Merge branch 'linus' into x86/core

Conflicts:
	arch/x86/kernel/genapic_64.c
	include/asm-x86/kvm_host.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

22 files changed, 296 insertions, 105 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 608a12ff483a..53ab36878736 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -22,7 +22,6 @@ config X86
         select HAVE_IDE
         select HAVE_OPROFILE
         select HAVE_IOREMAP_PROT
-        select HAVE_GET_USER_PAGES_FAST
         select HAVE_KPROBES
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select HAVE_KRETPROBES
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 9e341c9d9414..84318edad8fb 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1705,15 +1705,19 @@ static int __init parse_lapic_timer_c2_ok(char *arg)
 }
 early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);
 
-static int __init apic_set_verbosity(char *str)
+static int __init apic_set_verbosity(char *arg)
 {
-        if (strcmp("debug", str) == 0)
+        if (!arg)
+                return -EINVAL;
+
+        if (strcmp(arg, "debug") == 0)
                 apic_verbosity = APIC_DEBUG;
-        else if (strcmp("verbose", str) == 0)
+        else if (strcmp(arg, "verbose") == 0)
                 apic_verbosity = APIC_VERBOSE;
-        return 1;
+
+        return 0;
 }
-__setup("apic=", apic_set_verbosity);
+early_param("apic", apic_set_verbosity);
 
 static int __init lapic_insert_resource(void)
 {
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c9b58a806e85..c8e315f1aa83 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -50,6 +50,8 @@ static double __initdata y = 3145727.0;
  */
 static void __init check_fpu(void)
 {
+        s32 fdiv_bug;
+
         if (!boot_cpu_data.hard_math) {
 #ifndef CONFIG_MATH_EMULATION
                 printk(KERN_EMERG "No coprocessor found and no math emulation present.\n");
@@ -74,8 +76,10 @@ static void __init check_fpu(void)
                 "fistpl %0\n\t"
                 "fwait\n\t"
                 "fninit"
-                : "=m" (*&boot_cpu_data.fdiv_bug)
+                : "=m" (*&fdiv_bug)
                 : "m" (*&x), "m" (*&y));
+
+        boot_cpu_data.fdiv_bug = fdiv_bug;
         if (boot_cpu_data.fdiv_bug)
                 printk("Hmm, FPU with FDIV bug.\n");
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index cb7a5715596d..efae3b22a0ff 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -235,9 +235,9 @@ config X86_LONGHAUL
           If in doubt, say N.
 
 config X86_E_POWERSAVER
-        tristate "VIA C7 Enhanced PowerSaver (EXPERIMENTAL)"
+        tristate "VIA C7 Enhanced PowerSaver"
         select CPU_FREQ_TABLE
-        depends on X86_32 && EXPERIMENTAL
+        depends on X86_32
         help
           This adds the CPUFreq driver for VIA C7 processors.
 
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
index 94619c22f563..e4a4bf870e94 100644
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
@@ -44,7 +44,7 @@ struct s_elan_multiplier {
  * It is important that the frequencies
  * are listed in ascending order here!
  */
-struct s_elan_multiplier elan_multiplier[] = {
+static struct s_elan_multiplier elan_multiplier[] = {
         {1000,  0x02,   0x18},
         {2000,  0x02,   0x10},
         {4000,  0x02,   0x08},
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index c45ca6d4dce1..4e7271999a74 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -66,7 +66,6 @@ static u32 find_freq_from_fid(u32 fid)
         return 800 + (fid * 100);
 }
 
-
 /* Return a frequency in KHz, given an input fid */
 static u32 find_khz_freq_from_fid(u32 fid)
 {
@@ -78,7 +77,6 @@ static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, u32 p
         return data[pstate].frequency;
 }
 
-
 /* Return the vco fid for an input fid
  *
  * Each "low" fid has corresponding "high" fid, and you can get to "low" fids
@@ -166,7 +164,6 @@ static void fidvid_msr_init(void)
         wrmsr(MSR_FIDVID_CTL, lo, hi);
 }
 
-
 /* write the new fid value along with the other control fields to the msr */
 static int write_new_fid(struct powernow_k8_data *data, u32 fid)
 {
@@ -740,44 +737,63 @@ static int find_psb_table(struct powernow_k8_data *data)
 #ifdef CONFIG_X86_POWERNOW_K8_ACPI
 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index)
 {
-        if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE))
+        if (!data->acpi_data->state_count || (cpu_family == CPU_HW_PSTATE))
                 return;
 
-        data->irt = (data->acpi_data.states[index].control >> IRT_SHIFT) & IRT_MASK;
-        data->rvo = (data->acpi_data.states[index].control >> RVO_SHIFT) & RVO_MASK;
-        data->exttype = (data->acpi_data.states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK;
-        data->plllock = (data->acpi_data.states[index].control >> PLL_L_SHIFT) & PLL_L_MASK;
-        data->vidmvs = 1 << ((data->acpi_data.states[index].control >> MVS_SHIFT) & MVS_MASK);
-        data->vstable = (data->acpi_data.states[index].control >> VST_SHIFT) & VST_MASK;
+        data->irt = (data->acpi_data->states[index].control >> IRT_SHIFT) & IRT_MASK;
+        data->rvo = (data->acpi_data->states[index].control >> RVO_SHIFT) & RVO_MASK;
+        data->exttype = (data->acpi_data->states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK;
+        data->plllock = (data->acpi_data->states[index].control >> PLL_L_SHIFT) & PLL_L_MASK;
+        data->vidmvs = 1 << ((data->acpi_data->states[index].control >> MVS_SHIFT) & MVS_MASK);
+        data->vstable = (data->acpi_data->states[index].control >> VST_SHIFT) & VST_MASK;
+}
+
+
+static struct acpi_processor_performance *acpi_perf_data;
+static int preregister_valid;
+
+static int powernow_k8_cpu_preinit_acpi(void)
+{
+        acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
+        if (!acpi_perf_data)
+                return -ENODEV;
+
+        if (acpi_processor_preregister_performance(acpi_perf_data))
+                return -ENODEV;
+        else
+                preregister_valid = 1;
+        return 0;
 }
 
 static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 {
         struct cpufreq_frequency_table *powernow_table;
         int ret_val;
+        int cpu = 0;
 
-        if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) {
+        data->acpi_data = percpu_ptr(acpi_perf_data, cpu);
+        if (acpi_processor_register_performance(data->acpi_data, data->cpu)) {
                 dprintk("register performance failed: bad ACPI data\n");
                 return -EIO;
         }
 
         /* verify the data contained in the ACPI structures */
-        if (data->acpi_data.state_count <= 1) {
+        if (data->acpi_data->state_count <= 1) {
                 dprintk("No ACPI P-States\n");
                 goto err_out;
         }
 
-        if ((data->acpi_data.control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
-                (data->acpi_data.status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
+        if ((data->acpi_data->control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) ||
+                (data->acpi_data->status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) {
                 dprintk("Invalid control/status registers (%x - %x)\n",
-                        data->acpi_data.control_register.space_id,
-                        data->acpi_data.status_register.space_id);
+                        data->acpi_data->control_register.space_id,
+                        data->acpi_data->status_register.space_id);
                 goto err_out;
         }
 
         /* fill in data->powernow_table */
         powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table)
-                * (data->acpi_data.state_count + 1)), GFP_KERNEL);
+                * (data->acpi_data->state_count + 1)), GFP_KERNEL);
         if (!powernow_table) {
                 dprintk("powernow_table memory alloc failure\n");
                 goto err_out;
@@ -790,12 +806,12 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
         if (ret_val)
                 goto err_out_mem;
 
-        powernow_table[data->acpi_data.state_count].frequency = CPUFREQ_TABLE_END;
-        powernow_table[data->acpi_data.state_count].index = 0;
+        powernow_table[data->acpi_data->state_count].frequency = CPUFREQ_TABLE_END;
+        powernow_table[data->acpi_data->state_count].index = 0;
         data->powernow_table = powernow_table;
 
         /* fill in data */
-        data->numps = data->acpi_data.state_count;
+        data->numps = data->acpi_data->state_count;
         if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
                 print_basics(data);
         powernow_k8_acpi_pst_values(data, 0);
@@ -803,16 +819,31 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
         /* notify BIOS that we exist */
         acpi_processor_notify_smm(THIS_MODULE);
 
+        /* determine affinity, from ACPI if available */
+        if (preregister_valid) {
+                if ((data->acpi_data->shared_type == CPUFREQ_SHARED_TYPE_ALL) ||
+                        (data->acpi_data->shared_type == CPUFREQ_SHARED_TYPE_ANY))
+                        data->starting_core_affinity = data->acpi_data->shared_cpu_map;
+                else
+                        data->starting_core_affinity = cpumask_of_cpu(data->cpu);
+        } else {
+        /* best guess from family if not */
+                if (cpu_family == CPU_HW_PSTATE)
+                        data->starting_core_affinity = cpumask_of_cpu(data->cpu);
+                else
+                        data->starting_core_affinity = per_cpu(cpu_core_map, data->cpu);
+        }
+
         return 0;
 
 err_out_mem:
         kfree(powernow_table);
 
 err_out:
-        acpi_processor_unregister_performance(&data->acpi_data, data->cpu);
+        acpi_processor_unregister_performance(data->acpi_data, data->cpu);
 
         /* data->acpi_data.state_count informs us at ->exit() whether ACPI was used */
-        data->acpi_data.state_count = 0;
+        data->acpi_data->state_count = 0;
 
         return -ENODEV;
 }
@@ -824,10 +855,10 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf
         rdmsr(MSR_PSTATE_CUR_LIMIT, hi, lo);
         data->max_hw_pstate = (hi & HW_PSTATE_MAX_MASK) >> HW_PSTATE_MAX_SHIFT;
 
-        for (i = 0; i < data->acpi_data.state_count; i++) {
+        for (i = 0; i < data->acpi_data->state_count; i++) {
                 u32 index;
 
-                index = data->acpi_data.states[i].control & HW_PSTATE_MASK;
+                index = data->acpi_data->states[i].control & HW_PSTATE_MASK;
                 if (index > data->max_hw_pstate) {
                         printk(KERN_ERR PFX "invalid pstate %d - bad value %d.\n", i, index);
                         printk(KERN_ERR PFX "Please report to BIOS manufacturer\n");
@@ -843,7 +874,7 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf
 
                 powernow_table[i].index = index;
 
-                powernow_table[i].frequency = data->acpi_data.states[i].core_frequency * 1000;
+                powernow_table[i].frequency = data->acpi_data->states[i].core_frequency * 1000;
         }
         return 0;
 }
@@ -852,16 +883,16 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf
 {
         int i;
         int cntlofreq = 0;
-        for (i = 0; i < data->acpi_data.state_count; i++) {
+        for (i = 0; i < data->acpi_data->state_count; i++) {
                 u32 fid;
                 u32 vid;
 
                 if (data->exttype) {
-                        fid = data->acpi_data.states[i].status & EXT_FID_MASK;
-                        vid = (data->acpi_data.states[i].status >> VID_SHIFT) & EXT_VID_MASK;
+                        fid = data->acpi_data->states[i].status & EXT_FID_MASK;
+                        vid = (data->acpi_data->states[i].status >> VID_SHIFT) & EXT_VID_MASK;
                 } else {
-                        fid = data->acpi_data.states[i].control & FID_MASK;
-                        vid = (data->acpi_data.states[i].control >> VID_SHIFT) & VID_MASK;
+                        fid = data->acpi_data->states[i].control & FID_MASK;
+                        vid = (data->acpi_data->states[i].control >> VID_SHIFT) & VID_MASK;
                 }
 
                 dprintk("   %d : fid 0x%x, vid 0x%x\n", i, fid, vid);
@@ -902,10 +933,10 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf
                                 cntlofreq = i;
                 }
 
-                if (powernow_table[i].frequency != (data->acpi_data.states[i].core_frequency * 1000)) {
+                if (powernow_table[i].frequency != (data->acpi_data->states[i].core_frequency * 1000)) {
                         printk(KERN_INFO PFX "invalid freq entries %u kHz vs. %u kHz\n",
                                 powernow_table[i].frequency,
-                                (unsigned int) (data->acpi_data.states[i].core_frequency * 1000));
+                                (unsigned int) (data->acpi_data->states[i].core_frequency * 1000));
                         powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID;
                         continue;
                 }
@@ -915,11 +946,12 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf
 
 static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
 {
-        if (data->acpi_data.state_count)
-                acpi_processor_unregister_performance(&data->acpi_data, data->cpu);
+        if (data->acpi_data->state_count)
+                acpi_processor_unregister_performance(data->acpi_data, data->cpu);
 }
 
 #else
+static int powernow_k8_cpu_preinit_acpi(void) { return -ENODEV; }
 static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; }
 static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; }
 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; }
@@ -1104,7 +1136,7 @@ static int powernowk8_verify(struct cpufreq_policy *pol)
 static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
         struct powernow_k8_data *data;
-        cpumask_t oldmask;
+        cpumask_t oldmask = CPU_MASK_ALL;
         int rc;
 
         if (!cpu_online(pol->cpu))
@@ -1177,10 +1209,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
         /* run on any CPU again */
         set_cpus_allowed_ptr(current, &oldmask);
 
-        if (cpu_family == CPU_HW_PSTATE)
-                pol->cpus = cpumask_of_cpu(pol->cpu);
-        else
-                pol->cpus = per_cpu(cpu_core_map, pol->cpu);
+        pol->cpus = data->starting_core_affinity;
         data->available_cores = &(pol->cpus);
 
         /* Take a crude guess here.
@@ -1303,6 +1332,7 @@ static int __cpuinit powernowk8_init(void)
         }
 
         if (supported_cpus == num_online_cpus()) {
+                powernow_k8_cpu_preinit_acpi();
                 printk(KERN_INFO PFX "Found %d %s "
                         "processors (%d cpu cores) (" VERSION ")\n",
                         num_online_nodes(),
@@ -1319,6 +1349,10 @@ static void __exit powernowk8_exit(void)
         dprintk("exit\n");
 
         cpufreq_unregister_driver(&cpufreq_amd64_driver);
+
+#ifdef CONFIG_X86_POWERNOW_K8_ACPI
+        free_percpu(acpi_perf_data);
+#endif
 }
 
 MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and Mark Langsdorf <mark.langsdorf@amd.com>");
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index ab48cfed4d96..a62612cd4be8 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -33,12 +33,13 @@ struct powernow_k8_data {
 #ifdef CONFIG_X86_POWERNOW_K8_ACPI
         /* the acpi table needs to be kept. it's only available if ACPI was
          * used to determine valid frequency/vid/fid states */
-        struct acpi_processor_performance acpi_data;
+        struct acpi_processor_performance *acpi_data;
 #endif
         /* we need to keep track of associated cores, but let cpufreq
          * handle hotplug events - so just point at cpufreq pol->cpus
          * structure */
         cpumask_t *available_cores;
+        cpumask_t starting_core_affinity;
 };
 
 
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 72ba06314c7b..26ea3ea3fb30 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -58,7 +58,7 @@ atomic_t irq_mis_count;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
-static DEFINE_SPINLOCK(vector_lock);
+DEFINE_SPINLOCK(vector_lock);
 
 int timer_through_8259 __initdata;
 
@@ -1210,10 +1210,6 @@ static int assign_irq_vector(int irq)
         return vector;
 }
 
-void setup_vector_irq(int cpu)
-{
-}
-
 static struct irq_chip ioapic_chip;
 
 #define IOAPIC_AUTO     -1
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index b9950dae59b7..e63282e78864 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -103,7 +103,7 @@ int timer_through_8259 __initdata;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
-DEFINE_SPINLOCK(vector_lock);
+static DEFINE_SPINLOCK(vector_lock);
 
 /*
  * # of IRQ routing registers
@@ -770,6 +770,19 @@ static int pin_2_irq(int idx, int apic, int pin)
         return irq;
 }
 
+void lock_vector_lock(void)
+{
+        /* Used to the online set of cpus does not change
+         * during assign_irq_vector.
+         */
+        spin_lock(&vector_lock);
+}
+
+void unlock_vector_lock(void)
+{
+        spin_unlock(&vector_lock);
+}
+
 static int __assign_irq_vector(int irq, cpumask_t mask)
 {
         /*
@@ -875,7 +888,7 @@ static void __clear_irq_vector(int irq)
         cpus_clear(cfg->domain);
 }
 
-static void __setup_vector_irq(int cpu)
+void __setup_vector_irq(int cpu)
 {
         /* Initialize vector_irq on a new cpu */
         /* This function must be called with vector_lock held */
@@ -898,14 +911,6 @@ static void __setup_vector_irq(int cpu)
         }
 }
 
-void setup_vector_irq(int cpu)
-{
-        spin_lock(&vector_lock);
-        __setup_vector_irq(smp_processor_id());
-        spin_unlock(&vector_lock);
-}
-
-
 static struct irq_chip ioapic_chip;
 #ifdef CONFIG_INTR_REMAP
 static struct irq_chip ir_ioapic_chip;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index e362c6ab4d35..e5d23675bb7c 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -83,7 +83,7 @@ static void __init MP_bus_info(struct mpc_config_bus *m)
         if (x86_quirks->mpc_oem_bus_info)
                 x86_quirks->mpc_oem_bus_info(m, str);
         else
-                printk(KERN_INFO "Bus #%d is %s\n", m->mpc_busid, str);
+                apic_printk(APIC_VERBOSE, "Bus #%d is %s\n", m->mpc_busid, str);
 
 #if MAX_MP_BUSSES < 256
         if (m->mpc_busid >= MAX_MP_BUSSES) {
@@ -154,7 +154,7 @@ static void __init MP_ioapic_info(struct mpc_config_ioapic *m)
 
 static void print_MP_intsrc_info(struct mpc_config_intsrc *m)
 {
-        printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x,"
+        apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
                 " IRQ %02x, APIC ID %x, APIC INT %02x\n",
                 m->mpc_irqtype, m->mpc_irqflag & 3,
                 (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus,
@@ -163,7 +163,7 @@ static void print_MP_intsrc_info(struct mpc_config_intsrc *m)
 
 static void __init print_mp_irq_info(struct mp_config_intsrc *mp_irq)
 {
-        printk(KERN_CONT "Int: type %d, pol %d, trig %d, bus %02x,"
+        apic_printk(APIC_VERBOSE, "Int: type %d, pol %d, trig %d, bus %02x,"
                 " IRQ %02x, APIC ID %x, APIC INT %02x\n",
                 mp_irq->mp_irqtype, mp_irq->mp_irqflag & 3,
                 (mp_irq->mp_irqflag >> 2) & 3, mp_irq->mp_srcbus,
@@ -235,7 +235,7 @@ static void __init MP_intsrc_info(struct mpc_config_intsrc *m)
 
 static void __init MP_lintsrc_info(struct mpc_config_lintsrc *m)
 {
-        printk(KERN_INFO "Lint: type %d, pol %d, trig %d, bus %02x,"
+        apic_printk(APIC_VERBOSE, "Lint: type %d, pol %d, trig %d, bus %02x,"
                 " IRQ %02x, APIC ID %x, APIC LINT %02x\n",
                 m->mpc_irqtype, m->mpc_irqflag & 3,
                 (m->mpc_irqflag >> 2) & 3, m->mpc_srcbusid,
@@ -697,7 +697,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length,
         unsigned int *bp = phys_to_virt(base);
         struct intel_mp_floating *mpf;
 
-        printk(KERN_DEBUG "Scan SMP from %p for %ld bytes.\n", bp, length);
+        apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
+                        bp, length);
         BUILD_BUG_ON(sizeof(*mpf) != 16);
 
         while (length > 0) {
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index b67a4b1d4eae..02d19328525d 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1350,7 +1350,7 @@ static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl)
  * Function for kdump case. Get the tce tables from first kernel
  * by reading the contents of the base adress register of calgary iommu
  */
-static void get_tce_space_from_tar()
+static void get_tce_space_from_tar(void)
 {
         int bus;
         void __iomem *target;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 8dbffb846de9..87d4d6964ec2 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -123,6 +123,14 @@ void __init pci_iommu_alloc(void)
 
         pci_swiotlb_init();
 }
+
+unsigned long iommu_num_pages(unsigned long addr, unsigned long len)
+{
+        unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE);
+
+        return size >> PAGE_SHIFT;
+}
+EXPORT_SYMBOL(iommu_num_pages);
 #endif
 
 /*
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 792b87853a76..59f07e14d083 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -604,6 +604,14 @@ void __init setup_arch(char **cmdline_p)
         early_cpu_init();
         early_ioremap_init();
 
+#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
+        /*
+         * Must be before kernel pagetables are setup
+         * or fixmap area is touched.
+         */
+        vmi_init();
+#endif
+
         ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
         screen_info = boot_params.screen_info;
         edid_info = boot_params.edid_info;
@@ -790,10 +798,6 @@ void __init setup_arch(char **cmdline_p)
 
         initmem_init(0, max_pfn);
 
-#ifdef CONFIG_X86_64
-        dma32_reserve_bootmem();
-#endif
-
 #ifdef CONFIG_ACPI_SLEEP
         /*
          * Reserve low memory region for sleep support.
@@ -808,20 +812,21 @@ void __init setup_arch(char **cmdline_p)
 #endif
         reserve_crashkernel();
 
+#ifdef CONFIG_X86_64
+        /*
+         * dma32_reserve_bootmem() allocates bootmem which may conflict
+         * with the crashkernel command line, so do that after
+         * reserve_crashkernel()
+         */
+        dma32_reserve_bootmem();
+#endif
+
         reserve_ibft_region();
 
 #ifdef CONFIG_KVM_CLOCK
         kvmclock_init();
 #endif
 
-#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
-        /*
-         * Must be after max_low_pfn is determined, and before kernel
-         * pagetables are setup.
-         */
-        vmi_init();
-#endif
-
         paravirt_pagetable_setup_start(swapper_pg_dir);
         paging_init();
         paravirt_pagetable_setup_done(swapper_pg_dir);
@@ -858,12 +863,6 @@ void __init setup_arch(char **cmdline_p)
         init_apic_mappings();
         ioapic_init_mappings();
 
-#if defined(CONFIG_SMP) && defined(CONFIG_X86_PC) && defined(CONFIG_X86_32)
-        if (def_to_bigsmp)
-                printk(KERN_WARNING "More than 8 CPUs detected and "
-                        "CONFIG_X86_PC cannot handle it.\nUse "
-                        "CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
-#endif
         kvm_guest_init();
 
         e820_reserve_resources();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 626618bf2f81..04f78ab51b45 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -327,12 +327,16 @@ static void __cpuinit start_secondary(void *unused)
          * for which cpus receive the IPI. Holding this
          * lock helps us to not include this cpu in a currently in progress
          * smp_call_function().
+         *
+         * We need to hold vector_lock so there the set of online cpus
+         * does not change while we are assigning vectors to cpus.  Holding
+         * this lock ensures we don't half assign or remove an irq from a cpu.
          */
         ipi_call_lock_irq();
-#ifdef CONFIG_X86_IO_APIC
-        setup_vector_irq(smp_processor_id());
-#endif
+        lock_vector_lock();
+        __setup_vector_irq(smp_processor_id());
         cpu_set(smp_processor_id(), cpu_online_map);
+        unlock_vector_lock();
         ipi_call_unlock_irq();
         per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 
@@ -983,7 +987,17 @@ int __cpuinit native_cpu_up(unsigned int cpu)
         flush_tlb_all();
         low_mappings = 1;
 
+#ifdef CONFIG_X86_PC
+        if (def_to_bigsmp && apicid > 8) {
+                printk(KERN_WARNING
+                        "More than 8 CPUs detected - skipping them.\n"
+                        "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n");
+                err = -1;
+        } else
+                err = do_boot_cpu(apicid, cpu);
+#else
         err = do_boot_cpu(apicid, cpu);
+#endif
 
         zap_low_mappings();
         low_mappings = 0;
@@ -1336,7 +1350,9 @@ int __cpu_disable(void)
         remove_siblinginfo(cpu);
 
         /* It's now safe to remove this processor from the online map */
+        lock_vector_lock();
         remove_cpu_from_maps(cpu);
+        unlock_vector_lock();
         fixup_irqs(cpu_online_map);
         return 0;
 }
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 45c27c4e2a6e..61531d5c9507 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -37,6 +37,7 @@
 #include <asm/timer.h>
 #include <asm/vmi_time.h>
 #include <asm/kmap_types.h>
+#include <asm/setup.h>
 
 /* Convenient for calling VMI functions indirectly in the ROM */
 typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void);
@@ -683,7 +684,7 @@ void vmi_bringup(void)
 {
         /* We must establish the lowmem mapping for MMU ops to work */
         if (vmi_ops.set_linear_mapping)
-                vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, max_low_pfn, 0);
+                vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, MAXMEM_PFN, 0);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2fa231923cf7..0bfe2bd305eb 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -653,6 +653,84 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
         account_shadowed(kvm, gfn);
 }
 
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp)
+{
+        u64 *spte;
+        int need_tlb_flush = 0;
+
+        while ((spte = rmap_next(kvm, rmapp, NULL))) {
+                BUG_ON(!(*spte & PT_PRESENT_MASK));
+                rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte);
+                rmap_remove(kvm, spte);
+                set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+                need_tlb_flush = 1;
+        }
+        return need_tlb_flush;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+                          int (*handler)(struct kvm *kvm, unsigned long *rmapp))
+{
+        int i;
+        int retval = 0;
+
+        /*
+         * If mmap_sem isn't taken, we can look the memslots with only
+         * the mmu_lock by skipping over the slots with userspace_addr == 0.
+         */
+        for (i = 0; i < kvm->nmemslots; i++) {
+                struct kvm_memory_slot *memslot = &kvm->memslots[i];
+                unsigned long start = memslot->userspace_addr;
+                unsigned long end;
+
+                /* mmu_lock protects userspace_addr */
+                if (!start)
+                        continue;
+
+                end = start + (memslot->npages << PAGE_SHIFT);
+                if (hva >= start && hva < end) {
+                        gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+                        retval |= handler(kvm, &memslot->rmap[gfn_offset]);
+                        retval |= handler(kvm,
+                                          &memslot->lpage_info[
+                                                  gfn_offset /
+                                                  KVM_PAGES_PER_HPAGE].rmap_pde);
+                }
+        }
+
+        return retval;
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+        return kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
+{
+        u64 *spte;
+        int young = 0;
+
+        spte = rmap_next(kvm, rmapp, NULL);
+        while (spte) {
+                int _young;
+                u64 _spte = *spte;
+                BUG_ON(!(_spte & PT_PRESENT_MASK));
+                _young = _spte & PT_ACCESSED_MASK;
+                if (_young) {
+                        young = 1;
+                        clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
+                }
+                spte = rmap_next(kvm, rmapp, spte);
+        }
+        return young;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+        return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
+}
+
 #ifdef MMU_DEBUG
 static int is_empty_shadow_page(u64 *spt)
 {
@@ -1203,6 +1281,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
         int r;
         int largepage = 0;
         pfn_t pfn;
+        unsigned long mmu_seq;
 
         down_read(&current->mm->mmap_sem);
         if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
@@ -1210,6 +1289,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
                 largepage = 1;
         }
 
+        mmu_seq = vcpu->kvm->mmu_notifier_seq;
+        /* implicit mb(), we'll read before PT lock is unlocked */
         pfn = gfn_to_pfn(vcpu->kvm, gfn);
         up_read(&current->mm->mmap_sem);
 
@@ -1220,6 +1301,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
         }
 
         spin_lock(&vcpu->kvm->mmu_lock);
+        if (mmu_notifier_retry(vcpu, mmu_seq))
+                goto out_unlock;
         kvm_mmu_free_some_pages(vcpu);
         r = __direct_map(vcpu, v, write, largepage, gfn, pfn,
                          PT32E_ROOT_LEVEL);
@@ -1227,6 +1310,11 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
 
 
         return r;
+
+out_unlock:
+        spin_unlock(&vcpu->kvm->mmu_lock);
+        kvm_release_pfn_clean(pfn);
+        return 0;
 }
 
 
@@ -1345,6 +1433,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
         int r;
         int largepage = 0;
         gfn_t gfn = gpa >> PAGE_SHIFT;
+        unsigned long mmu_seq;
 
         ASSERT(vcpu);
         ASSERT(VALID_PAGE(vcpu->arch.mmu.root_hpa));
@@ -1358,6 +1447,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
                 gfn &= ~(KVM_PAGES_PER_HPAGE-1);
                 largepage = 1;
         }
+        mmu_seq = vcpu->kvm->mmu_notifier_seq;
+        /* implicit mb(), we'll read before PT lock is unlocked */
         pfn = gfn_to_pfn(vcpu->kvm, gfn);
         up_read(&current->mm->mmap_sem);
         if (is_error_pfn(pfn)) {
@@ -1365,12 +1456,19 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
                 return 1;
         }
         spin_lock(&vcpu->kvm->mmu_lock);
+        if (mmu_notifier_retry(vcpu, mmu_seq))
+                goto out_unlock;
         kvm_mmu_free_some_pages(vcpu);
         r = __direct_map(vcpu, gpa, error_code & PFERR_WRITE_MASK,
                          largepage, gfn, pfn, kvm_x86_ops->get_tdp_level());
         spin_unlock(&vcpu->kvm->mmu_lock);
 
         return r;
+
+out_unlock:
+        spin_unlock(&vcpu->kvm->mmu_lock);
+        kvm_release_pfn_clean(pfn);
+        return 0;
 }
 
 static void nonpaging_free(struct kvm_vcpu *vcpu)
@@ -1670,6 +1768,8 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
                 gfn &= ~(KVM_PAGES_PER_HPAGE-1);
                 vcpu->arch.update_pte.largepage = 1;
         }
+        vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq;
+        /* implicit mb(), we'll read before PT lock is unlocked */
         pfn = gfn_to_pfn(vcpu->kvm, gfn);
         up_read(&current->mm->mmap_sem);
 
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 4d918220baeb..f72ac1fa35f0 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -263,6 +263,8 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
         pfn = vcpu->arch.update_pte.pfn;
         if (is_error_pfn(pfn))
                 return;
+        if (mmu_notifier_retry(vcpu, vcpu->arch.update_pte.mmu_seq))
+                return;
         kvm_get_pfn(pfn);
         mmu_set_spte(vcpu, spte, page->role.access, pte_access, 0, 0,
                      gpte & PT_DIRTY_MASK, NULL, largepage, gpte_to_gfn(gpte),
@@ -380,6 +382,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
         int r;
         pfn_t pfn;
         int largepage = 0;
+        unsigned long mmu_seq;
 
         pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
         kvm_mmu_audit(vcpu, "pre page fault");
@@ -413,6 +416,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
                         largepage = 1;
                 }
         }
+        mmu_seq = vcpu->kvm->mmu_notifier_seq;
+        /* implicit mb(), we'll read before PT lock is unlocked */
         pfn = gfn_to_pfn(vcpu->kvm, walker.gfn);
         up_read(&current->mm->mmap_sem);
 
@@ -424,6 +429,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
         }
 
         spin_lock(&vcpu->kvm->mmu_lock);
+        if (mmu_notifier_retry(vcpu, mmu_seq))
+                goto out_unlock;
         kvm_mmu_free_some_pages(vcpu);
         shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
                                   largepage, &write_pt, pfn);
@@ -439,6 +446,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
         spin_unlock(&vcpu->kvm->mmu_lock);
 
         return write_pt;
+
+out_unlock:
+        spin_unlock(&vcpu->kvm->mmu_lock);
+        kvm_release_pfn_clean(pfn);
+        return 0;
 }
 
 static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5916191420c7..0d682fc6aeb3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -883,6 +883,7 @@ int kvm_dev_ioctl_check_extension(long ext)
         case KVM_CAP_PIT:
         case KVM_CAP_NOP_IO_DELAY:
         case KVM_CAP_MP_STATE:
+        case KVM_CAP_SYNC_MMU:
                 r = 1;
                 break;
         case KVM_CAP_COALESCED_MMIO:
@@ -1495,6 +1496,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
                 goto out;
 
         down_write(&kvm->slots_lock);
+        spin_lock(&kvm->mmu_lock);
 
         p = &kvm->arch.aliases[alias->slot];
         p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
@@ -1506,6 +1508,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
                         break;
         kvm->arch.naliases = n;
 
+        spin_unlock(&kvm->mmu_lock);
         kvm_mmu_zap_all(kvm);
 
         up_write(&kvm->slots_lock);
@@ -3972,16 +3975,23 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
          */
         if (!user_alloc) {
                 if (npages && !old.rmap) {
+                        unsigned long userspace_addr;
+
                         down_write(&current->mm->mmap_sem);
-                        memslot->userspace_addr = do_mmap(NULL, 0,
-                                                     npages * PAGE_SIZE,
-                                                     PROT_READ | PROT_WRITE,
-                                                     MAP_SHARED | MAP_ANONYMOUS,
-                                                     0);
+                        userspace_addr = do_mmap(NULL, 0,
+                                                 npages * PAGE_SIZE,
+                                                 PROT_READ | PROT_WRITE,
+                                                 MAP_SHARED | MAP_ANONYMOUS,
+                                                 0);
                         up_write(&current->mm->mmap_sem);
 
-                        if (IS_ERR((void *)memslot->userspace_addr))
-                                return PTR_ERR((void *)memslot->userspace_addr);
+                        if (IS_ERR((void *)userspace_addr))
+                                return PTR_ERR((void *)userspace_addr);
+
+                        /* set userspace_addr atomically for kvm_hva_to_rmapp */
+                        spin_lock(&kvm->mmu_lock);
+                        memslot->userspace_addr = userspace_addr;
+                        spin_unlock(&kvm->mmu_lock);
                 } else {
                         if (!old.user_alloc && old.rmap) {
                                 int ret;
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index dfdf428975c0..f118c110af32 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -52,7 +52,7 @@
         jnz 100b
 102:
         .section .fixup,"ax"
-103:    addl %r8d,%edx                  /* ecx is zerorest also */
+103:    addl %ecx,%edx                  /* ecx is zerorest also */
         jmp copy_user_handle_tail
         .previous
 
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index 40e0e309d27e..cb0c112386fb 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -32,7 +32,7 @@
         jnz 100b
 102:
         .section .fixup,"ax"
-103:    addl %r8d,%edx                  /* ecx is zerorest also */
+103:    addl %ecx,%edx                  /* ecx is zerorest also */
         jmp copy_user_handle_tail
         .previous
 
@@ -108,7 +108,6 @@ ENTRY(__copy_user_nocache)
         jmp 60f
 50:     movl %ecx,%edx
 60:     sfence
-        movl %r8d,%ecx
         jmp copy_user_handle_tail
         .previous
 
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 2977ea37791f..dfb932dcf136 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,6 @@
 obj-y   :=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-            pat.o pgtable.o
+            pat.o pgtable.o gup.o
 
-obj-$(CONFIG_HAVE_GET_USER_PAGES_FAST) += gup.o
 obj-$(CONFIG_X86_32)            += pgtable_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)      += hugetlbpage.o
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 557b2abceef8..d50302774fe2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -207,6 +207,9 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
         unsigned long addr;
         int i;
 
+        if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
+                return;
+
         pud = pud_offset(pgd, 0);
 
         for (addr = i = 0; i < PREALLOCATED_PMDS;