drm/i915: Wrap around the tail offset before setting ring->tail

The HW only accepts offsets within ring->size, and fails peculiarly if
the RING_HEAD or RING_TAIL is set to ring->size. Therefore whenever we
set ring->head/ring->tail we want to make sure it is within value (using
intel_ring_wrap()).

v2: Double check execlists as well
v3: Remove redundancy with assert_ring_tail_valid()
v4: Just assert in intel_ring_reset() rather than be over-defensive.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> #v2
Link: https://patchwork.freedesktop.org/patch/msgid/20180611110845.31890-2-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/intel_lrc.c

@@ -1414,6 +1414,7 @@ __execlists_context_pin(struct intel_engine_cs *engine,
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
 		i915_ggtt_offset(ce->ring->vma);
+	GEM_BUG_ON(!intel_ring_offset_valid(ce->ring, ce->ring->head));
 	ce->lrc_reg_state[CTX_RING_HEAD+1] = ce->ring->head;
 
 	ce->state->obj->pin_global++;
@@ -2002,9 +2003,10 @@ static void execlists_reset(struct intel_engine_cs *engine,
 
 	/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
 	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma);
-	regs[CTX_RING_HEAD + 1] = request->postfix;
 
-	request->ring->head = request->postfix;
+	request->ring->head = intel_ring_wrap(request->ring, request->postfix);
+	regs[CTX_RING_HEAD + 1] = request->ring->head;
+
 	intel_ring_update_space(request->ring);
 
 	/* Reset WaIdleLiteRestore:bdw,skl as well */

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -496,6 +496,10 @@ static int init_ring_common(struct intel_engine_cs *engine)
 		DRM_DEBUG_DRIVER("%s initialization failed [head=%08x], fudging\n",
 				 engine->name, I915_READ_HEAD(engine));
 
+	/* Check that the ring offsets point within the ring! */
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
+
 	intel_ring_update_space(ring);
 	I915_WRITE_HEAD(engine, ring->head);
 	I915_WRITE_TAIL(engine, ring->tail);
@@ -1062,6 +1066,8 @@ err:
 
 void intel_ring_reset(struct intel_ring *ring, u32 tail)
 {
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
+
 	ring->tail = tail;
 	ring->head = tail;
 	ring->emit = tail;

drivers/gpu/drm/i915/intel_ringbuffer.h

@@ -805,6 +805,19 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
 	return pos & (ring->size - 1);
 }
 
+static inline bool
+intel_ring_offset_valid(const struct intel_ring *ring,
+			unsigned int pos)
+{
+	if (pos & -ring->size) /* must be strictly within the ring */
+		return false;
+
+	if (!IS_ALIGNED(pos, 8)) /* must be qword aligned */
+		return false;
+
+	return true;
+}
+
 static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
 {
 	/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
@@ -816,12 +829,7 @@ static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
 static inline void
 assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail)
 {
-	/* We could combine these into a single tail operation, but keeping
-	 * them as seperate tests will help identify the cause should one
-	 * ever fire.
-	 */
-	GEM_BUG_ON(!IS_ALIGNED(tail, 8));
-	GEM_BUG_ON(tail >= ring->size);
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
 
 	/*
 	 * "Ring Buffer Use"