Merge branch 'irq/sparseirq' into cpus4096

Conflicts:
	arch/x86/kernel/io_apic.c

Merge irq/sparseirq here, to resolve conflicts.

2 files changed, 151 insertions, 2 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4a3f5851ec64..0ca2eb7573cd 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -243,7 +243,7 @@ config X86_HAS_BOOT_CPU_ID
 
 config SPARSE_IRQ
         bool "Support sparse irq numbering"
-        depends on (PCI_MSI || HT_IRQ) && SMP
+        depends on PCI_MSI || HT_IRQ
         default y
         help
           This enables support for sparse irq, esp for msi/msi-x. You may need
@@ -251,6 +251,15 @@ config SPARSE_IRQ
 
           If you don't know what to do here, say Y.
 
+config NUMA_MIGRATE_IRQ_DESC
+        bool "Move irq desc when changing irq smp_affinity"
+        depends on SPARSE_IRQ && SMP
+        default n
+        help
+          This enables moving irq_desc to cpu/node that irq will use handled.
+
+          If you don't know what to do here, say N.
+
 config X86_FIND_SMP_CONFIG
         def_bool y
         depends on X86_MPPARSE || X86_VOYAGER
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 60bb8b19f4cd..6bd51ce3ce32 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -141,6 +141,9 @@ struct irq_cfg {
         unsigned move_cleanup_count;
         u8 vector;
         u8 move_in_progress : 1;
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+        u8 move_desc_pending : 1;
+#endif
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -241,6 +244,121 @@ void arch_init_chip_data(struct irq_desc *desc, int cpu)
         }
 }
 
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+
+static void
+init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int cpu)
+{
+        struct irq_pin_list *old_entry, *head, *tail, *entry;
+
+        cfg->irq_2_pin = NULL;
+        old_entry = old_cfg->irq_2_pin;
+        if (!old_entry)
+                return;
+
+        entry = get_one_free_irq_2_pin(cpu);
+        if (!entry)
+                return;
+
+        entry->apic     = old_entry->apic;
+        entry->pin      = old_entry->pin;
+        head            = entry;
+        tail            = entry;
+        old_entry       = old_entry->next;
+        while (old_entry) {
+                entry = get_one_free_irq_2_pin(cpu);
+                if (!entry) {
+                        entry = head;
+                        while (entry) {
+                                head = entry->next;
+                                kfree(entry);
+                                entry = head;
+                        }
+                        /* still use the old one */
+                        return;
+                }
+                entry->apic     = old_entry->apic;
+                entry->pin      = old_entry->pin;
+                tail->next      = entry;
+                tail            = entry;
+                old_entry       = old_entry->next;
+        }
+
+        tail->next = NULL;
+        cfg->irq_2_pin = head;
+}
+
+static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
+{
+        struct irq_pin_list *entry, *next;
+
+        if (old_cfg->irq_2_pin == cfg->irq_2_pin)
+                return;
+
+        entry = old_cfg->irq_2_pin;
+
+        while (entry) {
+                next = entry->next;
+                kfree(entry);
+                entry = next;
+        }
+        old_cfg->irq_2_pin = NULL;
+}
+
+void arch_init_copy_chip_data(struct irq_desc *old_desc,
+                                 struct irq_desc *desc, int cpu)
+{
+        struct irq_cfg *cfg;
+        struct irq_cfg *old_cfg;
+
+        cfg = get_one_free_irq_cfg(cpu);
+
+        if (!cfg)
+                return;
+
+        desc->chip_data = cfg;
+
+        old_cfg = old_desc->chip_data;
+
+        memcpy(cfg, old_cfg, sizeof(struct irq_cfg));
+
+        init_copy_irq_2_pin(old_cfg, cfg, cpu);
+}
+
+static void free_irq_cfg(struct irq_cfg *old_cfg)
+{
+        kfree(old_cfg);
+}
+
+void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
+{
+        struct irq_cfg *old_cfg, *cfg;
+
+        old_cfg = old_desc->chip_data;
+        cfg = desc->chip_data;
+
+        if (old_cfg == cfg)
+                return;
+
+        if (old_cfg) {
+                free_irq_2_pin(old_cfg, cfg);
+                free_irq_cfg(old_cfg);
+                old_desc->chip_data = NULL;
+        }
+}
+
+static void set_extra_move_desc(struct irq_desc *desc, cpumask_t mask)
+{
+        struct irq_cfg *cfg = desc->chip_data;
+
+        if (!cfg->move_in_progress) {
+                /* it means that domain is not changed */
+                if (!cpus_intersects(desc->affinity, mask))
+                        cfg->move_desc_pending = 1;
+        }
+}
+#endif
+
 #else
 static struct irq_cfg *irq_cfg(unsigned int irq)
 {
@@ -249,10 +367,12 @@ static struct irq_cfg *irq_cfg(unsigned int irq)
 
 #endif
 
+#ifndef CONFIG_NUMA_MIGRATE_IRQ_DESC
 static inline void
 set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask)
 {
 }
+#endif
 
 struct io_apic {
         unsigned int index;
@@ -2397,11 +2517,31 @@ static void irq_complete_move(struct irq_desc **descp)
         struct irq_cfg *cfg = desc->chip_data;
         unsigned vector, me;
 
-        if (likely(!cfg->move_in_progress))
+        if (likely(!cfg->move_in_progress)) {
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+                if (likely(!cfg->move_desc_pending))
+                        return;
+
+                /* domain is not change, but affinity is changed */
+                me = smp_processor_id();
+                if (cpu_isset(me, desc->affinity)) {
+                        *descp = desc = move_irq_desc(desc, me);
+                        /* get the new one */
+                        cfg = desc->chip_data;
+                        cfg->move_desc_pending = 0;
+                }
+#endif
                 return;
+        }
 
         vector = ~get_irq_regs()->orig_ax;
         me = smp_processor_id();
+#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
+                *descp = desc = move_irq_desc(desc, me);
+                /* get the new one */
+                cfg = desc->chip_data;
+#endif
+
         if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
                 send_cleanup_vector(cfg);
 }