[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87ed5olmmc.fsf@mailhost.krisman.be>
Date: Thu, 12 Sep 2024 15:04:27 -0400
From: Gabriel Krisman Bertazi <gabriel@...sman.be>
To: André Almeida <andrealmeid@...lia.com>
Cc: Hugh Dickins <hughd@...gle.com>, Andrew Morton
<akpm@...ux-foundation.org>, Alexander Viro <viro@...iv.linux.org.uk>,
Christian Brauner <brauner@...nel.org>, Jan Kara <jack@...e.cz>,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
linux-fsdevel@...r.kernel.org, kernel-dev@...lia.com, Daniel Rosenberg
<drosen@...gle.com>, smcv@...labora.com, Christoph Hellwig <hch@....de>,
Theodore Ts'o <tytso@....edu>
Subject: Re: [PATCH v4 07/10] tmpfs: Add casefold lookup support
André Almeida <andrealmeid@...lia.com> writes:
> Enable casefold lookup in tmpfs, based on the encoding defined by
> userspace. That means that instead of comparing byte per byte a file
> name, it compares to a case-insensitive equivalent of the Unicode
> string.
I think this looks much better.
A few things left. First, I'd suggest you merge patch 5 and this
one. There is not much sense in keeping them separate; patch 5 is a
dependency that won't crash the build, but might cause runtime errors if anyone
cherry-picks the feature but forgets to pull it.
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 5a77acf6ac6a..4fde63596ab3 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -40,6 +40,8 @@
> #include <linux/fs_parser.h>
> #include <linux/swapfile.h>
> #include <linux/iversion.h>
> +#include <linux/unicode.h>
> +#include <linux/parser.h>
I think you don't need this header anymore
> #include "swap.h"
>
> static struct vfsmount *shm_mnt __ro_after_init;
> @@ -123,6 +125,8 @@ struct shmem_options {
> bool noswap;
> unsigned short quota_types;
> struct shmem_quota_limits qlimits;
> + struct unicode_map *encoding;
> + bool strict_encoding;
> #define SHMEM_SEEN_BLOCKS 1
> #define SHMEM_SEEN_INODES 2
> #define SHMEM_SEEN_HUGE 4
> @@ -3427,6 +3431,10 @@ shmem_mknod(struct mnt_idmap *idmap, struct inode *dir,
> if (IS_ERR(inode))
> return PTR_ERR(inode);
>
> + if (IS_ENABLED(CONFIG_UNICODE) &&
> + !generic_ci_validate_strict_name(dir, &dentry->d_name))
> + return -EINVAL;
> +
Commenting here, but this is about generic_ci_validate_strict_name. Can
you make it an inline function in the header file instead? This way you
can fold the IS_ENABLED into it and also avoid the function call.
> error = simple_acl_create(dir, inode);
> if (error)
> goto out_iput;
> @@ -3442,7 +3450,12 @@ shmem_mknod(struct mnt_idmap *idmap, struct inode *dir,
> dir->i_size += BOGO_DIRENT_SIZE;
> inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
> inode_inc_iversion(dir);
> - d_instantiate(dentry, inode);
> +
> + if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
> + d_add(dentry, inode);
> + else
> + d_instantiate(dentry, inode);
> +
> dget(dentry); /* Extra count - pin the dentry in core */
> return error;
>
> @@ -3533,7 +3546,10 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir,
> inc_nlink(inode);
> ihold(inode); /* New dentry reference */
> dget(dentry); /* Extra pinning count for the created dentry */
> - d_instantiate(dentry, inode);
> + if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
> + d_add(dentry, inode);
> + else
> + d_instantiate(dentry, inode);
> out:
> return ret;
> }
> @@ -3553,6 +3569,14 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry)
> inode_inc_iversion(dir);
> drop_nlink(inode);
> dput(dentry); /* Undo the count from "create" - does all the work */
> +
> + /*
> + * For now, VFS can't deal with case-insensitive negative dentries, so
> + * we invalidate them
> + */
> + if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
> + d_invalidate(dentry);
> +
> return 0;
> }
>
> @@ -3697,7 +3721,10 @@ static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir,
> dir->i_size += BOGO_DIRENT_SIZE;
> inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
> inode_inc_iversion(dir);
> - d_instantiate(dentry, inode);
> + if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
> + d_add(dentry, inode);
> + else
> + d_instantiate(dentry, inode);
> dget(dentry);
> return 0;
>
> @@ -4050,6 +4077,9 @@ enum shmem_param {
> Opt_usrquota_inode_hardlimit,
> Opt_grpquota_block_hardlimit,
> Opt_grpquota_inode_hardlimit,
> + Opt_casefold_version,
> + Opt_casefold,
> + Opt_strict_encoding,
> };
>
> static const struct constant_table shmem_param_enums_huge[] = {
> @@ -4081,9 +4111,53 @@ const struct fs_parameter_spec shmem_fs_parameters[] = {
> fsparam_string("grpquota_block_hardlimit", Opt_grpquota_block_hardlimit),
> fsparam_string("grpquota_inode_hardlimit", Opt_grpquota_inode_hardlimit),
> #endif
> + fsparam_string("casefold", Opt_casefold_version),
> + fsparam_flag ("casefold", Opt_casefold),
> + fsparam_flag ("strict_encoding", Opt_strict_encoding),
> {}
> };
>
> +#if IS_ENABLED(CONFIG_UNICODE)
> +static int shmem_parse_opt_casefold(struct fs_context *fc, struct fs_parameter *param,
> + bool latest_version)
> +{
> + struct shmem_options *ctx = fc->fs_private;
> + unsigned int version = UTF8_LATEST;
> + struct unicode_map *encoding;
> + char *version_str = param->string + 5;
> +
> + if (!latest_version) {
> + if (strncmp(param->string, "utf8-", 5))
> + return invalfc(fc, "Only UTF-8 encodings are supported "
> + "in the format: utf8-<version number>");
> +
> + version = utf8_parse_version(version_str);
> + if (version < 0)
> + return invalfc(fc, "Invalid UTF-8 version: %s", version_str);
> + }
> +
> + encoding = utf8_load(version);
> +
> + if (IS_ERR(encoding)) {
> + return invalfc(fc, "Failed loading UTF-8 version: utf8-%u.%u.%u\n",
> + unicode_major(version), unicode_minor(version), unicode_rev(version));
bad indentation?
> + }
> +
> + pr_info("tmpfs: Using encoding : utf8-%u.%u.%u\n",
> + unicode_major(version), unicode_minor(version), unicode_rev(version));
> +
> + ctx->encoding = encoding;
> +
> + return 0;
> +}
> +#else
> +static int shmem_parse_opt_casefold(struct fs_context *fc, struct fs_parameter *param,
> + bool latest_version)
> +{
> + return invalfc(fc, "tmpfs: Kernel not built with CONFIG_UNICODE\n");
> +}
> +#endif
> +
> static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
> {
> struct shmem_options *ctx = fc->fs_private;
> @@ -4242,6 +4316,13 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
> "Group quota inode hardlimit too large.");
> ctx->qlimits.grpquota_ihardlimit = size;
> break;
> + case Opt_casefold_version:
> + return shmem_parse_opt_casefold(fc, param, false);
> + case Opt_casefold:
> + return shmem_parse_opt_casefold(fc, param, true);
> + case Opt_strict_encoding:
> + ctx->strict_encoding = true;
Using strict_encoding without encoding should be explicitly forbidden.
> + break;
> }
> return 0;
>
> @@ -4471,6 +4552,11 @@ static void shmem_put_super(struct super_block *sb)
> {
> struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
>
> +#if IS_ENABLED(CONFIG_UNICODE)
> + if (sb->s_encoding)
> + utf8_unload(sb->s_encoding);
> +#endif
> +
> #ifdef CONFIG_TMPFS_QUOTA
> shmem_disable_quotas(sb);
> #endif
> @@ -4481,6 +4567,17 @@ static void shmem_put_super(struct super_block *sb)
> sb->s_fs_info = NULL;
> }
>
> +#if IS_ENABLED(CONFIG_UNICODE)
> +static const struct dentry_operations shmem_ci_dentry_ops = {
> + .d_hash = generic_ci_d_hash,
> + .d_compare = generic_ci_d_compare,
> +#ifdef CONFIG_FS_ENCRYPTION
> + .d_revalidate = fscrypt_d_revalidate,
> +#endif
> + .d_delete = always_delete_dentry,
> +};
> +#endif
> +
> static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
> {
> struct shmem_options *ctx = fc->fs_private;
> @@ -4515,9 +4612,21 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
> }
> sb->s_export_op = &shmem_export_ops;
> sb->s_flags |= SB_NOSEC | SB_I_VERSION;
> +
> +#if IS_ENABLED(CONFIG_UNICODE)
> + if (ctx->encoding) {
> + sb->s_encoding = ctx->encoding;
> + sb->s_d_op = &shmem_ci_dentry_ops;
> + if (ctx->strict_encoding)
> + sb->s_encoding_flags = SB_ENC_STRICT_MODE_FL;
> + }
> #else
> - sb->s_flags |= SB_NOUSER;
> + sb->s_d_op = &simple_dentry_operations;
Moving simple_dentry_operations to be set at s_d_op should be a separate
patch.
It is a change that has non-obvious side effects (i.e. the way we
treat the root dentry) so it needs proper review by itself. It is
also not related to the rest of the case-insensitive patch.
Also, why is it done only for CONFIG_UNICODE=n?
> #endif
> +
> +#else
> + sb->s_flags |= SB_NOUSER;
> +#endif /* CONFIG_TMPFS */
> sbinfo->max_blocks = ctx->blocks;
> sbinfo->max_inodes = ctx->inodes;
> sbinfo->free_ispace = sbinfo->max_inodes * BOGO_INODE_SIZE;
> @@ -4791,6 +4900,8 @@ int shmem_init_fs_context(struct fs_context *fc)
> ctx->uid = current_fsuid();
> ctx->gid = current_fsgid();
>
> + ctx->encoding = NULL;
> +
> fc->fs_private = ctx;
> fc->ops = &shmem_fs_context_ops;
> return 0;
--
Gabriel Krisman Bertazi
Powered by blists - more mailing lists