forked from Minki/linux
e0ae999414
For devices that support flushing, we allocate a bio, submit, wait for it and then free it. The bio allocation does not fail so ENOMEM is not a problem but we still may unnecessarily stress the allocation subsystem. Instead, we can allocate the bio at the same time we allocate the device and reuse it each time we need to flush the barriers. The bio is reset before each use. Reference counting is simplified to just device allocation (get) and freeing (put). The bio used to be submitted through the integrity checker which will find out that bio has no data attached and call submit_bio. Status of the bio in flight needs to be tracked separately in case the device caches get switched off between write and wait. Signed-off-by: David Sterba <dsterba@suse.com>
547 lines
16 KiB
C
547 lines
16 KiB
C
/*
|
|
* Copyright (C) 2007 Oracle. All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public
|
|
* License v2 as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public
|
|
* License along with this program; if not, write to the
|
|
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
|
|
* Boston, MA 021110-1307, USA.
|
|
*/
|
|
|
|
#ifndef __BTRFS_VOLUMES_
|
|
#define __BTRFS_VOLUMES_
|
|
|
|
#include <linux/bio.h>
|
|
#include <linux/sort.h>
|
|
#include <linux/btrfs.h>
|
|
#include "async-thread.h"
|
|
|
|
extern struct mutex uuid_mutex;
|
|
|
|
#define BTRFS_STRIPE_LEN SZ_64K
|
|
|
|
struct buffer_head;
|
|
struct btrfs_pending_bios {
|
|
struct bio *head;
|
|
struct bio *tail;
|
|
};
|
|
|
|
/*
|
|
* Use sequence counter to get consistent device stat data on
|
|
* 32-bit processors.
|
|
*/
|
|
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
|
|
#include <linux/seqlock.h>
|
|
#define __BTRFS_NEED_DEVICE_DATA_ORDERED
|
|
#define btrfs_device_data_ordered_init(device) \
|
|
seqcount_init(&device->data_seqcount)
|
|
#else
|
|
#define btrfs_device_data_ordered_init(device) do { } while (0)
|
|
#endif
|
|
|
|
struct btrfs_device {
|
|
struct list_head dev_list;
|
|
struct list_head dev_alloc_list;
|
|
struct btrfs_fs_devices *fs_devices;
|
|
struct btrfs_fs_info *fs_info;
|
|
|
|
struct rcu_string *name;
|
|
|
|
u64 generation;
|
|
|
|
spinlock_t io_lock ____cacheline_aligned;
|
|
int running_pending;
|
|
/* regular prio bios */
|
|
struct btrfs_pending_bios pending_bios;
|
|
/* sync bios */
|
|
struct btrfs_pending_bios pending_sync_bios;
|
|
|
|
struct block_device *bdev;
|
|
|
|
/* the mode sent to blkdev_get */
|
|
fmode_t mode;
|
|
|
|
int writeable;
|
|
int in_fs_metadata;
|
|
int missing;
|
|
int can_discard;
|
|
int is_tgtdev_for_dev_replace;
|
|
int last_flush_error;
|
|
int flush_bio_sent;
|
|
|
|
#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
|
|
seqcount_t data_seqcount;
|
|
#endif
|
|
|
|
/* the internal btrfs device id */
|
|
u64 devid;
|
|
|
|
/* size of the device in memory */
|
|
u64 total_bytes;
|
|
|
|
/* size of the device on disk */
|
|
u64 disk_total_bytes;
|
|
|
|
/* bytes used */
|
|
u64 bytes_used;
|
|
|
|
/* optimal io alignment for this device */
|
|
u32 io_align;
|
|
|
|
/* optimal io width for this device */
|
|
u32 io_width;
|
|
/* type and info about this device */
|
|
u64 type;
|
|
|
|
/* minimal io size for this device */
|
|
u32 sector_size;
|
|
|
|
/* physical drive uuid (or lvm uuid) */
|
|
u8 uuid[BTRFS_UUID_SIZE];
|
|
|
|
/*
|
|
* size of the device on the current transaction
|
|
*
|
|
* This variant is update when committing the transaction,
|
|
* and protected by device_list_mutex
|
|
*/
|
|
u64 commit_total_bytes;
|
|
|
|
/* bytes used on the current transaction */
|
|
u64 commit_bytes_used;
|
|
/*
|
|
* used to manage the device which is resized
|
|
*
|
|
* It is protected by chunk_lock.
|
|
*/
|
|
struct list_head resized_list;
|
|
|
|
/* for sending down flush barriers */
|
|
struct bio *flush_bio;
|
|
struct completion flush_wait;
|
|
|
|
/* per-device scrub information */
|
|
struct scrub_ctx *scrub_device;
|
|
|
|
struct btrfs_work work;
|
|
struct rcu_head rcu;
|
|
struct work_struct rcu_work;
|
|
|
|
/* readahead state */
|
|
spinlock_t reada_lock;
|
|
atomic_t reada_in_flight;
|
|
u64 reada_next;
|
|
struct reada_zone *reada_curr_zone;
|
|
struct radix_tree_root reada_zones;
|
|
struct radix_tree_root reada_extents;
|
|
|
|
/* disk I/O failure stats. For detailed description refer to
|
|
* enum btrfs_dev_stat_values in ioctl.h */
|
|
int dev_stats_valid;
|
|
|
|
/* Counter to record the change of device stats */
|
|
atomic_t dev_stats_ccnt;
|
|
atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX];
|
|
};
|
|
|
|
/*
|
|
* If we read those variants at the context of their own lock, we needn't
|
|
* use the following helpers, reading them directly is safe.
|
|
*/
|
|
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
|
|
#define BTRFS_DEVICE_GETSET_FUNCS(name) \
|
|
static inline u64 \
|
|
btrfs_device_get_##name(const struct btrfs_device *dev) \
|
|
{ \
|
|
u64 size; \
|
|
unsigned int seq; \
|
|
\
|
|
do { \
|
|
seq = read_seqcount_begin(&dev->data_seqcount); \
|
|
size = dev->name; \
|
|
} while (read_seqcount_retry(&dev->data_seqcount, seq)); \
|
|
return size; \
|
|
} \
|
|
\
|
|
static inline void \
|
|
btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
|
|
{ \
|
|
preempt_disable(); \
|
|
write_seqcount_begin(&dev->data_seqcount); \
|
|
dev->name = size; \
|
|
write_seqcount_end(&dev->data_seqcount); \
|
|
preempt_enable(); \
|
|
}
|
|
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
|
|
#define BTRFS_DEVICE_GETSET_FUNCS(name) \
|
|
static inline u64 \
|
|
btrfs_device_get_##name(const struct btrfs_device *dev) \
|
|
{ \
|
|
u64 size; \
|
|
\
|
|
preempt_disable(); \
|
|
size = dev->name; \
|
|
preempt_enable(); \
|
|
return size; \
|
|
} \
|
|
\
|
|
static inline void \
|
|
btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
|
|
{ \
|
|
preempt_disable(); \
|
|
dev->name = size; \
|
|
preempt_enable(); \
|
|
}
|
|
#else
|
|
#define BTRFS_DEVICE_GETSET_FUNCS(name) \
|
|
static inline u64 \
|
|
btrfs_device_get_##name(const struct btrfs_device *dev) \
|
|
{ \
|
|
return dev->name; \
|
|
} \
|
|
\
|
|
static inline void \
|
|
btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
|
|
{ \
|
|
dev->name = size; \
|
|
}
|
|
#endif
|
|
|
|
BTRFS_DEVICE_GETSET_FUNCS(total_bytes);
|
|
BTRFS_DEVICE_GETSET_FUNCS(disk_total_bytes);
|
|
BTRFS_DEVICE_GETSET_FUNCS(bytes_used);
|
|
|
|
struct btrfs_fs_devices {
|
|
u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
|
|
|
|
u64 num_devices;
|
|
u64 open_devices;
|
|
u64 rw_devices;
|
|
u64 missing_devices;
|
|
u64 total_rw_bytes;
|
|
u64 total_devices;
|
|
struct block_device *latest_bdev;
|
|
|
|
/* all of the devices in the FS, protected by a mutex
|
|
* so we can safely walk it to write out the supers without
|
|
* worrying about add/remove by the multi-device code.
|
|
* Scrubbing super can kick off supers writing by holding
|
|
* this mutex lock.
|
|
*/
|
|
struct mutex device_list_mutex;
|
|
struct list_head devices;
|
|
|
|
struct list_head resized_devices;
|
|
/* devices not currently being allocated */
|
|
struct list_head alloc_list;
|
|
struct list_head list;
|
|
|
|
struct btrfs_fs_devices *seed;
|
|
int seeding;
|
|
|
|
int opened;
|
|
|
|
/* set when we find or add a device that doesn't have the
|
|
* nonrot flag set
|
|
*/
|
|
int rotating;
|
|
|
|
struct btrfs_fs_info *fs_info;
|
|
/* sysfs kobjects */
|
|
struct kobject fsid_kobj;
|
|
struct kobject *device_dir_kobj;
|
|
struct completion kobj_unregister;
|
|
};
|
|
|
|
#define BTRFS_BIO_INLINE_CSUM_SIZE 64
|
|
|
|
/*
|
|
* we need the mirror number and stripe index to be passed around
|
|
* the call chain while we are processing end_io (especially errors).
|
|
* Really, what we need is a btrfs_bio structure that has this info
|
|
* and is properly sized with its stripe array, but we're not there
|
|
* quite yet. We have our own btrfs bioset, and all of the bios
|
|
* we allocate are actually btrfs_io_bios. We'll cram as much of
|
|
* struct btrfs_bio as we can into this over time.
|
|
*/
|
|
typedef void (btrfs_io_bio_end_io_t) (struct btrfs_io_bio *bio, int err);
|
|
struct btrfs_io_bio {
|
|
unsigned int mirror_num;
|
|
unsigned int stripe_index;
|
|
u64 logical;
|
|
u8 *csum;
|
|
u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
|
|
u8 *csum_allocated;
|
|
btrfs_io_bio_end_io_t *end_io;
|
|
struct bvec_iter iter;
|
|
/*
|
|
* This member must come last, bio_alloc_bioset will allocate enough
|
|
* bytes for entire btrfs_io_bio but relies on bio being last.
|
|
*/
|
|
struct bio bio;
|
|
};
|
|
|
|
static inline struct btrfs_io_bio *btrfs_io_bio(struct bio *bio)
|
|
{
|
|
return container_of(bio, struct btrfs_io_bio, bio);
|
|
}
|
|
|
|
struct btrfs_bio_stripe {
|
|
struct btrfs_device *dev;
|
|
u64 physical;
|
|
u64 length; /* only used for discard mappings */
|
|
};
|
|
|
|
struct btrfs_bio;
|
|
typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
|
|
|
|
struct btrfs_bio {
|
|
refcount_t refs;
|
|
atomic_t stripes_pending;
|
|
struct btrfs_fs_info *fs_info;
|
|
u64 map_type; /* get from map_lookup->type */
|
|
bio_end_io_t *end_io;
|
|
struct bio *orig_bio;
|
|
unsigned long flags;
|
|
void *private;
|
|
atomic_t error;
|
|
int max_errors;
|
|
int num_stripes;
|
|
int mirror_num;
|
|
int num_tgtdevs;
|
|
int *tgtdev_map;
|
|
/*
|
|
* logical block numbers for the start of each stripe
|
|
* The last one or two are p/q. These are sorted,
|
|
* so raid_map[0] is the start of our full stripe
|
|
*/
|
|
u64 *raid_map;
|
|
struct btrfs_bio_stripe stripes[];
|
|
};
|
|
|
|
struct btrfs_device_info {
|
|
struct btrfs_device *dev;
|
|
u64 dev_offset;
|
|
u64 max_avail;
|
|
u64 total_avail;
|
|
};
|
|
|
|
struct btrfs_raid_attr {
|
|
int sub_stripes; /* sub_stripes info for map */
|
|
int dev_stripes; /* stripes per dev */
|
|
int devs_max; /* max devs to use */
|
|
int devs_min; /* min devs needed */
|
|
int tolerated_failures; /* max tolerated fail devs */
|
|
int devs_increment; /* ndevs has to be a multiple of this */
|
|
int ncopies; /* how many copies to data has */
|
|
};
|
|
|
|
extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
|
|
extern const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES];
|
|
extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES];
|
|
|
|
struct map_lookup {
|
|
u64 type;
|
|
int io_align;
|
|
int io_width;
|
|
u64 stripe_len;
|
|
int sector_size;
|
|
int num_stripes;
|
|
int sub_stripes;
|
|
struct btrfs_bio_stripe stripes[];
|
|
};
|
|
|
|
#define map_lookup_size(n) (sizeof(struct map_lookup) + \
|
|
(sizeof(struct btrfs_bio_stripe) * (n)))
|
|
|
|
struct btrfs_balance_args;
|
|
struct btrfs_balance_progress;
|
|
struct btrfs_balance_control {
|
|
struct btrfs_fs_info *fs_info;
|
|
|
|
struct btrfs_balance_args data;
|
|
struct btrfs_balance_args meta;
|
|
struct btrfs_balance_args sys;
|
|
|
|
u64 flags;
|
|
|
|
struct btrfs_balance_progress stat;
|
|
};
|
|
|
|
enum btrfs_map_op {
|
|
BTRFS_MAP_READ,
|
|
BTRFS_MAP_WRITE,
|
|
BTRFS_MAP_DISCARD,
|
|
BTRFS_MAP_GET_READ_MIRRORS,
|
|
};
|
|
|
|
static inline enum btrfs_map_op btrfs_op(struct bio *bio)
|
|
{
|
|
switch (bio_op(bio)) {
|
|
case REQ_OP_DISCARD:
|
|
return BTRFS_MAP_DISCARD;
|
|
case REQ_OP_WRITE:
|
|
return BTRFS_MAP_WRITE;
|
|
default:
|
|
WARN_ON_ONCE(1);
|
|
case REQ_OP_READ:
|
|
return BTRFS_MAP_READ;
|
|
}
|
|
}
|
|
|
|
int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
|
|
u64 end, u64 *length);
|
|
void btrfs_get_bbio(struct btrfs_bio *bbio);
|
|
void btrfs_put_bbio(struct btrfs_bio *bbio);
|
|
int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
|
|
u64 logical, u64 *length,
|
|
struct btrfs_bio **bbio_ret, int mirror_num);
|
|
int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
|
|
u64 logical, u64 *length,
|
|
struct btrfs_bio **bbio_ret);
|
|
int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
|
|
u64 chunk_start, u64 physical, u64 devid,
|
|
u64 **logical, int *naddrs, int *stripe_len);
|
|
int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
|
|
int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
|
|
int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
|
|
struct btrfs_fs_info *fs_info, u64 type);
|
|
void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
|
|
void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
|
|
int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
|
|
int mirror_num, int async_submit);
|
|
int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
|
|
fmode_t flags, void *holder);
|
|
int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
|
|
struct btrfs_fs_devices **fs_devices_ret);
|
|
int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
|
|
void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step);
|
|
void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_device *device, struct btrfs_device *this_dev);
|
|
int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
|
|
const char *device_path,
|
|
struct btrfs_device **device);
|
|
int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
|
|
const char *devpath,
|
|
struct btrfs_device **device);
|
|
struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
|
|
const u64 *devid,
|
|
const u8 *uuid);
|
|
int btrfs_rm_device(struct btrfs_fs_info *fs_info,
|
|
const char *device_path, u64 devid);
|
|
void btrfs_cleanup_fs_uuids(void);
|
|
int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
|
|
int btrfs_grow_device(struct btrfs_trans_handle *trans,
|
|
struct btrfs_device *device, u64 new_size);
|
|
struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
|
|
u8 *uuid, u8 *fsid);
|
|
int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
|
|
int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
|
|
int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
|
|
const char *device_path,
|
|
struct btrfs_device *srcdev,
|
|
struct btrfs_device **device_out);
|
|
int btrfs_balance(struct btrfs_balance_control *bctl,
|
|
struct btrfs_ioctl_balance_args *bargs);
|
|
int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info);
|
|
int btrfs_recover_balance(struct btrfs_fs_info *fs_info);
|
|
int btrfs_pause_balance(struct btrfs_fs_info *fs_info);
|
|
int btrfs_cancel_balance(struct btrfs_fs_info *fs_info);
|
|
int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info);
|
|
int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info);
|
|
int btrfs_chunk_readonly(struct btrfs_fs_info *fs_info, u64 chunk_offset);
|
|
int find_free_dev_extent_start(struct btrfs_transaction *transaction,
|
|
struct btrfs_device *device, u64 num_bytes,
|
|
u64 search_start, u64 *start, u64 *max_avail);
|
|
int find_free_dev_extent(struct btrfs_trans_handle *trans,
|
|
struct btrfs_device *device, u64 num_bytes,
|
|
u64 *start, u64 *max_avail);
|
|
void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index);
|
|
int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_ioctl_get_dev_stats *stats);
|
|
void btrfs_init_devices_late(struct btrfs_fs_info *fs_info);
|
|
int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info);
|
|
int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
|
|
struct btrfs_fs_info *fs_info);
|
|
void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_device *srcdev);
|
|
void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_device *srcdev);
|
|
void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_device *tgtdev);
|
|
void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_device *tgtdev);
|
|
void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path);
|
|
int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
|
|
u64 logical, u64 len, int mirror_num);
|
|
unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_mapping_tree *map_tree,
|
|
u64 logical);
|
|
int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
|
|
struct btrfs_fs_info *fs_info,
|
|
u64 chunk_offset, u64 chunk_size);
|
|
int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
|
|
struct btrfs_fs_info *fs_info, u64 chunk_offset);
|
|
|
|
static inline int btrfs_dev_stats_dirty(struct btrfs_device *dev)
|
|
{
|
|
return atomic_read(&dev->dev_stats_ccnt);
|
|
}
|
|
|
|
static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
|
|
int index)
|
|
{
|
|
atomic_inc(dev->dev_stat_values + index);
|
|
smp_mb__before_atomic();
|
|
atomic_inc(&dev->dev_stats_ccnt);
|
|
}
|
|
|
|
static inline int btrfs_dev_stat_read(struct btrfs_device *dev,
|
|
int index)
|
|
{
|
|
return atomic_read(dev->dev_stat_values + index);
|
|
}
|
|
|
|
static inline int btrfs_dev_stat_read_and_reset(struct btrfs_device *dev,
|
|
int index)
|
|
{
|
|
int ret;
|
|
|
|
ret = atomic_xchg(dev->dev_stat_values + index, 0);
|
|
smp_mb__before_atomic();
|
|
atomic_inc(&dev->dev_stats_ccnt);
|
|
return ret;
|
|
}
|
|
|
|
static inline void btrfs_dev_stat_set(struct btrfs_device *dev,
|
|
int index, unsigned long val)
|
|
{
|
|
atomic_set(dev->dev_stat_values + index, val);
|
|
smp_mb__before_atomic();
|
|
atomic_inc(&dev->dev_stats_ccnt);
|
|
}
|
|
|
|
static inline void btrfs_dev_stat_reset(struct btrfs_device *dev,
|
|
int index)
|
|
{
|
|
btrfs_dev_stat_set(dev, index, 0);
|
|
}
|
|
|
|
void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info);
|
|
void btrfs_update_commit_device_bytes_used(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_transaction *transaction);
|
|
|
|
struct list_head *btrfs_get_fs_uuids(void);
|
|
void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info);
|
|
void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
|
|
|
|
#endif
|