summaryrefslogtreecommitdiffstats
path: root/fs/bcachefs/recovery.c
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-08-07 13:11:27 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-08-07 13:11:27 +0000
commit34996e42f82bfd60bc2c191e5cae3c6ab233ec6c (patch)
tree62db60558cbf089714b48daeabca82bf2b20b20e /fs/bcachefs/recovery.c
parentAdding debian version 6.8.12-1. (diff)
downloadlinux-34996e42f82bfd60bc2c191e5cae3c6ab233ec6c.tar.xz
linux-34996e42f82bfd60bc2c191e5cae3c6ab233ec6c.zip
Merging upstream version 6.9.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'fs/bcachefs/recovery.c')
-rw-r--r--fs/bcachefs/recovery.c490
1 files changed, 157 insertions, 333 deletions
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 21e13bb433..8091d06860 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -1,35 +1,31 @@
// SPDX-License-Identifier: GPL-2.0
#include "bcachefs.h"
-#include "backpointers.h"
-#include "bkey_buf.h"
#include "alloc_background.h"
-#include "btree_gc.h"
+#include "bkey_buf.h"
#include "btree_journal_iter.h"
+#include "btree_node_scan.h"
#include "btree_update.h"
#include "btree_update_interior.h"
#include "btree_io.h"
#include "buckets.h"
#include "dirent.h"
-#include "ec.h"
#include "errcode.h"
#include "error.h"
#include "fs-common.h"
-#include "fsck.h"
#include "journal_io.h"
#include "journal_reclaim.h"
#include "journal_seq_blacklist.h"
-#include "lru.h"
#include "logged_ops.h"
#include "move.h"
#include "quota.h"
#include "rebalance.h"
#include "recovery.h"
+#include "recovery_passes.h"
#include "replicas.h"
#include "sb-clean.h"
#include "sb-downgrade.h"
#include "snapshot.h"
-#include "subvolume.h"
#include "super-io.h"
#include <linux/sort.h>
@@ -37,30 +33,67 @@
#define QSTR(n) { { { .len = strlen(n) } }, .name = n }
-static bool btree_id_is_alloc(enum btree_id id)
+void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree)
{
- switch (id) {
- case BTREE_ID_alloc:
- case BTREE_ID_backpointers:
- case BTREE_ID_need_discard:
- case BTREE_ID_freespace:
- case BTREE_ID_bucket_gens:
- return true;
- default:
- return false;
+ u64 b = BIT_ULL(btree);
+
+ if (!(c->sb.btrees_lost_data & b)) {
+ bch_err(c, "flagging btree %s lost data", bch2_btree_id_str(btree));
+
+ mutex_lock(&c->sb_lock);
+ bch2_sb_field_get(c->disk_sb.sb, ext)->btrees_lost_data |= cpu_to_le64(b);
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
}
}
/* for -o reconstruct_alloc: */
-static void drop_alloc_keys(struct journal_keys *keys)
+static void bch2_reconstruct_alloc(struct bch_fs *c)
{
- size_t src, dst;
+ bch2_journal_log_msg(c, "dropping alloc info");
+ bch_info(c, "dropping and reconstructing all alloc info");
+
+ mutex_lock(&c->sb_lock);
+ struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
+
+ __set_bit_le64(BCH_RECOVERY_PASS_STABLE_check_allocations, ext->recovery_passes_required);
+ __set_bit_le64(BCH_RECOVERY_PASS_STABLE_check_alloc_info, ext->recovery_passes_required);
+ __set_bit_le64(BCH_RECOVERY_PASS_STABLE_check_lrus, ext->recovery_passes_required);
+ __set_bit_le64(BCH_RECOVERY_PASS_STABLE_check_extents_to_backpointers, ext->recovery_passes_required);
+ __set_bit_le64(BCH_RECOVERY_PASS_STABLE_check_alloc_to_lru_refs, ext->recovery_passes_required);
+
+ __set_bit_le64(BCH_FSCK_ERR_ptr_to_missing_alloc_key, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_ptr_gen_newer_than_bucket_gen, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_stale_dirty_ptr, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_alloc_key_data_type_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_alloc_key_gen_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_alloc_key_dirty_sectors_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_alloc_key_stripe_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_alloc_key_stripe_redundancy_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_need_discard_key_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_freespace_key_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_bucket_gens_key_wrong, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_freespace_hole_missing, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_ptr_to_missing_backpointer, ext->errors_silent);
+ __set_bit_le64(BCH_FSCK_ERR_lru_entry_bad, ext->errors_silent);
+ c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
- for (src = 0, dst = 0; src < keys->nr; src++)
- if (!btree_id_is_alloc(keys->d[src].btree_id))
- keys->d[dst++] = keys->d[src];
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
+
+ c->recovery_passes_explicit |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0]));
- keys->nr = dst;
+
+ bch2_shoot_down_journal_keys(c, BTREE_ID_alloc,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_backpointers,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_need_discard,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_freespace,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ bch2_shoot_down_journal_keys(c, BTREE_ID_bucket_gens,
+ 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
}
/*
@@ -70,9 +103,7 @@ static void drop_alloc_keys(struct journal_keys *keys)
*/
static void zero_out_btree_mem_ptr(struct journal_keys *keys)
{
- struct journal_key *i;
-
- for (i = keys->d; i < keys->d + keys->nr; i++)
+ darray_for_each(*keys, i)
if (i->k->k.type == KEY_TYPE_btree_ptr_v2)
bkey_i_to_btree_ptr_v2(i->k)->v.mem_ptr = 0;
}
@@ -124,6 +155,17 @@ static int bch2_journal_replay_key(struct btree_trans *trans,
if (ret)
goto out;
+ struct btree_path *path = btree_iter_path(trans, &iter);
+ if (unlikely(!btree_path_node(path, k->level))) {
+ bch2_trans_iter_exit(trans, &iter);
+ bch2_trans_node_iter_init(trans, &iter, k->btree_id, k->k->k.p,
+ BTREE_MAX_DEPTH, 0, iter_flags);
+ ret = bch2_btree_iter_traverse(&iter) ?:
+ bch2_btree_increase_depth(trans, iter.path, 0) ?:
+ -BCH_ERR_transaction_restart_nested;
+ goto out;
+ }
+
/* Must be checked with btree locked: */
if (k->overwritten)
goto out;
@@ -142,7 +184,7 @@ static int journal_sort_seq_cmp(const void *_l, const void *_r)
return cmp_int(l->journal_seq, r->journal_seq);
}
-static int bch2_journal_replay(struct bch_fs *c)
+int bch2_journal_replay(struct bch_fs *c)
{
struct journal_keys *keys = &c->journal_keys;
DARRAY(struct journal_key *) keys_sorted = { 0 };
@@ -150,6 +192,7 @@ static int bch2_journal_replay(struct bch_fs *c)
u64 start_seq = c->journal_replay_seq_start;
u64 end_seq = c->journal_replay_seq_start;
struct btree_trans *trans = bch2_trans_get(c);
+ bool immediate_flush = false;
int ret = 0;
if (keys->nr) {
@@ -161,15 +204,22 @@ static int bch2_journal_replay(struct bch_fs *c)
BUG_ON(!atomic_read(&keys->ref));
+ move_gap(keys, keys->nr);
+
/*
* First, attempt to replay keys in sorted order. This is more
* efficient - better locality of btree access - but some might fail if
* that would cause a journal deadlock.
*/
- for (size_t i = 0; i < keys->nr; i++) {
+ darray_for_each(*keys, k) {
cond_resched();
- struct journal_key *k = keys->d + i;
+ /*
+ * k->allocated means the key wasn't read in from the journal,
+ * rather it was from early repair code
+ */
+ if (k->allocated)
+ immediate_flush = true;
/* Skip fastpath if we're low on space in the journal */
ret = c->journal.watermark ? -1 :
@@ -199,7 +249,10 @@ static int bch2_journal_replay(struct bch_fs *c)
struct journal_key *k = *kp;
- replay_now_at(j, k->journal_seq);
+ if (k->journal_seq)
+ replay_now_at(j, k->journal_seq);
+ else
+ replay_now_at(j, j->replay_journal_seq_end);
ret = commit_do(trans, NULL, NULL,
BCH_TRANS_COMMIT_no_enospc|
@@ -222,7 +275,8 @@ static int bch2_journal_replay(struct bch_fs *c)
bch2_trans_put(trans);
trans = NULL;
- if (!c->opts.keep_journal)
+ if (!c->opts.retain_recovery_info &&
+ c->recovery_pass_done >= BCH_RECOVERY_PASS_journal_replay)
bch2_journal_keys_put_initial(c);
replay_now_at(j, j->replay_journal_seq_end);
@@ -230,6 +284,12 @@ static int bch2_journal_replay(struct bch_fs *c)
bch2_journal_set_replay_done(j);
+ /* if we did any repair, flush it immediately */
+ if (immediate_flush) {
+ bch2_journal_flush_all_pins(&c->journal);
+ ret = bch2_journal_meta(&c->journal);
+ }
+
if (keys->nr)
bch2_journal_log_msg(c, "journal replay finished");
err:
@@ -264,7 +324,7 @@ static int journal_replay_entry_early(struct bch_fs *c,
bkey_copy(&r->key, (struct bkey_i *) entry->start);
r->error = 0;
} else {
- r->error = -EIO;
+ r->error = -BCH_ERR_btree_node_read_error;
}
r->alive = true;
break;
@@ -359,7 +419,7 @@ static int journal_replay_early(struct bch_fs *c,
genradix_for_each(&c->journal_entries, iter, _i) {
i = *_i;
- if (!i || i->ignore)
+ if (journal_replay_ignore(i))
continue;
vstruct_for_each(&i->j, entry) {
@@ -379,202 +439,57 @@ static int journal_replay_early(struct bch_fs *c,
static int read_btree_roots(struct bch_fs *c)
{
- unsigned i;
int ret = 0;
- for (i = 0; i < btree_id_nr_alive(c); i++) {
+ for (unsigned i = 0; i < btree_id_nr_alive(c); i++) {
struct btree_root *r = bch2_btree_id_root(c, i);
if (!r->alive)
continue;
- if (btree_id_is_alloc(i) &&
- c->opts.reconstruct_alloc) {
- c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
+ if (btree_id_is_alloc(i) && c->opts.reconstruct_alloc)
continue;
- }
- if (r->error) {
- __fsck_err(c,
- btree_id_is_alloc(i)
- ? FSCK_CAN_IGNORE : 0,
- btree_root_bkey_invalid,
- "invalid btree root %s",
- bch2_btree_id_str(i));
- if (i == BTREE_ID_alloc)
+ if (mustfix_fsck_err_on((ret = r->error),
+ c, btree_root_bkey_invalid,
+ "invalid btree root %s",
+ bch2_btree_id_str(i)) ||
+ mustfix_fsck_err_on((ret = r->error = bch2_btree_root_read(c, i, &r->key, r->level)),
+ c, btree_root_read_error,
+ "error reading btree root %s l=%u: %s",
+ bch2_btree_id_str(i), r->level, bch2_err_str(ret))) {
+ if (btree_id_is_alloc(i)) {
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_allocations);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_info);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_lrus);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_extents_to_backpointers);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_alloc_to_lru_refs);
c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
- }
+ r->error = 0;
+ } else if (!(c->recovery_passes_explicit & BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes))) {
+ bch_info(c, "will run btree node scan");
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes);
+ c->recovery_passes_explicit |= BIT_ULL(BCH_RECOVERY_PASS_check_topology);
+ }
- ret = bch2_btree_root_read(c, i, &r->key, r->level);
- if (ret) {
- fsck_err(c,
- btree_root_read_error,
- "error reading btree root %s",
- bch2_btree_id_str(i));
- if (btree_id_is_alloc(i))
- c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
ret = 0;
+ bch2_btree_lost_data(c, i);
}
}
- for (i = 0; i < BTREE_ID_NR; i++) {
+ for (unsigned i = 0; i < BTREE_ID_NR; i++) {
struct btree_root *r = bch2_btree_id_root(c, i);
- if (!r->b) {
+ if (!r->b && !r->error) {
r->alive = false;
r->level = 0;
- bch2_btree_root_alloc(c, i);
+ bch2_btree_root_alloc_fake(c, i, 0);
}
}
fsck_err:
return ret;
}
-static int bch2_initialize_subvolumes(struct bch_fs *c)
-{
- struct bkey_i_snapshot_tree root_tree;
- struct bkey_i_snapshot root_snapshot;
- struct bkey_i_subvolume root_volume;
- int ret;
-
- bkey_snapshot_tree_init(&root_tree.k_i);
- root_tree.k.p.offset = 1;
- root_tree.v.master_subvol = cpu_to_le32(1);
- root_tree.v.root_snapshot = cpu_to_le32(U32_MAX);
-
- bkey_snapshot_init(&root_snapshot.k_i);
- root_snapshot.k.p.offset = U32_MAX;
- root_snapshot.v.flags = 0;
- root_snapshot.v.parent = 0;
- root_snapshot.v.subvol = cpu_to_le32(BCACHEFS_ROOT_SUBVOL);
- root_snapshot.v.tree = cpu_to_le32(1);
- SET_BCH_SNAPSHOT_SUBVOL(&root_snapshot.v, true);
-
- bkey_subvolume_init(&root_volume.k_i);
- root_volume.k.p.offset = BCACHEFS_ROOT_SUBVOL;
- root_volume.v.flags = 0;
- root_volume.v.snapshot = cpu_to_le32(U32_MAX);
- root_volume.v.inode = cpu_to_le64(BCACHEFS_ROOT_INO);
-
- ret = bch2_btree_insert(c, BTREE_ID_snapshot_trees, &root_tree.k_i, NULL, 0) ?:
- bch2_btree_insert(c, BTREE_ID_snapshots, &root_snapshot.k_i, NULL, 0) ?:
- bch2_btree_insert(c, BTREE_ID_subvolumes, &root_volume.k_i, NULL, 0);
- bch_err_fn(c, ret);
- return ret;
-}
-
-static int __bch2_fs_upgrade_for_subvolumes(struct btree_trans *trans)
-{
- struct btree_iter iter;
- struct bkey_s_c k;
- struct bch_inode_unpacked inode;
- int ret;
-
- k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes,
- SPOS(0, BCACHEFS_ROOT_INO, U32_MAX), 0);
- ret = bkey_err(k);
- if (ret)
- return ret;
-
- if (!bkey_is_inode(k.k)) {
- bch_err(trans->c, "root inode not found");
- ret = -BCH_ERR_ENOENT_inode;
- goto err;
- }
-
- ret = bch2_inode_unpack(k, &inode);
- BUG_ON(ret);
-
- inode.bi_subvol = BCACHEFS_ROOT_SUBVOL;
-
- ret = bch2_inode_write(trans, &iter, &inode);
-err:
- bch2_trans_iter_exit(trans, &iter);
- return ret;
-}
-
-/* set bi_subvol on root inode */
-noinline_for_stack
-static int bch2_fs_upgrade_for_subvolumes(struct bch_fs *c)
-{
- int ret = bch2_trans_do(c, NULL, NULL, BCH_TRANS_COMMIT_lazy_rw,
- __bch2_fs_upgrade_for_subvolumes(trans));
- bch_err_fn(c, ret);
- return ret;
-}
-
-const char * const bch2_recovery_passes[] = {
-#define x(_fn, ...) #_fn,
- BCH_RECOVERY_PASSES()
-#undef x
- NULL
-};
-
-static int bch2_check_allocations(struct bch_fs *c)
-{
- return bch2_gc(c, true, c->opts.norecovery);
-}
-
-static int bch2_set_may_go_rw(struct bch_fs *c)
-{
- struct journal_keys *keys = &c->journal_keys;
-
- /*
- * After we go RW, the journal keys buffer can't be modified (except for
- * setting journal_key->overwritten: it will be accessed by multiple
- * threads
- */
- move_gap(keys->d, keys->nr, keys->size, keys->gap, keys->nr);
- keys->gap = keys->nr;
-
- set_bit(BCH_FS_may_go_rw, &c->flags);
-
- if (keys->nr || c->opts.fsck || !c->sb.clean)
- return bch2_fs_read_write_early(c);
- return 0;
-}
-
-struct recovery_pass_fn {
- int (*fn)(struct bch_fs *);
- unsigned when;
-};
-
-static struct recovery_pass_fn recovery_pass_fns[] = {
-#define x(_fn, _id, _when) { .fn = bch2_##_fn, .when = _when },
- BCH_RECOVERY_PASSES()
-#undef x
-};
-
-u64 bch2_recovery_passes_to_stable(u64 v)
-{
- static const u8 map[] = {
-#define x(n, id, ...) [BCH_RECOVERY_PASS_##n] = BCH_RECOVERY_PASS_STABLE_##n,
- BCH_RECOVERY_PASSES()
-#undef x
- };
-
- u64 ret = 0;
- for (unsigned i = 0; i < ARRAY_SIZE(map); i++)
- if (v & BIT_ULL(i))
- ret |= BIT_ULL(map[i]);
- return ret;
-}
-
-u64 bch2_recovery_passes_from_stable(u64 v)
-{
- static const u8 map[] = {
-#define x(n, id, ...) [BCH_RECOVERY_PASS_STABLE_##n] = BCH_RECOVERY_PASS_##n,
- BCH_RECOVERY_PASSES()
-#undef x
- };
-
- u64 ret = 0;
- for (unsigned i = 0; i < ARRAY_SIZE(map); i++)
- if (v & BIT_ULL(i))
- ret |= BIT_ULL(map[i]);
- return ret;
-}
-
static bool check_version_upgrade(struct bch_fs *c)
{
unsigned latest_version = bcachefs_metadata_version_current;
@@ -647,96 +562,6 @@ static bool check_version_upgrade(struct bch_fs *c)
return false;
}
-u64 bch2_fsck_recovery_passes(void)
-{
- u64 ret = 0;
-
- for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++)
- if (recovery_pass_fns[i].when & PASS_FSCK)
- ret |= BIT_ULL(i);
- return ret;
-}
-
-static bool should_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
-{
- struct recovery_pass_fn *p = recovery_pass_fns + pass;
-
- if (c->opts.norecovery && pass > BCH_RECOVERY_PASS_snapshots_read)
- return false;
- if (c->recovery_passes_explicit & BIT_ULL(pass))
- return true;
- if ((p->when & PASS_FSCK) && c->opts.fsck)
- return true;
- if ((p->when & PASS_UNCLEAN) && !c->sb.clean)
- return true;
- if (p->when & PASS_ALWAYS)
- return true;
- return false;
-}
-
-static int bch2_run_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
-{
- struct recovery_pass_fn *p = recovery_pass_fns + pass;
- int ret;
-
- if (!(p->when & PASS_SILENT))
- bch2_print(c, KERN_INFO bch2_log_msg(c, "%s..."),
- bch2_recovery_passes[pass]);
- ret = p->fn(c);
- if (ret)
- return ret;
- if (!(p->when & PASS_SILENT))
- bch2_print(c, KERN_CONT " done\n");
-
- return 0;
-}
-
-static int bch2_run_recovery_passes(struct bch_fs *c)
-{
- int ret = 0;
-
- while (c->curr_recovery_pass < ARRAY_SIZE(recovery_pass_fns)) {
- if (should_run_recovery_pass(c, c->curr_recovery_pass)) {
- unsigned pass = c->curr_recovery_pass;
-
- ret = bch2_run_recovery_pass(c, c->curr_recovery_pass);
- if (bch2_err_matches(ret, BCH_ERR_restart_recovery) ||
- (ret && c->curr_recovery_pass < pass))
- continue;
- if (ret)
- break;
-
- c->recovery_passes_complete |= BIT_ULL(c->curr_recovery_pass);
- }
- c->curr_recovery_pass++;
- c->recovery_pass_done = max(c->recovery_pass_done, c->curr_recovery_pass);
- }
-
- return ret;
-}
-
-int bch2_run_online_recovery_passes(struct bch_fs *c)
-{
- int ret = 0;
-
- for (unsigned i = 0; i < ARRAY_SIZE(recovery_pass_fns); i++) {
- struct recovery_pass_fn *p = recovery_pass_fns + i;
-
- if (!(p->when & PASS_ONLINE))
- continue;
-
- ret = bch2_run_recovery_pass(c, i);
- if (bch2_err_matches(ret, BCH_ERR_restart_recovery)) {
- i = c->curr_recovery_pass;
- continue;
- }
- if (ret)
- break;
- }
-
- return ret;
-}
-
int bch2_fs_recovery(struct bch_fs *c)
{
struct bch_sb_field_clean *clean = NULL;
@@ -769,24 +594,14 @@ int bch2_fs_recovery(struct bch_fs *c)
goto err;
}
- if (c->opts.fsck && c->opts.norecovery) {
- bch_err(c, "cannot select both norecovery and fsck");
- ret = -EINVAL;
- goto err;
- }
+ if (c->opts.norecovery)
+ c->opts.recovery_pass_last = BCH_RECOVERY_PASS_journal_replay - 1;
if (!c->opts.nochanges) {
mutex_lock(&c->sb_lock);
+ struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
bool write_sb = false;
- struct bch_sb_field_ext *ext =
- bch2_sb_field_get_minsize(&c->disk_sb, ext, sizeof(*ext) / sizeof(u64));
- if (!ext) {
- ret = -BCH_ERR_ENOSPC_sb;
- mutex_unlock(&c->sb_lock);
- goto err;
- }
-
if (BCH_SB_HAS_TOPOLOGY_ERRORS(c->disk_sb.sb)) {
ext->recovery_passes_required[0] |=
cpu_to_le64(bch2_recovery_passes_to_stable(BIT_ULL(BCH_RECOVERY_PASS_check_topology)));
@@ -845,7 +660,7 @@ int bch2_fs_recovery(struct bch_fs *c)
goto err;
}
- if (!c->sb.clean || c->opts.fsck || c->opts.keep_journal) {
+ if (!c->sb.clean || c->opts.fsck || c->opts.retain_recovery_info) {
struct genradix_iter iter;
struct journal_replay **i;
@@ -862,7 +677,7 @@ int bch2_fs_recovery(struct bch_fs *c)
goto out;
genradix_for_each_reverse(&c->journal_entries, iter, i)
- if (*i && !(*i)->ignore) {
+ if (!journal_replay_ignore(*i)) {
last_journal_entry = &(*i)->j;
break;
}
@@ -887,7 +702,8 @@ int bch2_fs_recovery(struct bch_fs *c)
genradix_for_each_reverse(&c->journal_entries, iter, i)
if (*i) {
last_journal_entry = &(*i)->j;
- (*i)->ignore = false;
+ (*i)->ignore_blacklisted = false;
+ (*i)->ignore_not_dirty= false;
/*
* This was probably a NO_FLUSH entry,
* so last_seq was garbage - but we know
@@ -923,10 +739,8 @@ use_clean:
c->journal_replay_seq_start = last_seq;
c->journal_replay_seq_end = blacklist_seq - 1;
- if (c->opts.reconstruct_alloc) {
- c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info);
- drop_alloc_keys(&c->journal_keys);
- }
+ if (c->opts.reconstruct_alloc)
+ bch2_reconstruct_alloc(c);
zero_out_btree_mem_ptr(&c->journal_keys);
@@ -950,7 +764,7 @@ use_clean:
bch2_journal_seq_blacklist_add(c,
blacklist_seq, journal_seq);
if (ret) {
- bch_err(c, "error creating new journal seq blacklist entry");
+ bch_err_msg(c, ret, "error creating new journal seq blacklist entry");
goto err;
}
}
@@ -961,9 +775,6 @@ use_clean:
if (ret)
goto err;
- if (c->opts.reconstruct_alloc)
- bch2_journal_log_msg(c, "dropping alloc info");
-
/*
* Skip past versions that might have possibly been used (as nonces),
* but hadn't had their pointers written:
@@ -981,6 +792,12 @@ use_clean:
clear_bit(BCH_FS_fsck_running, &c->flags);
+ /* fsync if we fixed errors */
+ if (test_bit(BCH_FS_errors_fixed, &c->flags)) {
+ bch2_journal_flush_all_pins(&c->journal);
+ bch2_journal_meta(&c->journal);
+ }
+
/* If we fixed errors, verify that fs is actually clean now: */
if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG) &&
test_bit(BCH_FS_errors_fixed, &c->flags) &&
@@ -1015,6 +832,7 @@ use_clean:
}
mutex_lock(&c->sb_lock);
+ struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
bool write_sb = false;
if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) != le16_to_cpu(c->disk_sb.sb->version)) {
@@ -1028,15 +846,18 @@ use_clean:
write_sb = true;
}
- if (!test_bit(BCH_FS_error, &c->flags)) {
- struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
- if (ext &&
- (!bch2_is_zero(ext->recovery_passes_required, sizeof(ext->recovery_passes_required)) ||
- !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent)))) {
- memset(ext->recovery_passes_required, 0, sizeof(ext->recovery_passes_required));
- memset(ext->errors_silent, 0, sizeof(ext->errors_silent));
- write_sb = true;
- }
+ if (!test_bit(BCH_FS_error, &c->flags) &&
+ !bch2_is_zero(ext->errors_silent, sizeof(ext->errors_silent))) {
+ memset(ext->errors_silent, 0, sizeof(ext->errors_silent));
+ write_sb = true;
+ }
+
+ if (c->opts.fsck &&
+ !test_bit(BCH_FS_error, &c->flags) &&
+ c->recovery_pass_done == BCH_RECOVERY_PASS_NR - 1 &&
+ ext->btrees_lost_data) {
+ ext->btrees_lost_data = 0;
+ write_sb = true;
}
if (c->opts.fsck &&
@@ -1077,10 +898,12 @@ use_clean:
out:
bch2_flush_fsck_errs(c);
- if (!c->opts.keep_journal &&
- test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags))
+ if (!c->opts.retain_recovery_info) {
bch2_journal_keys_put_initial(c);
- kfree(clean);
+ bch2_find_btree_nodes_exit(&c->found_btree_nodes);
+ }
+ if (!IS_ERR(clean))
+ kfree(clean);
if (!ret &&
test_bit(BCH_FS_need_delete_dead_snapshots, &c->flags) &&
@@ -1105,6 +928,7 @@ int bch2_fs_initialize(struct bch_fs *c)
int ret;
bch_notice(c, "initializing new filesystem");
+ set_bit(BCH_FS_new_fs, &c->flags);
mutex_lock(&c->sb_lock);
c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done);
@@ -1119,11 +943,11 @@ int bch2_fs_initialize(struct bch_fs *c)
}
mutex_unlock(&c->sb_lock);
- c->curr_recovery_pass = ARRAY_SIZE(recovery_pass_fns);
+ c->curr_recovery_pass = BCH_RECOVERY_PASS_NR;
set_bit(BCH_FS_may_go_rw, &c->flags);
for (unsigned i = 0; i < BTREE_ID_NR; i++)
- bch2_btree_root_alloc(c, i);
+ bch2_btree_root_alloc_fake(c, i, 0);
for_each_member_device(c, ca)
bch2_dev_usage_init(ca);
@@ -1194,7 +1018,7 @@ int bch2_fs_initialize(struct bch_fs *c)
if (ret)
goto err;
- c->recovery_pass_done = ARRAY_SIZE(recovery_pass_fns) - 1;
+ c->recovery_pass_done = BCH_RECOVERY_PASS_NR - 1;
if (enabled_qtypes(c)) {
ret = bch2_fs_quota_read(c);