sst-linux/include/linux/io_uring.h
Jann Horn c034ce2668 io_uring: Fix registered ring file refcount leak
commit 12d908116f7efd34f255a482b9afc729d7a5fb78 upstream.

Currently, io_uring_unreg_ringfd() (which cleans up registered rings) is
only called on exit, but __io_uring_free (which frees the tctx in which the
registered ring pointers are stored) is also called on execve (via
begin_new_exec -> io_uring_task_cancel -> __io_uring_cancel ->
io_uring_cancel_generic -> __io_uring_free).

This means: A process going through execve while having registered rings
will leak references to the rings' `struct file`.

Fix it by zapping registered rings on execve(). This is implemented by
moving the io_uring_unreg_ringfd() from io_uring_files_cancel() into its
callee __io_uring_cancel(), which is called from io_uring_task_cancel() on
execve.

This could probably be exploited *on 32-bit kernels* by leaking 2^32
references to the same ring, because the file refcount is stored in a
pointer-sized field and get_file() doesn't have protection against
refcount overflow, just a WARN_ONCE(); but on 64-bit it should have no
impact beyond a memory leak.

Cc: stable@vger.kernel.org
Fixes: e7a6c00dc7 ("io_uring: add support for registering ring file descriptors")
Signed-off-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/r/20241218-uring-reg-ring-cleanup-v1-1-8f63e999045b@google.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-12-27 13:53:00 +01:00

100 lines
2.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _LINUX_IO_URING_H
#define _LINUX_IO_URING_H
#include <linux/sched.h>
#include <linux/xarray.h>
#include <uapi/linux/io_uring.h>
enum io_uring_cmd_flags {
IO_URING_F_COMPLETE_DEFER = 1,
IO_URING_F_UNLOCKED = 2,
/* int's last bit, sign checks are usually faster than a bit test */
IO_URING_F_NONBLOCK = INT_MIN,
/* ctx state flags, for URING_CMD */
IO_URING_F_SQE128 = 4,
IO_URING_F_CQE32 = 8,
IO_URING_F_IOPOLL = 16,
/* the request is executed from poll, it should not be freed */
IO_URING_F_MULTISHOT = 32,
};
struct io_uring_cmd {
struct file *file;
const void *cmd;
union {
/* callback to defer completions to task context */
void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
/* used for polled completion */
void *cookie;
};
u32 cmd_op;
u32 flags;
u8 pdu[32]; /* available inline for free use */
};
#if defined(CONFIG_IO_URING)
int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
struct iov_iter *iter, void *ioucmd);
void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
unsigned issue_flags);
void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
void (*task_work_cb)(struct io_uring_cmd *, unsigned));
void __io_uring_cancel(bool cancel_all);
void __io_uring_free(struct task_struct *tsk);
void io_uring_unreg_ringfd(void);
const char *io_uring_get_opcode(u8 opcode);
bool io_is_uring_fops(struct file *file);
static inline void io_uring_files_cancel(void)
{
if (current->io_uring)
__io_uring_cancel(false);
}
static inline void io_uring_task_cancel(void)
{
if (current->io_uring)
__io_uring_cancel(true);
}
static inline void io_uring_free(struct task_struct *tsk)
{
if (tsk->io_uring)
__io_uring_free(tsk);
}
#else
static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
struct iov_iter *iter, void *ioucmd)
{
return -EOPNOTSUPP;
}
static inline bool io_is_uring_fops(struct file *file)
{
return false;
}
static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
ssize_t ret2, unsigned issue_flags)
{
}
static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
void (*task_work_cb)(struct io_uring_cmd *, unsigned))
{
}
static inline void io_uring_task_cancel(void)
{
}
static inline void io_uring_files_cancel(void)
{
}
static inline void io_uring_free(struct task_struct *tsk)
{
}
static inline const char *io_uring_get_opcode(u8 opcode)
{
return "";
}
#endif
#endif