locking/spinlock, arch: Update and fix spin_unlock_wait() implementations

This patch updates/fixes all spin_unlock_wait() implementations.

The update is in semantics; where it previously was only a control
dependency, we now upgrade to a full load-acquire to match the
store-release from the spin_unlock() we waited on. This ensures that
when spin_unlock_wait() returns, we're guaranteed to observe the full
critical section we waited on.

This fixes a number of spin_unlock_wait() users that (not
unreasonably) rely on this.

I also fixed a number of ticket lock versions to only wait on the
current lock holder, instead of for a full unlock, as this is
sufficient.

Furthermore; again for ticket locks; I added an smp_rmb() in between
the initial ticket load and the spin loop testing the current value
because I could not convince myself the address dependency is
sufficient, esp. if the loads are of different sizes.

I'm more than happy to remove this smp_rmb() again if people are
certain the address dependency does indeed work as expected.

Note: PPC32 will be fixed independently

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: chris@zankel.net
Cc: cmetcalf@mellanox.com
Cc: davem@davemloft.net
Cc: dhowells@redhat.com
Cc: james.hogan@imgtec.com
Cc: jejb@parisc-linux.org
Cc: linux@armlinux.org.uk
Cc: mpe@ellerman.id.au
Cc: ralf@linux-mips.org
Cc: realmz6@gmail.com
Cc: rkuo@codeaurora.org
Cc: rth@twiddle.net
Cc: schwidefsky@de.ibm.com
Cc: tony.luck@intel.com
Cc: vgupta@synopsys.com
Cc: ysato@users.sourceforge.jp
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/alpha/include/asm/spinlock.h

@@ -3,6 +3,8 @@
 
 #include <linux/kernel.h>
 #include <asm/current.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
@@ -13,8 +15,11 @@
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 #define arch_spin_is_locked(x)	((x)->lock != 0)
-#define arch_spin_unlock_wait(x) \
+
-		do { cpu_relax(); } while ((x)->lock)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {

arch/arc/include/asm/spinlock.h

@@ -15,8 +15,11 @@
 
 #define arch_spin_is_locked(x)	((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__)
 #define arch_spin_lock_flags(lock, flags)	arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
+
-	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, !VAL);
+}
 
 #ifdef CONFIG_ARC_HAS_LLSC
 

arch/arm/include/asm/spinlock.h

@@ -6,6 +6,8 @@
 #endif
 
 #include <linux/prefetch.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
@@ -50,8 +52,21 @@ static inline void dsb_sev(void)
  * memory.
  */
 
-#define arch_spin_unlock_wait(lock) \
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+{
+	u16 owner = READ_ONCE(lock->tickets.owner);
+
+	for (;;) {
+		arch_spinlock_t tmp = READ_ONCE(*lock);
+
+		if (tmp.tickets.owner == tmp.tickets.next ||
+		    tmp.tickets.owner != owner)
+			break;
+
+		wfe();
+	}
+	smp_acquire__after_ctrl_dep();
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 

arch/blackfin/include/asm/spinlock.h

@@ -12,6 +12,8 @@
 #else
 
 #include <linux/atomic.h>
+#include <asm/processor.h>
+#include <asm/barrier.h>
 
 asmlinkage int __raw_spin_is_locked_asm(volatile int *ptr);
 asmlinkage void __raw_spin_lock_asm(volatile int *ptr);
@@ -48,8 +50,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
-	while (arch_spin_is_locked(lock))
+	smp_cond_load_acquire(&lock->lock, !VAL);
-		cpu_relax();
 }
 
 static inline int arch_read_can_lock(arch_rwlock_t *rw)

arch/hexagon/include/asm/spinlock.h

@@ -23,6 +23,8 @@
 #define _ASM_SPINLOCK_H
 
 #include <asm/irqflags.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * This file is pulled in for SMP builds.
@@ -176,8 +178,12 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock)
  * SMP spinlocks are intended to allow only a single CPU at the lock
  */
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(lock) \
+
-	do {while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
+
 #define arch_spin_is_locked(x) ((x)->lock != 0)
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)

arch/ia64/include/asm/spinlock.h

@@ -15,6 +15,8 @@
 
 #include <linux/atomic.h>
 #include <asm/intrinsics.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 #define arch_spin_lock_init(x)			((x)->lock = 0)
 
@@ -86,6 +88,8 @@ static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock)
 			return;
 		cpu_relax();
 	}
+
+	smp_acquire__after_ctrl_dep();
 }
 
 static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)

arch/m32r/include/asm/spinlock.h

@@ -13,6 +13,8 @@
 #include <linux/atomic.h>
 #include <asm/dcache_clear.h>
 #include <asm/page.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
@@ -27,8 +29,11 @@
 
 #define arch_spin_is_locked(x)		(*(volatile int *)(&(x)->slock) <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
+
-		do { cpu_relax(); } while (arch_spin_is_locked(x))
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, VAL > 0);
+}
 
 /**
  * arch_spin_trylock - Try spin lock and return a result

arch/metag/include/asm/spinlock.h

@@ -1,14 +1,24 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
 #ifdef CONFIG_METAG_ATOMICITY_LOCK1
 #include <asm/spinlock_lock1.h>
 #else
 #include <asm/spinlock_lnkget.h>
 #endif
 
-#define arch_spin_unlock_wait(lock) \
+/*
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+ * both lock1 and lnkget are test-and-set spinlocks with 0 unlocked and 1
+ * locked.
+ */
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 

arch/mips/include/asm/spinlock.h

@@ -12,6 +12,7 @@
 #include <linux/compiler.h>
 
 #include <asm/barrier.h>
+#include <asm/processor.h>
 #include <asm/compiler.h>
 #include <asm/war.h>
 
@@ -48,8 +49,22 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 }
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
+
-	while (arch_spin_is_locked(x)) { cpu_relax(); }
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	u16 owner = READ_ONCE(lock->h.serving_now);
+	smp_rmb();
+	for (;;) {
+		arch_spinlock_t tmp = READ_ONCE(*lock);
+
+		if (tmp.h.serving_now == tmp.h.ticket ||
+		    tmp.h.serving_now != owner)
+			break;
+
+		cpu_relax();
+	}
+	smp_acquire__after_ctrl_dep();
+}
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {

arch/mn10300/include/asm/spinlock.h

@@ -12,6 +12,8 @@
 #define _ASM_SPINLOCK_H
 
 #include <linux/atomic.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 #include <asm/rwlock.h>
 #include <asm/page.h>
 
@@ -23,7 +25,11 @@
  */
 
 #define arch_spin_is_locked(x)	(*(volatile signed char *)(&(x)->slock) != 0)
-#define arch_spin_unlock_wait(x) do { barrier(); } while (arch_spin_is_locked(x))
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, !VAL);
+}
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {

arch/parisc/include/asm/spinlock.h

@@ -13,8 +13,13 @@ static inline int arch_spin_is_locked(arch_spinlock_t *x)
 }
 
 #define arch_spin_lock(lock) arch_spin_lock_flags(lock, 0)
-#define arch_spin_unlock_wait(x) \
+
-		do { cpu_relax(); } while (arch_spin_is_locked(x))
+static inline void arch_spin_unlock_wait(arch_spinlock_t *x)
+{
+	volatile unsigned int *a = __ldcw_align(x);
+
+	smp_cond_load_acquire(a, VAL);
+}
 
 static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 					 unsigned long flags)

arch/s390/include/asm/spinlock.h

@@ -10,6 +10,8 @@
 #define __ASM_SPINLOCK_H
 
 #include <linux/smp.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
 
 #define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval)
 
@@ -97,6 +99,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	while (arch_spin_is_locked(lock))
 		arch_spin_relax(lock);
+	smp_acquire__after_ctrl_dep();
 }
 
 /*

arch/sh/include/asm/spinlock.h

@@ -19,14 +19,20 @@
 #error "Need movli.l/movco.l for spinlocks"
 #endif
 
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  */
 
 #define arch_spin_is_locked(x)		((x)->lock <= 0)
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
+
-	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->lock, VAL > 0);
+}
 
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's

arch/sparc/include/asm/spinlock_32.h

@@ -9,12 +9,15 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/psr.h>
+#include <asm/barrier.h>
 #include <asm/processor.h> /* for cpu_relax */
 
 #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0)
 
-#define arch_spin_unlock_wait(lock) \
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+{
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {

arch/sparc/include/asm/spinlock_64.h

@@ -8,6 +8,9 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/processor.h>
+#include <asm/barrier.h>
+
 /* To get debugging spinlocks which detect and catch
  * deadlock situations, set CONFIG_DEBUG_SPINLOCK
  * and rebuild your kernel.
@@ -23,9 +26,10 @@
 
 #define arch_spin_is_locked(lp)	((lp)->lock != 0)
 
-#define arch_spin_unlock_wait(lp)	\
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-	do {	rmb();			\
+{
-	} while((lp)->lock)
+	smp_cond_load_acquire(&lock->lock, !VAL);
+}
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {

arch/tile/lib/spinlock_32.c

@@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	do {
 		delay_backoff(iterations++);
 	} while (READ_ONCE(lock->current_ticket) == curr);
+
+	/*
+	 * The TILE architecture doesn't do read speculation; therefore
+	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
+	 */
+	barrier();
 }
 EXPORT_SYMBOL(arch_spin_unlock_wait);
 

arch/tile/lib/spinlock_64.c

@@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	do {
 		delay_backoff(iterations++);
 	} while (arch_spin_current(READ_ONCE(lock->lock)) == curr);
+
+	/*
+	 * The TILE architecture doesn't do read speculation; therefore
+	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
+	 */
+	barrier();
 }
 EXPORT_SYMBOL(arch_spin_unlock_wait);
 

arch/xtensa/include/asm/spinlock.h

@@ -11,6 +11,9 @@
 #ifndef _XTENSA_SPINLOCK_H
 #define _XTENSA_SPINLOCK_H
 
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
 /*
  * spinlock
  *
@@ -29,8 +32,11 @@
  */
 
 #define arch_spin_is_locked(x) ((x)->slock != 0)
-#define arch_spin_unlock_wait(lock) \
+
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, !VAL);
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 

include/asm-generic/barrier.h

@@ -194,7 +194,7 @@ do {									\
 })
 #endif
 
-#endif
+#endif	/* CONFIG_SMP */
 
 /* Barriers for virtual machine guests when talking to an SMP host */
 #define virt_mb() __smp_mb()

include/linux/spinlock_up.h

@@ -6,6 +6,7 @@
 #endif
 
 #include <asm/processor.h>	/* for cpu_relax() */
+#include <asm/barrier.h>
 
 /*
  * include/linux/spinlock_up.h - UP-debug version of spinlocks.
@@ -25,6 +26,11 @@
 #ifdef CONFIG_DEBUG_SPINLOCK
 #define arch_spin_is_locked(x)		((x)->slock == 0)
 
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	smp_cond_load_acquire(&lock->slock, VAL);
+}
+
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	lock->slock = 0;
@@ -67,6 +73,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 
 #else /* DEBUG_SPINLOCK */
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
+#define arch_spin_unlock_wait(lock)	do { barrier(); (void)(lock); } while (0)
 /* for sched/core.c and kernel_lock.c: */
 # define arch_spin_lock(lock)		do { barrier(); (void)(lock); } while (0)
 # define arch_spin_lock_flags(lock, flags)	do { barrier(); (void)(lock); } while (0)
@@ -79,7 +86,4 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 #define arch_read_can_lock(lock)	(((void)(lock), 1))
 #define arch_write_can_lock(lock)	(((void)(lock), 1))
 
-#define arch_spin_unlock_wait(lock) \
-		do { cpu_relax(); } while (arch_spin_is_locked(lock))
-
 #endif /* __LINUX_SPINLOCK_UP_H */