From 5f7a07646655fb4108da527565dcdc80124b14c4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Feb 2024 13:15:02 +0000 Subject: [PATCH 1/2] afs: Fix endless loop in directory parsing If a directory has a block with only ".__afsXXXX" files in it (from uncompleted silly-rename), these .__afsXXXX files are skipped but without advancing the file position in the dir_context. This leads to afs_dir_iterate() repeating the block again and again. Fix this by making the code that skips the .__afsXXXX file also manually advance the file position. The symptoms are a soft lookup: watchdog: BUG: soft lockup - CPU#3 stuck for 52s! [check:5737] ... RIP: 0010:afs_dir_iterate_block+0x39/0x1fd ... ? watchdog_timer_fn+0x1a6/0x213 ... ? asm_sysvec_apic_timer_interrupt+0x16/0x20 ? afs_dir_iterate_block+0x39/0x1fd afs_dir_iterate+0x10a/0x148 afs_readdir+0x30/0x4a iterate_dir+0x93/0xd3 __do_sys_getdents64+0x6b/0xd4 This is almost certainly the actual fix for: https://bugzilla.kernel.org/show_bug.cgi?id=218496 Fixes: 57e9d49c5452 ("afs: Hide silly-rename files from userspace") Signed-off-by: David Howells Link: https://lore.kernel.org/r/786185.1708694102@warthog.procyon.org.uk Reviewed-by: Marc Dionne cc: Marc Dionne cc: Markus Suvanto cc: linux-afs@lists.infradead.org Signed-off-by: Christian Brauner --- fs/afs/dir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index b5b8de521f99..8a67fc427e74 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -479,8 +479,10 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, dire->u.name[0] == '.' && ctx->actor != afs_lookup_filldir && ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) + memcmp(dire->u.name, ".__afs", 6) == 0) { + ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); continue; + } /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, From 54cbc058d86beca3515c994039b5c0f0a34f53dd Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 15 Feb 2024 12:47:39 -0800 Subject: [PATCH 2/2] 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(-) 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);