Merge commit 'v2.6.29-rc4' into perfcounters/core

Conflicts:
	arch/x86/kernel/setup_percpu.c
	arch/x86/mm/fault.c
	drivers/acpi/processor_idle.c
	kernel/irq/handle.c

17 files changed, 75 insertions, 55 deletions

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 4abff454c55..7c243a2c511 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -157,11 +157,11 @@ static int __init acpi_sleep_setup(char *str)
 #ifdef CONFIG_HIBERNATION
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
 			acpi_no_s4_hw_signature();
+		if (strncmp(str, "s4_nonvs", 8) == 0)
+			acpi_s4_no_nvs();
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
-		if (strncmp(str, "s4_nonvs", 8) == 0)
-			acpi_s4_no_nvs();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 849c23009bf..abfa0b641ae 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -1447,7 +1447,7 @@ static int __init detect_init_APIC(void)
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
 		if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model > 1) ||
-		    (boot_cpu_data.x86 == 15))
+		    (boot_cpu_data.x86 >= 15))
 			break;
 		goto no_apic;
 	case X86_VENDOR_INTEL:
diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index efae3b22a0f..65792c2cc46 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -245,17 +245,6 @@ config X86_E_POWERSAVER
 
 comment "shared options"
 
-config X86_ACPI_CPUFREQ_PROC_INTF
-	bool "/proc/acpi/processor/../performance interface (deprecated)"
-	depends on PROC_FS
-	depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI
-	help
-	  This enables the deprecated /proc/acpi/processor/../performance
-	  interface. While it is helpful for debugging, the generic,
-	  cross-architecture cpufreq interfaces should be used.
-
-	  If in doubt, say N.
-
 config X86_SPEEDSTEP_LIB
 	tristate
 	default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 8ea6929e974..430e5c38a54 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -29,6 +29,19 @@
 
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
+	/* Unmask CPUID levels if masked: */
+	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
+		u64 misc_enable;
+
+		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+
+		if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
+			misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
+			wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+			c->cpuid_level = cpuid_eax(0);
+		}
+	}
+
 	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 58527a9fc40..7293508d8f5 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -36,8 +36,11 @@ static struct _cache_table cache_table[] __cpuinitdata =
 {
 	{ 0x06, LVL_1_INST, 8 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x08, LVL_1_INST, 16 },	/* 4-way set assoc, 32 byte line size */
+	{ 0x09, LVL_1_INST, 32 },	/* 4-way set assoc, 64 byte line size */
 	{ 0x0a, LVL_1_DATA, 8 },	/* 2 way set assoc, 32 byte line size */
 	{ 0x0c, LVL_1_DATA, 16 },	/* 4-way set assoc, 32 byte line size */
+	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
+	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x23, LVL_3,      1024 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x25, LVL_3,      2048 },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -85,6 +88,18 @@ static struct _cache_table cache_table[] __cpuinitdata =
 	{ 0x85, LVL_2,    2048 },	/* 8-way set assoc, 32 byte line size */
 	{ 0x86, LVL_2,     512 },	/* 4-way set assoc, 64 byte line size */
 	{ 0x87, LVL_2,    1024 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd0, LVL_3,     512 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd1, LVL_3,    1024 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd2, LVL_3,    2048 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd6, LVL_3,    1024 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd7, LVL_3,    2038 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd8, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdc, LVL_3,    2048 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdd, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xde, LVL_3,    8192 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xe2, LVL_3,    2048 },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe3, LVL_3,    4096 },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe4, LVL_3,    8192 },	/* 16-way set assoc, 64 byte line size */
 	{ 0x00, 0, 0}
 };
 
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index b59ddcc88cd..0c0a455fe95 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -33,11 +33,13 @@ u64 mtrr_tom2;
 struct mtrr_state_type mtrr_state = {};
 EXPORT_SYMBOL_GPL(mtrr_state);
 
-#undef MODULE_PARAM_PREFIX
-#define MODULE_PARAM_PREFIX "mtrr."
-
-static int mtrr_show;
-module_param_named(show, mtrr_show, bool, 0);
+static int __initdata mtrr_show;
+static int __init mtrr_debug(char *opt)
+{
+	mtrr_show = 1;
+	return 0;
+}
+early_param("mtrr.show", mtrr_debug);
 
 /*
  * Returns the effective MTRR type for the region
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index d259e5d2e05..236a401b825 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -1594,8 +1594,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* kvm/qemu doesn't have mtrr set right, don't trim them all */
 	if (!highest_pfn) {
-		WARN(!kvm_para_available(), KERN_WARNING
-				"WARNING: strange, CPU MTRRs all blank?\n");
+		printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n");
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index da91701a234..169a120587b 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -15,8 +15,8 @@
  * - buffer allocation (memory accounting)
  *
  *
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Copyright (C) 2007-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
 
@@ -890,7 +890,7 @@ int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value)
 }
 
 static const struct ds_configuration ds_cfg_netburst = {
-	.name = "netburst",
+	.name = "Netburst",
 	.ctl[dsf_bts]		= (1 << 2) | (1 << 3),
 	.ctl[dsf_bts_kernel]	= (1 << 5),
 	.ctl[dsf_bts_user]	= (1 << 6),
@@ -904,7 +904,7 @@ static const struct ds_configuration ds_cfg_netburst = {
 #endif
 };
 static const struct ds_configuration ds_cfg_pentium_m = {
-	.name = "pentium m",
+	.name = "Pentium M",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 
 	.sizeof_field		= sizeof(long),
@@ -915,8 +915,8 @@ static const struct ds_configuration ds_cfg_pentium_m = {
 	.sizeof_rec[ds_pebs]	= sizeof(long) * 18,
 #endif
 };
-static const struct ds_configuration ds_cfg_core2 = {
-	.name = "core 2",
+static const struct ds_configuration ds_cfg_core2_atom = {
+	.name = "Core 2/Atom",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 	.ctl[dsf_bts_kernel]	= (1 << 9),
 	.ctl[dsf_bts_user]	= (1 << 10),
@@ -949,19 +949,22 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
-		case 0 ... 0xC:
-			/* sorry, don't know about them */
-			break;
-		case 0xD:
-		case 0xE: /* Pentium M */
+		case 0x9:
+		case 0xd: /* Pentium M */
 			ds_configure(&ds_cfg_pentium_m);
 			break;
-		default: /* Core2, Atom, ... */
-			ds_configure(&ds_cfg_core2);
+		case 0xf:
+		case 0x17: /* Core2 */
+		case 0x1c: /* Atom */
+			ds_configure(&ds_cfg_core2_atom);
+			break;
+		case 0x1a: /* i7 */
+		default:
+			/* sorry, don't know about them */
 			break;
 		}
 		break;
-	case 0xF:
+	case 0xf:
 		switch (c->x86_model) {
 		case 0x0:
 		case 0x1:
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index eb0a0703f4c..8f8f61a1fce 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -347,6 +347,7 @@ ENTRY(save_args)
 	popq_cfi %rax			/* move return address... */
 	mov PER_CPU_VAR(irq_stack_ptr),%rsp
 	EMPTY_FRAME 0
+	pushq_cfi %rbp			/* backlink for unwinder */
 	pushq_cfi %rax			/* ... to the new stack */
 	/*
 	 * We entered an interrupt context - irqs are off:
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index cd759ad9069..64d5ad0b8ad 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -628,11 +628,12 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 
 	switch (action & 0xf) {
 	case CPU_ONLINE:
-		INIT_DELAYED_WORK(&work.work, hpet_work);
+		INIT_DELAYED_WORK_ON_STACK(&work.work, hpet_work);
 		init_completion(&work.complete);
 		/* FIXME: add schedule_work_on() */
 		schedule_delayed_work_on(cpu, &work.work, 0);
 		wait_for_completion(&work.complete);
+		destroy_timer_on_stack(&work.work.timer);
 		break;
 	case CPU_DEAD:
 		if (hdev) {
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index e4d36bd56b6..0a7f6d6b120 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -2527,14 +2527,15 @@ static void irq_complete_move(struct irq_desc **descp)
 
 	vector = ~get_irq_regs()->orig_ax;
 	me = smp_processor_id();
+
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
 #ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
 		*descp = desc = move_irq_desc(desc, me);
 		/* get the new one */
 		cfg = desc->chip_data;
 #endif
-
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 		send_cleanup_vector(cfg);
+	}
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 520e6c1c5d2..f6ff71cdaba 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -78,15 +78,6 @@ void __init init_ISA_irqs(void)
 	}
 }
 
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.mask = CPU_MASK_NONE,
-	.name = "cascade",
-};
-
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
 	[0 ... IRQ0_VECTOR - 1] = -1,
 	[IRQ0_VECTOR] = 0,
@@ -198,9 +189,6 @@ void __init native_init_IRQ(void)
 			set_intr_gate(vector, interrupt[i]);
 	}
 
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-
 	/* setup after call gates are initialised (usually add in
 	 * the architecture specific gates)
 	 */
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 00c2bcd4146..d5768b1af08 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -5,7 +5,7 @@
  * This allows to use PCI devices that only support 32bit addresses on systems
  * with more than 4GB.
  *
- * See Documentation/DMA-mapping.txt for the interface specification.
+ * See Documentation/PCI/PCI-DMA-mapping.txt for the interface specification.
  *
  * Copyright 2002 Andi Kleen, SuSE Labs.
  * Subject to the GNU General Public License v2 only.
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 90b8e154bb5..e553803cd2d 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -80,7 +80,7 @@ static inline void setup_node_to_cpumask_map(void) { }
 #ifdef CONFIG_X86_64
 
 /* correctly size the local cpu masks */
-static void setup_cpu_local_masks(void)
+static void __init setup_cpu_local_masks(void)
 {
 	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
 	alloc_bootmem_cpumask_var(&cpu_callin_mask);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 4fa5243c206..0bc73d67acf 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -632,9 +632,16 @@ badframe:
 }
 
 #ifdef CONFIG_X86_32
-asmlinkage int sys_rt_sigreturn(struct pt_regs regs)
+/*
+ * Note: do not pass in pt_regs directly as with tail-call optimization
+ * GCC will incorrectly stomp on the caller's frame and corrupt user-space
+ * register state:
+ */
+asmlinkage int sys_rt_sigreturn(unsigned long __unused)
 {
-	return do_rt_sigreturn(&regs);
+	struct pt_regs *regs = (struct pt_regs *)&__unused;
+
+	return do_rt_sigreturn(regs);
 }
 #else /* !CONFIG_X86_32 */
 asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index aae15dd7260..89fce1b6d01 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -201,6 +201,7 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
 				destination_timeouts = 0;
 			}
 		}
+		cpu_relax();
 	}
 	return FLUSH_COMPLETE;
 }
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 23206ba1687..1d3302cc2dd 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -858,7 +858,7 @@ void __init vmi_init(void)
 #endif
 }
 
-void vmi_activate(void)
+void __init vmi_activate(void)
 {
 	unsigned long flags;