#include <linux/capability.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
-#include <asm/div64.h>
#include "compat.h"
#include "ctree.h"
#include "extent_map.h"
#include "async-thread.h"
#include "check-integrity.h"
#include "rcu-string.h"
+#include "math.h"
+#include "dev-replace.h"
static int init_first_rw_device(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
return NULL;
}
+static int
+btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
+ int flush, struct block_device **bdev,
+ struct buffer_head **bh)
+{
+ int ret;
+
+ *bdev = blkdev_get_by_path(device_path, flags, holder);
+
+ if (IS_ERR(*bdev)) {
+ ret = PTR_ERR(*bdev);
+ printk(KERN_INFO "btrfs: open %s failed\n", device_path);
+ goto error;
+ }
+
+ if (flush)
+ filemap_write_and_wait((*bdev)->bd_inode->i_mapping);
+ ret = set_blocksize(*bdev, 4096);
+ if (ret) {
+ blkdev_put(*bdev, flags);
+ goto error;
+ }
+ invalidate_bdev(*bdev);
+ *bh = btrfs_read_dev_super(*bdev);
+ if (!*bh) {
+ ret = -EINVAL;
+ blkdev_put(*bdev, flags);
+ goto error;
+ }
+
+ return 0;
+
+error:
+ *bdev = NULL;
+ *bh = NULL;
+ return ret;
+}
+
static void requeue_list(struct btrfs_pending_bios *pending_bios,
struct bio *head, struct bio *tail)
{
return ERR_PTR(-ENOMEM);
}
-void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices)
+void btrfs_close_extra_devices(struct btrfs_fs_info *fs_info,
+ struct btrfs_fs_devices *fs_devices, int step)
{
struct btrfs_device *device, *next;
/* This is the initialized path, it is safe to release the devices. */
list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
if (device->in_fs_metadata) {
- if (!latest_transid ||
- device->generation > latest_transid) {
+ if (!device->is_tgtdev_for_dev_replace &&
+ (!latest_transid ||
+ device->generation > latest_transid)) {
latest_devid = device->devid;
latest_transid = device->generation;
latest_bdev = device->bdev;
continue;
}
+ if (device->devid == BTRFS_DEV_REPLACE_DEVID) {
+ /*
+ * In the first step, keep the device which has
+ * the correct fsid and the devid that is used
+ * for the dev_replace procedure.
+ * In the second step, the dev_replace state is
+ * read from the device tree and it is known
+ * whether the procedure is really active or
+ * not, which means whether this device is
+ * used or whether it should be removed.
+ */
+ if (step == 0 || device->is_tgtdev_for_dev_replace) {
+ continue;
+ }
+ }
if (device->bdev) {
blkdev_put(device->bdev, device->mode);
device->bdev = NULL;
if (device->writeable) {
list_del_init(&device->dev_alloc_list);
device->writeable = 0;
- fs_devices->rw_devices--;
+ if (!device->is_tgtdev_for_dev_replace)
+ fs_devices->rw_devices--;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
if (device->bdev)
fs_devices->open_devices--;
- if (device->writeable) {
+ if (device->writeable && !device->is_tgtdev_for_dev_replace) {
list_del_init(&device->dev_alloc_list);
fs_devices->rw_devices--;
}
if (!device->name)
continue;
- bdev = blkdev_get_by_path(device->name->str, flags, holder);
- if (IS_ERR(bdev)) {
- printk(KERN_INFO "btrfs: open %s failed\n", device->name->str);
- goto error;
- }
- filemap_write_and_wait(bdev->bd_inode->i_mapping);
- invalidate_bdev(bdev);
- set_blocksize(bdev, 4096);
-
- bh = btrfs_read_dev_super(bdev);
- if (!bh)
- goto error_close;
+ ret = btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
+ &bdev, &bh);
+ if (ret)
+ continue;
disk_super = (struct btrfs_super_block *)bh->b_data;
devid = btrfs_stack_device_id(&disk_super->dev_item);
fs_devices->rotating = 1;
fs_devices->open_devices++;
- if (device->writeable) {
+ if (device->writeable && !device->is_tgtdev_for_dev_replace) {
fs_devices->rw_devices++;
list_add(&device->dev_alloc_list,
&fs_devices->alloc_list);
error_brelse:
brelse(bh);
-error_close:
blkdev_put(bdev, flags);
-error:
continue;
}
if (fs_devices->open_devices == 0) {
u64 total_devices;
flags |= FMODE_EXCL;
- bdev = blkdev_get_by_path(path, flags, holder);
-
- if (IS_ERR(bdev)) {
- ret = PTR_ERR(bdev);
- goto error;
- }
-
mutex_lock(&uuid_mutex);
- ret = set_blocksize(bdev, 4096);
+ ret = btrfs_get_bdev_and_sb(path, flags, holder, 0, &bdev, &bh);
if (ret)
- goto error_close;
- bh = btrfs_read_dev_super(bdev);
- if (!bh) {
- ret = -EINVAL;
- goto error_close;
- }
+ goto error;
disk_super = (struct btrfs_super_block *)bh->b_data;
devid = btrfs_stack_device_id(&disk_super->dev_item);
transid = btrfs_super_generation(disk_super);
total_devices = btrfs_super_num_devices(disk_super);
- if (disk_super->label[0])
+ if (disk_super->label[0]) {
+ if (disk_super->label[BTRFS_LABEL_SIZE - 1])
+ disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0';
printk(KERN_INFO "device label %s ", disk_super->label);
- else
+ } else {
printk(KERN_INFO "device fsid %pU ", disk_super->fsid);
+ }
printk(KERN_CONT "devid %llu transid %llu %s\n",
(unsigned long long)devid, (unsigned long long)transid, path);
ret = device_list_add(path, disk_super, devid, fs_devices_ret);
if (!ret && fs_devices_ret)
(*fs_devices_ret)->total_devices = total_devices;
brelse(bh);
-error_close:
- mutex_unlock(&uuid_mutex);
blkdev_put(bdev, flags);
error:
+ mutex_unlock(&uuid_mutex);
return ret;
}
*length = 0;
- if (start >= device->total_bytes)
+ if (start >= device->total_bytes || device->is_tgtdev_for_dev_replace)
return 0;
path = btrfs_alloc_path();
max_hole_size = 0;
hole_size = 0;
- if (search_start >= search_end) {
+ if (search_start >= search_end || device->is_tgtdev_for_dev_replace) {
ret = -ENOSPC;
goto error;
}
struct btrfs_key key;
WARN_ON(!device->in_fs_metadata);
+ WARN_ON(device->is_tgtdev_for_dev_replace);
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
root->fs_info->avail_system_alloc_bits |
root->fs_info->avail_metadata_alloc_bits;
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) &&
- root->fs_info->fs_devices->num_devices <= 4) {
+ num_devices = root->fs_info->fs_devices->num_devices;
+ btrfs_dev_replace_lock(&root->fs_info->dev_replace);
+ if (btrfs_dev_replace_is_ongoing(&root->fs_info->dev_replace)) {
+ WARN_ON(num_devices < 1);
+ num_devices--;
+ }
+ btrfs_dev_replace_unlock(&root->fs_info->dev_replace);
+
+ if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) {
printk(KERN_ERR "btrfs: unable to go below four devices "
"on raid10\n");
ret = -EINVAL;
goto out;
}
- if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) &&
- root->fs_info->fs_devices->num_devices <= 2) {
+ if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) && num_devices <= 2) {
printk(KERN_ERR "btrfs: unable to go below two "
"devices on raid1\n");
ret = -EINVAL;
* is held.
*/
list_for_each_entry(tmp, devices, dev_list) {
- if (tmp->in_fs_metadata && !tmp->bdev) {
+ if (tmp->in_fs_metadata &&
+ !tmp->is_tgtdev_for_dev_replace &&
+ !tmp->bdev) {
device = tmp;
break;
}
goto out;
}
} else {
- bdev = blkdev_get_by_path(device_path, FMODE_READ | FMODE_EXCL,
- root->fs_info->bdev_holder);
- if (IS_ERR(bdev)) {
- ret = PTR_ERR(bdev);
+ ret = btrfs_get_bdev_and_sb(device_path,
+ FMODE_READ | FMODE_EXCL,
+ root->fs_info->bdev_holder, 0,
+ &bdev, &bh);
+ if (ret)
goto out;
- }
-
- set_blocksize(bdev, 4096);
- invalidate_bdev(bdev);
- bh = btrfs_read_dev_super(bdev);
- if (!bh) {
- ret = -EINVAL;
- goto error_close;
- }
disk_super = (struct btrfs_super_block *)bh->b_data;
devid = btrfs_stack_device_id(&disk_super->dev_item);
dev_uuid = disk_super->dev_item.uuid;
- device = btrfs_find_device(root, devid, dev_uuid,
+ device = btrfs_find_device(root->fs_info, devid, dev_uuid,
disk_super->fsid);
if (!device) {
ret = -ENOENT;
}
}
+ if (device->is_tgtdev_for_dev_replace) {
+ pr_err("btrfs: unable to remove the dev_replace target dev\n");
+ ret = -EINVAL;
+ goto error_brelse;
+ }
+
if (device->writeable && root->fs_info->fs_devices->rw_devices == 1) {
printk(KERN_ERR "btrfs: unable to remove the only writeable "
"device\n");
if (ret)
goto error_undo;
+ /*
+ * TODO: the superblock still includes this device in its num_devices
+ * counter although write_all_supers() is not locked out. This
+ * could give a filesystem state which requires a degraded mount.
+ */
ret = btrfs_rm_dev_item(root->fs_info->chunk_root, device);
if (ret)
goto error_undo;
spin_unlock(&root->fs_info->free_chunk_lock);
device->in_fs_metadata = 0;
- btrfs_scrub_cancel_dev(root, device);
+ btrfs_scrub_cancel_dev(root->fs_info, device);
/*
* the device list mutex makes sure that we don't change
* at this point, the device is zero sized. We want to
* remove it from the devices list and zero out the old super
*/
- if (clear_super) {
+ if (clear_super && disk_super) {
/* make sure this device isn't detected as part of
* the FS anymore
*/
goto error_brelse;
}
+void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *srcdev)
+{
+ WARN_ON(!mutex_is_locked(&fs_info->fs_devices->device_list_mutex));
+ list_del_rcu(&srcdev->dev_list);
+ list_del_rcu(&srcdev->dev_alloc_list);
+ fs_info->fs_devices->num_devices--;
+ if (srcdev->missing) {
+ fs_info->fs_devices->missing_devices--;
+ fs_info->fs_devices->rw_devices++;
+ }
+ if (srcdev->can_discard)
+ fs_info->fs_devices->num_can_discard--;
+ if (srcdev->bdev)
+ fs_info->fs_devices->open_devices--;
+
+ call_rcu(&srcdev->rcu, free_device);
+}
+
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *tgtdev)
+{
+ struct btrfs_device *next_device;
+
+ WARN_ON(!tgtdev);
+ mutex_lock(&fs_info->fs_devices->device_list_mutex);
+ if (tgtdev->bdev) {
+ btrfs_scratch_superblock(tgtdev);
+ fs_info->fs_devices->open_devices--;
+ }
+ fs_info->fs_devices->num_devices--;
+ if (tgtdev->can_discard)
+ fs_info->fs_devices->num_can_discard++;
+
+ next_device = list_entry(fs_info->fs_devices->devices.next,
+ struct btrfs_device, dev_list);
+ if (tgtdev->bdev == fs_info->sb->s_bdev)
+ fs_info->sb->s_bdev = next_device->bdev;
+ if (tgtdev->bdev == fs_info->fs_devices->latest_bdev)
+ fs_info->fs_devices->latest_bdev = next_device->bdev;
+ list_del_rcu(&tgtdev->dev_list);
+
+ call_rcu(&tgtdev->rcu, free_device);
+
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+}
+
+int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path,
+ struct btrfs_device **device)
+{
+ int ret = 0;
+ struct btrfs_super_block *disk_super;
+ u64 devid;
+ u8 *dev_uuid;
+ struct block_device *bdev;
+ struct buffer_head *bh;
+
+ *device = NULL;
+ ret = btrfs_get_bdev_and_sb(device_path, FMODE_READ,
+ root->fs_info->bdev_holder, 0, &bdev, &bh);
+ if (ret)
+ return ret;
+ disk_super = (struct btrfs_super_block *)bh->b_data;
+ devid = btrfs_stack_device_id(&disk_super->dev_item);
+ dev_uuid = disk_super->dev_item.uuid;
+ *device = btrfs_find_device(root->fs_info, devid, dev_uuid,
+ disk_super->fsid);
+ brelse(bh);
+ if (!*device)
+ ret = -ENOENT;
+ blkdev_put(bdev, FMODE_READ);
+ return ret;
+}
+
+int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
+ char *device_path,
+ struct btrfs_device **device)
+{
+ *device = NULL;
+ if (strcmp(device_path, "missing") == 0) {
+ struct list_head *devices;
+ struct btrfs_device *tmp;
+
+ devices = &root->fs_info->fs_devices->devices;
+ /*
+ * It is safe to read the devices since the volume_mutex
+ * is held by the caller.
+ */
+ list_for_each_entry(tmp, devices, dev_list) {
+ if (tmp->in_fs_metadata && !tmp->bdev) {
+ *device = tmp;
+ break;
+ }
+ }
+
+ if (!*device) {
+ pr_err("btrfs: no missing device found\n");
+ return -ENOENT;
+ }
+
+ return 0;
+ } else {
+ return btrfs_find_device_by_path(root, device_path, device);
+ }
+}
+
/*
* does all the dirty work required for changing file system's UUID.
*/
read_extent_buffer(leaf, fs_uuid,
(unsigned long)btrfs_device_fsid(dev_item),
BTRFS_UUID_SIZE);
- device = btrfs_find_device(root, devid, dev_uuid, fs_uuid);
+ device = btrfs_find_device(root->fs_info, devid, dev_uuid,
+ fs_uuid);
BUG_ON(!device); /* Logic error */
if (device->fs_devices->seeding) {
filemap_write_and_wait(bdev->bd_inode->i_mapping);
devices = &root->fs_info->fs_devices->devices;
- /*
- * we have the volume lock, so we don't need the extra
- * device list mutex while reading the list here.
- */
+
+ mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
list_for_each_entry(device, devices, dev_list) {
if (device->bdev == bdev) {
ret = -EEXIST;
+ mutex_unlock(
+ &root->fs_info->fs_devices->device_list_mutex);
goto error;
}
}
+ mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
device = kzalloc(sizeof(*device), GFP_NOFS);
if (!device) {
device->dev_root = root->fs_info->dev_root;
device->bdev = bdev;
device->in_fs_metadata = 1;
+ device->is_tgtdev_for_dev_replace = 0;
device->mode = FMODE_EXCL;
set_blocksize(device->bdev, 4096);
"Failed to relocate sys chunks after "
"device initialization. This can be fixed "
"using the \"btrfs balance\" command.");
+ trans = btrfs_attach_transaction(root);
+ if (IS_ERR(trans)) {
+ if (PTR_ERR(trans) == -ENOENT)
+ return 0;
+ return PTR_ERR(trans);
+ }
+ ret = btrfs_commit_transaction(trans, root);
}
return ret;
return ret;
}
+int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, char *device_path,
+ struct btrfs_device **device_out)
+{
+ struct request_queue *q;
+ struct btrfs_device *device;
+ struct block_device *bdev;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct list_head *devices;
+ struct rcu_string *name;
+ int ret = 0;
+
+ *device_out = NULL;
+ if (fs_info->fs_devices->seeding)
+ return -EINVAL;
+
+ bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
+ fs_info->bdev_holder);
+ if (IS_ERR(bdev))
+ return PTR_ERR(bdev);
+
+ filemap_write_and_wait(bdev->bd_inode->i_mapping);
+
+ devices = &fs_info->fs_devices->devices;
+ list_for_each_entry(device, devices, dev_list) {
+ if (device->bdev == bdev) {
+ ret = -EEXIST;
+ goto error;
+ }
+ }
+
+ device = kzalloc(sizeof(*device), GFP_NOFS);
+ if (!device) {
+ ret = -ENOMEM;
+ goto error;
+ }
+
+ name = rcu_string_strdup(device_path, GFP_NOFS);
+ if (!name) {
+ kfree(device);
+ ret = -ENOMEM;
+ goto error;
+ }
+ rcu_assign_pointer(device->name, name);
+
+ q = bdev_get_queue(bdev);
+ if (blk_queue_discard(q))
+ device->can_discard = 1;
+ mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
+ device->writeable = 1;
+ device->work.func = pending_bios_fn;
+ generate_random_uuid(device->uuid);
+ device->devid = BTRFS_DEV_REPLACE_DEVID;
+ spin_lock_init(&device->io_lock);
+ device->generation = 0;
+ device->io_width = root->sectorsize;
+ device->io_align = root->sectorsize;
+ device->sector_size = root->sectorsize;
+ device->total_bytes = i_size_read(bdev->bd_inode);
+ device->disk_total_bytes = device->total_bytes;
+ device->dev_root = fs_info->dev_root;
+ device->bdev = bdev;
+ device->in_fs_metadata = 1;
+ device->is_tgtdev_for_dev_replace = 1;
+ device->mode = FMODE_EXCL;
+ set_blocksize(device->bdev, 4096);
+ device->fs_devices = fs_info->fs_devices;
+ list_add(&device->dev_list, &fs_info->fs_devices->devices);
+ fs_info->fs_devices->num_devices++;
+ fs_info->fs_devices->open_devices++;
+ if (device->can_discard)
+ fs_info->fs_devices->num_can_discard++;
+ mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
+
+ *device_out = device;
+ return ret;
+
+error:
+ blkdev_put(bdev, FMODE_EXCL);
+ return ret;
+}
+
+void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info,
+ struct btrfs_device *tgtdev)
+{
+ WARN_ON(fs_info->fs_devices->rw_devices == 0);
+ tgtdev->io_width = fs_info->dev_root->sectorsize;
+ tgtdev->io_align = fs_info->dev_root->sectorsize;
+ tgtdev->sector_size = fs_info->dev_root->sectorsize;
+ tgtdev->dev_root = fs_info->dev_root;
+ tgtdev->in_fs_metadata = 1;
+}
+
static noinline int btrfs_update_device(struct btrfs_trans_handle *trans,
struct btrfs_device *device)
{
if (!device->writeable)
return -EACCES;
- if (new_size <= device->total_bytes)
+ if (new_size <= device->total_bytes ||
+ device->is_tgtdev_for_dev_replace)
return -EINVAL;
btrfs_set_super_total_bytes(super_copy, old_total + diff);
return 1;
}
-static u64 div_factor_fine(u64 num, int factor)
-{
- if (factor <= 0)
- return 0;
- if (factor >= 100)
- return num;
-
- num *= factor;
- do_div(num, 100);
- return num;
-}
-
static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
struct btrfs_balance_args *bargs)
{
return 1;
}
-static u64 div_factor(u64 num, int factor)
-{
- if (factor == 10)
- return num;
- num *= factor;
- do_div(num, 10);
- return num;
-}
-
static int __btrfs_balance(struct btrfs_fs_info *fs_info)
{
struct btrfs_balance_control *bctl = fs_info->balance_ctl;
size_to_free = div_factor(old_size, 1);
size_to_free = min(size_to_free, (u64)1 * 1024 * 1024);
if (!device->writeable ||
- device->total_bytes - device->bytes_used > size_to_free)
+ device->total_bytes - device->bytes_used > size_to_free ||
+ device->is_tgtdev_for_dev_replace)
continue;
ret = btrfs_shrink_device(device, old_size - size_to_free);
u64 allowed;
int mixed = 0;
int ret;
+ u64 num_devices;
if (btrfs_fs_closing(fs_info) ||
atomic_read(&fs_info->balance_pause_req) ||
}
}
+ num_devices = fs_info->fs_devices->num_devices;
+ btrfs_dev_replace_lock(&fs_info->dev_replace);
+ if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace)) {
+ BUG_ON(num_devices < 1);
+ num_devices--;
+ }
+ btrfs_dev_replace_unlock(&fs_info->dev_replace);
allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
- if (fs_info->fs_devices->num_devices == 1)
+ if (num_devices == 1)
allowed |= BTRFS_BLOCK_GROUP_DUP;
- else if (fs_info->fs_devices->num_devices < 4)
+ else if (num_devices < 4)
allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
else
allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
ret = btrfs_balance(fs_info->balance_ctl, NULL);
}
+ atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
mutex_unlock(&fs_info->balance_mutex);
mutex_unlock(&fs_info->volume_mutex);
return 0;
}
+ WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
if (IS_ERR(tsk))
return PTR_ERR(tsk);
u64 old_size = device->total_bytes;
u64 diff = device->total_bytes - new_size;
- if (new_size >= device->total_bytes)
+ if (device->is_tgtdev_for_dev_replace)
return -EINVAL;
path = btrfs_alloc_path();
cur = cur->next;
if (!device->writeable) {
- printk(KERN_ERR
+ WARN(1, KERN_ERR
"btrfs: read-only device in alloc_list\n");
- WARN_ON(1);
continue;
}
- if (!device->in_fs_metadata)
+ if (!device->in_fs_metadata ||
+ device->is_tgtdev_for_dev_replace)
continue;
if (device->total_bytes > device->bytes_used)
devices_info[ndevs].total_avail = total_avail;
devices_info[ndevs].dev = device;
++ndevs;
+ WARN_ON(ndevs > fs_devices->rw_devices);
}
/*
}
}
-int btrfs_num_copies(struct btrfs_mapping_tree *map_tree, u64 logical, u64 len)
+int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
{
+ struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
struct extent_map *em;
struct map_lookup *map;
struct extent_map_tree *em_tree = &map_tree->map_tree;
return optimal;
}
-static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
+static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
u64 logical, u64 *length,
struct btrfs_bio **bbio_ret,
int mirror_num)
{
struct extent_map *em;
struct map_lookup *map;
+ struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
struct extent_map_tree *em_tree = &map_tree->map_tree;
u64 offset;
u64 stripe_offset;
stripe_nr_end - stripe_nr_orig);
stripe_index = do_div(stripe_nr, map->num_stripes);
} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
- if (rw & (REQ_WRITE | REQ_DISCARD))
+ if (rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS))
num_stripes = map->num_stripes;
else if (mirror_num)
stripe_index = mirror_num - 1;
}
} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
- if (rw & (REQ_WRITE | REQ_DISCARD)) {
+ if (rw & (REQ_WRITE | REQ_DISCARD | REQ_GET_READ_MIRRORS)) {
num_stripes = map->num_stripes;
} else if (mirror_num) {
stripe_index = mirror_num - 1;
stripe_index = do_div(stripe_nr, factor);
stripe_index *= map->sub_stripes;
- if (rw & REQ_WRITE)
+ if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS))
num_stripes = map->sub_stripes;
else if (rw & REQ_DISCARD)
num_stripes = min_t(u64, map->sub_stripes *
}
}
- if (rw & REQ_WRITE) {
+ if (rw & (REQ_WRITE | REQ_GET_READ_MIRRORS)) {
if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
BTRFS_BLOCK_GROUP_RAID10 |
BTRFS_BLOCK_GROUP_DUP)) {
return ret;
}
-int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
+int btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
u64 logical, u64 *length,
struct btrfs_bio **bbio_ret, int mirror_num)
{
- return __btrfs_map_block(map_tree, rw, logical, length, bbio_ret,
+ return __btrfs_map_block(fs_info, rw, logical, length, bbio_ret,
mirror_num);
}
&device->work);
}
+static int bio_size_ok(struct block_device *bdev, struct bio *bio,
+ sector_t sector)
+{
+ struct bio_vec *prev;
+ struct request_queue *q = bdev_get_queue(bdev);
+ unsigned short max_sectors = queue_max_sectors(q);
+ struct bvec_merge_data bvm = {
+ .bi_bdev = bdev,
+ .bi_sector = sector,
+ .bi_rw = bio->bi_rw,
+ };
+
+ if (bio->bi_vcnt == 0) {
+ WARN_ON(1);
+ return 1;
+ }
+
+ prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
+ if ((bio->bi_size >> 9) > max_sectors)
+ return 0;
+
+ if (!q->merge_bvec_fn)
+ return 1;
+
+ bvm.bi_size = bio->bi_size - prev->bv_len;
+ if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len)
+ return 0;
+ return 1;
+}
+
+static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
+ struct bio *bio, u64 physical, int dev_nr,
+ int rw, int async)
+{
+ struct btrfs_device *dev = bbio->stripes[dev_nr].dev;
+
+ bio->bi_private = bbio;
+ bio->bi_private = merge_stripe_index_into_bio_private(
+ bio->bi_private, (unsigned int)dev_nr);
+ bio->bi_end_io = btrfs_end_bio;
+ bio->bi_sector = physical >> 9;
+#ifdef DEBUG
+ {
+ struct rcu_string *name;
+
+ rcu_read_lock();
+ name = rcu_dereference(dev->name);
+ pr_debug("btrfs_map_bio: rw %d, sector=%llu, dev=%lu "
+ "(%s id %llu), size=%u\n", rw,
+ (u64)bio->bi_sector, (u_long)dev->bdev->bd_dev,
+ name->str, dev->devid, bio->bi_size);
+ rcu_read_unlock();
+ }
+#endif
+ bio->bi_bdev = dev->bdev;
+ if (async)
+ schedule_bio(root, dev, rw, bio);
+ else
+ btrfsic_submit_bio(rw, bio);
+}
+
+static int breakup_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
+ struct bio *first_bio, struct btrfs_device *dev,
+ int dev_nr, int rw, int async)
+{
+ struct bio_vec *bvec = first_bio->bi_io_vec;
+ struct bio *bio;
+ int nr_vecs = bio_get_nr_vecs(dev->bdev);
+ u64 physical = bbio->stripes[dev_nr].physical;
+
+again:
+ bio = btrfs_bio_alloc(dev->bdev, physical >> 9, nr_vecs, GFP_NOFS);
+ if (!bio)
+ return -ENOMEM;
+
+ while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) {
+ if (bio_add_page(bio, bvec->bv_page, bvec->bv_len,
+ bvec->bv_offset) < bvec->bv_len) {
+ u64 len = bio->bi_size;
+
+ atomic_inc(&bbio->stripes_pending);
+ submit_stripe_bio(root, bbio, bio, physical, dev_nr,
+ rw, async);
+ physical += len;
+ goto again;
+ }
+ bvec++;
+ }
+
+ submit_stripe_bio(root, bbio, bio, physical, dev_nr, rw, async);
+ return 0;
+}
+
+static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
+{
+ atomic_inc(&bbio->error);
+ if (atomic_dec_and_test(&bbio->stripes_pending)) {
+ bio->bi_private = bbio->private;
+ bio->bi_end_io = bbio->end_io;
+ bio->bi_bdev = (struct block_device *)
+ (unsigned long)bbio->mirror_num;
+ bio->bi_sector = logical >> 9;
+ kfree(bbio);
+ bio_endio(bio, -EIO);
+ }
+}
+
int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
int mirror_num, int async_submit)
{
- struct btrfs_mapping_tree *map_tree;
struct btrfs_device *dev;
struct bio *first_bio = bio;
u64 logical = (u64)bio->bi_sector << 9;
struct btrfs_bio *bbio = NULL;
length = bio->bi_size;
- map_tree = &root->fs_info->mapping_tree;
map_length = length;
- ret = btrfs_map_block(map_tree, rw, logical, &map_length, &bbio,
+ ret = btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
mirror_num);
- if (ret) /* -ENOMEM */
+ if (ret)
return ret;
total_devs = bbio->num_stripes;
atomic_set(&bbio->stripes_pending, bbio->num_stripes);
while (dev_nr < total_devs) {
+ dev = bbio->stripes[dev_nr].dev;
+ if (!dev || !dev->bdev || (rw & WRITE && !dev->writeable)) {
+ bbio_error(bbio, first_bio, logical);
+ dev_nr++;
+ continue;
+ }
+
+ /*
+ * Check and see if we're ok with this bio based on it's size
+ * and offset with the given device.
+ */
+ if (!bio_size_ok(dev->bdev, first_bio,
+ bbio->stripes[dev_nr].physical >> 9)) {
+ ret = breakup_stripe_bio(root, bbio, first_bio, dev,
+ dev_nr, rw, async_submit);
+ BUG_ON(ret);
+ dev_nr++;
+ continue;
+ }
+
if (dev_nr < total_devs - 1) {
bio = bio_clone(first_bio, GFP_NOFS);
BUG_ON(!bio); /* -ENOMEM */
} else {
bio = first_bio;
}
- bio->bi_private = bbio;
- bio->bi_private = merge_stripe_index_into_bio_private(
- bio->bi_private, (unsigned int)dev_nr);
- bio->bi_end_io = btrfs_end_bio;
- bio->bi_sector = bbio->stripes[dev_nr].physical >> 9;
- dev = bbio->stripes[dev_nr].dev;
- if (dev && dev->bdev && (rw != WRITE || dev->writeable)) {
-#ifdef DEBUG
- struct rcu_string *name;
-
- rcu_read_lock();
- name = rcu_dereference(dev->name);
- pr_debug("btrfs_map_bio: rw %d, secor=%llu, dev=%lu "
- "(%s id %llu), size=%u\n", rw,
- (u64)bio->bi_sector, (u_long)dev->bdev->bd_dev,
- name->str, dev->devid, bio->bi_size);
- rcu_read_unlock();
-#endif
- bio->bi_bdev = dev->bdev;
- if (async_submit)
- schedule_bio(root, dev, rw, bio);
- else
- btrfsic_submit_bio(rw, bio);
- } else {
- bio->bi_bdev = root->fs_info->fs_devices->latest_bdev;
- bio->bi_sector = logical >> 9;
- bio_endio(bio, -EIO);
- }
+
+ submit_stripe_bio(root, bbio, bio,
+ bbio->stripes[dev_nr].physical, dev_nr, rw,
+ async_submit);
dev_nr++;
}
return 0;
}
-struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid,
+struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
u8 *uuid, u8 *fsid)
{
struct btrfs_device *device;
struct btrfs_fs_devices *cur_devices;
- cur_devices = root->fs_info->fs_devices;
+ cur_devices = fs_info->fs_devices;
while (cur_devices) {
if (!fsid ||
!memcmp(cur_devices->fsid, fsid, BTRFS_UUID_SIZE)) {
read_extent_buffer(leaf, uuid, (unsigned long)
btrfs_stripe_dev_uuid_nr(chunk, i),
BTRFS_UUID_SIZE);
- map->stripes[i].dev = btrfs_find_device(root, devid, uuid,
- NULL);
+ map->stripes[i].dev = btrfs_find_device(root->fs_info, devid,
+ uuid, NULL);
if (!map->stripes[i].dev && !btrfs_test_opt(root, DEGRADED)) {
kfree(map);
free_extent_map(em);
device->io_align = btrfs_device_io_align(leaf, dev_item);
device->io_width = btrfs_device_io_width(leaf, dev_item);
device->sector_size = btrfs_device_sector_size(leaf, dev_item);
+ WARN_ON(device->devid == BTRFS_DEV_REPLACE_DEVID);
+ device->is_tgtdev_for_dev_replace = 0;
ptr = (unsigned long)btrfs_device_uuid(dev_item);
read_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
return ret;
}
- device = btrfs_find_device(root, devid, dev_uuid, fs_uuid);
+ device = btrfs_find_device(root->fs_info, devid, dev_uuid, fs_uuid);
if (!device || !device->bdev) {
if (!btrfs_test_opt(root, DEGRADED))
return -EIO;
fill_device_from_item(leaf, dev_item, device);
device->dev_root = root->fs_info->dev_root;
device->in_fs_metadata = 1;
- if (device->writeable) {
+ if (device->writeable && !device->is_tgtdev_for_dev_replace) {
device->fs_devices->total_rw_bytes += device->total_bytes;
spin_lock(&root->fs_info->free_chunk_lock);
root->fs_info->free_chunk_space += device->total_bytes -
int i;
mutex_lock(&fs_devices->device_list_mutex);
- dev = btrfs_find_device(root, stats->devid, NULL, NULL);
+ dev = btrfs_find_device(root->fs_info, stats->devid, NULL, NULL);
mutex_unlock(&fs_devices->device_list_mutex);
if (!dev) {
stats->nr_items = BTRFS_DEV_STAT_VALUES_MAX;
return 0;
}
+
+int btrfs_scratch_superblock(struct btrfs_device *device)
+{
+ struct buffer_head *bh;
+ struct btrfs_super_block *disk_super;
+
+ bh = btrfs_read_dev_super(device->bdev);
+ if (!bh)
+ return -EINVAL;
+ disk_super = (struct btrfs_super_block *)bh->b_data;
+
+ memset(&disk_super->magic, 0, sizeof(disk_super->magic));
+ set_buffer_dirty(bh);
+ sync_dirty_buffer(bh);
+ brelse(bh);
+
+ return 0;
+}
projects / cascardo / linux.git / blobdiff