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

Pull x86 cpufeature updates from Ingo Molnar:
 "The main changes in this cycle were related to enable ring-3
  MONITOR/MWAIT instructions support on supported CPUs, by Grzegorz
  Andrejczuk and Piotr Luc"

* 'x86-cpufeature-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpufeature: Move RING3MWAIT feature to avoid conflicts
  x86/cpufeature: Enable RING3MWAIT for Knights Mill
  x86/cpufeature: Enable RING3MWAIT for Knights Landing
  x86/cpufeature: Add RING3MWAIT to CPU features
  x86/elf: Add HWCAP2 to expose ring 3 MONITOR/MWAIT
  x86/msr: Add MSR_MISC_FEATURE_ENABLES and RING3MWAIT bit
  x86/cpufeature: Add AVX512_VPOPCNTDQ feature

7 files changed, 71 insertions, 2 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index eafee3161d1c..43c4ea9cd907 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -186,7 +186,7 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-
+#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
 #define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
@@ -288,6 +288,7 @@
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
@@ -320,5 +321,4 @@
 #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 */
 #define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index e7f155c3045e..9d49c18b5ea9 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -258,6 +258,15 @@ extern int force_personality32;
 
 #define ELF_HWCAP		(boot_cpu_data.x86_capability[CPUID_1_EDX])
 
+extern u32 elf_hwcap2;
+
+/*
+ * HWCAP2 supplies mask with kernel enabled CPU features, so that
+ * the application can discover that it can safely use them.
+ * The bits are defined in uapi/asm/hwcap2.h.
+ */
+#define ELF_HWCAP2		(elf_hwcap2)
+
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in
    intent than poking at uname or /proc/cpuinfo.
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 710273c617b8..00293a94ffaf 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -543,6 +543,11 @@
 #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)
 
+/* MISC_FEATURE_ENABLES non-architectural features */
+#define MSR_MISC_FEATURE_ENABLES	0x00000140
+
+#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT		1
+
 #define MSR_IA32_TSC_DEADLINE		0x000006E0
 
 /* P4/Xeon+ specific */
diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h
new file mode 100644
index 000000000000..0bd2be5c7617
--- /dev/null
+++ b/arch/x86/include/uapi/asm/hwcap2.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_HWCAP2_H
+#define _ASM_X86_HWCAP2_H
+
+/* MONITOR/MWAIT enabled in Ring 3 */
+#define HWCAP2_RING3MWAIT		(1 << 0)
+
+#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3bcf6d880611..5200adcaaac3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -35,6 +35,7 @@
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
 #include <asm/mtrr.h>
+#include <asm/hwcap2.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
 #include <asm/bugs.h>
@@ -51,6 +52,8 @@
 
 #include "cpu.h"
 
+u32 elf_hwcap2 __read_mostly;
+
 /* all of these masks are initialized in setup_cpu_local_masks() */
 cpumask_var_t cpu_initialized_mask;
 cpumask_var_t cpu_callout_mask;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 026c728d6ba7..017ecd3bb553 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -15,6 +15,8 @@
 #include <asm/cpu.h>
 #include <asm/intel-family.h>
 #include <asm/microcode_intel.h>
+#include <asm/hwcap2.h>
+#include <asm/elf.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -62,6 +64,46 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
 	}
 }
 
+static bool ring3mwait_disabled __read_mostly;
+
+static int __init ring3mwait_disable(char *__unused)
+{
+	ring3mwait_disabled = true;
+	return 0;
+}
+__setup("ring3mwait=disable", ring3mwait_disable);
+
+static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Ring 3 MONITOR/MWAIT feature cannot be detected without
+	 * cpu model and family comparison.
+	 */
+	if (c->x86 != 6)
+		return;
+	switch (c->x86_model) {
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
+		break;
+	default:
+		return;
+	}
+
+	if (ring3mwait_disabled) {
+		msr_clear_bit(MSR_MISC_FEATURE_ENABLES,
+			      MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+		return;
+	}
+
+	msr_set_bit(MSR_MISC_FEATURE_ENABLES,
+		    MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+
+	set_cpu_cap(c, X86_FEATURE_RING3MWAIT);
+
+	if (c == &boot_cpu_data)
+		ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -562,6 +604,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		detect_vmx_virtcap(c);
 
 	init_intel_energy_perf(c);
+
+	probe_xeon_phi_r3mwait(c);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 1d7770447b3e..35f7024aace5 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -78,6 +78,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_PKU);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ);
 }
 
 /*