1
0
Fork 0
alistair23-linux/arch/mips/include/asm/bitops.h

653 lines
16 KiB
C
Raw Normal View History

/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (c) 1994 - 1997, 99, 2000, 06, 07 Ralf Baechle (ralf@linux-mips.org)
* Copyright (c) 1999, 2000 Silicon Graphics, Inc.
*/
#ifndef _ASM_BITOPS_H
#define _ASM_BITOPS_H
#ifndef _LINUX_BITOPS_H
#error only <linux/bitops.h> can be included directly
#endif
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/barrier.h>
#include <asm/byteorder.h> /* sigh ... */
MIPS: Fix microMIPS LL/SC immediate offsets In the microMIPS encoding some memory access instructions have their immediate offset reduced to 12 bits only. That does not match the GCC `R' constraint we use in some places to satisfy the requirement, resulting in build failures like this: {standard input}: Assembler messages: {standard input}:720: Error: macro used $at after ".set noat" {standard input}:720: Warning: macro instruction expanded into multiple instructions Fix the problem by defining a macro, `GCC_OFF12_ASM', that expands to the right constraint depending on whether microMIPS or standard MIPS code is produced. Also apply the fix to where `m' is used as in the worst case this change does nothing, e.g. where the pointer was already in a register such as a function argument and no further offset was requested, and in the best case it avoids an extraneous sequence of up to two instructions to load the high 20 bits of the address in the LL/SC loop. This reduces the risk of lock contention that is the higher the more instructions there are in the critical section between LL and SC. Strictly speaking we could just bulk-replace `R' with `ZC' as the latter constraint adjusts automatically depending on the ISA selected. However it was only introduced with GCC 4.9 and we keep supporing older compilers for the standard MIPS configuration, hence the slightly more complicated approach I chose. The choice of a zero-argument function-like rather than an object-like macro was made so that it does not look like a function call taking the C expression used for the constraint as an argument. This is so as not to confuse the reader or formatting checkers like `checkpatch.pl' and follows previous practice. Signed-off-by: Maciej W. Rozycki <macro@codesourcery.com> Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/8482/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2014-11-15 15:08:48 -07:00
#include <asm/compiler.h>
#include <asm/cpu-features.h>
#include <asm/llsc.h>
#include <asm/sgidefs.h>
#include <asm/war.h>
/*
* These are the "slower" versions of the functions and are in bitops.c.
* These functions call raw_local_irq_{save,restore}().
*/
void __mips_set_bit(unsigned long nr, volatile unsigned long *addr);
void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr);
void __mips_change_bit(unsigned long nr, volatile unsigned long *addr);
int __mips_test_and_set_bit(unsigned long nr,
volatile unsigned long *addr);
int __mips_test_and_set_bit_lock(unsigned long nr,
volatile unsigned long *addr);
int __mips_test_and_clear_bit(unsigned long nr,
volatile unsigned long *addr);
int __mips_test_and_change_bit(unsigned long nr,
volatile unsigned long *addr);
/*
* set_bit - Atomically set a bit in memory
* @nr: the bit to set
* @addr: the address to start counting from
*
* This function is atomic and may not be reordered. See __set_bit()
* if you do not require the atomic 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(unsigned long nr, volatile unsigned long *addr)
{
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
int bit = nr & SZLONG_MASK;
unsigned long temp;
if (kernel_uses_llsc && R10000_LLSC_WAR) {
__asm__ __volatile__(
" .set push \n"
" .set arch=r4000 \n"
"1: " __LL "%0, %1 # set_bit \n"
" or %0, %2 \n"
" " __SC "%0, %1 \n"
" beqzl %0, 1b \n"
" .set pop \n"
: "=&r" (temp), "=" GCC_OFF_SMALL_ASM() (*m)
: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m)
: __LLSC_CLOBBER);
#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
MIPS: Loongson: Introduce and use loongson_llsc_mb() On the Loongson-2G/2H/3A/3B there is a hardware flaw that ll/sc and lld/scd is very weak ordering. We should add sync instructions "before each ll/lld" and "at the branch-target between ll/sc" to workaround. Otherwise, this flaw will cause deadlock occasionally (e.g. when doing heavy load test with LTP). Below is the explaination of CPU designer: "For Loongson 3 family, when a memory access instruction (load, store, or prefetch)'s executing occurs between the execution of LL and SC, the success or failure of SC is not predictable. Although programmer would not insert memory access instructions between LL and SC, the memory instructions before LL in program-order, may dynamically executed between the execution of LL/SC, so a memory fence (SYNC) is needed before LL/LLD to avoid this situation. Since Loongson-3A R2 (3A2000), we have improved our hardware design to handle this case. But we later deduce a rarely circumstance that some speculatively executed memory instructions due to branch misprediction between LL/SC still fall into the above case, so a memory fence (SYNC) at branch-target (if its target is not between LL/SC) is needed for Loongson 3A1000, 3B1500, 3A2000 and 3A3000. Our processor is continually evolving and we aim to to remove all these workaround-SYNCs around LL/SC for new-come processor." Here is an example: Both cpu1 and cpu2 simutaneously run atomic_add by 1 on same atomic var, this bug cause both 'sc' run by two cpus (in atomic_add) succeed at same time('sc' return 1), and the variable is only *added by 1*, sometimes, which is wrong and unacceptable(it should be added by 2). Why disable fix-loongson3-llsc in compiler? Because compiler fix will cause problems in kernel's __ex_table section. This patch fix all the cases in kernel, but: +. the fix at the end of futex_atomic_cmpxchg_inatomic is for branch-target of 'bne', there other cases which smp_mb__before_llsc() and smp_llsc_mb() fix the ll and branch-target coincidently such as atomic_sub_if_positive/ cmpxchg/xchg, just like this one. +. Loongson 3 does support CONFIG_EDAC_ATOMIC_SCRUB, so no need to touch edac.h +. local_ops and cmpxchg_local should not be affected by this bug since only the owner can write. +. mips_atomic_set for syscall.c is deprecated and rarely used, just let it go Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Huang Pei <huangpei@loongson.cn> [paul.burton@mips.com: - Simplify the addition of -mno-fix-loongson3-llsc to cflags, and add a comment describing why it's there. - Make loongson_llsc_mb() a no-op when CONFIG_CPU_LOONGSON3_WORKAROUNDS=n, rather than a compiler memory barrier. - Add a comment describing the bug & how loongson_llsc_mb() helps in asm/barrier.h.] Signed-off-by: Paul Burton <paul.burton@mips.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: ambrosehua@gmail.com Cc: Steven J . Hill <Steven.Hill@cavium.com> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: Li Xuefeng <lixuefeng@loongson.cn> Cc: Xu Chenghua <xuchenghua@loongson.cn>
2019-01-15 01:04:54 -07:00
loongson_llsc_mb();
do {
__asm__ __volatile__(
" " __LL "%0, %1 # set_bit \n"
" " __INS "%0, %3, %2, 1 \n"
" " __SC "%0, %1 \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
: "ir" (bit), "r" (~0)
: __LLSC_CLOBBER);
} while (unlikely(!temp));
#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
} else if (kernel_uses_llsc) {
MIPS: Loongson: Introduce and use loongson_llsc_mb() On the Loongson-2G/2H/3A/3B there is a hardware flaw that ll/sc and lld/scd is very weak ordering. We should add sync instructions "before each ll/lld" and "at the branch-target between ll/sc" to workaround. Otherwise, this flaw will cause deadlock occasionally (e.g. when doing heavy load test with LTP). Below is the explaination of CPU designer: "For Loongson 3 family, when a memory access instruction (load, store, or prefetch)'s executing occurs between the execution of LL and SC, the success or failure of SC is not predictable. Although programmer would not insert memory access instructions between LL and SC, the memory instructions before LL in program-order, may dynamically executed between the execution of LL/SC, so a memory fence (SYNC) is needed before LL/LLD to avoid this situation. Since Loongson-3A R2 (3A2000), we have improved our hardware design to handle this case. But we later deduce a rarely circumstance that some speculatively executed memory instructions due to branch misprediction between LL/SC still fall into the above case, so a memory fence (SYNC) at branch-target (if its target is not between LL/SC) is needed for Loongson 3A1000, 3B1500, 3A2000 and 3A3000. Our processor is continually evolving and we aim to to remove all these workaround-SYNCs around LL/SC for new-come processor." Here is an example: Both cpu1 and cpu2 simutaneously run atomic_add by 1 on same atomic var, this bug cause both 'sc' run by two cpus (in atomic_add) succeed at same time('sc' return 1), and the variable is only *added by 1*, sometimes, which is wrong and unacceptable(it should be added by 2). Why disable fix-loongson3-llsc in compiler? Because compiler fix will cause problems in kernel's __ex_table section. This patch fix all the cases in kernel, but: +. the fix at the end of futex_atomic_cmpxchg_inatomic is for branch-target of 'bne', there other cases which smp_mb__before_llsc() and smp_llsc_mb() fix the ll and branch-target coincidently such as atomic_sub_if_positive/ cmpxchg/xchg, just like this one. +. Loongson 3 does support CONFIG_EDAC_ATOMIC_SCRUB, so no need to touch edac.h +. local_ops and cmpxchg_local should not be affected by this bug since only the owner can write. +. mips_atomic_set for syscall.c is deprecated and rarely used, just let it go Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Huang Pei <huangpei@loongson.cn> [paul.burton@mips.com: - Simplify the addition of -mno-fix-loongson3-llsc to cflags, and add a comment describing why it's there. - Make loongson_llsc_mb() a no-op when CONFIG_CPU_LOONGSON3_WORKAROUNDS=n, rather than a compiler memory barrier. - Add a comment describing the bug & how loongson_llsc_mb() helps in asm/barrier.h.] Signed-off-by: Paul Burton <paul.burton@mips.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: ambrosehua@gmail.com Cc: Steven J . Hill <Steven.Hill@cavium.com> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: Li Xuefeng <lixuefeng@loongson.cn> Cc: Xu Chenghua <xuchenghua@loongson.cn>
2019-01-15 01:04:54 -07:00
loongson_llsc_mb();
do {
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_ARCH_LEVEL" \n"
" " __LL "%0, %1 # set_bit \n"
" or %0, %2 \n"
" " __SC "%0, %1 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
: "ir" (1UL << bit)
: __LLSC_CLOBBER);
} while (unlikely(!temp));
} else
__mips_set_bit(nr, addr);
}
/*
* clear_bit - Clears a bit in memory
* @nr: Bit to clear
* @addr: Address to start counting from
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
* you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
{
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
int bit = nr & SZLONG_MASK;
unsigned long temp;
if (kernel_uses_llsc && R10000_LLSC_WAR) {
__asm__ __volatile__(
" .set push \n"
" .set arch=r4000 \n"
"1: " __LL "%0, %1 # clear_bit \n"
" and %0, %2 \n"
" " __SC "%0, %1 \n"
" beqzl %0, 1b \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
: "ir" (~(1UL << bit))
: __LLSC_CLOBBER);
#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
MIPS: Loongson: Introduce and use loongson_llsc_mb() On the Loongson-2G/2H/3A/3B there is a hardware flaw that ll/sc and lld/scd is very weak ordering. We should add sync instructions "before each ll/lld" and "at the branch-target between ll/sc" to workaround. Otherwise, this flaw will cause deadlock occasionally (e.g. when doing heavy load test with LTP). Below is the explaination of CPU designer: "For Loongson 3 family, when a memory access instruction (load, store, or prefetch)'s executing occurs between the execution of LL and SC, the success or failure of SC is not predictable. Although programmer would not insert memory access instructions between LL and SC, the memory instructions before LL in program-order, may dynamically executed between the execution of LL/SC, so a memory fence (SYNC) is needed before LL/LLD to avoid this situation. Since Loongson-3A R2 (3A2000), we have improved our hardware design to handle this case. But we later deduce a rarely circumstance that some speculatively executed memory instructions due to branch misprediction between LL/SC still fall into the above case, so a memory fence (SYNC) at branch-target (if its target is not between LL/SC) is needed for Loongson 3A1000, 3B1500, 3A2000 and 3A3000. Our processor is continually evolving and we aim to to remove all these workaround-SYNCs around LL/SC for new-come processor." Here is an example: Both cpu1 and cpu2 simutaneously run atomic_add by 1 on same atomic var, this bug cause both 'sc' run by two cpus (in atomic_add) succeed at same time('sc' return 1), and the variable is only *added by 1*, sometimes, which is wrong and unacceptable(it should be added by 2). Why disable fix-loongson3-llsc in compiler? Because compiler fix will cause problems in kernel's __ex_table section. This patch fix all the cases in kernel, but: +. the fix at the end of futex_atomic_cmpxchg_inatomic is for branch-target of 'bne', there other cases which smp_mb__before_llsc() and smp_llsc_mb() fix the ll and branch-target coincidently such as atomic_sub_if_positive/ cmpxchg/xchg, just like this one. +. Loongson 3 does support CONFIG_EDAC_ATOMIC_SCRUB, so no need to touch edac.h +. local_ops and cmpxchg_local should not be affected by this bug since only the owner can write. +. mips_atomic_set for syscall.c is deprecated and rarely used, just let it go Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Huang Pei <huangpei@loongson.cn> [paul.burton@mips.com: - Simplify the addition of -mno-fix-loongson3-llsc to cflags, and add a comment describing why it's there. - Make loongson_llsc_mb() a no-op when CONFIG_CPU_LOONGSON3_WORKAROUNDS=n, rather than a compiler memory barrier. - Add a comment describing the bug & how loongson_llsc_mb() helps in asm/barrier.h.] Signed-off-by: Paul Burton <paul.burton@mips.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: ambrosehua@gmail.com Cc: Steven J . Hill <Steven.Hill@cavium.com> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: Li Xuefeng <lixuefeng@loongson.cn> Cc: Xu Chenghua <xuchenghua@loongson.cn>
2019-01-15 01:04:54 -07:00
loongson_llsc_mb();
do {
__asm__ __volatile__(
" " __LL "%0, %1 # clear_bit \n"
" " __INS "%0, $0, %2, 1 \n"
" " __SC "%0, %1 \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
: "ir" (bit)
: __LLSC_CLOBBER);
} while (unlikely(!temp));
#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
} else if (kernel_uses_llsc) {
MIPS: Loongson: Introduce and use loongson_llsc_mb() On the Loongson-2G/2H/3A/3B there is a hardware flaw that ll/sc and lld/scd is very weak ordering. We should add sync instructions "before each ll/lld" and "at the branch-target between ll/sc" to workaround. Otherwise, this flaw will cause deadlock occasionally (e.g. when doing heavy load test with LTP). Below is the explaination of CPU designer: "For Loongson 3 family, when a memory access instruction (load, store, or prefetch)'s executing occurs between the execution of LL and SC, the success or failure of SC is not predictable. Although programmer would not insert memory access instructions between LL and SC, the memory instructions before LL in program-order, may dynamically executed between the execution of LL/SC, so a memory fence (SYNC) is needed before LL/LLD to avoid this situation. Since Loongson-3A R2 (3A2000), we have improved our hardware design to handle this case. But we later deduce a rarely circumstance that some speculatively executed memory instructions due to branch misprediction between LL/SC still fall into the above case, so a memory fence (SYNC) at branch-target (if its target is not between LL/SC) is needed for Loongson 3A1000, 3B1500, 3A2000 and 3A3000. Our processor is continually evolving and we aim to to remove all these workaround-SYNCs around LL/SC for new-come processor." Here is an example: Both cpu1 and cpu2 simutaneously run atomic_add by 1 on same atomic var, this bug cause both 'sc' run by two cpus (in atomic_add) succeed at same time('sc' return 1), and the variable is only *added by 1*, sometimes, which is wrong and unacceptable(it should be added by 2). Why disable fix-loongson3-llsc in compiler? Because compiler fix will cause problems in kernel's __ex_table section. This patch fix all the cases in kernel, but: +. the fix at the end of futex_atomic_cmpxchg_inatomic is for branch-target of 'bne', there other cases which smp_mb__before_llsc() and smp_llsc_mb() fix the ll and branch-target coincidently such as atomic_sub_if_positive/ cmpxchg/xchg, just like this one. +. Loongson 3 does support CONFIG_EDAC_ATOMIC_SCRUB, so no need to touch edac.h +. local_ops and cmpxchg_local should not be affected by this bug since only the owner can write. +. mips_atomic_set for syscall.c is deprecated and rarely used, just let it go Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Huang Pei <huangpei@loongson.cn> [paul.burton@mips.com: - Simplify the addition of -mno-fix-loongson3-llsc to cflags, and add a comment describing why it's there. - Make loongson_llsc_mb() a no-op when CONFIG_CPU_LOONGSON3_WORKAROUNDS=n, rather than a compiler memory barrier. - Add a comment describing the bug & how loongson_llsc_mb() helps in asm/barrier.h.] Signed-off-by: Paul Burton <paul.burton@mips.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: ambrosehua@gmail.com Cc: Steven J . Hill <Steven.Hill@cavium.com> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: Li Xuefeng <lixuefeng@loongson.cn> Cc: Xu Chenghua <xuchenghua@loongson.cn>
2019-01-15 01:04:54 -07:00
loongson_llsc_mb();
do {
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_ARCH_LEVEL" \n"
" " __LL "%0, %1 # clear_bit \n"
" and %0, %2 \n"
" " __SC "%0, %1 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
: "ir" (~(1UL << bit))
: __LLSC_CLOBBER);
} while (unlikely(!temp));
} else
__mips_clear_bit(nr, addr);
}
/*
* clear_bit_unlock - Clears a bit in memory
* @nr: Bit to clear
* @addr: Address to start counting from
*
* clear_bit() is atomic and implies release semantics before the memory
* operation. It can be used for an unlock.
*/
static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
{
smp_mb__before_atomic();
clear_bit(nr, addr);
}
/*
* change_bit - Toggle a bit in memory
* @nr: Bit to change
* @addr: Address to start counting from
*
* change_bit() is atomic and may not be reordered.
* 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(unsigned long nr, volatile unsigned long *addr)
{
int bit = nr & SZLONG_MASK;
if (kernel_uses_llsc && R10000_LLSC_WAR) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
__asm__ __volatile__(
" .set push \n"
" .set arch=r4000 \n"
"1: " __LL "%0, %1 # change_bit \n"
" xor %0, %2 \n"
" " __SC "%0, %1 \n"
" beqzl %0, 1b \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
: "ir" (1UL << bit)
: __LLSC_CLOBBER);
} else if (kernel_uses_llsc) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
MIPS: Loongson: Introduce and use loongson_llsc_mb() On the Loongson-2G/2H/3A/3B there is a hardware flaw that ll/sc and lld/scd is very weak ordering. We should add sync instructions "before each ll/lld" and "at the branch-target between ll/sc" to workaround. Otherwise, this flaw will cause deadlock occasionally (e.g. when doing heavy load test with LTP). Below is the explaination of CPU designer: "For Loongson 3 family, when a memory access instruction (load, store, or prefetch)'s executing occurs between the execution of LL and SC, the success or failure of SC is not predictable. Although programmer would not insert memory access instructions between LL and SC, the memory instructions before LL in program-order, may dynamically executed between the execution of LL/SC, so a memory fence (SYNC) is needed before LL/LLD to avoid this situation. Since Loongson-3A R2 (3A2000), we have improved our hardware design to handle this case. But we later deduce a rarely circumstance that some speculatively executed memory instructions due to branch misprediction between LL/SC still fall into the above case, so a memory fence (SYNC) at branch-target (if its target is not between LL/SC) is needed for Loongson 3A1000, 3B1500, 3A2000 and 3A3000. Our processor is continually evolving and we aim to to remove all these workaround-SYNCs around LL/SC for new-come processor." Here is an example: Both cpu1 and cpu2 simutaneously run atomic_add by 1 on same atomic var, this bug cause both 'sc' run by two cpus (in atomic_add) succeed at same time('sc' return 1), and the variable is only *added by 1*, sometimes, which is wrong and unacceptable(it should be added by 2). Why disable fix-loongson3-llsc in compiler? Because compiler fix will cause problems in kernel's __ex_table section. This patch fix all the cases in kernel, but: +. the fix at the end of futex_atomic_cmpxchg_inatomic is for branch-target of 'bne', there other cases which smp_mb__before_llsc() and smp_llsc_mb() fix the ll and branch-target coincidently such as atomic_sub_if_positive/ cmpxchg/xchg, just like this one. +. Loongson 3 does support CONFIG_EDAC_ATOMIC_SCRUB, so no need to touch edac.h +. local_ops and cmpxchg_local should not be affected by this bug since only the owner can write. +. mips_atomic_set for syscall.c is deprecated and rarely used, just let it go Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Huang Pei <huangpei@loongson.cn> [paul.burton@mips.com: - Simplify the addition of -mno-fix-loongson3-llsc to cflags, and add a comment describing why it's there. - Make loongson_llsc_mb() a no-op when CONFIG_CPU_LOONGSON3_WORKAROUNDS=n, rather than a compiler memory barrier. - Add a comment describing the bug & how loongson_llsc_mb() helps in asm/barrier.h.] Signed-off-by: Paul Burton <paul.burton@mips.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: ambrosehua@gmail.com Cc: Steven J . Hill <Steven.Hill@cavium.com> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: Li Xuefeng <lixuefeng@loongson.cn> Cc: Xu Chenghua <xuchenghua@loongson.cn>
2019-01-15 01:04:54 -07:00
loongson_llsc_mb();
do {
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_ARCH_LEVEL" \n"
" " __LL "%0, %1 # change_bit \n"
" xor %0, %2 \n"
" " __SC "%0, %1 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m)
: "ir" (1UL << bit)
: __LLSC_CLOBBER);
} while (unlikely(!temp));
} else
__mips_change_bit(nr, addr);
}
/*
* test_and_set_bit - Set a bit and return its old value
* @nr: Bit to set
* @addr: Address to count from
*
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
static inline int test_and_set_bit(unsigned long nr,
volatile unsigned long *addr)
{
int bit = nr & SZLONG_MASK;
unsigned long res;
smp_mb__before_llsc();
if (kernel_uses_llsc && R10000_LLSC_WAR) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
__asm__ __volatile__(
" .set push \n"
" .set arch=r4000 \n"
"1: " __LL "%0, %1 # test_and_set_bit \n"
" or %2, %0, %3 \n"
" " __SC "%2, %1 \n"
" beqzl %2, 1b \n"
" and %2, %0, %3 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
} else if (kernel_uses_llsc) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
loongson_llsc_mb();
do {
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_ARCH_LEVEL" \n"
" " __LL "%0, %1 # test_and_set_bit \n"
" or %2, %0, %3 \n"
" " __SC "%2, %1 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
} while (unlikely(!res));
res = temp & (1UL << bit);
} else
res = __mips_test_and_set_bit(nr, addr);
smp_llsc_mb();
return res != 0;
}
/*
* test_and_set_bit_lock - Set a bit and return its old value
* @nr: Bit to set
* @addr: Address to count from
*
* This operation is atomic and implies acquire ordering semantics
* after the memory operation.
*/
static inline int test_and_set_bit_lock(unsigned long nr,
volatile unsigned long *addr)
{
int bit = nr & SZLONG_MASK;
unsigned long res;
if (kernel_uses_llsc && R10000_LLSC_WAR) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
__asm__ __volatile__(
" .set push \n"
" .set arch=r4000 \n"
"1: " __LL "%0, %1 # test_and_set_bit \n"
" or %2, %0, %3 \n"
" " __SC "%2, %1 \n"
" beqzl %2, 1b \n"
" and %2, %0, %3 \n"
" .set pop \n"
: "=&r" (temp), "+m" (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
} else if (kernel_uses_llsc) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
loongson_llsc_mb();
do {
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_ARCH_LEVEL" \n"
" " __LL "%0, %1 # test_and_set_bit \n"
" or %2, %0, %3 \n"
" " __SC "%2, %1 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
} while (unlikely(!res));
res = temp & (1UL << bit);
} else
res = __mips_test_and_set_bit_lock(nr, addr);
smp_llsc_mb();
return res != 0;
}
/*
* test_and_clear_bit - Clear a bit and return its old value
* @nr: Bit to clear
* @addr: Address to count from
*
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
static inline int test_and_clear_bit(unsigned long nr,
volatile unsigned long *addr)
{
int bit = nr & SZLONG_MASK;
unsigned long res;
smp_mb__before_llsc();
if (kernel_uses_llsc && R10000_LLSC_WAR) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
__asm__ __volatile__(
" .set push \n"
" .set arch=r4000 \n"
"1: " __LL "%0, %1 # test_and_clear_bit \n"
" or %2, %0, %3 \n"
" xor %2, %3 \n"
" " __SC "%2, %1 \n"
" beqzl %2, 1b \n"
" and %2, %0, %3 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
} else if (kernel_uses_llsc && __builtin_constant_p(nr)) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
loongson_llsc_mb();
do {
__asm__ __volatile__(
" " __LL "%0, %1 # test_and_clear_bit \n"
" " __EXT "%2, %0, %3, 1 \n"
" " __INS "%0, $0, %3, 1 \n"
" " __SC "%0, %1 \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "ir" (bit)
: __LLSC_CLOBBER);
} while (unlikely(!temp));
#endif
} else if (kernel_uses_llsc) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
loongson_llsc_mb();
do {
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_ARCH_LEVEL" \n"
" " __LL "%0, %1 # test_and_clear_bit \n"
" or %2, %0, %3 \n"
" xor %2, %3 \n"
" " __SC "%2, %1 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
} while (unlikely(!res));
res = temp & (1UL << bit);
} else
res = __mips_test_and_clear_bit(nr, addr);
smp_llsc_mb();
return res != 0;
}
/*
* 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(unsigned long nr,
volatile unsigned long *addr)
{
int bit = nr & SZLONG_MASK;
unsigned long res;
smp_mb__before_llsc();
if (kernel_uses_llsc && R10000_LLSC_WAR) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
__asm__ __volatile__(
" .set push \n"
" .set arch=r4000 \n"
"1: " __LL "%0, %1 # test_and_change_bit \n"
" xor %2, %0, %3 \n"
" " __SC "%2, %1 \n"
" beqzl %2, 1b \n"
" and %2, %0, %3 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
} else if (kernel_uses_llsc) {
unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
unsigned long temp;
loongson_llsc_mb();
do {
__asm__ __volatile__(
" .set push \n"
" .set "MIPS_ISA_ARCH_LEVEL" \n"
" " __LL "%0, %1 # test_and_change_bit \n"
" xor %2, %0, %3 \n"
" " __SC "\t%2, %1 \n"
" .set pop \n"
: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (*m), "=&r" (res)
: "r" (1UL << bit)
: __LLSC_CLOBBER);
} while (unlikely(!res));
res = temp & (1UL << bit);
} else
res = __mips_test_and_change_bit(nr, addr);
smp_llsc_mb();
return res != 0;
}
#include <asm-generic/bitops/non-atomic.h>
/*
* __clear_bit_unlock - Clears a bit in memory
* @nr: Bit to clear
* @addr: Address to start counting from
*
* __clear_bit() is non-atomic and implies release semantics before the memory
* operation. It can be used for an unlock if no other CPUs can concurrently
* modify other bits in the word.
*/
static inline void __clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
{
smp_mb__before_llsc();
__clear_bit(nr, addr);
nudge_writes();
}
/*
* Return the bit position (0..63) of the most significant 1 bit in a word
* Returns -1 if no 1 bit exists
*/
MIPS: mark __fls() and __ffs() as __always_inline This prepares to move CONFIG_OPTIMIZE_INLINING from x86 to a common place. We need to eliminate potential issues beforehand. If it is enabled for mips, the following errors are reported: arch/mips/mm/sc-mips.o: In function `mips_sc_prefetch_enable.part.2': sc-mips.c:(.text+0x98): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0x9c): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0xbc): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0xc8): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0xdc): undefined reference to `mips_gcr_base' arch/mips/mm/sc-mips.o:sc-mips.c:(.text.unlikely+0x44): more undefined references to `mips_gcr_base' Link: http://lkml.kernel.org/r/20190423034959.13525-7-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Boris Brezillon <bbrezillon@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Norris <computersforpeace@gmail.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Marek Vasut <marek.vasut@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Malaterre <malat@debian.org> Cc: Miquel Raynal <miquel.raynal@bootlin.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Stefan Agner <stefan@agner.ch> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 16:42:07 -06:00
static __always_inline unsigned long __fls(unsigned long word)
{
int num;
if (BITS_PER_LONG == 32 && !__builtin_constant_p(word) &&
__builtin_constant_p(cpu_has_clo_clz) && cpu_has_clo_clz) {
__asm__(
" .set push \n"
" .set "MIPS_ISA_LEVEL" \n"
" clz %0, %1 \n"
" .set pop \n"
: "=r" (num)
: "r" (word));
return 31 - num;
}
if (BITS_PER_LONG == 64 && !__builtin_constant_p(word) &&
__builtin_constant_p(cpu_has_mips64) && cpu_has_mips64) {
__asm__(
" .set push \n"
" .set "MIPS_ISA_LEVEL" \n"
" dclz %0, %1 \n"
" .set pop \n"
: "=r" (num)
: "r" (word));
return 63 - num;
}
num = BITS_PER_LONG - 1;
#if BITS_PER_LONG == 64
if (!(word & (~0ul << 32))) {
num -= 32;
word <<= 32;
}
#endif
if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
num -= 16;
word <<= 16;
}
if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
num -= 8;
word <<= 8;
}
if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
num -= 4;
word <<= 4;
}
if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
num -= 2;
word <<= 2;
}
if (!(word & (~0ul << (BITS_PER_LONG-1))))
num -= 1;
return num;
}
/*
* __ffs - find first bit in word.
* @word: The word to search
*
* Returns 0..SZLONG-1
* Undefined if no bit exists, so code should check against 0 first.
*/
MIPS: mark __fls() and __ffs() as __always_inline This prepares to move CONFIG_OPTIMIZE_INLINING from x86 to a common place. We need to eliminate potential issues beforehand. If it is enabled for mips, the following errors are reported: arch/mips/mm/sc-mips.o: In function `mips_sc_prefetch_enable.part.2': sc-mips.c:(.text+0x98): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0x9c): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0xbc): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0xc8): undefined reference to `mips_gcr_base' sc-mips.c:(.text+0xdc): undefined reference to `mips_gcr_base' arch/mips/mm/sc-mips.o:sc-mips.c:(.text.unlikely+0x44): more undefined references to `mips_gcr_base' Link: http://lkml.kernel.org/r/20190423034959.13525-7-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Boris Brezillon <bbrezillon@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Brian Norris <computersforpeace@gmail.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Marek Vasut <marek.vasut@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Malaterre <malat@debian.org> Cc: Miquel Raynal <miquel.raynal@bootlin.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Weinberger <richard@nod.at> Cc: Russell King <rmk+kernel@arm.linux.org.uk> Cc: Stefan Agner <stefan@agner.ch> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 16:42:07 -06:00
static __always_inline unsigned long __ffs(unsigned long word)
{
return __fls(word & -word);
}
/*
* fls - find last bit set.
* @word: The word to search
*
* This is defined the same way as ffs.
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
*/
static inline int fls(unsigned int x)
{
int r;
if (!__builtin_constant_p(x) &&
__builtin_constant_p(cpu_has_clo_clz) && cpu_has_clo_clz) {
__asm__(
" .set push \n"
" .set "MIPS_ISA_LEVEL" \n"
" clz %0, %1 \n"
" .set pop \n"
: "=r" (x)
: "r" (x));
return 32 - x;
}
r = 32;
if (!x)
return 0;
if (!(x & 0xffff0000u)) {
x <<= 16;
r -= 16;
}
if (!(x & 0xff000000u)) {
x <<= 8;
r -= 8;
}
if (!(x & 0xf0000000u)) {
x <<= 4;
r -= 4;
}
if (!(x & 0xc0000000u)) {
x <<= 2;
r -= 2;
}
if (!(x & 0x80000000u)) {
x <<= 1;
r -= 1;
}
return r;
}
#include <asm-generic/bitops/fls64.h>
/*
* ffs - find first bit set.
* @word: The word to search
*
* This is defined the same way as
* the libc and compiler builtin ffs routines, therefore
* differs in spirit from the above ffz (man ffs).
*/
static inline int ffs(int word)
{
if (!word)
return 0;
return fls(word & -word);
}
#include <asm-generic/bitops/ffz.h>
#include <asm-generic/bitops/find.h>
#ifdef __KERNEL__
#include <asm-generic/bitops/sched.h>
#include <asm/arch_hweight.h>
#include <asm-generic/bitops/const_hweight.h>
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/ext2-atomic.h>
#endif /* __KERNEL__ */
#endif /* _ASM_BITOPS_H */