Merge commit 'v2.6.30-rc6' into perfcounters/core

Merge reason: this branch was on an -rc4 base, merge it up to -rc6
              to get the latest upstream fixes.

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

18 files changed, 87 insertions, 53 deletions

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 563933e06a3..4f8c199584e 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -137,6 +137,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
 enum mcp_flags {
 	MCP_TIMESTAMP = (1 << 0),	/* log time stamp */
 	MCP_UC = (1 << 1),		/* log uncorrected errors */
+	MCP_DONTLOG = (1 << 2),		/* only clear, don't log */
 };
 extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
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/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a86769efe0d..591012fb949 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1205,6 +1205,8 @@ 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/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/kgdb.c b/arch/x86/kernel/kgdb.c
index eedfaebe106..b1f4dffb919 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -88,6 +88,7 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 	gdb_regs[GDB_SS]	= __KERNEL_DS;
 	gdb_regs[GDB_FS]	= 0xFFFF;
 	gdb_regs[GDB_GS]	= 0xFFFF;
+	gdb_regs[GDB_SP]	= (int)&regs->sp;
 #else
 	gdb_regs[GDB_R8]	= regs->r8;
 	gdb_regs[GDB_R9]	= regs->r9;
@@ -100,8 +101,8 @@ void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 	gdb_regs32[GDB_PS]	= regs->flags;
 	gdb_regs32[GDB_CS]	= regs->cs;
 	gdb_regs32[GDB_SS]	= regs->ss;
-#endif
 	gdb_regs[GDB_SP]	= regs->sp;
+#endif
 }
 
 /**
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/kvm/svm.c b/arch/x86/kvm/svm.c
index 1821c207819..1f8510c51d6 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -411,7 +411,6 @@ static __init int svm_hardware_setup(void)
 
 	iopm_va = page_address(iopm_pages);
 	memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
-	clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */
 	iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
 
 	if (boot_cpu_has(X86_FEATURE_NX))
@@ -796,6 +795,11 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
 	var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
 
+	/* AMD's VMCB does not have an explicit unusable field, so emulate it
+	 * for cross vendor migration purposes by "not present"
+	 */
+	var->unusable = !var->present || (var->type == 0);
+
 	switch (seg) {
 	case VCPU_SREG_CS:
 		/*
@@ -827,8 +831,6 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 			var->type |= 0x1;
 		break;
 	}
-
-	var->unusable = !var->present;
 }
 
 static int svm_get_cpl(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7c1ce5ac613..49079a46687 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1121,9 +1121,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 static int is_efer_nx(void)
 {
-	u64 efer;
+	unsigned long long efer = 0;
 
-	rdmsrl(MSR_EFER, efer);
+	rdmsrl_safe(MSR_EFER, &efer);
 	return efer & EFER_NX;
 }
 
@@ -1259,7 +1259,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) |
 		bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) |
 		bit(X86_FEATURE_SYSCALL) |
-		(bit(X86_FEATURE_NX) && is_efer_nx()) |
+		(is_efer_nx() ? bit(X86_FEATURE_NX) : 0) |
 #ifdef CONFIG_X86_64
 		bit(X86_FEATURE_LM) |
 #endif
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fd3da1dda1c..ae4f7b5d710 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -7,6 +7,7 @@
 #include <asm/page.h>
 #include <asm/page_types.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
 
@@ -304,8 +305,23 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 #endif
 
 #ifdef CONFIG_X86_64
-	if (!after_bootmem)
+	if (!after_bootmem && !start) {
+		pud_t *pud;
+		pmd_t *pmd;
+
 		mmu_cr4_features = read_cr4();
+
+		/*
+		 * _brk_end cannot change anymore, but it and _end may be
+		 * located on different 2M pages. cleanup_highmap(), however,
+		 * can only consider _end when it runs, so destroy any
+		 * mappings beyond _brk_end here.
+		 */
+		pud = pud_offset(pgd_offset_k(_brk_end), _brk_end);
+		pmd = pmd_offset(pud, _brk_end - 1);
+		while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1))
+			pmd_clear(pmd);
+	}
 #endif
 	__flush_tlb_all();
 
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 4f115e00486..50dc802a1c4 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -87,7 +87,7 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 {
 	struct kmmio_probe *p;
 	list_for_each_entry_rcu(p, &kmmio_probes, list) {
-		if (addr >= p->addr && addr <= (p->addr + p->len))
+		if (addr >= p->addr && addr < (p->addr + p->len))
 			return p;
 	}
 	return NULL;
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 16ae70fc57e..29a0e37114f 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -216,7 +216,7 @@ int __init get_memcfg_from_srat(void)
 
 	if (num_memory_chunks == 0) {
 		printk(KERN_WARNING
-			 "could not finy any ACPI SRAT memory areas.\n");
+			 "could not find any ACPI SRAT memory areas.\n");
 		goto out_fail;
 	}
 
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 33c5fa57e43..01765955baa 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -361,6 +361,7 @@ static void __init unparse_node(int node)
 {
 	int i;
 	node_clear(node, nodes_parsed);
+	node_clear(node, cpu_nodes_parsed);
 	for (i = 0; i < MAX_LOCAL_APIC; i++) {
 		if (apicid_to_node[i] == node)
 			apicid_to_node[i] = NUMA_NO_NODE;
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index d9d35824c56..6a40b78b46a 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -104,11 +104,13 @@ notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
 	if (likely(gtod->sysctl_enabled && gtod->clock.vread)) {
-		BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
-			     offsetof(struct timespec, tv_nsec) ||
-			     sizeof(*tv) != sizeof(struct timespec));
-		do_realtime((struct timespec *)tv);
-		tv->tv_usec /= 1000;
+		if (likely(tv != NULL)) {
+			BUILD_BUG_ON(offsetof(struct timeval, tv_usec) !=
+				     offsetof(struct timespec, tv_nsec) ||
+				     sizeof(*tv) != sizeof(struct timespec));
+			do_realtime((struct timespec *)tv);
+			tv->tv_usec /= 1000;
+		}
 		if (unlikely(tz != NULL)) {
 			/* Avoid memcpy. Some old compilers fail to inline it */
 			tz->tz_minuteswest = gtod->sys_tz.tz_minuteswest;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 9842b121240..e25a78e1113 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1794,6 +1794,11 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 
 	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
 
+	reserve_early(__pa(xen_start_info->pt_base),
+		      __pa(xen_start_info->pt_base +
+			   xen_start_info->nr_pt_frames * PAGE_SIZE),
+		      "XEN PAGETABLES");
+
 	return swapper_pg_dir;
 }
 #endif	/* CONFIG_X86_64 */