Merge branch 'x86/urgent' into x86-mm

Merge reason: Pick up the following two fix commits.

  2be19102b7: x86, NUMA: Fix empty memblk detection in numa_cleanup_meminfo()
  765af22da8: x86-32, NUMA: Fix ACPI NUMA init broken by recent x86-64 change

Scheduled NUMA init 32/64bit unification changes depend on these.

Signed-off-by: Tejun Heo <tj@kernel.org>

30 files changed, 236 insertions, 132 deletions

diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index cae3feb1035e..db75d07c3645 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -91,7 +91,7 @@ static int detect_memory_e801(void)
 	if (oreg.ax > 15*1024) {
 		return -1;	/* Bogus! */
 	} else if (oreg.ax == 15*1024) {
-		boot_params.alt_mem_k = (oreg.dx << 6) + oreg.ax;
+		boot_params.alt_mem_k = (oreg.bx << 6) + oreg.ax;
 	} else {
 		/*
 		 * This ignores memory above 16MB if we have a memory
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 43085bfc99c3..156cd5d18d2a 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -66,7 +66,7 @@ static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
 	 * Don't enable translation but enable GART IO and CPU accesses.
 	 * Also, set DISTLBWALKPRB since GART tables memory is UC.
 	 */
-	ctl = DISTLBWALKPRB | order << 1;
+	ctl = order << 1;
 
 	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
@@ -75,17 +75,17 @@ static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
 	u32 tmp, ctl;
 
-        /* address of the mappings table */
-        addr >>= 12;
-        tmp = (u32) addr<<4;
-        tmp &= ~0xf;
-        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
-
-        /* Enable GART translation for this hammer. */
-        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
-        ctl |= GARTEN;
-        ctl &= ~(DISGARTCPU | DISGARTIO);
-        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+	/* address of the mappings table */
+	addr >>= 12;
+	tmp = (u32) addr<<4;
+	tmp &= ~0xf;
+	pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+	/* Enable GART translation for this hammer. */
+	pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+	ctl |= GARTEN | DISTLBWALKPRB;
+	ctl &= ~(DISGARTCPU | DISGARTIO);
+	pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
 }
 
 static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index ef328901c802..c9e09ea05644 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -237,7 +237,7 @@ static inline void fpu_save_init(struct fpu *fpu)
 	} else if (use_fxsr()) {
 		fpu_fxsave(fpu);
 	} else {
-		asm volatile("fsave %[fx]; fwait"
+		asm volatile("fnsave %[fx]; fwait"
 			     : [fx] "=m" (fpu->state->fsave));
 		return;
 	}
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index c4bd267dfc50..a97a240f67f3 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -150,7 +150,7 @@ void setup_IO_APIC_irq_extra(u32 gsi);
 extern void ioapic_and_gsi_init(void);
 extern void ioapic_insert_resources(void);
 
-int io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr);
+int io_apic_setup_irq_pin_once(unsigned int irq, int node, struct io_apic_irq_attr *attr);
 
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index fd5a1f365c95..3cce71413d0b 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -96,11 +96,15 @@
 #define MSR_IA32_MC0_ADDR		0x00000402
 #define MSR_IA32_MC0_MISC		0x00000403
 
+#define MSR_AMD64_MC0_MASK		0xc0010044
+
 #define MSR_IA32_MCx_CTL(x)		(MSR_IA32_MC0_CTL + 4*(x))
 #define MSR_IA32_MCx_STATUS(x)		(MSR_IA32_MC0_STATUS + 4*(x))
 #define MSR_IA32_MCx_ADDR(x)		(MSR_IA32_MC0_ADDR + 4*(x))
 #define MSR_IA32_MCx_MISC(x)		(MSR_IA32_MC0_MISC + 4*(x))
 
+#define MSR_AMD64_MCx_MASK(x)		(MSR_AMD64_MC0_MASK + (x))
+
 /* These are consecutive and not in the normal 4er MCE bank block */
 #define MSR_IA32_MC0_CTL2		0x00000280
 #define MSR_IA32_MCx_CTL2(x)		(MSR_IA32_MC0_CTL2 + (x))
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 3d4dab43c994..a50fc9f493b3 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -51,7 +51,7 @@ static inline void numa_remove_cpu(int cpu)		{ }
 #endif	/* CONFIG_NUMA */
 
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable);
+void debug_cpumask_set_cpu(int cpu, int node, bool enable);
 #endif
 
 #endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 86d1ad4962a7..73fb469908c6 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -499,7 +499,7 @@ out:
 		 * Don't enable translation yet but enable GART IO and CPU
 		 * accesses and set DISTLBWALKPRB since GART table memory is UC.
 		 */
-		u32 ctl = DISTLBWALKPRB | aper_order << 1;
+		u32 ctl = aper_order << 1;
 
 		bus = amd_nb_bus_dev_ranges[i].bus;
 		dev_base = amd_nb_bus_dev_ranges[i].dev_base;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 68df09bba92e..45fd33d1fd3a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -128,8 +128,8 @@ static int __init parse_noapic(char *str)
 }
 early_param("noapic", parse_noapic);
 
-static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
-				      struct io_apic_irq_attr *attr);
+static int io_apic_setup_irq_pin(unsigned int irq, int node,
+				 struct io_apic_irq_attr *attr);
 
 /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
 void mp_save_irq(struct mpc_intsrc *m)
@@ -3570,7 +3570,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 }
 #endif /* CONFIG_HT_IRQ */
 
-int
+static int
 io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 {
 	struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node);
@@ -3585,8 +3585,8 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 	return ret;
 }
 
-static int io_apic_setup_irq_pin_once(unsigned int irq, int node,
-				      struct io_apic_irq_attr *attr)
+int io_apic_setup_irq_pin_once(unsigned int irq, int node,
+			       struct io_apic_irq_attr *attr)
 {
 	unsigned int id = attr->ioapic, pin = attr->ioapic_pin;
 	int ret;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 0b4be431c620..adee12e0da1f 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -228,6 +228,7 @@
 #include <linux/kthread.h>
 #include <linux/jiffies.h>
 #include <linux/acpi.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -1238,6 +1239,7 @@ static int suspend(int vetoable)
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_SUSPEND);
+	syscore_suspend();
 
 	local_irq_enable();
 
@@ -1255,6 +1257,7 @@ static int suspend(int vetoable)
 		apm_error("suspend", err);
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
 
+	syscore_resume();
 	sysdev_resume();
 	local_irq_enable();
 
@@ -1280,6 +1283,7 @@ static void standby(void)
 
 	local_irq_disable();
 	sysdev_suspend(PMSG_SUSPEND);
+	syscore_suspend();
 	local_irq_enable();
 
 	err = set_system_power_state(APM_STATE_STANDBY);
@@ -1287,6 +1291,7 @@ static void standby(void)
 		apm_error("standby", err);
 
 	local_irq_disable();
+	syscore_resume();
 	sysdev_resume();
 	local_irq_enable();
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3ecece0217ef..bb9eb29a52dd 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -615,6 +615,25 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	/* As a rule processors have APIC timer running in deep C states */
 	if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
 		set_cpu_cap(c, X86_FEATURE_ARAT);
+
+	/*
+	 * Disable GART TLB Walk Errors on Fam10h. We do this here
+	 * because this is always needed when GART is enabled, even in a
+	 * kernel which has no MCE support built in.
+	 */
+	if (c->x86 == 0x10) {
+		/*
+		 * BIOS should disable GartTlbWlk Errors themself. If
+		 * it doesn't do it here as suggested by the BKDG.
+		 *
+		 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
+		 */
+		u64 mask;
+
+		rdmsrl(MSR_AMD64_MCx_MASK(4), mask);
+		mask |= (1 << 10);
+		wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
+	}
 }
 
 #ifdef CONFIG_X86_32
@@ -679,7 +698,7 @@ cpu_dev_register(amd_cpu_dev);
  */
 
 const int amd_erratum_400[] =
-	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf),
 			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
 EXPORT_SYMBOL_GPL(amd_erratum_400);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index eed3673a8656..e638689279d3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -586,8 +586,12 @@ static int x86_setup_perfctr(struct perf_event *event)
 			return -EOPNOTSUPP;
 	}
 
+	/*
+	 * Do not allow config1 (extended registers) to propagate,
+	 * there's no sane user-space generalization yet:
+	 */
 	if (attr->type == PERF_TYPE_RAW)
-		return x86_pmu_extra_regs(event->attr.config, event);
+		return 0;
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, event);
@@ -609,8 +613,8 @@ static int x86_setup_perfctr(struct perf_event *event)
 	/*
 	 * Branch tracing:
 	 */
-	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
-	    (hwc->sample_period == 1)) {
+	if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS &&
+	    !attr->freq && hwc->sample_period == 1) {
 		/* BTS is not supported by this architecture. */
 		if (!x86_pmu.bts_active)
 			return -EOPNOTSUPP;
@@ -1284,6 +1288,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
+	/*
+	 * Some chipsets need to unmask the LVTPC in a particular spot
+	 * inside the nmi handler.  As a result, the unmasking was pushed
+	 * into all the nmi handlers.
+	 *
+	 * This generic handler doesn't seem to have any issues where the
+	 * unmasking occurs so it was left at the top.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		if (!test_bit(idx, cpuc->active_mask)) {
 			/*
@@ -1370,8 +1384,6 @@ perf_event_nmi_handler(struct notifier_block *self,
 		return NOTIFY_DONE;
 	}
 
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-
 	handled = x86_pmu.handle_irq(args->regs);
 	if (!handled)
 		return NOTIFY_DONE;
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 461f62bbd774..cf4e369cea67 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -8,7 +8,7 @@ static __initconst const u64 amd_hw_cache_event_ids
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
-		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
+		[ C(RESULT_MISS)   ] = 0x0141, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
@@ -427,7 +427,9 @@ static __initconst const struct x86_pmu amd_pmu = {
  *
  * Exceptions:
  *
+ * 0x000	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x003	FP	PERF_CTL[3]
+ * 0x004	FP	PERF_CTL[3], PERF_CTL[5:3] (*)
  * 0x00B	FP	PERF_CTL[3]
  * 0x00D	FP	PERF_CTL[3]
  * 0x023	DE	PERF_CTL[2:0]
@@ -448,6 +450,8 @@ static __initconst const struct x86_pmu amd_pmu = {
  * 0x0DF	LS	PERF_CTL[5:0]
  * 0x1D6	EX	PERF_CTL[5:0]
  * 0x1D8	EX	PERF_CTL[5:0]
+ *
+ * (*) depending on the umask all FPU counters may be used
  */
 
 static struct event_constraint amd_f15_PMC0  = EVENT_CONSTRAINT(0, 0x01, 0);
@@ -460,18 +464,28 @@ static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
 static struct event_constraint *
 amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event)
 {
-	unsigned int event_code = amd_get_event_code(&event->hw);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int event_code = amd_get_event_code(hwc);
 
 	switch (event_code & AMD_EVENT_TYPE_MASK) {
 	case AMD_EVENT_FP:
 		switch (event_code) {
+		case 0x000:
+			if (!(hwc->config & 0x0000F000ULL))
+				break;
+			if (!(hwc->config & 0x00000F00ULL))
+				break;
+			return &amd_f15_PMC3;
+		case 0x004:
+			if (hweight_long(hwc->config & ARCH_PERFMON_EVENTSEL_UMASK) <= 1)
+				break;
+			return &amd_f15_PMC3;
 		case 0x003:
 		case 0x00B:
 		case 0x00D:
 			return &amd_f15_PMC3;
-		default:
-			return &amd_f15_PMC53;
 		}
+		return &amd_f15_PMC53;
 	case AMD_EVENT_LS:
 	case AMD_EVENT_DC:
 	case AMD_EVENT_EX_LS:
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8fc2b2cee1da..e61539b07d2c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -25,7 +25,7 @@ struct intel_percore {
 /*
  * Intel PerfMon, used on Core and later.
  */
-static const u64 intel_perfmon_event_map[] =
+static u64 intel_perfmon_event_map[PERF_COUNT_HW_MAX] __read_mostly =
 {
   [PERF_COUNT_HW_CPU_CYCLES]		= 0x003c,
   [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
@@ -391,12 +391,12 @@ static __initconst const u64 nehalem_hw_cache_event_ids
 {
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f40, /* L1D_CACHE_LD.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0140, /* L1D_CACHE_LD.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS       */
+		[ C(RESULT_MISS)   ] = 0x0151, /* L1D.REPL                     */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0f41, /* L1D_CACHE_ST.MESI            */
-		[ C(RESULT_MISS)   ] = 0x0141, /* L1D_CACHE_ST.I_STATE         */
+		[ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES      */
+		[ C(RESULT_MISS)   ] = 0x0251, /* L1D.M_REPL                   */
 	},
 	[ C(OP_PREFETCH) ] = {
 		[ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS        */
@@ -933,6 +933,16 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
+	/*
+	 * Some chipsets need to unmask the LVTPC in a particular spot
+	 * inside the nmi handler.  As a result, the unmasking was pushed
+	 * into all the nmi handlers.
+	 *
+	 * This handler doesn't seem to have any issues with the unmasking
+	 * so it was left at the top.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+
 	intel_pmu_disable_all();
 	handled = intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
@@ -998,6 +1008,9 @@ intel_bts_constraints(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
 
+	if (event->attr.freq)
+		return NULL;
+
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
@@ -1305,7 +1318,7 @@ static void intel_clovertown_quirks(void)
 	 * AJ106 could possibly be worked around by not allowing LBR
 	 *       usage from PEBS, including the fixup.
 	 * AJ68  could possibly be worked around by always programming
-	 * 	 a pebs_event_reset[0] value and coping with the lost events.
+	 *	 a pebs_event_reset[0] value and coping with the lost events.
 	 *
 	 * But taken together it might just make sense to not enable PEBS on
 	 * these chips.
@@ -1409,6 +1422,18 @@ static __init int intel_pmu_init(void)
 		x86_pmu.percore_constraints = intel_nehalem_percore_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
+
+		if (ebx & 0x40) {
+			/*
+			 * Erratum AAJ80 detected, we work it around by using
+			 * the BR_MISP_EXEC.ANY event. This will over-count
+			 * branch-misses, but it's still much better than the
+			 * architectural event which is often completely bogus:
+			 */
+			intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+
+			pr_cont("erratum AAJ80 worked around, ");
+		}
 		pr_cont("Nehalem events, ");
 		break;
 
@@ -1425,6 +1450,7 @@ static __init int intel_pmu_init(void)
 
 	case 37: /* 32 nm nehalem, "Clarkdale" */
 	case 44: /* 32 nm nehalem, "Gulftown" */
+	case 47: /* 32 nm Xeon E7 */
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index c2520e178d32..e93fcd55fae1 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -947,14 +947,23 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 		if (perf_event_overflow(event, 1, &data, regs))
-			p4_pmu_disable_event(event);
+			x86_pmu_stop(event, 0);
 	}
 
-	if (handled) {
-		/* p4 quirk: unmask it again */
-		apic_write(APIC_LVTPC, apic_read(APIC_LVTPC) & ~APIC_LVT_MASKED);
+	if (handled)
 		inc_irq_stat(apic_perf_irqs);
-	}
+
+	/*
+	 * When dealing with the unmasking of the LVTPC on P4 perf hw, it has
+	 * been observed that the OVF bit flag has to be cleared first _before_
+	 * the LVTPC can be unmasked.
+	 *
+	 * The reason is the NMI line will continue to be asserted while the OVF
+	 * bit is set.  This causes a second NMI to generate if the LVTPC is
+	 * unmasked before the OVF bit is cleared, leading to unknown NMI
+	 * messages.
+	 */
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
 	return handled;
 }
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 706a9fb46a58..e90f08458e6b 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -391,7 +391,7 @@ static int ioapic_xlate(struct irq_domain *id, const u32 *intspec, u32 intsize,
 
 	set_io_apic_irq_attr(&attr, idx, line, it->trigger, it->polarity);
 
-	return io_apic_setup_irq_pin(*out_hwirq, cpu_to_node(0), &attr);
+	return io_apic_setup_irq_pin_once(*out_hwirq, cpu_to_node(0), &attr);
 }
 
 static void __init ioapic_add_ofnode(struct device_node *np)
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 82ada01625b9..b117efd24f71 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -81,6 +81,9 @@ static u32 gart_unmapped_entry;
 #define AGPEXTERN
 #endif
 
+/* GART can only remap to physical addresses < 1TB */
+#define GART_MAX_PHYS_ADDR	(1ULL << 40)
+
 /* backdoor interface to AGP driver */
 AGPEXTERN int agp_memory_reserved;
 AGPEXTERN __u32 *agp_gatt_table;
@@ -212,9 +215,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 				size_t size, int dir, unsigned long align_mask)
 {
 	unsigned long npages = iommu_num_pages(phys_mem, size, PAGE_SIZE);
-	unsigned long iommu_page = alloc_iommu(dev, npages, align_mask);
+	unsigned long iommu_page;
 	int i;
 
+	if (unlikely(phys_mem + size > GART_MAX_PHYS_ADDR))
+		return bad_dma_addr;
+
+	iommu_page = alloc_iommu(dev, npages, align_mask);
 	if (iommu_page == -1) {
 		if (!nonforced_iommu(dev, phys_mem, size))
 			return phys_mem;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5a0484a95ad6..4be9b398470e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -976,6 +976,11 @@ void __init setup_arch(char **cmdline_p)
 	paging_init();
 	x86_init.paging.pagetable_setup_done(swapper_pg_dir);
 
+	if (boot_cpu_data.cpuid_level >= 0) {
+		/* A CPU has %cr4 if and only if it has CPUID */
+		mmu_cr4_features = read_cr4();
+	}
+
 #ifdef CONFIG_X86_32
 	/* sync back kernel address range */
 	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 58f517b59645..934b4c6b0bf9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2395,9 +2395,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		int i;
 
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
-		for (i = 1; *nent < maxnent; ++i) {
-			if (entry[i - 1].eax == 0 && i != 2)
-				break;
+		for (i = 1; *nent < maxnent && i < 64; ++i) {
+			if (entry[i].eax == 0)
+				continue;
 			do_cpuid_1_ent(&entry[i], function, i);
 			entry[i].flags |=
 			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
@@ -4958,12 +4958,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 			best = e;
 			break;
 		}
-		/*
-		 * Both basic or both extended?
-		 */
-		if (((e->function ^ function) & 0x80000000) == 0)
-			if (!best || e->function > best->function)
-				best = e;
 	}
 	return best;
 }
@@ -4983,6 +4977,27 @@ not_found:
 	return 36;
 }
 
+/*
+ * If no match is found, check whether we exceed the vCPU's limit
+ * and return the content of the highest valid _standard_ leaf instead.
+ * This is to satisfy the CPUID specification.
+ */
+static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
+                                                  u32 function, u32 index)
+{
+	struct kvm_cpuid_entry2 *maxlevel;
+
+	maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+	if (!maxlevel || maxlevel->eax >= function)
+		return NULL;
+	if (function & 0x80000000) {
+		maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
+		if (!maxlevel)
+			return NULL;
+	}
+	return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+}
+
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 {
 	u32 function, index;
@@ -4995,6 +5010,10 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 	kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
 	kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
 	best = kvm_find_cpuid_entry(vcpu, function, index);
+
+	if (!best)
+		best = check_cpuid_limit(vcpu, function, index);
+
 	if (best) {
 		kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax);
 		kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 9559d360fde7..745258dfc4dc 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -213,53 +213,48 @@ int early_cpu_to_node(int cpu)
 	return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-struct cpumask __cpuinit *debug_cpumask_set_cpu(int cpu, int enable)
+void debug_cpumask_set_cpu(int cpu, int node, bool enable)
 {
-	int node = early_cpu_to_node(cpu);
 	struct cpumask *mask;
 	char buf[64];
 
 	if (node == NUMA_NO_NODE) {
 		/* early_cpu_to_node() already emits a warning and trace */
-		return NULL;
+		return;
 	}
 	mask = node_to_cpumask_map[node];
 	if (!mask) {
 		pr_err("node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
-		return NULL;
+		return;
 	}
 
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+
 	cpulist_scnprintf(buf, sizeof(buf), mask);
 	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
 		enable ? "numa_add_cpu" : "numa_remove_cpu",
 		cpu, node, buf);
-	return mask;
+	return;
 }
 
 # ifndef CONFIG_NUMA_EMU
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-
-	mask = debug_cpumask_set_cpu(cpu, enable);
-	if (!mask)
-		return;
-
-	if (enable)
-		cpumask_set_cpu(cpu, mask);
-	else
-		cpumask_clear_cpu(cpu, mask);
+	debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
 }
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 # endif	/* !CONFIG_NUMA_EMU */
 
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 13f5b068e8c2..a96767cb068f 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -191,7 +191,7 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 		bi->end = min(bi->end, high);
 
 		/* and there's no empty block */
-		if (bi->start == bi->end) {
+		if (bi->start >= bi->end) {
 			numa_remove_memblk_from(i--, mi);
 			continue;
 		}
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index ad091e4cff17..de84cc140379 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -454,10 +454,9 @@ void __cpuinit numa_remove_cpu(int cpu)
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
 }
 #else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
-static void __cpuinit numa_set_cpumask(int cpu, int enable)
+static void __cpuinit numa_set_cpumask(int cpu, bool enable)
 {
-	struct cpumask *mask;
-	int nid, physnid, i;
+	int nid, physnid;
 
 	nid = early_cpu_to_node(cpu);
 	if (nid == NUMA_NO_NODE) {
@@ -467,28 +466,21 @@ static void __cpuinit numa_set_cpumask(int cpu, int enable)
 
 	physnid = emu_nid_to_phys[nid];
 
-	for_each_online_node(i) {
+	for_each_online_node(nid) {
 		if (emu_nid_to_phys[nid] != physnid)
 			continue;
 
-		mask = debug_cpumask_set_cpu(cpu, enable);
-		if (!mask)
-			return;
-
-		if (enable)
-			cpumask_set_cpu(cpu, mask);
-		else
-			cpumask_clear_cpu(cpu, mask);
+		debug_cpumask_set_cpu(cpu, nid, enable);
 	}
 }
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 1);
+	numa_set_cpumask(cpu, true);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	numa_set_cpumask(cpu, 0);
+	numa_set_cpumask(cpu, false);
 }
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 1b9e82c96dc5..ae20046a9e98 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -211,10 +211,12 @@ int __init get_memcfg_from_srat(void)
 {
 	int i, j, nid;
 
-
 	if (srat_disabled())
 		goto out_fail;
 
+	if (acpi_numa_init() < 0)
+		goto out_fail;
+
 	if (num_memory_chunks == 0) {
 		printk(KERN_DEBUG
 			 "could not find any ACPI SRAT memory areas.\n");
diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts
index dc701ea58546..e70be38ce039 100644
--- a/arch/x86/platform/ce4100/falconfalls.dts
+++ b/arch/x86/platform/ce4100/falconfalls.dts
@@ -74,6 +74,7 @@
 				compatible = "intel,ce4100-pci", "pci";
 				device_type = "pci";
 				bus-range = <1 1>;
+				reg = <0x0800 0x0 0x0 0x0 0x0>;
 				ranges = <0x2000000 0 0xdffe0000 0x2000000 0 0xdffe0000 0 0x1000>;
 
 				interrupt-parent = <&ioapic2>;
@@ -346,7 +347,7 @@
 						   "pciclass0c03";
 
 					reg = <0x16800 0x0 0x0 0x0 0x0>;
-					interrupts = <22 3>;
+					interrupts = <22 1>;
 				};
 
 				usb@d,1 {
@@ -356,7 +357,7 @@
 						   "pciclass0c03";
 
 					reg = <0x16900 0x0 0x0 0x0 0x0>;
-					interrupts = <22 3>;
+					interrupts = <22 1>;
 				};
 
 				sata@e,0 {
@@ -366,7 +367,7 @@
 						   "pciclass0106";
 
 					reg = <0x17000 0x0 0x0 0x0 0x0>;
-					interrupts = <23 3>;
+					interrupts = <23 1>;
 				};
 
 				flash@f,0 {
@@ -412,6 +413,7 @@
 				#address-cells = <2>;
 				#size-cells = <1>;
 				compatible = "isa";
+				reg = <0xf800 0x0 0x0 0x0 0x0>;
 				ranges = <1 0 0 0 0 0x100>;
 
 				rtc@70 {
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 5c0207bf959b..275dbc19e2cf 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -97,11 +97,11 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table)
 			pentry->freq_hz, pentry->irq);
 			if (!pentry->irq)
 				continue;
-			mp_irq.type = MP_IOAPIC;
+			mp_irq.type = MP_INTSRC;
 			mp_irq.irqtype = mp_INT;
 /* triggering mode edge bit 2-3, active high polarity bit 0-1 */
 			mp_irq.irqflag = 5;
-			mp_irq.srcbus = 0;
+			mp_irq.srcbus = MP_BUS_ISA;
 			mp_irq.srcbusirq = pentry->irq;	/* IRQ */
 			mp_irq.dstapic = MP_APIC_ALL;
 			mp_irq.dstirq = pentry->irq;
@@ -168,10 +168,10 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 	for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) {
 		pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n",
 			totallen, (u32)pentry->phys_addr, pentry->irq);
-		mp_irq.type = MP_IOAPIC;
+		mp_irq.type = MP_INTSRC;
 		mp_irq.irqtype = mp_INT;
 		mp_irq.irqflag = 0xf;	/* level trigger and active low */
-		mp_irq.srcbus = 0;
+		mp_irq.srcbus = MP_BUS_ISA;
 		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
 		mp_irq.dstapic = MP_APIC_ALL;
 		mp_irq.dstirq = pentry->irq;
@@ -282,7 +282,7 @@ void __init x86_mrst_early_setup(void)
 	/* Avoid searching for BIOS MP tables */
 	x86_init.mpparse.find_smp_config = x86_init_noop;
 	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
-
+	set_bit(MP_BUS_ISA, mp_bus_not_pci);
 }
 
 /*
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 04cf645feb92..73d70d65e76e 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -100,9 +100,11 @@ int vrtc_set_mmss(unsigned long nowtime)
 
 void __init mrst_rtc_init(void)
 {
-	unsigned long vrtc_paddr = sfi_mrtc_array[0].phys_addr;
+	unsigned long vrtc_paddr;
 
 	sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
+
+	vrtc_paddr = sfi_mrtc_array[0].phys_addr;
 	if (!sfi_mrtc_num || !vrtc_paddr)
 		return;
 
diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c
index fe4cf8294878..c7abf13a213f 100644
--- a/arch/x86/platform/visws/visws_quirks.c
+++ b/arch/x86/platform/visws/visws_quirks.c
@@ -471,15 +471,7 @@ static unsigned int startup_piix4_master_irq(struct irq_data *data)
 {
 	legacy_pic->init(0);
 	enable_cobalt_irq(data);
-}
-
-static void end_piix4_master_irq(struct irq_data *data)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cobalt_lock, flags);
-	enable_cobalt_irq(data);
-	spin_unlock_irqrestore(&cobalt_lock, flags);
+	return 0;
 }
 
 static struct irq_chip piix4_master_irq_type = {
@@ -492,7 +484,7 @@ static void pii4_mask(struct irq_data *data) { }
 
 static struct irq_chip piix4_virtual_irq_type = {
 	.name		= "PIIX4-virtual",
-	.mask		= pii4_mask,
+	.irq_mask	= pii4_mask,
 };
 
 /*
@@ -580,9 +572,9 @@ static struct irqaction cascade_action = {
 
 static inline void set_piix4_virtual_irq_type(void)
 {
-	piix4_virtual_irq_type.enable =	i8259A_chip.unmask;
-	piix4_virtual_irq_type.disable = i8259A_chip.mask;
-	piix4_virtual_irq_type.unmask =	i8259A_chip.unmask;
+	piix4_virtual_irq_type.irq_enable = i8259A_chip.irq_unmask;
+	piix4_virtual_irq_type.irq_disable = i8259A_chip.irq_mask;
+	piix4_virtual_irq_type.irq_unmask = i8259A_chip.irq_unmask;
 }
 
 static void __init visws_pre_intr_init(void)
@@ -599,7 +591,7 @@ static void __init visws_pre_intr_init(void)
 		else if (i == CO_IRQ_IDE0)
 			chip = &cobalt_irq_type;
 		else if (i == CO_IRQ_IDE1)
-			>chip = &cobalt_irq_type;
+			chip = &cobalt_irq_type;
 		else if (i == CO_IRQ_8259)
 			chip = &piix4_master_irq_type;
 		else if (i < CO_IRQ_APIC0)
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 1c7121ba18ff..5cc821cb2e09 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -39,6 +39,7 @@ config XEN_MAX_DOMAIN_MEMORY
 config XEN_SAVE_RESTORE
        bool
        depends on XEN
+       select HIBERNATE_CALLBACKS
        default y
 
 config XEN_DEBUG_FS
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 49dbd78ec3cb..e3c6a06cf725 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -238,6 +238,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 static __init void xen_init_cpuid_mask(void)
 {
 	unsigned int ax, bx, cx, dx;
+	unsigned int xsave_mask;
 
 	cpuid_leaf1_edx_mask =
 		~((1 << X86_FEATURE_MCE)  |  /* disable MCE */
@@ -249,24 +250,16 @@ static __init void xen_init_cpuid_mask(void)
 		cpuid_leaf1_edx_mask &=
 			~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
 			  (1 << X86_FEATURE_ACPI));  /* disable ACPI */
-
 	ax = 1;
-	cx = 0;
 	xen_cpuid(&ax, &bx, &cx, &dx);
 
-	/* cpuid claims we support xsave; try enabling it to see what happens */
-	if (cx & (1 << (X86_FEATURE_XSAVE % 32))) {
-		unsigned long cr4;
-
-		set_in_cr4(X86_CR4_OSXSAVE);
-		
-		cr4 = read_cr4();
+	xsave_mask =
+		(1 << (X86_FEATURE_XSAVE % 32)) |
+		(1 << (X86_FEATURE_OSXSAVE % 32));
 
-		if ((cr4 & X86_CR4_OSXSAVE) == 0)
-			cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32));
-
-		clear_in_cr4(X86_CR4_OSXSAVE);
-	}
+	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
+	if ((cx & xsave_mask) != xsave_mask)
+		cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
 }
 
 static void xen_set_debugreg(int reg, unsigned long val)
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index c82df6c9c0f0..aef7af92b28b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -565,13 +565,13 @@ pte_t xen_make_pte_debug(pteval_t pte)
 	if (io_page &&
 	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
 		other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
-		WARN(addr != other_addr,
+		WARN_ONCE(addr != other_addr,
 			"0x%lx is using VM_IO, but it is 0x%lx!\n",
 			(unsigned long)addr, (unsigned long)other_addr);
 	} else {
 		pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
 		other_addr = (_pte.pte & PTE_PFN_MASK);
-		WARN((addr == other_addr) && (!io_page) && (!iomap_set),
+		WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
 			"0x%lx is missing VM_IO (and wasn't fixed)!\n",
 			(unsigned long)addr);
 	}
@@ -1473,16 +1473,20 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 #endif
 }
 
+#ifdef CONFIG_X86_32
 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 {
-	unsigned long pfn = pte_pfn(pte);
-
-#ifdef CONFIG_X86_32
 	/* If there's an existing pte, then don't allow _PAGE_RW to be set */
 	if (pte_val_ma(*ptep) & _PAGE_PRESENT)
 		pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
 			       pte_val_ma(pte));
-#endif
+
+	return pte;
+}
+#else /* CONFIG_X86_64 */
+static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
 
 	/*
 	 * If the new pfn is within the range of the newly allocated
@@ -1497,6 +1501,7 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
 
 	return pte;
 }
+#endif /* CONFIG_X86_64 */
 
 /* Init-time set_pte while constructing initial pagetables, which
    doesn't allow RO pagetable pages to be remapped RW */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index fa0269a99377..90bac0aac3a5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -227,7 +227,7 @@ char * __init xen_memory_setup(void)
 
 	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
-	xen_extra_mem_start = mem_end;
+	xen_extra_mem_start = max((1ULL << 32), mem_end);
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end;