Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

1 files changed, 70 insertions, 0 deletions

diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h
new file mode 100644
index 000000000..962b6e2d0
--- /dev/null
+++ b/io_uring/alloc_cache.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef IOU_ALLOC_CACHE_H
+#define IOU_ALLOC_CACHE_H
+
+#include <linux/io_uring_types.h>
+#include <linux/kasan.h>
+
+/*
+ * Don't allow the cache to grow beyond this size.
+ */
+#define IO_ALLOC_CACHE_MAX	128
+
+void io_alloc_cache_free(struct io_alloc_cache *cache,
+			 void (*free)(const void *));
+bool io_alloc_cache_init(struct io_alloc_cache *cache,
+			 unsigned max_nr, unsigned int size,
+			 unsigned int init_bytes);
+
+void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp);
+
+static inline bool io_alloc_cache_put(struct io_alloc_cache *cache,
+				      void *entry)
+{
+	if (cache->nr_cached < cache->max_cached) {
+		if (!kasan_mempool_poison_object(entry))
+			return false;
+		cache->entries[cache->nr_cached++] = entry;
+		return true;
+	}
+	return false;
+}
+
+static inline void *io_alloc_cache_get(struct io_alloc_cache *cache)
+{
+	if (cache->nr_cached) {
+		void *entry = cache->entries[--cache->nr_cached];
+
+		/*
+		 * If KASAN is enabled, always clear the initial bytes that
+		 * must be zeroed post alloc, in case any of them overlap
+		 * with KASAN storage.
+		 */
+#if defined(CONFIG_KASAN)
+		kasan_mempool_unpoison_object(entry, cache->elem_size);
+		if (cache->init_clear)
+			memset(entry, 0, cache->init_clear);
+#endif
+		return entry;
+	}
+
+	return NULL;
+}
+
+static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp)
+{
+	void *obj;
+
+	obj = io_alloc_cache_get(cache);
+	if (obj)
+		return obj;
+	return io_cache_alloc_new(cache, gfp);
+}
+
+static inline void io_cache_free(struct io_alloc_cache *cache, void *obj)
+{
+	if (!io_alloc_cache_put(cache, obj))
+		kvfree(obj);
+}
+
+#endif