From: Josh Magee Date: Sat, 1 Feb 2014 01:36:16 +0000 (+0000) Subject: [stackprotector] Implement the sspstrong rules for stack layout. X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=cde5c26c465d9831546896aa5f2e81358ae05e6c;p=oota-llvm.git [stackprotector] Implement the sspstrong rules for stack layout. This changes the PrologueEpilogInserter and LocalStackSlotAllocation passes to follow the extended stack layout rules for sspstrong and sspreq. The sspstrong layout rules are: 1. Large arrays and structures containing large arrays (>= ssp-buffer-size) are closest to the stack protector. 2. Small arrays and structures containing small arrays (< ssp-buffer-size) are 2nd closest to the protector. 3. Variables that have had their address taken are 3rd closest to the protector. Differential Revision: http://llvm-reviews.chandlerc.com/D2546 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200601 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/docs/LangRef.rst b/docs/LangRef.rst index 07e94a9f84e..e1880f2bc1e 100644 --- a/docs/LangRef.rst +++ b/docs/LangRef.rst @@ -1112,6 +1112,9 @@ example: - Calls to alloca() with variable sizes or constant sizes greater than ``ssp-buffer-size``. + Variables that are identified as requiring a protector will be arranged + on the stack such that they are adjacent to the stack protector guard. + If a function that has an ``ssp`` attribute is inlined into a function that doesn't have an ``ssp`` attribute, then the resulting function will have an ``ssp`` attribute. @@ -1120,6 +1123,17 @@ example: stack smashing protector. This overrides the ``ssp`` function attribute. + Variables that are identified as requiring a protector will be arranged + on the stack such that they are adjacent to the stack protector guard. + The specific layout rules are: + + #. Large arrays and structures containing large arrays + (``>= ssp-buffer-size``) are closest to the stack protector. + #. Small arrays and structures containing small arrays + (``< ssp-buffer-size``) are 2nd closest to the protector. + #. Variables that have had their address taken are 3rd closest to the + protector. + If a function that has an ``sspreq`` attribute is inlined into a function that doesn't have an ``sspreq`` attribute or which has an ``ssp`` or ``sspstrong`` attribute, then the resulting function will have @@ -1135,6 +1149,17 @@ example: - Calls to alloca(). - Local variables that have had their address taken. + Variables that are identified as requiring a protector will be arranged + on the stack such that they are adjacent to the stack protector guard. + The specific layout rules are: + + #. Large arrays and structures containing large arrays + (``>= ssp-buffer-size``) are closest to the stack protector. + #. Small arrays and structures containing small arrays + (``< ssp-buffer-size``) are 2nd closest to the protector. + #. Variables that have had their address taken are 3rd closest to the + protector. + This overrides the ``ssp`` function attribute. If a function that has an ``sspstrong`` attribute is inlined into a diff --git a/lib/CodeGen/LocalStackSlotAllocation.cpp b/lib/CodeGen/LocalStackSlotAllocation.cpp index f521548b213..08f0cc2f011 100644 --- a/lib/CodeGen/LocalStackSlotAllocation.cpp +++ b/lib/CodeGen/LocalStackSlotAllocation.cpp @@ -194,6 +194,9 @@ void LocalStackSlotPass::calculateFrameObjectOffsets(MachineFunction &Fn) { SmallSet ProtectedObjs; if (MFI->getStackProtectorIndex() >= 0) { StackObjSet LargeArrayObjs; + StackObjSet SmallArrayObjs; + StackObjSet AddrOfObjs; + AdjustStackOffset(MFI, MFI->getStackProtectorIndex(), Offset, StackGrowsDown, MaxAlign); @@ -206,8 +209,12 @@ void LocalStackSlotPass::calculateFrameObjectOffsets(MachineFunction &Fn) { switch (SP->getSSPLayout(MFI->getObjectAllocation(i))) { case StackProtector::SSPLK_None: + continue; case StackProtector::SSPLK_SmallArray: + SmallArrayObjs.insert(i); + continue; case StackProtector::SSPLK_AddrOf: + AddrOfObjs.insert(i); continue; case StackProtector::SSPLK_LargeArray: LargeArrayObjs.insert(i); @@ -218,6 +225,10 @@ void LocalStackSlotPass::calculateFrameObjectOffsets(MachineFunction &Fn) { AssignProtectedObjSet(LargeArrayObjs, ProtectedObjs, MFI, StackGrowsDown, Offset, MaxAlign); + AssignProtectedObjSet(SmallArrayObjs, ProtectedObjs, MFI, StackGrowsDown, + Offset, MaxAlign); + AssignProtectedObjSet(AddrOfObjs, ProtectedObjs, MFI, StackGrowsDown, + Offset, MaxAlign); } // Then assign frame offsets to stack objects that are not used to spill diff --git a/lib/CodeGen/PrologEpilogInserter.cpp b/lib/CodeGen/PrologEpilogInserter.cpp index 488e7ecf8cd..1215e5a5d16 100644 --- a/lib/CodeGen/PrologEpilogInserter.cpp +++ b/lib/CodeGen/PrologEpilogInserter.cpp @@ -553,6 +553,9 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { SmallSet ProtectedObjs; if (MFI->getStackProtectorIndex() >= 0) { StackObjSet LargeArrayObjs; + StackObjSet SmallArrayObjs; + StackObjSet AddrOfObjs; + AdjustStackOffset(MFI, MFI->getStackProtectorIndex(), StackGrowsDown, Offset, MaxAlign); @@ -572,8 +575,12 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { switch (SP->getSSPLayout(MFI->getObjectAllocation(i))) { case StackProtector::SSPLK_None: + continue; case StackProtector::SSPLK_SmallArray: + SmallArrayObjs.insert(i); + continue; case StackProtector::SSPLK_AddrOf: + AddrOfObjs.insert(i); continue; case StackProtector::SSPLK_LargeArray: LargeArrayObjs.insert(i); @@ -584,6 +591,10 @@ void PEI::calculateFrameObjectOffsets(MachineFunction &Fn) { AssignProtectedObjSet(LargeArrayObjs, ProtectedObjs, MFI, StackGrowsDown, Offset, MaxAlign); + AssignProtectedObjSet(SmallArrayObjs, ProtectedObjs, MFI, StackGrowsDown, + Offset, MaxAlign); + AssignProtectedObjSet(AddrOfObjs, ProtectedObjs, MFI, StackGrowsDown, + Offset, MaxAlign); } // Then assign frame offsets to stack objects that are not used to spill diff --git a/test/CodeGen/ARM/ssp-data-layout.ll b/test/CodeGen/ARM/ssp-data-layout.ll index ad4195b5192..e7dafac7020 100644 --- a/test/CodeGen/ARM/ssp-data-layout.ll +++ b/test/CodeGen/ARM/ssp-data-layout.ll @@ -165,6 +165,327 @@ entry: ret void } +define void @layout_sspstrong() sspstrong { +entry: +; Expected stack layout for sspstrong is +; 144 large_nonchar . Group 1, nested arrays, +; 136 large_char . arrays >= ssp-buffer-size +; 128 struct_large_char . +; 96 struct_large_nonchar . +; 84+8 small_non_char | Group 2, nested arrays, +; 90 small_char | arrays < ssp-buffer-size +; 88 struct_small_char | +; 84 struct_small_nonchar | +; 80 addrof * Group 3, addr-of local +; 76 scalar1 + Group 4, everything else +; 72 scalar2 + +; 68 scalar3 + +; +; CHECK: layout_sspstrong: +; r[[SP]] is used as an offset into the stack later +; CHECK: add r[[SP:[0-9]+]], sp, #84 + +; CHECK: bl get_scalar1 +; CHECK: str r0, [sp, #76] +; CHECK: bl end_scalar1 + +; CHECK: bl get_scalar2 +; CHECK: str r0, [sp, #72] +; CHECK: bl end_scalar2 + +; CHECK: bl get_scalar3 +; CHECK: str r0, [sp, #68] +; CHECK: bl end_scalar3 + +; CHECK: bl get_addrof +; CHECK: str r0, [sp, #80] +; CHECK: bl end_addrof + +; CHECK: get_small_nonchar +; CHECK: strh r0, [r[[SP]], #8] +; CHECK: bl end_small_nonchar + +; CHECK: bl get_large_nonchar +; CHECK: str r0, [sp, #144] +; CHECK: bl end_large_nonchar + +; CHECK: bl get_small_char +; CHECK: strb r0, [sp, #90] +; CHECK: bl end_small_char + +; CHECK: bl get_large_char +; CHECK: strb r0, [sp, #136] +; CHECK: bl end_large_char + +; CHECK: bl get_struct_large_char +; CHECK: strb r0, [sp, #128] +; CHECK: bl end_struct_large_char + +; CHECK: bl get_struct_small_char +; CHECK: strb r0, [sp, #88] +; CHECK: bl end_struct_small_char + +; CHECK: bl get_struct_large_nonchar +; CHECK: str r0, [sp, #96] +; CHECK: bl end_struct_large_nonchar + +; CHECK: bl get_struct_small_nonchar +; CHECK: strh r0, [r[[SP]]] +; CHECK: bl end_struct_small_nonchar + %x = alloca i32, align 4 + %y = alloca i32, align 4 + %z = alloca i32, align 4 + %ptr = alloca i32, align 4 + %small2 = alloca [2 x i16], align 2 + %large2 = alloca [8 x i32], align 16 + %small = alloca [2 x i8], align 1 + %large = alloca [8 x i8], align 1 + %a = alloca %struct.struct_large_char, align 1 + %b = alloca %struct.struct_small_char, align 1 + %c = alloca %struct.struct_large_nonchar, align 8 + %d = alloca %struct.struct_small_nonchar, align 2 + %call = call i32 @get_scalar1() + store i32 %call, i32* %x, align 4 + call void @end_scalar1() + %call1 = call i32 @get_scalar2() + store i32 %call1, i32* %y, align 4 + call void @end_scalar2() + %call2 = call i32 @get_scalar3() + store i32 %call2, i32* %z, align 4 + call void @end_scalar3() + %call3 = call i32 @get_addrof() + store i32 %call3, i32* %ptr, align 4 + call void @end_addrof() + %call4 = call signext i16 @get_small_nonchar() + %arrayidx = getelementptr inbounds [2 x i16]* %small2, i32 0, i64 0 + store i16 %call4, i16* %arrayidx, align 2 + call void @end_small_nonchar() + %call5 = call i32 @get_large_nonchar() + %arrayidx6 = getelementptr inbounds [8 x i32]* %large2, i32 0, i64 0 + store i32 %call5, i32* %arrayidx6, align 4 + call void @end_large_nonchar() + %call7 = call signext i8 @get_small_char() + %arrayidx8 = getelementptr inbounds [2 x i8]* %small, i32 0, i64 0 + store i8 %call7, i8* %arrayidx8, align 1 + call void @end_small_char() + %call9 = call signext i8 @get_large_char() + %arrayidx10 = getelementptr inbounds [8 x i8]* %large, i32 0, i64 0 + store i8 %call9, i8* %arrayidx10, align 1 + call void @end_large_char() + %call11 = call signext i8 @get_struct_large_char() + %foo = getelementptr inbounds %struct.struct_large_char* %a, i32 0, i32 0 + %arrayidx12 = getelementptr inbounds [8 x i8]* %foo, i32 0, i64 0 + store i8 %call11, i8* %arrayidx12, align 1 + call void @end_struct_large_char() + %call13 = call signext i8 @get_struct_small_char() + %foo14 = getelementptr inbounds %struct.struct_small_char* %b, i32 0, i32 0 + %arrayidx15 = getelementptr inbounds [2 x i8]* %foo14, i32 0, i64 0 + store i8 %call13, i8* %arrayidx15, align 1 + call void @end_struct_small_char() + %call16 = call i32 @get_struct_large_nonchar() + %foo17 = getelementptr inbounds %struct.struct_large_nonchar* %c, i32 0, i32 0 + %arrayidx18 = getelementptr inbounds [8 x i32]* %foo17, i32 0, i64 0 + store i32 %call16, i32* %arrayidx18, align 4 + call void @end_struct_large_nonchar() + %call19 = call signext i16 @get_struct_small_nonchar() + %foo20 = getelementptr inbounds %struct.struct_small_nonchar* %d, i32 0, i32 0 + %arrayidx21 = getelementptr inbounds [2 x i16]* %foo20, i32 0, i64 0 + store i16 %call19, i16* %arrayidx21, align 2 + call void @end_struct_small_nonchar() + %arraydecay = getelementptr inbounds [8 x i8]* %large, i32 0, i32 0 + %arraydecay22 = getelementptr inbounds [2 x i8]* %small, i32 0, i32 0 + %arraydecay23 = getelementptr inbounds [8 x i32]* %large2, i32 0, i32 0 + %arraydecay24 = getelementptr inbounds [2 x i16]* %small2, i32 0, i32 0 + %0 = load i32* %x, align 4 + %1 = load i32* %y, align 4 + %2 = load i32* %z, align 4 + %coerce.dive = getelementptr %struct.struct_large_char* %a, i32 0, i32 0 + %3 = bitcast [8 x i8]* %coerce.dive to i64* + %4 = load i64* %3, align 1 + %coerce.dive25 = getelementptr %struct.struct_small_char* %b, i32 0, i32 0 + %5 = bitcast [2 x i8]* %coerce.dive25 to i16* + %6 = load i16* %5, align 1 + %coerce.dive26 = getelementptr %struct.struct_small_nonchar* %d, i32 0, i32 0 + %7 = bitcast [2 x i16]* %coerce.dive26 to i32* + %8 = load i32* %7, align 1 + call void @takes_all(i64 %4, i16 %6, %struct.struct_large_nonchar* byval align 8 %c, i32 %8, i8* %arraydecay, i8* %arraydecay22, i32* %arraydecay23, i16* %arraydecay24, i32* %ptr, i32 %0, i32 %1, i32 %2) + ret void +} + +define void @layout_sspreq() sspreq { +entry: +; Expected stack layout for sspreq is the same as sspstrong +; +; CHECK: layout_sspreq: +; r[[SP]] is used as an offset into the stack later +; CHECK: add r[[SP:[0-9]+]], sp, #84 + +; CHECK: bl get_scalar1 +; CHECK: str r0, [sp, #76] +; CHECK: bl end_scalar1 + +; CHECK: bl get_scalar2 +; CHECK: str r0, [sp, #72] +; CHECK: bl end_scalar2 + +; CHECK: bl get_scalar3 +; CHECK: str r0, [sp, #68] +; CHECK: bl end_scalar3 + +; CHECK: bl get_addrof +; CHECK: str r0, [sp, #80] +; CHECK: bl end_addrof + +; CHECK: get_small_nonchar +; CHECK: strh r0, [r[[SP]], #8] +; CHECK: bl end_small_nonchar + +; CHECK: bl get_large_nonchar +; CHECK: str r0, [sp, #144] +; CHECK: bl end_large_nonchar + +; CHECK: bl get_small_char +; CHECK: strb r0, [sp, #90] +; CHECK: bl end_small_char + +; CHECK: bl get_large_char +; CHECK: strb r0, [sp, #136] +; CHECK: bl end_large_char + +; CHECK: bl get_struct_large_char +; CHECK: strb r0, [sp, #128] +; CHECK: bl end_struct_large_char + +; CHECK: bl get_struct_small_char +; CHECK: strb r0, [sp, #88] +; CHECK: bl end_struct_small_char + +; CHECK: bl get_struct_large_nonchar +; CHECK: str r0, [sp, #96] +; CHECK: bl end_struct_large_nonchar + +; CHECK: bl get_struct_small_nonchar +; CHECK: strh r0, [r[[SP]]] +; CHECK: bl end_struct_small_nonchar + %x = alloca i32, align 4 + %y = alloca i32, align 4 + %z = alloca i32, align 4 + %ptr = alloca i32, align 4 + %small2 = alloca [2 x i16], align 2 + %large2 = alloca [8 x i32], align 16 + %small = alloca [2 x i8], align 1 + %large = alloca [8 x i8], align 1 + %a = alloca %struct.struct_large_char, align 1 + %b = alloca %struct.struct_small_char, align 1 + %c = alloca %struct.struct_large_nonchar, align 8 + %d = alloca %struct.struct_small_nonchar, align 2 + %call = call i32 @get_scalar1() + store i32 %call, i32* %x, align 4 + call void @end_scalar1() + %call1 = call i32 @get_scalar2() + store i32 %call1, i32* %y, align 4 + call void @end_scalar2() + %call2 = call i32 @get_scalar3() + store i32 %call2, i32* %z, align 4 + call void @end_scalar3() + %call3 = call i32 @get_addrof() + store i32 %call3, i32* %ptr, align 4 + call void @end_addrof() + %call4 = call signext i16 @get_small_nonchar() + %arrayidx = getelementptr inbounds [2 x i16]* %small2, i32 0, i64 0 + store i16 %call4, i16* %arrayidx, align 2 + call void @end_small_nonchar() + %call5 = call i32 @get_large_nonchar() + %arrayidx6 = getelementptr inbounds [8 x i32]* %large2, i32 0, i64 0 + store i32 %call5, i32* %arrayidx6, align 4 + call void @end_large_nonchar() + %call7 = call signext i8 @get_small_char() + %arrayidx8 = getelementptr inbounds [2 x i8]* %small, i32 0, i64 0 + store i8 %call7, i8* %arrayidx8, align 1 + call void @end_small_char() + %call9 = call signext i8 @get_large_char() + %arrayidx10 = getelementptr inbounds [8 x i8]* %large, i32 0, i64 0 + store i8 %call9, i8* %arrayidx10, align 1 + call void @end_large_char() + %call11 = call signext i8 @get_struct_large_char() + %foo = getelementptr inbounds %struct.struct_large_char* %a, i32 0, i32 0 + %arrayidx12 = getelementptr inbounds [8 x i8]* %foo, i32 0, i64 0 + store i8 %call11, i8* %arrayidx12, align 1 + call void @end_struct_large_char() + %call13 = call signext i8 @get_struct_small_char() + %foo14 = getelementptr inbounds %struct.struct_small_char* %b, i32 0, i32 0 + %arrayidx15 = getelementptr inbounds [2 x i8]* %foo14, i32 0, i64 0 + store i8 %call13, i8* %arrayidx15, align 1 + call void @end_struct_small_char() + %call16 = call i32 @get_struct_large_nonchar() + %foo17 = getelementptr inbounds %struct.struct_large_nonchar* %c, i32 0, i32 0 + %arrayidx18 = getelementptr inbounds [8 x i32]* %foo17, i32 0, i64 0 + store i32 %call16, i32* %arrayidx18, align 4 + call void @end_struct_large_nonchar() + %call19 = call signext i16 @get_struct_small_nonchar() + %foo20 = getelementptr inbounds %struct.struct_small_nonchar* %d, i32 0, i32 0 + %arrayidx21 = getelementptr inbounds [2 x i16]* %foo20, i32 0, i64 0 + store i16 %call19, i16* %arrayidx21, align 2 + call void @end_struct_small_nonchar() + %arraydecay = getelementptr inbounds [8 x i8]* %large, i32 0, i32 0 + %arraydecay22 = getelementptr inbounds [2 x i8]* %small, i32 0, i32 0 + %arraydecay23 = getelementptr inbounds [8 x i32]* %large2, i32 0, i32 0 + %arraydecay24 = getelementptr inbounds [2 x i16]* %small2, i32 0, i32 0 + %0 = load i32* %x, align 4 + %1 = load i32* %y, align 4 + %2 = load i32* %z, align 4 + %coerce.dive = getelementptr %struct.struct_large_char* %a, i32 0, i32 0 + %3 = bitcast [8 x i8]* %coerce.dive to i64* + %4 = load i64* %3, align 1 + %coerce.dive25 = getelementptr %struct.struct_small_char* %b, i32 0, i32 0 + %5 = bitcast [2 x i8]* %coerce.dive25 to i16* + %6 = load i16* %5, align 1 + %coerce.dive26 = getelementptr %struct.struct_small_nonchar* %d, i32 0, i32 0 + %7 = bitcast [2 x i16]* %coerce.dive26 to i32* + %8 = load i32* %7, align 1 + call void @takes_all(i64 %4, i16 %6, %struct.struct_large_nonchar* byval align 8 %c, i32 %8, i8* %arraydecay, i8* %arraydecay22, i32* %arraydecay23, i16* %arraydecay24, i32* %ptr, i32 %0, i32 %1, i32 %2) + ret void +} + +define void @struct_with_protectable_arrays() sspstrong { +entry: +; Check to ensure that a structure which contains a small array followed by a +; large array is assigned to the stack properly as a large object. +; CHECK: struct_with_protectable_arrays: +; CHECK: bl get_struct_small_char +; CHECK: strb r0, [sp, #68] +; CHECK: bl end_struct_small_char +; CHECK: bl get_struct_large_char2 +; CHECK: strb r0, [sp, #106] +; CHECK: bl end_struct_large_char2 + %a = alloca %struct.struct_small_char, align 1 + %b = alloca %struct.struct_large_char2, align 1 + %d1 = alloca %struct.struct_large_nonchar, align 8 + %d2 = alloca %struct.struct_small_nonchar, align 2 + %call = call signext i8 @get_struct_small_char() + %foo = getelementptr inbounds %struct.struct_small_char* %a, i32 0, i32 0 + %arrayidx = getelementptr inbounds [2 x i8]* %foo, i32 0, i64 0 + store i8 %call, i8* %arrayidx, align 1 + call void @end_struct_small_char() + %call1 = call signext i8 @get_struct_large_char2() + %foo2 = getelementptr inbounds %struct.struct_large_char2* %b, i32 0, i32 1 + %arrayidx3 = getelementptr inbounds [8 x i8]* %foo2, i32 0, i64 0 + store i8 %call1, i8* %arrayidx3, align 1 + call void @end_struct_large_char2() + %0 = bitcast %struct.struct_large_char2* %b to %struct.struct_large_char* + %coerce.dive = getelementptr %struct.struct_large_char* %0, i32 0, i32 0 + %1 = bitcast [8 x i8]* %coerce.dive to i64* + %2 = load i64* %1, align 1 + %coerce.dive4 = getelementptr %struct.struct_small_char* %a, i32 0, i32 0 + %3 = bitcast [2 x i8]* %coerce.dive4 to i16* + %4 = load i16* %3, align 1 + %coerce.dive5 = getelementptr %struct.struct_small_nonchar* %d2, i32 0, i32 0 + %5 = bitcast [2 x i16]* %coerce.dive5 to i32* + %6 = load i32* %5, align 1 + call void @takes_all(i64 %2, i16 %4, %struct.struct_large_nonchar* byval align 8 %d1, i32 %6, i8* null, i8* null, i32* null, i16* null, i32* null, i32 0, i32 0, i32 0) + ret void +} + declare i32 @get_scalar1() declare void @end_scalar1() diff --git a/test/CodeGen/X86/ssp-data-layout.ll b/test/CodeGen/X86/ssp-data-layout.ll index 72194af96f1..e76ad7b871b 100644 --- a/test/CodeGen/X86/ssp-data-layout.ll +++ b/test/CodeGen/X86/ssp-data-layout.ll @@ -21,7 +21,6 @@ ; on a non-linux target the data layout rules are triggered. %struct.struct_large_char = type { [8 x i8] } -%struct.struct_large_char2 = type { [2 x i8], [8 x i8] } %struct.struct_small_char = type { [2 x i8] } %struct.struct_large_nonchar = type { [8 x i32] } %struct.struct_small_nonchar = type { [2 x i16] } @@ -170,6 +169,282 @@ entry: ret void } +define void @layout_sspstrong() nounwind uwtable sspstrong { +entry: +; Expected stack layout for sspstrong is +; -48 large_nonchar . Group 1, nested arrays, +; -56 large_char . arrays >= ssp-buffer-size +; -64 struct_large_char . +; -96 struct_large_nonchar . +; -100 small_non_char | Group 2, nested arrays, +; -102 small_char | arrays < ssp-buffer-size +; -104 struct_small_char | +; -112 struct_small_nonchar | +; -116 addrof * Group 3, addr-of local +; -120 scalar + Group 4, everything else +; -124 scalar + +; -128 scalar + +; +; CHECK: layout_sspstrong: +; CHECK: call{{l|q}} get_scalar1 +; CHECK: movl %eax, -120( +; CHECK: call{{l|q}} end_scalar1 + +; CHECK: call{{l|q}} get_scalar2 +; CHECK: movl %eax, -124( +; CHECK: call{{l|q}} end_scalar2 + +; CHECK: call{{l|q}} get_scalar3 +; CHECK: movl %eax, -128( +; CHECK: call{{l|q}} end_scalar3 + +; CHECK: call{{l|q}} get_addrof +; CHECK: movl %eax, -116( +; CHECK: call{{l|q}} end_addrof + +; CHECK: get_small_nonchar +; CHECK: movw %ax, -100( +; CHECK: call{{l|q}} end_small_nonchar + +; CHECK: call{{l|q}} get_large_nonchar +; CHECK: movl %eax, -48( +; CHECK: call{{l|q}} end_large_nonchar + +; CHECK: call{{l|q}} get_small_char +; CHECK: movb %al, -102( +; CHECK: call{{l|q}} end_small_char + +; CHECK: call{{l|q}} get_large_char +; CHECK: movb %al, -56( +; CHECK: call{{l|q}} end_large_char + +; CHECK: call{{l|q}} get_struct_large_char +; CHECK: movb %al, -64( +; CHECK: call{{l|q}} end_struct_large_char + +; CHECK: call{{l|q}} get_struct_small_char +; CHECK: movb %al, -104( +; CHECK: call{{l|q}} end_struct_small_char + +; CHECK: call{{l|q}} get_struct_large_nonchar +; CHECK: movl %eax, -96( +; CHECK: call{{l|q}} end_struct_large_nonchar + +; CHECK: call{{l|q}} get_struct_small_nonchar +; CHECK: movw %ax, -112( +; CHECK: call{{l|q}} end_struct_small_nonchar + %x = alloca i32, align 4 + %y = alloca i32, align 4 + %z = alloca i32, align 4 + %ptr = alloca i32, align 4 + %small2 = alloca [2 x i16], align 2 + %large2 = alloca [8 x i32], align 16 + %small = alloca [2 x i8], align 1 + %large = alloca [8 x i8], align 1 + %a = alloca %struct.struct_large_char, align 1 + %b = alloca %struct.struct_small_char, align 1 + %c = alloca %struct.struct_large_nonchar, align 8 + %d = alloca %struct.struct_small_nonchar, align 2 + %call = call i32 @get_scalar1() + store i32 %call, i32* %x, align 4 + call void @end_scalar1() + %call1 = call i32 @get_scalar2() + store i32 %call1, i32* %y, align 4 + call void @end_scalar2() + %call2 = call i32 @get_scalar3() + store i32 %call2, i32* %z, align 4 + call void @end_scalar3() + %call3 = call i32 @get_addrof() + store i32 %call3, i32* %ptr, align 4 + call void @end_addrof() + %call4 = call signext i16 @get_small_nonchar() + %arrayidx = getelementptr inbounds [2 x i16]* %small2, i32 0, i64 0 + store i16 %call4, i16* %arrayidx, align 2 + call void @end_small_nonchar() + %call5 = call i32 @get_large_nonchar() + %arrayidx6 = getelementptr inbounds [8 x i32]* %large2, i32 0, i64 0 + store i32 %call5, i32* %arrayidx6, align 4 + call void @end_large_nonchar() + %call7 = call signext i8 @get_small_char() + %arrayidx8 = getelementptr inbounds [2 x i8]* %small, i32 0, i64 0 + store i8 %call7, i8* %arrayidx8, align 1 + call void @end_small_char() + %call9 = call signext i8 @get_large_char() + %arrayidx10 = getelementptr inbounds [8 x i8]* %large, i32 0, i64 0 + store i8 %call9, i8* %arrayidx10, align 1 + call void @end_large_char() + %call11 = call signext i8 @get_struct_large_char() + %foo = getelementptr inbounds %struct.struct_large_char* %a, i32 0, i32 0 + %arrayidx12 = getelementptr inbounds [8 x i8]* %foo, i32 0, i64 0 + store i8 %call11, i8* %arrayidx12, align 1 + call void @end_struct_large_char() + %call13 = call signext i8 @get_struct_small_char() + %foo14 = getelementptr inbounds %struct.struct_small_char* %b, i32 0, i32 0 + %arrayidx15 = getelementptr inbounds [2 x i8]* %foo14, i32 0, i64 0 + store i8 %call13, i8* %arrayidx15, align 1 + call void @end_struct_small_char() + %call16 = call i32 @get_struct_large_nonchar() + %foo17 = getelementptr inbounds %struct.struct_large_nonchar* %c, i32 0, i32 0 + %arrayidx18 = getelementptr inbounds [8 x i32]* %foo17, i32 0, i64 0 + store i32 %call16, i32* %arrayidx18, align 4 + call void @end_struct_large_nonchar() + %call19 = call signext i16 @get_struct_small_nonchar() + %foo20 = getelementptr inbounds %struct.struct_small_nonchar* %d, i32 0, i32 0 + %arrayidx21 = getelementptr inbounds [2 x i16]* %foo20, i32 0, i64 0 + store i16 %call19, i16* %arrayidx21, align 2 + call void @end_struct_small_nonchar() + %arraydecay = getelementptr inbounds [8 x i8]* %large, i32 0, i32 0 + %arraydecay22 = getelementptr inbounds [2 x i8]* %small, i32 0, i32 0 + %arraydecay23 = getelementptr inbounds [8 x i32]* %large2, i32 0, i32 0 + %arraydecay24 = getelementptr inbounds [2 x i16]* %small2, i32 0, i32 0 + %0 = load i32* %x, align 4 + %1 = load i32* %y, align 4 + %2 = load i32* %z, align 4 + %coerce.dive = getelementptr %struct.struct_large_char* %a, i32 0, i32 0 + %3 = bitcast [8 x i8]* %coerce.dive to i64* + %4 = load i64* %3, align 1 + %coerce.dive25 = getelementptr %struct.struct_small_char* %b, i32 0, i32 0 + %5 = bitcast [2 x i8]* %coerce.dive25 to i16* + %6 = load i16* %5, align 1 + %coerce.dive26 = getelementptr %struct.struct_small_nonchar* %d, i32 0, i32 0 + %7 = bitcast [2 x i16]* %coerce.dive26 to i32* + %8 = load i32* %7, align 1 + call void @takes_all(i64 %4, i16 %6, %struct.struct_large_nonchar* byval align 8 %c, i32 %8, i8* %arraydecay, i8* %arraydecay22, i32* %arraydecay23, i16* %arraydecay24, i32* %ptr, i32 %0, i32 %1, i32 %2) + ret void +} + +define void @layout_sspreq() nounwind uwtable sspreq { +entry: +; Expected stack layout for sspreq is the same as sspstrong +; +; CHECK: layout_sspreq: +; CHECK: call{{l|q}} get_scalar1 +; CHECK: movl %eax, -120( +; CHECK: call{{l|q}} end_scalar1 + +; CHECK: call{{l|q}} get_scalar2 +; CHECK: movl %eax, -124( +; CHECK: call{{l|q}} end_scalar2 + +; CHECK: call{{l|q}} get_scalar3 +; CHECK: movl %eax, -128( +; CHECK: call{{l|q}} end_scalar3 + +; CHECK: call{{l|q}} get_addrof +; CHECK: movl %eax, -116( +; CHECK: call{{l|q}} end_addrof + +; CHECK: get_small_nonchar +; CHECK: movw %ax, -100( +; CHECK: call{{l|q}} end_small_nonchar + +; CHECK: call{{l|q}} get_large_nonchar +; CHECK: movl %eax, -48( +; CHECK: call{{l|q}} end_large_nonchar + +; CHECK: call{{l|q}} get_small_char +; CHECK: movb %al, -102( +; CHECK: call{{l|q}} end_small_char + +; CHECK: call{{l|q}} get_large_char +; CHECK: movb %al, -56( +; CHECK: call{{l|q}} end_large_char + +; CHECK: call{{l|q}} get_struct_large_char +; CHECK: movb %al, -64( +; CHECK: call{{l|q}} end_struct_large_char + +; CHECK: call{{l|q}} get_struct_small_char +; CHECK: movb %al, -104( +; CHECK: call{{l|q}} end_struct_small_char + +; CHECK: call{{l|q}} get_struct_large_nonchar +; CHECK: movl %eax, -96( +; CHECK: call{{l|q}} end_struct_large_nonchar + +; CHECK: call{{l|q}} get_struct_small_nonchar +; CHECK: movw %ax, -112( +; CHECK: call{{l|q}} end_struct_small_nonchar + %x = alloca i32, align 4 + %y = alloca i32, align 4 + %z = alloca i32, align 4 + %ptr = alloca i32, align 4 + %small2 = alloca [2 x i16], align 2 + %large2 = alloca [8 x i32], align 16 + %small = alloca [2 x i8], align 1 + %large = alloca [8 x i8], align 1 + %a = alloca %struct.struct_large_char, align 1 + %b = alloca %struct.struct_small_char, align 1 + %c = alloca %struct.struct_large_nonchar, align 8 + %d = alloca %struct.struct_small_nonchar, align 2 + %call = call i32 @get_scalar1() + store i32 %call, i32* %x, align 4 + call void @end_scalar1() + %call1 = call i32 @get_scalar2() + store i32 %call1, i32* %y, align 4 + call void @end_scalar2() + %call2 = call i32 @get_scalar3() + store i32 %call2, i32* %z, align 4 + call void @end_scalar3() + %call3 = call i32 @get_addrof() + store i32 %call3, i32* %ptr, align 4 + call void @end_addrof() + %call4 = call signext i16 @get_small_nonchar() + %arrayidx = getelementptr inbounds [2 x i16]* %small2, i32 0, i64 0 + store i16 %call4, i16* %arrayidx, align 2 + call void @end_small_nonchar() + %call5 = call i32 @get_large_nonchar() + %arrayidx6 = getelementptr inbounds [8 x i32]* %large2, i32 0, i64 0 + store i32 %call5, i32* %arrayidx6, align 4 + call void @end_large_nonchar() + %call7 = call signext i8 @get_small_char() + %arrayidx8 = getelementptr inbounds [2 x i8]* %small, i32 0, i64 0 + store i8 %call7, i8* %arrayidx8, align 1 + call void @end_small_char() + %call9 = call signext i8 @get_large_char() + %arrayidx10 = getelementptr inbounds [8 x i8]* %large, i32 0, i64 0 + store i8 %call9, i8* %arrayidx10, align 1 + call void @end_large_char() + %call11 = call signext i8 @get_struct_large_char() + %foo = getelementptr inbounds %struct.struct_large_char* %a, i32 0, i32 0 + %arrayidx12 = getelementptr inbounds [8 x i8]* %foo, i32 0, i64 0 + store i8 %call11, i8* %arrayidx12, align 1 + call void @end_struct_large_char() + %call13 = call signext i8 @get_struct_small_char() + %foo14 = getelementptr inbounds %struct.struct_small_char* %b, i32 0, i32 0 + %arrayidx15 = getelementptr inbounds [2 x i8]* %foo14, i32 0, i64 0 + store i8 %call13, i8* %arrayidx15, align 1 + call void @end_struct_small_char() + %call16 = call i32 @get_struct_large_nonchar() + %foo17 = getelementptr inbounds %struct.struct_large_nonchar* %c, i32 0, i32 0 + %arrayidx18 = getelementptr inbounds [8 x i32]* %foo17, i32 0, i64 0 + store i32 %call16, i32* %arrayidx18, align 4 + call void @end_struct_large_nonchar() + %call19 = call signext i16 @get_struct_small_nonchar() + %foo20 = getelementptr inbounds %struct.struct_small_nonchar* %d, i32 0, i32 0 + %arrayidx21 = getelementptr inbounds [2 x i16]* %foo20, i32 0, i64 0 + store i16 %call19, i16* %arrayidx21, align 2 + call void @end_struct_small_nonchar() + %arraydecay = getelementptr inbounds [8 x i8]* %large, i32 0, i32 0 + %arraydecay22 = getelementptr inbounds [2 x i8]* %small, i32 0, i32 0 + %arraydecay23 = getelementptr inbounds [8 x i32]* %large2, i32 0, i32 0 + %arraydecay24 = getelementptr inbounds [2 x i16]* %small2, i32 0, i32 0 + %0 = load i32* %x, align 4 + %1 = load i32* %y, align 4 + %2 = load i32* %z, align 4 + %coerce.dive = getelementptr %struct.struct_large_char* %a, i32 0, i32 0 + %3 = bitcast [8 x i8]* %coerce.dive to i64* + %4 = load i64* %3, align 1 + %coerce.dive25 = getelementptr %struct.struct_small_char* %b, i32 0, i32 0 + %5 = bitcast [2 x i8]* %coerce.dive25 to i16* + %6 = load i16* %5, align 1 + %coerce.dive26 = getelementptr %struct.struct_small_nonchar* %d, i32 0, i32 0 + %7 = bitcast [2 x i16]* %coerce.dive26 to i32* + %8 = load i32* %7, align 1 + call void @takes_all(i64 %4, i16 %6, %struct.struct_large_nonchar* byval align 8 %c, i32 %8, i8* %arraydecay, i8* %arraydecay22, i32* %arraydecay23, i16* %arraydecay24, i32* %ptr, i32 %0, i32 %1, i32 %2) + ret void +} + define void @fast_non_linux() ssp { entry: ; FAST-NON-LIN: fast_non_linux: @@ -222,9 +497,6 @@ declare void @end_large_char() declare signext i8 @get_struct_large_char() declare void @end_struct_large_char() -declare signext i8 @get_struct_large_char2() -declare void @end_struct_large_char2() - declare signext i8 @get_struct_small_char() declare void @end_struct_small_char()