Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit fab957c1 authored by Palmer Dabbelt's avatar Palmer Dabbelt
Browse files

RISC-V: Atomic and Locking Code



This contains all the code that directly interfaces with the RISC-V
memory model.  While this code corforms to the current RISC-V ISA
specifications (user 2.2 and priv 1.10), the memory model is somewhat
underspecified in those documents.  There is a working group that hopes
to produce a formal memory model by the end of the year, but my
understanding is that the basic definitions we're relying on here won't
change significantly.

Reviewed-by: default avatarArnd Bergmann <arnd@arndb.de>
Signed-off-by: default avatarPalmer Dabbelt <palmer@dabbelt.com>
parent 76d2a049
Loading
Loading
Loading
Loading
+375 −0
Original line number Original line Diff line number Diff line
/*
 * 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) }
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.
 */
#define ATOMIC_OP(op, asm_op, c_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");									\
}

#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I)			\
        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I)			\
        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )	\
        ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
#endif

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)

#undef ATOMIC_OP
#undef ATOMIC_OPS

/*
 * Atomic ops that have ordered, relaxed, acquire, and relese variants.
 * There's two flavors of these: the arithmatic ops have both fetch and return
 * versions, while the logical ops only have fetch versions.
 */
#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix)			\
static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v)	\
{													\
	register c_type ret;										\
	__asm__ __volatile__ (										\
		"amo" #asm_op "." #asm_type #asm_or " %1, %2, %0"					\
		: "+A" (v->counter), "=r" (ret)								\
		: "r" (I)										\
		: "memory");										\
	return ret;											\
}

#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix)			\
static __always_inline c_type atomic##prefix##_##op##_return##c_or(c_type i, atomic##prefix##_t *v)	\
{													\
        return atomic##prefix##_fetch_##op##c_or(i, v) c_op I;						\
}

#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
        ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
        ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64)	\
        ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
#endif

ATOMIC_OPS(add, add, +,  i,      , _relaxed)
ATOMIC_OPS(add, add, +,  i, .aq  , _acquire)
ATOMIC_OPS(add, add, +,  i, .rl  , _release)
ATOMIC_OPS(add, add, +,  i, .aqrl,         )

ATOMIC_OPS(sub, add, +, -i,      , _relaxed)
ATOMIC_OPS(sub, add, +, -i, .aq  , _acquire)
ATOMIC_OPS(sub, add, +, -i, .rl  , _release)
ATOMIC_OPS(sub, add, +, -i, .aqrl,         )

#undef ATOMIC_OPS

#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )		\
        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
#endif

ATOMIC_OPS(and, and, &,  i,      , _relaxed)
ATOMIC_OPS(and, and, &,  i, .aq  , _acquire)
ATOMIC_OPS(and, and, &,  i, .rl  , _release)
ATOMIC_OPS(and, and, &,  i, .aqrl,         )

ATOMIC_OPS( or,  or, |,  i,      , _relaxed)
ATOMIC_OPS( or,  or, |,  i, .aq  , _acquire)
ATOMIC_OPS( or,  or, |,  i, .rl  , _release)
ATOMIC_OPS( or,  or, |,  i, .aqrl,         )

ATOMIC_OPS(xor, xor, ^,  i,      , _relaxed)
ATOMIC_OPS(xor, xor, ^,  i, .aq  , _acquire)
ATOMIC_OPS(xor, xor, ^,  i, .rl  , _release)
ATOMIC_OPS(xor, xor, ^,  i, .aqrl,         )

#undef ATOMIC_OPS

#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN

/*
 * The extra atomic operations that are constructed from one of the core
 * AMO-based operations above (aside from sub, which is easier to fit above).
 * These are required to perform a barrier, but they're OK this way because
 * atomic_*_return is also required to perform a barrier.
 */
#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix)			\
static __always_inline bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
{										\
	return atomic##prefix##_##func_op##_return(i, v) comp_op I;		\
}

#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, func_op, comp_op, I)			\
        ATOMIC_OP (op, func_op, comp_op, I,  int,   )
#else
#define ATOMIC_OPS(op, func_op, comp_op, I)			\
        ATOMIC_OP (op, func_op, comp_op, I,  int,   )		\
        ATOMIC_OP (op, func_op, comp_op, I, long, 64)
#endif

ATOMIC_OPS(add_and_test, add, ==, 0)
ATOMIC_OPS(sub_and_test, sub, ==, 0)
ATOMIC_OPS(add_negative, add,  <, 0)

#undef ATOMIC_OP
#undef ATOMIC_OPS

#define ATOMIC_OP(op, func_op, c_op, I, c_type, prefix)				\
static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v)	\
{										\
	atomic##prefix##_##func_op(I, v);					\
}

#define ATOMIC_FETCH_OP(op, func_op, c_op, I, c_type, prefix)				\
static __always_inline c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)	\
{											\
	return atomic##prefix##_fetch_##func_op(I, v);					\
}

#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix)				\
static __always_inline c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v)	\
{											\
        return atomic##prefix##_fetch_##op(v) c_op I;					\
}

#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I)						\
        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I)						\
        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )				\
        ATOMIC_OP       (op, asm_op, c_op, I, long, 64)				\
        ATOMIC_FETCH_OP (op, asm_op, c_op, I, long, 64)				\
        ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
#endif

ATOMIC_OPS(inc, add, +,  1)
ATOMIC_OPS(dec, add, +, -1)

#undef ATOMIC_OPS
#undef ATOMIC_OP
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN

#define ATOMIC_OP(op, func_op, comp_op, I, prefix)				\
static __always_inline bool atomic##prefix##_##op(atomic##prefix##_t *v)	\
{										\
	return atomic##prefix##_##func_op##_return(v) comp_op I;		\
}

ATOMIC_OP(inc_and_test, inc, ==, 0,   )
ATOMIC_OP(dec_and_test, dec, ==, 0,   )
#ifndef CONFIG_GENERIC_ATOMIC64
ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
#endif

#undef ATOMIC_OP

/* This is required to provide a barrier on success. */
static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
       int prev, rc;

	__asm__ __volatile__ (
		"0:\n\t"
		"lr.w.aqrl  %[p],  %[c]\n\t"
		"beq        %[p],  %[u], 1f\n\t"
		"add       %[rc],  %[p], %[a]\n\t"
		"sc.w.aqrl %[rc], %[rc], %[c]\n\t"
		"bnez      %[rc], 0b\n\t"
		"1:"
		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
		: [a]"r" (a), [u]"r" (u)
		: "memory");
	return prev;
}

#ifndef CONFIG_GENERIC_ATOMIC64
static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
{
       long prev, rc;

	__asm__ __volatile__ (
		"0:\n\t"
		"lr.d.aqrl  %[p],  %[c]\n\t"
		"beq        %[p],  %[u], 1f\n\t"
		"add       %[rc],  %[p], %[a]\n\t"
		"sc.d.aqrl %[rc], %[rc], %[c]\n\t"
		"bnez      %[rc], 0b\n\t"
		"1:"
		: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
		: [a]"r" (a), [u]"r" (u)
		: "memory");
	return prev;
}

static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
{
	return __atomic64_add_unless(v, a, u) != u;
}
#endif

/*
 * The extra atomic operations that are constructed from one of the core
 * LR/SC-based operations above.
 */
static __always_inline int atomic_inc_not_zero(atomic_t *v)
{
        return __atomic_add_unless(v, 1, 0);
}

#ifndef CONFIG_GENERIC_ATOMIC64
static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
{
        return atomic64_add_unless(v, 1, 0);
}
#endif

/*
 * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
 * {cmp,}xchg and the operations that return, so they need a barrier.  We just
 * use the other implementations directly.
 */
#define ATOMIC_OP(c_t, prefix, c_or, size, asm_or)						\
static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) 	\
{												\
	return __cmpxchg(&(v->counter), o, n, size, asm_or, asm_or);				\
}												\
static __always_inline c_t atomic##prefix##_xchg##c_or(atomic##prefix##_t *v, c_t n) 		\
{												\
	return __xchg(n, &(v->counter), size, asm_or);						\
}

#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(c_or, asm_or)			\
	ATOMIC_OP( int,   , c_or, 4, asm_or)
#else
#define ATOMIC_OPS(c_or, asm_or)			\
	ATOMIC_OP( int,   , c_or, 4, asm_or)		\
	ATOMIC_OP(long, 64, c_or, 8, asm_or)
#endif

ATOMIC_OPS(        , .aqrl)
ATOMIC_OPS(_acquire,   .aq)
ATOMIC_OPS(_release,   .rl)
ATOMIC_OPS(_relaxed,      )

#undef ATOMIC_OPS
#undef ATOMIC_OP

static __always_inline int atomic_sub_if_positive(atomic_t *v, int offset)
{
       int prev, rc;

	__asm__ __volatile__ (
		"0:\n\t"
		"lr.w.aqrl  %[p],  %[c]\n\t"
		"sub       %[rc],  %[p], %[o]\n\t"
		"bltz      %[rc],    1f\n\t"
		"sc.w.aqrl %[rc], %[rc], %[c]\n\t"
		"bnez      %[rc],    0b\n\t"
		"1:"
		: [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__ (
		"0:\n\t"
		"lr.d.aqrl  %[p],  %[c]\n\t"
		"sub       %[rc],  %[p], %[o]\n\t"
		"bltz      %[rc],    1f\n\t"
		"sc.d.aqrl %[rc], %[rc], %[c]\n\t"
		"bnez      %[rc],    0b\n\t"
		"1:"
		: [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 */
+68 −0
Original line number Original line Diff line number Diff line
/*
 * Based on arch/arm/include/asm/barrier.h
 *
 * Copyright (C) 2012 ARM Ltd.
 * Copyright (C) 2013 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 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_RISCV_BARRIER_H
#define _ASM_RISCV_BARRIER_H

#ifndef __ASSEMBLY__

#define nop()		__asm__ __volatile__ ("nop")

#define RISCV_FENCE(p, s) \
	__asm__ __volatile__ ("fence " #p "," #s : : : "memory")

/* These barriers need to enforce ordering on both devices or memory. */
#define mb()		RISCV_FENCE(iorw,iorw)
#define rmb()		RISCV_FENCE(ir,ir)
#define wmb()		RISCV_FENCE(ow,ow)

/* These barriers do not need to enforce ordering on devices, just memory. */
#define smp_mb()	RISCV_FENCE(rw,rw)
#define smp_rmb()	RISCV_FENCE(r,r)
#define smp_wmb()	RISCV_FENCE(w,w)

/*
 * These fences exist to enforce ordering around the relaxed AMOs.  The
 * documentation defines that
 * "
 *     atomic_fetch_add();
 *   is equivalent to:
 *     smp_mb__before_atomic();
 *     atomic_fetch_add_relaxed();
 *     smp_mb__after_atomic();
 * "
 * So we emit full fences on both sides.
 */
#define __smb_mb__before_atomic()	smp_mb()
#define __smb_mb__after_atomic()	smp_mb()

/*
 * These barriers prevent accesses performed outside a spinlock from being moved
 * inside a spinlock.  Since RISC-V sets the aq/rl bits on our spinlock only
 * enforce release consistency, we need full fences here.
 */
#define smb_mb__before_spinlock()	smp_mb()
#define smb_mb__after_spinlock()	smp_mb()

#include <asm-generic/barrier.h>

#endif /* __ASSEMBLY__ */

#endif /* _ASM_RISCV_BARRIER_H */
+218 −0
Original line number Original line Diff line number Diff line
/*
 * Copyright (C) 2012 Regents of the University of California
 *
 *   This program is free software; you can redistribute it and/or
 *   modify it under the terms of the GNU General Public License
 *   as published by the Free Software Foundation, version 2.
 *
 *   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.
 */

#ifndef _ASM_RISCV_BITOPS_H
#define _ASM_RISCV_BITOPS_H

#ifndef _LINUX_BITOPS_H
#error "Only <linux/bitops.h> can be included directly"
#endif /* _LINUX_BITOPS_H */

#include <linux/compiler.h>
#include <linux/irqflags.h>
#include <asm/barrier.h>
#include <asm/bitsperlong.h>

#ifndef smp_mb__before_clear_bit
#define smp_mb__before_clear_bit()  smp_mb()
#define smp_mb__after_clear_bit()   smp_mb()
#endif /* smp_mb__before_clear_bit */

#include <asm-generic/bitops/__ffs.h>
#include <asm-generic/bitops/ffz.h>
#include <asm-generic/bitops/fls.h>
#include <asm-generic/bitops/__fls.h>
#include <asm-generic/bitops/fls64.h>
#include <asm-generic/bitops/find.h>
#include <asm-generic/bitops/sched.h>
#include <asm-generic/bitops/ffs.h>

#include <asm-generic/bitops/hweight.h>

#if (BITS_PER_LONG == 64)
#define __AMO(op)	"amo" #op ".d"
#elif (BITS_PER_LONG == 32)
#define __AMO(op)	"amo" #op ".w"
#else
#error "Unexpected BITS_PER_LONG"
#endif

#define __test_and_op_bit_ord(op, mod, nr, addr, ord)		\
({								\
	unsigned long __res, __mask;				\
	__mask = BIT_MASK(nr);					\
	__asm__ __volatile__ (					\
		__AMO(op) #ord " %0, %2, %1"			\
		: "=r" (__res), "+A" (addr[BIT_WORD(nr)])	\
		: "r" (mod(__mask))				\
		: "memory");					\
	((__res & __mask) != 0);				\
})

#define __op_bit_ord(op, mod, nr, addr, ord)			\
	__asm__ __volatile__ (					\
		__AMO(op) #ord " zero, %1, %0"			\
		: "+A" (addr[BIT_WORD(nr)])			\
		: "r" (mod(BIT_MASK(nr)))			\
		: "memory");

#define __test_and_op_bit(op, mod, nr, addr) 			\
	__test_and_op_bit_ord(op, mod, nr, addr, )
#define __op_bit(op, mod, nr, addr)				\
	__op_bit_ord(op, mod, nr, addr, )

/* Bitmask modifiers */
#define __NOP(x)	(x)
#define __NOT(x)	(~(x))

/**
 * test_and_set_bit - Set a bit and return its old value
 * @nr: Bit to set
 * @addr: Address to count from
 *
 * This operation may be reordered on other architectures than x86.
 */
static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
{
	return __test_and_op_bit(or, __NOP, nr, addr);
}

/**
 * test_and_clear_bit - Clear a bit and return its old value
 * @nr: Bit to clear
 * @addr: Address to count from
 *
 * This operation can be reordered on other architectures other than x86.
 */
static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
{
	return __test_and_op_bit(and, __NOT, nr, addr);
}

/**
 * test_and_change_bit - Change a bit and return its old value
 * @nr: Bit to change
 * @addr: Address to count from
 *
 * This operation is atomic and cannot be reordered.
 * It also implies a memory barrier.
 */
static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
{
	return __test_and_op_bit(xor, __NOP, nr, addr);
}

/**
 * set_bit - Atomically set a bit in memory
 * @nr: the bit to set
 * @addr: the address to start counting from
 *
 * Note: there are no guarantees that this function will not be reordered
 * on non x86 architectures, so if you are writing portable code,
 * make sure not to rely on its reordering guarantees.
 *
 * Note that @nr may be almost arbitrarily large; this function is not
 * restricted to acting on a single-word quantity.
 */
static inline void set_bit(int nr, volatile unsigned long *addr)
{
	__op_bit(or, __NOP, nr, addr);
}

/**
 * clear_bit - Clears a bit in memory
 * @nr: Bit to clear
 * @addr: Address to start counting from
 *
 * Note: there are no guarantees that this function will not be reordered
 * on non x86 architectures, so if you are writing portable code,
 * make sure not to rely on its reordering guarantees.
 */
static inline void clear_bit(int nr, volatile unsigned long *addr)
{
	__op_bit(and, __NOT, nr, addr);
}

/**
 * change_bit - Toggle a bit in memory
 * @nr: Bit to change
 * @addr: Address to start counting from
 *
 * change_bit()  may be reordered on other architectures than x86.
 * Note that @nr may be almost arbitrarily large; this function is not
 * restricted to acting on a single-word quantity.
 */
static inline void change_bit(int nr, volatile unsigned long *addr)
{
	__op_bit(xor, __NOP, nr, addr);
}

/**
 * test_and_set_bit_lock - Set a bit and return its old value, for lock
 * @nr: Bit to set
 * @addr: Address to count from
 *
 * This operation is atomic and provides acquire barrier semantics.
 * It can be used to implement bit locks.
 */
static inline int test_and_set_bit_lock(
	unsigned long nr, volatile unsigned long *addr)
{
	return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq);
}

/**
 * clear_bit_unlock - Clear a bit in memory, for unlock
 * @nr: the bit to set
 * @addr: the address to start counting from
 *
 * This operation is atomic and provides release barrier semantics.
 */
static inline void clear_bit_unlock(
	unsigned long nr, volatile unsigned long *addr)
{
	__op_bit_ord(and, __NOT, nr, addr, .rl);
}

/**
 * __clear_bit_unlock - Clear a bit in memory, for unlock
 * @nr: the bit to set
 * @addr: the address to start counting from
 *
 * This operation is like clear_bit_unlock, however it is not atomic.
 * It does provide release barrier semantics so it can be used to unlock
 * a bit lock, however it would only be used if no other CPU can modify
 * any bits in the memory until the lock is released (a good example is
 * if the bit lock itself protects access to the other bits in the word).
 *
 * On RISC-V systems there seems to be no benefit to taking advantage of the
 * non-atomic property here: it's a lot more instructions and we still have to
 * provide release semantics anyway.
 */
static inline void __clear_bit_unlock(
	unsigned long nr, volatile unsigned long *addr)
{
	clear_bit_unlock(nr, addr);
}

#undef __test_and_op_bit
#undef __op_bit
#undef __NOP
#undef __NOT
#undef __AMO

#include <asm-generic/bitops/non-atomic.h>
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/ext2-atomic.h>

#endif /* _ASM_RISCV_BITOPS_H */
+39 −0
Original line number Original line Diff line number Diff line
/*
 * Copyright (C) 2015 Regents of the University of California
 *
 *   This program is free software; you can redistribute it and/or
 *   modify it under the terms of the GNU General Public License
 *   as published by the Free Software Foundation, version 2.
 *
 *   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.
 */

#ifndef _ASM_RISCV_CACHEFLUSH_H
#define _ASM_RISCV_CACHEFLUSH_H

#include <asm-generic/cacheflush.h>

#undef flush_icache_range
#undef flush_icache_user_range

static inline void local_flush_icache_all(void)
{
	asm volatile ("fence.i" ::: "memory");
}

#ifndef CONFIG_SMP

#define flush_icache_range(start, end) local_flush_icache_all()
#define flush_icache_user_range(vma, pg, addr, len) local_flush_icache_all()

#else /* CONFIG_SMP */

#define flush_icache_range(start, end) sbi_remote_fence_i(0)
#define flush_icache_user_range(vma, pg, addr, len) sbi_remote_fence_i(0)

#endif /* CONFIG_SMP */

#endif /* _ASM_RISCV_CACHEFLUSH_H */
+134 −0
Original line number Original line Diff line number Diff line
/*
 * Copyright (C) 2014 Regents of the University of California
 *
 *   This program is free software; you can redistribute it and/or
 *   modify it under the terms of the GNU General Public License
 *   as published by the Free Software Foundation, version 2.
 *
 *   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.
 */

#ifndef _ASM_RISCV_CMPXCHG_H
#define _ASM_RISCV_CMPXCHG_H

#include <linux/bug.h>

#include <asm/barrier.h>

#define __xchg(new, ptr, size, asm_or)				\
({								\
	__typeof__(ptr) __ptr = (ptr);				\
	__typeof__(new) __new = (new);				\
	__typeof__(*(ptr)) __ret;				\
	switch (size) {						\
	case 4:							\
		__asm__ __volatile__ (				\
			"amoswap.w" #asm_or " %0, %2, %1"	\
			: "=r" (__ret), "+A" (*__ptr)		\
			: "r" (__new)				\
			: "memory");				\
		break;						\
	case 8:							\
		__asm__ __volatile__ (				\
			"amoswap.d" #asm_or " %0, %2, %1"	\
			: "=r" (__ret), "+A" (*__ptr)		\
			: "r" (__new)				\
			: "memory");				\
		break;						\
	default:						\
		BUILD_BUG();					\
	}							\
	__ret;							\
})

#define xchg(ptr, x)    (__xchg((x), (ptr), sizeof(*(ptr)), .aqrl))

#define xchg32(ptr, x)				\
({						\
	BUILD_BUG_ON(sizeof(*(ptr)) != 4);	\
	xchg((ptr), (x));			\
})

#define xchg64(ptr, x)				\
({						\
	BUILD_BUG_ON(sizeof(*(ptr)) != 8);	\
	xchg((ptr), (x));			\
})

/*
 * Atomic compare and exchange.  Compare OLD with MEM, if identical,
 * store NEW in MEM.  Return the initial value in MEM.  Success is
 * indicated by comparing RETURN with OLD.
 */
#define __cmpxchg(ptr, old, new, size, lrb, scb)			\
({									\
	__typeof__(ptr) __ptr = (ptr);					\
	__typeof__(*(ptr)) __old = (old);				\
	__typeof__(*(ptr)) __new = (new);				\
	__typeof__(*(ptr)) __ret;					\
	register unsigned int __rc;					\
	switch (size) {							\
	case 4:								\
		__asm__ __volatile__ (					\
		"0:"							\
			"lr.w" #scb " %0, %2\n"				\
			"bne         %0, %z3, 1f\n"			\
			"sc.w" #lrb " %1, %z4, %2\n"			\
			"bnez        %1, 0b\n"				\
		"1:"							\
			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
			: "rJ" (__old), "rJ" (__new)			\
			: "memory");					\
		break;							\
	case 8:								\
		__asm__ __volatile__ (					\
		"0:"							\
			"lr.d" #scb " %0, %2\n"				\
			"bne         %0, %z3, 1f\n"			\
			"sc.d" #lrb " %1, %z4, %2\n"			\
			"bnez        %1, 0b\n"				\
		"1:"							\
			: "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr)	\
			: "rJ" (__old), "rJ" (__new)			\
			: "memory");					\
		break;							\
	default:							\
		BUILD_BUG();						\
	}								\
	__ret;								\
})

#define cmpxchg(ptr, o, n) \
	(__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), .aqrl, .aqrl))

#define cmpxchg_local(ptr, o, n) \
	(__cmpxchg((ptr), (o), (n), sizeof(*(ptr)), , ))

#define cmpxchg32(ptr, o, n)			\
({						\
	BUILD_BUG_ON(sizeof(*(ptr)) != 4);	\
	cmpxchg((ptr), (o), (n));		\
})

#define cmpxchg32_local(ptr, o, n)		\
({						\
	BUILD_BUG_ON(sizeof(*(ptr)) != 4);	\
	cmpxchg_local((ptr), (o), (n));		\
})

#define cmpxchg64(ptr, o, n)			\
({						\
	BUILD_BUG_ON(sizeof(*(ptr)) != 8);	\
	cmpxchg((ptr), (o), (n));		\
})

#define cmpxchg64_local(ptr, o, n)		\
({						\
	BUILD_BUG_ON(sizeof(*(ptr)) != 8);	\
	cmpxchg_local((ptr), (o), (n));		\
})

#endif /* _ASM_RISCV_CMPXCHG_H */
Loading