/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
-#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/kthread.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/gfs2_ondisk.h>
+#include <linux/lm_interface.h>
#include "gfs2.h"
-#include "lm_interface.h"
#include "incore.h"
+#include "bmap.h"
#include "daemon.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "lm.h"
#include "mount.h"
-#include "ops_export.h"
#include "ops_fstype.h"
+#include "ops_dentry.h"
#include "ops_super.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "sys.h"
#include "util.h"
+#include "log.h"
#define DO 0
#define UNDO 1
-extern struct dentry_operations gfs2_dops;
-
static struct gfs2_sbd *init_sbd(struct super_block *sb)
{
struct gfs2_sbd *sdp;
- unsigned int x;
- sdp = vmalloc(sizeof(struct gfs2_sbd));
+ sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
if (!sdp)
return NULL;
- memset(sdp, 0, sizeof(struct gfs2_sbd));
-
sb->s_fs_info = sdp;
sdp->sd_vfs = sb;
gfs2_tune_init(&sdp->sd_tune);
- for (x = 0; x < GFS2_GL_HASH_SIZE; x++) {
- rwlock_init(&sdp->sd_gl_hash[x].hb_lock);
- INIT_LIST_HEAD(&sdp->sd_gl_hash[x].hb_list);
- }
INIT_LIST_HEAD(&sdp->sd_reclaim_list);
spin_lock_init(&sdp->sd_reclaim_lock);
init_waitqueue_head(&sdp->sd_reclaim_wq);
mutex_init(&sdp->sd_inum_mutex);
spin_lock_init(&sdp->sd_statfs_spin);
- mutex_init(&sdp->sd_statfs_mutex);
spin_lock_init(&sdp->sd_rindex_spin);
mutex_init(&sdp->sd_rindex_mutex);
spin_lock_init(&sdp->sd_log_lock);
- INIT_LIST_HEAD(&sdp->sd_log_le_gl);
INIT_LIST_HEAD(&sdp->sd_log_le_buf);
INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
INIT_LIST_HEAD(&sdp->sd_log_le_rg);
INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
+ INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
mutex_init(&sdp->sd_log_reserve_mutex);
INIT_LIST_HEAD(&sdp->sd_ail1_list);
INIT_LIST_HEAD(&sdp->sd_ail2_list);
init_rwsem(&sdp->sd_log_flush_lock);
- INIT_LIST_HEAD(&sdp->sd_log_flush_list);
+ atomic_set(&sdp->sd_log_in_flight, 0);
+ init_waitqueue_head(&sdp->sd_log_flush_wait);
INIT_LIST_HEAD(&sdp->sd_revoke_list);
sb->s_magic = GFS2_MAGIC;
sb->s_op = &gfs2_super_ops;
sb->s_export_op = &gfs2_export_ops;
+ sb->s_time_gran = 1;
sb->s_maxbytes = MAX_LFS_FILESIZE;
if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME))
static int init_names(struct gfs2_sbd *sdp, int silent)
{
- struct gfs2_sb *sb = NULL;
char *proto, *table;
int error = 0;
/* Try to autodetect */
if (!proto[0] || !table[0]) {
- struct buffer_head *bh;
- bh = sb_getblk(sdp->sd_vfs,
- GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
- lock_buffer(bh);
- clear_buffer_uptodate(bh);
- clear_buffer_dirty(bh);
- unlock_buffer(bh);
- ll_rw_block(READ, 1, &bh);
- wait_on_buffer(bh);
-
- if (!buffer_uptodate(bh)) {
- brelse(bh);
- return -EIO;
- }
-
- sb = kmalloc(sizeof(struct gfs2_sb), GFP_KERNEL);
- if (!sb) {
- brelse(bh);
- return -ENOMEM;
- }
- gfs2_sb_in(sb, bh->b_data);
- brelse(bh);
+ error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+ if (error)
+ return error;
- error = gfs2_check_sb(sdp, sb, silent);
+ error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
if (error)
goto out;
if (!proto[0])
- proto = sb->sb_lockproto;
+ proto = sdp->sd_sb.sb_lockproto;
if (!table[0])
- table = sb->sb_locktable;
+ table = sdp->sd_sb.sb_locktable;
}
if (!table[0])
snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto);
snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table);
+ table = sdp->sd_table_name;
+ while ((table = strchr(table, '/')))
+ *table = '_';
+
out:
- kfree(sb);
return error;
}
if (undo)
goto fail_trans;
- p = kthread_run(gfs2_scand, sdp, "gfs2_scand");
- error = IS_ERR(p);
- if (error) {
- fs_err(sdp, "can't start scand thread: %d\n", error);
- return error;
- }
- sdp->sd_scand_process = p;
-
for (sdp->sd_glockd_num = 0;
sdp->sd_glockd_num < sdp->sd_args.ar_num_glockd;
sdp->sd_glockd_num++) {
while (sdp->sd_glockd_num--)
kthread_stop(sdp->sd_glockd_process[sdp->sd_glockd_num]);
- kthread_stop(sdp->sd_scand_process);
return error;
}
-static struct inode *gfs2_lookup_root(struct super_block *sb,
- struct gfs2_inum *inum)
+static inline struct inode *gfs2_lookup_root(struct super_block *sb,
+ u64 no_addr)
{
- return gfs2_inode_lookup(sb, inum, DT_DIR);
+ return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
}
static int init_sb(struct gfs2_sbd *sdp, int silent, int undo)
{
struct super_block *sb = sdp->sd_vfs;
struct gfs2_holder sb_gh;
- struct gfs2_inum *inum;
+ u64 no_addr;
struct inode *inode;
int error = 0;
}
return 0;
}
-
+
error = gfs2_glock_nq_num(sdp, GFS2_SB_LOCK, &gfs2_meta_glops,
LM_ST_SHARED, 0, &sb_gh);
if (error) {
sb_set_blocksize(sb, sdp->sd_sb.sb_bsize);
/* Get the root inode */
- inum = &sdp->sd_sb.sb_root_dir;
+ no_addr = sdp->sd_sb.sb_root_dir.no_addr;
if (sb->s_type == &gfs2meta_fs_type)
- inum = &sdp->sd_sb.sb_master_dir;
- inode = gfs2_lookup_root(sb, inum);
+ no_addr = sdp->sd_sb.sb_master_dir.no_addr;
+ inode = gfs2_lookup_root(sb, no_addr);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
fs_err(sdp, "can't read in root inode: %d\n", error);
fs_err(sdp, "can't get root dentry\n");
error = -ENOMEM;
iput(inode);
- }
- sb->s_root->d_op = &gfs2_dops;
+ } else
+ sb->s_root->d_op = &gfs2_dops;
+
out:
gfs2_glock_dq_uninit(&sb_gh);
return error;
}
+/**
+ * map_journal_extents - create a reusable "extent" mapping from all logical
+ * blocks to all physical blocks for the given journal. This will save
+ * us time when writing journal blocks. Most journals will have only one
+ * extent that maps all their logical blocks. That's because gfs2.mkfs
+ * arranges the journal blocks sequentially to maximize performance.
+ * So the extent would map the first block for the entire file length.
+ * However, gfs2_jadd can happen while file activity is happening, so
+ * those journals may not be sequential. Less likely is the case where
+ * the users created their own journals by mounting the metafs and
+ * laying it out. But it's still possible. These journals might have
+ * several extents.
+ *
+ * TODO: This should be done in bigger chunks rather than one block at a time,
+ * but since it's only done at mount time, I'm not worried about the
+ * time it takes.
+ */
+static int map_journal_extents(struct gfs2_sbd *sdp)
+{
+ struct gfs2_jdesc *jd = sdp->sd_jdesc;
+ unsigned int lb;
+ u64 db, prev_db; /* logical block, disk block, prev disk block */
+ struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+ struct gfs2_journal_extent *jext = NULL;
+ struct buffer_head bh;
+ int rc = 0;
+
+ prev_db = 0;
+
+ for (lb = 0; lb < ip->i_di.di_size >> sdp->sd_sb.sb_bsize_shift; lb++) {
+ bh.b_state = 0;
+ bh.b_blocknr = 0;
+ bh.b_size = 1 << ip->i_inode.i_blkbits;
+ rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0);
+ db = bh.b_blocknr;
+ if (rc || !db) {
+ printk(KERN_INFO "GFS2 journal mapping error %d: lb="
+ "%u db=%llu\n", rc, lb, (unsigned long long)db);
+ break;
+ }
+ if (!prev_db || db != prev_db + 1) {
+ jext = kzalloc(sizeof(struct gfs2_journal_extent),
+ GFP_KERNEL);
+ if (!jext) {
+ printk(KERN_INFO "GFS2 error: out of memory "
+ "mapping journal extents.\n");
+ rc = -ENOMEM;
+ break;
+ }
+ jext->dblock = db;
+ jext->lblock = lb;
+ jext->blocks = 1;
+ list_add_tail(&jext->extent_list, &jd->extent_list);
+ } else {
+ jext->blocks++;
+ }
+ prev_db = db;
+ }
+ return rc;
+}
+
static int init_journal(struct gfs2_sbd *sdp, int undo)
{
struct gfs2_holder ji_gh;
error = -EINVAL;
if (!gfs2_jindex_size(sdp)) {
fs_err(sdp, "no journals!\n");
- goto fail_jindex;
+ goto fail_jindex;
}
if (sdp->sd_args.ar_spectator) {
sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
- sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+ atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
} else {
if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
fs_err(sdp, "can't mount journal #%u\n",
ip = GFS2_I(sdp->sd_jdesc->jd_inode);
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
- LM_FLAG_NOEXP | GL_EXACT,
+ LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
&sdp->sd_jinode_gh);
if (error) {
fs_err(sdp, "can't acquire journal inode glock: %d\n",
sdp->sd_jdesc->jd_jid, error);
goto fail_jinode_gh;
}
- sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks;
+ atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
+
+ /* Map the extents for this journal's blocks */
+ map_journal_extents(sdp);
}
if (sdp->sd_lockstruct.ls_first) {
if (undo)
goto fail_qinode;
- inode = gfs2_lookup_root(sdp->sd_vfs, &sdp->sd_sb.sb_master_dir);
+ inode = gfs2_lookup_root(sdp->sd_vfs, sdp->sd_sb.sb_master_dir.no_addr);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
fs_err(sdp, "can't read in master directory: %d\n", error);
if (error)
goto fail;
+ gfs2_create_debugfs_file(sdp);
+
error = gfs2_sys_fs_add(sdp);
if (error)
goto fail;
fail_sys:
gfs2_sys_fs_del(sdp);
fail:
- vfree(sdp);
+ gfs2_delete_debugfs_file(sdp);
+ kfree(sdp);
sb->s_fs_info = NULL;
return error;
}
if (error)
goto out;
sb = mnt->mnt_sb;
- sdp = (struct gfs2_sbd*)sb->s_fs_info;
+ sdp = sb->s_fs_info;
sdp->sd_gfs2mnt = mnt;
out:
return error;
}
-static int fill_super_meta(struct super_block *sb, struct super_block *new,
+static int fill_super_meta(struct super_block *sb, struct super_block *new,
void *data, int silent)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
fs_err(sdp, "can't get root dentry\n");
error = -ENOMEM;
iput(inode);
- }
- new->s_root->d_op = &gfs2_dops;
+ } else
+ new->s_root->d_op = &gfs2_dops;
return error;
}
s->s_dev = s->s_bdev->bd_dev;
return 0;
}
-
+
static int test_bdev_super(struct super_block *s, void *data)
{
- return (void *)s->s_bdev == data;
+ return s->s_bdev == data;
}
static struct super_block* get_gfs2_sb(const char *dev_name)
struct nameidata nd;
struct file_system_type *fstype;
struct super_block *sb = NULL, *s;
- struct list_head *l;
int error;
-
+
error = path_lookup(dev_name, LOOKUP_FOLLOW, &nd);
if (error) {
- printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
+ printk(KERN_WARNING "GFS2: path_lookup on %s returned error\n",
dev_name);
goto out;
}
error = vfs_getattr(nd.mnt, nd.dentry, &stat);
fstype = get_fs_type("gfs2");
- list_for_each(l, &fstype->fs_supers) {
- s = list_entry(l, struct super_block, s_instances);
+ list_for_each_entry(s, &fstype->fs_supers, s_instances) {
if ((S_ISBLK(stat.mode) && s->s_dev == stat.rdev) ||
(S_ISDIR(stat.mode) && s == nd.dentry->d_inode->i_sb)) {
sb = s;
}
printk(KERN_WARNING "GFS2: Unrecognized block device or "
- "mount point %s", dev_name);
+ "mount point %s\n", dev_name);
free_nd:
path_release(&nd);
int error = 0;
struct super_block *sb = NULL, *new;
struct gfs2_sbd *sdp;
- char *gfs2mnt = NULL;
sb = get_gfs2_sb(dev_name);
if (!sb) {
error = -ENOENT;
goto error;
}
- sdp = (struct gfs2_sbd*) sb->s_fs_info;
+ sdp = sb->s_fs_info;
if (sdp->sd_vfs_meta) {
printk(KERN_WARNING "GFS2: gfs2meta mount already exists\n");
error = -EBUSY;
goto error;
}
- mutex_lock(&sb->s_bdev->bd_mount_mutex);
+ down(&sb->s_bdev->bd_mount_sem);
new = sget(fs_type, test_bdev_super, set_bdev_super, sb->s_bdev);
- mutex_unlock(&sb->s_bdev->bd_mount_mutex);
+ up(&sb->s_bdev->bd_mount_sem);
if (IS_ERR(new)) {
error = PTR_ERR(new);
goto error;
deactivate_super(new);
goto error;
}
-
+
new->s_flags |= MS_ACTIVE;
-
+
/* Grab a reference to the gfs2 mount point */
atomic_inc(&sdp->sd_gfs2mnt->mnt_count);
return simple_set_mnt(mnt, new);
error:
- if (gfs2mnt)
- kfree(gfs2mnt);
return error;
}
static void gfs2_kill_sb(struct super_block *sb)
{
+ if (sb->s_fs_info) {
+ gfs2_delete_debugfs_file(sb->s_fs_info);
+ gfs2_meta_syncfs(sb->s_fs_info);
+ }
kill_block_super(sb);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff