int __intel_ring_space(int head, int tail, int size)
{
- int space = head - (tail + I915_RING_FREE_SPACE);
- if (space < 0)
+ int space = head - tail;
+ if (space <= 0)
space += size;
- return space;
+ return space - I915_RING_FREE_SPACE;
+}
+
+void intel_ring_update_space(struct intel_ringbuffer *ringbuf)
+{
+ if (ringbuf->last_retired_head != -1) {
+ ringbuf->head = ringbuf->last_retired_head;
+ ringbuf->last_retired_head = -1;
+ }
+
+ ringbuf->space = __intel_ring_space(ringbuf->head & HEAD_ADDR,
+ ringbuf->tail, ringbuf->size);
}
int intel_ring_space(struct intel_ringbuffer *ringbuf)
{
- return __intel_ring_space(ringbuf->head & HEAD_ADDR,
- ringbuf->tail, ringbuf->size);
+ intel_ring_update_space(ringbuf);
+ return ringbuf->space;
}
bool intel_ring_stopped(struct intel_engine_cs *ring)
goto out;
}
- if (!drm_core_check_feature(ring->dev, DRIVER_MODESET))
- i915_kernel_lost_context(ring->dev);
- else {
- ringbuf->head = I915_READ_HEAD(ring);
- ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
- ringbuf->space = intel_ring_space(ringbuf);
- ringbuf->last_retired_head = -1;
- }
+ ringbuf->last_retired_head = -1;
+ ringbuf->head = I915_READ_HEAD(ring);
+ ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
+ intel_ring_update_space(ringbuf);
memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
return ret;
}
-static inline void intel_ring_emit_wa(struct intel_engine_cs *ring,
- u32 addr, u32 value)
+static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
+ struct intel_context *ctx)
{
+ int ret, i;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct i915_workarounds *w = &dev_priv->workarounds;
- if (WARN_ON(dev_priv->num_wa_regs >= I915_MAX_WA_REGS))
- return;
+ if (WARN_ON(w->count == 0))
+ return 0;
- intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
- intel_ring_emit(ring, addr);
- intel_ring_emit(ring, value);
+ ring->gpu_caches_dirty = true;
+ ret = intel_ring_flush_all_caches(ring);
+ if (ret)
+ return ret;
- dev_priv->intel_wa_regs[dev_priv->num_wa_regs].addr = addr;
- dev_priv->intel_wa_regs[dev_priv->num_wa_regs].mask = value & 0xFFFF;
- /* value is updated with the status of remaining bits of this
- * register when it is read from debugfs file
- */
- dev_priv->intel_wa_regs[dev_priv->num_wa_regs].value = value;
- dev_priv->num_wa_regs++;
+ ret = intel_ring_begin(ring, (w->count * 2 + 2));
+ if (ret)
+ return ret;
+
+ intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(w->count));
+ for (i = 0; i < w->count; i++) {
+ intel_ring_emit(ring, w->reg[i].addr);
+ intel_ring_emit(ring, w->reg[i].value);
+ }
+ intel_ring_emit(ring, MI_NOOP);
+
+ intel_ring_advance(ring);
+
+ ring->gpu_caches_dirty = true;
+ ret = intel_ring_flush_all_caches(ring);
+ if (ret)
+ return ret;
+
+ DRM_DEBUG_DRIVER("Number of Workarounds emitted: %d\n", w->count);
- return;
+ return 0;
}
+static int wa_add(struct drm_i915_private *dev_priv,
+ const u32 addr, const u32 val, const u32 mask)
+{
+ const u32 idx = dev_priv->workarounds.count;
+
+ if (WARN_ON(idx >= I915_MAX_WA_REGS))
+ return -ENOSPC;
+
+ dev_priv->workarounds.reg[idx].addr = addr;
+ dev_priv->workarounds.reg[idx].value = val;
+ dev_priv->workarounds.reg[idx].mask = mask;
+
+ dev_priv->workarounds.count++;
+
+ return 0;
+}
+
+#define WA_REG(addr, val, mask) { \
+ const int r = wa_add(dev_priv, (addr), (val), (mask)); \
+ if (r) \
+ return r; \
+ }
+
+#define WA_SET_BIT_MASKED(addr, mask) \
+ WA_REG(addr, _MASKED_BIT_ENABLE(mask), (mask) & 0xffff)
+
+#define WA_CLR_BIT_MASKED(addr, mask) \
+ WA_REG(addr, _MASKED_BIT_DISABLE(mask), (mask) & 0xffff)
+
+#define WA_SET_BIT(addr, mask) WA_REG(addr, I915_READ(addr) | (mask), mask)
+#define WA_CLR_BIT(addr, mask) WA_REG(addr, I915_READ(addr) & ~(mask), mask)
+
+#define WA_WRITE(addr, val) WA_REG(addr, val, 0xffffffff)
+
static int bdw_init_workarounds(struct intel_engine_cs *ring)
{
- int ret;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- /*
- * workarounds applied in this fn are part of register state context,
- * they need to be re-initialized followed by gpu reset, suspend/resume,
- * module reload.
- */
- dev_priv->num_wa_regs = 0;
- memset(dev_priv->intel_wa_regs, 0, sizeof(dev_priv->intel_wa_regs));
-
- /*
- * update the number of dwords required based on the
- * actual number of workarounds applied
- */
- ret = intel_ring_begin(ring, 18);
- if (ret)
- return ret;
-
/* WaDisablePartialInstShootdown:bdw */
- /* WaDisableThreadStallDopClockGating:bdw */
- /* FIXME: Unclear whether we really need this on production bdw. */
- intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
- _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE
- | STALL_DOP_GATING_DISABLE));
+ /* WaDisableThreadStallDopClockGating:bdw (pre-production) */
+ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+ PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
+ STALL_DOP_GATING_DISABLE);
- /* WaDisableDopClockGating:bdw May not be needed for production */
- intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
- _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+ /* WaDisableDopClockGating:bdw */
+ WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
+ DOP_CLOCK_GATING_DISABLE);
- intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
- _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
+ WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
+ GEN8_SAMPLER_POWER_BYPASS_DIS);
/* Use Force Non-Coherent whenever executing a 3D context. This is a
* workaround for for a possible hang in the unlikely event a TLB
* invalidation occurs during a PSD flush.
*/
- intel_ring_emit_wa(ring, HDC_CHICKEN0,
- _MASKED_BIT_ENABLE(HDC_FORCE_NON_COHERENT));
+ /* WaDisableFenceDestinationToSLM:bdw (GT3 pre-production) */
+ WA_SET_BIT_MASKED(HDC_CHICKEN0,
+ HDC_FORCE_NON_COHERENT |
+ (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
/* Wa4x4STCOptimizationDisable:bdw */
- intel_ring_emit_wa(ring, CACHE_MODE_1,
- _MASKED_BIT_ENABLE(GEN8_4x4_STC_OPTIMIZATION_DISABLE));
+ WA_SET_BIT_MASKED(CACHE_MODE_1,
+ GEN8_4x4_STC_OPTIMIZATION_DISABLE);
/*
* BSpec recommends 8x4 when MSAA is used,
* disable bit, which we don't touch here, but it's good
* to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
*/
- intel_ring_emit_wa(ring, GEN7_GT_MODE,
- GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
-
- intel_ring_advance(ring);
-
- DRM_DEBUG_DRIVER("Number of Workarounds applied: %d\n",
- dev_priv->num_wa_regs);
+ WA_SET_BIT_MASKED(GEN7_GT_MODE,
+ GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
return 0;
}
static int chv_init_workarounds(struct intel_engine_cs *ring)
{
- int ret;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- /*
- * workarounds applied in this fn are part of register state context,
- * they need to be re-initialized followed by gpu reset, suspend/resume,
- * module reload.
+ /* WaDisablePartialInstShootdown:chv */
+ /* WaDisableThreadStallDopClockGating:chv */
+ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
+ PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
+ STALL_DOP_GATING_DISABLE);
+
+ /* 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.
*/
- dev_priv->num_wa_regs = 0;
- memset(dev_priv->intel_wa_regs, 0, sizeof(dev_priv->intel_wa_regs));
+ /* WaForceEnableNonCoherent:chv */
+ /* WaHdcDisableFetchWhenMasked:chv */
+ WA_SET_BIT_MASKED(HDC_CHICKEN0,
+ HDC_FORCE_NON_COHERENT |
+ HDC_DONOT_FETCH_MEM_WHEN_MASKED);
- ret = intel_ring_begin(ring, 12);
- if (ret)
- return ret;
+ return 0;
+}
- /* WaDisablePartialInstShootdown:chv */
- intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
- _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
+int init_workarounds_ring(struct intel_engine_cs *ring)
+{
+ struct drm_device *dev = ring->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
- /* WaDisableThreadStallDopClockGating:chv */
- intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
- _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+ WARN_ON(ring->id != RCS);
- /* WaDisableDopClockGating:chv (pre-production hw) */
- intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
- _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+ dev_priv->workarounds.count = 0;
- /* WaDisableSamplerPowerBypass:chv (pre-production hw) */
- intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
- _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
+ if (IS_BROADWELL(dev))
+ return bdw_init_workarounds(ring);
- intel_ring_advance(ring);
+ if (IS_CHERRYVIEW(dev))
+ return chv_init_workarounds(ring);
return 0;
}
*
* WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
*/
- if (INTEL_INFO(dev)->gen >= 6)
+ if (INTEL_INFO(dev)->gen >= 6 && INTEL_INFO(dev)->gen < 9)
I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
/* Required for the hardware to program scanline values for waiting */
_MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT) |
_MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
- if (INTEL_INFO(dev)->gen >= 5) {
- ret = intel_init_pipe_control(ring);
- if (ret)
- return ret;
- }
-
if (IS_GEN6(dev)) {
/* From the Sandybridge PRM, volume 1 part 3, page 24:
* "If this bit is set, STCunit will have LRA as replacement
if (HAS_L3_DPF(dev))
I915_WRITE_IMR(ring, ~GT_PARITY_ERROR(dev));
- return ret;
+ return init_workarounds_ring(ring);
}
static void render_ring_cleanup(struct intel_engine_cs *ring)
return ret;
for_each_ring(waiter, dev_priv, i) {
+ u32 seqno;
u64 gtt_offset = signaller->semaphore.signal_ggtt[i];
if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
continue;
+ seqno = i915_gem_request_get_seqno(
+ signaller->outstanding_lazy_request);
intel_ring_emit(signaller, GFX_OP_PIPE_CONTROL(6));
intel_ring_emit(signaller, PIPE_CONTROL_GLOBAL_GTT_IVB |
PIPE_CONTROL_QW_WRITE |
PIPE_CONTROL_FLUSH_ENABLE);
intel_ring_emit(signaller, lower_32_bits(gtt_offset));
intel_ring_emit(signaller, upper_32_bits(gtt_offset));
- intel_ring_emit(signaller, signaller->outstanding_lazy_seqno);
+ intel_ring_emit(signaller, seqno);
intel_ring_emit(signaller, 0);
intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL |
MI_SEMAPHORE_TARGET(waiter->id));
return ret;
for_each_ring(waiter, dev_priv, i) {
+ u32 seqno;
u64 gtt_offset = signaller->semaphore.signal_ggtt[i];
if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID)
continue;
+ seqno = i915_gem_request_get_seqno(
+ signaller->outstanding_lazy_request);
intel_ring_emit(signaller, (MI_FLUSH_DW + 1) |
MI_FLUSH_DW_OP_STOREDW);
intel_ring_emit(signaller, lower_32_bits(gtt_offset) |
MI_FLUSH_DW_USE_GTT);
intel_ring_emit(signaller, upper_32_bits(gtt_offset));
- intel_ring_emit(signaller, signaller->outstanding_lazy_seqno);
+ intel_ring_emit(signaller, seqno);
intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL |
MI_SEMAPHORE_TARGET(waiter->id));
intel_ring_emit(signaller, 0);
for_each_ring(useless, dev_priv, i) {
u32 mbox_reg = signaller->semaphore.mbox.signal[i];
if (mbox_reg != GEN6_NOSYNC) {
+ u32 seqno = i915_gem_request_get_seqno(
+ signaller->outstanding_lazy_request);
intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
intel_ring_emit(signaller, mbox_reg);
- intel_ring_emit(signaller, signaller->outstanding_lazy_seqno);
+ intel_ring_emit(signaller, seqno);
}
}
intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
- intel_ring_emit(ring, ring->outstanding_lazy_seqno);
+ intel_ring_emit(ring,
+ i915_gem_request_get_seqno(ring->outstanding_lazy_request));
intel_ring_emit(ring, MI_USER_INTERRUPT);
__intel_ring_advance(ring);
PIPE_CONTROL_WRITE_FLUSH |
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
- intel_ring_emit(ring, ring->outstanding_lazy_seqno);
+ intel_ring_emit(ring,
+ i915_gem_request_get_seqno(ring->outstanding_lazy_request));
intel_ring_emit(ring, 0);
PIPE_CONTROL_FLUSH(ring, scratch_addr);
scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
PIPE_CONTROL_NOTIFY);
intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT);
- intel_ring_emit(ring, ring->outstanding_lazy_seqno);
+ intel_ring_emit(ring,
+ i915_gem_request_get_seqno(ring->outstanding_lazy_request));
intel_ring_emit(ring, 0);
__intel_ring_advance(ring);
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned long flags;
- if (!dev->irq_enabled)
+ if (WARN_ON(!intel_irqs_enabled(dev_priv)))
return false;
spin_lock_irqsave(&dev_priv->irq_lock, flags);
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned long flags;
- if (!dev->irq_enabled)
+ if (!intel_irqs_enabled(dev_priv))
return false;
spin_lock_irqsave(&dev_priv->irq_lock, flags);
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned long flags;
- if (!dev->irq_enabled)
+ if (!intel_irqs_enabled(dev_priv))
return false;
spin_lock_irqsave(&dev_priv->irq_lock, flags);
intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
- intel_ring_emit(ring, ring->outstanding_lazy_seqno);
+ intel_ring_emit(ring,
+ i915_gem_request_get_seqno(ring->outstanding_lazy_request));
intel_ring_emit(ring, MI_USER_INTERRUPT);
__intel_ring_advance(ring);
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned long flags;
- if (!dev->irq_enabled)
- return false;
+ if (WARN_ON(!intel_irqs_enabled(dev_priv)))
+ return false;
spin_lock_irqsave(&dev_priv->irq_lock, flags);
if (ring->irq_refcount++ == 0) {
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned long flags;
- if (!dev->irq_enabled)
+ if (WARN_ON(!intel_irqs_enabled(dev_priv)))
return false;
spin_lock_irqsave(&dev_priv->irq_lock, flags);
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned long flags;
- if (!dev->irq_enabled)
- return;
-
spin_lock_irqsave(&dev_priv->irq_lock, flags);
if (--ring->irq_refcount == 0) {
I915_WRITE_IMR(ring, ~0);
struct drm_i915_private *dev_priv = dev->dev_private;
unsigned long flags;
- if (!dev->irq_enabled)
+ if (WARN_ON(!intel_irqs_enabled(dev_priv)))
return false;
spin_lock_irqsave(&dev_priv->irq_lock, flags);
return 0;
}
-void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
+void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
{
- if (!ringbuf->obj)
- return;
-
iounmap(ringbuf->virtual_start);
+ ringbuf->virtual_start = NULL;
i915_gem_object_ggtt_unpin(ringbuf->obj);
+}
+
+int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
+ struct intel_ringbuffer *ringbuf)
+{
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ struct drm_i915_gem_object *obj = ringbuf->obj;
+ int ret;
+
+ ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
+ if (ret)
+ return ret;
+
+ ret = i915_gem_object_set_to_gtt_domain(obj, true);
+ if (ret) {
+ i915_gem_object_ggtt_unpin(obj);
+ return ret;
+ }
+
+ ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base +
+ i915_gem_obj_ggtt_offset(obj), ringbuf->size);
+ if (ringbuf->virtual_start == NULL) {
+ i915_gem_object_ggtt_unpin(obj);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
+{
drm_gem_object_unreference(&ringbuf->obj->base);
ringbuf->obj = NULL;
}
int intel_alloc_ringbuffer_obj(struct drm_device *dev,
struct intel_ringbuffer *ringbuf)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
struct drm_i915_gem_object *obj;
- int ret;
-
- if (ringbuf->obj)
- return 0;
obj = NULL;
if (!HAS_LLC(dev))
/* mark ring buffers as read-only from GPU side by default */
obj->gt_ro = 1;
- ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
- if (ret)
- goto err_unref;
-
- ret = i915_gem_object_set_to_gtt_domain(obj, true);
- if (ret)
- goto err_unpin;
-
- ringbuf->virtual_start =
- ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
- ringbuf->size);
- if (ringbuf->virtual_start == NULL) {
- ret = -EINVAL;
- goto err_unpin;
- }
-
ringbuf->obj = obj;
- return 0;
-err_unpin:
- i915_gem_object_ggtt_unpin(obj);
-err_unref:
- drm_gem_object_unreference(&obj->base);
- return ret;
+ return 0;
}
static int intel_init_ring_buffer(struct drm_device *dev,
goto error;
}
- ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
- if (ret) {
- DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", ring->name, ret);
- goto error;
+ if (ringbuf->obj == NULL) {
+ ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
+ if (ret) {
+ DRM_ERROR("Failed to allocate ringbuffer %s: %d\n",
+ ring->name, ret);
+ goto error;
+ }
+
+ ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf);
+ if (ret) {
+ DRM_ERROR("Failed to pin and map ringbuffer %s: %d\n",
+ ring->name, ret);
+ intel_destroy_ringbuffer_obj(ringbuf);
+ goto error;
+ }
}
/* Workaround an erratum on the i830 which causes a hang if
if (ret)
goto error;
- ret = ring->init(ring);
- if (ret)
- goto error;
-
return 0;
error:
void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
{
- struct drm_i915_private *dev_priv = to_i915(ring->dev);
- struct intel_ringbuffer *ringbuf = ring->buffer;
+ struct drm_i915_private *dev_priv;
+ struct intel_ringbuffer *ringbuf;
if (!intel_ring_initialized(ring))
return;
+ dev_priv = to_i915(ring->dev);
+ ringbuf = ring->buffer;
+
intel_stop_ring_buffer(ring);
WARN_ON(!IS_GEN2(ring->dev) && (I915_READ_MODE(ring) & MODE_IDLE) == 0);
+ intel_unpin_ringbuffer_obj(ringbuf);
intel_destroy_ringbuffer_obj(ringbuf);
- ring->preallocated_lazy_request = NULL;
- ring->outstanding_lazy_seqno = 0;
+ i915_gem_request_assign(&ring->outstanding_lazy_request, NULL);
if (ring->cleanup)
ring->cleanup(ring);
{
struct intel_ringbuffer *ringbuf = ring->buffer;
struct drm_i915_gem_request *request;
- u32 seqno = 0;
int ret;
- if (ringbuf->last_retired_head != -1) {
- ringbuf->head = ringbuf->last_retired_head;
- ringbuf->last_retired_head = -1;
-
- ringbuf->space = intel_ring_space(ringbuf);
- if (ringbuf->space >= n)
- return 0;
- }
+ if (intel_ring_space(ringbuf) >= n)
+ return 0;
list_for_each_entry(request, &ring->request_list, list) {
if (__intel_ring_space(request->tail, ringbuf->tail,
ringbuf->size) >= n) {
- seqno = request->seqno;
break;
}
}
- if (seqno == 0)
+ if (&request->list == &ring->request_list)
return -ENOSPC;
- ret = i915_wait_seqno(ring, seqno);
+ ret = i915_wait_request(request);
if (ret)
return ret;
i915_gem_retire_requests_ring(ring);
- ringbuf->head = ringbuf->last_retired_head;
- ringbuf->last_retired_head = -1;
- ringbuf->space = intel_ring_space(ringbuf);
return 0;
}
* 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);
- ringbuf->space = intel_ring_space(ringbuf);
- if (ringbuf->space >= n) {
- ret = 0;
+ if (intel_ring_space(ringbuf) >= n)
break;
- }
-
- if (!drm_core_check_feature(dev, DRIVER_MODESET) &&
- dev->primary->master) {
- struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
- if (master_priv->sarea_priv)
- master_priv->sarea_priv->perf_boxes |= I915_BOX_WAIT;
- }
msleep(1);
iowrite32(MI_NOOP, virt++);
ringbuf->tail = 0;
- ringbuf->space = intel_ring_space(ringbuf);
+ intel_ring_update_space(ringbuf);
return 0;
}
int intel_ring_idle(struct intel_engine_cs *ring)
{
- u32 seqno;
+ 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_seqno) {
- ret = i915_add_request(ring, NULL);
+ if (ring->outstanding_lazy_request) {
+ ret = i915_add_request(ring);
if (ret)
return ret;
}
if (list_empty(&ring->request_list))
return 0;
- seqno = list_entry(ring->request_list.prev,
+ req = list_entry(ring->request_list.prev,
struct drm_i915_gem_request,
- list)->seqno;
+ list);
- return i915_wait_seqno(ring, seqno);
+ return i915_wait_request(req);
}
static int
-intel_ring_alloc_seqno(struct intel_engine_cs *ring)
+intel_ring_alloc_request(struct intel_engine_cs *ring)
{
- if (ring->outstanding_lazy_seqno)
+ int ret;
+ struct drm_i915_gem_request *request;
+
+ if (ring->outstanding_lazy_request)
return 0;
- if (ring->preallocated_lazy_request == NULL) {
- struct drm_i915_gem_request *request;
+ request = kmalloc(sizeof(*request), GFP_KERNEL);
+ if (request == NULL)
+ return -ENOMEM;
- request = kmalloc(sizeof(*request), GFP_KERNEL);
- if (request == NULL)
- return -ENOMEM;
+ kref_init(&request->ref);
+ request->ring = ring;
- ring->preallocated_lazy_request = request;
+ ret = i915_gem_get_seqno(ring->dev, &request->seqno);
+ if (ret) {
+ kfree(request);
+ return ret;
}
- return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno);
+ ring->outstanding_lazy_request = request;
+ return 0;
}
static int __intel_ring_prepare(struct intel_engine_cs *ring,
return ret;
/* Preallocate the olr before touching the ring */
- ret = intel_ring_alloc_seqno(ring);
+ ret = intel_ring_alloc_request(ring);
if (ret)
return ret;
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- BUG_ON(ring->outstanding_lazy_seqno);
+ BUG_ON(ring->outstanding_lazy_request);
if (INTEL_INFO(dev)->gen == 6 || INTEL_INFO(dev)->gen == 7) {
I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
u32 invalidate, u32 flush)
{
struct drm_device *dev = ring->dev;
+ struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t cmd;
int ret;
}
intel_ring_advance(ring);
- if (IS_GEN7(dev) && !invalidate && flush)
- return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
+ if (!invalidate && flush) {
+ if (IS_GEN7(dev))
+ return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
+ else if (IS_BROADWELL(dev))
+ dev_priv->fbc.need_sw_cache_clean = true;
+ }
return 0;
}
dev_priv->semaphore_obj = obj;
}
}
- if (IS_CHERRYVIEW(dev))
- ring->init_context = chv_init_workarounds;
- else
- ring->init_context = bdw_init_workarounds;
+
+ ring->init_context = intel_ring_workarounds_emit;
ring->add_request = gen6_add_request;
ring->flush = gen8_render_ring_flush;
ring->irq_get = gen8_ring_get_irq;
ring->dispatch_execbuffer = i830_dispatch_execbuffer;
else
ring->dispatch_execbuffer = i915_dispatch_execbuffer;
- ring->init = init_render_ring;
+ ring->init_hw = init_render_ring;
ring->cleanup = render_ring_cleanup;
/* Workaround batchbuffer to combat CS tlb bug. */
ring->scratch.gtt_offset = i915_gem_obj_ggtt_offset(obj);
}
- return intel_init_ring_buffer(dev, ring);
-}
-
-int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
-{
- struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_engine_cs *ring = &dev_priv->ring[RCS];
- struct intel_ringbuffer *ringbuf = ring->buffer;
- int ret;
-
- if (ringbuf == NULL) {
- ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
- if (!ringbuf)
- return -ENOMEM;
- ring->buffer = ringbuf;
- }
-
- ring->name = "render ring";
- ring->id = RCS;
- ring->mmio_base = RENDER_RING_BASE;
-
- if (INTEL_INFO(dev)->gen >= 6) {
- /* non-kms not supported on gen6+ */
- ret = -ENODEV;
- goto err_ringbuf;
- }
-
- /* Note: gem is not supported on gen5/ilk without kms (the corresponding
- * gem_init ioctl returns with -ENODEV). Hence we do not need to set up
- * the special gen5 functions. */
- ring->add_request = i9xx_add_request;
- if (INTEL_INFO(dev)->gen < 4)
- ring->flush = gen2_render_ring_flush;
- 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;
- } else {
- ring->irq_get = i9xx_ring_get_irq;
- ring->irq_put = i9xx_ring_put_irq;
- }
- ring->irq_enable_mask = I915_USER_INTERRUPT;
- ring->write_tail = ring_write_tail;
- if (INTEL_INFO(dev)->gen >= 4)
- ring->dispatch_execbuffer = i965_dispatch_execbuffer;
- else if (IS_I830(dev) || IS_845G(dev))
- ring->dispatch_execbuffer = i830_dispatch_execbuffer;
- else
- ring->dispatch_execbuffer = i915_dispatch_execbuffer;
- ring->init = init_render_ring;
- ring->cleanup = render_ring_cleanup;
-
- ring->dev = dev;
- INIT_LIST_HEAD(&ring->active_list);
- INIT_LIST_HEAD(&ring->request_list);
-
- ringbuf->size = size;
- ringbuf->effective_size = ringbuf->size;
- if (IS_I830(ring->dev) || IS_845G(ring->dev))
- ringbuf->effective_size -= 2 * CACHELINE_BYTES;
-
- ringbuf->virtual_start = ioremap_wc(start, size);
- if (ringbuf->virtual_start == NULL) {
- DRM_ERROR("can not ioremap virtual address for"
- " ring buffer\n");
- ret = -ENOMEM;
- goto err_ringbuf;
- }
+ ret = intel_init_ring_buffer(dev, ring);
+ if (ret)
+ return ret;
- if (!I915_NEED_GFX_HWS(dev)) {
- ret = init_phys_status_page(ring);
+ if (INTEL_INFO(dev)->gen >= 5) {
+ ret = intel_init_pipe_control(ring);
if (ret)
- goto err_vstart;
+ return ret;
}
return 0;
-
-err_vstart:
- iounmap(ringbuf->virtual_start);
-err_ringbuf:
- kfree(ringbuf);
- ring->buffer = NULL;
- return ret;
}
int intel_init_bsd_ring_buffer(struct drm_device *dev)
}
ring->dispatch_execbuffer = i965_dispatch_execbuffer;
}
- ring->init = init_ring_common;
+ ring->init_hw = init_ring_common;
return intel_init_ring_buffer(dev, ring);
}
ring->semaphore.signal = gen8_xcs_signal;
GEN8_RING_SEMAPHORE_INIT;
}
- ring->init = init_ring_common;
+ ring->init_hw = init_ring_common;
return intel_init_ring_buffer(dev, ring);
}
ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
}
}
- ring->init = init_ring_common;
+ ring->init_hw = init_ring_common;
return intel_init_ring_buffer(dev, ring);
}
ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
}
}
- ring->init = init_ring_common;
+ ring->init_hw = init_ring_common;
return intel_init_ring_buffer(dev, ring);
}