ret = i915_gem_render_state_init(req);
if (ret)
- DRM_ERROR("init render state: %d\n", ret);
+ return ret;
- return ret;
+ return 0;
}
static int wa_add(struct drm_i915_private *dev_priv,
#define WA_WRITE(addr, val) WA_REG(addr, 0xffffffff, val)
+static int wa_ring_whitelist_reg(struct intel_engine_cs *ring, i915_reg_t reg)
+{
+ struct drm_i915_private *dev_priv = ring->dev->dev_private;
+ struct i915_workarounds *wa = &dev_priv->workarounds;
+ const uint32_t index = wa->hw_whitelist_count[ring->id];
+
+ if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS))
+ return -EINVAL;
+
+ WA_WRITE(RING_FORCE_TO_NONPRIV(ring->mmio_base, index),
+ i915_mmio_reg_offset(reg));
+ wa->hw_whitelist_count[ring->id]++;
+
+ return 0;
+}
+
static int gen8_init_workarounds(struct intel_engine_cs *ring)
{
struct drm_device *dev = ring->dev;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t tmp;
+ int ret;
/* WaEnableLbsSlaRetryTimerDecrement:skl */
I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
/* WaForceContextSaveRestoreNonCoherent:skl,bxt */
tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT;
- if (IS_SKL_REVID(dev, SKL_REVID_F0, SKL_REVID_F0) ||
+ if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) ||
IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER))
tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
/* WaDisableSTUnitPowerOptimization:skl,bxt */
WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
+ /* WaOCLCoherentLineFlush:skl,bxt */
+ I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
+ GEN8_LQSC_FLUSH_COHERENT_LINES));
+
+ /* WaEnablePreemptionGranularityControlByUMD:skl,bxt */
+ ret= wa_ring_whitelist_reg(ring, GEN8_CS_CHICKEN1);
+ if (ret)
+ return ret;
+
+ /* WaAllowUMDToModifyHDCChicken1:skl,bxt */
+ ret = wa_ring_whitelist_reg(ring, GEN8_HDC_CHICKEN1);
+ if (ret)
+ return ret;
+
return 0;
}
if (ret)
return ret;
+ /*
+ * Actual WA is to disable percontext preemption granularity control
+ * until D0 which is the default case so this is equivalent to
+ * !WaDisablePerCtxtPreemptionGranularityControl:skl
+ */
+ if (IS_SKL_REVID(dev, SKL_REVID_E0, REVID_FOREVER)) {
+ I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
+ _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
+ }
+
if (IS_SKL_REVID(dev, 0, SKL_REVID_D0)) {
/* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
I915_WRITE(FF_SLICE_CS_CHICKEN2,
WA_SET_BIT_MASKED(HIZ_CHICKEN,
BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
- if (IS_SKL_REVID(dev, 0, SKL_REVID_F0)) {
+ /* This is tied to WaForceContextSaveRestoreNonCoherent */
+ if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) {
/*
*Use Force Non-Coherent whenever executing a 3D context. This
* is a workaround for a possible hang in the unlikely event
GEN7_HALF_SLICE_CHICKEN1,
GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
+ /* WaDisableLSQCROPERFforOCL:skl */
+ ret = wa_ring_whitelist_reg(ring, GEN8_L3SQCREG4);
+ if (ret)
+ return ret;
+
return skl_tune_iz_hashing(ring);
}
GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
}
+ /* WaDisableObjectLevelPreemptionForTrifanOrPolygon:bxt */
+ /* WaDisableObjectLevelPreemptionForInstancedDraw:bxt */
+ /* WaDisableObjectLevelPreemtionForInstanceId:bxt */
+ /* WaDisableLSQCROPERFforOCL:bxt */
+ if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+ ret = wa_ring_whitelist_reg(ring, GEN9_CS_DEBUG_MODE1);
+ if (ret)
+ return ret;
+
+ ret = wa_ring_whitelist_reg(ring, GEN8_L3SQCREG4);
+ if (ret)
+ return ret;
+ }
+
return 0;
}
WARN_ON(ring->id != RCS);
dev_priv->workarounds.count = 0;
+ dev_priv->workarounds.hw_whitelist_count[RCS] = 0;
if (IS_BROADWELL(dev))
return bdw_init_workarounds(ring);
offset = cs_offset;
}
- ret = intel_ring_begin(req, 4);
+ ret = intel_ring_begin(req, 2);
if (ret)
return ret;
- intel_ring_emit(ring, MI_BATCH_BUFFER);
+ intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
intel_ring_emit(ring, offset | (dispatch_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);
return 0;
return 0;
}
+static void cleanup_phys_status_page(struct intel_engine_cs *ring)
+{
+ struct drm_i915_private *dev_priv = to_i915(ring->dev);
+
+ if (!dev_priv->status_page_dmah)
+ return;
+
+ drm_pci_free(ring->dev, dev_priv->status_page_dmah);
+ ring->status_page.page_addr = NULL;
+}
+
static void cleanup_status_page(struct intel_engine_cs *ring)
{
struct drm_i915_gem_object *obj;
static int init_status_page(struct intel_engine_cs *ring)
{
- struct drm_i915_gem_object *obj;
+ struct drm_i915_gem_object *obj = ring->status_page.obj;
- if ((obj = ring->status_page.obj) == NULL) {
+ if (obj == NULL) {
unsigned flags;
int ret;
else
iounmap(ringbuf->virtual_start);
ringbuf->virtual_start = NULL;
+ ringbuf->vma = NULL;
i915_gem_object_ggtt_unpin(ringbuf->obj);
}
return ret;
}
+ /* Access through the GTT requires the device to be awake. */
+ assert_rpm_wakelock_held(dev_priv);
+
ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base +
i915_gem_obj_ggtt_offset(obj), ringbuf->size);
if (ringbuf->virtual_start == NULL) {
}
}
+ ringbuf->vma = i915_gem_obj_to_ggtt(obj);
+
return 0;
}
if (ret)
goto error;
} else {
- BUG_ON(ring->id != RCS);
+ WARN_ON(ring->id != RCS);
ret = init_phys_status_page(ring);
if (ret)
goto error;
if (ring->cleanup)
ring->cleanup(ring);
- cleanup_status_page(ring);
+ if (I915_NEED_GFX_HWS(ring->dev)) {
+ cleanup_status_page(ring);
+ } else {
+ WARN_ON(ring->id != RCS);
+ cleanup_phys_status_page(ring);
+ }
i915_cmd_parser_fini_ring(ring);
i915_gem_batch_pool_fini(&ring->batch_pool);
if (unlikely(total_bytes > remain_usable)) {
/*
* The base request will fit but the reserved space
- * falls off the end. So only need to to wait for the
- * reserved size after flushing out the remainder.
+ * falls off the end. So don't need an immediate wrap
+ * and only need to effectively wait for the reserved
+ * size space from the start of ringbuffer.
*/
wait_bytes = remain_actual + ringbuf->reserved_size;
- need_wrap = true;
} else if (total_bytes > ringbuf->space) {
/* No wrapping required, just waiting. */
wait_bytes = total_bytes;
ring->name = "render ring";
ring->id = RCS;
+ ring->exec_id = I915_EXEC_RENDER;
ring->mmio_base = RENDER_RING_BASE;
if (INTEL_INFO(dev)->gen >= 8) {
ring->name = "bsd ring";
ring->id = VCS;
+ ring->exec_id = I915_EXEC_BSD;
ring->write_tail = ring_write_tail;
if (INTEL_INFO(dev)->gen >= 6) {
ring->name = "bsd2 ring";
ring->id = VCS2;
+ ring->exec_id = I915_EXEC_BSD;
ring->write_tail = ring_write_tail;
ring->mmio_base = GEN8_BSD2_RING_BASE;
ring->name = "blitter ring";
ring->id = BCS;
+ ring->exec_id = I915_EXEC_BLT;
ring->mmio_base = BLT_RING_BASE;
ring->write_tail = ring_write_tail;
ring->name = "video enhancement ring";
ring->id = VECS;
+ ring->exec_id = I915_EXEC_VEBOX;
ring->mmio_base = VEBOX_RING_BASE;
ring->write_tail = ring_write_tail;
projects / linux-2.6-microblaze.git / blobdiff