Merge tag 'drm-fixes-2024-12-07' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Pretty quiet week which is probably expected after US holidays, the
  dma-fence and displayport MST message handling fixes make up the bulk
  of this, along with a couple of minor xe and other driver fixes.

  dma-fence:
   - Fix reference leak on fence-merge failure path
   - Simplify fence merging with kernel's sort()
   - Fix dma_fence_array_signaled() to ensure forward progress

  dp_mst:
   - Fix MST sideband message body length check
   - Fix a bunch of locking/state handling with DP MST msgs

  sti:
   - Add __iomem for mixer_dbg_mxn()'s parameter

  xe:
   - Missing init value and 64-bit write-order check
   - Fix a memory allocation issue causing lockdep violation

  v3d:
   - Performance counter fix"

* tag 'drm-fixes-2024-12-07' of https://gitlab.freedesktop.org/drm/kernel:
  drm/v3d: Enable Performance Counters before clearing them
  drm/dp_mst: Use reset_msg_rx_state() instead of open coding it
  drm/dp_mst: Reset message rx state after OOM in drm_dp_mst_handle_up_req()
  drm/dp_mst: Ensure mst_primary pointer is valid in drm_dp_mst_handle_up_req()
  drm/dp_mst: Fix down request message timeout handling
  drm/dp_mst: Simplify error path in drm_dp_mst_handle_down_rep()
  drm/dp_mst: Verify request type in the corresponding down message reply
  drm/dp_mst: Fix resetting msg rx state after topology removal
  drm/xe: Move the coredump registration to the worker thread
  drm/xe/guc: Fix missing init value and add register order check
  drm/sti: Add __iomem for mixer_dbg_mxn's parameter
  drm/dp_mst: Fix MST sideband message body length check
  dma-buf: fix dma_fence_array_signaled v4
  dma-fence: Use kernel's sort for merging fences
  dma-fence: Fix reference leak on fence merge failure path

Author: torvalds

drivers/dma-buf/dma-fence-array.c

@@ -103,10 +103,36 @@ static bool dma_fence_array_enable_signaling(struct dma_fence *fence)
 static bool dma_fence_array_signaled(struct dma_fence *fence)
 {
 	struct dma_fence_array *array = to_dma_fence_array(fence);
+	int num_pending;
+	unsigned int i;
 
-	if (atomic_read(&array->num_pending) > 0)
+	/*
+	 * We need to read num_pending before checking the enable_signal bit
+	 * to avoid racing with the enable_signaling() implementation, which
+	 * might decrement the counter, and cause a partial check.
+	 * atomic_read_acquire() pairs with atomic_dec_and_test() in
+	 * dma_fence_array_enable_signaling()
+	 *
+	 * The !--num_pending check is here to account for the any_signaled case
+	 * if we race with enable_signaling(), that means the !num_pending check
+	 * in the is_signalling_enabled branch might be outdated (num_pending
+	 * might have been decremented), but that's fine. The user will get the
+	 * right value when testing again later.
+	 */
+	num_pending = atomic_read_acquire(&array->num_pending);
+	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &array->base.flags)) {
+		if (num_pending <= 0)
+			goto signal;
 		return false;
+	}
+
+	for (i = 0; i < array->num_fences; ++i) {
+		if (dma_fence_is_signaled(array->fences[i]) && !--num_pending)
+			goto signal;
+	}
+	return false;
 
+signal:
 	dma_fence_array_clear_pending_error(array);
 	return true;
 }

drivers/dma-buf/dma-fence-unwrap.c

@@ -12,6 +12,7 @@
 #include <linux/dma-fence-chain.h>
 #include <linux/dma-fence-unwrap.h>
 #include <linux/slab.h>
+#include <linux/sort.h>
 
 /* Internal helper to start new array iteration, don't use directly */
 static struct dma_fence *
@@ -59,6 +60,25 @@ struct dma_fence *dma_fence_unwrap_next(struct dma_fence_unwrap *cursor)
 }
 EXPORT_SYMBOL_GPL(dma_fence_unwrap_next);
 
+
+static int fence_cmp(const void *_a, const void *_b)
+{
+	struct dma_fence *a = *(struct dma_fence **)_a;
+	struct dma_fence *b = *(struct dma_fence **)_b;
+
+	if (a->context < b->context)
+		return -1;
+	else if (a->context > b->context)
+		return 1;
+
+	if (dma_fence_is_later(b, a))
+		return 1;
+	else if (dma_fence_is_later(a, b))
+		return -1;
+
+	return 0;
+}
+
 /* Implementation for the dma_fence_merge() marco, don't use directly */
 struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
 					   struct dma_fence **fences,
@@ -67,8 +87,7 @@ struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
 	struct dma_fence_array *result;
 	struct dma_fence *tmp, **array;
 	ktime_t timestamp;
-	unsigned int i;
-	size_t count;
+	int i, j, count;
 
 	count = 0;
 	timestamp = ns_to_ktime(0);
@@ -96,78 +115,55 @@ struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
 	if (!array)
 		return NULL;
 
-	/*
-	 * This trashes the input fence array and uses it as position for the
-	 * following merge loop. This works because the dma_fence_merge()
-	 * wrapper macro is creating this temporary array on the stack together
-	 * with the iterators.
-	 */
-	for (i = 0; i < num_fences; ++i)
-		fences[i] = dma_fence_unwrap_first(fences[i], &iter[i]);
-
 	count = 0;
-	do {
-		unsigned int sel;
-
-restart:
-		tmp = NULL;
-		for (i = 0; i < num_fences; ++i) {
-			struct dma_fence *next;
-
-			while (fences[i] && dma_fence_is_signaled(fences[i]))
-				fences[i] = dma_fence_unwrap_next(&iter[i]);
-
-			next = fences[i];
-			if (!next)
-				continue;
-
-			/*
-			 * We can't guarantee that inpute fences are ordered by
-			 * context, but it is still quite likely when this
-			 * function is used multiple times. So attempt to order
-			 * the fences by context as we pass over them and merge
-			 * fences with the same context.
-			 */
-			if (!tmp || tmp->context > next->context) {
-				tmp = next;
-				sel = i;
-
-			} else if (tmp->context < next->context) {
-				continue;
-
-			} else if (dma_fence_is_later(tmp, next)) {
-				fences[i] = dma_fence_unwrap_next(&iter[i]);
-				goto restart;
+	for (i = 0; i < num_fences; ++i) {
+		dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) {
+			if (!dma_fence_is_signaled(tmp)) {
+				array[count++] = dma_fence_get(tmp);
 			} else {
-				fences[sel] = dma_fence_unwrap_next(&iter[sel]);
-				goto restart;
+				ktime_t t = dma_fence_timestamp(tmp);
+
+				if (ktime_after(t, timestamp))
+					timestamp = t;
 			}
 		}
+	}
 
-		if (tmp) {
-			array[count++] = dma_fence_get(tmp);
-			fences[sel] = dma_fence_unwrap_next(&iter[sel]);
-		}
-	} while (tmp);
+	if (count == 0 || count == 1)
+		goto return_fastpath;
 
-	if (count == 0) {
-		tmp = dma_fence_allocate_private_stub(ktime_get());
-		goto return_tmp;
-	}
+	sort(array, count, sizeof(*array), fence_cmp, NULL);
 
-	if (count == 1) {
-		tmp = array[0];
-		goto return_tmp;
+	/*
+	 * Only keep the most recent fence for each context.
+	 */
+	j = 0;
+	for (i = 1; i < count; i++) {
+		if (array[i]->context == array[j]->context)
+			dma_fence_put(array[i]);
+		else
+			array[++j] = array[i];
 	}
-
-	result = dma_fence_array_create(count, array,
-					dma_fence_context_alloc(1),
-					1, false);
-	if (!result) {
-		tmp = NULL;
-		goto return_tmp;
+	count = ++j;
+
+	if (count > 1) {
+		result = dma_fence_array_create(count, array,
+						dma_fence_context_alloc(1),
+						1, false);
+		if (!result) {
+			for (i = 0; i < count; i++)
+				dma_fence_put(array[i]);
+			tmp = NULL;
+			goto return_tmp;
+		}
+		return &result->base;
 	}
-	return &result->base;
+
+return_fastpath:
+	if (count == 0)
+		tmp = dma_fence_allocate_private_stub(timestamp);
+	else
+		tmp = array[0];
 
 return_tmp:
 	kfree(array);