bcachefs: bcachefs_metadata_version_disk_accounting_big_endian

Fix sort order for disk accounting keys, in order to fix a regression on
mount times.

The typetag is now the most significant byte of the key, meaning disk
accounting keys of the same type now sort together.

This lets us skip over disk accounting keys that aren't mirrored in
memory when reading accounting at startup, instead of having them
interleaved with other counter types.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

fs/bcachefs/bcachefs_format.h

@@ -679,7 +679,8 @@ struct bch_sb_field_ext {
 	x(disk_accounting_inum,		BCH_VERSION(1, 11))		\
 	x(rebalance_work_acct_fix,	BCH_VERSION(1, 12))		\
 	x(inode_has_child_snapshots,	BCH_VERSION(1, 13))		\
-	x(backpointer_bucket_gen,	BCH_VERSION(1, 14))
+	x(backpointer_bucket_gen,	BCH_VERSION(1, 14))		\
+	x(disk_accounting_big_endian,	BCH_VERSION(1, 15))
 
 enum bcachefs_metadata_version {
 	bcachefs_metadata_version_min = 9,

fs/bcachefs/disk_accounting.c

@@ -698,8 +698,11 @@ int bch2_accounting_read(struct bch_fs *c)
 	percpu_memset(c->usage, 0, sizeof(*c->usage));
 	percpu_up_write(&c->mark_lock);
 
-	int ret = for_each_btree_key(trans, iter,
-				BTREE_ID_accounting, POS_MIN,
+	struct btree_iter iter;
+	bch2_trans_iter_init(trans, &iter, BTREE_ID_accounting, POS_MIN,
+			     BTREE_ITER_prefetch|BTREE_ITER_all_snapshots);
+	iter.flags &= ~BTREE_ITER_with_journal;
+	int ret = for_each_btree_key_continue(trans, iter,
 				BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, ({
 			struct bkey u;
 			struct bkey_s_c k = bch2_btree_path_peek_slot_exact(btree_iter_path(trans, &iter), &u);
@@ -710,8 +713,14 @@ int bch2_accounting_read(struct bch_fs *c)
 			struct disk_accounting_pos acc_k;
 			bpos_to_disk_accounting_pos(&acc_k, k.k->p);
 
-			if (!bch2_accounting_is_mem(acc_k))
+			if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR)
+				break;
+
+			if (!bch2_accounting_is_mem(acc_k)) {
+				struct disk_accounting_pos next = { .type = acc_k.type + 1 };
+				bch2_btree_iter_set_pos(&iter, disk_accounting_pos_to_bpos(&next));
 				continue;
+			}
 
 			accounting_read_key(trans, k);
 		}));
@@ -896,10 +905,13 @@ void bch2_verify_accounting_clean(struct bch_fs *c)
 			bpos_to_disk_accounting_pos(&acc_k, k.k->p);
 
 			if (acc_k.type >= BCH_DISK_ACCOUNTING_TYPE_NR)
-				continue;
+				break;
 
-			if (acc_k.type == BCH_DISK_ACCOUNTING_inum)
+			if (!bch2_accounting_is_mem(acc_k)) {
+				struct disk_accounting_pos next = { .type = acc_k.type + 1 };
+				bch2_btree_iter_set_pos(&iter, disk_accounting_pos_to_bpos(&next));
 				continue;
+			}
 
 			bch2_accounting_mem_read(c, k.k->p, v, nr);
 

fs/bcachefs/disk_accounting.h

@@ -63,20 +63,24 @@ static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage
 
 static inline void bpos_to_disk_accounting_pos(struct disk_accounting_pos *acc, struct bpos p)
 {
-	acc->_pad = p;
+	BUILD_BUG_ON(sizeof(*acc) != sizeof(p));
+
 #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
-	bch2_bpos_swab(&acc->_pad);
+	acc->_pad = p;
+#else
+	memcpy_swab(acc, &p, sizeof(p));
 #endif
 }
 
-static inline struct bpos disk_accounting_pos_to_bpos(struct disk_accounting_pos *k)
+static inline struct bpos disk_accounting_pos_to_bpos(struct disk_accounting_pos *acc)
 {
-	struct bpos ret = k->_pad;
-
+	struct bpos p;
 #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
-	bch2_bpos_swab(&ret);
+	p = acc->_pad;
+#else
+	memcpy_swab(&p, acc, sizeof(p));
 #endif
-	return ret;
+	return p;
 }
 
 int bch2_disk_accounting_mod(struct btree_trans *, struct disk_accounting_pos *,

fs/bcachefs/sb-downgrade.c

@@ -85,7 +85,12 @@
 	x(backpointer_bucket_gen,				\
 	  BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\
 	  BCH_FSCK_ERR_backpointer_to_missing_ptr,		\
-	  BCH_FSCK_ERR_ptr_to_missing_backpointer)
+	  BCH_FSCK_ERR_ptr_to_missing_backpointer)		\
+	x(disk_accounting_big_endian,				\
+	  BIT_ULL(BCH_RECOVERY_PASS_check_allocations),		\
+	  BCH_FSCK_ERR_accounting_mismatch,			\
+	  BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0,	\
+	  BCH_FSCK_ERR_accounting_key_junk_at_end)
 
 #define DOWNGRADE_TABLE()					\
 	x(bucket_stripe_sectors,				\
@@ -128,7 +133,12 @@
 	  BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers),\
 	  BCH_FSCK_ERR_backpointer_bucket_offset_wrong,		\
 	  BCH_FSCK_ERR_backpointer_to_missing_ptr,		\
-	  BCH_FSCK_ERR_ptr_to_missing_backpointer)
+	  BCH_FSCK_ERR_ptr_to_missing_backpointer)		\
+	x(disk_accounting_big_endian,				\
+	  BIT_ULL(BCH_RECOVERY_PASS_check_allocations),		\
+	  BCH_FSCK_ERR_accounting_mismatch,			\
+	  BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0,	\
+	  BCH_FSCK_ERR_accounting_key_junk_at_end)
 
 struct upgrade_downgrade_entry {
 	u64		recovery_passes;

fs/bcachefs/util.h

@@ -709,4 +709,13 @@ static inline bool test_bit_le64(size_t bit, __le64 *addr)
 	return (addr[bit / 64] & cpu_to_le64(BIT_ULL(bit % 64))) != 0;
 }
 
+static inline void memcpy_swab(void *_dst, void *_src, size_t len)
+{
+	u8 *dst = _dst + len;
+	u8 *src = _src;
+
+	while (len--)
+		*--dst = *src++;
+}
+
 #endif /* _BCACHEFS_UTIL_H */