstream)) {
+		kfree(dst);
+		return NULL;
+	}
 
 	for_each_sgt_dma(dma, iter, vma->pages) {
 		int ret;
@@ -658,7 +785,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 
 		s = (void *__force)
 			io_mapping_map_atomic_wc(ggtt->mappable, slot);
-		ret = compress_page(s, dst);
+		ret = compress_page(&zstream, s, dst);
 		io_mapping_unmap_atomic(s);
 
 		if (ret)
@@ -673,6 +800,7 @@ unwind:
 	dst = NULL;
 
 out:
+	compress_fini(&zstream, dst);
 	ggtt->base.clear_range(&ggtt->base, slot, PAGE_SIZE, true);
 	return dst;
 }
-- 
2.8.1

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

Re: [PATCH 07/37] drm/i915: Reduce i915_gem_objects to only show object information

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:53 +0100, Chris Wilson wrote:
> No longer is knowing how much of the GTT (both mappable aperture and
> beyond) relevant, and the output clutters the real information - that is
> how many objects are allocated and bound (and by who) so that we can
> quickly grasp if there is a leak.
> 
> v2: Relent, and rename pinned to indicate display only. Since the
> display objects are semi-static and are of variable size, they are the
> interesting objects to watch over time for aperture leaking. The other
> pins are either static (such as the scratch page) or very short lived
> (such as execbuf) and not part of the precious GGTT.

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
>  drivers/gpu/drm/i915/i915_debugfs.c | 100 ++++++++++--------------------------
>  1 file changed, 28 insertions(+), 72 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index c535c4c2f7af..fd028953453d 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -269,17 +269,6 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
>  	return 0;
>  }
>  
> -#define count_objects(list, member) do { \
> -	list_for_each_entry(obj, list, member) { \
> -		size += i915_gem_obj_total_ggtt_size(obj); \
> -		++count; \
> -		if (obj->map_and_fenceable) { \
> -			mappable_size += i915_gem_obj_ggtt_size(obj); \
> -			++mappable_count; \
> -		} \
> -	} \
> -} while (0)
> -
>  struct file_stats {
>  	struct drm_i915_file_private *file_priv;
>  	unsigned long count;
> @@ -394,30 +383,16 @@ static void print_context_stats(struct seq_file *m,
>  	print_file_stats(m, "[k]contexts", stats);
>  }
>  
> -#define count_vmas(list, member) do { \
> -	list_for_each_entry(vma, list, member) { \
> -		size += i915_gem_obj_total_ggtt_size(vma->obj); \
> -		++count; \
> -		if (vma->obj->map_and_fenceable) { \
> -			mappable_size += i915_gem_obj_ggtt_size(vma->obj); \
> -			++mappable_count; \
> -		} \
> -	} \
> -} while (0)
> -
>  static int i915_gem_object_info(struct seq_file *m, void* data)
>  {
>  	struct drm_info_node *node = m->private;
>  	struct drm_device *dev = node->minor->dev;
>  	struct drm_i915_private *dev_priv = to_i915(dev);
>  	struct i915_ggtt *ggtt = &dev_priv->ggtt;
> -	u32 count, mappable_count, purgeable_count;
> -	u64 size, mappable_size, purgeable_size;
> -	unsigned long pin_mapped_count = 0, pin_mapped_purgeable_count = 0;
> -	u64 pin_mapped_size = 0, pin_mapped_purgeable_size = 0;
> +	u32 count, mapped_count, purgeable_count, dpy_count;
> +	u64 size, mapped_size, purgeable_size, dpy_size;
>  	struct drm_i915_gem_object *obj;
>  	struct drm_file *file;
> -	struct i915_vma *vma;
>  	int ret;
>  
>  	ret = mutex_lock_interruptible(&dev->struct_mutex);
> @@ -428,70 +403,51 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
>  		   dev_priv->mm.object_count,
>  		   dev_priv->mm.object_memory);
>  
> -	size = count = mappable_size = mappable_count = 0;
> -	count_objects(&dev_priv->mm.bound_list, global_list);
> -	seq_printf(m, "%u [%u] objects, %llu [%llu] bytes in gtt\n",
> -		   count, mappable_count, size, mappable_size);
> -
> -	size = count = mappable_size = mappable_count = 0;
> -	count_vmas(&ggtt->base.active_list, vm_link);
> -	seq_printf(m, "  %u [%u] active objects, %llu [%llu] bytes\n",
> -		   count, mappable_count, size, mappable_size);
> -
> -	size = count = mappable_size = mappable_count = 0;
> -	count_vmas(&ggtt->base.inactive_list, vm_link);
> -	seq_printf(m, "  %u [%u] inactive objects, %llu [%llu] bytes\n",
> -		   count, mappable_count, size, mappable_size);
> -
>  	size = count = purgeable_size = purgeable_count = 0;
>  	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
> -		size += obj->base.size, ++count;
> -		if (obj->madv == I915_MADV_DONTNEED)
> -			purgeable_size += obj->base.size, ++purgeable_count;
> +		size += obj->base.size;
> +		++count;
> +
> +		if (obj->madv == I915_MADV_DONTNEED) {
> +			purgeable_size += obj->base.size;
> +			++purgeable_count;
> +		}
> +
>  		if (obj->mapping) {
> -			pin_mapped_count++;
> -			pin_mapped_size += obj->base.size;
> -			if (obj->pages_pin_count == 0) {
> -				pin_mapped_purgeable_count++;
> -				pin_mapped_purgeable_size += obj->base.size;
> -			}
> +			mapped_count++;
> +			mapped_size += obj->base.size;
>  		}
>  	}
>  	seq_printf(m, "%u unbound objects, %llu bytes\n", count, size);
>  
> -	size = count = mappable_size = mappable_count = 0;
> +	size = count = dpy_size = dpy_count = 0;
>  	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
> -		if (obj->fault_mappable) {
> -			size += i915_gem_obj_ggtt_size(obj);
> -			++count;
> -		}
> +		size += obj->base.size;
> +		++count;
> +
>  		if (obj->pin_display) {
> -			mappable_size += i915_gem_obj_ggtt_size(obj);
> -			++mappable_count;
> +			dpy_size += obj->base.size;
> +			++dpy_count;
>  		}
> +
>  		if (obj->madv == I915_MADV_DONTNEED) {
>  			purgeable_size += obj->base.size;
>  			++purgeable_count;
>  		}
> +
>  		if (obj->mapping) {
> -			pin_mapped_count++;
> -			pin_mapped_size += obj->base.size;
> -			if (obj->pages_pin_count == 0) {
> -				pin_mapped_purgeable_count++;
> -				pin_mapped_purgeable_size += obj->base.size;
> -			}
> +			mapped_count++;
> +			mapped_size += obj->base.size;
>  		}
>  	}
> +	seq_printf(m, "%u bound objects, %llu bytes\n",
> +		   count, size);
>  	seq_printf(m, "%u purgeable objects, %llu bytes\n",
>  		   purgeable_count, purgeable_size);
> -	seq_printf(m, "%u pinned mappable objects, %llu bytes\n",
> -		   mappable_count, mappable_size);
> -	seq_printf(m, "%u fault mappable objects, %llu bytes\n",
> -		   count, size);
> -	seq_printf(m,
> -		   "%lu [%lu] pin mapped objects, %llu [%llu] bytes [purgeable]\n",
> -		   pin_mapped_count, pin_mapped_purgeable_count,
> -		   pin_mapped_size, pin_mapped_purgeable_size);
> +	seq_printf(m, "%u mapped objects, %llu bytes\n",
> +		   mapped_count, mapped_size);
> +	seq_printf(m, "%u display objects (pinned), %llu bytes\n",
> +		   dpy_count, dpy_size);
>  
>  	seq_printf(m, "%llu [%llu] gtt total\n",
>  		   ggtt->base.total, ggtt->mappable_end - ggtt->base.start);
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

✗ Ro.CI.BAT: failure for series starting with [01/37] drm/i915: Record the position of the start of the request

[Patchwork]

== Series Details ==

Series: series starting with [01/37] drm/i915: Record the position of the start of the request
URL   : https://patchwork.freedesktop.org/series/11006/
State : failure

== Summary ==

Series 11006v1 Series without cover letter
http://patchwork.freedesktop.org/api/1.0/series/11006/revisions/1/mbox

Test gem_exec_suspend:
        Subgroup basic-s3:
                dmesg-warn -> PASS       (ro-bdw-i7-5600u)
Test kms_cursor_legacy:
        Subgroup basic-cursor-vs-flip-varying-size:
                pass       -> FAIL       (ro-ilk1-i5-650)
        Subgroup basic-flip-vs-cursor-legacy:
                fail       -> PASS       (ro-bdw-i5-5250u)
        Subgroup basic-flip-vs-cursor-varying-size:
                fail       -> PASS       (ro-byt-n2820)
Test kms_pipe_crc_basic:
        Subgroup read-crc-pipe-b-frame-sequence:
                fail       -> PASS       (ro-ivb2-i7-3770)
        Subgroup suspend-read-crc-pipe-a:
                dmesg-warn -> SKIP       (ro-bdw-i5-5250u)
        Subgroup suspend-read-crc-pipe-b:
                skip       -> DMESG-WARN (ro-bdw-i5-5250u)
        Subgroup suspend-read-crc-pipe-c:
                skip       -> DMESG-WARN (ro-bdw-i5-5250u)

fi-hsw-i7-4770k  total:244  pass:222  dwarn:0   dfail:0   fail:0   skip:22 
fi-kbl-qkkr      total:244  pass:185  dwarn:29  dfail:0   fail:4   skip:26 
fi-skl-i5-6260u  total:244  pass:224  dwarn:4   dfail:0   fail:2   skip:14 
fi-skl-i7-6700k  total:244  pass:208  dwarn:4   dfail:2   fail:2   skip:28 
fi-snb-i7-2600   total:244  pass:202  dwarn:0   dfail:0   fail:0   skip:42 
ro-bdw-i5-5250u  total:240  pass:219  dwarn:3   dfail:0   fail:1   skip:17 
ro-bdw-i7-5600u  total:240  pass:207  dwarn:0   dfail:0   fail:1   skip:32 
ro-byt-n2820     total:240  pass:198  dwarn:0   dfail:0   fail:2   skip:40 
ro-hsw-i3-4010u  total:240  pass:214  dwarn:0   dfail:0   fail:0   skip:26 
ro-hsw-i7-4770r  total:240  pass:185  dwarn:0   dfail:0   fail:0   skip:55 
ro-ilk1-i5-650   total:235  pass:173  dwarn:0   dfail:0   fail:2   skip:60 
ro-ivb-i7-3770   total:240  pass:205  dwarn:0   dfail:0   fail:0   skip:35 
ro-ivb2-i7-3770  total:240  pass:209  dwarn:0   dfail:0   fail:0   skip:31 
ro-skl3-i5-6260u total:240  pass:222  dwarn:0   dfail:0   fail:4   skip:14 
ro-bsw-n3050 failed to connect after reboot

Results at /archive/results/CI_IGT_test/RO_Patchwork_1848/

4a26251 drm-intel-nightly: 2016y-08m-11d-16h-12m-42s UTC integration manifest
bbe321e drm/i915: Compress GPU objects in error state
c736465 drm/i915: Consolidate error object printing
b9d7ce6 drm/i915: Always use the GTT for error capture
2d78c73 drm/i915: Record the RING_MODE register for post-mortem debugging
8009c8b drm/i915: Only record active and pending requests upon a GPU hang
ac84df6 drm/i915: Move debug only per-request pid tracking from request to ctx
333b38b drm/i915: Print the batchbuffer offset next to BBADDR in error state
ab45e93 drm/i915: Introduce i915_ggtt_offset()
9383778 drm/i915: Track pinned VMA
0c5cfb1 drm/i915: Consolidate i915_vma_unpin_and_release()
2356caf drm/i915: Use VMA for wa_ctx tracking
faf444e drm/i915: Use VMA for render state page tracking
1458007 drm/i915: Use VMA as the primary tracker for semaphore page
8d5d67e drm/i915/overlay: Use VMA as the primary tracker for images
21afb26 drm/i915: Move common seqno reset to intel_engine_cs.c
9b03687 drm/i915: Move common scratch allocation/destroy to intel_engine_cs.c
70f6e29 drm/i915: Use VMA for scratch page tracking
fc4f6b1 drm/i915: Use VMA for ringbuffer tracking
5055bb5 drm/i915: Move assertion for iomap access to i915_vma_pin_iomap
5b56d16 drm/i915: Only clflush the context object when binding
9ea66dc drm/i915: Use VMA as the primary object for context state
bca03c1 drm/i915: Use VMA directly for checking tiling parameters
e16c22e drm/i915: Convert fence computations to use vma directly
88723a1 drm/i915: Track pinned vma inside guc
d949129 drm/i915: Add convenience wrappers for vma's object get/put
6fd6ac5 drm/i915: Add fetch_and_zero() macro
8a5a130 drm/i915: Create a VMA for an object
0f4173b drm/i915: Always set the vma->pages
223ca5c drm/i915: Remove redundant WARN_ON from __i915_add_request()
29e0a02 drm/i915: Record the device capabilities at the time of a hang
e07c634 drm/i915: Reduce i915_gem_objects to only show object information
af4a8f2 drm/i915: Focus debugfs/i915_gem_pinned to show only display pins
3ecd7e5 drm/i915: Remove inactive/active list from debugfs
ec122f6 drm/i915: Store the active context object on all engines upon error
9a8802c drm/i915: Stop the machine whilst capturing the GPU crash dump
1230c97 drm/i915: Reduce amount of duplicate buffer information captured on error
a55740d drm/i915: Record the position of the start of the request

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

Re: [PATCH 08/37] drm/i915: Record the device capabilities at the time of a hang

[Joonas Lahtinen]

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 10/37] drm/i915: Always set the vma->pages

[Joonas Lahtinen]

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation

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

Re: [PATCH 12/37] drm/i915: Add fetch_and_zero() macro

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> A simple little macro to clear a pointer and return the old value. This
> is useful for writing
> 
> 	value = *ptr;
> 	if (!value)
> 		return;
> 
> 	*ptr = 0;
> 	...
> 	free(value);
> 
> in a slightly more concise form:
> 
> 	value = fetch_and_zero(ptr);
> 	if (!value)
> 		return;
> 
> 	...
> 	free(value);
> 
> with the idea that this establishes a pattern that may be extended for
> atomic use (using xchg or cmpxchg) i.e. atomic_fetch_and_zero() and
> similar to llist.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
> ---
>  drivers/gpu/drm/i915/i915_drv.h | 6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index a4203ff0cf7f..731c67fc9796 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -3903,4 +3903,10 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req)
>  	return false;
>  }
>  
> +#define fetch_and_zero(ptr) ({					\
> +	typeof(*ptr) T__ = *(ptr);					\

Looking at container_of etc. it's always __ as prefix.

	const typeof(*ptr) __val = *(ptr);

And we're good to go (with kerneldoc almost ready for core submission
:P);

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

> +	*(ptr) = (typeof(*ptr))0;					\
> +	T__;								\
> +})
> +
>  #endif
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 13/37] drm/i915: Add convenience wrappers for vma's object get/put

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> +static inline struct i915_vma *i915_vma_get(struct i915_vma *vma)
> +{
> +	i915_gem_object_get(vma->obj);
> +	return vma;
> +}
> +
> +static inline void i915_vma_put(struct i915_vma *vma)
> +{
> +	lockdep_assert_held(&vma->vm->dev->struct_mutex);
> +	i915_gem_object_put(vma->obj);
> +}

As noted in IRC, the locking asymmetry is kinda meh, to be consolidated
in the future I hope.

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 12/37] drm/i915: Add fetch_and_zero() macro

[Chris Wilson]

On Fri, Aug 12, 2016 at 10:55:46AM +0300, Joonas Lahtinen wrote:
> On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> > A simple little macro to clear a pointer and return the old value. This
> > is useful for writing
> > 
> > 	value = *ptr;
> > 	if (!value)
> > 		return;
> > 
> > 	*ptr = 0;
> > 	...
> > 	free(value);
> > 
> > in a slightly more concise form:
> > 
> > 	value = fetch_and_zero(ptr);
> > 	if (!value)
> > 		return;
> > 
> > 	...
> > 	free(value);
> > 
> > with the idea that this establishes a pattern that may be extended for
> > atomic use (using xchg or cmpxchg) i.e. atomic_fetch_and_zero() and
> > similar to llist.
> > 
> > Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> > Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> > Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
> > ---
> >  drivers/gpu/drm/i915/i915_drv.h | 6 ++++++
> >  1 file changed, 6 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> > index a4203ff0cf7f..731c67fc9796 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -3903,4 +3903,10 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req)
> >  	return false;
> >  }
> >  
> > +#define fetch_and_zero(ptr) ({					\
> > +	typeof(*ptr) T__ = *(ptr);					\
> 
> Looking at container_of etc. it's always __ as prefix.

The advice to use the suffix is from gcc's manual iirc, and there are a
few macros that do dotted around the place, but it looks overwhelmingly
in favour of the prefix.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 16/37] drm/i915: Use VMA directly for checking tiling parameters

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
>  /* Is the current GTT allocation valid for the change in tiling? */
> -static bool
> +static int
>  i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)

As agreed in IRC, comment to be "Make " and change function name
approppriately and we're good;

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 18/37] drm/i915: Only clflush the context object when binding

[Joonas Lahtinen]

Only commit title could now talk about moving domains instead of
clflush, then;

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 19/37] drm/i915: Move assertion for iomap access to i915_vma_pin_iomap

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> Access through the GTT requires the device to be awake. Ideally
> i915_vma_pin_iomap() is short-lived and the pinning demarcates the
> access through the iomap. This is not entirely true, we have a mixture
> of long lived pins that exceed the wakelock (such as legacy ringbuffers)
> and short lived pin that do live within the wakelock (such as execlist
> ringbuffers).
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 20/37] drm/i915: Use VMA for ringbuffer tracking

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> Use the GGTT VMA as the primary cookie for handing ring objects as
> the most common action upon the ring is mapping and unmapping which act
> upon the VMA itself. By restructuring the code to work with the ring
> VMA, we can shrink the code and remove a few cycles from context pinning.
> 
> v2: Move the flush of the object back to before the first pin. We use
> the am-I-bound? query to only have to check the flush on the first
> bind and so avoid stalling on active rings.
> Lots of little renames and small hoops.

With this delta,

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 22/37] drm/i915: Move common scratch allocation/destroy to intel_engine_cs.c

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> Since the scratch allocation and cleanup is shared by all engine
> submission backends, move it out of the legacy intel_ringbuffer.c and
> into the new home for common routines, intel_engine_cs.c
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Reviewed-by: Matthew Auld <matthew.auld@intel.com>

Hmm, did not get my e-mail?

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

> ---
>  drivers/gpu/drm/i915/intel_engine_cs.c  | 50 +++++++++++++++++++++++++++++++++
>  drivers/gpu/drm/i915/intel_lrc.c        |  1 -
>  drivers/gpu/drm/i915/intel_ringbuffer.c | 50 ---------------------------------
>  drivers/gpu/drm/i915/intel_ringbuffer.h |  4 +--
>  4 files changed, 51 insertions(+), 54 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
> index 186c12d07f99..7104dec5e893 100644
> --- a/drivers/gpu/drm/i915/intel_engine_cs.c
> +++ b/drivers/gpu/drm/i915/intel_engine_cs.c
> @@ -195,6 +195,54 @@ void intel_engine_setup_common(struct intel_engine_cs *engine)
>  	i915_gem_batch_pool_init(engine, &engine->batch_pool);
>  }
>  
> +int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
> +{
> +	struct drm_i915_gem_object *obj;
> +	struct i915_vma *vma;
> +	int ret;
> +
> +	WARN_ON(engine->scratch);
> +
> +	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
> +	if (!obj)
> +		obj = i915_gem_object_create(&engine->i915->drm, size);
> +	if (IS_ERR(obj)) {
> +		DRM_ERROR("Failed to allocate scratch page\n");
> +		return PTR_ERR(obj);
> +	}
> +
> +	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
> +	if (IS_ERR(vma)) {
> +		ret = PTR_ERR(vma);
> +		goto err_unref;
> +	}
> +
> +	ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
> +	if (ret)
> +		goto err_unref;
> +
> +	engine->scratch = vma;
> +	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
> +			 engine->name, vma->node.start);
> +	return 0;
> +
> +err_unref:
> +	i915_gem_object_put(obj);
> +	return ret;
> +}
> +
> +static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
> +{
> +	struct i915_vma *vma;
> +
> +	vma = fetch_and_zero(&engine->scratch);
> +	if (!vma)
> +		return;
> +
> +	i915_vma_unpin(vma);
> +	i915_vma_put(vma);
> +}
> +
>  /**
>   * intel_engines_init_common - initialize cengine state which might require hw access
>   * @engine: Engine to initialize.
> @@ -226,6 +274,8 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
>   */
>  void intel_engine_cleanup_common(struct intel_engine_cs *engine)
>  {
> +	intel_engine_cleanup_scratch(engine);
> +
>  	intel_engine_cleanup_cmd_parser(engine);
>  	intel_engine_fini_breadcrumbs(engine);
>  	i915_gem_batch_pool_fini(&engine->batch_pool);
> diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
> index cdcdec83d640..88bc5d4ce243 100644
> --- a/drivers/gpu/drm/i915/intel_lrc.c
> +++ b/drivers/gpu/drm/i915/intel_lrc.c
> @@ -1844,7 +1844,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine)
>  	else
>  		engine->init_hw = gen8_init_render_ring;
>  	engine->init_context = gen8_init_rcs_context;
> -	engine->cleanup = intel_engine_cleanup_scratch;
>  	engine->emit_flush = gen8_emit_flush_render;
>  	engine->emit_request = gen8_emit_request_render;
>  
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 939632229320..0ecdd452a7f7 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -613,54 +613,6 @@ out:
>  	return ret;
>  }
>  
> -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
> -{
> -	struct i915_vma *vma;
> -
> -	vma = fetch_and_zero(&engine->scratch);
> -	if (!vma)
> -		return;
> -
> -	i915_vma_unpin(vma);
> -	i915_vma_put(vma);
> -}
> -
> -int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
> -{
> -	struct drm_i915_gem_object *obj;
> -	struct i915_vma *vma;
> -	int ret;
> -
> -	WARN_ON(engine->scratch);
> -
> -	obj = i915_gem_object_create_stolen(&engine->i915->drm, size);
> -	if (!obj)
> -		obj = i915_gem_object_create(&engine->i915->drm, size);
> -	if (IS_ERR(obj)) {
> -		DRM_ERROR("Failed to allocate scratch page\n");
> -		return PTR_ERR(obj);
> -	}
> -
> -	vma = i915_vma_create(obj, &engine->i915->ggtt.base, NULL);
> -	if (IS_ERR(vma)) {
> -		ret = PTR_ERR(vma);
> -		goto err_unref;
> -	}
> -
> -	ret = i915_vma_pin(vma, 0, 4096, PIN_GLOBAL | PIN_HIGH);
> -	if (ret)
> -		goto err_unref;
> -
> -	engine->scratch = vma;
> -	DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08llx\n",
> -			 engine->name, vma->node.start);
> -	return 0;
> -
> -err_unref:
> -	i915_gem_object_put(obj);
> -	return ret;
> -}
> -
>  static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
>  {
>  	struct intel_ring *ring = req->ring;
> @@ -1311,8 +1263,6 @@ static void render_ring_cleanup(struct intel_engine_cs *engine)
>  		i915_gem_object_put(dev_priv->semaphore_obj);
>  		dev_priv->semaphore_obj = NULL;
>  	}
> -
> -	intel_engine_cleanup_scratch(engine);
>  }
>  
>  static int gen8_rcs_signal(struct drm_i915_gem_request *req)
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index c6024db75f93..dca84258be16 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -472,11 +472,9 @@ void intel_ring_update_space(struct intel_ring *ring);
>  
>  void intel_engine_init_seqno(struct intel_engine_cs *engine, u32 seqno);
>  
> -int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
> -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine);
> -
>  void intel_engine_setup_common(struct intel_engine_cs *engine);
>  int intel_engine_init_common(struct intel_engine_cs *engine);
> +int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
>  void intel_engine_cleanup_common(struct intel_engine_cs *engine);
>  
>  static inline int intel_engine_idle(struct intel_engine_cs *engine,
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 23/37] drm/i915: Move common seqno reset to intel_engine_cs.c

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> Since the intel_engine_init_seqno() is shared by all engine submission
> backends, move it out of the legacy intel_ringbuffer.c and
> into the new home for common routines, intel_engine_cs.c
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Reviewed-by: Matthew Auld <matthew.auld@intel.com>

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 28/37] drm/i915: Consolidate i915_vma_unpin_and_release()

[Joonas Lahtinen]

Those functions look like they will get nuked in the future.

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 29/37] drm/i915: Track pinned VMA

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> Treat the VMA as the primary struct responsible for tracking bindings
> into the GPU's VM. That is we want to treat the VMA returned after we
> pin an object into the VM as the cookie we hold and eventually release
> when unpinning. Doing so eliminates the ambiguity in pinning the object
> and then searching for the relevant pin later.
> 
> v2: Joonas' stylistic nitpicks, a fun rebase.
> 

<SNIP>

>-	return vma;
>-
> err:
> 	i915_gem_object_unpin_pages(shadow_batch_obj);
>-	if (ret == -EACCES) /* unhandled chained batch */
>-		return NULL;
>-	else
>-		return ERR_PTR(ret);
>+	return vma;
> }

You made it the success path too, so just 'out'.

That's pretty much all I found by scrolling through it;

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 30/37] drm/i915: Introduce i915_ggtt_offset()

[Joonas Lahtinen]

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation

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

Re: [PATCH 32/37] drm/i915: Move debug only per-request pid tracking from request to ctx

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> Since contexts are not currently shared between userspace processes, we
> have an exact correspondence between context creator and guilty batch
> submitter. Therefore we can save some per-batch work by inspecting the
> context->pid upon error instead. Note that we take the context's
> creator's pid rather than the file's pid in order to better track fd
> passed over sockets.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 34/37] drm/i915: Record the RING_MODE register for post-mortem debugging

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
> Just another useful register to inspect following a GPU hang.
> 
> v2: Remove partial decoding of RING_MODE to userspace, be consistent and
> use GEN > 2 guards around RING_MODE everywhere.
> 
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 14/37] drm/i915: Track pinned vma inside guc

[Joonas Lahtinen]

CC'ing Dave to comment too.

On pe, 2016-08-12 at 07:54 +0100, Chris Wilson wrote:
>  /**
> - * gem_allocate_guc_obj() - Allocate gem object for GuC usage
> - * @dev_priv:	driver private data structure
> + * guc_allocate_vma() - Allocate a GGTT VMA for GuC usage
> + * @guc:	the guc
>   * @size:	size of object

s/object/VMA/

>   *
>   * This is a wrapper to create a gem obj. In order to use it inside GuC, the
> @@ -624,45 +623,49 @@ static void i915_guc_submit(struct drm_i915_gem_request *rq)
>   *
>   * Return:	A drm_i915_gem_object if successful, otherwise NULL.

s/drm_i915_gem_object/i915_vma/ And maybe update the comment wording
too.

>  /**
> - * gem_release_guc_obj() - Release gem object allocated for GuC usage
> - * @obj:	gem obj to be released
> + * guc_release_vma() - Release gem object allocated for GuC usage
> + * @vma:	gem obj to be released

The GEM object is kinda created implicitly, so not sure how to include
it in wording, improvise.

With the minor tweaks to comments,

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 01/37] drm/i915: Record the position of the start of the request

[Joonas Lahtinen]

On pe, 2016-08-12 at 07:53 +0100, Chris Wilson wrote:
> @@ -455,9 +455,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
>  				   dev_priv->engine[i].name,
>  				   ee->num_requests);
>  			for (j = 0; j < ee->num_requests; j++) {
> -				err_printf(m, "  seqno 0x%08x, emitted %ld, tail 0x%08x\n",
> +				err_printf(m, "  seqno 0x%08x, emitted %ld, head 0x%08x tail 0x%08x\n",

Maybe slap in a comma in there.

Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Regards, Joonas
-- 
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 33/37] drm/i915: Only record active and pending requests upon a GPU hang

[Matthew Auld]

> +static void engine_record_requests(struct intel_engine_cs *engine,
> +                                  struct drm_i915_gem_request *first,
> +                                  struct drm_i915_error_engine *ee)
> +{
> +       struct drm_i915_gem_request *request;
> +       int count;
> +
> +       count = 0;
> +       request = first;
> +       list_for_each_entry_from(request, &engine->request_list, link)
> +               count += !!request->batch;
> +
> +       ee->requests = NULL;
> +       kcalloc(count, sizeof(*ee->requests),
> +               GFP_ATOMIC);
Surely not Chris :)

With that fixed:
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: [PATCH 33/37] drm/i915: Only record active and pending requests upon a GPU hang

[Chris Wilson]

On Fri, Aug 12, 2016 at 01:39:34PM +0100, Matthew Auld wrote:
> > +static void engine_record_requests(struct intel_engine_cs *engine,
> > +                                  struct drm_i915_gem_request *first,
> > +                                  struct drm_i915_error_engine *ee)
> > +{
> > +       struct drm_i915_gem_request *request;
> > +       int count;
> > +
> > +       count = 0;
> > +       request = first;
> > +       list_for_each_entry_from(request, &engine->request_list, link)
> > +               count += !!request->batch;
> > +
> > +       ee->requests = NULL;
> > +       kcalloc(count, sizeof(*ee->requests),
> > +               GFP_ATOMIC);
> Surely not Chris :)

Crumbs. Missed that even trying to double check after each iteration.
Thanks,
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx