drm/i915: Update I915_GEM_BUSY IOCTL to understand composite fences

Parallel submission create composite fences (dma_fence_array) for excl /
shared slots in objects. The I915_GEM_BUSY IOCTL checks these slots to
determine the busyness of the object. Prior to patch it only check if
the fence in the slot was a i915_request. Update the check to understand
composite fences and correctly report the busyness.

v2:
 (Tvrtko)
  - Remove duplicate BUILD_BUG_ON

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-24-matthew.brost@intel.com

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
index 6234e17..7358beb 100644 (file)
--- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
@@ -4,6 +4,8 @@
  * Copyright © 2014-2016 Intel Corporation
  */
 
+#include <linux/dma-fence-array.h>
+
 #include "gt/intel_engine.h"
 
 #include "i915_gem_ioctls.h"
@@ -36,7 +38,7 @@ static __always_inline u32 __busy_write_id(u16 id)
 }
 
 static __always_inline unsigned int
-__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
+__busy_set_if_active(struct dma_fence *fence, u32 (*flag)(u16 id))
 {
        const struct i915_request *rq;
 
@@ -46,29 +48,60 @@ __busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
         * to eventually flush us, but to minimise latency just ask the
         * hardware.
         *
-        * Note we only report on the status of native fences.
+        * Note we only report on the status of native fences and we currently
+        * have two native fences:
+        *
+        * 1. A composite fence (dma_fence_array) constructed of i915 requests
+        * created during a parallel submission. In this case we deconstruct the
+        * composite fence into individual i915 requests and check the status of
+        * each request.
+        *
+        * 2. A single i915 request.
         */
-       if (!dma_fence_is_i915(fence))
+       if (dma_fence_is_array(fence)) {
+               struct dma_fence_array *array = to_dma_fence_array(fence);
+               struct dma_fence **child = array->fences;
+               unsigned int nchild = array->num_fences;
+
+               do {
+                       struct dma_fence *current_fence = *child++;
+
+                       /* Not an i915 fence, can't be busy per above */
+                       if (!dma_fence_is_i915(current_fence) ||
+                           !test_bit(I915_FENCE_FLAG_COMPOSITE,
+                                     &current_fence->flags)) {
+                               return 0;
+                       }
+
+                       rq = to_request(current_fence);
+                       if (!i915_request_completed(rq))
+                               return flag(rq->engine->uabi_class);
+               } while (--nchild);
+
+               /* All requests in array complete, not busy */
                return 0;
+       } else {
+               if (!dma_fence_is_i915(fence))
+                       return 0;
 
-       /* opencode to_request() in order to avoid const warnings */
-       rq = container_of(fence, const struct i915_request, fence);
-       if (i915_request_completed(rq))
-               return 0;
+               rq = to_request(fence);
+               if (i915_request_completed(rq))
+                       return 0;
 
-       /* Beware type-expansion follies! */
-       BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
-       return flag(rq->engine->uabi_class);
+               /* Beware type-expansion follies! */
+               BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
+               return flag(rq->engine->uabi_class);
+       }
 }
 
 static __always_inline unsigned int
-busy_check_reader(const struct dma_fence *fence)
+busy_check_reader(struct dma_fence *fence)
 {
        return __busy_set_if_active(fence, __busy_read_flag);
 }
 
 static __always_inline unsigned int
-busy_check_writer(const struct dma_fence *fence)
+busy_check_writer(struct dma_fence *fence)
 {
        if (!fence)
                return 0;

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 1cb2412..f20a3a5 100644 (file)
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2997,8 +2997,11 @@ eb_composite_fence_create(struct i915_execbuffer *eb, int out_fence_fd)
        if (!fences)
                return ERR_PTR(-ENOMEM);
 
-       for_each_batch_create_order(eb, i)
+       for_each_batch_create_order(eb, i) {
                fences[i] = &eb->requests[i]->fence;
+               __set_bit(I915_FENCE_FLAG_COMPOSITE,
+                         &eb->requests[i]->fence.flags);
+       }
 
        fence_array = dma_fence_array_create(eb->num_batches,
                                             fences,

diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 24db845..dc35924 100644 (file)
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -156,6 +156,12 @@ enum {
         * submission / relationship encoutered an error.
         */
        I915_FENCE_FLAG_SKIP_PARALLEL,
+
+       /*
+        * I915_FENCE_FLAG_COMPOSITE - Indicates fence is part of a composite
+        * fence (dma_fence_array) and i915 generated for parallel submission.
+        */
+       I915_FENCE_FLAG_COMPOSITE,
 };
 
 /**