23 files changed, 288 insertions, 161 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 6c327b852e23..430d5b24af7b 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -26,6 +26,8 @@ CFLAGS_tsc.o		:= $(nostackp)
 CFLAGS_paravirt.o       := $(nostackp)
 GCOV_PROFILE_vsyscall_64.o      := n
 GCOV_PROFILE_hpet.o             := n
+GCOV_PROFILE_tsc.o              := n
+GCOV_PROFILE_paravirt.o         := n
 
 obj-y                   := process_$(BITS).o signal.o entry_$(BITS).o
 obj-y                   += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 9372f0406ad4..6c99f5037801 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1192,7 +1192,7 @@ out:
         return 0;
 }
 
-struct notifier_block device_nb = {
+static struct notifier_block device_nb = {
         .notifier_call = device_change_notifier,
 };
 
@@ -1763,7 +1763,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
         flag |= __GFP_ZERO;
         virt_addr = (void *)__get_free_pages(flag, get_order(size));
         if (!virt_addr)
-                return 0;
+                return NULL;
 
         paddr = virt_to_phys(virt_addr);
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 10b2accd12ea..c1b17e97252e 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -472,6 +472,8 @@ static u8 * __init alloc_event_buffer(struct amd_iommu *iommu)
         if (iommu->evt_buf == NULL)
                 return NULL;
 
+        iommu->evt_buf_size = EVT_BUFFER_SIZE;
+
         return iommu->evt_buf;
 }
 
@@ -691,6 +693,7 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 
                         devid = e->devid;
                         devid_to = e->ext >> 8;
+                        set_dev_entry_from_acpi(iommu, devid   , e->flags, 0);
                         set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
                         amd_iommu_alias_table[devid] = devid_to;
                         break;
@@ -749,11 +752,13 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 
                         devid = e->devid;
                         for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
-                                if (alias)
+                                if (alias) {
                                         amd_iommu_alias_table[dev_i] = devid_to;
-                                set_dev_entry_from_acpi(iommu,
-                                                amd_iommu_alias_table[dev_i],
-                                                flags, ext_flags);
+                                        set_dev_entry_from_acpi(iommu,
+                                                devid_to, flags, ext_flags);
+                                }
+                                set_dev_entry_from_acpi(iommu, dev_i,
+                                                        flags, ext_flags);
                         }
                         break;
                 default:
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 8c7c042ecad1..0a1c2830ec66 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -140,7 +140,6 @@ int x2apic_mode;
 #ifdef CONFIG_X86_X2APIC
 /* x2apic enabled before OS handover */
 static int x2apic_preenabled;
-static int disable_x2apic;
 static __init int setup_nox2apic(char *str)
 {
         if (x2apic_enabled()) {
@@ -149,7 +148,6 @@ static __init int setup_nox2apic(char *str)
                 return 0;
         }
 
-        disable_x2apic = 1;
         setup_clear_cpu_cap(X86_FEATURE_X2APIC);
         return 0;
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 4d0216fcb36c..90b5e6efa938 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1716,25 +1716,19 @@ __apicdebuginit(void) print_IO_APIC(void)
         return;
 }
 
-__apicdebuginit(void) print_APIC_bitfield(int base)
+__apicdebuginit(void) print_APIC_field(int base)
 {
-        unsigned int v;
-        int i, j;
+        int i;
 
         if (apic_verbosity == APIC_QUIET)
                 return;
 
-        printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG);
-        for (i = 0; i < 8; i++) {
-                v = apic_read(base + i*0x10);
-                for (j = 0; j < 32; j++) {
-                        if (v & (1<<j))
-                                printk("1");
-                        else
-                                printk("0");
-                }
-                printk("\n");
-        }
+        printk(KERN_DEBUG);
+
+        for (i = 0; i < 8; i++)
+                printk(KERN_CONT "%08x", apic_read(base + i*0x10));
+
+        printk(KERN_CONT "\n");
 }
 
 __apicdebuginit(void) print_local_APIC(void *dummy)
@@ -1745,7 +1739,7 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
         if (apic_verbosity == APIC_QUIET)
                 return;
 
-        printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
+        printk(KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
                 smp_processor_id(), hard_smp_processor_id());
         v = apic_read(APIC_ID);
         printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, read_apic_id());
@@ -1786,11 +1780,11 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
         printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
 
         printk(KERN_DEBUG "... APIC ISR field:\n");
-        print_APIC_bitfield(APIC_ISR);
+        print_APIC_field(APIC_ISR);
         printk(KERN_DEBUG "... APIC TMR field:\n");
-        print_APIC_bitfield(APIC_TMR);
+        print_APIC_field(APIC_TMR);
         printk(KERN_DEBUG "... APIC IRR field:\n");
-        print_APIC_bitfield(APIC_IRR);
+        print_APIC_field(APIC_IRR);
 
         if (APIC_INTEGRATED(ver)) {             /* !82489DX */
                 if (maxlvt > 3)         /* Due to the Pentium erratum 3AP. */
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/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 81cbe64ed6b4..2a50ef891000 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -299,7 +299,7 @@ static int transition_pstate(struct powernow_k8_data *data, u32 pstate)
 static int transition_fid_vid(struct powernow_k8_data *data,
                 u32 reqfid, u32 reqvid)
 {
-        if (core_voltage_pre_transition(data, reqvid))
+        if (core_voltage_pre_transition(data, reqvid, reqfid))
                 return 1;
 
         if (core_frequency_transition(data, reqfid))
@@ -327,17 +327,20 @@ static int transition_fid_vid(struct powernow_k8_data *data,
 
 /* Phase 1 - core voltage transition ... setup voltage */
 static int core_voltage_pre_transition(struct powernow_k8_data *data,
-                u32 reqvid)
+                u32 reqvid, u32 reqfid)
 {
         u32 rvosteps = data->rvo;
         u32 savefid = data->currfid;
-        u32 maxvid, lo;
+        u32 maxvid, lo, rvomult = 1;
 
         dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, "
                 "reqvid 0x%x, rvo 0x%x\n",
                 smp_processor_id(),
                 data->currfid, data->currvid, reqvid, data->rvo);
 
+        if ((savefid < LO_FID_TABLE_TOP) && (reqfid < LO_FID_TABLE_TOP))
+                rvomult = 2;
+        rvosteps *= rvomult;
         rdmsr(MSR_FIDVID_STATUS, lo, maxvid);
         maxvid = 0x1f & (maxvid >> 16);
         dprintk("ph1 maxvid=0x%x\n", maxvid);
@@ -351,7 +354,8 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data,
                         return 1;
         }
 
-        while ((rvosteps > 0) && ((data->rvo + data->currvid) > reqvid)) {
+        while ((rvosteps > 0) &&
+                        ((rvomult * data->rvo + data->currvid) > reqvid)) {
                 if (data->currvid == maxvid) {
                         rvosteps = 0;
                 } else {
@@ -384,13 +388,6 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid)
         u32 vcoreqfid, vcocurrfid, vcofiddiff;
         u32 fid_interval, savevid = data->currvid;
 
-        if ((reqfid < HI_FID_TABLE_BOTTOM) &&
-            (data->currfid < HI_FID_TABLE_BOTTOM)) {
-                printk(KERN_ERR PFX "ph2: illegal lo-lo transition "
-                                "0x%x 0x%x\n", reqfid, data->currfid);
-                return 1;
-        }
-
         if (data->currfid == reqfid) {
                 printk(KERN_ERR PFX "ph2 null fid transition 0x%x\n",
                                 data->currfid);
@@ -407,6 +404,9 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid)
         vcofiddiff = vcocurrfid > vcoreqfid ? vcocurrfid - vcoreqfid
             : vcoreqfid - vcocurrfid;
 
+        if ((reqfid <= LO_FID_TABLE_TOP) && (data->currfid <= LO_FID_TABLE_TOP))
+                vcofiddiff = 0;
+
         while (vcofiddiff > 2) {
                 (data->currfid & 1) ? (fid_interval = 1) : (fid_interval = 2);
 
@@ -1081,14 +1081,6 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
                 return 0;
         }
 
-        if ((fid < HI_FID_TABLE_BOTTOM) &&
-            (data->currfid < HI_FID_TABLE_BOTTOM)) {
-                printk(KERN_ERR PFX
-                       "ignoring illegal change in lo freq table-%x to 0x%x\n",
-                       data->currfid, fid);
-                return 1;
-        }
-
         dprintk("cpu %d, changing to fid 0x%x, vid 0x%x\n",
                 smp_processor_id(), fid, vid);
         freqs.old = find_khz_freq_from_fid(data->currfid);
@@ -1267,7 +1259,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
         static const char ACPI_PSS_BIOS_BUG_MSG[] =
                 KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
-                KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n";
+                FW_BUG PFX "Try again with latest BIOS.\n";
         struct powernow_k8_data *data;
         struct init_on_cpu init_on_cpu;
         int rc;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index c9c1190b5e1f..02ce824073cb 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -215,7 +215,8 @@ struct pst_s {
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "powernow-k8", msg)
 
-static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid);
+static int core_voltage_pre_transition(struct powernow_k8_data *data,
+        u32 reqvid, u32 regfid);
 static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid);
 static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 284d1de968bc..484c1e5f658e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -194,14 +194,14 @@ static void print_mce(struct mce *m)
                        m->cs, m->ip);
                 if (m->cs == __KERNEL_CS)
                         print_symbol("{%s}", m->ip);
-                printk("\n");
+                printk(KERN_CONT "\n");
         }
         printk(KERN_EMERG "TSC %llx ", m->tsc);
         if (m->addr)
-                printk("ADDR %llx ", m->addr);
+                printk(KERN_CONT "ADDR %llx ", m->addr);
         if (m->misc)
-                printk("MISC %llx ", m->misc);
-        printk("\n");
+                printk(KERN_CONT "MISC %llx ", m->misc);
+        printk(KERN_CONT "\n");
         printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
                         m->cpuvendor, m->cpuid, m->time, m->socketid,
                         m->apicid);
@@ -209,13 +209,13 @@ static void print_mce(struct mce *m)
 
 static void print_mce_head(void)
 {
-        printk(KERN_EMERG "\n" KERN_EMERG "HARDWARE ERROR\n");
+        printk(KERN_EMERG "\nHARDWARE ERROR\n");
 }
 
 static void print_mce_tail(void)
 {
         printk(KERN_EMERG "This is not a software problem!\n"
-               KERN_EMERG "Run through mcelog --ascii to decode and contact your hardware vendor\n");
+               "Run through mcelog --ascii to decode and contact your hardware vendor\n");
 }
 
 #define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -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..36c3dc7b8991 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);
@@ -1563,6 +1561,7 @@ void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 
 static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry);
 static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry);
+static DEFINE_PER_CPU(int, in_nmi_frame);
 
 
 static void
@@ -1578,7 +1577,9 @@ static void backtrace_warning(void *data, char *msg)
 
 static int backtrace_stack(void *data, char *name)
 {
-        /* Process all stacks: */
+        per_cpu(in_nmi_frame, smp_processor_id()) =
+                        x86_is_stack_id(NMI_STACK, name);
+
         return 0;
 }
 
@@ -1586,6 +1587,9 @@ static void backtrace_address(void *data, unsigned long addr, int reliable)
 {
         struct perf_callchain_entry *entry = data;
 
+        if (per_cpu(in_nmi_frame, smp_processor_id()))
+                return;
+
         if (reliable)
                 callchain_store(entry, addr);
 }
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 5c481f6205bf..e60ed740d2b3 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -803,8 +803,3 @@ int __kprobes lapic_wd_event(unsigned nmi_hz)
         wd_ops->rearm(wd, nmi_hz);
         return 1;
 }
-
-int lapic_watchdog_ok(void)
-{
-        return wd_ops != NULL;
-}
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/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index d593cd1f58dc..bca5fba91c9e 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -19,6 +19,12 @@
 
 #include "dumpstack.h"
 
+/* Just a stub for now */
+int x86_is_stack_id(int id, char *name)
+{
+        return 0;
+}
+
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data)
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index d35db5993fd6..54b0a3276766 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -19,10 +19,8 @@
 
 #include "dumpstack.h"
 
-static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
-                                        unsigned *usedp, char **idp)
-{
-        static char ids[][8] = {
+
+static char x86_stack_ids[][8] = {
                 [DEBUG_STACK - 1] = "#DB",
                 [NMI_STACK - 1] = "NMI",
                 [DOUBLEFAULT_STACK - 1] = "#DF",
@@ -33,6 +31,15 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                         N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
 #endif
         };
+
+int x86_is_stack_id(int id, char *name)
+{
+        return x86_stack_ids[id - 1] == name;
+}
+
+static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
+                                        unsigned *usedp, char **idp)
+{
         unsigned k;
 
         /*
@@ -61,7 +68,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                         if (*usedp & (1U << k))
                                 break;
                         *usedp |= 1U << k;
-                        *idp = ids[k];
+                        *idp = x86_stack_ids[k];
                         return (unsigned long *)end;
                 }
                 /*
@@ -81,12 +88,13 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
                         do {
                                 ++j;
                                 end -= EXCEPTION_STKSZ;
-                                ids[j][4] = '1' + (j - N_EXCEPTION_STACKS);
+                                x86_stack_ids[j][4] = '1' +
+                                                (j - N_EXCEPTION_STACKS);
                         } while (stack < end - EXCEPTION_STKSZ);
                         if (*usedp & (1U << j))
                                 break;
                         *usedp |= 1U << j;
-                        *idp = ids[j];
+                        *idp = x86_stack_ids[j];
                         return (unsigned long *)end;
                 }
 #endif
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7271fa33d791..5cb5725b2bae 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -627,10 +627,9 @@ __init void e820_setup_gap(void)
 #ifdef CONFIG_X86_64
         if (!found) {
                 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
-                printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit "
-                       "address range\n"
-                       KERN_ERR "PCI: Unassigned devices with 32bit resource "
-                       "registers may break!\n");
+                printk(KERN_ERR
+        "PCI: Warning: Cannot find a gap in the 32bit address range\n"
+        "PCI: Unassigned devices with 32bit resource registers may break!\n");
         }
 #endif
 
@@ -1383,6 +1382,8 @@ 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 +1401,19 @@ 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/kvm.c b/arch/x86/kernel/kvm.c
index a78ecad0c900..c664d515f613 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -200,7 +200,7 @@ static void kvm_leave_lazy_mmu(void)
         state->mode = paravirt_get_lazy_mode();
 }
 
-static void paravirt_ops_setup(void)
+static void __init paravirt_ops_setup(void)
 {
         pv_info.name = "KVM";
         pv_info.paravirt_enabled = 1;
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/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index cfd9f9063896..d2e56b8f48e7 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -675,7 +675,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
  nommu:
         /* Should not happen anymore */
         printk(KERN_WARNING "PCI-DMA: More than 4GB of RAM and no IOMMU\n"
-               KERN_WARNING "falling back to iommu=soft.\n");
+               "falling back to iommu=soft.\n");
         return -1;
 }
 
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);