[PATCH] PCI: Run PCI driver initialization on local node

Run PCI driver initialization on local node

Instead of adding messy kmalloc_node()s everywhere run the
PCI driver probe on the node local to the device.

This would not have helped for IDE, but should for
other more clean drivers that do more initialization in probe().
It won't help for drivers that do most of the work
on first open (like many network drivers)

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

3 files changed, 32 insertions, 2 deletions

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index e4115a0d5ba6..414c77299c7d 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/device.h>
+#include <linux/mempolicy.h>
 #include "pci.h"
 
 /*
@@ -163,6 +164,34 @@ const struct pci_device_id *pci_match_device(struct pci_driver *drv,
         return NULL;
 }
 
+static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
+                          const struct pci_device_id *id)
+{
+        int error;
+#ifdef CONFIG_NUMA
+        /* Execute driver initialization on node where the
+           device's bus is attached to.  This way the driver likely
+           allocates its local memory on the right node without
+           any need to change it. */
+        struct mempolicy *oldpol;
+        cpumask_t oldmask = current->cpus_allowed;
+        int node = pcibus_to_node(dev->bus);
+        if (node >= 0 && node_online(node))
+            set_cpus_allowed(current, node_to_cpumask(node));
+        /* And set default memory allocation policy */
+        oldpol = current->mempolicy;
+        current->mempolicy = &default_policy;
+        mpol_get(current->mempolicy);
+#endif
+        error = drv->probe(dev, id);
+#ifdef CONFIG_NUMA
+        set_cpus_allowed(current, oldmask);
+        mpol_free(current->mempolicy);
+        current->mempolicy = oldpol;
+#endif
+        return error;
+}
+
 /**
  * __pci_device_probe()
  * 
@@ -180,7 +209,7 @@ __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev)
 
                 id = pci_match_device(drv, pci_dev);
                 if (id)
-                        error = drv->probe(pci_dev, id);
+                        error = pci_call_probe(drv, pci_dev, id);
                 if (error >= 0) {
                         pci_dev->driver = drv;
                         error = 0;
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 94a46f38c532..58385ee1c0ac 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -155,6 +155,7 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
+extern struct mempolicy default_policy;
 
 #else
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 13492d66b7c8..afa06e184d88 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -88,7 +88,7 @@ static kmem_cache_t *sn_cache;
    policied. */
 static int policy_zone;
 
-static struct mempolicy default_policy = {
+struct mempolicy default_policy = {
         .refcnt = ATOMIC_INIT(1), /* never free it */
         .policy = MPOL_DEFAULT,
 };