#include <linux/mutex.h>
#include <linux/percpu-refcount.h>
#include <linux/percpu-rwsem.h>
+#include <linux/refcount.h>
#include <linux/rhashtable.h>
#include <linux/rwsem.h>
#include <linux/semaphore.h>
#include "fifo.h"
#include "nocow_locking_types.h"
#include "opts.h"
+#include "recovery_types.h"
+#include "sb-errors_types.h"
+#include "seqmutex.h"
#include "util.h"
#ifdef CONFIG_BCACHEFS_DEBUG
#define BCH_WRITE_REF_DEBUG
#endif
+#ifndef dynamic_fault
#define dynamic_fault(...) 0
-#define race_fault(...) 0
+#endif
+
+#define race_fault(...) dynamic_fault("bcachefs:race")
+
+#define count_event(_c, _name) this_cpu_inc((_c)->counters[BCH_COUNTER_##_name])
#define trace_and_count(_c, _name, ...) \
do { \
- this_cpu_inc((_c)->counters[BCH_COUNTER_##_name]); \
+ count_event(_c, _name); \
trace_##_name(__VA_ARGS__); \
} while (0)
#define bch2_fmt(_c, fmt) bch2_log_msg(_c, fmt "\n")
+__printf(2, 3)
+void __bch2_print(struct bch_fs *c, const char *fmt, ...);
+
+#define maybe_dev_to_fs(_c) _Generic((_c), \
+ struct bch_dev *: ((struct bch_dev *) (_c))->fs, \
+ struct bch_fs *: (_c))
+
+#define bch2_print(_c, ...) __bch2_print(maybe_dev_to_fs(_c), __VA_ARGS__)
+
+#define bch2_print_ratelimited(_c, ...) \
+do { \
+ static DEFINE_RATELIMIT_STATE(_rs, \
+ DEFAULT_RATELIMIT_INTERVAL, \
+ DEFAULT_RATELIMIT_BURST); \
+ \
+ if (__ratelimit(&_rs)) \
+ bch2_print(_c, __VA_ARGS__); \
+} while (0)
+
#define bch_info(c, fmt, ...) \
- printk(KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_notice(c, fmt, ...) \
- printk(KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_warn(c, fmt, ...) \
- printk(KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_warn_ratelimited(c, fmt, ...) \
- printk_ratelimited(KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
+ bch2_print_ratelimited(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_err(c, fmt, ...) \
- printk(KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_err_dev(ca, fmt, ...) \
- printk(KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
#define bch_err_dev_offset(ca, _offset, fmt, ...) \
- printk(KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
#define bch_err_inum(c, _inum, fmt, ...) \
- printk(KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
#define bch_err_inum_offset(c, _inum, _offset, fmt, ...) \
- printk(KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
+ bch2_print(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
#define bch_err_ratelimited(c, fmt, ...) \
- printk_ratelimited(KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
+ bch2_print_ratelimited(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__)
#define bch_err_dev_ratelimited(ca, fmt, ...) \
- printk_ratelimited(KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
+ bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__)
#define bch_err_dev_offset_ratelimited(ca, _offset, fmt, ...) \
- printk_ratelimited(KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
+ bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__)
#define bch_err_inum_ratelimited(c, _inum, fmt, ...) \
- printk_ratelimited(KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
+ bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__)
#define bch_err_inum_offset_ratelimited(c, _inum, _offset, fmt, ...) \
- printk_ratelimited(KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
+ bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__)
+
+static inline bool should_print_err(int err)
+{
+ return err && !bch2_err_matches(err, BCH_ERR_transaction_restart);
+}
+
+#define bch_err_fn(_c, _ret) \
+do { \
+ if (should_print_err(_ret)) \
+ bch_err(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\
+} while (0)
+
+#define bch_err_fn_ratelimited(_c, _ret) \
+do { \
+ if (should_print_err(_ret)) \
+ bch_err_ratelimited(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\
+} while (0)
+
+#define bch_err_msg(_c, _ret, _msg, ...) \
+do { \
+ if (should_print_err(_ret)) \
+ bch_err(_c, "%s(): error " _msg " %s", __func__, \
+ ##__VA_ARGS__, bch2_err_str(_ret)); \
+} while (0)
#define bch_verbose(c, fmt, ...) \
do { \
#undef BCH_DEBUG_PARAM
#ifndef CONFIG_BCACHEFS_DEBUG
-#define BCH_DEBUG_PARAM(name, description) static const bool bch2_##name;
+#define BCH_DEBUG_PARAM(name, description) static const __maybe_unused bool bch2_##name;
BCH_DEBUG_PARAMS_DEBUG()
#undef BCH_DEBUG_PARAM
#endif
x(btree_node_merge) \
x(btree_node_sort) \
x(btree_node_read) \
+ x(btree_node_read_done) \
x(btree_interior_update_foreground) \
x(btree_interior_update_total) \
x(btree_gc) \
x(journal_flush_write) \
x(journal_noflush_write) \
x(journal_flush_seq) \
- x(blocked_journal) \
+ x(blocked_journal_low_on_space) \
+ x(blocked_journal_low_on_pin) \
+ x(blocked_journal_max_in_flight) \
x(blocked_allocate) \
x(blocked_allocate_open_bucket) \
+ x(blocked_write_buffer_full) \
x(nocow_lock_contended)
enum bch_time_stats {
#include "buckets_types.h"
#include "buckets_waiting_for_journal_types.h"
#include "clock_types.h"
+#include "disk_groups_types.h"
#include "ec_types.h"
#include "journal_types.h"
#include "keylist_types.h"
#include "replicas_types.h"
#include "subvolume_types.h"
#include "super_types.h"
+#include "thread_with_file_types.h"
/* Number of nodes btree coalesce will try to coalesce at once */
#define GC_MERGE_NODES 4U
GC_PHASE_BTREE_need_discard,
GC_PHASE_BTREE_backpointers,
GC_PHASE_BTREE_bucket_gens,
+ GC_PHASE_BTREE_snapshot_trees,
+ GC_PHASE_BTREE_deleted_inodes,
+ GC_PHASE_BTREE_logged_ops,
+ GC_PHASE_BTREE_rebalance_work,
GC_PHASE_PENDING_DELETE,
};
* Committed by bch2_write_super() -> bch_fs_mi_update()
*/
struct bch_member_cpu mi;
- uuid_le uuid;
+ atomic64_t errors[BCH_MEMBER_ERROR_NR];
+
+ __uuid_t uuid;
char name[BDEVNAME_SIZE];
struct bch_sb_handle disk_sb;
unsigned nr_open_buckets;
unsigned nr_btree_reserve;
- open_bucket_idx_t open_buckets_partial[OPEN_BUCKETS_COUNT];
- open_bucket_idx_t open_buckets_partial_nr;
-
size_t inc_gen_needs_gc;
size_t inc_gen_really_needs_gc;
size_t buckets_waiting_on_journal;
struct io_count __percpu *io_done;
};
-enum {
- /* startup: */
- BCH_FS_STARTED,
- BCH_FS_MAY_GO_RW,
- BCH_FS_RW,
- BCH_FS_WAS_RW,
-
- /* shutdown: */
- BCH_FS_STOPPING,
- BCH_FS_EMERGENCY_RO,
- BCH_FS_GOING_RO,
- BCH_FS_WRITE_DISABLE_COMPLETE,
- BCH_FS_CLEAN_SHUTDOWN,
-
- /* fsck passes: */
- BCH_FS_TOPOLOGY_REPAIR_DONE,
- BCH_FS_INITIAL_GC_DONE, /* kill when we enumerate fsck passes */
- BCH_FS_CHECK_ALLOC_DONE,
- BCH_FS_CHECK_LRUS_DONE,
- BCH_FS_CHECK_BACKPOINTERS_DONE,
- BCH_FS_CHECK_ALLOC_TO_LRU_REFS_DONE,
- BCH_FS_FSCK_DONE,
- BCH_FS_INITIAL_GC_UNFIXED, /* kill when we enumerate fsck errors */
- BCH_FS_NEED_ANOTHER_GC,
-
- BCH_FS_HAVE_DELETED_SNAPSHOTS,
-
- /* errors: */
- BCH_FS_ERROR,
- BCH_FS_TOPOLOGY_ERROR,
- BCH_FS_ERRORS_FIXED,
- BCH_FS_ERRORS_NOT_FIXED,
+/*
+ * initial_gc_unfixed
+ * error
+ * topology error
+ */
+
+#define BCH_FS_FLAGS() \
+ x(started) \
+ x(may_go_rw) \
+ x(rw) \
+ x(was_rw) \
+ x(stopping) \
+ x(emergency_ro) \
+ x(going_ro) \
+ x(write_disable_complete) \
+ x(clean_shutdown) \
+ x(fsck_running) \
+ x(initial_gc_unfixed) \
+ x(need_another_gc) \
+ x(need_delete_dead_snapshots) \
+ x(error) \
+ x(topology_error) \
+ x(errors_fixed) \
+ x(errors_not_fixed)
+
+enum bch_fs_flags {
+#define x(n) BCH_FS_##n,
+ BCH_FS_FLAGS()
+#undef x
};
struct btree_debug {
#define BCH_TRANSACTIONS_NR 128
struct btree_transaction_stats {
+ struct bch2_time_stats duration;
struct bch2_time_stats lock_hold_times;
struct mutex lock;
unsigned nr_max_paths;
- unsigned wb_updates_size;
+ unsigned journal_entries_size;
unsigned max_mem;
char *max_paths_text;
};
u64 start;
u64 end;
bool dirty;
- } entries[0];
+ } entries[];
};
struct journal_keys {
size_t gap;
size_t nr;
size_t size;
+ atomic_t ref;
+ bool initial_ref_held;
};
-struct btree_path_buf {
- struct btree_path *path;
+struct btree_trans_buf {
+ struct btree_trans *trans;
};
#define REPLICAS_DELTA_LIST_MAX (1U << 16)
-struct snapshot_t {
- u32 parent;
- u32 children[2];
- u32 subvol; /* Nonzero only if a subvolume points to this node: */
- u32 equiv;
-};
-
-typedef struct {
- u32 subvol;
- u64 inum;
-} subvol_inum;
-
#define BCACHEFS_ROOT_SUBVOL_INUM \
((subvol_inum) { BCACHEFS_ROOT_SUBVOL, BCACHEFS_ROOT_INO })
x(fallocate) \
x(discard) \
x(invalidate) \
- x(move) \
x(delete_dead_snapshots) \
x(snapshot_delete_pagecache) \
- x(sysfs)
+ x(sysfs) \
+ x(btree_write_buffer)
enum bch_write_ref {
#define x(n) BCH_WRITE_REF_##n,
struct super_block *vfs_sb;
dev_t dev;
char name[40];
+ struct stdio_redirect *stdio;
+ struct task_struct *stdio_filter;
/* ro/rw, add/remove/resize devices: */
struct rw_semaphore state_lock;
#else
struct percpu_ref writes;
#endif
+ /*
+ * Analagous to c->writes, for asynchronous ops that don't necessarily
+ * need fs to be read-write
+ */
+ refcount_t ro_ref;
+ wait_queue_head_t ro_ref_wait;
+
struct work_struct read_only_work;
struct bch_dev __rcu *devs[BCH_SB_MEMBERS_MAX];
/* Updated by bch2_sb_update():*/
struct {
- uuid_le uuid;
- uuid_le user_uuid;
+ __uuid_t uuid;
+ __uuid_t user_uuid;
u16 version;
u16 version_min;
+ u16 version_upgrade_complete;
u8 nr_devices;
u8 clean;
unsigned nsec_per_time_unit;
u64 features;
u64 compat;
+ unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)];
} sb;
struct mutex sb_lock;
/* snapshot.c: */
- GENRADIX(struct snapshot_t) snapshots;
- struct bch_snapshot_table __rcu *snapshot_table;
+ struct snapshot_table __rcu *snapshots;
+ size_t snapshot_table_size;
struct mutex snapshot_table_lock;
+ struct rw_semaphore snapshot_create_lock;
+
struct work_struct snapshot_delete_work;
struct work_struct snapshot_wait_for_pagecache_and_delete_work;
snapshot_id_list snapshots_unlinked;
struct bio_set btree_bio;
struct workqueue_struct *io_complete_wq;
- struct btree_root btree_roots[BTREE_ID_NR];
+ struct btree_root btree_roots_known[BTREE_ID_NR];
+ DARRAY(struct btree_root) btree_roots_extra;
struct mutex btree_root_lock;
struct btree_cache btree_cache;
} btree_write_stats[BTREE_WRITE_TYPE_NR];
/* btree_iter.c: */
- struct mutex btree_trans_lock;
+ struct seqmutex btree_trans_lock;
struct list_head btree_trans_list;
- mempool_t btree_paths_pool;
+ mempool_t btree_trans_pool;
mempool_t btree_trans_mem_pool;
- struct btree_path_buf __percpu *btree_paths_bufs;
+ struct btree_trans_buf __percpu *btree_trans_bufs;
struct srcu_struct btree_trans_barrier;
bool btree_trans_barrier_initialized;
struct workqueue_struct *btree_io_complete_wq;
/* copygc needs its own workqueue for index updates.. */
struct workqueue_struct *copygc_wq;
+ /*
+ * Use a dedicated wq for write ref holder tasks. Required to avoid
+ * dependency problems with other wq tasks that can block on ref
+ * draining, such as read-only transition.
+ */
+ struct workqueue_struct *write_ref_wq;
/* ALLOCATION */
struct bch_devs_mask rw_devs[BCH_DATA_NR];
struct open_bucket open_buckets[OPEN_BUCKETS_COUNT];
open_bucket_idx_t open_buckets_hash[OPEN_BUCKETS_COUNT];
+ open_bucket_idx_t open_buckets_partial[OPEN_BUCKETS_COUNT];
+ open_bucket_idx_t open_buckets_partial_nr;
+
struct write_point btree_write_point;
struct write_point rebalance_write_point;
mempool_t compression_bounce[2];
mempool_t compress_workspace[BCH_COMPRESSION_TYPE_NR];
mempool_t decompress_workspace;
- ZSTD_parameters zstd_params;
+ size_t zstd_workspace_size;
struct crypto_shash *sha256;
struct crypto_sync_skcipher *chacha20;
mempool_t large_bkey_pool;
+ /* MOVE.C */
+ struct list_head moving_context_list;
+ struct mutex moving_context_lock;
+
/* REBALANCE */
struct bch_fs_rebalance rebalance;
/* COPYGC */
struct task_struct *copygc_thread;
- copygc_heap copygc_heap;
struct write_point copygc_write_point;
+ s64 copygc_wait_at;
s64 copygc_wait;
bool copygc_running;
wait_queue_head_t copygc_running_wq;
- /* DATA PROGRESS STATS */
- struct list_head data_progress_list;
- struct mutex data_progress_lock;
-
/* STRIPES: */
GENRADIX(struct stripe) stripes;
GENRADIX(struct gc_stripe) gc_stripes;
+ struct hlist_head ec_stripes_new[32];
+ spinlock_t ec_stripes_new_lock;
+
ec_stripes_heap ec_stripes_heap;
- spinlock_t ec_stripes_heap_lock;
+ struct mutex ec_stripes_heap_lock;
/* ERASURE CODING */
struct list_head ec_stripe_head_list;
struct list_head ec_stripe_new_list;
struct mutex ec_stripe_new_lock;
+ wait_queue_head_t ec_stripe_new_wait;
struct work_struct ec_stripe_create_work;
u64 ec_stripe_hint;
- struct bio_set ec_bioset;
-
struct work_struct ec_stripe_delete_work;
- struct llist_head ec_stripe_delete_list;
+
+ struct bio_set ec_bioset;
/* REFLINK */
- u64 reflink_hint;
reflink_gc_table reflink_gc_table;
size_t reflink_gc_nr;
+ /* fs.c */
+ struct list_head vfs_inodes_list;
+ struct mutex vfs_inodes_lock;
+
/* VFS IO PATH - fs-io.c */
struct bio_set writepage_bioset;
struct bio_set dio_write_bioset;
struct bio_set dio_read_bioset;
struct bio_set nocow_flush_bioset;
- /* ERRORS */
- struct list_head fsck_errors;
- struct mutex fsck_error_lock;
- bool fsck_alloc_err;
-
/* QUOTAS */
struct bch_memquota_type quotas[QTYP_NR];
+ /* RECOVERY */
+ u64 journal_replay_seq_start;
+ u64 journal_replay_seq_end;
+ /*
+ * Two different uses:
+ * "Has this fsck pass?" - i.e. should this type of error be an
+ * emergency read-only
+ * And, in certain situations fsck will rewind to an earlier pass: used
+ * for signaling to the toplevel code which pass we want to run now.
+ */
+ enum bch_recovery_pass curr_recovery_pass;
+ /* bitmap of explicitly enabled recovery passes: */
+ u64 recovery_passes_explicit;
+ /* bitmask of recovery passes that we actually ran */
+ u64 recovery_passes_complete;
+ /* never rewinds version of curr_recovery_pass */
+ enum bch_recovery_pass recovery_pass_done;
+ struct semaphore online_fsck_mutex;
+
/* DEBUG JUNK */
struct dentry *fs_debug_dir;
struct dentry *btree_debug_dir;
struct bch2_time_stats times[BCH_TIME_STAT_NR];
struct btree_transaction_stats btree_transaction_stats[BCH_TRANSACTIONS_NR];
+
+ /* ERRORS */
+ struct list_head fsck_error_msgs;
+ struct mutex fsck_error_msgs_lock;
+ bool fsck_alloc_msgs_err;
+
+ bch_sb_errors_cpu fsck_error_counts;
+ struct mutex fsck_error_counts_lock;
};
extern struct wait_queue_head bch2_read_only_wait;
#endif
}
+static inline bool __bch2_write_ref_tryget(struct bch_fs *c, enum bch_write_ref ref)
+{
+#ifdef BCH_WRITE_REF_DEBUG
+ return !test_bit(BCH_FS_going_ro, &c->flags) &&
+ atomic_long_inc_not_zero(&c->writes[ref]);
+#else
+ return percpu_ref_tryget(&c->writes);
+#endif
+}
+
static inline bool bch2_write_ref_tryget(struct bch_fs *c, enum bch_write_ref ref)
{
#ifdef BCH_WRITE_REF_DEBUG
- return !test_bit(BCH_FS_GOING_RO, &c->flags) &&
+ return !test_bit(BCH_FS_going_ro, &c->flags) &&
atomic_long_inc_not_zero(&c->writes[ref]);
#else
return percpu_ref_tryget_live(&c->writes);
if (atomic_long_read(&c->writes[i]))
return;
- set_bit(BCH_FS_WRITE_DISABLE_COMPLETE, &c->flags);
+ set_bit(BCH_FS_write_disable_complete, &c->flags);
wake_up(&bch2_read_only_wait);
#else
percpu_ref_put(&c->writes);
#endif
}
+static inline bool bch2_ro_ref_tryget(struct bch_fs *c)
+{
+ if (test_bit(BCH_FS_stopping, &c->flags))
+ return false;
+
+ return refcount_inc_not_zero(&c->ro_ref);
+}
+
+static inline void bch2_ro_ref_put(struct bch_fs *c)
+{
+ if (refcount_dec_and_test(&c->ro_ref))
+ wake_up(&c->ro_ref_wait);
+}
+
static inline void bch2_set_ra_pages(struct bch_fs *c, unsigned ra_pages)
{
#ifndef NO_BCACHEFS_FS
return c->opts.block_size >> 9;
}
-static inline size_t btree_sectors(const struct bch_fs *c)
-{
- return c->opts.btree_node_size >> 9;
-}
-
static inline bool btree_id_cached(const struct bch_fs *c, enum btree_id btree)
{
return c->btree_key_cache_btrees & (1U << btree);
return dev < c->sb.nr_devices && c->devs[dev];
}
+static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c)
+{
+ struct stdio_redirect *stdio = c->stdio;
+
+ if (c->stdio_filter && c->stdio_filter != current)
+ stdio = NULL;
+ return stdio;
+}
+
+#define BKEY_PADDED_ONSTACK(key, pad) \
+ struct { struct bkey_i key; __u64 key ## _pad[pad]; }
+
#endif /* _BCACHEFS_H */