[Intel-gfx] [PATCH 07/10] drm/i915: Early alloc request
John.C.Harrison at Intel.com
John.C.Harrison at Intel.com
Tue Dec 9 04:59:10 PST 2014
From: John Harrison <John.C.Harrison at Intel.com>
The scheduler needs to explicitly allocate a request to track each submitted
batch buffer. This must happen a long time before any commands are actually
written to the ring.
Change-Id: Id01fbda123bcfaa84531896c38292435270025b1
For: VIZ-1587
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 ++
drivers/gpu/drm/i915/i915_gem.c | 2 ++
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 13 ++++++++++---
drivers/gpu/drm/i915/intel_lrc.c | 6 +++---
drivers/gpu/drm/i915/intel_lrc.h | 2 ++
drivers/gpu/drm/i915/intel_ringbuffer.c | 6 +++---
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 ++
7 files changed, 24 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0e280c4..8628a83 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1775,6 +1775,8 @@ struct drm_i915_private {
/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
struct {
+ int (*alloc_request)(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
int (*do_execbuf)(struct drm_device *dev, struct drm_file *file,
struct intel_engine_cs *ring,
struct intel_context *ctx,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b022a2d..09332ff 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4870,11 +4870,13 @@ int i915_gem_init(struct drm_device *dev)
}
if (!i915.enable_execlists) {
+ dev_priv->gt.alloc_request = intel_ring_alloc_request;
dev_priv->gt.do_execbuf = i915_gem_ringbuffer_submission;
dev_priv->gt.init_rings = i915_gem_init_rings;
dev_priv->gt.cleanup_ring = intel_cleanup_ring_buffer;
dev_priv->gt.stop_ring = intel_stop_ring_buffer;
} else {
+ dev_priv->gt.alloc_request = intel_logical_ring_alloc_request;
dev_priv->gt.do_execbuf = intel_execlists_submission;
dev_priv->gt.init_rings = intel_logical_rings_init;
dev_priv->gt.cleanup_ring = intel_logical_ring_cleanup;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 1268e89..f09501c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1287,7 +1287,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
u64 exec_start = args->batch_start_offset;
u32 dispatch_flags;
int ret;
- bool need_relocs;
+ bool need_relocs, batch_pinned = false;
if (!i915_gem_check_execbuffer(args))
return -EINVAL;
@@ -1436,23 +1436,30 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (ret)
goto err;
+ batch_pinned = true;
exec_start += i915_gem_obj_ggtt_offset(batch_obj);
} else
exec_start += i915_gem_obj_offset(batch_obj, vm);
+ /* Allocate a request for this batch buffer nice and early. */
+ ret = dev_priv->gt.alloc_request(ring, ctx);
+ if (ret)
+ goto err;
+
ret = dev_priv->gt.do_execbuf(dev, file, ring, ctx, args,
&eb->vmas, batch_obj, exec_start,
dispatch_flags);
+err:
/*
* FIXME: We crucially rely upon the active tracking for the (ppgtt)
* batch vma for correctness. For less ugly and less fragility this
* needs to be adjusted to also track the ggtt batch vma properly as
* active.
*/
- if (dispatch_flags & I915_DISPATCH_SECURE)
+ if (batch_pinned)
i915_gem_object_ggtt_unpin(batch_obj);
-err:
+
/* the request owns the ref now */
i915_gem_context_unreference(ctx);
eb_destroy(eb);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 643a56a..037cbd5 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -878,8 +878,8 @@ void intel_lr_context_unpin(struct intel_engine_cs *ring,
}
}
-static int logical_ring_alloc_request(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+int intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
+ struct intel_context *ctx)
{
struct drm_i915_gem_request *request;
struct drm_i915_private *dev_private = ring->dev->dev_private;
@@ -1082,7 +1082,7 @@ int intel_logical_ring_begin(struct intel_ringbuffer *ringbuf, int num_dwords)
return ret;
/* Preallocate the olr before touching the ring */
- ret = logical_ring_alloc_request(ring, ringbuf->FIXME_lrc_ctx);
+ ret = intel_logical_ring_alloc_request(ring, ringbuf->FIXME_lrc_ctx);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index b8d5364..2bf868a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -34,6 +34,8 @@
#define RING_CONTEXT_STATUS_PTR(ring) ((ring)->mmio_base+0x3a0)
/* Logical Rings */
+int __must_check intel_logical_ring_alloc_request(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
void intel_logical_ring_stop(struct intel_engine_cs *ring);
void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
int intel_logical_rings_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index f990ce4..65ffdd1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2023,8 +2023,8 @@ int intel_ring_idle(struct intel_engine_cs *ring)
return i915_wait_request(req);
}
-static int
-intel_ring_alloc_request(struct intel_engine_cs *ring)
+int
+intel_ring_alloc_request(struct intel_engine_cs *ring, struct intel_context *ctx)
{
int ret;
struct drm_i915_gem_request *request;
@@ -2088,7 +2088,7 @@ int intel_ring_begin(struct intel_engine_cs *ring,
return ret;
/* Preallocate the olr before touching the ring */
- ret = intel_ring_alloc_request(ring);
+ ret = intel_ring_alloc_request(ring, NULL);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index f15fc46..b313144 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -430,6 +430,8 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
+int __must_check intel_ring_alloc_request(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
static inline void intel_ring_emit(struct intel_engine_cs *ring,
u32 data)
{
--
1.7.9.5
More information about the Intel-gfx
mailing list