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, 108 insertions, 0 deletions

diff --git a/io_uring/advise.c b/io_uring/advise.c
new file mode 100644
index 000000000..0073f74e3
--- /dev/null
+++ b/io_uring/advise.c
@@ -0,0 +1,108 @@
+// 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 <uapi/linux/fadvise.h>
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "advise.h"
+
+struct io_fadvise {
+	struct file			*file;
+	u64				offset;
+	u64				len;
+	u32				advice;
+};
+
+struct io_madvise {
+	struct file			*file;
+	u64				addr;
+	u64				len;
+	u32				advice;
+};
+
+int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	struct io_madvise *ma = io_kiocb_to_cmd(req, struct io_madvise);
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	ma->addr = READ_ONCE(sqe->addr);
+	ma->len = READ_ONCE(sqe->off);
+	if (!ma->len)
+		ma->len = READ_ONCE(sqe->len);
+	ma->advice = READ_ONCE(sqe->fadvise_advice);
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+int io_madvise(struct io_kiocb *req, unsigned int issue_flags)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	struct io_madvise *ma = io_kiocb_to_cmd(req, struct io_madvise);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static bool io_fadvise_force_async(struct io_fadvise *fa)
+{
+	switch (fa->advice) {
+	case POSIX_FADV_NORMAL:
+	case POSIX_FADV_RANDOM:
+	case POSIX_FADV_SEQUENTIAL:
+		return false;
+	default:
+		return true;
+	}
+}
+
+int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_fadvise *fa = io_kiocb_to_cmd(req, struct io_fadvise);
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+
+	fa->offset = READ_ONCE(sqe->off);
+	fa->len = READ_ONCE(sqe->addr);
+	if (!fa->len)
+		fa->len = READ_ONCE(sqe->len);
+	fa->advice = READ_ONCE(sqe->fadvise_advice);
+	if (io_fadvise_force_async(fa))
+		req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_fadvise(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_fadvise *fa = io_kiocb_to_cmd(req, struct io_fadvise);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK && io_fadvise_force_async(fa));
+
+	ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}