x86/irq: change MSI irq_desc to be more numa aware

Try to get irq_desc on the home node in create_irq_nr().

v2: don't check if we can move it when sparse_irq is not used
v3: use move_irq_des, if that node is not what we want

[ Impact: optimization, make MSI IRQ descriptors more NUMA aware ]

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <49F6559F.7070005@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 14 insertions, 5 deletions

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 82376e021b5d..9cd4806cdf5f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3172,14 +3172,13 @@ static int nr_irqs_gsi = NR_IRQS_LEGACY;
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want)
+unsigned int create_irq_nr(unsigned int irq_want, int node)
 {
         /* Allocate an unused irq */
         unsigned int irq;
         unsigned int new;
         unsigned long flags;
         struct irq_cfg *cfg_new = NULL;
-        int node = cpu_to_node(boot_cpu_id);
         struct irq_desc *desc_new = NULL;
 
         irq = 0;
@@ -3197,6 +3196,13 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
                 if (cfg_new->vector != 0)
                         continue;
+
+#ifdef CONFIG_NUMA_IRQ_DESC
+                /* different node ?*/
+                if (desc_new->node != node)
+                        desc = move_irq_desc(desc, node);
+#endif
+
                 if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
                         irq = new;
                 break;
@@ -3214,11 +3220,12 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 int create_irq(void)
 {
+        int node = cpu_to_node(boot_cpu_id);
         unsigned int irq_want;
         int irq;
 
         irq_want = nr_irqs_gsi;
-        irq = create_irq_nr(irq_want);
+        irq = create_irq_nr(irq_want, node);
 
         if (irq == 0)
                 irq = -1;
@@ -3476,15 +3483,17 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
         unsigned int irq_want;
         struct intel_iommu *iommu = NULL;
         int index = 0;
+        int node;
 
         /* x86 doesn't support multiple MSI yet */
         if (type == PCI_CAP_ID_MSI && nvec > 1)
                 return 1;
 
+        node = dev_to_node(&dev->dev);
         irq_want = nr_irqs_gsi;
         sub_handle = 0;
         list_for_each_entry(msidesc, &dev->msi_list, list) {
-                irq = create_irq_nr(irq_want);
+                irq = create_irq_nr(irq_want, node);
                 if (irq == 0)
                         return -1;
                 irq_want = irq + 1;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index a09baf8f9d99..4b95ddb5304b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -376,7 +376,7 @@ extern void set_irq_noprobe(unsigned int irq);
 extern void set_irq_probe(unsigned int irq);
 
 /* Handle dynamic irq creation and destruction */
-extern unsigned int create_irq_nr(unsigned int irq_want);
+extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);