[v1.03][PPC] Fix bug where /sys/devices/system/cpu/cpu*/topology/physical_package_id contains -1 by adding a new way of finding the number of sockets. This happened in #178 and most probably in #153 too

src/common/udev.c

@@ -278,3 +278,99 @@ int get_num_caches_by_level(struct cpuInfo* cpu, uint32_t level) {
 
   return ret;
 }
+
+// TODO: This function is very similar to get_num_caches_from_files,
+// refactoring should be considered
+int get_num_sockets_from_files(char** paths, int num_paths) {
+  int filelen;
+  char* buf;
+  char* tmpbuf;
+
+  // 1. Count the number of bitmasks per file
+  if((buf = read_file(paths[0], &filelen)) == NULL) {
+    printWarn("Could not open '%s'", paths[0]);
+    return -1;
+  }
+  int num_bitmasks = 1;
+  for(int i=0; buf[i]; i++) {
+    num_bitmasks += (buf[i] == ',');
+  }
+
+  // 2. Read package_cpus from every core
+  uint32_t** package_cpus = emalloc(sizeof(uint32_t *) * num_paths);
+  for(int i=0; i < num_paths; i++) {
+    package_cpus[i] = emalloc(sizeof(uint32_t) * num_bitmasks);
+
+    if((buf = read_file(paths[i], &filelen)) == NULL) {
+      printWarn("Could not open '%s'", paths[i]);
+      return -1;
+    }
+
+    for(int j=0; j < num_bitmasks; j++) {
+      char* end;
+      tmpbuf = emalloc(sizeof(char) * (strlen(buf) + 1));
+      char* commaend = strstr(buf, ",");
+      if(commaend == NULL) {
+        strcpy(tmpbuf, buf);
+      }
+      else {
+        strncpy(tmpbuf, buf, commaend-buf);
+      }
+      errno = 0;
+      long ret = strtol(tmpbuf, &end, 16);
+      if(errno != 0) {
+        printf("strtol: %s", strerror(errno));
+        free(buf);
+        return -1;
+      }
+
+      package_cpus[i][j] = (uint32_t) ret;
+      buf = commaend + 1;
+      free(tmpbuf);
+    }
+  }
+
+  // 3. Count number of different packages; this is the number of sockets
+  int num_sockets = 0;
+  bool found = false;
+  uint32_t** unique_package_cpu = emalloc(sizeof(uint32_t *) * num_paths);
+  for(int i=0; i < num_paths; i++) {
+    unique_package_cpu[i] = emalloc(sizeof(uint32_t) * num_bitmasks);
+    for(int j=0; j < num_bitmasks; j++) {
+      unique_package_cpu[i][j] = 0;
+    }
+  }
+
+  for(int i=0; i < num_paths; i++) {
+    for(int j=0; j < num_paths && !found; j++) {
+      if(maps_equal(package_cpus[i], unique_package_cpu[j], num_bitmasks)) found = true;
+    }
+    if(!found) {
+      add_shared_map(package_cpus, i, unique_package_cpu, num_sockets, num_bitmasks);
+      num_sockets++;
+    }
+    found = false;
+  }
+
+  return num_sockets;
+}
+
+int get_num_sockets_package_cpus(struct topology* topo) {
+  // Get number of sockets using
+  // /sys/devices/system/cpu/cpu*/topology/package_cpus
+
+  char** paths = emalloc(sizeof(char *) * topo->total_cores);
+
+  for(int i=0; i < topo->total_cores; i++) {
+    paths[i] = emalloc(sizeof(char) * _PATH_PACKAGE_MAX_LEN);
+    sprintf(paths[i], "%s%s/cpu%d%s",  _PATH_SYS_SYSTEM, _PATH_SYS_CPU, i, _PATH_TOPO_PACKAGE_CPUS);
+  }
+
+  int ret = get_num_sockets_from_files(paths, topo->total_cores);
+
+  for(int i=0; i < topo->total_cores; i++)
+    free(paths[i]);
+  free(paths);
+
+  return ret;
+}

src/common/udev.h

@@ -24,9 +24,11 @@
 #define _PATH_CACHE_SIZE        "/size"
 #define _PATH_CACHE_SHARED_MAP  "/shared_cpu_map"
 #define _PATH_CPUS_PRESENT      _PATH_SYS_SYSTEM _PATH_SYS_CPU "/present"
+#define _PATH_TOPO_PACKAGE_CPUS "/topology/package_cpus"
 
 #define _PATH_FREQUENCY_MAX_LEN 100
 #define _PATH_CACHE_MAX_LEN     200
+#define _PATH_PACKAGE_MAX_LEN   200
 
 char* read_file(char* path, int* len);
 long get_max_freq_from_file(uint32_t core);
@@ -36,6 +38,7 @@ long get_l1d_cache_size(uint32_t core);
 long get_l2_cache_size(uint32_t core);
 long get_l3_cache_size(uint32_t core);
 int get_num_caches_by_level(struct cpuInfo* cpu, uint32_t level);
+int get_num_sockets_package_cpus(struct topology* topo);
 int get_ncores_from_cpuinfo(void);
 
 #endif

src/ppc/ppc.c

@@ -44,17 +44,6 @@ struct cache* get_cache_info(struct cpuInfo* cpu) {
   return cach;
 }
 
-bool check_package_ids_integrity(int* package_ids, int total_cores) {
-  for(int i=0; i < total_cores; i++) {
-    if(package_ids[i] >= total_cores || package_ids[i] < 0) {
-      printBug("check_package_ids_integrity: package_ids[%d]=%d", i, package_ids[i]);
-      return false;
-    }
-  }
-
-  return true;
-}
-
 struct topology* get_topology_info(struct cache* cach) {
   struct topology* topo = emalloc(sizeof(struct topology));
   init_topology_struct(topo, cach);
@@ -74,16 +63,17 @@ struct topology* get_topology_info(struct cache* cach) {
     printWarn("fill_core_ids_from_sys failed, output may be incomplete/invalid");
     for(int i=0; i < topo->total_cores; i++) core_ids[i] = 0;
   }
+
   if(!fill_package_ids_from_sys(package_ids, topo->total_cores)) {
     printWarn("fill_package_ids_from_sys failed, output may be incomplete/invalid");
     for(int i=0; i < topo->total_cores; i++) package_ids[i] = 0;
+    // fill_package_ids_from_sys failed, use a
+    // more sophisticated wat to find the number of sockets
+    topo->sockets = get_num_sockets_package_cpus(topo);
   }
-
-  if(!check_package_ids_integrity(package_ids, topo->total_cores)) {
-    return NULL;
-  }
-
-  // 2. Socket detection
+  else {
+    // fill_package_ids_from_sys succeeded, use the
+    // traditional socket detection algorithm
     int *package_ids_count = emalloc(sizeof(int) * topo->total_cores);
     for(int i=0; i < topo->total_cores; i++) {
       package_ids_count[i] = 0;
@@ -96,6 +86,8 @@ struct topology* get_topology_info(struct cache* cach) {
         topo->sockets++;
       }
     }
+    free(package_ids_count);
+  }
 
   // 3. Physical cores detection
   int *core_ids_unified = emalloc(sizeof(int) * topo->total_cores);
@@ -120,7 +112,6 @@ struct topology* get_topology_info(struct cache* cach) {
 
   free(core_ids);
   free(package_ids);
-  free(package_ids_count);
   free(core_ids_unified);
 
   return topo;
@@ -187,7 +178,9 @@ struct cpuInfo* get_cpu_info(void) {
   char* path = emalloc(sizeof(char) * (strlen(_PATH_DT) + strlen(_PATH_DT_PART) + 1));
   sprintf(path, "%s%s", _PATH_DT, _PATH_DT_PART);
 
-  cpu->cpu_name = read_file(path, &len);
+  if((cpu->cpu_name = read_file(path, &len)) == NULL) {
+    printWarn("Could not open '%s'", path);
+  }
   cpu->pvr = mfpvr();
   cpu->arch = get_cpu_uarch(cpu);
   cpu->freq = get_frequency_info();

src/ppc/udev.c

@@ -1,5 +1,6 @@
 #include <errno.h>
 
+#include "../common/udev.h"
 #include "../common/global.h"
 #include "udev.h"
 
@@ -11,6 +12,7 @@ bool fill_array_from_sys(int *core_ids, int total_cores, char* SYS_PATH) {
   char* buf;
   char* end;
   char path[128];
+  memset(path, 0, 128);
 
   for(int i=0; i < total_cores; i++) {
     sprintf(path, "%s%s/cpu%d/%s", _PATH_SYS_SYSTEM, _PATH_SYS_CPU, i, SYS_PATH);
@@ -36,5 +38,22 @@ bool fill_core_ids_from_sys(int *core_ids, int total_cores) {
 }
 
 bool fill_package_ids_from_sys(int* package_ids, int total_cores) {
-  return fill_array_from_sys(package_ids, total_cores, _PATH_TOPO_PACKAGE_ID);
+  bool status = fill_array_from_sys(package_ids, total_cores, _PATH_TOPO_PACKAGE_ID);
+  if(status) {
+    // fill_array_from_sys completed successfully, but we
+    // must to check the integrity of the package_ids array
+    for(int i=0; i < total_cores; i++) {
+      if(package_ids[i] == -1) {
+        printWarn("fill_package_ids_from_sys: package_ids[%d] = -1", i);
+        return false;
+      }
+      else if(package_ids[i] >= total_cores || package_ids[i] < 0) {
+        printBug("fill_package_ids_from_sys: package_ids[%d] = %d", i, package_ids[i]);
+        return false;
+      }
+    }
+
+    return true;
+  }
+  return false;
 }

src/ppc/udev.h

@@ -7,5 +7,6 @@
 
 bool fill_core_ids_from_sys(int *core_ids, int total_cores);
 bool fill_package_ids_from_sys(int* package_ids, int total_cores);
+int get_num_sockets_package_cpus(struct topology* topo);
 
 #endif