From b820de741ae48ccf50dd95e297889c286ff4f760 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 15 Feb 2024 12:47:38 -0800 Subject: fs/aio: Restrict kiocb_set_cancel_fn() to I/O submitted via libaio If kiocb_set_cancel_fn() is called for I/O submitted via io_uring, the following kernel warning appears: WARNING: CPU: 3 PID: 368 at fs/aio.c:598 kiocb_set_cancel_fn+0x9c/0xa8 Call trace: kiocb_set_cancel_fn+0x9c/0xa8 ffs_epfile_read_iter+0x144/0x1d0 io_read+0x19c/0x498 io_issue_sqe+0x118/0x27c io_submit_sqes+0x25c/0x5fc __arm64_sys_io_uring_enter+0x104/0xab0 invoke_syscall+0x58/0x11c el0_svc_common+0xb4/0xf4 do_el0_svc+0x2c/0xb0 el0_svc+0x2c/0xa4 el0t_64_sync_handler+0x68/0xb4 el0t_64_sync+0x1a4/0x1a8 Fix this by setting the IOCB_AIO_RW flag for read and write I/O that is submitted by libaio. Suggested-by: Jens Axboe Cc: Christoph Hellwig Cc: Avi Kivity Cc: Sandeep Dhavale Cc: Jens Axboe Cc: Greg Kroah-Hartman Cc: Kent Overstreet Cc: stable@vger.kernel.org Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240215204739.2677806-2-bvanassche@acm.org Signed-off-by: Christian Brauner --- fs/aio.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'fs/aio.c') diff --git a/fs/aio.c b/fs/aio.c index bb2ff48991f3..da18dbcfcb22 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { -- cgit From 54cbc058d86beca3515c994039b5c0f0a34f53dd Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 15 Feb 2024 12:47:39 -0800 Subject: fs/aio: Make io_cancel() generate completions again The following patch accidentally removed the code for delivering completions for cancelled reads and writes to user space: "[PATCH 04/33] aio: remove retry-based AIO" (https://lore.kernel.org/all/1363883754-27966-5-git-send-email-koverstreet@google.com/) >From that patch: - if (kiocbIsCancelled(iocb)) { - ret = -EINTR; - aio_complete(iocb, ret, 0); - /* must not access the iocb after this */ - goto out; - } This leads to a leak in user space of a struct iocb. Hence this patch that restores the code that reports to user space that a read or write has been cancelled successfully. Fixes: 41003a7bcfed ("aio: remove retry-based AIO") Cc: Christoph Hellwig Cc: Avi Kivity Cc: Sandeep Dhavale Cc: Jens Axboe Cc: Greg Kroah-Hartman Cc: Kent Overstreet Cc: stable@vger.kernel.org Signed-off-by: Bart Van Assche Link: https://lore.kernel.org/r/20240215204739.2677806-3-bvanassche@acm.org Signed-off-by: Christian Brauner --- fs/aio.c | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) (limited to 'fs/aio.c') diff --git a/fs/aio.c b/fs/aio.c index da18dbcfcb22..28223f511931 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -2165,14 +2165,11 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, #endif /* sys_io_cancel: - * Attempts to cancel an iocb previously passed to io_submit. If - * the operation is successfully cancelled, the resulting event is - * copied into the memory pointed to by result without being placed - * into the completion queue and 0 is returned. May fail with - * -EFAULT if any of the data structures pointed to are invalid. - * May fail with -EINVAL if aio_context specified by ctx_id is - * invalid. May fail with -EAGAIN if the iocb specified was not - * cancelled. Will fail with -ENOSYS if not implemented. + * Attempts to cancel an iocb previously passed to io_submit(). If the + * operation is successfully cancelled 0 is returned. May fail with + * -EFAULT if any of the data structures pointed to are invalid. May + * fail with -EINVAL if aio_context specified by ctx_id is invalid. Will + * fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) @@ -2203,14 +2200,12 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, } spin_unlock_irq(&ctx->ctx_lock); - if (!ret) { - /* - * The result argument is no longer used - the io_event is - * always delivered via the ring buffer. -EINPROGRESS indicates - * cancellation is progress: - */ - ret = -EINPROGRESS; - } + /* + * The result argument is no longer used - the io_event is always + * delivered via the ring buffer. + */ + if (ret == 0 && kiocb->rw.ki_flags & IOCB_AIO_RW) + aio_complete_rw(&kiocb->rw, -EINTR); percpu_ref_put(&ctx->users); -- cgit