drm/i915: Add per context timelines for fence objects

The purpose of this patch series is to convert the requst structure to
use fence objects for the underlying completion tracking. The fence
object requires a sequence number. The ultimate aim is to use the same
sequence number as for the request itself (or rather, to remove the
request's seqno field and just use the fence's value throughout the
driver). However, this is not currently possible and so this patch
introduces a separate numbering scheme as an intermediate step.

A major advantage of using the fence object is that it can be passed
outside of the i915 driver and used externally. The fence API allows
for various operations such as combining multiple fences. This
requires that fence seqnos within a single fence context be guaranteed
in-order. The GPU scheduler that is coming can re-order request
execution but not within a single GPU context. Thus the fence context
must be tied to the i915 context (and the engine within the context as
each engine runs asynchronously).

On the other hand, the driver as a whole currently only works with
request seqnos that are allocated from a global in-order timeline. It
will require a fair chunk of re-work to allow multiple independent
seqno timelines to be used. Hence the introduction of a temporary,
fence specific timeline. Once the work to update the rest of the
driver has been completed then the request can use the fence seqno
instead.

v2: New patch in series.

v3: Renamed/retyped timeline structure fields after review comments by
Tvrtko Ursulin.

Added context information to the timeline's name string for better
identification in debugfs output.

v5: Line wrapping and other white space fixes to keep style checker
happy.

v7: Updated to newer nightly (lots of ring -> engine renaming).

v8: Moved to earlier in patch series so no longer needs to remove the
quick hack timeline that was being added before.

v9: Updated to another newer nightly (changes to context structure
naming). Also updated commit message to match previous changes.

v10: Removed obsolete fields from timeline structure and a couple of
functions. Corrected some comments and debug prints. [Review comments
from Maarten Lankhorst & Tvrtko Ursulin]

Updated to yet more nightly changes (u64 for fence context).

For: VIZ-5190
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>

4 files changed, 70 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 53d9e3fab489..ca67b455b67f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -831,6 +831,15 @@ struct i915_ctx_hang_stats {
 	bool banned;
 };
 
+struct i915_fence_timeline {
+	char     name[32];
+	u64      fence_context;
+	unsigned next;
+};
+
+int i915_create_fence_timeline(struct i915_gem_context *ctx,
+			       struct intel_engine_cs *ring);
+
 /* This must match up with the value previously used for execbuf2.rsvd1. */
 #define DEFAULT_CONTEXT_HANDLE 0
 
@@ -875,6 +884,7 @@ struct i915_gem_context {
 		u64 lrc_desc;
 		int pin_count;
 		bool initialised;
+		struct i915_fence_timeline fence_timeline;
 	} engine[I915_NUM_ENGINES];
 
 	struct list_head link;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index eae8d7a89d09..ed45586f0972 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2772,6 +2772,42 @@ void i915_gem_request_free(struct kref *req_ref)
 	kmem_cache_free(req->i915->requests, req);
 }
 
+int i915_create_fence_timeline(struct i915_gem_context *ctx,
+			       struct intel_engine_cs *engine)
+{
+	struct i915_fence_timeline *timeline;
+
+	timeline = &ctx->engine[engine->id].fence_timeline;
+
+	WARN_ON(timeline->name[0]);
+
+	timeline->fence_context = fence_context_alloc(1);
+
+	/*
+	 * Start the timeline from seqno 1 as zero is a special value
+	 * that is reserved for invalid sync points.
+	 */
+	timeline->next = 1;
+
+	snprintf(timeline->name, sizeof(timeline->name), "%lld>%s:%d",
+		 timeline->fence_context, engine->name, ctx->user_handle);
+
+	return 0;
+}
+
+unsigned i915_fence_timeline_get_next_seqno(struct i915_fence_timeline *timeline)
+{
+	unsigned seqno;
+
+	seqno = timeline->next;
+
+	/* Reserve zero for invalid */
+	if (++timeline->next == 0)
+		timeline->next = 1;
+
+	return seqno;
+}
+
 static inline int
 __i915_gem_request_alloc(struct intel_engine_cs *engine,
 			 struct i915_gem_context *ctx,
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index a3b11aac23a4..a807c4ab36c3 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -320,6 +320,22 @@ i915_gem_create_context(struct drm_device *dev,
 	if (IS_ERR(ctx))
 		return ctx;
 
+	if (!i915.enable_execlists) {
+		struct intel_engine_cs *engine;
+
+		/* Create a per context timeline for fences */
+		for_each_engine(engine, to_i915(dev)) {
+			int ret = i915_create_fence_timeline(ctx, engine);
+			if (ret) {
+				DRM_ERROR("Fence timeline creation failed for legacy %s: %p/%d\n",
+					  engine->name, ctx, ctx->user_handle);
+				idr_remove(&file_priv->context_idr, ctx->user_handle);
+				i915_gem_context_unreference(ctx);
+				return ERR_PTR(ret);
+			}
+		}
+	}
+
 	if (USES_FULL_PPGTT(dev)) {
 		struct i915_hw_ppgtt *ppgtt = i915_ppgtt_create(dev, file_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4fad8303648e..dedb3f85629b 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2539,6 +2539,14 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 		goto error_ringbuf;
 	}
 
+	/* Create a per context timeline for fences */
+	ret = i915_create_fence_timeline(ctx, engine);
+	if (ret) {
+		DRM_ERROR("Fence timeline creation failed for %s, ctx %p/%d\n",
+			  engine->name, ctx, ctx->user_handle);
+		goto error_ringbuf;
+	}
+
 	ce->ringbuf = ringbuf;
 	ce->state = ctx_obj;
 	ce->initialised = engine->init_context == NULL;