[Intel-gfx] [PATCH 094/190] drm/i915: Remove early l3-remap

[Chris Wilson]

Since we do the l3-remap on context switch, and proceed to do a context
switch immediately after manually doing the l3-remap, we can remove the
redundant manual call.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_drv.h         |  1 -
 drivers/gpu/drm/i915/i915_gem.c         | 35 +--------------------------------
 drivers/gpu/drm/i915/i915_gem_context.c | 30 +++++++++++++++++++++++++++-
 3 files changed, 30 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f5f457920944..7dc3eed71eb3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2827,7 +2827,6 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_init(struct drm_device *dev);
 int i915_gem_init_rings(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 989222eb107b..379913221ab1 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3951,34 +3951,6 @@ err:
 	return ret;
 }
 
-int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
-{
-	struct drm_i915_private *dev_priv = req->i915;
-	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
-	int i, ret;
-
-	if (!HAS_L3_DPF(dev_priv) || !remap_info)
-		return 0;
-
-	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
-	if (ret)
-		return ret;
-
-	/*
-	 * Note: We do not worry about the concurrent register cacheline hang
-	 * here because no other code should access these registers other than
-	 * at initialization time.
-	 */
-	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
-		intel_ring_emit(req->ring, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit_reg(req->ring, GEN7_L3LOG(slice, i));
-		intel_ring_emit(req->ring, remap_info[i]);
-	}
-	intel_ring_advance(req->ring);
-
-	return ret;
-}
-
 void i915_gem_init_swizzling(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4083,7 +4055,7 @@ i915_gem_init_hw(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring;
-	int ret, i, j;
+	int ret, i;
 
 	if (INTEL_INFO(dev)->gen < 6 && !intel_enable_gtt())
 		return -EIO;
@@ -4158,11 +4130,6 @@ i915_gem_init_hw(struct drm_device *dev)
 			goto out;
 		}
 
-		if (ring->id == RCS) {
-			for (j = 0; j < NUM_L3_SLICES(dev); j++)
-				i915_gem_l3_remap(req, j);
-		}
-
 		ret = i915_ppgtt_init_ring(req);
 		if (ret && ret != -EIO) {
 			DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index e0ecfdfb0c8c..15e2e2abd72d 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -665,6 +665,34 @@ needs_pd_load_post(struct intel_engine_cs *ring, struct intel_context *to,
 	return false;
 }
 
+static int remap_l3(struct drm_i915_gem_request *req, int slice)
+{
+	struct drm_i915_private *dev_priv = req->i915;
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
+	int i, ret;
+
+	if (!HAS_L3_DPF(dev_priv) || !remap_info)
+		return 0;
+
+	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
+	if (ret)
+		return ret;
+
+	/*
+	 * Note: We do not worry about the concurrent register cacheline hang
+	 * here because no other code should access these registers other than
+	 * at initialization time.
+	 */
+	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
+		intel_ring_emit(req->ring, MI_LOAD_REGISTER_IMM(1));
+		intel_ring_emit_reg(req->ring, GEN7_L3LOG(slice, i));
+		intel_ring_emit(req->ring, remap_info[i]);
+	}
+	intel_ring_advance(req->ring);
+
+	return 0;
+}
+
 static int do_switch(struct drm_i915_gem_request *req)
 {
 	struct intel_context *to = req->ctx;
@@ -764,7 +792,7 @@ static int do_switch(struct drm_i915_gem_request *req)
 		if (!(to->remap_slice & (1<<i)))
 			continue;
 
-		ret = i915_gem_l3_remap(req, i);
+		ret = remap_l3(req, i);
 		/* If it failed, try again next round */
 		if (ret)
 			DRM_DEBUG_DRIVER("L3 remapping failed\n");
-- 
2.7.0.rc3