19 files changed, 69 insertions, 54 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e60c59b81bdd..93224b569187 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -957,7 +957,7 @@ config ARCH_PHYS_ADDR_T_64BIT
 config NUMA
         bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
         depends on SMP
-        depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
+        depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && BROKEN)
         default n if X86_PC
         default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
         help
@@ -1494,7 +1494,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID
         def_bool X86_64
         depends on NUMA
 
-menu "Power management options"
+menu "Power management and ACPI options"
         depends on !X86_VOYAGER
 
 config ARCH_HIBERNATION_HEADER
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index d843ed0e9b2e..0005adb0f941 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -101,30 +101,22 @@
 #define LAST_VM86_IRQ           15
 #define invalid_vm86_irq(irq)   ((irq) < 3 || (irq) > 15)
 
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
 # if NR_CPUS < MAX_IO_APICS
 #  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
 # else
 #  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
 # endif
 
-#elif !defined(CONFIG_X86_VOYAGER)
+#elif defined(CONFIG_X86_VOYAGER)
 
-# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
-
-#  define NR_IRQS               224
-
-# else /* IO_APIC || PARAVIRT */
-
-#  define NR_IRQS               16
-
-# endif
+# define NR_IRQS                224
 
-#else /* !VISWS && !VOYAGER */
+#else /* IO_APIC || VOYAGER */
 
-# define NR_IRQS                224
+# define NR_IRQS                16
 
-#endif /* VISWS */
+#endif
 
 /* Voyager specific defines */
 /* These define the CPIs we use in linux */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 46be2fa7ac26..c2a812ebde89 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -108,9 +108,7 @@ static __always_inline unsigned long long __native_read_tsc(void)
 {
         DECLARE_ARGS(val, low, high);
 
-        rdtsc_barrier();
         asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
-        rdtsc_barrier();
 
         return EAX_EDX_VAL(val, low, high);
 }
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 90ac7718469a..4850e4b02b61 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -154,7 +154,7 @@ extern unsigned long node_remap_size[];
 
 #endif
 
-/* sched_domains SD_NODE_INIT for NUMAQ machines */
+/* sched_domains SD_NODE_INIT for NUMA machines */
 #define SD_NODE_INIT (struct sched_domain) {            \
         .min_interval           = 8,                    \
         .max_interval           = 32,                   \
@@ -169,8 +169,9 @@ extern unsigned long node_remap_size[];
         .flags                  = SD_LOAD_BALANCE       \
                                 | SD_BALANCE_EXEC       \
                                 | SD_BALANCE_FORK       \
-                                | SD_SERIALIZE          \
-                                | SD_WAKE_BALANCE,      \
+                                | SD_WAKE_AFFINE        \
+                                | SD_WAKE_BALANCE       \
+                                | SD_SERIALIZE,         \
         .last_balance           = jiffies,              \
         .balance_interval       = 1,                    \
 }
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 38ae163cc91b..9cd83a8e40d5 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -34,6 +34,8 @@ static inline cycles_t get_cycles(void)
 
 static __always_inline cycles_t vget_cycles(void)
 {
+        cycles_t cycles;
+
         /*
          * We only do VDSOs on TSC capable CPUs, so this shouldnt
          * access boot_cpu_data (which is not VDSO-safe):
@@ -42,7 +44,11 @@ static __always_inline cycles_t vget_cycles(void)
         if (!cpu_has_tsc)
                 return 0;
 #endif
-        return (cycles_t)__native_read_tsc();
+        rdtsc_barrier();
+        cycles = (cycles_t)__native_read_tsc();
+        rdtsc_barrier();
+
+        return cycles;
 }
 
 extern void tsc_init(void);
diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h
index 9c811d2e6f91..b3e647307625 100644
--- a/arch/x86/include/asm/voyager.h
+++ b/arch/x86/include/asm/voyager.h
@@ -520,6 +520,7 @@ extern void voyager_restart(void);
 extern void voyager_cat_power_off(void);
 extern void voyager_cat_do_common_interrupt(void);
 extern void voyager_handle_nmi(void);
+extern void voyager_smp_intr_init(void);
 /* Commands for the following are */
 #define VOYAGER_PSI_READ        0
 #define VOYAGER_PSI_WRITE       1
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index a8fd9ebdc8e2..331b318304eb 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -50,7 +50,7 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 /* returns !0 if the IOMMU is caching non-present entries in its TLB */
 static int iommu_has_npcache(struct amd_iommu *iommu)
 {
-        return iommu->cap & IOMMU_CAP_NPCACHE;
+        return iommu->cap & (1UL << IOMMU_CAP_NPCACHE);
 }
 
 /****************************************************************************
@@ -536,6 +536,9 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
 {
         address >>= PAGE_SHIFT;
         iommu_area_free(dom->bitmap, address, pages);
+
+        if (address + pages >= dom->next_bit)
+                dom->need_flush = true;
 }
 
 /****************************************************************************
@@ -992,8 +995,10 @@ static void __unmap_single(struct amd_iommu *iommu,
 
         dma_ops_free_addresses(dma_dom, dma_addr, pages);
 
-        if (amd_iommu_unmap_flush)
+        if (amd_iommu_unmap_flush || dma_dom->need_flush) {
                 iommu_flush_pages(iommu, dma_dom->domain.id, dma_addr, size);
+                dma_dom->need_flush = false;
+        }
 }
 
 /*
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 77017e834cf7..067d8de913f6 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -322,7 +322,7 @@ static int hpet_next_event(unsigned long delta,
          * what we wrote hit the chip before we compare it to the
          * counter.
          */
-        WARN_ON((u32)hpet_readl(HPET_T0_CMP) != cnt);
+        WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt);
 
         return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
 }
@@ -445,7 +445,7 @@ static int hpet_setup_irq(struct hpet_dev *dev)
 {
 
         if (request_irq(dev->irq, hpet_interrupt_handler,
-                        IRQF_SHARED|IRQF_NOBALANCING, dev->name, dev))
+                        IRQF_DISABLED|IRQF_NOBALANCING, dev->name, dev))
                 return -1;
 
         disable_irq(dev->irq);
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index b764d7429c61..7a3f2028e2eb 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3611,6 +3611,8 @@ int __init probe_nr_irqs(void)
         /* something wrong ? */
         if (nr < nr_min)
                 nr = nr_min;
+        if (WARN_ON(nr > NR_IRQS))
+                nr = NR_IRQS;
 
         return nr;
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f4c93f1cfc19..724adfc63cb9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -29,11 +29,7 @@ EXPORT_SYMBOL(pm_power_off);
 
 static const struct desc_ptr no_idt = {};
 static int reboot_mode;
-/*
- * Keyboard reset and triple fault may result in INIT, not RESET, which
- * doesn't work when we're in vmx root mode.  Try ACPI first.
- */
-enum reboot_type reboot_type = BOOT_ACPI;
+enum reboot_type reboot_type = BOOT_KBD;
 int reboot_force;
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index e00534b33534..f4049f3513b6 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -154,6 +154,12 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
         flush_mm = mm;
         flush_va = va;
         cpus_or(flush_cpumask, cpumask, flush_cpumask);
+
+        /*
+         * Make the above memory operations globally visible before
+         * sending the IPI.
+         */
+        smp_mb();
         /*
          * We have to send the IPI only to
          * CPUs affected.
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
index dcbf7a1159ea..8f919ca69494 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/kernel/tlb_64.c
@@ -183,6 +183,11 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
         cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask);
 
         /*
+         * Make the above memory operations globally visible before
+         * sending the IPI.
+         */
+        smp_mb();
+        /*
          * We have to send the IPI only to
          * CPUs affected.
          */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 62348e4fd8d1..424093b157d3 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -55,7 +55,7 @@ u64 native_sched_clock(void)
         rdtscll(this_offset);
 
         /* return the value in ns */
-        return cycles_2_ns(this_offset);
+        return __cycles_2_ns(this_offset);
 }
 
 /* We need to define a real function for sched_clock, to override the
@@ -813,10 +813,6 @@ void __init tsc_init(void)
                 cpu_khz = calibrate_cpu();
 #endif
 
-        lpj = ((u64)tsc_khz * 1000);
-        do_div(lpj, HZ);
-        lpj_fine = lpj;
-
         printk("Detected %lu.%03lu MHz processor.\n",
                         (unsigned long)cpu_khz / 1000,
                         (unsigned long)cpu_khz % 1000);
@@ -836,6 +832,10 @@ void __init tsc_init(void)
         /* now allow native_sched_clock() to use rdtsc */
         tsc_disabled = 0;
 
+        lpj = ((u64)tsc_khz * 1000);
+        do_div(lpj, HZ);
+        lpj_fine = lpj;
+
         use_tsc_delay();
         /* Check and install the TSC clocksource */
         dmi_check_system(bad_tsc_dmi_table);
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index 6bbdd633864c..a580b9562e76 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -27,7 +27,7 @@ static struct irqaction irq2 = {
 void __init intr_init_hook(void)
 {
 #ifdef CONFIG_SMP
-        smp_intr_init();
+        voyager_smp_intr_init();
 #endif
 
         setup_irq(2, &irq2);
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 7f4c6af14351..0e331652681e 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -1258,7 +1258,7 @@ static void handle_vic_irq(unsigned int irq, struct irq_desc *desc)
 #define QIC_SET_GATE(cpi, vector) \
         set_intr_gate((cpi) + QIC_DEFAULT_CPI_BASE, (vector))
 
-void __init smp_intr_init(void)
+void __init voyager_smp_intr_init(void)
 {
         int i;
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f1dc1b75d166..e89d24815f26 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -67,18 +67,18 @@ static void split_page_count(int level)
 
 void arch_report_meminfo(struct seq_file *m)
 {
-        seq_printf(m, "DirectMap4k:  %8lu kB\n",
+        seq_printf(m, "DirectMap4k:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_4K] << 2);
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-        seq_printf(m, "DirectMap2M:  %8lu kB\n",
+        seq_printf(m, "DirectMap2M:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_2M] << 11);
 #else
-        seq_printf(m, "DirectMap4M:  %8lu kB\n",
+        seq_printf(m, "DirectMap4M:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_2M] << 12);
 #endif
 #ifdef CONFIG_X86_64
         if (direct_gbpages)
-                seq_printf(m, "DirectMap1G:  %8lu kB\n",
+                seq_printf(m, "DirectMap1G:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
 }
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 0620d6d45f7d..3f1b81a83e2e 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -27,8 +27,7 @@ static int num_counters = 2;
 static int counter_width = 32;
 
 #define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0)
-#define CTR_OVERFLOWED(n) (!((n) & (1U<<(counter_width-1))))
+#define CTR_OVERFLOWED(n) (!((n) & (1ULL<<(counter_width-1))))
 
 #define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
 #define CTRL_READ(l, h, msrs, c) do {rdmsr((msrs->controls[(c)].addr), (l), (h)); } while (0)
@@ -124,14 +123,14 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 static int ppro_check_ctrs(struct pt_regs * const regs,
                            struct op_msrs const * const msrs)
 {
-        unsigned int low, high;
+        u64 val;
         int i;
 
         for (i = 0 ; i < num_counters; ++i) {
                 if (!reset_value[i])
                         continue;
-                CTR_READ(low, high, msrs, i);
-                if (CTR_OVERFLOWED(low)) {
+                rdmsrl(msrs->counters[i].addr, val);
+                if (CTR_OVERFLOWED(val)) {
                         oprofile_add_sample(regs, i);
                         wrmsrl(msrs->counters[i].addr, -reset_value[i]);
                 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b61534c7a4c4..5e4686d70f62 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -863,15 +863,16 @@ static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned l
         if (PagePinned(virt_to_page(mm->pgd))) {
                 SetPagePinned(page);
 
+                vm_unmap_aliases();
                 if (!PageHighMem(page)) {
                         make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
                         if (level == PT_PTE && USE_SPLIT_PTLOCKS)
                                 pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
-                } else
+                } else {
                         /* make sure there are no stray mappings of
                            this page */
                         kmap_flush_unused();
-                        vm_unmap_aliases();
+                }
         }
 }
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index aba77b2b7d18..688936044dc9 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -850,13 +850,16 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
    read-only, and can be pinned. */
 static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 {
+        vm_unmap_aliases();
+
         xen_mc_batch();
 
-        if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
-                /* re-enable interrupts for kmap_flush_unused */
+         if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
+                /* re-enable interrupts for flushing */
                 xen_mc_issue(0);
+
                 kmap_flush_unused();
-                vm_unmap_aliases();
+
                 xen_mc_batch();
         }
 
@@ -874,7 +877,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 #else /* CONFIG_X86_32 */
 #ifdef CONFIG_X86_PAE
         /* Need to make sure unshared kernel PMD is pinnable */
-        xen_pin_page(mm, virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])),
+        xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
                      PT_PMD);
 #endif
         xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
@@ -991,7 +994,7 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
 
 #ifdef CONFIG_X86_PAE
         /* Need to make sure unshared kernel PMD is unpinned */
-        xen_unpin_page(mm, virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])),
+        xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
                        PT_PMD);
 #endif