1 files changed, 54 insertions, 49 deletions

diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index fb906467201e..0455a1001fec 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -25,6 +25,7 @@
 #include "clock.h"
 #include "compress.h"
 #include "debug.h"
+#include "disk_accounting.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "errcode.h"
@@ -88,6 +89,19 @@ const char * const bch2_fs_flag_strs[] = {
 	NULL
 };
 
+void bch2_print_str(struct bch_fs *c, const char *str)
+{
+#ifdef __KERNEL__
+	struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c);
+
+	if (unlikely(stdio)) {
+		bch2_stdio_redirect_printf(stdio, true, "%s", str);
+		return;
+	}
+#endif
+	bch2_print_string_as_lines(KERN_ERR, str);
+}
+
 __printf(2, 0)
 static void bch2_print_maybe_redirect(struct stdio_redirect *stdio, const char *fmt, va_list args)
 {
@@ -222,22 +236,6 @@ struct bch_fs *bch2_uuid_to_fs(__uuid_t uuid)
 	return c;
 }
 
-static void bch2_dev_usage_journal_reserve(struct bch_fs *c)
-{
-	unsigned nr = 0, u64s =
-		((sizeof(struct jset_entry_dev_usage) +
-		  sizeof(struct jset_entry_dev_usage_type) * BCH_DATA_NR)) /
-		sizeof(u64);
-
-	rcu_read_lock();
-	for_each_member_device_rcu(c, ca, NULL)
-		nr++;
-	rcu_read_unlock();
-
-	bch2_journal_entry_res_resize(&c->journal,
-			&c->dev_usage_journal_res, u64s * nr);
-}
-
 /* Filesystem RO/RW: */
 
 /*
@@ -376,6 +374,7 @@ void bch2_fs_read_only(struct bch_fs *c)
 		BUG_ON(atomic_long_read(&c->btree_key_cache.nr_dirty));
 		BUG_ON(c->btree_write_buffer.inc.keys.nr);
 		BUG_ON(c->btree_write_buffer.flushing.keys.nr);
+		bch2_verify_accounting_clean(c);
 
 		bch_verbose(c, "marking filesystem clean");
 		bch2_fs_mark_clean(c);
@@ -536,6 +535,7 @@ static void __bch2_fs_free(struct bch_fs *c)
 
 	bch2_find_btree_nodes_exit(&c->found_btree_nodes);
 	bch2_free_pending_node_rewrites(c);
+	bch2_fs_accounting_exit(c);
 	bch2_fs_sb_errors_exit(c);
 	bch2_fs_counters_exit(c);
 	bch2_fs_snapshots_exit(c);
@@ -563,11 +563,15 @@ static void __bch2_fs_free(struct bch_fs *c)
 	BUG_ON(atomic_read(&c->journal_keys.ref));
 	bch2_fs_btree_write_buffer_exit(c);
 	percpu_free_rwsem(&c->mark_lock);
-	EBUG_ON(c->online_reserved && percpu_u64_get(c->online_reserved));
-	free_percpu(c->online_reserved);
+	if (c->online_reserved) {
+		u64 v = percpu_u64_get(c->online_reserved);
+		WARN(v, "online_reserved not 0 at shutdown: %lli", v);
+		free_percpu(c->online_reserved);
+	}
 
 	darray_exit(&c->btree_roots_extra);
 	free_percpu(c->pcpu);
+	free_percpu(c->usage);
 	mempool_exit(&c->large_bkey_pool);
 	mempool_exit(&c->btree_bounce_pool);
 	bioset_exit(&c->btree_bio);
@@ -786,8 +790,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 
 	INIT_LIST_HEAD(&c->list);
 
-	mutex_init(&c->usage_scratch_lock);
-
 	mutex_init(&c->bio_bounce_pages_lock);
 	mutex_init(&c->snapshot_table_lock);
 	init_rwsem(&c->snapshot_create_lock);
@@ -895,6 +897,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 			    offsetof(struct btree_write_bio, wbio.bio)),
 			BIOSET_NEED_BVECS) ||
 	    !(c->pcpu = alloc_percpu(struct bch_fs_pcpu)) ||
+	    !(c->usage = alloc_percpu(struct bch_fs_usage_base)) ||
 	    !(c->online_reserved = alloc_percpu(u64)) ||
 	    mempool_init_kvmalloc_pool(&c->btree_bounce_pool, 1,
 				       c->opts.btree_node_size) ||
@@ -910,7 +913,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	    bch2_io_clock_init(&c->io_clock[READ]) ?:
 	    bch2_io_clock_init(&c->io_clock[WRITE]) ?:
 	    bch2_fs_journal_init(&c->journal) ?:
-	    bch2_fs_replicas_init(c) ?:
 	    bch2_fs_btree_iter_init(c) ?:
 	    bch2_fs_btree_cache_init(c) ?:
 	    bch2_fs_btree_key_cache_init(&c->btree_key_cache) ?:
@@ -941,7 +943,6 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts opts)
 	bch2_journal_entry_res_resize(&c->journal,
 			&c->btree_root_journal_res,
 			BTREE_ID_NR * (JSET_KEYS_U64s + BKEY_BTREE_PTR_U64s_MAX));
-	bch2_dev_usage_journal_reserve(c);
 	bch2_journal_entry_res_resize(&c->journal,
 			&c->clock_journal_res,
 			(sizeof(struct jset_entry_clock) / sizeof(u64)) * 2);
@@ -967,7 +968,7 @@ static void print_mount_opts(struct bch_fs *c)
 	struct printbuf p = PRINTBUF;
 	bool first = true;
 
-	prt_str(&p, "mounting version ");
+	prt_str(&p, "starting version ");
 	bch2_version_to_text(&p, c->sb.version);
 
 	if (c->opts.read_only) {
@@ -1612,7 +1613,8 @@ static int bch2_dev_remove_alloc(struct bch_fs *c, struct bch_dev *ca)
 		bch2_btree_delete_range(c, BTREE_ID_alloc, start, end,
 					BTREE_TRIGGER_norun, NULL) ?:
 		bch2_btree_delete_range(c, BTREE_ID_bucket_gens, start, end,
-					BTREE_TRIGGER_norun, NULL);
+					BTREE_TRIGGER_norun, NULL) ?:
+		bch2_dev_usage_remove(c, ca->dev_idx);
 	bch_err_msg(c, ret, "removing dev alloc info");
 	return ret;
 }
@@ -1649,6 +1651,16 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 	if (ret)
 		goto err;
 
+	/*
+	 * We need to flush the entire journal to get rid of keys that reference
+	 * the device being removed before removing the superblock entry
+	 */
+	bch2_journal_flush_all_pins(&c->journal);
+
+	/*
+	 * this is really just needed for the bch2_replicas_gc_(start|end)
+	 * calls, and could be cleaned up:
+	 */
 	ret = bch2_journal_flush_device_pins(&c->journal, ca->dev_idx);
 	bch_err_msg(ca, ret, "bch2_journal_flush_device_pins()");
 	if (ret)
@@ -1692,17 +1704,6 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 	bch2_dev_free(ca);
 
 	/*
-	 * At this point the device object has been removed in-core, but the
-	 * on-disk journal might still refer to the device index via sb device
-	 * usage entries. Recovery fails if it sees usage information for an
-	 * invalid device. Flush journal pins to push the back of the journal
-	 * past now invalid device index references before we update the
-	 * superblock, but after the device object has been removed so any
-	 * further journal writes elide usage info for the device.
-	 */
-	bch2_journal_flush_all_pins(&c->journal);
-
-	/*
 	 * Free this device's slot in the bch_member array - all pointers to
 	 * this device must be gone:
 	 */
@@ -1714,8 +1715,6 @@ int bch2_dev_remove(struct bch_fs *c, struct bch_dev *ca, int flags)
 
 	mutex_unlock(&c->sb_lock);
 	up_write(&c->state_lock);
-
-	bch2_dev_usage_journal_reserve(c);
 	return 0;
 err:
 	if (ca->mi.state == BCH_MEMBER_STATE_rw &&
@@ -1763,13 +1762,11 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 		goto err;
 	}
 
-	bch2_dev_usage_init(ca);
-
 	ret = __bch2_dev_attach_bdev(ca, &sb);
 	if (ret)
 		goto err;
 
-	ret = bch2_dev_journal_alloc(ca);
+	ret = bch2_dev_journal_alloc(ca, true);
 	bch_err_msg(c, ret, "allocating journal");
 	if (ret)
 		goto err;
@@ -1846,7 +1843,9 @@ have_slot:
 	bch2_write_super(c);
 	mutex_unlock(&c->sb_lock);
 
-	bch2_dev_usage_journal_reserve(c);
+	ret = bch2_dev_usage_init(ca, false);
+	if (ret)
+		goto err_late;
 
 	ret = bch2_trans_mark_dev_sb(c, ca, BTREE_TRIGGER_transactional);
 	bch_err_msg(ca, ret, "marking new superblock");
@@ -1929,7 +1928,7 @@ int bch2_dev_online(struct bch_fs *c, const char *path)
 	}
 
 	if (!ca->journal.nr) {
-		ret = bch2_dev_journal_alloc(ca);
+		ret = bch2_dev_journal_alloc(ca, false);
 		bch_err_msg(ca, ret, "allocating journal");
 		if (ret)
 			goto err;
@@ -2018,15 +2017,18 @@ int bch2_dev_resize(struct bch_fs *c, struct bch_dev *ca, u64 nbuckets)
 	mutex_unlock(&c->sb_lock);
 
 	if (ca->mi.freespace_initialized) {
-		ret = bch2_dev_freespace_init(c, ca, old_nbuckets, nbuckets);
+		struct disk_accounting_pos acc = {
+			.type = BCH_DISK_ACCOUNTING_dev_data_type,
+			.dev_data_type.dev = ca->dev_idx,
+			.dev_data_type.data_type = BCH_DATA_free,
+		};
+		u64 v[3] = { nbuckets - old_nbuckets, 0, 0 };
+
+		ret   = bch2_trans_do(ca->fs, NULL, NULL, 0,
+				bch2_disk_accounting_mod(trans, &acc, v, ARRAY_SIZE(v), false)) ?:
+			bch2_dev_freespace_init(c, ca, old_nbuckets, nbuckets);
 		if (ret)
 			goto err;
-
-		/*
-		 * XXX: this is all wrong transactionally - we'll be able to do
-		 * this correctly after the disk space accounting rewrite
-		 */
-		ca->usage_base->d[BCH_DATA_free].buckets += nbuckets - old_nbuckets;
 	}
 
 	bch2_recalc_capacity(c);
@@ -2038,6 +2040,9 @@ err:
 /* return with ref on ca->ref: */
 struct bch_dev *bch2_dev_lookup(struct bch_fs *c, const char *name)
 {
+	if (!strncmp(name, "/dev/", strlen("/dev/")))
+		name += strlen("/dev/");
+
 	for_each_member_device(c, ca)
 		if (!strcmp(name, ca->name))
 			return ca;