x86/irq: use move_irq_desc() in create_irq_nr()

move_irq_desc() will try to move irq_desc to the home node if
the allocated one is not correct, in create_irq_nr().

( This can happen on devices that are on different nodes that
  are using MSI, when drivers are loaded and unloaded randomly. )

v2: fix non-smp build
v3: add NUMA_IRQ_DESC to eliminate #ifdefs

[ Impact: improve irq descriptor locality on NUMA systems ]

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: <49F95EAE.2050903@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 15 insertions, 8 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e1b2543f8ed3..674e21e9f0a0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -274,6 +274,10 @@ config SPARSE_IRQ
 
           If you don't know what to do here, say N.
 
+config NUMA_IRQ_DESC
+        def_bool y
+        depends on SPARSE_IRQ && NUMA
+
 config X86_MPPARSE
         bool "Enable MPS table" if ACPI
         default y
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9cd4806cdf5f..e583291fe6c3 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3197,11 +3197,7 @@ unsigned int create_irq_nr(unsigned int irq_want, int node)
                 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
+                desc_new = move_irq_desc(desc_new, node);
 
                 if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
                         irq = new;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 4b95ddb5304b..eedbb8e5e0cc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -206,9 +206,16 @@ extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc
 
 #ifndef CONFIG_SPARSE_IRQ
 extern struct irq_desc irq_desc[NR_IRQS];
-#else /* CONFIG_SPARSE_IRQ */
+#endif
+
+#ifdef CONFIG_NUMA_IRQ_DESC
 extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
-#endif /* CONFIG_SPARSE_IRQ */
+#else
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
+        return desc;
+}
+#endif
 
 extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
 
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 2f065277f8ee..7d047808419d 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -3,5 +3,5 @@ obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
-obj-$(CONFIG_SPARSE_IRQ) += numa_migrate.o
+obj-$(CONFIG_NUMA_IRQ_DESC) += numa_migrate.o
 obj-$(CONFIG_PM_SLEEP) += pm.o