diff --git a/xen/arch/x86/Rules.mk b/xen/arch/x86/Rules.mk
index ac585a37ea..cc301cdc5b 100644
--- a/xen/arch/x86/Rules.mk
+++ b/xen/arch/x86/Rules.mk
@@ -29,6 +29,10 @@ $(call as-option-add,CFLAGS,CC,"invpcid (%rax)$$(comma)%rax",-DHAVE_AS_INVPCID)
 $(call as-option-add,CFLAGS,CC,\
     ".if ((1 > 0) < 0); .error \"\";.endif",,-DHAVE_AS_NEGATIVE_TRUE)
 
+# Check to see whether the assmbler supports the .nop directive.
+$(call as-option-add,CFLAGS,CC,\
+    ".L1: .L2: .nops (.L2 - .L1)$$(comma)9",-DHAVE_AS_NOPS_DIRECTIVE)
+
 CFLAGS += -mno-red-zone -fpic -fno-asynchronous-unwind-tables
 
 # Xen doesn't use SSE interally.  If the compiler supports it, also skip the
diff --git a/xen/arch/x86/alternative.c b/xen/arch/x86/alternative.c
index 0ef7a8ba1f..ea835d98a3 100644
--- a/xen/arch/x86/alternative.c
+++ b/xen/arch/x86/alternative.c
@@ -84,6 +84,19 @@ static const unsigned char * const p6_nops[ASM_NOP_MAX+1] init_or_livepatch_cons
 
 static const unsigned char * const *ideal_nops init_or_livepatch_data = p6_nops;
 
+#ifdef HAVE_AS_NOPS_DIRECTIVE
+
+/* Nops in .init.rodata to compare against the runtime ideal nops. */
+asm ( ".pushsection .init.rodata, \"a\", @progbits\n\t"
+      "toolchain_nops: .nops " __stringify(ASM_NOP_MAX) "\n\t"
+      ".popsection\n\t");
+extern char toolchain_nops[ASM_NOP_MAX];
+static bool __read_mostly toolchain_nops_are_ideal;
+
+#else
+# define toolchain_nops_are_ideal false
+#endif
+
 static void __init arch_init_ideal_nops(void)
 {
     switch ( boot_cpu_data.x86_vendor )
@@ -112,6 +125,11 @@ static void __init arch_init_ideal_nops(void)
             ideal_nops = k8_nops;
         break;
     }
+
+#ifdef HAVE_AS_NOPS_DIRECTIVE
+    if ( memcmp(ideal_nops[ASM_NOP_MAX], toolchain_nops, ASM_NOP_MAX) == 0 )
+        toolchain_nops_are_ideal = true;
+#endif
 }
 
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
@@ -209,7 +227,7 @@ void init_or_livepatch apply_alternatives(struct alt_instr *start,
             base->priv = 1;
 
             /* Nothing useful to do? */
-            if ( a->pad_len <= 1 )
+            if ( toolchain_nops_are_ideal || a->pad_len <= 1 )
                 continue;
 
             add_nops(buf, a->pad_len);
diff --git a/xen/include/asm-x86/alternative-asm.h b/xen/include/asm-x86/alternative-asm.h
index 0b6151634a..e6c42d721d 100644
--- a/xen/include/asm-x86/alternative-asm.h
+++ b/xen/include/asm-x86/alternative-asm.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_ALTERNATIVE_ASM_H_
 #define _ASM_X86_ALTERNATIVE_ASM_H_
 
+#include <asm/nops.h>
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -19,6 +21,14 @@
     .byte 0 /* priv */
 .endm
 
+.macro mknops nr_bytes
+#ifdef HAVE_AS_NOPS_DIRECTIVE
+    .nops \nr_bytes, ASM_NOP_MAX
+#else
+    .skip \nr_bytes, 0x90
+#endif
+.endm
+
 /* GAS's idea of true is -1, while Clang's idea is 1. */
 #ifdef HAVE_AS_NEGATIVE_TRUE
 # define as_true(x) (-(x))
@@ -29,7 +39,7 @@
 #define decl_orig(insn, padding)                  \
  .L\@_orig_s: insn; .L\@_orig_e:                  \
  .L\@_diff = padding;                             \
- .skip as_true(.L\@_diff > 0) * .L\@_diff, 0x90;  \
+ mknops (as_true(.L\@_diff > 0) * .L\@_diff);     \
  .L\@_orig_p:
 
 #define orig_len               (.L\@_orig_e       -     .L\@_orig_s)
diff --git a/xen/include/asm-x86/alternative.h b/xen/include/asm-x86/alternative.h
index 619472efcb..66fe791818 100644
--- a/xen/include/asm-x86/alternative.h
+++ b/xen/include/asm-x86/alternative.h
@@ -2,7 +2,6 @@
 #define __X86_ALTERNATIVE_H__
 
 #include <asm/alternative-asm.h>
-#include <asm/nops.h>
 
 #ifndef __ASSEMBLY__
 #include <xen/stringify.h>
@@ -27,6 +26,14 @@ extern void add_nops(void *insns, unsigned int len);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 extern void alternative_instructions(void);
 
+asm ( ".macro mknops nr_bytes\n\t"
+#ifdef HAVE_AS_NOPS_DIRECTIVE
+      ".nops \\nr_bytes, " __stringify(ASM_NOP_MAX) "\n\t"
+#else
+      ".skip \\nr_bytes, 0x90\n\t"
+#endif
+      ".endm\n\t" );
+
 #define alt_orig_len       "(.LXEN%=_orig_e - .LXEN%=_orig_s)"
 #define alt_pad_len        "(.LXEN%=_orig_p - .LXEN%=_orig_e)"
 #define alt_total_len      "(.LXEN%=_orig_p - .LXEN%=_orig_s)"
@@ -46,7 +53,7 @@ extern void alternative_instructions(void);
 #define OLDINSTR(oldinstr, padding)                              \
     ".LXEN%=_orig_s:\n\t" oldinstr "\n .LXEN%=_orig_e:\n\t"      \
     ".LXEN%=_diff = " padding "\n\t"                             \
-    ".skip "AS_TRUE"(.LXEN%=_diff > 0) * .LXEN%=_diff, 0x90\n\t" \
+    "mknops ("AS_TRUE"(.LXEN%=_diff > 0) * .LXEN%=_diff)\n\t"    \
     ".LXEN%=_orig_p:\n\t"
 
 #define OLDINSTR_1(oldinstr, n1)                                 \