diff --git a/[refs] b/[refs]
index ab707dac1ba7..4eea1916958c 100644
--- a/[refs]
+++ b/[refs]
@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 1edfbb4153bd29bcf8d2236676238d5237972be1
+refs/heads/master: 5870661c091e827973674cc3469b50c959008c2b
diff --git a/trunk/arch/x86/include/asm/bitops.h b/trunk/arch/x86/include/asm/bitops.h
index ebaee695394e..b2af6645ea7e 100644
--- a/trunk/arch/x86/include/asm/bitops.h
+++ b/trunk/arch/x86/include/asm/bitops.h
@@ -347,6 +347,19 @@ static int test_bit(int nr, const volatile unsigned long *addr);
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+#if (defined(CONFIG_X86_GENERIC) || defined(CONFIG_GENERIC_CPU)) \
+    && !defined(CONFIG_CC_OPTIMIZE_FOR_SIZE)
+/*
+ * Since BSF and TZCNT have sufficiently similar semantics for the purposes
+ * for which we use them here, BMI-capable hardware will decode the prefixed
+ * variant as 'tzcnt ...' and may execute that faster than 'bsf ...', while
+ * older hardware will ignore the REP prefix and decode it as 'bsf ...'.
+ */
+# define BSF_PREFIX "rep;"
+#else
+# define BSF_PREFIX
+#endif
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
@@ -355,7 +368,7 @@ static int test_bit(int nr, const volatile unsigned long *addr);
  */
 static inline unsigned long __ffs(unsigned long word)
 {
-	asm("bsf %1,%0"
+	asm(BSF_PREFIX "bsf %1,%0"
 		: "=r" (word)
 		: "rm" (word));
 	return word;
@@ -369,12 +382,14 @@ static inline unsigned long __ffs(unsigned long word)
  */
 static inline unsigned long ffz(unsigned long word)
 {
-	asm("bsf %1,%0"
+	asm(BSF_PREFIX "bsf %1,%0"
 		: "=r" (word)
 		: "r" (~word));
 	return word;
 }
 
+#undef BSF_PREFIX
+
 /*
  * __fls: find last set bit in word
  * @word: The word to search