[profile] Add interface to get profile filename

[tejohnson]

Summary

Add __llvm_profile_get_filename interface to get the profile filename,
which can be used for identifying which profile file belongs to an app
when multiple binaries are instrumented and dumping profiles into the
same directory. The filename includes the path.

[davidxl]

lib/profile/InstrProfilingFile.c

529 ↗

(On Diff #156206)

Why not directly passing the malloced buffer to getCurFilename?

[tejohnson]

lib/profile/InstrProfilingFile.c

529 ↗

(On Diff #156206)

getCurFilename doesn't always use the provided FilenameBuf, only if it needs to substitute in a value to the filename pattern. If not, the FilenamePat is returned (note also that this code is modeled after __llvm_profile_get_path_prefix).

[davidxl]

lib/profile/InstrProfilingFile.c

529 ↗

(On Diff #156206)

Perhaps add an additional argument to getCurFilename to force copying into the buffer?

[tejohnson]

Address comment

[davidxl]

lgtm

lib/profile/InstrProfiling.h

177 ↗

(On Diff #156305)

please also add a comment that if user calls __llvm_profile_set_filename later after this call, the actual file name may differ from what is returned here.

[tejohnson]

Address comment

compiler-rt/trunk/lib/profile/InstrProfiling.h

  * This is useful for users using \c -fprofile-generate=./path_prefix who do
  * not care about the default raw profile name. It is also useful to collect
  * more than more profile data files dumped in the same directory (Online
  * merge mode is turned on for instrumented programs with shared libs).
  * Side-effect: this API call will invoke malloc with dynamic memory allocation.
  */
 const char *__llvm_profile_get_path_prefix();
 
+/*!
+ * \brief Return filename (including path) of the profile data. Note that if the
+ * user calls __llvm_profile_set_filename later after invoking this interface,
+ * the actual file name may differ from what is returned here.
+ * Side-effect: this API call will invoke malloc with dynamic memory allocation.
+ */
+const char *__llvm_profile_get_filename();
+
 /*! \brief Get the magic token for the file format. */
 uint64_t __llvm_profile_get_magic(void);
 
 /*! \brief Get the version of the file format. */
 uint64_t __llvm_profile_get_version(void);
 
 /*! \brief Get the number of entries in the profile data section. */
 uint64_t __llvm_profile_get_data_size(const __llvm_profile_data *Begin,

compiler-rt/trunk/lib/profile/InstrProfilingFile.c

 /* Data structure holding the result of parsed filename pattern. */
 typedef struct lprofFilename {
   /* File name string possibly with %p or %h specifiers. */
   const char *FilenamePat;
   /* A flag indicating if FilenamePat's memory is allocated
    * by runtime. */
   unsigned OwnsFilenamePat;
   const char *ProfilePathPrefix;
+  const char *Filename;
   char PidChars[MAX_PID_SIZE];
   char Hostname[COMPILER_RT_MAX_HOSTLEN];
   unsigned NumPids;
   unsigned NumHosts;
   /* When in-process merging is enabled, this parameter specifies
    * the total number of profile data files shared by all the processes
    * spawned from the same binary. By default the value is 1. If merging
    * is not enabled, its value should be 0. This parameter is specified
    * by the %[0-9]m specifier. For instance %2m enables merging using
    * 2 profile data files. %1m is equivalent to %m. Also %m specifier
    * can only appear once at the end of the name pattern. */
   unsigned MergePoolSize;
   ProfileNameSpecifier PNS;
 } lprofFilename;
 
-COMPILER_RT_WEAK lprofFilename lprofCurFilename = {0, 0, 0, {0}, {0},
-                                                   0, 0, 0, PNS_unknown};
+COMPILER_RT_WEAK lprofFilename lprofCurFilename = {0,   0, 0, 0, {0},
+                                                   {0}, 0, 0, 0, PNS_unknown};
 
 static int getCurFilenameLength();
-static const char *getCurFilename(char *FilenameBuf);
+static const char *getCurFilename(char *FilenameBuf, int ForceUseBuf);
 static unsigned doMerging() { return lprofCurFilename.MergePoolSize; }
 
 /* Return 1 if there is an error, otherwise return  0.  */
 static uint32_t fileWriter(ProfDataWriter *This, ProfDataIOVec *IOVecs,
                            uint32_t NumIOVecs) {
   uint32_t I;
   FILE *File = (FILE *)This->WriterCtx;
   for (I = 0; I < NumIOVecs; I++) {

 static void truncateCurrentFile(void) {
   const char *Filename;
   char *FilenameBuf;
   FILE *File;
   int Length;
 
   Length = getCurFilenameLength();
   FilenameBuf = (char *)COMPILER_RT_ALLOCA(Length + 1);
-  Filename = getCurFilename(FilenameBuf);
+  Filename = getCurFilename(FilenameBuf, 0);
   if (!Filename)
     return;
 
   /* By pass file truncation to allow online raw profile
    * merging. */
   if (lprofCurFilename.MergePoolSize)
     return;
 

  * lprofcurFilename structure. */
 static int parseFilenamePattern(const char *FilenamePat,
                                 unsigned CopyFilenamePat) {
   int NumPids = 0, NumHosts = 0, I;
   char *PidChars = &lprofCurFilename.PidChars[0];
   char *Hostname = &lprofCurFilename.Hostname[0];
   int MergingEnabled = 0;
 
-  /* Clean up cached prefix.  */
+  /* Clean up cached prefix and filename.  */
   if (lprofCurFilename.ProfilePathPrefix)
     free((void *)lprofCurFilename.ProfilePathPrefix);
+  if (lprofCurFilename.Filename)
+    free((void *)lprofCurFilename.Filename);
+
   memset(&lprofCurFilename, 0, sizeof(lprofCurFilename));
 
   if (lprofCurFilename.FilenamePat && lprofCurFilename.OwnsFilenamePat) {
     free((void *)lprofCurFilename.FilenamePat);
   }
 
   if (!CopyFilenamePat)
     lprofCurFilename.FilenamePat = FilenamePat;
static int getCurFilenameLength() {
   if (lprofCurFilename.MergePoolSize)
     Len += SIGLEN;
   return Len;
 }
 
 /* Return the pointer to the current profile file name (after substituting
  * PIDs and Hostnames in filename pattern. \p FilenameBuf is the buffer
  * to store the resulting filename. If no substitution is needed, the
- * current filename pattern string is directly returned. */
-static const char *getCurFilename(char *FilenameBuf) {
-  int I, J, PidLength, HostNameLength;
+ * current filename pattern string is directly returned, unless ForceUseBuf
+ * is enabled. */
+static const char *getCurFilename(char *FilenameBuf, int ForceUseBuf) {
+  int I, J, PidLength, HostNameLength, FilenamePatLength;
   const char *FilenamePat = lprofCurFilename.FilenamePat;
 
   if (!lprofCurFilename.FilenamePat || !lprofCurFilename.FilenamePat[0])
     return 0;
 
   if (!(lprofCurFilename.NumPids || lprofCurFilename.NumHosts ||
-        lprofCurFilename.MergePoolSize))
+        lprofCurFilename.MergePoolSize)) {
+    if (!ForceUseBuf)
       return lprofCurFilename.FilenamePat;
 
+    FilenamePatLength = strlen(lprofCurFilename.FilenamePat);
+    memcpy(FilenameBuf, lprofCurFilename.FilenamePat, FilenamePatLength);
+    FilenameBuf[FilenamePatLength] = '\0';
+    return FilenameBuf;
+  }
+
   PidLength = strlen(lprofCurFilename.PidChars);
   HostNameLength = strlen(lprofCurFilename.Hostname);
   /* Construct the new filename. */
   for (I = 0, J = 0; FilenamePat[I]; ++I)
     if (FilenamePat[I] == '%') {
       if (FilenamePat[++I] == 'p') {
         memcpy(FilenameBuf + J, lprofCurFilename.PidChars, PidLength);
         J += PidLength;
const char *__llvm_profile_get_path_prefix(void) {
   char *FilenameBuf, *Prefix;
   const char *Filename, *PrefixEnd;
 
   if (lprofCurFilename.ProfilePathPrefix)
     return lprofCurFilename.ProfilePathPrefix;
 
   Length = getCurFilenameLength();
   FilenameBuf = (char *)COMPILER_RT_ALLOCA(Length + 1);
-  Filename = getCurFilename(FilenameBuf);
+  Filename = getCurFilename(FilenameBuf, 0);
   if (!Filename)
     return "\0";
 
   PrefixEnd = lprofFindLastDirSeparator(Filename);
   if (!PrefixEnd)
     return "\0";
 
   Length = PrefixEnd - Filename + 1;
   Prefix = (char *)malloc(Length + 1);
   if (!Prefix) {
     PROF_ERR("Failed to %s\n", "allocate memory.");
     return "\0";
   }
   memcpy(Prefix, Filename, Length);
   Prefix[Length] = '\0';
   lprofCurFilename.ProfilePathPrefix = Prefix;
   return Prefix;
 }
 
+COMPILER_RT_VISIBILITY
+const char *__llvm_profile_get_filename(void) {
+  int Length;
+  char *FilenameBuf;
+  const char *Filename;
+
+  if (lprofCurFilename.Filename)
+    return lprofCurFilename.Filename;
+
+  Length = getCurFilenameLength();
+  FilenameBuf = (char *)malloc(Length + 1);
+  if (!FilenameBuf) {
+    PROF_ERR("Failed to %s\n", "allocate memory.");
+    return "\0";
+  }
+  Filename = getCurFilename(FilenameBuf, 1);
+  if (!Filename)
+    return "\0";
+
+  lprofCurFilename.Filename = FilenameBuf;
+  return FilenameBuf;
+}
+
 /* This method is invoked by the runtime initialization hook
  * InstrProfilingRuntime.o if it is linked in. Both user specified
  * profile path via -fprofile-instr-generate= and LLVM_PROFILE_FILE
  * environment variable can override this default value. */
 COMPILER_RT_VISIBILITY
 void __llvm_profile_initialize_file(void) {
   const char *EnvFilenamePat;
   const char *SelectedPat = NULL;
int __llvm_profile_write_file(void) {
   if (lprofProfileDumped()) {
     PROF_NOTE("Profile data not written to file: %s.\n", 
               "already written");
     return 0;
   }
 
   Length = getCurFilenameLength();
   FilenameBuf = (char *)COMPILER_RT_ALLOCA(Length + 1);
-  Filename = getCurFilename(FilenameBuf);
+  Filename = getCurFilename(FilenameBuf, 0);
 
   /* Check the filename. */
   if (!Filename) {
     PROF_ERR("Failed to write file : %s\n", "Filename not set");
     return -1;
   }
 
   /* Check if there is llvm/runtime version mismatch.  */

compiler-rt/trunk/test/profile/instrprof-get-filename.c

+// Test __llvm_profile_get_filename.
+// RUN: %clang_pgogen -O2 -o %t %s
+// RUN: %run %t
+
+#include <stdio.h>
+#include <string.h>
+
+const char *__llvm_profile_get_filename();
+void __llvm_profile_set_filename(const char *);
+
+int main(int argc, const char *argv[]) {
+  int i;
+  const char *filename;
+  const char *new_filename = "/path/to/test.profraw";
+
+  filename = __llvm_profile_get_filename();
+  if (strncmp(filename, "default_", 8)) {
+    fprintf(stderr,
+            "Error: got filename %s, expected it to start with 'default_'\n",
+            filename);
+    return 1;
+  }
+  if (strcmp(filename + strlen(filename) - strlen(".profraw"), ".profraw")) {
+    fprintf(stderr,
+            "Error: got filename %s, expected it to end with '.profraw'\n",
+            filename);
+    return 1;
+  }
+
+  __llvm_profile_set_filename(new_filename);
+  filename = __llvm_profile_get_filename();
+  if (strcmp(filename, new_filename)) {
+    fprintf(stderr, "Error: got filename %s, expected '%s'\n", filename,
+            new_filename);
+    return 1;
+  }
+
+  return 0;
+}