intr_remap: Allocate intr-remapping table using numa locality info

Allocate intr-remapping table using numa locality info. On platforms
having remapping hardware units span different nodes, this enables
optimized intr-remapping table entry access by remapping hardware.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 0ed78a764ded2e10ede6f3f109ab481bca73be42..fccf0e2fcba330f8959ace4b3b1c9e99ff71c0c1 100644 (file)
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -548,7 +548,8 @@ static int setup_intr_remapping(struct intel_iommu *iommu, int mode)
        if (!iommu->ir_table)
                return -ENOMEM;
 
-       pages = alloc_pages(GFP_ATOMIC | __GFP_ZERO, INTR_REMAP_PAGE_ORDER);
+       pages = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
+                                INTR_REMAP_PAGE_ORDER);
 
        if (!pages) {
                printk(KERN_ERR "failed to allocate pages of order %d\n",