drm/i915/bdw: GEN-specific logical ring emit flush

Same as the legacy-style ring->flush.

v2: The BSD invalidate bit still exists in GEN8! Add it for the VCS
rings (but still consolidate the blt and bsd ring flushes into one).
This was noticed by Brad Volkin.

v3: The command for BSD and for other rings is slightly different:
get it exactly the same as in gen6_ring_flush + gen6_bsd_ring_flush

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 94f8b4087642550b14300b28fead691f7b48bd6b..a88fa6e9360b2e9ba6f7f74f97e6c6ddea4997e4 100644 (file)
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -340,6 +340,86 @@ static int gen8_init_render_ring(struct intel_engine_cs *ring)
        return ret;
 }
 
+static int gen8_emit_flush(struct intel_ringbuffer *ringbuf,
+                          u32 invalidate_domains,
+                          u32 unused)
+{
+       struct intel_engine_cs *ring = ringbuf->ring;
+       struct drm_device *dev = ring->dev;
+       struct drm_i915_private *dev_priv = dev->dev_private;
+       uint32_t cmd;
+       int ret;
+
+       ret = intel_logical_ring_begin(ringbuf, 4);
+       if (ret)
+               return ret;
+
+       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;
+       }
+
+       intel_logical_ring_emit(ringbuf, cmd);
+       intel_logical_ring_emit(ringbuf,
+                               I915_GEM_HWS_SCRATCH_ADDR |
+                               MI_FLUSH_DW_USE_GTT);
+       intel_logical_ring_emit(ringbuf, 0); /* upper addr */
+       intel_logical_ring_emit(ringbuf, 0); /* value */
+       intel_logical_ring_advance(ringbuf);
+
+       return 0;
+}
+
+static int gen8_emit_flush_render(struct intel_ringbuffer *ringbuf,
+                                 u32 invalidate_domains,
+                                 u32 flush_domains)
+{
+       struct intel_engine_cs *ring = ringbuf->ring;
+       u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
+       u32 flags = 0;
+       int ret;
+
+       flags |= PIPE_CONTROL_CS_STALL;
+
+       if (flush_domains) {
+               flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+               flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+       }
+
+       if (invalidate_domains) {
+               flags |= PIPE_CONTROL_TLB_INVALIDATE;
+               flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+               flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+               flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+               flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+               flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+               flags |= PIPE_CONTROL_QW_WRITE;
+               flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+       }
+
+       ret = intel_logical_ring_begin(ringbuf, 6);
+       if (ret)
+               return ret;
+
+       intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
+       intel_logical_ring_emit(ringbuf, flags);
+       intel_logical_ring_emit(ringbuf, scratch_addr);
+       intel_logical_ring_emit(ringbuf, 0);
+       intel_logical_ring_emit(ringbuf, 0);
+       intel_logical_ring_emit(ringbuf, 0);
+       intel_logical_ring_advance(ringbuf);
+
+       return 0;
+}
+
 static u32 gen8_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
 {
        return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
@@ -451,6 +531,7 @@ static int logical_render_ring_init(struct drm_device *dev)
        ring->get_seqno = gen8_get_seqno;
        ring->set_seqno = gen8_set_seqno;
        ring->emit_request = gen8_emit_request;
+       ring->emit_flush = gen8_emit_flush_render;
 
        return logical_ring_init(dev, ring);
 }
@@ -470,6 +551,7 @@ static int logical_bsd_ring_init(struct drm_device *dev)
        ring->get_seqno = gen8_get_seqno;
        ring->set_seqno = gen8_set_seqno;
        ring->emit_request = gen8_emit_request;
+       ring->emit_flush = gen8_emit_flush;
 
        return logical_ring_init(dev, ring);
 }
@@ -489,6 +571,7 @@ static int logical_bsd2_ring_init(struct drm_device *dev)
        ring->get_seqno = gen8_get_seqno;
        ring->set_seqno = gen8_set_seqno;
        ring->emit_request = gen8_emit_request;
+       ring->emit_flush = gen8_emit_flush;
 
        return logical_ring_init(dev, ring);
 }
@@ -508,6 +591,7 @@ static int logical_blt_ring_init(struct drm_device *dev)
        ring->get_seqno = gen8_get_seqno;
        ring->set_seqno = gen8_set_seqno;
        ring->emit_request = gen8_emit_request;
+       ring->emit_flush = gen8_emit_flush;
 
        return logical_ring_init(dev, ring);
 }
@@ -527,6 +611,7 @@ static int logical_vebox_ring_init(struct drm_device *dev)
        ring->get_seqno = gen8_get_seqno;
        ring->set_seqno = gen8_set_seqno;
        ring->emit_request = gen8_emit_request;
+       ring->emit_flush = gen8_emit_flush;
 
        return logical_ring_init(dev, ring);
 }

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 0bfa018fab200ec81925b340285f2a7950120ac2..4236014c1cda12ee9a342736d3be1a8c051e6db5 100644 (file)
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -33,13 +33,6 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
-/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
- * but keeps the logic simple. Indeed, the whole purpose of this macro is just
- * to give some inclination as to some of the magic values used in the various
- * workarounds!
- */
-#define CACHELINE_BYTES 64
-
 bool
 intel_ring_initialized(struct intel_engine_cs *ring)
 {

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 467885159a80426da4ee03b67901f9806b9b4444..e497837c7724ae40150461c594f3d39f59524273 100644 (file)
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -5,6 +5,13 @@
 
 #define I915_CMD_HASH_ORDER 9
 
+/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
+ * but keeps the logic simple. Indeed, the whole purpose of this macro is just
+ * to give some inclination as to some of the magic values used in the various
+ * workarounds!
+ */
+#define CACHELINE_BYTES 64
+
 /*
  * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
  * Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use"
@@ -218,6 +225,9 @@ struct  intel_engine_cs {
 
        /* Execlists */
        int             (*emit_request)(struct intel_ringbuffer *ringbuf);
+       int             (*emit_flush)(struct intel_ringbuffer *ringbuf,
+                                     u32 invalidate_domains,
+                                     u32 flush_domains);
 
        /**
         * List of objects currently involved in rendering from the