Re: [PATCH 1/4] Cherry-pick fprofile-generate-atomic from google/gcc-4_9 branch

["Martin Liška" <mliska@suse.cz>]

[-- Attachment #1: Type: text/plain, Size: 626 bytes --]

On 08/05/2016 03:14 PM, Nathan Sidwell wrote:
> On 08/05/16 08:48, Martin Liška wrote:
> 
>> Ok, after all the experimenting and inventing "almost" thread-safe code, I incline to not to include __gcov_one_value_profiler_body_atomic
>> counter. The final solution is cumbersome and probably does not worth doing. Moreover, even having a thread-safe implementation, result of an indirect call counter
>> is not going to be stable among different runs (due to a single value storage capability).
>>
>> If you agree, I'll prepare a final version of patch?
> 
> Agreed.
> 
> nathan
> 

Great, attaching install candidate.

Martin

[-- Attachment #2: 0001-Cherry-pick-fprofile-generate-atomic-from-google-gcc-v3.patch --]
[-- Type: text/x-patch, Size: 8707 bytes --]

From 0b3ac8636ef34b02e301f22c86dde0602f9969ef Mon Sep 17 00:00:00 2001
From: marxin <mliska@suse.cz>
Date: Thu, 28 Jul 2016 14:32:47 +0200
Subject: [PATCH 1/4] Cherry-pick fprofile-generate-atomic from google/gcc-4_9
 branch

gcc/ChangeLog:

2016-08-05  Martin Liska  <mliska@suse.cz>

	Cherry picked (and modified) from google-4_7 branch
	2012-12-26  Rong Xu  <xur@google.com>
	* common.opt (fprofile-update): Add new flag.
	* coretypes.h: Define enum profile_update.
	* doc/invoke.texi: Document -fprofile-update.
	* gcov-io.h: Declare GCOV_TYPE_ATOMIC_FETCH_ADD and
	GCOV_TYPE_ATOMIC_FETCH_ADD_FN.
	* tree-profile.c (gimple_init_edge_profiler): Generate
	also atomic profiler update.
	(gimple_gen_edge_profiler): Likewise.

gcc/testsuite/ChangeLog:

2016-08-05  Martin Liska  <mliska@suse.cz>

	* g++.dg/gcov/gcov-threads-1.C: New test.
---
 gcc/common.opt                             | 13 ++++++++
 gcc/coretypes.h                            |  6 ++++
 gcc/doc/invoke.texi                        | 12 +++++++
 gcc/gcov-io.h                              |  8 +++++
 gcc/testsuite/g++.dg/gcov/gcov-threads-1.C | 46 ++++++++++++++++++++++++++
 gcc/tree-profile.c                         | 53 ++++++++++++++++++++----------
 6 files changed, 120 insertions(+), 18 deletions(-)
 create mode 100644 gcc/testsuite/g++.dg/gcov/gcov-threads-1.C

diff --git a/gcc/common.opt b/gcc/common.opt
index 8a292ed..44adae8 100644
--- a/gcc/common.opt
+++ b/gcc/common.opt
@@ -1916,6 +1916,19 @@ fprofile-correction
 Common Report Var(flag_profile_correction)
 Enable correction of flow inconsistent profile data input.
 
+fprofile-update=
+Common Joined RejectNegative Enum(profile_update) Var(flag_profile_update) Init(PROFILE_UPDATE_SINGLE)
+-fprofile-update=[single|atomic]	Set the profile update method.
+
+Enum
+Name(profile_update) Type(enum profile_update) UnknownError(unknown profile update method %qs)
+
+EnumValue
+Enum(profile_update) String(single) Value(PROFILE_UPDATE_SINGLE)
+
+EnumValue
+Enum(profile_update) String(atomic) Value(PROFILE_UPDATE_ATOMIC)
+
 fprofile-generate
 Common
 Enable common options for generating profile info for profile feedback directed optimizations.
diff --git a/gcc/coretypes.h b/gcc/coretypes.h
index b3a91a6..fe1e984 100644
--- a/gcc/coretypes.h
+++ b/gcc/coretypes.h
@@ -174,6 +174,12 @@ enum offload_abi {
   OFFLOAD_ABI_ILP32
 };
 
+/* Types of profile update methods.  */
+enum profile_update {
+  PROFILE_UPDATE_SINGLE,
+  PROFILE_UPDATE_ATOMIC
+};
+
 /* Types of unwind/exception handling info that can be generated.  */
 
 enum unwind_info_type
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 22001f9..1cfaae7 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -9933,6 +9933,18 @@ the profile feedback data files. See @option{-fprofile-dir}.
 To optimize the program based on the collected profile information, use
 @option{-fprofile-use}.  @xref{Optimize Options}, for more information.
 
+@item -fprofile-update=@var{method}
+@opindex fprofile-update
+
+Alter the update method for an application instrumented for profile
+feedback based optimization.  The @var{method} argument should be one of
+@samp{single} or @samp{atomic}.  The first one is useful for single-threaded
+applications, while the second one prevents profile corruption by emitting
+thread-safe code.
+
+@strong{Warning:} When an application does not properly join all threads
+(or creates an detached thread), a profile file can be still corrupted.
+
 @item -fsanitize=address
 @opindex fsanitize=address
 Enable AddressSanitizer, a fast memory error detector.
diff --git a/gcc/gcov-io.h b/gcc/gcov-io.h
index bbf013a..afd00ac 100644
--- a/gcc/gcov-io.h
+++ b/gcc/gcov-io.h
@@ -164,6 +164,14 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #ifndef GCC_GCOV_IO_H
 #define GCC_GCOV_IO_H
 
+#if LONG_LONG_TYPE_SIZE > 32
+#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_8
+#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_8
+#else
+#define GCOV_TYPE_ATOMIC_FETCH_ADD_FN __atomic_fetch_add_4
+#define GCOV_TYPE_ATOMIC_FETCH_ADD BUILT_IN_ATOMIC_FETCH_ADD_4
+#endif
+
 #ifndef IN_LIBGCOV
 /* About the host */
 
diff --git a/gcc/testsuite/g++.dg/gcov/gcov-threads-1.C b/gcc/testsuite/g++.dg/gcov/gcov-threads-1.C
new file mode 100644
index 0000000..a4a6f0a
--- /dev/null
+++ b/gcc/testsuite/g++.dg/gcov/gcov-threads-1.C
@@ -0,0 +1,46 @@
+/* { dg-options "-fprofile-arcs -ftest-coverage -pthread -fprofile-update=atomic" } */
+/* { dg-do run { target native } } */
+
+#include <stdint.h>
+#include <pthread.h>
+#include <assert.h>
+
+#define NR 5
+
+pthread_mutex_t cndMs[NR];
+static void *ContentionNoDeadlock_thread(void *start)
+{
+  for (uint32_t k = 0; k < 100000; ++k)		/* count(500005) */
+    {
+      int starti = *(int*)start;		/* count(500000) */
+      for (uint32_t i = starti; i < NR; ++i) 
+	pthread_mutex_lock (&cndMs[i]);
+      for (int32_t i = NR - 1; i >= starti; --i)
+	pthread_mutex_unlock (&cndMs[i]);
+  }
+}
+int main(int argc, char **argv) {
+  for (unsigned i = 0; i < NR; i++)
+    cndMs[i] = PTHREAD_MUTEX_INITIALIZER;
+
+  pthread_t t[NR];
+  int ids[NR];
+
+  for (int i = 0; i < NR; i++)
+  {
+    ids[i] = i;
+    int r = pthread_create (&t[i], NULL, ContentionNoDeadlock_thread, &ids[i]);
+    assert (r == 0);				/* count(5) */
+  }
+
+  int ret;
+  for (int i = 0; i < NR; i++)
+    {
+      int r = pthread_join (t[i], (void**)&ret);
+      assert (r == 0);				/* count(5) */
+    }
+
+  return 0;					/* count(1) */
+}
+
+/* { dg-final { run-gcov gcov-threads-1.C } } */
diff --git a/gcc/tree-profile.c b/gcc/tree-profile.c
index 39fe15f..740f7ab 100644
--- a/gcc/tree-profile.c
+++ b/gcc/tree-profile.c
@@ -127,6 +127,7 @@ gimple_init_edge_profiler (void)
   tree ic_profiler_fn_type;
   tree average_profiler_fn_type;
   tree time_profiler_fn_type;
+  const char *profiler_fn_name;
 
   if (!gcov_type_node)
     {
@@ -180,11 +181,12 @@ gimple_init_edge_profiler (void)
 					  gcov_type_node,
 					  ptr_void,
 					  NULL_TREE);
+      profiler_fn_name = "__gcov_indirect_call_profiler_v2";
+      if (PARAM_VALUE (PARAM_INDIR_CALL_TOPN_PROFILE))
+	profiler_fn_name = "__gcov_indirect_call_topn_profiler";
+
       tree_indirect_call_profiler_fn
-	      = build_fn_decl ( (PARAM_VALUE (PARAM_INDIR_CALL_TOPN_PROFILE) ?
-				 "__gcov_indirect_call_topn_profiler":
-				 "__gcov_indirect_call_profiler_v2"),
-			       ic_profiler_fn_type);
+	      = build_fn_decl (profiler_fn_name, ic_profiler_fn_type);
 
       TREE_NOTHROW (tree_indirect_call_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_indirect_call_profiler_fn)
@@ -241,22 +243,37 @@ gimple_init_edge_profiler (void)
 void
 gimple_gen_edge_profiler (int edgeno, edge e)
 {
-  tree ref, one, gcov_type_tmp_var;
-  gassign *stmt1, *stmt2, *stmt3;
+  tree one;
 
-  ref = tree_coverage_counter_ref (GCOV_COUNTER_ARCS, edgeno);
   one = build_int_cst (gcov_type_node, 1);
-  gcov_type_tmp_var = make_temp_ssa_name (gcov_type_node,
-					  NULL, "PROF_edge_counter");
-  stmt1 = gimple_build_assign (gcov_type_tmp_var, ref);
-  gcov_type_tmp_var = make_temp_ssa_name (gcov_type_node,
-					  NULL, "PROF_edge_counter");
-  stmt2 = gimple_build_assign (gcov_type_tmp_var, PLUS_EXPR,
-			       gimple_assign_lhs (stmt1), one);
-  stmt3 = gimple_build_assign (unshare_expr (ref), gimple_assign_lhs (stmt2));
-  gsi_insert_on_edge (e, stmt1);
-  gsi_insert_on_edge (e, stmt2);
-  gsi_insert_on_edge (e, stmt3);
+
+  if (flag_profile_update == PROFILE_UPDATE_ATOMIC)
+    {
+      /* __atomic_fetch_add (&counter, 1, MEMMODEL_RELAXED); */
+      tree addr = tree_coverage_counter_addr (GCOV_COUNTER_ARCS, edgeno);
+      gcall *stmt
+	= gimple_build_call (builtin_decl_explicit (GCOV_TYPE_ATOMIC_FETCH_ADD),
+			     3, addr, one,
+			     build_int_cst (integer_type_node,
+					    MEMMODEL_RELAXED));
+      gsi_insert_on_edge (e, stmt);
+    }
+  else
+    {
+      tree ref = tree_coverage_counter_ref (GCOV_COUNTER_ARCS, edgeno);
+      tree gcov_type_tmp_var = make_temp_ssa_name (gcov_type_node,
+						   NULL, "PROF_edge_counter");
+      gassign *stmt1 = gimple_build_assign (gcov_type_tmp_var, ref);
+      gcov_type_tmp_var = make_temp_ssa_name (gcov_type_node,
+					      NULL, "PROF_edge_counter");
+      gassign *stmt2 = gimple_build_assign (gcov_type_tmp_var, PLUS_EXPR,
+					    gimple_assign_lhs (stmt1), one);
+      gassign *stmt3 = gimple_build_assign (unshare_expr (ref),
+					    gimple_assign_lhs (stmt2));
+      gsi_insert_on_edge (e, stmt1);
+      gsi_insert_on_edge (e, stmt2);
+      gsi_insert_on_edge (e, stmt3);
+    }
 }
 
 /* Emits code to get VALUE to instrument at GSI, and returns the
-- 
2.9.2