[PATCH] D60980: [fuzzer] Replace -seed_corpus with -seed_corpus_file

[Jonathan Metzman via Phabricator via llvm-commits]

metzman created this revision.
Herald added projects: Sanitizers, LLVM.
Herald added subscribers: llvm-commits, Sanitizers.

Pass seed corpus list in a file to get around
argument length limits on Windows.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D60980

Files:
  compiler-rt/lib/fuzzer/FuzzerDriver.cpp
  compiler-rt/lib/fuzzer/FuzzerFlags.def
  compiler-rt/lib/fuzzer/FuzzerFork.cpp
  compiler-rt/test/fuzzer/cross_over.test
  compiler-rt/test/fuzzer/len_control.test


Index: compiler-rt/test/fuzzer/len_control.test
===================================================================
--- compiler-rt/test/fuzzer/len_control.test
+++ compiler-rt/test/fuzzer/len_control.test
@@ -4,8 +4,9 @@
 LIM4: DONE{{.*}}lim: 4
 LIM77: DONE{{.*}}lim: 77
 LIM20: DONE{{.*}}lim: 20
-RUN: %run %t-SimpleTest -runs=1  2>&1 | FileCheck %s --check-prefix=LIM4
-RUN: %run %t-SimpleTest -seed_inputs=%t-SimpleTest -max_len=77 -runs=1  2>&1 | FileCheck %s --check-prefix=LIM77
+RUN: %run %t-SimpleTest -runs=1 2>&1 | FileCheck %s --check-prefix=LIM4
+RUN: python -c "import sys; sys.stdout.write(r'%t-SimpleTest')" > %t.seed-inputs
+RUN: %run %t-SimpleTest -seed_inputs_file=%t.seed-inputs -max_len=77 -runs=1 2>&1 | FileCheck %s --check-prefix=LIM77
 RUN: echo -n 01234567890123456789 > %t-temp
-RUN: %run %t-SimpleTest -seed_inputs=%t-temp -runs=1  2>&1 | FileCheck %s --check-prefix=LIM20
-
+RUN: python -c "import sys; sys.stdout.write(r'%t-temp')" > %t.seed-inputs
+RUN: %run %t-SimpleTest -seed_inputs_file=%t.seed-inputs -runs=1 2>&1 | FileCheck %s --check-prefix=LIM20
Index: compiler-rt/test/fuzzer/cross_over.test
===================================================================
--- compiler-rt/test/fuzzer/cross_over.test
+++ compiler-rt/test/fuzzer/cross_over.test
@@ -15,4 +15,5 @@
 RUN: not %run %t-CrossOverTest -max_len=10 -seed=1 -runs=10000000 %t-corpus
 
 # Test the same thing but using -seed_inputs instead of passing the corpus dir.
-RUN: not %run %t-CrossOverTest -max_len=10 -seed=1 -runs=10000000 -seed_inputs=%t-corpus/A,%t-corpus/B
+RUN: python -c "import sys; sys.stdout.write(r'%t-corpus/A,%t-corpus/B')" > %t.seed-inputs
+RUN: not %run %t-CrossOverTest -max_len=10 -seed=1 -runs=10000000 -seed_inputs_file=%t.seed-inputs
Index: compiler-rt/lib/fuzzer/FuzzerFork.cpp
===================================================================
--- compiler-rt/lib/fuzzer/FuzzerFork.cpp
+++ compiler-rt/lib/fuzzer/FuzzerFork.cpp
@@ -121,8 +121,13 @@
       for (size_t i = 0; i < CorpusSubsetSize; i++)
         Seeds += (Seeds.empty() ? "" : ",") +
                  Files[Rand->SkewTowardsLast(Files.size())];
-    if (!Seeds.empty())
-      Cmd.addFlag("seed_inputs", Seeds);
+
+
+    if (!Seeds.empty()) {
+      std::string SeedsFile = "seeds-list." + std::to_string(JobId);
+      WriteToFile(reinterpret_cast<const uint8_t*>(Seeds.c_str()), Seeds.size(), SeedsFile);
+      Cmd.addFlag("seed_inputs_file", SeedsFile);
+    }
     Job->LogPath = DirPlusFile(TempDir, std::to_string(JobId) + ".log");
     Job->CorpusDir = DirPlusFile(TempDir, "C" + std::to_string(JobId));
     Job->FeaturesDir = DirPlusFile(TempDir, "F" + std::to_string(JobId));
Index: compiler-rt/lib/fuzzer/FuzzerFlags.def
===================================================================
--- compiler-rt/lib/fuzzer/FuzzerFlags.def
+++ compiler-rt/lib/fuzzer/FuzzerFlags.def
@@ -20,8 +20,8 @@
   "then try larger inputs over time.  Specifies the rate at which the length "
   "limit is increased (smaller == faster).  If 0, immediately try inputs with "
   "size up to max_len.")
-FUZZER_FLAG_STRING(seed_inputs, "A comma-separated list of input files "
-  "to use as an additional seed corpus")
+FUZZER_FLAG_STRING(seed_inputs_file, "A file containing a comma-separated list "
+  "of input files " "to use as an additional seed corpus")
 FUZZER_FLAG_INT(cross_over, 1, "If 1, cross over inputs.")
 FUZZER_FLAG_INT(mutate_depth, 5,
             "Apply this number of consecutive mutations to each input.")
Index: compiler-rt/lib/fuzzer/FuzzerDriver.cpp
===================================================================
--- compiler-rt/lib/fuzzer/FuzzerDriver.cpp
+++ compiler-rt/lib/fuzzer/FuzzerDriver.cpp
@@ -765,14 +765,13 @@
 
   // Parse -seed_inputs=file1,file2,...
   Vector<std::string> ExtraSeedFiles;
-  if (Flags.seed_inputs) {
-    std::string s = Flags.seed_inputs;
-    size_t comma_pos;
-    while ((comma_pos = s.find_last_of(',')) != std::string::npos) {
-      ExtraSeedFiles.push_back(s.substr(comma_pos + 1));
-      s = s.substr(0, comma_pos);
-    }
-    ExtraSeedFiles.push_back(s);
+  if (Flags.seed_inputs_file) {
+    std::string SeedInputsFile(Flags.seed_inputs_file);
+    // RemoveFile(SeedInputsFile);
+    std::istringstream SeedInputsStream(FileToString(SeedInputsFile));
+    std::string seed_input;
+    while (std::getline(SeedInputsStream, seed_input, ','))
+      ExtraSeedFiles.push_back(seed_input);
   }
 
   F->Loop(*Inputs, ExtraSeedFiles);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D60980.196135.patch
Type: text/x-patch
Size: 4495 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190422/dc31c8c9/attachment.bin>