Merge tag 'bcachefs-2025-05-08' of git://evilpiepirate.org/bcachefsHEADmaster

Pull bcachefs fixes from Kent Overstreet:

 - Some fixes to help with filesystem analysis: ensure superblock
   error count gets written if we go ERO, don't discard the journal
   aggressively (so it's available for list_journal -a)

 - Fix lost wakeup on arm causing us to get stuck when reading btree
   nodes

 - Fix fsck failing to exit on ctrl-c

 - An additional fix for filesystems with misaligned bucket sizes: we
   now ensure that allocations are properly aligned

 - Setting background target but not promote target will now leave that
   data cached on the foreground target, as it used to

 - Revert a change to when we allocate the VFS superblock, this was done
   for implementing blk_holder_ops but ended up not being needed, and
   allocating a superblock and not setting SB_BORN while we do recovery
   caused sync() calls and other things to hang

 - Assorted fixes for harmless error messages that caused concern to
   users

* tag 'bcachefs-2025-05-08' of git://evilpiepirate.org/bcachefs:
  bcachefs: Don't aggressively discard the journal
  bcachefs: Ensure superblock gets written when we go ERO
  bcachefs: Filter out harmless EROFS error messages
  bcachefs: journal_shutdown is EROFS, not EIO
  bcachefs: Call bch2_fs_start before getting vfs superblock
  bcachefs: fix hung task timeout in journal read
  bcachefs: Add missing barriers before wake_up_bit()
  bcachefs: Ensure proper write alignment
  bcachefs: Improve want_cached_ptr()
  bcachefs: thread_with_stdio: fix spinning instead of exiting

12 files changed, 55 insertions, 19 deletions

diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c
index effafc3e0ced..7ec022e9361a 100644
--- a/fs/bcachefs/alloc_foreground.c
+++ b/fs/bcachefs/alloc_foreground.c
@@ -1422,11 +1422,31 @@ alloc_done:
 
 	wp->sectors_free = UINT_MAX;
 
-	open_bucket_for_each(c, &wp->ptrs, ob, i)
+	open_bucket_for_each(c, &wp->ptrs, ob, i) {
+		/*
+		 * Ensure proper write alignment - either due to misaligned
+		 * bucket sizes (from buggy bcachefs-tools), or writes that mix
+		 * logical/physical alignment:
+		 */
+		struct bch_dev *ca = ob_dev(c, ob);
+		u64 offset = bucket_to_sector(ca, ob->bucket) +
+			ca->mi.bucket_size -
+			ob->sectors_free;
+		unsigned align = round_up(offset, block_sectors(c)) - offset;
+
+		ob->sectors_free = max_t(int, 0, ob->sectors_free - align);
+
 		wp->sectors_free = min(wp->sectors_free, ob->sectors_free);
+	}
 
 	wp->sectors_free = rounddown(wp->sectors_free, block_sectors(c));
 
+	/* Did alignment use up space in an open_bucket? */
+	if (unlikely(!wp->sectors_free)) {
+		bch2_alloc_sectors_done(c, wp);
+		goto retry;
+	}
+
 	BUG_ON(!wp->sectors_free || wp->sectors_free == UINT_MAX);
 
 	return 0;
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 5fd4a58d2ad2..60782f3e5aec 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -41,6 +41,7 @@ void bch2_btree_node_io_unlock(struct btree *b)
 
 	clear_btree_node_write_in_flight_inner(b);
 	clear_btree_node_write_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
 }
 
@@ -1400,6 +1401,7 @@ start:
 
 	printbuf_exit(&buf);
 	clear_btree_node_read_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 }
 
@@ -1595,6 +1597,7 @@ fsck_err:
 	printbuf_exit(&buf);
 
 	clear_btree_node_read_in_flight(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 }
 
@@ -1721,6 +1724,7 @@ void bch2_btree_node_read(struct btree_trans *trans, struct btree *b,
 		set_btree_node_read_error(b);
 		bch2_btree_lost_data(c, b->c.btree_id);
 		clear_btree_node_read_in_flight(b);
+		smp_mb__after_atomic();
 		wake_up_bit(&b->flags, BTREE_NODE_read_in_flight);
 		printbuf_exit(&buf);
 		return;
@@ -2061,8 +2065,10 @@ static void __btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start
 
 	if (new & (1U << BTREE_NODE_write_in_flight))
 		__bch2_btree_node_write(c, b, BTREE_WRITE_ALREADY_STARTED|type);
-	else
+	else {
+		smp_mb__after_atomic();
 		wake_up_bit(&b->flags, BTREE_NODE_write_in_flight);
+	}
 }
 
 static void btree_node_write_done(struct bch_fs *c, struct btree *b, u64 start_time)
@@ -2175,6 +2181,7 @@ static void btree_node_write_endio(struct bio *bio)
 	}
 
 	clear_btree_node_write_in_flight_inner(b);
+	smp_mb__after_atomic();
 	wake_up_bit(&b->flags, BTREE_NODE_write_in_flight_inner);
 	INIT_WORK(&wb->work, btree_node_write_work);
 	queue_work(c->btree_io_complete_wq, &wb->work);
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 8d75b27a1418..af1532de4a37 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -44,6 +44,7 @@ static inline void bucket_unlock(struct bucket *b)
 	BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
 
 	clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &b->lock);
+	smp_mb__after_atomic();
 	wake_up_bit((void *) &b->lock, BUCKET_LOCK_BITNR);
 }
 
diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h
index 62d27e04d763..51893e1ee874 100644
--- a/fs/bcachefs/ec.h
+++ b/fs/bcachefs/ec.h
@@ -160,6 +160,7 @@ static inline void gc_stripe_unlock(struct gc_stripe *s)
 	BUILD_BUG_ON(!((union ulong_byte_assert) { .ulong = 1UL << BUCKET_LOCK_BITNR }).byte);
 
 	clear_bit_unlock(BUCKET_LOCK_BITNR, (void *) &s->lock);
+	smp_mb__after_atomic();
 	wake_up_bit((void *) &s->lock, BUCKET_LOCK_BITNR);
 }
 
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index a615e4852ded..d9ebffa5b3a2 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -269,7 +269,7 @@
 	x(BCH_ERR_invalid_sb,		invalid_sb_downgrade)			\
 	x(BCH_ERR_invalid,		invalid_bkey)				\
 	x(BCH_ERR_operation_blocked,    nocow_lock_blocked)			\
-	x(EIO,				journal_shutdown)			\
+	x(EROFS,			journal_shutdown)			\
 	x(EIO,				journal_flush_err)			\
 	x(EIO,				journal_write_err)			\
 	x(EIO,				btree_node_read_err)			\
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index dca2b8425cc0..e597fb9c9823 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -1056,8 +1056,9 @@ bch2_extent_has_ptr(struct bkey_s_c k1, struct extent_ptr_decoded p1, struct bke
 static bool want_cached_ptr(struct bch_fs *c, struct bch_io_opts *opts,
 			    struct bch_extent_ptr *ptr)
 {
-	if (!opts->promote_target ||
-	    !bch2_dev_in_target(c, ptr->dev, opts->promote_target))
+	unsigned target = opts->promote_target ?: opts->foreground_target;
+
+	if (target && !bch2_dev_in_target(c, ptr->dev, target))
 		return false;
 
 	struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev);
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 113db85b6ef9..b6801861c66f 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -2502,10 +2502,9 @@ static int bch2_fs_get_tree(struct fs_context *fc)
 
 	bch2_opts_apply(&c->opts, opts);
 
-	/*
-	 * need to initialise sb and set c->vfs_sb _before_ starting fs,
-	 * for blk_holder_ops
-	 */
+	ret = bch2_fs_start(c);
+	if (ret)
+		goto err_stop_fs;
 
 	sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c);
 	ret = PTR_ERR_OR_ZERO(sb);
@@ -2567,10 +2566,6 @@ got_sb:
 
 	sb->s_shrink->seeks = 0;
 
-	ret = bch2_fs_start(c);
-	if (ret)
-		goto err_put_super;
-
 #ifdef CONFIG_UNICODE
 	sb->s_encoding = c->cf_encoding;
 #endif
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 63cdf885c9e2..ded18a94ed02 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -19,6 +19,7 @@
 
 #include <linux/ioprio.h>
 #include <linux/string_choices.h>
+#include <linux/sched/sysctl.h>
 
 void bch2_journal_pos_from_member_info_set(struct bch_fs *c)
 {
@@ -1262,7 +1263,8 @@ int bch2_journal_read(struct bch_fs *c,
 			degraded = true;
 	}
 
-	closure_sync(&jlist.cl);
+	while (closure_sync_timeout(&jlist.cl, sysctl_hung_task_timeout_secs * HZ / 2))
+		;
 
 	if (jlist.ret)
 		return jlist.ret;
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index ea670c3c43d8..976464d8a695 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -266,10 +266,11 @@ out:
 
 static bool should_discard_bucket(struct journal *j, struct journal_device *ja)
 {
-	bool ret;
-
 	spin_lock(&j->lock);
-	ret = ja->discard_idx != ja->dirty_idx_ondisk;
+	unsigned min_free = max(4, ja->nr / 8);
+
+	bool ret = bch2_journal_dev_buckets_available(j, ja, journal_space_discarded) < min_free &&
+		ja->discard_idx != ja->dirty_idx_ondisk;
 	spin_unlock(&j->lock);
 
 	return ret;
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index fc396b9fa754..dfdbb9259985 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -784,7 +784,8 @@ static int __bch2_move_data_phys(struct moving_context *ctxt,
 		goto err;
 
 	ret = bch2_btree_write_buffer_tryflush(trans);
-	bch_err_msg(c, ret, "flushing btree write buffer");
+	if (!bch2_err_matches(ret, EROFS))
+		bch_err_msg(c, ret, "flushing btree write buffer");
 	if (ret)
 		goto err;
 
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 27943082c093..84a37d971ffd 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -377,6 +377,11 @@ void bch2_fs_read_only(struct bch_fs *c)
 		bch_verbose(c, "marking filesystem clean");
 		bch2_fs_mark_clean(c);
 	} else {
+		/* Make sure error counts/counters are persisted */
+		mutex_lock(&c->sb_lock);
+		bch2_write_super(c);
+		mutex_unlock(&c->sb_lock);
+
 		bch_verbose(c, "done going read-only, filesystem not clean");
 	}
 }
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index dea73bc1cb51..314a24d15d4e 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -455,8 +455,10 @@ ssize_t bch2_stdio_redirect_vprintf(struct stdio_redirect *stdio, bool nonblocki
 	struct stdio_buf *buf = &stdio->output;
 	unsigned long flags;
 	ssize_t ret;
-
 again:
+	if (stdio->done)
+		return -EPIPE;
+
 	spin_lock_irqsave(&buf->lock, flags);
 	ret = bch2_darray_vprintf(&buf->buf, GFP_NOWAIT, fmt, args);
 	spin_unlock_irqrestore(&buf->lock, flags);