lvi-hardening-indirectbr.ll
8 KB
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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
; RUN: llc -verify-machineinstrs -mtriple=x86_64-unknown -mattr=+lvi-cfi < %s | FileCheck %s --check-prefix=X64
; RUN: llc -verify-machineinstrs -mtriple=x86_64-unknown -mattr=+lvi-cfi -O0 < %s | FileCheck %s --check-prefix=X64FAST
;
; Note that a lot of this code was lifted from retpoline.ll.
declare void @bar(i32)
; Test a simple indirect call and tail call.
define void @icall_reg(void (i32)* %fp, i32 %x) {
entry:
tail call void @bar(i32 %x)
tail call void %fp(i32 %x)
tail call void @bar(i32 %x)
tail call void %fp(i32 %x)
ret void
}
; X64-LABEL: icall_reg:
; X64-DAG: movq %rdi, %[[fp:[^ ]*]]
; X64-DAG: movl %esi, %[[x:[^ ]*]]
; X64: movl %esi, %edi
; X64: callq bar
; X64-DAG: movl %[[x]], %edi
; X64-DAG: movq %[[fp]], %r11
; X64: callq __llvm_lvi_thunk_r11
; X64: movl %[[x]], %edi
; X64: callq bar
; X64-DAG: movl %[[x]], %edi
; X64-DAG: movq %[[fp]], %r11
; X64: jmp __llvm_lvi_thunk_r11 # TAILCALL
; X64FAST-LABEL: icall_reg:
; X64FAST: callq bar
; X64FAST: callq __llvm_lvi_thunk_r11
; X64FAST: callq bar
; X64FAST: jmp __llvm_lvi_thunk_r11 # TAILCALL
@global_fp = external global void (i32)*
; Test an indirect call through a global variable.
define void @icall_global_fp(i32 %x, void (i32)** %fpp) #0 {
%fp1 = load void (i32)*, void (i32)** @global_fp
call void %fp1(i32 %x)
%fp2 = load void (i32)*, void (i32)** @global_fp
tail call void %fp2(i32 %x)
ret void
}
; X64-LABEL: icall_global_fp:
; X64-DAG: movl %edi, %[[x:[^ ]*]]
; X64-DAG: movq global_fp(%rip), %r11
; X64: callq __llvm_lvi_thunk_r11
; X64-DAG: movl %[[x]], %edi
; X64-DAG: movq global_fp(%rip), %r11
; X64: jmp __llvm_lvi_thunk_r11 # TAILCALL
; X64FAST-LABEL: icall_global_fp:
; X64FAST: movq global_fp(%rip), %r11
; X64FAST: callq __llvm_lvi_thunk_r11
; X64FAST: movq global_fp(%rip), %r11
; X64FAST: jmp __llvm_lvi_thunk_r11 # TAILCALL
%struct.Foo = type { void (%struct.Foo*)** }
; Test an indirect call through a vtable.
define void @vcall(%struct.Foo* %obj) #0 {
%vptr_field = getelementptr %struct.Foo, %struct.Foo* %obj, i32 0, i32 0
%vptr = load void (%struct.Foo*)**, void (%struct.Foo*)*** %vptr_field
%vslot = getelementptr void(%struct.Foo*)*, void(%struct.Foo*)** %vptr, i32 1
%fp = load void(%struct.Foo*)*, void(%struct.Foo*)** %vslot
tail call void %fp(%struct.Foo* %obj)
tail call void %fp(%struct.Foo* %obj)
ret void
}
; X64-LABEL: vcall:
; X64: movq %rdi, %[[obj:[^ ]*]]
; X64: movq (%rdi), %[[vptr:[^ ]*]]
; X64: movq 8(%[[vptr]]), %[[fp:[^ ]*]]
; X64: movq %[[fp]], %r11
; X64: callq __llvm_lvi_thunk_r11
; X64-DAG: movq %[[obj]], %rdi
; X64-DAG: movq %[[fp]], %r11
; X64: jmp __llvm_lvi_thunk_r11 # TAILCALL
; X64FAST-LABEL: vcall:
; X64FAST: callq __llvm_lvi_thunk_r11
; X64FAST: jmp __llvm_lvi_thunk_r11 # TAILCALL
declare void @direct_callee()
define void @direct_tail() #0 {
tail call void @direct_callee()
ret void
}
; X64-LABEL: direct_tail:
; X64: jmp direct_callee # TAILCALL
; X64FAST-LABEL: direct_tail:
; X64FAST: jmp direct_callee # TAILCALL
declare void @nonlazybind_callee() #1
define void @nonlazybind_caller() #0 {
call void @nonlazybind_callee()
tail call void @nonlazybind_callee()
ret void
}
; X64-LABEL: nonlazybind_caller:
; X64: movq nonlazybind_callee@GOTPCREL(%rip), %[[REG:.*]]
; X64: movq %[[REG]], %r11
; X64: callq __llvm_lvi_thunk_r11
; X64: movq %[[REG]], %r11
; X64: jmp __llvm_lvi_thunk_r11 # TAILCALL
; X64FAST-LABEL: nonlazybind_caller:
; X64FAST: movq nonlazybind_callee@GOTPCREL(%rip), %r11
; X64FAST: callq __llvm_lvi_thunk_r11
; X64FAST: movq nonlazybind_callee@GOTPCREL(%rip), %r11
; X64FAST: jmp __llvm_lvi_thunk_r11 # TAILCALL
; Check that a switch gets lowered using a jump table
define void @switch_jumptable(i32* %ptr, i64* %sink) #0 {
; X64-LABEL: switch_jumptable:
; X64_NOT: jmpq *
entry:
br label %header
header:
%i = load volatile i32, i32* %ptr
switch i32 %i, label %bb0 [
i32 1, label %bb1
i32 2, label %bb2
i32 3, label %bb3
i32 4, label %bb4
i32 5, label %bb5
i32 6, label %bb6
i32 7, label %bb7
i32 8, label %bb8
i32 9, label %bb9
]
bb0:
store volatile i64 0, i64* %sink
br label %header
bb1:
store volatile i64 1, i64* %sink
br label %header
bb2:
store volatile i64 2, i64* %sink
br label %header
bb3:
store volatile i64 3, i64* %sink
br label %header
bb4:
store volatile i64 4, i64* %sink
br label %header
bb5:
store volatile i64 5, i64* %sink
br label %header
bb6:
store volatile i64 6, i64* %sink
br label %header
bb7:
store volatile i64 7, i64* %sink
br label %header
bb8:
store volatile i64 8, i64* %sink
br label %header
bb9:
store volatile i64 9, i64* %sink
br label %header
}
@indirectbr_rewrite.targets = constant [10 x i8*] [i8* blockaddress(@indirectbr_rewrite, %bb0),
i8* blockaddress(@indirectbr_rewrite, %bb1),
i8* blockaddress(@indirectbr_rewrite, %bb2),
i8* blockaddress(@indirectbr_rewrite, %bb3),
i8* blockaddress(@indirectbr_rewrite, %bb4),
i8* blockaddress(@indirectbr_rewrite, %bb5),
i8* blockaddress(@indirectbr_rewrite, %bb6),
i8* blockaddress(@indirectbr_rewrite, %bb7),
i8* blockaddress(@indirectbr_rewrite, %bb8),
i8* blockaddress(@indirectbr_rewrite, %bb9)]
; Check that when thunks are enabled the indirectbr instruction gets
; rewritten to use switch, and that in turn doesn't get lowered as a jump
; table.
define void @indirectbr_rewrite(i64* readonly %p, i64* %sink) #0 {
; X64-LABEL: indirectbr_rewrite:
; X64-NOT: jmpq *
entry:
%i0 = load i64, i64* %p
%target.i0 = getelementptr [10 x i8*], [10 x i8*]* @indirectbr_rewrite.targets, i64 0, i64 %i0
%target0 = load i8*, i8** %target.i0
indirectbr i8* %target0, [label %bb1, label %bb3]
bb0:
store volatile i64 0, i64* %sink
br label %latch
bb1:
store volatile i64 1, i64* %sink
br label %latch
bb2:
store volatile i64 2, i64* %sink
br label %latch
bb3:
store volatile i64 3, i64* %sink
br label %latch
bb4:
store volatile i64 4, i64* %sink
br label %latch
bb5:
store volatile i64 5, i64* %sink
br label %latch
bb6:
store volatile i64 6, i64* %sink
br label %latch
bb7:
store volatile i64 7, i64* %sink
br label %latch
bb8:
store volatile i64 8, i64* %sink
br label %latch
bb9:
store volatile i64 9, i64* %sink
br label %latch
latch:
%i.next = load i64, i64* %p
%target.i.next = getelementptr [10 x i8*], [10 x i8*]* @indirectbr_rewrite.targets, i64 0, i64 %i.next
%target.next = load i8*, i8** %target.i.next
; Potentially hit a full 10 successors here so that even if we rewrite as
; a switch it will try to be lowered with a jump table.
indirectbr i8* %target.next, [label %bb0,
label %bb1,
label %bb2,
label %bb3,
label %bb4,
label %bb5,
label %bb6,
label %bb7,
label %bb8,
label %bb9]
}
; Lastly check that the necessary thunks were emitted.
;
; X64-LABEL: .section .text.__llvm_lvi_thunk_r11,{{.*}},__llvm_lvi_thunk_r11,comdat
; X64-NEXT: .hidden __llvm_lvi_thunk_r11
; X64-NEXT: .weak __llvm_lvi_thunk_r11
; X64: __llvm_lvi_thunk_r11:
; X64-NEXT: # {{.*}} # %entry
; X64-NEXT: lfence
; X64-NEXT: jmpq *%r11
attributes #1 = { nonlazybind }