[X86] Fix cmp order in probing BuildStackAlignAND

Due to reversed arguments, the loop start was almost always skipping the whole loop, since FinalStackProbed is probably less than StackPtr for large alignments. The intent was to skip the loop if the first sub on StackPtr made it less than FinalStackProbed already, so flip it. Reviewed By: serge-sans-paille Differential Revision: https://reviews.llvm.org/D139756
llvm · Dec 13, 2022 · 9b8fcd0 · 9b8fcd0
1 parent d08e3ae
commit 9b8fcd0
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 5 deletions.
diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -1293,11 +1293,11 @@ void X86FrameLowering::BuildStackAlignAND(MachineBasicBlock &MBB,
 
         BuildMI(headMBB, DL,
                 TII.get(Uses64BitFramePtr ? X86::CMP64rr : X86::CMP32rr))
-            .addReg(FinalStackProbed)
             .addReg(StackPtr)
+            .addReg(FinalStackProbed)
             .setMIFlag(MachineInstr::FrameSetup);
 
-        // jump
+        // jump to the footer if StackPtr < FinalStackProbed
         BuildMI(headMBB, DL, TII.get(X86::JCC_1))
             .addMBB(footMBB)
             .addImm(X86::COND_B)
@@ -1329,7 +1329,7 @@ void X86FrameLowering::BuildStackAlignAND(MachineBasicBlock &MBB,
             .addReg(StackPtr)
             .setMIFlag(MachineInstr::FrameSetup);
 
-        // jump
+        // jump back while FinalStackProbed < StackPtr
         BuildMI(bodyMBB, DL, TII.get(X86::JCC_1))
             .addMBB(bodyMBB)
             .addImm(X86::COND_B)

diff --git a/llvm/test/CodeGen/X86/stack-clash-large-large-align.ll b/llvm/test/CodeGen/X86/stack-clash-large-large-align.ll
@@ -44,7 +44,7 @@ define i32 @foo_protect() local_unnamed_addr #0 {
 ; CHECK-NEXT:    je .LBB1_4
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
-; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    cmpq %r11, %rsp
 ; CHECK-NEXT:    jb .LBB1_3
 ; CHECK-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq $0, (%rsp)

diff --git a/llvm/test/CodeGen/X86/stack-clash-small-large-align.ll b/llvm/test/CodeGen/X86/stack-clash-small-large-align.ll
@@ -40,7 +40,7 @@ define i32 @foo_protect() local_unnamed_addr #0 {
 ; CHECK-NEXT:    je .LBB1_4
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    subq $4096, %rsp # imm = 0x1000
-; CHECK-NEXT:    cmpq %rsp, %r11
+; CHECK-NEXT:    cmpq %r11, %rsp
 ; CHECK-NEXT:    jb .LBB1_3
 ; CHECK-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq $0, (%rsp)