drbd: announce FLUSH/FUA capability to upper layers

Unconditionally announce FLUSH/FUA to upper layers.
If the lower layers on either node do not actually support this,
generic_make_request() will deal with it.

If this causes performance regressions on your setup,
make sure there are no volatile caches involved,
and mount -o nobarrier or equivalent.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

4 files changed, 23 insertions, 8 deletions

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 6ace11e..3fbef01 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -876,7 +876,11 @@ int __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector, int size,
 	unsigned int enr, count = 0;
 	struct lc_element *e;
 
-	if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_BIO_SIZE) {
+	/* this should be an empty REQ_FLUSH */
+	if (size == 0)
+		return 0;
+
+	if (size < 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_BIO_SIZE) {
 		dev_err(DEV, "sector: %llus, size: %d\n",
 			(unsigned long long)sector, size);
 		return 0;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 1ee1404..2e0e7fc 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -3636,6 +3636,7 @@ struct drbd_conf *drbd_new_device(unsigned int minor)
 	q->backing_dev_info.congested_data = mdev;
 
 	blk_queue_make_request(q, drbd_make_request);
+	blk_queue_flush(q, REQ_FLUSH | REQ_FUA);
 	/* Setting the max_hw_sectors to an odd value of 8kibyte here
 	   This triggers a max_bio_size message upon first attach or connect */
 	blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 83d9913..c74ca2d 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -277,6 +277,9 @@ static void drbd_pp_free(struct drbd_conf *mdev, struct page *page, int is_net)
 	atomic_t *a = is_net ? &mdev->pp_in_use_by_net : &mdev->pp_in_use;
 	int i;
 
+	if (page == NULL)
+		return;
+
 	if (drbd_pp_vacant > (DRBD_MAX_BIO_SIZE/PAGE_SIZE)*minor_count)
 		i = page_chain_free(page);
 	else {
@@ -316,7 +319,7 @@ struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev,
 				     gfp_t gfp_mask) __must_hold(local)
 {
 	struct drbd_epoch_entry *e;
-	struct page *page;
+	struct page *page = NULL;
 	unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT;
 
 	if (drbd_insert_fault(mdev, DRBD_FAULT_AL_EE))
@@ -329,9 +332,11 @@ struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev,
 		return NULL;
 	}
 
-	page = drbd_pp_alloc(mdev, nr_pages, (gfp_mask & __GFP_WAIT));
-	if (!page)
-		goto fail;
+	if (data_size) {
+		page = drbd_pp_alloc(mdev, nr_pages, (gfp_mask & __GFP_WAIT));
+		if (!page)
+			goto fail;
+	}
 
 	INIT_HLIST_NODE(&e->collision);
 	e->epoch = NULL;
@@ -1270,7 +1275,6 @@ read_in_block(struct drbd_conf *mdev, u64 id, sector_t sector, int data_size) __
 
 	data_size -= dgs;
 
-	ERR_IF(data_size == 0) return NULL;
 	ERR_IF(data_size &  0x1ff) return NULL;
 	ERR_IF(data_size >  DRBD_MAX_BIO_SIZE) return NULL;
 
@@ -1291,6 +1295,9 @@ read_in_block(struct drbd_conf *mdev, u64 id, sector_t sector, int data_size) __
 	if (!e)
 		return NULL;
 
+	if (!data_size)
+		return e;
+
 	ds = data_size;
 	page = e->pages;
 	page_chain_for_each(page) {
@@ -1715,6 +1722,10 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 
 	dp_flags = be32_to_cpu(p->dp_flags);
 	rw |= wire_flags_to_bio(mdev, dp_flags);
+	if (e->pages == NULL) {
+		D_ASSERT(e->size == 0);
+		D_ASSERT(dp_flags & DP_FLUSH);
+	}
 
 	if (dp_flags & DP_MAY_SET_IN_SYNC)
 		e->flags |= EE_MAY_SET_IN_SYNC;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 1f4b2db..910335c 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1111,13 +1111,12 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
 	/*
 	 * what we "blindly" assume:
 	 */
-	D_ASSERT(bio->bi_size > 0);
 	D_ASSERT((bio->bi_size & 0x1ff) == 0);
 
 	/* to make some things easier, force alignment of requests within the
 	 * granularity of our hash tables */
 	s_enr = bio->bi_sector >> HT_SHIFT;
-	e_enr = (bio->bi_sector+(bio->bi_size>>9)-1) >> HT_SHIFT;
+	e_enr = bio->bi_size ? (bio->bi_sector+(bio->bi_size>>9)-1) >> HT_SHIFT : s_enr;
 
 	if (likely(s_enr == e_enr)) {
 		do {