Revision 928a4c39484281f8ca366f53a1db79330d058401 authored by David Woodhouse on 10 February 2018, 23:39:24 UTC, committed by Ingo Molnar on 13 February 2018, 07:59:45 UTC
With retpoline, tight loops of "call this function for every XXX" are very much pessimised by taking a prediction miss *every* time. This one is by far the biggest contributor to the guest launch time with retpoline. By marking the iterator slot_handle_…() functions always_inline, we can ensure that the indirect function call can be optimised away into a direct call and it actually generates slightly smaller code because some of the other conditionals can get optimised away too. Performance is now pretty close to what we see with nospectre_v2 on the command line. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Tested-by: Filippo Sironi <sironi@amazon.de> Signed-off-by: David Woodhouse <dwmw@amazon.co.uk> Reviewed-by: Filippo Sironi <sironi@amazon.de> Acked-by: Paolo Bonzini <pbonzini@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arjan.van.de.ven@intel.com Cc: dave.hansen@intel.com Cc: jmattson@google.com Cc: karahmed@amazon.de Cc: kvm@vger.kernel.org Cc: rkrcmar@redhat.com Link: http://lkml.kernel.org/r/1518305967-31356-4-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar <mingo@kernel.org>
1 parent f208820
Kbuild
# SPDX-License-Identifier: GPL-2.0
#
# Kbuild for top-level directory of the kernel
# This file takes care of the following:
# 1) Generate bounds.h
# 2) Generate timeconst.h
# 3) Generate asm-offsets.h (may need bounds.h and timeconst.h)
# 4) Check for missing system calls
# 5) Generate constants.py (may need bounds.h)
#####
# 1) Generate bounds.h
bounds-file := include/generated/bounds.h
always := $(bounds-file)
targets := kernel/bounds.s
# We use internal kbuild rules to avoid the "is up to date" message from make
kernel/bounds.s: kernel/bounds.c FORCE
$(call if_changed_dep,cc_s_c)
$(obj)/$(bounds-file): kernel/bounds.s FORCE
$(call filechk,offsets,__LINUX_BOUNDS_H__)
#####
# 2) Generate timeconst.h
timeconst-file := include/generated/timeconst.h
targets += $(timeconst-file)
quiet_cmd_gentimeconst = GEN $@
define cmd_gentimeconst
(echo $(CONFIG_HZ) | bc -q $< ) > $@
endef
define filechk_gentimeconst
(echo $(CONFIG_HZ) | bc -q $< )
endef
$(obj)/$(timeconst-file): kernel/time/timeconst.bc FORCE
$(call filechk,gentimeconst)
#####
# 3) Generate asm-offsets.h
#
offsets-file := include/generated/asm-offsets.h
always += $(offsets-file)
targets += arch/$(SRCARCH)/kernel/asm-offsets.s
# We use internal kbuild rules to avoid the "is up to date" message from make
arch/$(SRCARCH)/kernel/asm-offsets.s: arch/$(SRCARCH)/kernel/asm-offsets.c \
$(obj)/$(timeconst-file) $(obj)/$(bounds-file) FORCE
$(call if_changed_dep,cc_s_c)
$(obj)/$(offsets-file): arch/$(SRCARCH)/kernel/asm-offsets.s FORCE
$(call filechk,offsets,__ASM_OFFSETS_H__)
#####
# 4) Check for missing system calls
#
always += missing-syscalls
targets += missing-syscalls
quiet_cmd_syscalls = CALL $<
cmd_syscalls = $(CONFIG_SHELL) $< $(CC) $(c_flags) $(missing_syscalls_flags)
missing-syscalls: scripts/checksyscalls.sh $(offsets-file) FORCE
$(call cmd,syscalls)
#####
# 5) Generate constants for Python GDB integration
#
extra-$(CONFIG_GDB_SCRIPTS) += build_constants_py
build_constants_py: $(obj)/$(timeconst-file) $(obj)/$(bounds-file)
@$(MAKE) $(build)=scripts/gdb/linux $@
# Keep these three files during make clean
no-clean-files := $(bounds-file) $(offsets-file) $(timeconst-file)
Computing file changes ...
