@@ -715,6 +715,10 @@ __create_context(struct drm_i915_private *i915)
ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
mutex_init(&ctx->mutex);
+ ctx->async.width = rounddown_pow_of_two(num_online_cpus());
+ ctx->async.context = dma_fence_context_alloc(ctx->async.width);
+ ctx->async.width--;
+
spin_lock_init(&ctx->stale.lock);
INIT_LIST_HEAD(&ctx->stale.engines);
@@ -134,6 +134,12 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data,
struct drm_file *file);
+static inline u64 i915_gem_context_async_id(struct i915_gem_context *ctx)
+{
+ return (ctx->async.context +
+ (atomic_fetch_inc(&ctx->async.cur) & ctx->async.width));
+}
+
static inline struct i915_gem_context *
i915_gem_context_get(struct i915_gem_context *ctx)
{
@@ -85,6 +85,12 @@ struct i915_gem_context {
struct intel_timeline *timeline;
+ struct {
+ u64 context;
+ atomic_t cur;
+ unsigned int width;
+ } async;
+
/**
* @vm: unique address space (GTT)
*
Allocate a few dma fence context id that we can use to associate async work [for the CPU] launched on behalf of this context. For extra fun, we allow a configurable concurrency width. A current example would be that we spawn an unbound worker for every userptr get_pages. In the future, we wish to charge this work to the context that initiated the async work and to impose concurrency limits based on the context. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 4 ++++ drivers/gpu/drm/i915/gem/i915_gem_context.h | 6 ++++++ drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 6 ++++++ 3 files changed, 16 insertions(+)