Merge commit 'v2.6.30-rc5' into core/iommu

Merge reason: core/iommu was on an .30-rc1 base,
              update it to .30-rc5 to refresh.

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

36 files changed, 348 insertions, 203 deletions

diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 42c33cebf00..8c0be0902da 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -49,10 +49,10 @@
 #define IVHD_DEV_EXT_SELECT             0x46
 #define IVHD_DEV_EXT_SELECT_RANGE       0x47
 
-#define IVHD_FLAG_HT_TUN_EN             0x00
-#define IVHD_FLAG_PASSPW_EN             0x01
-#define IVHD_FLAG_RESPASSPW_EN          0x02
-#define IVHD_FLAG_ISOC_EN               0x03
+#define IVHD_FLAG_HT_TUN_EN_MASK        0x01
+#define IVHD_FLAG_PASSPW_EN_MASK        0x02
+#define IVHD_FLAG_RESPASSPW_EN_MASK     0x04
+#define IVHD_FLAG_ISOC_EN_MASK          0x08
 
 #define IVMD_FLAG_EXCL_RANGE            0x08
 #define IVMD_FLAG_UNITY_MAP             0x01
@@ -569,19 +569,19 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	 * First set the recommended feature enable bits from ACPI
 	 * into the IOMMU control registers
 	 */
-	h->flags & IVHD_FLAG_HT_TUN_EN ?
+	h->flags & IVHD_FLAG_HT_TUN_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
 		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);
 
-	h->flags & IVHD_FLAG_PASSPW_EN ?
+	h->flags & IVHD_FLAG_PASSPW_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
 		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);
 
-	h->flags & IVHD_FLAG_RESPASSPW_EN ?
+	h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
 		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);
 
-	h->flags & IVHD_FLAG_ISOC_EN ?
+	h->flags & IVHD_FLAG_ISOC_EN_MASK ?
 		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
 		iommu_feature_disable(iommu, CONTROL_ISOC_EN);
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 098ec84b8c0..f2870920f24 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -431,6 +431,12 @@ static void __cpuinit setup_APIC_timer(void)
 {
 	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 
+	if (cpu_has(&current_cpu_data, X86_FEATURE_ARAT)) {
+		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
+		/* Make LAPIC timer preferrable over percpu HPET */
+		lapic_clockevent.rating = 150;
+	}
+
 	memcpy(levt, &lapic_clockevent, sizeof(*levt));
 	levt->cpumask = cpumask_of(smp_processor_id());
 
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 0014714ea97..306e5e88fb6 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -212,7 +212,7 @@ struct apic apic_flat =  {
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
 	.wait_for_init_deassert		= NULL,
 	.smp_callin_clear_local_apic	= NULL,
-	.inquire_remote_apic		= NULL,
+	.inquire_remote_apic		= default_inquire_remote_apic,
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
@@ -362,7 +362,7 @@ struct apic apic_physflat =  {
 	.trampoline_phys_high		= DEFAULT_TRAMPOLINE_PHYS_HIGH,
 	.wait_for_init_deassert		= NULL,
 	.smp_callin_clear_local_apic	= NULL,
-	.inquire_remote_apic		= NULL,
+	.inquire_remote_apic		= default_inquire_remote_apic,
 
 	.read				= native_apic_mem_read,
 	.write				= native_apic_mem_write,
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 767fe7e46d6..30da617d18e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2524,7 +2524,6 @@ static void irq_complete_move(struct irq_desc **descp)
 static inline void irq_complete_move(struct irq_desc **descp) {}
 #endif
 
-#ifdef CONFIG_X86_X2APIC
 static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 {
 	int apic, pin;
@@ -2558,6 +2557,7 @@ eoi_ioapic_irq(struct irq_desc *desc)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
+#ifdef CONFIG_X86_X2APIC
 static void ack_x2apic_level(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -2634,6 +2634,9 @@ static void ack_apic_level(unsigned int irq)
 	 */
 	ack_APIC_irq();
 
+	if (irq_remapped(irq))
+		eoi_ioapic_irq(desc);
+
 	/* Now we can move and renable the irq */
 	if (unlikely(do_unmask_irq)) {
 		/* Only migrate the irq if the ack has been received.
@@ -3667,12 +3670,14 @@ int arch_setup_hpet_msi(unsigned int irq)
 {
 	int ret;
 	struct msi_msg msg;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	ret = msi_compose_msg(NULL, irq, &msg);
 	if (ret < 0)
 		return ret;
 
 	hpet_msi_write(irq, &msg);
+	desc->status |= IRQ_MOVE_PCNTXT;
 	set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq,
 		"edge");
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index d6bd6240715..ce4fbfa315a 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -138,7 +138,7 @@ int __init check_nmi_watchdog(void)
 	if (!prev_nmi_count)
 		goto error;
 
-	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL);
+	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL|__GFP_ZERO);
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
 #ifdef CONFIG_SMP
@@ -414,7 +414,8 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		touched = 1;
 	}
 
-	if (cpumask_test_cpu(cpu, backtrace_mask)) {
+	/* We can be called before check_nmi_watchdog, hence NULL check. */
+	if (backtrace_mask != NULL && cpumask_test_cpu(cpu, backtrace_mask)) {
 		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
 
 		spin_lock(&lock);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1248318436e..2bda6935297 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -19,6 +19,7 @@
 #include <linux/timer.h>
 #include <linux/cpu.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
@@ -34,6 +35,17 @@ DEFINE_PER_CPU(int, x2apic_extra_bits);
 
 static enum uv_system_type uv_system_type;
 
+static int early_get_nodeid(void)
+{
+	union uvh_node_id_u node_id;
+	unsigned long *mmr;
+
+	mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
+	node_id.v = *mmr;
+	early_iounmap(mmr, sizeof(*mmr));
+	return node_id.s.node_id;
+}
+
 static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (!strcmp(oem_id, "SGI")) {
@@ -42,6 +54,8 @@ static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 		else if (!strcmp(oem_table_id, "UVX"))
 			uv_system_type = UV_X2APIC;
 		else if (!strcmp(oem_table_id, "UVH")) {
+			__get_cpu_var(x2apic_extra_bits) =
+				early_get_nodeid() << (UV_APIC_PNODE_SHIFT - 1);
 			uv_system_type = UV_NON_UNIQUE_APIC;
 			return 1;
 		}
@@ -549,7 +563,8 @@ void __init uv_system_init(void)
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
 	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
 	int max_pnode = 0;
-	unsigned long mmr_base, present;
+	unsigned long mmr_base, present, paddr;
+	unsigned short pnode_mask;
 
 	map_low_mmrs();
 
@@ -592,6 +607,7 @@ void __init uv_system_init(void)
 		}
 	}
 
+	pnode_mask = (1 << n_val) - 1;
 	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
 	gnode_upper = (((unsigned long)node_id.s.node_id) &
 		       ~((1 << n_val) - 1)) << m_val;
@@ -615,7 +631,7 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
 		uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
 		uv_cpu_hub_info(cpu)->pnode = pnode;
-		uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1;
+		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
@@ -631,6 +647,17 @@ void __init uv_system_init(void)
 			lcpu, blade);
 	}
 
+	/* Add blade/pnode info for nodes without cpus */
+	for_each_online_node(nid) {
+		if (uv_node_to_blade[nid] >= 0)
+			continue;
+		paddr = node_start_pfn(nid) << PAGE_SHIFT;
+		paddr = uv_soc_phys_ram_to_gpa(paddr);
+		pnode = (paddr >> m_val) & pnode_mask;
+		blade = boot_pnode_to_blade(pnode);
+		uv_node_to_blade[nid] = blade;
+	}
+
 	map_gru_high(max_pnode);
 	map_mmr_high(max_pnode);
 	map_config_high(max_pnode);
diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index f63882728d9..63a88e1f987 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -182,7 +182,8 @@ void uv_bios_init(void)
 	memcpy(&uv_systab, tab, sizeof(struct uv_systab));
 	iounmap(tab);
 
-	printk(KERN_INFO "EFI UV System Table Revision %d\n", tab->revision);
+	printk(KERN_INFO "EFI UV System Table Revision %d\n",
+					uv_systab.revision);
 }
 #else	/* !CONFIG_EFI */
 
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 8220ae69849..c965e521271 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 
 	static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
 		{ X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
+		{ X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 },
 		{ 0, 0, 0, 0 }
 	};
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c4f667896c2..c1caefc82e6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1203,6 +1203,8 @@ void __cpuinit cpu_init(void)
 	load_TR_desc();
 	load_LDT(&init_mm.context);
 
+	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+
 #ifdef CONFIG_DOUBLEFAULT
 	/* Set up doublefault TSS pointer in the GDT */
 	__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c
index 46e29ab96c6..46e29ab96c6 100755..100644
--- a/arch/x86/kernel/cpu/cpu_debug.c
+++ b/arch/x86/kernel/cpu/cpu_debug.c
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 19f6b9d27e8..208ecf6643d 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -65,13 +65,18 @@ enum {
 struct acpi_cpufreq_data {
 	struct acpi_processor_performance *acpi_data;
 	struct cpufreq_frequency_table *freq_table;
-	unsigned int max_freq;
 	unsigned int resume;
 	unsigned int cpu_feature;
 };
 
 static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
+struct acpi_msr_data {
+	u64 saved_aperf, saved_mperf;
+};
+
+static DEFINE_PER_CPU(struct acpi_msr_data, msr_data);
+
 DEFINE_TRACE(power_mark);
 
 /* acpi_perf_data is a pointer to percpu data. */
@@ -152,7 +157,8 @@ struct drv_cmd {
 	u32 val;
 };
 
-static long do_drv_read(void *_cmd)
+/* Called via smp_call_function_single(), on the target CPU */
+static void do_drv_read(void *_cmd)
 {
 	struct drv_cmd *cmd = _cmd;
 	u32 h;
@@ -169,10 +175,10 @@ static long do_drv_read(void *_cmd)
 	default:
 		break;
 	}
-	return 0;
 }
 
-static long do_drv_write(void *_cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
 {
 	struct drv_cmd *cmd = _cmd;
 	u32 lo, hi;
@@ -191,23 +197,24 @@ static long do_drv_write(void *_cmd)
 	default:
 		break;
 	}
-	return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
 	cmd->val = 0;
 
-	work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
+	smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
-	unsigned int i;
+	int this_cpu;
 
-	for_each_cpu(i, cmd->mask) {
-		work_on_cpu(i, do_drv_write, cmd);
-	}
+	this_cpu = get_cpu();
+	if (cpumask_test_cpu(this_cpu, cmd->mask))
+		do_drv_write(cmd);
+	smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
+	put_cpu();
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -241,28 +248,23 @@ static u32 get_cur_val(const struct cpumask *mask)
 	return cmd.val;
 }
 
-struct perf_cur {
+struct perf_pair {
 	union {
 		struct {
 			u32 lo;
 			u32 hi;
 		} split;
 		u64 whole;
-	} aperf_cur, mperf_cur;
+	} aperf, mperf;
 };
 
-
-static long read_measured_perf_ctrs(void *_cur)
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
 {
-	struct perf_cur *cur = _cur;
-
-	rdmsr(MSR_IA32_APERF, cur->aperf_cur.split.lo, cur->aperf_cur.split.hi);
-	rdmsr(MSR_IA32_MPERF, cur->mperf_cur.split.lo, cur->mperf_cur.split.hi);
+	struct perf_pair *cur = _cur;
 
-	wrmsr(MSR_IA32_APERF, 0, 0);
-	wrmsr(MSR_IA32_MPERF, 0, 0);
-
-	return 0;
+	rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi);
+	rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi);
 }
 
 /*
@@ -281,58 +283,63 @@ static long read_measured_perf_ctrs(void *_cur)
 static unsigned int get_measured_perf(struct cpufreq_policy *policy,
 				      unsigned int cpu)
 {
-	struct perf_cur cur;
+	struct perf_pair readin, cur;
 	unsigned int perf_percent;
 	unsigned int retval;
 
-	if (!work_on_cpu(cpu, read_measured_perf_ctrs, &cur))
+	if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1))
 		return 0;
 
+	cur.aperf.whole = readin.aperf.whole -
+				per_cpu(msr_data, cpu).saved_aperf;
+	cur.mperf.whole = readin.mperf.whole -
+				per_cpu(msr_data, cpu).saved_mperf;
+	per_cpu(msr_data, cpu).saved_aperf = readin.aperf.whole;
+	per_cpu(msr_data, cpu).saved_mperf = readin.mperf.whole;
+
 #ifdef __i386__
 	/*
 	 * We dont want to do 64 bit divide with 32 bit kernel
 	 * Get an approximate value. Return failure in case we cannot get
 	 * an approximate value.
 	 */
-	if (unlikely(cur.aperf_cur.split.hi || cur.mperf_cur.split.hi)) {
+	if (unlikely(cur.aperf.split.hi || cur.mperf.split.hi)) {
 		int shift_count;
 		u32 h;
 
-		h = max_t(u32, cur.aperf_cur.split.hi, cur.mperf_cur.split.hi);
+		h = max_t(u32, cur.aperf.split.hi, cur.mperf.split.hi);
 		shift_count = fls(h);
 
-		cur.aperf_cur.whole >>= shift_count;
-		cur.mperf_cur.whole >>= shift_count;
+		cur.aperf.whole >>= shift_count;
+		cur.mperf.whole >>= shift_count;
 	}
 
-	if (((unsigned long)(-1) / 100) < cur.aperf_cur.split.lo) {
+	if (((unsigned long)(-1) / 100) < cur.aperf.split.lo) {
 		int shift_count = 7;
-		cur.aperf_cur.split.lo >>= shift_count;
-		cur.mperf_cur.split.lo >>= shift_count;
+		cur.aperf.split.lo >>= shift_count;
+		cur.mperf.split.lo >>= shift_count;
 	}
 
-	if (cur.aperf_cur.split.lo && cur.mperf_cur.split.lo)
-		perf_percent = (cur.aperf_cur.split.lo * 100) /
-				cur.mperf_cur.split.lo;
+	if (cur.aperf.split.lo && cur.mperf.split.lo)
+		perf_percent = (cur.aperf.split.lo * 100) / cur.mperf.split.lo;
 	else
 		perf_percent = 0;
 
 #else
-	if (unlikely(((unsigned long)(-1) / 100) < cur.aperf_cur.whole)) {
+	if (unlikely(((unsigned long)(-1) / 100) < cur.aperf.whole)) {
 		int shift_count = 7;
-		cur.aperf_cur.whole >>= shift_count;
-		cur.mperf_cur.whole >>= shift_count;
+		cur.aperf.whole >>= shift_count;
+		cur.mperf.whole >>= shift_count;
 	}
 
-	if (cur.aperf_cur.whole && cur.mperf_cur.whole)
-		perf_percent = (cur.aperf_cur.whole * 100) /
-				cur.mperf_cur.whole;
+	if (cur.aperf.whole && cur.mperf.whole)
+		perf_percent = (cur.aperf.whole * 100) / cur.mperf.whole;
 	else
 		perf_percent = 0;
 
 #endif
 
-	retval = per_cpu(drv_data, policy->cpu)->max_freq * perf_percent / 100;
+	retval = (policy->cpuinfo.max_freq * perf_percent) / 100;
 
 	return retval;
 }
@@ -685,16 +692,11 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	/* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
 	if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
 	    policy->cpuinfo.transition_latency > 20 * 1000) {
-		static int print_once;
 		policy->cpuinfo.transition_latency = 20 * 1000;
-		if (!print_once) {
-			print_once = 1;
-			printk(KERN_INFO "Capping off P-state tranision latency"
-				" at 20 uS\n");
-		}
+			printk_once(KERN_INFO "Capping off P-state tranision"
+				    " latency at 20 uS\n");
 	}
 
-	data->max_freq = perf->states[0].core_frequency * 1000;
 	/* table init */
 	for (i = 0; i < perf->state_count; i++) {
 		if (i > 0 && perf->states[i].core_frequency >=
@@ -713,6 +715,9 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (result)
 		goto err_freqfree;
 
+	if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
+		printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
+
 	switch (perf->control_register.space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_IO:
 		/* Current speed is unknown and not detectable by IO port */
diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c
index 0bd48e65a0c..ce2ed3e4aad 100644
--- a/arch/x86/kernel/cpu/cpufreq/longhaul.c
+++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c
@@ -33,7 +33,6 @@
 #include <linux/timex.h>
 #include <linux/io.h>
 #include <linux/acpi.h>
-#include <linux/kernel.h>
 
 #include <asm/msr.h>
 #include <acpi/processor.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 863f89568b1..6fb0b359d2a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -239,9 +239,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		 * Don't get the IP here because it's unlikely to
 		 * have anything to do with the actual error location.
 		 */
-
-		mce_log(&m);
-		add_taint(TAINT_MACHINE_CHECK);
+		if (!(flags & MCP_DONTLOG)) {
+			mce_log(&m);
+			add_taint(TAINT_MACHINE_CHECK);
+		}
 
 		/*
 		 * Clear state for this bank.
@@ -452,13 +453,14 @@ void mce_log_therm_throt_event(__u64 status)
  */
 
 static int check_interval = 5 * 60; /* 5 minutes */
-static int next_interval; /* in jiffies */
+static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
 static void mcheck_timer(unsigned long);
 static DEFINE_PER_CPU(struct timer_list, mce_timer);
 
 static void mcheck_timer(unsigned long data)
 {
 	struct timer_list *t = &per_cpu(mce_timer, data);
+	int *n;
 
 	WARN_ON(smp_processor_id() != data);
 
@@ -470,14 +472,14 @@ static void mcheck_timer(unsigned long data)
 	 * Alert userspace if needed.  If we logged an MCE, reduce the
 	 * polling interval, otherwise increase the polling interval.
 	 */
+	n = &__get_cpu_var(next_interval);
 	if (mce_notify_user()) {
-		next_interval = max(next_interval/2, HZ/100);
+		*n = max(*n/2, HZ/100);
 	} else {
-		next_interval = min(next_interval * 2,
-				(int)round_jiffies_relative(check_interval*HZ));
+		*n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
 	}
 
-	t->expires = jiffies + next_interval;
+	t->expires = jiffies + *n;
 	add_timer(t);
 }
 
@@ -584,7 +586,7 @@ static void mce_init(void *dummy)
 	 * Log the machine checks left over from the previous reset.
 	 */
 	bitmap_fill(all_banks, MAX_NR_BANKS);
-	machine_check_poll(MCP_UC, &all_banks);
+	machine_check_poll(MCP_UC|(!mce_bootlog ? MCP_DONTLOG : 0), &all_banks);
 
 	set_in_cr4(X86_CR4_MCE);
 
@@ -632,14 +634,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
 static void mce_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
+	int *n = &__get_cpu_var(next_interval);
 
-	/* data race harmless because everyone sets to the same value */
-	if (!next_interval)
-		next_interval = check_interval * HZ;
-	if (!next_interval)
+	*n = check_interval * HZ;
+	if (!*n)
 		return;
 	setup_timer(t, mcheck_timer, smp_processor_id());
-	t->expires = round_jiffies(jiffies + next_interval);
+	t->expires = round_jiffies(jiffies + *n);
 	add_timer(t);
 }
 
@@ -907,7 +908,6 @@ static void mce_cpu_restart(void *data)
 /* Reinit MCEs after user configuration changes */
 static void mce_restart(void)
 {
-	next_interval = check_interval * HZ;
 	on_each_cpu(mce_cpu_restart, NULL, 1);
 }
 
@@ -1110,7 +1110,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		t->expires = round_jiffies(jiffies + next_interval);
+		t->expires = round_jiffies(jiffies +
+						__get_cpu_var(next_interval));
 		add_timer_on(t, cpu);
 		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
 		break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index d6b72df89d6..cef3ee30744 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -151,10 +151,11 @@ static void print_update(char *type, int *hdr, int num)
 static void cmci_discover(int banks, int boot)
 {
 	unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+	unsigned long flags;
 	int hdr = 0;
 	int i;
 
-	spin_lock(&cmci_discover_lock);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++) {
 		u64 val;
 
@@ -184,7 +185,7 @@ static void cmci_discover(int banks, int boot)
 			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
 		}
 	}
-	spin_unlock(&cmci_discover_lock);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 	if (hdr)
 		printk(KERN_CONT "\n");
 }
@@ -211,13 +212,14 @@ void cmci_recheck(void)
  */
 void cmci_clear(void)
 {
+	unsigned long flags;
 	int i;
 	int banks;
 	u64 val;
 
 	if (!cmci_supported(&banks))
 		return;
-	spin_lock(&cmci_discover_lock);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++) {
 		if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
 			continue;
@@ -227,7 +229,7 @@ void cmci_clear(void)
 		wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
 		__clear_bit(i, __get_cpu_var(mce_banks_owned));
 	}
-	spin_unlock(&cmci_discover_lock);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index f93047fed79..d5e30397246 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpumask_weight(cpu_sibling_mask(cpu)));
+			   cpumask_weight(cpu_core_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index ef2c3563357..00628130292 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1074,12 +1074,13 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 	u64 addr;
 	u64 start;
 
-	start = startt;
-	while (size < sizet && (start + 1))
+	for (start = startt; ; start += size) {
 		start = find_e820_area_size(start, &size, align);
-
-	if (size < sizet)
-		return 0;
+		if (!(start + 1))
+			return 0;
+		if (size >= sizet)
+			break;
+	}
 
 #ifdef CONFIG_X86_32
 	if (start >= MAXMEM)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a331ec38af9..38946c6e843 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1410,7 +1410,10 @@ ENTRY(paranoid_exit)
 paranoid_swapgs:
 	TRACE_IRQS_IRETQ 0
 	SWAPGS_UNSAFE_STACK
+	RESTORE_ALL 8
+	jmp irq_return
 paranoid_restore:
+	TRACE_IRQS_IRETQ 0
 	RESTORE_ALL 8
 	jmp irq_return
 paranoid_userspace:
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 70a10ca100f..18dfa30795c 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -18,6 +18,8 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <trace/syscall.h>
+
 #include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 #include <asm/nops.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 648b3a2a3a4..81408b93f88 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -236,6 +236,10 @@ static void hpet_stop_counter(void)
 	unsigned long cfg = hpet_readl(HPET_CFG);
 	cfg &= ~HPET_CFG_ENABLE;
 	hpet_writel(cfg, HPET_CFG);
+}
+
+static void hpet_reset_counter(void)
+{
 	hpet_writel(0, HPET_COUNTER);
 	hpet_writel(0, HPET_COUNTER + 4);
 }
@@ -250,6 +254,7 @@ static void hpet_start_counter(void)
 static void hpet_restart_counter(void)
 {
 	hpet_stop_counter();
+	hpet_reset_counter();
 	hpet_start_counter();
 }
 
@@ -309,7 +314,7 @@ static int hpet_setup_msi_irq(unsigned int irq);
 static void hpet_set_mode(enum clock_event_mode mode,
 			  struct clock_event_device *evt, int timer)
 {
-	unsigned long cfg;
+	unsigned long cfg, cmp, now;
 	uint64_t delta;
 
 	switch (mode) {
@@ -317,12 +322,23 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		hpet_stop_counter();
 		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
 		delta >>= evt->shift;
+		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));
+		hpet_writel(cmp, HPET_Tn_CMP(timer));
+		udelay(1);
+		/*
+		 * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL
+		 * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL
+		 * bit is automatically cleared after the first write.
+		 * (See AMD-8111 HyperTransport I/O Hub Data Sheet,
+		 * Publication # 24674)
+		 */
 		hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer));
 		hpet_start_counter();
 		hpet_print_config();
@@ -722,7 +738,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 /*
  * Clock source related code
  */
-static cycle_t read_hpet(void)
+static cycle_t read_hpet(struct clocksource *cs)
 {
 	return (cycle_t)hpet_readl(HPET_COUNTER);
 }
@@ -756,7 +772,7 @@ static int hpet_clocksource_register(void)
 	hpet_restart_counter();
 
 	/* Verify whether hpet counter works */
-	t1 = read_hpet();
+	t1 = hpet_readl(HPET_COUNTER);
 	rdtscll(start);
 
 	/*
@@ -770,7 +786,7 @@ static int hpet_clocksource_register(void)
 		rdtscll(now);
 	} while ((now - start) < 200000UL);
 
-	if (t1 == read_hpet()) {
+	if (t1 == hpet_readl(HPET_COUNTER)) {
 		printk(KERN_WARNING
 		       "HPET counter not counting. HPET disabled\n");
 		return -ENODEV;
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 3475440baa5..c2e0bb0890d 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -129,7 +129,7 @@ void __init setup_pit_timer(void)
  * to just read by itself. So use jiffies to emulate a free
  * running counter:
  */
-static cycle_t pit_read(void)
+static cycle_t pit_read(struct clocksource *cs)
 {
 	static int old_count;
 	static u32 old_jifs;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 3aaf7b9e3a8..c3fe010d74c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -65,7 +65,7 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	seq_printf(p, "  Spurious interrupts\n");
 #endif
 	if (generic_interrupt_extension) {
-		seq_printf(p, "PLT: ");
+		seq_printf(p, "%*s: ", prec, "PLT");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", irq_stats(j)->generic_irqs);
 		seq_printf(p, "  Platform interrupts\n");
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 137f2e8132d..223af43f152 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -77,6 +77,11 @@ static cycle_t kvm_clock_read(void)
 	return ret;
 }
 
+static cycle_t kvm_clock_get_cycles(struct clocksource *cs)
+{
+	return kvm_clock_read();
+}
+
 /*
  * If we don't do that, there is the possibility that the guest
  * will calibrate under heavy load - thus, getting a lower lpj -
@@ -107,7 +112,7 @@ static void kvm_get_preset_lpj(void)
 
 static struct clocksource kvm_clock = {
 	.name = "kvm-clock",
-	.read = kvm_clock_read,
+	.read = kvm_clock_get_cycles,
 	.rating = 400,
 	.mask = CLOCKSOURCE_MASK(64),
 	.mult = 1 << KVM_SCALE,
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index e7368c1da01..c1c429d0013 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -194,7 +194,7 @@ void machine_kexec(struct kimage *image)
 				       unsigned int preserve_context);
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		save_processor_state();
 #endif
 
@@ -253,7 +253,7 @@ void machine_kexec(struct kimage *image)
 					   image->preserve_context);
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		restore_processor_state();
 #endif
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 89cea4d4467..84c3bf209e9 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -274,7 +274,7 @@ void machine_kexec(struct kimage *image)
 	int save_ftrace_enabled;
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		save_processor_state();
 #endif
 
@@ -333,7 +333,7 @@ void machine_kexec(struct kimage *image)
 				       image->preserve_context);
 
 #ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context)
+	if (image->preserve_context)
 		restore_processor_state();
 #endif
 
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index a0f3851ef31..98c470c069d 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -108,40 +108,29 @@ struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 EXPORT_SYMBOL_GPL(ucode_cpu_info);
 
 #ifdef CONFIG_MICROCODE_OLD_INTERFACE
-struct update_for_cpu {
-	const void __user	*buf;
-	size_t			size;
-};
-
-static long update_for_cpu(void *_ufc)
-{
-	struct update_for_cpu *ufc = _ufc;
-	int error;
-
-	error = microcode_ops->request_microcode_user(smp_processor_id(),
-						      ufc->buf, ufc->size);
-	if (error < 0)
-		return error;
-	if (!error)
-		microcode_ops->apply_microcode(smp_processor_id());
-	return error;
-}
-
 static int do_microcode_update(const void __user *buf, size_t size)
 {
+	cpumask_t old;
 	int error = 0;
 	int cpu;
-	struct update_for_cpu ufc = { .buf = buf, .size = size };
+
+	old = current->cpus_allowed;
 
 	for_each_online_cpu(cpu) {
 		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 		if (!uci->valid)
 			continue;
-		error = work_on_cpu(cpu, update_for_cpu, &ufc);
+
+		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+		error = microcode_ops->request_microcode_user(cpu, buf, size);
 		if (error < 0)
-			break;
+			goto out;
+		if (!error)
+			microcode_ops->apply_microcode(cpu);
 	}
+out:
+	set_cpus_allowed_ptr(current, &old);
 	return error;
 }
 
@@ -391,8 +380,6 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
 		return err;
 
 	err = microcode_init_cpu(cpu);
-	if (err)
-		sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
 
 	return err;
 }
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index dce99dca6cf..70fd7e414c1 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -679,7 +679,7 @@ void __init get_smp_config(void)
 	__get_smp_config(0);
 }
 
-static void smp_reserve_bootmem(struct mpf_intel *mpf)
+static void __init smp_reserve_bootmem(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
 #ifdef CONFIG_X86_32
@@ -838,7 +838,7 @@ static int  __init get_MP_intsrc_index(struct mpc_intsrc *m)
 
 static struct mpc_intsrc __initdata *m_spare[SPARE_SLOT_NUM];
 
-static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
+static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
 {
 	int i;
 
@@ -866,7 +866,8 @@ static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare)
 	}
 }
 #else /* CONFIG_X86_IO_APIC */
-static inline void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
+static
+inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {}
 #endif /* CONFIG_X86_IO_APIC */
 
 static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 887388a1c57..a1712f2b50f 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -50,7 +50,7 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
 }
 
-struct dma_map_ops swiotlb_dma_ops = {
+static struct dma_map_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
 	.alloc_coherent = x86_swiotlb_alloc_coherent,
 	.free_coherent = swiotlb_free_coherent,
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index fe9345c967d..23b7c8f017e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,7 +21,6 @@
 #include <linux/audit.h>
 #include <linux/seccomp.h>
 #include <linux/signal.h>
-#include <linux/ftrace.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -35,6 +34,8 @@
 #include <asm/proto.h>
 #include <asm/ds.h>
 
+#include <trace/syscall.h>
+
 #include "tls.h"
 
 enum x86_regset {
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index e95022e4f5d..7563b31b4f0 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -261,8 +261,6 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev)
 {
 	if (hpet_force_user)
 		old_ich_force_enable_hpet(dev);
-	else
-		hpet_print_force_info();
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1,
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 2aef36d8aca..1340dad417f 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -224,6 +224,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"),
 		},
 	},
+	{	/* Handle problems with rebooting on Dell DXP061 */
+		.callback = set_bios_reboot,
+		.ident = "Dell DXP061",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index deb5ebb32c3..ed0c33761e6 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -25,6 +25,8 @@ static int			uv_bau_retry_limit __read_mostly;
 
 /* position of pnode (which is nasid>>1): */
 static int			uv_nshift __read_mostly;
+/* base pnode in this partition */
+static int			uv_partition_base_pnode __read_mostly;
 
 static unsigned long		uv_mmask __read_mostly;
 
@@ -32,6 +34,34 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats);
 static DEFINE_PER_CPU(struct bau_control, bau_control);
 
 /*
+ * Determine the first node on a blade.
+ */
+static int __init blade_to_first_node(int blade)
+{
+	int node, b;
+
+	for_each_online_node(node) {
+		b = uv_node_to_blade_id(node);
+		if (blade == b)
+			return node;
+	}
+	return -1; /* shouldn't happen */
+}
+
+/*
+ * Determine the apicid of the first cpu on a blade.
+ */
+static int __init blade_to_first_apicid(int blade)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu)
+		if (blade == uv_cpu_to_blade_id(cpu))
+			return per_cpu(x86_cpu_to_apicid, cpu);
+	return -1;
+}
+
+/*
  * Free a software acknowledge hardware resource by clearing its Pending
  * bit. This will return a reply to the sender.
  * If the message has timed out, a reply has already been sent by the
@@ -67,7 +97,7 @@ static void uv_bau_process_message(struct bau_payload_queue_entry *msg,
 	msp = __get_cpu_var(bau_control).msg_statuses + msg_slot;
 	cpu = uv_blade_processor_id();
 	msg->number_of_cpus =
-	    uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id()));
+		uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id()));
 	this_cpu_mask = 1UL << cpu;
 	if (msp->seen_by.bits & this_cpu_mask)
 		return;
@@ -215,14 +245,14 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
  * Returns @flush_mask if some remote flushing remains to be done. The
  * mask will have some bits still set.
  */
-const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
+const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode,
 					     struct bau_desc *bau_desc,
 					     struct cpumask *flush_mask)
 {
 	int completion_status = 0;
 	int right_shift;
 	int tries = 0;
-	int blade;
+	int pnode;
 	int bit;
 	unsigned long mmr_offset;
 	unsigned long index;
@@ -265,8 +295,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
 	 * use the IPI method of shootdown on them.
 	 */
 	for_each_cpu(bit, flush_mask) {
-		blade = uv_cpu_to_blade_id(bit);
-		if (blade == this_blade)
+		pnode = uv_cpu_to_pnode(bit);
+		if (pnode == this_pnode)
 			continue;
 		cpumask_clear_cpu(bit, flush_mask);
 	}
@@ -309,16 +339,16 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask);
 	int i;
 	int bit;
-	int blade;
+	int pnode;
 	int uv_cpu;
-	int this_blade;
+	int this_pnode;
 	int locals = 0;
 	struct bau_desc *bau_desc;
 
 	cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
 
 	uv_cpu = uv_blade_processor_id();
-	this_blade = uv_numa_blade_id();
+	this_pnode = uv_hub_info->pnode;
 	bau_desc = __get_cpu_var(bau_control).descriptor_base;
 	bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu;
 
@@ -326,13 +356,14 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 
 	i = 0;
 	for_each_cpu(bit, flush_mask) {
-		blade = uv_cpu_to_blade_id(bit);
-		BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1));
-		if (blade == this_blade) {
+		pnode = uv_cpu_to_pnode(bit);
+		BUG_ON(pnode > (UV_DISTRIBUTION_SIZE - 1));
+		if (pnode == this_pnode) {
 			locals++;
 			continue;
 		}
-		bau_node_set(blade, &bau_desc->distribution);
+		bau_node_set(pnode - uv_partition_base_pnode,
+				&bau_desc->distribution);
 		i++;
 	}
 	if (i == 0) {
@@ -350,7 +381,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 	bau_desc->payload.address = va;
 	bau_desc->payload.sending_cpu = cpu;
 
-	return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask);
+	return uv_flush_send_and_wait(uv_cpu, this_pnode, bau_desc, flush_mask);
 }
 
 /*
@@ -418,24 +449,58 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
+/*
+ * uv_enable_timeouts
+ *
+ * Each target blade (i.e. blades that have cpu's) needs to have
+ * shootdown message timeouts enabled.  The timeout does not cause
+ * an interrupt, but causes an error message to be returned to
+ * the sender.
+ */
 static void uv_enable_timeouts(void)
 {
-	int i;
 	int blade;
-	int last_blade;
+	int nblades;
 	int pnode;
-	int cur_cpu = 0;
-	unsigned long apicid;
+	unsigned long mmr_image;
 
-	last_blade = -1;
-	for_each_online_node(i) {
-		blade = uv_node_to_blade_id(i);
-		if (blade == last_blade)
+	nblades = uv_num_possible_blades();
+
+	for (blade = 0; blade < nblades; blade++) {
+		if (!uv_blade_nr_possible_cpus(blade))
 			continue;
-		last_blade = blade;
-		apicid = per_cpu(x86_cpu_to_apicid, cur_cpu);
+
 		pnode = uv_blade_to_pnode(blade);
-		cur_cpu += uv_blade_nr_possible_cpus(i);
+		mmr_image =
+		    uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL);
+		/*
+		 * Set the timeout period and then lock it in, in three
+		 * steps; captures and locks in the period.
+		 *
+		 * To program the period, the SOFT_ACK_MODE must be off.
+		 */
+		mmr_image &= ~((unsigned long)1 <<
+			       UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT);
+		uv_write_global_mmr64
+		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+		/*
+		 * Set the 4-bit period.
+		 */
+		mmr_image &= ~((unsigned long)0xf <<
+			UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT);
+		mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD <<
+			     UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT);
+		uv_write_global_mmr64
+		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+		/*
+		 * Subsequent reversals of the timebase bit (3) cause an
+		 * immediate timeout of one or all INTD resources as
+		 * indicated in bits 2:0 (7 causes all of them to timeout).
+		 */
+		mmr_image |= ((unsigned long)1 <<
+			      UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT);
+		uv_write_global_mmr64
+		    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
 	}
 }
 
@@ -482,8 +547,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
 			   stat->requestee, stat->onetlb, stat->alltlb,
 			   stat->s_retry, stat->d_retry, stat->ptc_i);
 		seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n",
-			   uv_read_global_mmr64(uv_blade_to_pnode
-					(uv_cpu_to_blade_id(cpu)),
+			   uv_read_global_mmr64(uv_cpu_to_pnode(cpu),
 					UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE),
 			   stat->sflush, stat->dflush,
 			   stat->retriesok, stat->nomsg,
@@ -617,16 +681,18 @@ static struct bau_control * __init uv_table_bases_init(int blade, int node)
  * finish the initialization of the per-blade control structures
  */
 static void __init
-uv_table_bases_finish(int blade, int node, int cur_cpu,
+uv_table_bases_finish(int blade,
 		      struct bau_control *bau_tablesp,
 		      struct bau_desc *adp)
 {
 	struct bau_control *bcp;
-	int i;
+	int cpu;
 
-	for (i = cur_cpu; i < cur_cpu + uv_blade_nr_possible_cpus(blade); i++) {
-		bcp = (struct bau_control *)&per_cpu(bau_control, i);
+	for_each_present_cpu(cpu) {
+		if (blade != uv_cpu_to_blade_id(cpu))
+			continue;
 
+		bcp = (struct bau_control *)&per_cpu(bau_control, cpu);
 		bcp->bau_msg_head	= bau_tablesp->va_queue_first;
 		bcp->va_queue_first	= bau_tablesp->va_queue_first;
 		bcp->va_queue_last	= bau_tablesp->va_queue_last;
@@ -649,11 +715,10 @@ uv_activation_descriptor_init(int node, int pnode)
 	struct bau_desc *adp;
 	struct bau_desc *ad2;
 
-	adp = (struct bau_desc *)
-	    kmalloc_node(16384, GFP_KERNEL, node);
+	adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node);
 	BUG_ON(!adp);
 
-	pa = __pa((unsigned long)adp);
+	pa = uv_gpa(adp); /* need the real nasid*/
 	n = pa >> uv_nshift;
 	m = pa & uv_mmask;
 
@@ -667,8 +732,12 @@ uv_activation_descriptor_init(int node, int pnode)
 	for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) {
 		memset(ad2, 0, sizeof(struct bau_desc));
 		ad2->header.sw_ack_flag = 1;
-		ad2->header.base_dest_nodeid =
-		    uv_blade_to_pnode(uv_cpu_to_blade_id(0));
+		/*
+		 * base_dest_nodeid is the first node in the partition, so
+		 * the bit map will indicate partition-relative node numbers.
+		 * note that base_dest_nodeid is actually a nasid.
+		 */
+		ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1;
 		ad2->header.command = UV_NET_ENDPOINT_INTD;
 		ad2->header.int_both = 1;
 		/*
@@ -686,6 +755,8 @@ static struct bau_payload_queue_entry * __init
 uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
 {
 	struct bau_payload_queue_entry *pqp;
+	unsigned long pa;
+	int pn;
 	char *cp;
 
 	pqp = (struct bau_payload_queue_entry *) kmalloc_node(
@@ -696,10 +767,14 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
 	cp = (char *)pqp + 31;
 	pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5);
 	bau_tablesp->va_queue_first = pqp;
+	/*
+	 * need the pnode of where the memory was really allocated
+	 */
+	pa = uv_gpa(pqp);
+	pn = pa >> uv_nshift;
 	uv_write_global_mmr64(pnode,
 			      UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST,
-			      ((unsigned long)pnode <<
-			       UV_PAYLOADQ_PNODE_SHIFT) |
+			      ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) |
 			      uv_physnodeaddr(pqp));
 	uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL,
 			      uv_physnodeaddr(pqp));
@@ -715,8 +790,9 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp)
 /*
  * Initialization of each UV blade's structures
  */
-static int __init uv_init_blade(int blade, int node, int cur_cpu)
+static int __init uv_init_blade(int blade)
 {
+	int node;
 	int pnode;
 	unsigned long pa;
 	unsigned long apicid;
@@ -724,16 +800,17 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu)
 	struct bau_payload_queue_entry *pqp;
 	struct bau_control *bau_tablesp;
 
+	node = blade_to_first_node(blade);
 	bau_tablesp = uv_table_bases_init(blade, node);
 	pnode = uv_blade_to_pnode(blade);
 	adp = uv_activation_descriptor_init(node, pnode);
 	pqp = uv_payload_queue_init(node, pnode, bau_tablesp);
-	uv_table_bases_finish(blade, node, cur_cpu, bau_tablesp, adp);
+	uv_table_bases_finish(blade, bau_tablesp, adp);
 	/*
 	 * the below initialization can't be in firmware because the
 	 * messaging IRQ will be determined by the OS
 	 */
-	apicid = per_cpu(x86_cpu_to_apicid, cur_cpu);
+	apicid = blade_to_first_apicid(blade);
 	pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG);
 	if ((pa & 0xff) != UV_BAU_MESSAGE) {
 		uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
@@ -748,9 +825,7 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu)
 static int __init uv_bau_init(void)
 {
 	int blade;
-	int node;
 	int nblades;
-	int last_blade;
 	int cur_cpu;
 
 	if (!is_uv_system())
@@ -763,29 +838,21 @@ static int __init uv_bau_init(void)
 	uv_bau_retry_limit = 1;
 	uv_nshift = uv_hub_info->n_val;
 	uv_mmask = (1UL << uv_hub_info->n_val) - 1;
-	nblades = 0;
-	last_blade = -1;
-	cur_cpu = 0;
-	for_each_online_node(node) {
-		blade = uv_node_to_blade_id(node);
-		if (blade == last_blade)
-			continue;
-		last_blade = blade;
-		nblades++;
-	}
+	nblades = uv_num_possible_blades();
+
 	uv_bau_table_bases = (struct bau_control **)
 	    kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL);
 	BUG_ON(!uv_bau_table_bases);
 
-	last_blade = -1;
-	for_each_online_node(node) {
-		blade = uv_node_to_blade_id(node);
-		if (blade == last_blade)
-			continue;
-		last_blade = blade;
-		uv_init_blade(blade, node, cur_cpu);
-		cur_cpu += uv_blade_nr_possible_cpus(blade);
-	}
+	uv_partition_base_pnode = 0x7fffffff;
+	for (blade = 0; blade < nblades; blade++)
+		if (uv_blade_nr_possible_cpus(blade) &&
+			(uv_blade_to_pnode(blade) < uv_partition_base_pnode))
+			uv_partition_base_pnode = uv_blade_to_pnode(blade);
+	for (blade = 0; blade < nblades; blade++)
+		if (uv_blade_nr_possible_cpus(blade))
+			uv_init_blade(blade);
+
 	alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1);
 	uv_enable_timeouts();
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 7a567ebe636..d57de05dc43 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -699,7 +699,7 @@ static struct clocksource clocksource_tsc;
  * code, which is necessary to support wrapping clocksources like pm
  * timer.
  */
-static cycle_t read_tsc(void)
+static cycle_t read_tsc(struct clocksource *cs)
 {
 	cycle_t ret = (cycle_t)get_cycles();
 
diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c
index 67f9b9dbf80..36afb98675a 100644
--- a/arch/x86/kernel/uv_sysfs.c
+++ b/arch/x86/kernel/uv_sysfs.c
@@ -21,6 +21,7 @@
 
 #include <linux/sysdev.h>
 #include <asm/uv/bios.h>
+#include <asm/uv/uv.h>
 
 struct kobject *sgi_uv_kobj;
 
@@ -47,6 +48,9 @@ static int __init sgi_uv_sysfs_init(void)
 {
 	unsigned long ret;
 
+	if (!is_uv_system())
+		return -ENODEV;
+
 	if (!sgi_uv_kobj)
 		sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj);
 	if (!sgi_uv_kobj) {
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 2ffb6c53326..583f11d5c48 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -29,7 +29,7 @@
 
 #define RTC_NAME		"sgi_rtc"
 
-static cycle_t uv_read_rtc(void);
+static cycle_t uv_read_rtc(struct clocksource *cs);
 static int uv_rtc_next_event(unsigned long, struct clock_event_device *);
 static void uv_rtc_timer_setup(enum clock_event_mode,
 				struct clock_event_device *);
@@ -123,7 +123,7 @@ static int uv_setup_intr(int cpu, u64 expires)
 	/* Initialize comparator value */
 	uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires);
 
-	return (expires < uv_read_rtc() && !uv_intr_pending(pnode));
+	return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode));
 }
 
 /*
@@ -256,7 +256,7 @@ static int uv_rtc_unset_timer(int cpu)
 
 	spin_lock_irqsave(&head->lock, flags);
 
-	if (head->next_cpu == bcpu && uv_read_rtc() >= *t)
+	if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t)
 		rc = 1;
 
 	*t = ULLONG_MAX;
@@ -278,7 +278,7 @@ static int uv_rtc_unset_timer(int cpu)
 /*
  * Read the RTC.
  */
-static cycle_t uv_read_rtc(void)
+static cycle_t uv_read_rtc(struct clocksource *cs)
 {
 	return (cycle_t)uv_read_local_mmr(UVH_RTC);
 }
@@ -291,7 +291,7 @@ static int uv_rtc_next_event(unsigned long delta,
 {
 	int ced_cpu = cpumask_first(ced->cpumask);
 
-	return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc());
+	return uv_rtc_set_timer(ced_cpu, delta + uv_read_rtc(NULL));
 }
 
 /*
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index d303369a7ba..2b3eb82efee 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -283,7 +283,7 @@ void __devinit vmi_time_ap_init(void)
 /** vmi clocksource */
 static struct clocksource clocksource_vmi;
 
-static cycle_t read_real_cycles(void)
+static cycle_t read_real_cycles(struct clocksource *cs)
 {
 	cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
 	return max(ret, clocksource_vmi.cycle_last);
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 2b54fe002e9..c5ee17e8c6d 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -89,7 +89,7 @@ int save_i387_xstate(void __user *buf)
 
 	if (!used_math())
 		return 0;
-	clear_used_math(); /* trigger finit */
+
 	if (task_thread_info(tsk)->status & TS_USEDFPU) {
 		/*
 	 	 * Start with clearing the user buffer. This will present a
@@ -114,6 +114,8 @@ int save_i387_xstate(void __user *buf)
 			return -1;
 	}
 
+	clear_used_math(); /* trigger finit */
+
 	if (task_thread_info(tsk)->status & TS_XSAVE) {
 		struct _fpstate __user *fx = buf;
 		struct _xstate __user *x = buf;
@@ -324,7 +326,7 @@ void __ref xsave_cntxt_init(void)
 	}
 
 	/*
-	 * for now OS knows only about FP/SSE
+	 * Support only the state known to OS.
 	 */
 	pcntxt_mask = pcntxt_mask & XCNTXT_MASK;
 	xsave_init();