aboutsummaryrefslogtreecommitdiffstats
path: root/fs/btrfs/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/super.c')
-rw-r--r--fs/btrfs/super.c200
1 files changed, 151 insertions, 49 deletions
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index e23991574fd..d8982e9601d 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -55,6 +55,7 @@
#include "export.h"
#include "compression.h"
#include "rcu-string.h"
+#include "dev-replace.h"
#define CREATE_TRACE_POINTS
#include <trace/events/btrfs.h>
@@ -100,10 +101,6 @@ static void __save_error_info(struct btrfs_fs_info *fs_info)
fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR;
}
-/* NOTE:
- * We move write_super stuff at umount in order to avoid deadlock
- * for umount hold all lock.
- */
static void save_error_info(struct btrfs_fs_info *fs_info)
{
__save_error_info(fs_info);
@@ -120,11 +117,21 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
sb->s_flags |= MS_RDONLY;
printk(KERN_INFO "btrfs is forced readonly\n");
- __btrfs_scrub_cancel(fs_info);
+ /*
+ * Note that a running device replace operation is not
+ * canceled here although there is no way to update
+ * the progress. It would add the risk of a deadlock,
+ * therefore the canceling is ommited. The only penalty
+ * is that some I/O remains active until the procedure
+ * completes. The next time when the filesystem is
+ * mounted writeable again, the device replace
+ * operation continues.
+ */
// WARN_ON(1);
}
}
+#ifdef CONFIG_PRINTK
/*
* __btrfs_std_error decodes expected errors from the caller and
* invokes the approciate error response.
@@ -167,7 +174,7 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
va_end(args);
}
-const char *logtypes[] = {
+static const char * const logtypes[] = {
"emergency",
"alert",
"critical",
@@ -185,22 +192,50 @@ void btrfs_printk(struct btrfs_fs_info *fs_info, const char *fmt, ...)
struct va_format vaf;
va_list args;
const char *type = logtypes[4];
+ int kern_level;
va_start(args, fmt);
- if (fmt[0] == '<' && isdigit(fmt[1]) && fmt[2] == '>') {
- memcpy(lvl, fmt, 3);
- lvl[3] = '\0';
- fmt += 3;
- type = logtypes[fmt[1] - '0'];
+ kern_level = printk_get_level(fmt);
+ if (kern_level) {
+ size_t size = printk_skip_level(fmt) - fmt;
+ memcpy(lvl, fmt, size);
+ lvl[size] = '\0';
+ fmt += size;
+ type = logtypes[kern_level - '0'];
} else
*lvl = '\0';
vaf.fmt = fmt;
vaf.va = &args;
+
printk("%sBTRFS %s (device %s): %pV", lvl, type, sb->s_id, &vaf);
+
+ va_end(args);
}
+#else
+
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+ unsigned int line, int errno, const char *fmt, ...)
+{
+ struct super_block *sb = fs_info->sb;
+
+ /*
+ * Special case: if the error is EROFS, and we're already
+ * under MS_RDONLY, then it is safe here.
+ */
+ if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
+ return;
+
+ /* Don't go through full error handling during mount */
+ if (sb->s_flags & MS_BORN) {
+ save_error_info(fs_info);
+ btrfs_handle_error(fs_info);
+ }
+}
+#endif
+
/*
* We only mark the transaction aborted and then set the file system read-only.
* This will prevent new transactions from starting or trying to join this
@@ -218,15 +253,21 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root, const char *function,
unsigned int line, int errno)
{
- WARN_ONCE(1, KERN_DEBUG "btrfs: Transaction aborted");
+ WARN_ONCE(1, KERN_DEBUG "btrfs: Transaction aborted\n");
trans->aborted = errno;
/* Nothing used. The other threads that have joined this
* transaction may be able to continue. */
if (!trans->blocks_used) {
- btrfs_printk(root->fs_info, "Aborting unused transaction.\n");
+ char nbuf[16];
+ const char *errstr;
+
+ errstr = btrfs_decode_error(root->fs_info, errno, nbuf);
+ btrfs_printk(root->fs_info,
+ "%s:%d: Aborting unused transaction(%s).\n",
+ function, line, errstr);
return;
}
- trans->transaction->aborted = errno;
+ ACCESS_ONCE(trans->transaction->aborted) = errno;
__btrfs_std_error(root->fs_info, function, line, errno, NULL);
}
/*
@@ -382,7 +423,15 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
btrfs_set_opt(info->mount_opt, NODATASUM);
break;
case Opt_nodatacow:
- printk(KERN_INFO "btrfs: setting nodatacow\n");
+ if (!btrfs_test_opt(root, COMPRESS) ||
+ !btrfs_test_opt(root, FORCE_COMPRESS)) {
+ printk(KERN_INFO "btrfs: setting nodatacow, compression disabled\n");
+ } else {
+ printk(KERN_INFO "btrfs: setting nodatacow\n");
+ }
+ info->compress_type = BTRFS_COMPRESS_NONE;
+ btrfs_clear_opt(info->mount_opt, COMPRESS);
+ btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
btrfs_set_opt(info->mount_opt, NODATACOW);
btrfs_set_opt(info->mount_opt, NODATASUM);
break;
@@ -396,15 +445,27 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
strcmp(args[0].from, "zlib") == 0) {
compress_type = "zlib";
info->compress_type = BTRFS_COMPRESS_ZLIB;
+ btrfs_set_opt(info->mount_opt, COMPRESS);
+ btrfs_clear_opt(info->mount_opt, NODATACOW);
+ btrfs_clear_opt(info->mount_opt, NODATASUM);
} else if (strcmp(args[0].from, "lzo") == 0) {
compress_type = "lzo";
info->compress_type = BTRFS_COMPRESS_LZO;
+ btrfs_set_opt(info->mount_opt, COMPRESS);
+ btrfs_clear_opt(info->mount_opt, NODATACOW);
+ btrfs_clear_opt(info->mount_opt, NODATASUM);
+ btrfs_set_fs_incompat(info, COMPRESS_LZO);
+ } else if (strncmp(args[0].from, "no", 2) == 0) {
+ compress_type = "no";
+ info->compress_type = BTRFS_COMPRESS_NONE;
+ btrfs_clear_opt(info->mount_opt, COMPRESS);
+ btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
+ compress_force = false;
} else {
ret = -EINVAL;
goto out;
}
- btrfs_set_opt(info->mount_opt, COMPRESS);
if (compress_force) {
btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
pr_info("btrfs: force %s compression\n",
@@ -510,11 +571,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
break;
case Opt_defrag:
- printk(KERN_INFO "btrfs: enabling auto defrag");
+ printk(KERN_INFO "btrfs: enabling auto defrag\n");
btrfs_set_opt(info->mount_opt, AUTO_DEFRAG);
break;
case Opt_recovery:
- printk(KERN_INFO "btrfs: enabling auto recovery");
+ printk(KERN_INFO "btrfs: enabling auto recovery\n");
btrfs_set_opt(info->mount_opt, RECOVERY);
break;
case Opt_skip_balance:
@@ -805,7 +866,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
struct btrfs_trans_handle *trans;
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *root = fs_info->tree_root;
- int ret;
trace_btrfs_sync_fs(wait);
@@ -814,13 +874,16 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
return 0;
}
- btrfs_wait_ordered_extents(root, 0, 0);
+ btrfs_wait_ordered_extents(root, 0);
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
+ trans = btrfs_attach_transaction(root);
+ if (IS_ERR(trans)) {
+ /* no transaction, don't bother */
+ if (PTR_ERR(trans) == -ENOENT)
+ return 0;
return PTR_ERR(trans);
- ret = btrfs_commit_transaction(trans, root);
- return ret;
+ }
+ return btrfs_commit_transaction(trans, root);
}
static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
@@ -1068,7 +1131,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
}
bdev = fs_devices->latest_bdev;
- s = sget(fs_type, btrfs_test_super, btrfs_set_super, fs_info);
+ s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC,
+ fs_info);
if (IS_ERR(s)) {
error = PTR_ERR(s);
goto error_close_devices;
@@ -1082,7 +1146,6 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
} else {
char b[BDEVNAME_SIZE];
- s->s_flags = flags | MS_NOSEC;
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
btrfs_sb(s)->bdev_holder = fs_type;
error = btrfs_fill_super(s, fs_devices, data,
@@ -1133,7 +1196,8 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
btrfs_set_max_workers(&fs_info->endio_freespace_worker, new_pool_size);
btrfs_set_max_workers(&fs_info->delayed_workers, new_pool_size);
btrfs_set_max_workers(&fs_info->readahead_workers, new_pool_size);
- btrfs_set_max_workers(&fs_info->scrub_workers, new_pool_size);
+ btrfs_set_max_workers(&fs_info->scrub_wr_completion_workers,
+ new_pool_size);
}
static int btrfs_remount(struct super_block *sb, int *flags, char *data)
@@ -1162,8 +1226,15 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
return 0;
if (*flags & MS_RDONLY) {
+ /*
+ * this also happens on 'umount -rf' or on shutdown, when
+ * the filesystem is busy.
+ */
sb->s_flags |= MS_RDONLY;
+ btrfs_dev_replace_suspend_for_unmount(fs_info);
+ btrfs_scrub_cancel(fs_info);
+
ret = btrfs_commit_super(root);
if (ret)
goto restore;
@@ -1173,6 +1244,15 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
goto restore;
}
+ if (fs_info->fs_devices->missing_devices >
+ fs_info->num_tolerated_disk_barrier_failures &&
+ !(*flags & MS_RDONLY)) {
+ printk(KERN_WARNING
+ "Btrfs: too many missing devices, writeable remount is not allowed\n");
+ ret = -EACCES;
+ goto restore;
+ }
+
if (btrfs_super_log_root(fs_info->super_copy) != 0) {
ret = -EINVAL;
goto restore;
@@ -1191,6 +1271,11 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
if (ret)
goto restore;
+ ret = btrfs_resume_dev_replace_async(fs_info);
+ if (ret) {
+ pr_warn("btrfs: failed to resume dev_replace\n");
+ goto restore;
+ }
sb->s_flags &= ~MS_RDONLY;
}
@@ -1283,7 +1368,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
min_stripe_size = BTRFS_STRIPE_LEN;
list_for_each_entry(device, &fs_devices->devices, dev_list) {
- if (!device->in_fs_metadata || !device->bdev)
+ if (!device->in_fs_metadata || !device->bdev ||
+ device->is_tgtdev_for_dev_replace)
continue;
avail_space = device->total_bytes - device->bytes_used;
@@ -1455,6 +1541,13 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
ret = btrfs_scan_one_device(vol->name, FMODE_READ,
&btrfs_fs_type, &fs_devices);
break;
+ case BTRFS_IOC_DEVICES_READY:
+ ret = btrfs_scan_one_device(vol->name, FMODE_READ,
+ &btrfs_fs_type, &fs_devices);
+ if (ret)
+ break;
+ ret = !(fs_devices->num_devices == fs_devices->total_devices);
+ break;
}
kfree(vol);
@@ -1463,30 +1556,24 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
static int btrfs_freeze(struct super_block *sb)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(sb);
- mutex_lock(&fs_info->transaction_kthread_mutex);
- mutex_lock(&fs_info->cleaner_mutex);
- return 0;
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+
+ trans = btrfs_attach_transaction(root);
+ if (IS_ERR(trans)) {
+ /* no transaction, don't bother */
+ if (PTR_ERR(trans) == -ENOENT)
+ return 0;
+ return PTR_ERR(trans);
+ }
+ return btrfs_commit_transaction(trans, root);
}
static int btrfs_unfreeze(struct super_block *sb)
{
- struct btrfs_fs_info *fs_info = btrfs_sb(sb);
- mutex_unlock(&fs_info->cleaner_mutex);
- mutex_unlock(&fs_info->transaction_kthread_mutex);
return 0;
}
-static void btrfs_fs_dirty_inode(struct inode *inode, int flags)
-{
- int ret;
-
- ret = btrfs_dirty_inode(inode);
- if (ret)
- printk_ratelimited(KERN_ERR "btrfs: fail to dirty inode %Lu "
- "error %d\n", btrfs_ino(inode), ret);
-}
-
static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
@@ -1500,6 +1587,8 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
while (cur_devices) {
head = &cur_devices->devices;
list_for_each_entry(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!first_dev || dev->devid < first_dev->devid)
first_dev = dev;
}
@@ -1526,7 +1615,6 @@ static const struct super_operations btrfs_super_ops = {
.show_options = btrfs_show_options,
.show_devname = btrfs_show_devname,
.write_inode = btrfs_write_inode,
- .dirty_inode = btrfs_fs_dirty_inode,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
.statfs = btrfs_statfs,
@@ -1559,7 +1647,7 @@ static int btrfs_interface_init(void)
static void btrfs_interface_exit(void)
{
if (misc_deregister(&btrfs_misc) < 0)
- printk(KERN_INFO "misc_deregister failed for control device");
+ printk(KERN_INFO "btrfs: misc_deregister failed for control device\n");
}
static int __init init_btrfs_fs(void)
@@ -1584,14 +1672,22 @@ static int __init init_btrfs_fs(void)
if (err)
goto free_extent_io;
- err = btrfs_delayed_inode_init();
+ err = ordered_data_init();
if (err)
goto free_extent_map;
- err = btrfs_interface_init();
+ err = btrfs_delayed_inode_init();
+ if (err)
+ goto free_ordered_data;
+
+ err = btrfs_auto_defrag_init();
if (err)
goto free_delayed_inode;
+ err = btrfs_interface_init();
+ if (err)
+ goto free_auto_defrag;
+
err = register_filesystem(&btrfs_fs_type);
if (err)
goto unregister_ioctl;
@@ -1603,8 +1699,12 @@ static int __init init_btrfs_fs(void)
unregister_ioctl:
btrfs_interface_exit();
+free_auto_defrag:
+ btrfs_auto_defrag_exit();
free_delayed_inode:
btrfs_delayed_inode_exit();
+free_ordered_data:
+ ordered_data_exit();
free_extent_map:
extent_map_exit();
free_extent_io:
@@ -1620,7 +1720,9 @@ free_compress:
static void __exit exit_btrfs_fs(void)
{
btrfs_destroy_cachep();
+ btrfs_auto_defrag_exit();
btrfs_delayed_inode_exit();
+ ordered_data_exit();
extent_map_exit();
extent_io_exit();
btrfs_interface_exit();