#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 <linux/seqlock.h>
#include <linux/shrinker.h>
#include <linux/srcu.h>
+#include <linux/thread_with_file_types.h>
+#include <linux/time_stats.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <linux/zstd.h>
#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), \
#define bch_err_inum_offset_ratelimited(c, _inum, _offset, fmt, ...) \
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 (_ret && !bch2_err_matches(_ret, BCH_ERR_transaction_restart))\
+ 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 (_ret && !bch2_err_matches(_ret, BCH_ERR_transaction_restart))\
+ if (should_print_err(_ret)) \
bch_err(_c, "%s(): error " _msg " %s", __func__, \
##__VA_ARGS__, bch2_err_str(_ret)); \
} while (0)
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(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 {
struct btree;
-struct log_output {
- spinlock_t lock;
- wait_queue_head_t wait;
- struct printbuf buf;
-};
-
enum gc_phase {
GC_PHASE_NOT_RUNNING,
GC_PHASE_START,
GC_PHASE_BTREE_deleted_inodes,
GC_PHASE_BTREE_logged_ops,
GC_PHASE_BTREE_rebalance_work,
+ GC_PHASE_BTREE_subvolume_children,
GC_PHASE_PENDING_DELETE,
};
/* The rest of this all shows up in sysfs */
atomic64_t cur_latency[2];
- struct bch2_time_stats io_latency[2];
+ struct time_stats_quantiles io_latency[2];
#define CONGESTED_MAX 1024
atomic_t congested;
};
/*
- * fsck_done - kill?
- *
- * replace with something more general from enumated fsck passes/errors:
* initial_gc_unfixed
* error
* topology error
x(going_ro) \
x(write_disable_complete) \
x(clean_shutdown) \
- x(fsck_done) \
+ x(fsck_running) \
x(initial_gc_unfixed) \
x(need_another_gc) \
x(need_delete_dead_snapshots) \
#define BCH_TRANSACTIONS_NR 128
struct btree_transaction_stats {
- struct bch2_time_stats lock_hold_times;
+ struct time_stats duration;
+ struct 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;
};
struct super_block *vfs_sb;
dev_t dev;
char name[40];
- struct log_output *output;
+ 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];
unsigned nsec_per_time_unit;
u64 features;
u64 compat;
+ unsigned long errors_silent[BITS_TO_LONGS(BCH_SB_ERR_MAX)];
} sb;
/* ALLOCATOR */
spinlock_t freelist_lock;
struct closure_waitlist freelist_wait;
- u64 blocked_allocate;
- u64 blocked_allocate_open_bucket;
open_bucket_idx_t open_buckets_freelist;
open_bucket_idx_t open_buckets_nr_free;
/* 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;
unsigned copy_gc_enabled:1;
bool promote_whole_extents;
- struct bch2_time_stats times[BCH_TIME_STAT_NR];
+ struct time_stats times[BCH_TIME_STAT_NR];
struct btree_transaction_stats btree_transaction_stats[BCH_TRANSACTIONS_NR];
#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
#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;
+}
+
+static inline unsigned metadata_replicas_required(struct bch_fs *c)
+{
+ return min(c->opts.metadata_replicas,
+ c->opts.metadata_replicas_required);
+}
+
+static inline unsigned data_replicas_required(struct bch_fs *c)
+{
+ return min(c->opts.data_replicas,
+ c->opts.data_replicas_required);
+}
+
#define BKEY_PADDED_ONSTACK(key, pad) \
struct { struct bkey_i key; __u64 key ## _pad[pad]; }