[PATCH v4 3/4] x86: Use HWCAP2 to expoose Xeon Phi ring 3 MWAIT

From: Grzegorz Andrejczuk
Date: Tue Oct 18 2016 - 06:03:46 EST


Add HWCAP2 for x86 and reserve its 1st bit to expose
Xeon Phi ring 3 monitor/mwait to userspace apps.

Signed-off-by: Grzegorz Andrejczuk <grzegorz.andrejczuk@xxxxxxxxx>
---
arch/x86/include/asm/elf.h | 9 +++++++++
arch/x86/include/uapi/asm/hwcap2.h | 7 +++++++
arch/x86/kernel/cpu/common.c | 3 +++
3 files changed, 19 insertions(+)
create mode 100644 arch/x86/include/uapi/asm/hwcap2.h

diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index e7f155c..59703aa 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 unsigned int 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/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h
new file mode 100644
index 0000000..90ef445
--- /dev/null
+++ b/arch/x86/include/uapi/asm/hwcap2.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_HWCAP2_H
+#define _ASM_HWCAP2_H
+
+/* Kernel enabled Ring 3 MWAIT for Xeon Phi*/
+#define HWCAP2_PHIR3MWAIT (1 << 0)
+
+#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index bcc9ccc..fdbf708 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"

+unsigned int 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;
--
2.5.1