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: (22 commits)
  x86: Fix code patching for paravirt-alternatives on 486
  x86, msr: change msr-reg.o to obj-y, and export its symbols
  x86: Use hard_smp_processor_id() to get apic id for AMD K8 cpus
  x86, sched: Workaround broken sched domain creation for AMD Magny-Cours
  x86, mcheck: Use correct cpumask for shared bank4
  x86, cacheinfo: Fixup L3 cache information for AMD multi-node processors
  x86: Fix CPU llc_shared_map information for AMD Magny-Cours
  x86, msr: Fix msr-reg.S compilation with gas 2.16.1, on 32-bit too
  x86: Move kernel_fpu_using to irq_fpu_usable in asm/i387.h
  x86, msr: fix msr-reg.S compilation with gas 2.16.1
  x86, msr: Export the register-setting MSR functions via /dev/*/msr
  x86, msr: Create _on_cpu helpers for {rw,wr}msr_safe_regs()
  x86, msr: Have the _safe MSR functions return -EIO, not -EFAULT
  x86, msr: CFI annotations, cleanups for msr-reg.S
  x86, asm: Make _ASM_EXTABLE() usable from assembly code
  x86, asm: Add 32-bit versions of the combined CFI macros
  x86, AMD: Disable wrongly set X86_FEATURE_LAHF_LM CPUID bit
  x86, msr: Rewrite AMD rd/wrmsr variants
  x86, msr: Add rd/wrmsr interfaces with preset registers
  x86: add specific support for Intel Atom architecture
  ...

Documentation/ioctl/ioctl-number.txt

@@ -121,6 +121,7 @@ Code	Seq#	Include File		Comments
 'c'	00-7F	linux/comstats.h	conflict!
 'c'	00-7F	linux/coda.h		conflict!
 'c'	80-9F	arch/s390/include/asm/chsc.h
+'c'	A0-AF   arch/x86/include/asm/msr.h
 'd'	00-FF	linux/char/drm/drm/h	conflict!
 'd'	F0-FF	linux/digi1.h
 'e'	all	linux/digi1.h		conflict!

arch/x86/Kconfig.cpu

@@ -262,6 +262,15 @@ config MCORE2
 	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
 	  (not a typo)
 
+config MATOM
+	bool "Intel Atom"
+	---help---
+
+	  Select this for the Intel Atom platform. Intel Atom CPUs have an
+	  in-order pipelining architecture and thus can benefit from
+	  accordingly optimized code. Use a recent GCC with specific Atom
+	  support in order to fully benefit from selecting this option.
+
 config GENERIC_CPU
 	bool "Generic-x86-64"
 	depends on X86_64
@@ -295,7 +304,7 @@ config X86_CPU
 config X86_L1_CACHE_BYTES
 	int
 	default "128" if MPSC
-	default "64" if GENERIC_CPU || MK8 || MCORE2 || X86_32
+	default "64" if GENERIC_CPU || MK8 || MCORE2 || MATOM || X86_32
 
 config X86_INTERNODE_CACHE_BYTES
 	int
@@ -310,7 +319,7 @@ config X86_L1_CACHE_SHIFT
 	default "7" if MPENTIUM4 || MPSC
 	default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 || X86_GENERIC || GENERIC_CPU
+	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
 
 config X86_XADD
 	def_bool y
@@ -359,7 +368,7 @@ config X86_INTEL_USERCOPY
 
 config X86_USE_PPRO_CHECKSUM
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
 
 config X86_USE_3DNOW
 	def_bool y
@@ -387,7 +396,7 @@ config X86_P6_NOP
 
 config X86_TSC
 	def_bool y
-	depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64
+	depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) && !X86_NUMAQ) || X86_64
 
 config X86_CMPXCHG64
 	def_bool y
@@ -397,7 +406,7 @@ config X86_CMPXCHG64
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64)
+	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM)
 
 config X86_MINIMUM_CPU_FAMILY
 	int

arch/x86/Makefile

@@ -55,6 +55,8 @@ else
 
         cflags-$(CONFIG_MCORE2) += \
                 $(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
+	cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \
+		$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
         cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
         KBUILD_CFLAGS += $(cflags-y)
 

arch/x86/Makefile_32.cpu

@@ -33,6 +33,8 @@ cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)-f
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
 cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
+cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \
+	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
 
 # AMD Elan support
 cflags-$(CONFIG_X86_ELAN)	+= -march=i486

arch/x86/crypto/aesni-intel_glue.c

@@ -59,13 +59,6 @@ asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out,
 asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
 
-static inline int kernel_fpu_using(void)
-{
-	if (in_interrupt() && !(read_cr0() & X86_CR0_TS))
-		return 1;
-	return 0;
-}
-
 static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx)
 {
 	unsigned long addr = (unsigned long)raw_ctx;
@@ -89,7 +82,7 @@ static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx,
 		return -EINVAL;
 	}
 
-	if (kernel_fpu_using())
+	if (irq_fpu_usable())
 		err = crypto_aes_expand_key(ctx, in_key, key_len);
 	else {
 		kernel_fpu_begin();
@@ -110,7 +103,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (kernel_fpu_using())
+	if (irq_fpu_usable())
 		crypto_aes_encrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -123,7 +116,7 @@ static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (kernel_fpu_using())
+	if (irq_fpu_usable())
 		crypto_aes_decrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -349,7 +342,7 @@ static int ablk_encrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (kernel_fpu_using()) {
+	if (irq_fpu_usable()) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 		memcpy(cryptd_req, req, sizeof(*req));
@@ -370,7 +363,7 @@ static int ablk_decrypt(struct ablkcipher_request *req)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 
-	if (kernel_fpu_using()) {
+	if (irq_fpu_usable()) {
 		struct ablkcipher_request *cryptd_req =
 			ablkcipher_request_ctx(req);
 		memcpy(cryptd_req, req, sizeof(*req));

arch/x86/include/asm/asm.h

@@ -3,7 +3,7 @@
 
 #ifdef __ASSEMBLY__
 # define __ASM_FORM(x)	x
-# define __ASM_EX_SEC	.section __ex_table
+# define __ASM_EX_SEC	.section __ex_table, "a"
 #else
 # define __ASM_FORM(x)	" " #x " "
 # define __ASM_EX_SEC	" .section __ex_table,\"a\"\n"
@@ -38,10 +38,18 @@
 #define _ASM_DI		__ASM_REG(di)
 
 /* Exception table entry */
+#ifdef __ASSEMBLY__
+# define _ASM_EXTABLE(from,to)	    \
+	__ASM_EX_SEC ;		    \
+	_ASM_ALIGN ;		    \
+	_ASM_PTR from , to ;	    \
+	.previous
+#else
 # define _ASM_EXTABLE(from,to) \
 	__ASM_EX_SEC	\
 	_ASM_ALIGN "\n" \
 	_ASM_PTR #from "," #to "\n" \
 	" .previous\n"
+#endif
 
 #endif /* _ASM_X86_ASM_H */

arch/x86/include/asm/cpufeature.h

@@ -95,6 +95,7 @@
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
 #define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
 #define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */

arch/x86/include/asm/dwarf2.h

@@ -87,9 +87,25 @@
 	CFI_RESTORE \reg
 	.endm
 #else /*!CONFIG_X86_64*/
+	.macro pushl_cfi reg
+	pushl \reg
+	CFI_ADJUST_CFA_OFFSET 4
+	.endm
 
-	/* 32bit defenitions are missed yet */
+	.macro popl_cfi reg
+	popl \reg
+	CFI_ADJUST_CFA_OFFSET -4
+	.endm
 
+	.macro movl_cfi reg offset=0
+	movl %\reg, \offset(%esp)
+	CFI_REL_OFFSET \reg, \offset
+	.endm
+
+	.macro movl_cfi_restore offset reg
+	movl \offset(%esp), %\reg
+	CFI_RESTORE \reg
+	.endm
 #endif /*!CONFIG_X86_64*/
 #endif /*__ASSEMBLY__*/
 

arch/x86/include/asm/i387.h

@@ -301,6 +301,14 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
+static inline bool irq_fpu_usable(void)
+{
+	struct pt_regs *regs;
+
+	return !in_interrupt() || !(regs = get_irq_regs()) || \
+		user_mode(regs) || (read_cr0() & X86_CR0_TS);
+}
+
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
  * DNA fault but don't modify SSE registers. And these instructions

arch/x86/include/asm/module.h

@@ -17,6 +17,8 @@
 #define MODULE_PROC_FAMILY "586MMX "
 #elif defined CONFIG_MCORE2
 #define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_MATOM
+#define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
 #define MODULE_PROC_FAMILY "686 "
 #elif defined CONFIG_MPENTIUMII

arch/x86/include/asm/msr.h

@@ -3,10 +3,16 @@
 
 #include <asm/msr-index.h>
 
-#ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define X86_IOC_RDMSR_REGS	_IOWR('c', 0xA0, __u32[8])
+#define X86_IOC_WRMSR_REGS	_IOWR('c', 0xA1, __u32[8])
+
+#ifdef __KERNEL__
+
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/cpumask.h>
@@ -67,23 +73,7 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 		     ".previous\n\t"
 		     _ASM_EXTABLE(2b, 3b)
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), [fault] "i" (-EFAULT));
-	return EAX_EDX_VAL(val, low, high);
-}
-
-static inline unsigned long long native_read_msr_amd_safe(unsigned int msr,
-						      int *err)
-{
-	DECLARE_ARGS(val, low, high);
-
-	asm volatile("2: rdmsr ; xor %0,%0\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %3,%0 ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
-		     : "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), "D" (0x9c5a203a), "i" (-EFAULT));
+		     : "c" (msr), [fault] "i" (-EIO));
 	return EAX_EDX_VAL(val, low, high);
 }
 
@@ -106,13 +96,16 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
 		     _ASM_EXTABLE(2b, 3b)
 		     : [err] "=a" (err)
 		     : "c" (msr), "0" (low), "d" (high),
-		       [fault] "i" (-EFAULT)
+		       [fault] "i" (-EIO)
 		     : "memory");
 	return err;
 }
 
 extern unsigned long long native_read_tsc(void);
 
+extern int native_rdmsr_safe_regs(u32 regs[8]);
+extern int native_wrmsr_safe_regs(u32 regs[8]);
+
 static __always_inline unsigned long long __native_read_tsc(void)
 {
 	DECLARE_ARGS(val, low, high);
@@ -181,14 +174,44 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 	*p = native_read_msr_safe(msr, &err);
 	return err;
 }
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
+	u32 gprs[8] = { 0 };
 	int err;
 
-	*p = native_read_msr_amd_safe(msr, &err);
+	gprs[1] = msr;
+	gprs[7] = 0x9c5a203a;
+
+	err = native_rdmsr_safe_regs(gprs);
+
+	*p = gprs[0] | ((u64)gprs[2] << 32);
+
 	return err;
 }
 
+static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+{
+	u32 gprs[8] = { 0 };
+
+	gprs[0] = (u32)val;
+	gprs[1] = msr;
+	gprs[2] = val >> 32;
+	gprs[7] = 0x9c5a203a;
+
+	return native_wrmsr_safe_regs(gprs);
+}
+
+static inline int rdmsr_safe_regs(u32 regs[8])
+{
+	return native_rdmsr_safe_regs(regs);
+}
+
+static inline int wrmsr_safe_regs(u32 regs[8])
+{
+	return native_wrmsr_safe_regs(regs);
+}
+
 #define rdtscl(low)						\
 	((low) = (u32)__native_read_tsc())
 
@@ -228,6 +251,8 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
 void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
+int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
 #else  /*  CONFIG_SMP  */
 static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
 {
@@ -258,7 +283,15 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 {
 	return wrmsr_safe(msr_no, l, h);
 }
+static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
+{
+	return rdmsr_safe_regs(regs);
+}
+static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
+{
+	return wrmsr_safe_regs(regs);
+}
 #endif  /* CONFIG_SMP */
-#endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
+#endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_MSR_H */

arch/x86/include/asm/processor.h

@@ -713,13 +713,23 @@ static inline void cpu_relax(void)
 	rep_nop();
 }
 
-/* Stop speculative execution: */
+/* Stop speculative execution and prefetching of modified code. */
 static inline void sync_core(void)
 {
 	int tmp;
 
-	asm volatile("cpuid" : "=a" (tmp) : "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
+#if defined(CONFIG_M386) || defined(CONFIG_M486)
+	if (boot_cpu_data.x86 < 5)
+		/* There is no speculative execution.
+		 * jmp is a barrier to prefetching. */
+		asm volatile("jmp 1f\n1:\n" ::: "memory");
+	else
+#endif
+		/* cpuid is a barrier to speculative execution.
+		 * Prefetched instructions are automatically
+		 * invalidated when modified. */
+		asm volatile("cpuid" : "=a" (tmp) : "0" (1)
+			     : "ebx", "ecx", "edx", "memory");
 }
 
 static inline void __monitor(const void *eax, unsigned long ecx,

arch/x86/kernel/alternative.c

@@ -498,8 +498,8 @@ static void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	unsigned long flags;
 	local_irq_save(flags);
 	memcpy(addr, opcode, len);
-	local_irq_restore(flags);
 	sync_core();
+	local_irq_restore(flags);
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
 	return addr;

arch/x86/kernel/cpu/amd.c

@@ -252,6 +252,64 @@ static int __cpuinit nearby_node(int apicid)
 }
 #endif
 
+/*
+ * Fixup core topology information for AMD multi-node processors.
+ * Assumption 1: Number of cores in each internal node is the same.
+ * Assumption 2: Mixed systems with both single-node and dual-node
+ *               processors are not supported.
+ */
+#ifdef CONFIG_X86_HT
+static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_PCI
+	u32 t, cpn;
+	u8 n, n_id;
+	int cpu = smp_processor_id();
+
+	/* fixup topology information only once for a core */
+	if (cpu_has(c, X86_FEATURE_AMD_DCM))
+		return;
+
+	/* check for multi-node processor on boot cpu */
+	t = read_pci_config(0, 24, 3, 0xe8);
+	if (!(t & (1 << 29)))
+		return;
+
+	set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+
+	/* cores per node: each internal node has half the number of cores */
+	cpn = c->x86_max_cores >> 1;
+
+	/* even-numbered NB_id of this dual-node processor */
+	n = c->phys_proc_id << 1;
+
+	/*
+	 * determine internal node id and assign cores fifty-fifty to
+	 * each node of the dual-node processor
+	 */
+	t = read_pci_config(0, 24 + n, 3, 0xe8);
+	n = (t>>30) & 0x3;
+	if (n == 0) {
+		if (c->cpu_core_id < cpn)
+			n_id = 0;
+		else
+			n_id = 1;
+	} else {
+		if (c->cpu_core_id < cpn)
+			n_id = 1;
+		else
+			n_id = 0;
+	}
+
+	/* compute entire NodeID, use llc_shared_map to store sibling info */
+	per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id;
+
+	/* fixup core id to be in range from 0 to cpn */
+	c->cpu_core_id = c->cpu_core_id % cpn;
+#endif
+}
+#endif
+
 /*
  * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
  * Assumes number of cores is a power of two.
@@ -269,6 +327,9 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+	/* fixup topology information on multi-node processors */
+	if ((c->x86 == 0x10) && (c->x86_model == 9))
+		amd_fixup_dcm(c);
 #endif
 }
 
@@ -277,9 +338,10 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
 	int cpu = smp_processor_id();
 	int node;
-	unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
+	unsigned apicid = c->apicid;
+
+	node = per_cpu(cpu_llc_id, cpu);
 
-	node = c->phys_proc_id;
 	if (apicid_to_node[apicid] != NUMA_NO_NODE)
 		node = apicid_to_node[apicid];
 	if (!node_online(node)) {
@@ -406,12 +468,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		/*
 		 * Some BIOSes incorrectly force this feature, but only K8
 		 * revision D (model = 0x14) and later actually support it.
+		 * (AMD Erratum #110, docId: 25759).
 		 */
-		if (c->x86_model < 0x14)
+		if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+			u64 val;
+
 			clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
+			if (!rdmsrl_amd_safe(0xc001100d, &val)) {
+				val &= ~(1ULL << 32);
+				wrmsrl_amd_safe(0xc001100d, val);
+			}
+		}
+
 	}
 	if (c->x86 == 0x10 || c->x86 == 0x11)
 		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	/* get apicid instead of initial apic id from cpuid */
+	c->apicid = hard_smp_processor_id();
 #else
 
 	/*

arch/x86/kernel/cpu/intel_cacheinfo.c

@@ -241,7 +241,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	case 0:
 		if (!l1->val)
 			return;
-		assoc = l1->assoc;
+		assoc = assocs[l1->assoc];
 		line_size = l1->line_size;
 		lines_per_tag = l1->lines_per_tag;
 		size_in_kb = l1->size_in_kb;
@@ -249,7 +249,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	case 2:
 		if (!l2.val)
 			return;
-		assoc = l2.assoc;
+		assoc = assocs[l2.assoc];
 		line_size = l2.line_size;
 		lines_per_tag = l2.lines_per_tag;
 		/* cpu_data has errata corrections for K7 applied */
@@ -258,10 +258,14 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	case 3:
 		if (!l3.val)
 			return;
-		assoc = l3.assoc;
+		assoc = assocs[l3.assoc];
 		line_size = l3.line_size;
 		lines_per_tag = l3.lines_per_tag;
 		size_in_kb = l3.size_encoded * 512;
+		if (boot_cpu_has(X86_FEATURE_AMD_DCM)) {
+			size_in_kb = size_in_kb >> 1;
+			assoc = assoc >> 1;
+		}
 		break;
 	default:
 		return;
@@ -270,18 +274,14 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	eax->split.is_self_initializing = 1;
 	eax->split.type = types[leaf];
 	eax->split.level = levels[leaf];
-	if (leaf == 3)
-		eax->split.num_threads_sharing =
-			current_cpu_data.x86_max_cores - 1;
-	else
-		eax->split.num_threads_sharing = 0;
+	eax->split.num_threads_sharing = 0;
 	eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
 
 
-	if (assoc == 0xf)
+	if (assoc == 0xffff)
 		eax->split.is_fully_associative = 1;
 	ebx->split.coherency_line_size = line_size - 1;
-	ebx->split.ways_of_associativity = assocs[assoc] - 1;
+	ebx->split.ways_of_associativity = assoc - 1;
 	ebx->split.physical_line_partition = lines_per_tag - 1;
 	ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
 		(ebx->split.ways_of_associativity + 1) - 1;
@@ -523,6 +523,18 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 	int index_msb, i;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
+	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
+		struct cpuinfo_x86 *d;
+		for_each_online_cpu(i) {
+			if (!per_cpu(cpuid4_info, i))
+				continue;
+			d = &cpu_data(i);
+			this_leaf = CPUID4_INFO_IDX(i, index);
+			cpumask_copy(to_cpumask(this_leaf->shared_cpu_map),
+				     d->llc_shared_map);
+		}
+		return;
+	}
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
 

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -489,12 +489,14 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	int i, err = 0;
 	struct threshold_bank *b = NULL;
 	char name[32];
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
 
 	sprintf(name, "threshold_bank%i", bank);
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = cpumask_first(cpu_core_mask(cpu));
+		i = cpumask_first(c->llc_shared_map);
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -514,7 +516,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		cpumask_copy(b->cpus, cpu_core_mask(cpu));
+		cpumask_copy(b->cpus, c->llc_shared_map);
 		per_cpu(threshold_banks, cpu)[bank] = b;
 
 		goto out;
@@ -539,7 +541,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, cpu_core_mask(cpu));
+	cpumask_copy(b->cpus, c->llc_shared_map);
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;

arch/x86/kernel/cpu/proc.c

@@ -116,11 +116,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize);
 #endif
 	seq_printf(m, "clflush size\t: %u\n", c->x86_clflush_size);
-#ifdef CONFIG_X86_64
 	seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment);
 	seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n",
 		   c->x86_phys_bits, c->x86_virt_bits);
-#endif
 
 	seq_printf(m, "power management:");
 	for (i = 0; i < 32; i++) {

arch/x86/kernel/msr.c

@@ -1,6 +1,7 @@
 /* ----------------------------------------------------------------------- *
  *
  *   Copyright 2000-2008 H. Peter Anvin - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author: H. Peter Anvin
  *
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -80,11 +81,8 @@ static ssize_t msr_read(struct file *file, char __user *buf,
 
 	for (; count; count -= 8) {
 		err = rdmsr_safe_on_cpu(cpu, reg, &data[0], &data[1]);
-		if (err) {
-			if (err == -EFAULT) /* Fix idiotic error code */
-				err = -EIO;
+		if (err)
 			break;
-		}
 		if (copy_to_user(tmp, &data, 8)) {
 			err = -EFAULT;
 			break;
@@ -115,11 +113,8 @@ static ssize_t msr_write(struct file *file, const char __user *buf,
 			break;
 		}
 		err = wrmsr_safe_on_cpu(cpu, reg, data[0], data[1]);
-		if (err) {
-			if (err == -EFAULT) /* Fix idiotic error code */
-				err = -EIO;
+		if (err)
 			break;
-		}
 		tmp += 2;
 		bytes += 8;
 	}
@@ -127,6 +122,54 @@ static ssize_t msr_write(struct file *file, const char __user *buf,
 	return bytes ? bytes : err;
 }
 
+static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg)
+{
+	u32 __user *uregs = (u32 __user *)arg;
+	u32 regs[8];
+	int cpu = iminor(file->f_path.dentry->d_inode);
+	int err;
+
+	switch (ioc) {
+	case X86_IOC_RDMSR_REGS:
+		if (!(file->f_mode & FMODE_READ)) {
+			err = -EBADF;
+			break;
+		}
+		if (copy_from_user(&regs, uregs, sizeof regs)) {
+			err = -EFAULT;
+			break;
+		}
+		err = rdmsr_safe_regs_on_cpu(cpu, regs);
+		if (err)
+			break;
+		if (copy_to_user(uregs, &regs, sizeof regs))
+			err = -EFAULT;
+		break;
+
+	case X86_IOC_WRMSR_REGS:
+		if (!(file->f_mode & FMODE_WRITE)) {
+			err = -EBADF;
+			break;
+		}
+		if (copy_from_user(&regs, uregs, sizeof regs)) {
+			err = -EFAULT;
+			break;
+		}
+		err = wrmsr_safe_regs_on_cpu(cpu, regs);
+		if (err)
+			break;
+		if (copy_to_user(uregs, &regs, sizeof regs))
+			err = -EFAULT;
+		break;
+
+	default:
+		err = -ENOTTY;
+		break;
+	}
+
+	return err;
+}
+
 static int msr_open(struct inode *inode, struct file *file)
 {
 	unsigned int cpu = iminor(file->f_path.dentry->d_inode);
@@ -157,6 +200,8 @@ static const struct file_operations msr_fops = {
 	.read = msr_read,
 	.write = msr_write,
 	.open = msr_open,
+	.unlocked_ioctl = msr_ioctl,
+	.compat_ioctl = msr_ioctl,
 };
 
 static int __cpuinit msr_device_create(int cpu)