18 files changed, 104 insertions, 65 deletions

diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 2e837f5080fe..fb7a5f052e2b 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -145,6 +145,15 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
                 percpu_entry->states[cx->index].eax = cx->address;
                 percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
         }
+
+        /*
+         * For _CST FFH on Intel, if GAS.access_size bit 1 is cleared,
+         * then we should skip checking BM_STS for this C-state.
+         * ref: "Intel Processor Vendor-Specific ACPI Interface Specification"
+         */
+        if ((c->x86_vendor == X86_VENDOR_INTEL) && !(reg->access_size & 0x2))
+                cx->bm_sts_skip = 1;
+
         return retval;
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 82e508677b91..fcc3c61fdecc 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -157,9 +157,14 @@ 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();
+                if (strncmp(str, "s4_nonvs", 8) == 0) {
+                        pr_warning("ACPI: acpi_sleep=s4_nonvs is deprecated, "
+                                        "please use acpi_sleep=nonvs instead");
+                        acpi_nvs_nosave();
+                }
 #endif
+                if (strncmp(str, "nonvs", 5) == 0)
+                        acpi_nvs_nosave();
                 if (strncmp(str, "old_ordering", 12) == 0)
                         acpi_old_suspend_ordering();
                 str = strchr(str, ',');
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index c02cc692985c..a96489ee6cab 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -921,7 +921,7 @@ void disable_local_APIC(void)
         unsigned int value;
 
         /* APIC hasn't been mapped yet */
-        if (!apic_phys)
+        if (!x2apic_mode && !apic_phys)
                 return;
 
         clear_local_APIC();
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
index ce7cde713e71..a36de5bbb622 100644
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
@@ -368,22 +368,16 @@ static int __init pcc_cpufreq_do_osc(acpi_handle *handle)
                 return -ENODEV;
 
         out_obj = output.pointer;
-        if (out_obj->type != ACPI_TYPE_BUFFER) {
-                ret = -ENODEV;
-                goto out_free;
-        }
+        if (out_obj->type != ACPI_TYPE_BUFFER)
+                return -ENODEV;
 
         errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0);
-        if (errors) {
-                ret = -ENODEV;
-                goto out_free;
-        }
+        if (errors)
+                return -ENODEV;
 
         supported = *((u32 *)(out_obj->buffer.pointer + 4));
-        if (!(supported & 0x1)) {
-                ret = -ENODEV;
-                goto out_free;
-        }
+        if (!(supported & 0x1))
+                return -ENODEV;
 
 out_free:
         kfree(output.pointer);
@@ -397,13 +391,17 @@ static int __init pcc_cpufreq_probe(void)
         struct pcc_memory_resource *mem_resource;
         struct pcc_register_resource *reg_resource;
         union acpi_object *out_obj, *member;
-        acpi_handle handle, osc_handle;
+        acpi_handle handle, osc_handle, pcch_handle;
         int ret = 0;
 
         status = acpi_get_handle(NULL, "\\_SB", &handle);
         if (ACPI_FAILURE(status))
                 return -ENODEV;
 
+        status = acpi_get_handle(handle, "PCCH", &pcch_handle);
+        if (ACPI_FAILURE(status))
+                return -ENODEV;
+
         status = acpi_get_handle(handle, "_OSC", &osc_handle);
         if (ACPI_SUCCESS(status)) {
                 ret = pcc_cpufreq_do_osc(&osc_handle);
@@ -543,13 +541,13 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
         if (!pcch_virt_addr) {
                 result = -1;
-                goto pcch_null;
+                goto out;
         }
 
         result = pcc_get_offset(cpu);
         if (result) {
                 dprintk("init: PCCP evaluation failed\n");
-                goto free;
+                goto out;
         }
 
         policy->max = policy->cpuinfo.max_freq =
@@ -558,14 +556,15 @@ static int pcc_cpufreq_cpu_init(struct cpufreq_policy *policy)
                 ioread32(&pcch_hdr->minimum_frequency) * 1000;
         policy->cur = pcc_get_freq(cpu);
 
+        if (!policy->cur) {
+                dprintk("init: Unable to get current CPU frequency\n");
+                result = -EINVAL;
+                goto out;
+        }
+
         dprintk("init: policy->max is %d, policy->min is %d\n",
                 policy->max, policy->min);
-
-        return 0;
-free:
-        pcc_clear_mapping();
-        free_percpu(pcc_cpu_info);
-pcch_null:
+out:
         return result;
 }
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 7ec2123838e6..3e90cce3dc8b 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1023,13 +1023,12 @@ static int get_transition_latency(struct powernow_k8_data *data)
         }
         if (max_latency == 0) {
                 /*
-                 * Fam 11h always returns 0 as transition latency.
-                 * This is intended and means "very fast". While cpufreq core
-                 * and governors currently can handle that gracefully, better
-                 * set it to 1 to avoid problems in the future.
-                 * For all others it's a BIOS bug.
+                 * Fam 11h and later may return 0 as transition latency. This
+                 * is intended and means "very fast". While cpufreq core and
+                 * governors currently can handle that gracefully, better set it
+                 * to 1 to avoid problems in the future.
                  */
-                if (boot_cpu_data.x86 != 0x11)
+                if (boot_cpu_data.x86 < 0x11)
                         printk(KERN_ERR FW_WARN PFX "Invalid zero transition "
                                 "latency\n");
                 max_latency = 1;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index ebdb85cf2686..e5cc7e82e60d 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -18,6 +18,7 @@
 #include <asm/apic.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
+#include <asm/hpet.h>
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
@@ -191,6 +192,21 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 }
 #endif
 
+/*
+ * Force the read back of the CMP register in hpet_next_event()
+ * to work around the problem that the CMP register write seems to be
+ * delayed. See hpet_next_event() for details.
+ *
+ * We do this on all SMBUS incarnations for now until we have more
+ * information about the affected chipsets.
+ */
+static void __init ati_hpet_bugs(int num, int slot, int func)
+{
+#ifdef CONFIG_HPET_TIMER
+        hpet_readback_cmp = 1;
+#endif
+}
+
 #define QFLAG_APPLY_ONCE        0x1
 #define QFLAG_APPLIED           0x2
 #define QFLAG_DONE              (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -220,6 +236,8 @@ static struct chipset early_qrk[] __initdata = {
           PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
         { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
           PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
+        { PCI_VENDOR_ID_ATI, PCI_ANY_ID,
+          PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs },
         {}
 };
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 0697ff139837..4db7c4d12ffa 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -571,8 +571,8 @@ auditsys:
          * masked off.
          */
 sysret_audit:
-        movq %rax,%rsi          /* second arg, syscall return value */
-        cmpq $0,%rax            /* is it < 0? */
+        movq RAX-ARGOFFSET(%rsp),%rsi   /* second arg, syscall return value */
+        cmpq $0,%rsi            /* is it < 0? */
         setl %al                /* 1 if so, 0 if not */
         movzbl %al,%edi         /* zero-extend that into %edi */
         inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index a198b7c87a12..ba390d731175 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -964,7 +964,7 @@ fs_initcall(hpet_late_init);
 
 void hpet_disable(void)
 {
-        if (is_hpet_capable()) {
+        if (is_hpet_capable() && hpet_virt_address) {
                 unsigned int cfg = hpet_readl(HPET_CFG);
 
                 if (hpet_legacy_int_enabled) {
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 7c9f02c130f3..cafa7c80ac95 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -276,16 +276,6 @@ static struct sys_device device_i8259A = {
         .cls    = &i8259_sysdev_class,
 };
 
-static int __init i8259A_init_sysfs(void)
-{
-        int error = sysdev_class_register(&i8259_sysdev_class);
-        if (!error)
-                error = sysdev_register(&device_i8259A);
-        return error;
-}
-
-device_initcall(i8259A_init_sysfs);
-
 static void mask_8259A(void)
 {
         unsigned long flags;
@@ -407,3 +397,18 @@ struct legacy_pic default_legacy_pic = {
 };
 
 struct legacy_pic *legacy_pic = &default_legacy_pic;
+
+static int __init i8259A_init_sysfs(void)
+{
+        int error;
+
+        if (legacy_pic != &default_legacy_pic)
+                return 0;
+
+        error = sysdev_class_register(&i8259_sysdev_class);
+        if (!error)
+                error = sysdev_register(&device_i8259A);
+        return error;
+}
+
+device_initcall(i8259A_init_sysfs);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 4f4af75b9482..01ab17ae2ae7 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -572,7 +572,6 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd)
         return NOTIFY_STOP;
 }
 
-#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 int kgdb_ll_trap(int cmd, const char *str,
                  struct pt_regs *regs, long err, int trap, int sig)
 {
@@ -590,7 +589,6 @@ int kgdb_ll_trap(int cmd, const char *str,
 
         return __kgdb_notify(&args, cmd);
 }
-#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
 static int
 kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
@@ -625,6 +623,12 @@ int kgdb_arch_init(void)
         return register_die_notifier(&kgdb_notifier);
 }
 
+static void kgdb_hw_overflow_handler(struct perf_event *event, int nmi,
+                struct perf_sample_data *data, struct pt_regs *regs)
+{
+        kgdb_ll_trap(DIE_DEBUG, "debug", regs, 0, 0, SIGTRAP);
+}
+
 void kgdb_arch_late(void)
 {
         int i, cpu;
@@ -655,6 +659,7 @@ void kgdb_arch_late(void)
                 for_each_online_cpu(cpu) {
                         pevent = per_cpu_ptr(breakinfo[i].pev, cpu);
                         pevent[0]->hw.sample_period = 1;
+                        pevent[0]->overflow_handler = kgdb_hw_overflow_handler;
                         if (pevent[0]->destroy != NULL) {
                                 pevent[0]->destroy = NULL;
                                 release_bp_slot(*pevent);
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 345a4b1fe144..675879b65ce6 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -640,8 +640,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
         /* Skip cs, ip, orig_ax and gs. */      \
         "       subl $16, %esp\n"       \
         "       pushl %fs\n"            \
-        "       pushl %ds\n"            \
         "       pushl %es\n"            \
+        "       pushl %ds\n"            \
         "       pushl %eax\n"           \
         "       pushl %ebp\n"           \
         "       pushl %edi\n"           \
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index e72d3fc6547d..939b9e98245f 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -498,15 +498,10 @@ void force_hpet_resume(void)
  * See erratum #27 (Misinterpreted MSI Requests May Result in
  * Corrupted LPC DMA Data) in AMD Publication #46837,
  * "SB700 Family Product Errata", Rev. 1.0, March 2010.
- *
- * Also force the read back of the CMP register in hpet_next_event()
- * to work around the problem that the CMP register write seems to be
- * delayed. See hpet_next_event() for details.
  */
 static void force_disable_hpet_msi(struct pci_dev *unused)
 {
         hpet_msi_disable = 1;
-        hpet_readback_cmp = 1;
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index de3b63ae3da2..a60df9ae6454 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -238,6 +238,15 @@ void __init setup_per_cpu_areas(void)
 #ifdef CONFIG_NUMA
                 per_cpu(x86_cpu_to_node_map, cpu) =
                         early_per_cpu_map(x86_cpu_to_node_map, cpu);
+                /*
+                 * Ensure that the boot cpu numa_node is correct when the boot
+                 * cpu is on a node that doesn't have memory installed.
+                 * Also cpu_up() will call cpu_to_node() for APs when
+                 * MEMORY_HOTPLUG is defined, before per_cpu(numa_node) is set
+                 * up later with c_init aka intel_init/amd_init.
+                 * So set them all (boot cpu and all APs).
+                 */
+                set_cpu_numa_node(cpu, early_cpu_to_node(cpu));
 #endif
 #endif
                 /*
@@ -257,14 +266,6 @@ void __init setup_per_cpu_areas(void)
         early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
 #endif
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
-        /*
-         * make sure boot cpu numa_node is right, when boot cpu is on the
-         * node that doesn't have mem installed
-         */
-        set_cpu_numa_node(boot_cpu_id, early_cpu_to_node(boot_cpu_id));
-#endif
-
         /* Setup node to cpumask map */
         setup_node_to_cpumask_map();
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 3699613e8830..b1ed0a1a5913 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2926,7 +2926,7 @@ static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm)
         return kvm_mmu_zap_page(kvm, page) + 1;
 }
 
-static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
+static int mmu_shrink(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
 {
         struct kvm *kvm;
         struct kvm *kvm_freed = NULL;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 89d66ca4d87c..2331bdc2b549 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -342,6 +342,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
                         /* advance table_gfn when emulating 1gb pages with 4k */
                         if (delta == 0)
                                 table_gfn += PT_INDEX(addr, level);
+                        access &= gw->pte_access;
                 } else {
                         direct = 0;
                         table_gfn = gw->table_gfn[level - 2];
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 05d571f6f196..7fa89c39c64f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1562,7 +1562,7 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
 
         r = -ENOMEM;
         size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
-        entries = vmalloc(size);
+        entries = kmalloc(size, GFP_KERNEL);
         if (!entries)
                 goto out;
 
@@ -1581,7 +1581,7 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
         r = n;
 
 out_free:
-        vfree(entries);
+        kfree(entries);
 out:
         return r;
 }
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 6fdb3ec30c31..55253095be84 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -184,6 +184,7 @@ static void __init pcibios_allocate_resources(int pass)
                                         idx, r, disabled, pass);
                                 if (pci_claim_resource(dev, idx) < 0) {
                                         /* We'll assign a new address later */
+                                        dev->fw_addr[idx] = r->start;
                                         r->end -= r->start;
                                         r->start = 0;
                                 }
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c
index 7ef3a2735df3..cb29191cee58 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/mrst.c
@@ -66,8 +66,9 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn)
                                           devfn, pos, 4, &pcie_cap))
                         return 0;
 
-                if (pcie_cap == 0xffffffff)
-                        return 0;
+                if (PCI_EXT_CAP_ID(pcie_cap) == 0x0000 ||
+                        PCI_EXT_CAP_ID(pcie_cap) == 0xffff)
+                        break;
 
                 if (PCI_EXT_CAP_ID(pcie_cap) == PCI_EXT_CAP_ID_VNDR) {
                         raw_pci_ext_ops->read(pci_domain_nr(bus), bus->number,
@@ -76,7 +77,7 @@ static int fixed_bar_cap(struct pci_bus *bus, unsigned int devfn)
                                 return pos;
                 }
 
-                pos = pcie_cap >> 20;
+                pos = PCI_EXT_CAP_NEXT(pcie_cap);
         }
 
         return 0;