RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 19:12:56 +02:00
Code Issues Projects Releases Wiki Activity

Replace the result usages while legalizing cmpxchg.

Browse Source 
We should update the usages to all of the results;
otherwise, we might get assertion failure or SEGV during
the type legalization of ATOMIC_CMP_SWAP_WITH_SUCCESS
with two or more illegal types.

For example, in the following sequence, both i8 and i1
might be illegal in some target, e.g. armv5, mipsel, mips64el,

    %0 = cmpxchg i8* %ptr, i8 %desire, i8 %new monotonic monotonic
    %1 = extractvalue { i8, i1 } %0, 1

Since both i8 and i1 should be legalized, the corresponding
ATOMIC_CMP_SWAP_WITH_SUCCESS dag will be checked/replaced/updated
twice.

If we don't update the usage to *ALL* of the results in the
first round, the DAG for extractvalue might be processed earlier.
The GetPromotedInteger() will result in assertion failure,
because its operand (i.e. the success bit of cmpxchg) is not
promoted beforehand.

llvm-svn: 213569
This commit is contained in:
Logan Chien 2014-07-21 17:33:44 +00:00
parent acd6079121
commit b6d535b47e
3 changed files with 98 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp
View File

@ -225,10 +225,9 @@ SDValue DAGTypeLegalizer::PromoteIntRes_AtomicCmpSwap(AtomicSDNode *N,
N->getOpcode(), SDLoc(N), N->getMemoryVT(), VTs, N->getChain(),
N->getBasePtr(), Op2, Op3, N->getMemOperand(), N->getSuccessOrdering(),
N->getFailureOrdering(), N->getSynchScope());
// Legalized the chain result - switch anything that used the old chain to
// use the new one.
unsigned ChainOp = N->getNumValues() - 1;
ReplaceValueWith(SDValue(N, ChainOp), Res.getValue(ChainOp));
// Update the use to N with the newly created Res.
for (unsigned i = 1, NumResults = N->getNumValues(); i < NumResults; ++i)
ReplaceValueWith(SDValue(N, i), Res.getValue(i));
return Res;
}

50
test/CodeGen/ARM/atomic-cmpxchg.ll Normal file
View File

@ -0,0 +1,50 @@
; RUN: llc < %s -mtriple=arm-linux-gnueabi -verify-machineinstrs | FileCheck %s -check-prefix=CHECK-ARM
; RUN: llc < %s -mtriple=thumb-linux-gnueabi -verify-machineinstrs | FileCheck %s -check-prefix=CHECK-THUMB
; RUN: llc < %s -mtriple=armv7-linux-gnueabi -verify-machineinstrs | FileCheck %s -check-prefix=CHECK-ARMV7
; RUN: llc < %s -mtriple=thumbv7-linux-gnueabi -verify-machineinstrs | FileCheck %s -check-prefix=CHECK-THUMBV7
define zeroext i1 @test_cmpxchg_res_i8(i8* %addr, i8 %desired, i8 zeroext %new) {
entry:
%0 = cmpxchg i8* %addr, i8 %desired, i8 %new monotonic monotonic
%1 = extractvalue { i8, i1 } %0, 1
ret i1 %1
}
; CHECK-ARM-LABEL: test_cmpxchg_res_i8
; CHECK-ARM: bl __sync_val_compare_and_swap_1
; CHECK-ARM: mov [[REG:r[0-9]+]], #0
; CHECK-ARM: cmp r0, {{r[0-9]+}}
; CHECK-ARM: moveq [[REG]], #1
; CHECK-ARM: mov r0, [[REG]]
; CHECK-THUMB-LABEL: test_cmpxchg_res_i8
; CHECK-THUMB: bl __sync_val_compare_and_swap_1
; CHECK-THUMB: mov [[R1:r[0-9]+]], r0
; CHECK-THUMB: movs r0, #1
; CHECK-THUMB: movs [[R2:r[0-9]+]], #0
; CHECK-THUMB: cmp [[R1]], {{r[0-9]+}}
; CHECK-THU<B: beq
; CHECK-THUMB: mov r0, [[R2]]
; CHECK-ARMV7-LABEL: test_cmpxchg_res_i8
; CHECK-ARMV7: ldrexb [[R3:r[0-9]+]], [r0]
; CHECK-ARMV7: mov [[R1:r[0-9]+]], #0
; CHECK-ARMV7: cmp [[R3]], {{r[0-9]+}}
; CHECK-ARMV7: bne
; CHECK-ARMV7: strexb [[R3]], {{r[0-9]+}}, [{{r[0-9]+}}]
; CHECK-ARMV7: mov [[R1]], #1
; CHECK-ARMV7: cmp [[R3]], #0
; CHECK-ARMV7: bne
; CHECK-ARMV7: mov r0, [[R1]]
; CHECK-THUMBV7-LABEL: test_cmpxchg_res_i8
; CHECK-THUMBV7: ldrexb [[R3:r[0-9]+]], [r0]
; CHECK-THUMBV7: cmp [[R3]], {{r[0-9]+}}
; CHECK-THUMBV7: movne r0, #0
; CHECK-THUMBV7: bxne lr
; CHECK-THUMBV7: strexb [[R3]], {{r[0-9]+}}, [{{r[0-9]+}}]
; CHECK-THUMBV7: cmp [[R3]], #0
; CHECK-THUMBV7: itt eq
; CHECK-THUMBV7: moveq r0, #1
; CHECK-THUMBV7: bxeq lr

46
test/CodeGen/Mips/atomic.ll
View File

@ -8,7 +8,7 @@
; Keep one big-endian check so that we don't reduce testing, but don't add more
; since endianness doesn't affect the body of the atomic operations.
; RUN: llc -march=mips --disable-machine-licm -mcpu=mips32 < %s | FileCheck %s -check-prefix=ALL -check-prefix=MIPS32-ANY -check-prefix=CHECK-EB
; RUN: llc -march=mips --disable-machine-licm -mcpu=mips32 < %s | FileCheck %s -check-prefix=ALL -check-prefix=MIPS32-ANY -check-prefix=NO-SEB-SEH -check-prefix=CHECK-EB
@x = common global i32 0, align 4
@ -246,6 +246,7 @@ entry:
; NO-SEB-SEH: sra $2, $[[R17]], 24
; HAS-SEB-SEH: seb $2, $[[R16]]
}
define signext i8 @AtomicCmpSwap8(i8 signext %oldval, i8 signext %newval) nounwind {
@ -292,6 +293,49 @@ entry:
; HAS-SEB-SEH: seb $2, $[[R17]]
}
define i1 @AtomicCmpSwapRes8(i8* %ptr, i8 %oldval, i8 signext %newval) nounwind {
entry:
%0 = cmpxchg i8* %ptr, i8 %oldval, i8 %newval monotonic monotonic
%1 = extractvalue { i8, i1 } %0, 1
ret i1 %1
; ALL-LABEL: AtomicCmpSwapRes8
; ALL: addiu $[[R1:[0-9]+]], $zero, -4
; ALL: and $[[R2:[0-9]+]], $4, $[[R1]]
; ALL: andi $[[R3:[0-9]+]], $4, 3
; CHECK-EL: sll $[[R5:[0-9]+]], $[[R3]], 3
; CHECK-EB: xori $[[R4:[0-9]+]], $[[R3]], 3
; CHECK-EB: sll $[[R5:[0-9]+]], $[[R4]], 3
; ALL: ori $[[R6:[0-9]+]], $zero, 255
; ALL: sllv $[[R7:[0-9]+]], $[[R6]], $[[R5]]
; ALL: nor $[[R8:[0-9]+]], $zero, $[[R7]]
; ALL: andi $[[R9:[0-9]+]], $5, 255
; ALL: sllv $[[R10:[0-9]+]], $[[R9]], $[[R5]]
; ALL: andi $[[R11:[0-9]+]], $6, 255
; ALL: sllv $[[R12:[0-9]+]], $[[R11]], $[[R5]]
; ALL: $[[BB0:[A-Z_0-9]+]]:
; ALL: ll $[[R13:[0-9]+]], 0($[[R2]])
; ALL: and $[[R14:[0-9]+]], $[[R13]], $[[R7]]
; ALL: bne $[[R14]], $[[R10]], $[[BB1:[A-Z_0-9]+]]
; ALL: and $[[R15:[0-9]+]], $[[R13]], $[[R8]]
; ALL: or $[[R16:[0-9]+]], $[[R15]], $[[R12]]
; ALL: sc $[[R16]], 0($[[R2]])
; ALL: beqz $[[R16]], $[[BB0]]
; ALL: $[[BB1]]:
; ALL: srlv $[[R17:[0-9]+]], $[[R14]], $[[R5]]
; NO-SEB-SEH: sll $[[R18:[0-9]+]], $[[R17]], 24
; NO-SEB-SEH: sra $[[R19:[0-9]+]], $[[R18]], 24
; HAS-SEB-SEH: seb $[[R19:[0-9]+]], $[[R17]]
; ALL: xor $[[R20:[0-9]+]], $[[R19]], $5
; ALL: sltiu $2, $[[R20]], 1
}
; Check one i16 so that we cover the seh sign extend
@z = common global i16 0, align 1