[Intel-gfx] [PATCH 3/6] drm/i915: Implement LRI based FBC tracking
ville.syrjala at linux.intel.com
ville.syrjala at linux.intel.com
Wed Nov 6 16:39:02 CET 2013
From: Ville Syrjälä <ville.syrjala at linux.intel.com>
As per the SNB and HSW PM guides, we should enable FBC render/blitter
tracking only during batches targetting the front buffer.
On SNB we must also update the FBC render tracking address whenever it
changes. And since the register in question is stored in the context,
we need to make sure we reload it with correct data after context
switches.
On IVB/HSW we use the render nuke mechanism, so no render tracking
address updates are needed. Hoever on the blitter side we need to
enable the blitter tracking like on SNB, and in addition we need
to issue the cache clean messages, which we already did.
Signed-off-by: Ville Syrjälä <ville.syrjala at linux.intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 7 ++++
drivers/gpu/drm/i915/i915_gem_execbuffer.c | 31 ++++++++++++++++
drivers/gpu/drm/i915/intel_display.c | 28 +++++++++++++--
drivers/gpu/drm/i915/intel_drv.h | 3 ++
drivers/gpu/drm/i915/intel_pm.c | 2 --
drivers/gpu/drm/i915/intel_ringbuffer.c | 58 +++++++++++++++++++++++++++++-
drivers/gpu/drm/i915/intel_ringbuffer.h | 2 ++
7 files changed, 126 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 72a3df3..d438ea1 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -404,6 +404,13 @@ mi_set_context(struct intel_ring_buffer *ring,
intel_ring_advance(ring);
+ /*
+ * FBC RT address is stored in the context, so we may have just
+ * restored it to an old value. Make sure we emit a new LRI
+ * to update the address.
+ */
+ ring->fbc_address_dirty = true;
+
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 885d595..a8f8634 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -886,6 +886,35 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
}
static void
+i915_gem_execbuffer_mark_fbc_dirty(struct intel_ring_buffer *ring,
+ struct list_head *vmas)
+{
+ struct i915_vma *vma;
+ struct drm_i915_gem_object *fbc_obj = NULL;
+ u32 fbc_address = -1;
+
+ list_for_each_entry(vma, vmas, exec_list) {
+ struct drm_i915_gem_object *obj = vma->obj;
+
+ if (obj->base.pending_write_domain == 0)
+ continue;
+
+ if (obj->pin_count) /* check for potential scanout */
+ intel_mark_fbc_dirty(obj, ring, &fbc_obj);
+ }
+
+ if (fbc_obj)
+ fbc_address = i915_gem_obj_ggtt_offset(fbc_obj);
+
+ /* need to nuke/cache_clean on IVB+? */
+ ring->fbc_dirty = fbc_obj != NULL;
+
+ /* need to update FBC tracking? */
+ ring->fbc_address_dirty = fbc_address != ring->fbc_address;
+ ring->fbc_address = fbc_address;
+}
+
+static void
i915_gem_execbuffer_move_to_active(struct list_head *vmas,
struct intel_ring_buffer *ring)
{
@@ -1150,6 +1179,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
if (flags & I915_DISPATCH_SECURE && !batch_obj->has_global_gtt_mapping)
i915_gem_gtt_bind_object(batch_obj, batch_obj->cache_level);
+ i915_gem_execbuffer_mark_fbc_dirty(ring, &eb->vmas);
+
ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->vmas);
if (ret)
goto err;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 12cf362..49c40aa 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8064,6 +8064,32 @@ void intel_mark_idle(struct drm_device *dev)
gen6_rps_idle(dev->dev_private);
}
+void intel_mark_fbc_dirty(struct drm_i915_gem_object *obj,
+ struct intel_ring_buffer *ring,
+ struct drm_i915_gem_object **fbc_obj)
+{
+ struct drm_device *dev = obj->base.dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct drm_crtc *crtc;
+
+ if (!i915_powersave)
+ return;
+
+ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+ if (!crtc->fb)
+ continue;
+
+ if (dev_priv->fbc.plane != to_intel_crtc(crtc)->plane)
+ continue;
+
+ if (to_intel_framebuffer(crtc->fb)->obj != obj)
+ continue;
+
+ WARN_ON(*fbc_obj && *fbc_obj != obj);
+ *fbc_obj = obj;
+ }
+}
+
void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
struct intel_ring_buffer *ring)
{
@@ -8081,8 +8107,6 @@ void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
continue;
intel_increase_pllclock(crtc);
- if (ring && intel_fbc_enabled(dev))
- ring->fbc_dirty = true;
}
}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 6d701e7..5841f60 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -614,6 +614,9 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
/* intel_display.c */
int intel_pch_rawclk(struct drm_device *dev);
void intel_mark_busy(struct drm_device *dev);
+void intel_mark_fbc_dirty(struct drm_i915_gem_object *obj,
+ struct intel_ring_buffer *ring,
+ struct drm_i915_gem_object **fbc_obj);
void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
struct intel_ring_buffer *ring);
void intel_mark_idle(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index dc306e1..bfec348 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -193,8 +193,6 @@ static void sandybridge_blit_fbc_update(struct drm_device *dev)
/* Make sure blitter notifies FBC of writes */
gen6_gt_force_wake_get(dev_priv);
blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD);
- blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY <<
- GEN6_BLITTER_LOCK_SHIFT;
I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY;
I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 4649bf5..43f7eab 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -207,6 +207,57 @@ intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
return 0;
}
+static int gen6_blt_fbc_tracking(struct intel_ring_buffer *ring)
+{
+ int ret;
+
+ if (!ring->fbc_address_dirty)
+ return 0;
+
+ ret = intel_ring_begin(ring, 4);
+ if (ret)
+ return ret;
+
+ intel_ring_emit(ring, MI_NOOP);
+ intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+ intel_ring_emit(ring, GEN6_BLITTER_ECOSKPD);
+ if (ring->fbc_address != -1)
+ intel_ring_emit(ring, _MASKED_BIT_ENABLE(GEN6_BLITTER_FBC_NOTIFY));
+ else
+ intel_ring_emit(ring, _MASKED_BIT_DISABLE(GEN6_BLITTER_FBC_NOTIFY));
+ intel_ring_advance(ring);
+
+ ring->fbc_address_dirty = true;
+
+ return 0;
+}
+
+static int gen6_render_fbc_tracking(struct intel_ring_buffer *ring)
+{
+ int ret;
+
+ if (!ring->fbc_address_dirty)
+ return 0;
+
+ ret = intel_ring_begin(ring, 4);
+ if (ret)
+ return ret;
+
+ intel_ring_emit(ring, MI_NOOP);
+ intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+ intel_ring_emit(ring, ILK_FBC_RT_BASE);
+ if (ring->fbc_address != -1)
+ intel_ring_emit(ring, ring->fbc_address |
+ SNB_FBC_FRONT_BUFFER | ILK_FBC_RT_VALID);
+ else
+ intel_ring_emit(ring, 0);
+ intel_ring_advance(ring);
+
+ ring->fbc_address_dirty = true;
+
+ return 0;
+}
+
static int
gen6_render_ring_flush(struct intel_ring_buffer *ring,
u32 invalidate_domains, u32 flush_domains)
@@ -256,6 +307,9 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
intel_ring_emit(ring, 0);
intel_ring_advance(ring);
+ if (invalidate_domains)
+ return gen6_render_fbc_tracking(ring);
+
return 0;
}
@@ -1839,7 +1893,9 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
}
intel_ring_advance(ring);
- if (IS_GEN7(dev) && !invalidate && flush)
+ if (invalidate)
+ return gen6_blt_fbc_tracking(ring);
+ else if (flush && IS_GEN7(dev))
return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
return 0;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 71a73f4..1e5bbd6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -143,8 +143,10 @@ struct intel_ring_buffer {
*/
struct drm_i915_gem_request *preallocated_lazy_request;
u32 outstanding_lazy_seqno;
+ u32 fbc_address;
bool gpu_caches_dirty;
bool fbc_dirty;
+ bool fbc_address_dirty;
wait_queue_head_t irq_queue;
--
1.8.1.5
More information about the Intel-gfx
mailing list