[profile] Add %t LLVM_PROFILE_FILE option to substitute $TMPDIR

[vsk]

Summary

Add support for expanding the %t filename specifier in LLVM_PROFILE_FILE
to the TMPDIR environment variable. This is supported on all platforms.

On Darwin, TMPDIR is used to specify a temporary application-specific
scratch directory. When testing apps on remote devices, it can be
challenging for the host device to determine the correct TMPDIR, so it's
helpful to have the runtime do this work.

rdar://68524185

[vsk]

• Document the new option.

[ejvaughan]

Changes look good to me. Thanks for implementing this, Vedant!

clang/docs/SourceBasedCodeCoverage.rst

 ``LLVM_PROFILE_FILE`` contains a path to a non-existent directory, the missing
 directory structure will be created.  Additionally, the following special
 **pattern strings** are rewritten:
 
 * "%p" expands out to the process ID.
 
 * "%h" expands out to the hostname of the machine running the program.
 
+* "%t" expands out to the value of the ``TMPDIR`` environment variable. On
+  Darwin, this is typically set to a temporary scratch directory.
+
 * "%Nm" expands out to the instrumented binary's signature. When this pattern
   is specified, the runtime creates a pool of N raw profiles which are used for
   on-line profile merging. The runtime takes care of selecting a raw profile
   from the pool, locking it, and updating it before the program exits.  If N is
   not specified (i.e the pattern is "%m"), it's assumed that ``N = 1``. N must
   be between 1 and 9. The merge pool specifier can only occur once per filename
   pattern.
 

compiler-rt/lib/profile/InstrProfilingFile.c

 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;
   char PidChars[MAX_PID_SIZE];
+  char *TmpDir;
   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;
 
-static lprofFilename lprofCurFilename = {0, 0, 0, {0},        {0},
-                                         0, 0, 0, PNS_unknown};
+static lprofFilename lprofCurFilename = {0,   0, 0, {0}, NULL,
+                                         {0}, 0, 0, 0,   PNS_unknown};
 
 static int ProfileMergeRequested = 0;
 static int isProfileMergeRequested() { return ProfileMergeRequested; }
 static void setProfileMergeRequested(int EnableMerge) {
   ProfileMergeRequested = EnableMerge;
 }
 
 static FILE *ProfileFile = NULL;
if (FilenamePat[I] == '%') {
       } else if (FilenamePat[I] == 'h') {
         if (!NumHosts++)
           if (COMPILER_RT_GETHOSTNAME(Hostname, COMPILER_RT_MAX_HOSTLEN)) {
             PROF_WARN("Unable to get hostname for filename pattern %s. Using "
                       "the default name.",
                       FilenamePat);
             return -1;
           }
+      } else if (FilenamePat[I] == 't') {
+        lprofCurFilename.TmpDir = getenv("TMPDIR");
+        if (!lprofCurFilename.TmpDir) {
+          PROF_WARN("Unable to get the TMPDIR environment variable, referenced "
+                    "in %s. Using the default path.",
+                    FilenamePat);
+          return -1;
+        }
       } else if (FilenamePat[I] == 'c') {
         if (__llvm_profile_is_continuous_mode_enabled()) {
           PROF_WARN("%%c specifier can only be specified once in %s.\n",
                     FilenamePat);
           return -1;
         }
 
         __llvm_profile_set_page_size(getpagesize());

 /* The length to hold uint64_t followed by 3 digits pool id including '_' */
 #define SIGLEN 24
 static int getCurFilenameLength() {
   int Len;
   if (!lprofCurFilename.FilenamePat || !lprofCurFilename.FilenamePat[0])
     return 0;
 
   if (!(lprofCurFilename.NumPids || lprofCurFilename.NumHosts ||
-        lprofCurFilename.MergePoolSize))
+        lprofCurFilename.TmpDir || lprofCurFilename.MergePoolSize))
     return strlen(lprofCurFilename.FilenamePat);
 
   Len = strlen(lprofCurFilename.FilenamePat) +
         lprofCurFilename.NumPids * (strlen(lprofCurFilename.PidChars) - 2) +
-        lprofCurFilename.NumHosts * (strlen(lprofCurFilename.Hostname) - 2);
+        lprofCurFilename.NumHosts * (strlen(lprofCurFilename.Hostname) - 2) +
+        (lprofCurFilename.TmpDir ? (strlen(lprofCurFilename.TmpDir) - 1) : 0);
   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, unless ForceUseBuf
  * is enabled. */
 static const char *getCurFilename(char *FilenameBuf, int ForceUseBuf) {
-  int I, J, PidLength, HostNameLength, FilenamePatLength;
+  int I, J, PidLength, HostNameLength, TmpDirLength, FilenamePatLength;
   const char *FilenamePat = lprofCurFilename.FilenamePat;
 
   if (!lprofCurFilename.FilenamePat || !lprofCurFilename.FilenamePat[0])
     return 0;
 
   if (!(lprofCurFilename.NumPids || lprofCurFilename.NumHosts ||
-        lprofCurFilename.MergePoolSize ||
+        lprofCurFilename.TmpDir || lprofCurFilename.MergePoolSize ||
         __llvm_profile_is_continuous_mode_enabled())) {
     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);
+  TmpDirLength = lprofCurFilename.TmpDir ? strlen(lprofCurFilename.TmpDir) : 0;
   /* 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;
       } else if (FilenamePat[I] == 'h') {
         memcpy(FilenameBuf + J, lprofCurFilename.Hostname, HostNameLength);
         J += HostNameLength;
+      } else if (FilenamePat[I] == 't') {
+        memcpy(FilenameBuf + J, lprofCurFilename.TmpDir, TmpDirLength);
+        FilenameBuf[J + TmpDirLength] = DIR_SEPARATOR;
+        J += TmpDirLength + 1;
       } else {
         if (!getMergePoolSize(FilenamePat, &I))
           continue;
         char LoadModuleSignature[SIGLEN + 1];
         int S;
         int ProfilePoolId = getpid() % lprofCurFilename.MergePoolSize;
         S = snprintf(LoadModuleSignature, SIGLEN + 1, "%" PRIu64 "_%d",
                      lprofGetLoadModuleSignature(), ProfilePoolId);

compiler-rt/test/profile/instrprof-tmpdir.c

+// RUN: rm -rf %t
+// RUN: mkdir -p %t
+// RUN: cd %t
+// RUN: %clang_profgen -o %t/binary %s
+//
+// Check that a dir separator is appended after %t is subsituted.
+// RUN: env TMPDIR="%t" LLVM_PROFILE_FILE="%%traw1.profraw" %run ./binary
+// RUN: llvm-profdata show ./raw1.profraw | FileCheck %s -check-prefix TMPDIR
+//
+// Check that substitution works even if a redundant dir separator is added.
+// RUN: env TMPDIR="%t" LLVM_PROFILE_FILE="%%t/raw2.profraw" %run ./binary
+// RUN: llvm-profdata show ./raw2.profraw | FileCheck %s -check-prefix TMPDIR
+//
+// Check that we fall back to the default path if TMPDIR is missing.
+// RUN: env -u TMPDIR LLVM_PROFILE_FILE="%%t/raw3.profraw" %run ./binary 2>&1 | FileCheck %s -check-prefix MISSING
+// RUN: llvm-profdata show ./default.profraw | FileCheck %s -check-prefix TMPDIR
+
+// TMPDIR: Maximum function count: 1
+
+// MISSING: Unable to get the TMPDIR environment variable, referenced in {{.*}}raw3.profraw. Using the default path.
+
+int main() { return 0; }