static inline int ring_space(struct intel_ring_buffer *ring)
{
- int space = (ring->head & HEAD_ADDR) - (ring->tail + 8);
+ int space = (ring->head & HEAD_ADDR) - (ring->tail + I915_RING_FREE_SPACE);
if (space < 0)
space += ring->size;
return space;
static void render_ring_cleanup(struct intel_ring_buffer *ring)
{
+ struct drm_device *dev = ring->dev;
+
if (!ring->private)
return;
+ if (HAS_BROKEN_CS_TLB(dev))
+ drm_gem_object_unreference(to_gem_object(ring->private));
+
cleanup_pipe_control(ring);
}
return 0;
}
+static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev,
+ u32 seqno)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ return dev_priv->last_seqno < seqno;
+}
+
/**
* intel_ring_sync - sync the waiter to the signaller on seqno
*
if (ret)
return ret;
- intel_ring_emit(waiter,
- dw1 | signaller->semaphore_register[waiter->id]);
- intel_ring_emit(waiter, seqno);
- intel_ring_emit(waiter, 0);
- intel_ring_emit(waiter, MI_NOOP);
+ /* If seqno wrap happened, omit the wait with no-ops */
+ if (likely(!i915_gem_has_seqno_wrapped(waiter->dev, seqno))) {
+ intel_ring_emit(waiter,
+ dw1 |
+ signaller->semaphore_register[waiter->id]);
+ intel_ring_emit(waiter, seqno);
+ intel_ring_emit(waiter, 0);
+ intel_ring_emit(waiter, MI_NOOP);
+ } else {
+ intel_ring_emit(waiter, MI_NOOP);
+ intel_ring_emit(waiter, MI_NOOP);
+ intel_ring_emit(waiter, MI_NOOP);
+ intel_ring_emit(waiter, MI_NOOP);
+ }
intel_ring_advance(waiter);
return 0;
return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
}
+static void
+ring_set_seqno(struct intel_ring_buffer *ring, u32 seqno)
+{
+ intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
+}
+
static u32
pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
{
return pc->cpu_page[0];
}
+static void
+pc_render_set_seqno(struct intel_ring_buffer *ring, u32 seqno)
+{
+ struct pipe_control *pc = ring->private;
+ pc->cpu_page[0] = seqno;
+}
+
static bool
gen5_ring_get_irq(struct intel_ring_buffer *ring)
{
return 0;
}
+/* Just userspace ABI convention to limit the wa batch bo to a resonable size */
+#define I830_BATCH_LIMIT (256*1024)
static int
i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
u32 offset, u32 len,
{
int ret;
- ret = intel_ring_begin(ring, 4);
- if (ret)
- return ret;
+ if (flags & I915_DISPATCH_PINNED) {
+ ret = intel_ring_begin(ring, 4);
+ if (ret)
+ return ret;
- intel_ring_emit(ring, MI_BATCH_BUFFER);
- intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
- intel_ring_emit(ring, offset + len - 8);
- intel_ring_emit(ring, 0);
- intel_ring_advance(ring);
+ intel_ring_emit(ring, MI_BATCH_BUFFER);
+ intel_ring_emit(ring, offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+ intel_ring_emit(ring, offset + len - 8);
+ intel_ring_emit(ring, MI_NOOP);
+ intel_ring_advance(ring);
+ } else {
+ struct drm_i915_gem_object *obj = ring->private;
+ u32 cs_offset = obj->gtt_offset;
+
+ if (len > I830_BATCH_LIMIT)
+ return -ENOSPC;
+
+ ret = intel_ring_begin(ring, 9+3);
+ if (ret)
+ return ret;
+ /* Blit the batch (which has now all relocs applied) to the stable batch
+ * scratch bo area (so that the CS never stumbles over its tlb
+ * invalidation bug) ... */
+ intel_ring_emit(ring, XY_SRC_COPY_BLT_CMD |
+ XY_SRC_COPY_BLT_WRITE_ALPHA |
+ XY_SRC_COPY_BLT_WRITE_RGB);
+ intel_ring_emit(ring, BLT_DEPTH_32 | BLT_ROP_GXCOPY | 4096);
+ intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, (DIV_ROUND_UP(len, 4096) << 16) | 1024);
+ intel_ring_emit(ring, cs_offset);
+ intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, 4096);
+ intel_ring_emit(ring, offset);
+ intel_ring_emit(ring, MI_FLUSH);
+
+ /* ... and execute it. */
+ intel_ring_emit(ring, MI_BATCH_BUFFER);
+ intel_ring_emit(ring, cs_offset | (flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE));
+ intel_ring_emit(ring, cs_offset + len - 8);
+ intel_ring_advance(ring);
+ }
return 0;
}
if (IS_I830(ring->dev) || IS_845G(ring->dev))
ring->effective_size -= 128;
+ intel_ring_init_seqno(ring, dev_priv->last_seqno);
+
return 0;
err_unmap:
if (request->tail == -1)
continue;
- space = request->tail - (ring->tail + 8);
+ space = request->tail - (ring->tail + I915_RING_FREE_SPACE);
if (space < 0)
space += ring->size;
if (space >= n) {
return __intel_ring_begin(ring, num_dwords * sizeof(uint32_t));
}
-int intel_ring_handle_seqno_wrap(struct intel_ring_buffer *ring)
+void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
{
- int ret;
+ struct drm_i915_private *dev_priv = ring->dev->dev_private;
BUG_ON(ring->outstanding_lazy_request);
- if (INTEL_INFO(ring->dev)->gen < 6)
- return 0;
-
- ret = __intel_ring_begin(ring, 6 * sizeof(uint32_t));
- if (ret)
- return ret;
-
- /* Leaving a stale, pre-wrap seqno behind in the mboxes will result in
- * post-wrap semaphore waits completing immediately. Clear them. */
- update_mboxes(ring, ring->signal_mbox[0]);
- update_mboxes(ring, ring->signal_mbox[1]);
- intel_ring_advance(ring);
+ if (INTEL_INFO(ring->dev)->gen >= 6) {
+ I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
+ I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
+ }
- return 0;
+ ring->set_seqno(ring, seqno);
}
void intel_ring_advance(struct intel_ring_buffer *ring)
ring->irq_put = gen6_ring_put_irq;
ring->irq_enable_mask = GT_USER_INTERRUPT;
ring->get_seqno = gen6_ring_get_seqno;
+ ring->set_seqno = ring_set_seqno;
ring->sync_to = gen6_ring_sync;
ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_INVALID;
ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_RV;
ring->add_request = pc_render_add_request;
ring->flush = gen4_render_ring_flush;
ring->get_seqno = pc_render_get_seqno;
+ ring->set_seqno = pc_render_set_seqno;
ring->irq_get = gen5_ring_get_irq;
ring->irq_put = gen5_ring_put_irq;
ring->irq_enable_mask = GT_USER_INTERRUPT | GT_PIPE_NOTIFY;
else
ring->flush = gen4_render_ring_flush;
ring->get_seqno = ring_get_seqno;
+ ring->set_seqno = ring_set_seqno;
if (IS_GEN2(dev)) {
ring->irq_get = i8xx_ring_get_irq;
ring->irq_put = i8xx_ring_put_irq;
ring->init = init_render_ring;
ring->cleanup = render_ring_cleanup;
+ /* Workaround batchbuffer to combat CS tlb bug. */
+ if (HAS_BROKEN_CS_TLB(dev)) {
+ struct drm_i915_gem_object *obj;
+ int ret;
+
+ obj = i915_gem_alloc_object(dev, I830_BATCH_LIMIT);
+ if (obj == NULL) {
+ DRM_ERROR("Failed to allocate batch bo\n");
+ return -ENOMEM;
+ }
+
+ ret = i915_gem_object_pin(obj, 0, true, false);
+ if (ret != 0) {
+ drm_gem_object_unreference(&obj->base);
+ DRM_ERROR("Failed to ping batch bo\n");
+ return ret;
+ }
+
+ ring->private = obj;
+ }
+
return intel_init_ring_buffer(dev, ring);
}
else
ring->flush = gen4_render_ring_flush;
ring->get_seqno = ring_get_seqno;
+ ring->set_seqno = ring_set_seqno;
if (IS_GEN2(dev)) {
ring->irq_get = i8xx_ring_get_irq;
ring->irq_put = i8xx_ring_put_irq;
ring->flush = gen6_ring_flush;
ring->add_request = gen6_add_request;
ring->get_seqno = gen6_ring_get_seqno;
+ ring->set_seqno = ring_set_seqno;
ring->irq_enable_mask = GEN6_BSD_USER_INTERRUPT;
ring->irq_get = gen6_ring_get_irq;
ring->irq_put = gen6_ring_put_irq;
ring->flush = bsd_ring_flush;
ring->add_request = i9xx_add_request;
ring->get_seqno = ring_get_seqno;
+ ring->set_seqno = ring_set_seqno;
if (IS_GEN5(dev)) {
ring->irq_enable_mask = GT_BSD_USER_INTERRUPT;
ring->irq_get = gen5_ring_get_irq;
ring->flush = blt_ring_flush;
ring->add_request = gen6_add_request;
ring->get_seqno = gen6_ring_get_seqno;
+ ring->set_seqno = ring_set_seqno;
ring->irq_enable_mask = GEN6_BLITTER_USER_INTERRUPT;
ring->irq_get = gen6_ring_get_irq;
ring->irq_put = gen6_ring_put_irq;
projects / deliverable / linux.git / blobdiff