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, 76 insertions, 0 deletions

diff --git a/mm/failslab.c b/mm/failslab.c
new file mode 100644
index 000000000..c3901b136
--- /dev/null
+++ b/mm/failslab.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fault-inject.h>
+#include <linux/error-injection.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include "slab.h"
+
+static struct {
+	struct fault_attr attr;
+	bool ignore_gfp_reclaim;
+	bool cache_filter;
+} failslab = {
+	.attr = FAULT_ATTR_INITIALIZER,
+	.ignore_gfp_reclaim = true,
+	.cache_filter = false,
+};
+
+int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+{
+	int flags = 0;
+
+	/* No fault-injection for bootstrap cache */
+	if (unlikely(s == kmem_cache))
+		return 0;
+
+	if (gfpflags & __GFP_NOFAIL)
+		return 0;
+
+	if (failslab.ignore_gfp_reclaim &&
+			(gfpflags & __GFP_DIRECT_RECLAIM))
+		return 0;
+
+	if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB))
+		return 0;
+
+	/*
+	 * In some cases, it expects to specify __GFP_NOWARN
+	 * to avoid printing any information(not just a warning),
+	 * thus avoiding deadlocks. See commit 6b9dbedbe349 for
+	 * details.
+	 */
+	if (gfpflags & __GFP_NOWARN)
+		flags |= FAULT_NOWARN;
+
+	return should_fail_ex(&failslab.attr, s->object_size, flags) ? -ENOMEM : 0;
+}
+ALLOW_ERROR_INJECTION(should_failslab, ERRNO);
+
+static int __init setup_failslab(char *str)
+{
+	return setup_fault_attr(&failslab.attr, str);
+}
+__setup("failslab=", setup_failslab);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+static int __init failslab_debugfs_init(void)
+{
+	struct dentry *dir;
+	umode_t mode = S_IFREG | 0600;
+
+	dir = fault_create_debugfs_attr("failslab", NULL, &failslab.attr);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+
+	debugfs_create_bool("ignore-gfp-wait", mode, dir,
+			    &failslab.ignore_gfp_reclaim);
+	debugfs_create_bool("cache-filter", mode, dir,
+			    &failslab.cache_filter);
+
+	return 0;
+}
+
+late_initcall(failslab_debugfs_init);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */