caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
dda73336ad22bd0b5ecda17040c50fb10fcbe5fb
clang-p2996/llvm/test/Transforms/MemCpyOpt/callslot.ll
Nikita Popov 369c9b791b [MemCpyOpt] Require writable object during call slot optimization (#71542) 
Call slot optimization may introduce writes to the destination object
that occur earlier than in the original function. We currently already
check that that the destination is dereferenceable and aligned, but we
do not make sure that it is writable. As such, we might introduce a
write to read-only memory, or introduce a data race.

Fix this by checking that the object is writable. For arguments, this is
indicated by the new writable attribute. Tests using
sret/dereferenceable are updated to use it.
2023-11-09 15:55:44 +01:00

241 lines
9.3 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -passes=memcpyopt < %s -verify-memoryssa | FileCheck %s
define i8 @read_dest_between_call_and_memcpy() {
; CHECK-LABEL: @read_dest_between_call_and_memcpy(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: store i8 1, ptr [[DEST]], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[SRC]], i8 0, i64 16, i1 false)
; CHECK-NEXT: [[X:%.*]] = load i8, ptr [[DEST]], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[DEST]], i8 0, i64 16, i1 false)
; CHECK-NEXT: ret i8 [[X]]
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
store i8 1, ptr %dest
call void @llvm.memset.p0.i64(ptr %src, i8 0, i64 16, i1 false)
%x = load i8, ptr %dest
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret i8 %x
}
define i8 @read_src_between_call_and_memcpy() {
; CHECK-LABEL: @read_src_between_call_and_memcpy(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[SRC]], i8 0, i64 16, i1 false)
; CHECK-NEXT: [[X:%.*]] = load i8, ptr [[SRC]], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[DEST]], i8 0, i64 16, i1 false)
; CHECK-NEXT: ret i8 [[X]]
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
call void @llvm.memset.p0.i64(ptr %src, i8 0, i64 16, i1 false)
%x = load i8, ptr %src
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret i8 %x
}
define void @write_dest_between_call_and_memcpy() {
; CHECK-LABEL: @write_dest_between_call_and_memcpy(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[SRC]], i8 0, i64 16, i1 false)
; CHECK-NEXT: store i8 1, ptr [[DEST]], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[DEST]], i8 0, i64 16, i1 false)
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
call void @llvm.memset.p0.i64(ptr %src, i8 0, i64 16, i1 false)
store i8 1, ptr %dest
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret void
}
define void @write_src_between_call_and_memcpy() {
; CHECK-LABEL: @write_src_between_call_and_memcpy(
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[SRC]], i8 0, i64 16, i1 false)
; CHECK-NEXT: store i8 1, ptr [[SRC]], align 1
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
call void @llvm.memset.p0.i64(ptr %src, i8 0, i64 16, i1 false)
store i8 1, ptr %src
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret void
}
define void @throw_between_call_and_mempy(ptr writable dereferenceable(16) %dest.i8) {
; CHECK-LABEL: @throw_between_call_and_mempy(
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[SRC]], i8 0, i64 16, i1 false)
; CHECK-NEXT: call void @may_throw() #[[ATTR2:[0-9]+]]
; CHECK-NEXT: call void @llvm.memset.p0.i64(ptr [[DEST_I8:%.*]], i8 0, i64 16, i1 false)
; CHECK-NEXT: ret void
;
%src = alloca [16 x i8]
call void @llvm.memset.p0.i64(ptr %src, i8 0, i64 16, i1 false)
call void @may_throw() readnone
call void @llvm.memcpy.p0.p0.i64(ptr %dest.i8, ptr %src, i64 16, i1 false)
ret void
}
define void @dest_is_gep_nounwind_call() {
; CHECK-LABEL: @dest_is_gep_nounwind_call(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [8 x i8], align 1
; CHECK-NEXT: [[DEST_I8:%.*]] = getelementptr [16 x i8], ptr [[DEST]], i64 0, i64 8
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST_I8]]) #[[ATTR3:[0-9]+]]
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [8 x i8]
%dest.i8 = getelementptr [16 x i8], ptr %dest, i64 0, i64 8
call void @accept_ptr(ptr %src) nounwind
call void @llvm.memcpy.p0.p0.i64(ptr %dest.i8, ptr %src, i64 8, i1 false)
ret void
}
define void @dest_is_gep_may_throw_call() {
; CHECK-LABEL: @dest_is_gep_may_throw_call(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [8 x i8], align 1
; CHECK-NEXT: [[DEST_I8:%.*]] = getelementptr [16 x i8], ptr [[DEST]], i64 0, i64 8
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST_I8]])
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [8 x i8]
%dest.i8 = getelementptr [16 x i8], ptr %dest, i64 0, i64 8
call void @accept_ptr(ptr %src)
call void @llvm.memcpy.p0.p0.i64(ptr %dest.i8, ptr %src, i64 8, i1 false)
ret void
}
define void @dest_is_gep_requires_movement() {
; CHECK-LABEL: @dest_is_gep_requires_movement(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [8 x i8], align 1
; CHECK-NEXT: [[DEST_I8:%.*]] = getelementptr [16 x i8], ptr [[DEST]], i64 0, i64 8
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST_I8]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [8 x i8]
call void @accept_ptr(ptr %src) nounwind
%dest.i8 = getelementptr [16 x i8], ptr %dest, i64 0, i64 8
call void @llvm.memcpy.p0.p0.i64(ptr %dest.i8, ptr %src, i64 8, i1 false)
ret void
}
define void @capture_before_call_argmemonly() {
; CHECK-LABEL: @capture_before_call_argmemonly(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST]])
; CHECK-NEXT: call void @accept_ptr(ptr nocapture [[DEST]]) #[[ATTR4:[0-9]+]]
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
call void @accept_ptr(ptr %dest) ; capture
call void @accept_ptr(ptr nocapture %src) argmemonly
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret void
}
define void @capture_before_call_argmemonly_nounwind() {
; CHECK-LABEL: @capture_before_call_argmemonly_nounwind(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST]])
; CHECK-NEXT: call void @accept_ptr(ptr nocapture [[DEST]]) #[[ATTR5:[0-9]+]]
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
call void @accept_ptr(ptr %dest) ; capture
; NB: argmemonly currently implies willreturn.
call void @accept_ptr(ptr nocapture %src) argmemonly nounwind
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret void
}
define void @capture_before_call_argmemonly_nounwind_willreturn() {
; CHECK-LABEL: @capture_before_call_argmemonly_nounwind_willreturn(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST]])
; CHECK-NEXT: call void @accept_ptr(ptr nocapture [[DEST]]) #[[ATTR6:[0-9]+]]
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
call void @accept_ptr(ptr %dest) ; capture
call void @accept_ptr(ptr nocapture %src) argmemonly nounwind willreturn
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret void
}
; There is no path from the capture back to the memcpy.
; So we are allowed to perform the call slot optimization.
define void @capture_nopath_call(i1 %cond) {
; CHECK-LABEL: @capture_nopath_call(
; CHECK-NEXT: [[DEST:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: br i1 [[COND:%.*]], label [[CAPTURES:%.*]], label [[NOCAPTURES:%.*]]
; CHECK: captures:
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST]])
; CHECK-NEXT: ret void
; CHECK: nocaptures:
; CHECK-NEXT: call void @accept_ptr(ptr [[DEST]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
%dest = alloca [16 x i8]
%src = alloca [16 x i8]
br i1 %cond, label %captures, label %nocaptures
captures:
call void @accept_ptr(ptr %dest) ; capture
ret void
nocaptures:
call void @accept_ptr(ptr %src) nounwind
call void @llvm.memcpy.p0.p0.i64(ptr %dest, ptr %src, i64 16, i1 false)
ret void
}
define void @source_alignment(ptr noalias writable dereferenceable(128) %dst) {
; CHECK-LABEL: @source_alignment(
; CHECK-NEXT: [[SRC:%.*]] = alloca [128 x i8], align 4
; CHECK-NEXT: call void @accept_ptr(ptr nocapture [[DST:%.*]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
%src = alloca [128 x i8], align 4
call void @accept_ptr(ptr nocapture %src) nounwind
call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr %src, i64 128, i1 false)
ret void
}
define void @dest_not_writable(ptr noalias dereferenceable(128) %dst) {
; CHECK-LABEL: @dest_not_writable(
; CHECK-NEXT: [[SRC:%.*]] = alloca [128 x i8], align 4
; CHECK-NEXT: call void @accept_ptr(ptr nocapture [[SRC]]) #[[ATTR3]]
; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DST:%.*]], ptr [[SRC]], i64 128, i1 false)
; CHECK-NEXT: ret void
;
%src = alloca [128 x i8], align 4
call void @accept_ptr(ptr nocapture %src) nounwind
call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr %src, i64 128, i1 false)
ret void
}
declare void @may_throw()
declare void @accept_ptr(ptr)
declare void @llvm.memcpy.p0.p0.i64(ptr, ptr, i64, i1)
declare void @llvm.memset.p0.i64(ptr, i8, i64, i1)
Reference in New Issue View Git Blame Copy Permalink