maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Instrumentation/ThreadSanitizer/do-not-instrument-memory-ac...

60 lines
2.5 KiB
LLVM
Raw Normal View History

[tsan] Do not instrument reads/writes to instruction profile counters. We have known races on profile counters, which can be reproduced by enabling -fsanitize=thread and -fprofile-instr-generate simultaneously on a multi-threaded program. This patch avoids reporting those races by not instrumenting the reads and writes coming from the instruction profiler. llvm-svn: 264805
2016-03-30 07:19:40 +08:00
; This test checks that we are not instrumenting unwanted acesses to globals:
; - Instruction profiler counter instrumentation has known intended races.
[tsan] Do not instrument accesses to the gcov counters array There is a known intended race here. This is a follow-up to r264805, which disabled tsan instrumentation for updates to instrprof counters. For more background on this please see the discussion in D18164. llvm-svn: 273202
2016-06-21 05:24:26 +08:00
; - The gcov counters array has a known intended race.
[tsan] Do not instrument reads/writes to instruction profile counters. We have known races on profile counters, which can be reproduced by enabling -fsanitize=thread and -fprofile-instr-generate simultaneously on a multi-threaded program. This patch avoids reporting those races by not instrumenting the reads and writes coming from the instruction profiler. llvm-svn: 264805
2016-03-30 07:19:40 +08:00
;
; RUN: opt < %s -tsan -S | FileCheck %s
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.9"
@__profc_test_gep = private global [1 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
@__profc_test_bitcast = private global [2 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
@__profc_test_bitcast_foo = private global [1 x i64] zeroinitializer, section "__DATA,__llvm_prf_cnts", align 8
[tsan] Do not instrument accesses to the gcov counters array There is a known intended race here. This is a follow-up to r264805, which disabled tsan instrumentation for updates to instrprof counters. For more background on this please see the discussion in D18164. llvm-svn: 273202
2016-06-21 05:24:26 +08:00
@__llvm_gcov_ctr = internal global [1 x i64] zeroinitializer
[tsan] Try harder to not instrument gcov counters GCOVProfiler::emitProfileArcs() can create many variables with names starting with "__llvm_gcov_ctr", so llvm appends a numeric suffix to most of them. Teach tsan about this. llvm-svn: 274801
2016-07-08 06:45:28 +08:00
@__llvm_gcov_ctr.1 = internal global [1 x i64] zeroinitializer
[tsan] Don't instrument __llvm_gcov_global_state_pred or __llvm_gcda* r274801 did not go far enough to allow gcov+tsan to cooperate. With this commit it's possible to run the following code without false positives: std::thread T1(fib), T2(fib); T1.join(); T2.join(); llvm-svn: 276015
2016-07-20 04:16:08 +08:00
@__llvm_gcov_global_state_pred = internal global i32 0
@__llvm_gcda_foo = internal global i32 0
[tsan] Do not instrument accesses to the gcov counters array There is a known intended race here. This is a follow-up to r264805, which disabled tsan instrumentation for updates to instrprof counters. For more background on this please see the discussion in D18164. llvm-svn: 273202
2016-06-21 05:24:26 +08:00
[tsan] Do not instrument reads/writes to instruction profile counters. We have known races on profile counters, which can be reproduced by enabling -fsanitize=thread and -fprofile-instr-generate simultaneously on a multi-threaded program. This patch avoids reporting those races by not instrumenting the reads and writes coming from the instruction profiler. llvm-svn: 264805
2016-03-30 07:19:40 +08:00
define i32 @test_gep() sanitize_thread {
entry:
%pgocount = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc_test_gep, i64 0, i64 0)
%0 = add i64 %pgocount, 1
store i64 %0, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc_test_gep, i64 0, i64 0)
[tsan] Do not instrument accesses to the gcov counters array There is a known intended race here. This is a follow-up to r264805, which disabled tsan instrumentation for updates to instrprof counters. For more background on this please see the discussion in D18164. llvm-svn: 273202
2016-06-21 05:24:26 +08:00
%gcovcount = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__llvm_gcov_ctr, i64 0, i64 0)
%1 = add i64 %gcovcount, 1
store i64 %1, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__llvm_gcov_ctr, i64 0, i64 0)
[tsan] Try harder to not instrument gcov counters GCOVProfiler::emitProfileArcs() can create many variables with names starting with "__llvm_gcov_ctr", so llvm appends a numeric suffix to most of them. Teach tsan about this. llvm-svn: 274801
2016-07-08 06:45:28 +08:00
%gcovcount.1 = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__llvm_gcov_ctr.1, i64 0, i64 0)
%2 = add i64 %gcovcount.1, 1
store i64 %2, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__llvm_gcov_ctr.1, i64 0, i64 0)
[tsan] Do not instrument reads/writes to instruction profile counters. We have known races on profile counters, which can be reproduced by enabling -fsanitize=thread and -fprofile-instr-generate simultaneously on a multi-threaded program. This patch avoids reporting those races by not instrumenting the reads and writes coming from the instruction profiler. llvm-svn: 264805
2016-03-30 07:19:40 +08:00
ret i32 1
}
define i32 @test_bitcast() sanitize_thread {
entry:
%0 = load <2 x i64>, <2 x i64>* bitcast ([2 x i64]* @__profc_test_bitcast to <2 x i64>*), align 8
%.promoted5 = load i64, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc_test_bitcast_foo, i64 0, i64 0), align 8
%1 = add i64 %.promoted5, 10
%2 = add <2 x i64> %0, <i64 1, i64 10>
store <2 x i64> %2, <2 x i64>* bitcast ([2 x i64]* @__profc_test_bitcast to <2 x i64>*), align 8
store i64 %1, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @__profc_test_bitcast_foo, i64 0, i64 0), align 8
ret i32 undef
}
[tsan] Don't instrument __llvm_gcov_global_state_pred or __llvm_gcda* r274801 did not go far enough to allow gcov+tsan to cooperate. With this commit it's possible to run the following code without false positives: std::thread T1(fib), T2(fib); T1.join(); T2.join(); llvm-svn: 276015
2016-07-20 04:16:08 +08:00
define void @test_load() sanitize_thread {
entry:
%0 = load i32, i32* @__llvm_gcov_global_state_pred
store i32 1, i32* @__llvm_gcov_global_state_pred
%1 = load i32, i32* @__llvm_gcda_foo
store i32 1, i32* @__llvm_gcda_foo
ret void
}
[tsan] Do not instrument reads/writes to instruction profile counters. We have known races on profile counters, which can be reproduced by enabling -fsanitize=thread and -fprofile-instr-generate simultaneously on a multi-threaded program. This patch avoids reporting those races by not instrumenting the reads and writes coming from the instruction profiler. llvm-svn: 264805
2016-03-30 07:19:40 +08:00
; CHECK-NOT: {{call void @__tsan_write}}
; CHECK: __tsan_init