summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorChris Wilson <chris@chris-wilson.co.uk>2018-11-05 09:43:05 +0000
committerJoonas Lahtinen <joonas.lahtinen@linux.intel.com>2018-11-12 17:07:12 +0200
commitfb5bbae9b1333d44023713946fdd28db0cd85751 (patch)
treec1a1fdc3c6d7c886a43d704cadd1b685a714c34d
parentccda4af0f4b92f7b4c308d3acc262f4a7e3affad (diff)
drm/i915/ringbuffer: Delay after EMIT_INVALIDATE for gen4/gen5
Exercising the gpu reloc path strenuously revealed an issue where the updated relocations (from MI_STORE_DWORD_IMM) were not being observed upon execution. After some experiments with adding pipecontrols (a lot of pipecontrols (32) as gen4/5 do not have a bit to wait on earlier pipe controls or even the current on), it was discovered that we merely needed to delay the EMIT_INVALIDATE by several flushes. It is important to note that it is the EMIT_INVALIDATE as opposed to the EMIT_FLUSH that needs the delay as opposed to what one might first expect -- that the delay is required for the TLB invalidation to take effect (one presumes to purge any CS buffers) as opposed to a delay after flushing to ensure the writes have landed before triggering invalidation. Testcase: igt/gem_tiled_fence_blits Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: stable@vger.kernel.org Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20181105094305.5767-1-chris@chris-wilson.co.uk (cherry picked from commit 55f99bf2a9c331838c981694bc872cd1ec4070b2) Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
-rw-r--r--drivers/gpu/drm/i915/intel_ringbuffer.c38
1 files changed, 36 insertions, 2 deletions
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d0ef50bf930a..187bb0ceb4ac 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -91,6 +91,7 @@ static int
gen4_render_ring_flush(struct i915_request *rq, u32 mode)
{
u32 cmd, *cs;
+ int i;
/*
* read/write caches:
@@ -127,12 +128,45 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode)
cmd |= MI_INVALIDATE_ISP;
}
- cs = intel_ring_begin(rq, 2);
+ i = 2;
+ if (mode & EMIT_INVALIDATE)
+ i += 20;
+
+ cs = intel_ring_begin(rq, i);
if (IS_ERR(cs))
return PTR_ERR(cs);
*cs++ = cmd;
- *cs++ = MI_NOOP;
+
+ /*
+ * A random delay to let the CS invalidate take effect? Without this
+ * delay, the GPU relocation path fails as the CS does not see
+ * the updated contents. Just as important, if we apply the flushes
+ * to the EMIT_FLUSH branch (i.e. immediately after the relocation
+ * write and before the invalidate on the next batch), the relocations
+ * still fail. This implies that is a delay following invalidation
+ * that is required to reset the caches as opposed to a delay to
+ * ensure the memory is written.
+ */
+ if (mode & EMIT_INVALIDATE) {
+ *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE;
+ *cs++ = i915_ggtt_offset(rq->engine->scratch) |
+ PIPE_CONTROL_GLOBAL_GTT;
+ *cs++ = 0;
+ *cs++ = 0;
+
+ for (i = 0; i < 12; i++)
+ *cs++ = MI_FLUSH;
+
+ *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE;
+ *cs++ = i915_ggtt_offset(rq->engine->scratch) |
+ PIPE_CONTROL_GLOBAL_GTT;
+ *cs++ = 0;
+ *cs++ = 0;
+ }
+
+ *cs++ = cmd;
+
intel_ring_advance(rq, cs);
return 0;