aboutsummaryrefslogtreecommitdiff
path: root/fs/ocfs2/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ocfs2/super.c')
-rw-r--r--fs/ocfs2/super.c468
1 files changed, 260 insertions, 208 deletions
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index fa1be1b304d..ddb662b3244 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -41,9 +41,11 @@
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/quotaops.h>
-#include <linux/smp_lock.h>
+#include <linux/cleancache.h>
+
+#define CREATE_TRACE_POINTS
+#include "ocfs2_trace.h"
-#define MLOG_MASK_PREFIX ML_SUPER
#include <cluster/masklog.h>
#include "ocfs2.h"
@@ -52,6 +54,7 @@
#include "ocfs1_fs_compat.h"
#include "alloc.h"
+#include "aops.h"
#include "blockcheck.h"
#include "dlmglue.h"
#include "export.h"
@@ -65,7 +68,6 @@
#include "super.h"
#include "sysfile.h"
#include "uptodate.h"
-#include "ver.h"
#include "xattr.h"
#include "quota.h"
#include "refcounttree.h"
@@ -73,20 +75,21 @@
#include "buffer_head_io.h"
-static struct kmem_cache *ocfs2_inode_cachep = NULL;
+static struct kmem_cache *ocfs2_inode_cachep;
struct kmem_cache *ocfs2_dquot_cachep;
struct kmem_cache *ocfs2_qf_chunk_cachep;
-/* OCFS2 needs to schedule several differnt types of work which
+/* OCFS2 needs to schedule several different types of work which
* require cluster locking, disk I/O, recovery waits, etc. Since these
* types of work tend to be heavy we avoid using the kernel events
* workqueue and schedule on our own. */
struct workqueue_struct *ocfs2_wq = NULL;
-static struct dentry *ocfs2_debugfs_root = NULL;
+static struct dentry *ocfs2_debugfs_root;
MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("OCFS2 cluster file system");
struct mount_options
{
@@ -105,7 +108,7 @@ static int ocfs2_parse_options(struct super_block *sb, char *options,
int is_remount);
static int ocfs2_check_set_options(struct super_block *sb,
struct mount_options *options);
-static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt);
+static int ocfs2_show_options(struct seq_file *s, struct dentry *root);
static void ocfs2_put_super(struct super_block *sb);
static int ocfs2_mount_volume(struct super_block *sb);
static int ocfs2_remount(struct super_block *sb, int *flags, char *data);
@@ -162,6 +165,7 @@ enum {
Opt_nointr,
Opt_hb_none,
Opt_hb_local,
+ Opt_hb_global,
Opt_data_ordered,
Opt_data_writeback,
Opt_atime_quantum,
@@ -177,6 +181,8 @@ enum {
Opt_noacl,
Opt_usrquota,
Opt_grpquota,
+ Opt_coherency_buffered,
+ Opt_coherency_full,
Opt_resv_level,
Opt_dir_resv_level,
Opt_err,
@@ -190,6 +196,7 @@ static const match_table_t tokens = {
{Opt_nointr, "nointr"},
{Opt_hb_none, OCFS2_HB_NONE},
{Opt_hb_local, OCFS2_HB_LOCAL},
+ {Opt_hb_global, OCFS2_HB_GLOBAL},
{Opt_data_ordered, "data=ordered"},
{Opt_data_writeback, "data=writeback"},
{Opt_atime_quantum, "atime_quantum=%u"},
@@ -205,6 +212,8 @@ static const match_table_t tokens = {
{Opt_noacl, "noacl"},
{Opt_usrquota, "usrquota"},
{Opt_grpquota, "grpquota"},
+ {Opt_coherency_buffered, "coherency=buffered"},
+ {Opt_coherency_full, "coherency=full"},
{Opt_resv_level, "resv_level=%u"},
{Opt_dir_resv_level, "dir_resv_level=%u"},
{Opt_err, NULL}
@@ -277,10 +286,9 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
spin_unlock(&osb->osb_lock);
out += snprintf(buf + out, len - out,
- "%10s => Pid: %d Interval: %lu Needs: %d\n", "Commit",
+ "%10s => Pid: %d Interval: %lu\n", "Commit",
(osb->commit_task ? task_pid_nr(osb->commit_task) : -1),
- osb->osb_commit_interval,
- atomic_read(&osb->needs_checkpoint));
+ osb->osb_commit_interval);
out += snprintf(buf + out, len - out,
"%10s => State: %d TxnId: %lu NumTxns: %d\n",
@@ -436,8 +444,6 @@ static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb)
int status = 0;
int i;
- mlog_entry_void();
-
new = ocfs2_iget(osb, osb->root_blkno, OCFS2_FI_FLAG_SYSFILE, 0);
if (IS_ERR(new)) {
status = PTR_ERR(new);
@@ -473,7 +479,8 @@ static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb)
}
bail:
- mlog_exit(status);
+ if (status)
+ mlog_errno(status);
return status;
}
@@ -483,8 +490,6 @@ static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb)
int status = 0;
int i;
- mlog_entry_void();
-
for (i = OCFS2_LAST_GLOBAL_SYSTEM_INODE + 1;
i < NUM_SYSTEM_INODES;
i++) {
@@ -503,7 +508,8 @@ static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb)
}
bail:
- mlog_exit(status);
+ if (status)
+ mlog_errno(status);
return status;
}
@@ -512,13 +518,11 @@ static void ocfs2_release_system_inodes(struct ocfs2_super *osb)
int i;
struct inode *inode;
- mlog_entry_void();
-
- for (i = 0; i < NUM_SYSTEM_INODES; i++) {
- inode = osb->system_inodes[i];
+ for (i = 0; i < NUM_GLOBAL_SYSTEM_INODES; i++) {
+ inode = osb->global_system_inodes[i];
if (inode) {
iput(inode);
- osb->system_inodes[i] = NULL;
+ osb->global_system_inodes[i] = NULL;
}
}
@@ -534,7 +538,18 @@ static void ocfs2_release_system_inodes(struct ocfs2_super *osb)
osb->root_inode = NULL;
}
- mlog_exit(0);
+ if (!osb->local_system_inodes)
+ return;
+
+ for (i = 0; i < NUM_LOCAL_SYSTEM_INODES * osb->max_slots; i++) {
+ if (osb->local_system_inodes[i]) {
+ iput(osb->local_system_inodes[i]);
+ osb->local_system_inodes[i] = NULL;
+ }
+ }
+
+ kfree(osb->local_system_inodes);
+ osb->local_system_inodes = NULL;
}
/* We're allocating fs objects, use GFP_NOFS */
@@ -546,15 +561,24 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb)
if (!oi)
return NULL;
+ oi->i_sync_tid = 0;
+ oi->i_datasync_tid = 0;
+
jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode);
return &oi->vfs_inode;
}
-static void ocfs2_destroy_inode(struct inode *inode)
+static void ocfs2_i_callback(struct rcu_head *head)
{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(ocfs2_inode_cachep, OCFS2_I(inode));
}
+static void ocfs2_destroy_inode(struct inode *inode)
+{
+ call_rcu(&inode->i_rcu, ocfs2_i_callback);
+}
+
static unsigned long long ocfs2_max_file_offset(unsigned int bbits,
unsigned int cbits)
{
@@ -608,8 +632,9 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
int ret = 0;
struct mount_options parsed_options;
struct ocfs2_super *osb = OCFS2_SB(sb);
+ u32 tmp;
- lock_kernel();
+ sync_filesystem(sb);
if (!ocfs2_parse_options(sb, data, &parsed_options, 1) ||
!ocfs2_check_set_options(sb, &parsed_options)) {
@@ -617,8 +642,9 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
goto out;
}
- if ((osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) !=
- (parsed_options.mount_opt & OCFS2_MOUNT_HB_LOCAL)) {
+ tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
+ OCFS2_MOUNT_HB_NONE;
+ if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
ret = -EINVAL;
mlog(ML_ERROR, "Cannot change heartbeat mode on remount\n");
goto out;
@@ -658,12 +684,9 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
}
if (*flags & MS_RDONLY) {
- mlog(0, "Going to ro mode.\n");
sb->s_flags |= MS_RDONLY;
osb->osb_flags |= OCFS2_OSB_SOFT_RO;
} else {
- mlog(0, "Making ro filesystem writeable.\n");
-
if (osb->osb_flags & OCFS2_OSB_ERROR_FS) {
mlog(ML_ERROR, "Cannot remount RDWR "
"filesystem due to previous errors.\n");
@@ -681,6 +704,7 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
sb->s_flags &= ~MS_RDONLY;
osb->osb_flags &= ~OCFS2_OSB_SOFT_RO;
}
+ trace_ocfs2_remount(sb->s_flags, osb->osb_flags, *flags);
unlock_osb:
spin_unlock(&osb->osb_lock);
/* Enable quota accounting after remounting RW */
@@ -717,7 +741,6 @@ unlock_osb:
MS_POSIXACL : 0);
}
out:
- unlock_kernel();
return ret;
}
@@ -809,23 +832,29 @@ bail:
static int ocfs2_verify_heartbeat(struct ocfs2_super *osb)
{
- if (ocfs2_mount_local(osb)) {
- if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) {
+ u32 hb_enabled = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL;
+
+ if (osb->s_mount_opt & hb_enabled) {
+ if (ocfs2_mount_local(osb)) {
mlog(ML_ERROR, "Cannot heartbeat on a locally "
"mounted device.\n");
return -EINVAL;
}
- }
-
- if (ocfs2_userspace_stack(osb)) {
- if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) {
+ if (ocfs2_userspace_stack(osb)) {
mlog(ML_ERROR, "Userspace stack expected, but "
"o2cb heartbeat arguments passed to mount\n");
return -EINVAL;
}
+ if (((osb->s_mount_opt & OCFS2_MOUNT_HB_GLOBAL) &&
+ !ocfs2_cluster_o2cb_global_heartbeat(osb)) ||
+ ((osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) &&
+ ocfs2_cluster_o2cb_global_heartbeat(osb))) {
+ mlog(ML_ERROR, "Mismatching o2cb heartbeat modes\n");
+ return -EINVAL;
+ }
}
- if (!(osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL)) {
+ if (!(osb->s_mount_opt & hb_enabled)) {
if (!ocfs2_mount_local(osb) && !ocfs2_is_hard_readonly(osb) &&
!ocfs2_userspace_stack(osb)) {
mlog(ML_ERROR, "Heartbeat has to be started to mount "
@@ -962,8 +991,7 @@ static void ocfs2_disable_quotas(struct ocfs2_super *osb)
}
/* Handle quota on quotactl */
-static int ocfs2_quota_on(struct super_block *sb, int type, int format_id,
- char *path)
+static int ocfs2_quota_on(struct super_block *sb, int type, int format_id)
{
unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
@@ -982,7 +1010,7 @@ static int ocfs2_quota_off(struct super_block *sb, int type)
}
static const struct quotactl_ops ocfs2_quotactl_ops = {
- .quota_on = ocfs2_quota_on,
+ .quota_on_meta = ocfs2_quota_on,
.quota_off = ocfs2_quota_off,
.quota_sync = dquot_quota_sync,
.get_info = dquot_get_dqinfo,
@@ -999,10 +1027,10 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
struct inode *inode = NULL;
struct ocfs2_super *osb = NULL;
struct buffer_head *bh = NULL;
- char nodestr[8];
+ char nodestr[12];
struct ocfs2_blockcheck_stats stats;
- mlog_entry("%p, %p, %i", sb, data, silent);
+ trace_ocfs2_fill_super(sb, data, silent);
if (!ocfs2_parse_options(sb, data, &parsed_options, 0)) {
status = -EINVAL;
@@ -1048,7 +1076,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
sb->s_magic = OCFS2_SUPER_MAGIC;
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ sb->s_flags = (sb->s_flags & ~(MS_POSIXACL | MS_NOSEC)) |
((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
/* Hard readonly mode only if: bdev_read_only, MS_RDONLY,
@@ -1083,9 +1111,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
ocfs2_set_ro_flag(osb, 1);
- printk(KERN_NOTICE "Readonly device detected. No cluster "
- "services will be utilized for this mount. Recovery "
- "will be skipped.\n");
+ printk(KERN_NOTICE "ocfs2: Readonly device (%s) detected. "
+ "Cluster services will not be used for this mount. "
+ "Recovery will be skipped.\n", osb->dev_str);
}
if (!ocfs2_is_hard_readonly(osb)) {
@@ -1130,19 +1158,19 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
}
status = ocfs2_mount_volume(sb);
- if (osb->root_inode)
- inode = igrab(osb->root_inode);
-
if (status < 0)
goto read_super_error;
+ if (osb->root_inode)
+ inode = igrab(osb->root_inode);
+
if (!inode) {
status = -EIO;
mlog_errno(status);
goto read_super_error;
}
- root = d_alloc_root(inode);
+ root = d_make_root(inode);
if (!root) {
status = -ENOMEM;
mlog_errno(status);
@@ -1178,7 +1206,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
mlog_errno(status);
atomic_set(&osb->vol_state, VOLUME_DISABLED);
wake_up(&osb->osb_mount_event);
- mlog_exit(status);
return status;
}
}
@@ -1192,63 +1219,39 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
/* Start this when the mount is almost sure of being successful */
ocfs2_orphan_scan_start(osb);
- mlog_exit(status);
return status;
read_super_error:
brelse(bh);
- if (inode)
- iput(inode);
-
if (osb) {
atomic_set(&osb->vol_state, VOLUME_DISABLED);
wake_up(&osb->osb_mount_event);
ocfs2_dismount_volume(sb, 1);
}
- mlog_exit(status);
+ if (status)
+ mlog_errno(status);
return status;
}
-static int ocfs2_get_sb(struct file_system_type *fs_type,
+static struct dentry *ocfs2_mount(struct file_system_type *fs_type,
int flags,
const char *dev_name,
- void *data,
- struct vfsmount *mnt)
-{
- return get_sb_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super,
- mnt);
-}
-
-static void ocfs2_kill_sb(struct super_block *sb)
+ void *data)
{
- struct ocfs2_super *osb = OCFS2_SB(sb);
-
- /* Failed mount? */
- if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED)
- goto out;
-
- /* Prevent further queueing of inode drop events */
- spin_lock(&dentry_list_lock);
- ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
- spin_unlock(&dentry_list_lock);
- /* Wait for work to finish and/or remove it */
- cancel_work_sync(&osb->dentry_lock_work);
-out:
- kill_block_super(sb);
+ return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super);
}
static struct file_system_type ocfs2_fs_type = {
.owner = THIS_MODULE,
.name = "ocfs2",
- .get_sb = ocfs2_get_sb, /* is this called when we mount
- * the fs? */
- .kill_sb = ocfs2_kill_sb,
-
+ .mount = ocfs2_mount,
+ .kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
.next = NULL
};
+MODULE_ALIAS_FS("ocfs2");
static int ocfs2_check_set_options(struct super_block *sb,
struct mount_options *options)
@@ -1289,11 +1292,11 @@ static int ocfs2_parse_options(struct super_block *sb,
struct mount_options *mopt,
int is_remount)
{
- int status;
+ int status, user_stack = 0;
char *p;
+ u32 tmp;
- mlog_entry("remount: %d, options: \"%s\"\n", is_remount,
- options ? options : "(none)");
+ trace_ocfs2_parse_options(is_remount, options ? options : "(none)");
mopt->commit_interval = 0;
mopt->mount_opt = OCFS2_MOUNT_NOINTR;
@@ -1322,7 +1325,10 @@ static int ocfs2_parse_options(struct super_block *sb,
mopt->mount_opt |= OCFS2_MOUNT_HB_LOCAL;
break;
case Opt_hb_none:
- mopt->mount_opt &= ~OCFS2_MOUNT_HB_LOCAL;
+ mopt->mount_opt |= OCFS2_MOUNT_HB_NONE;
+ break;
+ case Opt_hb_global:
+ mopt->mount_opt |= OCFS2_MOUNT_HB_GLOBAL;
break;
case Opt_barrier:
if (match_int(&args[0], &option)) {
@@ -1428,6 +1434,15 @@ static int ocfs2_parse_options(struct super_block *sb,
memcpy(mopt->cluster_stack, args[0].from,
OCFS2_STACK_LABEL_LEN);
mopt->cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
+ /*
+ * Open code the memcmp here as we don't have
+ * an osb to pass to
+ * ocfs2_userspace_stack().
+ */
+ if (memcmp(mopt->cluster_stack,
+ OCFS2_CLASSIC_CLUSTER_STACK,
+ OCFS2_STACK_LABEL_LEN))
+ user_stack = 1;
break;
case Opt_inode64:
mopt->mount_opt |= OCFS2_MOUNT_INODE64;
@@ -1438,6 +1453,12 @@ static int ocfs2_parse_options(struct super_block *sb,
case Opt_grpquota:
mopt->mount_opt |= OCFS2_MOUNT_GRPQUOTA;
break;
+ case Opt_coherency_buffered:
+ mopt->mount_opt |= OCFS2_MOUNT_COHERENCY_BUFFERED;
+ break;
+ case Opt_coherency_full:
+ mopt->mount_opt &= ~OCFS2_MOUNT_COHERENCY_BUFFERED;
+ break;
case Opt_acl:
mopt->mount_opt |= OCFS2_MOUNT_POSIX_ACL;
mopt->mount_opt &= ~OCFS2_MOUNT_NO_POSIX_ACL;
@@ -1477,23 +1498,38 @@ static int ocfs2_parse_options(struct super_block *sb,
}
}
+ if (user_stack == 0) {
+ /* Ensure only one heartbeat mode */
+ tmp = mopt->mount_opt & (OCFS2_MOUNT_HB_LOCAL |
+ OCFS2_MOUNT_HB_GLOBAL |
+ OCFS2_MOUNT_HB_NONE);
+ if (hweight32(tmp) != 1) {
+ mlog(ML_ERROR, "Invalid heartbeat mount options\n");
+ status = 0;
+ goto bail;
+ }
+ }
+
status = 1;
bail:
- mlog_exit(status);
return status;
}
-static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
+static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
{
- struct ocfs2_super *osb = OCFS2_SB(mnt->mnt_sb);
+ struct ocfs2_super *osb = OCFS2_SB(root->d_sb);
unsigned long opts = osb->s_mount_opt;
unsigned int local_alloc_megs;
- if (opts & OCFS2_MOUNT_HB_LOCAL)
- seq_printf(s, ",_netdev,heartbeat=local");
- else
- seq_printf(s, ",heartbeat=none");
+ if (opts & (OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL)) {
+ seq_printf(s, ",_netdev");
+ if (opts & OCFS2_MOUNT_HB_LOCAL)
+ seq_printf(s, ",%s", OCFS2_HB_LOCAL);
+ else
+ seq_printf(s, ",%s", OCFS2_HB_GLOBAL);
+ } else
+ seq_printf(s, ",%s", OCFS2_HB_NONE);
if (opts & OCFS2_MOUNT_NOINTR)
seq_printf(s, ",nointr");
@@ -1514,8 +1550,7 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
if (osb->preferred_slot != OCFS2_INVALID_SLOT)
seq_printf(s, ",preferred_slot=%d", osb->preferred_slot);
- if (osb->s_atime_quantum != OCFS2_DEFAULT_ATIME_QUANTUM)
- seq_printf(s, ",atime_quantum=%u", osb->s_atime_quantum);
+ seq_printf(s, ",atime_quantum=%u", osb->s_atime_quantum);
if (osb->osb_commit_interval)
seq_printf(s, ",commit=%u",
@@ -1536,6 +1571,11 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
if (opts & OCFS2_MOUNT_GRPQUOTA)
seq_printf(s, ",grpquota");
+ if (opts & OCFS2_MOUNT_COHERENCY_BUFFERED)
+ seq_printf(s, ",coherency=buffered");
+ else
+ seq_printf(s, ",coherency=full");
+
if (opts & OCFS2_MOUNT_NOUSERXATTR)
seq_printf(s, ",nouser_xattr");
else
@@ -1562,26 +1602,18 @@ static int __init ocfs2_init(void)
{
int status;
- mlog_entry_void();
-
- ocfs2_print_version();
-
status = init_ocfs2_uptodate_cache();
- if (status < 0) {
- mlog_errno(status);
- goto leave;
- }
+ if (status < 0)
+ goto out1;
status = ocfs2_initialize_mem_caches();
- if (status < 0) {
- mlog_errno(status);
- goto leave;
- }
+ if (status < 0)
+ goto out2;
ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
if (!ocfs2_wq) {
status = -ENOMEM;
- goto leave;
+ goto out3;
}
ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
@@ -1590,34 +1622,30 @@ static int __init ocfs2_init(void)
mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
}
- status = ocfs2_quota_setup();
- if (status)
- goto leave;
-
ocfs2_set_locking_protocol();
status = register_quota_format(&ocfs2_quota_format);
-leave:
- if (status < 0) {
- ocfs2_quota_shutdown();
- ocfs2_free_mem_caches();
- exit_ocfs2_uptodate_cache();
- }
-
- mlog_exit(status);
+ if (status < 0)
+ goto out4;
+ status = register_filesystem(&ocfs2_fs_type);
+ if (!status)
+ return 0;
- if (status >= 0) {
- return register_filesystem(&ocfs2_fs_type);
- } else
- return -1;
+ unregister_quota_format(&ocfs2_quota_format);
+out4:
+ destroy_workqueue(ocfs2_wq);
+ debugfs_remove(ocfs2_debugfs_root);
+out3:
+ ocfs2_free_mem_caches();
+out2:
+ exit_ocfs2_uptodate_cache();
+out1:
+ mlog_errno(status);
+ return status;
}
static void __exit ocfs2_exit(void)
{
- mlog_entry_void();
-
- ocfs2_quota_shutdown();
-
if (ocfs2_wq) {
flush_workqueue(ocfs2_wq);
destroy_workqueue(ocfs2_wq);
@@ -1632,22 +1660,14 @@ static void __exit ocfs2_exit(void)
unregister_filesystem(&ocfs2_fs_type);
exit_ocfs2_uptodate_cache();
-
- mlog_exit_void();
}
static void ocfs2_put_super(struct super_block *sb)
{
- mlog_entry("(0x%p)\n", sb);
-
- lock_kernel();
+ trace_ocfs2_put_super(sb);
ocfs2_sync_blockdev(sb);
ocfs2_dismount_volume(sb, 0);
-
- unlock_kernel();
-
- mlog_exit_void();
}
static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1659,7 +1679,7 @@ static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
struct buffer_head *bh = NULL;
struct inode *inode = NULL;
- mlog_entry("(%p, %p)\n", dentry->d_sb, buf);
+ trace_ocfs2_statfs(dentry->d_sb, buf);
osb = OCFS2_SB(dentry->d_sb);
@@ -1706,7 +1726,8 @@ bail:
if (inode)
iput(inode);
- mlog_exit(status);
+ if (status)
+ mlog_errno(status);
return status;
}
@@ -1721,7 +1742,7 @@ static void ocfs2_inode_init_once(void *data)
ocfs2_extent_map_init(&oi->vfs_inode);
INIT_LIST_HEAD(&oi->ip_io_markers);
oi->ip_dir_start_lookup = 0;
-
+ mutex_init(&oi->ip_unaligned_aio);
init_rwsem(&oi->ip_alloc_sem);
init_rwsem(&oi->ip_xattr_sem);
mutex_init(&oi->ip_io_mutex);
@@ -1776,6 +1797,11 @@ static int ocfs2_initialize_mem_caches(void)
static void ocfs2_free_mem_caches(void)
{
+ /*
+ * Make sure all delayed rcu free inodes are flushed before we
+ * destroy cache.
+ */
+ rcu_barrier();
if (ocfs2_inode_cachep)
kmem_cache_destroy(ocfs2_inode_cachep);
ocfs2_inode_cachep = NULL;
@@ -1801,8 +1827,8 @@ static int ocfs2_get_sector(struct super_block *sb,
*bh = sb_getblk(sb, block);
if (!*bh) {
- mlog_errno(-EIO);
- return -EIO;
+ mlog_errno(-ENOMEM);
+ return -ENOMEM;
}
lock_buffer(*bh);
if (!buffer_dirty(*bh))
@@ -1826,8 +1852,6 @@ static int ocfs2_mount_volume(struct super_block *sb)
int unlock_super = 0;
struct ocfs2_super *osb = OCFS2_SB(sb);
- mlog_entry_void();
-
if (ocfs2_is_hard_readonly(osb))
goto leave;
@@ -1872,7 +1896,6 @@ leave:
if (unlock_super)
ocfs2_super_unlock(osb, 1);
- mlog_exit(status);
return status;
}
@@ -1880,9 +1903,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
{
int tmp, hangup_needed = 0;
struct ocfs2_super *osb = NULL;
- char nodestr[8];
+ char nodestr[12];
- mlog_entry("(0x%p)\n", sb);
+ trace_ocfs2_dismount_volume(sb);
BUG_ON(!sb);
osb = OCFS2_SB(sb);
@@ -1890,17 +1913,16 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
debugfs_remove(osb->osb_ctxt);
- /*
- * Flush inode dropping work queue so that deletes are
- * performed while the filesystem is still working
- */
- ocfs2_drop_all_dl_inodes(osb);
-
/* Orphan scan should be stopped as early as possible */
ocfs2_orphan_scan_stop(osb);
ocfs2_disable_quotas(osb);
+ /* All dquots should be freed by now */
+ WARN_ON(!llist_empty(&osb->dquot_drop_list));
+ /* Wait for worker to be done with the work structure in osb */
+ cancel_work_sync(&osb->dquot_drop_work);
+
ocfs2_shutdown_local_alloc(osb);
ocfs2_truncate_log_shutdown(osb);
@@ -1938,7 +1960,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
* If we failed before we got a uuid_str yet, we can't stop
* heartbeat. Otherwise, do it.
*/
- if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str)
+ if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str &&
+ !ocfs2_is_hard_readonly(osb))
hangup_needed = 1;
if (osb->cconn)
@@ -1990,6 +2013,36 @@ static int ocfs2_setup_osb_uuid(struct ocfs2_super *osb, const unsigned char *uu
return 0;
}
+/* Make sure entire volume is addressable by our journal. Requires
+ osb_clusters_at_boot to be valid and for the journal to have been
+ initialized by ocfs2_journal_init(). */
+static int ocfs2_journal_addressable(struct ocfs2_super *osb)
+{
+ int status = 0;
+ u64 max_block =
+ ocfs2_clusters_to_blocks(osb->sb,
+ osb->osb_clusters_at_boot) - 1;
+
+ /* 32-bit block number is always OK. */
+ if (max_block <= (u32)~0ULL)
+ goto out;
+
+ /* Volume is "huge", so see if our journal is new enough to
+ support it. */
+ if (!(OCFS2_HAS_COMPAT_FEATURE(osb->sb,
+ OCFS2_FEATURE_COMPAT_JBD2_SB) &&
+ jbd2_journal_check_used_features(osb->journal->j_journal, 0, 0,
+ JBD2_FEATURE_INCOMPAT_64BIT))) {
+ mlog(ML_ERROR, "The journal cannot address the entire volume. "
+ "Enable the 'block64' journal option with tunefs.ocfs2");
+ status = -EFBIG;
+ goto out;
+ }
+
+ out:
+ return status;
+}
+
static int ocfs2_initialize_super(struct super_block *sb,
struct buffer_head *bh,
int sector_size,
@@ -2000,10 +2053,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
struct inode *inode = NULL;
struct ocfs2_journal *journal;
- __le32 uuid_net_key;
struct ocfs2_super *osb;
-
- mlog_entry_void();
+ u64 total_blocks;
osb = kzalloc(sizeof(struct ocfs2_super), GFP_KERNEL);
if (!osb) {
@@ -2014,6 +2065,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
sb->s_fs_info = osb;
sb->s_op = &ocfs2_sops;
+ sb->s_d_op = &ocfs2_dentry_ops;
sb->s_export_op = &ocfs2_export_ops;
sb->s_qcop = &ocfs2_quotactl_ops;
sb->dq_op = &ocfs2_quota_operations;
@@ -2046,6 +2098,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
spin_lock_init(&osb->osb_xattr_lock);
ocfs2_init_steal_slots(osb);
+ mutex_init(&osb->system_file_mutex);
+
atomic_set(&osb->alloc_stats.moves, 0);
atomic_set(&osb->alloc_stats.local_data, 0);
atomic_set(&osb->alloc_stats.bitmap_data, 0);
@@ -2060,6 +2114,14 @@ static int ocfs2_initialize_super(struct super_block *sb,
snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u",
MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
+ osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
+ if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) {
+ mlog(ML_ERROR, "Invalid number of node slots (%u)\n",
+ osb->max_slots);
+ status = -EINVAL;
+ goto bail;
+ }
+
ocfs2_orphan_scan_init(osb);
status = ocfs2_recovery_init(osb);
@@ -2070,7 +2132,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
}
init_waitqueue_head(&osb->checkpoint_event);
- atomic_set(&osb->needs_checkpoint, 0);
osb->s_atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;
@@ -2098,15 +2159,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
- osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
- if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) {
- mlog(ML_ERROR, "Invalid number of node slots (%u)\n",
- osb->max_slots);
- status = -EINVAL;
- goto bail;
- }
- mlog(0, "max_slots for this device: %u\n", osb->max_slots);
-
osb->slot_recovery_generations =
kcalloc(osb->max_slots, sizeof(*osb->slot_recovery_generations),
GFP_KERNEL);
@@ -2149,11 +2201,12 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
- if (ocfs2_userspace_stack(osb)) {
- memcpy(osb->osb_cluster_stack,
+ if (ocfs2_clusterinfo_valid(osb)) {
+ osb->osb_stackflags =
+ OCFS2_RAW_SB(di)->s_cluster_info.ci_stackflags;
+ strlcpy(osb->osb_cluster_stack,
OCFS2_RAW_SB(di)->s_cluster_info.ci_stack,
- OCFS2_STACK_LABEL_LEN);
- osb->osb_cluster_stack[OCFS2_STACK_LABEL_LEN] = '\0';
+ OCFS2_STACK_LABEL_LEN + 1);
if (strlen(osb->osb_cluster_stack) != OCFS2_STACK_LABEL_LEN) {
mlog(ML_ERROR,
"couldn't mount because of an invalid "
@@ -2162,6 +2215,9 @@ static int ocfs2_initialize_super(struct super_block *sb,
status = -EINVAL;
goto bail;
}
+ strlcpy(osb->osb_cluster_name,
+ OCFS2_RAW_SB(di)->s_cluster_info.ci_cluster,
+ OCFS2_CLUSTER_NAME_LEN + 1);
} else {
/* The empty string is identical with classic tools that
* don't know about s_cluster_info. */
@@ -2197,14 +2253,13 @@ static int ocfs2_initialize_super(struct super_block *sb,
INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
journal->j_state = OCFS2_JOURNAL_FREE;
- INIT_WORK(&osb->dentry_lock_work, ocfs2_drop_dl_inodes);
- osb->dentry_lock_list = NULL;
+ INIT_WORK(&osb->dquot_drop_work, ocfs2_drop_dquot_refs);
+ init_llist_head(&osb->dquot_drop_list);
/* get some pseudo constants for clustersize bits */
osb->s_clustersize_bits =
le32_to_cpu(di->id2.i_super.s_clustersize_bits);
osb->s_clustersize = 1 << osb->s_clustersize_bits;
- mlog(0, "clusterbits=%d\n", osb->s_clustersize_bits);
if (osb->s_clustersize < OCFS2_MIN_CLUSTERSIZE ||
osb->s_clustersize > OCFS2_MAX_CLUSTERSIZE) {
@@ -2214,11 +2269,15 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
- if (ocfs2_clusters_to_blocks(osb->sb, le32_to_cpu(di->i_clusters) - 1)
- > (u32)~0UL) {
- mlog(ML_ERROR, "Volume might try to write to blocks beyond "
- "what jbd can address in 32 bits.\n");
- status = -EINVAL;
+ total_blocks = ocfs2_clusters_to_blocks(osb->sb,
+ le32_to_cpu(di->i_clusters));
+
+ status = generic_check_addressable(osb->sb->s_blocksize_bits,
+ total_blocks);
+ if (status) {
+ mlog(ML_ERROR, "Volume too large "
+ "to mount safely on this system");
+ status = -EFBIG;
goto bail;
}
@@ -2229,21 +2288,18 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
- memcpy(&uuid_net_key, di->id2.i_super.s_uuid, sizeof(uuid_net_key));
-
- strncpy(osb->vol_label, di->id2.i_super.s_label, 63);
- osb->vol_label[63] = '\0';
+ strlcpy(osb->vol_label, di->id2.i_super.s_label,
+ OCFS2_MAX_VOL_LABEL_LEN);
osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno);
osb->system_dir_blkno = le64_to_cpu(di->id2.i_super.s_system_dir_blkno);
osb->first_cluster_group_blkno =
le64_to_cpu(di->id2.i_super.s_first_cluster_group);
osb->fs_generation = le32_to_cpu(di->i_fs_generation);
osb->uuid_hash = le32_to_cpu(di->id2.i_super.s_uuid_hash);
- mlog(0, "vol_label: %s\n", osb->vol_label);
- mlog(0, "uuid: %s\n", osb->uuid_str);
- mlog(0, "root_blkno=%llu, system_dir_blkno=%llu\n",
- (unsigned long long)osb->root_blkno,
- (unsigned long long)osb->system_dir_blkno);
+ trace_ocfs2_initialize_super(osb->vol_label, osb->uuid_str,
+ (unsigned long long)osb->root_blkno,
+ (unsigned long long)osb->system_dir_blkno,
+ osb->s_clustersize_bits);
osb->osb_dlm_debug = ocfs2_new_dlm_debug();
if (!osb->osb_dlm_debug) {
@@ -2284,9 +2340,9 @@ static int ocfs2_initialize_super(struct super_block *sb,
mlog_errno(status);
goto bail;
}
+ cleancache_init_shared_fs((char *)&di->id2.i_super.s_uuid, sb);
bail:
- mlog_exit(status);
return status;
}
@@ -2302,8 +2358,6 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
{
int status = -EAGAIN;
- mlog_entry_void();
-
if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE,
strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) {
/* We have to do a raw check of the feature here */
@@ -2358,7 +2412,8 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
}
out:
- mlog_exit(status);
+ if (status && status != -EAGAIN)
+ mlog_errno(status);
return status;
}
@@ -2371,8 +2426,6 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
* recover
* ourselves. */
- mlog_entry_void();
-
/* Init our journal object. */
status = ocfs2_journal_init(osb->journal, &dirty);
if (status < 0) {
@@ -2380,6 +2433,12 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
goto finally;
}
+ /* Now that journal has been initialized, check to make sure
+ entire volume is addressable. */
+ status = ocfs2_journal_addressable(osb);
+ if (status)
+ goto finally;
+
/* If the journal was unmounted cleanly then we don't want to
* recover anything. Otherwise, journal_load will do that
* dirty work for us :) */
@@ -2390,8 +2449,8 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
goto finally;
}
} else {
- mlog(ML_NOTICE, "File system was not unmounted cleanly, "
- "recovering volume.\n");
+ printk(KERN_NOTICE "ocfs2: File system on device (%s) was not "
+ "unmounted cleanly, recovering it.\n", osb->dev_str);
}
local = ocfs2_mount_local(osb);
@@ -2416,8 +2475,6 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
* ourselves as mounted. */
}
- mlog(0, "Journal loaded.\n");
-
status = ocfs2_load_local_alloc(osb);
if (status < 0) {
mlog_errno(status);
@@ -2446,10 +2503,10 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
mlog_errno(status);
finally:
- if (local_alloc)
- kfree(local_alloc);
+ kfree(local_alloc);
- mlog_exit(status);
+ if (status)
+ mlog_errno(status);
return status;
}
@@ -2461,8 +2518,6 @@ finally:
*/
static void ocfs2_delete_osb(struct ocfs2_super *osb)
{
- mlog_entry_void();
-
/* This function assumes that the caller has the main osb resource */
ocfs2_free_slot_info(osb);
@@ -2475,13 +2530,10 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
* we free it here.
*/
kfree(osb->journal);
- if (osb->local_alloc_copy)
- kfree(osb->local_alloc_copy);
+ kfree(osb->local_alloc_copy);
kfree(osb->uuid_str);
ocfs2_put_dlm_debug(osb->osb_dlm_debug);
memset(osb, 0, sizeof(struct ocfs2_super));
-
- mlog_exit_void();
}
/* Put OCFS2 into a readonly state, or (if the user specifies it),
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-06 22:22:01 +0000