2012-03-05 18:49:29 +07:00
|
|
|
/*
|
|
|
|
|
* Based on arch/arm/include/asm/atomic.h
|
|
|
|
|
*
|
|
|
|
|
* Copyright (C) 1996 Russell King.
|
|
|
|
|
* Copyright (C) 2002 Deep Blue Solutions Ltd.
|
|
|
|
|
* Copyright (C) 2012 ARM Ltd.
|
|
|
|
|
*
|
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
|
*
|
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
|
*
|
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef __ASM_ATOMIC_H
|
|
|
|
|
#define __ASM_ATOMIC_H
|
|
|
|
|
|
|
|
|
|
#include <linux/compiler.h>
|
|
|
|
|
#include <linux/types.h>
|
|
|
|
|
|
|
|
|
|
#include <asm/barrier.h>
|
|
|
|
|
#include <asm/cmpxchg.h>
|
|
|
|
|
|
|
|
|
|
#define ATOMIC_INIT(i) { (i) }
|
|
|
|
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* On ARM, ordinary assignment (str instruction) doesn't clear the local
|
|
|
|
|
* strex/ldrex monitor on some implementations. The reason we can use it for
|
|
|
|
|
* atomic_set() is the clrex or dummy strex done on every exception return.
|
|
|
|
|
*/
|
2014-09-23 21:29:50 +07:00
|
|
|
#define atomic_read(v) ACCESS_ONCE((v)->counter)
|
2012-03-05 18:49:29 +07:00
|
|
|
#define atomic_set(v,i) (((v)->counter) = (i))
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* AArch64 UP and SMP safe atomic ops. We use load exclusive and
|
|
|
|
|
* store exclusive to ensure that these are atomic. We may loop
|
|
|
|
|
* to ensure that the update happens.
|
|
|
|
|
*/
|
|
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
#define ATOMIC_OP(op, asm_op) \
|
|
|
|
|
static inline void atomic_##op(int i, atomic_t *v) \
|
|
|
|
|
{ \
|
|
|
|
|
unsigned long tmp; \
|
|
|
|
|
int result; \
|
|
|
|
|
\
|
|
|
|
|
asm volatile("// atomic_" #op "\n" \
|
|
|
|
|
"1: ldxr %w0, %2\n" \
|
|
|
|
|
" " #asm_op " %w0, %w0, %w3\n" \
|
|
|
|
|
" stxr %w1, %w0, %2\n" \
|
|
|
|
|
" cbnz %w1, 1b" \
|
|
|
|
|
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
|
|
|
|
|
: "Ir" (i)); \
|
|
|
|
|
} \
|
|
|
|
|
|
|
|
|
|
#define ATOMIC_OP_RETURN(op, asm_op) \
|
|
|
|
|
static inline int atomic_##op##_return(int i, atomic_t *v) \
|
|
|
|
|
{ \
|
|
|
|
|
unsigned long tmp; \
|
|
|
|
|
int result; \
|
|
|
|
|
\
|
|
|
|
|
asm volatile("// atomic_" #op "_return\n" \
|
|
|
|
|
"1: ldxr %w0, %2\n" \
|
|
|
|
|
" " #asm_op " %w0, %w0, %w3\n" \
|
|
|
|
|
" stlxr %w1, %w0, %2\n" \
|
|
|
|
|
" cbnz %w1, 1b" \
|
|
|
|
|
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
|
|
|
|
|
: "Ir" (i) \
|
|
|
|
|
: "memory"); \
|
|
|
|
|
\
|
|
|
|
|
smp_mb(); \
|
|
|
|
|
return result; \
|
2012-03-05 18:49:29 +07:00
|
|
|
}
|
|
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
#define ATOMIC_OPS(op, asm_op) \
|
|
|
|
|
ATOMIC_OP(op, asm_op) \
|
|
|
|
|
ATOMIC_OP_RETURN(op, asm_op)
|
2012-03-05 18:49:29 +07:00
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
ATOMIC_OPS(add, add)
|
|
|
|
|
ATOMIC_OPS(sub, sub)
|
2012-03-05 18:49:29 +07:00
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
#undef ATOMIC_OPS
|
|
|
|
|
#undef ATOMIC_OP_RETURN
|
|
|
|
|
#undef ATOMIC_OP
|
2012-03-05 18:49:29 +07:00
|
|
|
|
|
|
|
|
static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
|
|
|
|
|
{
|
|
|
|
|
unsigned long tmp;
|
|
|
|
|
int oldval;
|
|
|
|
|
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
smp_mb();
|
|
|
|
|
|
2012-03-05 18:49:29 +07:00
|
|
|
asm volatile("// atomic_cmpxchg\n"
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
"1: ldxr %w1, %2\n"
|
2013-02-04 19:12:33 +07:00
|
|
|
" cmp %w1, %w3\n"
|
2012-03-05 18:49:29 +07:00
|
|
|
" b.ne 2f\n"
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
" stxr %w0, %w4, %2\n"
|
2012-03-05 18:49:29 +07:00
|
|
|
" cbnz %w0, 1b\n"
|
|
|
|
|
"2:"
|
2013-02-04 19:12:33 +07:00
|
|
|
: "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
|
|
|
|
|
: "Ir" (old), "r" (new)
|
2014-02-04 19:29:13 +07:00
|
|
|
: "cc");
|
2012-03-05 18:49:29 +07:00
|
|
|
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
smp_mb();
|
2012-03-05 18:49:29 +07:00
|
|
|
return oldval;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
|
|
|
|
|
|
|
|
|
|
static inline int __atomic_add_unless(atomic_t *v, int a, int u)
|
|
|
|
|
{
|
|
|
|
|
int c, old;
|
|
|
|
|
|
|
|
|
|
c = atomic_read(v);
|
|
|
|
|
while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
|
|
|
|
|
c = old;
|
|
|
|
|
return c;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define atomic_inc(v) atomic_add(1, v)
|
|
|
|
|
#define atomic_dec(v) atomic_sub(1, v)
|
|
|
|
|
|
|
|
|
|
#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
|
|
|
|
|
#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
|
|
|
|
|
#define atomic_inc_return(v) (atomic_add_return(1, v))
|
|
|
|
|
#define atomic_dec_return(v) (atomic_sub_return(1, v))
|
|
|
|
|
#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
|
|
|
|
|
|
|
|
|
|
#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* 64-bit atomic operations.
|
|
|
|
|
*/
|
|
|
|
|
#define ATOMIC64_INIT(i) { (i) }
|
|
|
|
|
|
2014-09-23 21:29:50 +07:00
|
|
|
#define atomic64_read(v) ACCESS_ONCE((v)->counter)
|
2012-03-05 18:49:29 +07:00
|
|
|
#define atomic64_set(v,i) (((v)->counter) = (i))
|
|
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
#define ATOMIC64_OP(op, asm_op) \
|
|
|
|
|
static inline void atomic64_##op(long i, atomic64_t *v) \
|
|
|
|
|
{ \
|
|
|
|
|
long result; \
|
|
|
|
|
unsigned long tmp; \
|
|
|
|
|
\
|
|
|
|
|
asm volatile("// atomic64_" #op "\n" \
|
|
|
|
|
"1: ldxr %0, %2\n" \
|
|
|
|
|
" " #asm_op " %0, %0, %3\n" \
|
|
|
|
|
" stxr %w1, %0, %2\n" \
|
|
|
|
|
" cbnz %w1, 1b" \
|
|
|
|
|
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
|
|
|
|
|
: "Ir" (i)); \
|
|
|
|
|
} \
|
|
|
|
|
|
|
|
|
|
#define ATOMIC64_OP_RETURN(op, asm_op) \
|
|
|
|
|
static inline long atomic64_##op##_return(long i, atomic64_t *v) \
|
|
|
|
|
{ \
|
|
|
|
|
long result; \
|
|
|
|
|
unsigned long tmp; \
|
|
|
|
|
\
|
|
|
|
|
asm volatile("// atomic64_" #op "_return\n" \
|
|
|
|
|
"1: ldxr %0, %2\n" \
|
|
|
|
|
" " #asm_op " %0, %0, %3\n" \
|
|
|
|
|
" stlxr %w1, %0, %2\n" \
|
|
|
|
|
" cbnz %w1, 1b" \
|
|
|
|
|
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \
|
|
|
|
|
: "Ir" (i) \
|
|
|
|
|
: "memory"); \
|
|
|
|
|
\
|
|
|
|
|
smp_mb(); \
|
|
|
|
|
return result; \
|
2012-03-05 18:49:29 +07:00
|
|
|
}
|
|
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
#define ATOMIC64_OPS(op, asm_op) \
|
|
|
|
|
ATOMIC64_OP(op, asm_op) \
|
|
|
|
|
ATOMIC64_OP_RETURN(op, asm_op)
|
2012-03-05 18:49:29 +07:00
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
ATOMIC64_OPS(add, add)
|
|
|
|
|
ATOMIC64_OPS(sub, sub)
|
2012-03-05 18:49:29 +07:00
|
|
|
|
2014-03-23 22:57:20 +07:00
|
|
|
#undef ATOMIC64_OPS
|
|
|
|
|
#undef ATOMIC64_OP_RETURN
|
|
|
|
|
#undef ATOMIC64_OP
|
2012-03-05 18:49:29 +07:00
|
|
|
|
|
|
|
|
static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new)
|
|
|
|
|
{
|
|
|
|
|
long oldval;
|
|
|
|
|
unsigned long res;
|
|
|
|
|
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
smp_mb();
|
|
|
|
|
|
2012-03-05 18:49:29 +07:00
|
|
|
asm volatile("// atomic64_cmpxchg\n"
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
"1: ldxr %1, %2\n"
|
2013-02-04 19:12:33 +07:00
|
|
|
" cmp %1, %3\n"
|
2012-03-05 18:49:29 +07:00
|
|
|
" b.ne 2f\n"
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
" stxr %w0, %4, %2\n"
|
2012-03-05 18:49:29 +07:00
|
|
|
" cbnz %w0, 1b\n"
|
|
|
|
|
"2:"
|
2013-02-04 19:12:33 +07:00
|
|
|
: "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
|
|
|
|
|
: "Ir" (old), "r" (new)
|
2014-02-04 19:29:13 +07:00
|
|
|
: "cc");
|
2012-03-05 18:49:29 +07:00
|
|
|
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
smp_mb();
|
2012-03-05 18:49:29 +07:00
|
|
|
return oldval;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
|
|
|
|
|
|
|
|
|
|
static inline long atomic64_dec_if_positive(atomic64_t *v)
|
|
|
|
|
{
|
|
|
|
|
long result;
|
|
|
|
|
unsigned long tmp;
|
|
|
|
|
|
|
|
|
|
asm volatile("// atomic64_dec_if_positive\n"
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
"1: ldxr %0, %2\n"
|
2012-03-05 18:49:29 +07:00
|
|
|
" subs %0, %0, #1\n"
|
|
|
|
|
" b.mi 2f\n"
|
2013-02-04 19:12:33 +07:00
|
|
|
" stlxr %w1, %0, %2\n"
|
2012-03-05 18:49:29 +07:00
|
|
|
" cbnz %w1, 1b\n"
|
arm64: atomics: fix use of acquire + release for full barrier semantics
Linux requires a number of atomic operations to provide full barrier
semantics, that is no memory accesses after the operation can be
observed before any accesses up to and including the operation in
program order.
On arm64, these operations have been incorrectly implemented as follows:
// A, B, C are independent memory locations
<Access [A]>
// atomic_op (B)
1: ldaxr x0, [B] // Exclusive load with acquire
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
<Access [C]>
The assumption here being that two half barriers are equivalent to a
full barrier, so the only permitted ordering would be A -> B -> C
(where B is the atomic operation involving both a load and a store).
Unfortunately, this is not the case by the letter of the architecture
and, in fact, the accesses to A and C are permitted to pass their
nearest half barrier resulting in orderings such as Bl -> A -> C -> Bs
or Bl -> C -> A -> Bs (where Bl is the load-acquire on B and Bs is the
store-release on B). This is a clear violation of the full barrier
requirement.
The simple way to fix this is to implement the same algorithm as ARMv7
using explicit barriers:
<Access [A]>
// atomic_op (B)
dmb ish // Full barrier
1: ldxr x0, [B] // Exclusive load
<op(B)>
stxr w1, x0, [B] // Exclusive store
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
but this has the undesirable effect of introducing *two* full barrier
instructions. A better approach is actually the following, non-intuitive
sequence:
<Access [A]>
// atomic_op (B)
1: ldxr x0, [B] // Exclusive load
<op(B)>
stlxr w1, x0, [B] // Exclusive store with release
cbnz w1, 1b
dmb ish // Full barrier
<Access [C]>
The simple observations here are:
- The dmb ensures that no subsequent accesses (e.g. the access to C)
can enter or pass the atomic sequence.
- The dmb also ensures that no prior accesses (e.g. the access to A)
can pass the atomic sequence.
- Therefore, no prior access can pass a subsequent access, or
vice-versa (i.e. A is strictly ordered before C).
- The stlxr ensures that no prior access can pass the store component
of the atomic operation.
The only tricky part remaining is the ordering between the ldxr and the
access to A, since the absence of the first dmb means that we're now
permitting re-ordering between the ldxr and any prior accesses.
From an (arbitrary) observer's point of view, there are two scenarios:
1. We have observed the ldxr. This means that if we perform a store to
[B], the ldxr will still return older data. If we can observe the
ldxr, then we can potentially observe the permitted re-ordering
with the access to A, which is clearly an issue when compared to
the dmb variant of the code. Thankfully, the exclusive monitor will
save us here since it will be cleared as a result of the store and
the ldxr will retry. Notice that any use of a later memory
observation to imply observation of the ldxr will also imply
observation of the access to A, since the stlxr/dmb ensure strict
ordering.
2. We have not observed the ldxr. This means we can perform a store
and influence the later ldxr. However, that doesn't actually tell
us anything about the access to [A], so we've not lost anything
here either when compared to the dmb variant.
This patch implements this solution for our barriered atomic operations,
ensuring that we satisfy the full barrier requirements where they are
needed.
Cc: <stable@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
2014-02-04 19:29:12 +07:00
|
|
|
" dmb ish\n"
|
2012-03-05 18:49:29 +07:00
|
|
|
"2:"
|
2013-02-04 19:12:33 +07:00
|
|
|
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
|
|
|
|
|
:
|
|
|
|
|
: "cc", "memory");
|
2012-03-05 18:49:29 +07:00
|
|
|
|
|
|
|
|
return result;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
|
|
|
|
|
{
|
|
|
|
|
long c, old;
|
|
|
|
|
|
|
|
|
|
c = atomic64_read(v);
|
|
|
|
|
while (c != u && (old = atomic64_cmpxchg((v), c, c + a)) != c)
|
|
|
|
|
c = old;
|
|
|
|
|
|
|
|
|
|
return c != u;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
|
|
|
|
|
#define atomic64_inc(v) atomic64_add(1LL, (v))
|
|
|
|
|
#define atomic64_inc_return(v) atomic64_add_return(1LL, (v))
|
|
|
|
|
#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
|
|
|
|
|
#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
|
|
|
|
|
#define atomic64_dec(v) atomic64_sub(1LL, (v))
|
|
|
|
|
#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v))
|
|
|
|
|
#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
|
|
|
|
|
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)
|
|
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
#endif
|