@@ -536,9 +536,6 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
struct intel_engine_cs **siblings = NULL;
intel_engine_mask_t prev_mask;
- if (!(intel_uc_uses_guc_submission(&i915->gt.uc)))
- return -ENODEV;
-
if (get_user(slot, &ext->engine_index))
return -EFAULT;
@@ -548,6 +545,12 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
if (get_user(num_siblings, &ext->num_siblings))
return -EFAULT;
+ if (!intel_uc_uses_guc_submission(&i915->gt.uc) && num_siblings != 1) {
+ drm_dbg(&i915->drm, "Only 1 sibling (%d) supported in non-GuC mode\n",
+ num_siblings);
+ return -EINVAL;
+ }
+
if (slot >= set->num_engines) {
drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
slot, set->num_engines);
@@ -79,7 +79,8 @@ static int intel_context_active_acquire(struct intel_context *ce)
__i915_active_acquire(&ce->active);
- if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine))
+ if (intel_context_is_barrier(ce) || intel_engine_uses_guc(ce->engine) ||
+ intel_context_is_parallel(ce))
return 0;
/* Preallocate tracking nodes */
@@ -554,7 +555,6 @@ void intel_context_bind_parent_child(struct intel_context *parent,
* Callers responsibility to validate that this function is used
* correctly but we use GEM_BUG_ON here ensure that they do.
*/
- GEM_BUG_ON(!intel_engine_uses_guc(parent->engine));
GEM_BUG_ON(intel_context_is_pinned(parent));
GEM_BUG_ON(intel_context_is_child(parent));
GEM_BUG_ON(intel_context_is_pinned(child));
@@ -927,8 +927,7 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
static bool ctx_single_port_submission(const struct intel_context *ce)
{
- return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
- intel_context_force_single_submission(ce));
+ return intel_context_force_single_submission(ce);
}
static bool can_merge_ctx(const struct intel_context *prev,
@@ -2598,6 +2597,59 @@ static void execlists_context_cancel_request(struct intel_context *ce,
current->comm);
}
+static struct intel_context *
+execlists_create_parallel(struct intel_engine_cs **engines,
+ unsigned int num_siblings,
+ unsigned int width)
+{
+ struct intel_engine_cs **siblings = NULL;
+ struct intel_context *parent = NULL, *ce, *err;
+ int i, j;
+
+ GEM_BUG_ON(num_siblings != 1);
+
+ siblings = kmalloc_array(num_siblings,
+ sizeof(*siblings),
+ GFP_KERNEL);
+ if (!siblings)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < width; ++i) {
+ for (j = 0; j < num_siblings; ++j)
+ siblings[j] = engines[i * num_siblings + j];
+
+ ce = intel_context_create(siblings[0]);
+ if (!ce) {
+ err = ERR_PTR(-ENOMEM);
+ goto unwind;
+ }
+
+ if (i == 0) {
+ parent = ce;
+ } else {
+ intel_context_bind_parent_child(parent, ce);
+ }
+ }
+
+ parent->fence_context = dma_fence_context_alloc(1);
+
+ intel_context_set_nopreempt(parent);
+ intel_context_set_single_submission(parent);
+ for_each_child(parent, ce) {
+ intel_context_set_nopreempt(ce);
+ intel_context_set_single_submission(ce);
+ }
+
+ kfree(siblings);
+ return parent;
+
+unwind:
+ if (parent)
+ intel_context_put(parent);
+ kfree(siblings);
+ return err;
+}
+
static const struct intel_context_ops execlists_context_ops = {
.flags = COPS_HAS_INFLIGHT,
@@ -2616,6 +2668,7 @@ static const struct intel_context_ops execlists_context_ops = {
.reset = lrc_reset,
.destroy = lrc_destroy,
+ .create_parallel = execlists_create_parallel,
.create_virtual = execlists_create_virtual,
};
@@ -983,6 +983,8 @@ lrc_pin(struct intel_context *ce,
void lrc_unpin(struct intel_context *ce)
{
+ if (unlikely(ce->last_rq))
+ i915_request_put(ce->last_rq);
check_redzone((void *)ce->lrc_reg_state - LRC_STATE_OFFSET,
ce->engine);
}
@@ -2901,8 +2901,6 @@ static void guc_parent_context_unpin(struct intel_context *ce)
GEM_BUG_ON(!intel_context_is_parent(ce));
GEM_BUG_ON(!intel_engine_is_virtual(ce->engine));
- if (ce->last_rq)
- i915_request_put(ce->last_rq);
unpin_guc_id(guc, ce);
lrc_unpin(ce);
}
A weak implementation of parallel submission (multi-bb execbuf IOCTL) for execlists. Basically doing as little as possible to support this interface for execlists - basically just passing submit fences between each request generated and virtual engines are not allowed. This is on par with what is there for the existing (hopefully soon deprecated) bonding interface. We perma-pin these execlists contexts to align with GuC implementation. Signed-off-by: Matthew Brost <matthew.brost@intel.com> --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 9 ++- drivers/gpu/drm/i915/gt/intel_context.c | 4 +- .../drm/i915/gt/intel_execlists_submission.c | 57 ++++++++++++++++++- drivers/gpu/drm/i915/gt/intel_lrc.c | 2 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 2 - 5 files changed, 65 insertions(+), 9 deletions(-)