Re: [PATCH 5/N] Add new *_atomic counter update function, (-fprofile-update=atomic)

["Martin Liška" <mliska@suse.cz>]

[-- Attachment #1: Type: text/plain, Size: 2503 bytes --]

On 08/08/2016 06:50 PM, Martin Liška wrote:
> On 08/08/2016 05:24 PM, Nathan Sidwell wrote:
>> On 08/08/16 09:59, Martin Liška wrote:
>>> Hello.
>>>
>>> This patch is follow-up of the series where I introduce a set of counter update
>>> function that are thread-safe. I originally thought that majority of profile corruptions are
>>> caused by non-atomic updated of CFG (-fprofile-arc). But there are multiple counters that compare
>>> it's count to a number of execution of a basic block:
>>>
>>> blake2s.cpp:150:40: error: corrupted value profile: value profile counter (11301120 out of 11314388) inconsistent with basic-block count (11555117)
>>>        memcpy( S->buf + left, in, fill ); // Fill buffer
>>>
>>> This can be seen for unrar binary: PR58306. I'm also adding a simple test-case which reveals the inconsistency: val-profiler-threads-1.c.
>>>
>>> I've been running regression tests, ready to install after it finishes?
>>
>>
>> +      fn_name = concat ("__gcov_interval_profiler", fn_suffix, NULL);
>> +      tree_interval_profiler_fn = build_fn_decl (fn_name,
>> +                         interval_profiler_fn_type);
>>
>> I like this idiom, but doesn't 'concat' call for a following 'free'?
> 
> Fixed in the second version of patch.
> 
> 
>>
>> +__gcov_pow2_profiler_atomic (gcov_type *counters, gcov_type value)
>> +{
>> +  if (value & (value - 1))
>> +    __atomic_fetch_add (&counters[0], 1, MEMMODEL_RELAXED);
>>
>> This seems to think '0' is  a power of 2.  (I suspect a bug in the existing code, not  something you've  introduced)
> 
> I'll send separate email for that issue.
> 
>>
>> -__gcov_one_value_profiler_body (gcov_type *counters, gcov_type value)
>> +__gcov_one_value_profiler_body (gcov_type *counters, gcov_type value,
>> +                int use_atomic)
>>  {
>>    if (value == counters[0])
>>
>> This function should be commented along the lines of the email discussion we had last week.  the 'atomic' param doesn't make it completely thread safe.
> 
> Done, with a link to this mailing list thread.
> 
>>
>>  /* Counter for first visit of each function.  */
>> -static gcov_type function_counter;
>> +gcov_type function_counter;
>>
>> why is this no longer static?  If  it must be globally visible, it'll need a suitable rename.  (perhaps it's simpler to put the 2(?) fns that access it into a single object file?)
> 
> Yeah, I'm putting these 2 functions to the same object.
> 
> Martin
> 
>>
>> nathan
> 

v3: fixed wrong defines in libgcc/Makefine.in

Martin

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: 0005-Add-new-_atomic-counter-update-function-fprofile-upd-v3.patch --]
[-- Type: text/x-patch; name="0005-Add-new-_atomic-counter-update-function-fprofile-upd-v3.patch", Size: 14816 bytes --]

From 7f442afa98e037ee9839fad1ced8a0055842b4e6 Mon Sep 17 00:00:00 2001
From: marxin <mliska@suse.cz>
Date: Mon, 8 Aug 2016 15:44:28 +0200
Subject: [PATCH 5/5] Add new *_atomic counter update function
 (-fprofile-update=atomic)

libgcc/ChangeLog:

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

	PR gcov-profile/58306
	* Makefile.in: New functions (modules) are added.
	* libgcov-profiler.c (__gcov_interval_profiler_atomic): New
	function.
	(__gcov_pow2_profiler_atomic): New function.
	(__gcov_one_value_profiler_body): New argument is instroduced.
	(__gcov_one_value_profiler): Call with the new argument.
	(__gcov_one_value_profiler_atomic): Likewise.
	(__gcov_indirect_call_profiler_v2): Likewise.
	(__gcov_time_profiler_atomic): New function.
	(__gcov_average_profiler_atomic): Likewise.
	(__gcov_ior_profiler_atomic): Likewise.
	* libgcov.h: Declare the aforementioned functions.

gcc/testsuite/ChangeLog:

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

	PR gcov-profile/58306
	* gcc.dg/tree-prof/val-profiler-threads-1.c: New test.

gcc/ChangeLog:

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

	PR gcov-profile/58306
	* tree-profile.c (gimple_init_edge_profiler): Create conditionally
	atomic variants of profile update functions.
---
 .../gcc.dg/tree-prof/val-profiler-threads-1.c      |  41 ++++++++
 gcc/tree-profile.c                                 |  42 +++++----
 libgcc/Makefile.in                                 |  15 ++-
 libgcc/libgcov-profiler.c                          | 103 ++++++++++++++++++++-
 libgcc/libgcov.h                                   |   7 ++
 5 files changed, 182 insertions(+), 26 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/tree-prof/val-profiler-threads-1.c

diff --git a/gcc/testsuite/gcc.dg/tree-prof/val-profiler-threads-1.c b/gcc/testsuite/gcc.dg/tree-prof/val-profiler-threads-1.c
new file mode 100644
index 0000000..0f7477e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-prof/val-profiler-threads-1.c
@@ -0,0 +1,41 @@
+/* { dg-options "-O0 -pthread -fprofile-update=atomic" } */
+#include <pthread.h>
+
+#define NUM_THREADS	8
+#define SIZE 1024
+#define ITERATIONS (1000 * 1000)
+
+char buffer[SIZE];
+char buffer2[SIZE];
+
+void *copy_memory(char *dst, char *src, unsigned size)
+{
+   for (unsigned i = 0; i < ITERATIONS; i++)
+   {
+     dst[size % 10] = src[size % 20];
+   }
+}
+
+void *foo(void *d)
+{
+  copy_memory (buffer, buffer2, SIZE);
+}
+
+int main(int argc, char *argv[])
+{
+   pthread_t threads[NUM_THREADS];
+   int rc;
+   long t;
+   for(t=0;t<NUM_THREADS;t++){
+     rc = pthread_create(&threads[t], NULL, foo, 0);
+     if (rc){
+	 return 1;
+       }
+     }
+
+   int retval;
+   for(t=0;t<NUM_THREADS;t++)
+     pthread_join (threads[t], (void**)&retval);
+
+   return buffer[10];
+}
diff --git a/gcc/tree-profile.c b/gcc/tree-profile.c
index 740f7ab..fdf0201 100644
--- a/gcc/tree-profile.c
+++ b/gcc/tree-profile.c
@@ -128,9 +128,13 @@ gimple_init_edge_profiler (void)
   tree average_profiler_fn_type;
   tree time_profiler_fn_type;
   const char *profiler_fn_name;
+  const char *fn_name;
 
   if (!gcov_type_node)
     {
+      const char *fn_suffix
+	= flag_profile_update == PROFILE_UPDATE_ATOMIC ? "_atomic" : "";
+
       gcov_type_node = get_gcov_type ();
       gcov_type_ptr = build_pointer_type (gcov_type_node);
 
@@ -140,9 +144,10 @@ gimple_init_edge_profiler (void)
 					  gcov_type_ptr, gcov_type_node,
 					  integer_type_node,
 					  unsigned_type_node, NULL_TREE);
-      tree_interval_profiler_fn
-	      = build_fn_decl ("__gcov_interval_profiler",
-				     interval_profiler_fn_type);
+      fn_name = concat ("__gcov_interval_profiler", fn_suffix, NULL);
+      tree_interval_profiler_fn = build_fn_decl (fn_name,
+						 interval_profiler_fn_type);
+      free (CONST_CAST (char *, fn_name));
       TREE_NOTHROW (tree_interval_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_interval_profiler_fn)
 	= tree_cons (get_identifier ("leaf"), NULL,
@@ -153,8 +158,9 @@ gimple_init_edge_profiler (void)
 	      = build_function_type_list (void_type_node,
 					  gcov_type_ptr, gcov_type_node,
 					  NULL_TREE);
-      tree_pow2_profiler_fn = build_fn_decl ("__gcov_pow2_profiler",
-						   pow2_profiler_fn_type);
+      fn_name = concat ("__gcov_pow2_profiler", fn_suffix, NULL);
+      tree_pow2_profiler_fn = build_fn_decl (fn_name, pow2_profiler_fn_type);
+      free (CONST_CAST (char *, fn_name));
       TREE_NOTHROW (tree_pow2_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_pow2_profiler_fn)
 	= tree_cons (get_identifier ("leaf"), NULL,
@@ -165,9 +171,10 @@ gimple_init_edge_profiler (void)
 	      = build_function_type_list (void_type_node,
 					  gcov_type_ptr, gcov_type_node,
 					  NULL_TREE);
-      tree_one_value_profiler_fn
-	      = build_fn_decl ("__gcov_one_value_profiler",
-				     one_value_profiler_fn_type);
+      fn_name = concat ("__gcov_one_value_profiler", fn_suffix, NULL);
+      tree_one_value_profiler_fn = build_fn_decl (fn_name,
+						  one_value_profiler_fn_type);
+      free (CONST_CAST (char *, fn_name));
       TREE_NOTHROW (tree_one_value_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_one_value_profiler_fn)
 	= tree_cons (get_identifier ("leaf"), NULL,
@@ -197,9 +204,9 @@ gimple_init_edge_profiler (void)
       time_profiler_fn_type
 	       = build_function_type_list (void_type_node,
 					  gcov_type_ptr, NULL_TREE);
-      tree_time_profiler_fn
-	      = build_fn_decl ("__gcov_time_profiler",
-				     time_profiler_fn_type);
+      fn_name = concat ("__gcov_time_profiler", fn_suffix, NULL);
+      tree_time_profiler_fn = build_fn_decl (fn_name, time_profiler_fn_type);
+      free (CONST_CAST (char *, fn_name));
       TREE_NOTHROW (tree_time_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_time_profiler_fn)
 	= tree_cons (get_identifier ("leaf"), NULL,
@@ -209,16 +216,17 @@ gimple_init_edge_profiler (void)
       average_profiler_fn_type
 	      = build_function_type_list (void_type_node,
 					  gcov_type_ptr, gcov_type_node, NULL_TREE);
-      tree_average_profiler_fn
-	      = build_fn_decl ("__gcov_average_profiler",
-				     average_profiler_fn_type);
+      fn_name = concat ("__gcov_average_profiler", fn_suffix, NULL);
+      tree_average_profiler_fn = build_fn_decl (fn_name,
+						average_profiler_fn_type);
+      free (CONST_CAST (char *, fn_name));
       TREE_NOTHROW (tree_average_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_average_profiler_fn)
 	= tree_cons (get_identifier ("leaf"), NULL,
 		     DECL_ATTRIBUTES (tree_average_profiler_fn));
-      tree_ior_profiler_fn
-	      = build_fn_decl ("__gcov_ior_profiler",
-				     average_profiler_fn_type);
+      fn_name = concat ("__gcov_ior_profiler", fn_suffix, NULL);
+      tree_ior_profiler_fn = build_fn_decl (fn_name, average_profiler_fn_type);
+      free (CONST_CAST (char *, fn_name));
       TREE_NOTHROW (tree_ior_profiler_fn) = 1;
       DECL_ATTRIBUTES (tree_ior_profiler_fn)
 	= tree_cons (get_identifier ("leaf"), NULL,
diff --git a/libgcc/Makefile.in b/libgcc/Makefile.in
index efaf7f7..b478056 100644
--- a/libgcc/Makefile.in
+++ b/libgcc/Makefile.in
@@ -858,10 +858,17 @@ include $(iterator)
 
 LIBGCOV_MERGE = _gcov_merge_add _gcov_merge_single _gcov_merge_delta	\
 	_gcov_merge_ior _gcov_merge_time_profile _gcov_merge_icall_topn
-LIBGCOV_PROFILER = _gcov_interval_profiler _gcov_pow2_profiler		\
-	_gcov_one_value_profiler					\
- 	_gcov_average_profiler _gcov_ior_profiler			\
-	_gcov_indirect_call_profiler_v2 _gcov_time_profiler		\
+LIBGCOV_PROFILER = _gcov_interval_profiler				\
+	_gcov_interval_profiler_atomic					\
+	_gcov_pow2_profiler						\
+	_gcov_pow2_profiler_atomic					\
+	_gcov_one_value_profiler_atomic					\
+	_gcov_average_profiler						\
+	_gcov_average_profiler_atomic					\
+	_gcov_ior_profiler						\
+	_gcov_ior_profiler_atomic					\
+	_gcov_indirect_call_profiler_v2					\
+	_gcov_time_profiler						\
 	_gcov_indirect_call_topn_profiler
 LIBGCOV_INTERFACE = _gcov_dump _gcov_flush _gcov_fork			\
 	_gcov_execl _gcov_execlp					\
diff --git a/libgcc/libgcov-profiler.c b/libgcc/libgcov-profiler.c
index a99d93b..70a821d 100644
--- a/libgcc/libgcov-profiler.c
+++ b/libgcc/libgcov-profiler.c
@@ -46,6 +46,26 @@ __gcov_interval_profiler (gcov_type *counters, gcov_type value,
 }
 #endif
 
+#ifdef L_gcov_interval_profiler_atomic
+/* If VALUE is in interval <START, START + STEPS - 1>, then increases the
+   corresponding counter in COUNTERS.  If the VALUE is above or below
+   the interval, COUNTERS[STEPS] or COUNTERS[STEPS + 1] is increased
+   instead.  Function is thread-safe.  */
+
+void
+__gcov_interval_profiler_atomic (gcov_type *counters, gcov_type value,
+				 int start, unsigned steps)
+{
+  gcov_type delta = value - start;
+  if (delta < 0)
+    __atomic_fetch_add (&counters[steps + 1], 1, MEMMODEL_RELAXED);
+  else if (delta >= steps)
+    __atomic_fetch_add (&counters[steps], 1, MEMMODEL_RELAXED);
+  else
+    __atomic_fetch_add (&counters[delta], 1, MEMMODEL_RELAXED);
+}
+#endif
+
 #ifdef L_gcov_pow2_profiler
 /* If VALUE is a power of two, COUNTERS[1] is incremented.  Otherwise
    COUNTERS[0] is incremented.  */
@@ -60,6 +80,21 @@ __gcov_pow2_profiler (gcov_type *counters, gcov_type value)
 }
 #endif
 
+#ifdef L_gcov_pow2_profiler_atomic
+/* If VALUE is a power of two, COUNTERS[1] is incremented.  Otherwise
+   COUNTERS[0] is incremented.  Function is thread-safe.  */
+
+void
+__gcov_pow2_profiler_atomic (gcov_type *counters, gcov_type value)
+{
+  if (value == 0 || (value & (value - 1)))
+    __atomic_fetch_add (&counters[0], 1, MEMMODEL_RELAXED);
+  else
+    __atomic_fetch_add (&counters[1], 1, MEMMODEL_RELAXED);
+}
+#endif
+
+
 /* Tries to determine the most common value among its inputs.  Checks if the
    value stored in COUNTERS[0] matches VALUE.  If this is the case, COUNTERS[1]
    is incremented.  If this is not the case and COUNTERS[1] is not zero,
@@ -68,10 +103,12 @@ __gcov_pow2_profiler (gcov_type *counters, gcov_type value)
    function is called more than 50% of the time with one value, this value
    will be in COUNTERS[0] in the end.
 
-   In any case, COUNTERS[2] is incremented.  */
+   In any case, COUNTERS[2] is incremented.  If USE_ATOMIC is set to 1,
+   COUNTERS[2] is updated with an atomic instruction.  */
 
 static inline void
-__gcov_one_value_profiler_body (gcov_type *counters, gcov_type value)
+__gcov_one_value_profiler_body (gcov_type *counters, gcov_type value,
+				int use_atomic)
 {
   if (value == counters[0])
     counters[1]++;
@@ -82,14 +119,36 @@ __gcov_one_value_profiler_body (gcov_type *counters, gcov_type value)
     }
   else
     counters[1]--;
-  counters[2]++;
+
+  if (use_atomic)
+    __atomic_fetch_add (&counters[2], 1, MEMMODEL_RELAXED);
+  else
+    counters[2]++;
 }
 
 #ifdef L_gcov_one_value_profiler
 void
 __gcov_one_value_profiler (gcov_type *counters, gcov_type value)
 {
-  __gcov_one_value_profiler_body (counters, value);
+  __gcov_one_value_profiler_body (counters, value, 0);
+}
+#endif
+
+#ifdef L_gcov_one_value_profiler_atomic
+
+/* Update one value profilers (COUNTERS) for a given VALUE.
+
+   CAVEAT: Following function is not thread-safe, only total number
+   of executions (COUNTERS[2]) is update with an atomic instruction.
+   Problem is that one cannot atomically update two counters
+   (COUNTERS[0] and COUNTERS[1]), for more information please read
+   following email thread:
+   https://gcc.gnu.org/ml/gcc-patches/2016-08/msg00024.html.  */
+
+void
+__gcov_one_value_profiler_atomic (gcov_type *counters, gcov_type value)
+{
+  __gcov_one_value_profiler_body (counters, value, 1);
 }
 #endif
 
@@ -265,7 +324,7 @@ __gcov_indirect_call_profiler_v2 (gcov_type value, void* cur_func)
   if (cur_func == __gcov_indirect_call_callee
       || (__LIBGCC_VTABLE_USES_DESCRIPTORS__ && __gcov_indirect_call_callee
           && *(void **) cur_func == *(void **) __gcov_indirect_call_callee))
-    __gcov_one_value_profiler_body (__gcov_indirect_call_counters, value);
+    __gcov_one_value_profiler_body (__gcov_indirect_call_counters, value, 0);
 }
 #endif
 
@@ -282,8 +341,19 @@ __gcov_time_profiler (gcov_type* counters)
   if (!counters[0])
     counters[0] = ++function_counter;
 }
+
+/* Sets corresponding COUNTERS if there is no value.
+   Function is thread-safe.  */
+
+void
+__gcov_time_profiler_atomic (gcov_type* counters)
+{
+  if (!counters[0])
+    counters[0] = __atomic_add_fetch (&function_counter, 1, MEMMODEL_RELAXED);
+}
 #endif
 
+
 #ifdef L_gcov_average_profiler
 /* Increase corresponding COUNTER by VALUE.  FIXME: Perhaps we want
    to saturate up.  */
@@ -296,6 +366,18 @@ __gcov_average_profiler (gcov_type *counters, gcov_type value)
 }
 #endif
 
+#ifdef L_gcov_average_profiler_atomic
+/* Increase corresponding COUNTER by VALUE.  FIXME: Perhaps we want
+   to saturate up.  Function is thread-safe.  */
+
+void
+__gcov_average_profiler_atomic (gcov_type *counters, gcov_type value)
+{
+  __atomic_fetch_add (&counters[0], value, MEMMODEL_RELAXED);
+  __atomic_fetch_add (&counters[1], 1, MEMMODEL_RELAXED);
+}
+#endif
+
 #ifdef L_gcov_ior_profiler
 /* Bitwise-OR VALUE into COUNTER.  */
 
@@ -306,4 +388,15 @@ __gcov_ior_profiler (gcov_type *counters, gcov_type value)
 }
 #endif
 
+#ifdef L_gcov_ior_profiler_atomic
+/* Bitwise-OR VALUE into COUNTER.  Function is thread-safe.  */
+
+void
+__gcov_ior_profiler_atomic (gcov_type *counters, gcov_type value)
+{
+  __atomic_fetch_or (&counters[0], value, MEMMODEL_RELAXED);
+}
+#endif
+
+
 #endif /* inhibit_libc */
diff --git a/libgcc/libgcov.h b/libgcc/libgcov.h
index 80f13e2..25147de 100644
--- a/libgcc/libgcov.h
+++ b/libgcc/libgcov.h
@@ -268,12 +268,19 @@ extern void __gcov_merge_icall_topn (gcov_type *, unsigned) ATTRIBUTE_HIDDEN;
 
 /* The profiler functions.  */
 extern void __gcov_interval_profiler (gcov_type *, gcov_type, int, unsigned);
+extern void __gcov_interval_profiler_atomic (gcov_type *, gcov_type, int,
+					     unsigned);
 extern void __gcov_pow2_profiler (gcov_type *, gcov_type);
+extern void __gcov_pow2_profiler_atomic (gcov_type *, gcov_type);
 extern void __gcov_one_value_profiler (gcov_type *, gcov_type);
+extern void __gcov_one_value_profiler_atomic (gcov_type *, gcov_type);
 extern void __gcov_indirect_call_profiler_v2 (gcov_type, void *);
 extern void __gcov_time_profiler (gcov_type *);
+extern void __gcov_time_profiler_atomic (gcov_type *);
 extern void __gcov_average_profiler (gcov_type *, gcov_type);
+extern void __gcov_average_profiler_atomic (gcov_type *, gcov_type);
 extern void __gcov_ior_profiler (gcov_type *, gcov_type);
+extern void __gcov_ior_profiler_atomic (gcov_type *, gcov_type);
 extern void __gcov_indirect_call_topn_profiler (gcov_type, void *);
 extern void gcov_sort_n_vals (gcov_type *, int);
 
-- 
2.9.2