linux-kernel - [PATCH v5 1/7] locking/qspinlock: Add ARCH_USE_QUEUED_SPINLOCKS

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sun, 28 Mar 2021 06:30:22 +0000
From:   guoren@...nel.org
To:     guoren@...nel.org
Cc:     linux-riscv@...ts.infradead.org, linux-kernel@...r.kernel.org,
        linux-csky@...r.kernel.org, linux-arch@...r.kernel.org,
        linuxppc-dev@...ts.ozlabs.org, linux-xtensa@...ux-xtensa.org,
        openrisc@...ts.librecores.org, sparclinux@...r.kernel.org,
        Guo Ren <guoren@...ux.alibaba.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Will Deacon <will@...nel.org>, Ingo Molnar <mingo@...hat.com>,
        Waiman Long <longman@...hat.com>,
        Arnd Bergmann <arnd@...db.de>, Anup Patel <anup@...infault.org>
Subject: [PATCH v5 1/7] locking/qspinlock: Add ARCH_USE_QUEUED_SPINLOCKS_XCHG32

From: Guo Ren <guoren@...ux.alibaba.com>

Some architectures don't have sub-word swap atomic instruction,
they only have the full word's one.

The sub-word swap only improve the performance when:
NR_CPUS < 16K
 *  0- 7: locked byte
 *     8: pending
 *  9-15: not used
 * 16-17: tail index
 * 18-31: tail cpu (+1)

The 9-15 bits are wasted to use xchg16 in xchg_tail.

Please let architecture select xchg16/xchg32 to implement
xchg_tail.

Signed-off-by: Guo Ren <guoren@...ux.alibaba.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Will Deacon <will@...nel.org>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Waiman Long <longman@...hat.com>
Cc: Arnd Bergmann <arnd@...db.de>
Cc: Anup Patel <anup@...infault.org>
---
 kernel/Kconfig.locks       |  3 +++
 kernel/locking/qspinlock.c | 46 +++++++++++++++++++++-----------------
 2 files changed, 28 insertions(+), 21 deletions(-)

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 3de8fd11873b..d02f1261f73f 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -239,6 +239,9 @@ config LOCK_SPIN_ON_OWNER
 config ARCH_USE_QUEUED_SPINLOCKS
 	bool
 
+config ARCH_USE_QUEUED_SPINLOCKS_XCHG32
+	bool
+
 config QUEUED_SPINLOCKS
 	def_bool y if ARCH_USE_QUEUED_SPINLOCKS
 	depends on SMP
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index cbff6ba53d56..4bfaa969bd15 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -163,26 +163,6 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
 	WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
 }
 
-/*
- * xchg_tail - Put in the new queue tail code word & retrieve previous one
- * @lock : Pointer to queued spinlock structure
- * @tail : The new queue tail code word
- * Return: The previous queue tail code word
- *
- * xchg(lock, tail), which heads an address dependency
- *
- * p,*,* -> n,*,* ; prev = xchg(lock, node)
- */
-static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
-{
-	/*
-	 * We can use relaxed semantics since the caller ensures that the
-	 * MCS node is properly initialized before updating the tail.
-	 */
-	return (u32)xchg_relaxed(&lock->tail,
-				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
-}
-
 #else /* _Q_PENDING_BITS == 8 */
 
 /**
@@ -206,6 +186,30 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
 {
 	atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val);
 }
+#endif /* _Q_PENDING_BITS == 8 */
+
+#if _Q_PENDING_BITS == 8 && !defined(CONFIG_ARCH_USE_QUEUED_SPINLOCKS_XCHG32)
+/*
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail), which heads an address dependency
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
+{
+	/*
+	 * We can use relaxed semantics since the caller ensures that the
+	 * MCS node is properly initialized before updating the tail.
+	 */
+	return (u32)xchg_relaxed(&lock->tail,
+				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+}
+
+#else
 
 /**
  * xchg_tail - Put in the new queue tail code word & retrieve previous one
@@ -236,7 +240,7 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 	}
 	return old;
 }
-#endif /* _Q_PENDING_BITS == 8 */
+#endif
 
 /**
  * queued_fetch_set_pending_acquire - fetch the whole lock value and set pending
-- 
2.17.1