[Intel-gfx] [PATCH v2 3/6] drm/i915: Use ordered seqno write interrupt generation on gen8+ execlists

[Chris Wilson]

Broadwell and later currently use the same unordered command sequence to
update the seqno in the HWS status page and then assert the user
interrupt. We should apply the w/a from legacy (where we do an mmio
read to delay the seqno read after the interrupt), but this is not
enough to enforce coherent seqno visibilty on Skylake. Rather than
search for the proper post-interrupt seqno barrier, use a strongly
ordered command sequence to write the seqno, then assert the user
interrupt from the ring.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/intel_lrc.c        | 50 +++++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 2 files changed, 45 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3ed4ab7f571e..7b5b3180bed9 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1818,7 +1818,6 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
 {
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	struct intel_engine_cs *ring = ringbuf->ring;
-	u32 cmd;
 	int ret;
 
 	/*
@@ -1830,13 +1829,12 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
 	if (ret)
 		return ret;
 
-	cmd = MI_STORE_DWORD_IMM_GEN4;
-	cmd |= MI_GLOBAL_GTT;
-
-	intel_logical_ring_emit(ringbuf, cmd);
 	intel_logical_ring_emit(ringbuf,
+				(MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW);
+	intel_logical_ring_emit(ringbuf,
+				MI_FLUSH_DW_USE_GTT |
 				(ring->status_page.gfx_addr +
-				(I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)));
+				 I915_GEM_HWS_INDEX_ADDR));
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
@@ -1854,6 +1852,45 @@ static int gen8_emit_request(struct drm_i915_gem_request *request)
 	return 0;
 }
 
+static int gen8_emit_request_render(struct drm_i915_gem_request *request)
+{
+	struct intel_ringbuffer *ringbuf = request->ringbuf;
+	struct intel_engine_cs *ring = ringbuf->ring;
+	int ret;
+
+	/*
+	 * Reserve space for 2 NOOPs at the end of each request to be
+	 * used as a workaround for not being allowed to do lite
+	 * restore with HEAD==TAIL (WaIdleLiteRestore).
+	 */
+	ret = intel_logical_ring_begin(request, 8);
+	if (ret)
+		return ret;
+
+	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(5));
+	intel_logical_ring_emit(ringbuf,
+				(PIPE_CONTROL_GLOBAL_GTT_IVB |
+				 PIPE_CONTROL_CS_STALL |
+				 PIPE_CONTROL_QW_WRITE));
+	intel_logical_ring_emit(ringbuf,
+				ring->status_page.gfx_addr +
+				I915_GEM_HWS_INDEX_ADDR);
+	intel_logical_ring_emit(ringbuf, 0);
+	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
+	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
+	intel_logical_ring_advance_and_submit(request);
+
+	/*
+	 * Here we add two extra NOOPs as padding to avoid
+	 * lite restore of a context with HEAD==TAIL.
+	 */
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
+	intel_logical_ring_advance(ringbuf);
+
+	return 0;
+}
+
 static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req)
 {
 	struct render_state so;
@@ -2034,6 +2071,7 @@ static int logical_render_ring_init(struct drm_device *dev)
 	ring->init_context = gen8_init_rcs_context;
 	ring->cleanup = intel_fini_pipe_control;
 	ring->emit_flush = gen8_emit_flush_render;
+	ring->emit_request = gen8_emit_request_render;
 
 	ring->dev = dev;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 8fb02b21e75d..e1797d42054c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -424,6 +424,7 @@ intel_write_status_page(struct intel_engine_cs *ring,
  * The area from dword 0x30 to 0x3ff is available for driver usage.
  */
 #define I915_GEM_HWS_INDEX		0x30
+#define I915_GEM_HWS_INDEX_ADDR (I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 #define I915_GEM_HWS_SCRATCH_INDEX	0x40
 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 
-- 
2.7.0.rc3