6 files changed, 68 insertions, 50 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c4f667896c28..77848d9fca68 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -114,6 +114,13 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
+static int __init x86_xsave_setup(char *s)
+{
+        setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+        return 1;
+}
+__setup("noxsave", x86_xsave_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_serial_nr __cpuinitdata = 1;
@@ -1203,6 +1210,8 @@ void __cpuinit cpu_init(void)
         load_TR_desc();
         load_LDT(&init_mm.context);
 
+        t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+
 #ifdef CONFIG_DOUBLEFAULT
         /* Set up doublefault TSS pointer in the GDT */
         __set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 9d3af380c6bd..208ecf6643df 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -65,14 +65,18 @@ enum {
 struct acpi_cpufreq_data {
         struct acpi_processor_performance *acpi_data;
         struct cpufreq_frequency_table *freq_table;
-        unsigned int max_freq;
         unsigned int resume;
         unsigned int cpu_feature;
-        u64 saved_aperf, saved_mperf;
 };
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
+struct acpi_msr_data {
+        u64 saved_aperf, saved_mperf;
+};
+
+static DEFINE_PER_CPU(struct acpi_msr_data, msr_data);
+
 DEFINE_TRACE(power_mark);
 
 /* acpi_perf_data is a pointer to percpu data. */
@@ -153,7 +157,8 @@ struct drv_cmd {
         u32 val;
 };
 
-static long do_drv_read(void *_cmd)
+/* Called via smp_call_function_single(), on the target CPU */
+static void do_drv_read(void *_cmd)
 {
         struct drv_cmd *cmd = _cmd;
         u32 h;
@@ -170,10 +175,10 @@ static long do_drv_read(void *_cmd)
         default:
                 break;
         }
-        return 0;
 }
 
-static long do_drv_write(void *_cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
 {
         struct drv_cmd *cmd = _cmd;
         u32 lo, hi;
@@ -192,23 +197,24 @@ static long do_drv_write(void *_cmd)
         default:
                 break;
         }
-        return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
         cmd->val = 0;
 
-        work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
+        smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-        unsigned int i;
+        int this_cpu;
 
-        for_each_cpu(i, cmd->mask) {
-                work_on_cpu(i, do_drv_write, cmd);
-        }
+        this_cpu = get_cpu();
+        if (cpumask_test_cpu(this_cpu, cmd->mask))
+                do_drv_write(cmd);
+        smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
+        put_cpu();
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -252,15 +258,13 @@ struct perf_pair {
         } aperf, mperf;
 };
 
-
-static long read_measured_perf_ctrs(void *_cur)
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
 {
         struct perf_pair *cur = _cur;
 
         rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi);
         rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi);
-
-        return 0;
 }
 
 /*
@@ -283,15 +287,15 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
         unsigned int perf_percent;
         unsigned int retval;
 
-        if (!work_on_cpu(cpu, read_measured_perf_ctrs, &readin))
+        if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1))
                 return 0;
 
         cur.aperf.whole = readin.aperf.whole -
-                                per_cpu(drv_data, cpu)->saved_aperf;
+                                per_cpu(msr_data, cpu).saved_aperf;
         cur.mperf.whole = readin.mperf.whole -
-                                per_cpu(drv_data, cpu)->saved_mperf;
-        per_cpu(drv_data, cpu)->saved_aperf = readin.aperf.whole;
-        per_cpu(drv_data, cpu)->saved_mperf = readin.mperf.whole;
+                                per_cpu(msr_data, cpu).saved_mperf;
+        per_cpu(msr_data, cpu).saved_aperf = readin.aperf.whole;
+        per_cpu(msr_data, cpu).saved_mperf = readin.mperf.whole;
 
 #ifdef __i386__
         /*
@@ -335,7 +339,7 @@ static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 
 #endif
 
-        retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100;
+        retval = (policy->cpuinfo.max_freq * perf_percent) / 100;
 
         return retval;
 }
@@ -688,16 +692,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
         /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
         if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
             policy->cpuinfo.transition_latency > 20 * 1000) {
-                static int print_once;
                 policy->cpuinfo.transition_latency = 20 * 1000;
-                if (!print_once) {
-                        print_once = 1;
-                        printk(KERN_INFO "Capping off P-state tranision latency"
-                                " at 20 uS\n");
-                }
+                        printk_once(KERN_INFO "Capping off P-state tranision"
+                                    " latency at 20 uS\n");
         }
 
-        data->max_freq = perf->states[0].core_frequency * 1000;
         /* table init */
         for (i = 0; i < perf->state_count; i++) {
                 if (i > 0 && perf->states[i].core_frequency >=
@@ -716,6 +715,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
         if (result)
                 goto err_freqfree;
 
+        if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
+                printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
+
         switch (perf->control_register.space_id) {
         case ACPI_ADR_SPACE_SYSTEM_IO:
                 /* Current speed is unknown and not detectable by IO port */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 863f89568b1a..6fb0b359d2a5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -239,9 +239,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
                  * Don't get the IP here because it's unlikely to
                  * have anything to do with the actual error location.
                  */
-
-                mce_log(&m);
-                add_taint(TAINT_MACHINE_CHECK);
+                if (!(flags & MCP_DONTLOG)) {
+                        mce_log(&m);
+                        add_taint(TAINT_MACHINE_CHECK);
+                }
 
                 /*
                  * Clear state for this bank.
@@ -452,13 +453,14 @@ void mce_log_therm_throt_event(__u64 status)
  */
 
 static int check_interval = 5 * 60; /* 5 minutes */
-static int next_interval; /* in jiffies */
+static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
 static void mcheck_timer(unsigned long);
 static DEFINE_PER_CPU(struct timer_list, mce_timer);
 
 static void mcheck_timer(unsigned long data)
 {
         struct timer_list *t = &per_cpu(mce_timer, data);
+        int *n;
 
         WARN_ON(smp_processor_id() != data);
 
@@ -470,14 +472,14 @@ static void mcheck_timer(unsigned long data)
          * Alert userspace if needed.  If we logged an MCE, reduce the
          * polling interval, otherwise increase the polling interval.
          */
+        n = &__get_cpu_var(next_interval);
         if (mce_notify_user()) {
-                next_interval = max(next_interval/2, HZ/100);
+                *n = max(*n/2, HZ/100);
         } else {
-                next_interval = min(next_interval * 2,
-                                (int)round_jiffies_relative(check_interval*HZ));
+                *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
         }
 
-        t->expires = jiffies + next_interval;
+        t->expires = jiffies + *n;
         add_timer(t);
 }
 
@@ -584,7 +586,7 @@ static void mce_init(void *dummy)
          * Log the machine checks left over from the previous reset.
          */
         bitmap_fill(all_banks, MAX_NR_BANKS);
-        machine_check_poll(MCP_UC, &all_banks);
+        machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks);
 
         set_in_cr4(X86_CR4_MCE);
 
@@ -632,14 +634,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
 static void mce_init_timer(void)
 {
         struct timer_list *t = &__get_cpu_var(mce_timer);
+        int *n = &__get_cpu_var(next_interval);
 
-        /* data race harmless because everyone sets to the same value */
-        if (!next_interval)
-                next_interval = check_interval * HZ;
-        if (!next_interval)
+        *n = check_interval * HZ;
+        if (!*n)
                 return;
         setup_timer(t, mcheck_timer, smp_processor_id());
-        t->expires = round_jiffies(jiffies + next_interval);
+        t->expires = round_jiffies(jiffies + *n);
         add_timer(t);
 }
 
@@ -907,7 +908,6 @@ static void mce_cpu_restart(void *data)
 /* Reinit MCEs after user configuration changes */
 static void mce_restart(void)
 {
-        next_interval = check_interval * HZ;
         on_each_cpu(mce_cpu_restart, NULL, 1);
 }
 
@@ -1110,7 +1110,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
                 break;
         case CPU_DOWN_FAILED:
         case CPU_DOWN_FAILED_FROZEN:
-                t->expires = round_jiffies(jiffies + next_interval);
+                t->expires = round_jiffies(jiffies +
+                                                __get_cpu_var(next_interval));
                 add_timer_on(t, cpu);
                 smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
                 break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index d6b72df89d69..cef3ee30744b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -151,10 +151,11 @@ static void print_update(char *type, int *hdr, int num)
 static void cmci_discover(int banks, int boot)
 {
         unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+        unsigned long flags;
         int hdr = 0;
         int i;
 
-        spin_lock(&cmci_discover_lock);
+        spin_lock_irqsave(&cmci_discover_lock, flags);
         for (i = 0; i < banks; i++) {
                 u64 val;
 
@@ -184,7 +185,7 @@ static void cmci_discover(int banks, int boot)
                         WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
                 }
         }
-        spin_unlock(&cmci_discover_lock);
+        spin_unlock_irqrestore(&cmci_discover_lock, flags);
         if (hdr)
                 printk(KERN_CONT "\n");
 }
@@ -211,13 +212,14 @@ void cmci_recheck(void)
  */
 void cmci_clear(void)
 {
+        unsigned long flags;
         int i;
         int banks;
         u64 val;
 
         if (!cmci_supported(&banks))
                 return;
-        spin_lock(&cmci_discover_lock);
+        spin_lock_irqsave(&cmci_discover_lock, flags);
         for (i = 0; i < banks; i++) {
                 if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
                         continue;
@@ -227,7 +229,7 @@ void cmci_clear(void)
                 wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
                 __clear_bit(i, __get_cpu_var(mce_banks_owned));
         }
-        spin_unlock(&cmci_discover_lock);
+        spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 0b776c09aff3..d21d4fb161f7 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -275,7 +275,11 @@ static void __init print_mtrr_state(void)
         }
         printk(KERN_DEBUG "MTRR variable ranges %sabled:\n",
                mtrr_state.enabled & 2 ? "en" : "dis");
-        high_width = ((size_or_mask ? ffs(size_or_mask) - 1 : 32) - (32 - PAGE_SHIFT) + 3) / 4;
+        if (size_or_mask & 0xffffffffUL)
+                high_width = ffs(size_or_mask & 0xffffffffUL) - 1;
+        else
+                high_width = ffs(size_or_mask>>32) + 32 - 1;
+        high_width = (high_width - (32 - PAGE_SHIFT) + 3) / 4;
         for (i = 0; i < num_var_ranges; ++i) {
                 if (mtrr_state.var_ranges[i].mask_lo & (1 << 11))
                         printk(KERN_DEBUG "  %u base %0*X%05X000 mask %0*X%05X000 %s\n",
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index f93047fed791..d5e30397246b 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
         if (c->x86_max_cores * smp_num_siblings > 1) {
                 seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
                 seq_printf(m, "siblings\t: %d\n",
-                           cpumask_weight(cpu_sibling_mask(cpu)));
+                           cpumask_weight(cpu_core_mask(cpu)));
                 seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
                 seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
                 seq_printf(m, "apicid\t\t: %d\n", c->apicid);