1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
|
;; Test that dynamically exported symbols prevent devirtualization.
;; Note that --export-dynamic-symbol and --dynamic-list are tested similarly
;; in the v1.16 directory, because those were not properly passed down to the
;; plugin until then.
;; First check that we get devirtualization without any export dynamic options.
;; Index based WPD
;; Generate unsplit module with summary for ThinLTO index-based WPD.
; RUN: opt -thinlto-bc -o %t2.o %s
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=save-temps \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t2.o -o %t3 2>&1 | FileCheck %s --check-prefix=REMARK
; RUN: llvm-dis %t2.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-IR
;; Hybrid WPD
;; Generate split module with summary for hybrid Thin/Regular LTO WPD.
; RUN: opt -thinlto-bc -thinlto-split-lto-unit -o %t.o %s
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=save-temps \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t.o -o %t3 2>&1 | FileCheck %s --check-prefix=REMARK
; RUN: llvm-dis %t.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-IR
;; Regular LTO WPD
; RUN: opt -o %t4.o %s
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=save-temps \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t4.o -o %t3 2>&1 | FileCheck %s --check-prefix=REMARK
; RUN: llvm-dis %t3.0.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-IR
; REMARK-DAG: single-impl: devirtualized a call to _ZN1A1nEi
; REMARK-DAG: single-impl: devirtualized a call to _ZN1D1mEi
;; Check that all WPD fails with --export-dynamic.
;; Index based WPD
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=save-temps \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t2.o -o %t3 \
; RUN: --export-dynamic 2>&1 | FileCheck /dev/null --implicit-check-not single-impl --allow-empty
; RUN: llvm-dis %t2.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-NODEVIRT-IR
;; Hybrid WPD
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=save-temps \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t.o -o %t3 \
; RUN: --export-dynamic 2>&1 | FileCheck /dev/null --implicit-check-not single-impl --allow-empty
; RUN: llvm-dis %t.o.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-NODEVIRT-IR
;; Regular LTO WPD
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=save-temps \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t4.o -o %t3 \
; RUN: --export-dynamic 2>&1 | FileCheck /dev/null --implicit-check-not single-impl --allow-empty
; RUN: llvm-dis %t3.0.4.opt.bc -o - | FileCheck %s --check-prefix=CHECK-NODEVIRT-IR
;; Check that all WPD fails with when linking against a shared library containing
;; preemptible versions of the vtables. In this case the symbols in the object being
;; linked against the shared library must be exported to .dynsym to allow the runtime
;; preemption, even without any options.
;; Index based WPD
; RUN: opt -relocation-model=pic --thinlto-bc -o %t5.o %s
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: %t5.o -o %t5.so -shared
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t5.o %t5.so -o %t5 \
; RUN: --export-dynamic 2>&1 | FileCheck /dev/null --implicit-check-not single-impl --allow-empty
;; Hybrid WPD
; RUN: opt -relocation-model=pic --thinlto-bc --thinlto-split-lto-unit -o %t5.o %s
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: %t5.o -o %t5.so -shared
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t5.o %t5.so -o %t5 \
; RUN: --export-dynamic 2>&1 | FileCheck /dev/null --implicit-check-not single-impl --allow-empty
;; Regular LTO WPD
; RUN: opt -relocation-model=pic -o %t5.o %s
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: %t5.o -o %t5.so -shared
; RUN: %gold -m elf_x86_64 -plugin %llvmshlibdir/LLVMgold%shlibext \
; RUN: --plugin-opt=whole-program-visibility \
; RUN: --plugin-opt=-pass-remarks=. \
; RUN: %t5.o %t5.so -o %t5 \
; RUN: --export-dynamic 2>&1 | FileCheck /dev/null --implicit-check-not single-impl --allow-empty
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-grtev4-linux-gnu"
%struct.A = type { i32 (...)** }
%struct.B = type { %struct.A }
%struct.C = type { %struct.A }
%struct.D = type { i32 (...)** }
@_ZTV1B = linkonce_odr unnamed_addr constant { [4 x i8*] } { [4 x i8*] [i8* null, i8* undef, i8* bitcast (i32 (%struct.B*, i32)* @_ZN1B1fEi to i8*), i8* bitcast (i32 (%struct.A*, i32)* @_ZN1A1nEi to i8*)] }, !type !0, !type !1, !vcall_visibility !5
@_ZTV1C = linkonce_odr unnamed_addr constant { [4 x i8*] } { [4 x i8*] [i8* null, i8* undef, i8* bitcast (i32 (%struct.C*, i32)* @_ZN1C1fEi to i8*), i8* bitcast (i32 (%struct.A*, i32)* @_ZN1A1nEi to i8*)] }, !type !0, !type !2, !vcall_visibility !5
@_ZTV1D = linkonce_odr unnamed_addr constant { [3 x i8*] } { [3 x i8*] [i8* null, i8* undef, i8* bitcast (i32 (%struct.D*, i32)* @_ZN1D1mEi to i8*)] }, !type !3, !vcall_visibility !5
;; Prevent the vtables from being dead code eliminated.
@llvm.used = appending global [3 x i8*] [ i8* bitcast ( { [4 x i8*] }* @_ZTV1B to i8*), i8* bitcast ( { [4 x i8*] }* @_ZTV1C to i8*), i8* bitcast ( { [3 x i8*] }* @_ZTV1D to i8*)]
; CHECK-IR-LABEL: define dso_local i32 @_start
define i32 @_start(%struct.A* %obj, %struct.D* %obj2, i32 %a) {
entry:
%0 = bitcast %struct.A* %obj to i8***
%vtable = load i8**, i8*** %0
%1 = bitcast i8** %vtable to i8*
%p = call i1 @llvm.type.test(i8* %1, metadata !"_ZTS1A")
call void @llvm.assume(i1 %p)
%fptrptr = getelementptr i8*, i8** %vtable, i32 1
%2 = bitcast i8** %fptrptr to i32 (%struct.A*, i32)**
%fptr1 = load i32 (%struct.A*, i32)*, i32 (%struct.A*, i32)** %2, align 8
;; Check that the call was devirtualized.
; CHECK-IR: %call = tail call i32 @_ZN1A1nEi
; CHECK-NODEVIRT-IR: %call = tail call i32 %fptr1
%call = tail call i32 %fptr1(%struct.A* nonnull %obj, i32 %a)
%3 = bitcast i8** %vtable to i32 (%struct.A*, i32)**
%fptr22 = load i32 (%struct.A*, i32)*, i32 (%struct.A*, i32)** %3, align 8
;; We still have to call it as virtual.
; CHECK-IR: %call3 = tail call i32 %fptr22
; CHECK-NODEVIRT-IR: %call3 = tail call i32 %fptr22
%call3 = tail call i32 %fptr22(%struct.A* nonnull %obj, i32 %call)
%4 = bitcast %struct.D* %obj2 to i8***
%vtable2 = load i8**, i8*** %4
%5 = bitcast i8** %vtable2 to i8*
%p2 = call i1 @llvm.type.test(i8* %5, metadata !4)
call void @llvm.assume(i1 %p2)
%6 = bitcast i8** %vtable2 to i32 (%struct.D*, i32)**
%fptr33 = load i32 (%struct.D*, i32)*, i32 (%struct.D*, i32)** %6, align 8
;; Check that the call was devirtualized.
; CHECK-IR: %call4 = tail call i32 @_ZN1D1mEi
; CHECK-NODEVIRT-IR: %call4 = tail call i32 %fptr33
%call4 = tail call i32 %fptr33(%struct.D* nonnull %obj2, i32 %call3)
ret i32 %call4
}
; CHECK-IR-LABEL: ret i32
; CHECK-IR-LABEL: }
declare i1 @llvm.type.test(i8*, metadata)
declare void @llvm.assume(i1)
define i32 @_ZN1B1fEi(%struct.B* %this, i32 %a) #0 {
ret i32 0;
}
define i32 @_ZN1A1nEi(%struct.A* %this, i32 %a) #0 {
ret i32 0;
}
define i32 @_ZN1C1fEi(%struct.C* %this, i32 %a) #0 {
ret i32 0;
}
define i32 @_ZN1D1mEi(%struct.D* %this, i32 %a) #0 {
ret i32 0;
}
;; Make sure we don't inline or otherwise optimize out the direct calls.
attributes #0 = { noinline optnone }
!0 = !{i64 16, !"_ZTS1A"}
!1 = !{i64 16, !"_ZTS1B"}
!2 = !{i64 16, !"_ZTS1C"}
!3 = !{i64 16, !4}
!4 = distinct !{}
!5 = !{i64 0}
|
