Replace BKL with superblock lock in fat/msdos/vfat

This replaces the use of the BKL in the FAT family of filesystems with the
existing superblock lock instead.

The code already appears to do mostly proper locking with its own private
spinlocks (and mutexes), but while the BKL could possibly have been
dropped entirely, converting it to use the superblock lock (which is just
a regular mutex) is the conservative thing to do.

As a per-filesystem mutex, it not only won't have any of the possible
latency issues related to the BKL, but the lock is obviously private to
the particular filesystem instance and will thus not cause problems for
entirely unrelated users like the BKL can.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>

diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index fda25479af26720690969dde01f444d8bc730f07..3a9ecac8d61f081e295655822d311dc27f51f02f 100644 (file)
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -61,7 +61,7 @@ void fat_cache_destroy(void)
 
 static inline struct fat_cache *fat_cache_alloc(struct inode *inode)
 {
-       return kmem_cache_alloc(fat_cache_cachep, GFP_KERNEL);
+       return kmem_cache_alloc(fat_cache_cachep, GFP_NOFS);
 }
 
 static inline void fat_cache_free(struct fat_cache *cache)

diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 486725ee99ae68a977bc9ca2d8e8cd47990ed579..34541d06e6263b1817d96ee4d640f2cc8aa35eb7 100644 (file)
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -472,7 +472,7 @@ static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent,
        loff_t cpos;
        int ret = 0;
 
-       lock_kernel();
+       lock_super(sb);
 
        cpos = filp->f_pos;
        /* Fake . and .. for the root directory. */
@@ -654,7 +654,7 @@ FillFailed:
        if (unicode)
                __putname(unicode);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        return ret;
 }
 

diff --git a/fs/fat/file.c b/fs/fat/file.c
index 27cc1164ec36baa84284836686d1603a36451423..7059928fb351aededd9198350ec1b54be60c785c 100644 (file)
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -229,7 +229,8 @@ static int fat_free(struct inode *inode, int skip)
 
 void fat_truncate(struct inode *inode)
 {
-       struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+       struct super_block *sb = inode->i_sb;
+       struct msdos_sb_info *sbi = MSDOS_SB(sb);
        const unsigned int cluster_size = sbi->cluster_size;
        int nr_clusters;
 
@@ -242,9 +243,9 @@ void fat_truncate(struct inode *inode)
 
        nr_clusters = (inode->i_size + (cluster_size - 1)) >> sbi->cluster_bits;
 
-       lock_kernel();
+       lock_super(sb);
        fat_free(inode, nr_clusters);
-       unlock_kernel();
+       unlock_super(sb);
        fat_flush_inodes(inode->i_sb, inode, NULL);
 }
 
@@ -297,12 +298,13 @@ static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode)
 
 int fat_setattr(struct dentry *dentry, struct iattr *attr)
 {
+       struct super_block *sb = dentry->d_sb;
        struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
        struct inode *inode = dentry->d_inode;
        int mask, error = 0;
        unsigned int ia_valid;
 
-       lock_kernel();
+       lock_super(sb);
 
        /*
         * Expand the file. Since inode_setattr() updates ->i_size
@@ -356,7 +358,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
                mask = sbi->options.fs_fmask;
        inode->i_mode &= S_IFMT | (S_IRWXUGO & ~mask);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        return error;
 }
 EXPORT_SYMBOL_GPL(fat_setattr);

diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 4e0a3dd9d6779a1d9101704d470b1263b194d7d5..46a4508ffd2eba5cbf10be8122d60f721883f934 100644 (file)
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -440,14 +440,13 @@ static void fat_delete_inode(struct inode *inode)
 
 static void fat_clear_inode(struct inode *inode)
 {
-       struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+       struct super_block *sb = inode->i_sb;
+       struct msdos_sb_info *sbi = MSDOS_SB(sb);
 
-       lock_kernel();
        spin_lock(&sbi->inode_hash_lock);
        fat_cache_inval_inode(inode);
        hlist_del_init(&MSDOS_I(inode)->i_fat_hash);
        spin_unlock(&sbi->inode_hash_lock);
-       unlock_kernel();
 }
 
 static void fat_write_super(struct super_block *sb)
@@ -485,7 +484,7 @@ static struct kmem_cache *fat_inode_cachep;
 static struct inode *fat_alloc_inode(struct super_block *sb)
 {
        struct msdos_inode_info *ei;
-       ei = kmem_cache_alloc(fat_inode_cachep, GFP_KERNEL);
+       ei = kmem_cache_alloc(fat_inode_cachep, GFP_NOFS);
        if (!ei)
                return NULL;
        return &ei->vfs_inode;
@@ -567,7 +566,7 @@ retry:
        if (inode->i_ino == MSDOS_ROOT_INO || !i_pos)
                return 0;
 
-       lock_kernel();
+       lock_super(sb);
        bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits);
        if (!bh) {
                printk(KERN_ERR "FAT: unable to read inode block "
@@ -579,7 +578,7 @@ retry:
        if (i_pos != MSDOS_I(inode)->i_pos) {
                spin_unlock(&sbi->inode_hash_lock);
                brelse(bh);
-               unlock_kernel();
+               unlock_super(sb);
                goto retry;
        }
 
@@ -606,7 +605,7 @@ retry:
                err = sync_dirty_buffer(bh);
        brelse(bh);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        return err;
 }
 
@@ -736,6 +735,7 @@ fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable)
 
 static struct dentry *fat_get_parent(struct dentry *child)
 {
+       struct super_block *sb = child->d_sb;
        struct buffer_head *bh;
        struct msdos_dir_entry *de;
        loff_t i_pos;
@@ -743,14 +743,14 @@ static struct dentry *fat_get_parent(struct dentry *child)
        struct inode *inode;
        int err;
 
-       lock_kernel();
+       lock_super(sb);
 
        err = fat_get_dotdot_entry(child->d_inode, &bh, &de, &i_pos);
        if (err) {
                parent = ERR_PTR(err);
                goto out;
        }
-       inode = fat_build_inode(child->d_sb, de, i_pos);
+       inode = fat_build_inode(sb, de, i_pos);
        brelse(bh);
        if (IS_ERR(inode)) {
                parent = ERR_CAST(inode);
@@ -762,7 +762,7 @@ static struct dentry *fat_get_parent(struct dentry *child)
                parent = ERR_PTR(-ENOMEM);
        }
 out:
-       unlock_kernel();
+       unlock_super(sb);
 
        return parent;
 }
@@ -1172,6 +1172,12 @@ int fat_fill_super(struct super_block *sb, void *data, int silent,
        long error;
        char buf[50];
 
+       /*
+        * GFP_KERNEL is ok here, because while we do hold the
+        * supeblock lock, memory pressure can't call back into
+        * the filesystem, since we're only just about to mount
+        * it and have no inodes etc active!
+        */
        sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL);
        if (!sbi)
                return -ENOMEM;

diff --git a/fs/msdos/namei.c b/fs/msdos/namei.c
index 05ff4f1d7026f4fbed45d09208c4b8cda3a0a72e..1f7f2956412ac9527be5867aa5c5bca8ecc81db6 100644 (file)
--- a/fs/msdos/namei.c
+++ b/fs/msdos/namei.c
@@ -214,7 +214,7 @@ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
 
        dentry->d_op = &msdos_dentry_operations;
 
-       lock_kernel();
+       lock_super(sb);
        res = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
        if (res == -ENOENT)
                goto add;
@@ -232,7 +232,7 @@ add:
        if (dentry)
                dentry->d_op = &msdos_dentry_operations;
 out:
-       unlock_kernel();
+       unlock_super(sb);
        if (!res)
                return dentry;
        return ERR_PTR(res);
@@ -286,7 +286,7 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, int mode,
        unsigned char msdos_name[MSDOS_NAME];
        int err, is_hid;
 
-       lock_kernel();
+       lock_super(sb);
 
        err = msdos_format_name(dentry->d_name.name, dentry->d_name.len,
                                msdos_name, &MSDOS_SB(sb)->options);
@@ -315,7 +315,7 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, int mode,
 
        d_instantiate(dentry, inode);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        if (!err)
                err = fat_flush_inodes(sb, dir, inode);
        return err;
@@ -324,11 +324,12 @@ out:
 /***** Remove a directory */
 static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
 {
+       struct super_block *sb = dir->i_sb;
        struct inode *inode = dentry->d_inode;
        struct fat_slot_info sinfo;
        int err;
 
-       lock_kernel();
+       lock_super(sb);
        /*
         * Check whether the directory is not in use, then check
         * whether it is empty.
@@ -349,9 +350,9 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
        inode->i_ctime = CURRENT_TIME_SEC;
        fat_detach(inode);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        if (!err)
-               err = fat_flush_inodes(inode->i_sb, dir, inode);
+               err = fat_flush_inodes(sb, dir, inode);
 
        return err;
 }
@@ -366,7 +367,7 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, int mode)
        struct timespec ts;
        int err, is_hid, cluster;
 
-       lock_kernel();
+       lock_super(sb);
 
        err = msdos_format_name(dentry->d_name.name, dentry->d_name.len,
                                msdos_name, &MSDOS_SB(sb)->options);
@@ -404,14 +405,14 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
        d_instantiate(dentry, inode);
 
-       unlock_kernel();
+       unlock_super(sb);
        fat_flush_inodes(sb, dir, inode);
        return 0;
 
 out_free:
        fat_free_clusters(dir, cluster);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        return err;
 }
 
@@ -419,10 +420,11 @@ out:
 static int msdos_unlink(struct inode *dir, struct dentry *dentry)
 {
        struct inode *inode = dentry->d_inode;
+       struct super_block *sb= inode->i_sb;
        struct fat_slot_info sinfo;
        int err;
 
-       lock_kernel();
+       lock_super(sb);
        err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
        if (err)
                goto out;
@@ -434,9 +436,9 @@ static int msdos_unlink(struct inode *dir, struct dentry *dentry)
        inode->i_ctime = CURRENT_TIME_SEC;
        fat_detach(inode);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        if (!err)
-               err = fat_flush_inodes(inode->i_sb, dir, inode);
+               err = fat_flush_inodes(sb, dir, inode);
 
        return err;
 }
@@ -618,10 +620,11 @@ error_inode:
 static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry,
                        struct inode *new_dir, struct dentry *new_dentry)
 {
+       struct super_block *sb = old_dir->i_sb;
        unsigned char old_msdos_name[MSDOS_NAME], new_msdos_name[MSDOS_NAME];
        int err, is_hid;
 
-       lock_kernel();
+       lock_super(sb);
 
        err = msdos_format_name(old_dentry->d_name.name,
                                old_dentry->d_name.len, old_msdos_name,
@@ -640,9 +643,9 @@ static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry,
        err = do_msdos_rename(old_dir, old_msdos_name, old_dentry,
                              new_dir, new_msdos_name, new_dentry, is_hid);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        if (!err)
-               err = fat_flush_inodes(old_dir->i_sb, old_dir, new_dir);
+               err = fat_flush_inodes(sb, old_dir, new_dir);
        return err;
 }
 

diff --git a/fs/vfat/namei.c b/fs/vfat/namei.c
index a3522727ea5b090ea4ee02d925e7327cde21fe7b..b546ba69be8224f79253e75770a93ff2fdb8a621 100644 (file)
--- a/fs/vfat/namei.c
+++ b/fs/vfat/namei.c
@@ -645,7 +645,7 @@ static int vfat_add_entry(struct inode *dir, struct qstr *qname, int is_dir,
        if (len == 0)
                return -ENOENT;
 
-       slots = kmalloc(sizeof(*slots) * MSDOS_SLOTS, GFP_KERNEL);
+       slots = kmalloc(sizeof(*slots) * MSDOS_SLOTS, GFP_NOFS);
        if (slots == NULL)
                return -ENOMEM;
 
@@ -687,7 +687,7 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
        struct dentry *alias;
        int err, table;
 
-       lock_kernel();
+       lock_super(sb);
        table = (MSDOS_SB(sb)->options.name_check == 's') ? 2 : 0;
        dentry->d_op = &vfat_dentry_ops[table];
 
@@ -699,7 +699,7 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
        inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
        brelse(sinfo.bh);
        if (IS_ERR(inode)) {
-               unlock_kernel();
+               unlock_super(sb);
                return ERR_CAST(inode);
        }
        alias = d_find_alias(inode);
@@ -708,13 +708,13 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
                        dput(alias);
                else {
                        iput(inode);
-                       unlock_kernel();
+                       unlock_super(sb);
                        return alias;
                }
 
        }
 error:
-       unlock_kernel();
+       unlock_super(sb);
        dentry->d_op = &vfat_dentry_ops[table];
        dentry->d_time = dentry->d_parent->d_inode->i_version;
        dentry = d_splice_alias(inode, dentry);
@@ -734,7 +734,7 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, int mode,
        struct timespec ts;
        int err;
 
-       lock_kernel();
+       lock_super(sb);
 
        ts = CURRENT_TIME_SEC;
        err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo);
@@ -755,17 +755,18 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, int mode,
        dentry->d_time = dentry->d_parent->d_inode->i_version;
        d_instantiate(dentry, inode);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        return err;
 }
 
 static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
 {
        struct inode *inode = dentry->d_inode;
+       struct super_block *sb = dir->i_sb;
        struct fat_slot_info sinfo;
        int err;
 
-       lock_kernel();
+       lock_super(sb);
 
        err = fat_dir_empty(inode);
        if (err)
@@ -783,7 +784,7 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
        inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC;
        fat_detach(inode);
 out:
-       unlock_kernel();
+       unlock_super(sb);
 
        return err;
 }
@@ -791,10 +792,11 @@ out:
 static int vfat_unlink(struct inode *dir, struct dentry *dentry)
 {
        struct inode *inode = dentry->d_inode;
+       struct super_block *sb = dir->i_sb;
        struct fat_slot_info sinfo;
        int err;
 
-       lock_kernel();
+       lock_super(sb);
 
        err = vfat_find(dir, &dentry->d_name, &sinfo);
        if (err)
@@ -807,7 +809,7 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry)
        inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC;
        fat_detach(inode);
 out:
-       unlock_kernel();
+       unlock_super(sb);
 
        return err;
 }
@@ -820,7 +822,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, int mode)
        struct timespec ts;
        int err, cluster;
 
-       lock_kernel();
+       lock_super(sb);
 
        ts = CURRENT_TIME_SEC;
        cluster = fat_alloc_new_dir(dir, &ts);
@@ -849,13 +851,13 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, int mode)
        dentry->d_time = dentry->d_parent->d_inode->i_version;
        d_instantiate(dentry, inode);
 
-       unlock_kernel();
+       unlock_super(sb);
        return 0;
 
 out_free:
        fat_free_clusters(dir, cluster);
 out:
-       unlock_kernel();
+       unlock_super(sb);
        return err;
 }
 
@@ -869,11 +871,12 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
        struct timespec ts;
        loff_t dotdot_i_pos, new_i_pos;
        int err, is_dir, update_dotdot, corrupt = 0;
+       struct super_block *sb = old_dir->i_sb;
 
        old_sinfo.bh = sinfo.bh = dotdot_bh = NULL;
        old_inode = old_dentry->d_inode;
        new_inode = new_dentry->d_inode;
-       lock_kernel();
+       lock_super(sb);
        err = vfat_find(old_dir, &old_dentry->d_name, &old_sinfo);
        if (err)
                goto out;
@@ -951,7 +954,7 @@ out:
        brelse(sinfo.bh);
        brelse(dotdot_bh);
        brelse(old_sinfo.bh);
-       unlock_kernel();
+       unlock_super(sb);
 
        return err;