Skip to contentSkip to conversation

x86/cpu for v2.6.32

GIT PULL Ingo Molnar 1 participant 1 message Sep 11, 2009

Subsystems (6)
lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the x86-cpu-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git x86-cpu-for-linus

Thanks,

Ingo

------------------>
Andreas Herrmann (4):
x86: Fix CPU llc_shared_map information for AMD Magny-Cours x86, cacheinfo: Fixup L3 cache information for AMD multi-node processors x86, mcheck: Use correct cpumask for shared bank4
x86, sched: Workaround broken sched domain creation for AMD Magny-Cours

Ben Hutchings (1):
x86: Fix code patching for paravirt-alternatives on 486

Borislav Petkov (3):
x86, msr: Add rd/wrmsr interfaces with preset registers x86, msr: Rewrite AMD rd/wrmsr variants
x86, AMD: Disable wrongly set X86_FEATURE_LAHF_LM CPUID bit

H. Peter Anvin (8):
x86, asm: Add 32-bit versions of the combined CFI macros x86, asm: Make _ASM_EXTABLE() usable from assembly code x86, msr: CFI annotations, cleanups for msr-reg.S
x86, msr: Have the _safe MSR functions return -EIO, not -EFAULT x86, msr: Create _on_cpu helpers for {rw,wr}msr_safe_regs() x86, msr: Export the register-setting MSR functions via /dev/*/msr x86, msr: fix msr-reg.S compilation with gas 2.16.1 x86, msr: change msr-reg.o to obj-y, and export its symbols

Huang Ying (1):
x86: Move kernel_fpu_using to irq_fpu_usable in asm/i387.h

Ingo Molnar (1):
x86, msr: Fix msr-reg.S compilation with gas 2.16.1, on 32-bit too

Jaswinder Singh Rajput (1):
x86, cpu: cpu/proc.c display cache alignment and address sizes for 32 bit

Jeremy Fitzhardinge (1):
x86/paravirt: split paravirt definitions into paravirt_types.h

Tobias Doerffel (1):
x86: add specific support for Intel Atom architecture

Yinghai Lu (1):
x86: Use hard_smp_processor_id() to get apic id for AMD K8 cpus

 Documentation/ioctl/ioctl-number.txt  |    1 +
 arch/x86/Kconfig.cpu                  |   19 +-
 arch/x86/Makefile                     |    2 +
 arch/x86/Makefile_32.cpu              |    2 +
 arch/x86/crypto/aesni-intel_glue.c    |   17 +-
 arch/x86/include/asm/asm.h            |   10 +-
 arch/x86/include/asm/cpufeature.h     |    1 +
 arch/x86/include/asm/dwarf2.h         |   18 +-
 arch/x86/include/asm/i387.h           |    8 +
 arch/x86/include/asm/module.h         |    2 +
 arch/x86/include/asm/msr.h            |   75 +++-
 arch/x86/include/asm/paravirt.h       |  746 ++-------------------------------
 arch/x86/include/asm/paravirt_types.h |  721 +++++++++++++++++++++++++++++++
 arch/x86/include/asm/processor.h      |   16 +-
 arch/x86/kernel/alternative.c         |    2 +-
 arch/x86/kernel/cpu/amd.c             |   80 ++++-
 arch/x86/kernel/cpu/intel_cacheinfo.c |   32 +-
 arch/x86/kernel/cpu/mcheck/mce_amd.c  |    8 +-
 arch/x86/kernel/cpu/proc.c            |    2 -
 arch/x86/kernel/msr.c                 |   61 +++-
 arch/x86/kernel/paravirt.c            |    3 +-
 arch/x86/kernel/smpboot.c             |    3 +-
 arch/x86/lib/Makefile                 |    2 +
 arch/x86/lib/msr-reg-export.c         |    5 +
 arch/x86/lib/msr-reg.S                |  102 +++++
 arch/x86/lib/msr.c                    |   49 +++
 arch/x86/xen/enlighten.c              |    2 +-
 27 files changed, 1203 insertions(+), 786 deletions(-)
 create mode 100644 arch/x86/include/asm/paravirt_types.h
 create mode 100644 arch/x86/lib/msr-reg-export.c
 create mode 100644 arch/x86/lib/msr-reg.S
Documentation/ioctl/ioctl-number.txt +1 -0
index dbea4f9..1c058b5 100644
@@ -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 +14 -5
index 8130334..527519b 100644
@@ -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 +2 -0
index 1b68659..8a4c24c 100644
@@ -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 +2 -0
index 80177ec..30e9a26 100644
@@ -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 +5 -12
index c580c5e..7667235 100644
@@ -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 +9 -1
index 56be78f..b3ed1e1 100644
@@ -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 +1 -0
index 4a28d22..847fee6 100644
@@ -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 +17 -1
index 3afc5e8..ae6253a 100644
@@ -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 +8 -0
index 175adf5..fb7f0d6 100644
@@ -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 +2 -0
index 47d6274..e959c4a 100644
@@ -28,6 +28,8 @@ struct mod_arch_specific {};
 #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 +54 -21

127 lines not on this page · raw message

arch/x86/include/asm/paravirt.h +33 -713

804 lines not on this page · raw message

arch/x86/include/asm/paravirt_types.h new file +721 -0

721 lines not on this page · raw message

arch/x86/include/asm/processor.h +13 -3
index c776826..2db56c5 100644
@@ -703,13 +703,23 @@ 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 +1 -1
index f576587..b8ebd0b 100644
@@ -490,8 +490,8 @@ void *text_poke_early(void *addr, const void *opcode, size_t len)
 	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 +77 -3

110 lines not on this page · raw message

arch/x86/kernel/cpu/intel_cacheinfo.c +22 -10
index 789efe2..cb98a73 100644
@@ -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;
@@ -522,6 +522,18 @@ 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 +5 -3
index ddae216..1fecba4 100644
@@ -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 +0 -2
index d5e3039..f82706a 100644
@@ -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 +53 -8

93 lines not on this page · raw message

arch/x86/kernel/paravirt.c +2 -1
index 70ec9b9..f5b0b4a 100644
@@ -362,8 +362,9 @@ struct pv_cpu_ops pv_cpu_ops = {
 #endif
 	.wbinvd = native_wbinvd,
 	.read_msr = native_read_msr_safe,
-	.read_msr_amd = native_read_msr_amd_safe,
+	.rdmsr_regs = native_rdmsr_safe_regs,
 	.write_msr = native_write_msr_safe,
+	.wrmsr_regs = native_wrmsr_safe_regs,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
 	.read_tscp = native_read_tscp,
arch/x86/kernel/smpboot.c +2 -1
index 2fecda6..c36cc14 100644
@@ -434,7 +434,8 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	 * For perf, we return last level cache shared map.
 	 * And for power savings, we return cpu_core_map
 	 */
-	if (sched_mc_power_savings || sched_smt_power_savings)
+	if ((sched_mc_power_savings || sched_smt_power_savings) &&
+	    !(cpu_has(c, X86_FEATURE_AMD_DCM)))
 		return cpu_core_mask(cpu);
 	else
 		return c->llc_shared_map;
arch/x86/lib/Makefile +2 -0
index 07c3189..9e60920 100644
@@ -9,6 +9,8 @@ lib-y += thunk_$(BITS).o
 lib-y += usercopy_$(BITS).o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
 
+obj-y += msr-reg.o msr-reg-export.o
+
 ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
         lib-y += checksum_32.o
arch/x86/lib/msr-reg-export.c new file +5 -0
new file mode 100644
index 0000000..a311cc5
@@ -0,0 +1,5 @@
+#include <linux/module.h>
+#include <asm/msr.h>
+
+EXPORT_SYMBOL(native_rdmsr_safe_regs);
+EXPORT_SYMBOL(native_wrmsr_safe_regs);
arch/x86/lib/msr-reg.S new file +102 -0

102 lines not on this page · raw message

arch/x86/lib/msr.c +49 -0

52 lines not on this page · raw message

arch/x86/xen/enlighten.c +1 -1
index 0a1700a..a8432d8 100644
@@ -713,7 +713,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 	set:
 		base = ((u64)high << 32) | low;
 		if (HYPERVISOR_set_segment_base(which, base) != 0)
-			ret = -EFAULT;
+			ret = -EIO;
 		break;
 #endif