When the per-CPU bio cache is enabled but empty, bio_alloc_percpu_cache() returns NULL and bio_alloc_bioset() falls straight through to the mempool fallback: if (unlikely(!bio)) { if (!(saved_gfp & __GFP_DIRECT_RECLAIM)) return NULL; ... } For non-sleeping allocations (no __GFP_DIRECT_RECLAIM) this returns NULL without ever attempting a slab allocation, even when there is plenty of free memory. Commit b520c4eef83d ("block: split bio_alloc_bioset more clearly into a fast and slowpath") introduced this. Before it, a percpu cache miss fell through to mempool_alloc(), which attempted the underlying slab allocation first and only failed when that slab allocation failed. The restructuring dropped the slab attempt that non-sleeping callers of a cache-enabled bioset (such as the default fs_bio_set used by bio_alloc()) relied on. Try a slab allocation with optimistic GFP_ flags before falling back to the mempool whenever the bio is still NULL, so both the cache-empty and non-cache paths share the same slab attempt. This restores the previous behavior for non-sleeping allocations. Fixes: b520c4eef83d ("block: split bio_alloc_bioset more clearly into a fast and slowpath") Suggested-by: Christoph Hellwig Signed-off-by: Joseph Qi --- block/bio.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/block/bio.c b/block/bio.c index f2a5f4d0a9672..982f2e47a4218 100644 --- a/block/bio.c +++ b/block/bio.c @@ -555,6 +555,14 @@ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, bio = bio_alloc_percpu_cache(bs); } else { opf &= ~REQ_ALLOC_CACHE; + } + + /* + * For a bioset without a percpu cache, or when the percpu cache was + * empty, try a slab allocation with optimistic GFP_ flags before + * falling back to the mempool. + */ + if (!bio) { p = kmem_cache_alloc(bs->bio_slab, gfp); if (p) bio = p + bs->front_pad; -- 2.39.3