2017-07-11 08:02:19 +07:00
|
|
|
/*
|
|
|
|
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
|
|
|
|
* Copyright (C) 2012 Regents of the University of California
|
|
|
|
* Copyright (C) 2017 SiFive
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public Licence
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the Licence, or (at your option) any later version.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _ASM_RISCV_ATOMIC_H
|
|
|
|
#define _ASM_RISCV_ATOMIC_H
|
|
|
|
|
|
|
|
#ifdef CONFIG_GENERIC_ATOMIC64
|
|
|
|
# include <asm-generic/atomic64.h>
|
|
|
|
#else
|
|
|
|
# if (__riscv_xlen < 64)
|
|
|
|
# error "64-bit atomics require XLEN to be at least 64"
|
|
|
|
# endif
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include <asm/cmpxchg.h>
|
|
|
|
#include <asm/barrier.h>
|
|
|
|
|
|
|
|
#define ATOMIC_INIT(i) { (i) }
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
|
2018-07-16 18:30:11 +07:00
|
|
|
#define __atomic_acquire_fence() \
|
|
|
|
__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
|
|
|
|
|
|
|
|
#define __atomic_release_fence() \
|
|
|
|
__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
|
2017-07-11 08:02:19 +07:00
|
|
|
static __always_inline int atomic_read(const atomic_t *v)
|
|
|
|
{
|
|
|
|
return READ_ONCE(v->counter);
|
|
|
|
}
|
|
|
|
static __always_inline void atomic_set(atomic_t *v, int i)
|
|
|
|
{
|
|
|
|
WRITE_ONCE(v->counter, i);
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifndef CONFIG_GENERIC_ATOMIC64
|
|
|
|
#define ATOMIC64_INIT(i) { (i) }
|
|
|
|
static __always_inline long atomic64_read(const atomic64_t *v)
|
|
|
|
{
|
|
|
|
return READ_ONCE(v->counter);
|
|
|
|
}
|
|
|
|
static __always_inline void atomic64_set(atomic64_t *v, long i)
|
|
|
|
{
|
|
|
|
WRITE_ONCE(v->counter, i);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* First, the atomic ops that have no ordering constraints and therefor don't
|
|
|
|
* have the AQ or RL bits set. These don't return anything, so there's only
|
|
|
|
* one version to worry about.
|
|
|
|
*/
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix) \
|
|
|
|
static __always_inline \
|
|
|
|
void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
|
|
|
|
{ \
|
|
|
|
__asm__ __volatile__ ( \
|
|
|
|
" amo" #asm_op "." #asm_type " zero, %1, %0" \
|
|
|
|
: "+A" (v->counter) \
|
|
|
|
: "r" (I) \
|
|
|
|
: "memory"); \
|
|
|
|
} \
|
2017-07-11 08:02:19 +07:00
|
|
|
|
|
|
|
#ifdef CONFIG_GENERIC_ATOMIC64
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS(op, asm_op, I) \
|
2017-11-15 02:35:37 +07:00
|
|
|
ATOMIC_OP (op, asm_op, I, w, int, )
|
2017-07-11 08:02:19 +07:00
|
|
|
#else
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS(op, asm_op, I) \
|
|
|
|
ATOMIC_OP (op, asm_op, I, w, int, ) \
|
2017-11-15 02:35:37 +07:00
|
|
|
ATOMIC_OP (op, asm_op, I, d, long, 64)
|
2017-07-11 08:02:19 +07:00
|
|
|
#endif
|
|
|
|
|
2017-11-15 02:35:37 +07:00
|
|
|
ATOMIC_OPS(add, add, i)
|
|
|
|
ATOMIC_OPS(sub, add, -i)
|
|
|
|
ATOMIC_OPS(and, and, i)
|
|
|
|
ATOMIC_OPS( or, or, i)
|
|
|
|
ATOMIC_OPS(xor, xor, i)
|
2017-07-11 08:02:19 +07:00
|
|
|
|
|
|
|
#undef ATOMIC_OP
|
|
|
|
#undef ATOMIC_OPS
|
|
|
|
|
|
|
|
/*
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
* Atomic ops that have ordered, relaxed, acquire, and release variants.
|
2017-07-11 08:02:19 +07:00
|
|
|
* There's two flavors of these: the arithmatic ops have both fetch and return
|
|
|
|
* versions, while the logical ops only have fetch versions.
|
|
|
|
*/
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix) \
|
|
|
|
static __always_inline \
|
|
|
|
c_type atomic##prefix##_fetch_##op##_relaxed(c_type i, \
|
|
|
|
atomic##prefix##_t *v) \
|
|
|
|
{ \
|
|
|
|
register c_type ret; \
|
|
|
|
__asm__ __volatile__ ( \
|
|
|
|
" amo" #asm_op "." #asm_type " %1, %2, %0" \
|
|
|
|
: "+A" (v->counter), "=r" (ret) \
|
|
|
|
: "r" (I) \
|
|
|
|
: "memory"); \
|
|
|
|
return ret; \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_type atomic##prefix##_fetch_##op(c_type i, atomic##prefix##_t *v) \
|
|
|
|
{ \
|
|
|
|
register c_type ret; \
|
|
|
|
__asm__ __volatile__ ( \
|
|
|
|
" amo" #asm_op "." #asm_type ".aqrl %1, %2, %0" \
|
|
|
|
: "+A" (v->counter), "=r" (ret) \
|
|
|
|
: "r" (I) \
|
|
|
|
: "memory"); \
|
|
|
|
return ret; \
|
2017-07-11 08:02:19 +07:00
|
|
|
}
|
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_type, c_type, prefix) \
|
|
|
|
static __always_inline \
|
|
|
|
c_type atomic##prefix##_##op##_return_relaxed(c_type i, \
|
|
|
|
atomic##prefix##_t *v) \
|
|
|
|
{ \
|
|
|
|
return atomic##prefix##_fetch_##op##_relaxed(i, v) c_op I; \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_type atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v) \
|
|
|
|
{ \
|
|
|
|
return atomic##prefix##_fetch_##op(i, v) c_op I; \
|
2017-07-11 08:02:19 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_GENERIC_ATOMIC64
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS(op, asm_op, c_op, I) \
|
|
|
|
ATOMIC_FETCH_OP( op, asm_op, I, w, int, ) \
|
|
|
|
ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int, )
|
2017-07-11 08:02:19 +07:00
|
|
|
#else
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS(op, asm_op, c_op, I) \
|
|
|
|
ATOMIC_FETCH_OP( op, asm_op, I, w, int, ) \
|
|
|
|
ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int, ) \
|
|
|
|
ATOMIC_FETCH_OP( op, asm_op, I, d, long, 64) \
|
|
|
|
ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, long, 64)
|
2017-07-11 08:02:19 +07:00
|
|
|
#endif
|
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
ATOMIC_OPS(add, add, +, i)
|
|
|
|
ATOMIC_OPS(sub, add, +, -i)
|
|
|
|
|
|
|
|
#define atomic_add_return_relaxed atomic_add_return_relaxed
|
|
|
|
#define atomic_sub_return_relaxed atomic_sub_return_relaxed
|
|
|
|
#define atomic_add_return atomic_add_return
|
|
|
|
#define atomic_sub_return atomic_sub_return
|
2017-07-11 08:02:19 +07:00
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
|
|
|
|
#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
|
|
|
|
#define atomic_fetch_add atomic_fetch_add
|
|
|
|
#define atomic_fetch_sub atomic_fetch_sub
|
|
|
|
|
|
|
|
#ifndef CONFIG_GENERIC_ATOMIC64
|
|
|
|
#define atomic64_add_return_relaxed atomic64_add_return_relaxed
|
|
|
|
#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
|
|
|
|
#define atomic64_add_return atomic64_add_return
|
|
|
|
#define atomic64_sub_return atomic64_sub_return
|
|
|
|
|
|
|
|
#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
|
|
|
|
#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
|
|
|
|
#define atomic64_fetch_add atomic64_fetch_add
|
|
|
|
#define atomic64_fetch_sub atomic64_fetch_sub
|
|
|
|
#endif
|
2017-07-11 08:02:19 +07:00
|
|
|
|
|
|
|
#undef ATOMIC_OPS
|
|
|
|
|
|
|
|
#ifdef CONFIG_GENERIC_ATOMIC64
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS(op, asm_op, I) \
|
|
|
|
ATOMIC_FETCH_OP(op, asm_op, I, w, int, )
|
2017-07-11 08:02:19 +07:00
|
|
|
#else
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS(op, asm_op, I) \
|
|
|
|
ATOMIC_FETCH_OP(op, asm_op, I, w, int, ) \
|
|
|
|
ATOMIC_FETCH_OP(op, asm_op, I, d, long, 64)
|
2017-07-11 08:02:19 +07:00
|
|
|
#endif
|
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
ATOMIC_OPS(and, and, i)
|
|
|
|
ATOMIC_OPS( or, or, i)
|
|
|
|
ATOMIC_OPS(xor, xor, i)
|
2017-07-11 08:02:19 +07:00
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
|
|
|
|
#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed
|
|
|
|
#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
|
|
|
|
#define atomic_fetch_and atomic_fetch_and
|
|
|
|
#define atomic_fetch_or atomic_fetch_or
|
|
|
|
#define atomic_fetch_xor atomic_fetch_xor
|
2017-07-11 08:02:19 +07:00
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#ifndef CONFIG_GENERIC_ATOMIC64
|
|
|
|
#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
|
|
|
|
#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed
|
|
|
|
#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
|
|
|
|
#define atomic64_fetch_and atomic64_fetch_and
|
|
|
|
#define atomic64_fetch_or atomic64_fetch_or
|
|
|
|
#define atomic64_fetch_xor atomic64_fetch_xor
|
|
|
|
#endif
|
2017-07-11 08:02:19 +07:00
|
|
|
|
|
|
|
#undef ATOMIC_OPS
|
|
|
|
|
|
|
|
#undef ATOMIC_FETCH_OP
|
|
|
|
#undef ATOMIC_OP_RETURN
|
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
/* This is required to provide a full barrier on success. */
|
atomics/treewide: Rename __atomic_add_unless() => atomic_fetch_add_unless()
While __atomic_add_unless() was originally intended as a building-block
for atomic_add_unless(), it's now used in a number of places around the
kernel. It's the only common atomic operation named __atomic*(), rather
than atomic_*(), and for consistency it would be better named
atomic_fetch_add_unless().
This lack of consistency is slightly confusing, and gets in the way of
scripting atomics. Given that, let's clean things up and promote it to
an official part of the atomics API, in the form of
atomic_fetch_add_unless().
This patch converts definitions and invocations over to the new name,
including the instrumented version, using the following script:
----
git grep -w __atomic_add_unless | while read line; do
sed -i '{s/\<__atomic_add_unless\>/atomic_fetch_add_unless/}' "${line%%:*}";
done
git grep -w __arch_atomic_add_unless | while read line; do
sed -i '{s/\<__arch_atomic_add_unless\>/arch_atomic_fetch_add_unless/}' "${line%%:*}";
done
----
Note that we do not have atomic{64,_long}_fetch_add_unless(), which will
be introduced by later patches.
There should be no functional change as a result of this patch.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Palmer Dabbelt <palmer@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-2-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-06-21 19:13:04 +07:00
|
|
|
static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
|
2017-07-11 08:02:19 +07:00
|
|
|
{
|
|
|
|
int prev, rc;
|
|
|
|
|
|
|
|
__asm__ __volatile__ (
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
"0: lr.w %[p], %[c]\n"
|
|
|
|
" beq %[p], %[u], 1f\n"
|
|
|
|
" add %[rc], %[p], %[a]\n"
|
|
|
|
" sc.w.rl %[rc], %[rc], %[c]\n"
|
|
|
|
" bnez %[rc], 0b\n"
|
|
|
|
" fence rw, rw\n"
|
|
|
|
"1:\n"
|
2017-07-11 08:02:19 +07:00
|
|
|
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
|
|
|
|
: [a]"r" (a), [u]"r" (u)
|
|
|
|
: "memory");
|
|
|
|
return prev;
|
|
|
|
}
|
2018-06-21 19:13:09 +07:00
|
|
|
#define atomic_fetch_add_unless atomic_fetch_add_unless
|
2017-07-11 08:02:19 +07:00
|
|
|
|
|
|
|
#ifndef CONFIG_GENERIC_ATOMIC64
|
2018-06-21 19:13:16 +07:00
|
|
|
static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
|
2017-07-11 08:02:19 +07:00
|
|
|
{
|
|
|
|
long prev, rc;
|
|
|
|
|
|
|
|
__asm__ __volatile__ (
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
"0: lr.d %[p], %[c]\n"
|
|
|
|
" beq %[p], %[u], 1f\n"
|
|
|
|
" add %[rc], %[p], %[a]\n"
|
|
|
|
" sc.d.rl %[rc], %[rc], %[c]\n"
|
|
|
|
" bnez %[rc], 0b\n"
|
|
|
|
" fence rw, rw\n"
|
|
|
|
"1:\n"
|
2017-07-11 08:02:19 +07:00
|
|
|
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
|
|
|
|
: [a]"r" (a), [u]"r" (u)
|
|
|
|
: "memory");
|
|
|
|
return prev;
|
|
|
|
}
|
2018-06-21 19:13:16 +07:00
|
|
|
#define atomic64_fetch_add_unless atomic64_fetch_add_unless
|
2017-07-11 08:02:19 +07:00
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
* {cmp,}xchg and the operations that return, so they need a full barrier.
|
2017-07-11 08:02:19 +07:00
|
|
|
*/
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OP(c_t, prefix, size) \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_xchg_relaxed(atomic##prefix##_t *v, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __xchg_relaxed(&(v->counter), n, size); \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_xchg_acquire(atomic##prefix##_t *v, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __xchg_acquire(&(v->counter), n, size); \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __xchg_release(&(v->counter), n, size); \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __xchg(&(v->counter), n, size); \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_cmpxchg_relaxed(atomic##prefix##_t *v, \
|
|
|
|
c_t o, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __cmpxchg_relaxed(&(v->counter), o, n, size); \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_cmpxchg_acquire(atomic##prefix##_t *v, \
|
|
|
|
c_t o, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __cmpxchg_acquire(&(v->counter), o, n, size); \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_cmpxchg_release(atomic##prefix##_t *v, \
|
|
|
|
c_t o, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __cmpxchg_release(&(v->counter), o, n, size); \
|
|
|
|
} \
|
|
|
|
static __always_inline \
|
|
|
|
c_t atomic##prefix##_cmpxchg(atomic##prefix##_t *v, c_t o, c_t n) \
|
|
|
|
{ \
|
|
|
|
return __cmpxchg(&(v->counter), o, n, size); \
|
2017-07-11 08:02:19 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_GENERIC_ATOMIC64
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS() \
|
|
|
|
ATOMIC_OP( int, , 4)
|
2017-07-11 08:02:19 +07:00
|
|
|
#else
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
#define ATOMIC_OPS() \
|
|
|
|
ATOMIC_OP( int, , 4) \
|
|
|
|
ATOMIC_OP(long, 64, 8)
|
2017-07-11 08:02:19 +07:00
|
|
|
#endif
|
|
|
|
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
ATOMIC_OPS()
|
2017-07-11 08:02:19 +07:00
|
|
|
|
|
|
|
#undef ATOMIC_OPS
|
|
|
|
#undef ATOMIC_OP
|
|
|
|
|
|
|
|
static __always_inline int atomic_sub_if_positive(atomic_t *v, int offset)
|
|
|
|
{
|
|
|
|
int prev, rc;
|
|
|
|
|
|
|
|
__asm__ __volatile__ (
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
"0: lr.w %[p], %[c]\n"
|
|
|
|
" sub %[rc], %[p], %[o]\n"
|
|
|
|
" bltz %[rc], 1f\n"
|
|
|
|
" sc.w.rl %[rc], %[rc], %[c]\n"
|
|
|
|
" bnez %[rc], 0b\n"
|
|
|
|
" fence rw, rw\n"
|
|
|
|
"1:\n"
|
2017-07-11 08:02:19 +07:00
|
|
|
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
|
|
|
|
: [o]"r" (offset)
|
|
|
|
: "memory");
|
|
|
|
return prev - offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define atomic_dec_if_positive(v) atomic_sub_if_positive(v, 1)
|
|
|
|
|
|
|
|
#ifndef CONFIG_GENERIC_ATOMIC64
|
|
|
|
static __always_inline long atomic64_sub_if_positive(atomic64_t *v, int offset)
|
|
|
|
{
|
|
|
|
long prev, rc;
|
|
|
|
|
|
|
|
__asm__ __volatile__ (
|
riscv/atomic: Strengthen implementations with fences
Atomics present the same issue with locking: release and acquire
variants need to be strengthened to meet the constraints defined
by the Linux-kernel memory consistency model [1].
Atomics present a further issue: implementations of atomics such
as atomic_cmpxchg() and atomic_add_unless() rely on LR/SC pairs,
which do not give full-ordering with .aqrl; for example, current
implementations allow the "lr-sc-aqrl-pair-vs-full-barrier" test
below to end up with the state indicated in the "exists" clause.
In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the atomics operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
and by replacing .aqrl LR/SC pairs in sequences such as:
0: lr.w.aqrl %0, %addr
bne %0, %old, 1f
...
sc.w.aqrl %1, %new, %addr
bnez %1, 0b
1:
with sequences of the form:
0: lr.w %0, %addr
bne %0, %old, 1f
...
sc.w.rl %1, %new, %addr /* SC-release */
bnez %1, 0b
fence rw, rw /* "full" fence */
1:
following Daniel's suggestion.
These modifications were validated with simulation of the RISC-V
memory consistency model.
C lr-sc-aqrl-pair-vs-full-barrier
{}
P0(int *x, int *y, atomic_t *u)
{
int r0;
int r1;
WRITE_ONCE(*x, 1);
r0 = atomic_cmpxchg(u, 0, 1);
r1 = READ_ONCE(*y);
}
P1(int *x, int *y, atomic_t *v)
{
int r0;
int r1;
WRITE_ONCE(*y, 1);
r0 = atomic_cmpxchg(v, 0, 1);
r1 = READ_ONCE(*x);
}
exists (u=1 /\ v=1 /\ 0:r1=0 /\ 1:r1=0)
[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
https://marc.info/?l=linux-kernel&m=151633436614259&w=2
Suggested-by: Daniel Lustig <dlustig@nvidia.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-riscv@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
2018-03-09 19:13:40 +07:00
|
|
|
"0: lr.d %[p], %[c]\n"
|
|
|
|
" sub %[rc], %[p], %[o]\n"
|
|
|
|
" bltz %[rc], 1f\n"
|
|
|
|
" sc.d.rl %[rc], %[rc], %[c]\n"
|
|
|
|
" bnez %[rc], 0b\n"
|
|
|
|
" fence rw, rw\n"
|
|
|
|
"1:\n"
|
2017-07-11 08:02:19 +07:00
|
|
|
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
|
|
|
|
: [o]"r" (offset)
|
|
|
|
: "memory");
|
|
|
|
return prev - offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define atomic64_dec_if_positive(v) atomic64_sub_if_positive(v, 1)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#endif /* _ASM_RISCV_ATOMIC_H */
|