[PATCH v3 1/4] scsi: scan: allocate sdev and starget on the NUMA node of the host adapter

[Sumit Saxena <sumit.saxena@broadcom.com>]

From: James Rizzo <james.rizzo@broadcom.com>

When a host adapter is attached to a specific NUMA node, allocating
scsi_device and scsi_target via kzalloc() may place them on a remote
node.  All hot-path I/O accesses to these structures then cross the NUMA
interconnect, adding latency and consuming inter-node bandwidth.

Use kzalloc_node() with dev_to_node(shost->dma_dev) so allocations land
on the same node as the HBA, reducing cross-node traffic and improving
I/O performance on NUMA systems.

Signed-off-by: James Rizzo <james.rizzo@broadcom.com>
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
---
 drivers/scsi/scsi_scan.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index e27da038603a..121a14d5fdb8 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -34,6 +34,7 @@
 #include <linux/kthread.h>
 #include <linux/spinlock.h>
 #include <linux/async.h>
+#include <linux/topology.h>
 #include <linux/slab.h>
 #include <linux/unaligned.h>
 
@@ -287,8 +288,8 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
 	struct queue_limits lim;
 
-	sdev = kzalloc(sizeof(*sdev) + shost->transportt->device_size,
-		       GFP_KERNEL);
+	sdev = kzalloc_node(sizeof(*sdev) + shost->transportt->device_size,
+		       GFP_KERNEL, dev_to_node(shost->dma_dev));
 	if (!sdev)
 		goto out;
 
@@ -502,7 +503,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	struct scsi_target *found_target;
 	int error, ref_got;
 
-	starget = kzalloc(size, GFP_KERNEL);
+	starget = kzalloc_node(size, GFP_KERNEL, dev_to_node(shost->dma_dev));
 	if (!starget) {
 		printk(KERN_ERR "%s: allocation failure\n", __func__);
 		return NULL;
-- 
2.43.7