[Intel-gfx] [PATCH v5] drm/i915/vlv: Added a rendering specific Hw WA 'WaTlbInvalidateStoreDataBefore'

[sourab.gupta at intel.com]

From: Akash Goel <akash.goel at intel.com>

Added a new rendering specific Workaround 'WaTlbInvalidateStoreDataBefore'.
This workaround has to be applied before doing TLB Invalidation.
In this WA, before pipecontrol with TLB invalidate set, need to add 2 MI
Store data commands.
Without this, hardware cannot guarantee the command after the PIPE_CONTROL
with TLB inv will not use the old TLB values.

v2: Modified the WA comment (Ville)

v3: Added the vlv identifier with WA name (Damien)

v4: Reworked based on Chris' comments (WA moved to gen7 ring flush func,
sending 6 dwords instead of 8) (Chris)

v5: Enhancing the scope of WA to gen6, gen7. Having a common WA func being
called from gen6, gen7 flush functions. (Ville)

Signed-off-by: Sourab Gupta <sourab.gupta at intel.com>
Signed-off-by: Akash Goel <akash.goel at intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 52 +++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 87d1a2d..ef4ca3dd 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -208,6 +208,30 @@ intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
 }
 
 static int
+gen6_tlb_invalidate_wa(struct intel_ring_buffer *ring)
+{
+	/*
+	 * WaTlbInvalidateStoreDataBefore:gen6,gen7
+	 * This workaround has to be applied before doing TLB invalidation.
+	 * Before pipecontrol with TLB invalidate set, need 2 store
+	 * data commands (such as MI_STORE_DATA_IMM or MI_STORE_DATA_INDEX)
+	 * Without this, hardware cannot guarantee the command after the
+	 * PIPE_CONTROL with TLB inv will not use the old TLB values.
+	 */
+	int i, ret;
+	ret = intel_ring_begin(ring, 3 * 2);
+	if (ret)
+		return ret;
+	for (i = 0; i < 2; i++) {
+		intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
+		intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR);
+		intel_ring_emit(ring, 0);
+	}
+	intel_ring_advance(ring);
+	return 0;
+}
+
+static int
 gen6_render_ring_flush(struct intel_ring_buffer *ring,
                          u32 invalidate_domains, u32 flush_domains)
 {
@@ -215,6 +239,13 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 	u32 scratch_addr = ring->scratch.gtt_offset + 128;
 	int ret;
 
+	/* Apply WaTlbInvalidateStoreDataBefore workaround */
+	if (invalidate_domains) {
+		ret = gen6_tlb_invalidate_wa(ring);
+		if (ret)
+			return ret;
+	}
+
 	/* Force SNB workarounds for PIPE_CONTROL flushes */
 	ret = intel_emit_post_sync_nonzero_flush(ring);
 	if (ret)
@@ -309,6 +340,13 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 	u32 scratch_addr = ring->scratch.gtt_offset + 128;
 	int ret;
 
+	/* Apply WaTlbInvalidateStoreDataBefore workaround */
+	if (invalidate_domains) {
+		ret = gen6_tlb_invalidate_wa(ring);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * Ensure that any following seqno writes only happen when the render
 	 * cache is indeed flushed.
@@ -1733,6 +1771,13 @@ static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring,
 	uint32_t cmd;
 	int ret;
 
+	/* Apply WaTlbInvalidateStoreDataBefore workaround */
+	if (invalidate) {
+		ret = gen6_tlb_invalidate_wa(ring);
+		if (ret)
+			return ret;
+	}
+
 	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		return ret;
@@ -1837,6 +1882,13 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
 	uint32_t cmd;
 	int ret;
 
+	/* Apply WaTlbInvalidateStoreDataBefore workaround */
+	if (invalidate) {
+		ret = gen6_tlb_invalidate_wa(ring);
+		if (ret)
+			return ret;
+	}
+
 	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		return ret;
-- 
1.8.5.1