27 files changed, 305 insertions, 156 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d1430ef6b4f9..c07f72205909 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1913,25 +1913,14 @@ config DMAR_DEFAULT_ON
           recommended you say N here while the DMAR code remains
           experimental.
 
-config DMAR_GFX_WA
-        def_bool y
-        prompt "Support for Graphics workaround"
-        depends on DMAR
-        ---help---
-          Current Graphics drivers tend to use physical address
-          for DMA and avoid using DMA APIs. Setting this config
-          option permits the IOMMU driver to set a unity map for
-          all the OS-visible memory. Hence the driver can continue
-          to use physical addresses for DMA.
-
 config DMAR_FLOPPY_WA
         def_bool y
         depends on DMAR
         ---help---
-          Floppy disk drivers are know to bypass DMA API calls
+          Floppy disk drivers are known to bypass DMA API calls
           thereby failing to work when IOMMU is enabled. This
           workaround will setup a 1:1 mapping for the first
-          16M to make floppy (an ISA device) work.
+          16MiB to make floppy (an ISA device) work.
 
 config INTR_REMAP
         bool "Support for Interrupt Remapping (EXPERIMENTAL)"
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 418e632d4a80..7a1065958ba9 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -8,7 +8,7 @@
 
 #ifdef __KERNEL__
 
-#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
 
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
@@ -16,10 +16,10 @@
                                 & ~(CONFIG_PHYSICAL_ALIGN - 1))
 
 /* Minimum kernel alignment, as a power of two */
-#ifdef CONFIG_x86_64
+#ifdef CONFIG_X86_64
 #define MIN_KERNEL_ALIGN_LG2    PMD_SHIFT
 #else
-#define MIN_KERNEL_ALIGN_LG2    (PAGE_SHIFT+1)
+#define MIN_KERNEL_ALIGN_LG2    (PAGE_SHIFT + THREAD_ORDER)
 #endif
 #define MIN_KERNEL_ALIGN        (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
 
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 927958d13c19..1ff685ca221c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -91,7 +91,7 @@ extern void pci_iommu_alloc(void);
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG)
+#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG)
 
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
                 dma_addr_t ADDR_NAME;
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 02ecb30982a3..103f1ddb0d85 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -42,6 +42,7 @@
 
 #else /* ...!ASSEMBLY */
 
+#include <linux/kernel.h>
 #include <linux/stringify.h>
 
 #ifdef CONFIG_SMP
@@ -155,6 +156,15 @@ do {							\
 /* We can use this directly for local CPU (faster). */
 DECLARE_PER_CPU(unsigned long, this_cpu_off);
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+void *pcpu_lpage_remapped(void *kaddr);
+#else
+static inline void *pcpu_lpage_remapped(void *kaddr)
+{
+        return NULL;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index 5fb33e160ea0..fa64e401589d 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -87,6 +87,9 @@ union cpuid10_edx {
 #ifdef CONFIG_PERF_COUNTERS
 extern void init_hw_perf_counters(void);
 extern void perf_counters_lapic_init(void);
+
+#define PERF_COUNTER_INDEX_OFFSET                       0
+
 #else
 static inline void init_hw_perf_counters(void)          { }
 static inline void perf_counters_lapic_init(void)       { }
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 49fb3ecf3bb3..621f56d73121 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -22,7 +22,14 @@ extern int reboot_force;
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
-#define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
-#define round_down(x, y) ((x) & ~((y) - 1))
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x,y) ((__typeof__(x))((y)-1))
+#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
+#define round_down(x,y) ((x) & ~__round_mask(x,y))
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e5b27d8f1b47..28e5f5956042 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -258,13 +258,15 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_HT
         unsigned bits;
+        int cpu = smp_processor_id();
 
         bits = c->x86_coreid_bits;
-
         /* Low order bits define the core id (index of core in socket) */
         c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
         /* Convert the initial APIC ID into the socket ID */
         c->phys_proc_id = c->initial_apicid >> bits;
+        /* use socket ID also for last level cache */
+        per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6b26d4deada0..f1961c07af9a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -848,9 +848,6 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
         numa_add_cpu(smp_processor_id());
 #endif
-
-        /* Cap the iomem address space to what is addressable on all CPUs */
-        iomem_resource.end &= (1ULL << c->x86_phys_bits) - 1;
 }
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 284d1de968bc..af425b83202b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1117,7 +1117,7 @@ static void mcheck_timer(unsigned long data)
                 *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
 
         t->expires = jiffies + *n;
-        add_timer(t);
+        add_timer_on(t, smp_processor_id());
 }
 
 static void mce_do_trigger(struct work_struct *work)
@@ -1321,7 +1321,7 @@ static void mce_init_timer(void)
                 return;
         setup_timer(t, mcheck_timer, smp_processor_id());
         t->expires = round_jiffies(jiffies + *n);
-        add_timer(t);
+        add_timer_on(t, smp_processor_id());
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 76dfef23f789..d4cf4ce19aac 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -401,7 +401,7 @@ static const u64 amd_hw_cache_event_ids
                 [ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
         },
         [ C(OP_WRITE) ] = {
-                [ C(RESULT_ACCESS) ] = 0x0042, /* Data Cache Refills from L2 */
+                [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
                 [ C(RESULT_MISS)   ] = 0,
         },
         [ C(OP_PREFETCH) ] = {
@@ -912,6 +912,8 @@ x86_perf_counter_set_period(struct perf_counter *counter,
         err = checking_wrmsrl(hwc->counter_base + idx,
                              (u64)(-left) & x86_pmu.counter_mask);
 
+        perf_counter_update_userpage(counter);
+
         return ret;
 }
 
@@ -969,13 +971,6 @@ fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc)
         if (!x86_pmu.num_counters_fixed)
                 return -1;
 
-        /*
-         * Quirk, IA32_FIXED_CTRs do not work on current Atom processors:
-         */
-        if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-                                        boot_cpu_data.x86_model == 28)
-                return -1;
-
         event = hwc->config & ARCH_PERFMON_EVENT_MASK;
 
         if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
@@ -1041,6 +1036,8 @@ try_generic:
         x86_perf_counter_set_period(counter, hwc, idx);
         x86_pmu.enable(hwc, idx);
 
+        perf_counter_update_userpage(counter);
+
         return 0;
 }
 
@@ -1133,6 +1130,8 @@ static void x86_pmu_disable(struct perf_counter *counter)
         x86_perf_counter_update(counter, hwc, idx);
         cpuc->counters[idx] = NULL;
         clear_bit(idx, cpuc->used_mask);
+
+        perf_counter_update_userpage(counter);
 }
 
 /*
@@ -1428,8 +1427,6 @@ static int intel_pmu_init(void)
          */
         x86_pmu.num_counters_fixed      = max((int)edx.split.num_counters_fixed, 3);
 
-        rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
-
         /*
          * Install the hw-cache-events table:
          */
@@ -1499,21 +1496,22 @@ void __init init_hw_perf_counters(void)
         pr_cont("%s PMU driver.\n", x86_pmu.name);
 
         if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
-                x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
                 WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!",
                      x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+                x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
         }
         perf_counter_mask = (1 << x86_pmu.num_counters) - 1;
         perf_max_counters = x86_pmu.num_counters;
 
         if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
-                x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
                 WARN(1, KERN_ERR "hw perf counters fixed %d > max(%d), clipping!",
                      x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+                x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
         }
 
         perf_counter_mask |=
                 ((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+        x86_pmu.intel_ctrl = perf_counter_mask;
 
         perf_counters_lapic_init();
         register_die_notifier(&perf_counter_nmi_notifier);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 95ea5fa7d444..c8405718a4c3 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,6 +22,7 @@
 #include "dumpstack.h"
 
 int panic_on_unrecovered_nmi;
+int panic_on_io_nmi;
 unsigned int code_bytes = 64;
 int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
 static int die_counter;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7271fa33d791..c4ca89d9aaf4 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1383,6 +1383,8 @@ static unsigned long ram_alignment(resource_size_t pos)
         return 32*1024*1024;
 }
 
+#define MAX_RESOURCE_SIZE ((resource_size_t)-1)
+
 void __init e820_reserve_resources_late(void)
 {
         int i;
@@ -1400,17 +1402,19 @@ void __init e820_reserve_resources_late(void)
          * avoid stolen RAM:
          */
         for (i = 0; i < e820.nr_map; i++) {
-                struct e820entry *entry = &e820_saved.map[i];
-                resource_size_t start, end;
+                struct e820entry *entry = &e820.map[i];
+                u64 start, end;
 
                 if (entry->type != E820_RAM)
                         continue;
                 start = entry->addr + entry->size;
-                end = round_up(start, ram_alignment(start));
-                if (start == end)
+                end = round_up(start, ram_alignment(start)) - 1;
+                if (end > MAX_RESOURCE_SIZE)
+                        end = MAX_RESOURCE_SIZE;
+                if (start >= end)
                         continue;
-                reserve_region_with_split(&iomem_resource, start,
-                                                  end - 1, "RAM buffer");
+                reserve_region_with_split(&iomem_resource, start, end,
+                                          "RAM buffer");
         }
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 47630479b067..1a041bcf506b 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -211,11 +211,11 @@ static __init int iommu_setup(char *p)
 #ifdef CONFIG_SWIOTLB
                 if (!strncmp(p, "soft", 4))
                         swiotlb = 1;
+#endif
                 if (!strncmp(p, "pt", 2)) {
                         iommu_pass_through = 1;
                         return 1;
                 }
-#endif
 
                 gart_parse_options(p);
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index be5ae80f897f..de2cab132844 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -289,6 +289,20 @@ void * __init extend_brk(size_t size, size_t align)
         return ret;
 }
 
+#ifdef CONFIG_X86_64
+static void __init init_gbpages(void)
+{
+        if (direct_gbpages && cpu_has_gbpages)
+                printk(KERN_INFO "Using GB pages for direct mapping\n");
+        else
+                direct_gbpages = 0;
+}
+#else
+static inline void init_gbpages(void)
+{
+}
+#endif
+
 static void __init reserve_brk(void)
 {
         if (_brk_end > _brk_start)
@@ -871,6 +885,8 @@ void __init setup_arch(char **cmdline_p)
 
         reserve_brk();
 
+        init_gbpages();
+
         /* max_pfn_mapped is updated here */
         max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
         max_pfn_mapped = max_low_pfn_mapped;
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 9c3f0823e6aa..29a3eef7cf4a 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -124,7 +124,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
 }
 
 /*
- * Remap allocator
+ * Large page remap allocator
  *
  * This allocator uses PMD page as unit.  A PMD page is allocated for
  * each cpu and each is remapped into vmalloc area using PMD mapping.
@@ -137,105 +137,185 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
  * better than only using 4k mappings while still being NUMA friendly.
  */
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-static size_t pcpur_size __initdata;
-static void **pcpur_ptrs __initdata;
+struct pcpul_ent {
+        unsigned int    cpu;
+        void            *ptr;
+};
+
+static size_t pcpul_size;
+static struct pcpul_ent *pcpul_map;
+static struct vm_struct pcpul_vm;
 
-static struct page * __init pcpur_get_page(unsigned int cpu, int pageno)
+static struct page * __init pcpul_get_page(unsigned int cpu, int pageno)
 {
         size_t off = (size_t)pageno << PAGE_SHIFT;
 
-        if (off >= pcpur_size)
+        if (off >= pcpul_size)
                 return NULL;
 
-        return virt_to_page(pcpur_ptrs[cpu] + off);
+        return virt_to_page(pcpul_map[cpu].ptr + off);
 }
 
-static ssize_t __init setup_pcpu_remap(size_t static_size)
+static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 {
-        static struct vm_struct vm;
-        size_t ptrs_size, dyn_size;
+        size_t map_size, dyn_size;
         unsigned int cpu;
+        int i, j;
         ssize_t ret;
 
-        /*
-         * If large page isn't supported, there's no benefit in doing
-         * this.  Also, on non-NUMA, embedding is better.
-         *
-         * NOTE: disabled for now.
-         */
-        if (true || !cpu_has_pse || !pcpu_need_numa())
+        if (!chosen) {
+                size_t vm_size = VMALLOC_END - VMALLOC_START;
+                size_t tot_size = num_possible_cpus() * PMD_SIZE;
+
+                /* on non-NUMA, embedding is better */
+                if (!pcpu_need_numa())
+                        return -EINVAL;
+
+                /* don't consume more than 20% of vmalloc area */
+                if (tot_size > vm_size / 5) {
+                        pr_info("PERCPU: too large chunk size %zuMB for "
+                                "large page remap\n", tot_size >> 20);
+                        return -EINVAL;
+                }
+        }
+
+        /* need PSE */
+        if (!cpu_has_pse) {
+                pr_warning("PERCPU: lpage allocator requires PSE\n");
                 return -EINVAL;
+        }
 
         /*
          * Currently supports only single page.  Supporting multiple
          * pages won't be too difficult if it ever becomes necessary.
          */
-        pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
+        pcpul_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE +
                                PERCPU_DYNAMIC_RESERVE);
-        if (pcpur_size > PMD_SIZE) {
+        if (pcpul_size > PMD_SIZE) {
                 pr_warning("PERCPU: static data is larger than large page, "
                            "can't use large page\n");
                 return -EINVAL;
         }
-        dyn_size = pcpur_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
+        dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE;
 
         /* allocate pointer array and alloc large pages */
-        ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpur_ptrs[0]));
-        pcpur_ptrs = alloc_bootmem(ptrs_size);
+        map_size = PFN_ALIGN(num_possible_cpus() * sizeof(pcpul_map[0]));
+        pcpul_map = alloc_bootmem(map_size);
 
         for_each_possible_cpu(cpu) {
-                pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PMD_SIZE, PMD_SIZE);
-                if (!pcpur_ptrs[cpu])
+                pcpul_map[cpu].cpu = cpu;
+                pcpul_map[cpu].ptr = pcpu_alloc_bootmem(cpu, PMD_SIZE,
+                                                        PMD_SIZE);
+                if (!pcpul_map[cpu].ptr) {
+                        pr_warning("PERCPU: failed to allocate large page "
+                                   "for cpu%u\n", cpu);
                         goto enomem;
+                }
 
                 /*
-                 * Only use pcpur_size bytes and give back the rest.
+                 * Only use pcpul_size bytes and give back the rest.
                  *
                  * Ingo: The 2MB up-rounding bootmem is needed to make
                  * sure the partial 2MB page is still fully RAM - it's
                  * not well-specified to have a PAT-incompatible area
                  * (unmapped RAM, device memory, etc.) in that hole.
                  */
-                free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size),
-                             PMD_SIZE - pcpur_size);
+                free_bootmem(__pa(pcpul_map[cpu].ptr + pcpul_size),
+                             PMD_SIZE - pcpul_size);
 
-                memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size);
+                memcpy(pcpul_map[cpu].ptr, __per_cpu_load, static_size);
         }
 
         /* allocate address and map */
-        vm.flags = VM_ALLOC;
-        vm.size = num_possible_cpus() * PMD_SIZE;
-        vm_area_register_early(&vm, PMD_SIZE);
+        pcpul_vm.flags = VM_ALLOC;
+        pcpul_vm.size = num_possible_cpus() * PMD_SIZE;
+        vm_area_register_early(&pcpul_vm, PMD_SIZE);
 
         for_each_possible_cpu(cpu) {
-                pmd_t *pmd;
+                pmd_t *pmd, pmd_v;
 
-                pmd = populate_extra_pmd((unsigned long)vm.addr
-                                         + cpu * PMD_SIZE);
-                set_pmd(pmd, pfn_pmd(page_to_pfn(virt_to_page(pcpur_ptrs[cpu])),
-                                     PAGE_KERNEL_LARGE));
+                pmd = populate_extra_pmd((unsigned long)pcpul_vm.addr +
+                                         cpu * PMD_SIZE);
+                pmd_v = pfn_pmd(page_to_pfn(virt_to_page(pcpul_map[cpu].ptr)),
+                                PAGE_KERNEL_LARGE);
+                set_pmd(pmd, pmd_v);
         }
 
         /* we're ready, commit */
         pr_info("PERCPU: Remapped at %p with large pages, static data "
-                "%zu bytes\n", vm.addr, static_size);
+                "%zu bytes\n", pcpul_vm.addr, static_size);
 
-        ret = pcpu_setup_first_chunk(pcpur_get_page, static_size,
+        ret = pcpu_setup_first_chunk(pcpul_get_page, static_size,
                                      PERCPU_FIRST_CHUNK_RESERVE, dyn_size,
-                                     PMD_SIZE, vm.addr, NULL);
-        goto out_free_ar;
+                                     PMD_SIZE, pcpul_vm.addr, NULL);
+
+        /* sort pcpul_map array for pcpu_lpage_remapped() */
+        for (i = 0; i < num_possible_cpus() - 1; i++)
+                for (j = i + 1; j < num_possible_cpus(); j++)
+                        if (pcpul_map[i].ptr > pcpul_map[j].ptr) {
+                                struct pcpul_ent tmp = pcpul_map[i];
+                                pcpul_map[i] = pcpul_map[j];
+                                pcpul_map[j] = tmp;
+                        }
+
+        return ret;
 
 enomem:
         for_each_possible_cpu(cpu)
-                if (pcpur_ptrs[cpu])
-                        free_bootmem(__pa(pcpur_ptrs[cpu]), PMD_SIZE);
-        ret = -ENOMEM;
-out_free_ar:
-        free_bootmem(__pa(pcpur_ptrs), ptrs_size);
-        return ret;
+                if (pcpul_map[cpu].ptr)
+                        free_bootmem(__pa(pcpul_map[cpu].ptr), pcpul_size);
+        free_bootmem(__pa(pcpul_map), map_size);
+        return -ENOMEM;
+}
+
+/**
+ * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area
+ * @kaddr: the kernel address in question
+ *
+ * Determine whether @kaddr falls in the pcpul recycled area.  This is
+ * used by pageattr to detect VM aliases and break up the pcpu PMD
+ * mapping such that the same physical page is not mapped under
+ * different attributes.
+ *
+ * The recycled area is always at the tail of a partially used PMD
+ * page.
+ *
+ * RETURNS:
+ * Address of corresponding remapped pcpu address if match is found;
+ * otherwise, NULL.
+ */
+void *pcpu_lpage_remapped(void *kaddr)
+{
+        void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK);
+        unsigned long offset = (unsigned long)kaddr & ~PMD_MASK;
+        int left = 0, right = num_possible_cpus() - 1;
+        int pos;
+
+        /* pcpul in use at all? */
+        if (!pcpul_map)
+                return NULL;
+
+        /* okay, perform binary search */
+        while (left <= right) {
+                pos = (left + right) / 2;
+
+                if (pcpul_map[pos].ptr < pmd_addr)
+                        left = pos + 1;
+                else if (pcpul_map[pos].ptr > pmd_addr)
+                        right = pos - 1;
+                else {
+                        /* it shouldn't be in the area for the first chunk */
+                        WARN_ON(offset < pcpul_size);
+
+                        return pcpul_vm.addr +
+                                pcpul_map[pos].cpu * PMD_SIZE + offset;
+                }
+        }
+
+        return NULL;
 }
 #else
-static ssize_t __init setup_pcpu_remap(size_t static_size)
+static ssize_t __init setup_pcpu_lpage(size_t static_size, bool chosen)
 {
         return -EINVAL;
 }
@@ -249,7 +329,7 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
  * mapping so that it can use PMD mapping without additional TLB
  * pressure.
  */
-static ssize_t __init setup_pcpu_embed(size_t static_size)
+static ssize_t __init setup_pcpu_embed(size_t static_size, bool chosen)
 {
         size_t reserve = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
 
@@ -258,7 +338,7 @@ static ssize_t __init setup_pcpu_embed(size_t static_size)
          * this.  Also, embedding allocation doesn't play well with
          * NUMA.
          */
-        if (!cpu_has_pse || pcpu_need_numa())
+        if (!chosen && (!cpu_has_pse || pcpu_need_numa()))
                 return -EINVAL;
 
         return pcpu_embed_first_chunk(static_size, PERCPU_FIRST_CHUNK_RESERVE,
@@ -308,8 +388,11 @@ static ssize_t __init setup_pcpu_4k(size_t static_size)
                         void *ptr;
 
                         ptr = pcpu_alloc_bootmem(cpu, PAGE_SIZE, PAGE_SIZE);
-                        if (!ptr)
+                        if (!ptr) {
+                                pr_warning("PERCPU: failed to allocate "
+                                           "4k page for cpu%u\n", cpu);
                                 goto enomem;
+                        }
 
                         memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE);
                         pcpu4k_pages[j++] = virt_to_page(ptr);
@@ -333,6 +416,16 @@ out_free_ar:
         return ret;
 }
 
+/* for explicit first chunk allocator selection */
+static char pcpu_chosen_alloc[16] __initdata;
+
+static int __init percpu_alloc_setup(char *str)
+{
+        strncpy(pcpu_chosen_alloc, str, sizeof(pcpu_chosen_alloc) - 1);
+        return 0;
+}
+early_param("percpu_alloc", percpu_alloc_setup);
+
 static inline void setup_percpu_segment(int cpu)
 {
 #ifdef CONFIG_X86_32
@@ -346,11 +439,6 @@ static inline void setup_percpu_segment(int cpu)
 #endif
 }
 
-/*
- * Great future plan:
- * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
- * Always point %gs to its beginning
- */
 void __init setup_per_cpu_areas(void)
 {
         size_t static_size = __per_cpu_end - __per_cpu_start;
@@ -367,9 +455,26 @@ void __init setup_per_cpu_areas(void)
          * of large page mappings.  Please read comments on top of
          * each allocator for details.
          */
-        ret = setup_pcpu_remap(static_size);
-        if (ret < 0)
-                ret = setup_pcpu_embed(static_size);
+        ret = -EINVAL;
+        if (strlen(pcpu_chosen_alloc)) {
+                if (strcmp(pcpu_chosen_alloc, "4k")) {
+                        if (!strcmp(pcpu_chosen_alloc, "lpage"))
+                                ret = setup_pcpu_lpage(static_size, true);
+                        else if (!strcmp(pcpu_chosen_alloc, "embed"))
+                                ret = setup_pcpu_embed(static_size, true);
+                        else
+                                pr_warning("PERCPU: unknown allocator %s "
+                                           "specified\n", pcpu_chosen_alloc);
+                        if (ret < 0)
+                                pr_warning("PERCPU: %s allocator failed (%zd), "
+                                           "falling back to 4k\n",
+                                           pcpu_chosen_alloc, ret);
+                }
+        } else {
+                ret = setup_pcpu_lpage(static_size, false);
+                if (ret < 0)
+                        ret = setup_pcpu_embed(static_size, false);
+        }
         if (ret < 0)
                 ret = setup_pcpu_4k(static_size);
         if (ret < 0)
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 124d40c575df..8ccabb8a2f6a 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -711,7 +711,6 @@ uv_activation_descriptor_init(int node, int pnode)
         unsigned long pa;
         unsigned long m;
         unsigned long n;
-        unsigned long mmr_image;
         struct bau_desc *adp;
         struct bau_desc *ad2;
 
@@ -727,12 +726,8 @@ uv_activation_descriptor_init(int node, int pnode)
         n = pa >> uv_nshift;
         m = pa & uv_mmask;
 
-        mmr_image = uv_read_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE);
-        if (mmr_image) {
-                uv_write_global_mmr64(pnode, (unsigned long)
-                                      UVH_LB_BAU_SB_DESCRIPTOR_BASE,
-                                      (n << UV_DESC_BASE_PNODE_SHIFT | m));
-        }
+        uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
+                              (n << UV_DESC_BASE_PNODE_SHIFT | m));
 
         /*
          * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a0f48f5671c0..5204332f475d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -346,6 +346,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
         printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
         show_registers(regs);
 
+        if (panic_on_io_nmi)
+                panic("NMI IOCK error: Not continuing");
+
         /* Re-enable the IOCK line, wait for a few seconds */
         reason = (reason & 0xf) | 8;
         outb(reason, 0x61);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5c3d6e81a7dc..7030b5f911bf 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2157,7 +2157,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
                 else
                         /* 32 bits PSE 4MB page */
                         context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
-                context->rsvd_bits_mask[1][0] = ~0ull;
+                context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
                 break;
         case PT32E_ROOT_LEVEL:
                 context->rsvd_bits_mask[0][2] =
@@ -2170,7 +2170,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
                 context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
                         rsvd_bits(maxphyaddr, 62) |
                         rsvd_bits(13, 20);              /* large page */
-                context->rsvd_bits_mask[1][0] = ~0ull;
+                context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
                 break;
         case PT64_ROOT_LEVEL:
                 context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
@@ -2186,7 +2186,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
                 context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
                         rsvd_bits(maxphyaddr, 51) |
                         rsvd_bits(13, 20);              /* large page */
-                context->rsvd_bits_mask[1][0] = ~0ull;
+                context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
                 break;
         }
 }
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 258e4591e1ca..67785f635399 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -281,7 +281,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 {
         unsigned access = gw->pt_access;
         struct kvm_mmu_page *shadow_page;
-        u64 spte, *sptep;
+        u64 spte, *sptep = NULL;
         int direct;
         gfn_t table_gfn;
         int r;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e770bf349ec4..356a0ce85c68 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3012,6 +3012,12 @@ static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
         return 1;
 }
 
+static int handle_vmx_insn(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+        kvm_queue_exception(vcpu, UD_VECTOR);
+        return 1;
+}
+
 static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
         unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
@@ -3198,6 +3204,15 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
         [EXIT_REASON_HLT]                     = handle_halt,
         [EXIT_REASON_INVLPG]                  = handle_invlpg,
         [EXIT_REASON_VMCALL]                  = handle_vmcall,
+        [EXIT_REASON_VMCLEAR]                 = handle_vmx_insn,
+        [EXIT_REASON_VMLAUNCH]                = handle_vmx_insn,
+        [EXIT_REASON_VMPTRLD]                 = handle_vmx_insn,
+        [EXIT_REASON_VMPTRST]                 = handle_vmx_insn,
+        [EXIT_REASON_VMREAD]                  = handle_vmx_insn,
+        [EXIT_REASON_VMRESUME]                = handle_vmx_insn,
+        [EXIT_REASON_VMWRITE]                 = handle_vmx_insn,
+        [EXIT_REASON_VMOFF]                   = handle_vmx_insn,
+        [EXIT_REASON_VMON]                    = handle_vmx_insn,
         [EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
         [EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
         [EXIT_REASON_WBINVD]                  = handle_wbinvd,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 249540f98513..fe5474aec41a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -898,6 +898,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
         case MSR_VM_HSAVE_PA:
         case MSR_P6_EVNTSEL0:
         case MSR_P6_EVNTSEL1:
+        case MSR_K7_EVNTSEL0:
                 data = 0;
                 break;
         case MSR_MTRRcap:
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index c1b6c232e02b..616de4628d60 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -1361,7 +1361,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt,
         return 0;
 }
 
-void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
+static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
 {
         u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(ctxt->vcpu, mask);
         /*
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index f4568605d7d5..ff485d361182 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -55,8 +55,10 @@ static void delay_tsc(unsigned long loops)
 
         preempt_disable();
         cpu = smp_processor_id();
+        rdtsc_barrier();
         rdtscl(bclock);
         for (;;) {
+                rdtsc_barrier();
                 rdtscl(now);
                 if ((now - bclock) >= loops)
                         break;
@@ -78,6 +80,7 @@ static void delay_tsc(unsigned long loops)
                 if (unlikely(cpu != smp_processor_id())) {
                         loops -= (now - bclock);
                         cpu = smp_processor_id();
+                        rdtsc_barrier();
                         rdtscl(bclock);
                 }
         }
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f53b57e4086f..47ce9a2ce5e7 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -177,20 +177,6 @@ static int __meminit save_mr(struct map_range *mr, int nr_range,
         return nr_range;
 }
 
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
-        if (direct_gbpages && cpu_has_gbpages)
-                printk(KERN_INFO "Using GB pages for direct mapping\n");
-        else
-                direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
-#endif
-
 /*
  * Setup the direct mapping of the physical memory at PAGE_OFFSET.
  * This runs before bootmem is initialized and gets pages directly from
@@ -210,9 +196,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
         printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
 
-        if (!after_bootmem)
-                init_gbpages();
-
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
         /*
          * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c4378f4fd4a5..b177652251a4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -598,6 +598,8 @@ void __init paging_init(void)
 
         sparse_memory_present_with_active_regions(MAX_NUMNODES);
         sparse_init();
+        /* clear the default setting with node 0 */
+        nodes_clear(node_states[N_NORMAL_MEMORY]);
         free_area_init_nodes(max_zone_pfns);
 }
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3cfe9ced8a4c..1b734d7a8966 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/pfn.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -681,8 +682,9 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias);
 static int cpa_process_alias(struct cpa_data *cpa)
 {
         struct cpa_data alias_cpa;
-        int ret = 0;
-        unsigned long temp_cpa_vaddr, vaddr;
+        unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
+        unsigned long vaddr, remapped;
+        int ret;
 
         if (cpa->pfn >= max_pfn_mapped)
                 return 0;
@@ -706,42 +708,55 @@ static int cpa_process_alias(struct cpa_data *cpa)
                     PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {
 
                 alias_cpa = *cpa;
-                temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
-                alias_cpa.vaddr = &temp_cpa_vaddr;
+                alias_cpa.vaddr = &laddr;
                 alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 
-
                 ret = __change_page_attr_set_clr(&alias_cpa, 0);
+                if (ret)
+                        return ret;
         }
 
 #ifdef CONFIG_X86_64
-        if (ret)
-                return ret;
         /*
-         * No need to redo, when the primary call touched the high
-         * mapping already:
-         */
-        if (within(vaddr, (unsigned long) _text, _brk_end))
-                return 0;
-
-        /*
-         * If the physical address is inside the kernel map, we need
+         * If the primary call didn't touch the high mapping already
+         * and the physical address is inside the kernel map, we need
          * to touch the high mapped kernel as well:
          */
-        if (!within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn()))
-                return 0;
+        if (!within(vaddr, (unsigned long)_text, _brk_end) &&
+            within(cpa->pfn, highmap_start_pfn(), highmap_end_pfn())) {
+                unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
+                                               __START_KERNEL_map - phys_base;
+                alias_cpa = *cpa;
+                alias_cpa.vaddr = &temp_cpa_vaddr;
+                alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
 
-        alias_cpa = *cpa;
-        temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base;
-        alias_cpa.vaddr = &temp_cpa_vaddr;
-        alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+                /*
+                 * The high mapping range is imprecise, so ignore the
+                 * return value.
+                 */
+                __change_page_attr_set_clr(&alias_cpa, 0);
+        }
+#endif
 
         /*
-         * The high mapping range is imprecise, so ignore the return value.
+         * If the PMD page was partially used for per-cpu remapping,
+         * the recycled area needs to be split and modified.  Because
+         * the area is always proper subset of a PMD page
+         * cpa->numpages is guaranteed to be 1 for these areas, so
+         * there's no need to loop over and check for further remaps.
          */
-        __change_page_attr_set_clr(&alias_cpa, 0);
-#endif
-        return ret;
+        remapped = (unsigned long)pcpu_lpage_remapped((void *)laddr);
+        if (remapped) {
+                WARN_ON(cpa->numpages > 1);
+                alias_cpa = *cpa;
+                alias_cpa.vaddr = &remapped;
+                alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+                ret = __change_page_attr_set_clr(&alias_cpa, 0);
+                if (ret)
+                        return ret;
+        }
+
+        return 0;
 }
 
 static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index d277ef1eea51..b3d20b9cac63 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -244,7 +244,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
         do_fpu_end();
         mtrr_ap_init();
 
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_OLD_MCE
         mcheck_init(&boot_cpu_data);
 #endif
 }