diff options
| author |   Theodore Ts'o <tytso@mit.edu> | 2025-02-07 23:08:02 -0500 |
|---|---|---|
| committer | Theodore Ts'o <tytso@mit.edu> | 2025-02-13 15:05:53 -0500 |
| commit | 9e28059d56649a7212d5b3f8751ec021154ba3dd (patch) | |
| tree | 9fac8e85a3b73f9da30eed155a425e6aa3f445fd | |
| parent | jbd2: Avoid long replay times due to high number or revoke blocks (diff) | |
| download | wireguard-linux-9e28059d56649a7212d5b3f8751ec021154ba3dd.tar.xz wireguard-linux-9e28059d56649a7212d5b3f8751ec021154ba3dd.zip | |
ext4: introduce linear search for dentries
This patch addresses an issue where some files in case-insensitive
directories become inaccessible due to changes in how the kernel
function, utf8_casefold(), generates case-folded strings from the
commit 5c26d2f1d3f5 ("unicode: Don't special case ignorable code
points").
There are good reasons why this change should be made; it's actually
quite stupid that Unicode seems to think that the characters ❤ and ❤️
should be casefolded. Unfortimately because of the backwards
compatibility issue, this commit was reverted in 231825b2e1ff.
This problem is addressed by instituting a brute-force linear fallback
if a lookup fails on case-folded directory, which does result in a
performance hit when looking up files affected by the changing how
thekernel treats ignorable Uniode characters, or when attempting to
look up non-existent file names. So this fallback can be disabled by
setting an encoding flag if in the future, the system administrator or
the manufacturer of a mobile handset or tablet can be sure that there
was no opportunity for a kernel to insert file names with incompatible
encodings.
Fixes: 5c26d2f1d3f5 ("unicode: Don't special case ignorable code points")
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Gabriel Krisman Bertazi <krisman@suse.de>
| -rw-r--r-- | fs/ext4/namei.c | 14 | ||||
| -rw-r--r-- | include/linux/fs.h | 10 |
2 files changed, 19 insertions, 5 deletions
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 536d56d15072..820e7ab7f3a3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1462,7 +1462,8 @@ static bool ext4_match(struct inode *parent, * sure cf_name was properly initialized before * considering the calculated hash. */ - if (IS_ENCRYPTED(parent) && fname->cf_name.name && + if (sb_no_casefold_compat_fallback(parent->i_sb) && + IS_ENCRYPTED(parent) && fname->cf_name.name && (fname->hinfo.hash != EXT4_DIRENT_HASH(de) || fname->hinfo.minor_hash != EXT4_DIRENT_MINOR_HASH(de))) return false; @@ -1595,10 +1596,15 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, * return. Otherwise, fall back to doing a search the * old fashioned way. */ - if (!IS_ERR(ret) || PTR_ERR(ret) != ERR_BAD_DX_DIR) + if (IS_ERR(ret) && PTR_ERR(ret) == ERR_BAD_DX_DIR) + dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, " + "falling back\n")); + else if (!sb_no_casefold_compat_fallback(dir->i_sb) && + *res_dir == NULL && IS_CASEFOLDED(dir)) + dxtrace(printk(KERN_DEBUG "ext4_find_entry: casefold " + "failed, falling back\n")); + else goto cleanup_and_exit; - dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, " - "falling back\n")); ret = NULL; } nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c3b2f8a621f..aa4ec39202c3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1258,11 +1258,19 @@ extern int send_sigurg(struct file *file); #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ -#define SB_ENC_STRICT_MODE_FL (1 << 0) +#define SB_ENC_STRICT_MODE_FL (1 << 0) +#define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) +#if IS_ENABLED(CONFIG_UNICODE) +#define sb_no_casefold_compat_fallback(sb) \ + (sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL) +#else +#define sb_no_casefold_compat_fallback(sb) (1) +#endif + /* * Umount options */ |