From eb3a04a8516ee9b5174379306f94279fc90424c4 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 10 Feb 2025 15:11:22 +0100 Subject: [PATCH 01/12] ovl: don't allow datadir only In theory overlayfs could support upper layer directly referring to a data layer, but there's no current use case for this. Originally, when data-only layers were introduced, this wasn't allowed, only introduced by the "datadir+" feature, but without actually handling this case, resulting in an Oops. Fix by disallowing datadir without lowerdir. Reported-by: Giuseppe Scrivano Fixes: 24e16e385f22 ("ovl: add support for appending lowerdirs one by one") Cc: # v6.7 Reviewed-by: Amir Goldstein Reviewed-by: Alexander Larsson Reviewed-by: Christian Brauner Signed-off-by: Miklos Szeredi --- fs/overlayfs/super.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index b63474d1b064..e19940d649ca 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1138,6 +1138,11 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, return ERR_PTR(-EINVAL); } + if (ctx->nr == ctx->nr_data) { + pr_err("at least one non-data lowerdir is required\n"); + return ERR_PTR(-EINVAL); + } + err = -EINVAL; for (i = 0; i < ctx->nr; i++) { l = &ctx->lower[i]; From a6eb9a4a69cc360b930dad9dc8513f8fd9b3577f Mon Sep 17 00:00:00 2001 From: Giuseppe Scrivano Date: Mon, 10 Feb 2025 13:07:55 +0100 Subject: [PATCH 02/12] ovl: remove unused forward declaration The ovl_get_verity_xattr() function was never added, only its declaration. Signed-off-by: Giuseppe Scrivano Fixes: 184996e92e86 ("ovl: Validate verity xattr when resolving lowerdata") Reviewed-by: Amir Goldstein Reviewed-by: Alexander Larsson Reviewed-by: Christian Brauner Signed-off-by: Miklos Szeredi --- fs/overlayfs/overlayfs.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 6f2f8f4cfbbc..aef942a758ce 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -541,8 +541,6 @@ int ovl_set_metacopy_xattr(struct ovl_fs *ofs, struct dentry *d, bool ovl_is_metacopy_dentry(struct dentry *dentry); char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding); int ovl_ensure_verity_loaded(struct path *path); -int ovl_get_verity_xattr(struct ovl_fs *ofs, const struct path *path, - u8 *digest_buf, int *buf_length); int ovl_validate_verity(struct ovl_fs *ofs, struct path *metapath, struct path *datapath); From cfa5f336bdbde49cf0102ab55007b34361988fd1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Apr 2025 13:17:54 +0100 Subject: [PATCH 03/12] devpts: Fix type for uid and gid params Fix devpts to parse uid and gid params using the correct type so that they get interpreted in the context of the user namespace. Fixes: cc0876f817d6 ("vfs: Convert devpts to use the new mount API") Reported-by: Debarshi Ray Closes: https://github.com/containers/podman/issues/25751 Signed-off-by: Giuseppe Scrivano Signed-off-by: David Howells Link: https://lore.kernel.org/r/759134.1743596274@warthog.procyon.org.uk cc: Eric Sandeen cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/devpts/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 42e4d6eeb29f..9c20d78e41f6 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -89,12 +89,12 @@ enum { }; static const struct fs_parameter_spec devpts_param_specs[] = { - fsparam_u32 ("gid", Opt_gid), + fsparam_gid ("gid", Opt_gid), fsparam_s32 ("max", Opt_max), fsparam_u32oct ("mode", Opt_mode), fsparam_flag ("newinstance", Opt_newinstance), fsparam_u32oct ("ptmxmode", Opt_ptmxmode), - fsparam_u32 ("uid", Opt_uid), + fsparam_uid ("uid", Opt_uid), {} }; From a94fd938df2b1628da66b498aa0eeb89593bc7a2 Mon Sep 17 00:00:00 2001 From: Xiangsheng Hou Date: Mon, 7 Apr 2025 19:50:49 +0800 Subject: [PATCH 04/12] virtiofs: add filesystem context source name check In certain scenarios, for example, during fuzz testing, the source name may be NULL, which could lead to a kernel panic. Therefore, an extra check for the source name should be added. Fixes: a62a8ef9d97d ("virtio-fs: add virtiofs filesystem") Cc: # all LTS kernels Signed-off-by: Xiangsheng Hou Link: https://lore.kernel.org/20250407115111.25535-1-xiangsheng.hou@mediatek.com Signed-off-by: Christian Brauner --- fs/fuse/virtio_fs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 2c7b24cb67ad..53c2626e90e7 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1669,6 +1669,9 @@ static int virtio_fs_get_tree(struct fs_context *fsc) unsigned int virtqueue_size; int err = -EIO; + if (!fsc->source) + return invalf(fsc, "No source specified"); + /* This gets a reference on virtio_fs object. This ptr gets installed * in fc->iq->priv. Once fuse_conn is going away, it calls ->put() * to drop the reference to this object. From bb5e07cb927724e0b47be371fa081141cfb14414 Mon Sep 17 00:00:00 2001 From: Vasiliy Kovalev Date: Sat, 19 Oct 2024 22:13:03 +0300 Subject: [PATCH 05/12] hfs/hfsplus: fix slab-out-of-bounds in hfs_bnode_read_key Syzbot reported an issue in hfs subsystem: BUG: KASAN: slab-out-of-bounds in memcpy_from_page include/linux/highmem.h:423 [inline] BUG: KASAN: slab-out-of-bounds in hfs_bnode_read fs/hfs/bnode.c:35 [inline] BUG: KASAN: slab-out-of-bounds in hfs_bnode_read_key+0x314/0x450 fs/hfs/bnode.c:70 Write of size 94 at addr ffff8880123cd100 by task syz-executor237/5102 Call Trace: __dump_stack lib/dump_stack.c:94 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 kasan_check_range+0x282/0x290 mm/kasan/generic.c:189 __asan_memcpy+0x40/0x70 mm/kasan/shadow.c:106 memcpy_from_page include/linux/highmem.h:423 [inline] hfs_bnode_read fs/hfs/bnode.c:35 [inline] hfs_bnode_read_key+0x314/0x450 fs/hfs/bnode.c:70 hfs_brec_insert+0x7f3/0xbd0 fs/hfs/brec.c:159 hfs_cat_create+0x41d/0xa50 fs/hfs/catalog.c:118 hfs_mkdir+0x6c/0xe0 fs/hfs/dir.c:232 vfs_mkdir+0x2f9/0x4f0 fs/namei.c:4257 do_mkdirat+0x264/0x3a0 fs/namei.c:4280 __do_sys_mkdir fs/namei.c:4300 [inline] __se_sys_mkdir fs/namei.c:4298 [inline] __x64_sys_mkdir+0x6c/0x80 fs/namei.c:4298 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fbdd6057a99 Add a check for key length in hfs_bnode_read_key to prevent out-of-bounds memory access. If the key length is invalid, the key buffer is cleared, improving stability and reliability. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot+5f3a973ed3dfb85a6683@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=5f3a973ed3dfb85a6683 Cc: stable@vger.kernel.org Signed-off-by: Vasiliy Kovalev Link: https://lore.kernel.org/20241019191303.24048-1-kovalev@altlinux.org Reviewed-by: Cengiz Can Signed-off-by: Christian Brauner --- fs/hfs/bnode.c | 6 ++++++ fs/hfsplus/bnode.c | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 6add6ebfef89..cb823a8a6ba9 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) else key_len = tree->max_key_len + 1; + if (key_len > sizeof(hfs_btree_key) || key_len < 1) { + memset(key, 0, sizeof(hfs_btree_key)); + pr_err("hfs: Invalid key length: %d\n", key_len); + return; + } + hfs_bnode_read(node, key, off, key_len); } diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c index 87974d5e6791..079ea80534f7 100644 --- a/fs/hfsplus/bnode.c +++ b/fs/hfsplus/bnode.c @@ -67,6 +67,12 @@ void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) else key_len = tree->max_key_len + 2; + if (key_len > sizeof(hfsplus_btree_key) || key_len < 1) { + memset(key, 0, sizeof(hfsplus_btree_key)); + pr_err("hfsplus: Invalid key length: %d\n", key_len); + return; + } + hfs_bnode_read(node, key, off, key_len); } From a64e4d48a0b77e4ada19ac26ca3a08cd492f6362 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 8 Apr 2025 21:46:29 +0100 Subject: [PATCH 06/12] afs: Fix afs_dynroot_readdir() to not use the RCU read lock afs_dynroot_readdir() uses the RCU read lock to walk the cell list whilst emitting cell automount entries - but dir_emit() may write to a userspace buffer, thereby causing a fault to occur and waits to happen. Fix afs_dynroot_readdir() to get a shared lock on net->cells_lock instead. This can be triggered by enabling lockdep, preconfiguring a number of cells, doing "mount -t afs none /afs -o dyn" (or using the kafs-client package with afs.mount systemd unit enabled) and then doing "ls /afs". Fixes: 1d0b929fc070 ("afs: Change dynroot to create contents on demand") Reported-by: syzbot+3b6c5c6a1d0119b687a1@syzkaller.appspotmail.com Reported-by: syzbot+8245611446194a52150d@syzkaller.appspotmail.com Reported-by: syzbot+1aa62e6852a6ad1c7944@syzkaller.appspotmail.com Reported-by: syzbot+54e6c2176ba76c56217e@syzkaller.appspotmail.com Signed-off-by: David Howells Link: https://lore.kernel.org/1638014.1744145189@warthog.procyon.org.uk cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/afs/dynroot.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 691e0ae607a1..8c6130789fde 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -348,9 +348,9 @@ static int afs_dynroot_readdir(struct file *file, struct dir_context *ctx) } if ((unsigned long long)ctx->pos <= AFS_MAX_DYNROOT_CELL_INO) { - rcu_read_lock(); + down_read(&net->cells_lock); ret = afs_dynroot_readdir_cells(net, ctx); - rcu_read_unlock(); + up_read(&net->cells_lock); } return ret; } From b2b4483b5d05026218127fc8f38c69adf69c235b Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 8 Apr 2025 13:00:53 -0700 Subject: [PATCH 07/12] dcache: convert dentry flag macros to enum Commit 9748cb2dc393 ("VFS: repack DENTRY_ flags.") changed the value of DCACHE_MOUNTED, which broke drgn's path_lookup() helper. drgn is forced to hard-code it because it's a macro, and macros aren't preserved in debugging information by default. Enums, on the other hand, are included in debugging information. Convert the DCACHE_* flag macros to an enum so that debugging tools like drgn and bpftrace can make use of them. Link: https://github.com/osandov/drgn/blob/2027d0fea84d74b835e77392f7040c2a333180c6/drgn/helpers/linux/fs.py#L43-L46 Signed-off-by: Omar Sandoval Link: https://lore.kernel.org/177665a082f048cf536b9cd6af467b3be6b6e6ed.1744141838.git.osandov@fb.com Signed-off-by: Christian Brauner --- include/linux/dcache.h | 104 +++++++++++++++++++---------------------- 1 file changed, 49 insertions(+), 55 deletions(-) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 8d1395f945bf..e9f07e37dd6f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -173,65 +173,59 @@ struct dentry_operations { */ /* d_flags entries */ -#define DCACHE_OP_HASH BIT(0) -#define DCACHE_OP_COMPARE BIT(1) -#define DCACHE_OP_REVALIDATE BIT(2) -#define DCACHE_OP_DELETE BIT(3) -#define DCACHE_OP_PRUNE BIT(4) +enum dentry_flags { + DCACHE_OP_HASH = BIT(0), + DCACHE_OP_COMPARE = BIT(1), + DCACHE_OP_REVALIDATE = BIT(2), + DCACHE_OP_DELETE = BIT(3), + DCACHE_OP_PRUNE = BIT(4), + /* + * This dentry is possibly not currently connected to the dcache tree, + * in which case its parent will either be itself, or will have this + * flag as well. nfsd will not use a dentry with this bit set, but will + * first endeavour to clear the bit either by discovering that it is + * connected, or by performing lookup operations. Any filesystem which + * supports nfsd_operations MUST have a lookup function which, if it + * finds a directory inode with a DCACHE_DISCONNECTED dentry, will + * d_move that dentry into place and return that dentry rather than the + * passed one, typically using d_splice_alias. + */ + DCACHE_DISCONNECTED = BIT(5), + DCACHE_REFERENCED = BIT(6), /* Recently used, don't discard. */ + DCACHE_DONTCACHE = BIT(7), /* Purge from memory on final dput() */ + DCACHE_CANT_MOUNT = BIT(8), + DCACHE_GENOCIDE = BIT(9), + DCACHE_SHRINK_LIST = BIT(10), + DCACHE_OP_WEAK_REVALIDATE = BIT(11), + /* + * this dentry has been "silly renamed" and has to be deleted on the + * last dput() + */ + DCACHE_NFSFS_RENAMED = BIT(12), + DCACHE_FSNOTIFY_PARENT_WATCHED = BIT(13), /* Parent inode is watched by some fsnotify listener */ + DCACHE_DENTRY_KILLED = BIT(14), + DCACHE_MOUNTED = BIT(15), /* is a mountpoint */ + DCACHE_NEED_AUTOMOUNT = BIT(16), /* handle automount on this dir */ + DCACHE_MANAGE_TRANSIT = BIT(17), /* manage transit from this dirent */ + DCACHE_LRU_LIST = BIT(18), + DCACHE_ENTRY_TYPE = (7 << 19), /* bits 19..21 are for storing type: */ + DCACHE_MISS_TYPE = (0 << 19), /* Negative dentry */ + DCACHE_WHITEOUT_TYPE = (1 << 19), /* Whiteout dentry (stop pathwalk) */ + DCACHE_DIRECTORY_TYPE = (2 << 19), /* Normal directory */ + DCACHE_AUTODIR_TYPE = (3 << 19), /* Lookupless directory (presumed automount) */ + DCACHE_REGULAR_TYPE = (4 << 19), /* Regular file type */ + DCACHE_SPECIAL_TYPE = (5 << 19), /* Other file type */ + DCACHE_SYMLINK_TYPE = (6 << 19), /* Symlink */ + DCACHE_NOKEY_NAME = BIT(22), /* Encrypted name encoded without key */ + DCACHE_OP_REAL = BIT(23), + DCACHE_PAR_LOOKUP = BIT(24), /* being looked up (with parent locked shared) */ + DCACHE_DENTRY_CURSOR = BIT(25), + DCACHE_NORCU = BIT(26), /* No RCU delay for freeing */ +}; -#define DCACHE_DISCONNECTED BIT(5) - /* This dentry is possibly not currently connected to the dcache tree, in - * which case its parent will either be itself, or will have this flag as - * well. nfsd will not use a dentry with this bit set, but will first - * endeavour to clear the bit either by discovering that it is connected, - * or by performing lookup operations. Any filesystem which supports - * nfsd_operations MUST have a lookup function which, if it finds a - * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that - * dentry into place and return that dentry rather than the passed one, - * typically using d_splice_alias. */ - -#define DCACHE_REFERENCED BIT(6) /* Recently used, don't discard. */ - -#define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */ - -#define DCACHE_CANT_MOUNT BIT(8) -#define DCACHE_GENOCIDE BIT(9) -#define DCACHE_SHRINK_LIST BIT(10) - -#define DCACHE_OP_WEAK_REVALIDATE BIT(11) - -#define DCACHE_NFSFS_RENAMED BIT(12) - /* this dentry has been "silly renamed" and has to be deleted on the last - * dput() */ -#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(13) - /* Parent inode is watched by some fsnotify listener */ - -#define DCACHE_DENTRY_KILLED BIT(14) - -#define DCACHE_MOUNTED BIT(15) /* is a mountpoint */ -#define DCACHE_NEED_AUTOMOUNT BIT(16) /* handle automount on this dir */ -#define DCACHE_MANAGE_TRANSIT BIT(17) /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) -#define DCACHE_LRU_LIST BIT(18) - -#define DCACHE_ENTRY_TYPE (7 << 19) /* bits 19..21 are for storing type: */ -#define DCACHE_MISS_TYPE (0 << 19) /* Negative dentry */ -#define DCACHE_WHITEOUT_TYPE (1 << 19) /* Whiteout dentry (stop pathwalk) */ -#define DCACHE_DIRECTORY_TYPE (2 << 19) /* Normal directory */ -#define DCACHE_AUTODIR_TYPE (3 << 19) /* Lookupless directory (presumed automount) */ -#define DCACHE_REGULAR_TYPE (4 << 19) /* Regular file type */ -#define DCACHE_SPECIAL_TYPE (5 << 19) /* Other file type */ -#define DCACHE_SYMLINK_TYPE (6 << 19) /* Symlink */ - -#define DCACHE_NOKEY_NAME BIT(22) /* Encrypted name encoded without key */ -#define DCACHE_OP_REAL BIT(23) - -#define DCACHE_PAR_LOOKUP BIT(24) /* being looked up (with parent locked shared) */ -#define DCACHE_DENTRY_CURSOR BIT(25) -#define DCACHE_NORCU BIT(26) /* No RCU delay for freeing */ - extern seqlock_t rename_lock; /* From d43dbf7322a356733b3e3a997cad51dce174d83c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Wed, 9 Apr 2025 10:00:23 +0200 Subject: [PATCH 08/12] mount: ensure we don't pointlessly walk the mount tree This logic got broken recently. Add it back. Fixes: 474f7825d533 ("fs: add copy_mount_setattr() helper") Link: https://lore.kernel.org/20250409-sektflaschen-gecko-27c021fbd222@brauner Tested-by: Mikhail Gavrilov Signed-off-by: Christian Brauner --- fs/namespace.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 14935a0500a2..1eb76d6312de 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -5189,8 +5189,8 @@ static void finish_mount_kattr(struct mount_kattr *kattr) mnt_idmap_put(kattr->mnt_idmap); } -static int copy_mount_setattr(struct mount_attr __user *uattr, size_t usize, - struct mount_kattr *kattr) +static int wants_mount_setattr(struct mount_attr __user *uattr, size_t usize, + struct mount_kattr *kattr) { int ret; struct mount_attr attr; @@ -5213,9 +5213,13 @@ static int copy_mount_setattr(struct mount_attr __user *uattr, size_t usize, if (attr.attr_set == 0 && attr.attr_clr == 0 && attr.propagation == 0) - return 0; + return 0; /* Tell caller to not bother. */ - return build_mount_kattr(&attr, usize, kattr); + ret = build_mount_kattr(&attr, usize, kattr); + if (ret < 0) + return ret; + + return 1; } SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, @@ -5247,8 +5251,8 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, if (flags & AT_RECURSIVE) kattr.kflags |= MOUNT_KATTR_RECURSE; - err = copy_mount_setattr(uattr, usize, &kattr); - if (err) + err = wants_mount_setattr(uattr, usize, &kattr); + if (err <= 0) return err; err = user_path_at(dfd, path, kattr.lookup_flags, &target); @@ -5282,15 +5286,17 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename, if (flags & AT_RECURSIVE) kattr.kflags |= MOUNT_KATTR_RECURSE; - ret = copy_mount_setattr(uattr, usize, &kattr); - if (ret) + ret = wants_mount_setattr(uattr, usize, &kattr); + if (ret < 0) return ret; - ret = do_mount_setattr(&file->f_path, &kattr); - if (ret) - return ret; + if (ret) { + ret = do_mount_setattr(&file->f_path, &kattr); + if (ret) + return ret; - finish_mount_kattr(&kattr); + finish_mount_kattr(&kattr); + } } fd = get_unused_fd_flags(flags & O_CLOEXEC); From 40cb48eba3b4b79e110c1a35d33a48cac54507a2 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Apr 2025 10:00:15 -0700 Subject: [PATCH 09/12] netfs: Only create /proc/fs/netfs with CONFIG_PROC_FS When testing a special config: CONFIG_NETFS_SUPPORTS=y CONFIG_PROC_FS=n The system crashes with something like: [ 3.766197] ------------[ cut here ]------------ [ 3.766484] kernel BUG at mm/mempool.c:560! [ 3.766789] Oops: invalid opcode: 0000 [#1] SMP NOPTI [ 3.767123] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Tainted: G W [ 3.767777] Tainted: [W]=WARN [ 3.767968] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), [ 3.768523] RIP: 0010:mempool_alloc_slab.cold+0x17/0x19 [ 3.768847] Code: 50 fe ff 58 5b 5d 41 5c 41 5d 41 5e 41 5f e9 93 95 13 00 [ 3.769977] RSP: 0018:ffffc90000013998 EFLAGS: 00010286 [ 3.770315] RAX: 000000000000002f RBX: ffff888100ba8640 RCX: 0000000000000000 [ 3.770749] RDX: 0000000000000000 RSI: 0000000000000003 RDI: 00000000ffffffff [ 3.771217] RBP: 0000000000092880 R08: 0000000000000000 R09: ffffc90000013828 [ 3.771664] R10: 0000000000000001 R11: 00000000ffffffea R12: 0000000000092cc0 [ 3.772117] R13: 0000000000000400 R14: ffff8881004b1620 R15: ffffea0004ef7e40 [ 3.772554] FS: 0000000000000000(0000) GS:ffff8881b5f3c000(0000) knlGS:0000000000000000 [ 3.773061] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3.773443] CR2: ffffffff830901b4 CR3: 0000000004296001 CR4: 0000000000770ef0 [ 3.773884] PKRU: 55555554 [ 3.774058] Call Trace: [ 3.774232] [ 3.774371] mempool_alloc_noprof+0x6a/0x190 [ 3.774649] ? _printk+0x57/0x80 [ 3.774862] netfs_alloc_request+0x85/0x2ce [ 3.775147] netfs_readahead+0x28/0x170 [ 3.775395] read_pages+0x6c/0x350 [ 3.775623] ? srso_alias_return_thunk+0x5/0xfbef5 [ 3.775928] page_cache_ra_unbounded+0x1bd/0x2a0 [ 3.776247] filemap_get_pages+0x139/0x970 [ 3.776510] ? srso_alias_return_thunk+0x5/0xfbef5 [ 3.776820] filemap_read+0xf9/0x580 [ 3.777054] ? srso_alias_return_thunk+0x5/0xfbef5 [ 3.777368] ? srso_alias_return_thunk+0x5/0xfbef5 [ 3.777674] ? find_held_lock+0x32/0x90 [ 3.777929] ? netfs_start_io_read+0x19/0x70 [ 3.778221] ? netfs_start_io_read+0x19/0x70 [ 3.778489] ? srso_alias_return_thunk+0x5/0xfbef5 [ 3.778800] ? lock_acquired+0x1e6/0x450 [ 3.779054] ? srso_alias_return_thunk+0x5/0xfbef5 [ 3.779379] netfs_buffered_read_iter+0x57/0x80 [ 3.779670] __kernel_read+0x158/0x2c0 [ 3.779927] bprm_execve+0x300/0x7a0 [ 3.780185] kernel_execve+0x10c/0x140 [ 3.780423] ? __pfx_kernel_init+0x10/0x10 [ 3.780690] kernel_init+0xd5/0x150 [ 3.780910] ret_from_fork+0x2d/0x50 [ 3.781156] ? __pfx_kernel_init+0x10/0x10 [ 3.781414] ret_from_fork_asm+0x1a/0x30 [ 3.781677] [ 3.781823] Modules linked in: [ 3.782065] ---[ end trace 0000000000000000 ]--- This is caused by the following error path in netfs_init(): if (!proc_mkdir("fs/netfs", NULL)) goto error_proc; Fix this by adding ifdef in netfs_main(), so that /proc/fs/netfs is only created with CONFIG_PROC_FS. Signed-off-by: Song Liu Link: https://lore.kernel.org/20250409170015.2651829-1-song@kernel.org Acked-by: David Howells Signed-off-by: Christian Brauner --- fs/netfs/main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/netfs/main.c b/fs/netfs/main.c index 4e3e62040831..70ecc8f5f210 100644 --- a/fs/netfs/main.c +++ b/fs/netfs/main.c @@ -127,11 +127,13 @@ static int __init netfs_init(void) if (mempool_init_slab_pool(&netfs_subrequest_pool, 100, netfs_subrequest_slab) < 0) goto error_subreqpool; +#ifdef CONFIG_PROC_FS if (!proc_mkdir("fs/netfs", NULL)) goto error_proc; if (!proc_create_seq("fs/netfs/requests", S_IFREG | 0444, NULL, &netfs_requests_seq_ops)) goto error_procfile; +#endif #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/netfs/stats", S_IFREG | 0444, NULL, netfs_stats_show)) @@ -144,9 +146,11 @@ static int __init netfs_init(void) return 0; error_fscache: +#ifdef CONFIG_PROC_FS error_procfile: remove_proc_subtree("fs/netfs", NULL); error_proc: +#endif mempool_exit(&netfs_subrequest_pool); error_subreqpool: kmem_cache_destroy(netfs_subrequest_slab); From b463d7fd118b984884da7493ae999a62c9892aa3 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 9 Apr 2025 15:05:34 -0700 Subject: [PATCH 10/12] fs: Fix filename init after recent refactoring getname_flags() should save __user pointer "filename" in filename->uptr. However, this logic is broken by a recent refactoring. Fix it by passing __user pointer filename to helper initname(). Fixes: 611851010c74 ("fs: dedup handling of struct filename init and refcounts bumps") Cc: Mateusz Guzik Cc: Christian Brauner Signed-off-by: Song Liu Link: https://lore.kernel.org/20250409220534.3635801-1-song@kernel.org Signed-off-by: Christian Brauner --- fs/namei.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 360a86ca1f02..8510ff53f12e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -125,9 +125,9 @@ #define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) -static inline void initname(struct filename *name) +static inline void initname(struct filename *name, const char __user *uptr) { - name->uptr = NULL; + name->uptr = uptr; name->aname = NULL; atomic_set(&name->refcnt, 1); } @@ -210,7 +210,7 @@ getname_flags(const char __user *filename, int flags) return ERR_PTR(-ENAMETOOLONG); } } - initname(result); + initname(result, filename); audit_getname(result); return result; } @@ -268,7 +268,7 @@ struct filename *getname_kernel(const char * filename) return ERR_PTR(-ENAMETOOLONG); } memcpy((char *)result->name, filename, len); - initname(result); + initname(result, NULL); audit_getname(result); return result; } From 8e3c15ee0d292c413c66fe10201d1b035a0bea72 Mon Sep 17 00:00:00 2001 From: Gou Hao Date: Thu, 10 Apr 2025 15:12:36 +0800 Subject: [PATCH 11/12] iomap: skip unnecessary ifs_block_is_uptodate check In iomap_adjust_read_range, i is either the first !uptodate block, or it is past last for the second loop looking for trailing uptodate blocks. Assuming there's no overflow (there's no combination of huge folios and tiny blksize) then yeah, there is no point in retesting that the same block pointed to by i is uptodate since we hold the folio lock so nobody else could have set it uptodate. Signed-off-by: Gou Hao Link: https://lore.kernel.org/20250410071236.16017-1-gouhao@uniontech.com Reviewed-by: "Darrick J. Wong" Reviewed-by: Christoph Hellwig Suggested-by: Christoph Hellwig Signed-off-by: Christian Brauner --- fs/iomap/buffered-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 31553372b33a..5b08bd417b28 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -259,7 +259,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio, } /* truncate len if we find any trailing uptodate block(s) */ - for ( ; i <= last; i++) { + while (++i <= last) { if (ifs_block_is_uptodate(ifs, i)) { plen -= (last - i + 1) * block_size; last = i - 1; From 47a742fd977a7a8c39fea890712e9bfdf76f98f1 Mon Sep 17 00:00:00 2001 From: Jan Stancek Date: Thu, 10 Apr 2025 17:05:42 +0200 Subject: [PATCH 12/12] fs: use namespace_{lock,unlock} in dissolve_on_fput() In commit b73ec10a4587 ("fs: add fastpath for dissolve_on_fput()"), the namespace_{lock,unlock} has been replaced with scoped_guard using the namespace_sem. This however now also skips processing of 'unmounted' list in namespace_unlock(), and mount is not (immediately) cleaned up. For example, this causes LTP move_mount02 fail: ... move_mount02.c:80: TPASS: invalid-from-fd: move_mount() failed as expected: EBADF (9) move_mount02.c:80: TPASS: invalid-from-path: move_mount() failed as expected: ENOENT (2) move_mount02.c:80: TPASS: invalid-to-fd: move_mount() failed as expected: EBADF (9) move_mount02.c:80: TPASS: invalid-to-path: move_mount() failed as expected: ENOENT (2) move_mount02.c:80: TPASS: invalid-flags: move_mount() failed as expected: EINVAL (22) tst_test.c:1833: TINFO: === Testing on ext3 === tst_test.c:1170: TINFO: Formatting /dev/loop0 with ext3 opts='' extra opts='' mke2fs 1.47.2 (1-Jan-2025) /dev/loop0 is apparently in use by the system; will not make a filesystem here! tst_test.c:1170: TBROK: mkfs.ext3 failed with exit code 1 The test makes number of move_mount() calls but these are all designed to fail with specific errno. Even after test, 'losetup -d' can't detach loop device. Define a new guard for dissolve_on_fput, that will use namespace_{lock,unlock}. Fixes: b73ec10a4587 ("fs: add fastpath for dissolve_on_fput()") Signed-off-by: Jan Stancek Link: https://lore.kernel.org/cad2f042b886bf0ced3d8e3aff120ec5e0125d61.1744297468.git.jstancek@redhat.com Signed-off-by: Christian Brauner --- fs/namespace.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/namespace.c b/fs/namespace.c index 1eb76d6312de..d9ca80dcc544 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1830,6 +1830,8 @@ static inline void namespace_lock(void) down_write(&namespace_sem); } +DEFINE_GUARD(namespace_lock, struct rw_semaphore *, namespace_lock(), namespace_unlock()) + enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, @@ -2383,7 +2385,7 @@ void dissolve_on_fput(struct vfsmount *mnt) return; } - scoped_guard(rwsem_write, &namespace_sem) { + scoped_guard(namespace_lock, &namespace_sem) { ns = m->mnt_ns; if (!must_dissolve(ns)) return;