return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings);
}
-static int __i915_spin_request(struct drm_i915_gem_request *req)
+static unsigned long local_clock_us(unsigned *cpu)
+{
+ unsigned long t;
+
+ /* Cheaply and approximately convert from nanoseconds to microseconds.
+ * The result and subsequent calculations are also defined in the same
+ * approximate microseconds units. The principal source of timing
+ * error here is from the simple truncation.
+ *
+ * Note that local_clock() is only defined wrt to the current CPU;
+ * the comparisons are no longer valid if we switch CPUs. Instead of
+ * blocking preemption for the entire busywait, we can detect the CPU
+ * switch and use that as indicator of system load and a reason to
+ * stop busywaiting, see busywait_stop().
+ */
+ *cpu = get_cpu();
+ t = local_clock() >> 10;
+ put_cpu();
+
+ return t;
+}
+
+static bool busywait_stop(unsigned long timeout, unsigned cpu)
+{
+ unsigned this_cpu;
+
+ if (time_after(local_clock_us(&this_cpu), timeout))
+ return true;
+
+ return this_cpu != cpu;
+}
+
+static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
{
unsigned long timeout;
+ unsigned cpu;
+
+ /* When waiting for high frequency requests, e.g. during synchronous
+ * rendering split between the CPU and GPU, the finite amount of time
+ * required to set up the irq and wait upon it limits the response
+ * rate. By busywaiting on the request completion for a short while we
+ * can service the high frequency waits as quick as possible. However,
+ * if it is a slow request, we want to sleep as quickly as possible.
+ * The tradeoff between waiting and sleeping is roughly the time it
+ * takes to sleep on a request, on the order of a microsecond.
+ */
- if (i915_gem_request_get_ring(req)->irq_refcount)
+ if (req->ring->irq_refcount)
return -EBUSY;
- timeout = jiffies + 1;
+ /* Only spin if we know the GPU is processing this request */
+ if (!i915_gem_request_started(req, true))
+ return -EAGAIN;
+
+ timeout = local_clock_us(&cpu) + 5;
while (!need_resched()) {
if (i915_gem_request_completed(req, true))
return 0;
- if (time_after_eq(jiffies, timeout))
+ if (signal_pending_state(state, current))
+ break;
+
+ if (busywait_stop(timeout, cpu))
break;
cpu_relax_lowlatency();
}
+
if (i915_gem_request_completed(req, false))
return 0;
struct drm_i915_private *dev_priv = dev->dev_private;
const bool irq_test_in_progress =
ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring);
+ int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE;
DEFINE_WAIT(wait);
unsigned long timeout_expire;
- s64 before, now;
+ s64 before = 0; /* Only to silence a compiler warning. */
int ret;
WARN(!intel_irqs_enabled(dev_priv), "IRQs disabled");
if (i915_gem_request_completed(req, true))
return 0;
- timeout_expire = timeout ?
- jiffies + nsecs_to_jiffies_timeout((u64)*timeout) : 0;
+ timeout_expire = 0;
+ if (timeout) {
+ if (WARN_ON(*timeout < 0))
+ return -EINVAL;
+
+ if (*timeout == 0)
+ return -ETIME;
+
+ timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout);
+
+ /*
+ * Record current time in case interrupted by signal, or wedged.
+ */
+ before = ktime_get_raw_ns();
+ }
if (INTEL_INFO(dev_priv)->gen >= 6)
gen6_rps_boost(dev_priv, rps, req->emitted_jiffies);
- /* Record current time in case interrupted by signal, or wedged */
trace_i915_gem_request_wait_begin(req);
- before = ktime_get_raw_ns();
/* Optimistic spin for the next jiffie before touching IRQs */
- ret = __i915_spin_request(req);
+ ret = __i915_spin_request(req, state);
if (ret == 0)
goto out;
for (;;) {
struct timer_list timer;
- prepare_to_wait(&ring->irq_queue, &wait,
- interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(&ring->irq_queue, &wait, state);
/* We need to check whether any gpu reset happened in between
* the caller grabbing the seqno and now ... */
break;
}
- if (interruptible && signal_pending(current)) {
+ if (signal_pending_state(state, current)) {
ret = -ERESTARTSYS;
break;
}
finish_wait(&ring->irq_queue, &wait);
out:
- now = ktime_get_raw_ns();
trace_i915_gem_request_wait_end(req);
if (timeout) {
- s64 tres = *timeout - (now - before);
+ s64 tres = *timeout - (ktime_get_raw_ns() - before);
*timeout = tres < 0 ? 0 : tres;
request->batch_obj = obj;
request->emitted_jiffies = jiffies;
+ request->previous_seqno = ring->last_submitted_seqno;
ring->last_submitted_seqno = request->seqno;
list_add_tail(&request->list, &ring->request_list);
i915_gem_request_remove_from_client(req);
if (ctx) {
- if (i915.enable_execlists) {
- if (ctx != req->ring->default_context)
- intel_lr_context_unpin(req);
- }
+ if (i915.enable_execlists && ctx != req->i915->kernel_context)
+ intel_lr_context_unpin(req);
i915_gem_context_unreference(ctx);
}
kmem_cache_free(req->i915->requests, req);
}
-int i915_gem_request_alloc(struct intel_engine_cs *ring,
- struct intel_context *ctx,
- struct drm_i915_gem_request **req_out)
+static inline int
+__i915_gem_request_alloc(struct intel_engine_cs *ring,
+ struct intel_context *ctx,
+ struct drm_i915_gem_request **req_out)
{
struct drm_i915_private *dev_priv = to_i915(ring->dev);
struct drm_i915_gem_request *req;
return ret;
}
+/**
+ * i915_gem_request_alloc - allocate a request structure
+ *
+ * @engine: engine that we wish to issue the request on.
+ * @ctx: context that the request will be associated with.
+ * This can be NULL if the request is not directly related to
+ * any specific user context, in which case this function will
+ * choose an appropriate context to use.
+ *
+ * Returns a pointer to the allocated request if successful,
+ * or an error code if not.
+ */
+struct drm_i915_gem_request *
+i915_gem_request_alloc(struct intel_engine_cs *engine,
+ struct intel_context *ctx)
+{
+ struct drm_i915_gem_request *req;
+ int err;
+
+ if (ctx == NULL)
+ ctx = to_i915(engine->dev)->kernel_context;
+ err = __i915_gem_request_alloc(engine, ctx, &req);
+ return err ? ERR_PTR(err) : req;
+}
+
void i915_gem_request_cancel(struct drm_i915_gem_request *req)
{
intel_ring_reserved_space_cancel(req->ringbuf);
if (!list_empty(&ring->request_list))
return;
+ /* we probably should sync with hangcheck here, using cancel_work_sync.
+ * Also locking seems to be fubar here, ring->request_list is protected
+ * by dev->struct_mutex. */
+
intel_mark_idle(dev);
if (mutex_trylock(&dev->struct_mutex)) {
return 0;
if (*to_req == NULL) {
- ret = i915_gem_request_alloc(to, to->default_context, to_req);
- if (ret)
- return ret;
+ struct drm_i915_gem_request *req;
+
+ req = i915_gem_request_alloc(to, NULL);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ *to_req = req;
}
trace_i915_gem_ring_sync_to(*to_req, from, from_req);
if (!i915.enable_execlists) {
struct drm_i915_gem_request *req;
- ret = i915_gem_request_alloc(ring, ring->default_context, &req);
- if (ret)
- return ret;
+ req = i915_gem_request_alloc(ring, NULL);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
ret = i915_switch_context(req);
if (ret) {
if (flags & PIN_MAPPABLE)
end = min_t(u64, end, dev_priv->gtt.mappable_end);
if (flags & PIN_ZONE_4G)
- end = min_t(u64, end, (1ULL << 32));
+ end = min_t(u64, end, (1ULL << 32) - PAGE_SIZE);
if (alignment == 0)
alignment = flags & PIN_MAPPABLE ? fence_alignment :
return false;
}
+void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
+{
+ struct drm_i915_gem_object *obj = vma->obj;
+ bool mappable, fenceable;
+ u32 fence_size, fence_alignment;
+
+ fence_size = i915_gem_get_gtt_size(obj->base.dev,
+ obj->base.size,
+ obj->tiling_mode);
+ fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev,
+ obj->base.size,
+ obj->tiling_mode,
+ true);
+
+ fenceable = (vma->node.size == fence_size &&
+ (vma->node.start & (fence_alignment - 1)) == 0);
+
+ mappable = (vma->node.start + fence_size <=
+ to_i915(obj->base.dev)->gtt.mappable_end);
+
+ obj->map_and_fenceable = mappable && fenceable;
+}
+
static int
i915_gem_object_do_pin(struct drm_i915_gem_object *obj,
struct i915_address_space *vm,
if (ggtt_view && ggtt_view->type == I915_GGTT_VIEW_NORMAL &&
(bound ^ vma->bound) & GLOBAL_BIND) {
- bool mappable, fenceable;
- u32 fence_size, fence_alignment;
-
- fence_size = i915_gem_get_gtt_size(obj->base.dev,
- obj->base.size,
- obj->tiling_mode);
- fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev,
- obj->base.size,
- obj->tiling_mode,
- true);
-
- fenceable = (vma->node.size == fence_size &&
- (vma->node.start & (fence_alignment - 1)) == 0);
-
- mappable = (vma->node.start + fence_size <=
- dev_priv->gtt.mappable_end);
-
- obj->map_and_fenceable = mappable && fenceable;
-
+ __i915_vma_set_map_and_fenceable(vma);
WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable);
}
if (ret)
goto unref;
- BUILD_BUG_ON(I915_NUM_RINGS > 16);
- args->busy = obj->active << 16;
- if (obj->last_write_req)
- args->busy |= obj->last_write_req->ring->id;
+ args->busy = 0;
+ if (obj->active) {
+ int i;
+
+ for (i = 0; i < I915_NUM_RINGS; i++) {
+ struct drm_i915_gem_request *req;
+
+ req = obj->last_read_req[i];
+ if (req)
+ args->busy |= 1 << (16 + req->ring->exec_id);
+ }
+ if (obj->last_write_req)
+ args->busy |= obj->last_write_req->ring->exec_id;
+ }
unref:
drm_gem_object_unreference(&obj->base);
*/
init_unused_rings(dev);
- BUG_ON(!dev_priv->ring[RCS].default_context);
+ BUG_ON(!dev_priv->kernel_context);
ret = i915_ppgtt_init_hw(dev);
if (ret) {
for_each_ring(ring, dev_priv, i) {
struct drm_i915_gem_request *req;
- WARN_ON(!ring->default_context);
-
- ret = i915_gem_request_alloc(ring, ring->default_context, &req);
- if (ret) {
- i915_gem_cleanup_ringbuffer(dev);
+ req = i915_gem_request_alloc(ring, NULL);
+ if (IS_ERR(req)) {
+ ret = PTR_ERR(req);
+ i915_gem_cleanup_engines(dev);
goto out;
}
if (ret && ret != -EIO) {
DRM_ERROR("PPGTT enable ring #%d failed %d\n", i, ret);
i915_gem_request_cancel(req);
- i915_gem_cleanup_ringbuffer(dev);
+ i915_gem_cleanup_engines(dev);
goto out;
}
if (ret && ret != -EIO) {
DRM_ERROR("Context enable ring #%d failed %d\n", i, ret);
i915_gem_request_cancel(req);
- i915_gem_cleanup_ringbuffer(dev);
+ i915_gem_cleanup_engines(dev);
goto out;
}
}
void
-i915_gem_cleanup_ringbuffer(struct drm_device *dev)
+i915_gem_cleanup_engines(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_engine_cs *ring;
for_each_ring(ring, dev_priv, i)
dev_priv->gt.cleanup_ring(ring);
- if (i915.enable_execlists)
- /*
- * Neither the BIOS, ourselves or any other kernel
- * expects the system to be in execlists mode on startup,
- * so we need to reset the GPU back to legacy mode.
- */
- intel_gpu_reset(dev);
+ if (i915.enable_execlists) {
+ /*
+ * Neither the BIOS, ourselves or any other kernel
+ * expects the system to be in execlists mode on startup,
+ * so we need to reset the GPU back to legacy mode.
+ */
+ intel_gpu_reset(dev);
+ }
}
static void
spin_lock_init(&file_priv->mm.lock);
INIT_LIST_HEAD(&file_priv->mm.request_list);
+ file_priv->bsd_ring = -1;
+
ret = i915_gem_context_open(dev, file);
if (ret)
kfree(file_priv);