[PATCH 45/58] drm/i915/gt: Use indices for writing into relative timelines

[Chris Wilson]

Relative timelines are relative to either the global or per-process
HWSP, and so we can replace the absolute addressing with store-index
variants for position invariance.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 98 +++++++++++++++++-------
 drivers/gpu/drm/i915/gt/intel_timeline.h | 12 +++
 2 files changed, 82 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 29c9930e47ec..5d4cdb3baf6a 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -505,7 +505,19 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
 
 static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	unsigned int flags = MI_FLUSH_DW_OP_STOREDW;
+	u32 offset = hwsp_offset(rq);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= MI_FLUSH_DW_STORE_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		offset |= MI_FLUSH_DW_USE_GTT;
+
+	return __gen8_emit_flush_dw(cs, rq->fence.seqno, offset, flags);
 }
 
 u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
@@ -515,6 +527,18 @@ u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 
 u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	unsigned int flags = PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_CS_STALL;
+	u32 offset = hwsp_offset(rq);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
 	cs = gen8_emit_pipe_control(cs,
 				    PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 				    PIPE_CONTROL_DEPTH_CACHE_FLUSH |
@@ -522,26 +546,33 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 				    0);
 
 	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
-	cs = gen8_emit_ggtt_write_rcs(cs,
-				      rq->fence.seqno,
-				      hwsp_offset(rq),
-				      PIPE_CONTROL_FLUSH_ENABLE |
-				      PIPE_CONTROL_CS_STALL);
+	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
 
 	return gen8_emit_fini_breadcrumb_tail(rq, cs);
 }
 
 u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
-	cs = gen8_emit_ggtt_write_rcs(cs,
-				      rq->fence.seqno,
-				      hwsp_offset(rq),
-				      PIPE_CONTROL_CS_STALL |
-				      PIPE_CONTROL_TILE_CACHE_FLUSH |
-				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
-				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
-				      PIPE_CONTROL_DC_FLUSH_ENABLE |
-				      PIPE_CONTROL_FLUSH_ENABLE);
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = hwsp_offset(rq);
+	unsigned int flags;
+
+	flags = (PIPE_CONTROL_CS_STALL |
+		 PIPE_CONTROL_TILE_CACHE_FLUSH |
+		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+		 PIPE_CONTROL_DC_FLUSH_ENABLE |
+		 PIPE_CONTROL_FLUSH_ENABLE);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
 
 	return gen8_emit_fini_breadcrumb_tail(rq, cs);
 }
@@ -604,19 +635,30 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
 
 u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 {
-	cs = gen12_emit_ggtt_write_rcs(cs,
-				       rq->fence.seqno,
-				       hwsp_offset(rq),
-				       PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
-				       PIPE_CONTROL_CS_STALL |
-				       PIPE_CONTROL_TILE_CACHE_FLUSH |
-				       PIPE_CONTROL_FLUSH_L3 |
-				       PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
-				       PIPE_CONTROL_DEPTH_CACHE_FLUSH |
-				       /* Wa_1409600907:tgl */
-				       PIPE_CONTROL_DEPTH_STALL |
-				       PIPE_CONTROL_DC_FLUSH_ENABLE |
-				       PIPE_CONTROL_FLUSH_ENABLE);
+	struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+	u32 offset = hwsp_offset(rq);
+	unsigned int flags;
+
+	flags = (PIPE_CONTROL_CS_STALL |
+		 PIPE_CONTROL_TILE_CACHE_FLUSH |
+		 PIPE_CONTROL_FLUSH_L3 |
+		 PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+		 PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+		 /* Wa_1409600907:tgl */
+		 PIPE_CONTROL_DEPTH_STALL |
+		 PIPE_CONTROL_DC_FLUSH_ENABLE |
+		 PIPE_CONTROL_FLUSH_ENABLE);
+
+	if (intel_timeline_is_relative(tl)) {
+		offset = offset_in_page(offset);
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+	}
+	GEM_BUG_ON(offset & 7);
+	if (!intel_timeline_in_context(tl))
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+	cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset,
+				   PIPE_CONTROL0_HDC_PIPELINE_FLUSH, flags);
 
 	return gen12_emit_fini_breadcrumb_tail(rq, cs);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index dbe3aa07065e..0e7a3ef4597c 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -67,6 +67,18 @@ intel_timeline_has_initial_breadcrumb(const struct intel_timeline *tl)
 	return tl->mode == INTEL_TIMELINE_ABSOLUTE;
 }
 
+static inline bool
+intel_timeline_is_relative(const struct intel_timeline *tl)
+{
+	return tl->mode != INTEL_TIMELINE_ABSOLUTE;
+}
+
+static inline bool
+intel_timeline_in_context(const struct intel_timeline *tl)
+{
+	return tl->mode == INTEL_TIMELINE_RELATIVE_CONTEXT;
+}
+
 static inline int __intel_timeline_sync_set(struct intel_timeline *tl,
 					    u64 context, u32 seqno)
 {
-- 
2.20.1