10 files changed, 92 insertions, 56 deletions

diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index ccc4a7fb97a3..e856804c447f 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -370,6 +370,8 @@ config HOTPLUG_CPU
                 can be controlled through /sys/devices/system/cpu/cpu#.
                 Say N if you want to disable CPU hotplug.
 
+config ARCH_ENABLE_MEMORY_HOTPLUG
+        def_bool y
 
 config HPET_TIMER
         bool
@@ -459,10 +461,10 @@ config KEXEC
         help
           kexec is a system call that implements the ability to shutdown your
           current kernel, and to start another kernel.  It is like a reboot
-          but it is indepedent of the system firmware.   And like a reboot
+          but it is independent of the system firmware.   And like a reboot
           you can start any kernel with it, not just Linux.
 
-          The name comes from the similiarity to the exec system call.
+          The name comes from the similarity to the exec system call.
 
           It is an ongoing process to be certain the hardware in a machine
           is properly shutdown, so do not be surprised if this code does not
diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index 7290e72b9a34..22cac4487b57 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -588,7 +588,7 @@ END(common_interrupt)
  */             
         .macro apicinterrupt num,func
         INTR_FRAME
-        pushq $\num-256
+        pushq $~(\num)
         CFI_ADJUST_CFA_OFFSET 8
         interrupt \func
         jmp ret_from_intr
diff --git a/arch/x86_64/kernel/i8259.c b/arch/x86_64/kernel/i8259.c
index 86b2c1e197aa..3dd1659427dc 100644
--- a/arch/x86_64/kernel/i8259.c
+++ b/arch/x86_64/kernel/i8259.c
@@ -235,7 +235,7 @@ void make_8259A_irq(unsigned int irq)
 {
         disable_irq_nosync(irq);
         io_apic_irqs &= ~(1<<irq);
-        irq_desc[irq].handler = &i8259A_irq_type;
+        irq_desc[irq].chip = &i8259A_irq_type;
         enable_irq(irq);
 }
 
@@ -468,12 +468,12 @@ void __init init_ISA_irqs (void)
                         /*
                          * 16 old-style INTA-cycle interrupts:
                          */
-                        irq_desc[i].handler = &i8259A_irq_type;
+                        irq_desc[i].chip = &i8259A_irq_type;
                 } else {
                         /*
                          * 'high' PCI IRQs filled in on demand
                          */
-                        irq_desc[i].handler = &no_irq_type;
+                        irq_desc[i].chip = &no_irq_type;
                 }
         }
 }
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index c768d8a036d0..401b687fef21 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -876,15 +876,17 @@ static struct hw_interrupt_type ioapic_edge_type;
 #define IOAPIC_EDGE     0
 #define IOAPIC_LEVEL    1
 
-static inline void ioapic_register_intr(int irq, int vector, unsigned long trigger)
+static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 {
-        unsigned idx = use_pci_vector() && !platform_legacy_irq(irq) ? vector : irq;
+        unsigned idx;
+
+        idx = use_pci_vector() && !platform_legacy_irq(irq) ? vector : irq;
 
         if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
                         trigger == IOAPIC_LEVEL)
-                irq_desc[idx].handler = &ioapic_level_type;
+                irq_desc[idx].chip = &ioapic_level_type;
         else
-                irq_desc[idx].handler = &ioapic_edge_type;
+                irq_desc[idx].chip = &ioapic_edge_type;
         set_intr_gate(vector, interrupt[idx]);
 }
 
@@ -986,7 +988,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
          * The timer IRQ doesn't have to know that behind the
          * scene we have a 8259A-master in AEOI mode ...
          */
-        irq_desc[0].handler = &ioapic_edge_type;
+        irq_desc[0].chip = &ioapic_edge_type;
 
         /*
          * Add it to the IO-APIC irq-routing table:
@@ -1616,6 +1618,13 @@ static void set_ioapic_affinity_vector (unsigned int vector,
 #endif // CONFIG_SMP
 #endif // CONFIG_PCI_MSI
 
+static int ioapic_retrigger(unsigned int irq)
+{
+        send_IPI_self(IO_APIC_VECTOR(irq));
+
+        return 1;
+}
+
 /*
  * Level and edge triggered IO-APIC interrupts need different handling,
  * so we use two separate IRQ descriptors. Edge triggered IRQs can be
@@ -1636,6 +1645,7 @@ static struct hw_interrupt_type ioapic_edge_type __read_mostly = {
 #ifdef CONFIG_SMP
         .set_affinity = set_ioapic_affinity,
 #endif
+        .retrigger      = ioapic_retrigger,
 };
 
 static struct hw_interrupt_type ioapic_level_type __read_mostly = {
@@ -1649,6 +1659,7 @@ static struct hw_interrupt_type ioapic_level_type __read_mostly = {
 #ifdef CONFIG_SMP
         .set_affinity = set_ioapic_affinity,
 #endif
+        .retrigger      = ioapic_retrigger,
 };
 
 static inline void init_IO_APIC_traps(void)
@@ -1683,7 +1694,7 @@ static inline void init_IO_APIC_traps(void)
                                 make_8259A_irq(irq);
                         else
                                 /* Strange. Oh, well.. */
-                                irq_desc[irq].handler = &no_irq_type;
+                                irq_desc[irq].chip = &no_irq_type;
                 }
         }
 }
@@ -1900,7 +1911,7 @@ static inline void check_timer(void)
         apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
         disable_8259A_irq(0);
-        irq_desc[0].handler = &lapic_irq_type;
+        irq_desc[0].chip = &lapic_irq_type;
         apic_write(APIC_LVT0, APIC_DM_FIXED | vector);  /* Fixed mode */
         enable_8259A_irq(0);
 
diff --git a/arch/x86_64/kernel/irq.c b/arch/x86_64/kernel/irq.c
index 59518d4d4358..a1f1df5f7bfc 100644
--- a/arch/x86_64/kernel/irq.c
+++ b/arch/x86_64/kernel/irq.c
@@ -79,7 +79,7 @@ int show_interrupts(struct seq_file *p, void *v)
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
-                seq_printf(p, " %14s", irq_desc[i].handler->typename);
+                seq_printf(p, " %14s", irq_desc[i].chip->typename);
 
                 seq_printf(p, "  %s", action->name);
                 for (action=action->next; action; action = action->next)
@@ -115,8 +115,14 @@ skip:
  */
 asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 {       
-        /* high bits used in ret_from_ code  */
-        unsigned irq = regs->orig_rax & 0xff;
+        /* high bit used in ret_from_ code  */
+        unsigned irq = ~regs->orig_rax;
+
+        if (unlikely(irq >= NR_IRQS)) {
+                printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
+                                        __FUNCTION__, irq);
+                BUG();
+        }
 
         exit_idle();
         irq_enter();
@@ -140,13 +146,13 @@ void fixup_irqs(cpumask_t map)
                 if (irq == 2)
                         continue;
 
-                cpus_and(mask, irq_affinity[irq], map);
+                cpus_and(mask, irq_desc[irq].affinity, map);
                 if (any_online_cpu(mask) == NR_CPUS) {
                         printk("Breaking affinity for irq %i\n", irq);
                         mask = map;
                 }
-                if (irq_desc[irq].handler->set_affinity)
-                        irq_desc[irq].handler->set_affinity(irq, mask);
+                if (irq_desc[irq].chip->set_affinity)
+                        irq_desc[irq].chip->set_affinity(irq, mask);
                 else if (irq_desc[irq].action && !(warned++))
                         printk("Cannot set affinity for irq %i\n", irq);
         }
diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index acd5816b1a6f..88845674c661 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -629,7 +629,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 #endif
 
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
-static int
+static __cpuinit int
 mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
@@ -647,7 +647,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
         return NOTIFY_OK;
 }
 
-static struct notifier_block mce_cpu_notifier = {
+static struct notifier_block __cpuinitdata mce_cpu_notifier = {
         .notifier_call = mce_cpu_callback,
 };
 
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 399489c93132..0ef9cf2bc45e 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -607,11 +607,13 @@ void set_nmi_callback(nmi_callback_t callback)
         vmalloc_sync_all();
         rcu_assign_pointer(nmi_callback, callback);
 }
+EXPORT_SYMBOL_GPL(set_nmi_callback);
 
 void unset_nmi_callback(void)
 {
         nmi_callback = dummy_nmi_callback;
 }
+EXPORT_SYMBOL_GPL(unset_nmi_callback);
 
 #ifdef CONFIG_SYSCTL
 
diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c
index acee4bc3f6fa..5a1c0a3bf872 100644
--- a/arch/x86_64/kernel/smp.c
+++ b/arch/x86_64/kernel/smp.c
@@ -135,10 +135,10 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs)
 
         cpu = smp_processor_id();
         /*
-         * orig_rax contains the interrupt vector - 256.
+         * orig_rax contains the negated interrupt vector.
          * Use that to determine where the sender put the data.
          */
-        sender = regs->orig_rax + 256 - INVALIDATE_TLB_VECTOR_START;
+        sender = ~regs->orig_rax - INVALIDATE_TLB_VECTOR_START;
         f = &per_cpu(flush_state, sender);
 
         if (!cpu_isset(cpu, f->flush_cpumask))
diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c
index 4e9755179ecf..540c0ccbcccc 100644
--- a/arch/x86_64/kernel/smpboot.c
+++ b/arch/x86_64/kernel/smpboot.c
@@ -455,10 +455,12 @@ cpumask_t cpu_coregroup_map(int cpu)
         struct cpuinfo_x86 *c = cpu_data + cpu;
         /*
          * For perf, we return last level cache shared map.
-         * TBD: when power saving sched policy is added, we will return
-         *      cpu_core_map when power saving policy is enabled
+         * And for power savings, we return cpu_core_map
          */
-        return c->llc_shared_map;
+        if (sched_mc_power_savings || sched_smt_power_savings)
+                return cpu_core_map[cpu];
+        else
+                return c->llc_shared_map;
 }
 
 /* representing cpus for which sibling maps can be computed */
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 02add1d1dfa8..95bd232ff0cf 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -23,6 +23,7 @@
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
+#include <linux/poison.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
@@ -506,8 +507,6 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size)
 /*
  * Memory hotplug specific functions
  */
-#if defined(CONFIG_ACPI_HOTPLUG_MEMORY) || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)
-
 void online_page(struct page *page)
 {
         ClearPageReserved(page);
@@ -517,31 +516,17 @@ void online_page(struct page *page)
         num_physpages++;
 }
 
-#ifndef CONFIG_MEMORY_HOTPLUG
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
- * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
- * just online the pages.
+ * XXX: memory_add_physaddr_to_nid() is to find node id from physical address
+ *      via probe interface of sysfs. If acpi notifies hot-add event, then it
+ *      can tell node id by searching dsdt. But, probe interface doesn't have
+ *      node id. So, return 0 as node id at this time.
  */
-int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+#ifdef CONFIG_NUMA
+int memory_add_physaddr_to_nid(u64 start)
 {
-        int err = -EIO;
-        unsigned long pfn;
-        unsigned long total = 0, mem = 0;
-        for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
-                if (pfn_valid(pfn)) {
-                        online_page(pfn_to_page(pfn));
-                        err = 0;
-                        mem++;
-                }
-                total++;
-        }
-        if (!err) {
-                z->spanned_pages += total;
-                z->present_pages += mem;
-                z->zone_pgdat->node_spanned_pages += total;
-                z->zone_pgdat->node_present_pages += mem;
-        }
-        return err;
+        return 0;
 }
 #endif
 
@@ -549,9 +534,9 @@ int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
  * Memory is added always to NORMAL zone. This means you will never get
  * additional DMA/DMA32 memory.
  */
-int add_memory(u64 start, u64 size)
+int arch_add_memory(int nid, u64 start, u64 size)
 {
-        struct pglist_data *pgdat = NODE_DATA(0);
+        struct pglist_data *pgdat = NODE_DATA(nid);
         struct zone *zone = pgdat->node_zones + MAX_NR_ZONES-2;
         unsigned long start_pfn = start >> PAGE_SHIFT;
         unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -568,7 +553,7 @@ error:
         printk("%s: Problem encountered in __add_pages!\n", __func__);
         return ret;
 }
-EXPORT_SYMBOL_GPL(add_memory);
+EXPORT_SYMBOL_GPL(arch_add_memory);
 
 int remove_memory(u64 start, u64 size)
 {
@@ -576,7 +561,33 @@ int remove_memory(u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(remove_memory);
 
-#endif
+#else /* CONFIG_MEMORY_HOTPLUG */
+/*
+ * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance,
+ * just online the pages.
+ */
+int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages)
+{
+        int err = -EIO;
+        unsigned long pfn;
+        unsigned long total = 0, mem = 0;
+        for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) {
+                if (pfn_valid(pfn)) {
+                        online_page(pfn_to_page(pfn));
+                        err = 0;
+                        mem++;
+                }
+                total++;
+        }
+        if (!err) {
+                z->spanned_pages += total;
+                z->present_pages += mem;
+                z->zone_pgdat->node_spanned_pages += total;
+                z->zone_pgdat->node_present_pages += mem;
+        }
+        return err;
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
 
 static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules,
                          kcore_vsyscall;
@@ -650,7 +661,8 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
         for (addr = begin; addr < end; addr += PAGE_SIZE) {
                 ClearPageReserved(virt_to_page(addr));
                 init_page_count(virt_to_page(addr));
-                memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE); 
+                memset((void *)(addr & ~(PAGE_SIZE-1)),
+                        POISON_FREE_INITMEM, PAGE_SIZE);
                 free_page(addr);
                 totalram_pages++;
         }
@@ -658,7 +670,8 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 
 void free_initmem(void)
 {
-        memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin);
+        memset(__initdata_begin, POISON_FREE_INITDATA,
+                __initdata_end - __initdata_begin);
         free_init_pages("unused kernel memory",
                         (unsigned long)(&__init_begin),
                         (unsigned long)(&__init_end));