diff options
-rw-r--r-- | Documentation/filesystems/ext3.txt | 6 | ||||
-rw-r--r-- | fs/ext2/balloc.c | 4 | ||||
-rw-r--r-- | fs/ext2/ialloc.c | 2 | ||||
-rw-r--r-- | fs/ext2/super.c | 18 | ||||
-rw-r--r-- | fs/ext2/xattr.c | 1 | ||||
-rw-r--r-- | fs/ext3/dir.c | 167 | ||||
-rw-r--r-- | fs/ext3/ext3.h | 6 | ||||
-rw-r--r-- | fs/ext3/hash.c | 4 | ||||
-rw-r--r-- | fs/ext3/ialloc.c | 20 | ||||
-rw-r--r-- | fs/ext3/super.c | 6 | ||||
-rw-r--r-- | fs/ext4/super.c | 6 | ||||
-rw-r--r-- | fs/jbd/checkpoint.c | 23 | ||||
-rw-r--r-- | fs/jbd/commit.c | 21 | ||||
-rw-r--r-- | fs/jbd/journal.c | 206 | ||||
-rw-r--r-- | fs/jbd/transaction.c | 2 | ||||
-rw-r--r-- | fs/quota/dquot.c | 32 | ||||
-rw-r--r-- | fs/reiserfs/super.c | 6 | ||||
-rw-r--r-- | include/linux/jbd.h | 18 | ||||
-rw-r--r-- | include/trace/events/jbd.h | 39 |
19 files changed, 342 insertions, 245 deletions
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt index b100adc38adb..293855e95000 100644 --- a/Documentation/filesystems/ext3.txt +++ b/Documentation/filesystems/ext3.txt @@ -59,9 +59,9 @@ commit=nrsec (*) Ext3 can be told to sync all its data and metadata Setting it to very large values will improve performance. -barrier=<0(*)|1> This enables/disables the use of write barriers in -barrier the jbd code. barrier=0 disables, barrier=1 enables. -nobarrier (*) This also requires an IO stack which can support +barrier=<0|1(*)> This enables/disables the use of write barriers in +barrier (*) the jbd code. barrier=0 disables, barrier=1 enables. +nobarrier This also requires an IO stack which can support barriers, and if jbd gets an error on a barrier write, it will disable again with a warning. Write barriers enforce proper on-disk ordering diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 030c6d277e14..1c3613998862 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -165,7 +165,6 @@ static void release_blocks(struct super_block *sb, int count) struct ext2_sb_info *sbi = EXT2_SB(sb); percpu_counter_add(&sbi->s_freeblocks_counter, count); - sb->s_dirt = 1; } } @@ -180,7 +179,6 @@ static void group_adjust_blocks(struct super_block *sb, int group_no, free_blocks = le16_to_cpu(desc->bg_free_blocks_count); desc->bg_free_blocks_count = cpu_to_le16(free_blocks + count); spin_unlock(sb_bgl_lock(sbi, group_no)); - sb->s_dirt = 1; mark_buffer_dirty(bh); } } @@ -479,7 +477,7 @@ void ext2_discard_reservation(struct inode *inode) } /** - * ext2_free_blocks_sb() -- Free given blocks and update quota and i_blocks + * ext2_free_blocks() -- Free given blocks and update quota and i_blocks * @inode: inode * @block: start physcial block to free * @count: number of blocks to free diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 8b15cf8cef37..c13eb7b91a11 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -81,7 +81,6 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir) spin_unlock(sb_bgl_lock(EXT2_SB(sb), group)); if (dir) percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter); - sb->s_dirt = 1; mark_buffer_dirty(bh); } @@ -543,7 +542,6 @@ got: } spin_unlock(sb_bgl_lock(sbi, group)); - sb->s_dirt = 1; mark_buffer_dirty(bh2); if (test_opt(sb, GRPID)) { inode->i_mode = mode; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 38f816071ddb..b3621cb7ea31 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -130,9 +130,6 @@ static void ext2_put_super (struct super_block * sb) dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); - if (sb->s_dirt) - ext2_write_super(sb); - ext2_xattr_put_super(sb); if (!(sb->s_flags & MS_RDONLY)) { struct ext2_super_block *es = sbi->s_es; @@ -307,7 +304,6 @@ static const struct super_operations ext2_sops = { .write_inode = ext2_write_inode, .evict_inode = ext2_evict_inode, .put_super = ext2_put_super, - .write_super = ext2_write_super, .sync_fs = ext2_sync_fs, .statfs = ext2_statfs, .remount_fs = ext2_remount, @@ -358,11 +354,6 @@ static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid, ext2_nfs_get_inode); } -/* Yes, most of these are left as NULL!! - * A NULL value implies the default, which works with ext2-like file - * systems, but can be improved upon. - * Currently only get_parent is required. - */ static const struct export_operations ext2_export_ops = { .fh_to_dentry = ext2_fh_to_dentry, .fh_to_parent = ext2_fh_to_parent, @@ -1176,7 +1167,6 @@ static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es, mark_buffer_dirty(EXT2_SB(sb)->s_sbh); if (wait) sync_dirty_buffer(EXT2_SB(sb)->s_sbh); - sb->s_dirt = 0; } /* @@ -1209,8 +1199,6 @@ void ext2_write_super(struct super_block *sb) { if (!(sb->s_flags & MS_RDONLY)) ext2_sync_fs(sb, 1); - else - sb->s_dirt = 0; } static int ext2_remount (struct super_block * sb, int * flags, char * data) @@ -1456,7 +1444,6 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type, struct buffer_head tmp_bh; struct buffer_head *bh; - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); while (towrite > 0) { tocopy = sb->s_blocksize - offset < towrite ? sb->s_blocksize - offset : towrite; @@ -1486,16 +1473,13 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) { - mutex_unlock(&inode->i_mutex); + if (len == towrite) return err; - } if (inode->i_size < off+len-towrite) i_size_write(inode, off+len-towrite); inode->i_version++; inode->i_mtime = inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); - mutex_unlock(&inode->i_mutex); return len - towrite; } diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 6dcafc7efdfd..b6754dbbce3c 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -339,7 +339,6 @@ static void ext2_xattr_update_super_block(struct super_block *sb) spin_lock(&EXT2_SB(sb)->s_lock); EXT2_SET_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR); spin_unlock(&EXT2_SB(sb)->s_lock); - sb->s_dirt = 1; mark_buffer_dirty(EXT2_SB(sb)->s_sbh); } diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index cc761ad8fa57..92490e9f85ca 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 7977973a24f0..e85ff15a060e 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 d10231ddcf8a..ede315cdf126 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 e3c39e4cec19..082afd78b107 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 94ef7e616129..8c3a44b7c375 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; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 436b4223df66..1867a98e0c49 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4758,7 +4758,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, return -EIO; } - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); bh = ext4_bread(handle, inode, blk, 1, &err); if (!bh) goto out; @@ -4774,16 +4773,13 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, err = ext4_handle_dirty_metadata(handle, NULL, bh); 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); EXT4_I(inode)->i_disksize = inode->i_size; ext4_mark_inode_dirty(handle, inode); } - mutex_unlock(&inode->i_mutex); return len; } diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 05f0754f2b46..08c03044abdd 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -508,20 +508,19 @@ int cleanup_journal_tail(journal_t *journal) /* * We need to make sure that any blocks that were recently written out * --- perhaps by log_do_checkpoint() --- are flushed out before we - * drop the transactions from the journal. It's unlikely this will be - * necessary, especially with an appropriately sized journal, but we - * need this to guarantee correctness. Fortunately - * cleanup_journal_tail() doesn't get called all that often. + * drop the transactions from the journal. Similarly we need to be sure + * superblock makes it to disk before next transaction starts reusing + * freed space (otherwise we could replay some blocks of the new + * transaction thinking they belong to the old one). So we use + * WRITE_FLUSH_FUA. It's unlikely this will be necessary, especially + * with an appropriately sized journal, but we need this to guarantee + * correctness. Fortunately cleanup_journal_tail() doesn't get called + * all that often. */ - if (journal->j_flags & JFS_BARRIER) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + journal_update_sb_log_tail(journal, first_tid, blocknr, + WRITE_FLUSH_FUA); spin_lock(&journal->j_state_lock); - if (!tid_gt(first_tid, journal->j_tail_sequence)) { - spin_unlock(&journal->j_state_lock); - /* Someone else cleaned up journal so return 0 */ - return 0; - } /* OK, update the superblock to recover the freed space. * Physical blocks come first: have we wrapped beyond the end of * the log? */ @@ -539,8 +538,6 @@ int cleanup_journal_tail(journal_t *journal) journal->j_tail_sequence = first_tid; journal->j_tail = blocknr; spin_unlock(&journal->j_state_lock); - if (!(journal->j_flags & JFS_ABORT)) - journal_update_superblock(journal, 1); return 0; } diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index f2b9a571f4cf..52c15c776029 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -298,6 +298,7 @@ void journal_commit_transaction(journal_t *journal) int tag_flag; int i; struct blk_plug plug; + int write_op = WRITE; /* * First job: lock down the current transaction and wait for @@ -307,7 +308,16 @@ void journal_commit_transaction(journal_t *journal) /* Do we need to erase the effects of a prior journal_flush? */ if (journal->j_flags & JFS_FLUSHED) { jbd_debug(3, "super block updated\n"); - journal_update_superblock(journal, 1); + mutex_lock(&journal->j_checkpoint_mutex); + /* + * We hold j_checkpoint_mutex so tail cannot change under us. + * We don't need any special data guarantees for writing sb + * since journal is empty and it is ok for write to be + * flushed only with transaction commit. + */ + journal_update_sb_log_tail(journal, journal->j_tail_sequence, + journal->j_tail, WRITE_SYNC); + mutex_unlock(&journal->j_checkpoint_mutex); } else { jbd_debug(3, "superblock not updated\n"); } @@ -413,13 +423,16 @@ void journal_commit_transaction(journal_t *journal) jbd_debug (3, "JBD: commit phase 2\n"); + if (tid_geq(journal->j_commit_waited, commit_transaction->t_tid)) + write_op = WRITE_SYNC; + /* * Now start flushing things to disk, in the order they appear * on the transaction lists. Data blocks go first. */ blk_start_plug(&plug); err = journal_submit_data_buffers(journal, commit_transaction, - WRITE_SYNC); + write_op); blk_finish_plug(&plug); /* @@ -478,7 +491,7 @@ void journal_commit_transaction(journal_t *journal) blk_start_plug(&plug); - journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC); + journal_write_revoke_records(journal, commit_transaction, write_op); /* * If we found any dirty or locked buffers, then we should have @@ -649,7 +662,7 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(WRITE_SYNC, bh); + submit_bh(write_op, bh); } cond_resched(); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 0971e9217808..425c2f2cf170 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -563,6 +563,8 @@ int log_wait_commit(journal_t *journal, tid_t tid) spin_unlock(&journal->j_state_lock); #endif spin_lock(&journal->j_state_lock); + if (!tid_geq(journal->j_commit_waited, tid)) + journal->j_commit_waited = tid; while (tid_gt(tid, journal->j_commit_sequence)) { jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n", tid, journal->j_commit_sequence); @@ -921,8 +923,33 @@ static int journal_reset(journal_t *journal) journal->j_max_transaction_buffers = journal->j_maxlen / 4; - /* Add the dynamic fields and write it to disk. */ - journal_update_superblock(journal, 1); + /* + * As a special case, if the on-disk copy is already marked as needing + * no recovery (s_start == 0), then we can safely defer the superblock + * update until the next commit by setting JFS_FLUSHED. This avoids + * attempting a write to a potential-readonly device. + */ + if (sb->s_start == 0) { + jbd_debug(1,"JBD: Skipping superblock update on recovered sb " + "(start %u, seq %d, errno %d)\n", + journal->j_tail, journal->j_tail_sequence, + journal->j_errno); + journal->j_flags |= JFS_FLUSHED; + } else { + /* Lock here to make assertions happy... */ + mutex_lock(&journal->j_checkpoint_mutex); + /* + * Update log tail information. We use WRITE_FUA since new + * transaction will start reusing journal space and so we + * must make sure information about current log tail is on + * disk before that. + */ + journal_update_sb_log_tail(journal, + journal->j_tail_sequence, + journal->j_tail, + WRITE_FUA); + mutex_unlock(&journal->j_checkpoint_mutex); + } return journal_start_thread(journal); } @@ -999,35 +1026,15 @@ int journal_create(journal_t *journal) return journal_reset(journal); } -/** - * void journal_update_superblock() - Update journal sb on disk. - * @journal: The journal to update. - * @wait: Set to '0' if you don't want to wait for IO completion. - * - * Update a journal's dynamic superblock fields and write it to disk, - * optionally waiting for the IO to complete. - */ -void journal_update_superblock(journal_t *journal, int wait) +static void journal_write_superblock(journal_t *journal, int write_op) { - journal_superblock_t *sb = journal->j_superblock; struct buffer_head *bh = journal->j_sb_buffer; + int ret; - /* - * As a special case, if the on-disk copy is already marked as needing - * no recovery (s_start == 0) and there are no outstanding transactions - * in the filesystem, then we can safely defer the superblock update - * until the next commit by setting JFS_FLUSHED. This avoids - * attempting a write to a potential-readonly device. - */ - if (sb->s_start == 0 && journal->j_tail_sequence == - journal->j_transaction_sequence) { - jbd_debug(1,"JBD: Skipping superblock update on recovered sb " - "(start %u, seq %d, errno %d)\n", - journal->j_tail, journal->j_tail_sequence, - journal->j_errno); - goto out; - } - + trace_journal_write_superblock(journal, write_op); + if (!(journal->j_flags & JFS_BARRIER)) + write_op &= ~(REQ_FUA | REQ_FLUSH); + lock_buffer(bh); if (buffer_write_io_error(bh)) { char b[BDEVNAME_SIZE]; /* @@ -1045,42 +1052,100 @@ void journal_update_superblock(journal_t *journal, int wait) set_buffer_uptodate(bh); } + get_bh(bh); + bh->b_end_io = end_buffer_write_sync; + ret = submit_bh(write_op, bh); + wait_on_buffer(bh); + if (buffer_write_io_error(bh)) { + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + ret = -EIO; + } + if (ret) { + char b[BDEVNAME_SIZE]; + printk(KERN_ERR "JBD: Error %d detected " + "when updating journal superblock for %s.\n", + ret, journal_dev_name(journal, b)); + } +} + +/** + * journal_update_sb_log_tail() - Update log tail in journal sb on disk. + * @journal: The journal to update. + * @tail_tid: TID of the new transaction at the tail of the log + * @tail_block: The first block of the transaction at the tail of the log + * @write_op: With which operation should we write the journal sb + * + * Update a journal's superblock information about log tail and write it to + * disk, waiting for the IO to complete. + */ +void journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, + unsigned int tail_block, int write_op) +{ + journal_superblock_t *sb = journal->j_superblock; + + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); + jbd_debug(1,"JBD: updating superblock (start %u, seq %u)\n", + tail_block, tail_tid); + + sb->s_sequence = cpu_to_be32(tail_tid); + sb->s_start = cpu_to_be32(tail_block); + + journal_write_superblock(journal, write_op); + + /* Log is no longer empty */ + spin_lock(&journal->j_state_lock); + WARN_ON(!sb->s_sequence); + journal->j_flags &= ~JFS_FLUSHED; + spin_unlock(&journal->j_state_lock); +} + +/** + * mark_journal_empty() - Mark on disk journal as empty. + * @journal: The journal to update. + * + * Update a journal's dynamic superblock fields to show that journal is empty. + * Write updated superblock to disk waiting for IO to complete. + */ +static void mark_journal_empty(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); spin_lock(&journal->j_state_lock); - jbd_debug(1,"JBD: updating superblock (start %u, seq %d, errno %d)\n", - journal->j_tail, journal->j_tail_sequence, journal->j_errno); + jbd_debug(1, "JBD: Marking journal as empty (seq %d)\n", + journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); - sb->s_start = cpu_to_be32(journal->j_tail); - sb->s_errno = cpu_to_be32(journal->j_errno); + sb->s_start = cpu_to_be32(0); spin_unlock(&journal->j_state_lock); - BUFFER_TRACE(bh, "marking dirty"); - mark_buffer_dirty(bh); - if (wait) { - sync_dirty_buffer(bh); - if (buffer_write_io_error(bh)) { - char b[BDEVNAME_SIZE]; - printk(KERN_ERR "JBD: I/O error detected " - "when updating journal superblock for %s.\n", - journal_dev_name(journal, b)); - clear_buffer_write_io_error(bh); - set_buffer_uptodate(bh); - } - } else - write_dirty_buffer(bh, WRITE); + journal_write_superblock(journal, WRITE_FUA); - trace_jbd_update_superblock_end(journal, wait); -out: - /* If we have just flushed the log (by marking s_start==0), then - * any future commit will have to be careful to update the - * superblock again to re-record the true start of the log. */ + spin_lock(&journal->j_state_lock); + /* Log is empty */ + journal->j_flags |= JFS_FLUSHED; + spin_unlock(&journal->j_state_lock); +} + +/** + * journal_update_sb_errno() - Update error in the journal. + * @journal: The journal to update. + * + * Update a journal's errno. Write updated superblock to disk waiting for IO + * to complete. + */ +static void journal_update_sb_errno(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; spin_lock(&journal->j_state_lock); - if (sb->s_start) - journal->j_flags &= ~JFS_FLUSHED; - else - journal->j_flags |= JFS_FLUSHED; + jbd_debug(1, "JBD: updating superblock error (errno %d)\n", + journal->j_errno); + sb->s_errno = cpu_to_be32(journal->j_errno); spin_unlock(&journal->j_state_lock); + + journal_write_superblock(journal, WRITE_SYNC); } /* @@ -1251,6 +1316,8 @@ int journal_destroy(journal_t *journal) /* Force any old transactions to disk */ + /* We cannot race with anybody but must keep assertions happy */ + mutex_lock(&journal->j_checkpoint_mutex); /* Totally anal locking here... */ spin_lock(&journal->j_list_lock); while (journal->j_checkpoint_transactions != NULL) { @@ -1266,16 +1333,14 @@ int journal_destroy(journal_t *journal) if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { - /* We can now mark the journal as empty. */ - journal->j_tail = 0; journal->j_tail_sequence = ++journal->j_transaction_sequence; - journal_update_superblock(journal, 1); - } el |