[stack-clash] Fix probing of dynamic alloca

- Perform the probing in the correct direction.
  Related to rust-lang/rust#77885 (comment)

- The first touch on a dynamic alloca cannot use a mov because it clobbers
  existing space. Use a xor 0 instead

Differential Revision: https://reviews.llvm.org/D90216

(cherry picked from commit 0f60bcc)

Author: serge-sans-paille

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -31876,7 +31876,7 @@ X86TargetLowering::EmitLoweredProbedAlloca(MachineInstr &MI,
 
   BuildMI(testMBB, DL, TII->get(X86::JCC_1))
       .addMBB(tailMBB)
-      .addImm(X86::COND_LE);
+      .addImm(X86::COND_GE);
   testMBB->addSuccessor(blockMBB);
   testMBB->addSuccessor(tailMBB);
 
@@ -31892,9 +31892,9 @@ X86TargetLowering::EmitLoweredProbedAlloca(MachineInstr &MI,
   //
   // The property we want to enforce is to never have more than [page alloc] between two probes.
 
-  const unsigned MovMIOpc =
-      TFI.Uses64BitFramePtr ? X86::MOV64mi32 : X86::MOV32mi;
-  addRegOffset(BuildMI(blockMBB, DL, TII->get(MovMIOpc)), physSPReg, false, 0)
+  const unsigned XORMIOpc =
+      TFI.Uses64BitFramePtr ? X86::XOR64mi8 : X86::XOR32mi8;
+  addRegOffset(BuildMI(blockMBB, DL, TII->get(XORMIOpc)), physSPReg, false, 0)
       .addImm(0);
 
   BuildMI(blockMBB, DL,

llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll

@@ -24,12 +24,12 @@ attributes #0 =  {"probe-stack"="inline-asm"}
 ; CHECK-X86-64-NEXT:  	andq	$-16, %rcx
 ; CHECK-X86-64-NEXT:  	subq	%rcx, %rax
 ; CHECK-X86-64-NEXT:  	cmpq	%rsp, %rax
-; CHECK-X86-64-NEXT:  	jle	.LBB0_3
+; CHECK-X86-64-NEXT:  	jge	.LBB0_3
 ; CHECK-X86-64-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
-; CHECK-X86-64-NEXT:  	movq	$0, (%rsp)
+; CHECK-X86-64-NEXT:  	xorq	$0, (%rsp)
 ; CHECK-X86-64-NEXT:  	subq	$4096, %rsp # imm = 0x1000
 ; CHECK-X86-64-NEXT:  	cmpq	%rsp, %rax
-; CHECK-X86-64-NEXT:  	jg	.LBB0_2
+; CHECK-X86-64-NEXT:  	jl	.LBB0_2
 ; CHECK-X86-64-NEXT:  .LBB0_3:
 ; CHECK-X86-64-NEXT:  	movq	%rax, %rsp
 ; CHECK-X86-64-NEXT:  	movl	$1, 4792(%rax)
@@ -54,12 +54,12 @@ attributes #0 =  {"probe-stack"="inline-asm"}
 ; CHECK-X86-32-NEXT:    andl    $-16, %ecx
 ; CHECK-X86-32-NEXT:    subl    %ecx, %eax
 ; CHECK-X86-32-NEXT:    cmpl    %esp, %eax
-; CHECK-X86-32-NEXT:    jle  .LBB0_3
+; CHECK-X86-32-NEXT:    jge  .LBB0_3
 ; CHECK-X86-32-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
-; CHECK-X86-32-NEXT:    movl    $0, (%esp)
+; CHECK-X86-32-NEXT:    xorl    $0, (%esp)
 ; CHECK-X86-32-NEXT:    subl    $4096, %esp # imm = 0x1000
 ; CHECK-X86-32-NEXT:    cmpl    %esp, %eax
-; CHECK-X86-32-NEXT:    jg .LBB0_2
+; CHECK-X86-32-NEXT:    jl .LBB0_2
 ; CHECK-X86-32-NEXT:  .LBB0_3:
 ; CHECK-X86-32-NEXT:    movl    %eax, %esp
 ; CHECK-X86-32-NEXT:    movl    $1, 4792(%eax)

llvm/test/CodeGen/X86/stack-clash-small-alloc-medium-align.ll

@@ -106,12 +106,12 @@ define i32 @foo4(i64 %i) local_unnamed_addr #0 {
 ; CHECK-NEXT:	andq	$-16, %rcx
 ; CHECK-NEXT:	subq	%rcx, %rax
 ; CHECK-NEXT:	cmpq	%rsp, %rax
-; CHECK-NEXT:	jle	.LBB3_3
+; CHECK-NEXT:	jge	.LBB3_3
 ; CHECK-NEXT:.LBB3_2:                                # =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:	movq	$0, (%rsp)
+; CHECK-NEXT:	xorq	$0, (%rsp)
 ; CHECK-NEXT:	subq	$4096, %rsp                     # imm = 0x1000
 ; CHECK-NEXT:	cmpq	%rsp, %rax
-; CHECK-NEXT:	jg	.LBB3_2
+; CHECK-NEXT:	jl	.LBB3_2
 ; CHECK-NEXT:.LBB3_3:
 ; CHECK-NEXT:	andq	$-64, %rax
 ; CHECK-NEXT:	movq	%rax, %rsp