[PATCH RFC] x86: avoid atomic operation in test_and_set_bit_lock if possible

[Nikanth Karthikesan <knikanth@suse.de>]

On x86_64 SMP with lots of CPU atomic instructions which assert the LOCK #
signal can stall other CPUs. And as the number of cores increase this penalty
scales proportionately. So it is best to try and avoid atomic instructions
wherever possible. test_and_set_bit_lock() can avoid using LOCK_PREFIX if it
finds the bit set already.

Signed-off-by: Nikanth Karthikesan <knikanth@suse.de>

---

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 903683b..26a42ff 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -203,19 +203,6 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
 }
 
 /**
- * test_and_set_bit_lock - Set a bit and return its old value for lock
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This is the same as test_and_set_bit on x86.
- */
-static __always_inline int
-test_and_set_bit_lock(int nr, volatile unsigned long *addr)
-{
-	return test_and_set_bit(nr, addr);
-}
-
-/**
  * __test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
@@ -339,6 +326,25 @@ static int test_bit(int nr, const volatile unsigned long *addr);
 	 : variable_test_bit((nr), (addr)))
 
 /**
+ * test_and_set_bit_lock - Set a bit and return its old value for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This is the same as test_and_set_bit on x86. But atomic operation is
+ * avoided, if the bit was already set.
+ */
+static __always_inline int
+test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+{
+#ifdef CONFIG_SMP
+	barrier();
+	if (test_bit(nr, addr))
+		return 1;
+#endif
+	return test_and_set_bit(nr, addr);
+}
+
+/**
  * __ffs - find first set bit in word
  * @word: The word to search
  *