drm/i915: Insert a command barrier on BLT/BSD cache flushes

commit f0a1fb10e5f79f5aaf8d7e94b9fa6bf2fa9aeebf upstream.

This looked like an odd regression from

commit ec5cc0f9b019af95e4571a9fa162d94294c8d90b
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Thu Jun 12 10:28:55 2014 +0100

    drm/i915: Restrict GPU boost to the RCS engine

but in reality it undercovered a much older coherency bug. The issue that
boosting the GPU frequency on the BCS ring was masking was that we could
wake the CPU up after completion of a BCS batch and inspect memory prior
to the write cache being fully evicted. In order to serialise the
breadcrumb interrupt (and so ensure that the CPU's view of memory is
coherent) we need to perform a post-sync operation in the MI_FLUSH_DW.

v2: Fix all the MI_FLUSH_DW (bsd plus the duplication in execlists).

Also fix the invalidate_domains mask in gen8_emit_flush() for ring !=
VCS.

Testcase: gpuX-rcs-gpu-read-after-write
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index bafd38b5703eba00e2ca3c2ffb00fea7840b4638..a97b83b78ae7622743ba64d8d4df997a7303708e 100644 (file)
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1106,15 +1106,17 @@ static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
 
        cmd = MI_FLUSH_DW + 1;
 
-       if (ring == &dev_priv->ring[VCS]) {
-               if (invalidate_domains & I915_GEM_GPU_DOMAINS)
-                       cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-                               MI_FLUSH_DW_STORE_INDEX |
-                               MI_FLUSH_DW_OP_STOREDW;
-       } else {
-               if (invalidate_domains & I915_GEM_DOMAIN_RENDER)
-                       cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-                               MI_FLUSH_DW_OP_STOREDW;
+       /* We always require a command barrier so that subsequent
+        * commands, such as breadcrumb interrupts, are strictly ordered
+        * wrt the contents of the write cache being flushed to memory
+        * (and thus being coherent from the CPU).
+        */
+       cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
+       if (invalidate_domains & I915_GEM_GPU_DOMAINS) {
+               cmd |= MI_INVALIDATE_TLB;
+               if (ring == &dev_priv->ring[VCS])
+                       cmd |= MI_INVALIDATE_BSD;
        }
 
        intel_logical_ring_emit(ringbuf, cmd);

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index ae17e77dc08d330278fe9d2ca4ee01cdd8292557..9f10b771319f20997cd43d79261fe87d4e6e97dd 100644 (file)
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2139,6 +2139,14 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
        cmd = MI_FLUSH_DW;
        if (INTEL_INFO(ring->dev)->gen >= 8)
                cmd += 1;
+
+       /* We always require a command barrier so that subsequent
+        * commands, such as breadcrumb interrupts, are strictly ordered
+        * wrt the contents of the write cache being flushed to memory
+        * (and thus being coherent from the CPU).
+        */
+       cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
        /*
         * Bspec vol 1c.5 - video engine command streamer:
         * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2146,8 +2154,8 @@ static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
         * Post-Sync Operation field is a value of 1h or 3h."
         */
        if (invalidate & I915_GEM_GPU_DOMAINS)
-               cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD |
-                       MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+               cmd |= MI_INVALIDATE_TLB | MI_INVALIDATE_BSD;
+
        intel_ring_emit(ring, cmd);
        intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
        if (INTEL_INFO(ring->dev)->gen >= 8) {
@@ -2242,6 +2250,14 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
        cmd = MI_FLUSH_DW;
        if (INTEL_INFO(ring->dev)->gen >= 8)
                cmd += 1;
+
+       /* We always require a command barrier so that subsequent
+        * commands, such as breadcrumb interrupts, are strictly ordered
+        * wrt the contents of the write cache being flushed to memory
+        * (and thus being coherent from the CPU).
+        */
+       cmd |= MI_FLUSH_DW_STORE_INDEX | MI_FLUSH_DW_OP_STOREDW;
+
        /*
         * Bspec vol 1c.3 - blitter engine command streamer:
         * "If ENABLED, all TLBs will be invalidated once the flush
@@ -2249,8 +2265,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
         * Post-Sync Operation field is a value of 1h or 3h."
         */
        if (invalidate & I915_GEM_DOMAIN_RENDER)
-               cmd |= MI_INVALIDATE_TLB | MI_FLUSH_DW_STORE_INDEX |
-                       MI_FLUSH_DW_OP_STOREDW;
+               cmd |= MI_INVALIDATE_TLB;
        intel_ring_emit(ring, cmd);
        intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
        if (INTEL_INFO(ring->dev)->gen >= 8) {