[PATCH v1 5/5] spinlock: reimplement with atomic one-way barrier builtins

[Gavin Hu <gavin.hu@arm.com>]

The __sync builtin based implementation generates full memory barriers
('dmb ish') on Arm platforms. Using C11 atomic builtins to generate one way
barriers.

Here is the assembly code of __sync_compare_and_swap builtin.
__sync_bool_compare_and_swap(dst, exp, src);
   0x000000000090f1b0 <+16>:    e0 07 40 f9 ldr x0, [sp, #8]
   0x000000000090f1b4 <+20>:    e1 0f 40 79 ldrh    w1, [sp, #6]
   0x000000000090f1b8 <+24>:    e2 0b 40 79 ldrh    w2, [sp, #4]
   0x000000000090f1bc <+28>:    21 3c 00 12 and w1, w1, #0xffff
   0x000000000090f1c0 <+32>:    03 7c 5f 48 ldxrh   w3, [x0]
   0x000000000090f1c4 <+36>:    7f 00 01 6b cmp w3, w1
   0x000000000090f1c8 <+40>:    61 00 00 54 b.ne    0x90f1d4
<rte_atomic16_cmpset+52>  // b.any
   0x000000000090f1cc <+44>:    02 fc 04 48 stlxrh  w4, w2, [x0]
   0x000000000090f1d0 <+48>:    84 ff ff 35 cbnz    w4, 0x90f1c0
<rte_atomic16_cmpset+32>
   0x000000000090f1d4 <+52>:    bf 3b 03 d5 dmb ish
   0x000000000090f1d8 <+56>:    e0 17 9f 1a cset    w0, eq  // eq = none

The benchmarking results showed 3X performance gain on Cavium ThunderX2 and
13% on Qualcomm Falmon and 3.7% on 4-A72 Marvell macchiatobin.
Here is the example test result on TX2:

*** spinlock_autotest without this patch ***
Core [123] Cost Time = 639822 us
Core [124] Cost Time = 633253 us
Core [125] Cost Time = 646030 us
Core [126] Cost Time = 643189 us
Core [127] Cost Time = 647039 us
Total Cost Time = 95433298 us

*** spinlock_autotest with this patch ***
Core [123] Cost Time = 163615 us
Core [124] Cost Time = 166471 us
Core [125] Cost Time = 189044 us
Core [126] Cost Time = 195745 us
Core [127] Cost Time = 78423 us
Total Cost Time = 27339656 us

Signed-off-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
Reviewed-by: Ola Liljedahl <Ola.Liljedahl@arm.com>
Reviewed-by: Steve Capper <Steve.Capper@arm.com>
---
 lib/librte_eal/common/include/arch/arm/rte_spinlock.h | 16 ++++++++++++----
 lib/librte_eal/common/include/generic/rte_spinlock.h  |  2 +-
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/lib/librte_eal/common/include/arch/arm/rte_spinlock.h b/lib/librte_eal/common/include/arch/arm/rte_spinlock.h
index 25d22fd1e..33a6d382f 100644
--- a/lib/librte_eal/common/include/arch/arm/rte_spinlock.h
+++ b/lib/librte_eal/common/include/arch/arm/rte_spinlock.h
@@ -19,21 +19,29 @@ extern "C" {
 static inline void
 rte_spinlock_lock(rte_spinlock_t *sl)
 {
-	while (__sync_lock_test_and_set(&sl->locked, 1))
-		while (sl->locked)
+	int exp = 0;
+
+	while (!__atomic_compare_exchange_n(&sl->locked, &exp, 1, 1,
+				__ATOMIC_ACQUIRE, __ATOMIC_RELAXED)) {
+		while (__atomic_load_n(&sl->locked, __ATOMIC_RELAXED))
 			rte_pause();
+		exp = 0;
+	}
 }
 
 static inline void
 rte_spinlock_unlock(rte_spinlock_t *sl)
 {
-	__sync_lock_release(&sl->locked);
+	__atomic_store_n(&sl->locked, 0, __ATOMIC_RELEASE);
 }
 
 static inline int
 rte_spinlock_trylock(rte_spinlock_t *sl)
 {
-	return __sync_lock_test_and_set(&sl->locked, 1) == 0;
+	int exp = 0;
+	return __atomic_compare_exchange_n(&sl->locked, &exp, 1,
+				false, /* disallow spurious failure */
+				__ATOMIC_ACQUIRE, __ATOMIC_RELAXED);
 }
 
 static inline int rte_tm_supported(void)
diff --git a/lib/librte_eal/common/include/generic/rte_spinlock.h b/lib/librte_eal/common/include/generic/rte_spinlock.h
index e555ecb95..a8cc75adc 100644
--- a/lib/librte_eal/common/include/generic/rte_spinlock.h
+++ b/lib/librte_eal/common/include/generic/rte_spinlock.h
@@ -87,7 +87,7 @@ rte_spinlock_trylock (rte_spinlock_t *sl);
  */
 static inline int rte_spinlock_is_locked (rte_spinlock_t *sl)
 {
-	return sl->locked;
+	return __atomic_load_n(&sl->locked, __ATOMIC_ACQUIRE);
 }
 
 /**
-- 
2.11.0