38 files changed, 339 insertions, 201 deletions
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d37593c2f438..7678f10c4568 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -973,6 +973,29 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
        nr_ioapics++;
 }
+int __init acpi_probe_gsi(void)
+{
+        int idx;
+        int gsi;
+        int max_gsi = 0;
+        if (acpi_disabled)
+                return 0;
+        if (!acpi_ioapic)
+                return 0;
+        max_gsi = 0;
+        for (idx = 0; idx < nr_ioapics; idx++) {
+                gsi = mp_ioapic_routing[idx].gsi_end;
+                if (gsi > max_gsi)
+                        max_gsi = gsi;
+        }
+        return max_gsi + 1;
+}
 static void assign_to_mp_irq(struct mp_config_intsrc *m,
                                    struct mp_config_intsrc *mp_irq)
 {
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 707c1f6f95fa..a60c1f3bcb87 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -156,11 +156,11 @@ static int __init acpi_sleep_setup(char *str)
 #ifdef CONFIG_HIBERNATION
                if (strncmp(str, "s4_nohwsig", 10) == 0)
                        acpi_no_s4_hw_signature();
+                if (strncmp(str, "s4_nonvs", 8) == 0)
+                        acpi_s4_no_nvs();
 #endif
                if (strncmp(str, "old_ordering", 12) == 0)
                        acpi_old_suspend_ordering();
-                if (strncmp(str, "s4_nonvs", 8) == 0)
-                        acpi_s4_no_nvs();
                str = strchr(str, ',');
                if (str != NULL)
                        str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index bcc293423a70..96258d9dc974 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -13,7 +13,6 @@
         * Hooray, we are in Long 64-bit mode (but still running in low memory)
         */
 ENTRY(wakeup_long64)
-wakeup_long64:
        movq    saved_magic, %rax
        movq    $0x123456789abcdef0, %rdx
        cmpq    %rdx, %rax
@@ -34,16 +33,12 @@ wakeup_long64:
        movq    saved_rip, %rax
        jmp     *%rax
+ENDPROC(wakeup_long64)
 bogus_64_magic:
        jmp     bogus_64_magic
-        .align 2
+ENTRY(do_suspend_lowlevel)
-        .p2align 4,,15
-.globl do_suspend_lowlevel
-        .type   do_suspend_lowlevel,@function
-do_suspend_lowlevel:
-.LFB5:
        subq    $8, %rsp
        xorl    %eax, %eax
        call    save_processor_state
@@ -67,7 +62,7 @@ do_suspend_lowlevel:
        pushfq
        popq    pt_regs_flags(%rax)
-        movq    $.L97, saved_rip(%rip)
+        movq    $resume_point, saved_rip(%rip)
        movq    %rsp, saved_rsp
        movq    %rbp, saved_rbp
@@ -78,14 +73,12 @@ do_suspend_lowlevel:
        addq    $8, %rsp
        movl    $3, %edi
        xorl    %eax, %eax
-        jmp     acpi_enter_sleep_state
+        call    acpi_enter_sleep_state
-.L97:
+        /* in case something went wrong, restore the machine status and go on */
-        .p2align 4,,7
+        jmp     resume_point
-.L99:
-        .align 4
-        movl    $24, %eax
-        movw    %ax, %ds
+        .align 4
+resume_point:
        /* We don't restore %rax, it must be 0 anyway */
        movq    $saved_context, %rax
        movq    saved_context_cr4(%rax), %rbx
@@ -117,12 +110,9 @@ do_suspend_lowlevel:
        xorl    %eax, %eax
        addq    $8, %rsp
        jmp     restore_processor_state
-.LFE5:
+ENDPROC(do_suspend_lowlevel)
-.Lfe5:
-        .size   do_suspend_lowlevel, .Lfe5-do_suspend_lowlevel
-        
 .data
-ALIGN
 ENTRY(saved_rbp)        .quad   0
 ENTRY(saved_rsi)        .quad   0
 ENTRY(saved_rdi)        .quad   0
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 4b6df2469fe3..570f36e44e59 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -862,7 +862,7 @@ void clear_local_APIC(void)
        }
        /* lets not touch this if we didn't frob it */
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL)
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
        if (maxlvt >= 5) {
                v = apic_read(APIC_LVTTHMR);
                apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
@@ -1436,7 +1436,7 @@ static int __init detect_init_APIC(void)
        switch (boot_cpu_data.x86_vendor) {
        case X86_VENDOR_AMD:
                if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model > 1) ||
-                    (boot_cpu_data.x86 == 15))
+                    (boot_cpu_data.x86 >= 15))
                        break;
                goto no_apic;
        case X86_VENDOR_INTEL:
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 98807bb095ad..266ec6c18b6c 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1192,6 +1192,7 @@ static int suspend(int vetoable)
        device_suspend(PMSG_SUSPEND);
        local_irq_disable();
        device_power_down(PMSG_SUSPEND);
+        sysdev_suspend(PMSG_SUSPEND);
        local_irq_enable();
@@ -1208,6 +1209,7 @@ static int suspend(int vetoable)
        if (err != APM_SUCCESS)
                apm_error("suspend", err);
        err = (err == APM_SUCCESS) ? 0 : -EIO;
+        sysdev_resume();
        device_power_up(PMSG_RESUME);
        local_irq_enable();
        device_resume(PMSG_RESUME);
@@ -1228,6 +1230,7 @@ static void standby(void)
        local_irq_disable();
        device_power_down(PMSG_SUSPEND);
+        sysdev_suspend(PMSG_SUSPEND);
        local_irq_enable();
        err = set_system_power_state(APM_STATE_STANDBY);
@@ -1235,6 +1238,7 @@ static void standby(void)
                apm_error("standby", err);
        local_irq_disable();
+        sysdev_resume();
        device_power_up(PMSG_RESUME);
        local_irq_enable();
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index efae3b22a0ff..65792c2cc462 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -245,17 +245,6 @@ config X86_E_POWERSAVER
 comment "shared options"
-config X86_ACPI_CPUFREQ_PROC_INTF
-        bool "/proc/acpi/processor/../performance interface (deprecated)"
-        depends on PROC_FS
-        depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI
-        help
-          This enables the deprecated /proc/acpi/processor/../performance
-          interface. While it is helpful for debugging, the generic,
-          cross-architecture cpufreq interfaces should be used.
-          If in doubt, say N.
 config X86_SPEEDSTEP_LIB
        tristate
        default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index b585e04cbc9e..3178c3acd97e 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -277,7 +277,6 @@ static struct cpufreq_driver p4clockmod_driver = {
        .name           = "p4-clockmod",
        .owner          = THIS_MODULE,
        .attr           = p4clockmod_attr,
-        .hide_interface = 1,
 };
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 5c28b37dea11..6428aa17b40e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -939,10 +939,25 @@ static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
        free_cpumask_var(data->acpi_data.shared_cpu_map);
 }
+static int get_transition_latency(struct powernow_k8_data *data)
+{
+        int max_latency = 0;
+        int i;
+        for (i = 0; i < data->acpi_data.state_count; i++) {
+                int cur_latency = data->acpi_data.states[i].transition_latency
+                        + data->acpi_data.states[i].bus_master_latency;
+                if (cur_latency > max_latency)
+                        max_latency = cur_latency;
+        }
+        /* value in usecs, needs to be in nanoseconds */
+        return 1000 * max_latency;
+}
 #else
 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; }
+static int get_transition_latency(struct powernow_k8_data *data) { return 0; }
 #endif /* CONFIG_X86_POWERNOW_K8_ACPI */
 /* Take a frequency, and issue the fid/vid transition command */
@@ -1142,8 +1157,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
        data->cpu = pol->cpu;
        data->currpstate = HW_PSTATE_INVALID;
-        rc = powernow_k8_cpu_init_acpi(data);
+        if (powernow_k8_cpu_init_acpi(data)) {
-        if (rc) {
                /*
                 * Use the PSB BIOS structure. This is only availabe on
                 * an UP version, and is deprecated by AMD.
@@ -1161,19 +1175,28 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
                               "ACPI maintainers and complain to your BIOS "
                               "vendor.\n");
 #endif
-                        goto err_out;
+                        kfree(data);
+                        return -ENODEV;
                }
                if (pol->cpu != 0) {
                        printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for "
                               "CPU other than CPU0. Complain to your BIOS "
                               "vendor.\n");
-                        goto err_out;
+                        kfree(data);
+                        return -ENODEV;
                }
                rc = find_psb_table(data);
                if (rc) {
-                        goto err_out;
+                        kfree(data);
+                        return -ENODEV;
                }
-        }
+                /* Take a crude guess here.
+                 * That guess was in microseconds, so multiply with 1000 */
+                pol->cpuinfo.transition_latency = (
+                         ((data->rvo + 8) * data->vstable * VST_UNITS_20US) +
+                         ((1 << data->irt) * 30)) * 1000;
+        } else /* ACPI _PSS objects available */
+                pol->cpuinfo.transition_latency = get_transition_latency(data);
        /* only run on specific CPU from here on */
        oldmask = current->cpus_allowed;
@@ -1204,11 +1227,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
                cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
        data->available_cores = pol->cpus;
-        /* Take a crude guess here.
-         * That guess was in microseconds, so multiply with 1000 */
-        pol->cpuinfo.transition_latency = (((data->rvo + 8) * data->vstable * VST_UNITS_20US)
-            + (3 * (1 << data->irt) * 10)) * 1000;
        if (cpu_family == CPU_HW_PSTATE)
                pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate);
        else
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 549f2ada55f5..24ff26a38ade 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -30,7 +30,7 @@
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
        /* Unmask CPUID levels if masked: */
-        if (c->x86 == 6 && c->x86_model >= 15) {
+        if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
                u64 misc_enable;
                rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
@@ -291,6 +291,9 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
                ds_init_intel(c);
        }
+        if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+                set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
 #ifdef CONFIG_X86_64
        if (c->x86 == 15)
                c->x86_cache_alignment = c->x86_clflush_size * 2;
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 48533d77be78..da299eb85fc0 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -36,8 +36,11 @@ static struct _cache_table cache_table[] __cpuinitdata =
 {
        { 0x06, LVL_1_INST, 8 },        /* 4-way set assoc, 32 byte line size */
        { 0x08, LVL_1_INST, 16 },       /* 4-way set assoc, 32 byte line size */
+        { 0x09, LVL_1_INST, 32 },       /* 4-way set assoc, 64 byte line size */
        { 0x0a, LVL_1_DATA, 8 },        /* 2 way set assoc, 32 byte line size */
        { 0x0c, LVL_1_DATA, 16 },       /* 4-way set assoc, 32 byte line size */
+        { 0x0d, LVL_1_DATA, 16 },       /* 4-way set assoc, 64 byte line size */
+        { 0x21, LVL_2,      256 },      /* 8-way set assoc, 64 byte line size */
        { 0x22, LVL_3,      512 },      /* 4-way set assoc, sectored cache, 64 byte line size */
        { 0x23, LVL_3,      1024 },     /* 8-way set assoc, sectored cache, 64 byte line size */
        { 0x25, LVL_3,      2048 },     /* 8-way set assoc, sectored cache, 64 byte line size */
@@ -85,6 +88,18 @@ static struct _cache_table cache_table[] __cpuinitdata =
        { 0x85, LVL_2,    2048 },       /* 8-way set assoc, 32 byte line size */
        { 0x86, LVL_2,     512 },       /* 4-way set assoc, 64 byte line size */
        { 0x87, LVL_2,    1024 },       /* 8-way set assoc, 64 byte line size */
+        { 0xd0, LVL_3,     512 },       /* 4-way set assoc, 64 byte line size */
+        { 0xd1, LVL_3,    1024 },       /* 4-way set assoc, 64 byte line size */
+        { 0xd2, LVL_3,    2048 },       /* 4-way set assoc, 64 byte line size */
+        { 0xd6, LVL_3,    1024 },       /* 8-way set assoc, 64 byte line size */
+        { 0xd7, LVL_3,    2038 },       /* 8-way set assoc, 64 byte line size */
+        { 0xd8, LVL_3,    4096 },       /* 12-way set assoc, 64 byte line size */
+        { 0xdc, LVL_3,    2048 },       /* 12-way set assoc, 64 byte line size */
+        { 0xdd, LVL_3,    4096 },       /* 12-way set assoc, 64 byte line size */
+        { 0xde, LVL_3,    8192 },       /* 12-way set assoc, 64 byte line size */
+        { 0xe2, LVL_3,    2048 },       /* 16-way set assoc, 64 byte line size */
+        { 0xe3, LVL_3,    4096 },       /* 16-way set assoc, 64 byte line size */
+        { 0xe4, LVL_3,    8192 },       /* 16-way set assoc, 64 byte line size */
        { 0x00, 0, 0}
 };
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 1c838032fd37..fe79985ce0f2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -295,11 +295,11 @@ void do_machine_check(struct pt_regs * regs, long error_code)
                 * If we know that the error was in user space, send a
                 * SIGBUS.  Otherwise, panic if tolerance is low.
                 *
-                 * do_exit() takes an awful lot of locks and has a slight
+                 * force_sig() takes an awful lot of locks and has a slight
                 * risk of deadlocking.
                 */
                if (user_space) {
-                        do_exit(SIGBUS);
+                        force_sig(SIGBUS, current);
                } else if (panic_on_oops || tolerant < 2) {
                        mce_panic("Uncorrected machine check",
                                &panicm, mcestart);
@@ -490,7 +490,7 @@ static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
 }
-static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
+static void mce_cpu_features(struct cpuinfo_x86 *c)
 {
        switch (c->x86_vendor) {
        case X86_VENDOR_INTEL:
@@ -734,6 +734,7 @@ __setup("mce=", mcheck_enable);
 static int mce_resume(struct sys_device *dev)
 {
        mce_init(NULL);
+        mce_cpu_features(&current_cpu_data);
        return 0;
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 8ae8c4ff094d..f2ee0ae29bd6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -121,7 +121,7 @@ static long threshold_restart_bank(void *_tr)
 }
 /* cpu init entry point, called from mce.c with preempt off */
-void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
+void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
        unsigned int bank, block;
        unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 4b48f251fd39..f44c36624360 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -30,7 +30,7 @@ asmlinkage void smp_thermal_interrupt(void)
        irq_exit();
 }
-static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c)
+static void intel_init_thermal(struct cpuinfo_x86 *c)
 {
        u32 l, h;
        int tm2 = 0;
@@ -84,7 +84,7 @@ static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c)
        return;
 }
-void __cpuinit mce_intel_feature_init(struct cpuinfo_x86 *c)
+void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
        intel_init_thermal(c);
 }
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index d259e5d2e054..236a401b8259 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -1594,8 +1594,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
        /* kvm/qemu doesn't have mtrr set right, don't trim them all */
        if (!highest_pfn) {
-                WARN(!kvm_para_available(), KERN_WARNING
+                printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n");
-                                "WARNING: strange, CPU MTRRs all blank?\n");
                return 0;
        }
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index da91701a2348..87b67e3a765a 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -15,8 +15,8 @@
 * - buffer allocation (memory accounting)
 *
 *
- * Copyright (C) 2007-2008 Intel Corporation.
+ * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
 */
@@ -729,7 +729,7 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task,
        spin_unlock_irqrestore(&ds_lock, irq);
-        ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+        ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
        ds_resume_pebs(tracer);
        return tracer;
@@ -890,7 +890,7 @@ int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value)
 }
 static const struct ds_configuration ds_cfg_netburst = {
-        .name = "netburst",
+        .name = "Netburst",
        .ctl[dsf_bts]           = (1 << 2) | (1 << 3),
        .ctl[dsf_bts_kernel]    = (1 << 5),
        .ctl[dsf_bts_user]      = (1 << 6),
@@ -904,7 +904,7 @@ static const struct ds_configuration ds_cfg_netburst = {
 #endif
 };
 static const struct ds_configuration ds_cfg_pentium_m = {
-        .name = "pentium m",
+        .name = "Pentium M",
        .ctl[dsf_bts]           = (1 << 6) | (1 << 7),
        .sizeof_field           = sizeof(long),
@@ -915,8 +915,8 @@ static const struct ds_configuration ds_cfg_pentium_m = {
        .sizeof_rec[ds_pebs]    = sizeof(long) * 18,
 #endif
 };
-static const struct ds_configuration ds_cfg_core2 = {
+static const struct ds_configuration ds_cfg_core2_atom = {
-        .name = "core 2",
+        .name = "Core 2/Atom",
        .ctl[dsf_bts]           = (1 << 6) | (1 << 7),
        .ctl[dsf_bts_kernel]    = (1 << 9),
        .ctl[dsf_bts_user]      = (1 << 10),
@@ -949,19 +949,22 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
        switch (c->x86) {
        case 0x6:
                switch (c->x86_model) {
-                case 0 ... 0xC:
+                case 0x9:
-                        /* sorry, don't know about them */
+                case 0xd: /* Pentium M */
-                        break;
-                case 0xD:
-                case 0xE: /* Pentium M */
                        ds_configure(&ds_cfg_pentium_m);
                        break;
-                default: /* Core2, Atom, ... */
+                case 0xf:
-                        ds_configure(&ds_cfg_core2);
+                case 0x17: /* Core2 */
+                case 0x1c: /* Atom */
+                        ds_configure(&ds_cfg_core2_atom);
+                        break;
+                case 0x1a: /* i7 */
+                default:
+                        /* sorry, don't know about them */
                        break;
                }
                break;
-        case 0xF:
+        case 0xf:
                switch (c->x86_model) {
                case 0x0:
                case 0x1:
@@ -1026,5 +1029,4 @@ void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
 void ds_exit_thread(struct task_struct *tsk)
 {
-        WARN_ON(tsk->thread.ds_ctx);
 }
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 1119d247fe11..eb1ef3b67dd5 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -467,7 +467,7 @@ void __init efi_enter_virtual_mode(void)
        efi_memory_desc_t *md;
        efi_status_t status;
        unsigned long size;
-        u64 end, systab, addr, npages;
+        u64 end, systab, addr, npages, end_pfn;
        void *p, *va;
        efi.systab = NULL;
@@ -479,7 +479,10 @@ void __init efi_enter_virtual_mode(void)
                size = md->num_pages << EFI_PAGE_SHIFT;
                end = md->phys_addr + size;
-                if (PFN_UP(end) <= max_low_pfn_mapped)
+                end_pfn = PFN_UP(end);
+                if (end_pfn <= max_low_pfn_mapped
+                    || (end_pfn > (1UL << (32 - PAGE_SHIFT))
+                        && end_pfn <= max_pfn_mapped))
                        va = __va(md->phys_addr);
                else
                        va = efi_ioremap(md->phys_addr, size);
diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c
index 652c5287215f..cb783b92c50c 100644
--- a/arch/x86/kernel/efi_64.c
+++ b/arch/x86/kernel/efi_64.c
@@ -99,24 +99,11 @@ void __init efi_call_phys_epilog(void)
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size)
 {
-        static unsigned pages_mapped __initdata;
+        unsigned long last_map_pfn;
-        unsigned i, pages;
-        unsigned long offset;
-        pages = PFN_UP(phys_addr + size) - PFN_DOWN(phys_addr);
+        last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
-        offset = phys_addr & ~PAGE_MASK;
+        if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size)
-        phys_addr &= PAGE_MASK;
-        if (pages_mapped + pages > MAX_EFI_IO_PAGES)
                return NULL;
-        for (i = 0; i < pages; i++) {
+        return (void __iomem *)__va(phys_addr);
-                __set_fixmap(FIX_EFI_IO_MAP_FIRST_PAGE - pages_mapped,
-                             phys_addr, PAGE_KERNEL);
-                phys_addr += PAGE_SIZE;
-                pages_mapped++;
-        }
-        return (void __iomem *)__fix_to_virt(FIX_EFI_IO_MAP_FIRST_PAGE - \
-                                             (pages_mapped - pages)) + offset;
 }
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e28c7a987793..a1346217e43c 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -346,6 +346,7 @@ ENTRY(save_args)
        popq_cfi %rax                   /* move return address... */
        mov %gs:pda_irqstackptr,%rsp
        EMPTY_FRAME 0
+        pushq_cfi %rbp                  /* backlink for unwinder */
        pushq_cfi %rax                  /* ... to the new stack */
        /*
         * We entered an interrupt context - irqs are off:
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 1b43086b097a..231bdd3c5b1c 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -488,20 +488,21 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
         * ignore such a protection.
         */
        asm volatile(
-                "1: " _ASM_MOV " (%[parent_old]), %[old]\n"
+                "1: " _ASM_MOV " (%[parent]), %[old]\n"
-                "2: " _ASM_MOV " %[return_hooker], (%[parent_replaced])\n"
+                "2: " _ASM_MOV " %[return_hooker], (%[parent])\n"
                "   movl $0, %[faulted]\n"
+                "3:\n"
                ".section .fixup, \"ax\"\n"
-                "3: movl $1, %[faulted]\n"
+                "4: movl $1, %[faulted]\n"
+                "   jmp 3b\n"
                ".previous\n"
-                _ASM_EXTABLE(1b, 3b)
+                _ASM_EXTABLE(1b, 4b)
-                _ASM_EXTABLE(2b, 3b)
+                _ASM_EXTABLE(2b, 4b)
-                : [parent_replaced] "=r" (parent), [old] "=r" (old),
+                : [old] "=r" (old), [faulted] "=r" (faulted)
-                  [faulted] "=r" (faulted)
+                : [parent] "r" (parent), [return_hooker] "r" (return_hooker)
-                : [parent_old] "0" (parent), [return_hooker] "r" (return_hooker)
                : "memory"
        );
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 64d5ad0b8add..a00545fe5cdd 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -269,6 +269,8 @@ static void hpet_set_mode(enum clock_event_mode mode,
                now = hpet_readl(HPET_COUNTER);
                cmp = now + (unsigned long) delta;
                cfg = hpet_readl(HPET_Tn_CFG(timer));
+                /* Make sure we use edge triggered interrupts */
+                cfg &= ~HPET_TN_LEVEL;
                cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
                       HPET_TN_SETVAL | HPET_TN_32BIT;
                hpet_writel(cfg, HPET_Tn_CFG(timer));
@@ -897,7 +899,7 @@ static unsigned long hpet_rtc_flags;
 static int hpet_prev_update_sec;
 static struct rtc_time hpet_alarm_time;
 static unsigned long hpet_pie_count;
-static unsigned long hpet_t1_cmp;
+static u32 hpet_t1_cmp;
 static unsigned long hpet_default_delta;
 static unsigned long hpet_pie_delta;
 static unsigned long hpet_pie_limit;
@@ -905,6 +907,14 @@ static unsigned long hpet_pie_limit;
 static rtc_irq_handler irq_handler;
 /*
+ * Check that the hpet counter c1 is ahead of the c2
+ */
+static inline int hpet_cnt_ahead(u32 c1, u32 c2)
+{
+        return (s32)(c2 - c1) < 0;
+}
+/*
 * Registers a IRQ handler.
 */
 int hpet_register_irq_handler(rtc_irq_handler handler)
@@ -1075,7 +1085,7 @@ static void hpet_rtc_timer_reinit(void)
                hpet_t1_cmp += delta;
                hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
                lost_ints++;
-        } while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
+        } while (!hpet_cnt_ahead(hpet_t1_cmp, hpet_readl(HPET_COUNTER)));
        if (lost_ints) {
                if (hpet_rtc_flags & RTC_PIE)
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index b0f61f0dcd0a..f2f8540a7f3d 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -136,7 +136,7 @@ int init_fpu(struct task_struct *tsk)
 #ifdef CONFIG_X86_32
        if (!HAVE_HWFP) {
                memset(tsk->thread.xstate, 0, xstate_size);
-                finit();
+                finit_task(tsk);
                set_stopped_child_used_math(tsk);
                return 0;
        }
diff --git a/arch/x86/kernel/i8237.c b/arch/x86/kernel/i8237.c
index dbd6c1d1b638..b42ca694dc68 100644
--- a/arch/x86/kernel/i8237.c
+++ b/arch/x86/kernel/i8237.c
@@ -28,10 +28,10 @@ static int i8237A_resume(struct sys_device *dev)
        flags = claim_dma_lock();
-        dma_outb(DMA1_RESET_REG, 0);
+        dma_outb(0, DMA1_RESET_REG);
-        dma_outb(DMA2_RESET_REG, 0);
+        dma_outb(0, DMA2_RESET_REG);
-        for (i = 0;i < 8;i++) {
+        for (i = 0; i < 8; i++) {
                set_dma_addr(i, 0x000000);
                /* DMA count is a bit weird so this is not 0 */
                set_dma_count(i, 1);
@@ -51,14 +51,14 @@ static int i8237A_suspend(struct sys_device *dev, pm_message_t state)
 }
 static struct sysdev_class i8237_sysdev_class = {
-        .name = "i8237",
+        .name           = "i8237",
-        .suspend = i8237A_suspend,
+        .suspend        = i8237A_suspend,
-        .resume = i8237A_resume,
+        .resume         = i8237A_resume,
 };
 static struct sys_device device_i8237A = {
-        .id     = 0,
+        .id             = 0,
-        .cls    = &i8237_sysdev_class,
+        .cls            = &i8237_sysdev_class,
 };
 static int __init i8237A_init_sysfs(void)
@@ -68,5 +68,4 @@ static int __init i8237A_init_sysfs(void)
                error = sysdev_register(&device_i8237A);
        return error;
 }
 device_initcall(i8237A_init_sysfs);
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1c4a1302536c..bc7ac4da90d7 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -2528,14 +2528,15 @@ static void irq_complete_move(struct irq_desc **descp)
        vector = ~get_irq_regs()->orig_ax;
        me = smp_processor_id();
+        if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
 #ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
                *descp = desc = move_irq_desc(desc, me);
                /* get the new one */
                cfg = desc->chip_data;
 #endif
-        if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
                send_cleanup_vector(cfg);
+        }
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
@@ -3840,14 +3841,24 @@ int __init io_apic_get_redir_entries (int ioapic)
 void __init probe_nr_irqs_gsi(void)
 {
-        int idx;
        int nr = 0;
-        for (idx = 0; idx < nr_ioapics; idx++)
+        nr = acpi_probe_gsi();
-                nr += io_apic_get_redir_entries(idx) + 1;
+        if (nr > nr_irqs_gsi) {
-        if (nr > nr_irqs_gsi)
                nr_irqs_gsi = nr;
+        } else {
+                /* for acpi=off or acpi is not compiled in */
+                int idx;
+                nr = 0;
+                for (idx = 0; idx < nr_ioapics; idx++)
+                        nr += io_apic_get_redir_entries(idx) + 1;
+                if (nr > nr_irqs_gsi)
+                        nr_irqs_gsi = nr;
+        }
+        printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
 }
 /* --------------------------------------------------------------------------
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 1507ad4e674d..10a09c2f1828 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -78,15 +78,6 @@ void __init init_ISA_irqs(void)
        }
 }
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
-        .handler = no_action,
-        .mask = CPU_MASK_NONE,
-        .name = "cascade",
-};
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
        [0 ... IRQ0_VECTOR - 1] = -1,
        [IRQ0_VECTOR] = 0,
@@ -178,9 +169,6 @@ void __init native_init_IRQ(void)
        alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
 #endif
-        if (!acpi_ioapic)
-                setup_irq(2, &irq2);
        /* setup after call gates are initialised (usually add in
         * the architecture specific gates)
         */
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index e948b28a5a9a..4558dd3918cf 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -193,6 +193,9 @@ static int __kprobes can_boost(kprobe_opcode_t *opcodes)
        kprobe_opcode_t opcode;
        kprobe_opcode_t *orig_opcodes = opcodes;
+        if (search_exception_tables(opcodes))
+                return 0;       /* Page fault may occur on this address. */
 retry:
        if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
                return 0;
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 7a13fac63a1f..4006c522adc7 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -203,7 +203,7 @@ static void __init platform_detect(void)
 static void __init platform_detect(void)
 {
        /* stopgap until OFW support is added to the kernel */
-        olpc_platform_info.boardrev = 0xc2;
+        olpc_platform_info.boardrev = olpc_board(0xc2);
 }
 #endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e4c8fb608873..c6520a4e85d4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -268,6 +268,32 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
        return __get_cpu_var(paravirt_lazy_mode);
 }
+void arch_flush_lazy_mmu_mode(void)
+{
+        preempt_disable();
+        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+                WARN_ON(preempt_count() == 1);
+                arch_leave_lazy_mmu_mode();
+                arch_enter_lazy_mmu_mode();
+        }
+        preempt_enable();
+}
+void arch_flush_lazy_cpu_mode(void)
+{
+        preempt_disable();
+        if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
+                WARN_ON(preempt_count() == 1);
+                arch_leave_lazy_cpu_mode();
+                arch_enter_lazy_cpu_mode();
+        }
+        preempt_enable();
+}
 struct pv_info pv_info = {
        .name = "bare hardware",
        .paravirt_enabled = 0,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e68bb9e30864..6d12f7e37f8c 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -180,6 +180,9 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
        trace_power_start(&it, POWER_CSTATE, (ax>>4)+1);
        if (!need_resched()) {
+                if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+                        clflush((void *)&current_thread_info()->flags);
                __monitor((void *)&current_thread_info()->flags, 0, 0);
                smp_mb();
                if (!need_resched())
@@ -194,6 +197,9 @@ static void mwait_idle(void)
        struct power_trace it;
        if (!need_resched()) {
                trace_power_start(&it, POWER_CSTATE, 1);
+                if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+                        clflush((void *)&current_thread_info()->flags);
                __monitor((void *)&current_thread_info()->flags, 0, 0);
                smp_mb();
                if (!need_resched())
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a546f55c77b4..bd4da2af08ae 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -104,9 +104,6 @@ void cpu_idle(void)
                        check_pgt_cache();
                        rmb();
-                        if (rcu_pending(cpu))
-                                rcu_check_callbacks(cpu, 0);
                        if (cpu_is_offline(cpu))
                                play_dead();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 416fb9282f4f..85b4cb5c1980 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -40,6 +40,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/ftrace.h>
+#include <linux/dmi.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -151,14 +152,18 @@ void __show_regs(struct pt_regs *regs, int all)
        unsigned long d0, d1, d2, d3, d6, d7;
        unsigned int fsindex, gsindex;
        unsigned int ds, cs, es;
+        const char *board;
        printk("\n");
        print_modules();
-        printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n",
+        board = dmi_get_system_info(DMI_PRODUCT_NAME);
+        if (!board)
+                board = "";
+        printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n",
                current->pid, current->comm, print_tainted(),
                init_utsname()->release,
                (int)strcspn(init_utsname()->version, " "),
-                init_utsname()->version);
+                init_utsname()->version, board);
        printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
        printk_address(regs->ip, 1);
        printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0a5df5f82fb9..06ca07f6ad86 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -810,12 +810,16 @@ static void ptrace_bts_untrace(struct task_struct *child)
 static void ptrace_bts_detach(struct task_struct *child)
 {
-        if (unlikely(child->bts)) {
+        /*
-                ds_release_bts(child->bts);
+         * Ptrace_detach() races with ptrace_untrace() in case
-                child->bts = NULL;
+         * the child dies and is reaped by another thread.
+         *
-                ptrace_bts_free_buffer(child);
+         * We only do the memory accounting at this point and
-        }
+         * leave the buffer deallocation and the bts tracer
+         * release to ptrace_bts_untrace() which will be called
+         * later on with tasklist_lock held.
+         */
+        release_locked_buffer(child->bts_buffer, child->bts_size);
 }
 #else
 static inline void ptrace_bts_fork(struct task_struct *tsk) {}
@@ -1384,7 +1388,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 #ifdef CONFIG_X86_32
 # define IS_IA32        1
 #elif defined CONFIG_IA32_EMULATION
-# define IS_IA32        test_thread_flag(TIF_IA32)
+# define IS_IA32        is_compat_task()
 #else
 # define IS_IA32        0
 #endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2b46eb41643b..4526b3a75ed2 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -217,6 +217,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
                        DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"),
                },
        },
+        {       /* Handle problems with rebooting on Dell XPS710 */
+                .callback = set_bios_reboot,
+                .ident = "Dell XPS710",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"),
+                },
+        },
        { }
 };
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ae0d8042cf69..6a8811a69324 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -607,7 +607,7 @@ struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
 static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 {
        printk(KERN_NOTICE
-                "%s detected: BIOS may corrupt low RAM, working it around.\n",
+                "%s detected: BIOS may corrupt low RAM, working around it.\n",
                d->ident);
        e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
@@ -770,6 +770,9 @@ void __init setup_arch(char **cmdline_p)
        finish_e820_parsing();
+        if (efi_enabled)
+                efi_init();
        dmi_scan_machine();
        dmi_check_system(bad_bios_dmi_table);
@@ -789,8 +792,6 @@ void __init setup_arch(char **cmdline_p)
        insert_resource(&iomem_resource, &data_resource);
        insert_resource(&iomem_resource, &bss_resource);
-        if (efi_enabled)
-                efi_init();
 #ifdef CONFIG_X86_32
        if (ppro_with_ram_bug()) {
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index e6e695acd725..241ec3923f61 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -115,7 +115,7 @@ unsigned long __init calibrate_cpu(void)
 static struct irqaction irq0 = {
        .handler        = timer_interrupt,
-        .flags          = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING,
+        .flags          = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER,
        .mask           = CPU_MASK_NONE,
        .name           = "timer"
 };
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 98c2d055284b..a9e7548e1790 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -99,6 +99,12 @@ static inline void preempt_conditional_sti(struct pt_regs *regs)
                local_irq_enable();
 }
+static inline void conditional_cli(struct pt_regs *regs)
+{
+        if (regs->flags & X86_EFLAGS_IF)
+                local_irq_disable();
+}
 static inline void preempt_conditional_cli(struct pt_regs *regs)
 {
        if (regs->flags & X86_EFLAGS_IF)
@@ -626,8 +632,10 @@ clear_dr7:
 #ifdef CONFIG_X86_32
 debug_vm86:
+        /* reenable preemption: handle_vm86_trap() might sleep */
+        dec_preempt_count();
        handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
-        preempt_conditional_cli(regs);
+        conditional_cli(regs);
        return;
 #endif
@@ -896,7 +904,7 @@ asmlinkage void math_state_restore(void)
 EXPORT_SYMBOL_GPL(math_state_restore);
 #ifndef CONFIG_MATH_EMULATION
-asmlinkage void math_emulate(long arg)
+void math_emulate(struct math_emu_info *info)
 {
        printk(KERN_EMERG
                "math-emulation not enabled and no coprocessor found.\n");
@@ -906,16 +914,19 @@ asmlinkage void math_emulate(long arg)
 }
 #endif /* CONFIG_MATH_EMULATION */
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes do_device_not_available(struct pt_regs regs)
-do_device_not_available(struct pt_regs *regs, long error)
 {
 #ifdef CONFIG_X86_32
        if (read_cr0() & X86_CR0_EM) {
-                conditional_sti(regs);
+                struct math_emu_info info = { };
-                math_emulate(0);
+                conditional_sti(&regs);
+                info.regs = &regs;
+                math_emulate(&info);
        } else {
                math_state_restore(); /* interrupts still off */
-                conditional_sti(regs);
+                conditional_sti(&regs);
        }
 #else
        math_state_restore();
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 599e58168631..d5cebb52d45b 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -273,30 +273,43 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
 * use the TSC value at the transitions to calculate a pretty
 * good value for the TSC frequencty.
 */
-static inline int pit_expect_msb(unsigned char val)
+static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
 {
-        int count = 0;
+        int count;
+        u64 tsc = 0;
        for (count = 0; count < 50000; count++) {
                /* Ignore LSB */
                inb(0x42);
                if (inb(0x42) != val)
                        break;
+                tsc = get_cycles();
        }
-        return count > 50;
+        *deltap = get_cycles() - tsc;
+        *tscp = tsc;
+        /*
+         * We require _some_ success, but the quality control
+         * will be based on the error terms on the TSC values.
+         */
+        return count > 5;
 }
 /*
- * How many MSB values do we want to see? We aim for a
+ * How many MSB values do we want to see? We aim for
- * 15ms calibration, which assuming a 2us counter read
+ * a maximum error rate of 500ppm (in practice the
- * error should give us roughly 150 ppm precision for
+ * real error is much smaller), but refuse to spend
- * the calibration.
+ * more than 25ms on it.
 */
-#define QUICK_PIT_MS 15
+#define MAX_QUICK_PIT_MS 25
-#define QUICK_PIT_ITERATIONS (QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
+#define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
 static unsigned long quick_pit_calibrate(void)
 {
+        int i;
+        u64 tsc, delta;
+        unsigned long d1, d2;
        /* Set the Gate high, disable speaker */
        outb((inb(0x61) & ~0x02) | 0x01, 0x61);
@@ -315,45 +328,52 @@ static unsigned long quick_pit_calibrate(void)
        outb(0xff, 0x42);
        outb(0xff, 0x42);
-        if (pit_expect_msb(0xff)) {
+        /*
-                int i;
+         * The PIT starts counting at the next edge, so we
-                u64 t1, t2, delta;
+         * need to delay for a microsecond. The easiest way
-                unsigned char expect = 0xfe;
+         * to do that is to just read back the 16-bit counter
+         * once from the PIT.
-                t1 = get_cycles();
+         */
-                for (i = 0; i < QUICK_PIT_ITERATIONS; i++, expect--) {
+        inb(0x42);
-                        if (!pit_expect_msb(expect))
+        inb(0x42);
-                                goto failed;
+        if (pit_expect_msb(0xff, &tsc, &d1)) {
+                for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) {
+                        if (!pit_expect_msb(0xff-i, &delta, &d2))
+                                break;
+                        /*
+                         * Iterate until the error is less than 500 ppm
+                         */
+                        delta -= tsc;
+                        if (d1+d2 < delta >> 11)
+                                goto success;
                }
-                t2 = get_cycles();
-                /*
-                 * Make sure we can rely on the second TSC timestamp:
-                 */
-                if (!pit_expect_msb(expect))
-                        goto failed;
-                /*
-                 * Ok, if we get here, then we've seen the
-                 * MSB of the PIT decrement QUICK_PIT_ITERATIONS
-                 * times, and each MSB had many hits, so we never
-                 * had any sudden jumps.
-                 *
-                 * As a result, we can depend on there not being
-                 * any odd delays anywhere, and the TSC reads are
-                 * reliable.
-                 *
-                 * kHz = ticks / time-in-seconds / 1000;
-                 * kHz = (t2 - t1) / (QPI * 256 / PIT_TICK_RATE) / 1000
-                 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (QPI * 256 * 1000)
-                 */
-                delta = (t2 - t1)*PIT_TICK_RATE;
-                do_div(delta, QUICK_PIT_ITERATIONS*256*1000);
-                printk("Fast TSC calibration using PIT\n");
-                return delta;
        }
-failed:
+        printk("Fast TSC calibration failed\n");
        return 0;
+success:
+        /*
+         * Ok, if we get here, then we've seen the
+         * MSB of the PIT decrement 'i' times, and the
+         * error has shrunk to less than 500 ppm.
+         *
+         * As a result, we can depend on there not being
+         * any odd delays anywhere, and the TSC reads are
+         * reliable (within the error). We also adjust the
+         * delta to the middle of the error bars, just
+         * because it looks nicer.
+         *
+         * kHz = ticks / time-in-seconds / 1000;
+         * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000
+         * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000)
+         */
+        delta += (long)(d2 - d1)/2;
+        delta *= PIT_TICK_RATE;
+        do_div(delta, i*256*1000);
+        printk("Fast TSC calibration using PIT\n");
+        return delta;
 }
 /**
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 1d3302cc2ddf..bef58b4982db 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -321,6 +321,16 @@ static void vmi_release_pmd(unsigned long pfn)
 }
 /*
+ * We use the pgd_free hook for releasing the pgd page:
+ */
+static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+        unsigned long pfn = __pa(pgd) >> PAGE_SHIFT;
+        vmi_ops.release_page(pfn, VMI_PAGE_L2);
+}
+/*
 * Helper macros for MMU update flags.  We can defer updates until a flush
 * or page invalidation only if the update is to the current address space
 * (otherwise, there is no flush).  We must check against init_mm, since
@@ -762,6 +772,7 @@ static inline int __init activate_vmi(void)
        if (vmi_ops.release_page) {
                pv_mmu_ops.release_pte = vmi_release_pte;
                pv_mmu_ops.release_pmd = vmi_release_pmd;
+                pv_mmu_ops.pgd_free = vmi_pgd_free;
        }
        /* Set linear is needed in all cases */
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index c4c1f9e09402..e5b088fffa40 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -202,7 +202,7 @@ static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
 static struct irqaction vmi_clock_action  = {
        .name           = "vmi-timer",
        .handler        = vmi_timer_interrupt,
-        .flags          = IRQF_DISABLED | IRQF_NOBALANCING,
+        .flags          = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
        .mask           = CPU_MASK_ALL,
 };
@@ -283,10 +283,13 @@ void __devinit vmi_time_ap_init(void)
 #endif
 /** vmi clocksource */
+static struct clocksource clocksource_vmi;
 static cycle_t read_real_cycles(void)
 {
-        return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+        cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+        return ret >= clocksource_vmi.cycle_last ?
+                ret : clocksource_vmi.cycle_last;
 }
 static struct clocksource clocksource_vmi = {