scsi: target: iblock: Add backend plug/unplug callouts

This patch adds plug/unplug callouts for iblock. For an initiator driver
like iSCSI which wants to pass multiple cmds to its xmit thread instead of
one cmd at a time, this increases IOPS by around 10% with vhost-scsi
(combined with the last patches we can see a total 40-50% increase). For
driver combos like tcm_loop and faster drivers like the iSER initiator, we
can still see IOPS increase by 20-30% when tcm_loop's nr_hw_queues setting
is also increased.

Link: https://lore.kernel.org/r/20210227170006.5077-23-michael.christie@oracle.com
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 43 insertions, 1 deletions

diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index ee3d52061281..90e1c65ad4b6 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -61,9 +61,18 @@ static struct se_device *iblock_alloc_device(struct se_hba *hba, const char *nam
 		return NULL;
 	}
 
+	ib_dev->ibd_plug = kcalloc(nr_cpu_ids, sizeof(*ib_dev->ibd_plug),
+				   GFP_KERNEL);
+	if (!ib_dev->ibd_plug)
+		goto free_dev;
+
 	pr_debug( "IBLOCK: Allocated ib_dev for %s\n", name);
 
 	return &ib_dev->dev;
+
+free_dev:
+	kfree(ib_dev);
+	return NULL;
 }
 
 static int iblock_configure_device(struct se_device *dev)
@@ -171,6 +180,7 @@ static void iblock_dev_call_rcu(struct rcu_head *p)
 	struct se_device *dev = container_of(p, struct se_device, rcu_head);
 	struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
 
+	kfree(ib_dev->ibd_plug);
 	kfree(ib_dev);
 }
 
@@ -188,6 +198,33 @@ static void iblock_destroy_device(struct se_device *dev)
 	bioset_exit(&ib_dev->ibd_bio_set);
 }
 
+static struct se_dev_plug *iblock_plug_device(struct se_device *se_dev)
+{
+	struct iblock_dev *ib_dev = IBLOCK_DEV(se_dev);
+	struct iblock_dev_plug *ib_dev_plug;
+
+	/*
+	 * Each se_device has a per cpu work this can be run from. Wwe
+	 * shouldn't have multiple threads on the same cpu calling this
+	 * at the same time.
+	 */
+	ib_dev_plug = &ib_dev->ibd_plug[smp_processor_id()];
+	if (test_and_set_bit(IBD_PLUGF_PLUGGED, &ib_dev_plug->flags))
+		return NULL;
+
+	blk_start_plug(&ib_dev_plug->blk_plug);
+	return &ib_dev_plug->se_plug;
+}
+
+static void iblock_unplug_device(struct se_dev_plug *se_plug)
+{
+	struct iblock_dev_plug *ib_dev_plug = container_of(se_plug,
+					struct iblock_dev_plug, se_plug);
+
+	blk_finish_plug(&ib_dev_plug->blk_plug);
+	clear_bit(IBD_PLUGF_PLUGGED, &ib_dev_plug->flags);
+}
+
 static unsigned long long iblock_emulate_read_cap_with_block_size(
 	struct se_device *dev,
 	struct block_device *bd,
@@ -335,7 +372,10 @@ static void iblock_submit_bios(struct bio_list *list)
 {
 	struct blk_plug plug;
 	struct bio *bio;
-
+	/*
+	 * The block layer handles nested plugs, so just plug/unplug to handle
+	 * fabric drivers that didn't support batching and multi bio cmds.
+	 */
 	blk_start_plug(&plug);
 	while ((bio = bio_list_pop(list)))
 		submit_bio(bio);
@@ -867,6 +907,8 @@ static const struct target_backend_ops iblock_ops = {
 	.configure_device	= iblock_configure_device,
 	.destroy_device		= iblock_destroy_device,
 	.free_device		= iblock_free_device,
+	.plug_device		= iblock_plug_device,
+	.unplug_device		= iblock_unplug_device,
 	.parse_cdb		= iblock_parse_cdb,
 	.set_configfs_dev_params = iblock_set_configfs_dev_params,
 	.show_configfs_dev_params = iblock_show_configfs_dev_params,