On 06/07/2020 07:19, Chris Wilson wrote:
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@xxxxxxxxxxxxxxxxxx>
---
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(+)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 41784df51e58..bd68746327b3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -714,6 +714,10 @@ __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--;
Hey I had a tri-core CPU back in the day.. :) Really, I can only assume
you are oding some tricks with masks which maybe only work with power of
2 num cpus? Hard to say.. please explain in a comment.
I don't even understand what the context will be for yet and why it
needs a separate context id.
+
spin_lock_init(&ctx->stale.lock);
INIT_LIST_HEAD(&ctx->stale.engines);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 3702b2fb27ab..e104ff0ae740 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -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)
{
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index ae14ca24a11f..52561f98000f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -85,6 +85,12 @@ struct i915_gem_context {
struct intel_timeline *timeline;
+ struct {
+ u64 context;
+ atomic_t cur;
What is cur? In which patch it gets used? (Can't see it.)
+ unsigned int width;
+ } async;
+
/**
* @vm: unique address space (GTT)
*
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
