Merge tag 'bcachefs-2023-11-5' of https://evilpiepirate.org/git/bcachefs

Pull more bcachefs updates from Kent Overstreet:
 "Here's the second big bcachefs pull request. This brings your tree up
  to date with my master branch, which is what existing bcachefs users
  are currently running.

  New features:
   - rebalance_work btree (and metadata version 1.3): the rebalance
     thread no longer has to scan to find extents that need processing -
     big scalability improvement.
   - sb_errors superblock section: this adds counters for each fsck
     error type, since filesystem creation, along with the date of the
     most recent error. It'll get us better bug reports (since users do
     not typically report errors that fsck was able to fix), and I might
     add telemetry for this in the future.

  Fixes include:
   - multiple snapshot deletion fixes
   - members_v2 fixups
   - deleted_inodes btree fixes
   - copygc thread no longer spins when a device is full but has no
     fragmented buckets (i.e. rebalance needs to move data around
     instead)
   - a fix for a memory reclaim issue with the btree key cache: we're
     now careful not to hold the srcu read lock that blocks key cache
     reclaim for too long
   - an early allocator locking fix, from Brian
   - endianness fixes, from Brian
   - CONFIG_BCACHEFS_DEBUG_TRANSACTIONS no longer defaults to y, a big
     performance improvement on multithreaded workloads"

* tag 'bcachefs-2023-11-5' of https://evilpiepirate.org/git/bcachefs: (70 commits)
  bcachefs: Improve stripe checksum error message
  bcachefs: Simplify, fix bch2_backpointer_get_key()
  bcachefs: kill thing_it_points_to arg to backpointer_not_found()
  bcachefs: bch2_ec_read_extent() now takes btree_trans
  bcachefs: bch2_stripe_to_text() now prints ptr gens
  bcachefs: Don't iterate over journal entries just for btree roots
  bcachefs: Break up bch2_journal_write()
  bcachefs: Replace ERANGE with private error codes
  bcachefs: bkey_copy() is no longer a macro
  bcachefs: x-macro-ify inode flags enum
  bcachefs: Convert bch2_fs_open() to darray
  bcachefs: Move __bch2_members_v2_get_mut to sb-members.h
  bcachefs: bch2_prt_datetime()
  bcachefs: CONFIG_BCACHEFS_DEBUG_TRANSACTIONS no longer defaults to y
  bcachefs: Add a comment for BTREE_INSERT_NOJOURNAL usage
  bcachefs: rebalance_work btree is not a snapshots btree
  bcachefs: Add missing printk newlines
  bcachefs: Fix recovery when forced to use JSET_NO_FLUSH journal entry
  bcachefs: .get_parent() should return an error pointer
  bcachefs: Fix bch2_delete_dead_inodes()
  ...

107 files changed, 3966 insertions, 2291 deletions

diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig
index df13a4f9a6e3..c08c2c7d6fbb 100644
--- a/fs/bcachefs/Kconfig
+++ b/fs/bcachefs/Kconfig
@@ -24,7 +24,6 @@ config BCACHEFS_FS
 	select XXHASH
 	select SRCU
 	select SYMBOLIC_ERRNAME
-	select MEAN_AND_VARIANCE
 	help
 	The bcachefs filesystem - a modern, copy on write filesystem, with
 	support for multiple devices, compression, checksumming, etc.
@@ -42,7 +41,6 @@ config BCACHEFS_POSIX_ACL
 config BCACHEFS_DEBUG_TRANSACTIONS
 	bool "bcachefs runtime info"
 	depends on BCACHEFS_FS
-	default y
 	help
 	This makes the list of running btree transactions available in debugfs.
 
@@ -78,7 +76,7 @@ config BCACHEFS_NO_LATENCY_ACCT
 config MEAN_AND_VARIANCE_UNIT_TEST
 	tristate "mean_and_variance unit tests" if !KUNIT_ALL_TESTS
 	depends on KUNIT
-	select MEAN_AND_VARIANCE
+	depends on BCACHEFS_FS
 	default KUNIT_ALL_TESTS
 	help
 	  This option enables the kunit tests for mean_and_variance module.
diff --git a/fs/bcachefs/Makefile b/fs/bcachefs/Makefile
index 0749731b9072..45b64f89258c 100644
--- a/fs/bcachefs/Makefile
+++ b/fs/bcachefs/Makefile
@@ -70,6 +70,7 @@ bcachefs-y		:=	\
 	reflink.o		\
 	replicas.o		\
 	sb-clean.o		\
+	sb-errors.o		\
 	sb-members.o		\
 	siphash.o		\
 	six.o			\
diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index 2d516207e223..1fec0e67891f 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -192,123 +192,109 @@ static unsigned bch_alloc_v1_val_u64s(const struct bch_alloc *a)
 	return DIV_ROUND_UP(bytes, sizeof(u64));
 }
 
-int bch2_alloc_v1_invalid(const struct bch_fs *c, struct bkey_s_c k,
+int bch2_alloc_v1_invalid(struct bch_fs *c, struct bkey_s_c k,
 			  enum bkey_invalid_flags flags,
 			  struct printbuf *err)
 {
 	struct bkey_s_c_alloc a = bkey_s_c_to_alloc(k);
+	int ret = 0;
 
 	/* allow for unknown fields */
-	if (bkey_val_u64s(a.k) < bch_alloc_v1_val_u64s(a.v)) {
-		prt_printf(err, "incorrect value size (%zu < %u)",
-		       bkey_val_u64s(a.k), bch_alloc_v1_val_u64s(a.v));
-		return -BCH_ERR_invalid_bkey;
-	}
-
-	return 0;
+	bkey_fsck_err_on(bkey_val_u64s(a.k) < bch_alloc_v1_val_u64s(a.v), c, err,
+			 alloc_v1_val_size_bad,
+			 "incorrect value size (%zu < %u)",
+			 bkey_val_u64s(a.k), bch_alloc_v1_val_u64s(a.v));
+fsck_err:
+	return ret;
 }
 
-int bch2_alloc_v2_invalid(const struct bch_fs *c, struct bkey_s_c k,
+int bch2_alloc_v2_invalid(struct bch_fs *c, struct bkey_s_c k,
 			  enum bkey_invalid_flags flags,
 			  struct printbuf *err)
 {
 	struct bkey_alloc_unpacked u;
+	int ret = 0;
 
-	if (bch2_alloc_unpack_v2(&u, k)) {
-		prt_printf(err, "unpack error");
-		return -BCH_ERR_invalid_bkey;
-	}
-
-	return 0;
+	bkey_fsck_err_on(bch2_alloc_unpack_v2(&u, k), c, err,
+			 alloc_v2_unpack_error,
+			 "unpack error");
+fsck_err:
+	return ret;
 }
 
-int bch2_alloc_v3_invalid(const struct bch_fs *c, struct bkey_s_c k,
+int bch2_alloc_v3_invalid(struct bch_fs *c, struct bkey_s_c k,
 			  enum bkey_invalid_flags flags,
 			  struct printbuf *err)
 {
 	struct bkey_alloc_unpacked u;
+	int ret = 0;
 
-	if (bch2_alloc_unpack_v3(&u, k)) {
-		prt_printf(err, "unpack error");
-		return -BCH_ERR_invalid_bkey;
-	}
-
-	return 0;
+	bkey_fsck_err_on(bch2_alloc_unpack_v3(&u, k), c, err,
+			 alloc_v2_unpack_error,
+			 "unpack error");
+fsck_err:
+	return ret;
 }
 
-int bch2_alloc_v4_invalid(const struct bch_fs *c, struct bkey_s_c k,
+int bch2_alloc_v4_invalid(struct bch_fs *c, struct bkey_s_c k,
 			  enum bkey_invalid_flags flags, struct printbuf *err)
 {
 	struct bkey_s_c_alloc_v4 a = bkey_s_c_to_alloc_v4(k);
+	int ret = 0;
 
-	if (alloc_v4_u64s(a.v) > bkey_val_u64s(k.k)) {
-		prt_printf(err, "bad val size (%u > %zu)",
-		       alloc_v4_u64s(a.v), bkey_val_u64s(k.k));
-		return -BCH_ERR_invalid_bkey;
-	}
+	bkey_fsck_err_on(alloc_v4_u64s(a.v) > bkey_val_u64s(k.k), c, err,
+			 alloc_v4_val_size_bad,
+			 "bad val size (%u > %zu)",
+			 alloc_v4_u64s(a.v), bkey_val_u64s(k.k));
 
-	if (!BCH_ALLOC_V4_BACKPOINTERS_START(a.v) &&
-	    BCH_ALLOC_V4_NR_BACKPOINTERS(a.v)) {
-		prt_printf(err, "invalid backpointers_start");
-		return -BCH_ERR_invalid_bkey;
-	}
+	bkey_fsck_err_on(!BCH_ALLOC_V4_BACKPOINTERS_START(a.v) &&
+			 BCH_ALLOC_V4_NR_BACKPOINTERS(a.v), c, err,
+			 alloc_v4_backpointers_start_bad,
+			 "invalid backpointers_start");
 
-	if (alloc_data_type(*a.v, a.v->data_type) != a.v->data_type) {
-		prt_printf(err, "invalid data type (got %u should be %u)",
-		       a.v->data_type, alloc_data_type(*a.v, a.v->data_type));
-		return -BCH_ERR_invalid_bkey;
-	}
+	bkey_fsck_err_on(alloc_data_type(*a.v, a.v->data_type) != a.v->data_type, c, err,
+			 alloc_key_data_type_bad,
+			 "invalid data type (got %u should be %u)",
+			 a.v->data_type, alloc_data_type(*a.v, a.v->data_type));
 
 	switch (a.v->data_type) {
 	case BCH_DATA_free:
 	case BCH_DATA_need_gc_gens:
 	case BCH_DATA_need_discard:
-		if (a.v->dirty_sectors ||
-		    a.v->cached_sectors ||
-		    a.v->stripe) {
-			prt_printf(err, "empty data type free but have data");
-			return -BCH_ERR_invalid_bkey;
-		}
+		bkey_fsck_err_on(a.v->dirty_sectors ||
+				 a.v->cached_sectors ||
+				 a.v->stripe, c, err,
+				 alloc_key_empty_but_have_data,
+				 "empty data type free but have data");
 		break;
 	case BCH_DATA_sb:
 	case BCH_DATA_journal:
 	case BCH_DATA_btree:
 	case BCH_DATA_user:
 	case BCH_DATA_parity:
-		if (!a.v->dirty_sectors) {
-			prt_printf(err, "data_type %s but dirty_sectors==0",
-			       bch2_data_types[a.v->data_type]);
-			return -BCH_ERR_invalid_bkey;
-		}
+		bkey_fsck_err_on(!a.v->dirty_sectors, c, err,
+				 alloc_key_dirty_sectors_0,
+				 "data_type %s but dirty_sectors==0",
+				 bch2_data_types[a.v->data_type]);
 		break;
 	case BCH_DATA_cached:
-		if (!a.v->cached_sectors ||
-		    a.v->dirty_sectors ||
-		    a.v->stripe) {
-			prt_printf(err, "data type inconsistency");
-			return -BCH_ERR_invalid_bkey;
-		}
-
-		if (!a.v->io_time[READ] &&
-		    c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_to_lru_refs) {
-			prt_printf(err, "cached bucket with read_time == 0");
-			return -BCH_ERR_invalid_bkey;
-		}
+		bkey_fsck_err_on(!a.v->cached_sectors ||
+				 a.v->dirty_sectors ||
+				 a.v->stripe, c, err,
+				 alloc_key_cached_inconsistency,
+				 "data type inconsistency");
+
+		bkey_fsck_err_on(!a.v->io_time[READ] &&
+				 c->curr_recovery_pass > BCH_RECOVERY_PASS_check_alloc_to_lru_refs,
+				 c, err,
+				 alloc_key_cached_but_read_time_zero,
+				 "cached bucket with read_time == 0");
 		break;
 	case BCH_DATA_stripe:
 		break;
 	}