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, 54 insertions, 0 deletions

diff --git a/lib/bucket_locks.c b/lib/bucket_locks.c
new file mode 100644
index 000000000..d29516ca0
--- /dev/null
+++ b/lib/bucket_locks.c
@@ -0,0 +1,54 @@
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/* Allocate an array of spinlocks to be accessed by a hash. Two arguments
+ * indicate the number of elements to allocate in the array. max_size
+ * gives the maximum number of elements to allocate. cpu_mult gives
+ * the number of locks per CPU to allocate. The size is rounded up
+ * to a power of 2 to be suitable as a hash table.
+ */
+
+int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *locks_mask,
+			     size_t max_size, unsigned int cpu_mult, gfp_t gfp,
+			     const char *name, struct lock_class_key *key)
+{
+	spinlock_t *tlocks = NULL;
+	unsigned int i, size;
+#if defined(CONFIG_PROVE_LOCKING)
+	unsigned int nr_pcpus = 2;
+#else
+	unsigned int nr_pcpus = num_possible_cpus();
+#endif
+
+	if (cpu_mult) {
+		nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL);
+		size = min_t(unsigned int, nr_pcpus * cpu_mult, max_size);
+	} else {
+		size = max_size;
+	}
+
+	if (sizeof(spinlock_t) != 0) {
+		tlocks = kvmalloc_objs(spinlock_t, size, gfp);
+		if (!tlocks)
+			return -ENOMEM;
+		for (i = 0; i < size; i++) {
+			spin_lock_init(&tlocks[i]);
+			lockdep_init_map(&tlocks[i].dep_map, name, key, 0);
+		}
+	}
+
+	*locks = tlocks;
+	*locks_mask = size - 1;
+
+	return 0;
+}
+EXPORT_SYMBOL(__alloc_bucket_spinlocks);
+
+void free_bucket_spinlocks(spinlock_t *locks)
+{
+	kvfree(locks);
+}
+EXPORT_SYMBOL(free_bucket_spinlocks);