forbid fix {SQ,IO}POLL
v2 cover forbid fix {SQ,IO}POLL
The first one adds checks {SQPOLL,IOPOLL}. IOPOLL check can be moved in the common path later, or rethinked entirely, e.g. not io_iopoll_req_issued()'ed for unsupported opcodes.
3 others are just cleanups on top.
v2: add IOPOLL to the whole bunch of opcodes in [1/4].
dirty and effective.
Pavel Begunkov (4):
io_uring: fix {SQ,IO}POLL with unsupported opcodes
io_uring: do build_open_how() only once
io_uring: deduplicate io_openat{,2}_prep()
io_uring: move send/recv IOPOLL check into prep
fs/io_uring.c | 94 ++++++++++++++++++++++++++------------------------- 1 file changed, 48 insertions(+), 46 deletions(-)
Signature · 1 line
2.24.0
PATCH v2 1/4 io_uring: fix {SQ,IO}POLL with unsupported opcodes
IORING_SETUP_IOPOLL is defined only for read/write, other opcodes should be disallowed, otherwise it'll get an error as below. Also refuse open/cloes with SQPOLL, as the polling thread wouldn't know which file table to use.
RIP: 0010:io_iopoll_getevents+0x111/0x5a0 Call Trace: ? _raw_spin_unlock_irqrestore+0x24/0x40 ? do_send_sig_info+0x64/0x90 io_iopoll_reap_events.part.0+0x5e/0xa0 io_ring_ctx_wait_and_kill+0x132/0x1c0 io_uring_release+0x20/0x30 __fput+0xcd/0x230 ____fput+0xe/0x10 task_work_run+0x67/0xa0 do_exit+0x353/0xb10 ? handle_mm_fault+0xd4/0x200 ? syscall_trace_enter+0x18c/0x2c0 do_group_exit+0x43/0xa0 __x64_sys_exit_group+0x18/0x20 do_syscall_64+0x60/0x1e0 entry_SYSCALL_64_after_hwframe+0x44/0xa9
--- fs/io_uring.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)
fs/io_uring.c +24 -0
@@ -2765,6 +2765,8 @@ static int __io_splice_prep(struct io_kiocb *req,if (req->flags &REQ_F_NEED_CLEANUP )return 0 ; +if (unlikely (ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; sp->file_in =NULL ; sp->len =READ_ONCE (sqe->len);
@@ -2965,6 +2967,8 @@ static int io_fallocate_prep(struct io_kiocb *req, {if (sqe->ioprio || sqe->buf_index || sqe->rw_flags)return -EINVAL ; +if (unlikely (ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; req->sync.off =READ_ONCE (sqe->off); req->sync.len =READ_ONCE (sqe->addr);
@@ -2990,6 +2994,8 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)const char __user *fname;int ret; +if (unlikely (req->ctx->flags & (IORING_SETUP_IOPOLL |IORING_SETUP_SQPOLL ))) +return -EINVAL ;if (sqe->ioprio || sqe->buf_index)return -EINVAL ;if (req->flags &REQ_F_FIXED_FILE )
@@ -3023,6 +3029,8 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)size_t len;int ret; +if (unlikely (req->ctx->flags & (IORING_SETUP_IOPOLL |IORING_SETUP_SQPOLL ))) +return -EINVAL ;if (sqe->ioprio || sqe->buf_index)return -EINVAL ;if (req->flags &REQ_F_FIXED_FILE )
@@ -3107,6 +3115,8 @@ static int io_remove_buffers_prep(struct io_kiocb *req,if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off)return -EINVAL ; +if (unlikely (ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; tmp =READ_ONCE (sqe->fd);if (!tmp || tmp >USHRT_MAX )
@@ -3174,6 +3184,8 @@ static int io_provide_buffers_prep(struct io_kiocb *req,struct io_provide_buf *p = &req->pbuf;u64 tmp; +if (unlikely (ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ;if (sqe->ioprio || sqe->rw_flags)return -EINVAL ;
@@ -3262,6 +3274,8 @@ static int io_epoll_ctl_prep(struct io_kiocb *req,#if defined(CONFIG_EPOLL )if (sqe->ioprio || sqe->buf_index)return -EINVAL ; +if (unlikely (ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; req->epoll.epfd =READ_ONCE (sqe->fd); req->epoll.op =READ_ONCE (sqe->len);
@@ -3306,6 +3320,8 @@ static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)#if defined(CONFIG_ADVISE_SYSCALLS ) && defined(CONFIG_MMU )if (sqe->ioprio || sqe->buf_index || sqe->off)return -EINVAL ; +if (unlikely (ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; req->madvise.addr =READ_ONCE (sqe->addr); req->madvise.len =READ_ONCE (sqe->len);
@@ -3340,6 +3356,8 @@ static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) {if (sqe->ioprio || sqe->buf_index || sqe->addr)return -EINVAL ; +if (unlikely (ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; req->fadvise.offset =READ_ONCE (sqe->off); req->fadvise.len =READ_ONCE (sqe->len);
@@ -3373,6 +3391,8 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock)static int io_statx_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) { +if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ;if (sqe->ioprio || sqe->buf_index)return -EINVAL ;if (req->flags &REQ_F_FIXED_FILE )
@@ -3417,6 +3437,8 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)*/ req->work.flags |=IO_WQ_WORK_NO_CANCEL ; +if (unlikely (req->ctx->flags & (IORING_SETUP_IOPOLL |IORING_SETUP_SQPOLL ))) +return -EINVAL ;if (sqe->ioprio || sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index)return -EINVAL ;
@@ -4906,6 +4928,8 @@ static int io_files_update_prep(struct io_kiocb *req, {if (sqe->flags || sqe->ioprio || sqe->rw_flags)return -EINVAL ; +if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; req->files_update.offset =READ_ONCE (sqe->off); req->files_update.nr_args =READ_ONCE (sqe->len);
Signature · 1 line
2.24.0
PATCH v2 2/4 io_uring: do build_open_how() only once
In reply to Pavel Begunkovbuild_open_how() is just adjusting open_flags/mode. Do it once during prep. It looks better than storing raw values for the future.
--- fs/io_uring.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)
fs/io_uring.c +7 -6
@@ -2992,6 +2992,7 @@ static int io_fallocate(struct io_kiocb *req, bool force_nonblock)static int io_openat_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) {const char __user *fname; +u64 flags, mode;int ret;if (unlikely (req->ctx->flags & (IORING_SETUP_IOPOLL |IORING_SETUP_SQPOLL )))
@@ -3003,13 +3004,14 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)if (req->flags &REQ_F_NEED_CLEANUP )return 0 ; - req->open.dfd =READ_ONCE (sqe->fd); - req->open.how.mode =READ_ONCE (sqe->len); - fname =u64_to_user_ptr (READ_ONCE (sqe->addr)); - req->open.how.flags =READ_ONCE (sqe->open_flags); + mode =READ_ONCE (sqe->len); + flags =READ_ONCE (sqe->open_flags);if (force_o_largefile ()) - req->open.how.flags |=O_LARGEFILE ; + flags |=O_LARGEFILE ; + req->open.how =build_open_how (flags, mode); + req->open.dfd =READ_ONCE (sqe->fd); + fname =u64_to_user_ptr (READ_ONCE (sqe->addr)); req->open.filename =getname (fname);if (IS_ERR (req->open.filename)) { ret =PTR_ERR (req->open.filename);
@@ -3103,7 +3105,6 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock)static int io_openat (struct io_kiocb *req,bool force_nonblock) { - req->open.how =build_open_how (req->open.how.flags, req->open.how.mode);return io_openat2 (req, force_nonblock); }
Signature · 1 line
2.24.0
PATCH v2 4/4 io_uring: move send/recv IOPOLL check into prep
In reply to Pavel BegunkovFail recv/send in case of IORING_SETUP_IOPOLL earlier during prep, so it'd be done only once. Removes duplication as well
--- fs/io_uring.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-)
fs/io_uring.c +6 -12
@@ -3555,6 +3555,9 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)struct io_async_ctx *io = req->io;int ret; +if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; + sr->msg_flags =READ_ONCE (sqe->msg_flags); sr->msg =u64_to_user_ptr (READ_ONCE (sqe->addr)); sr->len =READ_ONCE (sqe->len);
@@ -3584,9 +3587,6 @@ static int io_sendmsg(struct io_kiocb *req, bool force_nonblock)struct socket *sock;int ret; -if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) -return -EINVAL ; - sock =sock_from_file (req->file, &ret);if (sock) {struct io_async_ctx io;
@@ -3640,9 +3640,6 @@ static int io_send(struct io_kiocb *req, bool force_nonblock)struct socket *sock;int ret; -if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) -return -EINVAL ; - sock =sock_from_file (req->file, &ret);if (sock) {struct io_sr_msg *sr = &req->sr_msg;
@@ -3795,6 +3792,9 @@ static int io_recvmsg_prep(struct io_kiocb *req,struct io_async_ctx *io = req->io;int ret; +if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) +return -EINVAL ; + sr->msg_flags =READ_ONCE (sqe->msg_flags); sr->msg =u64_to_user_ptr (READ_ONCE (sqe->addr)); sr->len =READ_ONCE (sqe->len);
@@ -3823,9 +3823,6 @@ static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)struct socket *sock;int ret, cflags =0 ; -if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) -return -EINVAL ; - sock =sock_from_file (req->file, &ret);if (sock) {struct io_buffer *kbuf;
@@ -3887,9 +3884,6 @@ static int io_recv(struct io_kiocb *req, bool force_nonblock)struct socket *sock;int ret, cflags =0 ; -if (unlikely (req->ctx->flags &IORING_SETUP_IOPOLL )) -return -EINVAL ; - sock =sock_from_file (req->file, &ret);if (sock) {struct io_sr_msg *sr = &req->sr_msg;
Signature · 1 line
2.24.0
PATCH v2 3/4 io_uring: deduplicate io_openat{,2}_prep()
In reply to Pavel Begunkovio_openat_prep() and io_openat2_prep() are identical except for how struct open_how is built. Deduplicate it with a helper.
--- fs/io_uring.c | 55 ++++++++++++++++++--------------------------------- 1 file changed, 19 insertions(+), 36 deletions(-)
fs/io_uring.c +19 -36
@@ -2989,26 +2989,21 @@ static int io_fallocate(struct io_kiocb *req, bool force_nonblock)return 0 ; } -static int io_openat_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) +static int __io_openat_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) {const char __user *fname; -u64 flags, mode;int ret;if (unlikely (req->ctx->flags & (IORING_SETUP_IOPOLL |IORING_SETUP_SQPOLL )))return -EINVAL ; -if (sqe->ioprio || sqe->buf_index) +if (unlikely (sqe->ioprio || sqe->buf_index))return -EINVAL ; -if (req->flags &REQ_F_FIXED_FILE ) +if (unlikely (req->flags &REQ_F_FIXED_FILE ))return -EBADF ; -if (req->flags &REQ_F_NEED_CLEANUP ) -return 0 ; - mode =READ_ONCE (sqe->len); - flags =READ_ONCE (sqe->open_flags); -if (force_o_largefile ()) - flags |=O_LARGEFILE ; - req->open.how =build_open_how (flags, mode); +/* open.how should be already initialised */ +if (!(req->open.how.flags &O_PATH ) &&force_o_largefile ()) + req->open.how.flags |=O_LARGEFILE ; req->open.dfd =READ_ONCE (sqe->fd); fname =u64_to_user_ptr (READ_ONCE (sqe->addr));
@@ -3018,33 +3013,33 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->open.filename =NULL ;return ret; } - req->open.nofile =rlimit (RLIMIT_NOFILE ); req->flags |=REQ_F_NEED_CLEANUP ;return 0 ; } +static int io_openat_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) +{ +u64 flags, mode; + +if (req->flags &REQ_F_NEED_CLEANUP ) +return 0 ; + mode =READ_ONCE (sqe->len); + flags =READ_ONCE (sqe->open_flags); + req->open.how =build_open_how (flags, mode); +return __io_openat_prep (req, sqe); +} +static int io_openat2_prep (struct io_kiocb *req,const struct io_uring_sqe *sqe) {struct open_how __user *how; -const char __user *fname;size_t len;int ret; -if (unlikely (req->ctx->flags & (IORING_SETUP_IOPOLL |IORING_SETUP_SQPOLL ))) -return -EINVAL ; -if (sqe->ioprio || sqe->buf_index) -return -EINVAL ; -if (req->flags &REQ_F_FIXED_FILE ) -return -EBADF ;if (req->flags &REQ_F_NEED_CLEANUP )return 0 ; - - req->open.dfd =READ_ONCE (sqe->fd); - fname =u64_to_user_ptr (READ_ONCE (sqe->addr)); how =u64_to_user_ptr (READ_ONCE (sqe->addr2)); len =READ_ONCE (sqe->len); -if (len <OPEN_HOW_SIZE_VER0 )return -EINVAL ;
@@ -3053,19 +3048,7 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)if (ret)return ret; -if (!(req->open.how.flags &O_PATH ) &&force_o_largefile ()) - req->open.how.flags |=O_LARGEFILE ; - - req->open.filename =getname (fname); -if (IS_ERR (req->open.filename)) { - ret =PTR_ERR (req->open.filename); - req->open.filename =NULL ; -return ret; - } - - req->open.nofile =rlimit (RLIMIT_NOFILE ); - req->flags |=REQ_F_NEED_CLEANUP ; -return 0 ; +return __io_openat_prep (req, sqe); }static int io_openat2 (struct io_kiocb *req,bool force_nonblock)
Signature · 1 line
2.24.0
Something went wrong, don't mind it
Quoted 19 lines · Pavel Begunkov
The first one adds checks {SQPOLL,IOPOLL}. IOPOLL check can be moved in the common path later, or rethinked entirely, e.g. not io_iopoll_req_issued()'ed for unsupported opcodes.
3 others are just cleanups on top.
v2: add IOPOLL to the whole bunch of opcodes in [1/4].
dirty and effective.Pavel Begunkov (4):
io_uring: fix {SQ,IO}POLL with unsupported opcodes
io_uring: dobuild_open_how()only once
io_uring: deduplicate io_openat{,2}_prep()
io_uring: move send/recv IOPOLL check into prepfs/io_uring.c | 94 ++++++++++++++++++++++++++------------------------- 1 file changed, 48 insertions(+), 46 deletions(-)
Signature · 1 line
Pavel Begunkov