From 12d560f4ea87030667438a169912380be00cea4b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 14 Jul 2015 18:35:23 -0700 Subject: [PATCH] rcu,locking: Privatize smp_mb__after_unlock_lock() RCU is the only thing that uses smp_mb__after_unlock_lock(), and is likely the only thing that ever will use it, so this commit makes this macro private to RCU. Signed-off-by: Paul E. McKenney Cc: Will Deacon Cc: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: "linux-arch@vger.kernel.org" --- Documentation/memory-barriers.txt | 71 ++--------------------------- arch/powerpc/include/asm/spinlock.h | 2 - include/linux/spinlock.h | 10 ---- kernel/rcu/tree.h | 12 +++++ 4 files changed, 16 insertions(+), 79 deletions(-) diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 318523872db5..eafa6a53f72c 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1854,16 +1854,10 @@ RELEASE are to the same lock variable, but only from the perspective of another CPU not holding that lock. In short, a ACQUIRE followed by an RELEASE may -not- be assumed to be a full memory barrier. -Similarly, the reverse case of a RELEASE followed by an ACQUIRE does not -imply a full memory barrier. If it is necessary for a RELEASE-ACQUIRE -pair to produce a full barrier, the ACQUIRE can be followed by an -smp_mb__after_unlock_lock() invocation. This will produce a full barrier -(including transitivity) if either (a) the RELEASE and the ACQUIRE are -executed by the same CPU or task, or (b) the RELEASE and ACQUIRE act on -the same variable. The smp_mb__after_unlock_lock() primitive is free -on many architectures. Without smp_mb__after_unlock_lock(), the CPU's -execution of the critical sections corresponding to the RELEASE and the -ACQUIRE can cross, so that: +Similarly, the reverse case of a RELEASE followed by an ACQUIRE does +not imply a full memory barrier. Therefore, the CPU's execution of the +critical sections corresponding to the RELEASE and the ACQUIRE can cross, +so that: *A = a; RELEASE M @@ -1901,29 +1895,6 @@ the RELEASE would simply complete, thereby avoiding the deadlock. a sleep-unlock race, but the locking primitive needs to resolve such races properly in any case. -With smp_mb__after_unlock_lock(), the two critical sections cannot overlap. -For example, with the following code, the store to *A will always be -seen by other CPUs before the store to *B: - - *A = a; - RELEASE M - ACQUIRE N - smp_mb__after_unlock_lock(); - *B = b; - -The operations will always occur in one of the following orders: - - STORE *A, RELEASE, ACQUIRE, smp_mb__after_unlock_lock(), STORE *B - STORE *A, ACQUIRE, RELEASE, smp_mb__after_unlock_lock(), STORE *B - ACQUIRE, STORE *A, RELEASE, smp_mb__after_unlock_lock(), STORE *B - -If the RELEASE and ACQUIRE were instead both operating on the same lock -variable, only the first of these alternatives can occur. In addition, -the more strongly ordered systems may rule out some of the above orders. -But in any case, as noted earlier, the smp_mb__after_unlock_lock() -ensures that the store to *A will always be seen as happening before -the store to *B. - Locks and semaphores may not provide any guarantee of ordering on UP compiled systems, and so cannot be counted on in such a situation to actually achieve anything at all - especially with respect to I/O accesses - unless combined @@ -2154,40 +2125,6 @@ But it won't see any of: *E, *F or *G following RELEASE Q -However, if the following occurs: - - CPU 1 CPU 2 - =============================== =============================== - WRITE_ONCE(*A, a); - ACQUIRE M [1] - WRITE_ONCE(*B, b); - WRITE_ONCE(*C, c); - RELEASE M [1] - WRITE_ONCE(*D, d); WRITE_ONCE(*E, e); - ACQUIRE M [2] - smp_mb__after_unlock_lock(); - WRITE_ONCE(*F, f); - WRITE_ONCE(*G, g); - RELEASE M [2] - WRITE_ONCE(*H, h); - -CPU 3 might see: - - *E, ACQUIRE M [1], *C, *B, *A, RELEASE M [1], - ACQUIRE M [2], *H, *F, *G, RELEASE M [2], *D - -But assuming CPU 1 gets the lock first, CPU 3 won't see any of: - - *B, *C, *D, *F, *G or *H preceding ACQUIRE M [1] - *A, *B or *C following RELEASE M [1] - *F, *G or *H preceding ACQUIRE M [2] - *A, *B, *C, *E, *F or *G following RELEASE M [2] - -Note that the smp_mb__after_unlock_lock() is critically important -here: Without it CPU 3 might see some of the above orderings. -Without smp_mb__after_unlock_lock(), the accesses are not guaranteed -to be seen in order unless CPU 3 holds lock M. - ACQUIRES VS I/O ACCESSES ------------------------ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 4dbe072eecbe..523673d7583c 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -28,8 +28,6 @@ #include #include -#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ - #ifdef CONFIG_PPC64 /* use 0x800000yy when locked, where yy == CPU number */ #ifdef __BIG_ENDIAN__ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 0063b24b4f36..16c5ed5a627c 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -130,16 +130,6 @@ do { \ #define smp_mb__before_spinlock() smp_wmb() #endif -/* - * Place this after a lock-acquisition primitive to guarantee that - * an UNLOCK+LOCK pair act as a full barrier. This guarantee applies - * if the UNLOCK and LOCK are executed by the same CPU or if the - * UNLOCK and LOCK operate on the same lock variable. - */ -#ifndef smp_mb__after_unlock_lock -#define smp_mb__after_unlock_lock() do { } while (0) -#endif - /** * raw_spin_unlock_wait - wait until the spinlock gets unlocked * @lock: the spinlock in question. diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 0412030ca882..2e991f8361e4 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -653,3 +653,15 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ } #endif /* #ifdef CONFIG_RCU_TRACE */ + +/* + * Place this after a lock-acquisition primitive to guarantee that + * an UNLOCK+LOCK pair act as a full barrier. This guarantee applies + * if the UNLOCK and LOCK are executed by the same CPU or if the + * UNLOCK and LOCK operate on the same lock variable. + */ +#ifdef CONFIG_PPC +#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ +#else /* #ifdef CONFIG_PPC */ +#define smp_mb__after_unlock_lock() do { } while (0) +#endif /* #else #ifdef CONFIG_PPC */