RDS/IB: add _to_node() macros for numa and use {k,v}malloc_node()

Allocate send/recv rings in memory that is node-local to the HCA.
This significantly helps performance.

Signed-off-by: Andy Grover <andy.grover@oracle.com>
diff --git a/net/rds/ib.h b/net/rds/ib.h
index c506604..4bc3e2f 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -3,6 +3,8 @@
 
 #include <rdma/ib_verbs.h>
 #include <rdma/rdma_cm.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
 #include "rds.h"
 #include "rdma_transport.h"
 
@@ -167,6 +169,10 @@
 	spinlock_t		spinlock;	/* protect the above */
 };
 
+#define pcidev_to_node(pcidev) pcibus_to_node(pcidev->bus)
+#define ibdev_to_node(ibdev) pcidev_to_node(to_pci_dev(ibdev->dma_device))
+#define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev)
+
 /* bits for i_ack_flags */
 #define IB_ACK_IN_FLIGHT	0
 #define IB_ACK_REQUESTED	1