drm/i915: Workaround to avoid lite restore with HEAD==TAIL

WaIdleLiteRestore is an execlists-only workaround, and requires the driver
to ensure that any context always has HEAD!=TAIL when attempting lite
restore.

Add two extra MI_NOOP instructions at the end of each request, but keep
the requests tail pointing before the MI_NOOPs. We may not need to
executed them, and this is why request->tail is sampled before adding
these extra instructions.

If we submit a context to the ELSP which has previously been submitted,
move the tail pointer past the MI_NOOPs. This ensures HEAD!=TAIL.

v2: Move overallocation to gen8_emit_request, and added note about
sampling request->tail in commit message (Chris).

v3: Remove redundant request->tail assignment in __i915_add_request, in
lrc mode this is already set in execlists_context_queue.
Do not add wa implementation details inside gem (Chris).

v4: Apply the wa whenever the req has been resubmitted and update
comment (Chris).

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

2 files changed, 36 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d07c0b1fb498..53394f998a1f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2377,10 +2377,11 @@ int __i915_add_request(struct intel_engine_cs *ring,
                 ret = ring->add_request(ring);
                 if (ret)
                         return ret;
+
+                request->tail = intel_ring_get_tail(ringbuf);
         }
 
         request->head = request_start;
-        request->tail = intel_ring_get_tail(ringbuf);
 
         /* Whilst this request exists, batch_obj will be on the
          * active_list, and so will hold the active reference. Only when this
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index fcb074bd55dc..09df74b8e917 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -393,6 +393,26 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring)
                 }
         }
 
+        if (IS_GEN8(ring->dev) || IS_GEN9(ring->dev)) {
+                /*
+                 * WaIdleLiteRestore: make sure we never cause a lite
+                 * restore with HEAD==TAIL
+                 */
+                if (req0 && req0->elsp_submitted) {
+                        /*
+                         * Apply the wa NOOPS to prevent ring:HEAD == req:TAIL
+                         * as we resubmit the request. See gen8_emit_request()
+                         * for where we prepare the padding after the end of the
+                         * request.
+                         */
+                        struct intel_ringbuffer *ringbuf;
+
+                        ringbuf = req0->ctx->engine[ring->id].ringbuf;
+                        req0->tail += 8;
+                        req0->tail &= ringbuf->size - 1;
+                }
+        }
+
         WARN_ON(req1 && req1->elsp_submitted);
 
         execlists_submit_contexts(ring, req0->ctx, req0->tail,
@@ -1315,7 +1335,12 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
         u32 cmd;
         int ret;
 
-        ret = intel_logical_ring_begin(ringbuf, request->ctx, 6);
+        /*
+         * 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(ringbuf, request->ctx, 8);
         if (ret)
                 return ret;
 
@@ -1333,6 +1358,14 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf,
         intel_logical_ring_emit(ringbuf, MI_NOOP);
         intel_logical_ring_advance_and_submit(ringbuf, request->ctx, 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;
 }