From: Jingbo Xu <jefflexu@linux.alibaba.com> mainline inclusion from mainline-v6.9-rc1 commit e022f6a1c711ab6d76e9e59dce77e2b25df75076 category: feature bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC6CFR Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- open_by_handle_at(2) can fail with -ESTALE with a valid handle returned by a previous name_to_handle_at(2) for evicted fuse inodes, which is especially common when entry_valid_timeout is 0, e.g. when the fuse daemon is in "cache=none" mode. The time sequence is like: name_to_handle_at(2) # succeed evict fuse inode open_by_handle_at(2) # fail The root cause is that, with 0 entry_valid_timeout, the dput() called in name_to_handle_at(2) will trigger iput -> evict(), which will send FUSE_FORGET to the daemon. The following open_by_handle_at(2) will send a new FUSE_LOOKUP request upon inode cache miss since the previous inode eviction. Then the fuse daemon may fail the FUSE_LOOKUP request with -ENOENT as the cached metadata of the requested inode has already been cleaned up during the previous FUSE_FORGET. The returned -ENOENT is treated as -ESTALE when open_by_handle_at(2) returns. This confuses the application somehow, as open_by_handle_at(2) fails when the previous name_to_handle_at(2) succeeds. The returned errno is also confusing as the requested file is not deleted and already there. It is reasonable to fail name_to_handle_at(2) early in this case, after which the application can fallback to open(2) to access files. Since this issue typically appears when entry_valid_timeout is 0 which is configured by the fuse daemon, the fuse daemon is the right person to explicitly disable the export when required. Also considering FUSE_EXPORT_SUPPORT actually indicates the support for lookups of "." and "..", and there are existing fuse daemons supporting export without FUSE_EXPORT_SUPPORT set, for compatibility, we add a new INIT flag for such purpose. Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com> Signed-off-by: Miklos Szeredi <mszeredi@redhat.com> Conflicts: fs/fuse/inode.c [Conflicts with mainline commit 3ab394b363c5 ("fuse: disable the combination of passthrough and writeback cache").] Signed-off-by: Wang Zhaolong <wangzhaolong1@huawei.com> --- fs/fuse/inode.c | 11 ++++++++++- include/uapi/linux/fuse.h | 3 +++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d771ce993e3e..26b670daf204 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1148,10 +1148,15 @@ static struct dentry *fuse_get_parent(struct dentry *child) fuse_invalidate_entry_cache(parent); return parent; } +/* only for fid encoding; no support for file handle */ +static const struct export_operations fuse_export_fid_operations = { + .encode_fh = fuse_encode_fh, +}; + static const struct export_operations fuse_export_operations = { .fh_to_dentry = fuse_fh_to_dentry, .fh_to_parent = fuse_fh_to_parent, .encode_fh = fuse_encode_fh, .get_parent = fuse_get_parent, @@ -1345,10 +1350,12 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, !(flags & FUSE_WRITEBACK_CACHE)) { fc->passthrough = 1; fc->max_stack_depth = arg->max_stack_depth; fm->sb->s_stack_depth = arg->max_stack_depth; } + if (flags & FUSE_NO_EXPORT_SUPPORT) + fm->sb->s_export_op = &fuse_export_fid_operations; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; fc->no_flock = 1; } @@ -1391,11 +1398,12 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL | FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | - FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP; + FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP | + FUSE_NO_EXPORT_SUPPORT; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; if (fuse_is_inode_dax_mode(fm->fc->dax_mode)) flags |= FUSE_HAS_INODE_DAX; @@ -1588,10 +1596,11 @@ static int fuse_fill_super_submount(struct super_block *sb, WARN_ON(sb->s_bdi != &noop_backing_dev_info); sb->s_bdi = bdi_get(parent_sb->s_bdi); sb->s_xattr = parent_sb->s_xattr; + sb->s_export_op = parent_sb->s_export_op; sb->s_time_gran = parent_sb->s_time_gran; sb->s_blocksize = parent_sb->s_blocksize; sb->s_blocksize_bits = parent_sb->s_blocksize_bits; sb->s_subtype = kstrdup(parent_sb->s_subtype, GFP_KERNEL); if (parent_sb->s_subtype && !sb->s_subtype) diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 1162a47b6a42..a86c2cad65ad 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -213,10 +213,11 @@ * - add FUSE_STATX and related structures * * 7.40 * - add max_stack_depth to fuse_init_out, add FUSE_PASSTHROUGH init flag * - add backing_id to fuse_open_out, add FOPEN_PASSTHROUGH open flag + * - add FUSE_NO_EXPORT_SUPPORT init flag */ #ifndef _LINUX_FUSE_H #define _LINUX_FUSE_H @@ -414,10 +415,11 @@ struct fuse_file_lock { * FUSE_HAS_INODE_DAX: use per inode DAX * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. + * FUSE_NO_EXPORT_SUPPORT: explicitly disable export support */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) #define FUSE_FILE_OPS (1 << 2) #define FUSE_ATOMIC_O_TRUNC (1 << 3) @@ -454,10 +456,11 @@ struct fuse_file_lock { #define FUSE_HAS_INODE_DAX (1ULL << 33) #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) #define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) #define FUSE_PASSTHROUGH (1ULL << 37) +#define FUSE_NO_EXPORT_SUPPORT (1ULL << 38) /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP /** -- 2.34.3