![Huacai Chen](/assets/img/avatar_default.png)
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>
78 lines
3 KiB
Plaintext
78 lines
3 KiB
Plaintext
#
|
|
# Loongson Processors' Support
|
|
#
|
|
|
|
# Only gcc >= 4.4 have Loongson specific support
|
|
cflags-$(CONFIG_CPU_LOONGSON2) += -Wa,--trap
|
|
cflags-$(CONFIG_CPU_LOONGSON2E) += \
|
|
$(call cc-option,-march=loongson2e,-march=r4600)
|
|
cflags-$(CONFIG_CPU_LOONGSON2F) += \
|
|
$(call cc-option,-march=loongson2f,-march=r4600)
|
|
# Enable the workarounds for Loongson2f
|
|
ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
|
|
ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-nop,),)
|
|
$(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-nop)
|
|
else
|
|
cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-nop
|
|
endif
|
|
ifeq ($(call as-option,-Wa$(comma)-mfix-loongson2f-jump,),)
|
|
$(error only binutils >= 2.20.2 have needed option -mfix-loongson2f-jump)
|
|
else
|
|
cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa$(comma)-mfix-loongson2f-jump
|
|
endif
|
|
endif
|
|
|
|
cflags-$(CONFIG_CPU_LOONGSON3) += -Wa,--trap
|
|
|
|
#
|
|
# Some versions of binutils, not currently mainline as of 2019/02/04, support
|
|
# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction
|
|
# to work around a CPU bug (see loongson_llsc_mb() in asm/barrier.h for a
|
|
# description).
|
|
#
|
|
# We disable this in order to prevent the assembler meddling with the
|
|
# instruction that labels refer to, ie. if we label an ll instruction:
|
|
#
|
|
# 1: ll v0, 0(a0)
|
|
#
|
|
# ...then with the assembler fix applied the label may actually point at a sync
|
|
# instruction inserted by the assembler, and if we were using the label in an
|
|
# exception table the table would no longer contain the address of the ll
|
|
# instruction.
|
|
#
|
|
# Avoid this by explicitly disabling that assembler behaviour. If upstream
|
|
# binutils does not merge support for the flag then we can revisit & remove
|
|
# this later - for now it ensures vendor toolchains don't cause problems.
|
|
#
|
|
cflags-$(CONFIG_CPU_LOONGSON3) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,)
|
|
|
|
#
|
|
# binutils from v2.25 on and gcc starting from v4.9.0 treat -march=loongson3a
|
|
# as MIPS64 R2; older versions as just R1. This leaves the possibility open
|
|
# that GCC might generate R2 code for -march=loongson3a which then is rejected
|
|
# by GAS. The cc-option can't probe for this behaviour so -march=loongson3a
|
|
# can't easily be used safely within the kbuild framework.
|
|
#
|
|
ifeq ($(call cc-ifversion, -ge, 0409, y), y)
|
|
ifeq ($(call ld-ifversion, -ge, 225000000, y), y)
|
|
cflags-$(CONFIG_CPU_LOONGSON3) += \
|
|
$(call cc-option,-march=loongson3a -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64)
|
|
else
|
|
cflags-$(CONFIG_CPU_LOONGSON3) += \
|
|
$(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64)
|
|
endif
|
|
else
|
|
cflags-$(CONFIG_CPU_LOONGSON3) += \
|
|
$(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64)
|
|
endif
|
|
|
|
#
|
|
# Loongson Machines' Support
|
|
#
|
|
|
|
platform-$(CONFIG_MACH_LOONGSON64) += loongson64/
|
|
cflags-$(CONFIG_MACH_LOONGSON64) += -I$(srctree)/arch/mips/include/asm/mach-loongson64 -mno-branch-likely
|
|
load-$(CONFIG_LEMOTE_FULOONG2E) += 0xffffffff80100000
|
|
load-$(CONFIG_LEMOTE_MACH2F) += 0xffffffff80200000
|
|
load-$(CONFIG_LOONGSON_MACH3X) += 0xffffffff80200000
|