ARM: 9485/1: mm: acquire mmap write lock around show_pte() for user faultsgrafted

When CONFIG_DEBUG_USER=y, and cmdline "user_debug=31" is set,
a user fault may trigger show_pte() without any lock.
If another thread in the same process concurrently calls munmap(),
the page table pages may be freed while show_pte() is still traversing
them, causing a use-after-free in show_pte().

If CONFIG_ARM_LPAE=y, this may cause a kernel panic if the pages table
of PMD are freed when show_pte() is running.

Acquire mmap_write_lock() around show_pte() for user faults to fix the
contention.

For user faults, additionally restrict that show_pte() is called only
when the addr is a user-space address (addr < TASK_SIZE). This is because
the lock of tsk->mm only protects the virtual memory of user address space,
furthermore, dumping the page tables of a kernel-space address for user
faults is unnecessary and may have security implications.

Keep everything unchanged for kernel faults, because the kernel is
already in the "oops" state, acquiring a lock may risk a deadlock.

Co-developed-by: Qi Xi <xiqi2@huawei.com>

Fixes: 6d021b724481 ("ARM: dump pgd, pmd and pte states on unhandled data abort faults")
Link: https://lore.kernel.org/20260716014022.2823-1-xieyuanbin1@huawei.com
Acked-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Linus Walleij <linusw@kernel.org>
Signed-off-by: Qi Xi <xiqi2@huawei.com>
Signed-off-by: Xie Yuanbin <xieyuanbin1@huawei.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>

1 files changed, 68 insertions, 0 deletions

diff --git a/io_uring/statx.c b/io_uring/statx.c
new file mode 100644
index 000000000..7bcae4a6c
--- /dev/null
+++ b/io_uring/statx.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "../fs/internal.h"
+
+#include "io_uring.h"
+#include "statx.h"
+
+struct io_statx {
+	struct file			*file;
+	int				dfd;
+	unsigned int			mask;
+	unsigned int			flags;
+	struct delayed_filename		filename;
+	struct statx __user		*buffer;
+};
+
+int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_statx *sx = io_kiocb_to_cmd(req, struct io_statx);
+	const char __user *path;
+	int ret;
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+	if (req->flags & REQ_F_FIXED_FILE)
+		return -EBADF;
+
+	sx->dfd = READ_ONCE(sqe->fd);
+	sx->mask = READ_ONCE(sqe->len);
+	path = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	sx->buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	sx->flags = READ_ONCE(sqe->statx_flags);
+
+	ret = delayed_getname_uflags(&sx->filename, path, sx->flags);
+
+	if (unlikely(ret))
+		return ret;
+
+	req->flags |= REQ_F_NEED_CLEANUP;
+	req->flags |= REQ_F_FORCE_ASYNC;
+	return 0;
+}
+
+int io_statx(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_statx *sx = io_kiocb_to_cmd(req, struct io_statx);
+	CLASS(filename_complete_delayed, name)(&sx->filename);
+	int ret;
+
+	WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK);
+
+	ret = do_statx(sx->dfd, name, sx->flags, sx->mask, sx->buffer);
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}
+
+void io_statx_cleanup(struct io_kiocb *req)
+{
+	struct io_statx *sx = io_kiocb_to_cmd(req, struct io_statx);
+
+	dismiss_delayed_filename(&sx->filename);
+}