[PATCH 61/98] drm/i915: Treat ringbuffer writes as write to normal memory

[Chris Wilson]

Ringbuffers are now being written to either through LLC or WC paths, so
treating them as simply iomem is no longer adequate. However, for the
older !llc hardware, the hardware is documentated as treating the TAIL
register update as serialising, so we can relax the barriers when filling
the rings (but even if it were not, it is still an uncached register write
and so serialising anyway.).

For simplicity, let's ignore the iomem annotation.

v2: Remove iomem from ringbuffer->virtual_address

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala at linux.intel.com>
---
 drivers/gpu/drm/i915/intel_lrc.c        |  7 +------
 drivers/gpu/drm/i915/intel_lrc.h        |  6 +++---
 drivers/gpu/drm/i915/intel_ringbuffer.c |  7 +------
 drivers/gpu/drm/i915/intel_ringbuffer.h | 22 ++++++++++++++--------
 4 files changed, 19 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 197c2c94bbd9..6926c64f24cb 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -797,13 +797,8 @@ intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request)
 
 static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
 {
-	uint32_t __iomem *virt;
 	int rem = ringbuf->size - ringbuf->tail;
-
-	virt = ringbuf->virtual_start + ringbuf->tail;
-	rem /= 4;
-	while (rem--)
-		iowrite32(MI_NOOP, virt++);
+	memset(ringbuf->virtual_start + ringbuf->tail, 0, rem);
 
 	ringbuf->tail = 0;
 	intel_ring_update_space(ringbuf);
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 4b1c896b5019..791e4a7eaa2d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -74,8 +74,9 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req);
  */
 static inline void intel_logical_ring_advance(struct intel_ringbuffer *ringbuf)
 {
-	ringbuf->tail &= ringbuf->size - 1;
+	__intel_ringbuffer_advance(ringbuf);
 }
+
 /**
  * intel_logical_ring_emit() - write a DWORD to the ringbuffer.
  * @ringbuf: Ringbuffer to write to.
@@ -84,8 +85,7 @@ static inline void intel_logical_ring_advance(struct intel_ringbuffer *ringbuf)
 static inline void intel_logical_ring_emit(struct intel_ringbuffer *ringbuf,
 					   u32 data)
 {
-	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
-	ringbuf->tail += 4;
+	__intel_ringbuffer_emit(ringbuf, data);
 }
 static inline void intel_logical_ring_emit_reg(struct intel_ringbuffer *ringbuf,
 					       i915_reg_t reg)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 0684c273c2d2..7b0a19cf036a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2125,13 +2125,8 @@ static int ring_wait_for_space(struct intel_engine_cs *engine, int n)
 
 static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf)
 {
-	uint32_t __iomem *virt;
 	int rem = ringbuf->size - ringbuf->tail;
-
-	virt = ringbuf->virtual_start + ringbuf->tail;
-	rem /= 4;
-	while (rem--)
-		iowrite32(MI_NOOP, virt++);
+	memset(ringbuf->virtual_start + ringbuf->tail, 0, rem);
 
 	ringbuf->tail = 0;
 	intel_ring_update_space(ringbuf);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 25773a1b2842..7ebb97aaed3c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -96,7 +96,7 @@ struct intel_ring_hangcheck {
 
 struct intel_ringbuffer {
 	struct drm_i915_gem_object *obj;
-	void __iomem *virtual_start;
+	void *virtual_start;
 	struct i915_vma *vma;
 
 	struct intel_engine_cs *engine;
@@ -465,12 +465,19 @@ int intel_ring_alloc_request_extras(struct drm_i915_gem_request *request);
 
 int __must_check intel_ring_begin(struct drm_i915_gem_request *req, int n);
 int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
-static inline void intel_ring_emit(struct intel_engine_cs *engine,
-				   u32 data)
+static inline void __intel_ringbuffer_emit(struct intel_ringbuffer *rb,
+					   u32 data)
 {
-	struct intel_ringbuffer *ringbuf = engine->buffer;
-	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
-	ringbuf->tail += 4;
+	*(uint32_t *)(rb->virtual_start + rb->tail) = data;
+	rb->tail += 4;
+}
+static inline void __intel_ringbuffer_advance(struct intel_ringbuffer *rb)
+{
+	rb->tail &= rb->size - 1;
+}
+static inline void intel_ring_emit(struct intel_engine_cs *engine, u32 data)
+{
+	__intel_ringbuffer_emit(engine->buffer, data);
 }
 static inline void intel_ring_emit_reg(struct intel_engine_cs *engine,
 				       i915_reg_t reg)
@@ -479,8 +486,7 @@ static inline void intel_ring_emit_reg(struct intel_engine_cs *engine,
 }
 static inline void intel_ring_advance(struct intel_engine_cs *engine)
 {
-	struct intel_ringbuffer *ringbuf = engine->buffer;
-	ringbuf->tail &= ringbuf->size - 1;
+	__intel_ringbuffer_advance(engine->buffer);
 }
 int __intel_ring_space(int head, int tail, int size);
 void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
-- 
2.8.1