Index: lib/Target/X86/X86MCInstLower.cpp
===================================================================
--- lib/Target/X86/X86MCInstLower.cpp
+++ lib/Target/X86/X86MCInstLower.cpp
@@ -1039,7 +1039,7 @@
   // We want to emit the following pattern:
   //
   // .Lxray_sled_N:
-  //   .palign 2, ...
+  //   .p2align 1, ...
   //   jmp .tmpN
   //   # 9 bytes worth of noops
   // .tmpN
@@ -1052,7 +1052,7 @@
   //
   auto CurSled = OutContext.createTempSymbol("xray_sled_", true);
   OutStreamer->EmitLabel(CurSled);
-  OutStreamer->EmitCodeAlignment(4);
+  OutStreamer->EmitCodeAlignment(2);
   auto Target = OutContext.createTempSymbol();
 
   // Use a two-byte `jmp`. This version of JMP takes an 8-bit relative offset as
@@ -1075,12 +1075,14 @@
   // We should emit the RET followed by sleds.
   //
   // .Lxray_sled_N:
+  //   .p2align 1, ...
   //   ret  # or equivalent instruction
   //   # 10 bytes worth of noops
   //
   // This just makes sure that the alignment for the next instruction is 2.
   auto CurSled = OutContext.createTempSymbol("xray_sled_", true);
   OutStreamer->EmitLabel(CurSled);
+  OutStreamer->EmitCodeAlignment(2);
   unsigned OpCode = MI.getOperand(0).getImm();
   MCInst Ret;
   Ret.setOpcode(OpCode);
Index: test/CodeGen/X86/xray-attribute-instrumentation.ll
===================================================================
--- test/CodeGen/X86/xray-attribute-instrumentation.ll
+++ test/CodeGen/X86/xray-attribute-instrumentation.ll
@@ -2,12 +2,13 @@
 
 define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always" {
 ; CHECK-LABEL: Lxray_sled_0:
-; CHECK-NEXT:  .p2align 2, 0x90
+; CHECK-NEXT:  .p2align 1, 0x90
 ; CHECK-NEXT:  .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
 ; CHECK-LABEL: Ltmp0:
   ret i32 0
 ; CHECK-LABEL: Lxray_sled_1:
+; CHECK-NEXT:  .p2align 1, 0x90
 ; CHECK-NEXT:  retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 }