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
struct ext2_sb_info *sbi = EXT2_SB(sb);
percpu_counter_add(&sbi->s_freeblocks_counter, count);
- sb->s_dirt = 1;
}
}
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);
}
}
}
/**
- * 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
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);
}
}
spin_unlock(sb_bgl_lock(sbi, group));
- sb->s_dirt = 1;
mark_buffer_dirty(bh2);
if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
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;
.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,
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,
mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
if (wait)
sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
- sb->s_dirt = 0;
}
/*
{
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)
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;
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;
}
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);
}
*
*/
+#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)
{
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,
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;
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
}
-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;
}
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,
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 */
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);
}
/*
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);
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;
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,
+};
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
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;
* 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
* 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;
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);
(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;
}
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;
inode->i_version++;
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
ext3_mark_inode_dirty(handle, inode);
- mutex_unlock(&inode->i_mutex);
return len;
}
return -EIO;
}
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
bh = ext4_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
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;
}
/*
* 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? */
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;
}
int tag_flag;
int i;
struct blk_plug plug;
+ int write_op = WRITE;
/*
* First job: lock down the current transaction and wait for
/* 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");
}
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);
/*
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
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();
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);
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);
}
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];
/*
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);
}
/*
/* 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) {
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);
- } else {
+ mark_journal_empty(journal);
+ } else
err = -EIO;
- }
brelse(journal->j_sb_buffer);
}
+ mutex_unlock(&journal->j_checkpoint_mutex);
if (journal->j_inode)
iput(journal->j_inode);
{
int err = 0;
transaction_t *transaction = NULL;
- unsigned int old_tail;
spin_lock(&journal->j_state_lock);
if (is_journal_aborted(journal))
return -EIO;
+ mutex_lock(&journal->j_checkpoint_mutex);
cleanup_journal_tail(journal);
/* Finally, mark the journal as really needing no recovery.
* the magic code for a fully-recovered superblock. Any future
* commits of data to the journal will restore the current
* s_start value. */
+ mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
spin_lock(&journal->j_state_lock);
- old_tail = journal->j_tail;
- journal->j_tail = 0;
- spin_unlock(&journal->j_state_lock);
- journal_update_superblock(journal, 1);
- spin_lock(&journal->j_state_lock);
- journal->j_tail = old_tail;
-
J_ASSERT(!journal->j_running_transaction);
J_ASSERT(!journal->j_committing_transaction);
J_ASSERT(!journal->j_checkpoint_transactions);
write ? "Clearing" : "Ignoring");
err = journal_skip_recovery(journal);
- if (write)
- journal_update_superblock(journal, 1);
+ if (write) {
+ /* Lock to make assertions happy... */
+ mutex_lock(&journal->j_checkpoint_mutex);
+ mark_journal_empty(journal);
+ mutex_unlock(&journal->j_checkpoint_mutex);
+ }
no_recovery:
return err;
__journal_abort_hard(journal);
if (errno)
- journal_update_superblock(journal, 1);
+ journal_update_sb_errno(journal);
}
/**
}
}
- if (handle->h_sync)
- transaction->t_synchronous_commit = 1;
current->journal_info = NULL;
spin_lock(&journal->j_state_lock);
spin_lock(&transaction->t_handle_lock);
* spinlock to internal buffers before writing.
*
* Lock ordering (including related VFS locks) is the following:
- * i_mutex > dqonoff_sem > journal_lock > dqptr_sem > dquot->dq_lock >
+ * dqonoff_mutex > i_mutex > journal_lock > dqptr_sem > dquot->dq_lock >
* dqio_mutex
+ * dqonoff_mutex > i_mutex comes from dquot_quota_sync, dquot_enable, etc.
* The lock ordering of dqptr_sem imposed by quota code is only dqonoff_sem >
* dqptr_sem. But filesystem has to count with the fact that functions such as
* dquot_alloc_space() acquire dqptr_sem and they usually have to be called
* from inside a transaction to keep filesystem consistency after a crash. Also
* filesystems usually want to do some IO on dquot from ->mark_dirty which is
* called with dqptr_sem held.
- * i_mutex on quota files is special (it's below dqio_mutex)
*/
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock);
dqstats_inc(DQST_SYNCS);
mutex_unlock(&dqopt->dqonoff_mutex);
- if (!wait || (sb_dqopt(sb)->flags & DQUOT_QUOTA_SYS_FILE))
+ if (!wait || (dqopt->flags & DQUOT_QUOTA_SYS_FILE))
return 0;
/* This is not very clever (and fast) but currently I don't know about
* Now when everything is written we can discard the pagecache so
* that userspace sees the changes.
*/
- mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
+ mutex_lock(&dqopt->dqonoff_mutex);
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
if (type != -1 && cnt != type)
continue;
if (!sb_has_quota_active(sb, cnt))
continue;
- mutex_lock_nested(&sb_dqopt(sb)->files[cnt]->i_mutex,
- I_MUTEX_QUOTA);
- truncate_inode_pages(&sb_dqopt(sb)->files[cnt]->i_data, 0);
- mutex_unlock(&sb_dqopt(sb)->files[cnt]->i_mutex);
+ mutex_lock(&dqopt->files[cnt]->i_mutex);
+ truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
+ mutex_unlock(&dqopt->files[cnt]->i_mutex);
}
- mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex);
+ mutex_unlock(&dqopt->dqonoff_mutex);
return 0;
}
spin_unlock(&inode->i_lock);
continue;
}
-#ifdef CONFIG_QUOTA_DEBUG
- if (unlikely(inode_get_rsv_space(inode) > 0))
- reserved = 1;
-#endif
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_sb_list_lock);
+#ifdef CONFIG_QUOTA_DEBUG
+ if (unlikely(inode_get_rsv_space(inode) > 0))
+ reserved = 1;
+#endif
iput(old_inode);
__dquot_initialize(inode, type);
/* If quota was reenabled in the meantime, we have
* nothing to do */
if (!sb_has_quota_loaded(sb, cnt)) {
- mutex_lock_nested(&toputinode[cnt]->i_mutex,
- I_MUTEX_QUOTA);
+ mutex_lock(&toputinode[cnt]->i_mutex);
toputinode[cnt]->i_flags &= ~(S_IMMUTABLE |
S_NOATIME | S_NOQUOTA);
truncate_inode_pages(&toputinode[cnt]->i_data,
/* We don't want quota and atime on quota files (deadlocks
* possible) Also nobody should write to the file - we use
* special IO operations which ignore the immutable bit. */
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
+ mutex_lock(&inode->i_mutex);
oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE |
S_NOQUOTA);
inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE;
iput(inode);
out_lock:
if (oldflags != -1) {
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
+ mutex_lock(&inode->i_mutex);
/* Set the flags back (in the case of accidental quotaon()
* on a wrong file we don't want to mess up the flags) */
inode->i_flags &= ~(S_NOATIME | S_NOQUOTA | S_IMMUTABLE);
(unsigned long long)off, (unsigned long long)len);
return -EIO;
}
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
while (towrite > 0) {
tocopy = sb->s_blocksize - offset < towrite ?
sb->s_blocksize - offset : towrite;
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;
}
* How many handles used this transaction? [t_handle_lock]
*/
int t_handle_count;
-
- /*
- * This transaction is being forced and some process is
- * waiting for it to finish.
- */
- unsigned int t_synchronous_commit:1;
};
/**
* transaction
* @j_commit_request: Sequence number of the most recent transaction wanting
* commit
+ * @j_commit_waited: Sequence number of the most recent transaction someone
+ * is waiting for to commit.
* @j_uuid: Uuid of client object.
* @j_task: Pointer to the current commit thread for this journal
* @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a
*/
tid_t j_commit_request;
+ /*
+ * Sequence number of the most recent transaction someone is waiting
+ * for to commit.
+ * [j_state_lock]
+ */
+ tid_t j_commit_waited;
+
/*
* Journal uuid: identifies the object (filesystem, LVM volume etc)
* backed by this journal. This will eventually be replaced by an array
extern int journal_recover (journal_t *journal);
extern int journal_wipe (journal_t *, int);
extern int journal_skip_recovery (journal_t *);
-extern void journal_update_superblock (journal_t *, int);
+extern void journal_update_sb_log_tail (journal_t *, tid_t, unsigned int,
+ int);
extern void journal_abort (journal_t *, int);
extern int journal_errno (journal_t *);
extern void journal_ack_err (journal_t *);
TP_STRUCT__entry(
__field( dev_t, dev )
- __field( char, sync_commit )
__field( int, transaction )
),
TP_fast_assign(
__entry->dev = journal->j_fs_dev->bd_dev;
- __entry->sync_commit = commit_transaction->t_synchronous_commit;
__entry->transaction = commit_transaction->t_tid;
),
- TP_printk("dev %d,%d transaction %d sync %d",
+ TP_printk("dev %d,%d transaction %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->transaction, __entry->sync_commit)
+ __entry->transaction)
);
DEFINE_EVENT(jbd_commit, jbd_start_commit,
TP_STRUCT__entry(
__field( dev_t, dev )
- __field( char, sync_commit )
__field( int, transaction )
),
TP_fast_assign(
__entry->dev = journal->j_fs_dev->bd_dev;
- __entry->sync_commit = commit_transaction->t_synchronous_commit;
__entry->transaction = commit_transaction->t_tid;
),
- TP_printk("dev %d,%d transaction %d sync %d",
+ TP_printk("dev %d,%d transaction %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->transaction, __entry->sync_commit)
+ __entry->transaction)
);
TRACE_EVENT(jbd_end_commit,
TP_STRUCT__entry(
__field( dev_t, dev )
- __field( char, sync_commit )
__field( int, transaction )
__field( int, head )
),
TP_fast_assign(
__entry->dev = journal->j_fs_dev->bd_dev;
- __entry->sync_commit = commit_transaction->t_synchronous_commit;
__entry->transaction = commit_transaction->t_tid;
__entry->head = journal->j_tail_sequence;
),
- TP_printk("dev %d,%d transaction %d sync %d head %d",
+ TP_printk("dev %d,%d transaction %d head %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->transaction, __entry->sync_commit, __entry->head)
+ __entry->transaction, __entry->head)
);
TRACE_EVENT(jbd_do_submit_data,
TP_STRUCT__entry(
__field( dev_t, dev )
- __field( char, sync_commit )
__field( int, transaction )
),
TP_fast_assign(
__entry->dev = journal->j_fs_dev->bd_dev;
- __entry->sync_commit = commit_transaction->t_synchronous_commit;
__entry->transaction = commit_transaction->t_tid;
),
- TP_printk("dev %d,%d transaction %d sync %d",
+ TP_printk("dev %d,%d transaction %d",
MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->transaction, __entry->sync_commit)
+ __entry->transaction)
);
TRACE_EVENT(jbd_cleanup_journal_tail,
__entry->block_nr, __entry->freed)
);
-TRACE_EVENT(jbd_update_superblock_end,
- TP_PROTO(journal_t *journal, int wait),
+TRACE_EVENT(journal_write_superblock,
+ TP_PROTO(journal_t *journal, int write_op),
- TP_ARGS(journal, wait),
+ TP_ARGS(journal, write_op),
TP_STRUCT__entry(
__field( dev_t, dev )
- __field( int, wait )
+ __field( int, write_op )
),
TP_fast_assign(
__entry->dev = journal->j_fs_dev->bd_dev;
- __entry->wait = wait;
+ __entry->write_op = write_op;
),
- TP_printk("dev %d,%d wait %d",
- MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->wait)
+ TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev),
+ MINOR(__entry->dev), __entry->write_op)
);
#endif /* _TRACE_JBD_H */
git.openpandora.org / pandora-kernel.git / commitdiff