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

Pull x86 cpufeature updates from Thomas Gleixner:

 - a workaround for the MONITOR instruction erratum of Goldmont CPUs

 - small fixes and cleanups here and there

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu: Add workaround for MONITOR instruction erratum on Goldmont based CPUs
  x86/cpu: Rename "WESTMERE2" family to "NEHALEM_G"
  x86/amd_nb: Clean up init path
  x86/cpufeature: Add helper macro for mask check macros
  x86/cpufeature: Make sure DISABLED/REQUIRED macros are updated
  x86/cpufeature: Update cpufeaure macros

arch/x86/events/msr.c

@@ -36,11 +36,11 @@ static bool test_intel(int idx)
 
 	switch (boot_cpu_data.x86_model) {
 	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_G:
 	case INTEL_FAM6_NEHALEM_EP:
 	case INTEL_FAM6_NEHALEM_EX:
 
 	case INTEL_FAM6_WESTMERE:
-	case INTEL_FAM6_WESTMERE2:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
 

arch/x86/include/asm/cpufeature.h

@@ -49,43 +49,59 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define REQUIRED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & REQUIRED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & REQUIRED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & REQUIRED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & REQUIRED_MASK3 )) ||	\
-	   (((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)==8  && (1UL<<((bit)&31) & REQUIRED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & REQUIRED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & REQUIRED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
-
-#define DISABLED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & DISABLED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & DISABLED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & DISABLED_MASK3 )) ||	\
-	   (((bit)>>5)==4  && (1UL<<((bit)&31) & DISABLED_MASK4 )) ||	\
-	   (((bit)>>5)==5  && (1UL<<((bit)&31) & DISABLED_MASK5 )) ||	\
-	   (((bit)>>5)==6  && (1UL<<((bit)&31) & DISABLED_MASK6 )) ||	\
-	   (((bit)>>5)==7  && (1UL<<((bit)&31) & DISABLED_MASK7 )) ||	\
-	   (((bit)>>5)==8  && (1UL<<((bit)&31) & DISABLED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & DISABLED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & DISABLED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
+/*
+ * There are 32 bits/features in each mask word.  The high bits
+ * (selected with (bit>>5) give us the word number and the low 5
+ * bits give us the bit/feature number inside the word.
+ * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
+ * see if it is set in the mask word.
+ */
+#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
+	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
+
+#define REQUIRED_MASK_BIT_SET(feature_bit)		\
+	 ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
+	   REQUIRED_MASK_CHECK					  ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+
+#define DISABLED_MASK_BIT_SET(feature_bit)				\
+	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
+	   DISABLED_MASK_CHECK					  ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\

arch/x86/include/asm/cpufeatures.h

@@ -309,5 +309,5 @@
 #endif
 #define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
-
+#define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
 #endif /* _ASM_X86_CPUFEATURES_H */

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

@@ -56,5 +56,7 @@
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */

arch/x86/include/asm/intel-family.h

@@ -8,7 +8,7 @@
  * "Extreme" ones, like Broadwell-E.
  *
  * Things ending in "2" are usually because we have no better
- * name for them.  There's no processor called "WESTMERE2".
+ * name for them.  There's no processor called "SILVERMONT2".
  */
 
 #define INTEL_FAM6_CORE_YONAH		0x0E
@@ -18,10 +18,10 @@
 #define INTEL_FAM6_CORE2_DUNNINGTON	0x1D
 
 #define INTEL_FAM6_NEHALEM		0x1E
+#define INTEL_FAM6_NEHALEM_G		0x1F /* Auburndale / Havendale */
 #define INTEL_FAM6_NEHALEM_EP		0x1A
 #define INTEL_FAM6_NEHALEM_EX		0x2E
 #define INTEL_FAM6_WESTMERE		0x25
-#define INTEL_FAM6_WESTMERE2		0x1F
 #define INTEL_FAM6_WESTMERE_EP		0x2C
 #define INTEL_FAM6_WESTMERE_EX		0x2F
 

arch/x86/include/asm/mwait.h

@@ -97,7 +97,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  */
 static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
-	if (!current_set_polling_and_test()) {
+	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
 		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
 			mb();
 			clflush((void *)&current_thread_info()->flags);

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

@@ -99,5 +99,7 @@
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	0
+#define REQUIRED_MASK17	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */

arch/x86/kernel/amd_nb.c

@@ -219,24 +219,22 @@ int amd_set_subcaches(int cpu, unsigned long mask)
 	return 0;
 }
 
-static int amd_cache_gart(void)
+static void amd_cache_gart(void)
 {
 	u16 i;
 
-       if (!amd_nb_has_feature(AMD_NB_GART))
-               return 0;
-
-       flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
-       if (!flush_words) {
-               amd_northbridges.flags &= ~AMD_NB_GART;
-               return -ENOMEM;
-       }
+	if (!amd_nb_has_feature(AMD_NB_GART))
+		return;
 
-       for (i = 0; i != amd_nb_num(); i++)
-               pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c,
-                                     &flush_words[i]);
+	flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
+	if (!flush_words) {
+		amd_northbridges.flags &= ~AMD_NB_GART;
+		pr_notice("Cannot initialize GART flush words, GART support disabled\n");
+		return;
+	}
 
-       return 0;
+	for (i = 0; i != amd_nb_num(); i++)
+		pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c, &flush_words[i]);
 }
 
 void amd_flush_garts(void)
@@ -278,17 +276,10 @@ EXPORT_SYMBOL_GPL(amd_flush_garts);
 
 static __init int init_amd_nbs(void)
 {
-	int err = 0;
+	amd_cache_northbridges();
+	amd_cache_gart();
 
-	err = amd_cache_northbridges();
-
-	if (err < 0)
-		pr_notice("Cannot enumerate AMD northbridges\n");
-
-	if (amd_cache_gart() < 0)
-		pr_notice("Cannot initialize GART flush words, GART support disabled\n");
-
-	return err;
+	return 0;
 }
 
 /* This has to go after the PCI subsystem */

arch/x86/kernel/cpu/intel.c

@@ -13,6 +13,7 @@
 #include <asm/msr.h>
 #include <asm/bugs.h>
 #include <asm/cpu.h>
+#include <asm/intel-family.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -508,6 +509,10 @@ static void init_intel(struct cpuinfo_x86 *c)
 	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
 		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
+	if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_MWAIT) &&
+		((c->x86_model == INTEL_FAM6_ATOM_GOLDMONT)))
+		set_cpu_bug(c, X86_BUG_MONITOR);
+
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;

arch/x86/kernel/process.c

@@ -404,7 +404,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
-	if (!cpu_has(c, X86_FEATURE_MWAIT))
+	if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR))
 		return 0;
 
 	return 1;

drivers/idle/intel_idle.c

@@ -1055,7 +1055,7 @@ static const struct idle_cpu idle_cpu_dnv = {
 static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 	ICPU(INTEL_FAM6_NEHALEM_EP,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_NEHALEM,		idle_cpu_nehalem),
-	ICPU(INTEL_FAM6_WESTMERE2,		idle_cpu_nehalem),
+	ICPU(INTEL_FAM6_NEHALEM_G,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_WESTMERE,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_WESTMERE_EP,		idle_cpu_nehalem),
 	ICPU(INTEL_FAM6_NEHALEM_EX,		idle_cpu_nehalem),