From 726328d92a42b6d4b76078e2659f43067f82c4e8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 May 2016 10:35:03 +0200 Subject: 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) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner 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 --- arch/arm/include/asm/spinlock.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'arch/arm/include/asm') diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 0fa418463f49..4bec45442072 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -6,6 +6,8 @@ #endif #include +#include +#include /* * 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) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + 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) -- cgit v1.2.3 From 6da068c1beba684b2a0dbf43a07b0529edd9e959 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 01:10:52 +0200 Subject: locking/atomic, arch/arm: Implement atomic{,64}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}() Implement FETCH-OP atomic primitives, these are very similar to the existing OP-RETURN primitives we already have, except they return the value of the atomic variable _before_ modification. This is especially useful for irreversible operations -- such as bitops (because it becomes impossible to reconstruct the state prior to modification). Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Russell King Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/arm/include/asm/atomic.h | 108 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 98 insertions(+), 10 deletions(-) (limited to 'arch/arm/include/asm') diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 9e10c4567eb4..0feb110ec542 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -77,8 +77,36 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v) \ return result; \ } +#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ +static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ +{ \ + unsigned long tmp; \ + int result, val; \ + \ + prefetchw(&v->counter); \ + \ + __asm__ __volatile__("@ atomic_fetch_" #op "\n" \ +"1: ldrex %0, [%4]\n" \ +" " #asm_op " %1, %0, %5\n" \ +" strex %2, %1, [%4]\n" \ +" teq %2, #0\n" \ +" bne 1b" \ + : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Qo" (v->counter) \ + : "r" (&v->counter), "Ir" (i) \ + : "cc"); \ + \ + return result; \ +} + #define atomic_add_return_relaxed atomic_add_return_relaxed #define atomic_sub_return_relaxed atomic_sub_return_relaxed +#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed +#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed + +#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed +#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed +#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new) { @@ -159,6 +187,22 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ return val; \ } +#define ATOMIC_FETCH_OP(op, c_op, asm_op) \ +static inline int atomic_fetch_##op(int i, atomic_t *v) \ +{ \ + unsigned long flags; \ + int val; \ + \ + raw_local_irq_save(flags); \ + val = v->counter; \ + v->counter c_op i; \ + raw_local_irq_restore(flags); \ + \ + return val; \ +} + +#define atomic_fetch_or atomic_fetch_or + static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; @@ -187,19 +231,26 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) #define ATOMIC_OPS(op, c_op, asm_op) \ ATOMIC_OP(op, c_op, asm_op) \ - ATOMIC_OP_RETURN(op, c_op, asm_op) + ATOMIC_OP_RETURN(op, c_op, asm_op) \ + ATOMIC_FETCH_OP(op, c_op, asm_op) ATOMIC_OPS(add, +=, add) ATOMIC_OPS(sub, -=, sub) #define atomic_andnot atomic_andnot -ATOMIC_OP(and, &=, and) -ATOMIC_OP(andnot, &= ~, bic) -ATOMIC_OP(or, |=, orr) -ATOMIC_OP(xor, ^=, eor) +#undef ATOMIC_OPS +#define ATOMIC_OPS(op, c_op, asm_op) \ + ATOMIC_OP(op, c_op, asm_op) \ + ATOMIC_FETCH_OP(op, c_op, asm_op) + +ATOMIC_OPS(and, &=, and) +ATOMIC_OPS(andnot, &= ~, bic) +ATOMIC_OPS(or, |=, orr) +ATOMIC_OPS(xor, ^=, eor) #undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP @@ -317,24 +368,61 @@ atomic64_##op##_return_relaxed(long long i, atomic64_t *v) \ return result; \ } +#define ATOMIC64_FETCH_OP(op, op1, op2) \ +static inline long long \ +atomic64_fetch_##op##_relaxed(long long i, atomic64_t *v) \ +{ \ + long long result, val; \ + unsigned long tmp; \ + \ + prefetchw(&v->counter); \ + \ + __asm__ __volatile__("@ atomic64_fetch_" #op "\n" \ +"1: ldrexd %0, %H0, [%4]\n" \ +" " #op1 " %Q1, %Q0, %Q5\n" \ +" " #op2 " %R1, %R0, %R5\n" \ +" strexd %2, %1, %H1, [%4]\n" \ +" teq %2, #0\n" \ +" bne 1b" \ + : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Qo" (v->counter) \ + : "r" (&v->counter), "r" (i) \ + : "cc"); \ + \ + return result; \ +} + #define ATOMIC64_OPS(op, op1, op2) \ ATOMIC64_OP(op, op1, op2) \ - ATOMIC64_OP_RETURN(op, op1, op2) + ATOMIC64_OP_RETURN(op, op1, op2) \ + ATOMIC64_FETCH_OP(op, op1, op2) ATOMIC64_OPS(add, adds, adc) ATOMIC64_OPS(sub, subs, sbc) #define atomic64_add_return_relaxed atomic64_add_return_relaxed #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed +#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed + +#undef ATOMIC64_OPS +#define ATOMIC64_OPS(op, op1, op2) \ + ATOMIC64_OP(op, op1, op2) \ + ATOMIC64_FETCH_OP(op, op1, op2) #define atomic64_andnot atomic64_andnot -ATOMIC64_OP(and, and, and) -ATOMIC64_OP(andnot, bic, bic) -ATOMIC64_OP(or, orr, orr) -ATOMIC64_OP(xor, eor, eor) +ATOMIC64_OPS(and, and, and) +ATOMIC64_OPS(andnot, bic, bic) +ATOMIC64_OPS(or, orr, orr) +ATOMIC64_OPS(xor, eor, eor) + +#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed +#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed +#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed #undef ATOMIC64_OPS +#undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP -- cgit v1.2.3 From b53d6bedbe781974097fd8c38263f6cc78ff9ea7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 00:58:25 +0200 Subject: locking/atomic: Remove linux/atomic.h:atomic_fetch_or() Since all architectures have this implemented now natively, remove this dead code. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/arm/include/asm/atomic.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/arm/include/asm') diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 0feb110ec542..66d0e215a773 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -201,8 +201,6 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ return val; \ } -#define atomic_fetch_or atomic_fetch_or - static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; -- cgit v1.2.3