return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring);
}
-void __intel_ring_advance(struct intel_engine_cs *ring)
+static void __intel_ring_advance(struct intel_engine_cs *ring)
{
struct intel_ringbuffer *ringbuf = ring->buffer;
ringbuf->tail &= ringbuf->size - 1;
return ret;
}
-static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
{
int ret, i;
+ struct intel_engine_cs *ring = req->ring;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
struct i915_workarounds *w = &dev_priv->workarounds;
return 0;
ring->gpu_caches_dirty = true;
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(req);
if (ret)
return ret;
intel_ring_advance(ring);
ring->gpu_caches_dirty = true;
- ret = intel_ring_flush_all_caches(ring);
+ ret = intel_ring_flush_all_caches(req);
if (ret)
return ret;
return 0;
}
-static int intel_rcs_ctx_init(struct intel_engine_cs *ring,
- struct intel_context *ctx)
+static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
{
int ret;
- ret = intel_ring_workarounds_emit(ring, ctx);
+ ret = intel_ring_workarounds_emit(req);
if (ret != 0)
return ret;
- ret = i915_gem_render_state_init(ring);
+ ret = i915_gem_render_state_init(req);
if (ret)
DRM_ERROR("init render state: %d\n", ret);
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
+
+ /* WaDisableAsyncFlipPerfMode:bdw */
+ WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
/* WaDisablePartialInstShootdown:bdw */
/* WaDisableThreadStallDopClockGating:bdw (pre-production) */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING);
+
+ /* WaDisableAsyncFlipPerfMode:chv */
+ WA_SET_BIT_MASKED(MI_MODE, ASYNC_FLIP_PERF_DISABLE);
+
/* WaDisablePartialInstShootdown:chv */
/* WaDisableThreadStallDopClockGating:chv */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
GEN6_WIZ_HASHING_MASK,
GEN6_WIZ_HASHING_16x4);
- if (INTEL_REVID(dev) == SKL_REVID_C0 ||
- INTEL_REVID(dev) == SKL_REVID_D0)
- /* WaBarrierPerformanceFixDisable:skl */
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- HDC_FENCE_DEST_SLM_DISABLE |
- HDC_BARRIER_PERFORMANCE_DISABLE);
-
return 0;
}
{
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ uint32_t tmp;
- /* WaDisablePartialInstShootdown:skl */
+ /* WaDisablePartialInstShootdown:skl,bxt */
WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
- /* Syncing dependencies between camera and graphics */
+ /* Syncing dependencies between camera and graphics:skl,bxt */
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
- if (INTEL_REVID(dev) == SKL_REVID_A0 ||
- INTEL_REVID(dev) == SKL_REVID_B0) {
- /* WaDisableDgMirrorFixInHalfSliceChicken5:skl */
+ if ((IS_SKYLAKE(dev) && (INTEL_REVID(dev) == SKL_REVID_A0 ||
+ INTEL_REVID(dev) == SKL_REVID_B0)) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0)) {
+ /* WaDisableDgMirrorFixInHalfSliceChicken5:skl,bxt */
WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
GEN9_DG_MIRROR_FIX_ENABLE);
}
- if (IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) {
- /* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl */
+ if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0)) {
+ /* WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken:skl,bxt */
WA_SET_BIT_MASKED(GEN7_COMMON_SLICE_CHICKEN1,
GEN9_RHWO_OPTIMIZATION_DISABLE);
WA_SET_BIT_MASKED(GEN9_SLICE_COMMON_ECO_CHICKEN0,
DISABLE_PIXEL_MASK_CAMMING);
}
- if (INTEL_REVID(dev) >= SKL_REVID_C0) {
- /* WaEnableYV12BugFixInHalfSliceChicken7:skl */
+ if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) >= SKL_REVID_C0) ||
+ IS_BROXTON(dev)) {
+ /* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt */
WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
GEN9_ENABLE_YV12_BUGFIX);
}
- if (INTEL_REVID(dev) <= SKL_REVID_D0) {
- /*
- *Use Force Non-Coherent whenever executing a 3D context. This
- * is a workaround for a possible hang in the unlikely event
- * a TLB invalidation occurs during a PSD flush.
- */
- /* WaForceEnableNonCoherent:skl */
- WA_SET_BIT_MASKED(HDC_CHICKEN0,
- HDC_FORCE_NON_COHERENT);
- }
-
- /* Wa4x4STCOptimizationDisable:skl */
+ /* Wa4x4STCOptimizationDisable:skl,bxt */
WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
- /* WaDisablePartialResolveInVc:skl */
+ /* WaDisablePartialResolveInVc:skl,bxt */
WA_SET_BIT_MASKED(CACHE_MODE_1, GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE);
- /* WaCcsTlbPrefetchDisable:skl */
+ /* WaCcsTlbPrefetchDisable:skl,bxt */
WA_CLR_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN5,
GEN9_CCS_TLB_PREFETCH_ENABLE);
+ /* WaDisableMaskBasedCammingInRCC:skl,bxt */
+ if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) == SKL_REVID_C0) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) < BXT_REVID_B0))
+ WA_SET_BIT_MASKED(SLICE_ECO_CHICKEN0,
+ PIXEL_MASK_CAMMING_DISABLE);
+
+ /* WaForceContextSaveRestoreNonCoherent:skl,bxt */
+ tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT;
+ if ((IS_SKYLAKE(dev) && INTEL_REVID(dev) == SKL_REVID_F0) ||
+ (IS_BROXTON(dev) && INTEL_REVID(dev) >= BXT_REVID_B0))
+ tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
+ WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
+
return 0;
}
WA_SET_BIT_MASKED(HIZ_CHICKEN,
BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
+ if (INTEL_REVID(dev) <= SKL_REVID_D0) {
+ /*
+ *Use Force Non-Coherent whenever executing a 3D context. This
+ * is a workaround for a possible hang in the unlikely event
+ * a TLB invalidation occurs during a PSD flush.
+ */
+ /* WaForceEnableNonCoherent:skl */
+ WA_SET_BIT_MASKED(HDC_CHICKEN0,
+ HDC_FORCE_NON_COHERENT);
+ }
+
+ if (INTEL_REVID(dev) == SKL_REVID_C0 ||
+ INTEL_REVID(dev) == SKL_REVID_D0)
+ /* WaBarrierPerformanceFixDisable:skl */
+ WA_SET_BIT_MASKED(HDC_CHICKEN0,
+ HDC_FENCE_DEST_SLM_DISABLE |
+ HDC_BARRIER_PERFORMANCE_DISABLE);
+
return skl_tune_iz_hashing(ring);
}
+static int bxt_init_workarounds(struct intel_engine_cs *ring)
+{
+ struct drm_device *dev = ring->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ gen9_init_workarounds(ring);
+
+ /* WaDisableThreadStallDopClockGating:bxt */
+ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+ STALL_DOP_GATING_DISABLE);
+
+ /* WaDisableSbeCacheDispatchPortSharing:bxt */
+ if (INTEL_REVID(dev) <= BXT_REVID_B0) {
+ WA_SET_BIT_MASKED(
+ GEN7_HALF_SLICE_CHICKEN1,
+ GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+ }
+
+ return 0;
+}
+
int init_workarounds_ring(struct intel_engine_cs *ring)
{
struct drm_device *dev = ring->dev;
if (IS_SKYLAKE(dev))
return skl_init_workarounds(ring);
- else if (IS_GEN9(dev))
- return gen9_init_workarounds(ring);
+
+ if (IS_BROXTON(dev))
+ return bxt_init_workarounds(ring);
return 0;
}
* to use MI_WAIT_FOR_EVENT within the CS. It should already be
* programmed to '1' on all products.
*
- * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
+ * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
*/
- if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 9)
+ if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
/* Required for the hardware to program scanline values for waiting */
_MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
}
- if (INTEL_INFO(dev)->gen >= 6)
+ if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 8)
I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
if (HAS_L3_DPF(dev))
INIT_LIST_HEAD(&ring->active_list);
INIT_LIST_HEAD(&ring->request_list);
INIT_LIST_HEAD(&ring->execlist_queue);
+ i915_gem_batch_pool_init(dev, &ring->batch_pool);
ringbuf->size = 32 * PAGE_SIZE;
ringbuf->ring = ring;
memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno));
cleanup_status_page(ring);
i915_cmd_parser_fini_ring(ring);
+ i915_gem_batch_pool_fini(&ring->batch_pool);
kfree(ringbuf);
ring->buffer = NULL;
}
-static int intel_ring_wait_request(struct intel_engine_cs *ring, int n)
+static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
{
struct intel_ringbuffer *ringbuf = ring->buffer;
struct drm_i915_gem_request *request;
+ unsigned space;
int ret;
+ /* The whole point of reserving space is to not wait! */
+ WARN_ON(ringbuf->reserved_in_use);
+
if (intel_ring_space(ringbuf) >= n)
return 0;
list_for_each_entry(request, &ring->request_list, list) {
- if (__intel_ring_space(request->postfix, ringbuf->tail,
- ringbuf->size) >= n) {
+ space = __intel_ring_space(request->postfix, ringbuf->tail,
+ ringbuf->size);
+ if (space >= n)
break;
- }
}
- if (&request->list == &ring->request_list)
+ if (WARN_ON(&request->list == &ring->request_list))
return -ENOSPC;
ret = i915_wait_request(request);
if (ret)
return ret;
- i915_gem_retire_requests_ring(ring);
-
+ ringbuf->space = space;
return 0;
}
-static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
-{
- struct drm_device *dev = ring->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_ringbuffer *ringbuf = ring->buffer;
- unsigned long end;
- int ret;
-
- ret = intel_ring_wait_request(ring, n);
- if (ret != -ENOSPC)
- return ret;
-
- /* force the tail write in case we have been skipping them */
- __intel_ring_advance(ring);
-
- /* With GEM the hangcheck timer should kick us out of the loop,
- * leaving it early runs the risk of corrupting GEM state (due
- * to running on almost untested codepaths). But on resume
- * timers don't work yet, so prevent a complete hang in that
- * case by choosing an insanely large timeout. */
- end = jiffies + 60 * HZ;
-
- ret = 0;
- trace_i915_ring_wait_begin(ring);
- do {
- if (intel_ring_space(ringbuf) >= n)
- break;
- ringbuf->head = I915_READ_HEAD(ring);
- if (intel_ring_space(ringbuf) >= n)
- break;
-
- msleep(1);
-
- if (dev_priv->mm.interruptible && signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
-
- ret = i915_gem_check_wedge(&dev_priv->gpu_error,
- dev_priv->mm.interruptible);
- if (ret)
- break;
-
- if (time_after(jiffies, end)) {
- ret = -EBUSY;
- break;
- }
- } while (1);
- trace_i915_ring_wait_end(ring);
- return ret;
-}
-
static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
{
uint32_t __iomem *virt;
struct intel_ringbuffer *ringbuf = ring->buffer;
int rem = ringbuf->size - ringbuf->tail;
+ /* Can't wrap if space has already been reserved! */
+ WARN_ON(ringbuf->reserved_in_use);
+
if (ringbuf->space < rem) {
int ret = ring_wait_for_space(ring, rem);
if (ret)
int intel_ring_idle(struct intel_engine_cs *ring)
{
struct drm_i915_gem_request *req;
- int ret;
/* We need to add any requests required to flush the objects and ring */
- if (ring->outstanding_lazy_request) {
- ret = i915_add_request(ring);
- if (ret)
- return ret;
- }
+ WARN_ON(ring->outstanding_lazy_request);
+ if (ring->outstanding_lazy_request)
+ i915_add_request(ring->outstanding_lazy_request);
/* Wait upon the last request to be completed */
if (list_empty(&ring->request_list))
return 0;
req = list_entry(ring->request_list.prev,
- struct drm_i915_gem_request,
- list);
+ struct drm_i915_gem_request,
+ list);
- return i915_wait_request(req);
+ /* Make sure we do not trigger any retires */
+ return __i915_wait_request(req,
+ atomic_read(&to_i915(ring->dev)->gpu_error.reset_counter),
+ to_i915(ring->dev)->mm.interruptible,
+ NULL, NULL);
}
-static int
-intel_ring_alloc_request(struct intel_engine_cs *ring)
+int intel_ring_alloc_request_extras(struct drm_i915_gem_request *request)
{
- int ret;
- struct drm_i915_gem_request *request;
- struct drm_i915_private *dev_private = ring->dev->dev_private;
+ request->ringbuf = request->ring->buffer;
+ return 0;
+}
- if (ring->outstanding_lazy_request)
- return 0;
+void intel_ring_reserved_space_reserve(struct intel_ringbuffer *ringbuf, int size)
+{
+ /* NB: Until request management is fully tidied up and the OLR is
+ * removed, there are too many ways for get false hits on this
+ * anti-recursion check! */
+ /*WARN_ON(ringbuf->reserved_size);*/
+ WARN_ON(ringbuf->reserved_in_use);
- request = kzalloc(sizeof(*request), GFP_KERNEL);
- if (request == NULL)
- return -ENOMEM;
+ ringbuf->reserved_size = size;
- kref_init(&request->ref);
- request->ring = ring;
- request->ringbuf = ring->buffer;
- request->uniq = dev_private->request_uniq++;
+ /*
+ * Really need to call _begin() here but that currently leads to
+ * recursion problems! This will be fixed later but for now just
+ * return and hope for the best. Note that there is only a real
+ * problem if the create of the request never actually calls _begin()
+ * but if they are not submitting any work then why did they create
+ * the request in the first place?
+ */
+}
- ret = i915_gem_get_seqno(ring->dev, &request->seqno);
- if (ret) {
- kfree(request);
- return ret;
- }
+void intel_ring_reserved_space_cancel(struct intel_ringbuffer *ringbuf)
+{
+ WARN_ON(ringbuf->reserved_in_use);
- ring->outstanding_lazy_request = request;
- return 0;
+ ringbuf->reserved_size = 0;
+ ringbuf->reserved_in_use = false;
}
-static int __intel_ring_prepare(struct intel_engine_cs *ring,
- int bytes)
+void intel_ring_reserved_space_use(struct intel_ringbuffer *ringbuf)
+{
+ WARN_ON(ringbuf->reserved_in_use);
+
+ ringbuf->reserved_in_use = true;
+ ringbuf->reserved_tail = ringbuf->tail;
+}
+
+void intel_ring_reserved_space_end(struct intel_ringbuffer *ringbuf)
+{
+ WARN_ON(!ringbuf->reserved_in_use);
+ WARN(ringbuf->tail > ringbuf->reserved_tail + ringbuf->reserved_size,
+ "request reserved size too small: %d vs %d!\n",
+ ringbuf->tail - ringbuf->reserved_tail, ringbuf->reserved_size);
+
+ ringbuf->reserved_size = 0;
+ ringbuf->reserved_in_use = false;
+}
+
+static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes)
{
struct intel_ringbuffer *ringbuf = ring->buffer;
int ret;
+ /*
+ * Add on the reserved size to the request to make sure that after
+ * the intended commands have been emitted, there is guaranteed to
+ * still be enough free space to send them to the hardware.
+ */
+ if (!ringbuf->reserved_in_use)
+ bytes += ringbuf->reserved_size;
+
if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
ret = intel_wrap_ring_buffer(ring);
if (unlikely(ret))
return ret;
+
+ if(ringbuf->reserved_size) {
+ uint32_t size = ringbuf->reserved_size;
+
+ intel_ring_reserved_space_cancel(ringbuf);
+ intel_ring_reserved_space_reserve(ringbuf, size);
+ }
}
if (unlikely(ringbuf->space < bytes)) {
int intel_ring_begin(struct intel_engine_cs *ring,
int num_dwords)
{
+ struct drm_i915_gem_request *req;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
int ret;
return ret;
/* Preallocate the olr before touching the ring */
- ret = intel_ring_alloc_request(ring);
+ ret = i915_gem_request_alloc(ring, ring->default_context, &req);
if (ret)
return ret;
}
int
-intel_ring_flush_all_caches(struct intel_engine_cs *ring)
+intel_ring_flush_all_caches(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
int ret;
if (!ring->gpu_caches_dirty)
}
int
-intel_ring_invalidate_all_caches(struct intel_engine_cs *ring)
+intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req)
{
+ struct intel_engine_cs *ring = req->ring;
uint32_t flush_domains;
int ret;