WSL2-Linux-Kernel/fs/btrfs/volumes.h

573 строки
16 KiB
C
Исходник Обычный вид История

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#ifndef BTRFS_VOLUMES_H
#define BTRFS_VOLUMES_H
#include <linux/bio.h>
#include <linux/sort.h>
#include <linux/btrfs.h>
#include "async-thread.h"
#define BTRFS_MAX_DATA_CHUNK_SIZE (10ULL * SZ_1G)
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
#define BTRFS_DEV_STATE_WRITEABLE (0)
#define BTRFS_DEV_STATE_IN_FS_METADATA (1)
#define BTRFS_DEV_STATE_MISSING (2)
#define BTRFS_DEV_STATE_REPLACE_TGT (3)
#define BTRFS_DEV_STATE_FLUSH_SENT (4)
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;
unsigned long dev_state;
blk_status_t 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_ctx;
struct btrfs_work work;
struct rcu_head rcu;
/* readahead state */
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 */
btrfs: Introduce support for FSID change without metadata rewrite This field is going to be used when the user wants to change the UUID of the filesystem without having to rewrite all metadata blocks. This field adds another level of indirection such that when the FSID is changed what really happens is the current UUID (the one with which the fs was created) is copied to the 'metadata_uuid' field in the superblock as well as a new incompat flag is set METADATA_UUID. When the kernel detects this flag is set it knows that the superblock in fact has 2 UUIDs: 1. Is the UUID which is user-visible, currently known as FSID. 2. Metadata UUID - this is the UUID which is stamped into all on-disk datastructures belonging to this file system. When the new incompat flag is present device scanning checks whether both fsid/metadata_uuid of the scanned device match any of the registered filesystems. When the flag is not set then both UUIDs are equal and only the FSID is retained on disk, metadata_uuid is set only in-memory during mount. Additionally a new metadata_uuid field is also added to the fs_info struct. It's initialised either with the FSID in case METADATA_UUID incompat flag is not set or with the metdata_uuid of the superblock otherwise. This commit introduces the new fields as well as the new incompat flag and switches all users of the fsid to the new logic. Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> [ minor updates in comments ] Signed-off-by: David Sterba <dsterba@suse.com>
2018-10-30 17:43:23 +03:00
u8 metadata_uuid[BTRFS_FSID_SIZE];
bool fsid_change;
struct list_head fs_list;
u64 num_devices;
u64 open_devices;
u64 rw_devices;
u64 missing_devices;
u64 total_rw_bytes;
u64 total_devices;
/* Highest generation number of seen devices */
u64 latest_generation;
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 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.
*/
struct btrfs_io_bio {
unsigned int mirror_num;
unsigned int stripe_index;
u64 logical;
u8 *csum;
u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
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);
}
static inline void btrfs_io_bio_free_csum(struct btrfs_io_bio *io_bio)
{
if (io_bio->csum != io_bio->csum_inline) {
kfree(io_bio->csum);
io_bio->csum = NULL;
}
}
struct btrfs_bio_stripe {
struct btrfs_device *dev;
u64 physical;
u64 length; /* only used for discard mappings */
};
struct btrfs_bio {
refcount_t refs;
atomic_t stripes_pending;
Btrfs: fix use-after-free in the finishing procedure of the device replace During device replace test, we hit a null pointer deference (It was very easy to reproduce it by running xfstests' btrfs/011 on the devices with the virtio scsi driver). There were two bugs that caused this problem: - We might allocate new chunks on the replaced device after we updated the mapping tree. And we forgot to replace the source device in those mapping of the new chunks. - We might get the mapping information which including the source device before the mapping information update. And then submit the bio which was based on that mapping information after we freed the source device. For the first bug, we can fix it by doing mapping tree update and source device remove in the same context of the chunk mutex. The chunk mutex is used to protect the allocable device list, the above method can avoid the new chunk allocation, and after we remove the source device, all the new chunks will be allocated on the new device. So it can fix the first bug. For the second bug, we need make sure all flighting bios are finished and no new bios are produced during we are removing the source device. To fix this problem, we introduced a global @bio_counter, we not only inc/dec @bio_counter outsize of map_blocks, but also inc it before submitting bio and dec @bio_counter when ending bios. Since Raid56 is a little different and device replace dosen't support raid56 yet, it is not addressed in the patch and I add comments to make sure we will fix it in the future. Reported-by: Qu Wenruo <quwenruo@cn.fujitsu.com> Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com> Signed-off-by: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Josef Bacik <jbacik@fb.com>
2014-01-30 12:46:55 +04:00
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 */
int nparity; /* number of stripes worth of bytes to store
* parity information */
int mindev_error; /* error code if min devs requisite is unmet */
const char raid_name[8]; /* name of the raid */
u64 bg_flag; /* block group flag of the raid */
};
extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
Btrfs: add initial tracepoint support for btrfs Tracepoints can provide insight into why btrfs hits bugs and be greatly helpful for debugging, e.g dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0 dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0 btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0) btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0) btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8 flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0) flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0) flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0) Here is what I have added: 1) ordere_extent: btrfs_ordered_extent_add btrfs_ordered_extent_remove btrfs_ordered_extent_start btrfs_ordered_extent_put These provide critical information to understand how ordered_extents are updated. 2) extent_map: btrfs_get_extent extent_map is used in both read and write cases, and it is useful for tracking how btrfs specific IO is running. 3) writepage: __extent_writepage btrfs_writepage_end_io_hook Pages are cirtical resourses and produce a lot of corner cases during writeback, so it is valuable to know how page is written to disk. 4) inode: btrfs_inode_new btrfs_inode_request btrfs_inode_evict These can show where and when a inode is created, when a inode is evicted. 5) sync: btrfs_sync_file btrfs_sync_fs These show sync arguments. 6) transaction: btrfs_transaction_commit In transaction based filesystem, it will be useful to know the generation and who does commit. 7) back reference and cow: btrfs_delayed_tree_ref btrfs_delayed_data_ref btrfs_delayed_ref_head btrfs_cow_block Btrfs natively supports back references, these tracepoints are helpful on understanding btrfs's COW mechanism. 8) chunk: btrfs_chunk_alloc btrfs_chunk_free Chunk is a link between physical offset and logical offset, and stands for space infomation in btrfs, and these are helpful on tracing space things. 9) reserved_extent: btrfs_reserved_extent_alloc btrfs_reserved_extent_free These can show how btrfs uses its space. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 14:18:59 +03:00
struct map_lookup {
u64 type;
int io_align;
int io_width;
u64 stripe_len;
Btrfs: add initial tracepoint support for btrfs Tracepoints can provide insight into why btrfs hits bugs and be greatly helpful for debugging, e.g dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0 dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0 btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0) btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0) btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8 flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0) flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0) flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0) Here is what I have added: 1) ordere_extent: btrfs_ordered_extent_add btrfs_ordered_extent_remove btrfs_ordered_extent_start btrfs_ordered_extent_put These provide critical information to understand how ordered_extents are updated. 2) extent_map: btrfs_get_extent extent_map is used in both read and write cases, and it is useful for tracking how btrfs specific IO is running. 3) writepage: __extent_writepage btrfs_writepage_end_io_hook Pages are cirtical resourses and produce a lot of corner cases during writeback, so it is valuable to know how page is written to disk. 4) inode: btrfs_inode_new btrfs_inode_request btrfs_inode_evict These can show where and when a inode is created, when a inode is evicted. 5) sync: btrfs_sync_file btrfs_sync_fs These show sync arguments. 6) transaction: btrfs_transaction_commit In transaction based filesystem, it will be useful to know the generation and who does commit. 7) back reference and cow: btrfs_delayed_tree_ref btrfs_delayed_data_ref btrfs_delayed_ref_head btrfs_cow_block Btrfs natively supports back references, these tracepoints are helpful on understanding btrfs's COW mechanism. 8) chunk: btrfs_chunk_alloc btrfs_chunk_free Chunk is a link between physical offset and logical offset, and stands for space infomation in btrfs, and these are helpful on tracing space things. 9) reserved_extent: btrfs_reserved_extent_alloc btrfs_reserved_extent_free These can show how btrfs uses its space. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 14:18:59 +03:00
int num_stripes;
int sub_stripes;
int verified_stripes; /* For mount time dev extent verification */
Btrfs: add initial tracepoint support for btrfs Tracepoints can provide insight into why btrfs hits bugs and be greatly helpful for debugging, e.g dd-7822 [000] 2121.641088: btrfs_inode_request: root = 5(FS_TREE), gen = 4, ino = 256, blocks = 8, disk_i_size = 0, last_trans = 8, logged_trans = 0 dd-7822 [000] 2121.641100: btrfs_inode_new: root = 5(FS_TREE), gen = 8, ino = 257, blocks = 0, disk_i_size = 0, last_trans = 0, logged_trans = 0 btrfs-transacti-7804 [001] 2146.935420: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29368320 (orig_level = 0), cow_buf = 29388800 (cow_level = 0) btrfs-transacti-7804 [001] 2146.935473: btrfs_cow_block: root = 1(ROOT_TREE), refs = 2, orig_buf = 29364224 (orig_level = 0), cow_buf = 29392896 (cow_level = 0) btrfs-transacti-7804 [001] 2146.972221: btrfs_transaction_commit: root = 1(ROOT_TREE), gen = 8 flush-btrfs-2-7821 [001] 2155.824210: btrfs_chunk_alloc: root = 3(CHUNK_TREE), offset = 1103101952, size = 1073741824, num_stripes = 1, sub_stripes = 0, type = DATA flush-btrfs-2-7821 [001] 2155.824241: btrfs_cow_block: root = 2(EXTENT_TREE), refs = 2, orig_buf = 29388800 (orig_level = 0), cow_buf = 29396992 (cow_level = 0) flush-btrfs-2-7821 [001] 2155.824255: btrfs_cow_block: root = 4(DEV_TREE), refs = 2, orig_buf = 29372416 (orig_level = 0), cow_buf = 29401088 (cow_level = 0) flush-btrfs-2-7821 [000] 2155.824329: btrfs_cow_block: root = 3(CHUNK_TREE), refs = 2, orig_buf = 20971520 (orig_level = 0), cow_buf = 20975616 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898019: btrfs_cow_block: root = 5(FS_TREE), refs = 2, orig_buf = 29384704 (orig_level = 0), cow_buf = 29405184 (cow_level = 0) btrfs-endio-wri-7800 [001] 2155.898043: btrfs_cow_block: root = 7(CSUM_TREE), refs = 2, orig_buf = 29376512 (orig_level = 0), cow_buf = 29409280 (cow_level = 0) Here is what I have added: 1) ordere_extent: btrfs_ordered_extent_add btrfs_ordered_extent_remove btrfs_ordered_extent_start btrfs_ordered_extent_put These provide critical information to understand how ordered_extents are updated. 2) extent_map: btrfs_get_extent extent_map is used in both read and write cases, and it is useful for tracking how btrfs specific IO is running. 3) writepage: __extent_writepage btrfs_writepage_end_io_hook Pages are cirtical resourses and produce a lot of corner cases during writeback, so it is valuable to know how page is written to disk. 4) inode: btrfs_inode_new btrfs_inode_request btrfs_inode_evict These can show where and when a inode is created, when a inode is evicted. 5) sync: btrfs_sync_file btrfs_sync_fs These show sync arguments. 6) transaction: btrfs_transaction_commit In transaction based filesystem, it will be useful to know the generation and who does commit. 7) back reference and cow: btrfs_delayed_tree_ref btrfs_delayed_data_ref btrfs_delayed_ref_head btrfs_cow_block Btrfs natively supports back references, these tracepoints are helpful on understanding btrfs's COW mechanism. 8) chunk: btrfs_chunk_alloc btrfs_chunk_free Chunk is a link between physical offset and logical offset, and stands for space infomation in btrfs, and these are helpful on tracing space things. 9) reserved_extent: btrfs_reserved_extent_alloc btrfs_reserved_extent_free These can show how btrfs uses its space. Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-03-24 14:18:59 +03:00
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_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;
}
}
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 **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, u64 type);
void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
blk_status_t 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);
struct btrfs_device *btrfs_scan_one_device(const char *path,
fmode_t flags, void *holder);
int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step);
void btrfs_assign_next_active_device(struct btrfs_device *device,
struct btrfs_device *this_dev);
struct btrfs_device *btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info,
u64 devid,
const char *devpath);
struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
const u64 *devid,
const u8 *uuid);
void btrfs_free_device(struct btrfs_device *device);
int btrfs_rm_device(struct btrfs_fs_info *fs_info,
const char *device_path, u64 devid);
void __exit 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_balance(struct btrfs_fs_info *fs_info,
struct btrfs_balance_control *bctl,
struct btrfs_ioctl_balance_args *bargs);
void btrfs_describe_block_groups(u64 flags, char *buf, u32 size_buf);
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);
2015-06-15 16:41:17 +03:00
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_device *srcdev);
btrfs: Fix a lockdep warning when running xfstest. The following lockdep warning is triggered during xfstests: [ 1702.980872] ========================================================= [ 1702.981181] [ INFO: possible irq lock inversion dependency detected ] [ 1702.981482] 3.18.0-rc1 #27 Not tainted [ 1702.981781] --------------------------------------------------------- [ 1702.982095] kswapd0/77 just changed the state of lock: [ 1702.982415] (&delayed_node->mutex){+.+.-.}, at: [<ffffffffa03b0b51>] __btrfs_release_delayed_node+0x41/0x1f0 [btrfs] [ 1702.982794] but this lock took another, RECLAIM_FS-unsafe lock in the past: [ 1702.983160] (&fs_info->dev_replace.lock){+.+.+.} and interrupts could create inverse lock ordering between them. [ 1702.984675] other info that might help us debug this: [ 1702.985524] Chain exists of: &delayed_node->mutex --> &found->groups_sem --> &fs_info->dev_replace.lock [ 1702.986799] Possible interrupt unsafe locking scenario: [ 1702.987681] CPU0 CPU1 [ 1702.988137] ---- ---- [ 1702.988598] lock(&fs_info->dev_replace.lock); [ 1702.989069] local_irq_disable(); [ 1702.989534] lock(&delayed_node->mutex); [ 1702.990038] lock(&found->groups_sem); [ 1702.990494] <Interrupt> [ 1702.990938] lock(&delayed_node->mutex); [ 1702.991407] *** DEADLOCK *** It is because the btrfs_kobj_{add/rm}_device() will call memory allocation with GFP_KERNEL, which may flush fs page cache to free space, waiting for it self to do the commit, causing the deadlock. To solve the problem, move btrfs_kobj_{add/rm}_device() out of the dev_replace lock range, also involing split the btrfs_rm_dev_replace_srcdev() function into remove and free parts. Now only btrfs_rm_dev_replace_remove_srcdev() is called in dev_replace lock range, and kobj_{add/rm} and btrfs_rm_dev_replace_free_srcdev() are called out of the lock range. Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com> Signed-off-by: Chris Mason <clm@fb.com>
2014-10-30 11:52:31 +03:00
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_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);
unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
u64 logical);
int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
u64 chunk_offset, u64 chunk_size);
int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
u64 logical, u64 length);
static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
int index)
{
atomic_inc(dev->dev_stat_values + index);
/*
* This memory barrier orders stores updating statistics before stores
* updating dev_stats_ccnt.
*
* It pairs with smp_rmb() in btrfs_run_dev_stats().
*/
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);
/*
* atomic_xchg implies a full memory barriers as per atomic_t.txt:
* - RMW operations that have a return value are fully ordered;
*
* This implicit memory barriers is paired with the smp_rmb in
* btrfs_run_dev_stats
*/
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);
/*
* This memory barrier orders stores updating statistics before stores
* updating dev_stats_ccnt.
*
* It pairs with smp_rmb() in btrfs_run_dev_stats().
*/
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);
}
/*
* Convert block group flags (BTRFS_BLOCK_GROUP_*) to btrfs_raid_types, which
* can be used as index to access btrfs_raid_array[].
*/
static inline enum btrfs_raid_types btrfs_bg_flags_to_raid_index(u64 flags)
{
if (flags & BTRFS_BLOCK_GROUP_RAID10)
return BTRFS_RAID_RAID10;
else if (flags & BTRFS_BLOCK_GROUP_RAID1)
return BTRFS_RAID_RAID1;
else if (flags & BTRFS_BLOCK_GROUP_DUP)
return BTRFS_RAID_DUP;
else if (flags & BTRFS_BLOCK_GROUP_RAID0)
return BTRFS_RAID_RAID0;
else if (flags & BTRFS_BLOCK_GROUP_RAID5)
return BTRFS_RAID_RAID5;
else if (flags & BTRFS_BLOCK_GROUP_RAID6)
return BTRFS_RAID_RAID6;
return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
}
const char *get_raid_name(enum btrfs_raid_types type);
void btrfs_update_commit_device_size(struct btrfs_fs_info *fs_info);
void btrfs_update_commit_device_bytes_used(struct btrfs_transaction *trans);
Btrfs: fix race between fs trimming and block group remove/allocation Our fs trim operation, which is completely transactionless (doesn't start or joins an existing transaction) consists of visiting all block groups and then for each one to iterate its free space entries and perform a discard operation against the space range represented by the free space entries. However before performing a discard, the corresponding free space entry is removed from the free space rbtree, and when the discard completes it is added back to the free space rbtree. If a block group remove operation happens while the discard is ongoing (or before it starts and after a free space entry is hidden), we end up not waiting for the discard to complete, remove the extent map that maps logical address to physical addresses and the corresponding chunk metadata from the the chunk and device trees. After that and before the discard completes, the current running transaction can finish and a new one start, allowing for new block groups that map to the same physical addresses to be allocated and written to. So fix this by keeping the extent map in memory until the discard completes so that the same physical addresses aren't reused before it completes. If the physical locations that are under a discard operation end up being used for a new metadata block group for example, and dirty metadata extents are written before the discard finishes (the VM might call writepages() of our btree inode's i_mapping for example, or an fsync log commit happens) we end up overwriting metadata with zeroes, which leads to errors from fsck like the following: checking extents Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 read block failed check_tree_block owner ref check failed [833912832 16384] Errors found in extent allocation tree or chunk allocation checking free space cache checking fs roots Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 Check tree block failed, want=833912832, have=0 read block failed check_tree_block root 5 root dir 256 error root 5 inode 260 errors 2001, no inode item, link count wrong unresolved ref dir 256 index 0 namelen 8 name foobar_3 filetype 1 errors 6, no dir index, no inode ref root 5 inode 262 errors 2001, no inode item, link count wrong unresolved ref dir 256 index 0 namelen 8 name foobar_5 filetype 1 errors 6, no dir index, no inode ref root 5 inode 263 errors 2001, no inode item, link count wrong (...) Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2014-11-28 00:14:15 +03:00
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);
bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
struct btrfs_device *failing_dev);
btrfs: Introduce a function to check if all chunks a OK for degraded rw mount Introduce a new function, btrfs_check_rw_degradable(), to check if all chunks in btrfs is OK for degraded rw mount. It provides the new basis for accurate btrfs mount/remount and even runtime degraded mount check other than old one-size-fit-all method. Btrfs currently uses num_tolerated_disk_barrier_failures to do global check for tolerated missing device. Although the one-size-fit-all solution is quite safe, it's too strict if data and metadata has different duplication level. For example, if one use Single data and RAID1 metadata for 2 disks, it means any missing device will make the fs unable to be degraded mounted. But in fact, some times all single chunks may be in the existing device and in that case, we should allow it to be rw degraded mounted. Such case can be easily reproduced using the following script: # mkfs.btrfs -f -m raid1 -d sing /dev/sdb /dev/sdc # wipefs -f /dev/sdc # mount /dev/sdb -o degraded,rw If using btrfs-debug-tree to check /dev/sdb, one should find that the data chunk is only in sdb, so in fact it should allow degraded mount. This patchset will introduce a new per-chunk degradable check for btrfs, allow above case to succeed, and it's quite small anyway. Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com> Signed-off-by: Anand Jain <anand.jain@oracle.com> Reviewed-by: David Sterba <dsterba@suse.com> [ copied text from cover letter with more details about the problem being solved ] Signed-off-by: David Sterba <dsterba@suse.com>
2017-03-09 04:34:36 +03:00
int btrfs_bg_type_to_factor(u64 flags);
int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info);
#endif