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, 114 insertions, 0 deletions

diff --git a/io_uring/sync.c b/io_uring/sync.c
new file mode 100644
index 000000000..ab7fa1cd7
--- /dev/null
+++ b/io_uring/sync.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/io_uring.h>
+#include <linux/fsnotify.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "sync.h"
+
+struct io_sync {
+	struct file			*file;
+	loff_t				len;
+	loff_t				off;
+	int				flags;
+	int				mode;
+};
+
+int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+
+	if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
+		return -EINVAL;
+
+	sync->off = READ_ONCE(sqe->off);
+	sync->len = READ_ONCE(sqe->len);
+	sync->flags = READ_ONCE(sqe->sync_range_flags);
+	req->flags |= REQ_F_FORCE_ASYNC;
+
+	return 0;
+}
+
+int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+	int ret;
+
+	/* sync_file_range always requires a blocking context */
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = sync_file_range(req->file, sync->off, sync->len, sync->flags);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+
+	if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
+		return -EINVAL;
+
+	sync->flags = READ_ONCE(sqe->fsync_flags);
+	if (unlikely(sync->flags & ~IORING_FSYNC_DATASYNC))
+		return -EINVAL;
+
+	sync->off = READ_ONCE(sqe->off);
+	if (sync->off < 0)
+		return -EINVAL;
+	sync->len = READ_ONCE(sqe->len);
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_fsync(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+	loff_t end = sync->off + sync->len;
+	int ret;
+
+	/* fsync always requires a blocking context */
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = vfs_fsync_range(req->file, sync->off, end > 0 ? end : LLONG_MAX,
+				sync->flags & IORING_FSYNC_DATASYNC);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+int io_fallocate_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+
+	if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
+		return -EINVAL;
+
+	sync->off = READ_ONCE(sqe->off);
+	sync->len = READ_ONCE(sqe->addr);
+	sync->mode = READ_ONCE(sqe->len);
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_fallocate(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_sync *sync = io_kiocb_to_cmd(req, struct io_sync);
+	int ret;
+
+	/* fallocate always requiring blocking context */
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = vfs_fallocate(req->file, sync->mode, sync->off, sync->len);
+	if (ret >= 0)
+		fsnotify_modify(req->file);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}