From b98186aee22fa593bc8c6b2c5d839c2ee518bc8c Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 17 Nov 2022 18:40:14 +0000 Subject: [PATCH 1/5] io_uring: update res mask in io_poll_check_events When io_poll_check_events() collides with someone attempting to queue a task work, it'll spin for one more time. However, it'll continue to use the mask from the first iteration instead of updating it. For example, if the first wake up was a EPOLLIN and the second EPOLLOUT, the userspace will not get EPOLLOUT in time. Clear the mask for all subsequent iterations to force vfs_poll(). Cc: stable@vger.kernel.org Fixes: aa43477b04025 ("io_uring: poll rework") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/2dac97e8f691231049cb259c4ae57e79e40b537c.1668710222.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/poll.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/poll.c b/io_uring/poll.c index f500506984ec..90920abf91ff 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -258,6 +258,9 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) return ret; } + /* force the next iteration to vfs_poll() */ + req->cqe.res = 0; + /* * Release all references, retry if someone tried to restart * task_work while we were executing it. From 539bcb57da2f58886d7d5c17134236b0ec9cd15d Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 17 Nov 2022 18:40:15 +0000 Subject: [PATCH 2/5] io_uring: fix tw losing poll events We may never try to process a poll wake and its mask if there was multiple wake ups racing for queueing up a tw. Force io_poll_check_events() to update the mask by vfs_poll(). Cc: stable@vger.kernel.org Fixes: aa43477b04025 ("io_uring: poll rework") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/00344d60f8b18907171178d7cf598de71d127b0b.1668710222.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/poll.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/io_uring/poll.c b/io_uring/poll.c index 90920abf91ff..c34019b18211 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -228,6 +228,13 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) return IOU_POLL_DONE; if (v & IO_POLL_CANCEL_FLAG) return -ECANCELED; + /* + * cqe.res contains only events of the first wake up + * and all others are be lost. Redo vfs_poll() to get + * up to date state. + */ + if ((v & IO_POLL_REF_MASK) != 1) + req->cqe.res = 0; /* the mask was stashed in __io_poll_execute */ if (!req->cqe.res) { From 91482864768a874c4290ef93b84a78f4f1dac51b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 17 Nov 2022 18:40:16 +0000 Subject: [PATCH 3/5] io_uring: fix multishot accept request leaks Having REQ_F_POLLED set doesn't guarantee that the request is executed as a multishot from the polling path. Fortunately for us, if the code thinks it's multishot issue when it's not, it can only ask to skip completion so leaking the request. Use issue_flags to mark multipoll issues. Cc: stable@vger.kernel.org Fixes: 390ed29b5e425 ("io_uring: add IORING_ACCEPT_MULTISHOT for accept") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/7700ac57653f2823e30b34dc74da68678c0c5f13.1668710222.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 3 +++ io_uring/io_uring.c | 2 +- io_uring/io_uring.h | 4 ++-- io_uring/net.c | 7 ++----- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 43bc8a2edccf..0ded9e271523 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -16,6 +16,9 @@ enum io_uring_cmd_flags { 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 { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4a1e482747cc..8840cf3e20f2 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1768,7 +1768,7 @@ int io_poll_issue(struct io_kiocb *req, bool *locked) io_tw_lock(req->ctx, locked); if (unlikely(req->task->flags & PF_EXITING)) return -EFAULT; - return io_issue_sqe(req, IO_URING_F_NONBLOCK); + return io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_MULTISHOT); } struct io_wq_work *io_wq_free_work(struct io_wq_work *work) diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index e99a79f2df9b..cef5ff924e63 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -17,8 +17,8 @@ enum { IOU_ISSUE_SKIP_COMPLETE = -EIOCBQUEUED, /* - * Intended only when both REQ_F_POLLED and REQ_F_APOLL_MULTISHOT - * are set to indicate to the poll runner that multishot should be + * Intended only when both IO_URING_F_MULTISHOT is passed + * to indicate to the poll runner that multishot should be * removed and the result is set on req->cqe.res. */ IOU_STOP_MULTISHOT = -ECANCELED, diff --git a/io_uring/net.c b/io_uring/net.c index 15dea91625e2..a390d3ea486c 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1289,8 +1289,7 @@ retry: * return EAGAIN to arm the poll infra since it * has already been done */ - if ((req->flags & IO_APOLL_MULTI_POLLED) == - IO_APOLL_MULTI_POLLED) + if (issue_flags & IO_URING_F_MULTISHOT) ret = IOU_ISSUE_SKIP_COMPLETE; return ret; } @@ -1315,9 +1314,7 @@ retry: goto retry; io_req_set_res(req, ret, 0); - if (req->flags & REQ_F_POLLED) - return IOU_STOP_MULTISHOT; - return IOU_OK; + return (issue_flags & IO_URING_F_MULTISHOT) ? IOU_STOP_MULTISHOT : IOU_OK; } int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) From 100d6b17c06ee4c2b42fdddf0fe4ab77c86eb77e Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 17 Nov 2022 18:40:17 +0000 Subject: [PATCH 4/5] io_uring: fix multishot recv request leaks Having REQ_F_POLLED set doesn't guarantee that the request is executed as a multishot from the polling path. Fortunately for us, if the code thinks it's multishot issue when it's not, it can only ask to skip completion so leaking the request. Use issue_flags to mark multipoll issues. Cc: stable@vger.kernel.org Fixes: 1300ebb20286b ("io_uring: multishot recv") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/37762040ba9c52b81b92a2f5ebfd4ee484088951.1668710222.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/net.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/io_uring/net.c b/io_uring/net.c index a390d3ea486c..ab83da7e80f0 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -67,8 +67,6 @@ struct io_sr_msg { struct io_kiocb *notif; }; -#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED) - int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown); @@ -591,7 +589,8 @@ static inline void io_recv_prep_retry(struct io_kiocb *req) * again (for multishot). */ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, - unsigned int cflags, bool mshot_finished) + unsigned int cflags, bool mshot_finished, + unsigned issue_flags) { if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { io_req_set_res(req, *ret, cflags); @@ -614,7 +613,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret, io_req_set_res(req, *ret, cflags); - if (req->flags & REQ_F_POLLED) + if (issue_flags & IO_URING_F_MULTISHOT) *ret = IOU_STOP_MULTISHOT; else *ret = IOU_OK; @@ -773,8 +772,7 @@ retry_multishot: if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) { ret = io_setup_async_msg(req, kmsg, issue_flags); - if (ret == -EAGAIN && (req->flags & IO_APOLL_MULTI_POLLED) == - IO_APOLL_MULTI_POLLED) { + if (ret == -EAGAIN && (issue_flags & IO_URING_F_MULTISHOT)) { io_kbuf_recycle(req, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } @@ -803,7 +801,7 @@ retry_multishot: if (kmsg->msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - if (!io_recv_finish(req, &ret, cflags, mshot_finished)) + if (!io_recv_finish(req, &ret, cflags, mshot_finished, issue_flags)) goto retry_multishot; if (mshot_finished) { @@ -869,7 +867,7 @@ retry_multishot: ret = sock_recvmsg(sock, &msg, flags); if (ret < min_ret) { if (ret == -EAGAIN && force_nonblock) { - if ((req->flags & IO_APOLL_MULTI_POLLED) == IO_APOLL_MULTI_POLLED) { + if (issue_flags & IO_URING_F_MULTISHOT) { io_kbuf_recycle(req, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } @@ -902,7 +900,7 @@ out_free: if (msg.msg_inq) cflags |= IORING_CQE_F_SOCK_NONEMPTY; - if (!io_recv_finish(req, &ret, cflags, ret <= 0)) + if (!io_recv_finish(req, &ret, cflags, ret <= 0, issue_flags)) goto retry_multishot; return ret; From 7fdbc5f014c3f71bc44673a2d6c5bb2d12d45f25 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Fri, 18 Nov 2022 15:41:41 +0000 Subject: [PATCH 5/5] io_uring: disallow self-propelled ring polling When we post a CQE we wake all ring pollers as it normally should be. However, if a CQE was generated by a multishot poll request targeting its own ring, it'll wake that request up, which will make it to post a new CQE, which will wake the request and so on until it exhausts all CQ entries. Don't allow multishot polling io_uring files but downgrade them to oneshots, which was always stated as a correct behaviour that the userspace should check for. Cc: stable@vger.kernel.org Fixes: aa43477b04025 ("io_uring: poll rework") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/3124038c0e7474d427538c2d915335ec28c92d21.1668785722.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/poll.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/io_uring/poll.c b/io_uring/poll.c index c34019b18211..055632e9092a 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -246,6 +246,8 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) continue; if (req->apoll_events & EPOLLONESHOT) return IOU_POLL_DONE; + if (io_is_uring_fops(req->file)) + return IOU_POLL_DONE; /* multishot, just fill a CQE and proceed */ if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {