This one is much faster than the spinlock based fallback rwsem code, with certain artifical benchmarks having shown 300%+ improvement on threaded page faults etc. Again, note the 32767-thread limit here. So this really does need that whole "make rwsem_count_t be 64-bit and fix the BIAS values to match" extension on top of it, but that is conceptually a totally independent issue. NOT TESTED! The original patch that this all was based on were tested by KAMEZAWA Hiroyuki, but maybe I screwed up something when I created the cleaned-up series, so caveat emptor.. Also note that it _may_ be a good idea to mark some more registers clobbered on x86-64 in the inline asms instead of saving/restoring them. They are inline functions, but they are only used in places where there are not a lot of live registers _anyway_, so doing for example the clobbers of %r8-%r11 in the asm wouldn't make the fast-path code any worse, and would make the slow-path code smaller. (Not that the slow-path really matters to that degree. Saving a few unnecessary registers is the _least_ of our problems when we hit the slow path. The instruction/cycle counting really only matters in the fast path). Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <alpine.LFD.2.00.1001121810410.17145@localhost.localdomain> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
44 lines
1.3 KiB
Makefile
44 lines
1.3 KiB
Makefile
#
|
|
# Makefile for x86 specific library files.
|
|
#
|
|
|
|
inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
|
|
inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
|
|
quiet_cmd_inat_tables = GEN $@
|
|
cmd_inat_tables = $(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
|
|
|
|
$(obj)/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
|
|
$(call cmd,inat_tables)
|
|
|
|
$(obj)/inat.o: $(obj)/inat-tables.c
|
|
|
|
clean-files := inat-tables.c
|
|
|
|
obj-$(CONFIG_SMP) += msr-smp.o
|
|
|
|
lib-y := delay.o
|
|
lib-y += thunk_$(BITS).o
|
|
lib-y += usercopy_$(BITS).o getuser.o putuser.o
|
|
lib-y += memcpy_$(BITS).o
|
|
lib-$(CONFIG_KPROBES) += insn.o inat.o
|
|
|
|
obj-y += msr.o msr-reg.o msr-reg-export.o
|
|
|
|
ifeq ($(CONFIG_X86_32),y)
|
|
obj-y += atomic64_32.o
|
|
lib-y += checksum_32.o
|
|
lib-y += strstr_32.o
|
|
lib-y += semaphore_32.o string_32.o
|
|
ifneq ($(CONFIG_X86_CMPXCHG64),y)
|
|
lib-y += cmpxchg8b_emu.o
|
|
endif
|
|
lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o
|
|
else
|
|
obj-y += io_64.o iomap_copy_64.o
|
|
lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
|
|
lib-y += thunk_64.o clear_page_64.o copy_page_64.o
|
|
lib-y += memmove_64.o memset_64.o
|
|
lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o
|
|
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem_64.o
|
|
endif
|