dm integrity: fix flush with external metadata device

With external metadata device, flush requests are not passed down to the
data device.

Fix this by submitting the flush request in dm_integrity_flush_buffers. In
order to not degrade performance, we overlap the data device flush with
the metadata device flush.

Reported-by: Lukas Straub <lukasstraub2@web.de>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Author: Mikulas Patocka

drivers/md/dm-bufio.c

@@ -1534,6 +1534,12 @@ sector_t dm_bufio_get_device_size(struct dm_bufio_client *c)
 }
 EXPORT_SYMBOL_GPL(dm_bufio_get_device_size);
 
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c)
+{
+	return c->dm_io;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client);
+
 sector_t dm_bufio_get_block_number(struct dm_buffer *b)
 {
 	return b->block;

drivers/md/dm-integrity.c

@@ -1379,12 +1379,52 @@ static int dm_integrity_rw_tag(struct dm_integrity_c *ic, unsigned char *tag, se
 #undef MAY_BE_HASH
 }
 
-static void dm_integrity_flush_buffers(struct dm_integrity_c *ic)
+struct flush_request {
+	struct dm_io_request io_req;
+	struct dm_io_region io_reg;
+	struct dm_integrity_c *ic;
+	struct completion comp;
+};
+
+static void flush_notify(unsigned long error, void *fr_)
+{
+	struct flush_request *fr = fr_;
+	if (unlikely(error != 0))
+		dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO);
+	complete(&fr->comp);
+}
+
+static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data)
 {
 	int r;
+
+	struct flush_request fr;
+
+	if (!ic->meta_dev)
+		flush_data = false;
+	if (flush_data) {
+		fr.io_req.bi_op = REQ_OP_WRITE,
+		fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+		fr.io_req.mem.type = DM_IO_KMEM,
+		fr.io_req.mem.ptr.addr = NULL,
+		fr.io_req.notify.fn = flush_notify,
+		fr.io_req.notify.context = &fr;
+		fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
+		fr.io_reg.bdev = ic->dev->bdev,
+		fr.io_reg.sector = 0,
+		fr.io_reg.count = 0,
+		fr.ic = ic;
+		init_completion(&fr.comp);
+		r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
+		BUG_ON(r);
+	}
+
 	r = dm_bufio_write_dirty_buffers(ic->bufio);
 	if (unlikely(r))
 		dm_integrity_io_error(ic, "writing tags", r);
+
+	if (flush_data)
+		wait_for_completion(&fr.comp);
 }
 
 static void sleep_on_endio_wait(struct dm_integrity_c *ic)
@@ -2110,7 +2150,7 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
 
 	if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) {
 		integrity_metadata(&dio->work);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, false);
 
 		dio->in_flight = (atomic_t)ATOMIC_INIT(1);
 		dio->completion = NULL;
@@ -2195,7 +2235,7 @@ static void integrity_commit(struct work_struct *w)
 	flushes = bio_list_get(&ic->flush_bio_list);
 	if (unlikely(ic->mode != 'J')) {
 		spin_unlock_irq(&ic->endio_wait.lock);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 		goto release_flush_bios;
 	}
 
@@ -2409,7 +2449,7 @@ static void do_journal_write(struct dm_integrity_c *ic, unsigned write_start,
 	complete_journal_op(&comp);
 	wait_for_completion_io(&comp.comp);
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, true);
 }
 
 static void integrity_writer(struct work_struct *w)
@@ -2451,7 +2491,7 @@ static void recalc_write_super(struct dm_integrity_c *ic)
 {
 	int r;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 	if (dm_integrity_failed(ic))
 		return;
 
@@ -2654,7 +2694,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	unsigned long limit;
 	struct bio *bio;
 
-	dm_integrity_flush_buffers(ic);
+	dm_integrity_flush_buffers(ic, false);
 
 	range.logical_sector = 0;
 	range.n_sectors = ic->provided_data_sectors;
@@ -2663,9 +2703,7 @@ static void bitmap_flush_work(struct work_struct *work)
 	add_new_range_and_wait(ic, &range);
 	spin_unlock_irq(&ic->endio_wait.lock);
 
-	dm_integrity_flush_buffers(ic);
-	if (ic->meta_dev)
-		blkdev_issue_flush(ic->dev->bdev, GFP_NOIO);
+	dm_integrity_flush_buffers(ic, true);
 
 	limit = ic->provided_data_sectors;
 	if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
@@ -2934,11 +2972,11 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
 		if (ic->meta_dev)
 			queue_work(ic->writer_wq, &ic->writer_work);
 		drain_workqueue(ic->writer_wq);
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 	}
 
 	if (ic->mode == 'B') {
-		dm_integrity_flush_buffers(ic);
+		dm_integrity_flush_buffers(ic, true);
 #if 1
 		/* set to 0 to test bitmap replay code */
 		init_journal(ic, 0, ic->journal_sections, 0);

include/linux/dm-bufio.h

@@ -150,6 +150,7 @@ void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n);
 
 unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
 sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c);
 sector_t dm_bufio_get_block_number(struct dm_buffer *b);
 void *dm_bufio_get_block_data(struct dm_buffer *b);
 void *dm_bufio_get_aux_data(struct dm_buffer *b);