[llvm] 9573c9f - Fix limit behavior of dynamic alloca

[via llvm-commits]

Author: serge-sans-paille
Date: 2020-10-02T11:10:02+02:00
New Revision: 9573c9f2a363da71b2c07a3add4e52721e6028a0

URL: https://github.com/llvm/llvm-project/commit/9573c9f2a363da71b2c07a3add4e52721e6028a0
DIFF: https://github.com/llvm/llvm-project/commit/9573c9f2a363da71b2c07a3add4e52721e6028a0.diff

LOG: Fix limit behavior of dynamic alloca

When the allocation size is 0, we shouldn't probe. Within [1,  PAGE_SIZE], we
should probe once etc.

This fixes https://bugs.llvm.org/show_bug.cgi?id=47657

Differential Revision: https://reviews.llvm.org/D88548

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86ISelLowering.cpp
    llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 8306e3a23f47..935fab44e7c1 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -32394,7 +32394,7 @@ X86TargetLowering::EmitLoweredProbedAlloca(MachineInstr &MI,
 
   BuildMI(testMBB, DL, TII->get(X86::JCC_1))
       .addMBB(tailMBB)
-      .addImm(X86::COND_L);
+      .addImm(X86::COND_LE);
   testMBB->addSuccessor(blockMBB);
   testMBB->addSuccessor(tailMBB);
 

diff  --git a/llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll b/llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll
index bc4678564083..82fd67842c8a 100644
--- a/llvm/test/CodeGen/X86/stack-clash-dynamic-alloca.ll
+++ b/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:  	jl	.LBB0_3
+; CHECK-X86-64-NEXT:  	jle	.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:  	subq	$4096, %rsp # imm = 0x1000
 ; CHECK-X86-64-NEXT:  	cmpq	%rsp, %rax
-; CHECK-X86-64-NEXT:  	jge	.LBB0_2
+; CHECK-X86-64-NEXT:  	jg	.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:    jl  .LBB0_3
+; CHECK-X86-32-NEXT:    jle  .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:    subl    $4096, %esp # imm = 0x1000
 ; CHECK-X86-32-NEXT:    cmpl    %esp, %eax
-; CHECK-X86-32-NEXT:    jge .LBB0_2
+; CHECK-X86-32-NEXT:    jg .LBB0_2
 ; CHECK-X86-32-NEXT:  .LBB0_3:
 ; CHECK-X86-32-NEXT:    movl    %eax, %esp
 ; CHECK-X86-32-NEXT:    movl    $1, 4792(%eax)