drm/i915: Implement inter-engine read-read optimisations

Currently, we only track the last request globally across all engines.
This prevents us from issuing concurrent read requests on e.g. the RCS
and BCS engines (or more likely the render and media engines). Without
semaphores, we incur costly stalls as we synchronise between rings -
greatly impacting the current performance of Broadwell versus Haswell in
certain workloads (like video decode). With the introduction of
reference counted requests, it is much easier to track the last request
per ring, as well as the last global write request so that we can
optimise inter-engine read read requests (as well as better optimise
certain CPU waits).

v2: Fix inverted readonly condition for nonblocking waits.
v3: Handle non-continguous engine array after waits
v4: Rebase, tidy, rewrite ring list debugging
v5: Use obj->active as a bitfield, it looks cool
v6: Micro-optimise, mostly involving moving code around
v7: Fix retire-requests-upto for execlists (and multiple rq->ringbuf)
v8: Rebase
v9: Refactor i915_gem_object_sync() to allow the compiler to better
optimise it.

Benchmark: igt/gem_read_read_speed
hsw:gt3e (with semaphores):
Before: Time to read-read 1024k:		275.794µs
After:  Time to read-read 1024k:		123.260µs

hsw:gt3e (w/o semaphores):
Before: Time to read-read 1024k:		230.433µs
After:  Time to read-read 1024k:		124.593µs

bdw-u (w/o semaphores):             Before          After
Time to read-read 1x1:            26.274µs       10.350µs
Time to read-read 128x128:        40.097µs       21.366µs
Time to read-read 256x256:        77.087µs       42.608µs
Time to read-read 512x512:       281.999µs      181.155µs
Time to read-read 1024x1024:    1196.141µs     1118.223µs
Time to read-read 2048x2048:    5639.072µs     5225.837µs
Time to read-read 4096x4096:   22401.662µs    21137.067µs
Time to read-read 8192x8192:   89617.735µs    85637.681µs

Testcase: igt/gem_concurrent_blit (read-read and friends)
Cc: Lionel Landwerlin <lionel.g.landwerlin@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> [v8]
[danvet: s/\<rq\>/req/g]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 11 insertions, 5 deletions

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index f465af1b02f8..5fceb9400a91 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -120,10 +120,13 @@ static inline const char *get_global_flag(struct drm_i915_gem_object *obj)
 static void
 describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 {
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct intel_engine_cs *ring;
 	struct i915_vma *vma;
 	int pin_count = 0;
+	int i;
 
-	seq_printf(m, "%pK: %s%s%s%s %8zdKiB %02x %02x %x %x %x%s%s%s",
+	seq_printf(m, "%pK: %s%s%s%s %8zdKiB %02x %02x [ ",
 		   &obj->base,
 		   obj->active ? "*" : " ",
 		   get_pin_flag(obj),
@@ -131,8 +134,11 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   get_global_flag(obj),
 		   obj->base.size / 1024,
 		   obj->base.read_domains,
-		   obj->base.write_domain,
-		   i915_gem_request_get_seqno(obj->last_read_req),
+		   obj->base.write_domain);
+	for_each_ring(ring, dev_priv, i)
+		seq_printf(m, "%x ",
+				i915_gem_request_get_seqno(obj->last_read_req[i]));
+	seq_printf(m, "] %x %x%s%s%s",
 		   i915_gem_request_get_seqno(obj->last_write_req),
 		   i915_gem_request_get_seqno(obj->last_fenced_req),
 		   i915_cache_level_str(to_i915(obj->base.dev), obj->cache_level),
@@ -169,9 +175,9 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		*t = '\0';
 		seq_printf(m, " (%s mappable)", s);
 	}
-	if (obj->last_read_req != NULL)
+	if (obj->last_write_req != NULL)
 		seq_printf(m, " (%s)",
-			   i915_gem_request_get_ring(obj->last_read_req)->name);
+			   i915_gem_request_get_ring(obj->last_write_req)->name);
 	if (obj->frontbuffer_bits)
 		seq_printf(m, " (frontbuffer: 0x%03x)", obj->frontbuffer_bits);
 }