#define GEN8_LR_CONTEXT_RENDER_SIZE (20 * PAGE_SIZE)
#define GEN8_LR_CONTEXT_OTHER_SIZE (2 * PAGE_SIZE)
-#define GEN8_LR_CONTEXT_ALIGN 4096
-
#define RING_EXECLIST_QFULL (1 << 0x2)
#define RING_EXECLIST1_VALID (1 << 0x3)
#define RING_EXECLIST0_VALID (1 << 0x4)
};
#define GEN8_CTX_ID_SHIFT 32
+static int intel_lr_context_pin(struct intel_engine_cs *ring,
+ struct intel_context *ctx);
+
/**
* intel_sanitize_enable_execlists() - sanitize i915.enable_execlists
* @dev: DRM device.
spin_unlock_irqrestore(&dev_priv->uncore.lock, flags);
}
-static int execlists_ctx_write_tail(struct drm_i915_gem_object *ctx_obj, u32 tail)
+static int execlists_update_context(struct drm_i915_gem_object *ctx_obj,
+ struct drm_i915_gem_object *ring_obj,
+ u32 tail)
{
struct page *page;
uint32_t *reg_state;
reg_state = kmap_atomic(page);
reg_state[CTX_RING_TAIL+1] = tail;
+ reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
kunmap_atomic(reg_state);
struct intel_context *to0, u32 tail0,
struct intel_context *to1, u32 tail1)
{
- struct drm_i915_gem_object *ctx_obj0;
+ struct drm_i915_gem_object *ctx_obj0 = to0->engine[ring->id].state;
+ struct intel_ringbuffer *ringbuf0 = to0->engine[ring->id].ringbuf;
struct drm_i915_gem_object *ctx_obj1 = NULL;
+ struct intel_ringbuffer *ringbuf1 = NULL;
- ctx_obj0 = to0->engine[ring->id].state;
BUG_ON(!ctx_obj0);
WARN_ON(!i915_gem_obj_is_pinned(ctx_obj0));
+ WARN_ON(!i915_gem_obj_is_pinned(ringbuf0->obj));
- execlists_ctx_write_tail(ctx_obj0, tail0);
+ execlists_update_context(ctx_obj0, ringbuf0->obj, tail0);
if (to1) {
+ ringbuf1 = to1->engine[ring->id].ringbuf;
ctx_obj1 = to1->engine[ring->id].state;
BUG_ON(!ctx_obj1);
WARN_ON(!i915_gem_obj_is_pinned(ctx_obj1));
+ WARN_ON(!i915_gem_obj_is_pinned(ringbuf1->obj));
- execlists_ctx_write_tail(ctx_obj1, tail1);
+ execlists_update_context(ctx_obj1, ringbuf1->obj, tail1);
}
execlists_elsp_write(ring, ctx_obj0, ctx_obj1);
{
struct intel_ctx_submit_request *req0 = NULL, *req1 = NULL;
struct intel_ctx_submit_request *cursor = NULL, *tmp = NULL;
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
assert_spin_locked(&ring->execlist_lock);
* will update tail past first request's workload */
cursor->elsp_submitted = req0->elsp_submitted;
list_del(&req0->execlist_link);
- queue_work(dev_priv->wq, &req0->work);
+ list_add_tail(&req0->execlist_link,
+ &ring->execlist_retired_req_list);
req0 = cursor;
} else {
req1 = cursor;
static bool execlists_check_remove_request(struct intel_engine_cs *ring,
u32 request_id)
{
- struct drm_i915_private *dev_priv = ring->dev->dev_private;
struct intel_ctx_submit_request *head_req;
assert_spin_locked(&ring->execlist_lock);
if (--head_req->elsp_submitted <= 0) {
list_del(&head_req->execlist_link);
- queue_work(dev_priv->wq, &head_req->work);
+ list_add_tail(&head_req->execlist_link,
+ &ring->execlist_retired_req_list);
return true;
}
}
((u32)ring->next_context_status_buffer & 0x07) << 8);
}
-static void execlists_free_request_task(struct work_struct *work)
-{
- struct intel_ctx_submit_request *req =
- container_of(work, struct intel_ctx_submit_request, work);
- struct drm_device *dev = req->ring->dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
-
- intel_runtime_pm_put(dev_priv);
-
- mutex_lock(&dev->struct_mutex);
- i915_gem_context_unreference(req->ctx);
- mutex_unlock(&dev->struct_mutex);
-
- kfree(req);
-}
-
static int execlists_context_queue(struct intel_engine_cs *ring,
struct intel_context *to,
u32 tail)
return -ENOMEM;
req->ctx = to;
i915_gem_context_reference(req->ctx);
+
+ if (to != ring->default_context)
+ intel_lr_context_pin(ring, to);
+
req->ring = ring;
req->tail = tail;
- INIT_WORK(&req->work, execlists_free_request_task);
intel_runtime_pm_get(dev_priv);
if (to == tail_req->ctx) {
WARN(tail_req->elsp_submitted != 0,
- "More than 2 already-submitted reqs queued\n");
+ "More than 2 already-submitted reqs queued\n");
list_del(&tail_req->execlist_link);
- queue_work(dev_priv->wq, &tail_req->work);
+ list_add_tail(&tail_req->execlist_link,
+ &ring->execlist_retired_req_list);
}
}
return 0;
}
+void intel_execlists_retire_requests(struct intel_engine_cs *ring)
+{
+ struct intel_ctx_submit_request *req, *tmp;
+ struct drm_i915_private *dev_priv = ring->dev->dev_private;
+ unsigned long flags;
+ struct list_head retired_list;
+
+ WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
+ if (list_empty(&ring->execlist_retired_req_list))
+ return;
+
+ INIT_LIST_HEAD(&retired_list);
+ spin_lock_irqsave(&ring->execlist_lock, flags);
+ list_replace_init(&ring->execlist_retired_req_list, &retired_list);
+ spin_unlock_irqrestore(&ring->execlist_lock, flags);
+
+ list_for_each_entry_safe(req, tmp, &retired_list, execlist_link) {
+ struct intel_context *ctx = req->ctx;
+ struct drm_i915_gem_object *ctx_obj =
+ ctx->engine[ring->id].state;
+
+ if (ctx_obj && (ctx != ring->default_context))
+ intel_lr_context_unpin(ring, ctx);
+ intel_runtime_pm_put(dev_priv);
+ i915_gem_context_unreference(req->ctx);
+ list_del(&req->execlist_link);
+ kfree(req);
+ }
+}
+
void intel_logical_ring_stop(struct intel_engine_cs *ring)
{
struct drm_i915_private *dev_priv = ring->dev->dev_private;
execlists_context_queue(ring, ctx, ringbuf->tail);
}
+static int intel_lr_context_pin(struct intel_engine_cs *ring,
+ struct intel_context *ctx)
+{
+ struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
+ struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+ int ret = 0;
+
+ WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
+ if (ctx->engine[ring->id].unpin_count++ == 0) {
+ ret = i915_gem_obj_ggtt_pin(ctx_obj,
+ GEN8_LR_CONTEXT_ALIGN, 0);
+ if (ret)
+ goto reset_unpin_count;
+
+ ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf);
+ if (ret)
+ goto unpin_ctx_obj;
+ }
+
+ return ret;
+
+unpin_ctx_obj:
+ i915_gem_object_ggtt_unpin(ctx_obj);
+reset_unpin_count:
+ ctx->engine[ring->id].unpin_count = 0;
+
+ return ret;
+}
+
+void intel_lr_context_unpin(struct intel_engine_cs *ring,
+ struct intel_context *ctx)
+{
+ struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state;
+ struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf;
+
+ if (ctx_obj) {
+ WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex));
+ if (--ctx->engine[ring->id].unpin_count == 0) {
+ intel_unpin_ringbuffer_obj(ringbuf);
+ i915_gem_object_ggtt_unpin(ctx_obj);
+ }
+ }
+}
+
static int logical_ring_alloc_seqno(struct intel_engine_cs *ring,
struct intel_context *ctx)
{
- if (ring->outstanding_lazy_seqno)
+ struct drm_i915_gem_request *request;
+ int ret;
+
+ /* XXX: The aim is to replace seqno values with request structures.
+ * A step along the way is to switch to using the PLR in preference
+ * to the OLS. That requires the PLR to only be valid when the OLS is
+ * also valid. I.e., the two must be kept in step. */
+
+ if (ring->outstanding_lazy_seqno) {
+ WARN_ON(ring->preallocated_lazy_request == NULL);
return 0;
+ }
+ WARN_ON(ring->preallocated_lazy_request != NULL);
- 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;
+ if (ctx != ring->default_context) {
+ ret = intel_lr_context_pin(ring, ctx);
+ if (ret) {
+ kfree(request);
+ return ret;
+ }
+ }
- /* Hold a reference to the context this request belongs to
- * (we will need it when the time comes to emit/retire the
- * request).
- */
- request->ctx = ctx;
- i915_gem_context_reference(request->ctx);
+ kref_init(&request->ref);
- ring->preallocated_lazy_request = request;
+ ret = i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno);
+ if (ret) {
+ intel_lr_context_unpin(ring, ctx);
+ kfree(request);
+ return ret;
}
- return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno);
+ /* Hold a reference to the context this request belongs to
+ * (we will need it when the time comes to emit/retire the
+ * request).
+ */
+ request->ctx = ctx;
+ i915_gem_context_reference(request->ctx);
+
+ ring->preallocated_lazy_request = request;
+ return 0;
}
static int logical_ring_wait_request(struct intel_ringbuffer *ringbuf,
}
list_for_each_entry(request, &ring->request_list, list) {
+ /*
+ * The request queue is per-engine, so can contain requests
+ * from multiple ringbuffers. Here, we must ignore any that
+ * aren't from the ringbuffer we're considering.
+ */
+ struct intel_context *ctx = request->ctx;
+ if (ctx->engine[ring->id].ringbuf != ringbuf)
+ continue;
+
+ /* Would completion of this request free enough space? */
if (__intel_ring_space(request->tail, ringbuf->tail,
ringbuf->size) >= bytes) {
seqno = request->seqno;
end = jiffies + 60 * HZ;
do {
- ringbuf->head = I915_READ_HEAD(ring);
ringbuf->space = intel_ring_space(ringbuf);
if (ringbuf->space >= bytes) {
ret = 0;
intel_logical_ring_stop(ring);
WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0);
- ring->preallocated_lazy_request = NULL;
+ i915_gem_request_assign(&ring->preallocated_lazy_request, NULL);
ring->outstanding_lazy_seqno = 0;
if (ring->cleanup)
init_waitqueue_head(&ring->irq_queue);
INIT_LIST_HEAD(&ring->execlist_queue);
+ INIT_LIST_HEAD(&ring->execlist_retired_req_list);
spin_lock_init(&ring->execlist_lock);
ring->next_context_status_buffer = 0;
{
struct drm_device *dev = ring->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
- struct drm_i915_gem_object *ring_obj = ringbuf->obj;
struct i915_hw_ppgtt *ppgtt = ctx->ppgtt;
struct page *page;
uint32_t *reg_state;
reg_state[CTX_RING_TAIL] = RING_TAIL(ring->mmio_base);
reg_state[CTX_RING_TAIL+1] = 0;
reg_state[CTX_RING_BUFFER_START] = RING_START(ring->mmio_base);
- reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(ring_obj);
+ /* Ring buffer start address is not known until the buffer is pinned.
+ * It is written to the context image in execlists_update_context()
+ */
reg_state[CTX_RING_BUFFER_CONTROL] = RING_CTL(ring->mmio_base);
reg_state[CTX_RING_BUFFER_CONTROL+1] =
((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID;
for (i = 0; i < I915_NUM_RINGS; i++) {
struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state;
- struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf;
if (ctx_obj) {
+ struct intel_ringbuffer *ringbuf =
+ ctx->engine[i].ringbuf;
+ struct intel_engine_cs *ring = ringbuf->ring;
+
+ if (ctx == ring->default_context) {
+ intel_unpin_ringbuffer_obj(ringbuf);
+ i915_gem_object_ggtt_unpin(ctx_obj);
+ }
intel_destroy_ringbuffer_obj(ringbuf);
kfree(ringbuf);
- i915_gem_object_ggtt_unpin(ctx_obj);
drm_gem_object_unreference(&ctx_obj->base);
}
}
return ret;
}
-static int lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
+static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring,
struct drm_i915_gem_object *default_ctx_obj)
{
struct drm_i915_private *dev_priv = ring->dev->dev_private;
ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(default_ctx_obj);
ring->status_page.page_addr =
kmap(sg_page(default_ctx_obj->pages->sgl));
- if (ring->status_page.page_addr == NULL)
- return -ENOMEM;
ring->status_page.obj = default_ctx_obj;
I915_WRITE(RING_HWS_PGA(ring->mmio_base),
(u32)ring->status_page.gfx_addr);
POSTING_READ(RING_HWS_PGA(ring->mmio_base));
-
- return 0;
}
/**
int intel_lr_context_deferred_create(struct intel_context *ctx,
struct intel_engine_cs *ring)
{
+ const bool is_global_default_ctx = (ctx == ring->default_context);
struct drm_device *dev = ring->dev;
struct drm_i915_gem_object *ctx_obj;
uint32_t context_size;
return ret;
}
- ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, 0);
- if (ret) {
- DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n", ret);
- drm_gem_object_unreference(&ctx_obj->base);
- return ret;
+ if (is_global_default_ctx) {
+ ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, 0);
+ if (ret) {
+ DRM_DEBUG_DRIVER("Pin LRC backing obj failed: %d\n",
+ ret);
+ drm_gem_object_unreference(&ctx_obj->base);
+ return ret;
+ }
}
ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
if (!ringbuf) {
DRM_DEBUG_DRIVER("Failed to allocate ringbuffer %s\n",
ring->name);
- i915_gem_object_ggtt_unpin(ctx_obj);
- drm_gem_object_unreference(&ctx_obj->base);
ret = -ENOMEM;
- return ret;
+ goto error_unpin_ctx;
}
ringbuf->ring = ring;
ringbuf->space = ringbuf->size;
ringbuf->last_retired_head = -1;
- /* TODO: For now we put this in the mappable region so that we can reuse
- * the existing ringbuffer code which ioremaps it. When we start
- * creating many contexts, this will no longer work and we must switch
- * to a kmapish interface.
- */
- ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
- if (ret) {
- DRM_DEBUG_DRIVER("Failed to allocate ringbuffer obj %s: %d\n",
+ if (ringbuf->obj == NULL) {
+ ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
+ if (ret) {
+ DRM_DEBUG_DRIVER(
+ "Failed to allocate ringbuffer obj %s: %d\n",
ring->name, ret);
- goto error;
+ goto error_free_rbuf;
+ }
+
+ if (is_global_default_ctx) {
+ 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);
+ goto error_destroy_rbuf;
+ }
+ }
+
}
ret = populate_lr_context(ctx, ctx_obj, ring, ringbuf);
if (ret) {
DRM_DEBUG_DRIVER("Failed to populate LRC: %d\n", ret);
- intel_destroy_ringbuffer_obj(ringbuf);
goto error;
}
ctx->engine[ring->id].ringbuf = ringbuf;
ctx->engine[ring->id].state = ctx_obj;
- if (ctx == ring->default_context) {
- ret = lrc_setup_hardware_status_page(ring, ctx_obj);
- if (ret) {
- DRM_ERROR("Failed to setup hardware status page\n");
- goto error;
- }
- }
+ if (ctx == ring->default_context)
+ lrc_setup_hardware_status_page(ring, ctx_obj);
if (ring->id == RCS && !ctx->rcs_initialized) {
if (ring->init_context) {
DRM_ERROR("Init render state failed: %d\n", ret);
ctx->engine[ring->id].ringbuf = NULL;
ctx->engine[ring->id].state = NULL;
- intel_destroy_ringbuffer_obj(ringbuf);
goto error;
}
ctx->rcs_initialized = true;
return 0;
error:
+ if (is_global_default_ctx)
+ intel_unpin_ringbuffer_obj(ringbuf);
+error_destroy_rbuf:
+ intel_destroy_ringbuffer_obj(ringbuf);
+error_free_rbuf:
kfree(ringbuf);
- i915_gem_object_ggtt_unpin(ctx_obj);
+error_unpin_ctx:
+ if (is_global_default_ctx)
+ i915_gem_object_ggtt_unpin(ctx_obj);
drm_gem_object_unreference(&ctx_obj->base);
return ret;
}