Merge tag 'bcachefs-2024-02-25' of https://evilpiepirate.org/git/bcachefs

Pull bcachefs fixes from Kent Overstreet:
 "Some more mostly boring fixes, but some not

  User reported ones:

   - the BTREE_ITER_FILTER_SNAPSHOTS one fixes a really nasty
     performance bug; user reported an untar initially taking two
     seconds and then ~2 minutes

   - kill a __GFP_NOFAIL in the buffered read path; this was a leftover
     from the trickier fix to kill __GFP_NOFAIL in readahead, where we
     can't return errors (and have to silently truncate the read
     ourselves).

     bcachefs can't use GFP_NOFAIL for folio state unlike iomap based
     filesystems because our folio state is just barely too big, 2MB
     hugepages cause us to exceed the 2 page threshhold for GFP_NOFAIL.

     additionally, the flags argument was just buggy, we weren't
     supplying GFP_KERNEL previously (!)"

* tag 'bcachefs-2024-02-25' of https://evilpiepirate.org/git/bcachefs:
  bcachefs: fix bch2_save_backtrace()
  bcachefs: Fix check_snapshot() memcpy
  bcachefs: Fix bch2_journal_flush_device_pins()
  bcachefs: fix iov_iter count underflow on sub-block dio read
  bcachefs: Fix BTREE_ITER_FILTER_SNAPSHOTS on inodes btree
  bcachefs: Kill __GFP_NOFAIL in buffered read path
  bcachefs: fix backpointer_to_text() when dev does not exist

fs/bcachefs/backpointers.c

@@ -68,9 +68,11 @@ void bch2_backpointer_to_text(struct printbuf *out, const struct bch_backpointer
 
 void bch2_backpointer_k_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k)
 {
+	if (bch2_dev_exists2(c, k.k->p.inode)) {
 		prt_str(out, "bucket=");
 		bch2_bpos_to_text(out, bp_pos_to_bucket(c, k.k->p));
 		prt_str(out, " ");
+	}
 
 	bch2_backpointer_to_text(out, bkey_s_c_to_backpointer(k).v);
 }

fs/bcachefs/btree_iter.c

@@ -2156,7 +2156,9 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e
 		 * isn't monotonically increasing before FILTER_SNAPSHOTS, and
 		 * that's what we check against in extents mode:
 		 */
-		if (k.k->p.inode > end.inode)
+		if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS)
+			     ? bkey_gt(k.k->p, end)
+			     : k.k->p.inode > end.inode))
 			goto end;
 
 		if (iter->update_path &&

fs/bcachefs/fs-io-buffered.c

@@ -303,18 +303,6 @@ void bch2_readahead(struct readahead_control *ractl)
 	darray_exit(&readpages_iter.folios);
 }
 
-static void __bchfs_readfolio(struct bch_fs *c, struct bch_read_bio *rbio,
-			     subvol_inum inum, struct folio *folio)
-{
-	bch2_folio_create(folio, __GFP_NOFAIL);
-
-	rbio->bio.bi_opf = REQ_OP_READ|REQ_SYNC;
-	rbio->bio.bi_iter.bi_sector = folio_sector(folio);
-	BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0));
-
-	bch2_trans_run(c, (bchfs_read(trans, rbio, inum, NULL), 0));
-}
-
 static void bch2_read_single_folio_end_io(struct bio *bio)
 {
 	complete(bio->bi_private);
@@ -329,6 +317,9 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping)
 	int ret;
 	DECLARE_COMPLETION_ONSTACK(done);
 
+	if (!bch2_folio_create(folio, GFP_KERNEL))
+		return -ENOMEM;
+
 	bch2_inode_opts_get(&opts, c, &inode->ei_inode);
 
 	rbio = rbio_init(bio_alloc_bioset(NULL, 1, REQ_OP_READ, GFP_KERNEL, &c->bio_read),
@@ -336,7 +327,11 @@ int bch2_read_single_folio(struct folio *folio, struct address_space *mapping)
 	rbio->bio.bi_private = &done;
 	rbio->bio.bi_end_io = bch2_read_single_folio_end_io;
 
-	__bchfs_readfolio(c, rbio, inode_inum(inode), folio);
+	rbio->bio.bi_opf = REQ_OP_READ|REQ_SYNC;
+	rbio->bio.bi_iter.bi_sector = folio_sector(folio);
+	BUG_ON(!bio_add_folio(&rbio->bio, folio, folio_size(folio), 0));
+
+	bch2_trans_run(c, (bchfs_read(trans, rbio, inode_inum(inode), NULL), 0));
 	wait_for_completion(&done);
 
 	ret = blk_status_to_errno(rbio->bio.bi_status);

fs/bcachefs/fs-io-direct.c

@@ -88,6 +88,8 @@ static int bch2_direct_IO_read(struct kiocb *req, struct iov_iter *iter)
 		return ret;
 
 	shorten = iov_iter_count(iter) - round_up(ret, block_bytes(c));
+	if (shorten >= iter->count)
+		shorten = 0;
 	iter->count -= shorten;
 
 	bio = bio_alloc_bioset(NULL,

fs/bcachefs/journal_reclaim.c

@@ -892,10 +892,12 @@ int bch2_journal_flush_device_pins(struct journal *j, int dev_idx)
 					 journal_seq_pin(j, seq)->devs);
 		seq++;
 
+		if (replicas.e.nr_devs) {
 			spin_unlock(&j->lock);
 			ret = bch2_mark_replicas(c, &replicas.e);
 			spin_lock(&j->lock);
 		}
+	}
 	spin_unlock(&j->lock);
 err:
 	ret = bch2_replicas_gc_end(c, ret);

fs/bcachefs/snapshot.c

@@ -728,7 +728,7 @@ static int check_snapshot(struct btree_trans *trans,
 		return 0;
 
 	memset(&s, 0, sizeof(s));
-	memcpy(&s, k.v, bkey_val_bytes(k.k));
+	memcpy(&s, k.v, min(sizeof(s), bkey_val_bytes(k.k)));
 
 	id = le32_to_cpu(s.parent);
 	if (id) {

fs/bcachefs/util.c

@@ -289,7 +289,7 @@ int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *task, unsigne
 	do {
 		nr_entries = stack_trace_save_tsk(task, stack->data, stack->size, skipnr + 1);
 	} while (nr_entries == stack->size &&
-		 !(ret = darray_make_room(stack, stack->size * 2)));
+		 !(ret = darray_make_room_gfp(stack, stack->size * 2, gfp)));
 
 	stack->nr = nr_entries;
 	up_read(&task->signal->exec_update_lock);