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

Pull x86 cpu handling changes from Ingo Molnar:
 "Bigger changes:

   - Intel CPU hardware-enablement: new vector instructions support
     (AVX-512), by Fenghua Yu.

   - Support the clflushopt instruction and use it in appropriate
     places.  clflushopt is similar to clflush but with more relaxed
     ordering, by Ross Zwisler.

   - MSR accessor cleanups, by Borislav Petkov.

   - 'forcepae' boot flag for those who have way too much time to spend
     on way too old Pentium-M systems and want to live way too
     dangerously, by Chris Bainbridge"

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, cpu: Add forcepae parameter for booting PAE kernels on PAE-disabled Pentium M
  Rename TAINT_UNSAFE_SMP to TAINT_CPU_OUT_OF_SPEC
  x86, intel: Make MSR_IA32_MISC_ENABLE bit constants systematic
  x86, Intel: Convert to the new bit access MSR accessors
  x86, AMD: Convert to the new bit access MSR accessors
  x86: Add another set of MSR accessor functions
  x86: Use clflushopt in drm_clflush_virt_range
  x86: Use clflushopt in drm_clflush_page
  x86: Use clflushopt in clflush_cache_range
  x86: Add support for the clflushopt instruction
  x86, AVX-512: Enable AVX-512 States Context Switch
  x86, AVX-512: AVX-512 Feature Detection

5 files changed, 75 insertions, 31 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e099f9502ac..bc507d7640f 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -217,9 +217,14 @@
 #define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_MPX		(9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	(9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_RDSEED	(9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		(9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	(9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_CLFLUSHOPT	(9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_AVX512PF	(9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	(9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	(9*32+28) /* AVX-512 Conflict Detection */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index e139b13f2a3..de36f22eb0b 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -214,6 +214,8 @@ do {                                                            \
 
 struct msr *msrs_alloc(void);
 void msrs_free(struct msr *msrs);
+int msr_set_bit(u32 msr, u8 bit);
+int msr_clear_bit(u32 msr, u8 bit);
 
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 645cad2c95f..e820c080a4e 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -191,6 +191,14 @@ static inline void clflush(volatile void *__p)
 	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
 }
 
+static inline void clflushopt(volatile void *__p)
+{
+	alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
+		       ".byte 0x66; clflush %P0",
+		       X86_FEATURE_CLFLUSHOPT,
+		       "+m" (*(volatile char __force *)__p));
+}
+
 #define nop() asm volatile ("nop")
 
 
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 554738963b2..6c1d7411eb0 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -6,11 +6,14 @@
 
 #define XSTATE_CPUID		0x0000000d
 
-#define XSTATE_FP	0x1
-#define XSTATE_SSE	0x2
-#define XSTATE_YMM	0x4
-#define XSTATE_BNDREGS	0x8
-#define XSTATE_BNDCSR	0x10
+#define XSTATE_FP		0x1
+#define XSTATE_SSE		0x2
+#define XSTATE_YMM		0x4
+#define XSTATE_BNDREGS		0x8
+#define XSTATE_BNDCSR		0x10
+#define XSTATE_OPMASK		0x20
+#define XSTATE_ZMM_Hi256	0x40
+#define XSTATE_Hi16_ZMM		0x80
 
 #define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
 
@@ -23,7 +26,8 @@
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
 /* Supported features which support lazy state saving */
-#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
+#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
+			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
 
 /* Supported features which require eager state saving */
 #define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c19fc60ff06..4924f4be2b9 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -368,33 +368,58 @@
 #define THERM_LOG_THRESHOLD1           (1 << 9)
 
 /* MISC_ENABLE bits: architectural */
-#define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
-#define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)
-#define MSR_IA32_MISC_ENABLE_EMON		(1ULL << 7)
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL	(1ULL << 11)
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL	(1ULL << 12)
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP	(1ULL << 16)
-#define MSR_IA32_MISC_ENABLE_MWAIT		(1ULL << 18)
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID	(1ULL << 22)
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE	(1ULL << 23)
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE		(1ULL << 34)
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT		0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING		(1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+#define MSR_IA32_MISC_ENABLE_TCC_BIT			1
+#define MSR_IA32_MISC_ENABLE_TCC			(1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
+#define MSR_IA32_MISC_ENABLE_EMON_BIT			7
+#define MSR_IA32_MISC_ENABLE_EMON			(1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT		11
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT		12
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL		(1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT	16
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP		(1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
+#define MSR_IA32_MISC_ENABLE_MWAIT_BIT			18
+#define MSR_IA32_MISC_ENABLE_MWAIT			(1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT		22
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT);
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT		23
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT		34
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE			(1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
 
 /* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT		(1ULL << 2)
-#define MSR_IA32_MISC_ENABLE_TM1		(1ULL << 3)
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE	(1ULL << 4)
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE	(1ULL << 6)
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK	(1ULL << 8)
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE	(1ULL << 9)
-#define MSR_IA32_MISC_ENABLE_FERR		(1ULL << 10)
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX	(1ULL << 10)
-#define MSR_IA32_MISC_ENABLE_TM2		(1ULL << 13)
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE	(1ULL << 19)
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK	(1ULL << 20)
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT	(1ULL << 24)
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE	(1ULL << 37)
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE	(1ULL << 38)
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE	(1ULL << 39)
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT		2
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT			(1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
+#define MSR_IA32_MISC_ENABLE_TM1_BIT			3
+#define MSR_IA32_MISC_ENABLE_TM1			(1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT	4
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT	6
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT		8
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT	9
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_BIT			10
+#define MSR_IA32_MISC_ENABLE_FERR			(1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT		10
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX		(1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
+#define MSR_IA32_MISC_ENABLE_TM2_BIT			13
+#define MSR_IA32_MISC_ENABLE_TM2			(1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT	19
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT		20
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK		(1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT		24
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT		(1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT	37
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT		38
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
 
 #define MSR_IA32_TSC_DEADLINE		0x000006E0