Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/tip/linux-2.6-tip

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86: Fix keeping track of AMD C1E
  x86, cpu: Package Level Thermal Control, Power Limit Notification definitions
  x86, cpu: Export AMD errata definitions
  x86, cpu: Use AMD errata checking framework for erratum 383
  x86, cpu: Clean up AMD erratum 400 workaround
  x86, cpu: AMD errata checking framework
  x86, cpu: Split addon_cpuid_features.c
  x86, cpu: Clean up formatting in cpufeature.h, remove override
  x86, cpu: Enumerate xsaveopt
  x86, cpu: Add xsaveopt cpufeature
  x86, cpu: Make init_scattered_cpuid_features() consider cpuid subleaves
  x86, cpu: Support the features flags in new CPUID leaf 7
  x86, cpu: Add CPU flags for F16C and RDRND
  x86: Look for IA32_ENERGY_PERF_BIAS support
  x86, AMD: Extend support to future families
  x86, cacheinfo: Carve out L3 cache slot accessors
  x86, xsave: Cleanup return codes in check_for_xstate()

arch/x86/include/asm/acpi.h

@@ -134,7 +134,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 	    boot_cpu_data.x86_model <= 0x05 &&
 	    boot_cpu_data.x86_mask < 0x0A)
 		return 1;
-	else if (boot_cpu_has(X86_FEATURE_AMDC1E))
+	else if (c1e_detected)
 		return 1;
 	else
 		return max_cstate;

arch/x86/include/asm/cpufeature.h

@@ -6,7 +6,7 @@
 
 #include <asm/required-features.h>
 
-#define NCAPINTS	9	/* N 32-bit words worth of info */
+#define NCAPINTS	10	/* N 32-bit words worth of info */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used
@@ -89,7 +89,7 @@
 #define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
 #define X86_FEATURE_11AP	(3*32+19) /* "" Bad local APIC aka 11AP */
 #define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_AMDC1E	(3*32+21) /* AMD C1E detected */
+					  /* 21 available, was AMD_C1E */
 #define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
@@ -124,6 +124,8 @@
 #define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
 #define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
 #define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C	(4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRND	(4*32+30) /* The RDRAND instruction */
 #define X86_FEATURE_HYPERVISOR	(4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
@@ -157,22 +159,29 @@
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
- * CPUID levels like 0x6, 0xA etc
+ * CPUID levels like 0x6, 0xA etc, word 7
  */
 #define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
 #define X86_FEATURE_ARAT	(7*32+ 1) /* Always Running APIC Timer */
 #define X86_FEATURE_CPB		(7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB		(7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_XSAVEOPT	(7*32+ 4) /* Optimized Xsave */
+#define X86_FEATURE_PLN		(7*32+ 5) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		(7*32+ 6) /* Intel Package Thermal Status */
 
-/* Virtualization flags: Linux defined */
+/* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        (8*32+ 1) /* Intel Virtual NMI */
 #define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
 #define X86_FEATURE_EPT         (8*32+ 3) /* Intel Extended Page Table */
 #define X86_FEATURE_VPID        (8*32+ 4) /* Intel Virtual Processor ID */
-#define X86_FEATURE_NPT		(8*32+5)  /* AMD Nested Page Table support */
-#define X86_FEATURE_LBRV	(8*32+6)  /* AMD LBR Virtualization support */
-#define X86_FEATURE_SVML	(8*32+7)  /* "svm_lock" AMD SVM locking MSR */
-#define X86_FEATURE_NRIPS	(8*32+8)  /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_NPT		(8*32+ 5) /* AMD Nested Page Table support */
+#define X86_FEATURE_LBRV	(8*32+ 6) /* AMD LBR Virtualization support */
+#define X86_FEATURE_SVML	(8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
+#define X86_FEATURE_NRIPS	(8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
+#define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -194,7 +203,9 @@ extern const char * const x86_power_flags[32];
 	   (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) ||	\
 	   (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) ||	\
 	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
-	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) )	\
+	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ||	\
+	   (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) ||	\
+	   (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )	\
 	  ? 1 :								\
 	 test_cpu_cap(c, bit))
 

arch/x86/include/asm/msr-index.h

@@ -226,12 +226,14 @@
 #define MSR_IA32_THERM_CONTROL		0x0000019a
 #define MSR_IA32_THERM_INTERRUPT	0x0000019b
 
-#define THERM_INT_LOW_ENABLE		(1 << 0)
-#define THERM_INT_HIGH_ENABLE		(1 << 1)
+#define THERM_INT_HIGH_ENABLE		(1 << 0)
+#define THERM_INT_LOW_ENABLE		(1 << 1)
+#define THERM_INT_PLN_ENABLE		(1 << 24)
 
 #define MSR_IA32_THERM_STATUS		0x0000019c
 
 #define THERM_STATUS_PROCHOT		(1 << 0)
+#define THERM_STATUS_POWER_LIMIT	(1 << 10)
 
 #define MSR_THERM2_CTL			0x0000019d
 
@@ -241,6 +243,19 @@
 
 #define MSR_IA32_TEMPERATURE_TARGET	0x000001a2
 
+#define MSR_IA32_ENERGY_PERF_BIAS	0x000001b0
+
+#define MSR_IA32_PACKAGE_THERM_STATUS		0x000001b1
+
+#define PACKAGE_THERM_STATUS_PROCHOT		(1 << 0)
+#define PACKAGE_THERM_STATUS_POWER_LIMIT	(1 << 10)
+
+#define MSR_IA32_PACKAGE_THERM_INTERRUPT	0x000001b2
+
+#define PACKAGE_THERM_INT_HIGH_ENABLE		(1 << 0)
+#define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
+#define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
+
 /* MISC_ENABLE bits: architectural */
 #define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
 #define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)

arch/x86/include/asm/processor.h

@@ -762,6 +762,7 @@ extern void init_c1e_mask(void);
 extern unsigned long		boot_option_idle_override;
 extern unsigned long		idle_halt;
 extern unsigned long		idle_nomwait;
+extern bool			c1e_detected;
 
 /*
  * on systems with caches, caches must be flashed as the absolute
@@ -1025,4 +1026,24 @@ unsigned long calc_aperfmperf_ratio(struct aperfmperf *old,
 	return ratio;
 }
 
+/*
+ * AMD errata checking
+ */
+#ifdef CONFIG_CPU_SUP_AMD
+extern const int amd_erratum_383[];
+extern const int amd_erratum_400[];
+extern bool cpu_has_amd_erratum(const int *);
+
+#define AMD_LEGACY_ERRATUM(...)		{ -1, __VA_ARGS__, 0 }
+#define AMD_OSVW_ERRATUM(osvw_id, ...)	{ osvw_id, __VA_ARGS__, 0 }
+#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \
+	((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end))
+#define AMD_MODEL_RANGE_FAMILY(range)	(((range) >> 24) & 0xff)
+#define AMD_MODEL_RANGE_START(range)	(((range) >> 12) & 0xfff)
+#define AMD_MODEL_RANGE_END(range)	((range) & 0xfff)
+
+#else
+#define cpu_has_amd_erratum(x)	(false)
+#endif /* CONFIG_CPU_SUP_AMD */
+
 #endif /* _ASM_X86_PROCESSOR_H */

arch/x86/include/asm/required-features.h

@@ -84,5 +84,7 @@
 #define REQUIRED_MASK5	0
 #define REQUIRED_MASK6	0
 #define REQUIRED_MASK7	0
+#define REQUIRED_MASK8	0
+#define REQUIRED_MASK9	0
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */

arch/x86/kernel/cpu/Makefile

@@ -12,7 +12,7 @@ endif
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_common.o		:= $(nostackp)
 
-obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
+obj-y			:= intel_cacheinfo.o scattered.o topology.o
 obj-y			+= proc.o capflags.o powerflags.o common.o
 obj-y			+= vmware.o hypervisor.o sched.o mshyperv.o
 

arch/x86/kernel/cpu/amd.c

@@ -466,7 +466,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 
 	}
-	if (c->x86 == 0x10 || c->x86 == 0x11)
+	if (c->x86 >= 0x10)
 		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
 	/* get apicid instead of initial apic id from cpuid */
@@ -529,7 +529,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 			num_cache_leaves = 3;
 	}
 
-	if (c->x86 >= 0xf && c->x86 <= 0x11)
+	if (c->x86 >= 0xf)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
 	if (cpu_has_xmm2) {
@@ -546,7 +546,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		fam10h_check_enable_mmcfg();
 	}
 
-	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
+	if (c == &boot_cpu_data && c->x86 >= 0xf) {
 		unsigned long long tseg;
 
 		/*
@@ -609,3 +609,74 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
 };
 
 cpu_dev_register(amd_cpu_dev);
+
+/*
+ * AMD errata checking
+ *
+ * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
+ * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that
+ * have an OSVW id assigned, which it takes as first argument. Both take a
+ * variable number of family-specific model-stepping ranges created by
+ * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const
+ * int[] in arch/x86/include/asm/processor.h.
+ *
+ * Example:
+ *
+ * const int amd_erratum_319[] =
+ *	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2),
+ *			   AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0),
+ *			   AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0));
+ */
+
+const int amd_erratum_400[] =
+	AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+			    AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
+EXPORT_SYMBOL_GPL(amd_erratum_400);
+
+const int amd_erratum_383[] =
+	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
+EXPORT_SYMBOL_GPL(amd_erratum_383);
+
+bool cpu_has_amd_erratum(const int *erratum)
+{
+	struct cpuinfo_x86 *cpu = &current_cpu_data;
+	int osvw_id = *erratum++;
+	u32 range;
+	u32 ms;
+
+	/*
+	 * If called early enough that current_cpu_data hasn't been initialized
+	 * yet, fall back to boot_cpu_data.
+	 */
+	if (cpu->x86 == 0)
+		cpu = &boot_cpu_data;
+
+	if (cpu->x86_vendor != X86_VENDOR_AMD)
+		return false;
+
+	if (osvw_id >= 0 && osvw_id < 65536 &&
+	    cpu_has(cpu, X86_FEATURE_OSVW)) {
+		u64 osvw_len;
+
+		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len);
+		if (osvw_id < osvw_len) {
+			u64 osvw_bits;
+
+			rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6),
+			    osvw_bits);
+			return osvw_bits & (1ULL << (osvw_id & 0x3f));
+		}
+	}
+
+	/* OSVW unavailable or ID unknown, match family-model-stepping range */
+	ms = (cpu->x86_model << 8) | cpu->x86_mask;
+	while ((range = *erratum++))
+		if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) &&
+		    (ms >= AMD_MODEL_RANGE_START(range)) &&
+		    (ms <= AMD_MODEL_RANGE_END(range)))
+			return true;
+
+	return false;
+}
+
+EXPORT_SYMBOL_GPL(cpu_has_amd_erratum);

arch/x86/kernel/cpu/common.c

@@ -551,6 +551,16 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[4] = excap;
 	}
 
+	/* Additional Intel-defined flags: level 0x00000007 */
+	if (c->cpuid_level >= 0x00000007) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx);
+
+		if (eax > 0)
+			c->x86_capability[9] = ebx;
+	}
+
 	/* AMD-defined flags: level 0x80000001 */
 	xlvl = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = xlvl;