#include "buckets_types.h"
#include "extents.h"
-#include "super.h"
+#include "sb-members.h"
+
+static inline size_t sector_to_bucket(const struct bch_dev *ca, sector_t s)
+{
+ return div_u64(s, ca->mi.bucket_size);
+}
+
+static inline sector_t bucket_to_sector(const struct bch_dev *ca, size_t b)
+{
+ return ((sector_t) b) * ca->mi.bucket_size;
+}
+
+static inline sector_t bucket_remainder(const struct bch_dev *ca, sector_t s)
+{
+ u32 remainder;
+
+ div_u64_rem(s, ca->mi.bucket_size, &remainder);
+ return remainder;
+}
+
+static inline size_t sector_to_bucket_and_offset(const struct bch_dev *ca, sector_t s,
+ u32 *offset)
+{
+ return div_u64_rem(s, ca->mi.bucket_size, offset);
+}
#define for_each_bucket(_b, _buckets) \
for (_b = (_buckets)->b + (_buckets)->first_bucket; \
_b < (_buckets)->b + (_buckets)->nbuckets; _b++)
+/*
+ * Ugly hack alert:
+ *
+ * We need to cram a spinlock in a single byte, because that's what we have left
+ * in struct bucket, and we care about the size of these - during fsck, we need
+ * in memory state for every single bucket on every device.
+ *
+ * We used to do
+ * while (xchg(&b->lock, 1) cpu_relax();
+ * but, it turns out not all architectures support xchg on a single byte.
+ *
+ * So now we use bit_spin_lock(), with fun games since we can't burn a whole
+ * ulong for this - we just need to make sure the lock bit always ends up in the
+ * first byte.
+ */
+
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define BUCKET_LOCK_BITNR 0
+#else
+#define BUCKET_LOCK_BITNR (BITS_PER_LONG - 1)
+#endif
+
+union ulong_byte_assert {
+ ulong ulong;
+ u8 byte;
+};
+
static inline void bucket_unlock(struct bucket *b)
{
- smp_store_release(&b->lock, 0);
+ BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
+
+ clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock);
+ wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR);
}
static inline void bucket_lock(struct bucket *b)
{
- while (xchg(&b->lock, 1))
- cpu_relax();
+ wait_on_bit_lock((void *) &b->lock, BUCKET_LOCK_BITNR,
+ TASK_UNINTERRUPTIBLE);
}
static inline struct bucket_array *gc_bucket_array(struct bch_dev *ca)
}
void bch2_dev_usage_init(struct bch_dev *);
+void bch2_dev_usage_to_text(struct printbuf *, struct bch_dev_usage *);
-static inline u64 bch2_dev_buckets_reserved(struct bch_dev *ca, enum alloc_reserve reserve)
+static inline u64 bch2_dev_buckets_reserved(struct bch_dev *ca, enum bch_watermark watermark)
{
s64 reserved = 0;
- switch (reserve) {
- case RESERVE_none:
+ switch (watermark) {
+ case BCH_WATERMARK_NR:
+ BUG();
+ case BCH_WATERMARK_stripe:
+ reserved += ca->mi.nbuckets >> 6;
+ fallthrough;
+ case BCH_WATERMARK_normal:
reserved += ca->mi.nbuckets >> 6;
fallthrough;
- case RESERVE_movinggc:
+ case BCH_WATERMARK_copygc:
reserved += ca->nr_btree_reserve;
fallthrough;
- case RESERVE_btree:
+ case BCH_WATERMARK_btree:
reserved += ca->nr_btree_reserve;
fallthrough;
- case RESERVE_btree_movinggc:
+ case BCH_WATERMARK_btree_copygc:
+ case BCH_WATERMARK_reclaim:
break;
}
static inline u64 dev_buckets_free(struct bch_dev *ca,
struct bch_dev_usage usage,
- enum alloc_reserve reserve)
+ enum bch_watermark watermark)
{
return max_t(s64, 0,
usage.d[BCH_DATA_free].buckets -
ca->nr_open_buckets -
- bch2_dev_buckets_reserved(ca, reserve));
+ bch2_dev_buckets_reserved(ca, watermark));
}
static inline u64 __dev_buckets_available(struct bch_dev *ca,
struct bch_dev_usage usage,
- enum alloc_reserve reserve)
+ enum bch_watermark watermark)
{
return max_t(s64, 0,
usage.d[BCH_DATA_free].buckets
+ usage.d[BCH_DATA_need_gc_gens].buckets
+ usage.d[BCH_DATA_need_discard].buckets
- ca->nr_open_buckets
- - bch2_dev_buckets_reserved(ca, reserve));
+ - bch2_dev_buckets_reserved(ca, watermark));
}
static inline u64 dev_buckets_available(struct bch_dev *ca,
- enum alloc_reserve reserve)
+ enum bch_watermark watermark)
{
- return __dev_buckets_available(ca, bch2_dev_usage_read(ca), reserve);
+ return __dev_buckets_available(ca, bch2_dev_usage_read(ca), watermark);
}
/* Filesystem usage: */
+static inline unsigned __fs_usage_u64s(unsigned nr_replicas)
+{
+ return sizeof(struct bch_fs_usage) / sizeof(u64) + nr_replicas;
+}
+
static inline unsigned fs_usage_u64s(struct bch_fs *c)
{
- return sizeof(struct bch_fs_usage) / sizeof(u64) +
- READ_ONCE(c->replicas.nr);
+ return __fs_usage_u64s(READ_ONCE(c->replicas.nr));
+}
+
+static inline unsigned __fs_usage_online_u64s(unsigned nr_replicas)
+{
+ return sizeof(struct bch_fs_usage_online) / sizeof(u64) + nr_replicas;
+}
+
+static inline unsigned fs_usage_online_u64s(struct bch_fs *c)
+{
+ return __fs_usage_online_u64s(READ_ONCE(c->replicas.nr));
}
static inline unsigned dev_usage_u64s(void)
struct bch_fs_usage_short
bch2_fs_usage_read_short(struct bch_fs *);
+void bch2_dev_usage_update(struct bch_fs *, struct bch_dev *,
+ const struct bch_alloc_v4 *,
+ const struct bch_alloc_v4 *, u64, bool);
+void bch2_dev_usage_update_m(struct bch_fs *, struct bch_dev *,
+ struct bucket *, struct bucket *);
+
/* key/bucket marking: */
+static inline struct bch_fs_usage *fs_usage_ptr(struct bch_fs *c,
+ unsigned journal_seq,
+ bool gc)
+{
+ percpu_rwsem_assert_held(&c->mark_lock);
+ BUG_ON(!gc && !journal_seq);
+
+ return this_cpu_ptr(gc
+ ? c->usage_gc
+ : c->usage[journal_seq & JOURNAL_BUF_MASK]);
+}
+
+int bch2_update_replicas(struct bch_fs *, struct bkey_s_c,
+ struct bch_replicas_entry_v1 *, s64,
+ unsigned, bool);
+int bch2_update_replicas_list(struct btree_trans *,
+ struct bch_replicas_entry_v1 *, s64);
+int bch2_update_cached_sectors_list(struct btree_trans *, unsigned, s64);
+int bch2_replicas_deltas_realloc(struct btree_trans *, unsigned);
+
void bch2_fs_usage_initialize(struct bch_fs *);
+int bch2_check_bucket_ref(struct btree_trans *, struct bkey_s_c,
+ const struct bch_extent_ptr *,
+ s64, enum bch_data_type, u8, u8, u32);
+
int bch2_mark_metadata_bucket(struct bch_fs *, struct bch_dev *,
size_t, enum bch_data_type, unsigned,
struct gc_pos, unsigned);
-int bch2_mark_alloc(struct btree_trans *, struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_extent(struct btree_trans *, struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_stripe(struct btree_trans *, struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_inode(struct btree_trans *, struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_reservation(struct btree_trans *, struct bkey_s_c, struct bkey_s_c, unsigned);
-int bch2_mark_reflink_p(struct btree_trans *, struct bkey_s_c, struct bkey_s_c, unsigned);
-
-int bch2_trans_mark_extent(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_stripe(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_inode(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_reservation(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-int bch2_trans_mark_reflink_p(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *, unsigned);
-
+int bch2_trigger_extent(struct btree_trans *, enum btree_id, unsigned,
+ struct bkey_s_c, struct bkey_s, unsigned);
+int bch2_trigger_reservation(struct btree_trans *, enum btree_id, unsigned,
+ struct bkey_s_c, struct bkey_s, unsigned);
+
+#define trigger_run_overwrite_then_insert(_fn, _trans, _btree_id, _level, _old, _new, _flags)\
+({ \
+ int ret = 0; \
+ \
+ if (_old.k->type) \
+ ret = _fn(_trans, _btree_id, _level, _old, _flags & ~BTREE_TRIGGER_INSERT); \
+ if (!ret && _new.k->type) \
+ ret = _fn(_trans, _btree_id, _level, _new.s_c, _flags & ~BTREE_TRIGGER_OVERWRITE);\
+ ret; \
+})
+
+void bch2_trans_account_disk_usage_change(struct btree_trans *);
+
+void bch2_trans_fs_usage_revert(struct btree_trans *, struct replicas_delta_list *);
int bch2_trans_fs_usage_apply(struct btree_trans *, struct replicas_delta_list *);
int bch2_trans_mark_metadata_bucket(struct btree_trans *, struct bch_dev *,
size_t, enum bch_data_type, unsigned);
int bch2_trans_mark_dev_sb(struct bch_fs *, struct bch_dev *);
+int bch2_trans_mark_dev_sbs(struct bch_fs *);
+
+static inline bool is_superblock_bucket(struct bch_dev *ca, u64 b)
+{
+ struct bch_sb_layout *layout = &ca->disk_sb.sb->layout;
+ u64 b_offset = bucket_to_sector(ca, b);
+ u64 b_end = bucket_to_sector(ca, b + 1);
+ unsigned i;
+
+ if (!b)
+ return true;
+
+ for (i = 0; i < layout->nr_superblocks; i++) {
+ u64 offset = le64_to_cpu(layout->sb_offset[i]);
+ u64 end = offset + (1 << layout->sb_max_size_bits);
+
+ if (!(offset >= b_end || end <= b_offset))
+ return true;
+ }
+
+ return false;
+}
+
+static inline const char *bch2_data_type_str(enum bch_data_type type)
+{
+ return type < BCH_DATA_NR
+ ? __bch2_data_types[type]
+ : "(invalid data type)";
+}
+
+static inline void bch2_prt_data_type(struct printbuf *out, enum bch_data_type type)
+{
+ if (type < BCH_DATA_NR)
+ prt_str(out, __bch2_data_types[type]);
+ else
+ prt_printf(out, "(invalid data type %u)", type);
+}
/* disk reservations: */