11 files changed, 104 insertions, 85 deletions

diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 7b598b84c902..f744f54cb248 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -698,9 +698,11 @@ void __init uv_system_init(void)
                 for (j = 0; j < 64; j++) {
                         if (!test_bit(j, &present))
                                 continue;
-                        uv_blade_info[blade].pnode = (i * 64 + j);
+                        pnode = (i * 64 + j);
+                        uv_blade_info[blade].pnode = pnode;
                         uv_blade_info[blade].nr_possible_cpus = 0;
                         uv_blade_info[blade].nr_online_cpus = 0;
+                        max_pnode = max(pnode, max_pnode);
                         blade++;
                 }
         }
@@ -738,7 +740,6 @@ void __init uv_system_init(void)
                 uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid);
                 uv_node_to_blade[nid] = blade;
                 uv_cpu_to_blade[cpu] = blade;
-                max_pnode = max(pnode, max_pnode);
         }
 
         /* Add blade/pnode info for nodes without cpus */
@@ -750,7 +751,6 @@ void __init uv_system_init(void)
                 pnode = (paddr >> m_val) & pnode_mask;
                 blade = boot_pnode_to_blade(pnode);
                 uv_node_to_blade[nid] = blade;
-                max_pnode = max(pnode, max_pnode);
         }
 
         map_gru_high(max_pnode);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 224392d8fe8c..5e975298fa81 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -530,7 +530,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
                 err = -ENOMEM;
                 goto out;
         }
-        if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
+        if (!zalloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
                 kfree(b);
                 err = -ENOMEM;
                 goto out;
@@ -543,7 +543,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
         cpumask_setall(b->cpus);
 #else
-        cpumask_copy(b->cpus, c->llc_shared_map);
+        cpumask_set_cpu(cpu, b->cpus);
 #endif
 
         per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index c2a8b26d4fea..d9368eeda309 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -202,10 +202,11 @@ static int therm_throt_process(bool new_event, int event, int level)
 
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
-static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
+static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
+                                unsigned int cpu)
 {
         int err;
-        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+        struct cpuinfo_x86 *c = &cpu_data(cpu);
 
         err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group);
         if (err)
@@ -251,7 +252,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
                 mutex_lock(&therm_cpu_lock);
-                err = thermal_throttle_add_dev(sys_dev);
+                err = thermal_throttle_add_dev(sys_dev, cpu);
                 mutex_unlock(&therm_cpu_lock);
                 WARN_ON(err);
                 break;
@@ -287,7 +288,7 @@ static __init int thermal_throttle_init_device(void)
 #endif
         /* connect live CPUs to sysfs */
         for_each_online_cpu(cpu) {
-                err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
+                err = thermal_throttle_add_dev(get_cpu_sysdev(cpu), cpu);
                 WARN_ON(err);
         }
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index f2da20fda02d..3efdf2870a35 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1154,7 +1154,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
                 /*
                  * event overflow
                  */
-                handled         = 1;
+                handled++;
                 data.period     = event->hw.last_period;
 
                 if (!x86_perf_event_set_period(event))
@@ -1200,12 +1200,20 @@ void perf_events_lapic_init(void)
         apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
+struct pmu_nmi_state {
+        unsigned int    marked;
+        int             handled;
+};
+
+static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
+
 static int __kprobes
 perf_event_nmi_handler(struct notifier_block *self,
                          unsigned long cmd, void *__args)
 {
         struct die_args *args = __args;
-        struct pt_regs *regs;
+        unsigned int this_nmi;
+        int handled;
 
         if (!atomic_read(&active_events))
                 return NOTIFY_DONE;
@@ -1214,22 +1222,47 @@ perf_event_nmi_handler(struct notifier_block *self,
         case DIE_NMI:
         case DIE_NMI_IPI:
                 break;
-
+        case DIE_NMIUNKNOWN:
+                this_nmi = percpu_read(irq_stat.__nmi_count);
+                if (this_nmi != __get_cpu_var(pmu_nmi).marked)
+                        /* let the kernel handle the unknown nmi */
+                        return NOTIFY_DONE;
+                /*
+                 * This one is a PMU back-to-back nmi. Two events
+                 * trigger 'simultaneously' raising two back-to-back
+                 * NMIs. If the first NMI handles both, the latter
+                 * will be empty and daze the CPU. So, we drop it to
+                 * avoid false-positive 'unknown nmi' messages.
+                 */
+                return NOTIFY_STOP;
         default:
                 return NOTIFY_DONE;
         }
 
-        regs = args->regs;
-
         apic_write(APIC_LVTPC, APIC_DM_NMI);
-        /*
-         * Can't rely on the handled return value to say it was our NMI, two
-         * events could trigger 'simultaneously' raising two back-to-back NMIs.
-         *
-         * If the first NMI handles both, the latter will be empty and daze
-         * the CPU.
-         */
-        x86_pmu.handle_irq(regs);
+
+        handled = x86_pmu.handle_irq(args->regs);
+        if (!handled)
+                return NOTIFY_DONE;
+
+        this_nmi = percpu_read(irq_stat.__nmi_count);
+        if ((handled > 1) ||
+                /* the next nmi could be a back-to-back nmi */
+            ((__get_cpu_var(pmu_nmi).marked == this_nmi) &&
+             (__get_cpu_var(pmu_nmi).handled > 1))) {
+                /*
+                 * We could have two subsequent back-to-back nmis: The
+                 * first handles more than one counter, the 2nd
+                 * handles only one counter and the 3rd handles no
+                 * counter.
+                 *
+                 * This is the 2nd nmi because the previous was
+                 * handling more than one counter. We will mark the
+                 * next (3rd) and then drop it if unhandled.
+                 */
+                __get_cpu_var(pmu_nmi).marked   = this_nmi + 1;
+                __get_cpu_var(pmu_nmi).handled  = handled;
+        }
 
         return NOTIFY_STOP;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index d8d86d014008..ee05c90012d2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -712,7 +712,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
         struct perf_sample_data data;
         struct cpu_hw_events *cpuc;
         int bit, loops;
-        u64 ack, status;
+        u64 status;
+        int handled = 0;
 
         perf_sample_data_init(&data, 0);
 
@@ -728,6 +729,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
         loops = 0;
 again:
+        intel_pmu_ack_status(status);
         if (++loops > 100) {
                 WARN_ONCE(1, "perfevents: irq loop stuck!\n");
                 perf_event_print_debug();
@@ -736,19 +738,22 @@ again:
         }
 
         inc_irq_stat(apic_perf_irqs);
-        ack = status;
 
         intel_pmu_lbr_read();
 
         /*
          * PEBS overflow sets bit 62 in the global status register
          */
-        if (__test_and_clear_bit(62, (unsigned long *)&status))
+        if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+                handled++;
                 x86_pmu.drain_pebs(regs);
+        }
 
         for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
                 struct perf_event *event = cpuc->events[bit];
 
+                handled++;
+
                 if (!test_bit(bit, cpuc->active_mask))
                         continue;
 
@@ -761,8 +766,6 @@ again:
                         x86_pmu_stop(event);
         }
 
-        intel_pmu_ack_status(ack);
-
         /*
          * Repeat if there is more work to be done:
          */
@@ -772,7 +775,7 @@ again:
 
 done:
         intel_pmu_enable_all(0);
-        return 1;
+        return handled;
 }
 
 static struct event_constraint *
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 7e578e9cc58b..b560db3305be 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -692,7 +692,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
                 inc_irq_stat(apic_perf_irqs);
         }
 
-        return handled > 0;
+        return handled;
 }
 
 /*
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index e5cc7e82e60d..ebdb85cf2686 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -18,7 +18,6 @@
 #include <asm/apic.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
-#include <asm/hpet.h>
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -192,21 +191,6 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 }
 #endif
 
-/*
- * Force the read back of the CMP register in hpet_next_event()
- * to work around the problem that the CMP register write seems to be
- * delayed. See hpet_next_event() for details.
- *
- * We do this on all SMBUS incarnations for now until we have more
- * information about the affected chipsets.
- */
-static void __init ati_hpet_bugs(int num, int slot, int func)
-{
-#ifdef CONFIG_HPET_TIMER
-        hpet_readback_cmp = 1;
-#endif
-}
-
 #define QFLAG_APPLY_ONCE        0x1
 #define QFLAG_APPLIED           0x2
 #define QFLAG_DONE              (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -236,8 +220,6 @@ static struct chipset early_qrk[] __initdata = {
           PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
         { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
           PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
-        { PCI_VENDOR_ID_ATI, PCI_ANY_ID,
-          PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs },
         {}
 };
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 351f9c0fea1f..410fdb3f1939 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -35,7 +35,6 @@
 unsigned long                           hpet_address;
 u8                                      hpet_blockid; /* OS timer block num */
 u8                                      hpet_msi_disable;
-u8                                      hpet_readback_cmp;
 
 #ifdef CONFIG_PCI_MSI
 static unsigned long                    hpet_num_timers;
@@ -395,23 +394,27 @@ static int hpet_next_event(unsigned long delta,
          * at that point and we would wait for the next hpet interrupt
          * forever. We found out that reading the CMP register back
          * forces the transfer so we can rely on the comparison with
-         * the counter register below.
+         * the counter register below. If the read back from the
+         * compare register does not match the value we programmed
+         * then we might have a real hardware problem. We can not do
+         * much about it here, but at least alert the user/admin with
+         * a prominent warning.
          *
-         * That works fine on those ATI chipsets, but on newer Intel
-         * chipsets (ICH9...) this triggers due to an erratum: Reading
-         * the comparator immediately following a write is returning
-         * the old value.
+         * An erratum on some chipsets (ICH9,..), results in
+         * comparator read immediately following a write returning old
+         * value. Workaround for this is to read this value second
+         * time, when first read returns old value.
          *
-         * We restrict the read back to the affected ATI chipsets (set
-         * by quirks) and also run it with hpet=verbose for debugging
-         * purposes.
+         * In fact the write to the comparator register is delayed up
+         * to two HPET cycles so the workaround we tried to restrict
+         * the readback to those known to be borked ATI chipsets
+         * failed miserably. So we give up on optimizations forever
+         * and penalize all HPET incarnations unconditionally.
          */
-        if (hpet_readback_cmp || hpet_verbose) {
-                u32 cmp = hpet_readl(HPET_Tn_CMP(timer));
-
-                if (cmp != cnt)
+        if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
+                if (hpet_readl(HPET_Tn_CMP(timer)) != cnt)
                         printk_once(KERN_WARNING
-                            "hpet: compare register read back failed.\n");
+                                "hpet: compare register read back failed.\n");
         }
 
         return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index a474ec37c32f..ff15c9dcc25d 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -206,11 +206,27 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
 int arch_bp_generic_fields(int x86_len, int x86_type,
                            int *gen_len, int *gen_type)
 {
-        /* Len */
-        switch (x86_len) {
-        case X86_BREAKPOINT_LEN_X:
+        /* Type */
+        switch (x86_type) {
+        case X86_BREAKPOINT_EXECUTE:
+                if (x86_len != X86_BREAKPOINT_LEN_X)
+                        return -EINVAL;
+
+                *gen_type = HW_BREAKPOINT_X;
                 *gen_len = sizeof(long);
+                return 0;
+        case X86_BREAKPOINT_WRITE:
+                *gen_type = HW_BREAKPOINT_W;
                 break;
+        case X86_BREAKPOINT_RW:
+                *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        /* Len */
+        switch (x86_len) {
         case X86_BREAKPOINT_LEN_1:
                 *gen_len = HW_BREAKPOINT_LEN_1;
                 break;
@@ -229,21 +245,6 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
                 return -EINVAL;
         }
 
-        /* Type */
-        switch (x86_type) {
-        case X86_BREAKPOINT_EXECUTE:
-                *gen_type = HW_BREAKPOINT_X;
-                break;
-        case X86_BREAKPOINT_WRITE:
-                *gen_type = HW_BREAKPOINT_W;
-                break;
-        case X86_BREAKPOINT_RW:
-                *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R;
-                break;
-        default:
-                return -EINVAL;
-        }
-
         return 0;
 }
 
@@ -316,9 +317,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
         ret = -EINVAL;
 
         switch (info->len) {
-        case X86_BREAKPOINT_LEN_X:
-                align = sizeof(long) -1;
-                break;
         case X86_BREAKPOINT_LEN_1:
                 align = 0;
                 break;
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index a874495b3673..e2a595257390 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -45,8 +45,7 @@ void __init setup_trampoline_page_table(void)
         /* Copy kernel address range */
         clone_pgd_range(trampoline_pg_dir + KERNEL_PGD_BOUNDARY,
                         swapper_pg_dir + KERNEL_PGD_BOUNDARY,
-                        min_t(unsigned long, KERNEL_PGD_PTRS,
-                              KERNEL_PGD_BOUNDARY));
+                        KERNEL_PGD_PTRS);
 
         /* Initialize low mappings */
         clone_pgd_range(trampoline_pg_dir,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index d632934cb638..26a863a9c2a8 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -655,7 +655,7 @@ void restore_sched_clock_state(void)
 
         local_irq_save(flags);
 
-        get_cpu_var(cyc2ns_offset) = 0;
+        __get_cpu_var(cyc2ns_offset) = 0;
         offset = cyc2ns_suspend - sched_clock();
 
         for_each_possible_cpu(cpu)