[v1.05] Add support for frequency measurement (both x86 and ARM) (branch measure-freq #220)

Makefile

@@ -7,8 +7,8 @@ PREFIX ?= /usr
 
 SRC_COMMON=src/common/
 
-COMMON_SRC = $(SRC_COMMON)main.c $(SRC_COMMON)cpu.c $(SRC_COMMON)udev.c $(SRC_COMMON)printer.c $(SRC_COMMON)args.c $(SRC_COMMON)global.c
+COMMON_SRC = $(SRC_COMMON)main.c $(SRC_COMMON)cpu.c $(SRC_COMMON)udev.c $(SRC_COMMON)printer.c $(SRC_COMMON)args.c $(SRC_COMMON)global.c $(SRC_COMMON)freq.c
-COMMON_HDR = $(SRC_COMMON)ascii.h $(SRC_COMMON)cpu.h $(SRC_COMMON)udev.h $(SRC_COMMON)printer.h $(SRC_COMMON)args.h $(SRC_COMMON)global.h
+COMMON_HDR = $(SRC_COMMON)ascii.h $(SRC_COMMON)cpu.h $(SRC_COMMON)udev.h $(SRC_COMMON)printer.h $(SRC_COMMON)args.h $(SRC_COMMON)global.h $(SRC_COMMON)freq.h
 
 ifneq ($(OS),Windows_NT)
 	GIT_VERSION := "$(shell git describe --abbrev=4 --dirty --always --tags)"

src/arm/midr.c

@@ -8,6 +8,7 @@
 #ifdef __linux__
   #include <sys/auxv.h>
   #include <asm/hwcap.h>
+  #include "../common/freq.h"
 #elif defined __APPLE__ || __MACH__
   #include "sysctl.h"
 #endif
@@ -41,6 +42,12 @@ struct frequency* get_frequency_info(uint32_t core) {
 
   freq->base = UNKNOWN_DATA;
   freq->max = get_max_freq_from_file(core);
+  #ifdef __linux__
+    if (freq->max == UNKNOWN_DATA) {
+      printWarn("Unable to find max frequency from udev, measuring CPU frequency");
+      freq->max = measure_max_frequency(core);
+    }
+  #endif
 
   return freq;
 }

src/common/freq.c

@@ -0,0 +1,154 @@
+#ifdef __linux__
+
+#define _GNU_SOURCE
+
+#include <time.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+#include <sys/ioctl.h>
+#include <linux/perf_event.h>
+
+#include "global.h"
+
+static long
+perf_event_open(struct perf_event_attr *hw_event, pid_t pid,
+                int cpu, int group_fd, unsigned long flags) {
+    int ret;
+    ret = syscall(__NR_perf_event_open, hw_event, pid, cpu,
+                    group_fd, flags);
+    return ret;
+}
+
+#define INSERT_ASM_ONCE __asm volatile("nop");
+#define INSERT_ASM_10_TIMES \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+    INSERT_ASM_ONCE         \
+
+#define INSERT_ASM_100_TIMES \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES      \
+    INSERT_ASM_10_TIMES
+
+#define INSERT_ASM_1000_TIMES \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+    INSERT_ASM_100_TIMES     \
+
+void nop_function(uint64_t iters) {
+  for (uint64_t i = 0; i < iters; i++) {
+    INSERT_ASM_1000_TIMES
+    INSERT_ASM_1000_TIMES
+    INSERT_ASM_1000_TIMES
+    INSERT_ASM_1000_TIMES
+  }
+}
+
+// Differences between x86 measure_frequency this measure_max_frequency:
+// - measure_frequency employs all cores simultaneously wherease 
+//   measure_max_frequency only employs 1.
+// - measure_frequency runs the computation and checks /proc/cpuinfo whereas
+//   measure_max_frequency does not rely on /proc/cpuinfo and simply
+//   counts cpu cycles to measure frequency.
+// - measure_frequency uses actual computation while measuring the frequency
+//   whereas measure_max_frequency uses nop instructions. This makes the former
+//   x86 dependant whereas the latter is architecture independant.
+int64_t measure_max_frequency(uint32_t core) {
+  if (!bind_to_cpu(core)) {
+    printErr("Failed binding the process to CPU %d", core);
+    return -1;
+  }
+
+  clockid_t clock = CLOCK_PROCESS_CPUTIME_ID;
+
+  struct perf_event_attr pe;
+  uint64_t instructions;
+  int fd;
+  int pid = 0;
+
+  memset(&pe, 0, sizeof(struct perf_event_attr));
+  pe.type = PERF_TYPE_HARDWARE;
+  pe.size = sizeof(struct perf_event_attr);
+  pe.config = PERF_COUNT_HW_CPU_CYCLES;
+  pe.disabled = 1;
+  pe.exclude_kernel = 1;
+  pe.exclude_hv = 1;
+
+  fd = perf_event_open(&pe, pid, core, -1, 0);
+  if (fd == -1) {
+    perror("perf_event_open");
+    if (errno == EPERM || errno == EACCES) {
+      printf("You may not have permission to collect stats.\n");
+      printf("Consider tweaking /proc/sys/kernel/perf_event_paranoid or running as root.\n");
+    }
+    return -1;
+  }
+
+  const char* frequency_banner = "cpufetch is measuring the max frequency...";
+  printf("%s", frequency_banner);
+  fflush(stdout);
+
+  uint64_t iters = 10000000;
+  struct timespec start, end;
+  if (clock_gettime(clock, &start) == -1) {
+    perror("clock_gettime");
+    return -1;
+  }
+  if(ioctl(fd, PERF_EVENT_IOC_RESET, 0) == -1) {
+    perror("ioctl");
+    return -1;
+  }
+  if(ioctl(fd, PERF_EVENT_IOC_ENABLE, 0) == -1) {
+    perror("ioctl");
+    return -1;
+  }
+
+  nop_function(iters);
+
+  read(fd, &instructions, sizeof(uint64_t));
+  if(ioctl(fd, PERF_EVENT_IOC_DISABLE, 0) == -1) {
+    perror("ioctl");
+    return -1;
+  }
+  if (clock_gettime(clock, &end) == -1) {
+    perror("clock_gettime");
+    return -1;
+  }
+
+  uint64_t nsecs = (end.tv_sec*1e9 + end.tv_nsec) - (start.tv_sec*1e9 + start.tv_nsec);
+  uint64_t usecs = nsecs/1000;  
+  double frequency = instructions/((double)usecs);
+
+  printf("\r%*c\r", (int) strlen(frequency_banner), ' ');
+  
+  // Discard last digit in the frequency, which should help providing
+  // more reliable and predictable values.
+  return (((int) frequency + 5)/10) * 10;
+}
+
+#endif // #ifdef __linux__

src/common/freq.h

@@ -0,0 +1,6 @@
+#ifndef __COMMON_FREQ__
+#define __COMMON_FREQ__
+
+int64_t measure_max_frequency(uint32_t core);
+
+#endif

src/x86/cpuid.c

@@ -6,6 +6,10 @@
   #include <unistd.h>
 #endif
 
+#ifdef __linux__
+  #include "../common/freq.h"
+#endif
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -967,6 +971,14 @@ struct frequency* get_frequency_info(struct cpuInfo* cpu) {
     }
   }
 
+  #ifdef __linux__
+    if (freq->max == UNKNOWN_DATA) {
+      printWarn("All previous methods failed, measuring CPU frequency");
+      // TODO: Support hybrid architectures
+      freq->max = measure_max_frequency(0);
+    }
+  #endif
+
   return freq;
 }