ARM64: Accessing perf counters from userspace

1/5

---
 app_readcounter.c |   83 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 app_readcounter.c
 ARMv8_Module/Makefile         |    8 ++++
 ARMv8_Module/README           |    1 +
 ARMv8_Module/enable_arm_pmu.c |   96 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 105 insertions(+)
 create mode 100644 ARMv8_Module/Makefile
 create mode 100644 ARMv8_Module/README
 create mode 100644 ARMv8_Module/enable_arm_pmu.c
---
 README.directaccess |    8 ++++
 direct_access.c     |   65 ++++++++++++++++++++++++++++
 direct_access.h     |  117 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 190 insertions(+)
 create mode 100644 README.directaccess
 create mode 100644 direct_access.c
 create mode 100644 direct_access.h
 arch/arm64/kernel/vdso/Makefile     |    6 +++---
 arch/arm64/kernel/vdso/vdso.lds.S   |    5 +++++
 arch/arm64/kernel/vdso/vdso_perfc.c |   20 ++++++++++++++++++++
 3 files changed, 28 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kernel/vdso/vdso_perfc.c
 vdso_userspace_perf.c |   58 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 vdso_userspace_perf.c
1.7.9.5
---
 app_readcounter.c |   83 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 app_readcounter.c
new file mode 100644
index 0000000..5363dd4
@@ -0,0 +1,83 @@
+/*
+Application to Read perf cycle counter using perf_event_open syscall
+
+To Run: pass randon number to create busy loop
+e.g.: $./app_readcounter 64
+
+*/
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/syscall.h>
+#include <linux/perf_event.h>
+
+static int fddev = -1;
+__attribute__((constructor)) static void
+init(void)
+{
+	static struct perf_event_attr attr;
+	attr.type = PERF_TYPE_HARDWARE;
+	attr.config = PERF_COUNT_HW_CPU_CYCLES;
+	fddev = syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0);
+}
+
+__attribute__((destructor)) static void
+fini(void)
+{
+	close(fddev);
+}
+
+static inline long long
+cpucycles(void)
+{
+	long long result = 0;
+	if (read(fddev, &result, sizeof(result)) < sizeof(result)) return 0;
+	return result;
+}
+
+/* Simple loop body to keep things interested. Make sure it gets inlined. */
+static inline int
+loop(int* __restrict__ a, int* __restrict__ b, int n)
+{
+	unsigned sum = 0;
+	int i=0;
+	for ( i = 0; i < n; ++i)
+		if(a[i] > b[i])
+			sum += a[i] + 5;
+	return sum;
+}
+
+int
+main(int ac, char **av)
+{
+        long long time_start = 0;
+        long long time_end   = 0;
+
+        int *a  = NULL;
+        int *b  = NULL;
+        int len = 0;
+	int i,sum = 0;
+        if (ac != 2) return -1;
+        len = atoi(av[1]);
+	printf("%s: len = %d\n", av[0], len);
+
+        a = malloc(len*sizeof(*a));
+        b = malloc(len*sizeof(*b));
+
+        for (i = 0; i < len; ++i) {
+                a[i] = i+128;
+                b[i] = i+64;
+        }
+
+        printf("%s: beginning loop\n", av[0]);
+        time_start = cpucycles();
+        sum = loop(a, b, len);
+        time_end   = cpucycles();
+        printf("%s: done. sum = %d; time delta = %llu\n", av[0], sum, time_end - time_start);
+
+        free(a); free(b);
+        return 0;
+}

1.7.9.5
---
 ARMv8_Module/Makefile         |    8 ++++
 ARMv8_Module/README           |    1 +
 ARMv8_Module/enable_arm_pmu.c |   96 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 105 insertions(+)
 create mode 100644 ARMv8_Module/Makefile
 create mode 100644 ARMv8_Module/README
 create mode 100644 ARMv8_Module/enable_arm_pmu.c
new file mode 100644
index 0000000..19a31ea
@@ -0,0 +1,8 @@
+obj-m	:= enable_arm_pmu.o
+KDIR	:= /lib/modules/$(shell uname -r)/build
+PWD	:= $(shell pwd)
+
+all:
+	$(MAKE) -C $(KDIR) SUBDIRS=$(PWD) modules
+clean:
+	$(MAKE) -C $(KDIR) SUBDIRS=$(PWD) clean

new file mode 100644
index 0000000..648456b
@@ -0,0 +1 @@
+make ARCH=arm64 clean;make ARCH=arm64 CROSS_COMPILE=~/arm64-tc-14.06/bin/aarch64-linux-gnu- -C ~/work/lava_ci/juno/linux-linaro/workspace/builddir-3.16.0-linaro-juno/ SUBDIRS=`pwd`

1.7.9.5
M?ns Rullg?rd
mans at mansr.com
---
 ARMv8_Module/Makefile         |    8 ++++
 ARMv8_Module/README           |    1 +
 ARMv8_Module/enable_arm_pmu.c |   96 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 105 insertions(+)
 create mode 100644 ARMv8_Module/Makefile
 create mode 100644 ARMv8_Module/README
 create mode 100644 ARMv8_Module/enable_arm_pmu.c
new file mode 100644
index 0000000..19a31ea
@@ -0,0 +1,8 @@
+obj-m	:= enable_arm_pmu.o
+KDIR	:= /lib/modules/$(shell uname -r)/build
+PWD	:= $(shell pwd)
+
+all:
+	$(MAKE) -C $(KDIR) SUBDIRS=$(PWD) modules
+clean:
+	$(MAKE) -C $(KDIR) SUBDIRS=$(PWD) clean

new file mode 100644
index 0000000..648456b
@@ -0,0 +1 @@
+make ARCH=arm64 clean;make ARCH=arm64 CROSS_COMPILE=~/arm64-tc-14.06/bin/aarch64-linux-gnu- -C ~/work/lava_ci/juno/linux-linaro/workspace/builddir-3.16.0-linaro-juno/ SUBDIRS=`pwd`

new file mode 100644
index 0000000..5c87b08
@@ -0,0 +1,96 @@
+/*
+ * Enable user-mode ARM performance counter access.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+/** -- Configuration stuff ------------------------------------------------- */
+
+#define DRVR_NAME "enable_arm_pmu"
+
+#if !defined(__aarch64__)
+	#error Module can only be compiled on ARM 64 machines.
+#endif
+
+/** -- Initialization & boilerplate ---------------------------------------- */
+
+#define PERF_DEF_OPTS 		(1 | 16)
+#define PERF_OPT_RESET_CYCLES 	(2 | 4)
+#define PERF_OPT_DIV64 		(8)
+#define ARMV8_PMCR_MASK         0x3f
+#define ARMV8_PMCR_E            (1 << 0) /* Enable all counters */
+#define ARMV8_PMCR_P            (1 << 1) /* Reset all counters */
+#define ARMV8_PMCR_C            (1 << 2) /* Cycle counter reset */
+#define ARMV8_PMCR_D            (1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV8_PMCR_X            (1 << 4) /* Export to ETM */
+#define ARMV8_PMCR_DP           (1 << 5) /* Disable CCNT if non-invasive debug*/
+#define ARMV8_PMCR_N_SHIFT      11       /* Number of counters supported */
+#define ARMV8_PMCR_N_MASK       0x1f
+
+#define ARMV8_PMUSERENR_EN_EL0  (1 << 0) /* EL0 access enable */
+#define ARMV8_PMUSERENR_CR      (1 << 2) /* Cycle counter read enable */
+#define ARMV8_PMUSERENR_ER      (1 << 3) /* Event counter read enable */
+
+static inline u32 armv8pmu_pmcr_read(void)
+{
+        u64 val=0;
+        asm volatile("mrs %0, pmcr_el0" : "=r" (val));
+        return (u32)val;
+}
+static inline void armv8pmu_pmcr_write(u32 val)
+{
+        val &= ARMV8_PMCR_MASK;
+        isb();
+        asm volatile("msr pmcr_el0, %0" : : "r" ((u64)val));
+}
+ 
+static void
+enable_cpu_counters(void* data)
+{
+	u32 val=0;
+/* Enable user-mode access to counters. */
+	asm volatile("msr pmuserenr_el0, %0" : : "r"((u64)ARMV8_PMUSERENR_EN_EL0|ARMV8_PMUSERENR_ER|ARMV8_PMUSERENR_CR));
+/* Initialize & Reset PMNC: C and P bits. */
+	armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C); 
+/*G4.4.11
+PMINTENSET, Performance Monitors Interrupt Enable Set register */
+/*cycle counter overflow interrupt request is disabled */
+	asm volatile("msr pmintenset_el1, %0" : : "r" ((u64)(0 << 31)));
+/*start*/
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMCR_E);
+}
+
+static void
+disable_cpu_counters(void* data)
+{
+	u32 val=0;
+	printk(KERN_INFO "\n [" DRVR_NAME "] disabling user-mode PMU access on CPU #%d",
+	smp_processor_id());
+
+	/* Program PMU and disable all counters */
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() |~ARMV8_PMCR_E);
+	/* disable user-mode access to counters. */
+	asm volatile("msr pmuserenr_el0, %0" : : "r"((u64)0));
+
+}
+
+static int __init
+init(void)
+{
+	on_each_cpu(enable_cpu_counters, NULL, 1);
+	printk(KERN_INFO "[" DRVR_NAME "] initialized");
+	return 0;
+}
+
+static void __exit
+fini(void)
+{
+	on_each_cpu(disable_cpu_counters, NULL, 1);
+	printk(KERN_INFO "[" DRVR_NAME "] unloaded");
+}
+
+MODULE_AUTHOR("Yogesh Tillu ");
+MODULE_DESCRIPTION("Enables user-mode access to ARMv8 PMU counters");
+MODULE_VERSION("0:0.1-dev");
+module_init(init);
+module_exit(fini);

1.7.9.5


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel at lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
---
 README.directaccess |    8 ++++
 direct_access.c     |   65 ++++++++++++++++++++++++++++
 direct_access.h     |  117 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 190 insertions(+)
 create mode 100644 README.directaccess
 create mode 100644 direct_access.c
 create mode 100644 direct_access.h
new file mode 100644
index 0000000..99e929c
@@ -0,0 +1,8 @@
+To Cross-compile application:
+ ~/arm64-tc-14.06/bin/aarch64-linux-gnu-gcc -std=gnu99 -O3 direct_access.c
+ -o direct_access
+
+Run:
+1) Insert kernel module to enable userspace access of perf cycle counter
+2) $./direct_access 64 [ Pass same random number as with test 
+			of perf_event_open ]

1.7.9.5
---
 arch/arm64/kernel/vdso/Makefile     |    6 +++---
 arch/arm64/kernel/vdso/vdso.lds.S   |    5 +++++
 arch/arm64/kernel/vdso/vdso_perfc.c |   20 ++++++++++++++++++++
 3 files changed, 28 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kernel/vdso/vdso_perfc.c
index 6d20b7d..4fde490 100644
@@ -5,7 +5,7 @@
 # Heavily based on the vDSO Makefiles for other archs.
 #
 
-obj-vdso := gettimeofday.o note.o sigreturn.o
+obj-vdso := gettimeofday.o note.o sigreturn.o armpmu.o
 
 # Build rules
 targets := $(obj-vdso) vdso.so vdso.so.dbg

@@ -43,8 +43,8 @@ $(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 	$(call if_changed,vdsosym)
 
 # Assembly rules for the .S files
-$(obj-vdso): %.o: %.S
-	$(call if_changed_dep,vdsoas)
+#$(obj-vdso): %.o: %.S
+#	$(call if_changed_dep,vdsoas)
 
 # Actual build commands
 quiet_cmd_vdsold = VDSOL $@

index 8154b8d..8cb56e0 100644
@@ -90,6 +90,11 @@ VERSION
 		__kernel_gettimeofday;
 		__kernel_clock_gettime;
 		__kernel_clock_getres;
+		 /* ADD YOUR VDSO STUFF HERE */
+		perf_read_counter;
+		__vdso_perf_read_counter;
+		perf_open_counter;
+		__vdso_perf_open_counter;
 	local: *;
 	};
 }

new file mode 100644
index 0000000..c363d64
@@ -0,0 +1,20 @@
+#include <linux/compiler.h>
+
+int perf_read_counter(void)
+    __attribute__((weak, alias("__vdso__perf_read_counter")));
+int perf_open_counter(void)
+    __attribute__((weak, alias("__vdso__perf_open_counter")));
+
+#define ARMV8_PMCNTENSET_EL0_ENABLE (1<<31) /**< Enable Perf count reg */
+
+__attribute__((no_instrument_function)) int __vdso__perf_read_counter(void)
+{
+int ret = 0;
+asm volatile("mrs %0, pmccntr_el0" : "=r" (ret));
+return ret;
+}
+
+__attribute__((no_instrument_function)) void __vdso__perf_open_counter(void)
+{
+asm volatile("msr pmcntenset_el0, %0" : : "r" (ARMV8_PMCNTENSET_EL0_ENABLE));
+}

1.7.9.5
---
 arch/arm64/kernel/vdso/Makefile     |    6 +++---
 arch/arm64/kernel/vdso/vdso.lds.S   |    5 +++++
 arch/arm64/kernel/vdso/vdso_perfc.c |   20 ++++++++++++++++++++
 3 files changed, 28 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kernel/vdso/vdso_perfc.c
index 6d20b7d..4fde490 100644
@@ -5,7 +5,7 @@
 # Heavily based on the vDSO Makefiles for other archs.
 #
 
-obj-vdso := gettimeofday.o note.o sigreturn.o
+obj-vdso := gettimeofday.o note.o sigreturn.o armpmu.o
 
 # Build rules
 targets := $(obj-vdso) vdso.so vdso.so.dbg

@@ -43,8 +43,8 @@ $(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 	$(call if_changed,vdsosym)
 
 # Assembly rules for the .S files
-$(obj-vdso): %.o: %.S
-	$(call if_changed_dep,vdsoas)
+#$(obj-vdso): %.o: %.S
+#	$(call if_changed_dep,vdsoas)

 # Actual build commands
 quiet_cmd_vdsold = VDSOL $@

index 8154b8d..8cb56e0 100644
@@ -90,6 +90,11 @@ VERSION
 		__kernel_gettimeofday;
 		__kernel_clock_gettime;
 		__kernel_clock_getres;
+		 /* ADD YOUR VDSO STUFF HERE */

+		perf_read_counter;
+		__vdso_perf_read_counter;
+		perf_open_counter;
+		__vdso_perf_open_counter;

 	local: *;
 	};
 }

new file mode 100644
index 0000000..c363d64

@@ -0,0 +1,20 @@
+#include <linux/compiler.h>
+
+int perf_read_counter(void)
+    __attribute__((weak, alias("__vdso__perf_read_counter")));
+int perf_open_counter(void)
+    __attribute__((weak, alias("__vdso__perf_open_counter")));

+
+#define ARMV8_PMCNTENSET_EL0_ENABLE (1<<31) /**< Enable Perf count reg */
+
+__attribute__((no_instrument_function)) int __vdso__perf_read_counter(void)

+{
+int ret = 0;
+asm volatile("mrs %0, pmccntr_el0" : "=r" (ret));
+return ret;
+}
+
+__attribute__((no_instrument_function)) void __vdso__perf_open_counter(void)
+{
+asm volatile("msr pmcntenset_el0, %0" : : "r" (ARMV8_PMCNTENSET_EL0_ENABLE));
+}

---
 vdso_userspace_perf.c |   58 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 vdso_userspace_perf.c
new file mode 100644
index 0000000..42d2682
@@ -0,0 +1,58 @@
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <sys/time.h>
+/* Simple loop body to keep things interested. Make sure it gets inlined. */
+static inline int
+loop(int* __restrict__ a, int* __restrict__ b, int n)
+{
+	unsigned sum = 0;
+	for (int i = 0; i < n; ++i)
+		if(a[i] > b[i])
+			sum += a[i] + 5;
+	return sum;
+}
+
+int
+main(int ac, char **av)
+{
+	uint32_t time_start = 0;
+	uint32_t time_end   = 0;
+	int result=0;
+	int *a  = NULL;
+	int *b  = NULL;
+	int len = 0;
+	int sum = 0;
+	int i;
+	struct timeval tv;
+
+	if (ac != 2) return -1;
+	len = atoi(av[1]);
+
+	a = malloc(len*sizeof(*a));
+	b = malloc(len*sizeof(*b));
+
+	for (int i = 0; i < len; ++i) {
+		a[i] = i+128;
+		b[i] = i+64;
+	}
+/* Read Counter  with Busy loop */
+	perf_open_counter();
+	time_start = perf_read_counter();
+	sum = loop(a, b, len);
+	time_end   = perf_read_counter();
+	printf("**********************************************************************\n");
+	printf("Busyloop sum = %d\nTime delta Including Busyloop = %lu [clockcycle]\n", sum, time_end - time_start);
+
+/* Read Counter with profiling read_counter */
+	time_start = perf_read_counter();
+	perf_read_counter();
+	time_end   = perf_read_counter();
+	printf("\nTime delta Without Busyloop   = %lu   [clockcycle]\n", time_end - time_start);
+	printf("**********************************************************************\n");
+
+	free(a); free(b);
+	return 0;
+cleanup: 
+	return -1;
+}

1.7.9.5
---
 app_readcounter.c |   83 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 app_readcounter.c
 ARMv8_Module/Makefile         |    8 ++++
 ARMv8_Module/README           |    1 +
 ARMv8_Module/enable_arm_pmu.c |   96 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 105 insertions(+)
 create mode 100644 ARMv8_Module/Makefile
 create mode 100644 ARMv8_Module/README
 create mode 100644 ARMv8_Module/enable_arm_pmu.c
---
 README.directaccess |    8 ++++
 direct_access.c     |   65 ++++++++++++++++++++++++++++
 direct_access.h     |  117 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 190 insertions(+)
 create mode 100644 README.directaccess
 create mode 100644 direct_access.c
 create mode 100644 direct_access.h
 arch/arm64/kernel/vdso/Makefile     |    6 +++---
 arch/arm64/kernel/vdso/vdso.lds.S   |    5 +++++
 arch/arm64/kernel/vdso/vdso_perfc.c |   20 ++++++++++++++++++++
 3 files changed, 28 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kernel/vdso/vdso_perfc.c
 vdso_userspace_perf.c |   58 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 vdso_userspace_perf.c
1.7.9.5


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel at lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
---
 app_readcounter.c |   83 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)
 create mode 100644 app_readcounter.c
 ARMv8_Module/Makefile         |    8 ++++
 ARMv8_Module/README           |    1 +
 ARMv8_Module/enable_arm_pmu.c |   96 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 105 insertions(+)
 create mode 100644 ARMv8_Module/Makefile
 create mode 100644 ARMv8_Module/README
 create mode 100644 ARMv8_Module/enable_arm_pmu.c
---
 README.directaccess |    8 ++++
 direct_access.c     |   65 ++++++++++++++++++++++++++++
 direct_access.h     |  117 +++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 190 insertions(+)
 create mode 100644 README.directaccess
 create mode 100644 direct_access.c
 create mode 100644 direct_access.h
 arch/arm64/kernel/vdso/Makefile     |    6 +++---
 arch/arm64/kernel/vdso/vdso.lds.S   |    5 +++++
 arch/arm64/kernel/vdso/vdso_perfc.c |   20 ++++++++++++++++++++
 3 files changed, 28 insertions(+), 3 deletions(-)
 create mode 100644 arch/arm64/kernel/vdso/vdso_perfc.c
 vdso_userspace_perf.c |   58 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 vdso_userspace_perf.c
     Hi,
     ? ?Please find my reply inline.
     On 3 November 2014 21:10, Mark Rutland <[2][email protected]> wrote:
     >
     > Hi,
     >
     > On Mon, Nov 03, 2014 at 03:04:00PM +0000, Yogesh Tillu wrote:
     > > We have tried to implement some changes to allow perf counters to be
     accessed
     > > from user space. Benchmarking so far has show that these are 100s of
     times
     > > faster than using syscall(perf_event_open). This would be useful for
     many use
     > > cases like networking(critical to fast path code), benchmark
     executionpath with
     > > low budget of cpu cycles etc.
     > >
     > > Benchmark figures on ArmV8, "reading perf cycle counter" with below
     approaches
     > > 1) Reading perf cycle counter through perf_event_open syscall
     > > Result[cpu cycles]: 2000 (For Armv7[Arndale] 5407)
     > > 2) Direct access of perf counters from userspace through asm
     > > Result[cpu cycles]: 2 (For Armv7[Arndale] 16)
     > > 3) Reading perf cycle counter through vDSO path
     > > Result[cpu cycles]: ~20
     > >
     > >
     > > Could you please let me know your comments/review. Below are the
     details about
     > > setup and patchset.
     >
     > For there to be any meaningful review of this, it needs to be based on
     a
     > kernel tree, and implemented within the existing perf framework; it
     > cannot be a module on the side. This is impossible to review, because
     it
     > looks nothing like what a real solution will have to.
     Agree, I will resend patchset based on kernel tree.
     I will rework on Module implementation and try to reimplement it with
     CONFIG_ based design to co-exist with kernel perf framework
     (as in armv8pmu_reset it Disable access to counters from userspace).
     >
     > Please base this on a kernel tree, and integrate with the existing
     > frameworks.
     >
     > It would also be helpful if you could describe a use case for which
     the
     > current mechanisms are too expensive. It will certainly be cheaper to
     > read the registers directly, but there is additional work userspace
     will
     > need to do in addition to simply reading the registers. That can
     impact
     > the use-case.
     With Current mechanism, it takes lot of cpu cycles where "only read of
     perf counter" operations are interested. For example, To Benchmark
     networking fastpath code like control plane where we have very limited
     budget for reading value of counters.
     >
     > It's unclear to me why you cannot amortize the cost of the reads over
     a
     > number of iterations. A specific (non-trivial) example would help.
     Agree, I will try to modify tests with number of iterations.

     Thanks,
     Yogesh
     > Thanks,
     > Mark.
     >
     > >
     > > ** Setup details **
     > > Architecture: ArmV8
     > > Board? ? ? ?: Juno Board
     > > Linux kernel: 3.16.0+
     > > Kernel Repo :
     git://[3]git.linaro.org/kernel/linux-linaro-tracking.git
     > > (Branch:linux-linaro)
     > > Rootfs? ? ? : Linaro Ubuntu rootfs
     > > Toolchain? ?: gcc version 4.9.1 20140529 (prerelease)
     > > (crosstool-NG linaro-1.13.1-4.9-2014.06-02 - Linaro GCC 4.9-2014.06)
     > >
     > > 1) Reading perf cycle counter through perf_event_open syscall
     > > *Application to read counter using perf_event_open syscall.
     > > [PATCH] Application reads perf cycle counter using perf_event_open
     > > syscall, and prints Benchmark results.
     > >
     > > Signed-off-by: Yogesh Tillu <[4][email protected]>
     > > ---
     > >? app_readcounter.c |? ?83
     +++++++++++++++++++++++++++++++++++++++++++++++++++++
     > >? 1 file changed, 83 insertions(+)
     > >? create mode 100644 app_readcounter.c
     > >
     > >
     > > 2) Direct access of perf counters from userspace using asm
     > > This setup contains kernel module + header file with implemented asm
     to access
     > > perf counters + Application uses api provided in header file to
     access counter.
     > >
     > > * Kernel Module: To enable access of counters from userspace
     > > Yogesh Tillu (1):
     > >? ?Kernel module to Enable userspace access to PMU counters for
     > >? ? ?ArmV8
     > >
     > >? ARMv8_Module/Makefile? ? ? ? ?|? ? 8 ++++
     > >? ARMv8_Module/README? ? ? ? ? ?|? ? 1 +
     > >? ARMv8_Module/enable_arm_pmu.c |? ?96
     +++++++++++++++++++++++++++++++++++++++++
     > >? 3 files changed, 105 insertions(+)
     > >? create mode 100644 ARMv8_Module/Makefile
     > >? create mode 100644 ARMv8_Module/README
     > >? create mode 100644 ARMv8_Module/enable_arm_pmu.c
     > >
     > > * Application:
     > > [PATCH] Added test for Direct access of perf counter from userspace
     > >? using asm.
     > >
     > > Signed-off-by: Yogesh Tillu <[5][email protected]>
     > > ---
     > >? README.directaccess |? ? 8 ++++
     > >? direct_access.c? ? ?|? ?65 ++++++++++++++++++++++++++++
     > >? direct_access.h? ? ?|? 117
     +++++++++++++++++++++++++++++++++++++++++++++++++++
     > >? 3 files changed, 190 insertions(+)
     > >? create mode 100644 README.directaccess
     > >? create mode 100644 direct_access.c
     > >? create mode 100644 direct_access.h
     > >
     > > 3) Reading perf cycle counter through vDSO path
     > > * Kernel Module: To enable access of counters from userspace ( Same
     as setup (2) )
     > > * Kernel vDSO implementation: vDSO implementation for reading of
     perf cycle counter
     > > [PATCH] provide open/read function through vDSO for PMU counters
     > > Yogesh Tillu (1):
     > >? ?To read PMU cycle counter through vDSO Path
     > >
     > >? arch/arm64/kernel/vdso/Makefile? ? ?|? ? 6 +++---
     > >? arch/arm64/kernel/vdso/vdso.lds.S? ?|? ? 5 +++++
     > >? arch/arm64/kernel/vdso/vdso_perfc.c |? ?20 ++++++++++++++++++++
     > >? 3 files changed, 28 insertions(+), 3 deletions(-)
     > >? create mode 100644 arch/arm64/kernel/vdso/vdso_perfc.c
     > >
     > > * application? : To read perf counter through api(implemented
     through vDSO)
     > > [PATCH] Test Application: access PMU counter through vDSO
     > > Yogesh Tillu (1):
     > >? ?Test application to read PMU counter through vdso
     > >
     > >? vdso_userspace_perf.c |? ?58
     +++++++++++++++++++++++++++++++++++++++++++++++++
     > >? 1 file changed, 58 insertions(+)
     > >? create mode 100644 vdso_userspace_perf.c
     > >
     > > NOTE: This codebase mainly for POC of "Access perf counters from
     userspace",
     > > not much concentration towards api standard forms.
     > >
     > > --
     > > 1.7.9.5
     > >
     > >
     > > _______________________________________________
     > > linux-arm-kernel mailing list
     > > [6]linux-arm-kernel at lists.infradead.org
     > > [7]http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
     > >