Support, LTO: When pruning a directory, ignore files matching a prefix.

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.

Differential Revision: https://reviews.llvm.org/D31109

llvm-svn: 298271

6 files changed, 30 insertions, 11 deletions

diff --git a/lld/test/ELF/lto/cache.ll b/lld/test/ELF/lto/cache.ll
index deb11b61de2..55e3a3d6f6c 100644
--- a/lld/test/ELF/lto/cache.ll
+++ b/lld/test/ELF/lto/cache.ll
@@ -4,12 +4,13 @@
 ; 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"
diff --git a/llvm/include/llvm/Support/CachePruning.h b/llvm/include/llvm/Support/CachePruning.h
index 46bab386a21..e826938878e 100644
--- a/llvm/include/llvm/Support/CachePruning.h
+++ b/llvm/include/llvm/Support/CachePruning.h
@@ -52,6 +52,10 @@ 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
diff --git a/llvm/lib/LTO/Caching.cpp b/llvm/lib/LTO/Caching.cpp
index 16edbece145..00373ddd1c4 100644
--- a/llvm/lib/LTO/Caching.cpp
+++ b/llvm/lib/LTO/Caching.cpp
@@ -27,9 +27,11 @@ Expected<NativeObjectCache> lto::localCache(StringRef 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) {
diff --git a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
index b793d0c9e3e..aa4d32a9c57 100644
--- a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
+++ b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
@@ -348,7 +348,10 @@ public:
             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.
diff --git a/llvm/lib/Support/CachePruning.cpp b/llvm/lib/Support/CachePruning.cpp
index 5d81e10469b..aca12363956 100644
--- a/llvm/lib/Support/CachePruning.cpp
+++ b/llvm/lib/Support/CachePruning.cpp
@@ -180,8 +180,11 @@ bool llvm::pruneCache(StringRef Path, CachePruningPolicy Policy) {
   // 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
diff --git a/llvm/test/ThinLTO/X86/cache.ll b/llvm/test/ThinLTO/X86/cache.ll
index d654d3468e3..426654f31d2 100644
--- a/llvm/test/ThinLTO/X86/cache.ll
+++ b/llvm/test/ThinLTO/X86/cache.ll
@@ -23,11 +23,16 @@
 ; 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
@@ -36,6 +41,7 @@
 ; 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"