--- zzzz-none-000/linux-3.10.107/fs/btrfs/volumes.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/fs/btrfs/volumes.h 2021-02-04 17:41:59.000000000 +0000 @@ -24,6 +24,8 @@ #include #include "async-thread.h" +extern struct mutex uuid_mutex; + #define BTRFS_STRIPE_LEN (64 * 1024) struct buffer_head; @@ -32,19 +34,41 @@ 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 +#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_root *dev_root; + struct rcu_string *name; + + u64 generation; + + spinlock_t io_lock ____cacheline_aligned; + int running_pending; /* regular prio bios */ struct btrfs_pending_bios pending_bios; /* WRITE_SYNC bios */ struct btrfs_pending_bios pending_sync_bios; - int running_pending; - u64 generation; + struct block_device *bdev; + + /* the mode sent to blkdev_get */ + fmode_t mode; int writeable; int in_fs_metadata; @@ -52,22 +76,17 @@ int can_discard; int is_tgtdev_for_dev_replace; - spinlock_t io_lock; - - struct block_device *bdev; - - /* the mode sent to blkdev_get */ - fmode_t mode; - - struct rcu_string *name; +#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED + seqcount_t data_seqcount; +#endif /* the internal btrfs device id */ u64 devid; - /* size of the device */ + /* size of the device in memory */ u64 total_bytes; - /* size of the disk */ + /* size of the device on disk */ u64 disk_total_bytes; /* bytes used */ @@ -78,16 +97,37 @@ /* 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; - /* type and info about this device */ - u64 type; - /* 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 */ + int nobarriers; + struct bio *flush_bio; + struct completion flush_wait; + /* per-device scrub information */ struct scrub_ctx *scrub_device; @@ -103,40 +143,103 @@ struct radix_tree_root reada_zones; struct radix_tree_root reada_extents; - /* for sending down flush barriers */ - struct bio *flush_bio; - struct completion flush_wait; - int nobarriers; - /* disk I/O failure stats. For detailed description refer to * enum btrfs_dev_stat_values in ioctl.h */ int dev_stats_valid; - int dev_stats_dirty; /* counters need to be written to disk */ + + /* 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 */ - /* the device with this id has the most recent copy of the super */ - u64 latest_devid; - u64 latest_trans; u64 num_devices; u64 open_devices; u64 rw_devices; u64 missing_devices; u64 total_rw_bytes; - u64 num_can_discard; 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 + * 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; @@ -150,8 +253,16 @@ * 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). @@ -161,9 +272,15 @@ * 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 long mirror_num; - unsigned long stripe_index; + 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 bio bio; }; @@ -182,14 +299,26 @@ typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err); struct btrfs_bio { + atomic_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[]; }; @@ -205,10 +334,15 @@ 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 u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES]; + struct map_lookup { u64 type; int io_align; @@ -245,6 +379,21 @@ #define BTRFS_BALANCE_ARGS_DEVID (1ULL << 2) #define BTRFS_BALANCE_ARGS_DRANGE (1ULL << 3) #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) +#define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) +#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7) +#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 10) + +#define BTRFS_BALANCE_ARGS_MASK \ + (BTRFS_BALANCE_ARGS_PROFILES | \ + BTRFS_BALANCE_ARGS_USAGE | \ + BTRFS_BALANCE_ARGS_DEVID | \ + BTRFS_BALANCE_ARGS_DRANGE | \ + BTRFS_BALANCE_ARGS_VRANGE | \ + BTRFS_BALANCE_ARGS_LIMIT | \ + BTRFS_BALANCE_ARGS_LIMIT_RANGE | \ + BTRFS_BALANCE_ARGS_STRIPES_RANGE | \ + BTRFS_BALANCE_ARGS_USAGE_RANGE) /* * Profile changing flags. When SOFT is set we won't relocate chunk if @@ -270,13 +419,15 @@ int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start, u64 end, u64 *length); - -#define btrfs_bio_size(n) (sizeof(struct btrfs_bio) + \ - (sizeof(struct btrfs_bio_stripe) * (n))) - +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, int rw, u64 logical, u64 *length, struct btrfs_bio **bbio_ret, int mirror_num); +int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int rw, + u64 logical, u64 *length, + struct btrfs_bio **bbio_ret, int mirror_num, + int need_raid_map); int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, u64 chunk_start, u64 physical, u64 devid, u64 **logical, int *naddrs, int *stripe_len); @@ -293,11 +444,13 @@ 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_info *fs_info, - struct btrfs_fs_devices *fs_devices, int step); +void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step); int btrfs_find_device_missing_or_by_path(struct btrfs_root *root, char *device_path, 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_root *root, char *device_path); void btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); @@ -308,6 +461,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_init_dev_replace_tgtdev(struct btrfs_root *root, 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); @@ -315,32 +469,53 @@ 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_root *root, u64 chunk_offset); -int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, +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_root *root, 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_srcdev(struct btrfs_fs_info *fs_info, - struct btrfs_device *srcdev); +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); -int btrfs_scratch_superblock(struct btrfs_device *device); +void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path); int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree, u64 logical, u64 len, int mirror_num); unsigned long btrfs_full_stripe_len(struct btrfs_root *root, struct btrfs_mapping_tree *map_tree, u64 logical); +int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, + struct btrfs_root *extent_root, + u64 chunk_offset, u64 chunk_size); +int btrfs_remove_chunk(struct btrfs_trans_handle *trans, + struct btrfs_root *root, 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); - dev->dev_stats_dirty = 1; + smp_mb__before_atomic(); + atomic_inc(&dev->dev_stats_ccnt); } static inline int btrfs_dev_stat_read(struct btrfs_device *dev, @@ -355,7 +530,8 @@ int ret; ret = atomic_xchg(dev->dev_stat_values + index, 0); - dev->dev_stats_dirty = 1; + smp_mb__before_atomic(); + atomic_inc(&dev->dev_stats_ccnt); return ret; } @@ -363,7 +539,8 @@ int index, unsigned long val) { atomic_set(dev->dev_stat_values + index, val); - dev->dev_stats_dirty = 1; + smp_mb__before_atomic(); + atomic_inc(&dev->dev_stats_ccnt); } static inline void btrfs_dev_stat_reset(struct btrfs_device *dev, @@ -371,4 +548,24 @@ { 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_root *root, + struct btrfs_transaction *transaction); + +static inline void lock_chunks(struct btrfs_root *root) +{ + mutex_lock(&root->fs_info->chunk_mutex); +} + +static inline void unlock_chunks(struct btrfs_root *root) +{ + mutex_unlock(&root->fs_info->chunk_mutex); +} + +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); +void btrfs_close_one_device(struct btrfs_device *device); + #endif