tsan: split thread into logical and physical state

Currently ThreadState holds both logical state (required for race-detection algorithm, user-visible)
and physical state (various caches, most notably malloc cache). Move physical state in a new
Process entity. Besides just being the right thing from abstraction point of view, this solves several
problems:
1. Cache everything on P level in Go. Currently we cache on a mix of goroutine and OS thread levels.
This unnecessary increases memory consumption.
2. Properly handle free operations in Go. Frees are issue by GC which don't have goroutine context.
As the result we could not do anything more than just clearing shadow. For example, we leaked
sync objects and heap block descriptors.
3. This will allow to get rid of libc malloc in Go (now we have Processor context for internal allocator cache).
This in turn will allow to get rid of dependency on libc entirely.
4. Potentially we can make Processor per-CPU in C++ mode instead of per-thread, which will
reduce resource consumption.
The distinction between Thread and Processor is currently used only by Go, C++ creates Processor per OS thread,
which is equivalent to the current scheme.



git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@262037 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 5 insertions, 17 deletions

diff --git a/lib/tsan/rtl/tsan_rtl_thread.cc b/lib/tsan/rtl/tsan_rtl_thread.cc
index dcae255f7..353e086c7 100644
--- a/lib/tsan/rtl/tsan_rtl_thread.cc
+++ b/lib/tsan/rtl/tsan_rtl_thread.cc
@@ -42,7 +42,7 @@ void ThreadContext::OnDead() {
 void ThreadContext::OnJoined(void *arg) {
   ThreadState *caller_thr = static_cast<ThreadState *>(arg);
   AcquireImpl(caller_thr, 0, &sync);
-  sync.Reset(&caller_thr->clock_cache);
+  sync.Reset(&caller_thr->proc->clock_cache);
 }
 
 struct OnCreatedArgs {
@@ -74,7 +74,7 @@ void ThreadContext::OnReset() {
 
 void ThreadContext::OnDetached(void *arg) {
   ThreadState *thr1 = static_cast<ThreadState*>(arg);
-  sync.Reset(&thr1->clock_cache);
+  sync.Reset(&thr1->proc->clock_cache);
 }
 
 struct OnStartedArgs {
@@ -106,13 +106,8 @@ void ThreadContext::OnStarted(void *arg) {
   thr->shadow_stack_pos = thr->shadow_stack;
   thr->shadow_stack_end = thr->shadow_stack + kInitStackSize;
 #endif
-#ifndef SANITIZER_GO
-  AllocatorThreadStart(thr);
-#endif
-  if (common_flags()->detect_deadlocks) {
-    thr->dd_pt = ctx->dd->CreatePhysicalThread();
+  if (common_flags()->detect_deadlocks)
     thr->dd_lt = ctx->dd->CreateLogicalThread(unique_id);
-  }
   thr->fast_state.SetHistorySize(flags()->history_size);
   // Commit switch to the new part of the trace.
   // TraceAddEvent will reset stack0/mset0 in the new part for us.
@@ -121,7 +116,7 @@ void ThreadContext::OnStarted(void *arg) {
   thr->fast_synch_epoch = epoch0;
   AcquireImpl(thr, 0, &sync);
   StatInc(thr, StatSyncAcquire);
-  sync.Reset(&thr->clock_cache);
+  sync.Reset(&thr->proc->clock_cache);
   thr->is_inited = true;
   DPrintf("#%d: ThreadStart epoch=%zu stk_addr=%zx stk_size=%zx "
           "tls_addr=%zx tls_size=%zx\n",
@@ -138,15 +133,8 @@ void ThreadContext::OnFinished() {
   }
   epoch1 = thr->fast_state.epoch();
 
-  if (common_flags()->detect_deadlocks) {
-    ctx->dd->DestroyPhysicalThread(thr->dd_pt);
+  if (common_flags()->detect_deadlocks)
     ctx->dd->DestroyLogicalThread(thr->dd_lt);
-  }
-  ctx->clock_alloc.FlushCache(&thr->clock_cache);
-  ctx->metamap.OnThreadIdle(thr);
-#ifndef SANITIZER_GO
-  AllocatorThreadFinish(thr);
-#endif
   thr->~ThreadState();
 #if TSAN_COLLECT_STATS
   StatAggregate(ctx->stat, thr->stat);