aboutsummaryrefslogtreecommitdiff
path: root/fs/ext3
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-05-25 08:14:59 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-05-25 08:14:59 -0700
commitece78b7df734726e790dcab207f463401ff80440 (patch)
tree4a0b23c28c6a727d5eebc8a88a22fe3720c425fd /fs/ext3
parent07acfc2a9349a8ce45b236c2624dad452001966b (diff)
parent0324876628a9c7faf8127e20af29373dc6dec876 (diff)
downloadlinux-ece78b7df734726e790dcab207f463401ff80440.tar.gz
Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs
Pull ext2, ext3 and quota fixes from Jan Kara: "Interesting bits are: - removal of a special i_mutex locking subclass (I_MUTEX_QUOTA) since quota code does not need i_mutex anymore in any unusual way. - backport (from ext4) of a fix of a checkpointing bug (missing cache flush) that could lead to fs corruption on power failure The rest are just random small fixes & cleanups." * 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: ext2: trivial fix to comment for ext2_free_blocks ext2: remove the redundant comment for ext2_export_ops ext3: return 32/64-bit dir name hash according to usage type quota: Get rid of nested I_MUTEX_QUOTA locking subclass quota: Use precomputed value of sb_dqopt in dquot_quota_sync ext2: Remove i_mutex use from ext2_quota_write() reiserfs: Remove i_mutex use from reiserfs_quota_write() ext4: Remove i_mutex use from ext4_quota_write() ext3: Remove i_mutex use from ext3_quota_write() quota: Fix double lock in add_dquot_ref() with CONFIG_QUOTA_DEBUG jbd: Write journal superblock with WRITE_FUA after checkpointing jbd: protect all log tail updates with j_checkpoint_mutex jbd: Split updating of journal superblock and marking journal empty ext2: do not register write_super within VFS ext2: Remove s_dirt handling ext2: write superblock only once on unmount ext3: update documentation with barrier=1 default ext3: remove max_debt in find_group_orlov() jbd: Refine commit writeout logic
Diffstat (limited to 'fs/ext3')
-rw-r--r--fs/ext3/dir.c167
-rw-r--r--fs/ext3/ext3.h6
-rw-r--r--fs/ext3/hash.c4
-rw-r--r--fs/ext3/ialloc.c20
-rw-r--r--fs/ext3/super.c6
5 files changed, 132 insertions, 71 deletions
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index cc761ad8fa5..92490e9f85c 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -21,30 +21,15 @@
*
*/
+#include <linux/compat.h>
#include "ext3.h"
static unsigned char ext3_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
-static int ext3_readdir(struct file *, void *, filldir_t);
static int ext3_dx_readdir(struct file * filp,
void * dirent, filldir_t filldir);
-static int ext3_release_dir (struct inode * inode,
- struct file * filp);
-
-const struct file_operations ext3_dir_operations = {
- .llseek = generic_file_llseek,
- .read = generic_read_dir,
- .readdir = ext3_readdir, /* we take BKL. needed?*/
- .unlocked_ioctl = ext3_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ext3_compat_ioctl,
-#endif
- .fsync = ext3_sync_file, /* BKL held */
- .release = ext3_release_dir,
-};
-
static unsigned char get_dtype(struct super_block *sb, int filetype)
{
@@ -55,6 +40,25 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
return (ext3_filetype_table[filetype]);
}
+/**
+ * Check if the given dir-inode refers to an htree-indexed directory
+ * (or a directory which chould potentially get coverted to use htree
+ * indexing).
+ *
+ * Return 1 if it is a dx dir, 0 if not
+ */
+static int is_dx_dir(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
+ EXT3_FEATURE_COMPAT_DIR_INDEX) &&
+ ((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) ||
+ ((inode->i_size >> sb->s_blocksize_bits) == 1)))
+ return 1;
+
+ return 0;
+}
int ext3_check_dir_entry (const char * function, struct inode * dir,
struct ext3_dir_entry_2 * de,
@@ -94,18 +98,13 @@ static int ext3_readdir(struct file * filp,
unsigned long offset;
int i, stored;
struct ext3_dir_entry_2 *de;
- struct super_block *sb;
int err;
struct inode *inode = filp->f_path.dentry->d_inode;
+ struct super_block *sb = inode->i_sb;
int ret = 0;
int dir_has_error = 0;
- sb = inode->i_sb;
-
- if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
- EXT3_FEATURE_COMPAT_DIR_INDEX) &&
- ((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) ||
- ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+ if (is_dx_dir(inode)) {
err = ext3_dx_readdir(filp, dirent, filldir);
if (err != ERR_BAD_DX_DIR) {
ret = err;
@@ -227,22 +226,87 @@ out:
return ret;
}
+static inline int is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+ return is_compat_task();
+#else
+ return (BITS_PER_LONG == 32);
+#endif
+}
+
/*
* These functions convert from the major/minor hash to an f_pos
- * value.
+ * value for dx directories
*
- * Currently we only use major hash numer. This is unfortunate, but
- * on 32-bit machines, the same VFS interface is used for lseek and
- * llseek, so if we use the 64 bit offset, then the 32-bit versions of
- * lseek/telldir/seekdir will blow out spectacularly, and from within
- * the ext2 low-level routine, we don't know if we're being called by
- * a 64-bit version of the system call or the 32-bit version of the
- * system call. Worse yet, NFSv2 only allows for a 32-bit readdir
- * cookie. Sigh.
+ * Upper layer (for example NFS) should specify FMODE_32BITHASH or
+ * FMODE_64BITHASH explicitly. On the other hand, we allow ext3 to be mounted
+ * directly on both 32-bit and 64-bit nodes, under such case, neither
+ * FMODE_32BITHASH nor FMODE_64BITHASH is specified.
*/
-#define hash2pos(major, minor) (major >> 1)
-#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff)
-#define pos2min_hash(pos) (0)
+static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return major >> 1;
+ else
+ return ((__u64)(major >> 1) << 32) | (__u64)minor;
+}
+
+static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return (pos << 1) & 0xffffffff;
+ else
+ return ((pos >> 32) << 1) & 0xffffffff;
+}
+
+static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return 0;
+ else
+ return pos & 0xffffffff;
+}
+
+/*
+ * Return 32- or 64-bit end-of-file for dx directories
+ */
+static inline loff_t ext3_get_htree_eof(struct file *filp)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return EXT3_HTREE_EOF_32BIT;
+ else
+ return EXT3_HTREE_EOF_64BIT;
+}
+
+
+/*
+ * ext3_dir_llseek() calls generic_file_llseek[_size]() to handle both
+ * non-htree and htree directories, where the "offset" is in terms
+ * of the filename hash value instead of the byte offset.
+ *
+ * Because we may return a 64-bit hash that is well beyond s_maxbytes,
+ * we need to pass the max hash as the maximum allowable offset in
+ * the htree directory case.
+ *
+ * NOTE: offsets obtained *before* ext3_set_inode_flag(dir, EXT3_INODE_INDEX)
+ * will be invalid once the directory was converted into a dx directory
+ */
+loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct inode *inode = file->f_mapping->host;
+ int dx_dir = is_dx_dir(inode);
+
+ if (likely(dx_dir))
+ return generic_file_llseek_size(file, offset, origin,
+ ext3_get_htree_eof(file));
+ else
+ return generic_file_llseek(file, offset, origin);
+}
/*
* This structure holds the nodes of the red-black tree used to store
@@ -303,15 +367,16 @@ static void free_rb_tree_fname(struct rb_root *root)
}
-static struct dir_private_info *ext3_htree_create_dir_info(loff_t pos)
+static struct dir_private_info *ext3_htree_create_dir_info(struct file *filp,
+ loff_t pos)
{
struct dir_private_info *p;
p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
if (!p)
return NULL;
- p->curr_hash = pos2maj_hash(pos);
- p->curr_minor_hash = pos2min_hash(pos);
+ p->curr_hash = pos2maj_hash(filp, pos);
+ p->curr_minor_hash = pos2min_hash(filp, pos);
return p;
}
@@ -401,7 +466,7 @@ static int call_filldir(struct file * filp, void * dirent,
printk("call_filldir: called with null fname?!?\n");
return 0;
}
- curr_pos = hash2pos(fname->hash, fname->minor_hash);
+ curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
while (fname) {
error = filldir(dirent, fname->name,
fname->name_len, curr_pos,
@@ -426,13 +491,13 @@ static int ext3_dx_readdir(struct file * filp,
int ret;
if (!info) {
- info = ext3_htree_create_dir_info(filp->f_pos);
+ info = ext3_htree_create_dir_info(filp, filp->f_pos);
if (!info)
return -ENOMEM;
filp->private_data = info;
}
- if (filp->f_pos == EXT3_HTREE_EOF)
+ if (filp->f_pos == ext3_get_htree_eof(filp))
return 0; /* EOF */
/* Some one has messed with f_pos; reset the world */
@@ -440,8 +505,8 @@ static int ext3_dx_readdir(struct file * filp,
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
- info->curr_hash = pos2maj_hash(filp->f_pos);
- info->curr_minor_hash = pos2min_hash(filp->f_pos);
+ info->curr_hash = pos2maj_hash(filp, filp->f_pos);
+ info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
}
/*
@@ -473,7 +538,7 @@ static int ext3_dx_readdir(struct file * filp,
if (ret < 0)
return ret;
if (ret == 0) {
- filp->f_pos = EXT3_HTREE_EOF;
+ filp->f_pos = ext3_get_htree_eof(filp);
break;
}
info->curr_node = rb_first(&info->root);
@@ -493,7 +558,7 @@ static int ext3_dx_readdir(struct file * filp,
info->curr_minor_hash = fname->minor_hash;
} else {
if (info->next_hash == ~0) {
- filp->f_pos = EXT3_HTREE_EOF;
+ filp->f_pos = ext3_get_htree_eof(filp);
break;
}
info->curr_hash = info->next_hash;
@@ -512,3 +577,15 @@ static int ext3_release_dir (struct inode * inode, struct file * filp)
return 0;
}
+
+const struct file_operations ext3_dir_operations = {
+ .llseek = ext3_dir_llseek,
+ .read = generic_read_dir,
+ .readdir = ext3_readdir,
+ .unlocked_ioctl = ext3_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ext3_compat_ioctl,
+#endif
+ .fsync = ext3_sync_file,
+ .release = ext3_release_dir,
+};
diff --git a/fs/ext3/ext3.h b/fs/ext3/ext3.h
index 7977973a24f..e85ff15a060 100644
--- a/fs/ext3/ext3.h
+++ b/fs/ext3/ext3.h
@@ -920,7 +920,11 @@ struct dx_hash_info
u32 *seed;
};
-#define EXT3_HTREE_EOF 0x7fffffff
+
+/* 32 and 64 bit signed EOF for dx directories */
+#define EXT3_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1)
+#define EXT3_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1)
+
/*
* Control parameters used by ext3_htree_next_block
diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c
index d10231ddcf8..ede315cdf12 100644
--- a/fs/ext3/hash.c
+++ b/fs/ext3/hash.c
@@ -198,8 +198,8 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
return -1;
}
hash = hash & ~1;
- if (hash == (EXT3_HTREE_EOF << 1))
- hash = (EXT3_HTREE_EOF-1) << 1;
+ if (hash == (EXT3_HTREE_EOF_32BIT << 1))
+ hash = (EXT3_HTREE_EOF_32BIT - 1) << 1;
hinfo->hash = hash;
hinfo->minor_hash = minor_hash;
return 0;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index e3c39e4cec1..082afd78b10 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -180,8 +180,7 @@ error_return:
* It's OK to put directory into a group unless
* it has too many directories already (max_dirs) or
* it has too few free inodes left (min_inodes) or
- * it has too few free blocks left (min_blocks) or
- * it's already running too large debt (max_debt).
+ * it has too few free blocks left (min_blocks).
* Parent's group is preferred, if it doesn't satisfy these
* conditions we search cyclically through the rest. If none
* of the groups look good we just look for a group with more
@@ -191,21 +190,16 @@ error_return:
* when we allocate an inode, within 0--255.
*/
-#define INODE_COST 64
-#define BLOCK_COST 256
-
static int find_group_orlov(struct super_block *sb, struct inode *parent)
{
int parent_group = EXT3_I(parent)->i_block_group;
struct ext3_sb_info *sbi = EXT3_SB(sb);
- struct ext3_super_block *es = sbi->s_es;
int ngroups = sbi->s_groups_count;
int inodes_per_group = EXT3_INODES_PER_GROUP(sb);
unsigned int freei, avefreei;
ext3_fsblk_t freeb, avefreeb;
- ext3_fsblk_t blocks_per_dir;
unsigned int ndirs;
- int max_debt, max_dirs, min_inodes;
+ int max_dirs, min_inodes;
ext3_grpblk_t min_blocks;
int group = -1, i;
struct ext3_group_desc *desc;
@@ -242,20 +236,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
goto fallback;
}
- blocks_per_dir = (le32_to_cpu(es->s_blocks_count) - freeb) / ndirs;
-
max_dirs = ndirs / ngroups + inodes_per_group / 16;
min_inodes = avefreei - inodes_per_group / 4;
min_blocks = avefreeb - EXT3_BLOCKS_PER_GROUP(sb) / 4;
- max_debt = EXT3_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, (ext3_fsblk_t)BLOCK_COST);
- if (max_debt * INODE_COST > inodes_per_group)
- max_debt = inodes_per_group / INODE_COST;
- if (max_debt > 255)
- max_debt = 255;
- if (max_debt == 0)
- max_debt = 1;
-
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
desc = ext3_get_group_desc (sb, group, NULL);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 94ef7e61612..8c3a44b7c37 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -3015,7 +3015,6 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type,
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
bh = ext3_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
@@ -3039,10 +3038,8 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type,
}
brelse(bh);
out:
- if (err) {
- mutex_unlock(&inode->i_mutex);
+ if (err)
return err;
- }
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT3_I(inode)->i_disksize = inode->i_size;
@@ -3050,7 +3047,6 @@ out:
inode->i_version++;
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext3_mark_inode_dirty(handle, inode);
- mutex_unlock(&inode->i_mutex);
return len;
}