From cd0265fcd2eae9004c68ef2123a9dac0dc5a666a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Mar 2019 10:23:33 -0700 Subject: fscrypt: drop inode argument from fscrypt_get_ctx() The only reason the inode is being passed to fscrypt_get_ctx() is to verify that the encryption key is available. However, all callers already ensure this because if we get as far as trying to do I/O to an encrypted file without the key, there's already a bug. Therefore, remove this unnecessary argument. Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- fs/ext4/readpage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4') diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 3adadf461825..75cef6af6080 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -244,7 +244,7 @@ int ext4_mpage_readpages(struct address_space *mapping, struct fscrypt_ctx *ctx = NULL; if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) { - ctx = fscrypt_get_ctx(inode, GFP_NOFS); + ctx = fscrypt_get_ctx(GFP_NOFS); if (IS_ERR(ctx)) goto set_error_page; } -- cgit v1.2.3 From b01531db6cec2aa330dbc91bfbfaaef4a0d387a4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 20 Mar 2019 11:39:13 -0700 Subject: fscrypt: fix race where ->lookup() marks plaintext dentry as ciphertext ->lookup() in an encrypted directory begins as follows: 1. fscrypt_prepare_lookup(): a. Try to load the directory's encryption key. b. If the key is unavailable, mark the dentry as a ciphertext name via d_flags. 2. fscrypt_setup_filename(): a. Try to load the directory's encryption key. b. If the key is available, encrypt the name (treated as a plaintext name) to get the on-disk name. Otherwise decode the name (treated as a ciphertext name) to get the on-disk name. But if the key is concurrently added, it may be found at (2a) but not at (1a). In this case, the dentry will be wrongly marked as a ciphertext name even though it was actually treated as plaintext. This will cause the dentry to be wrongly invalidated on the next lookup, potentially causing problems. For example, if the racy ->lookup() was part of sys_mount(), then the new mount will be detached when anything tries to access it. This is despite the mountpoint having a plaintext path, which should remain valid now that the key was added. Of course, this is only possible if there's a userspace race. Still, the additional kernel-side race is confusing and unexpected. Close the kernel-side race by changing fscrypt_prepare_lookup() to also set the on-disk filename (step 2b), consistent with the d_flags update. Fixes: 28b4c263961c ("ext4 crypto: revalidate dentry after adding or removing the key") Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 62 ++++++++++++++++++++++++++++++++++------------ fs/ext4/namei.c | 76 +++++++++++++++++++++++++++++++++++++++------------------ 2 files changed, 99 insertions(+), 39 deletions(-) (limited to 'fs/ext4') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 82ffdacdc7fa..e64a4ee96d30 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2287,23 +2287,47 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); #ifdef CONFIG_FS_ENCRYPTION +static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, + const struct fscrypt_name *src) +{ + memset(dst, 0, sizeof(*dst)); + + dst->usr_fname = src->usr_fname; + dst->disk_name = src->disk_name; + dst->hinfo.hash = src->hash; + dst->hinfo.minor_hash = src->minor_hash; + dst->crypto_buf = src->crypto_buf; +} + static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct ext4_filename *fname) + const struct qstr *iname, + int lookup, + struct ext4_filename *fname) { struct fscrypt_name name; int err; - memset(fname, 0, sizeof(struct ext4_filename)); - err = fscrypt_setup_filename(dir, iname, lookup, &name); + if (err) + return err; - fname->usr_fname = name.usr_fname; - fname->disk_name = name.disk_name; - fname->hinfo.hash = name.hash; - fname->hinfo.minor_hash = name.minor_hash; - fname->crypto_buf = name.crypto_buf; - return err; + ext4_fname_from_fscrypt_name(fname, &name); + return 0; +} + +static inline int ext4_fname_prepare_lookup(struct inode *dir, + struct dentry *dentry, + struct ext4_filename *fname) +{ + struct fscrypt_name name; + int err; + + err = fscrypt_prepare_lookup(dir, dentry, &name); + if (err) + return err; + + ext4_fname_from_fscrypt_name(fname, &name); + return 0; } static inline void ext4_fname_free_filename(struct ext4_filename *fname) @@ -2317,19 +2341,27 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->usr_fname = NULL; fname->disk_name.name = NULL; } -#else +#else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, - const struct qstr *iname, - int lookup, struct ext4_filename *fname) + const struct qstr *iname, + int lookup, + struct ext4_filename *fname) { fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; return 0; } -static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } -#endif +static inline int ext4_fname_prepare_lookup(struct inode *dir, + struct dentry *dentry, + struct ext4_filename *fname) +{ + return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname); +} + +static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } +#endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ extern int __ext4_check_dir_entry(const char *, unsigned int, struct inode *, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 980166a8122a..3ba6f30db8d9 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1327,7 +1327,7 @@ static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, } /* - * ext4_find_entry() + * __ext4_find_entry() * * finds an entry in the specified directory with the wanted name. It * returns the cache buffer in which the entry was found, and the entry @@ -1337,39 +1337,32 @@ static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, * The returned buffer_head has ->b_count elevated. The caller is expected * to brelse() it when appropriate. */ -static struct buffer_head * ext4_find_entry (struct inode *dir, - const struct qstr *d_name, - struct ext4_dir_entry_2 **res_dir, - int *inlined) +static struct buffer_head *__ext4_find_entry(struct inode *dir, + struct ext4_filename *fname, + struct ext4_dir_entry_2 **res_dir, + int *inlined) { struct super_block *sb; struct buffer_head *bh_use[NAMEI_RA_SIZE]; struct buffer_head *bh, *ret = NULL; ext4_lblk_t start, block; - const u8 *name = d_name->name; + const u8 *name = fname->usr_fname->name; size_t ra_max = 0; /* Number of bh's in the readahead buffer, bh_use[] */ size_t ra_ptr = 0; /* Current index into readahead buffer */ ext4_lblk_t nblocks; int i, namelen, retval; - struct ext4_filename fname; *res_dir = NULL; sb = dir->i_sb; - namelen = d_name->len; + namelen = fname->usr_fname->len; if (namelen > EXT4_NAME_LEN) return NULL; - retval = ext4_fname_setup_filename(dir, d_name, 1, &fname); - if (retval == -ENOENT) - return NULL; - if (retval) - return ERR_PTR(retval); - if (ext4_has_inline_data(dir)) { int has_inline_data = 1; - ret = ext4_find_inline_entry(dir, &fname, res_dir, + ret = ext4_find_inline_entry(dir, fname, res_dir, &has_inline_data); if (has_inline_data) { if (inlined) @@ -1389,7 +1382,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, goto restart; } if (is_dx(dir)) { - ret = ext4_dx_find_entry(dir, &fname, res_dir); + ret = ext4_dx_find_entry(dir, fname, res_dir); /* * On success, or if the error was file not found, * return. Otherwise, fall back to doing a search the @@ -1453,7 +1446,7 @@ restart: goto cleanup_and_exit; } set_buffer_verified(bh); - i = search_dirblock(bh, dir, &fname, + i = search_dirblock(bh, dir, fname, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (i == 1) { EXT4_I(dir)->i_dir_start_lookup = block; @@ -1484,10 +1477,50 @@ cleanup_and_exit: /* Clean up the read-ahead blocks */ for (; ra_ptr < ra_max; ra_ptr++) brelse(bh_use[ra_ptr]); - ext4_fname_free_filename(&fname); return ret; } +static struct buffer_head *ext4_find_entry(struct inode *dir, + const struct qstr *d_name, + struct ext4_dir_entry_2 **res_dir, + int *inlined) +{ + int err; + struct ext4_filename fname; + struct buffer_head *bh; + + err = ext4_fname_setup_filename(dir, d_name, 1, &fname); + if (err == -ENOENT) + return NULL; + if (err) + return ERR_PTR(err); + + bh = __ext4_find_entry(dir, &fname, res_dir, inlined); + + ext4_fname_free_filename(&fname); + return bh; +} + +static struct buffer_head *ext4_lookup_entry(struct inode *dir, + struct dentry *dentry, + struct ext4_dir_entry_2 **res_dir) +{ + int err; + struct ext4_filename fname; + struct buffer_head *bh; + + err = ext4_fname_prepare_lookup(dir, dentry, &fname); + if (err == -ENOENT) + return NULL; + if (err) + return ERR_PTR(err); + + bh = __ext4_find_entry(dir, &fname, res_dir, NULL); + + ext4_fname_free_filename(&fname); + return bh; +} + static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir) @@ -1546,16 +1579,11 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi struct inode *inode; struct ext4_dir_entry_2 *de; struct buffer_head *bh; - int err; - - err = fscrypt_prepare_lookup(dir, dentry, flags); - if (err) - return ERR_PTR(err); if (dentry->d_name.len > EXT4_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); + bh = ext4_lookup_entry(dir, dentry, &de); if (IS_ERR(bh)) return ERR_CAST(bh); inode = NULL; -- cgit v1.2.3 From 2c58d548f5706d085c4b009f6abb945220460632 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 10 Apr 2019 13:21:15 -0700 Subject: fscrypt: cache decrypted symlink target in ->i_link Path lookups that traverse encrypted symlink(s) are very slow because each encrypted symlink needs to be decrypted each time it's followed. This also involves dropping out of rcu-walk mode. Make encrypted symlinks faster by caching the decrypted symlink target in ->i_link. The first call to fscrypt_get_symlink() sets it. Then, the existing VFS path lookup code uses the non-NULL ->i_link to take the fast path where ->get_link() isn't called, and lookups in rcu-walk mode remain in rcu-walk mode. Also set ->i_link immediately when a new encrypted symlink is created. To safely free the symlink target after an RCU grace period has elapsed, introduce a new function fscrypt_free_inode(), and make the relevant filesystems call it just before actually freeing the inode. Cc: Al Viro Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/ext4') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6ed4eb81e674..5b92054bf8ea 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1110,6 +1110,9 @@ static int ext4_drop_inode(struct inode *inode) static void ext4_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); + + fscrypt_free_inode(inode); + kmem_cache_free(ext4_inode_cachep, EXT4_I(inode)); } -- cgit v1.2.3