From: Arunpravin Paneer Selvam <[email protected]>
Range-restricted allocations (the visible-VRAM aperture) skip
dirty_steer_window() and reach __alloc_range_bias() with no clear/dirty
eligibility guard, so a dirty allocation freely splits clear extents (and
vice versa), interleaving the two classes until no large same-class run
survives and a 4K scanout pin fails with -ENOSPC. Use a two-pass range
search instead: block_incompatible() rejects opposite-class blocks in the
strict pass and relaxes only when the strict pass returns -ENOSPC, so a
request still succeeds when only opposite-class space remains. A KUnit
regression test covers the interleaving pattern and fails without the
guard.
v2: the strict pass can split a block and then reject both children, so
a split no longer implies a compatible block exists. Sashiko reported
the resulting leaked splits; fix as suggested by Matthew:
- Push the parent back on the DFS stack after each split and merge it
back with unsplit_block() if both children are still free.
- Make block_incompatible() judge free blocks only (split nodes keep a
stale clear bit) and take the requested order, so mixed blocks that
can hold a compatible block are descended instead of skipped.
- Extend the KUnit test with a coalesced mixed block and a check that
a rejected split is merged back.
v3: igt@kms_plane@plane-panning-bottom-right failed on Radeon RX 9070 XT
with -ENOSPC: the range allocator's strict pass split mixed blocks to
look for a wholly-clear (or wholly-dirty) leaf, discarded the mixed
leaves it found, and ran unsplit_block to merge the splits back, whose
per-allocation cost and residual fragmentation starved the large
pipe-A scanout. Fix: accept a mixed block at the requested order as-is
(caller re-clears), so the first pass no longer splits and discards
mixed blocks. This clear/dirty compatibility relaxation applies only
to range-biased allocation, where keeping blocks intact reduces
fragmentation and preserves large contiguous spaces. The now-unneeded
unsplit_block helper is dropped.
Fixes: 1ad5e807f716 ("gpu/buddy: replace dual-tree/force_merge with decoupled
dirty tracker")
Assisted-by: LLM
Cc: Matthew Auld <[email protected]>
Cc: Christian König <[email protected]>
Signed-off-by: Arunpravin Paneer Selvam <[email protected]>
---
drivers/gpu/buddy.c | 75 +++++++++++++-------------
drivers/gpu/tests/gpu_buddy_test.c | 84 ++++++++++++++++++++++++++++++
2 files changed, 122 insertions(+), 37 deletions(-)
diff --git a/drivers/gpu/buddy.c b/drivers/gpu/buddy.c
index 28cff97d57dc..f2914f919b04 100644
--- a/drivers/gpu/buddy.c
+++ b/drivers/gpu/buddy.c
@@ -1240,11 +1240,23 @@ static void __gpu_buddy_undo_splits(struct gpu_buddy
*mm,
}
}
+static bool block_incompatible(struct gpu_buddy_block *block, unsigned int
flags)
+{
+ bool needs_clear = flags & GPU_BUDDY_CLEAR_ALLOCATION;
+
+ if (!gpu_buddy_block_is_free(block))
+ return false;
+
+ return needs_clear ? !block->has_clear :
+ gpu_buddy_block_is_clear(block);
+}
+
static struct gpu_buddy_block *
__alloc_range_bias(struct gpu_buddy *mm,
u64 start, u64 end,
unsigned int order,
- unsigned long flags)
+ unsigned long flags,
+ bool fallback)
{
u64 req_size = mm->chunk_size << order;
struct gpu_buddy_block *block;
@@ -1258,9 +1270,7 @@ __alloc_range_bias(struct gpu_buddy *mm,
* This range-constrained search hands back the highest/right-most
* address that satisfies the request: the roots are seeded high-to-low
* and the right (higher-address) child is descended first, making
- * top-down the default placement here. A non-top-down clear request is
- * the only exception, where the descent is biased towards clear or
- * clear-containing subtrees to satisfy the clear preference.
+ * top-down the default placement here.
*/
for (i = mm->n_roots - 1; i >= 0; --i)
list_add_tail(&mm->roots[i]->tmp_link, &dfs);
@@ -1298,6 +1308,9 @@ __alloc_range_bias(struct gpu_buddy *mm,
continue;
}
+ if (!fallback && block_incompatible(block, flags))
+ continue;
+
if (contains(start, end, block_start, block_end) &&
order == gpu_buddy_block_order(block)) {
/*
@@ -1315,38 +1328,8 @@ __alloc_range_bias(struct gpu_buddy *mm,
goto err_undo;
}
- /*
- * Top-down is a strict address-placement policy, so when it is
- * requested we ignore clear steering and simply descend the
- * right (higher-address) child first. Only a non-top-down clear
- * request biases the descent towards clear/has_clear subtrees.
- */
- if ((flags & GPU_BUDDY_CLEAR_ALLOCATION) &&
- !(flags & GPU_BUDDY_TOPDOWN_ALLOCATION)) {
- struct gpu_buddy_block *prefer;
-
- if (gpu_buddy_block_is_clear(block->right))
- prefer = block->right;
- else if (gpu_buddy_block_is_clear(block->left))
- prefer = block->left;
- else if (block->right->has_clear)
- prefer = block->right;
- else if (block->left->has_clear)
- prefer = block->left;
- else
- prefer = block->right;
-
- if (prefer == block->right) {
- list_add(&block->left->tmp_link, &dfs);
- list_add(&block->right->tmp_link, &dfs);
- } else {
- list_add(&block->right->tmp_link, &dfs);
- list_add(&block->left->tmp_link, &dfs);
- }
- } else {
- list_add(&block->left->tmp_link, &dfs);
- list_add(&block->right->tmp_link, &dfs);
- }
+ list_add(&block->left->tmp_link, &dfs);
+ list_add(&block->right->tmp_link, &dfs);
} while (1);
return ERR_PTR(-ENOSPC);
@@ -1361,6 +1344,24 @@ __alloc_range_bias(struct gpu_buddy *mm,
return ERR_PTR(err);
}
+static struct gpu_buddy_block *
+__gpu_buddy_alloc_range_bias(struct gpu_buddy *mm,
+ u64 start, u64 end,
+ unsigned int order,
+ unsigned long flags)
+{
+ struct gpu_buddy_block *block;
+ bool fallback = false;
+
+ block = __alloc_range_bias(mm, start, end, order,
+ flags, fallback);
+ if (IS_ERR(block))
+ return __alloc_range_bias(mm, start, end, order,
+ flags, !fallback);
+
+ return block;
+}
+
/* Return the highest-address free block of at least @order. */
static struct gpu_buddy_block *
get_maxblock(struct gpu_buddy *mm,
@@ -1924,7 +1925,7 @@ __gpu_buddy_alloc_blocks(struct gpu_buddy *mm,
if (flags & GPU_BUDDY_RANGE_ALLOCATION) {
/* Allocate traversing within the range */
- block = __alloc_range_bias(mm, start, end, order, flags);
+ block = __gpu_buddy_alloc_range_bias(mm, start, end, order,
flags);
if (!IS_ERR(block) || !steered)
return block;
diff --git a/drivers/gpu/tests/gpu_buddy_test.c
b/drivers/gpu/tests/gpu_buddy_test.c
index 2c6f1da1a6d1..9aaca2fc6a02 100644
--- a/drivers/gpu/tests/gpu_buddy_test.c
+++ b/drivers/gpu/tests/gpu_buddy_test.c
@@ -1606,6 +1606,89 @@ static int gpu_buddy_suite_init(struct kunit_suite
*suite)
return 0;
}
+static void gpu_test_buddy_alloc_range_clear_guard(struct kunit *test)
+{
+ const unsigned long chunk = SZ_1M, mm_size = SZ_4M;
+ struct gpu_buddy_block *block;
+ LIST_HEAD(low_dirty);
+ LIST_HEAD(high_a);
+ LIST_HEAD(high_b);
+ LIST_HEAD(barrier);
+ LIST_HEAD(dirty_res);
+ LIST_HEAD(clear_res);
+ struct gpu_buddy mm;
+
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, chunk),
+ "buddy_init failed\n");
+
+ /*
+ * Idea is to lay out a range allocation as a low dirty block, an
+ * allocated barrier, and a high naturally-aligned clear extent, then
+ * issue a dirty range allocation. It must take the low dirty block and
+ * leave the clear extent intact; if it instead cuts the clear extent,
+ * a following same-class clear allocation can no longer find a
+ * contiguous clear run and fails with -ENOSPC.
+ *
+ * [0, 1M) dirty free
+ * [1M, 2M) allocated (barrier, keeps the halves un-mergeable)
+ * [2M, 4M) clear free (one naturally aligned 2 MiB extent)
+ */
+ KUNIT_ASSERT_FALSE_MSG(test,
+ gpu_buddy_alloc_blocks(&mm, 0, chunk, chunk,
chunk,
+ &low_dirty,
GPU_BUDDY_RANGE_ALLOCATION),
+ "alloc [0, 1M) failed\n");
+ KUNIT_ASSERT_FALSE_MSG(test,
+ gpu_buddy_alloc_blocks(&mm, chunk, 2 * chunk,
chunk, chunk,
+ &barrier,
GPU_BUDDY_RANGE_ALLOCATION),
+ "alloc [1M, 2M) failed\n");
+ KUNIT_ASSERT_FALSE_MSG(test,
+ gpu_buddy_alloc_blocks(&mm, 2 * chunk, 3 *
chunk, chunk, chunk,
+ &high_a,
GPU_BUDDY_RANGE_ALLOCATION),
+ "alloc [2M, 3M) failed\n");
+ KUNIT_ASSERT_FALSE_MSG(test,
+ gpu_buddy_alloc_blocks(&mm, 3 * chunk, 4 *
chunk, chunk, chunk,
+ &high_b,
GPU_BUDDY_RANGE_ALLOCATION),
+ "alloc [3M, 4M) failed\n");
+
+ /* [2M, 4M) coalesces into one aligned clear extent; [0, 1M) stays
dirty. */
+ gpu_buddy_free_list(&mm, &low_dirty, 0);
+ gpu_buddy_free_list(&mm, &high_a, GPU_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &high_b, GPU_BUDDY_CLEARED);
+
+ /* Dirty 1 MiB range alloc: must land at [0, 1M), not cut the clear
extent. */
+ KUNIT_ASSERT_FALSE_MSG(test,
+ gpu_buddy_alloc_blocks(&mm, 0, mm_size, chunk,
chunk,
+ &dirty_res,
GPU_BUDDY_RANGE_ALLOCATION),
+ "dirty range alloc failed\n");
+ block = list_first_entry(&dirty_res, struct gpu_buddy_block, link);
+ KUNIT_EXPECT_FALSE_MSG(test, gpu_buddy_block_is_clear(block),
+ "dirty range alloc cut the clear extent
(offset=%llx)\n",
+ gpu_buddy_block_offset(block));
+ KUNIT_EXPECT_EQ(test, gpu_buddy_block_offset(block), 0ULL);
+
+ /*
+ * The 2 MiB clear extent must still be intact: a clear order-1 range
+ * allocation has to succeed. Without the guard the extent was cut
+ * above and this returns -ENOSPC.
+ */
+ KUNIT_EXPECT_FALSE_MSG(test,
+ gpu_buddy_alloc_blocks(&mm, 0, mm_size, 2 *
chunk, 2 * chunk,
+ &clear_res,
+
GPU_BUDDY_RANGE_ALLOCATION |
+
GPU_BUDDY_CLEAR_ALLOCATION),
+ "clear 2M range alloc failed: clear extent was
fragmented (-ENOSPC)\n");
+ if (!list_empty(&clear_res)) {
+ block = list_first_entry(&clear_res, struct gpu_buddy_block,
link);
+ KUNIT_EXPECT_TRUE(test, gpu_buddy_block_is_clear(block));
+ KUNIT_EXPECT_EQ(test, gpu_buddy_block_offset(block), (u64)(2 *
chunk));
+ }
+
+ gpu_buddy_free_list(&mm, &clear_res, GPU_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &dirty_res, 0);
+ gpu_buddy_free_list(&mm, &barrier, 0);
+ gpu_buddy_fini(&mm);
+}
+
static struct kunit_case gpu_buddy_tests[] = {
KUNIT_CASE(gpu_test_buddy_alloc_limit),
KUNIT_CASE(gpu_test_buddy_alloc_optimistic),
@@ -1615,6 +1698,7 @@ static struct kunit_case gpu_buddy_tests[] = {
KUNIT_CASE(gpu_test_buddy_alloc_clear),
KUNIT_CASE(gpu_test_buddy_alloc_range),
KUNIT_CASE(gpu_test_buddy_alloc_range_bias),
+ KUNIT_CASE(gpu_test_buddy_alloc_range_clear_guard),
KUNIT_CASE_SLOW(gpu_test_buddy_fragmentation_performance),
KUNIT_CASE_SLOW(gpu_test_buddy_dirty_tracker_performance),
KUNIT_CASE(gpu_test_buddy_alloc_exceeds_max_order),
base-commit: 6f7098738fff3ec7393f924343188cb8e6ebc5d2
--
2.43.0
