[PATCH 2/6] Centralize access to APERF and MPERF MSRs on Intel CPUs

[Darrick J. Wong]

This patch provides helper functions to detect and to access the APERF
and MPERF MSRs on certain Intel CPUs.  These two registers are useful
for determining the measured performance over a period of time while
the CPU is in C0 state.

Signed-off-by: Darrick J. Wong <djwong@xxxxxxxxxx>
---
 arch/x86/include/asm/system.h |   19 ++++++++
 arch/x86/kernel/Makefile      |    2 -
 arch/x86/kernel/time.c        |  103 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 123 insertions(+), 1 deletions(-)

diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 2ed3f0f..787f5c2 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -422,4 +422,23 @@ static inline void rdtsc_barrier(void)
 	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
 }
 
+#define U64_MAX	(u64)(~((u64)0))
+
+static inline u64 delta_perf(u64 now, u64 *old)
+{
+	u64 delta;
+
+	if (now > *old)
+		delta = now - *old;
+	else
+		delta = now + (U64_MAX - *old);
+
+	*old = now;
+	return delta;
+}
+
+void get_intel_aperf_mperf_registers(u64 *aperf, u64 *mperf);
+u64 scale_with_perf(u64 input, u64 aperf, u64 mperf);
+#define CPUID_6_ECX_APERFMPERF_CAPABILITY	(0x1)
+
 #endif /* _ASM_X86_SYSTEM_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index e489ff9..7c20f6f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -25,7 +25,7 @@ CFLAGS_tsc.o		:= $(nostackp)
 
 obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time_$(BITS).o ioport.o ldt.o
+obj-y			+= time_$(BITS).o ioport.o ldt.o time.o
 obj-y			+= setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
new file mode 100644
index 0000000..41ff323
--- /dev/null
+++ b/arch/x86/kernel/time.c
@@ -0,0 +1,103 @@
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+
+void get_intel_aperf_mperf_registers(u64 *aperf, u64 *mperf)
+{
+	union {
+		struct {
+			u32 lo;
+			u32 hi;
+		} split;
+		u64 whole;
+	} aperf_cur, mperf_cur;
+	unsigned long flags;
+
+	/* Read current values of APERF and MPERF MSRs*/
+	local_irq_save(flags);
+	rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi);
+	rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi);
+	local_irq_restore(flags);
+
+	*mperf = mperf_cur.whole;
+	*aperf = aperf_cur.whole;
+}
+EXPORT_SYMBOL_GPL(get_intel_aperf_mperf_registers);
+
+u64 scale_with_perf(u64 input, u64 aperf, u64 mperf)
+{
+	union {
+		struct {
+			u32 lo;
+			u32 hi;
+		} split;
+		u64 whole;
+	} aperf_cur, mperf_cur;
+
+	aperf_cur.whole = aperf;
+	mperf_cur.whole = mperf;
+
+#ifdef __i386__
+	/*
+	 * We dont want to do 64 bit divide with 32 bit kernel
+	 * Get an approximate value. Return failure in case we cannot get
+	 * an approximate value.
+	 */
+	if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) {
+		int shift_count;
+		u32 h;
+
+		h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi);
+		shift_count = fls(h);
+
+		aperf_cur.whole >>= shift_count;
+		mperf_cur.whole >>= shift_count;
+	}
+
+	if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) {
+		int shift_count = 7;
+		aperf_cur.split.lo >>= shift_count;
+		mperf_cur.split.lo >>= shift_count;
+	}
+
+	if (aperf_cur.split.lo && mperf_cur.split.lo)
+		return (aperf_cur.split.lo * input) / mperf_cur.split.lo;
+#else
+	if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) {
+		int shift_count = 7;
+		aperf_cur.whole >>= shift_count;
+		mperf_cur.whole >>= shift_count;
+	}
+
+	if (aperf_cur.whole && mperf_cur.whole)
+		return (aperf_cur.whole * input) / mperf_cur.whole;
+#endif
+	return 0;
+}
+EXPORT_SYMBOL_GPL(scale_with_perf);
+
+static inline int is_intel_cpu_with_aperf(void)
+{
+	struct cpuinfo_x86 *c;
+	static int has_aperf = -1;
+
+	if (has_aperf >= 0)
+		return has_aperf;
+
+	/* If cpuid_level = 0, it might not have been set yet */
+	c = &cpu_data(smp_processor_id());
+	if (!c->x86_vendor && !c->cpuid_level)
+		return 0;
+
+	/* Check for APERF/MPERF support in hardware */
+	has_aperf = 0;
+	if (c->x86_vendor == X86_VENDOR_INTEL && c->cpuid_level >= 6) {
+		unsigned int ecx;
+		ecx = cpuid_ecx(6);
+		if (ecx & CPUID_6_ECX_APERFMPERF_CAPABILITY)
+			has_aperf = 1;
+	}
+
+	return has_aperf;
+}
+EXPORT_SYMBOL_GPL(is_intel_cpu_with_aperf);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/