Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/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()

8 files changed, 248 insertions, 128 deletions

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 3a785da..5e3a351 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/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
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e485825..60a57b1 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/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);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 68e4a6f..c735830 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/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;
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 33eae20..898c2f4 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -347,8 +347,8 @@ static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
 	return l3;
 }
 
-static void __cpuinit
-amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
+					   int index)
 {
 	int node;
 
@@ -396,20 +396,39 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
 	this_leaf->l3 = l3_caches[node];
 }
 
+/*
+ * check whether a slot used for disabling an L3 index is occupied.
+ * @l3: L3 cache descriptor
+ * @slot: slot number (0..1)
+ *
+ * @returns: the disabled index if used or negative value if slot free.
+ */
+int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot)
+{
+	unsigned int reg = 0;
+
+	pci_read_config_dword(l3->dev, 0x1BC + slot * 4, &reg);
+
+	/* check whether this slot is activated already */
+	if (reg & (3UL << 30))
+		return reg & 0xfff;
+
+	return -1;
+}
+
 static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
 				  unsigned int slot)
 {
-	struct pci_dev *dev = this_leaf->l3->dev;
-	unsigned int reg = 0;
+	int index;
 
 	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
 		return -EINVAL;
 
-	if (!dev)
-		return -EINVAL;
+	index = amd_get_l3_disable_slot(this_leaf->l3, slot);
+	if (index >= 0)
+		return sprintf(buf, "%d\n", index);
 
-	pci_read_config_dword(dev, 0x1BC + slot * 4, &reg);
-	return sprintf(buf, "0x%08x\n", reg);
+	return sprintf(buf, "FREE\n");
 }
 
 #define SHOW_CACHE_DISABLE(slot)					\
@@ -451,37 +470,74 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
 	}
 }
 
-
-static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
-				   const char *buf, size_t count,
-				   unsigned int slot)
+/*
+ * disable a L3 cache index by using a disable-slot
+ *
+ * @l3:    L3 cache descriptor
+ * @cpu:   A CPU on the node containing the L3 cache
+ * @slot:  slot number (0..1)
+ * @index: index to disable
+ *
+ * @return: 0 on success, error status on failure
+ */
+int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot,
+			    unsigned long index)
 {
-	struct pci_dev *dev = this_leaf->l3->dev;
-	int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
-	unsigned long val = 0;
+	int ret = 0;
 
 #define SUBCACHE_MASK	(3UL << 20)
 #define SUBCACHE_INDEX	0xfff
 
-	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+	/*
+	 * check whether this slot is already used or
+	 * the index is already disabled
+	 */
+	ret = amd_get_l3_disable_slot(l3, slot);
+	if (ret >= 0)
 		return -EINVAL;
 
+	/*
+	 * check whether the other slot has disabled the
+	 * same index already
+	 */
+	if (index == amd_get_l3_disable_slot(l3, !slot))
+		return -EINVAL;
+
+	/* do not allow writes outside of allowed bits */
+	if ((index & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
+	    ((index & SUBCACHE_INDEX) > l3->indices))
+		return -EINVAL;
+
+	amd_l3_disable_index(l3, cpu, slot, index);
+
+	return 0;
+}
+
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+				  const char *buf, size_t count,
+				  unsigned int slot)
+{
+	unsigned long val = 0;
+	int cpu, err = 0;
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!dev)
+	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
 		return -EINVAL;
 
-	if (strict_strtoul(buf, 10, &val) < 0)
-		return -EINVAL;
+	cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
 
-	/* do not allow writes outside of allowed bits */
-	if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
-	    ((val & SUBCACHE_INDEX) > this_leaf->l3->indices))
+	if (strict_strtoul(buf, 10, &val) < 0)
 		return -EINVAL;
 
-	amd_l3_disable_index(this_leaf->l3, cpu, slot, val);
-
+	err = amd_set_l3_disable_slot(this_leaf->l3, cpu, slot, val);
+	if (err) {
+		if (err == -EEXIST)
+			printk(KERN_WARNING "L3 disable slot %d in use!\n",
+					    slot);
+		return err;
+	}
 	return count;
 }
 
@@ -502,7 +558,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
 
 #else	/* CONFIG_CPU_SUP_AMD */
 static void __cpuinit
-amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
 {
 };
 #endif /* CONFIG_CPU_SUP_AMD */
@@ -518,7 +574,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 		amd_cpuid4(index, &eax, &ebx, &ecx);
-		amd_check_l3_disable(index, this_leaf);
+		amd_check_l3_disable(this_leaf, index);
 	} else {
 		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
 	}
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
new file mode 100644
index 0000000..34b4dad
--- /dev/null
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -0,0 +1,63 @@
+/*
+ *	Routines to indentify additional cpu features that are scattered in
+ *	cpuid space.
+ */
+#include <linux/cpu.h>
+
+#include <asm/pat.h>
+#include <asm/processor.h>
+
+#include <asm/apic.h>
+
+struct cpuid_bit {
+	u16 feature;
+	u8 reg;
+	u8 bit;
+	u32 level;
+	u32 sub_leaf;
+};
+
+enum cpuid_regs {
+	CR_EAX = 0,
+	CR_ECX,
+	CR_EDX,
+	CR_EBX
+};
+
+void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
+{
+	u32 max_level;
+	u32 regs[4];
+	const struct cpuid_bit *cb;
+
+	static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
+		{ X86_FEATURE_IDA,		CR_EAX, 1, 0x00000006, 0 },
+		{ X86_FEATURE_ARAT,		CR_EAX, 2, 0x00000006, 0 },
+		{ X86_FEATURE_PLN,		CR_EAX, 4, 0x00000006, 0 },
+		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
+		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
+		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
+		{ X86_FEATURE_XSAVEOPT,		CR_EAX,	0, 0x0000000d, 1 },
+		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
+		{ X86_FEATURE_NPT,		CR_EDX, 0, 0x8000000a, 0 },
+		{ X86_FEATURE_LBRV,		CR_EDX, 1, 0x8000000a, 0 },
+		{ X86_FEATURE_SVML,		CR_EDX, 2, 0x8000000a, 0 },
+		{ X86_FEATURE_NRIPS,		CR_EDX, 3, 0x8000000a, 0 },
+		{ 0, 0, 0, 0, 0 }
+	};
+
+	for (cb = cpuid_bits; cb->feature; cb++) {
+
+		/* Verify that the level is valid */
+		max_level = cpuid_eax(cb->level & 0xffff0000);
+		if (max_level < cb->level ||
+		    max_level > (cb->level | 0xffff))
+			continue;
+
+		cpuid_count(cb->level, cb->sub_leaf, &regs[CR_EAX],
+			    &regs[CR_EBX], &regs[CR_ECX], &regs[CR_EDX]);
+
+		if (regs[cb->reg] & (1 << cb->bit))
+			set_cpu_cap(c, cb->feature);
+	}
+}
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/topology.c
index 10fa568..4397e98 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -1,62 +1,14 @@
 /*
- *	Routines to indentify additional cpu features that are scattered in
- *	cpuid space.
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
  */
-#include <linux/cpu.h>
 
+#include <linux/cpu.h>
+#include <asm/apic.h>
 #include <asm/pat.h>
 #include <asm/processor.h>
 
-#include <asm/apic.h>
-
-struct cpuid_bit {
-	u16 feature;
-	u8 reg;
-	u8 bit;
-	u32 level;
-};
-
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
-};
-
-void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
-{
-	u32 max_level;
-	u32 regs[4];
-	const struct cpuid_bit *cb;
-
-	static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
-		{ X86_FEATURE_IDA,   		CR_EAX, 1, 0x00000006 },
-		{ X86_FEATURE_ARAT,  		CR_EAX, 2, 0x00000006 },
-		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006 },
-		{ X86_FEATURE_CPB,   		CR_EDX, 9, 0x80000007 },
-		{ X86_FEATURE_NPT,   		CR_EDX, 0, 0x8000000a },
-		{ X86_FEATURE_LBRV,  		CR_EDX, 1, 0x8000000a },
-		{ X86_FEATURE_SVML,  		CR_EDX, 2, 0x8000000a },
-		{ X86_FEATURE_NRIPS, 		CR_EDX, 3, 0x8000000a },
-		{ 0, 0, 0, 0 }
-	};
-
-	for (cb = cpuid_bits; cb->feature; cb++) {
-
-		/* Verify that the level is valid */
-		max_level = cpuid_eax(cb->level & 0xffff0000);
-		if (max_level < cb->level ||
-		    max_level > (cb->level | 0xffff))
-			continue;
-
-		cpuid(cb->level, &regs[CR_EAX], &regs[CR_EBX],
-			&regs[CR_ECX], &regs[CR_EDX]);
-
-		if (regs[cb->reg] & (1 << cb->bit))
-			set_cpu_cap(c, cb->feature);
-	}
-}
-
 /* leaf 0xb SMT level */
 #define SMT_LEVEL	0
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index cbcf013..d401f1d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -526,44 +526,10 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 	return (edx & MWAIT_EDX_C1);
 }
 
-/*
- * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e.
- * For more information see
- * - Erratum #400 for NPT family 0xf and family 0x10 CPUs
- * - Erratum #365 for family 0x11 (not affected because C1e not in use)
- */
-static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
-{
-	u64 val;
-	if (c->x86_vendor != X86_VENDOR_AMD)
-		goto no_c1e_idle;
-
-	/* Family 0x0f models < rev F do not have C1E */
-	if (c->x86 == 0x0F && c->x86_model >= 0x40)
-		return 1;
-
-	if (c->x86 == 0x10) {
-		/*
-		 * check OSVW bit for CPUs that are not affected
-		 * by erratum #400
-		 */
-		if (cpu_has(c, X86_FEATURE_OSVW)) {
-			rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
-			if (val >= 2) {
-				rdmsrl(MSR_AMD64_OSVW_STATUS, val);
-				if (!(val & BIT(1)))
-					goto no_c1e_idle;
-			}
-		}
-		return 1;
-	}
-
-no_c1e_idle:
-	return 0;
-}
+bool c1e_detected;
+EXPORT_SYMBOL(c1e_detected);
 
 static cpumask_var_t c1e_mask;
-static int c1e_detected;
 
 void c1e_remove_cpu(int cpu)
 {
@@ -585,12 +551,12 @@ static void c1e_idle(void)
 		u32 lo, hi;
 
 		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+
 		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-			c1e_detected = 1;
+			c1e_detected = true;
 			if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
 				mark_tsc_unstable("TSC halt in AMD C1E");
 			printk(KERN_INFO "System has AMD C1E enabled\n");
-			set_cpu_cap(&boot_cpu_data, X86_FEATURE_AMDC1E);
 		}
 	}
 
@@ -639,7 +605,8 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		 */
 		printk(KERN_INFO "using mwait in idle threads.\n");
 		pm_idle = mwait_idle;
-	} else if (check_c1e_idle(c)) {
+	} else if (cpu_has_amd_erratum(amd_erratum_400)) {
+		/* E400: APIC timer interrupt does not wake up CPU from C1e */
 		printk(KERN_INFO "using C1E aware idle routine\n");
 		pm_idle = c1e_idle;
 	} else
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 37e68fc..9801498 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -36,15 +36,14 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf,
 
 	err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0],
 			       sizeof(struct _fpx_sw_bytes));
-
 	if (err)
-		return err;
+		return -EFAULT;
 
 	/*
 	 * First Magic check failed.
 	 */
 	if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1)
-		return -1;
+		return -EINVAL;
 
 	/*
 	 * Check for error scenarios.
@@ -52,19 +51,21 @@ int check_for_xstate(struct i387_fxsave_struct __user *buf,
 	if (fx_sw_user->xstate_size < min_xstate_size ||
 	    fx_sw_user->xstate_size > xstate_size ||
 	    fx_sw_user->xstate_size > fx_sw_user->extended_size)
-		return -1;
+		return -EINVAL;
 
 	err = __get_user(magic2, (__u32 *) (((void *)fpstate) +
 					    fx_sw_user->extended_size -
 					    FP_XSTATE_MAGIC2_SIZE));
+	if (err)
+		return err;
 	/*
 	 * Check for the presence of second magic word at the end of memory
 	 * layout. This detects the case where the user just copied the legacy
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (err || magic2 != FP_XSTATE_MAGIC2)
-		return -1;
+	if (magic2 != FP_XSTATE_MAGIC2)
+		return -EFAULT;
 
 	return 0;
 }