mirror of
https://github.com/torvalds/linux.git
synced 2026-05-30 01:53:29 +02:00
bef64bcb94
Add an assembly implementation of strrchr() for RISC-V. This implementation minimizes instruction count and avoids unnecessary memory access to the stack. The performance benefits are most visible on small workloads (1-16 bytes) where the architectural savings in function overhead outweigh the execution time of the scan loop. Benchmark results (QEMU TCG, rv64): Length | Original (MB/s) | Optimized (MB/s) | Improvement -------|-----------------|------------------|------------ 1 B | 20 | 21 | +5.0% 7 B | 111 | 120 | +8.1% 16 B | 189 | 199 | +5.3% 512 B | 361 | 382 | +5.8% 4096 B | 388 | 391 | +0.8% Signed-off-by: Feng Jiang <jiangfeng@kylinos.cn> Tested-by: Joel Stanley <joel@jms.id.au> Link: https://patch.msgid.link/20260130025018.172925-9-jiangfeng@kylinos.cn Signed-off-by: Paul Walmsley <pjw@kernel.org>
118 lines
3.7 KiB
Makefile
118 lines
3.7 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
|
|
purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o
|
|
ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),)
|
|
purgatory-y += strcmp.o strlen.o strncmp.o strnlen.o strchr.o strrchr.o
|
|
endif
|
|
|
|
targets += $(purgatory-y)
|
|
PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
|
|
|
|
$(obj)/string.o: $(srctree)/lib/string.c FORCE
|
|
$(call if_changed_rule,cc_o_c)
|
|
|
|
$(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE
|
|
$(call if_changed_rule,cc_o_c)
|
|
|
|
$(obj)/memcpy.o: $(srctree)/arch/riscv/lib/memcpy.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
$(obj)/memset.o: $(srctree)/arch/riscv/lib/memset.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
$(obj)/strcmp.o: $(srctree)/arch/riscv/lib/strcmp.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
$(obj)/strlen.o: $(srctree)/arch/riscv/lib/strlen.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
$(obj)/strncmp.o: $(srctree)/arch/riscv/lib/strncmp.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
|
|
$(call if_changed_rule,cc_o_c)
|
|
|
|
$(obj)/strnlen.o: $(srctree)/arch/riscv/lib/strnlen.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
$(obj)/strchr.o: $(srctree)/arch/riscv/lib/strchr.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
$(obj)/strrchr.o: $(srctree)/arch/riscv/lib/strrchr.S FORCE
|
|
$(call if_changed_rule,as_o_S)
|
|
|
|
CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
|
|
CFLAGS_string.o := -D__DISABLE_EXPORTS
|
|
CFLAGS_ctype.o := -D__DISABLE_EXPORTS
|
|
|
|
# When profile-guided optimization is enabled, llvm emits two different
|
|
# overlapping text sections, which is not supported by kexec. Remove profile
|
|
# optimization flags.
|
|
KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
|
|
|
|
# When linking purgatory.ro with -r unresolved symbols are not checked,
|
|
# also link a purgatory.chk binary without -r to check for unresolved symbols.
|
|
PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib
|
|
LDFLAGS_purgatory.ro := -r $(PURGATORY_LDFLAGS)
|
|
LDFLAGS_purgatory.chk := $(PURGATORY_LDFLAGS)
|
|
targets += purgatory.ro purgatory.chk
|
|
|
|
# These are adjustments to the compiler flags used for objects that
|
|
# make up the standalone purgatory.ro
|
|
|
|
PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
|
|
PURGATORY_CFLAGS := -mcmodel=medany -ffreestanding -fno-zero-initialized-in-bss
|
|
PURGATORY_CFLAGS += $(DISABLE_KSTACK_ERASE) -DDISABLE_BRANCH_PROFILING
|
|
PURGATORY_CFLAGS += -fno-stack-protector -g0
|
|
|
|
# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
|
|
# in turn leaves some undefined symbols like __fentry__ in purgatory and not
|
|
# sure how to relocate those.
|
|
ifdef CONFIG_FUNCTION_TRACER
|
|
PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_FTRACE)
|
|
endif
|
|
|
|
ifdef CONFIG_STACKPROTECTOR
|
|
PURGATORY_CFLAGS_REMOVE += -fstack-protector
|
|
endif
|
|
|
|
ifdef CONFIG_STACKPROTECTOR_STRONG
|
|
PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong
|
|
endif
|
|
|
|
ifdef CONFIG_CFI
|
|
PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI)
|
|
endif
|
|
|
|
ifdef CONFIG_RELOCATABLE
|
|
PURGATORY_CFLAGS_REMOVE += -fPIE
|
|
endif
|
|
|
|
ifdef CONFIG_SHADOW_CALL_STACK
|
|
PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_SCS)
|
|
endif
|
|
|
|
CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE)
|
|
CFLAGS_purgatory.o += $(PURGATORY_CFLAGS)
|
|
|
|
CFLAGS_REMOVE_sha256.o += $(PURGATORY_CFLAGS_REMOVE)
|
|
CFLAGS_sha256.o += $(PURGATORY_CFLAGS)
|
|
|
|
CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE)
|
|
CFLAGS_string.o += $(PURGATORY_CFLAGS)
|
|
|
|
CFLAGS_REMOVE_ctype.o += $(PURGATORY_CFLAGS_REMOVE)
|
|
CFLAGS_ctype.o += $(PURGATORY_CFLAGS)
|
|
|
|
asflags-remove-y += $(foreach x, -g -gdwarf-4 -gdwarf-5, $(x) -Wa,$(x))
|
|
|
|
$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
|
|
$(call if_changed,ld)
|
|
|
|
$(obj)/purgatory.chk: $(obj)/purgatory.ro FORCE
|
|
$(call if_changed,ld)
|
|
|
|
$(obj)/kexec-purgatory.o: $(obj)/purgatory.ro $(obj)/purgatory.chk
|
|
|
|
obj-y += kexec-purgatory.o
|