Support, LTO: When pruning a directory, ignore files not matching a prefix.

[pcc]

Summary

This is a safeguard against data loss if the user specifies a directory
that is not a cache directory. Teach the existing cache pruning clients
to create files with appropriate names.

[krasin]

Generally, looks good, modulo the comment.

llvm/lib/Support/CachePruning.cpp

193 ↗

(On Diff #92223)

We should just ignore files not created by LLVM. If a user decided to put something there, then she has a reason. And there's no actual harm to our code, if these files exist but ignored.

[pcc]

• Address review comments

llvm/lib/Support/CachePruning.cpp

193 ↗

(On Diff #92223)

Makes sense, done.

[krasin]

Thank you, Peter!

lld/trunk/test/ELF/lto/cache.ll

 ; REQUIRES: x86
 
 ; RUN: opt -module-hash -module-summary %s -o %t.o
 ; RUN: opt -module-hash -module-summary %p/Inputs/cache.ll -o %t2.o
 
 ; RUN: rm -Rf %t.cache && mkdir %t.cache
-; Create a file that will be removed by cache pruning due to age.
-; RUN: touch -t 197001011200 %t.cache/foo
+; Create two files that would be removed by cache pruning due to age.
+; We should only remove files matching the pattern "llvmcache-*".
+; RUN: touch -t 197001011200 %t.cache/llvmcache-foo %t.cache/foo
 ; RUN: ld.lld --thinlto-cache-dir=%t.cache --thinlto-cache-policy prune_after=1h -o %t3 %t2.o %t.o
 
-; Two cached objects, plus a timestamp file, minus the file we removed.
-; RUN: ls %t.cache | count 3
+; Two cached objects, plus a timestamp file and "foo", minus the file we removed.
+; RUN: ls %t.cache | count 4
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 define void @globalfunc() #0 {
 entry:
   ret void
 }

llvm/trunk/include/llvm/Support/CachePruning.h

 /// default constructed CachePruningPolicy object.
 /// For example: "prune_interval=30s:prune_after=24h:cache_size=50%"
 /// which means a pruning interval of 30 seconds, expiration time of 24 hours
 /// and maximum cache size of 50% of available disk space.
 Expected<CachePruningPolicy> parseCachePruningPolicy(StringRef PolicyStr);
 
 /// Peform pruning using the supplied policy, returns true if pruning
 /// occured, i.e. if Policy.Interval was expired.
+///
+/// As a safeguard against data loss if the user specifies the wrong directory
+/// as their cache directory, this function will ignore files not matching the
+/// pattern "llvmcache-*".
 bool pruneCache(StringRef Path, CachePruningPolicy Policy);
 
 } // namespace llvm
 
 #endif

llvm/trunk/lib/LTO/Caching.cpp

 using namespace llvm::lto;
 
 Expected<NativeObjectCache> lto::localCache(StringRef CacheDirectoryPath,
                                             AddBufferFn AddBuffer) {
   if (std::error_code EC = sys::fs::create_directories(CacheDirectoryPath))
     return errorCodeToError(EC);
 
   return [=](unsigned Task, StringRef Key) -> AddStreamFn {
-    // First, see if we have a cache hit.
+    // This choice of file name allows the cache to be pruned (see pruneCache()
+    // in include/llvm/Support/CachePruning.h).
     SmallString<64> EntryPath;
-    sys::path::append(EntryPath, CacheDirectoryPath, Key);
+    sys::path::append(EntryPath, CacheDirectoryPath, "llvmcache-" + Key);
+    // First, see if we have a cache hit.
     ErrorOr<std::unique_ptr<MemoryBuffer>> MBOrErr =
         MemoryBuffer::getFile(EntryPath);
     if (MBOrErr) {
       AddBuffer(Task, std::move(*MBOrErr));
       return AddStreamFn();
     }
 
     // FIXME: Workaround for libstdc++ version mismatch bug, see D31063 review

llvm/trunk/lib/LTO/ThinLTOCodeGenerator.cpp

#endif
 
     // Include the hash for the preserved symbols.
     for (auto &Entry : PreservedSymbols) {
       if (DefinedFunctions.count(Entry))
         Hasher.update(
             ArrayRef<uint8_t>((const uint8_t *)&Entry, sizeof(GlobalValue::GUID)));
     }
 
-    sys::path::append(EntryPath, CachePath, toHex(Hasher.result()));
+    // This choice of file name allows the cache to be pruned (see pruneCache()
+    // in include/llvm/Support/CachePruning.h).
+    sys::path::append(EntryPath, CachePath,
+                      "llvmcache-" + toHex(Hasher.result()));
   }
 
   // Access the path to this entry in the cache.
   StringRef getEntryPath() { return EntryPath; }
 
   // Try loading the buffer for this cache entry.
   ErrorOr<std::unique_ptr<MemoryBuffer>> tryLoadingBuffer() {
     if (EntryPath.empty())

llvm/trunk/lib/Support/CachePruning.cpp

bool llvm::pruneCache(StringRef Path, CachePruningPolicy Policy) {
 
   // Walk the entire directory cache, looking for unused files.
   std::error_code EC;
   SmallString<128> CachePathNative;
   sys::path::native(Path, CachePathNative);
   // Walk all of the files within this directory.
   for (sys::fs::directory_iterator File(CachePathNative, EC), FileEnd;
        File != FileEnd && !EC; File.increment(EC)) {
-    // Do not touch the timestamp.
-    if (File->path() == TimestampFile)
+    // Ignore any files not beginning with the string "llvmcache-". This
+    // includes the timestamp file as well as any files created by the user.
+    // This acts as a safeguard against data loss if the user specifies the
+    // wrong directory as their cache directory.
+    if (!sys::path::filename(File->path()).startswith("llvmcache-"))
       continue;
 
     // Look at this file. If we can't stat it, there's nothing interesting
     // there.
     if (sys::fs::status(File->path(), FileStatus)) {
       DEBUG(dbgs() << "Ignore " << File->path() << " (can't stat)\n");
       continue;
     }

llvm/trunk/test/ThinLTO/X86/cache.ll

 ; RUN: ls %t.cache | count 0
 
 
 ; Repeat again, *with* hash this time.
 
 ; RUN: opt -module-hash -module-summary %s -o %t.bc
 ; RUN: opt -module-hash -module-summary %p/Inputs/cache.ll -o %t2.bc
 
-; Verify that enabling caching is working
+; Verify that enabling caching is working, and that the pruner only removes
+; files matching the pattern "llvmcache-*".
 ; RUN: rm -Rf %t.cache && mkdir %t.cache
+; RUN: touch -t 197001011200 %t.cache/llvmcache-foo %t.cache/foo
 ; RUN: llvm-lto -thinlto-action=run -exported-symbol=globalfunc %t2.bc  %t.bc -thinlto-cache-dir %t.cache
+; RUN: ls %t.cache | count 4
 ; RUN: ls %t.cache/llvmcache.timestamp
-; RUN: ls %t.cache | count 3
+; RUN: ls %t.cache/foo
+; RUN: not ls %t.cache/llvmcache-foo
+; RUN: ls %t.cache/llvmcache-* | count 2
 
 ; Verify that enabling caching is working with llvm-lto2
 ; RUN: rm -Rf %t.cache
 ; RUN: llvm-lto2 -o %t.o %t2.bc  %t.bc -cache-dir %t.cache \
 ; RUN:  -r=%t2.bc,_main,plx \
 ; RUN:  -r=%t2.bc,_globalfunc,lx \
 ; RUN:  -r=%t.bc,_globalfunc,plx
 ; RUN: ls %t.cache | count 2
+; RUN: ls %t.cache/llvmcache-* | count 2
 
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.11.0"
 
 define void @globalfunc() #0 {
 entry:
   ret void
 }