maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/ObjCARC/tail-call-invariant-enforce...

90 lines
2.7 KiB
LLVM
Raw Normal View History

Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
; RUN: opt -objc-arc -S < %s | FileCheck %s
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
declare void @objc_release(i8* %x)
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
declare i8* @objc_retain(i8* %x)
declare i8* @objc_autorelease(i8* %x)
declare i8* @objc_autoreleaseReturnValue(i8* %x)
declare i8* @objc_retainAutoreleasedReturnValue(i8* %x)
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
declare i8* @tmp(i8*)
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
; Never tail call objc_autorelease.
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
; CHECK: define i8* @test0(i8* %x) [[NUW:#[0-9]+]] {
; CHECK: %tmp0 = call i8* @objc_autorelease(i8* %x) [[NUW]]
; CHECK: %tmp1 = call i8* @objc_autorelease(i8* %x) [[NUW]]
; CHECK: }
define i8* @test0(i8* %x) nounwind {
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
entry:
%tmp0 = call i8* @objc_autorelease(i8* %x)
%tmp1 = tail call i8* @objc_autorelease(i8* %x)
ret i8* %x
}
; Always tail call autoreleaseReturnValue.
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
; CHECK: define i8* @test1(i8* %x) [[NUW]] {
; CHECK: %tmp0 = tail call i8* @objc_autoreleaseReturnValue(i8* %x) [[NUW]]
; CHECK: %tmp1 = tail call i8* @objc_autoreleaseReturnValue(i8* %x) [[NUW]]
; CHECK: }
define i8* @test1(i8* %x) nounwind {
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
entry:
%tmp0 = call i8* @objc_autoreleaseReturnValue(i8* %x)
%tmp1 = tail call i8* @objc_autoreleaseReturnValue(i8* %x)
ret i8* %x
}
; Always tail call objc_retain.
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
; CHECK: define i8* @test2(i8* %x) [[NUW]] {
; CHECK: %tmp0 = tail call i8* @objc_retain(i8* %x) [[NUW]]
; CHECK: %tmp1 = tail call i8* @objc_retain(i8* %x) [[NUW]]
; CHECK: }
define i8* @test2(i8* %x) nounwind {
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
entry:
%tmp0 = call i8* @objc_retain(i8* %x)
%tmp1 = tail call i8* @objc_retain(i8* %x)
ret i8* %x
}
; Always tail call objc_retainAutoreleasedReturnValue.
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
; CHECK: define i8* @test3(i8* %x) [[NUW]] {
; CHECK: %tmp0 = tail call i8* @objc_retainAutoreleasedReturnValue(i8* %y) [[NUW]]
; CHECK: %tmp1 = tail call i8* @objc_retainAutoreleasedReturnValue(i8* %z) [[NUW]]
; CHECK: }
define i8* @test3(i8* %x) nounwind {
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
entry:
%y = call i8* @tmp(i8* %x)
%tmp0 = call i8* @objc_retainAutoreleasedReturnValue(i8* %y)
%z = call i8* @tmp(i8* %x)
%tmp1 = tail call i8* @objc_retainAutoreleasedReturnValue(i8* %z)
ret i8* %x
}
; By itself, we should never change whether or not objc_release is tail called.
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
; CHECK: define void @test4(i8* %x) [[NUW]] {
; CHECK: call void @objc_release(i8* %x) [[NUW]]
; CHECK: tail call void @objc_release(i8* %x) [[NUW]]
; CHECK: }
define void @test4(i8* %x) nounwind {
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
entry:
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
call void @objc_release(i8* %x)
tail call void @objc_release(i8* %x)
ret void
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
}
; If we convert a tail called @objc_autoreleaseReturnValue to an
; @objc_autorelease, ensure that the tail call is removed.
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
; CHECK: define i8* @test5(i8* %x) [[NUW]] {
; CHECK: %tmp0 = call i8* @objc_autorelease(i8* %x) [[NUW]]
; CHECK: }
define i8* @test5(i8* %x) nounwind {
Fixed a bug where we were tail calling objc_autorelease causing an object to not be placed into an autorelease pool. The reason that this occurs is that tail calling objc_autorelease eventually tail calls -[NSObject autorelease] which supports fast autorelease. This can cause us to violate the semantic gaurantees of __autoreleasing variables that assignment to an __autoreleasing variables always yields an object that is placed into the innermost autorelease pool. The fix included in this patch works by: 1. In the peephole optimization function OptimizeIndividualFunctions, always remove tail call from objc_autorelease. 2. Whenever we convert to/from an objc_autorelease, set/unset the tail call keyword as appropriate. *NOTE* I also handled the case where objc_autorelease is converted in OptimizeReturns to an autoreleaseRV which still violates the ARC semantics. I will be removing that in a later patch and I wanted to make sure that the tree is in a consistent state vis-a-vis ARC always. Additionally some test cases are provided and all tests that have tail call marked objc_autorelease keywords have been modified so that tail call has been removed. *NOTE* One test fails due to a separate bug that I am going to commit soon. Thus I marked the check line TMP: instead of CHECK: so make check does not fail. llvm-svn: 172287
2013-01-12 09:25:15 +08:00
entry:
%tmp0 = tail call i8* @objc_autoreleaseReturnValue(i8* %x)
ret i8* %tmp0
}
[objc-arc] Cleaned up tail-call-invariant-enforcement.ll. Specifically: 1. Added checks that unwind is being properly added to various instructions. 2. Fixed the declaration/calling of objc_release to have a return type of void. 3. Moved all checks to precede the functions and added checks to ensure that the checks would only match inside the specific function that we are attempting to check. llvm-svn: 179973
2013-04-21 10:59:44 +08:00
; CHECK: attributes [[NUW]] = { nounwind }